From e5b9778761558ff3d239ed76925a1a7a734918ea Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Tue, 28 Feb 2017 19:54:40 +0300 Subject: [PATCH 01/64] tty: n_hdlc: get rid of racy n_hdlc.tbuf commit 82f2341c94d270421f383641b7cd670e474db56b upstream. Currently N_HDLC line discipline uses a self-made singly linked list for data buffers and has n_hdlc.tbuf pointer for buffer retransmitting after an error. The commit be10eb7589337e5defbe214dae038a53dd21add8 ("tty: n_hdlc add buffer flushing") introduced racy access to n_hdlc.tbuf. After tx error concurrent flush_tx_queue() and n_hdlc_send_frames() can put one data buffer to tx_free_buf_list twice. That causes double free in n_hdlc_release(). Let's use standard kernel linked list and get rid of n_hdlc.tbuf: in case of tx error put current data buffer after the head of tx_buf_list. Signed-off-by: Alexander Popov Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_hdlc.c | 132 ++++++++++++++++++++++--------------------- 1 file changed, 69 insertions(+), 63 deletions(-) diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c index a7fa016f31eb..6d1e2f746ab4 100644 --- a/drivers/tty/n_hdlc.c +++ b/drivers/tty/n_hdlc.c @@ -114,7 +114,7 @@ #define DEFAULT_TX_BUF_COUNT 3 struct n_hdlc_buf { - struct n_hdlc_buf *link; + struct list_head list_item; int count; char buf[1]; }; @@ -122,8 +122,7 @@ struct n_hdlc_buf { #define N_HDLC_BUF_SIZE (sizeof(struct n_hdlc_buf) + maxframe) struct n_hdlc_buf_list { - struct n_hdlc_buf *head; - struct n_hdlc_buf *tail; + struct list_head list; int count; spinlock_t spinlock; }; @@ -136,7 +135,6 @@ struct n_hdlc_buf_list { * @backup_tty - TTY to use if tty gets closed * @tbusy - reentrancy flag for tx wakeup code * @woke_up - FIXME: describe this field - * @tbuf - currently transmitting tx buffer * @tx_buf_list - list of pending transmit frame buffers * @rx_buf_list - list of received frame buffers * @tx_free_buf_list - list unused transmit frame buffers @@ -149,7 +147,6 @@ struct n_hdlc { struct tty_struct *backup_tty; int tbusy; int woke_up; - struct n_hdlc_buf *tbuf; struct n_hdlc_buf_list tx_buf_list; struct n_hdlc_buf_list rx_buf_list; struct n_hdlc_buf_list tx_free_buf_list; @@ -159,6 +156,8 @@ struct n_hdlc { /* * HDLC buffer list manipulation functions */ +static void n_hdlc_buf_return(struct n_hdlc_buf_list *buf_list, + struct n_hdlc_buf *buf); static void n_hdlc_buf_put(struct n_hdlc_buf_list *list, struct n_hdlc_buf *buf); static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *list); @@ -208,16 +207,9 @@ static void flush_tx_queue(struct tty_struct *tty) { struct n_hdlc *n_hdlc = tty2n_hdlc(tty); struct n_hdlc_buf *buf; - unsigned long flags; while ((buf = n_hdlc_buf_get(&n_hdlc->tx_buf_list))) n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, buf); - spin_lock_irqsave(&n_hdlc->tx_buf_list.spinlock, flags); - if (n_hdlc->tbuf) { - n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, n_hdlc->tbuf); - n_hdlc->tbuf = NULL; - } - spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock, flags); } static struct tty_ldisc_ops n_hdlc_ldisc = { @@ -283,7 +275,6 @@ static void n_hdlc_release(struct n_hdlc *n_hdlc) } else break; } - kfree(n_hdlc->tbuf); kfree(n_hdlc); } /* end of n_hdlc_release() */ @@ -402,13 +393,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty) n_hdlc->woke_up = 0; spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock, flags); - /* get current transmit buffer or get new transmit */ - /* buffer from list of pending transmit buffers */ - - tbuf = n_hdlc->tbuf; - if (!tbuf) - tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list); - + tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list); while (tbuf) { if (debuglevel >= DEBUG_LEVEL_INFO) printk("%s(%d)sending frame %p, count=%d\n", @@ -420,7 +405,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty) /* rollback was possible and has been done */ if (actual == -ERESTARTSYS) { - n_hdlc->tbuf = tbuf; + n_hdlc_buf_return(&n_hdlc->tx_buf_list, tbuf); break; } /* if transmit error, throw frame away by */ @@ -435,10 +420,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty) /* free current transmit buffer */ n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, tbuf); - - /* this tx buffer is done */ - n_hdlc->tbuf = NULL; - + /* wait up sleeping writers */ wake_up_interruptible(&tty->write_wait); @@ -448,10 +430,12 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty) if (debuglevel >= DEBUG_LEVEL_INFO) printk("%s(%d)frame %p pending\n", __FILE__,__LINE__,tbuf); - - /* buffer not accepted by driver */ - /* set this buffer as pending buffer */ - n_hdlc->tbuf = tbuf; + + /* + * the buffer was not accepted by driver, + * return it back into tx queue + */ + n_hdlc_buf_return(&n_hdlc->tx_buf_list, tbuf); break; } } @@ -749,7 +733,8 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file, int error = 0; int count; unsigned long flags; - + struct n_hdlc_buf *buf = NULL; + if (debuglevel >= DEBUG_LEVEL_INFO) printk("%s(%d)n_hdlc_tty_ioctl() called %d\n", __FILE__,__LINE__,cmd); @@ -763,8 +748,10 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file, /* report count of read data available */ /* in next available frame (if any) */ spin_lock_irqsave(&n_hdlc->rx_buf_list.spinlock,flags); - if (n_hdlc->rx_buf_list.head) - count = n_hdlc->rx_buf_list.head->count; + buf = list_first_entry_or_null(&n_hdlc->rx_buf_list.list, + struct n_hdlc_buf, list_item); + if (buf) + count = buf->count; else count = 0; spin_unlock_irqrestore(&n_hdlc->rx_buf_list.spinlock,flags); @@ -776,8 +763,10 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file, count = tty_chars_in_buffer(tty); /* add size of next output frame in queue */ spin_lock_irqsave(&n_hdlc->tx_buf_list.spinlock,flags); - if (n_hdlc->tx_buf_list.head) - count += n_hdlc->tx_buf_list.head->count; + buf = list_first_entry_or_null(&n_hdlc->tx_buf_list.list, + struct n_hdlc_buf, list_item); + if (buf) + count += buf->count; spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock,flags); error = put_user(count, (int __user *)arg); break; @@ -825,14 +814,14 @@ static unsigned int n_hdlc_tty_poll(struct tty_struct *tty, struct file *filp, poll_wait(filp, &tty->write_wait, wait); /* set bits for operations that won't block */ - if (n_hdlc->rx_buf_list.head) + if (!list_empty(&n_hdlc->rx_buf_list.list)) mask |= POLLIN | POLLRDNORM; /* readable */ if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) mask |= POLLHUP; if (tty_hung_up_p(filp)) mask |= POLLHUP; if (!tty_is_writelocked(tty) && - n_hdlc->tx_free_buf_list.head) + !list_empty(&n_hdlc->tx_free_buf_list.list)) mask |= POLLOUT | POLLWRNORM; /* writable */ } return mask; @@ -856,7 +845,12 @@ static struct n_hdlc *n_hdlc_alloc(void) spin_lock_init(&n_hdlc->tx_free_buf_list.spinlock); spin_lock_init(&n_hdlc->rx_buf_list.spinlock); spin_lock_init(&n_hdlc->tx_buf_list.spinlock); - + + INIT_LIST_HEAD(&n_hdlc->rx_free_buf_list.list); + INIT_LIST_HEAD(&n_hdlc->tx_free_buf_list.list); + INIT_LIST_HEAD(&n_hdlc->rx_buf_list.list); + INIT_LIST_HEAD(&n_hdlc->tx_buf_list.list); + /* allocate free rx buffer list */ for(i=0;ispinlock, flags); + + list_add(&buf->list_item, &buf_list->list); + buf_list->count++; + + spin_unlock_irqrestore(&buf_list->spinlock, flags); +} + /** * n_hdlc_buf_put - add specified HDLC buffer to tail of specified list - * @list - pointer to buffer list + * @buf_list - pointer to buffer list * @buf - pointer to buffer */ -static void n_hdlc_buf_put(struct n_hdlc_buf_list *list, +static void n_hdlc_buf_put(struct n_hdlc_buf_list *buf_list, struct n_hdlc_buf *buf) { unsigned long flags; - spin_lock_irqsave(&list->spinlock,flags); - - buf->link=NULL; - if (list->tail) - list->tail->link = buf; - else - list->head = buf; - list->tail = buf; - (list->count)++; - - spin_unlock_irqrestore(&list->spinlock,flags); - + + spin_lock_irqsave(&buf_list->spinlock, flags); + + list_add_tail(&buf->list_item, &buf_list->list); + buf_list->count++; + + spin_unlock_irqrestore(&buf_list->spinlock, flags); } /* end of n_hdlc_buf_put() */ /** * n_hdlc_buf_get - remove and return an HDLC buffer from list - * @list - pointer to HDLC buffer list + * @buf_list - pointer to HDLC buffer list * * Remove and return an HDLC buffer from the head of the specified HDLC buffer * list. * Returns a pointer to HDLC buffer if available, otherwise %NULL. */ -static struct n_hdlc_buf* n_hdlc_buf_get(struct n_hdlc_buf_list *list) +static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *buf_list) { unsigned long flags; struct n_hdlc_buf *buf; - spin_lock_irqsave(&list->spinlock,flags); - - buf = list->head; + + spin_lock_irqsave(&buf_list->spinlock, flags); + + buf = list_first_entry_or_null(&buf_list->list, + struct n_hdlc_buf, list_item); if (buf) { - list->head = buf->link; - (list->count)--; + list_del(&buf->list_item); + buf_list->count--; } - if (!list->head) - list->tail = NULL; - - spin_unlock_irqrestore(&list->spinlock,flags); + + spin_unlock_irqrestore(&buf_list->spinlock, flags); return buf; - } /* end of n_hdlc_buf_get() */ static char hdlc_banner[] __initdata = From c4c590be494404531f54fa1acf580a08031f5bb9 Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Fri, 3 Feb 2017 20:25:00 +0000 Subject: [PATCH 02/64] serial: 8250_pci: Add MKS Tenta SCOM-0800 and SCOM-0801 cards commit 1c9c858e2ff8ae8024a3d75d2ed080063af43754 upstream. The MKS Instruments SCOM-0800 and SCOM-0801 cards (originally by Tenta Technologies) are 3U CompactPCI serial cards with 4 and 8 serial ports, respectively. The first 4 ports are implemented by an OX16PCI954 chip, and the second 4 ports are implemented by an OX16C954 chip on a local bus, bridged by the second PCI function of the OX16PCI954. The ports are jumper-selectable as RS-232 and RS-422/485, and the UARTs use a non-standard oscillator frequency of 20 MHz (base_baud = 1250000). Signed-off-by: Ian Abbott Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_pci.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index b98c1578f45a..4d09bd495a88 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -2688,6 +2688,8 @@ enum pci_board_num_t { pbn_b0_4_1152000_200, pbn_b0_8_1152000_200, + pbn_b0_4_1250000, + pbn_b0_2_1843200, pbn_b0_4_1843200, @@ -2919,6 +2921,13 @@ static struct pciserial_board pci_boards[] = { .uart_offset = 0x200, }, + [pbn_b0_4_1250000] = { + .flags = FL_BASE0, + .num_ports = 4, + .base_baud = 1250000, + .uart_offset = 8, + }, + [pbn_b0_2_1843200] = { .flags = FL_BASE0, .num_ports = 2, @@ -5549,6 +5558,10 @@ static struct pci_device_id serial_pci_tbl[] = { { PCI_DEVICE(0x1c29, 0x1108), .driver_data = pbn_fintek_8 }, { PCI_DEVICE(0x1c29, 0x1112), .driver_data = pbn_fintek_12 }, + /* MKS Tenta SCOM-080x serial cards */ + { PCI_DEVICE(0x1601, 0x0800), .driver_data = pbn_b0_4_1250000 }, + { PCI_DEVICE(0x1601, 0xa801), .driver_data = pbn_b0_4_1250000 }, + /* * These entries match devices with class COMMUNICATION_SERIAL, * COMMUNICATION_MODEM or COMMUNICATION_MULTISERIAL From 035dcc8e87f63b36f3456b39a352f0a1c785b93b Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Thu, 2 Feb 2017 16:39:31 +0100 Subject: [PATCH 03/64] KVM: s390: Disable dirty log retrieval for UCONTROL guests commit e1e8a9624f7ba8ead4f056ff558ed070e86fa747 upstream. User controlled KVM guests do not support the dirty log, as they have no single gmap that we can check for changes. As they have no single gmap, kvm->arch.gmap is NULL and all further referencing to it for dirty checking will result in a NULL dereference. Let's return -EINVAL if a caller tries to sync dirty logs for a UCONTROL guest. Fixes: 15f36eb ("KVM: s390: Add proper dirty bitmap support to S390 kvm.") Signed-off-by: Janosch Frank Reported-by: Martin Schwidefsky Reviewed-by: Cornelia Huck Signed-off-by: Christian Borntraeger Signed-off-by: Greg Kroah-Hartman --- arch/s390/kvm/kvm-s390.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 47a1de77b18d..5ba494ed18c1 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -442,6 +442,9 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot; int is_dirty = 0; + if (kvm_is_ucontrol(kvm)) + return -EINVAL; + mutex_lock(&kvm->slots_lock); r = -EINVAL; From 7c3bab189c16a21742172b09979fd84c13698202 Mon Sep 17 00:00:00 2001 From: Chao Peng Date: Tue, 21 Feb 2017 03:50:01 -0500 Subject: [PATCH 04/64] KVM: VMX: use correct vmcs_read/write for guest segment selector/base commit 96794e4ed4d758272c486e1529e431efb7045265 upstream. Guest segment selector is 16 bit field and guest segment base is natural width field. Fix two incorrect invocations accordingly. Without this patch, build fails when aggressive inlining is used with ICC. Signed-off-by: Chao Peng Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/vmx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 64774f419c72..69b8f8a5ecb0 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3693,7 +3693,7 @@ static void fix_rmode_seg(int seg, struct kvm_segment *save) } vmcs_write16(sf->selector, var.selector); - vmcs_write32(sf->base, var.base); + vmcs_writel(sf->base, var.base); vmcs_write32(sf->limit, var.limit); vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var)); } @@ -8202,7 +8202,7 @@ static void kvm_flush_pml_buffers(struct kvm *kvm) static void vmx_dump_sel(char *name, uint32_t sel) { pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", - name, vmcs_read32(sel), + name, vmcs_read16(sel), vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR), vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR), vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR)); From 519b6cead21ee66ad7825750ce8aefaf64dd6792 Mon Sep 17 00:00:00 2001 From: Dmitry Tunin Date: Thu, 5 Jan 2017 13:19:53 +0300 Subject: [PATCH 05/64] Bluetooth: Add another AR3012 04ca:3018 device commit 441ad62d6c3f131f1dbd7dcdd9cbe3f74dbd8501 upstream. T: Bus=01 Lev=01 Prnt=01 Port=07 Cnt=04 Dev#= 5 Spd=12 MxCh= 0 D: Ver= 1.10 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=04ca ProdID=3018 Rev=00.01 C: #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=100mA I: If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb I: If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb Signed-off-by: Dmitry Tunin Signed-off-by: Marcel Holtmann Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/ath3k.c | 2 ++ drivers/bluetooth/btusb.c | 1 + 2 files changed, 3 insertions(+) diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index fadba88745dc..b793853ff05f 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -94,6 +94,7 @@ static const struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x04CA, 0x300f) }, { USB_DEVICE(0x04CA, 0x3010) }, { USB_DEVICE(0x04CA, 0x3014) }, + { USB_DEVICE(0x04CA, 0x3018) }, { USB_DEVICE(0x0930, 0x0219) }, { USB_DEVICE(0x0930, 0x021c) }, { USB_DEVICE(0x0930, 0x0220) }, @@ -162,6 +163,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = { { USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3014), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3018), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x021c), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 }, diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 2f633df9f4e6..dd220fad366c 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -209,6 +209,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3014), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3018), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x021c), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 }, From 5cec5e32ba5637076aa8f06d61f89cecd877b78e Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Mon, 21 Nov 2016 13:37:48 +0100 Subject: [PATCH 06/64] s390/qdio: clear DSCI prior to scanning multiple input queues commit 1e4a382fdc0ba8d1a85b758c0811de3a3631085e upstream. For devices with multiple input queues, tiqdio_call_inq_handlers() iterates over all input queues and clears the device's DSCI during each iteration. If the DSCI is re-armed during one of the later iterations, we therefore do not scan the previous queues again. The re-arming also raises a new adapter interrupt. But its handler does not trigger a rescan for the device, as the DSCI has already been erroneously cleared. This can result in queue stalls on devices with multiple input queues. Fix it by clearing the DSCI just once, prior to scanning the queues. As the code is moved in front of the loop, we also need to access the DSCI directly (ie irq->dsci) instead of going via each queue's parent pointer to the same irq. This is not a functional change, and a follow-up patch will clean up the other users. In practice, this bug only affects CQ-enabled HiperSockets devices, ie. devices with sysfs-attribute "hsuid" set. Setting a hsuid is needed for AF_IUCV socket applications that use HiperSockets communication. Fixes: 104ea556ee7f ("qdio: support asynchronous delivery of storage blocks") Reviewed-by: Ursula Braun Signed-off-by: Julian Wiedmann Signed-off-by: Martin Schwidefsky Signed-off-by: Greg Kroah-Hartman --- drivers/s390/cio/qdio_thinint.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c index 5d06253c2a7a..30e9fbbff051 100644 --- a/drivers/s390/cio/qdio_thinint.c +++ b/drivers/s390/cio/qdio_thinint.c @@ -147,11 +147,11 @@ static inline void tiqdio_call_inq_handlers(struct qdio_irq *irq) struct qdio_q *q; int i; - for_each_input_queue(irq, q, i) { - if (!references_shared_dsci(irq) && - has_multiple_inq_on_dsci(irq)) - xchg(q->irq_ptr->dsci, 0); + if (!references_shared_dsci(irq) && + has_multiple_inq_on_dsci(irq)) + xchg(irq->dsci, 0); + for_each_input_queue(irq, q, i) { if (q->u.in.queue_start_poll) { /* skip if polling is enabled or already in work */ if (test_and_set_bit(QDIO_QUEUE_IRQS_DISABLED, From b848102542f5cab63606ad4a45da2e5edc14c571 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Mon, 30 Jan 2017 15:52:14 +0100 Subject: [PATCH 07/64] s390/dcssblk: fix device size calculation in dcssblk_direct_access() commit a63f53e34db8b49675448d03ae324f6c5bc04fe6 upstream. Since commit dd22f551 "block: Change direct_access calling convention", the device size calculation in dcssblk_direct_access() is off-by-one. This results in bdev_direct_access() always returning -ENXIO because the returned value is not page aligned. Fix this by adding 1 to the dev_sz calculation. Fixes: dd22f551 ("block: Change direct_access calling convention") Signed-off-by: Gerald Schaefer Signed-off-by: Martin Schwidefsky Signed-off-by: Greg Kroah-Hartman --- drivers/s390/block/dcssblk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 9d66b4fb174b..415d10a67b7a 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -892,7 +892,7 @@ dcssblk_direct_access (struct block_device *bdev, sector_t secnum, dev_info = bdev->bd_disk->private_data; if (!dev_info) return -ENODEV; - dev_sz = dev_info->end - dev_info->start; + dev_sz = dev_info->end - dev_info->start + 1; offset = secnum * 512; *kaddr = (void *) dev_info->start + offset; *pfn = __pfn_to_pfn_t(PFN_DOWN(dev_info->start + offset), PFN_DEV); From 91cfcaa6ed46e41c8b44ee09754988b64e075ef2 Mon Sep 17 00:00:00 2001 From: Michael Holzheu Date: Tue, 7 Feb 2017 18:09:14 +0100 Subject: [PATCH 08/64] s390/kdump: Use "LINUX" ELF note name instead of "CORE" commit a4a81d8eebdc1d209d034f62a082a5131e4242b5 upstream. In binutils/libbfd (bfd/elf.c) it is enforced that all s390 specific ELF notes like e.g. NT_S390_PREFIX or NT_S390_CTRS have "LINUX" specified as note name. Otherwise the notes are ignored. For /proc/vmcore we currently use "CORE" for these notes. Up to now this has not been a real problem because the dump analysis tool "crash" does not check the note name. But it will break all programs that use libbfd for processing ELF notes. So fix this and use "LINUX" for all s390 specific notes to comply with libbfd. Reported-by: Philipp Rudo Reviewed-by: Philipp Rudo Signed-off-by: Michael Holzheu Signed-off-by: Martin Schwidefsky Signed-off-by: Greg Kroah-Hartman --- arch/s390/kernel/crash_dump.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index f9293bfefb7f..408b4f4fda0f 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -329,7 +329,11 @@ static void *nt_init_name(void *buf, Elf64_Word type, void *desc, int d_len, static inline void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len) { - return nt_init_name(buf, type, desc, d_len, KEXEC_CORE_NOTE_NAME); + const char *note_name = "LINUX"; + + if (type == NT_PRPSINFO || type == NT_PRSTATUS || type == NT_PRFPREG) + note_name = KEXEC_CORE_NOTE_NAME; + return nt_init_name(buf, type, desc, d_len, note_name); } /* From dc31841fcdce435ed88f87489f9ab09b48b43505 Mon Sep 17 00:00:00 2001 From: Peter Oberparleiter Date: Mon, 20 Feb 2017 14:52:58 +0100 Subject: [PATCH 09/64] s390/chsc: Add exception handler for CHSC instruction commit 77759137248f34864a8f7a58bbcebfcf1047504a upstream. Prevent kernel crashes due to unhandled exceptions raised by the CHSC instruction which may for example be triggered by invalid ioctl data. Fixes: 64150adf89df ("s390/cio: Introduce generic synchronous CHSC IOCTL") Signed-off-by: Peter Oberparleiter Reviewed-by: Sebastian Ott Reviewed-by: Cornelia Huck Signed-off-by: Martin Schwidefsky Signed-off-by: Greg Kroah-Hartman --- drivers/s390/cio/ioasm.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/s390/cio/ioasm.c b/drivers/s390/cio/ioasm.c index 8225da619014..4182f60124da 100644 --- a/drivers/s390/cio/ioasm.c +++ b/drivers/s390/cio/ioasm.c @@ -165,13 +165,15 @@ int tpi(struct tpi_info *addr) int chsc(void *chsc_area) { typedef struct { char _[4096]; } addr_type; - int cc; + int cc = -EIO; asm volatile( " .insn rre,0xb25f0000,%2,0\n" - " ipm %0\n" + "0: ipm %0\n" " srl %0,28\n" - : "=d" (cc), "=m" (*(addr_type *) chsc_area) + "1:\n" + EX_TABLE(0b, 1b) + : "+d" (cc), "=m" (*(addr_type *) chsc_area) : "d" (chsc_area), "m" (*(addr_type *) chsc_area) : "cc"); trace_s390_cio_chsc(chsc_area, cc); From 9d38fd6a4f6c097b32128995a260a55351dc7667 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 24 Feb 2017 07:43:51 +0100 Subject: [PATCH 10/64] s390: TASK_SIZE for kernel threads commit fb94a687d96c570d46332a4a890f1dcb7310e643 upstream. Return a sensible value if TASK_SIZE if called from a kernel thread. This gets us around an issue with copy_mount_options that does a magic size calculation "TASK_SIZE - (unsigned long)data" while in a kernel thread and data pointing to kernel space. Signed-off-by: Martin Schwidefsky Signed-off-by: Greg Kroah-Hartman --- arch/s390/include/asm/processor.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 602af692efdc..6bcbbece082b 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -89,7 +89,8 @@ extern void execve_tail(void); * User space process size: 2GB for 31 bit, 4TB or 8PT for 64 bit. */ -#define TASK_SIZE_OF(tsk) ((tsk)->mm->context.asce_limit) +#define TASK_SIZE_OF(tsk) ((tsk)->mm ? \ + (tsk)->mm->context.asce_limit : TASK_MAX_SIZE) #define TASK_UNMAPPED_BASE (test_thread_flag(TIF_31BIT) ? \ (1UL << 30) : (1UL << 41)) #define TASK_SIZE TASK_SIZE_OF(current) From 321081d522d332b44fd506ea366e1c82cfd94d4e Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sat, 4 Feb 2017 11:40:36 +0100 Subject: [PATCH 11/64] s390: make setup_randomness work commit da8fd820f389a0e29080b14c61bf5cf1d8ef5ca1 upstream. Commit bcfcbb6bae64 ("s390: add system information as device randomness") intended to add some virtual machine specific information to the randomness pool. Unfortunately it uses the page allocator before it is ready to use. In result the page allocator always returns NULL and the setup_randomness function never adds anything to the randomness pool. To fix this use memblock_alloc and memblock_free instead. Fixes: bcfcbb6bae64 ("s390: add system information as device randomness") Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky Signed-off-by: Greg Kroah-Hartman --- arch/s390/kernel/setup.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index d027f2eb3559..d2bc8fa8b4e6 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -819,10 +819,10 @@ static void __init setup_randomness(void) { struct sysinfo_3_2_2 *vmms; - vmms = (struct sysinfo_3_2_2 *) alloc_page(GFP_KERNEL); - if (vmms && stsi(vmms, 3, 2, 2) == 0 && vmms->count) + vmms = (struct sysinfo_3_2_2 *) memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (stsi(vmms, 3, 2, 2) == 0 && vmms->count) add_device_randomness(&vmms, vmms->count); - free_page((unsigned long) vmms); + memblock_free((unsigned long) vmms, PAGE_SIZE); } /* From e067f68db256c2dc04aae8acb42ebfc138d87a7e Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sun, 5 Feb 2017 23:03:18 +0100 Subject: [PATCH 12/64] s390: use correct input data address for setup_randomness commit 4920e3cf77347d7d7373552d4839e8d832321313 upstream. The current implementation of setup_randomness uses the stack address and therefore the pointer to the SYSIB 3.2.2 block as input data address. Furthermore the length of the input data is the number of virtual-machine description blocks which is typically one. This means that typically a single zero byte is fed to add_device_randomness. Fix both of these and use the address of the first virtual machine description block as input data address and also use the correct length. Fixes: bcfcbb6bae64 ("s390: add system information as device randomness") Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky Signed-off-by: Greg Kroah-Hartman --- arch/s390/kernel/setup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index d2bc8fa8b4e6..e974e53ab597 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -821,7 +821,7 @@ static void __init setup_randomness(void) vmms = (struct sysinfo_3_2_2 *) memblock_alloc(PAGE_SIZE, PAGE_SIZE); if (stsi(vmms, 3, 2, 2) == 0 && vmms->count) - add_device_randomness(&vmms, vmms->count); + add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count); memblock_free((unsigned long) vmms, PAGE_SIZE); } From 60037aa689bac37816dca4eab2e8319eaa785dc6 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 21 Feb 2017 11:28:01 +0100 Subject: [PATCH 13/64] net: mvpp2: fix DMA address calculation in mvpp2_txq_inc_put() commit 239a3b663647869330955ec59caac0100ef9b60a upstream. When TX descriptors are filled in, the buffer DMA address is split between the tx_desc->buf_phys_addr field (high-order bits) and tx_desc->packet_offset field (5 low-order bits). However, when we re-calculate the DMA address from the TX descriptor in mvpp2_txq_inc_put(), we do not take tx_desc->packet_offset into account. This means that when the DMA address is not aligned on a 32 bytes boundary, we end up calling dma_unmap_single() with a DMA address that was not the one returned by dma_map_single(). This inconsistency is detected by the kernel when DMA_API_DEBUG is enabled. We fix this problem by properly calculating the DMA address in mvpp2_txq_inc_put(). Signed-off-by: Thomas Petazzoni Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/marvell/mvpp2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 930c8165f2a8..0a4e81a253fb 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -991,7 +991,7 @@ static void mvpp2_txq_inc_put(struct mvpp2_txq_pcpu *txq_pcpu, txq_pcpu->buffs + txq_pcpu->txq_put_index; tx_buf->skb = skb; tx_buf->size = tx_desc->data_size; - tx_buf->phys = tx_desc->buf_phys_addr; + tx_buf->phys = tx_desc->buf_phys_addr + tx_desc->packet_offset; txq_pcpu->txq_put_index++; if (txq_pcpu->txq_put_index == txq_pcpu->size) txq_pcpu->txq_put_index = 0; From 411d0b0ced692dd2c0d7c10514ca8b923d8fa0f8 Mon Sep 17 00:00:00 2001 From: Andrew Donnellan Date: Fri, 9 Dec 2016 17:18:50 +1100 Subject: [PATCH 14/64] cxl: Prevent read/write to AFU config space while AFU not configured commit 14a3ae34bfd0bcb1cc12d55b06a8584c11fac6fc upstream. During EEH recovery, we deconfigure all AFUs whilst leaving the corresponding vPHB and virtual PCI device in place. If something attempts to interact with the AFU's PCI config space (e.g. running lspci) after the AFU has been deconfigured and before it's reconfigured, cxl_pcie_{read,write}_config() will read invalid values from the deconfigured struct cxl_afu and proceed to Oops when they try to dereference pointers that have been set to NULL during deconfiguration. Add a rwsem to struct cxl_afu so we can prevent interaction with config space while the AFU is deconfigured. Reported-by: Pradipta Ghosh Suggested-by: Frederic Barrat Signed-off-by: Andrew Donnellan Signed-off-by: Vaibhav Jain Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- drivers/misc/cxl/cxl.h | 2 ++ drivers/misc/cxl/main.c | 3 ++- drivers/misc/cxl/pci.c | 2 ++ drivers/misc/cxl/vphb.c | 51 +++++++++++++++++++++++------------------ 4 files changed, 35 insertions(+), 23 deletions(-) diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h index a144073593fa..379c463e0c4f 100644 --- a/drivers/misc/cxl/cxl.h +++ b/drivers/misc/cxl/cxl.h @@ -418,6 +418,8 @@ struct cxl_afu { struct dentry *debugfs; struct mutex contexts_lock; spinlock_t afu_cntl_lock; + /* Used to block access to AFU config space while deconfigured */ + struct rw_semaphore configured_rwsem; /* AFU error buffer fields and bin attribute for sysfs */ u64 eb_len, eb_offset; diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c index 62e0dfb5f15b..2a6bf1d0a3a4 100644 --- a/drivers/misc/cxl/main.c +++ b/drivers/misc/cxl/main.c @@ -268,7 +268,8 @@ struct cxl_afu *cxl_alloc_afu(struct cxl *adapter, int slice) idr_init(&afu->contexts_idr); mutex_init(&afu->contexts_lock); spin_lock_init(&afu->afu_cntl_lock); - + init_rwsem(&afu->configured_rwsem); + down_write(&afu->configured_rwsem); afu->prefault_mode = CXL_PREFAULT_NONE; afu->irqs_max = afu->adapter->user_irqs; diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index e96be9ca4e60..b2ff10891775 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -1129,6 +1129,7 @@ static int pci_configure_afu(struct cxl_afu *afu, struct cxl *adapter, struct pc if ((rc = cxl_native_register_psl_irq(afu))) goto err2; + up_write(&afu->configured_rwsem); return 0; err2: @@ -1141,6 +1142,7 @@ err1: static void pci_deconfigure_afu(struct cxl_afu *afu) { + down_write(&afu->configured_rwsem); cxl_native_release_psl_irq(afu); if (afu->adapter->native->sl_ops->release_serr_irq) afu->adapter->native->sl_ops->release_serr_irq(afu); diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c index 3519acebfdab..639a343b7836 100644 --- a/drivers/misc/cxl/vphb.c +++ b/drivers/misc/cxl/vphb.c @@ -76,23 +76,22 @@ static int cxl_pcie_cfg_record(u8 bus, u8 devfn) return (bus << 8) + devfn; } -static int cxl_pcie_config_info(struct pci_bus *bus, unsigned int devfn, - struct cxl_afu **_afu, int *_record) +static inline struct cxl_afu *pci_bus_to_afu(struct pci_bus *bus) +{ + struct pci_controller *phb = bus ? pci_bus_to_host(bus) : NULL; + + return phb ? phb->private_data : NULL; +} + +static inline int cxl_pcie_config_info(struct pci_bus *bus, unsigned int devfn, + struct cxl_afu *afu, int *_record) { - struct pci_controller *phb; - struct cxl_afu *afu; int record; - phb = pci_bus_to_host(bus); - if (phb == NULL) - return PCIBIOS_DEVICE_NOT_FOUND; - - afu = (struct cxl_afu *)phb->private_data; record = cxl_pcie_cfg_record(bus->number, devfn); if (record > afu->crs_num) return PCIBIOS_DEVICE_NOT_FOUND; - *_afu = afu; *_record = record; return 0; } @@ -106,9 +105,14 @@ static int cxl_pcie_read_config(struct pci_bus *bus, unsigned int devfn, u16 val16; u32 val32; - rc = cxl_pcie_config_info(bus, devfn, &afu, &record); + afu = pci_bus_to_afu(bus); + /* Grab a reader lock on afu. */ + if (afu == NULL || !down_read_trylock(&afu->configured_rwsem)) + return PCIBIOS_DEVICE_NOT_FOUND; + + rc = cxl_pcie_config_info(bus, devfn, afu, &record); if (rc) - return rc; + goto out; switch (len) { case 1: @@ -127,10 +131,9 @@ static int cxl_pcie_read_config(struct pci_bus *bus, unsigned int devfn, WARN_ON(1); } - if (rc) - return PCIBIOS_DEVICE_NOT_FOUND; - - return PCIBIOS_SUCCESSFUL; +out: + up_read(&afu->configured_rwsem); + return rc ? PCIBIOS_DEVICE_NOT_FOUND : PCIBIOS_SUCCESSFUL; } static int cxl_pcie_write_config(struct pci_bus *bus, unsigned int devfn, @@ -139,9 +142,14 @@ static int cxl_pcie_write_config(struct pci_bus *bus, unsigned int devfn, int rc, record; struct cxl_afu *afu; - rc = cxl_pcie_config_info(bus, devfn, &afu, &record); + afu = pci_bus_to_afu(bus); + /* Grab a reader lock on afu. */ + if (afu == NULL || !down_read_trylock(&afu->configured_rwsem)) + return PCIBIOS_DEVICE_NOT_FOUND; + + rc = cxl_pcie_config_info(bus, devfn, afu, &record); if (rc) - return rc; + goto out; switch (len) { case 1: @@ -157,10 +165,9 @@ static int cxl_pcie_write_config(struct pci_bus *bus, unsigned int devfn, WARN_ON(1); } - if (rc) - return PCIBIOS_SET_FAILED; - - return PCIBIOS_SUCCESSFUL; +out: + up_read(&afu->configured_rwsem); + return rc ? PCIBIOS_SET_FAILED : PCIBIOS_SUCCESSFUL; } static struct pci_ops cxl_pcie_pci_ops = From 53d43706f2ba5cd805093d21d69fd700584a71ab Mon Sep 17 00:00:00 2001 From: Andrew Donnellan Date: Mon, 6 Feb 2017 12:07:17 +1100 Subject: [PATCH 15/64] cxl: fix nested locking hang during EEH hotplug commit 171ed0fcd8966d82c45376f1434678e7b9d4d9b1 upstream. Commit 14a3ae34bfd0 ("cxl: Prevent read/write to AFU config space while AFU not configured") introduced a rwsem to fix an invalid memory access that occurred when someone attempts to access the config space of an AFU on a vPHB whilst the AFU is deconfigured, such as during EEH recovery. It turns out that it's possible to run into a nested locking issue when EEH recovery fails and a full device hotplug is required. cxl_pci_error_detected() deconfigures the AFU, taking a writer lock on configured_rwsem. When EEH recovery fails, the EEH code calls pci_hp_remove_devices() to remove the device, which in turn calls cxl_remove() -> cxl_pci_remove_afu() -> pci_deconfigure_afu(), which tries to grab the writer lock that's already held. Standard rwsem semantics don't express what we really want to do here and don't allow for nested locking. Fix this by replacing the rwsem with an atomic_t which we can control more finely. Allow the AFU to be locked multiple times so long as there are no readers. Fixes: 14a3ae34bfd0 ("cxl: Prevent read/write to AFU config space while AFU not configured") Signed-off-by: Andrew Donnellan Acked-by: Frederic Barrat Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- drivers/misc/cxl/cxl.h | 5 +++-- drivers/misc/cxl/main.c | 3 +-- drivers/misc/cxl/pci.c | 11 +++++++++-- drivers/misc/cxl/vphb.c | 18 ++++++++++++++---- 4 files changed, 27 insertions(+), 10 deletions(-) diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h index 379c463e0c4f..52ee3da85366 100644 --- a/drivers/misc/cxl/cxl.h +++ b/drivers/misc/cxl/cxl.h @@ -418,8 +418,9 @@ struct cxl_afu { struct dentry *debugfs; struct mutex contexts_lock; spinlock_t afu_cntl_lock; - /* Used to block access to AFU config space while deconfigured */ - struct rw_semaphore configured_rwsem; + + /* -1: AFU deconfigured/locked, >= 0: number of readers */ + atomic_t configured_state; /* AFU error buffer fields and bin attribute for sysfs */ u64 eb_len, eb_offset; diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c index 2a6bf1d0a3a4..cc1706a92ace 100644 --- a/drivers/misc/cxl/main.c +++ b/drivers/misc/cxl/main.c @@ -268,8 +268,7 @@ struct cxl_afu *cxl_alloc_afu(struct cxl *adapter, int slice) idr_init(&afu->contexts_idr); mutex_init(&afu->contexts_lock); spin_lock_init(&afu->afu_cntl_lock); - init_rwsem(&afu->configured_rwsem); - down_write(&afu->configured_rwsem); + atomic_set(&afu->configured_state, -1); afu->prefault_mode = CXL_PREFAULT_NONE; afu->irqs_max = afu->adapter->user_irqs; diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index b2ff10891775..dd99b06e121a 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -1129,7 +1129,7 @@ static int pci_configure_afu(struct cxl_afu *afu, struct cxl *adapter, struct pc if ((rc = cxl_native_register_psl_irq(afu))) goto err2; - up_write(&afu->configured_rwsem); + atomic_set(&afu->configured_state, 0); return 0; err2: @@ -1142,7 +1142,14 @@ err1: static void pci_deconfigure_afu(struct cxl_afu *afu) { - down_write(&afu->configured_rwsem); + /* + * It's okay to deconfigure when AFU is already locked, otherwise wait + * until there are no readers + */ + if (atomic_read(&afu->configured_state) != -1) { + while (atomic_cmpxchg(&afu->configured_state, 0, -1) != -1) + schedule(); + } cxl_native_release_psl_irq(afu); if (afu->adapter->native->sl_ops->release_serr_irq) afu->adapter->native->sl_ops->release_serr_irq(afu); diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c index 639a343b7836..512a4897dbf6 100644 --- a/drivers/misc/cxl/vphb.c +++ b/drivers/misc/cxl/vphb.c @@ -83,6 +83,16 @@ static inline struct cxl_afu *pci_bus_to_afu(struct pci_bus *bus) return phb ? phb->private_data : NULL; } +static void cxl_afu_configured_put(struct cxl_afu *afu) +{ + atomic_dec_if_positive(&afu->configured_state); +} + +static bool cxl_afu_configured_get(struct cxl_afu *afu) +{ + return atomic_inc_unless_negative(&afu->configured_state); +} + static inline int cxl_pcie_config_info(struct pci_bus *bus, unsigned int devfn, struct cxl_afu *afu, int *_record) { @@ -107,7 +117,7 @@ static int cxl_pcie_read_config(struct pci_bus *bus, unsigned int devfn, afu = pci_bus_to_afu(bus); /* Grab a reader lock on afu. */ - if (afu == NULL || !down_read_trylock(&afu->configured_rwsem)) + if (afu == NULL || !cxl_afu_configured_get(afu)) return PCIBIOS_DEVICE_NOT_FOUND; rc = cxl_pcie_config_info(bus, devfn, afu, &record); @@ -132,7 +142,7 @@ static int cxl_pcie_read_config(struct pci_bus *bus, unsigned int devfn, } out: - up_read(&afu->configured_rwsem); + cxl_afu_configured_put(afu); return rc ? PCIBIOS_DEVICE_NOT_FOUND : PCIBIOS_SUCCESSFUL; } @@ -144,7 +154,7 @@ static int cxl_pcie_write_config(struct pci_bus *bus, unsigned int devfn, afu = pci_bus_to_afu(bus); /* Grab a reader lock on afu. */ - if (afu == NULL || !down_read_trylock(&afu->configured_rwsem)) + if (afu == NULL || !cxl_afu_configured_get(afu)) return PCIBIOS_DEVICE_NOT_FOUND; rc = cxl_pcie_config_info(bus, devfn, afu, &record); @@ -166,7 +176,7 @@ static int cxl_pcie_write_config(struct pci_bus *bus, unsigned int devfn, } out: - up_read(&afu->configured_rwsem); + cxl_afu_configured_put(afu); return rc ? PCIBIOS_SET_FAILED : PCIBIOS_SUCCESSFUL; } From c9b3f3173fa5178df2c8fe2279442f48faaf7a98 Mon Sep 17 00:00:00 2001 From: Gavin Li Date: Tue, 17 Jan 2017 15:24:05 -0800 Subject: [PATCH 16/64] brcmfmac: fix incorrect event channel deduction commit 8e290cecdd0178f3d4cf7d463c51dc7e462843b4 upstream. brcmf_sdio_fromevntchan() was being called on the the data frame rather than the software header, causing some frames to be mischaracterized as on the event channel rather than the data channel. This fixes a major performance regression (due to dropped packets). With this patch the download speed jumped from 1Mbit/s back up to 40MBit/s due to the sheer amount of packets being incorrectly processed. Fixes: c56caa9db8ab ("brcmfmac: screening firmware event packet") Signed-off-by: Gavin Li Acked-by: Arend van Spriel [kvalo@codeaurora.org: improve commit logs based on email discussion] Signed-off-by: Kalle Valo Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index b892dac70f4b..2458e6e05276 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -1660,7 +1660,7 @@ static u8 brcmf_sdio_rxglom(struct brcmf_sdio *bus, u8 rxseq) pfirst->len, pfirst->next, pfirst->prev); skb_unlink(pfirst, &bus->glom); - if (brcmf_sdio_fromevntchan(pfirst->data)) + if (brcmf_sdio_fromevntchan(&dptr[SDPCM_HWHDR_LEN])) brcmf_rx_event(bus->sdiodev->dev, pfirst); else brcmf_rx_frame(bus->sdiodev->dev, pfirst, From 808e83e5add13152bd4a88346487de68395c136b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 20 Jan 2017 18:28:35 +1300 Subject: [PATCH 17/64] mnt: Tuck mounts under others instead of creating shadow/side mounts. commit 1064f874abc0d05eeed8993815f584d847b72486 upstream. Ever since mount propagation was introduced in cases where a mount in propagated to parent mount mountpoint pair that is already in use the code has placed the new mount behind the old mount in the mount hash table. This implementation detail is problematic as it allows creating arbitrary length mount hash chains. Furthermore it invalidates the constraint maintained elsewhere in the mount code that a parent mount and a mountpoint pair will have exactly one mount upon them. Making it hard to deal with and to talk about this special case in the mount code. Modify mount propagation to notice when there is already a mount at the parent mount and mountpoint where a new mount is propagating to and place that preexisting mount on top of the new mount. Modify unmount propagation to notice when a mount that is being unmounted has another mount on top of it (and no other children), and to replace the unmounted mount with the mount on top of it. Move the MNT_UMUONT test from __lookup_mnt_last into __propagate_umount as that is the only call of __lookup_mnt_last where MNT_UMOUNT may be set on any mount visible in the mount hash table. These modifications allow: - __lookup_mnt_last to be removed. - attach_shadows to be renamed __attach_mnt and its shadow handling to be removed. - commit_tree to be simplified - copy_tree to be simplified The result is an easier to understand tree of mounts that does not allow creation of arbitrary length hash chains in the mount hash table. The result is also a very slight userspace visible difference in semantics. The following two cases now behave identically, where before order mattered: case 1: (explicit user action) B is a slave of A mount something on A/a , it will propagate to B/a and than mount something on B/a case 2: (tucked mount) B is a slave of A mount something on B/a and than mount something on A/a Histroically umount A/a would fail in case 1 and succeed in case 2. Now umount A/a succeeds in both configurations. This very small change in semantics appears if anything to be a bug fix to me and my survey of userspace leads me to believe that no programs will notice or care of this subtle semantic change. v2: Updated to mnt_change_mountpoint to not call dput or mntput and instead to decrement the counts directly. It is guaranteed that there will be other references when mnt_change_mountpoint is called so this is safe. v3: Moved put_mountpoint under mount_lock in attach_recursive_mnt As the locking in fs/namespace.c changed between v2 and v3. v4: Reworked the logic in propagate_mount_busy and __propagate_umount that detects when a mount completely covers another mount. v5: Removed unnecessary tests whose result is alwasy true in find_topper and attach_recursive_mnt. v6: Document the user space visible semantic difference. Fixes: b90fa9ae8f51 ("[PATCH] shared mount handling: bind and rbind") Tested-by: Andrei Vagin Signed-off-by: "Eric W. Biederman" Signed-off-by: Greg Kroah-Hartman --- fs/mount.h | 1 - fs/namespace.c | 110 +++++++++++++++++++++++++++---------------------- fs/pnode.c | 61 +++++++++++++++++++++------ fs/pnode.h | 2 + 4 files changed, 111 insertions(+), 63 deletions(-) diff --git a/fs/mount.h b/fs/mount.h index d2e25d7b64b3..d8295f273a2f 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -89,7 +89,6 @@ static inline int is_mounted(struct vfsmount *mnt) } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *); -extern struct mount *__lookup_mnt_last(struct vfsmount *, struct dentry *); extern int __legitimize_mnt(struct vfsmount *, unsigned); extern bool legitimize_mnt(struct vfsmount *, unsigned); diff --git a/fs/namespace.c b/fs/namespace.c index 7cea503ae06d..ea751263fefa 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -640,28 +640,6 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) return NULL; } -/* - * find the last mount at @dentry on vfsmount @mnt. - * mount_lock must be held. - */ -struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry) -{ - struct mount *p, *res = NULL; - p = __lookup_mnt(mnt, dentry); - if (!p) - goto out; - if (!(p->mnt.mnt_flags & MNT_UMOUNT)) - res = p; - hlist_for_each_entry_continue(p, mnt_hash) { - if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry) - break; - if (!(p->mnt.mnt_flags & MNT_UMOUNT)) - res = p; - } -out: - return res; -} - /* * lookup_mnt - Return the first child mount mounted at path * @@ -882,6 +860,13 @@ void mnt_set_mountpoint(struct mount *mnt, hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); } +static void __attach_mnt(struct mount *mnt, struct mount *parent) +{ + hlist_add_head_rcu(&mnt->mnt_hash, + m_hash(&parent->mnt, mnt->mnt_mountpoint)); + list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); +} + /* * vfsmount lock must be held for write */ @@ -890,28 +875,45 @@ static void attach_mnt(struct mount *mnt, struct mountpoint *mp) { mnt_set_mountpoint(parent, mp, mnt); - hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry)); - list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); + __attach_mnt(mnt, parent); } -static void attach_shadowed(struct mount *mnt, - struct mount *parent, - struct mount *shadows) +void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) { - if (shadows) { - hlist_add_behind_rcu(&mnt->mnt_hash, &shadows->mnt_hash); - list_add(&mnt->mnt_child, &shadows->mnt_child); - } else { - hlist_add_head_rcu(&mnt->mnt_hash, - m_hash(&parent->mnt, mnt->mnt_mountpoint)); - list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); - } + struct mountpoint *old_mp = mnt->mnt_mp; + struct dentry *old_mountpoint = mnt->mnt_mountpoint; + struct mount *old_parent = mnt->mnt_parent; + + list_del_init(&mnt->mnt_child); + hlist_del_init(&mnt->mnt_mp_list); + hlist_del_init_rcu(&mnt->mnt_hash); + + attach_mnt(mnt, parent, mp); + + put_mountpoint(old_mp); + + /* + * Safely avoid even the suggestion this code might sleep or + * lock the mount hash by taking advantage of the knowledge that + * mnt_change_mountpoint will not release the final reference + * to a mountpoint. + * + * During mounting, the mount passed in as the parent mount will + * continue to use the old mountpoint and during unmounting, the + * old mountpoint will continue to exist until namespace_unlock, + * which happens well after mnt_change_mountpoint. + */ + spin_lock(&old_mountpoint->d_lock); + old_mountpoint->d_lockref.count--; + spin_unlock(&old_mountpoint->d_lock); + + mnt_add_count(old_parent, -1); } /* * vfsmount lock must be held for write */ -static void commit_tree(struct mount *mnt, struct mount *shadows) +static void commit_tree(struct mount *mnt) { struct mount *parent = mnt->mnt_parent; struct mount *m; @@ -929,7 +931,7 @@ static void commit_tree(struct mount *mnt, struct mount *shadows) n->mounts += n->pending_mounts; n->pending_mounts = 0; - attach_shadowed(mnt, parent, shadows); + __attach_mnt(mnt, parent); touch_mnt_namespace(n); } @@ -1737,7 +1739,6 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, continue; for (s = r; s; s = next_mnt(s, r)) { - struct mount *t = NULL; if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { s = skip_mnt_tree(s); @@ -1759,14 +1760,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, goto out; lock_mount_hash(); list_add_tail(&q->mnt_list, &res->mnt_list); - mnt_set_mountpoint(parent, p->mnt_mp, q); - if (!list_empty(&parent->mnt_mounts)) { - t = list_last_entry(&parent->mnt_mounts, - struct mount, mnt_child); - if (t->mnt_mp != p->mnt_mp) - t = NULL; - } - attach_shadowed(q, parent, t); + attach_mnt(q, parent, p->mnt_mp); unlock_mount_hash(); } } @@ -1967,10 +1961,18 @@ static int attach_recursive_mnt(struct mount *source_mnt, { HLIST_HEAD(tree_list); struct mnt_namespace *ns = dest_mnt->mnt_ns; + struct mountpoint *smp; struct mount *child, *p; struct hlist_node *n; int err; + /* Preallocate a mountpoint in case the new mounts need + * to be tucked under other mounts. + */ + smp = get_mountpoint(source_mnt->mnt.mnt_root); + if (IS_ERR(smp)) + return PTR_ERR(smp); + /* Is there space to add these mounts to the mount namespace? */ if (!parent_path) { err = count_mounts(ns, source_mnt); @@ -1997,16 +1999,19 @@ static int attach_recursive_mnt(struct mount *source_mnt, touch_mnt_namespace(source_mnt->mnt_ns); } else { mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); - commit_tree(source_mnt, NULL); + commit_tree(source_mnt); } hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { struct mount *q; hlist_del_init(&child->mnt_hash); - q = __lookup_mnt_last(&child->mnt_parent->mnt, - child->mnt_mountpoint); - commit_tree(child, q); + q = __lookup_mnt(&child->mnt_parent->mnt, + child->mnt_mountpoint); + if (q) + mnt_change_mountpoint(child, smp, q); + commit_tree(child); } + put_mountpoint(smp); unlock_mount_hash(); return 0; @@ -2021,6 +2026,11 @@ static int attach_recursive_mnt(struct mount *source_mnt, cleanup_group_ids(source_mnt, NULL); out: ns->pending_mounts = 0; + + read_seqlock_excl(&mount_lock); + put_mountpoint(smp); + read_sequnlock_excl(&mount_lock); + return err; } diff --git a/fs/pnode.c b/fs/pnode.c index 234a9ac49958..b394ca5307ec 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -324,6 +324,21 @@ out: return ret; } +static struct mount *find_topper(struct mount *mnt) +{ + /* If there is exactly one mount covering mnt completely return it. */ + struct mount *child; + + if (!list_is_singular(&mnt->mnt_mounts)) + return NULL; + + child = list_first_entry(&mnt->mnt_mounts, struct mount, mnt_child); + if (child->mnt_mountpoint != mnt->mnt.mnt_root) + return NULL; + + return child; +} + /* * return true if the refcount is greater than count */ @@ -344,9 +359,8 @@ static inline int do_refcount_check(struct mount *mnt, int count) */ int propagate_mount_busy(struct mount *mnt, int refcnt) { - struct mount *m, *child; + struct mount *m, *child, *topper; struct mount *parent = mnt->mnt_parent; - int ret = 0; if (mnt == parent) return do_refcount_check(mnt, refcnt); @@ -361,12 +375,24 @@ int propagate_mount_busy(struct mount *mnt, int refcnt) for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { - child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint); - if (child && list_empty(&child->mnt_mounts) && - (ret = do_refcount_check(child, 1))) - break; + int count = 1; + child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); + if (!child) + continue; + + /* Is there exactly one mount on the child that covers + * it completely whose reference should be ignored? + */ + topper = find_topper(child); + if (topper) + count += 1; + else if (!list_empty(&child->mnt_mounts)) + continue; + + if (do_refcount_check(child, count)) + return 1; } - return ret; + return 0; } /* @@ -383,7 +409,7 @@ void propagate_mount_unlock(struct mount *mnt) for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { - child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint); + child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); if (child) child->mnt.mnt_flags &= ~MNT_LOCKED; } @@ -401,9 +427,11 @@ static void mark_umount_candidates(struct mount *mnt) for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { - struct mount *child = __lookup_mnt_last(&m->mnt, + struct mount *child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); - if (child && (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m))) { + if (!child || (child->mnt.mnt_flags & MNT_UMOUNT)) + continue; + if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) { SET_MNT_MARK(child); } } @@ -422,8 +450,8 @@ static void __propagate_umount(struct mount *mnt) for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { - - struct mount *child = __lookup_mnt_last(&m->mnt, + struct mount *topper; + struct mount *child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); /* * umount the child only if the child has no children @@ -432,6 +460,15 @@ static void __propagate_umount(struct mount *mnt) if (!child || !IS_MNT_MARKED(child)) continue; CLEAR_MNT_MARK(child); + + /* If there is exactly one mount covering all of child + * replace child with that mount. + */ + topper = find_topper(child); + if (topper) + mnt_change_mountpoint(child->mnt_parent, child->mnt_mp, + topper); + if (list_empty(&child->mnt_mounts)) { list_del_init(&child->mnt_child); child->mnt.mnt_flags |= MNT_UMOUNT; diff --git a/fs/pnode.h b/fs/pnode.h index 550f5a8b4fcf..dc87e65becd2 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -49,6 +49,8 @@ int get_dominating_id(struct mount *mnt, const struct path *root); unsigned int mnt_get_count(struct mount *mnt); void mnt_set_mountpoint(struct mount *, struct mountpoint *, struct mount *); +void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, + struct mount *mnt); struct mount *copy_tree(struct mount *, struct dentry *, int); bool is_path_reachable(struct mount *, struct dentry *, const struct path *root); From 1626076b8e1cde49becc0e68d2779174e6a6f599 Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Wed, 28 Dec 2016 14:47:23 +0200 Subject: [PATCH 18/64] IB/ipoib: Fix deadlock between rmmod and set_mode commit 0a0007f28304cb9fc87809c86abb80ec71317f20 upstream. When calling set_mode from sys/fs, the call flow locks the sys/fs lock first and then tries to lock rtnl_lock (when calling ipoib_set_mod). On the other hand, the rmmod call flow takes the rtnl_lock first (when calling unregister_netdev) and then tries to take the sys/fs lock. Deadlock a->b, b->a. The problem starts when ipoib_set_mod frees it's rtnl_lck and tries to get it after that. set_mod: [] ? check_preempt_curr+0x6d/0x90 [] __mutex_lock_slowpath+0x13e/0x180 [] ? __rtnl_unlock+0x15/0x20 [] mutex_lock+0x2b/0x50 [] rtnl_lock+0x15/0x20 [] ipoib_set_mode+0x97/0x160 [ib_ipoib] [] set_mode+0x3b/0x80 [ib_ipoib] [] dev_attr_store+0x20/0x30 [] sysfs_write_file+0xe5/0x170 [] vfs_write+0xb8/0x1a0 [] sys_write+0x51/0x90 [] system_call_fastpath+0x16/0x1b rmmod: [] ? put_dec+0x10c/0x110 [] ? number+0x2ee/0x320 [] schedule_timeout+0x215/0x2e0 [] ? vsnprintf+0x484/0x5f0 [] ? string+0x40/0x100 [] wait_for_common+0x123/0x180 [] ? default_wake_function+0x0/0x20 [] ? ifind_fast+0x5e/0xb0 [] wait_for_completion+0x1d/0x20 [] sysfs_addrm_finish+0x228/0x270 [] sysfs_remove_dir+0xa3/0xf0 [] kobject_del+0x16/0x40 [] device_del+0x184/0x1e0 [] netdev_unregister_kobject+0xab/0xc0 [] rollback_registered+0xae/0x130 [] unregister_netdevice+0x22/0x70 [] unregister_netdev+0x1e/0x30 [] ipoib_remove_one+0xe0/0x120 [ib_ipoib] [] ib_unregister_device+0x4f/0x100 [ib_core] [] mlx4_ib_remove+0x41/0x180 [mlx4_ib] [] mlx4_remove_device+0x71/0x90 [mlx4_core] Fixes: 862096a8bbf8 ("IB/ipoib: Add more rtnl_link_ops callbacks") Cc: Or Gerlitz Signed-off-by: Feras Daoud Signed-off-by: Erez Shitrit Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/ulp/ipoib/ipoib_cm.c | 12 +++++++----- drivers/infiniband/ulp/ipoib/ipoib_main.c | 6 ++---- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 81a8080c18b3..0616a65f0d78 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -1511,12 +1511,14 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr, ret = ipoib_set_mode(dev, buf); - rtnl_unlock(); + /* The assumption is that the function ipoib_set_mode returned + * with the rtnl held by it, if not the value -EBUSY returned, + * then no need to rtnl_unlock + */ + if (ret != -EBUSY) + rtnl_unlock(); - if (!ret) - return count; - - return ret; + return (!ret || ret == -EBUSY) ? count : ret; } static DEVICE_ATTR(mode, S_IWUSR | S_IRUGO, show_mode, set_mode); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index b58d9dca5c93..a5d9678f3b33 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -468,8 +468,7 @@ int ipoib_set_mode(struct net_device *dev, const char *buf) priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM; ipoib_flush_paths(dev); - rtnl_lock(); - return 0; + return (!rtnl_trylock()) ? -EBUSY : 0; } if (!strcmp(buf, "datagram\n")) { @@ -478,8 +477,7 @@ int ipoib_set_mode(struct net_device *dev, const char *buf) dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu)); rtnl_unlock(); ipoib_flush_paths(dev); - rtnl_lock(); - return 0; + return (!rtnl_trylock()) ? -EBUSY : 0; } return -EINVAL; From 2e539fa49efda450229e3a13db5202b4d9ae2997 Mon Sep 17 00:00:00 2001 From: Erez Shitrit Date: Wed, 1 Feb 2017 19:10:05 +0200 Subject: [PATCH 19/64] IB/IPoIB: Add destination address when re-queue packet commit 2b0841766a898aba84630fb723989a77a9d3b4e6 upstream. When sending packet to destination that was not resolved yet via path query, the driver keeps the skb and tries to re-send it again when the path is resolved. But when re-sending via dev_queue_xmit the kernel doesn't call to dev_hard_header, so IPoIB needs to keep 20 bytes in the skb and to put the destination address inside them. In that way the dev_start_xmit will have the correct destination, and the driver won't take the destination from the skb->data, while nothing exists there, which causes to packet be be dropped. The test flow is: 1. Run the SM on remote node, 2. Restart the driver. 4. Ping some destination, 3. Observe that first ICMP request will be dropped. Fixes: fc791b633515 ("IB/ipoib: move back IB LL address into the hard header") Signed-off-by: Erez Shitrit Signed-off-by: Noa Osherovich Signed-off-by: Leon Romanovsky Tested-by: Yuval Shaia Signed-off-by: Doug Ledford Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/ulp/ipoib/ipoib_main.c | 30 +++++++++++++---------- 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index a5d9678f3b33..3ef7b8f049c4 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -701,6 +701,14 @@ int ipoib_check_sm_sendonly_fullmember_support(struct ipoib_dev_priv *priv) return ret; } +static void push_pseudo_header(struct sk_buff *skb, const char *daddr) +{ + struct ipoib_pseudo_header *phdr; + + phdr = (struct ipoib_pseudo_header *)skb_push(skb, sizeof(*phdr)); + memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN); +} + void ipoib_flush_paths(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); @@ -925,8 +933,7 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr, } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { - /* put pseudoheader back on for next time */ - skb_push(skb, IPOIB_PSEUDO_LEN); + push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); } else { ipoib_warn(priv, "queue length limit %d. Packet drop.\n", @@ -944,10 +951,12 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr, if (!path->query && path_rec_start(dev, path)) goto err_path; - if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) + if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { + push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); - else + } else { goto err_drop; + } } spin_unlock_irqrestore(&priv->lock, flags); @@ -983,8 +992,7 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, } if (path) { if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) { - /* put pseudoheader back on for next time */ - skb_push(skb, IPOIB_PSEUDO_LEN); + push_pseudo_header(skb, phdr->hwaddr); __skb_queue_tail(&path->queue, skb); } else { ++dev->stats.tx_dropped; @@ -1016,8 +1024,7 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, return; } else if ((path->query || !path_rec_start(dev, path)) && skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) { - /* put pseudoheader back on for next time */ - skb_push(skb, IPOIB_PSEUDO_LEN); + push_pseudo_header(skb, phdr->hwaddr); __skb_queue_tail(&path->queue, skb); } else { ++dev->stats.tx_dropped; @@ -1098,8 +1105,7 @@ send_using_neigh: } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { - /* put pseudoheader back on for next time */ - skb_push(skb, sizeof(*phdr)); + push_pseudo_header(skb, phdr->hwaddr); spin_lock_irqsave(&priv->lock, flags); __skb_queue_tail(&neigh->queue, skb); spin_unlock_irqrestore(&priv->lock, flags); @@ -1131,7 +1137,6 @@ static int ipoib_hard_header(struct sk_buff *skb, unsigned short type, const void *daddr, const void *saddr, unsigned len) { - struct ipoib_pseudo_header *phdr; struct ipoib_header *header; header = (struct ipoib_header *) skb_push(skb, sizeof *header); @@ -1144,8 +1149,7 @@ static int ipoib_hard_header(struct sk_buff *skb, * destination address into skb hard header so we can figure out where * to send the packet later. */ - phdr = (struct ipoib_pseudo_header *) skb_push(skb, sizeof(*phdr)); - memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN); + push_pseudo_header(skb, daddr); return IPOIB_HARD_LEN; } From 04f16db056d035785f217f1b958fe49ca3cd9be5 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 18 Jan 2017 14:10:30 +0200 Subject: [PATCH 20/64] IB/mlx5: Fix out-of-bound access commit 0fd27a88c2e4f548937fd7d93fc6e65c4ad7c278 upstream. When we initialize buffer to create SRQ in kernel, the number of pages was less than actually used in following mlx5_fill_page_array(). Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Leon Romanovsky Reviewed-by: Eli Cohen Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/hw/mlx5/srq.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index 729b0696626e..d61fd2c727c0 100644 --- a/drivers/infiniband/hw/mlx5/srq.c +++ b/drivers/infiniband/hw/mlx5/srq.c @@ -165,8 +165,6 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq, int err; int i; struct mlx5_wqe_srq_next_seg *next; - int page_shift; - int npages; err = mlx5_db_alloc(dev->mdev, &srq->db); if (err) { @@ -179,7 +177,6 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq, err = -ENOMEM; goto err_db; } - page_shift = srq->buf.page_shift; srq->head = 0; srq->tail = srq->msrq.max - 1; @@ -191,10 +188,8 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq, cpu_to_be16((i + 1) & (srq->msrq.max - 1)); } - npages = DIV_ROUND_UP(srq->buf.npages, 1 << (page_shift - PAGE_SHIFT)); - mlx5_ib_dbg(dev, "buf_size %d, page_shift %d, npages %d, calc npages %d\n", - buf_size, page_shift, srq->buf.npages, npages); - in->pas = mlx5_vzalloc(sizeof(*in->pas) * npages); + mlx5_ib_dbg(dev, "srq->buf.page_shift = %d\n", srq->buf.page_shift); + in->pas = mlx5_vzalloc(sizeof(*in->pas) * srq->buf.npages); if (!in->pas) { err = -ENOMEM; goto err_buf; @@ -210,7 +205,7 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq, } srq->wq_sig = !!srq_signature; - in->log_page_size = page_shift - MLX5_ADAPTER_PAGE_SHIFT; + in->log_page_size = srq->buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT; if (MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1 && in->type == IB_SRQT_XRC) in->user_index = MLX5_IB_DEFAULT_UIDX; From 516a12ab11bdd66104b1775a097a9a28c311cecb Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 14 Feb 2017 10:56:29 -0800 Subject: [PATCH 21/64] IB/SRP: Avoid using IB_MR_TYPE_SG_GAPS commit d6c58dc40fec35ff6cdb350b53bce0fcf9143709 upstream. Tests have shown that the following error message is reported when using SG-GAPS registration with an mlx5 adapter: scsi host1: ib_srp: failed RECV status WR flushed (5) for CQE ffff880bd4270eb0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0f007806 2500002a ad9fafd1 scsi host1: ib_srp: reconnect succeeded mlx5_0:dump_cqe:262:(pid 7369): dump error cqe 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0f007806 25000032 00105dd0 scsi host1: ib_srp: failed FAST REG status memory management operation error (6) for CQE ffff880b92860138 Hence avoid using SG-GAPS memory registrations. Additionally, always configure the blk_queue_virt_boundary() to avoid to trigger a mapping failure when using adapters that support SG-GAPS (e.g. mlx5). Fixes: commit ad8e66b4a801 ("IB/srp: fix mr allocation when the device supports sg gaps") Fixes: commit 509c5f33f4f6 ("IB/srp: Prevent mapping failures") Reported-by: Laurence Oberman Signed-off-by: Bart Van Assche Cc: Israel Rukshin Cc: Max Gurtovoy Cc: Leon Romanovsky Cc: Mark Bloch Cc: Yuval Shaia Signed-off-by: Doug Ledford Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/ulp/srp/ib_srp.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index e7dcf14a76e2..97247582eaa6 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -366,7 +366,6 @@ static struct srp_fr_pool *srp_create_fr_pool(struct ib_device *device, struct srp_fr_desc *d; struct ib_mr *mr; int i, ret = -EINVAL; - enum ib_mr_type mr_type; if (pool_size <= 0) goto err; @@ -380,13 +379,9 @@ static struct srp_fr_pool *srp_create_fr_pool(struct ib_device *device, spin_lock_init(&pool->lock); INIT_LIST_HEAD(&pool->free_list); - if (device->attrs.device_cap_flags & IB_DEVICE_SG_GAPS_REG) - mr_type = IB_MR_TYPE_SG_GAPS; - else - mr_type = IB_MR_TYPE_MEM_REG; - for (i = 0, d = &pool->desc[0]; i < pool->size; i++, d++) { - mr = ib_alloc_mr(pd, mr_type, max_page_list_len); + mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, + max_page_list_len); if (IS_ERR(mr)) { ret = PTR_ERR(mr); goto destroy_pool; @@ -2652,9 +2647,8 @@ static int srp_slave_alloc(struct scsi_device *sdev) struct Scsi_Host *shost = sdev->host; struct srp_target_port *target = host_to_target(shost); struct srp_device *srp_dev = target->srp_host->srp_dev; - struct ib_device *ibdev = srp_dev->dev; - if (!(ibdev->attrs.device_cap_flags & IB_DEVICE_SG_GAPS_REG)) + if (true) blk_queue_virt_boundary(sdev->request_queue, ~srp_dev->mr_page_mask); From d5d1d2cc4be76abdabb58e1bdad84fc06090042c Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 14 Feb 2017 10:56:30 -0800 Subject: [PATCH 22/64] IB/srp: Avoid that duplicate responses trigger a kernel bug commit 6cb72bc1b40bb2c1750ee7a5ebade93bed49a5fb upstream. After srp_process_rsp() returns there is a short time during which the scsi_host_find_tag() call will return a pointer to the SCSI command that is being completed. If during that time a duplicate response is received, avoid that the following call stack appears: BUG: unable to handle kernel NULL pointer dereference at (null) IP: srp_recv_done+0x450/0x6b0 [ib_srp] Oops: 0000 [#1] SMP CPU: 10 PID: 0 Comm: swapper/10 Not tainted 4.10.0-rc7-dbg+ #1 Call Trace: __ib_process_cq+0x4b/0xd0 [ib_core] ib_poll_handler+0x1d/0x70 [ib_core] irq_poll_softirq+0xba/0x120 __do_softirq+0xba/0x4c0 irq_exit+0xbe/0xd0 smp_apic_timer_interrupt+0x38/0x50 apic_timer_interrupt+0x90/0xa0 RIP: srp_recv_done+0x450/0x6b0 [ib_srp] RSP: ffff88046f483e20 Signed-off-by: Bart Van Assche Cc: Israel Rukshin Cc: Max Gurtovoy Cc: Laurence Oberman Cc: Steve Feeley Reviewed-by: Leon Romanovsky Signed-off-by: Doug Ledford Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/ulp/srp/ib_srp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 97247582eaa6..a8239656e571 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -1880,9 +1880,11 @@ static void srp_process_rsp(struct srp_rdma_ch *ch, struct srp_rsp *rsp) complete(&ch->tsk_mgmt_done); } else { scmnd = scsi_host_find_tag(target->scsi_host, rsp->tag); - if (scmnd) { + if (scmnd && scmnd->host_scribble) { req = (void *)scmnd->host_scribble; scmnd = srp_claim_req(ch, req, NULL, scmnd); + } else { + scmnd = NULL; } if (!scmnd) { shost_printk(KERN_ERR, target->scsi_host, From 48e2181b0b8d1a1e226b2932a11d6f94aef28fb8 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 14 Feb 2017 10:56:31 -0800 Subject: [PATCH 23/64] IB/srp: Fix race conditions related to task management commit 0a6fdbdeb1c25e31763c1fb333fa2723a7d2aba6 upstream. Avoid that srp_process_rsp() overwrites the status information in ch if the SRP target response timed out and processing of another task management function has already started. Avoid that issuing multiple task management functions concurrently triggers list corruption. This patch prevents that the following stack trace appears in the system log: WARNING: CPU: 8 PID: 9269 at lib/list_debug.c:52 __list_del_entry_valid+0xbc/0xc0 list_del corruption. prev->next should be ffffc90004bb7b00, but was ffff8804052ecc68 CPU: 8 PID: 9269 Comm: sg_reset Tainted: G W 4.10.0-rc7-dbg+ #3 Call Trace: dump_stack+0x68/0x93 __warn+0xc6/0xe0 warn_slowpath_fmt+0x4a/0x50 __list_del_entry_valid+0xbc/0xc0 wait_for_completion_timeout+0x12e/0x170 srp_send_tsk_mgmt+0x1ef/0x2d0 [ib_srp] srp_reset_device+0x5b/0x110 [ib_srp] scsi_ioctl_reset+0x1c7/0x290 scsi_ioctl+0x12a/0x420 sd_ioctl+0x9d/0x100 blkdev_ioctl+0x51e/0x9f0 block_ioctl+0x38/0x40 do_vfs_ioctl+0x8f/0x700 SyS_ioctl+0x3c/0x70 entry_SYSCALL_64_fastpath+0x18/0xad Signed-off-by: Bart Van Assche Cc: Israel Rukshin Cc: Max Gurtovoy Cc: Laurence Oberman Cc: Steve Feeley Signed-off-by: Doug Ledford Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/ulp/srp/ib_srp.c | 45 +++++++++++++++++++---------- drivers/infiniband/ulp/srp/ib_srp.h | 1 + 2 files changed, 30 insertions(+), 16 deletions(-) diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index a8239656e571..1eee8f7e75ca 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -1872,12 +1872,17 @@ static void srp_process_rsp(struct srp_rdma_ch *ch, struct srp_rsp *rsp) if (unlikely(rsp->tag & SRP_TAG_TSK_MGMT)) { spin_lock_irqsave(&ch->lock, flags); ch->req_lim += be32_to_cpu(rsp->req_lim_delta); + if (rsp->tag == ch->tsk_mgmt_tag) { + ch->tsk_mgmt_status = -1; + if (be32_to_cpu(rsp->resp_data_len) >= 4) + ch->tsk_mgmt_status = rsp->data[3]; + complete(&ch->tsk_mgmt_done); + } else { + shost_printk(KERN_ERR, target->scsi_host, + "Received tsk mgmt response too late for tag %#llx\n", + rsp->tag); + } spin_unlock_irqrestore(&ch->lock, flags); - - ch->tsk_mgmt_status = -1; - if (be32_to_cpu(rsp->resp_data_len) >= 4) - ch->tsk_mgmt_status = rsp->data[3]; - complete(&ch->tsk_mgmt_done); } else { scmnd = scsi_host_find_tag(target->scsi_host, rsp->tag); if (scmnd && scmnd->host_scribble) { @@ -2516,19 +2521,18 @@ srp_change_queue_depth(struct scsi_device *sdev, int qdepth) } static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, u64 lun, - u8 func) + u8 func, u8 *status) { struct srp_target_port *target = ch->target; struct srp_rport *rport = target->rport; struct ib_device *dev = target->srp_host->srp_dev->dev; struct srp_iu *iu; struct srp_tsk_mgmt *tsk_mgmt; + int res; if (!ch->connected || target->qp_in_error) return -1; - init_completion(&ch->tsk_mgmt_done); - /* * Lock the rport mutex to avoid that srp_create_ch_ib() is * invoked while a task management function is being sent. @@ -2551,10 +2555,16 @@ static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, u64 lun, tsk_mgmt->opcode = SRP_TSK_MGMT; int_to_scsilun(lun, &tsk_mgmt->lun); - tsk_mgmt->tag = req_tag | SRP_TAG_TSK_MGMT; tsk_mgmt->tsk_mgmt_func = func; tsk_mgmt->task_tag = req_tag; + spin_lock_irq(&ch->lock); + ch->tsk_mgmt_tag = (ch->tsk_mgmt_tag + 1) | SRP_TAG_TSK_MGMT; + tsk_mgmt->tag = ch->tsk_mgmt_tag; + spin_unlock_irq(&ch->lock); + + init_completion(&ch->tsk_mgmt_done); + ib_dma_sync_single_for_device(dev, iu->dma, sizeof *tsk_mgmt, DMA_TO_DEVICE); if (srp_post_send(ch, iu, sizeof(*tsk_mgmt))) { @@ -2563,13 +2573,15 @@ static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, u64 lun, return -1; } + res = wait_for_completion_timeout(&ch->tsk_mgmt_done, + msecs_to_jiffies(SRP_ABORT_TIMEOUT_MS)); + if (res > 0 && status) + *status = ch->tsk_mgmt_status; mutex_unlock(&rport->mutex); - if (!wait_for_completion_timeout(&ch->tsk_mgmt_done, - msecs_to_jiffies(SRP_ABORT_TIMEOUT_MS))) - return -1; + WARN_ON_ONCE(res < 0); - return 0; + return res > 0 ? 0 : -1; } static int srp_abort(struct scsi_cmnd *scmnd) @@ -2595,7 +2607,7 @@ static int srp_abort(struct scsi_cmnd *scmnd) shost_printk(KERN_ERR, target->scsi_host, "Sending SRP abort for tag %#x\n", tag); if (srp_send_tsk_mgmt(ch, tag, scmnd->device->lun, - SRP_TSK_ABORT_TASK) == 0) + SRP_TSK_ABORT_TASK, NULL) == 0) ret = SUCCESS; else if (target->rport->state == SRP_RPORT_LOST) ret = FAST_IO_FAIL; @@ -2613,14 +2625,15 @@ static int srp_reset_device(struct scsi_cmnd *scmnd) struct srp_target_port *target = host_to_target(scmnd->device->host); struct srp_rdma_ch *ch; int i; + u8 status; shost_printk(KERN_ERR, target->scsi_host, "SRP reset_device called\n"); ch = &target->ch[0]; if (srp_send_tsk_mgmt(ch, SRP_TAG_NO_REQ, scmnd->device->lun, - SRP_TSK_LUN_RESET)) + SRP_TSK_LUN_RESET, &status)) return FAILED; - if (ch->tsk_mgmt_status) + if (status) return FAILED; for (i = 0; i < target->ch_count; i++) { diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h index 21c69695f9d4..32ed40db3ca2 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.h +++ b/drivers/infiniband/ulp/srp/ib_srp.h @@ -163,6 +163,7 @@ struct srp_rdma_ch { int max_ti_iu_len; int comp_vector; + u64 tsk_mgmt_tag; struct completion tsk_mgmt_done; u8 tsk_mgmt_status; bool connected; From d3381fab77cbca6f9664cf49b3f5dd3171f1f6d3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 1 Feb 2017 06:06:16 +1300 Subject: [PATCH 24/64] fs: Better permission checking for submounts commit 93faccbbfa958a9668d3ab4e30f38dd205cee8d8 upstream. To support unprivileged users mounting filesystems two permission checks have to be performed: a test to see if the user allowed to create a mount in the mount namespace, and a test to see if the user is allowed to access the specified filesystem. The automount case is special in that mounting the original filesystem grants permission to mount the sub-filesystems, to any user who happens to stumble across the their mountpoint and satisfies the ordinary filesystem permission checks. Attempting to handle the automount case by using override_creds almost works. It preserves the idea that permission to mount the original filesystem is permission to mount the sub-filesystem. Unfortunately using override_creds messes up the filesystems ordinary permission checks. Solve this by being explicit that a mount is a submount by introducing vfs_submount, and using it where appropriate. vfs_submount uses a new mount internal mount flags MS_SUBMOUNT, to let sget and friends know that a mount is a submount so they can take appropriate action. sget and sget_userns are modified to not perform any permission checks on submounts. follow_automount is modified to stop using override_creds as that has proven problemantic. do_mount is modified to always remove the new MS_SUBMOUNT flag so that we know userspace will never by able to specify it. autofs4 is modified to stop using current_real_cred that was put in there to handle the previous version of submount permission checking. cifs is modified to pass the mountpoint all of the way down to vfs_submount. debugfs is modified to pass the mountpoint all of the way down to trace_automount by adding a new parameter. To make this change easier a new typedef debugfs_automount_t is introduced to capture the type of the debugfs automount function. Fixes: 069d5ac9ae0d ("autofs: Fix automounts by using current_real_cred()->uid") Fixes: aeaa4a79ff6a ("fs: Call d_automount with the filesystems creds") Reviewed-by: Trond Myklebust Reviewed-by: Seth Forshee Signed-off-by: "Eric W. Biederman" Signed-off-by: Greg Kroah-Hartman --- fs/afs/mntpt.c | 2 +- fs/autofs4/waitq.c | 4 ++-- fs/cifs/cifs_dfs_ref.c | 7 ++++--- fs/debugfs/inode.c | 8 ++++---- fs/namei.c | 3 --- fs/namespace.c | 17 ++++++++++++++++- fs/nfs/namespace.c | 2 +- fs/nfs/nfs4namespace.c | 2 +- fs/super.c | 13 ++++++++++--- include/linux/debugfs.h | 3 ++- include/linux/mount.h | 3 +++ include/uapi/linux/fs.h | 1 + kernel/trace/trace.c | 4 ++-- 13 files changed, 47 insertions(+), 22 deletions(-) diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 81dd075356b9..d4fb0afc0097 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -202,7 +202,7 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt) /* try and do the mount */ _debug("--- attempting mount %s -o %s ---", devname, options); - mnt = vfs_kern_mount(&afs_fs_type, 0, devname, options); + mnt = vfs_submount(mntpt, &afs_fs_type, devname, options); _debug("--- mount result %p ---", mnt); free_page((unsigned long) devname); diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index e44271dfceb6..5db6c8d745ea 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -431,8 +431,8 @@ int autofs4_wait(struct autofs_sb_info *sbi, memcpy(&wq->name, &qstr, sizeof(struct qstr)); wq->dev = autofs4_get_dev(sbi); wq->ino = autofs4_get_ino(sbi); - wq->uid = current_real_cred()->uid; - wq->gid = current_real_cred()->gid; + wq->uid = current_cred()->uid; + wq->gid = current_cred()->gid; wq->pid = pid; wq->tgid = tgid; wq->status = -EINTR; /* Status return if interrupted */ diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index ec9dbbcca3b9..9156be545b0f 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -245,7 +245,8 @@ compose_mount_options_err: * @fullpath: full path in UNC format * @ref: server's referral */ -static struct vfsmount *cifs_dfs_do_refmount(struct cifs_sb_info *cifs_sb, +static struct vfsmount *cifs_dfs_do_refmount(struct dentry *mntpt, + struct cifs_sb_info *cifs_sb, const char *fullpath, const struct dfs_info3_param *ref) { struct vfsmount *mnt; @@ -259,7 +260,7 @@ static struct vfsmount *cifs_dfs_do_refmount(struct cifs_sb_info *cifs_sb, if (IS_ERR(mountdata)) return (struct vfsmount *)mountdata; - mnt = vfs_kern_mount(&cifs_fs_type, 0, devname, mountdata); + mnt = vfs_submount(mntpt, &cifs_fs_type, devname, mountdata); kfree(mountdata); kfree(devname); return mnt; @@ -334,7 +335,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) mnt = ERR_PTR(-EINVAL); break; } - mnt = cifs_dfs_do_refmount(cifs_sb, + mnt = cifs_dfs_do_refmount(mntpt, cifs_sb, full_path, referrals + i); cifs_dbg(FYI, "%s: cifs_dfs_do_refmount:%s , mnt:%p\n", __func__, referrals[i].node_name, mnt); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index f17fcf89e18e..1e30f74a9527 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -187,9 +187,9 @@ static const struct super_operations debugfs_super_operations = { static struct vfsmount *debugfs_automount(struct path *path) { - struct vfsmount *(*f)(void *); - f = (struct vfsmount *(*)(void *))path->dentry->d_fsdata; - return f(d_inode(path->dentry)->i_private); + debugfs_automount_t f; + f = (debugfs_automount_t)path->dentry->d_fsdata; + return f(path->dentry, d_inode(path->dentry)->i_private); } static const struct dentry_operations debugfs_dops = { @@ -504,7 +504,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_dir); */ struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, - struct vfsmount *(*f)(void *), + debugfs_automount_t f, void *data) { struct dentry *dentry = start_creating(name, parent); diff --git a/fs/namei.c b/fs/namei.c index 5b4eed221530..d5e5140c1045 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1100,7 +1100,6 @@ static int follow_automount(struct path *path, struct nameidata *nd, bool *need_mntput) { struct vfsmount *mnt; - const struct cred *old_cred; int err; if (!path->dentry->d_op || !path->dentry->d_op->d_automount) @@ -1129,9 +1128,7 @@ static int follow_automount(struct path *path, struct nameidata *nd, if (nd->total_link_count >= 40) return -ELOOP; - old_cred = override_creds(&init_cred); mnt = path->dentry->d_op->d_automount(path); - revert_creds(old_cred); if (IS_ERR(mnt)) { /* * The filesystem is allowed to return -EISDIR here to indicate diff --git a/fs/namespace.c b/fs/namespace.c index ea751263fefa..5e35057f07ac 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -995,6 +995,21 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void } EXPORT_SYMBOL_GPL(vfs_kern_mount); +struct vfsmount * +vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, + const char *name, void *data) +{ + /* Until it is worked out how to pass the user namespace + * through from the parent mount to the submount don't support + * unprivileged mounts with submounts. + */ + if (mountpoint->d_sb->s_user_ns != &init_user_ns) + return ERR_PTR(-EPERM); + + return vfs_kern_mount(type, MS_SUBMOUNT, name, data); +} +EXPORT_SYMBOL_GPL(vfs_submount); + static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { @@ -2779,7 +2794,7 @@ long do_mount(const char *dev_name, const char __user *dir_name, flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN | MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT | - MS_STRICTATIME | MS_NOREMOTELOCK); + MS_STRICTATIME | MS_NOREMOTELOCK | MS_SUBMOUNT); if (flags & MS_REMOUNT) retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags, diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 5551e8ef67fd..e49d831c4e85 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -226,7 +226,7 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, const char *devname, struct nfs_clone_mount *mountdata) { - return vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata); + return vfs_submount(mountdata->dentry, &nfs_xdev_fs_type, devname, mountdata); } /** diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index d21104912676..d8b040bd9814 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -279,7 +279,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, mountdata->hostname, mountdata->mnt_path); - mnt = vfs_kern_mount(&nfs4_referral_fs_type, 0, page, mountdata); + mnt = vfs_submount(mountdata->dentry, &nfs4_referral_fs_type, page, mountdata); if (!IS_ERR(mnt)) break; } diff --git a/fs/super.c b/fs/super.c index c183835566c1..1058bf3e8724 100644 --- a/fs/super.c +++ b/fs/super.c @@ -470,7 +470,7 @@ struct super_block *sget_userns(struct file_system_type *type, struct super_block *old; int err; - if (!(flags & MS_KERNMOUNT) && + if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT)) && !(type->fs_flags & FS_USERNS_MOUNT) && !capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); @@ -500,7 +500,7 @@ retry: } if (!s) { spin_unlock(&sb_lock); - s = alloc_super(type, flags, user_ns); + s = alloc_super(type, (flags & ~MS_SUBMOUNT), user_ns); if (!s) return ERR_PTR(-ENOMEM); goto retry; @@ -541,8 +541,15 @@ struct super_block *sget(struct file_system_type *type, { struct user_namespace *user_ns = current_user_ns(); + /* We don't yet pass the user namespace of the parent + * mount through to here so always use &init_user_ns + * until that changes. + */ + if (flags & MS_SUBMOUNT) + user_ns = &init_user_ns; + /* Ensure the requestor has permissions over the target filesystem */ - if (!(flags & MS_KERNMOUNT) && !ns_capable(user_ns, CAP_SYS_ADMIN)) + if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT)) && !ns_capable(user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); return sget_userns(type, test, set, flags, user_ns, data); diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 1b413a9aab81..b20a0945b550 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -96,9 +96,10 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent); struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, const char *dest); +typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *); struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, - struct vfsmount *(*f)(void *), + debugfs_automount_t f, void *data); void debugfs_remove(struct dentry *dentry); diff --git a/include/linux/mount.h b/include/linux/mount.h index 1172cce949a4..e0f3a82eee6d 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -90,6 +90,9 @@ struct file_system_type; extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data); +extern struct vfsmount *vfs_submount(const struct dentry *mountpoint, + struct file_system_type *type, + const char *name, void *data); extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list); extern void mark_mounts_for_expiry(struct list_head *mounts); diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index acb2b6152ba0..474995568f35 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -132,6 +132,7 @@ struct inodes_stat_t { #define MS_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ +#define MS_SUBMOUNT (1<<26) #define MS_NOREMOTELOCK (1<<27) #define MS_NOSEC (1<<28) #define MS_BORN (1<<29) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8696ce6bf2f6..90b66ed6f0e2 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7241,7 +7241,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) ftrace_init_tracefs(tr, d_tracer); } -static struct vfsmount *trace_automount(void *ingore) +static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore) { struct vfsmount *mnt; struct file_system_type *type; @@ -7254,7 +7254,7 @@ static struct vfsmount *trace_automount(void *ingore) type = get_fs_type("tracefs"); if (!type) return NULL; - mnt = vfs_kern_mount(type, 0, "tracefs", NULL); + mnt = vfs_submount(mntpt, type, "tracefs", NULL); put_filesystem(type); if (IS_ERR(mnt)) return NULL; From b2b0f6ffd3f97953044e909ca311d2a580ae8575 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 24 Feb 2017 16:43:36 +0100 Subject: [PATCH 25/64] orangefs: Use RCU for destroy_inode commit 0695d7dc1d9f19b82ec2cae24856bddce278cfe6 upstream. freeing of inodes must be RCU-delayed on all filesystems Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman --- fs/orangefs/super.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index c48859f16e7b..67c24351a67f 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -115,6 +115,13 @@ static struct inode *orangefs_alloc_inode(struct super_block *sb) return &orangefs_inode->vfs_inode; } +static void orangefs_i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); + kmem_cache_free(orangefs_inode_cache, orangefs_inode); +} + static void orangefs_destroy_inode(struct inode *inode) { struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); @@ -123,7 +130,7 @@ static void orangefs_destroy_inode(struct inode *inode) "%s: deallocated %p destroying inode %pU\n", __func__, orangefs_inode, get_khandle_from_ino(inode)); - kmem_cache_free(orangefs_inode_cache, orangefs_inode); + call_rcu(&inode->i_rcu, orangefs_i_callback); } /* From 1f2ca141ec53a9c43ea0852f013907d19c435986 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Mon, 28 Nov 2016 16:17:56 +0100 Subject: [PATCH 26/64] memory/atmel-ebi: Fix ns <-> cycles conversions commit ee194289502a6901cc77dc9a893bf2afd351ac5e upstream. at91sam9_ebi_get_config() is incorrectly converting timings in clock cycles into timings in nanoseconds by multiplying the cycle values by the clk rate instead of the clk period. at91sam9_ebi_xslate_config() has the same problem for the tdf_ns -> tdf_cycles conversion. Signed-off-by: Boris Brezillon Reported-by: Chris Leahy Fixes: 6a4ec4cd0888 ("memory: add Atmel EBI (External Bus Interface) driver") Signed-off-by: Alexandre Belloni Signed-off-by: Greg Kroah-Hartman --- drivers/memory/atmel-ebi.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/drivers/memory/atmel-ebi.c b/drivers/memory/atmel-ebi.c index b5ed3bd082b5..e9ebc4f31d16 100644 --- a/drivers/memory/atmel-ebi.c +++ b/drivers/memory/atmel-ebi.c @@ -93,7 +93,7 @@ static void at91sam9_ebi_get_config(struct at91_ebi_dev *ebid, struct at91_ebi_dev_config *conf) { struct at91sam9_smc_generic_fields *fields = &ebid->ebi->sam9; - unsigned int clk_rate = clk_get_rate(ebid->ebi->clk); + unsigned int clk_period = NSEC_PER_SEC / clk_get_rate(ebid->ebi->clk); struct at91sam9_ebi_dev_config *config = &conf->sam9; struct at91sam9_smc_timings *timings = &config->timings; unsigned int val; @@ -102,43 +102,43 @@ static void at91sam9_ebi_get_config(struct at91_ebi_dev *ebid, config->mode = val & ~AT91_SMC_TDF; val = (val & AT91_SMC_TDF) >> 16; - timings->tdf_ns = clk_rate * val; + timings->tdf_ns = clk_period * val; regmap_fields_read(fields->setup, conf->cs, &val); timings->ncs_rd_setup_ns = (val >> 24) & 0x1f; timings->ncs_rd_setup_ns += ((val >> 29) & 0x1) * 128; - timings->ncs_rd_setup_ns *= clk_rate; + timings->ncs_rd_setup_ns *= clk_period; timings->nrd_setup_ns = (val >> 16) & 0x1f; timings->nrd_setup_ns += ((val >> 21) & 0x1) * 128; - timings->nrd_setup_ns *= clk_rate; + timings->nrd_setup_ns *= clk_period; timings->ncs_wr_setup_ns = (val >> 8) & 0x1f; timings->ncs_wr_setup_ns += ((val >> 13) & 0x1) * 128; - timings->ncs_wr_setup_ns *= clk_rate; + timings->ncs_wr_setup_ns *= clk_period; timings->nwe_setup_ns = val & 0x1f; timings->nwe_setup_ns += ((val >> 5) & 0x1) * 128; - timings->nwe_setup_ns *= clk_rate; + timings->nwe_setup_ns *= clk_period; regmap_fields_read(fields->pulse, conf->cs, &val); timings->ncs_rd_pulse_ns = (val >> 24) & 0x3f; timings->ncs_rd_pulse_ns += ((val >> 30) & 0x1) * 256; - timings->ncs_rd_pulse_ns *= clk_rate; + timings->ncs_rd_pulse_ns *= clk_period; timings->nrd_pulse_ns = (val >> 16) & 0x3f; timings->nrd_pulse_ns += ((val >> 22) & 0x1) * 256; - timings->nrd_pulse_ns *= clk_rate; + timings->nrd_pulse_ns *= clk_period; timings->ncs_wr_pulse_ns = (val >> 8) & 0x3f; timings->ncs_wr_pulse_ns += ((val >> 14) & 0x1) * 256; - timings->ncs_wr_pulse_ns *= clk_rate; + timings->ncs_wr_pulse_ns *= clk_period; timings->nwe_pulse_ns = val & 0x3f; timings->nwe_pulse_ns += ((val >> 6) & 0x1) * 256; - timings->nwe_pulse_ns *= clk_rate; + timings->nwe_pulse_ns *= clk_period; regmap_fields_read(fields->cycle, conf->cs, &val); timings->nrd_cycle_ns = (val >> 16) & 0x7f; timings->nrd_cycle_ns += ((val >> 23) & 0x3) * 256; - timings->nrd_cycle_ns *= clk_rate; + timings->nrd_cycle_ns *= clk_period; timings->nwe_cycle_ns = val & 0x7f; timings->nwe_cycle_ns += ((val >> 7) & 0x3) * 256; - timings->nwe_cycle_ns *= clk_rate; + timings->nwe_cycle_ns *= clk_period; } static int at91_xlate_timing(struct device_node *np, const char *prop, @@ -334,6 +334,7 @@ static int at91sam9_ebi_apply_config(struct at91_ebi_dev *ebid, struct at91_ebi_dev_config *conf) { unsigned int clk_rate = clk_get_rate(ebid->ebi->clk); + unsigned int clk_period = NSEC_PER_SEC / clk_rate; struct at91sam9_ebi_dev_config *config = &conf->sam9; struct at91sam9_smc_timings *timings = &config->timings; struct at91sam9_smc_generic_fields *fields = &ebid->ebi->sam9; @@ -376,7 +377,7 @@ static int at91sam9_ebi_apply_config(struct at91_ebi_dev *ebid, val |= AT91SAM9_SMC_NWECYCLE(coded_val); regmap_fields_write(fields->cycle, conf->cs, val); - val = DIV_ROUND_UP(timings->tdf_ns, clk_rate); + val = DIV_ROUND_UP(timings->tdf_ns, clk_period); if (val > AT91_SMC_TDF_MAX) val = AT91_SMC_TDF_MAX; regmap_fields_write(fields->mode, conf->cs, From ff61e0123b7d8fe13ae8b6f96e5c3abfc11357fc Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 7 Feb 2017 12:05:25 -0500 Subject: [PATCH 27/64] ktest: Fix child exit code processing commit 32677207dcc5e594254b7fb4fb2352b1755b1d5b upstream. The child_exit errno needs to be shifted by 8 bits to compare against the return values for the bisect variables. Fixes: c5dacb88f0a64 ("ktest: Allow overriding bisect test results") Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Greg Kroah-Hartman --- tools/testing/ktest/ktest.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index d08e214ec6e7..223d88e25e05 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -2629,7 +2629,7 @@ sub do_run_test { } waitpid $child_pid, 0; - $child_exit = $?; + $child_exit = $? >> 8; my $end_time = time; $test_time = $end_time - $start_time; From 5da90d0018a7f9ed23698663d046146426991ffa Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 14 Feb 2017 10:09:40 -0500 Subject: [PATCH 28/64] ceph: remove req from unsafe list when unregistering it commit df963ea8a082d31521a120e8e31a29ad8a1dc215 upstream. There's no reason a request should ever be on a s_unsafe list but not in the request tree. Link: http://tracker.ceph.com/issues/18474 Signed-off-by: Jeff Layton Reviewed-by: Yan, Zheng Signed-off-by: Ilya Dryomov Signed-off-by: Greg Kroah-Hartman --- fs/ceph/mds_client.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 6a26c7bd1286..e3e1a80b351e 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -628,6 +628,9 @@ static void __unregister_request(struct ceph_mds_client *mdsc, { dout("__unregister_request %p tid %lld\n", req, req->r_tid); + /* Never leave an unregistered request on an unsafe list! */ + list_del_init(&req->r_unsafe_item); + if (req->r_tid == mdsc->oldest_tid) { struct rb_node *p = rb_next(&req->r_node); mdsc->oldest_tid = 0; @@ -1036,7 +1039,6 @@ static void cleanup_session_requests(struct ceph_mds_client *mdsc, while (!list_empty(&session->s_unsafe)) { req = list_first_entry(&session->s_unsafe, struct ceph_mds_request, r_unsafe_item); - list_del_init(&req->r_unsafe_item); pr_warn_ratelimited(" dropping unsafe request %llu\n", req->r_tid); __unregister_request(mdsc, req); @@ -2423,7 +2425,6 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) * useful we could do with a revised return value. */ dout("got safe reply %llu, mds%d\n", tid, mds); - list_del_init(&req->r_unsafe_item); /* last unsafe request during umount? */ if (mdsc->stopping && !__get_oldest_req(mdsc)) From 4ee3508f7abece538c4a99c71d81e94f8df44d97 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 16 Feb 2017 10:22:32 +1100 Subject: [PATCH 29/64] pci/hotplug/pnv-php: Remove WARN_ON() in pnv_php_put_slot() commit 36c7c9da40c408a71e5e6bfe12e57dcf549a296d upstream. The WARN_ON() causes unnecessary backtrace when putting the parent slot, which is likely to be NULL. WARNING: CPU: 2 PID: 1071 at drivers/pci/hotplug/pnv_php.c:85 \ pnv_php_release+0xcc/0x150 [pnv_php] : Call Trace: [c0000003bc007c10] [d00000000ad613c4] pnv_php_release+0x144/0x150 [pnv_php] [c0000003bc007c40] [c0000000006641d8] pci_hp_deregister+0x238/0x330 [c0000003bc007cd0] [d00000000ad61440] pnv_php_unregister_one+0x70/0xa0 [pnv_php] [c0000003bc007d10] [d00000000ad614c0] pnv_php_unregister+0x50/0x80 [pnv_php] [c0000003bc007d40] [d00000000ad61e84] pnv_php_exit+0x50/0xcb4 [pnv_php] [c0000003bc007d70] [c00000000019499c] SyS_delete_module+0x1fc/0x2a0 [c0000003bc007e30] [c00000000000b184] system_call+0x38/0xe0 Fixes: 66725152fb9f ("PCI/hotplug: PowerPC PowerNV PCI hotplug driver") Signed-off-by: Gavin Shan Reviewed-by: Andrew Donnellan Tested-by: Vaibhav Jain Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- drivers/pci/hotplug/pnv_php.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c index acb2be0c8c2c..f96588a8f29b 100644 --- a/drivers/pci/hotplug/pnv_php.c +++ b/drivers/pci/hotplug/pnv_php.c @@ -82,7 +82,7 @@ static void pnv_php_free_slot(struct kref *kref) static inline void pnv_php_put_slot(struct pnv_php_slot *php_slot) { - if (WARN_ON(!php_slot)) + if (!php_slot) return; kref_put(&php_slot->kref, pnv_php_free_slot); From 54eff720c99f2aeb096eb3bb98b4475bd1a0ebd9 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 16 Feb 2017 10:22:33 +1100 Subject: [PATCH 30/64] pci/hotplug/pnv-php: Disable surprise hotplug capability on conflicts commit 303529d6ef1293513c2c73c9ab86489eebb37d08 upstream. The root port or PCIe switch downstream port might have been associated with driver other than pnv-php. The MSI or MSIx might also have been enabled by that driver (e.g. pcieport_drv). Attempt to enable MSI incurs below backtrace: PowerPC PowerNV PCI Hotplug Driver version: 0.1 ------------[ cut here ]------------ WARNING: CPU: 19 PID: 1004 at drivers/pci/msi.c:1071 \ __pci_enable_msi_range+0x84/0x4e0 NIP [c000000000665c34] __pci_enable_msi_range+0x84/0x4e0 LR [c000000000665c24] __pci_enable_msi_range+0x74/0x4e0 Call Trace: [c000000384d67600] [c000000000665c24] __pci_enable_msi_range+0x74/0x4e0 [c000000384d676e0] [d00000000aa31b04] pnv_php_register+0x564/0x5a0 [pnv_php] [c000000384d677c0] [d00000000aa31658] pnv_php_register+0xb8/0x5a0 [pnv_php] [c000000384d678a0] [d00000000aa31658] pnv_php_register+0xb8/0x5a0 [pnv_php] [c000000384d67980] [d00000000aa31dfc] pnv_php_init+0x60/0x98 [pnv_php] [c000000384d679f0] [c00000000000cfdc] do_one_initcall+0x6c/0x1d0 [c000000384d67ab0] [c000000000b92354] do_init_module+0x94/0x254 [c000000384d67b40] [c00000000019719c] load_module+0x258c/0x2c60 [c000000384d67d30] [c000000000197bb0] SyS_finit_module+0xf0/0x170 [c000000384d67e30] [c00000000000b184] system_call+0x38/0xe0 This fixes the issue by skipping enabling the surprise hotplug capability if the MSI or MSIx on the PCI slot's upstream port has been enabled by other driver. Fixes: 360aebd85a4c ("drivers/pci/hotplug: Support surprise hotplug in powernv driver") Signed-off-by: Gavin Shan Reviewed-by: Andrew Donnellan Tested-by: Vaibhav Jain Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- drivers/pci/hotplug/pnv_php.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c index f96588a8f29b..99b05338b4bc 100644 --- a/drivers/pci/hotplug/pnv_php.c +++ b/drivers/pci/hotplug/pnv_php.c @@ -799,6 +799,14 @@ static void pnv_php_enable_irq(struct pnv_php_slot *php_slot) struct pci_dev *pdev = php_slot->pdev; int irq, ret; + /* + * The MSI/MSIx interrupt might have been occupied by other + * drivers. Don't populate the surprise hotplug capability + * in that case. + */ + if (pci_dev_msi_enabled(pdev)) + return; + ret = pci_enable_device(pdev); if (ret) { dev_warn(&pdev->dev, "Error %d enabling device\n", ret); From 17ea11d553220281ab037799642ecd45246c3a65 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Wed, 22 Feb 2017 22:06:32 -0800 Subject: [PATCH 31/64] target: Fix NULL dereference during LUN lookup + active I/O shutdown commit bd4e2d2907fa23a11d46217064ecf80470ddae10 upstream. When transport_clear_lun_ref() is shutting down a se_lun via configfs with new I/O in-flight, it's possible to trigger a NULL pointer dereference in transport_lookup_cmd_lun() due to the fact percpu_ref_get() doesn't do any __PERCPU_REF_DEAD checking before incrementing lun->lun_ref.count after lun->lun_ref has switched to atomic_t mode. This results in a NULL pointer dereference as LUN shutdown code in core_tpg_remove_lun() continues running after the existing ->release() -> core_tpg_lun_ref_release() callback completes, and clears the RCU protected se_lun->lun_se_dev pointer. During the OOPs, the state of lun->lun_ref in the process which triggered the NULL pointer dereference looks like the following on v4.1.y stable code: struct se_lun { lun_link_magic = 4294932337, lun_status = TRANSPORT_LUN_STATUS_FREE, ..... lun_se_dev = 0x0, lun_sep = 0x0, ..... lun_ref = { count = { counter = 1 }, percpu_count_ptr = 3, release = 0xffffffffa02fa1e0 , confirm_switch = 0x0, force_atomic = false, rcu = { next = 0xffff88154fa1a5d0, func = 0xffffffff8137c4c0 } } } To address this bug, use percpu_ref_tryget_live() to ensure once __PERCPU_REF_DEAD is visable on all CPUs and ->lun_ref has switched to atomic_t, all new I/Os will fail to obtain a new lun->lun_ref reference. Also use an explicit percpu_ref_kill_and_confirm() callback to block on ->lun_ref_comp to allow the first stage and associated RCU grace period to complete, and then block on ->lun_ref_shutdown waiting for the final percpu_ref_put() to drop the last reference via transport_lun_remove_cmd() before continuing with core_tpg_remove_lun() shutdown. Reported-by: Rob Millner Tested-by: Rob Millner Cc: Rob Millner Tested-by: Vaibhav Tandon Cc: Vaibhav Tandon Tested-by: Bryant G. Ly Signed-off-by: Nicholas Bellinger Signed-off-by: Greg Kroah-Hartman --- drivers/target/target_core_device.c | 10 +++++++-- drivers/target/target_core_tpg.c | 3 ++- drivers/target/target_core_transport.c | 31 +++++++++++++++++++++++++- include/target/target_core_base.h | 1 + 4 files changed, 41 insertions(+), 4 deletions(-) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index ea9617c7b403..cc38a3509f78 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -77,12 +77,16 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun) &deve->read_bytes); se_lun = rcu_dereference(deve->se_lun); + + if (!percpu_ref_tryget_live(&se_lun->lun_ref)) { + se_lun = NULL; + goto out_unlock; + } + se_cmd->se_lun = rcu_dereference(deve->se_lun); se_cmd->pr_res_key = deve->pr_res_key; se_cmd->orig_fe_lun = unpacked_lun; se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD; - - percpu_ref_get(&se_lun->lun_ref); se_cmd->lun_ref_active = true; if ((se_cmd->data_direction == DMA_TO_DEVICE) && @@ -96,6 +100,7 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun) goto ref_dev; } } +out_unlock: rcu_read_unlock(); if (!se_lun) { @@ -815,6 +820,7 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) xcopy_lun = &dev->xcopy_lun; rcu_assign_pointer(xcopy_lun->lun_se_dev, dev); init_completion(&xcopy_lun->lun_ref_comp); + init_completion(&xcopy_lun->lun_shutdown_comp); INIT_LIST_HEAD(&xcopy_lun->lun_deve_list); INIT_LIST_HEAD(&xcopy_lun->lun_dev_link); mutex_init(&xcopy_lun->lun_tg_pt_md_mutex); diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index d99752c6cd60..2744251178ad 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -445,7 +445,7 @@ static void core_tpg_lun_ref_release(struct percpu_ref *ref) { struct se_lun *lun = container_of(ref, struct se_lun, lun_ref); - complete(&lun->lun_ref_comp); + complete(&lun->lun_shutdown_comp); } int core_tpg_register( @@ -571,6 +571,7 @@ struct se_lun *core_tpg_alloc_lun( lun->lun_link_magic = SE_LUN_LINK_MAGIC; atomic_set(&lun->lun_acl_count, 0); init_completion(&lun->lun_ref_comp); + init_completion(&lun->lun_shutdown_comp); INIT_LIST_HEAD(&lun->lun_deve_list); INIT_LIST_HEAD(&lun->lun_dev_link); atomic_set(&lun->lun_tg_pt_secondary_offline, 0); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 767d1eb6e035..cae4dea6464e 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -2702,10 +2702,39 @@ void target_wait_for_sess_cmds(struct se_session *se_sess) } EXPORT_SYMBOL(target_wait_for_sess_cmds); +static void target_lun_confirm(struct percpu_ref *ref) +{ + struct se_lun *lun = container_of(ref, struct se_lun, lun_ref); + + complete(&lun->lun_ref_comp); +} + void transport_clear_lun_ref(struct se_lun *lun) { - percpu_ref_kill(&lun->lun_ref); + /* + * Mark the percpu-ref as DEAD, switch to atomic_t mode, drop + * the initial reference and schedule confirm kill to be + * executed after one full RCU grace period has completed. + */ + percpu_ref_kill_and_confirm(&lun->lun_ref, target_lun_confirm); + /* + * The first completion waits for percpu_ref_switch_to_atomic_rcu() + * to call target_lun_confirm after lun->lun_ref has been marked + * as __PERCPU_REF_DEAD on all CPUs, and switches to atomic_t + * mode so that percpu_ref_tryget_live() lookup of lun->lun_ref + * fails for all new incoming I/O. + */ wait_for_completion(&lun->lun_ref_comp); + /* + * The second completion waits for percpu_ref_put_many() to + * invoke ->release() after lun->lun_ref has switched to + * atomic_t mode, and lun->lun_ref.count has reached zero. + * + * At this point all target-core lun->lun_ref references have + * been dropped via transport_lun_remove_cmd(), and it's safe + * to proceed with the remaining LUN shutdown. + */ + wait_for_completion(&lun->lun_shutdown_comp); } static bool diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 48bc1ac1da43..6233e8fd95b5 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -732,6 +732,7 @@ struct se_lun { struct config_group lun_group; struct se_port_stat_grps port_stat_grps; struct completion lun_ref_comp; + struct completion lun_shutdown_comp; struct percpu_ref lun_ref; struct list_head lun_dev_link; struct hlist_node link; From 1afe7b4ac3df20d2b9afd90d475fa466027a6595 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Wed, 11 Jan 2017 11:50:06 +1100 Subject: [PATCH 32/64] drivers/pci/hotplug: Handle presence detection change properly commit d7d55536c6cd1f80295b6d7483ad0587b148bde4 upstream. The surprise hotplug is driven by interrupt in PowerNV PCI hotplug driver. In the interrupt handler, pnv_php_interrupt(), we bail when pnv_pci_get_presence_state() returns zero wrongly. It causes the presence change event is always ignored incorrectly. This fixes the issue by bailing on error (non-zero value) returned from pnv_pci_get_presence_state(). Fixes: 360aebd85a4 ("drivers/pci/hotplug: Support surprise hotplug in powernv driver") Reported-by: Hank Chang Signed-off-by: Gavin Shan Tested-by: Willie Liauw Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- drivers/pci/hotplug/pnv_php.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c index 99b05338b4bc..e1c29909e7d3 100644 --- a/drivers/pci/hotplug/pnv_php.c +++ b/drivers/pci/hotplug/pnv_php.c @@ -713,8 +713,12 @@ static irqreturn_t pnv_php_interrupt(int irq, void *data) added = !!(lsts & PCI_EXP_LNKSTA_DLLLA); } else if (sts & PCI_EXP_SLTSTA_PDC) { ret = pnv_pci_get_presence_state(php_slot->id, &presence); - if (!ret) + if (ret) { + dev_warn(&pdev->dev, "PCI slot [%s] error %d getting presence (0x%04x), to retry the operation.\n", + php_slot->name, ret, sts); return IRQ_HANDLED; + } + added = !!(presence == OPAL_PCI_SLOT_PRESENT); } else { return IRQ_NONE; From 4f77c55c3ac232c4dfa308ce147d943b594a17ca Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Wed, 11 Jan 2017 11:50:07 +1100 Subject: [PATCH 33/64] drivers/pci/hotplug: Fix initial state for empty slot commit d0c424971f70501ec0a0364117b9934db039c9cc upstream. In PowerNV PCI hotplug driver, the initial PCI slot's state is set to PNV_PHP_STATE_POPULATED if no PCI devices are connected to the slot. The PCI devices that are hot added to the slot won't be probed and populated because of the check in pnv_php_enable(): /* Check if the slot has been configured */ if (php_slot->state != PNV_PHP_STATE_REGISTERED) return 0; This fixes the issue by leaving the slot in PNV_PHP_STATE_REGISTERED state initially if nothing is connected to the slot. Fixes: 360aebd85a4 ("drivers/pci/hotplug: Support surprise hotplug in powernv driver") Reported-by: Hank Chang Signed-off-by: Gavin Shan Tested-by: Willie Liauw Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- drivers/pci/hotplug/pnv_php.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c index e1c29909e7d3..e96973b95e7a 100644 --- a/drivers/pci/hotplug/pnv_php.c +++ b/drivers/pci/hotplug/pnv_php.c @@ -436,9 +436,21 @@ static int pnv_php_enable(struct pnv_php_slot *php_slot, bool rescan) if (ret) return ret; - /* Proceed if there have nothing behind the slot */ - if (presence == OPAL_PCI_SLOT_EMPTY) + /* + * Proceed if there have nothing behind the slot. However, + * we should leave the slot in registered state at the + * beginning. Otherwise, the PCI devices inserted afterwards + * won't be probed and populated. + */ + if (presence == OPAL_PCI_SLOT_EMPTY) { + if (!php_slot->power_state_check) { + php_slot->power_state_check = true; + + return 0; + } + goto scan; + } /* * If the power supply to the slot is off, we can't detect From 1f2f16c7b7e307ce0ef1764e6142e1dd2007e40e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 11 Feb 2017 10:37:38 -0500 Subject: [PATCH 34/64] nlm: Ensure callback code also checks that the files match commit 251af29c320d86071664f02c76f0d063a19fefdf upstream. It is not sufficient to just check that the lock pids match when granting a callback, we also need to ensure that we're granting the callback on the right file. Reported-by: Pankaj Singh Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Greg Kroah-Hartman --- include/linux/lockd/lockd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index c15373894a42..b37dee3acaba 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -355,7 +355,8 @@ static inline int nlm_privileged_requester(const struct svc_rqst *rqstp) static inline int nlm_compare_locks(const struct file_lock *fl1, const struct file_lock *fl2) { - return fl1->fl_pid == fl2->fl_pid + return file_inode(fl1->fl_file) == file_inode(fl2->fl_file) + && fl1->fl_pid == fl2->fl_pid && fl1->fl_owner == fl2->fl_owner && fl1->fl_start == fl2->fl_start && fl1->fl_end == fl2->fl_end From 019c088dc403448aa29e8650c551baa1e5e29e0f Mon Sep 17 00:00:00 2001 From: Clemens Gruber Date: Tue, 13 Dec 2016 16:52:50 +0100 Subject: [PATCH 35/64] pwm: pca9685: Fix period change with same duty cycle commit 8d254a340efb12b40c4c1ff25a48a4f48f7bbd6b upstream. When first implementing support for changing the output frequency, an optimization was added to continue the PWM after changing the prescaler without having to reprogram the ON and OFF registers for the duty cycle, in case the duty cycle stayed the same. This was flawed, because we compared the absolute value of the duty cycle in nanoseconds instead of the ratio to the period. Fix the problem by removing the shortcut. Fixes: 01ec8472009c9 ("pwm-pca9685: Support changing the output frequency") Signed-off-by: Clemens Gruber Reviewed-by: Mika Westerberg Signed-off-by: Thierry Reding Signed-off-by: Greg Kroah-Hartman --- drivers/pwm/pwm-pca9685.c | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/drivers/pwm/pwm-pca9685.c b/drivers/pwm/pwm-pca9685.c index 117fccf7934a..01a6a83f625d 100644 --- a/drivers/pwm/pwm-pca9685.c +++ b/drivers/pwm/pwm-pca9685.c @@ -65,7 +65,6 @@ #define PCA9685_MAXCHAN 0x10 #define LED_FULL (1 << 4) -#define MODE1_RESTART (1 << 7) #define MODE1_SLEEP (1 << 4) #define MODE2_INVRT (1 << 4) #define MODE2_OUTDRV (1 << 2) @@ -117,16 +116,6 @@ static int pca9685_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, udelay(500); pca->period_ns = period_ns; - - /* - * If the duty cycle did not change, restart PWM with - * the same duty cycle to period ratio and return. - */ - if (duty_ns == pca->duty_ns) { - regmap_update_bits(pca->regmap, PCA9685_MODE1, - MODE1_RESTART, 0x1); - return 0; - } } else { dev_err(chip->dev, "prescaler not set: period out of bounds!\n"); From a7b9c9ddb6f457bab2fc8527ffccf16eefba4af4 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Tue, 3 Jan 2017 09:37:34 -0800 Subject: [PATCH 36/64] xtensa: move parse_tag_fdt out of #ifdef CONFIG_BLK_DEV_INITRD commit 4ab18701c66552944188dbcd0ce0012729baab84 upstream. FDT tag parsing is not related to whether BLK_DEV_INITRD is configured or not, move it out of the corresponding #ifdef/#endif block. This fixes passing external FDT to the kernel configured w/o BLK_DEV_INITRD support. Signed-off-by: Max Filippov Signed-off-by: Greg Kroah-Hartman --- arch/xtensa/kernel/setup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 32cdc2c52e98..a45d32abea26 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -133,6 +133,8 @@ static int __init parse_tag_initrd(const bp_tag_t* tag) __tagtable(BP_TAG_INITRD, parse_tag_initrd); +#endif /* CONFIG_BLK_DEV_INITRD */ + #ifdef CONFIG_OF static int __init parse_tag_fdt(const bp_tag_t *tag) @@ -145,8 +147,6 @@ __tagtable(BP_TAG_FDT, parse_tag_fdt); #endif /* CONFIG_OF */ -#endif /* CONFIG_BLK_DEV_INITRD */ - static int __init parse_tag_cmdline(const bp_tag_t* tag) { strlcpy(command_line, (char *)(tag->data), COMMAND_LINE_SIZE); From 9ad1571da2c0139db952d8df5a9e4d67a752948b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 28 Feb 2017 18:32:48 -0800 Subject: [PATCH 37/64] nfit, libnvdimm: fix interleave set cookie calculation commit 86ef58a4e35e8fa66afb5898cf6dec6a3bb29f67 upstream. The interleave-set cookie is a sum that sanity checks the composition of an interleave set has not changed from when the namespace was initially created. The checksum is calculated by sorting the DIMMs by their location in the interleave-set. The comparison for the sort must be 64-bit wide, not byte-by-byte as performed by memcmp() in the broken case. Fix the implementation to accept correct cookie values in addition to the Linux "memcmp" order cookies, but only allow correct cookies to be generated going forward. It does mean that namespaces created by third-party-tooling, or created by newer kernels with this fix, will not validate on older kernels. However, there are a couple mitigating conditions: 1/ platforms with namespace-label capable NVDIMMs are not widely available. 2/ interleave-sets with a single-dimm are by definition not affected (nothing to sort). This covers the QEMU-KVM NVDIMM emulation case. The cookie stored in the namespace label will be fixed by any write the namespace label, the most straightforward way to achieve this is to write to the "alt_name" attribute of a namespace in sysfs. Fixes: eaf961536e16 ("libnvdimm, nfit: add interleave-set state-tracking infrastructure") Reported-by: Nicholas Moulin Tested-by: Nicholas Moulin Signed-off-by: Dan Williams Signed-off-by: Greg Kroah-Hartman --- drivers/acpi/nfit/core.c | 16 +++++++++++++++- drivers/nvdimm/namespace_devs.c | 18 ++++++++++++++---- drivers/nvdimm/nd.h | 1 + drivers/nvdimm/region_devs.c | 9 +++++++++ include/linux/libnvdimm.h | 2 ++ 5 files changed, 41 insertions(+), 5 deletions(-) diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 6eb6733a7a5c..d1664df001f8 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1603,7 +1603,7 @@ static size_t sizeof_nfit_set_info(int num_mappings) + num_mappings * sizeof(struct nfit_set_info_map); } -static int cmp_map(const void *m0, const void *m1) +static int cmp_map_compat(const void *m0, const void *m1) { const struct nfit_set_info_map *map0 = m0; const struct nfit_set_info_map *map1 = m1; @@ -1612,6 +1612,14 @@ static int cmp_map(const void *m0, const void *m1) sizeof(u64)); } +static int cmp_map(const void *m0, const void *m1) +{ + const struct nfit_set_info_map *map0 = m0; + const struct nfit_set_info_map *map1 = m1; + + return map0->region_offset - map1->region_offset; +} + /* Retrieve the nth entry referencing this spa */ static struct acpi_nfit_memory_map *memdev_from_spa( struct acpi_nfit_desc *acpi_desc, u16 range_index, int n) @@ -1667,6 +1675,12 @@ static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc, sort(&info->mapping[0], nr, sizeof(struct nfit_set_info_map), cmp_map, NULL); nd_set->cookie = nd_fletcher64(info, sizeof_nfit_set_info(nr), 0); + + /* support namespaces created with the wrong sort order */ + sort(&info->mapping[0], nr, sizeof(struct nfit_set_info_map), + cmp_map_compat, NULL); + nd_set->altcookie = nd_fletcher64(info, sizeof_nfit_set_info(nr), 0); + ndr_desc->nd_set = nd_set; devm_kfree(dev, info); diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index aefca644219b..a38ae34b74e4 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -1700,6 +1700,7 @@ static int select_pmem_id(struct nd_region *nd_region, u8 *pmem_id) struct device *create_namespace_pmem(struct nd_region *nd_region, struct nd_namespace_label *nd_label) { + u64 altcookie = nd_region_interleave_set_altcookie(nd_region); u64 cookie = nd_region_interleave_set_cookie(nd_region); struct nd_label_ent *label_ent; struct nd_namespace_pmem *nspm; @@ -1718,7 +1719,11 @@ struct device *create_namespace_pmem(struct nd_region *nd_region, if (__le64_to_cpu(nd_label->isetcookie) != cookie) { dev_dbg(&nd_region->dev, "invalid cookie in label: %pUb\n", nd_label->uuid); - return ERR_PTR(-EAGAIN); + if (__le64_to_cpu(nd_label->isetcookie) != altcookie) + return ERR_PTR(-EAGAIN); + + dev_dbg(&nd_region->dev, "valid altcookie in label: %pUb\n", + nd_label->uuid); } nspm = kzalloc(sizeof(*nspm), GFP_KERNEL); @@ -1733,9 +1738,14 @@ struct device *create_namespace_pmem(struct nd_region *nd_region, res->name = dev_name(&nd_region->dev); res->flags = IORESOURCE_MEM; - for (i = 0; i < nd_region->ndr_mappings; i++) - if (!has_uuid_at_pos(nd_region, nd_label->uuid, cookie, i)) - break; + for (i = 0; i < nd_region->ndr_mappings; i++) { + if (has_uuid_at_pos(nd_region, nd_label->uuid, cookie, i)) + continue; + if (has_uuid_at_pos(nd_region, nd_label->uuid, altcookie, i)) + continue; + break; + } + if (i < nd_region->ndr_mappings) { struct nvdimm_drvdata *ndd = to_ndd(&nd_region->mapping[i]); diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index d3b2fca8deec..d869236b474f 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -327,6 +327,7 @@ struct nd_region *to_nd_region(struct device *dev); int nd_region_to_nstype(struct nd_region *nd_region); int nd_region_register_namespaces(struct nd_region *nd_region, int *err); u64 nd_region_interleave_set_cookie(struct nd_region *nd_region); +u64 nd_region_interleave_set_altcookie(struct nd_region *nd_region); void nvdimm_bus_lock(struct device *dev); void nvdimm_bus_unlock(struct device *dev); bool is_nvdimm_bus_locked(struct device *dev); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 6af5e629140c..9cf6f1a88fce 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -505,6 +505,15 @@ u64 nd_region_interleave_set_cookie(struct nd_region *nd_region) return 0; } +u64 nd_region_interleave_set_altcookie(struct nd_region *nd_region) +{ + struct nd_interleave_set *nd_set = nd_region->nd_set; + + if (nd_set) + return nd_set->altcookie; + return 0; +} + void nd_mapping_free_labels(struct nd_mapping *nd_mapping) { struct nd_label_ent *label_ent, *e; diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 8458c5351e56..77e7af32543f 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -70,6 +70,8 @@ struct nd_cmd_desc { struct nd_interleave_set { u64 cookie; + /* compatibility with initial buggy Linux implementation */ + u64 altcookie; }; struct nd_mapping_desc { From b116db0da1bd97ce405c19b304955d54f650eea9 Mon Sep 17 00:00:00 2001 From: Matt Chen Date: Sun, 22 Jan 2017 02:16:58 +0800 Subject: [PATCH 38/64] mac80211: flush delayed work when entering suspend commit a9e9200d8661c1a0be8c39f93deb383dc940de35 upstream. The issue was found when entering suspend and resume. It triggers a warning in: mac80211/key.c: ieee80211_enable_keys() ... WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt || sdata->crypto_tx_tailroom_pending_dec); ... It points out sdata->crypto_tx_tailroom_pending_dec isn't cleaned up successfully in a delayed_work during suspend. Add a flush_delayed_work to fix it. Signed-off-by: Matt Chen Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- net/mac80211/pm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 28a3a0957c9e..76a8bcd8ef11 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -168,6 +168,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) break; } + flush_delayed_work(&sdata->dec_tailroom_needed_wk); drv_remove_interface(local, sdata); } From 42e7f3771429d40b5307f0db0ecdba61e79272ac Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Mon, 6 Feb 2017 15:28:42 +0200 Subject: [PATCH 39/64] mac80211: don't reorder frames with SN smaller than SSN commit b7540d8f25c8034de7e4163fc23ac457bf057731 upstream. When RX aggregation starts, transmitter may continue send frames with SN smaller than SSN until the AddBA response is received. However, the reorder buffer is already initialized at this point, which will cause the drop of such frames as duplicates since the head SN of the reorder buffer is set to the SSN, which is bigger. Signed-off-by: Sara Sharon Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- net/mac80211/agg-rx.c | 1 + net/mac80211/rx.c | 14 +++++++++++++- net/mac80211/sta_info.h | 6 ++++-- 3 files changed, 18 insertions(+), 3 deletions(-) diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 3b5fd4188f2a..58ad23a44109 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -398,6 +398,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, tid_agg_rx->timeout = timeout; tid_agg_rx->stored_mpdu_num = 0; tid_agg_rx->auto_seq = auto_seq; + tid_agg_rx->started = false; tid_agg_rx->reorder_buf_filtered = 0; status = WLAN_STATUS_SUCCESS; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 2384b4aae064..8a344bd3b52a 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4,7 +4,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright(c) 2015 - 2016 Intel Deutschland GmbH + * Copyright(c) 2015 - 2017 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1034,6 +1034,18 @@ static bool ieee80211_sta_manage_reorder_buf(struct ieee80211_sub_if_data *sdata buf_size = tid_agg_rx->buf_size; head_seq_num = tid_agg_rx->head_seq_num; + /* + * If the current MPDU's SN is smaller than the SSN, it shouldn't + * be reordered. + */ + if (unlikely(!tid_agg_rx->started)) { + if (ieee80211_sn_less(mpdu_seq_num, head_seq_num)) { + ret = false; + goto out; + } + tid_agg_rx->started = true; + } + /* frame with out of date sequence number */ if (ieee80211_sn_less(mpdu_seq_num, head_seq_num)) { dev_kfree_skb(skb); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index dd06ef0b8861..15599c70a38f 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -189,6 +189,7 @@ struct tid_ampdu_tx { * @auto_seq: used for offloaded BA sessions to automatically pick head_seq_and * and ssn. * @removed: this session is removed (but might have been found due to RCU) + * @started: this session has started (head ssn or higher was received) * * This structure's lifetime is managed by RCU, assignments to * the array holding it must hold the aggregation mutex. @@ -212,8 +213,9 @@ struct tid_ampdu_rx { u16 ssn; u16 buf_size; u16 timeout; - bool auto_seq; - bool removed; + u8 auto_seq:1, + removed:1, + started:1; }; /** From 39813849996f96a764df9b993ba726e995aa1dda Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 22 Feb 2017 16:16:07 +0100 Subject: [PATCH 40/64] mac80211: don't handle filtered frames within a BA session commit 890030d3c425f49abaa4acf60e20f288b599f980 upstream. When running a BA session, the driver (or the hardware) already takes care of retransmitting failed frames, since it has to keep the receiver reorder window in sync. Adding another layer of retransmit around that does not improve anything. In fact, it can only lead to some strong reordering with huge latency. Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- net/mac80211/status.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mac80211/status.c b/net/mac80211/status.c index ddf71c648cab..ad37b4e58c2f 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -51,7 +51,8 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, struct ieee80211_hdr *hdr = (void *)skb->data; int ac; - if (info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER) { + if (info->flags & (IEEE80211_TX_CTL_NO_PS_BUFFER | + IEEE80211_TX_CTL_AMPDU)) { ieee80211_free_txskb(&local->hw, skb); return; } From b507df2e236e5edc868ea8ac572567f1de0107f7 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 27 Feb 2017 09:38:11 +0100 Subject: [PATCH 41/64] mac80211: use driver-indicated transmitter STA only for data frames MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 19d19e960598161be92a7e4828eb7706c6410ce6 upstream. When I originally introduced using the driver-indicated station as an optimisation to avoid the hashtable lookup/iteration, of course it wasn't intended to really functionally change anything. I neglected, however, to take into account VLAN interfaces, which have the property that management and data frames are handled differently: data frames go directly to the station and the VLAN while management frames continue to be processed over the underlying/associated AP-type interface. As a consequence, when a driver used this optimisation for management frames and the user enabled VLANs, my change broke things since any management frames, particularly disassoc/deauth, were missed by hostapd. Fix this by restoring the original code path for non-data frames, they aren't critical for performance to begin with. This fixes https://bugzilla.kernel.org/show_bug.cgi?id=194713. Big thanks goes to Jarek who bisected the issue and provided a very detailed bug report, including the crucial information that he was using VLANs in his configuration. Fixes: 771e846bea9e ("mac80211: allow passing transmitter station on RX") Reported-and-tested-by: Jarek Kamiński Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- net/mac80211/rx.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 8a344bd3b52a..a697ddf56334 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4092,15 +4092,17 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, ieee80211_is_beacon(hdr->frame_control))) ieee80211_scan_rx(local, skb); - if (pubsta) { - rx.sta = container_of(pubsta, struct sta_info, sta); - rx.sdata = rx.sta->sdata; - if (ieee80211_prepare_and_rx_handle(&rx, skb, true)) - return; - goto out; - } else if (ieee80211_is_data(fc)) { + if (ieee80211_is_data(fc)) { struct sta_info *sta, *prev_sta; + if (pubsta) { + rx.sta = container_of(pubsta, struct sta_info, sta); + rx.sdata = rx.sta->sdata; + if (ieee80211_prepare_and_rx_handle(&rx, skb, true)) + return; + goto out; + } + prev_sta = NULL; for_each_sta_info(local, hdr->addr2, sta, tmp) { From 0734a3213ca83c92e27167624737fd7a2fcbcca5 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 10 Feb 2017 00:00:52 -0500 Subject: [PATCH 42/64] drm/amdgpu: add more cases to DCE11 possible crtc mask setup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 4ce3bd45b351633f2a0512c587f7fcba2ce044e8 upstream. Add cases for asics with 3 and 5 crtcs. Fixes an artificial limitation on asics with 3 or 5 crtcs. Fixes: https://bugs.freedesktop.org/show_bug.cgi?id=99744 Reviewed-by: Michel Dänzer Reviewed-by: Christian König Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/dce_v11_0.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index 7ddc32127d88..64a1df62cc65 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -3814,9 +3814,15 @@ static void dce_v11_0_encoder_add(struct amdgpu_device *adev, default: encoder->possible_crtcs = 0x3; break; + case 3: + encoder->possible_crtcs = 0x7; + break; case 4: encoder->possible_crtcs = 0xf; break; + case 5: + encoder->possible_crtcs = 0x1f; + break; case 6: encoder->possible_crtcs = 0x3f; break; From 54aa80e300d6e64d569962f25c50bc37436ae9de Mon Sep 17 00:00:00 2001 From: "Y.C. Chen" Date: Wed, 22 Feb 2017 15:10:50 +1100 Subject: [PATCH 43/64] drm/ast: Fix test for VGA enabled commit 905f21a49d388de3e99438235f3301cabf0c0ef4 upstream. The test to see if VGA was already enabled is doing an unnecessary second test from a register that may or may not have been initialized to a valid value. Remove it. Signed-off-by: Y.C. Chen Signed-off-by: Benjamin Herrenschmidt Acked-by: Joel Stanley Tested-by: Y.C. Chen Signed-off-by: Dave Airlie Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/ast/ast_post.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c index 810c51d92b99..4e8aaab5dd52 100644 --- a/drivers/gpu/drm/ast/ast_post.c +++ b/drivers/gpu/drm/ast/ast_post.c @@ -58,13 +58,9 @@ bool ast_is_vga_enabled(struct drm_device *dev) /* TODO 1180 */ } else { ch = ast_io_read8(ast, AST_IO_VGA_ENABLE_PORT); - if (ch) { - ast_open_key(ast); - ch = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb6, 0xff); - return ch & 0x04; - } + return !!(ch & 0x01); } - return 0; + return false; } static const u8 extreginfo[] = { 0x0f, 0x04, 0x1c, 0xff }; From 5da03582e2120b04a58aabc7caa61109106e6c3d Mon Sep 17 00:00:00 2001 From: "Y.C. Chen" Date: Wed, 22 Feb 2017 15:14:19 +1100 Subject: [PATCH 44/64] drm/ast: Call open_key before enable_mmio in POST code commit 9bb92f51558f2ef5f56c257bdcea0588f31d857e upstream. open_key enables access the registers used by enable_mmio Signed-off-by: Y.C. Chen Signed-off-by: Benjamin Herrenschmidt Acked-by: Joel Stanley Tested-by: Y.C. Chen Signed-off-by: Dave Airlie Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/ast/ast_post.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c index 4e8aaab5dd52..50836e549867 100644 --- a/drivers/gpu/drm/ast/ast_post.c +++ b/drivers/gpu/drm/ast/ast_post.c @@ -371,8 +371,8 @@ void ast_post_gpu(struct drm_device *dev) pci_write_config_dword(ast->dev->pdev, 0x04, reg); ast_enable_vga(dev); - ast_enable_mmio(dev); ast_open_key(ast); + ast_enable_mmio(dev); ast_set_def_ext_reg(dev); if (ast->chip == AST2300 || ast->chip == AST2400) From f96c10c2bd1ba4c438cb5e61700825f6ab376a7e Mon Sep 17 00:00:00 2001 From: "Y.C. Chen" Date: Thu, 23 Feb 2017 15:52:33 +0800 Subject: [PATCH 45/64] drm/ast: Fix AST2400 POST failure without BMC FW or VBIOS commit 3856081eede297b617560b85e948cfb00bb395ec upstream. The current POST code for the AST2300/2400 family doesn't work properly if the chip hasn't been initialized previously by either the BMC own FW or the VBIOS. This fixes it. Signed-off-by: Y.C. Chen Signed-off-by: Benjamin Herrenschmidt Tested-by: Y.C. Chen Acked-by: Joel Stanley Signed-off-by: Dave Airlie Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/ast/ast_post.c | 38 +++++++++++++++++++++++++++++++--- 1 file changed, 35 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c index 50836e549867..30672a3df8a9 100644 --- a/drivers/gpu/drm/ast/ast_post.c +++ b/drivers/gpu/drm/ast/ast_post.c @@ -1626,12 +1626,44 @@ static void ast_init_dram_2300(struct drm_device *dev) temp |= 0x73; ast_write32(ast, 0x12008, temp); + param.dram_freq = 396; param.dram_type = AST_DDR3; + temp = ast_mindwm(ast, 0x1e6e2070); if (temp & 0x01000000) param.dram_type = AST_DDR2; - param.dram_chipid = ast->dram_type; - param.dram_freq = ast->mclk; - param.vram_size = ast->vram_size; + switch (temp & 0x18000000) { + case 0: + param.dram_chipid = AST_DRAM_512Mx16; + break; + default: + case 0x08000000: + param.dram_chipid = AST_DRAM_1Gx16; + break; + case 0x10000000: + param.dram_chipid = AST_DRAM_2Gx16; + break; + case 0x18000000: + param.dram_chipid = AST_DRAM_4Gx16; + break; + } + switch (temp & 0x0c) { + default: + case 0x00: + param.vram_size = AST_VIDMEM_SIZE_8M; + break; + + case 0x04: + param.vram_size = AST_VIDMEM_SIZE_16M; + break; + + case 0x08: + param.vram_size = AST_VIDMEM_SIZE_32M; + break; + + case 0x0c: + param.vram_size = AST_VIDMEM_SIZE_64M; + break; + } if (param.dram_type == AST_DDR3) { get_ddr3_info(ast, ¶m); From ec8e40b117c3064cb826a4f25d77e45a7f87d602 Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Mon, 20 Feb 2017 16:25:45 +0100 Subject: [PATCH 46/64] drm/edid: Add EDID_QUIRK_FORCE_8BPC quirk for Rotel RSX-1058 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 36fc579761b50784b63dafd0f2e796b659e0f5ee upstream. Rotel RSX-1058 is a receiver with 4 HDMI inputs and a HDMI output, all 1.1. When a sink that supports deep color is connected to the output, the receiver will send EDIDs that advertise this capability, even if it isn't possible with HDMI versions earlier than 1.3. Currently the kernel is assuming that deep color is possible and the sink displays an error. This quirk will make sure that deep color isn't used with this particular receiver. Fixes: 7a0baa623446 ("Revert "drm/i915: Disable 12bpc hdmi for now"") Signed-off-by: Tomeu Vizoso Link: http://patchwork.freedesktop.org/patch/msgid/20170220152545.13153-1-tomeu.vizoso@collabora.com Cc: Matt Horan Tested-by: Matt Horan Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=99869 Reviewed-by: Ville Syrjälä Signed-off-by: Ville Syrjälä Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_edid.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index ec77bd3e1f08..7491180698d1 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -145,6 +145,9 @@ static struct edid_quirk { /* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */ { "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC }, + + /* Rotel RSX-1058 forwards sink's EDID but only does HDMI 1.1*/ + { "ETR", 13896, EDID_QUIRK_FORCE_8BPC }, }; /* From 55f47122c2e8d77a2bdb0f4bd7da57423f947824 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michel=20D=C3=A4nzer?= Date: Wed, 25 Jan 2017 17:21:31 +0900 Subject: [PATCH 47/64] drm/ttm: Make sure BOs being swapped out are cacheable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 239ac65fa5ffab71adf66e642750f940e7241d99 upstream. The current caching state may not be tt_cached, even though the placement contains TTM_PL_FLAG_CACHED, because placement can contain multiple caching flags. Trying to swap out such a BO would trip up the BUG_ON(ttm->caching_state != tt_cached); in ttm_tt_swapout. Signed-off-by: Michel Dänzer Reviewed-by: Thomas Hellstrom Reviewed-by: Christian König . Reviewed-by: Sinclair Yeh Signed-off-by: Christian König Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/ttm/ttm_bo.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index fc6217dfe401..35cc16f9fec9 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1654,7 +1654,6 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink) struct ttm_buffer_object *bo; int ret = -EBUSY; int put_count; - uint32_t swap_placement = (TTM_PL_FLAG_CACHED | TTM_PL_FLAG_SYSTEM); spin_lock(&glob->lru_lock); list_for_each_entry(bo, &glob->swap_lru, swap) { @@ -1685,7 +1684,8 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink) * Move to system cached */ - if ((bo->mem.placement & swap_placement) != swap_placement) { + if (bo->mem.mem_type != TTM_PL_SYSTEM || + bo->ttm->caching_state != tt_cached) { struct ttm_mem_reg evict_mem; evict_mem = bo->mem; From 56a567de553e0ad1440b111077dce521ecdd0cd8 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Tue, 21 Feb 2017 17:42:27 +0700 Subject: [PATCH 48/64] drm/vmwgfx: Work around drm removal of control nodes commit 31788ca803a0c89078f9e604e64286fbd9077926 upstream. vmware tools has a daemon that gets layout information from the GUI and forwards it to DRM so that the modesetting code can set preferred connector locations and modes. This daemon was using control nodes but since control nodes were just removed, make it possible for the daemon to use render- or primary nodes instead. This is a bit ugly but will allow drm to proceed with removal of the mostly unused control-node code and allow vmware to proceed with fixing up automatic layout settings for gnome-shell/wayland. We bump minor to inform user-space about the api change. Signed-off-by: Thomas Hellstrom Reviewed-by: Sinclair Yeh Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20170221104227.2854-1-thellstrom@vmware.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 11 ++++++++++- drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 4 ++-- 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 18061a4bc2f2..36005bdf3749 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -199,9 +199,14 @@ static const struct drm_ioctl_desc vmw_ioctls[] = { VMW_IOCTL_DEF(VMW_PRESENT_READBACK, vmw_present_readback_ioctl, DRM_MASTER | DRM_AUTH), + /* + * The permissions of the below ioctl are overridden in + * vmw_generic_ioctl(). We require either + * DRM_MASTER or capable(CAP_SYS_ADMIN). + */ VMW_IOCTL_DEF(VMW_UPDATE_LAYOUT, vmw_kms_update_layout_ioctl, - DRM_MASTER | DRM_CONTROL_ALLOW), + DRM_RENDER_ALLOW), VMW_IOCTL_DEF(VMW_CREATE_SHADER, vmw_shader_define_ioctl, DRM_AUTH | DRM_RENDER_ALLOW), @@ -1125,6 +1130,10 @@ static long vmw_generic_ioctl(struct file *filp, unsigned int cmd, return (long) vmw_execbuf_ioctl(dev, arg, file_priv, _IOC_SIZE(cmd)); + } else if (nr == DRM_COMMAND_BASE + DRM_VMW_UPDATE_LAYOUT) { + if (!drm_is_current_master(file_priv) && + !capable(CAP_SYS_ADMIN)) + return -EACCES; } if (unlikely(ioctl->cmd != cmd)) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 1e59a486bba8..59ff4197173a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -41,9 +41,9 @@ #include #include "vmwgfx_fence.h" -#define VMWGFX_DRIVER_DATE "20160210" +#define VMWGFX_DRIVER_DATE "20170221" #define VMWGFX_DRIVER_MAJOR 2 -#define VMWGFX_DRIVER_MINOR 11 +#define VMWGFX_DRIVER_MINOR 12 #define VMWGFX_DRIVER_PATCHLEVEL 0 #define VMWGFX_FILE_PAGE_OFFSET 0x00100000 #define VMWGFX_FIFO_STATIC_SIZE (1024*1024) From 3a654a85932fa7a909b11934df7657c1a2cb3609 Mon Sep 17 00:00:00 2001 From: Nandor Han Date: Tue, 11 Oct 2016 14:13:41 +0300 Subject: [PATCH 49/64] dmaengine: imx-sdma - correct the dma transfer residue calculation commit 85f57752b33cf12f1d583f0c10b752292de00abe upstream. The residue calculation was taking in consideration that dma transaction status will be always retrieved in the dma callback used to inform that dma transfer is complete. However this is not the case for all subsystems that use dma. Some subsystems use a timer to check the dma status periodically. Therefore the calculation was updated and residue is calculated accordingly by a) update the residue calculation taking in consideration the last used buffer index by using *buf_ptail* variable and b) chn_real_count (number of bytes transferred) is initialized to zero, when dma channel is created, to avoid using an uninitialized value in residue calculation when dma status is checked without waiting dma complete event. Signed-off-by: Nandor Han Acked-by: Peter Senna Tschudin Tested-by: Peter Senna Tschudin Tested-by: Marek Vasut Signed-off-by: Vinod Koul Cc: Fabio Estevam Signed-off-by: Greg Kroah-Hartman --- drivers/dma/imx-sdma.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index b9629b2bfc05..d1651a50c349 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -298,6 +298,7 @@ struct sdma_engine; * @event_id1 for channels that use 2 events * @word_size peripheral access size * @buf_tail ID of the buffer that was processed + * @buf_ptail ID of the previous buffer that was processed * @num_bd max NUM_BD. number of descriptors currently handling */ struct sdma_channel { @@ -309,6 +310,7 @@ struct sdma_channel { unsigned int event_id1; enum dma_slave_buswidth word_size; unsigned int buf_tail; + unsigned int buf_ptail; unsigned int num_bd; unsigned int period_len; struct sdma_buffer_descriptor *bd; @@ -700,6 +702,8 @@ static void sdma_update_channel_loop(struct sdma_channel *sdmac) sdmac->chn_real_count = bd->mode.count; bd->mode.status |= BD_DONE; bd->mode.count = sdmac->period_len; + sdmac->buf_ptail = sdmac->buf_tail; + sdmac->buf_tail = (sdmac->buf_tail + 1) % sdmac->num_bd; /* * The callback is called from the interrupt context in order @@ -710,9 +714,6 @@ static void sdma_update_channel_loop(struct sdma_channel *sdmac) dmaengine_desc_get_callback_invoke(&sdmac->desc, NULL); - sdmac->buf_tail++; - sdmac->buf_tail %= sdmac->num_bd; - if (error) sdmac->status = old_status; } @@ -1186,6 +1187,8 @@ static struct dma_async_tx_descriptor *sdma_prep_slave_sg( sdmac->flags = 0; sdmac->buf_tail = 0; + sdmac->buf_ptail = 0; + sdmac->chn_real_count = 0; dev_dbg(sdma->dev, "setting up %d entries for channel %d.\n", sg_len, channel); @@ -1288,6 +1291,8 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic( sdmac->status = DMA_IN_PROGRESS; sdmac->buf_tail = 0; + sdmac->buf_ptail = 0; + sdmac->chn_real_count = 0; sdmac->period_len = period_len; sdmac->flags |= IMX_DMA_SG_LOOP; @@ -1385,7 +1390,7 @@ static enum dma_status sdma_tx_status(struct dma_chan *chan, u32 residue; if (sdmac->flags & IMX_DMA_SG_LOOP) - residue = (sdmac->num_bd - sdmac->buf_tail) * + residue = (sdmac->num_bd - sdmac->buf_ptail) * sdmac->period_len - sdmac->chn_real_count; else residue = sdmac->chn_count - sdmac->chn_real_count; From 98620b564fadc0f997194b3da0393b78b2c17447 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Wed, 8 Feb 2017 10:47:49 -0200 Subject: [PATCH 50/64] drm/imx: imx-tve: Do not set the regulator voltage commit fc12bccda8b6f5c38139eceec9e369ed78091b2b upstream. Commit deb65870b5d9d ("drm/imx: imx-tve: check the value returned by regulator_set_voltage()") exposes the following probe issue: 63ff0000.tve supply dac not found, using dummy regulator imx-drm display-subsystem: failed to bind 63ff0000.tve (ops imx_tve_ops): -22 When the 'dac-supply' is not passed in the device tree a dummy regulator is used and setting its voltage is not allowed. To fix this issue, do not set the dac-supply voltage inside the driver and let its voltage be specified in the device tree. Print a warning if the the 'dac-supply' voltage has a value different from 2.75V. Fixes: deb65870b5d9d ("drm/imx: imx-tve: check the value returned by regulator_set_voltage()") Suggested-by: Lucas Stach Signed-off-by: Fabio Estevam Signed-off-by: Philipp Zabel Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/imx/imx-tve.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c index 8fc088843e55..89cf0090feac 100644 --- a/drivers/gpu/drm/imx/imx-tve.c +++ b/drivers/gpu/drm/imx/imx-tve.c @@ -98,6 +98,8 @@ /* TVE_TST_MODE_REG */ #define TVE_TVDAC_TEST_MODE_MASK (0x7 << 0) +#define IMX_TVE_DAC_VOLTAGE 2750000 + enum { TVE_MODE_TVOUT, TVE_MODE_VGA, @@ -628,9 +630,8 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data) tve->dac_reg = devm_regulator_get(dev, "dac"); if (!IS_ERR(tve->dac_reg)) { - ret = regulator_set_voltage(tve->dac_reg, 2750000, 2750000); - if (ret) - return ret; + if (regulator_get_voltage(tve->dac_reg) != IMX_TVE_DAC_VOLTAGE) + dev_warn(dev, "dac voltage is not %d uV\n", IMX_TVE_DAC_VOLTAGE); ret = regulator_enable(tve->dac_reg); if (ret) return ret; From f72b751f434062deaf16a1aca2c5f53ddf71ed8f Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 8 Feb 2017 02:46:01 +0300 Subject: [PATCH 51/64] drm/atomic: fix an error code in mode_fixup() commit f9ad86e42d0303eeb8e0d41bb208153022ebd9d2 upstream. Having "ret" be a bool type works for everything except ret = funcs->atomic_check(). The other functions all return zero on error but ->atomic_check() returns negative error codes. We want to propagate the error code but instead we return 1. I found this bug with static analysis and I don't know if it affects run time. Fixes: 4cd4df8080a3 ("drm/atomic: Add ->atomic_check() to encoder helpers") Signed-off-by: Dan Carpenter Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20170207234601.GA23981@mwanda Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_atomic_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index a05bb3891119..2e42a0584a84 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -362,7 +362,7 @@ mode_fixup(struct drm_atomic_state *state) struct drm_connector *connector; struct drm_connector_state *conn_state; int i; - bool ret; + int ret; for_each_crtc_in_state(state, crtc, crtc_state, i) { if (!crtc_state->mode_changed && From 868a747c77cbf1d5e183dbceb912baa4db2be913 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 9 Nov 2016 10:39:05 +0000 Subject: [PATCH 52/64] drm/i915/gvt: Disable access to stolen memory as a guest commit ddd09373628adcbdc3f7b9098d22328834f8d772 upstream. Explicitly disable stolen memory when running as a guest in a virtual machine, since the memory is not mediated between clients and reserved entirely for the host. The actual size should be reported as zero, but like every other quirk we want to tell the user what is happening. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=99028 Signed-off-by: Chris Wilson Cc: Zhenyu Wang Cc: Joonas Lahtinen Link: http://patchwork.freedesktop.org/patch/msgid/20161109103905.17860-1-chris@chris-wilson.co.uk Reviewed-by: Zhenyu Wang (cherry picked from commit 04a68a35ce6d7b54749989f943993020f48fed62) Signed-off-by: Jani Nikula Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_gem_stolen.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index 9a71ed546b90..f46aac1e85fb 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -415,6 +415,11 @@ int i915_gem_init_stolen(struct drm_device *dev) mutex_init(&dev_priv->mm.stolen_lock); + if (intel_vgpu_active(dev_priv)) { + DRM_INFO("iGVT-g active, disabling use of stolen memory\n"); + return 0; + } + #ifdef CONFIG_INTEL_IOMMU if (intel_iommu_gfx_mapped && INTEL_INFO(dev)->gen < 8) { DRM_INFO("DMAR active, disabling use of stolen memory\n"); From 9edc456fe621f3ba33859ea3ad3c285e544db9ad Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 7 Feb 2017 12:49:55 +0000 Subject: [PATCH 53/64] drm: Cancel drm_fb_helper_dirty_work on unload MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit f21b9a92ca7c29382909eaab9facc2cf46f2cc0b upstream. We can not allow the worker to run after its fbdev, or even the module, has been removed. Fixes: eaa434defaca ("drm/fb-helper: Add fb_deferred_io support") Signed-off-by: Chris Wilson Cc: Noralf Trønnes Cc: Daniel Vetter Cc: Jani Nikula Cc: Sean Paul Cc: dri-devel@lists.freedesktop.org Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20170207124956.14954-1-chris@chris-wilson.co.uk Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_fb_helper.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 6c75e62c0b22..cc8938bb9ff4 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -848,6 +848,8 @@ void drm_fb_helper_fini(struct drm_fb_helper *fb_helper) if (!drm_fbdev_emulation) return; + cancel_work_sync(&fb_helper->dirty_work); + if (!list_empty(&fb_helper->kernel_fb_list)) { list_del(&fb_helper->kernel_fb_list); if (list_empty(&kernel_fb_helper_list)) { From 967e17bcc96da9ab48fd621a6859d1ca55e82df9 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 7 Feb 2017 12:49:56 +0000 Subject: [PATCH 54/64] drm: Cancel drm_fb_helper_resume_work on unload MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 24f76b2c87ed68f79f9f0705b11ccbefaaa0d390 upstream. We can not allow the worker to run after its fbdev, or even the module, has been removed. Fixes: cfe63423d9be ("drm/fb-helper: Add drm_fb_helper_set_suspend_unlocked()") Signed-off-by: Chris Wilson Cc: Noralf Trønnes Cc: Daniel Vetter Cc: Jani Nikula Cc: Sean Paul Cc: dri-devel@lists.freedesktop.org Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20170207124956.14954-2-chris@chris-wilson.co.uk Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_fb_helper.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index cc8938bb9ff4..6a48d6637e5c 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -848,6 +848,7 @@ void drm_fb_helper_fini(struct drm_fb_helper *fb_helper) if (!drm_fbdev_emulation) return; + cancel_work_sync(&fb_helper->resume_work); cancel_work_sync(&fb_helper->dirty_work); if (!list_empty(&fb_helper->kernel_fb_list)) { From 686ea5862eb61e070881c221271f6563cb74a7f0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Wed, 8 Feb 2017 19:52:54 +0200 Subject: [PATCH 55/64] drm/i915: Avoid spurious WARNs about the wrong pipe in the PPS code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit aa9323dd49b23932a09023012f050556de64f118 upstream. Until recently vlv_steal_power_sequencer() wasn't being called for normal DP ports, and hence it could assert that it should only be called for pipe A and B (since pipe C doesn't support eDP). However that changed when we started to consider normal DP ports as well when choosing a PPS. So we will now get spurious warnings when vlv_steal_power_sequencer() does get called for pipe C. Avoid this by moving the WARN down into vlv_detach_power_sequencer() where this assertion should still hold. Cc: Imre Deak Fixes: 9f2bdb006a7e ("drm/i915: Prevent PPS stealing from a normal DP port on VLV/CHV") References: https://bugs.freedesktop.org/show_bug.cgi?id=95287 Signed-off-by: Ville Syrjälä Link: http://patchwork.freedesktop.org/patch/msgid/20170208175254.10958-1-ville.syrjala@linux.intel.com Reviewed-by: Imre Deak (cherry picked from commit d158694f452252d0fef335a775aeb3eb74fe7af0) Signed-off-by: Jani Nikula Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/intel_dp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 055525013d2f..7b06280b23aa 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -2832,6 +2832,9 @@ static void vlv_detach_power_sequencer(struct intel_dp *intel_dp) enum pipe pipe = intel_dp->pps_pipe; i915_reg_t pp_on_reg = PP_ON_DELAYS(pipe); + if (WARN_ON(pipe != PIPE_A && pipe != PIPE_B)) + return; + edp_panel_vdd_off_sync(intel_dp); /* @@ -2859,9 +2862,6 @@ static void vlv_steal_power_sequencer(struct drm_device *dev, lockdep_assert_held(&dev_priv->pps_mutex); - if (WARN_ON(pipe != PIPE_A && pipe != PIPE_B)) - return; - for_each_intel_encoder(dev, encoder) { struct intel_dp *intel_dp; enum port port; From ff3bcdc9b5f00809a18cc1a3ea42a72e00b1a895 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 14 Feb 2017 18:12:38 +0200 Subject: [PATCH 56/64] drm/i915: Fix not finding the VBT when it overlaps with OPREGION_ASLE_EXT commit 998d75730b40afc218c059d811869abe9676b305 upstream. If there is no OPREGION_ASLE_EXT then a VBT stored in mailbox #4 may use the ASLE_EXT parts of the opregion. Adjust the vbt_size calculation for a vbt in mailbox #4 for this. This fixes the driver not finding the VBT on a jumper ezpad mini3 cherrytrail tablet and on a ACER SW5_017 machine. Signed-off-by: Hans de Goede Signed-off-by: Jani Nikula Link: http://patchwork.freedesktop.org/patch/msgid/1487088758-30050-1-git-send-email-jani.nikula@intel.com (cherry picked from commit dfb65e71ea2c1d97ac373cc0587dc60b3307581a) Signed-off-by: Jani Nikula Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/intel_opregion.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c index 7acbbbf97833..4534e4cadccf 100644 --- a/drivers/gpu/drm/i915/intel_opregion.c +++ b/drivers/gpu/drm/i915/intel_opregion.c @@ -1031,7 +1031,18 @@ int intel_opregion_setup(struct drm_i915_private *dev_priv) opregion->vbt_size = vbt_size; } else { vbt = base + OPREGION_VBT_OFFSET; - vbt_size = OPREGION_ASLE_EXT_OFFSET - OPREGION_VBT_OFFSET; + /* + * The VBT specification says that if the ASLE ext + * mailbox is not used its area is reserved, but + * on some CHT boards the VBT extends into the + * ASLE ext area. Allow this even though it is + * against the spec, so we do not end up rejecting + * the VBT on those boards (and end up not finding the + * LCD panel because of this). + */ + vbt_size = (mboxes & MBOX_ASLE_EXT) ? + OPREGION_ASLE_EXT_OFFSET : OPREGION_SIZE; + vbt_size -= OPREGION_VBT_OFFSET; if (intel_bios_is_valid_vbt(vbt, vbt_size)) { DRM_DEBUG_KMS("Found valid VBT in ACPI OpRegion (Mailbox #4)\n"); opregion->vbt = vbt; From 290215a2abfd9c0ede35dfc753439ef61cfd679b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 16 Jan 2017 12:06:09 +0100 Subject: [PATCH 57/64] libceph: use BUG() instead of BUG_ON(1) commit d24cdcd3e40a6825135498e11c20c7976b9bf545 upstream. I ran into this compile warning, which is the result of BUG_ON(1) not always leading to the compiler treating the code path as unreachable: include/linux/ceph/osdmap.h: In function 'ceph_can_shift_osds': include/linux/ceph/osdmap.h:62:1: error: control reaches end of non-void function [-Werror=return-type] Using BUG() here avoids the warning. Signed-off-by: Arnd Bergmann Signed-off-by: Ilya Dryomov Cc: Heinrich Schuchardt Signed-off-by: Greg Kroah-Hartman --- include/linux/ceph/osdmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 9a9041784dcf..412906609954 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -57,7 +57,7 @@ static inline bool ceph_can_shift_osds(struct ceph_pg_pool_info *pool) case CEPH_POOL_TYPE_EC: return false; default: - BUG_ON(1); + BUG(); } } From 91cdd9d79616ccea16e2e26fe329a15d226feb0b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 9 Mar 2017 16:16:42 -0800 Subject: [PATCH 58/64] x86, mm: fix gup_pte_range() vs DAX mappings commit ef947b2529f918d9606533eb9c32b187ed6a5ede upstream. gup_pte_range() fails to check pte_allows_gup() before translating a DAX pte entry, pte_devmap(), to a page. This allows writes to read-only mappings, and bypasses the DAX cacheline dirty tracking due to missed 'mkwrite' faults. The gup_huge_pmd() path and the gup_huge_pud() path correctly check pte_allows_gup() before checking for _devmap() entries. Fixes: 3565fce3a659 ("mm, x86: get_user_pages() for dax mappings") Link: http://lkml.kernel.org/r/148804251312.36605.12665024794196605053.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Ross Zwisler Signed-off-by: Dan Williams Reported-by: Dave Hansen Reported-by: Ross Zwisler Cc: Xiong Zhou Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/x86/mm/gup.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 0d4fb3ebbbac..1680768d392c 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -120,6 +120,11 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, return 0; } + if (!pte_allows_gup(pte_val(pte), write)) { + pte_unmap(ptep); + return 0; + } + if (pte_devmap(pte)) { pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); if (unlikely(!pgmap)) { @@ -127,8 +132,7 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, pte_unmap(ptep); return 0; } - } else if (!pte_allows_gup(pte_val(pte), write) || - pte_special(pte)) { + } else if (pte_special(pte)) { pte_unmap(ptep); return 0; } From 2f18b39499b23579a60e8ed1d2c0b56154388323 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 11 Mar 2017 01:31:19 +0100 Subject: [PATCH 59/64] x86/tlb: Fix tlb flushing when lguest clears PGE commit 2c4ea6e28dbf15ab93632c5c189f3948366b8885 upstream. Fengguang reported random corruptions from various locations on x86-32 after commits d2852a224050 ("arch: add ARCH_HAS_SET_MEMORY config") and 9d876e79df6a ("bpf: fix unlocking of jited image when module ronx not set") that uses the former. While x86-32 doesn't have a JIT like x86_64, the bpf_prog_lock_ro() and bpf_prog_unlock_ro() got enabled due to ARCH_HAS_SET_MEMORY, whereas Fengguang's test kernel doesn't have module support built in and therefore never had the DEBUG_SET_MODULE_RONX setting enabled. After investigating the crashes further, it turned out that using set_memory_ro() and set_memory_rw() didn't have the desired effect, for example, setting the pages as read-only on x86-32 would still let probe_kernel_write() succeed without error. This behavior would manifest itself in situations where the vmalloc'ed buffer was accessed prior to set_memory_*() such as in case of bpf_prog_alloc(). In cases where it wasn't, the page attribute changes seemed to have taken effect, leading to the conclusion that a TLB invalidate didn't happen. Moreover, it turned out that this issue reproduced with qemu in "-cpu kvm64" mode, but not for "-cpu host". When the issue occurs, change_page_attr_set_clr() did trigger a TLB flush as expected via __flush_tlb_all() through cpa_flush_range(), though. There are 3 variants for issuing a TLB flush: invpcid_flush_all() (depends on CPU feature bits X86_FEATURE_INVPCID, X86_FEATURE_PGE), cr4 based flush (depends on X86_FEATURE_PGE), and cr3 based flush. For "-cpu host" case in my setup, the flush used invpcid_flush_all() variant, whereas for "-cpu kvm64", the flush was cr4 based. Switching the kvm64 case to cr3 manually worked fine, and further investigating the cr4 one turned out that X86_CR4_PGE bit was not set in cr4 register, meaning the __native_flush_tlb_global_irq_disabled() wrote cr4 twice with the same value instead of clearing X86_CR4_PGE in the first write to trigger the flush. It turned out that X86_CR4_PGE was cleared from cr4 during init from lguest_arch_host_init() via adjust_pge(). The X86_FEATURE_PGE bit is also cleared from there due to concerns of using PGE in guest kernel that can lead to hard to trace bugs (see bff672e630a0 ("lguest: documentation V: Host") in init()). The CPU feature bits are cleared in dynamic boot_cpu_data, but they never propagated to __flush_tlb_all() as it uses static_cpu_has() instead of boot_cpu_has() for testing which variant of TLB flushing to use, meaning they still used the old setting of the host kernel. Clearing via setup_clear_cpu_cap(X86_FEATURE_PGE) so this would propagate to static_cpu_has() checks is too late at this point as sections have been patched already, so for now, it seems reasonable to switch back to boot_cpu_has(X86_FEATURE_PGE) as it was prior to commit c109bf95992b ("x86/cpufeature: Remove cpu_has_pge"). This lets the TLB flush trigger via cr3 as originally intended, properly makes the new page attributes visible and thus fixes the crashes seen by Fengguang. Fixes: c109bf95992b ("x86/cpufeature: Remove cpu_has_pge") Reported-by: Fengguang Wu Signed-off-by: Daniel Borkmann Cc: bp@suse.de Cc: Kees Cook Cc: "David S. Miller" Cc: netdev@vger.kernel.org Cc: Rusty Russell Cc: Alexei Starovoitov Cc: Linus Torvalds Cc: lkp@01.org Cc: Laura Abbott Link: http://lkml.kernrl.org/r/20170301125426.l4nf65rx4wahohyl@wfg-t540p.sh.intel.com Link: http://lkml.kernel.org/r/25c41ad9eca164be4db9ad84f768965b7eb19d9e.1489191673.git.daniel@iogearbox.net Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/tlbflush.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 6fa85944af83..fc5abff9b7fd 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -188,7 +188,7 @@ static inline void __native_flush_tlb_single(unsigned long addr) static inline void __flush_tlb_all(void) { - if (static_cpu_has(X86_FEATURE_PGE)) + if (boot_cpu_has(X86_FEATURE_PGE)) __flush_tlb_global(); else __flush_tlb(); From 1771fc58a35d6c61861c08a190ecf13cd70a38eb Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 9 Mar 2017 16:17:23 -0800 Subject: [PATCH 60/64] thp: fix another corner case of munlock() vs. THPs commit 6ebb4a1b848fe75323135f93e72c78f8780fd268 upstream. The following test case triggers BUG() in munlock_vma_pages_range(): int main(int argc, char *argv[]) { int fd; system("mount -t tmpfs -o huge=always none /mnt"); fd = open("/mnt/test", O_CREAT | O_RDWR); ftruncate(fd, 4UL << 20); mmap(NULL, 4UL << 20, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_FIXED | MAP_LOCKED, fd, 0); mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_LOCKED, fd, 0); munlockall(); return 0; } The second mmap() create PTE-mapping of the first huge page in file. It makes kernel munlock the page as we never keep PTE-mapped page mlocked. On munlockall() when we handle vma created by the first mmap(), munlock_vma_page() returns page_mask == 0, as the page is not mlocked anymore. On next iteration follow_page_mask() return tail page, but page_mask is HPAGE_NR_PAGES - 1. It makes us skip to the first tail page of the next huge page and step on VM_BUG_ON_PAGE(PageMlocked(page)). The fix is not use the page_mask from follow_page_mask() at all. It has no use for us. Link: http://lkml.kernel.org/r/20170302150252.34120-1-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/mlock.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/mm/mlock.c b/mm/mlock.c index cdbed8aaa426..665ab75b5533 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -441,7 +441,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, while (start < end) { struct page *page; - unsigned int page_mask; + unsigned int page_mask = 0; unsigned long page_increm; struct pagevec pvec; struct zone *zone; @@ -455,8 +455,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, * suits munlock very well (and if somehow an abnormal page * has sneaked into the range, we won't oops here: great). */ - page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP, - &page_mask); + page = follow_page(vma, start, FOLL_GET | FOLL_DUMP); if (page && !IS_ERR(page)) { if (PageTransTail(page)) { @@ -467,8 +466,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, /* * Any THP page found by follow_page_mask() may * have gotten split before reaching - * munlock_vma_page(), so we need to recompute - * the page_mask here. + * munlock_vma_page(), so we need to compute + * the page_mask here instead. */ page_mask = munlock_vma_page(page); unlock_page(page); From 16ace91043bf5fa192bb6e42451524b3c6ad7bd7 Mon Sep 17 00:00:00 2001 From: Tahsin Erdogan Date: Thu, 9 Mar 2017 16:17:26 -0800 Subject: [PATCH 61/64] mm: do not call mem_cgroup_free() from within mem_cgroup_alloc() commit 40e952f9d687928b32db20226f085ae660a7237c upstream. mem_cgroup_free() indirectly calls wb_domain_exit() which is not prepared to deal with a struct wb_domain object that hasn't executed wb_domain_init(). For instance, the following warning message is printed by lockdep if alloc_percpu() fails in mem_cgroup_alloc(): INFO: trying to register non-static key. the code is fine but needs lockdep annotation. turning off the locking correctness validator. CPU: 1 PID: 1950 Comm: mkdir Not tainted 4.10.0+ #151 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x67/0x99 register_lock_class+0x36d/0x540 __lock_acquire+0x7f/0x1a30 lock_acquire+0xcc/0x200 del_timer_sync+0x3c/0xc0 wb_domain_exit+0x14/0x20 mem_cgroup_free+0x14/0x40 mem_cgroup_css_alloc+0x3f9/0x620 cgroup_apply_control_enable+0x190/0x390 cgroup_mkdir+0x290/0x3d0 kernfs_iop_mkdir+0x58/0x80 vfs_mkdir+0x10e/0x1a0 SyS_mkdirat+0xa8/0xd0 SyS_mkdir+0x14/0x20 entry_SYSCALL_64_fastpath+0x18/0xad Add __mem_cgroup_free() which skips wb_domain_exit(). This is used by both mem_cgroup_free() and mem_cgroup_alloc() clean up. Fixes: 0b8f73e104285 ("mm: memcontrol: clean up alloc, online, offline, free functions") Link: http://lkml.kernel.org/r/20170306192122.24262-1-tahsin@google.com Signed-off-by: Tahsin Erdogan Acked-by: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/memcontrol.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4c6ade54d833..0de26691f0f5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4139,17 +4139,22 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) kfree(memcg->nodeinfo[node]); } -static void mem_cgroup_free(struct mem_cgroup *memcg) +static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; - memcg_wb_domain_exit(memcg); for_each_node(node) free_mem_cgroup_per_node_info(memcg, node); free_percpu(memcg->stat); kfree(memcg); } +static void mem_cgroup_free(struct mem_cgroup *memcg) +{ + memcg_wb_domain_exit(memcg); + __mem_cgroup_free(memcg); +} + static struct mem_cgroup *mem_cgroup_alloc(void) { struct mem_cgroup *memcg; @@ -4200,7 +4205,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) fail: if (memcg->id.id > 0) idr_remove(&mem_cgroup_idr, memcg->id.id); - mem_cgroup_free(memcg); + __mem_cgroup_free(memcg); return NULL; } From 63e873679ba99649bf22cc7b964315591cedf4c5 Mon Sep 17 00:00:00 2001 From: OGAWA Hirofumi Date: Thu, 9 Mar 2017 16:17:37 -0800 Subject: [PATCH 62/64] fat: fix using uninitialized fields of fat_inode/fsinfo_inode commit c0d0e351285161a515396b7b1ee53ec9ffd97e3c upstream. Recently fallocate patch was merged and it uses MSDOS_I(inode)->mmu_private at fat_evict_inode(). However, fat_inode/fsinfo_inode that was introduced in past didn't initialize MSDOS_I(inode) properly. With those combinations, it became the cause of accessing random entry in FAT area. Link: http://lkml.kernel.org/r/87pohrj4i8.fsf@mail.parknet.co.jp Signed-off-by: OGAWA Hirofumi Reported-by: Moreno Bartalucci Tested-by: Moreno Bartalucci Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/fat/inode.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 338d2f73eb29..a2c05f2ada6d 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1359,6 +1359,16 @@ out: return 0; } +static void fat_dummy_inode_init(struct inode *inode) +{ + /* Initialize this dummy inode to work as no-op. */ + MSDOS_I(inode)->mmu_private = 0; + MSDOS_I(inode)->i_start = 0; + MSDOS_I(inode)->i_logstart = 0; + MSDOS_I(inode)->i_attrs = 0; + MSDOS_I(inode)->i_pos = 0; +} + static int fat_read_root(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); @@ -1803,12 +1813,13 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, fat_inode = new_inode(sb); if (!fat_inode) goto out_fail; - MSDOS_I(fat_inode)->i_pos = 0; + fat_dummy_inode_init(fat_inode); sbi->fat_inode = fat_inode; fsinfo_inode = new_inode(sb); if (!fsinfo_inode) goto out_fail; + fat_dummy_inode_init(fsinfo_inode); fsinfo_inode->i_ino = MSDOS_FSINFO_INO; sbi->fsinfo_inode = fsinfo_inode; insert_inode_hash(fsinfo_inode); From 182ff0ebbdab926578728784299cc9d9c195d515 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Wed, 8 Feb 2017 18:30:56 -0700 Subject: [PATCH 63/64] drivers: hv: Turn off write permission on the hypercall page commit 372b1e91343e657a7cc5e2e2bcecd5140ac28119 upstream. The hypercall page only needs to be executable but currently it is setup to be writable as well. Fix the issue. Signed-off-by: K. Y. Srinivasan Acked-by: Kees Cook Reported-by: Stephen Hemminger Tested-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- drivers/hv/hv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 6e49a4dd99c0..e0a8216ecf2b 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -220,7 +220,7 @@ int hv_init(void) /* See if the hypercall page is already set */ rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); - virtaddr = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_EXEC); + virtaddr = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX); if (!virtaddr) goto cleanup; From d962bf8dd954db6db513b42cc484a9528df3e5a3 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 15 Mar 2017 10:03:13 +0800 Subject: [PATCH 64/64] Linux 4.9.15 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 5e7706e94622..03df4fcacdf2 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 9 -SUBLEVEL = 14 +SUBLEVEL = 15 EXTRAVERSION = NAME = Roaring Lionus