From a3622b6d5f83a6088298515fd1fdfc9b75450f4e Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Thu, 7 Nov 2019 09:48:01 +0100 Subject: [PATCH 01/93] CDC-NCM: handle incomplete transfer of MTU [ Upstream commit 332f989a3b0041b810836c5c3747e59aad7e9d0b ] A malicious device may give half an answer when asked for its MTU. The driver will proceed after this with a garbage MTU. Anything but a complete answer must be treated as an error. V2: used sizeof as request by Alexander Reported-and-tested-by: syzbot+0631d878823ce2411636@syzkaller.appspotmail.com Signed-off-by: Oliver Neukum Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/usb/cdc_ncm.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 43e28d2b0de7..cbb9b4343d1e 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -576,8 +576,8 @@ static void cdc_ncm_set_dgram_size(struct usbnet *dev, int new_size) /* read current mtu value from device */ err = usbnet_read_cmd(dev, USB_CDC_GET_MAX_DATAGRAM_SIZE, USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE, - 0, iface_no, &max_datagram_size, 2); - if (err < 0) { + 0, iface_no, &max_datagram_size, sizeof(max_datagram_size)); + if (err < sizeof(max_datagram_size)) { dev_dbg(&dev->intf->dev, "GET_MAX_DATAGRAM_SIZE failed\n"); goto out; } @@ -588,7 +588,7 @@ static void cdc_ncm_set_dgram_size(struct usbnet *dev, int new_size) max_datagram_size = cpu_to_le16(ctx->max_datagram_size); err = usbnet_write_cmd(dev, USB_CDC_SET_MAX_DATAGRAM_SIZE, USB_TYPE_CLASS | USB_DIR_OUT | USB_RECIP_INTERFACE, - 0, iface_no, &max_datagram_size, 2); + 0, iface_no, &max_datagram_size, sizeof(max_datagram_size)); if (err < 0) dev_dbg(&dev->intf->dev, "SET_MAX_DATAGRAM_SIZE failed\n"); From ed9acfe27588dd883a29d2564c87fecd1fd1cb24 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 7 Nov 2019 18:29:52 +0000 Subject: [PATCH 02/93] ipv4: Fix table id reference in fib_sync_down_addr [ Upstream commit e0a312629fefa943534fc46f7bfbe6de3fdaf463 ] Hendrik reported routes in the main table using source address are not removed when the address is removed. The problem is that fib_sync_down_addr does not account for devices in the default VRF which are associated with the main table. Fix by updating the table id reference. Fixes: 5a56a0b3a45d ("net: Don't delete routes in different VRFs") Reported-by: Hendrik Donner Signed-off-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/fib_semantics.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 90c654012510..6aec95e1fc13 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1358,8 +1358,8 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local) int ret = 0; unsigned int hash = fib_laddr_hashfn(local); struct hlist_head *head = &fib_info_laddrhash[hash]; + int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; struct net *net = dev_net(dev); - int tb_id = l3mdev_fib_table(dev); struct fib_info *fi; if (!fib_info_laddrhash || local == 0) From a723c971b1f7fb96f2553e020565d19dc2ef54e0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Nov 2019 20:08:19 -0800 Subject: [PATCH 03/93] net: fix data-race in neigh_event_send() [ Upstream commit 1b53d64435d56902fc234ff2507142d971a09687 ] KCSAN reported the following data-race [1] The fix will also prevent the compiler from optimizing out the condition. [1] BUG: KCSAN: data-race in neigh_resolve_output / neigh_resolve_output write to 0xffff8880a41dba78 of 8 bytes by interrupt on cpu 1: neigh_event_send include/net/neighbour.h:443 [inline] neigh_resolve_output+0x78/0x480 net/core/neighbour.c:1474 neigh_output include/net/neighbour.h:511 [inline] ip_finish_output2+0x4af/0xe40 net/ipv4/ip_output.c:228 __ip_finish_output net/ipv4/ip_output.c:308 [inline] __ip_finish_output+0x23a/0x490 net/ipv4/ip_output.c:290 ip_finish_output+0x41/0x160 net/ipv4/ip_output.c:318 NF_HOOK_COND include/linux/netfilter.h:294 [inline] ip_output+0xdf/0x210 net/ipv4/ip_output.c:432 dst_output include/net/dst.h:436 [inline] ip_local_out+0x74/0x90 net/ipv4/ip_output.c:125 __ip_queue_xmit+0x3a8/0xa40 net/ipv4/ip_output.c:532 ip_queue_xmit+0x45/0x60 include/net/ip.h:237 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169 tcp_transmit_skb net/ipv4/tcp_output.c:1185 [inline] __tcp_retransmit_skb+0x4bd/0x15f0 net/ipv4/tcp_output.c:2976 tcp_retransmit_skb+0x36/0x1a0 net/ipv4/tcp_output.c:2999 tcp_retransmit_timer+0x719/0x16d0 net/ipv4/tcp_timer.c:515 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:598 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:618 read to 0xffff8880a41dba78 of 8 bytes by interrupt on cpu 0: neigh_event_send include/net/neighbour.h:442 [inline] neigh_resolve_output+0x57/0x480 net/core/neighbour.c:1474 neigh_output include/net/neighbour.h:511 [inline] ip_finish_output2+0x4af/0xe40 net/ipv4/ip_output.c:228 __ip_finish_output net/ipv4/ip_output.c:308 [inline] __ip_finish_output+0x23a/0x490 net/ipv4/ip_output.c:290 ip_finish_output+0x41/0x160 net/ipv4/ip_output.c:318 NF_HOOK_COND include/linux/netfilter.h:294 [inline] ip_output+0xdf/0x210 net/ipv4/ip_output.c:432 dst_output include/net/dst.h:436 [inline] ip_local_out+0x74/0x90 net/ipv4/ip_output.c:125 __ip_queue_xmit+0x3a8/0xa40 net/ipv4/ip_output.c:532 ip_queue_xmit+0x45/0x60 include/net/ip.h:237 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169 tcp_transmit_skb net/ipv4/tcp_output.c:1185 [inline] __tcp_retransmit_skb+0x4bd/0x15f0 net/ipv4/tcp_output.c:2976 tcp_retransmit_skb+0x36/0x1a0 net/ipv4/tcp_output.c:2999 tcp_retransmit_timer+0x719/0x16d0 net/ipv4/tcp_timer.c:515 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:598 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/neighbour.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index f6017ddc4ded..1c0d07376125 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -425,8 +425,8 @@ static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) { unsigned long now = jiffies; - if (neigh->used != now) - neigh->used = now; + if (READ_ONCE(neigh->used) != now) + WRITE_ONCE(neigh->used, now); if (!(neigh->nud_state&(NUD_CONNECTED|NUD_DELAY|NUD_PROBE))) return __neigh_event_send(neigh, skb); return 0; From 17ac2bde66ce95e0f8a9ccb4bb0164fdf8b699b7 Mon Sep 17 00:00:00 2001 From: Aleksander Morgado Date: Thu, 7 Nov 2019 11:57:01 +0100 Subject: [PATCH 04/93] net: usb: qmi_wwan: add support for DW5821e with eSIM support [ Upstream commit e497df686e8fed8c1dd69179010656362858edb3 ] Exactly same layout as the default DW5821e module, just a different vid/pid. The QMI interface is exposed in USB configuration #1: P: Vendor=413c ProdID=81e0 Rev=03.18 S: Manufacturer=Dell Inc. S: Product=DW5821e-eSIM Snapdragon X20 LTE S: SerialNumber=0123456789ABCDEF C: #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#=0x0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I: If#=0x1 Alt= 0 #EPs= 1 Cls=03(HID ) Sub=00 Prot=00 Driver=usbhid I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option Signed-off-by: Aleksander Morgado Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 0d48714c3f28..de7b431fdd6b 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -951,6 +951,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */ + {QMI_FIXED_INTF(0x413c, 0x81e0, 0)}, /* Dell Wireless 5821e with eSIM support*/ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ From 6134e4fc1f4839020607cef76ab3dadf157caf73 Mon Sep 17 00:00:00 2001 From: Pan Bian Date: Tue, 5 Nov 2019 16:34:07 +0800 Subject: [PATCH 05/93] NFC: fdp: fix incorrect free object [ Upstream commit 517ce4e93368938b204451285e53014549804868 ] The address of fw_vsc_cfg is on stack. Releasing it with devm_kfree() is incorrect, which may result in a system crash or other security impacts. The expected object to free is *fw_vsc_cfg. Signed-off-by: Pan Bian Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/nfc/fdp/i2c.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c index 712936f5d2d6..f1addfd7b31a 100644 --- a/drivers/nfc/fdp/i2c.c +++ b/drivers/nfc/fdp/i2c.c @@ -268,7 +268,7 @@ static void fdp_nci_i2c_read_device_properties(struct device *dev, *fw_vsc_cfg, len); if (r) { - devm_kfree(dev, fw_vsc_cfg); + devm_kfree(dev, *fw_vsc_cfg); goto vsc_read_err; } } else { From 8a0a54313cc9f3a143ad64a2790e9f86adbcfe8b Mon Sep 17 00:00:00 2001 From: Pan Bian Date: Thu, 7 Nov 2019 14:29:50 +0800 Subject: [PATCH 06/93] nfc: netlink: fix double device reference drop [ Upstream commit 025ec40b81d785a98f76b8bdb509ac10773b4f12 ] The function nfc_put_device(dev) is called twice to drop the reference to dev when there is no associated local llcp. Remove one of them to fix the bug. Fixes: 52feb444a903 ("NFC: Extend netlink interface for LTO, RW, and MIUX parameters support") Fixes: d9b8d8e19b07 ("NFC: llcp: Service Name Lookup netlink interface") Signed-off-by: Pan Bian Reviewed-by: Johan Hovold Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/nfc/netlink.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index ad878302924f..d3c8dd5dc817 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1103,7 +1103,6 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) local = nfc_llcp_find_local(dev); if (!local) { - nfc_put_device(dev); rc = -ENODEV; goto exit; } @@ -1163,7 +1162,6 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) local = nfc_llcp_find_local(dev); if (!local) { - nfc_put_device(dev); rc = -ENODEV; goto exit; } From 79049c11e38a816c2d620f11e3ad3c6b909907ba Mon Sep 17 00:00:00 2001 From: Pan Bian Date: Thu, 7 Nov 2019 09:33:20 +0800 Subject: [PATCH 07/93] NFC: st21nfca: fix double free [ Upstream commit 99a8efbb6e30b72ac98cecf81103f847abffb1e5 ] The variable nfcid_skb is not changed in the callee nfc_hci_get_param() if error occurs. Consequently, the freed variable nfcid_skb will be freed again, resulting in a double free bug. Set nfcid_skb to NULL after releasing it to fix the bug. Signed-off-by: Pan Bian Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/nfc/st21nfca/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nfc/st21nfca/core.c b/drivers/nfc/st21nfca/core.c index dacb9166081b..2f08e16ba566 100644 --- a/drivers/nfc/st21nfca/core.c +++ b/drivers/nfc/st21nfca/core.c @@ -719,6 +719,7 @@ static int st21nfca_hci_complete_target_discovered(struct nfc_hci_dev *hdev, NFC_PROTO_FELICA_MASK; } else { kfree_skb(nfcid_skb); + nfcid_skb = NULL; /* P2P in type A */ r = nfc_hci_get_param(hdev, ST21NFCA_RF_READER_F_GATE, ST21NFCA_RF_READER_F_NFCID1, From 3e68866fcb4dcb81180f6f231f85c020fd8ff5ef Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Fri, 8 Nov 2019 02:42:30 -0800 Subject: [PATCH 08/93] qede: fix NULL pointer deref in __qede_remove() [ Upstream commit deabc87111c690097c03765ea017cd500f7376fc ] While rebooting the system with SR-IOV vfs enabled leads to below crash due to recurrence of __qede_remove() on the VF devices (first from .shutdown() flow of the VF itself and another from PF's .shutdown() flow executing pci_disable_sriov()) This patch adds a safeguard in __qede_remove() flow to fix this, so that driver doesn't attempt to remove "already removed" devices. [ 194.360134] BUG: unable to handle kernel NULL pointer dereference at 00000000000008dc [ 194.360227] IP: [] __qede_remove+0x24/0x130 [qede] [ 194.360304] PGD 0 [ 194.360325] Oops: 0000 [#1] SMP [ 194.360360] Modules linked in: tcp_lp fuse tun bridge stp llc devlink bonding ip_set nfnetlink ib_isert iscsi_target_mod ib_srpt target_core_mod ib_srp scsi_transport_srp scsi_tgt ib_ipoib ib_umad rpcrdma sunrpc rdma_ucm ib_uverbs ib_iser rdma_cm iw_cm ib_cm libiscsi scsi_transport_iscsi dell_smbios iTCO_wdt iTCO_vendor_support dell_wmi_descriptor dcdbas vfat fat pcc_cpufreq skx_edac intel_powerclamp coretemp intel_rapl iosf_mbi kvm_intel kvm irqbypass crc32_pclmul ghash_clmulni_intel aesni_intel lrw gf128mul glue_helper ablk_helper cryptd qedr ib_core pcspkr ses enclosure joydev ipmi_ssif sg i2c_i801 lpc_ich mei_me mei wmi ipmi_si ipmi_devintf ipmi_msghandler tpm_crb acpi_pad acpi_power_meter xfs libcrc32c sd_mod crc_t10dif crct10dif_generic crct10dif_pclmul crct10dif_common crc32c_intel mgag200 [ 194.361044] qede i2c_algo_bit drm_kms_helper qed syscopyarea sysfillrect nvme sysimgblt fb_sys_fops ttm nvme_core mpt3sas crc8 ptp drm pps_core ahci raid_class scsi_transport_sas libahci libata drm_panel_orientation_quirks nfit libnvdimm dm_mirror dm_region_hash dm_log dm_mod [last unloaded: ip_tables] [ 194.361297] CPU: 51 PID: 7996 Comm: reboot Kdump: loaded Not tainted 3.10.0-1062.el7.x86_64 #1 [ 194.361359] Hardware name: Dell Inc. PowerEdge MX840c/0740HW, BIOS 2.4.6 10/15/2019 [ 194.361412] task: ffff9cea9b360000 ti: ffff9ceabebdc000 task.ti: ffff9ceabebdc000 [ 194.361463] RIP: 0010:[] [] __qede_remove+0x24/0x130 [qede] [ 194.361534] RSP: 0018:ffff9ceabebdfac0 EFLAGS: 00010282 [ 194.361570] RAX: 0000000000000000 RBX: ffff9cd013846098 RCX: 0000000000000000 [ 194.361621] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff9cd013846098 [ 194.361668] RBP: ffff9ceabebdfae8 R08: 0000000000000000 R09: 0000000000000000 [ 194.361715] R10: 00000000bfe14201 R11: ffff9ceabfe141e0 R12: 0000000000000000 [ 194.361762] R13: ffff9cd013846098 R14: 0000000000000000 R15: ffff9ceab5e48000 [ 194.361810] FS: 00007f799c02d880(0000) GS:ffff9ceacb0c0000(0000) knlGS:0000000000000000 [ 194.361865] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 194.361903] CR2: 00000000000008dc CR3: 0000001bdac76000 CR4: 00000000007607e0 [ 194.361953] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 194.362002] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 194.362051] PKRU: 55555554 [ 194.362073] Call Trace: [ 194.362109] [] qede_remove+0x10/0x20 [qede] [ 194.362180] [] pci_device_remove+0x3e/0xc0 [ 194.362240] [] __device_release_driver+0x82/0xf0 [ 194.362285] [] device_release_driver+0x23/0x30 [ 194.362343] [] pci_stop_bus_device+0x84/0xa0 [ 194.362388] [] pci_stop_and_remove_bus_device+0x12/0x20 [ 194.362450] [] pci_iov_remove_virtfn+0xaf/0x160 [ 194.362496] [] sriov_disable+0x3c/0xf0 [ 194.362534] [] pci_disable_sriov+0x23/0x30 [ 194.362599] [] qed_sriov_disable+0x5e3/0x650 [qed] [ 194.362658] [] ? kfree+0x106/0x140 [ 194.362709] [] ? qed_free_stream_mem+0x70/0x90 [qed] [ 194.362754] [] ? kfree+0x106/0x140 [ 194.362803] [] qed_slowpath_stop+0x1a9/0x1d0 [qed] [ 194.362854] [] __qede_remove+0xae/0x130 [qede] [ 194.362904] [] qede_shutdown+0x10/0x20 [qede] [ 194.362956] [] pci_device_shutdown+0x3a/0x60 [ 194.363010] [] device_shutdown+0xfb/0x1f0 [ 194.363066] [] kernel_restart_prepare+0x36/0x40 [ 194.363107] [] kernel_restart+0x12/0x60 [ 194.363146] [] SYSC_reboot+0x229/0x260 [ 194.363196] [] ? handle_mm_fault+0x39d/0x9b0 [ 194.363253] [] ? __switch_to+0x151/0x580 [ 194.363304] [] ? __schedule+0x448/0x9c0 [ 194.363343] [] SyS_reboot+0xe/0x10 [ 194.363387] [] system_call_fastpath+0x25/0x2a [ 194.363430] Code: f9 e9 37 ff ff ff 90 0f 1f 44 00 00 55 48 89 e5 41 57 41 56 41 55 4c 8d af 98 00 00 00 41 54 4c 89 ef 41 89 f4 53 e8 4c e4 55 f9 <80> b8 dc 08 00 00 01 48 89 c3 4c 8d b8 c0 08 00 00 4c 8b b0 c0 [ 194.363712] RIP [] __qede_remove+0x24/0x130 [qede] [ 194.363764] RSP [ 194.363791] CR2: 00000000000008dc Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: Sudarsana Kalluru Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/qlogic/qede/qede_main.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 85f46dbecd5b..9b1920b58594 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -2619,8 +2619,16 @@ enum qede_remove_mode { static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode) { struct net_device *ndev = pci_get_drvdata(pdev); - struct qede_dev *edev = netdev_priv(ndev); - struct qed_dev *cdev = edev->cdev; + struct qede_dev *edev; + struct qed_dev *cdev; + + if (!ndev) { + dev_info(&pdev->dev, "Device has already been removed\n"); + return; + } + + edev = netdev_priv(ndev); + cdev = edev->cdev; DP_INFO(edev, "Starting qede_remove\n"); From 8bdaac0c926f7dc65a60ef756740ef2353e4f54f Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 6 Nov 2019 17:55:47 +0100 Subject: [PATCH 09/93] ALSA: timer: Fix incorrectly assigned timer instance commit e7af6307a8a54f0b873960b32b6a644f2d0fbd97 upstream. The clean up commit 41672c0c24a6 ("ALSA: timer: Simplify error path in snd_timer_open()") unified the error handling code paths with the standard goto, but it introduced a subtle bug: the timer instance is stored in snd_timer_open() incorrectly even if it returns an error. This may eventually lead to UAF, as spotted by fuzzer. The culprit is the snd_timer_open() code checks the SNDRV_TIMER_IFLG_EXCLUSIVE flag with the common variable timeri. This variable is supposed to be the newly created instance, but we (ab-)used it for a temporary check before the actual creation of a timer instance. After that point, there is another check for the max number of instances, and it bails out if over the threshold. Before the refactoring above, it worked fine because the code returned directly from that point. After the refactoring, however, it jumps to the unified error path that stores the timeri variable in return -- even if it returns an error. Unfortunately this stored value is kept in the caller side (snd_timer_user_tselect()) in tu->timeri. This causes inconsistency later, as if the timer was successfully assigned. In this patch, we fix it by not re-using timeri variable but a temporary variable for testing the exclusive connection, so timeri remains NULL at that point. Fixes: 41672c0c24a6 ("ALSA: timer: Simplify error path in snd_timer_open()") Reported-and-tested-by: Tristan Madani Cc: Link: https://lore.kernel.org/r/20191106165547.23518-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/timer.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/sound/core/timer.c b/sound/core/timer.c index 19d90aa08218..e944d27f79c3 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -297,11 +297,11 @@ int snd_timer_open(struct snd_timer_instance **ti, goto unlock; } if (!list_empty(&timer->open_list_head)) { - timeri = list_entry(timer->open_list_head.next, + struct snd_timer_instance *t = + list_entry(timer->open_list_head.next, struct snd_timer_instance, open_list); - if (timeri->flags & SNDRV_TIMER_IFLG_EXCLUSIVE) { + if (t->flags & SNDRV_TIMER_IFLG_EXCLUSIVE) { err = -EBUSY; - timeri = NULL; goto unlock; } } From ce8b4a95c86eec527a1056a013dc5379ba3122cf Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Sun, 3 Nov 2019 00:09:20 +0900 Subject: [PATCH 10/93] ALSA: bebob: fix to detect configured source of sampling clock for Focusrite Saffire Pro i/o series commit 706ad6746a66546daf96d4e4a95e46faf6cf689a upstream. For Focusrite Saffire Pro i/o, the lowest 8 bits of register represents configured source of sampling clock. The next lowest 8 bits represents whether the configured source is actually detected or not just after the register is changed for the source. Current implementation evaluates whole the register to detect configured source. This results in failure due to the next lowest 8 bits when the source is connected in advance. This commit fixes the bug. Fixes: 25784ec2d034 ("ALSA: bebob: Add support for Focusrite Saffire/SaffirePro series") Cc: # v3.16+ Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20191102150920.20367-1-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/firewire/bebob/bebob_focusrite.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/firewire/bebob/bebob_focusrite.c b/sound/firewire/bebob/bebob_focusrite.c index f11090057949..d0a8736613a1 100644 --- a/sound/firewire/bebob/bebob_focusrite.c +++ b/sound/firewire/bebob/bebob_focusrite.c @@ -28,6 +28,8 @@ #define SAFFIRE_CLOCK_SOURCE_SPDIF 1 /* clock sources as returned from register of Saffire Pro 10 and 26 */ +#define SAFFIREPRO_CLOCK_SOURCE_SELECT_MASK 0x000000ff +#define SAFFIREPRO_CLOCK_SOURCE_DETECT_MASK 0x0000ff00 #define SAFFIREPRO_CLOCK_SOURCE_INTERNAL 0 #define SAFFIREPRO_CLOCK_SOURCE_SKIP 1 /* never used on hardware */ #define SAFFIREPRO_CLOCK_SOURCE_SPDIF 2 @@ -190,6 +192,7 @@ saffirepro_both_clk_src_get(struct snd_bebob *bebob, unsigned int *id) map = saffirepro_clk_maps[1]; /* In a case that this driver cannot handle the value of register. */ + value &= SAFFIREPRO_CLOCK_SOURCE_SELECT_MASK; if (value >= SAFFIREPRO_CLOCK_SOURCE_COUNT || map[value] < 0) { err = -EIO; goto end; From 1125e871d61a10a304e4a61569df6810aeda0c73 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 5 Nov 2019 14:43:16 +0100 Subject: [PATCH 11/93] ALSA: hda/ca0132 - Fix possible workqueue stall commit 15c2b3cc09a31620914955cb2a89c277c18ee999 upstream. The unsolicited event handler for the headphone jack on CA0132 codec driver tries to reschedule the another delayed work with cancel_delayed_work_sync(). It's no good idea, unfortunately, especially after we changed the work queue to the standard global one; this may lead to a stall because both works are using the same global queue. Fix it by dropping the _sync but does call cancel_delayed_work() instead. Fixes: 993884f6a26c ("ALSA: hda/ca0132 - Delay HP amp turnon.") BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1155836 Cc: Link: https://lore.kernel.org/r/20191105134316.19294-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_ca0132.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 280999961226..475b2c6c43d6 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -4440,7 +4440,7 @@ static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb) /* Delay enabling the HP amp, to let the mic-detection * state machine run. */ - cancel_delayed_work_sync(&spec->unsol_hp_work); + cancel_delayed_work(&spec->unsol_hp_work); schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); tbl = snd_hda_jack_tbl_get(codec, cb->nid); if (tbl) From 967fcde64f209b8f87ee320ffe0c9974ed1fc68d Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Tue, 5 Nov 2019 21:16:30 -0800 Subject: [PATCH 12/93] mm: thp: handle page cache THP correctly in PageTransCompoundMap commit 169226f7e0d275c1879551f37484ef6683579a5c upstream. We have a usecase to use tmpfs as QEMU memory backend and we would like to take the advantage of THP as well. But, our test shows the EPT is not PMD mapped even though the underlying THP are PMD mapped on host. The number showed by /sys/kernel/debug/kvm/largepage is much less than the number of PMD mapped shmem pages as the below: 7f2778200000-7f2878200000 rw-s 00000000 00:14 262232 /dev/shm/qemu_back_mem.mem.Hz2hSf (deleted) Size: 4194304 kB [snip] AnonHugePages: 0 kB ShmemPmdMapped: 579584 kB [snip] Locked: 0 kB cat /sys/kernel/debug/kvm/largepages 12 And some benchmarks do worse than with anonymous THPs. By digging into the code we figured out that commit 127393fbe597 ("mm: thp: kvm: fix memory corruption in KVM with THP enabled") checks if there is a single PTE mapping on the page for anonymous THP when setting up EPT map. But the _mapcount < 0 check doesn't work for page cache THP since every subpage of page cache THP would get _mapcount inc'ed once it is PMD mapped, so PageTransCompoundMap() always returns false for page cache THP. This would prevent KVM from setting up PMD mapped EPT entry. So we need handle page cache THP correctly. However, when page cache THP's PMD gets split, kernel just remove the map instead of setting up PTE map like what anonymous THP does. Before KVM calls get_user_pages() the subpages may get PTE mapped even though it is still a THP since the page cache THP may be mapped by other processes at the mean time. Checking its _mapcount and whether the THP has PTE mapped or not. Although this may report some false negative cases (PTE mapped by other processes), it looks not trivial to make this accurate. With this fix /sys/kernel/debug/kvm/largepage would show reasonable pages are PMD mapped by EPT as the below: 7fbeaee00000-7fbfaee00000 rw-s 00000000 00:14 275464 /dev/shm/qemu_back_mem.mem.SKUvat (deleted) Size: 4194304 kB [snip] AnonHugePages: 0 kB ShmemPmdMapped: 557056 kB [snip] Locked: 0 kB cat /sys/kernel/debug/kvm/largepages 271 And the benchmarks are as same as anonymous THPs. [yang.shi@linux.alibaba.com: v4] Link: http://lkml.kernel.org/r/1571865575-42913-1-git-send-email-yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/1571769577-89735-1-git-send-email-yang.shi@linux.alibaba.com Fixes: dd78fedde4b9 ("rmap: support file thp") Signed-off-by: Yang Shi Reported-by: Gang Deng Tested-by: Gang Deng Suggested-by: Hugh Dickins Acked-by: Kirill A. Shutemov Cc: Andrea Arcangeli Cc: Matthew Wilcox Cc: [4.8+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/mm.h | 5 ----- include/linux/mm_types.h | 5 +++++ include/linux/page-flags.h | 20 ++++++++++++++++++-- 3 files changed, 23 insertions(+), 7 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index ade072a6fd24..ca6f213fa4f0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -504,11 +504,6 @@ static inline int is_vmalloc_or_module_addr(const void *x) extern void kvfree(const void *addr); -static inline atomic_t *compound_mapcount_ptr(struct page *page) -{ - return &page[1].compound_mapcount; -} - static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8d6decd50220..21b18b755c0e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -262,6 +262,11 @@ struct page_frag_cache { typedef unsigned long vm_flags_t; +static inline atomic_t *compound_mapcount_ptr(struct page *page) +{ + return &page[1].compound_mapcount; +} + /* * A region containing a mapping of a non-memory backed file under NOMMU * conditions. These are held in a global tree and are pinned by the VMAs that diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 74e4dda91238..896e4199623a 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -545,12 +545,28 @@ static inline int PageTransCompound(struct page *page) * * Unlike PageTransCompound, this is safe to be called only while * split_huge_pmd() cannot run from under us, like if protected by the - * MMU notifier, otherwise it may result in page->_mapcount < 0 false + * MMU notifier, otherwise it may result in page->_mapcount check false * positives. + * + * We have to treat page cache THP differently since every subpage of it + * would get _mapcount inc'ed once it is PMD mapped. But, it may be PTE + * mapped in the current process so comparing subpage's _mapcount to + * compound_mapcount to filter out PTE mapped case. */ static inline int PageTransCompoundMap(struct page *page) { - return PageTransCompound(page) && atomic_read(&page->_mapcount) < 0; + struct page *head; + + if (!PageTransCompound(page)) + return 0; + + if (PageAnon(page)) + return atomic_read(&page->_mapcount) < 0; + + head = compound_head(page); + /* File THP is PMD mapped and not PTE mapped */ + return atomic_read(&page->_mapcount) == + atomic_read(compound_mapcount_ptr(head)); } /* From ba0520468be556ae1c574c5092cea65c2938a76d Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 5 Nov 2019 21:16:40 -0800 Subject: [PATCH 13/93] mm, vmstat: hide /proc/pagetypeinfo from normal users commit abaed0112c1db08be15a784a2c5c8a8b3063cdd3 upstream. /proc/pagetypeinfo is a debugging tool to examine internal page allocator state wrt to fragmentation. It is not very useful for any other use so normal users really do not need to read this file. Waiman Long has noticed that reading this file can have negative side effects because zone->lock is necessary for gathering data and that a) interferes with the page allocator and its users and b) can lead to hard lockups on large machines which have very long free_list. Reduce both issues by simply not exporting the file to regular users. Link: http://lkml.kernel.org/r/20191025072610.18526-2-mhocko@kernel.org Fixes: 467c996c1e19 ("Print out statistics in relation to fragmentation avoidance to /proc/pagetypeinfo") Signed-off-by: Michal Hocko Reported-by: Waiman Long Acked-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Waiman Long Acked-by: Rafael Aquini Acked-by: David Rientjes Reviewed-by: Andrew Morton Cc: David Hildenbrand Cc: Johannes Weiner Cc: Roman Gushchin Cc: Konstantin Khlebnikov Cc: Jann Horn Cc: Song Liu Cc: Greg Kroah-Hartman Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/vmstat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/vmstat.c b/mm/vmstat.c index 9af8d369e112..e60435d556e3 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1794,7 +1794,7 @@ static int __init setup_vmstat(void) #endif #ifdef CONFIG_PROC_FS proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations); - proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops); + proc_create("pagetypeinfo", 0400, NULL, &pagetypeinfo_file_ops); proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations); proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations); #endif From 1bb77722ad2a9ad419066c4a724b77d0ca59b9f4 Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Tue, 5 Nov 2019 21:16:57 -0800 Subject: [PATCH 14/93] dump_stack: avoid the livelock of the dump_lock commit 5cbf2fff3bba8d3c6a4d47c1754de1cf57e2b01f upstream. In the current code, we use the atomic_cmpxchg() to serialize the output of the dump_stack(), but this implementation suffers the thundering herd problem. We have observed such kind of livelock on a Marvell cn96xx board(24 cpus) when heavily using the dump_stack() in a kprobe handler. Actually we can let the competitors to wait for the releasing of the lock before jumping to atomic_cmpxchg(). This will definitely mitigate the thundering herd problem. Thanks Linus for the suggestion. [akpm@linux-foundation.org: fix comment] Link: http://lkml.kernel.org/r/20191030031637.6025-1-haokexin@gmail.com Fixes: b58d977432c8 ("dump_stack: serialize the output from dump_stack()") Signed-off-by: Kevin Hao Suggested-by: Linus Torvalds Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- lib/dump_stack.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/lib/dump_stack.c b/lib/dump_stack.c index c30d07e99dba..72de6444934d 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -44,7 +44,12 @@ retry: was_locked = 1; } else { local_irq_restore(flags); - cpu_relax(); + /* + * Wait for the lock to release before jumping to + * atomic_cmpxchg() in order to mitigate the thundering herd + * problem. + */ + do { cpu_relax(); } while (atomic_read(&dump_lock) != -1); goto retry; } From 9666d5292c79d4ff873f26e4827088402bb5867f Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 5 Nov 2019 00:27:11 +0100 Subject: [PATCH 15/93] perf tools: Fix time sorting commit 722ddfde366fd46205456a9c5ff9b3359dc9a75e upstream. The final sort might get confused when the comparison is done over bigger numbers than int like for -s time. Check the following report for longer workloads: $ perf report -s time -F time,overhead --stdio Fix hist_entry__sort() to properly return int64_t and not possible cut int. Fixes: 043ca389a318 ("perf tools: Use hpp formats to sort final output") Signed-off-by: Jiri Olsa Reviewed-by: Andi Kleen Cc: Alexander Shishkin Cc: Michael Petlan Cc: Namhyung Kim Cc: Peter Zijlstra Cc: stable@vger.kernel.org # v3.16+ Link: http://lore.kernel.org/lkml/20191104232711.16055-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/perf/util/hist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 82833ceba339..32f991d28497 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1485,7 +1485,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog) return 0; } -static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b) +static int64_t hist_entry__sort(struct hist_entry *a, struct hist_entry *b) { struct hists *hists = a->hists; struct perf_hpp_fmt *fmt; From 4acc45713e69667892a8243895abb2c4577c947e Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 30 Oct 2019 10:21:28 -0400 Subject: [PATCH 16/93] drm/radeon: fix si_enable_smc_cac() failed issue commit 2c409ba81be25516afe05ae27a4a15da01740b01 upstream. Need to set the dte flag on this asic. Port the fix from amdgpu: 5cb818b861be114 ("drm/amd/amdgpu: fix si_enable_smc_cac() failed issue") Reviewed-by: Yong Zhao Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/radeon/si_dpm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index b82ef5ed727c..ac7ae206f2e7 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -1956,6 +1956,7 @@ static void si_initialize_powertune_defaults(struct radeon_device *rdev) case 0x682C: si_pi->cac_weights = cac_weights_cape_verde_pro; si_pi->dte_data = dte_data_sun_xt; + update_dte_from_pl2 = true; break; case 0x6825: case 0x6827: From a4d310043c0d317a2da60e540bc9a77391085c1b Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Fri, 25 Oct 2019 14:05:24 +0100 Subject: [PATCH 17/93] ceph: fix use-after-free in __ceph_remove_cap() commit ea60ed6fcf29eebc78f2ce91491e6309ee005a01 upstream. KASAN reports a use-after-free when running xfstest generic/531, with the following trace: [ 293.903362] kasan_report+0xe/0x20 [ 293.903365] rb_erase+0x1f/0x790 [ 293.903370] __ceph_remove_cap+0x201/0x370 [ 293.903375] __ceph_remove_caps+0x4b/0x70 [ 293.903380] ceph_evict_inode+0x4e/0x360 [ 293.903386] evict+0x169/0x290 [ 293.903390] __dentry_kill+0x16f/0x250 [ 293.903394] dput+0x1c6/0x440 [ 293.903398] __fput+0x184/0x330 [ 293.903404] task_work_run+0xb9/0xe0 [ 293.903410] exit_to_usermode_loop+0xd3/0xe0 [ 293.903413] do_syscall_64+0x1a0/0x1c0 [ 293.903417] entry_SYSCALL_64_after_hwframe+0x44/0xa9 This happens because __ceph_remove_cap() may queue a cap release (__ceph_queue_cap_release) which can be scheduled before that cap is removed from the inode list with rb_erase(&cap->ci_node, &ci->i_caps); And, when this finally happens, the use-after-free will occur. This can be fixed by removing the cap from the inode list before being removed from the session list, and thus eliminating the risk of an UAF. Cc: stable@vger.kernel.org Signed-off-by: Luis Henriques Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov Signed-off-by: Greg Kroah-Hartman --- fs/ceph/caps.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 82df349b84f7..f5d9835264aa 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -933,6 +933,11 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode); + /* remove from inode's cap rbtree, and clear auth cap */ + rb_erase(&cap->ci_node, &ci->i_caps); + if (ci->i_auth_cap == cap) + ci->i_auth_cap = NULL; + /* remove from session list */ spin_lock(&session->s_cap_lock); if (session->s_cap_iterator == cap) { @@ -968,11 +973,6 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) spin_unlock(&session->s_cap_lock); - /* remove from inode list */ - rb_erase(&cap->ci_node, &ci->i_caps); - if (ci->i_auth_cap == cap) - ci->i_auth_cap = NULL; - if (removed) ceph_put_cap(mdsc, cap); From 454face064828c3714d87f219a650e8a444641f0 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Tue, 8 Oct 2019 17:15:37 +0300 Subject: [PATCH 18/93] iio: imu: adis16480: make sure provided frequency is positive commit 24e1eb5c0d78cfb9750b690bbe997d4d59170258 upstream. It could happen that either `val` or `val2` [provided from userspace] is negative. In that case the computed frequency could get a weird value. Fix this by checking that neither of the 2 variables is negative, and check that the computed result is not-zero. Fixes: e4f959390178 ("iio: imu: adis16480 switch sampling frequency attr to core support") Signed-off-by: Alexandru Ardelean Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/imu/adis16480.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/iio/imu/adis16480.c b/drivers/iio/imu/adis16480.c index 12898424d838..6f975538996c 100644 --- a/drivers/iio/imu/adis16480.c +++ b/drivers/iio/imu/adis16480.c @@ -266,8 +266,11 @@ static int adis16480_set_freq(struct iio_dev *indio_dev, int val, int val2) struct adis16480 *st = iio_priv(indio_dev); unsigned int t; + if (val < 0 || val2 < 0) + return -EINVAL; + t = val * 1000 + val2 / 1000; - if (t <= 0) + if (t == 0) return -EINVAL; t = 2460000 / t; From f823bf0fd93818e0a3feac87426e292ee7f4c5c4 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Thu, 31 Oct 2019 11:06:24 +0100 Subject: [PATCH 19/93] netfilter: nf_tables: Align nft_expr private data to 64-bit commit 250367c59e6ba0d79d702a059712d66edacd4a1a upstream. Invoking the following commands on a 32-bit architecture with strict alignment requirements (such as an ARMv7-based Raspberry Pi) results in an alignment exception: # nft add table ip test-ip4 # nft add chain ip test-ip4 output { type filter hook output priority 0; } # nft add rule ip test-ip4 output quota 1025 bytes Alignment trap: not handling instruction e1b26f9f at [<7f4473f8>] Unhandled fault: alignment exception (0x001) at 0xb832e824 Internal error: : 1 [#1] PREEMPT SMP ARM Hardware name: BCM2835 [<7f4473fc>] (nft_quota_do_init [nft_quota]) [<7f447448>] (nft_quota_init [nft_quota]) [<7f4260d0>] (nf_tables_newrule [nf_tables]) [<7f4168dc>] (nfnetlink_rcv_batch [nfnetlink]) [<7f416bd0>] (nfnetlink_rcv [nfnetlink]) [<8078b334>] (netlink_unicast) [<8078b664>] (netlink_sendmsg) [<8071b47c>] (sock_sendmsg) [<8071bd18>] (___sys_sendmsg) [<8071ce3c>] (__sys_sendmsg) [<8071ce94>] (sys_sendmsg) The reason is that nft_quota_do_init() calls atomic64_set() on an atomic64_t which is only aligned to 32-bit, not 64-bit, because it succeeds struct nft_expr in memory which only contains a 32-bit pointer. Fix by aligning the nft_expr private data to 64-bit. Fixes: 96518518cc41 ("netfilter: add nftables") Signed-off-by: Lukas Wunner Cc: stable@vger.kernel.org # v3.13+ Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_tables.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 66f6b84df287..7ba9a624090f 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -705,7 +705,8 @@ struct nft_expr_ops { */ struct nft_expr { const struct nft_expr_ops *ops; - unsigned char data[]; + unsigned char data[] + __attribute__((aligned(__alignof__(u64)))); }; static inline void *nft_expr_priv(const struct nft_expr *expr) From 0e0965a22e57db12b0fb6cc8c015e9865642eb07 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 24 Aug 2019 17:49:55 +0300 Subject: [PATCH 20/93] netfilter: ipset: Fix an error code in ip_set_sockfn_get() commit 30b7244d79651460ff114ba8f7987ed94c86b99a upstream. The copy_to_user() function returns the number of bytes remaining to be copied. In this code, that positive return is checked at the end of the function and we return zero/success. What we should do instead is return -EFAULT. Fixes: a7b4f989a629 ("netfilter: ipset: IP set core support") Signed-off-by: Dan Carpenter Signed-off-by: Jozsef Kadlecsik Signed-off-by: Greg Kroah-Hartman --- net/netfilter/ipset/ip_set_core.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index a748b0c2c981..fa5229fd3703 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1942,8 +1942,9 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) } req_version->version = IPSET_PROTOCOL; - ret = copy_to_user(user, req_version, - sizeof(struct ip_set_req_version)); + if (copy_to_user(user, req_version, + sizeof(struct ip_set_req_version))) + ret = -EFAULT; goto done; } case IP_SET_OP_GET_BYNAME: { @@ -2000,7 +2001,8 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) } /* end of switch(op) */ copy: - ret = copy_to_user(user, data, copylen); + if (copy_to_user(user, data, copylen)) + ret = -EFAULT; done: vfree(data); From 0589de2de3c89d149e7ee0f6696ed98b22b5537c Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 1 Oct 2019 12:29:14 +0200 Subject: [PATCH 21/93] can: usb_8dev: fix use-after-free on disconnect commit 3759739426186a924675651b388d1c3963c5710e upstream. The driver was accessing its driver data after having freed it. Fixes: 0024d8ad1639 ("can: usb_8dev: Add support for USB2CAN interface from 8 devices") Cc: stable # 3.9 Cc: Bernd Krumboeck Cc: Wolfgang Grandegger Signed-off-by: Johan Hovold Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/usb/usb_8dev.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c index 27861c417c94..3e4416473607 100644 --- a/drivers/net/can/usb/usb_8dev.c +++ b/drivers/net/can/usb/usb_8dev.c @@ -1007,9 +1007,8 @@ static void usb_8dev_disconnect(struct usb_interface *intf) netdev_info(priv->netdev, "device disconnected\n"); unregister_netdev(priv->netdev); - free_candev(priv->netdev); - unlink_all_urbs(priv); + free_candev(priv->netdev); } } From 7a5f2a35384292d7a18ffd54bc9f0971014f2d42 Mon Sep 17 00:00:00 2001 From: Kurt Van Dijck Date: Tue, 1 Oct 2019 09:40:36 +0200 Subject: [PATCH 22/93] can: c_can: c_can_poll(): only read status register after status IRQ commit 3cb3eaac52c0f145d895f4b6c22834d5f02b8569 upstream. When the status register is read without the status IRQ pending, the chip may not raise the interrupt line for an upcoming status interrupt and the driver may miss a status interrupt. It is critical that the BUSOFF status interrupt is forwarded to the higher layers, since no more interrupts will follow without intervention. Thanks to Wolfgang and Joe for bringing up the first idea. Signed-off-by: Kurt Van Dijck Cc: Wolfgang Grandegger Cc: Joe Burmeister Fixes: fa39b54ccf28 ("can: c_can: Get rid of pointless interrupts") Cc: linux-stable Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/c_can/c_can.c | 25 ++++++++++++++++++++----- drivers/net/can/c_can/c_can.h | 1 + 2 files changed, 21 insertions(+), 5 deletions(-) diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index e3dccd3200d5..7d35f6737499 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -97,6 +97,9 @@ #define BTR_TSEG2_SHIFT 12 #define BTR_TSEG2_MASK (0x7 << BTR_TSEG2_SHIFT) +/* interrupt register */ +#define INT_STS_PENDING 0x8000 + /* brp extension register */ #define BRP_EXT_BRPE_MASK 0x0f #define BRP_EXT_BRPE_SHIFT 0 @@ -1029,10 +1032,16 @@ static int c_can_poll(struct napi_struct *napi, int quota) u16 curr, last = priv->last_status; int work_done = 0; - priv->last_status = curr = priv->read_reg(priv, C_CAN_STS_REG); - /* Ack status on C_CAN. D_CAN is self clearing */ - if (priv->type != BOSCH_D_CAN) - priv->write_reg(priv, C_CAN_STS_REG, LEC_UNUSED); + /* Only read the status register if a status interrupt was pending */ + if (atomic_xchg(&priv->sie_pending, 0)) { + priv->last_status = curr = priv->read_reg(priv, C_CAN_STS_REG); + /* Ack status on C_CAN. D_CAN is self clearing */ + if (priv->type != BOSCH_D_CAN) + priv->write_reg(priv, C_CAN_STS_REG, LEC_UNUSED); + } else { + /* no change detected ... */ + curr = last; + } /* handle state changes */ if ((curr & STATUS_EWARN) && (!(last & STATUS_EWARN))) { @@ -1083,10 +1092,16 @@ static irqreturn_t c_can_isr(int irq, void *dev_id) { struct net_device *dev = (struct net_device *)dev_id; struct c_can_priv *priv = netdev_priv(dev); + int reg_int; - if (!priv->read_reg(priv, C_CAN_INT_REG)) + reg_int = priv->read_reg(priv, C_CAN_INT_REG); + if (!reg_int) return IRQ_NONE; + /* save for later use */ + if (reg_int & INT_STS_PENDING) + atomic_set(&priv->sie_pending, 1); + /* disable all interrupts and schedule the NAPI */ c_can_irq_control(priv, false); napi_schedule(&priv->napi); diff --git a/drivers/net/can/c_can/c_can.h b/drivers/net/can/c_can/c_can.h index 8acdc7fa4792..d5567a7c1c6d 100644 --- a/drivers/net/can/c_can/c_can.h +++ b/drivers/net/can/c_can/c_can.h @@ -198,6 +198,7 @@ struct c_can_priv { struct net_device *dev; struct device *device; atomic_t tx_active; + atomic_t sie_pending; unsigned long tx_dir; int last_status; u16 (*read_reg) (const struct c_can_priv *priv, enum reg index); From d9510ea12a1c42948c69dfc1a23657bea4d7244e Mon Sep 17 00:00:00 2001 From: Stephane Grosjean Date: Tue, 8 Oct 2019 10:35:44 +0200 Subject: [PATCH 23/93] can: peak_usb: fix a potential out-of-sync while decoding packets commit de280f403f2996679e2607384980703710576fed upstream. When decoding a buffer received from PCAN-USB, the first timestamp read in a packet is a 16-bit coded time base, and the next ones are an 8-bit offset to this base, regardless of the type of packet read. This patch corrects a potential loss of synchronization by using a timestamp index read from the buffer, rather than an index of received data packets, to determine on the sizeof the timestamp to be read from the packet being decoded. Signed-off-by: Stephane Grosjean Fixes: 46be265d3388 ("can: usb: PEAK-System Technik PCAN-USB specific part") Cc: linux-stable Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/usb/peak_usb/pcan_usb.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index 838545ce468d..e626c2afbbb1 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -108,7 +108,7 @@ struct pcan_usb_msg_context { u8 *end; u8 rec_cnt; u8 rec_idx; - u8 rec_data_idx; + u8 rec_ts_idx; struct net_device *netdev; struct pcan_usb *pdev; }; @@ -552,10 +552,15 @@ static int pcan_usb_decode_status(struct pcan_usb_msg_context *mc, mc->ptr += PCAN_USB_CMD_ARGS; if (status_len & PCAN_USB_STATUSLEN_TIMESTAMP) { - int err = pcan_usb_decode_ts(mc, !mc->rec_idx); + int err = pcan_usb_decode_ts(mc, !mc->rec_ts_idx); if (err) return err; + + /* Next packet in the buffer will have a timestamp on a single + * byte + */ + mc->rec_ts_idx++; } switch (f) { @@ -638,10 +643,13 @@ static int pcan_usb_decode_data(struct pcan_usb_msg_context *mc, u8 status_len) cf->can_dlc = get_can_dlc(rec_len); - /* first data packet timestamp is a word */ - if (pcan_usb_decode_ts(mc, !mc->rec_data_idx)) + /* Only first packet timestamp is a word */ + if (pcan_usb_decode_ts(mc, !mc->rec_ts_idx)) goto decode_failed; + /* Next packet in the buffer will have a timestamp on a single byte */ + mc->rec_ts_idx++; + /* read data */ memset(cf->data, 0x0, sizeof(cf->data)); if (status_len & PCAN_USB_STATUSLEN_RTR) { @@ -695,7 +703,6 @@ static int pcan_usb_decode_msg(struct peak_usb_device *dev, u8 *ibuf, u32 lbuf) /* handle normal can frames here */ } else { err = pcan_usb_decode_data(&mc, sl); - mc.rec_data_idx++; } } From b46a2067f36d7c5f2f259c4ed476359e6e9d668f Mon Sep 17 00:00:00 2001 From: Navid Emamdoost Date: Thu, 19 Sep 2019 21:44:38 -0500 Subject: [PATCH 24/93] can: gs_usb: gs_can_open(): prevent memory leak commit fb5be6a7b4863ecc44963bb80ca614584b6c7817 upstream. In gs_can_open() if usb_submit_urb() fails the allocated urb should be released. Fixes: d08e973a77d1 ("can: gs_usb: Added support for the GS_USB CAN devices") Cc: linux-stable Signed-off-by: Navid Emamdoost Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/usb/gs_usb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 5d5012337d9e..014b9ae3dc17 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -632,6 +632,7 @@ static int gs_can_open(struct net_device *netdev) rc); usb_unanchor_urb(urb); + usb_free_urb(urb); break; } From da281558d20bfbf82823cab457ba7d343ba6b0a0 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 23 Oct 2019 10:27:05 +0200 Subject: [PATCH 25/93] can: peak_usb: fix slab info leak commit f7a1337f0d29b98733c8824e165fca3371d7d4fd upstream. Fix a small slab info leak due to a failure to clear the command buffer at allocation. The first 16 bytes of the command buffer are always sent to the device in pcan_usb_send_cmd() even though only the first two may have been initialised in case no argument payload is provided (e.g. when waiting for a response). Fixes: bb4785551f64 ("can: usb: PEAK-System Technik USB adapters driver core") Cc: stable # 3.4 Reported-by: syzbot+863724e7128e14b26732@syzkaller.appspotmail.com Signed-off-by: Johan Hovold Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/usb/peak_usb/pcan_usb_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index ce0a352a5eaa..6cd4317fe94d 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -774,7 +774,7 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter, dev = netdev_priv(netdev); /* allocate a buffer large enough to send commands */ - dev->cmd_buf = kmalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL); + dev->cmd_buf = kzalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL); if (!dev->cmd_buf) { err = -ENOMEM; goto lbl_free_candev; From 539938daf0340bf22d40d1208bebb5aa99dd4ba4 Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Sat, 7 Oct 2017 16:02:21 +0200 Subject: [PATCH 26/93] configfs: Fix bool initialization/comparison commit 3f6928c347707a65cee10a9f54b85ad5fb078b3f upstream. Bool initializations should use true and false. Bool tests don't need comparisons. Signed-off-by: Thomas Meyer Signed-off-by: Christoph Hellwig Signed-off-by: Greg Kroah-Hartman --- fs/configfs/file.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/configfs/file.c b/fs/configfs/file.c index 2c6312db8516..39bac169f915 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -166,7 +166,7 @@ configfs_read_bin_file(struct file *file, char __user *buf, retval = -ETXTBSY; goto out; } - buffer->read_in_progress = 1; + buffer->read_in_progress = true; if (buffer->needs_read_fill) { /* perform first read with buf == NULL to get extent */ @@ -325,7 +325,7 @@ configfs_write_bin_file(struct file *file, const char __user *buf, len = -ETXTBSY; goto out; } - buffer->write_in_progress = 1; + buffer->write_in_progress = true; /* buffer grows? */ if (*ppos + count > buffer->bin_buffer_size) { @@ -429,8 +429,8 @@ static int check_perm(struct inode * inode, struct file * file, int type) } mutex_init(&buffer->mutex); buffer->needs_read_fill = 1; - buffer->read_in_progress = 0; - buffer->write_in_progress = 0; + buffer->read_in_progress = false; + buffer->write_in_progress = false; buffer->ops = ops; file->private_data = buffer; goto Done; @@ -488,10 +488,10 @@ static int configfs_release_bin_file(struct inode *inode, struct file *filp) ssize_t len = 0; int ret; - buffer->read_in_progress = 0; + buffer->read_in_progress = false; if (buffer->write_in_progress) { - buffer->write_in_progress = 0; + buffer->write_in_progress = false; len = bin_attr->write(item, buffer->bin_buffer, buffer->bin_buffer_size); From 0c5b0cbeae18e4cd5201b597c24e4071467688fc Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 30 Aug 2019 11:30:03 -0400 Subject: [PATCH 27/93] configfs: stash the data we need into configfs_buffer at open time commit ff4dd081977da56566a848f071aed8fa92d604a1 upstream. simplifies the ->read()/->write()/->release() instances nicely Signed-off-by: Al Viro Signed-off-by: Christoph Hellwig Signed-off-by: Greg Kroah-Hartman --- fs/configfs/file.c | 227 +++++++++++++++++++-------------------------- 1 file changed, 94 insertions(+), 133 deletions(-) diff --git a/fs/configfs/file.c b/fs/configfs/file.c index 39bac169f915..bab13084fa73 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -53,24 +53,18 @@ struct configfs_buffer { bool write_in_progress; char *bin_buffer; int bin_buffer_size; + int cb_max_size; + struct config_item *item; + struct module *owner; + union { + struct configfs_attribute *attr; + struct configfs_bin_attribute *bin_attr; + }; }; -/** - * fill_read_buffer - allocate and fill buffer from item. - * @dentry: dentry pointer. - * @buffer: data buffer for file. - * - * Allocate @buffer->page, if it hasn't been already, then call the - * config_item's show() method to fill the buffer with this attribute's - * data. - * This is called only once, on the file's first read. - */ -static int fill_read_buffer(struct dentry * dentry, struct configfs_buffer * buffer) +static int fill_read_buffer(struct configfs_buffer * buffer) { - struct configfs_attribute * attr = to_attr(dentry); - struct config_item * item = to_item(dentry->d_parent); - int ret = 0; ssize_t count; if (!buffer->page) @@ -78,15 +72,15 @@ static int fill_read_buffer(struct dentry * dentry, struct configfs_buffer * buf if (!buffer->page) return -ENOMEM; - count = attr->show(item, buffer->page); + count = buffer->attr->show(buffer->item, buffer->page); + if (count < 0) + return count; + if (WARN_ON_ONCE(count > (ssize_t)SIMPLE_ATTR_SIZE)) + return -EIO; - BUG_ON(count > (ssize_t)SIMPLE_ATTR_SIZE); - if (count >= 0) { - buffer->needs_read_fill = 0; - buffer->count = count; - } else - ret = count; - return ret; + buffer->needs_read_fill = 0; + buffer->count = count; + return 0; } /** @@ -111,12 +105,13 @@ static int fill_read_buffer(struct dentry * dentry, struct configfs_buffer * buf static ssize_t configfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - struct configfs_buffer * buffer = file->private_data; + struct configfs_buffer *buffer = file->private_data; ssize_t retval = 0; mutex_lock(&buffer->mutex); if (buffer->needs_read_fill) { - if ((retval = fill_read_buffer(file->f_path.dentry,buffer))) + retval = fill_read_buffer(buffer); + if (retval) goto out; } pr_debug("%s: count = %zd, ppos = %lld, buf = %s\n", @@ -153,9 +148,6 @@ configfs_read_bin_file(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct configfs_buffer *buffer = file->private_data; - struct dentry *dentry = file->f_path.dentry; - struct config_item *item = to_item(dentry->d_parent); - struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry); ssize_t retval = 0; ssize_t len = min_t(size_t, count, PAGE_SIZE); @@ -170,14 +162,14 @@ configfs_read_bin_file(struct file *file, char __user *buf, if (buffer->needs_read_fill) { /* perform first read with buf == NULL to get extent */ - len = bin_attr->read(item, NULL, 0); + len = buffer->bin_attr->read(buffer->item, NULL, 0); if (len <= 0) { retval = len; goto out; } /* do not exceed the maximum value */ - if (bin_attr->cb_max_size && len > bin_attr->cb_max_size) { + if (buffer->cb_max_size && len > buffer->cb_max_size) { retval = -EFBIG; goto out; } @@ -190,7 +182,8 @@ configfs_read_bin_file(struct file *file, char __user *buf, buffer->bin_buffer_size = len; /* perform second read to fill buffer */ - len = bin_attr->read(item, buffer->bin_buffer, len); + len = buffer->bin_attr->read(buffer->item, + buffer->bin_buffer, len); if (len < 0) { retval = len; vfree(buffer->bin_buffer); @@ -240,25 +233,10 @@ fill_write_buffer(struct configfs_buffer * buffer, const char __user * buf, size return error ? -EFAULT : count; } - -/** - * flush_write_buffer - push buffer to config_item. - * @dentry: dentry to the attribute - * @buffer: data buffer for file. - * @count: number of bytes - * - * Get the correct pointers for the config_item and the attribute we're - * dealing with, then call the store() method for the attribute, - * passing the buffer that we acquired in fill_write_buffer(). - */ - static int -flush_write_buffer(struct dentry * dentry, struct configfs_buffer * buffer, size_t count) +flush_write_buffer(struct configfs_buffer *buffer, size_t count) { - struct configfs_attribute * attr = to_attr(dentry); - struct config_item * item = to_item(dentry->d_parent); - - return attr->store(item, buffer->page, count); + return buffer->attr->store(buffer->item, buffer->page, count); } @@ -282,13 +260,13 @@ flush_write_buffer(struct dentry * dentry, struct configfs_buffer * buffer, size static ssize_t configfs_write_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct configfs_buffer * buffer = file->private_data; + struct configfs_buffer *buffer = file->private_data; ssize_t len; mutex_lock(&buffer->mutex); len = fill_write_buffer(buffer, buf, count); if (len > 0) - len = flush_write_buffer(file->f_path.dentry, buffer, len); + len = flush_write_buffer(buffer, len); if (len > 0) *ppos += len; mutex_unlock(&buffer->mutex); @@ -313,8 +291,6 @@ configfs_write_bin_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct configfs_buffer *buffer = file->private_data; - struct dentry *dentry = file->f_path.dentry; - struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry); void *tbuf = NULL; ssize_t len; @@ -330,8 +306,8 @@ configfs_write_bin_file(struct file *file, const char __user *buf, /* buffer grows? */ if (*ppos + count > buffer->bin_buffer_size) { - if (bin_attr->cb_max_size && - *ppos + count > bin_attr->cb_max_size) { + if (buffer->cb_max_size && + *ppos + count > buffer->cb_max_size) { len = -EFBIG; goto out; } @@ -363,31 +339,45 @@ out: return len; } -static int check_perm(struct inode * inode, struct file * file, int type) +static int __configfs_open_file(struct inode *inode, struct file *file, int type) { - struct config_item *item = configfs_get_config_item(file->f_path.dentry->d_parent); - struct configfs_attribute * attr = to_attr(file->f_path.dentry); - struct configfs_bin_attribute *bin_attr = NULL; - struct configfs_buffer * buffer; - struct configfs_item_operations * ops = NULL; - int error = 0; + struct dentry *dentry = file->f_path.dentry; + struct configfs_attribute *attr; + struct configfs_buffer *buffer; + int error; - if (!item || !attr) - goto Einval; + error = -ENOMEM; + buffer = kzalloc(sizeof(struct configfs_buffer), GFP_KERNEL); + if (!buffer) + goto out; - if (type & CONFIGFS_ITEM_BIN_ATTR) - bin_attr = to_bin_attr(file->f_path.dentry); + error = -EINVAL; + buffer->item = configfs_get_config_item(dentry->d_parent); + if (!buffer->item) + goto out_free_buffer; - /* Grab the module reference for this attribute if we have one */ - if (!try_module_get(attr->ca_owner)) { - error = -ENODEV; - goto Done; + attr = to_attr(dentry); + if (!attr) + goto out_put_item; + + if (type & CONFIGFS_ITEM_BIN_ATTR) { + buffer->bin_attr = to_bin_attr(dentry); + buffer->cb_max_size = buffer->bin_attr->cb_max_size; + } else { + buffer->attr = attr; } - if (item->ci_type) - ops = item->ci_type->ct_item_ops; - else - goto Eaccess; + buffer->owner = attr->ca_owner; + /* Grab the module reference for this attribute if we have one */ + error = -ENODEV; + if (!try_module_get(buffer->owner)) + goto out_put_item; + + error = -EACCES; + if (!buffer->item->ci_type) + goto out_put_module; + + buffer->ops = buffer->item->ci_type->ct_item_ops; /* File needs write support. * The inode's perms must say it's ok, @@ -395,13 +385,11 @@ static int check_perm(struct inode * inode, struct file * file, int type) */ if (file->f_mode & FMODE_WRITE) { if (!(inode->i_mode & S_IWUGO)) - goto Eaccess; - + goto out_put_module; if ((type & CONFIGFS_ITEM_ATTR) && !attr->store) - goto Eaccess; - - if ((type & CONFIGFS_ITEM_BIN_ATTR) && !bin_attr->write) - goto Eaccess; + goto out_put_module; + if ((type & CONFIGFS_ITEM_BIN_ATTR) && !buffer->bin_attr->write) + goto out_put_module; } /* File needs read support. @@ -410,90 +398,65 @@ static int check_perm(struct inode * inode, struct file * file, int type) */ if (file->f_mode & FMODE_READ) { if (!(inode->i_mode & S_IRUGO)) - goto Eaccess; - + goto out_put_module; if ((type & CONFIGFS_ITEM_ATTR) && !attr->show) - goto Eaccess; - - if ((type & CONFIGFS_ITEM_BIN_ATTR) && !bin_attr->read) - goto Eaccess; + goto out_put_module; + if ((type & CONFIGFS_ITEM_BIN_ATTR) && !buffer->bin_attr->read) + goto out_put_module; } - /* No error? Great, allocate a buffer for the file, and store it - * it in file->private_data for easy access. - */ - buffer = kzalloc(sizeof(struct configfs_buffer),GFP_KERNEL); - if (!buffer) { - error = -ENOMEM; - goto Enomem; - } mutex_init(&buffer->mutex); buffer->needs_read_fill = 1; buffer->read_in_progress = false; buffer->write_in_progress = false; - buffer->ops = ops; file->private_data = buffer; - goto Done; + return 0; - Einval: - error = -EINVAL; - goto Done; - Eaccess: - error = -EACCES; - Enomem: - module_put(attr->ca_owner); - Done: - if (error && item) - config_item_put(item); +out_put_module: + module_put(buffer->owner); +out_put_item: + config_item_put(buffer->item); +out_free_buffer: + kfree(buffer); +out: return error; } static int configfs_release(struct inode *inode, struct file *filp) { - struct config_item * item = to_item(filp->f_path.dentry->d_parent); - struct configfs_attribute * attr = to_attr(filp->f_path.dentry); - struct module * owner = attr->ca_owner; - struct configfs_buffer * buffer = filp->private_data; + struct configfs_buffer *buffer = filp->private_data; - if (item) - config_item_put(item); - /* After this point, attr should not be accessed. */ - module_put(owner); - - if (buffer) { - if (buffer->page) - free_page((unsigned long)buffer->page); - mutex_destroy(&buffer->mutex); - kfree(buffer); - } + if (buffer->item) + config_item_put(buffer->item); + module_put(buffer->owner); + if (buffer->page) + free_page((unsigned long)buffer->page); + mutex_destroy(&buffer->mutex); + kfree(buffer); return 0; } static int configfs_open_file(struct inode *inode, struct file *filp) { - return check_perm(inode, filp, CONFIGFS_ITEM_ATTR); + return __configfs_open_file(inode, filp, CONFIGFS_ITEM_ATTR); } static int configfs_open_bin_file(struct inode *inode, struct file *filp) { - return check_perm(inode, filp, CONFIGFS_ITEM_BIN_ATTR); + return __configfs_open_file(inode, filp, CONFIGFS_ITEM_BIN_ATTR); } -static int configfs_release_bin_file(struct inode *inode, struct file *filp) +static int configfs_release_bin_file(struct inode *inode, struct file *file) { - struct configfs_buffer *buffer = filp->private_data; - struct dentry *dentry = filp->f_path.dentry; - struct config_item *item = to_item(dentry->d_parent); - struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry); - ssize_t len = 0; - int ret; + struct configfs_buffer *buffer = file->private_data; buffer->read_in_progress = false; if (buffer->write_in_progress) { buffer->write_in_progress = false; - len = bin_attr->write(item, buffer->bin_buffer, + /* result of ->release() is ignored */ + buffer->bin_attr->write(buffer->item, buffer->bin_buffer, buffer->bin_buffer_size); /* vfree on NULL is safe */ @@ -503,10 +466,8 @@ static int configfs_release_bin_file(struct inode *inode, struct file *filp) buffer->needs_read_fill = 1; } - ret = configfs_release(inode, filp); - if (len < 0) - return len; - return ret; + configfs_release(inode, file); + return 0; } From 41faa5d86d90af469a2b7793894550644396895c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 29 Aug 2019 23:13:30 -0400 Subject: [PATCH 28/93] configfs_register_group() shouldn't be (and isn't) called in rmdirable parts commit f19e4ed1e1edbfa3c9ccb9fed17759b7d6db24c6 upstream. revert cc57c07343bd "configfs: fix registered group removal" It was an attempt to handle something that fundamentally doesn't work - configfs_register_group() should never be done in a part of tree that can be rmdir'ed. And in mainline it never had been, so let's not borrow trouble; the fix was racy anyway, it would take a lot more to make that work and desired semantics is not clear. Signed-off-by: Al Viro Signed-off-by: Christoph Hellwig Signed-off-by: Greg Kroah-Hartman --- fs/configfs/dir.c | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index a1985a9ad2d6..64fdb12e6ad6 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1782,16 +1782,6 @@ void configfs_unregister_group(struct config_group *group) struct dentry *dentry = group->cg_item.ci_dentry; struct dentry *parent = group->cg_item.ci_parent->ci_dentry; - mutex_lock(&subsys->su_mutex); - if (!group->cg_item.ci_parent->ci_group) { - /* - * The parent has already been unlinked and detached - * due to a rmdir. - */ - goto unlink_group; - } - mutex_unlock(&subsys->su_mutex); - inode_lock_nested(d_inode(parent), I_MUTEX_PARENT); spin_lock(&configfs_dirent_lock); configfs_detach_prep(dentry, NULL); @@ -1806,7 +1796,6 @@ void configfs_unregister_group(struct config_group *group) dput(dentry); mutex_lock(&subsys->su_mutex); -unlink_group: unlink_group(group); mutex_unlock(&subsys->su_mutex); } From 77590eb3a942508f2069dc1fa56bdc8d56a56fd5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 25 Aug 2019 19:56:13 -0400 Subject: [PATCH 29/93] configfs: new object reprsenting tree fragments commit 47320fbe11a6059ae502c9c16b668022fdb4cf76 upstream. Refcounted, hangs of configfs_dirent, created by operations that add fragments to configfs tree (mkdir and configfs_register_{subsystem,group}). Will be used in the next commit to provide exclusion between fragment removal and ->show/->store calls. Signed-off-by: Al Viro Signed-off-by: Christoph Hellwig Signed-off-by: Greg Kroah-Hartman --- fs/configfs/configfs_internal.h | 15 ++++- fs/configfs/dir.c | 105 +++++++++++++++++++++++++------- fs/configfs/file.c | 4 +- 3 files changed, 97 insertions(+), 27 deletions(-) diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h index ccc31fa6f1a7..16eb59adf5aa 100644 --- a/fs/configfs/configfs_internal.h +++ b/fs/configfs/configfs_internal.h @@ -34,6 +34,15 @@ #include #include +struct configfs_fragment { + atomic_t frag_count; + struct rw_semaphore frag_sem; + bool frag_dead; +}; + +void put_fragment(struct configfs_fragment *); +struct configfs_fragment *get_fragment(struct configfs_fragment *); + struct configfs_dirent { atomic_t s_count; int s_dependent_count; @@ -48,6 +57,7 @@ struct configfs_dirent { #ifdef CONFIG_LOCKDEP int s_depth; #endif + struct configfs_fragment *s_frag; }; #define CONFIGFS_ROOT 0x0001 @@ -75,8 +85,8 @@ extern int configfs_create(struct dentry *, umode_t mode, void (*init)(struct in extern int configfs_create_file(struct config_item *, const struct configfs_attribute *); extern int configfs_create_bin_file(struct config_item *, const struct configfs_bin_attribute *); -extern int configfs_make_dirent(struct configfs_dirent *, - struct dentry *, void *, umode_t, int); +extern int configfs_make_dirent(struct configfs_dirent *, struct dentry *, + void *, umode_t, int, struct configfs_fragment *); extern int configfs_dirent_is_ready(struct configfs_dirent *); extern void configfs_hash_and_remove(struct dentry * dir, const char * name); @@ -151,6 +161,7 @@ static inline void release_configfs_dirent(struct configfs_dirent * sd) { if (!(sd->s_type & CONFIGFS_ROOT)) { kfree(sd->s_iattr); + put_fragment(sd->s_frag); kmem_cache_free(configfs_dir_cachep, sd); } } diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 64fdb12e6ad6..1362208a8618 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -164,11 +164,38 @@ configfs_adjust_dir_dirent_depth_after_populate(struct configfs_dirent *sd) #endif /* CONFIG_LOCKDEP */ +static struct configfs_fragment *new_fragment(void) +{ + struct configfs_fragment *p; + + p = kmalloc(sizeof(struct configfs_fragment), GFP_KERNEL); + if (p) { + atomic_set(&p->frag_count, 1); + init_rwsem(&p->frag_sem); + p->frag_dead = false; + } + return p; +} + +void put_fragment(struct configfs_fragment *frag) +{ + if (frag && atomic_dec_and_test(&frag->frag_count)) + kfree(frag); +} + +struct configfs_fragment *get_fragment(struct configfs_fragment *frag) +{ + if (likely(frag)) + atomic_inc(&frag->frag_count); + return frag; +} + /* * Allocates a new configfs_dirent and links it to the parent configfs_dirent */ static struct configfs_dirent *configfs_new_dirent(struct configfs_dirent *parent_sd, - void *element, int type) + void *element, int type, + struct configfs_fragment *frag) { struct configfs_dirent * sd; @@ -188,6 +215,7 @@ static struct configfs_dirent *configfs_new_dirent(struct configfs_dirent *paren kmem_cache_free(configfs_dir_cachep, sd); return ERR_PTR(-ENOENT); } + sd->s_frag = get_fragment(frag); list_add(&sd->s_sibling, &parent_sd->s_children); spin_unlock(&configfs_dirent_lock); @@ -222,11 +250,11 @@ static int configfs_dirent_exists(struct configfs_dirent *parent_sd, int configfs_make_dirent(struct configfs_dirent * parent_sd, struct dentry * dentry, void * element, - umode_t mode, int type) + umode_t mode, int type, struct configfs_fragment *frag) { struct configfs_dirent * sd; - sd = configfs_new_dirent(parent_sd, element, type); + sd = configfs_new_dirent(parent_sd, element, type, frag); if (IS_ERR(sd)) return PTR_ERR(sd); @@ -273,7 +301,8 @@ static void init_symlink(struct inode * inode) * until it is validated by configfs_dir_set_ready() */ -static int configfs_create_dir(struct config_item *item, struct dentry *dentry) +static int configfs_create_dir(struct config_item *item, struct dentry *dentry, + struct configfs_fragment *frag) { int error; umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO; @@ -286,7 +315,8 @@ static int configfs_create_dir(struct config_item *item, struct dentry *dentry) return error; error = configfs_make_dirent(p->d_fsdata, dentry, item, mode, - CONFIGFS_DIR | CONFIGFS_USET_CREATING); + CONFIGFS_DIR | CONFIGFS_USET_CREATING, + frag); if (unlikely(error)) return error; @@ -351,9 +381,10 @@ int configfs_create_link(struct configfs_symlink *sl, { int err = 0; umode_t mode = S_IFLNK | S_IRWXUGO; + struct configfs_dirent *p = parent->d_fsdata; - err = configfs_make_dirent(parent->d_fsdata, dentry, sl, mode, - CONFIGFS_ITEM_LINK); + err = configfs_make_dirent(p, dentry, sl, mode, + CONFIGFS_ITEM_LINK, p->s_frag); if (!err) { err = configfs_create(dentry, mode, init_symlink); if (err) { @@ -612,7 +643,8 @@ static int populate_attrs(struct config_item *item) static int configfs_attach_group(struct config_item *parent_item, struct config_item *item, - struct dentry *dentry); + struct dentry *dentry, + struct configfs_fragment *frag); static void configfs_detach_group(struct config_item *item); static void detach_groups(struct config_group *group) @@ -660,7 +692,8 @@ static void detach_groups(struct config_group *group) * try using vfs_mkdir. Just a thought. */ static int create_default_group(struct config_group *parent_group, - struct config_group *group) + struct config_group *group, + struct configfs_fragment *frag) { int ret; struct configfs_dirent *sd; @@ -676,7 +709,7 @@ static int create_default_group(struct config_group *parent_group, d_add(child, NULL); ret = configfs_attach_group(&parent_group->cg_item, - &group->cg_item, child); + &group->cg_item, child, frag); if (!ret) { sd = child->d_fsdata; sd->s_type |= CONFIGFS_USET_DEFAULT; @@ -690,13 +723,14 @@ static int create_default_group(struct config_group *parent_group, return ret; } -static int populate_groups(struct config_group *group) +static int populate_groups(struct config_group *group, + struct configfs_fragment *frag) { struct config_group *new_group; int ret = 0; list_for_each_entry(new_group, &group->default_groups, group_entry) { - ret = create_default_group(group, new_group); + ret = create_default_group(group, new_group, frag); if (ret) { detach_groups(group); break; @@ -810,11 +844,12 @@ static void link_group(struct config_group *parent_group, struct config_group *g */ static int configfs_attach_item(struct config_item *parent_item, struct config_item *item, - struct dentry *dentry) + struct dentry *dentry, + struct configfs_fragment *frag) { int ret; - ret = configfs_create_dir(item, dentry); + ret = configfs_create_dir(item, dentry, frag); if (!ret) { ret = populate_attrs(item); if (ret) { @@ -844,12 +879,13 @@ static void configfs_detach_item(struct config_item *item) static int configfs_attach_group(struct config_item *parent_item, struct config_item *item, - struct dentry *dentry) + struct dentry *dentry, + struct configfs_fragment *frag) { int ret; struct configfs_dirent *sd; - ret = configfs_attach_item(parent_item, item, dentry); + ret = configfs_attach_item(parent_item, item, dentry, frag); if (!ret) { sd = dentry->d_fsdata; sd->s_type |= CONFIGFS_USET_DIR; @@ -865,7 +901,7 @@ static int configfs_attach_group(struct config_item *parent_item, */ inode_lock_nested(d_inode(dentry), I_MUTEX_CHILD); configfs_adjust_dir_dirent_depth_before_populate(sd); - ret = populate_groups(to_config_group(item)); + ret = populate_groups(to_config_group(item), frag); if (ret) { configfs_detach_item(item); d_inode(dentry)->i_flags |= S_DEAD; @@ -1260,6 +1296,7 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode struct configfs_dirent *sd; struct config_item_type *type; struct module *subsys_owner = NULL, *new_item_owner = NULL; + struct configfs_fragment *frag; char *name; sd = dentry->d_parent->d_fsdata; @@ -1278,6 +1315,12 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode goto out; } + frag = new_fragment(); + if (!frag) { + ret = -ENOMEM; + goto out; + } + /* Get a working ref for the duration of this function */ parent_item = configfs_get_config_item(dentry->d_parent); type = parent_item->ci_type; @@ -1380,9 +1423,9 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode spin_unlock(&configfs_dirent_lock); if (group) - ret = configfs_attach_group(parent_item, item, dentry); + ret = configfs_attach_group(parent_item, item, dentry, frag); else - ret = configfs_attach_item(parent_item, item, dentry); + ret = configfs_attach_item(parent_item, item, dentry, frag); spin_lock(&configfs_dirent_lock); sd->s_type &= ~CONFIGFS_USET_IN_MKDIR; @@ -1419,6 +1462,7 @@ out_put: * reference. */ config_item_put(parent_item); + put_fragment(frag); out: return ret; @@ -1587,7 +1631,7 @@ static int configfs_dir_open(struct inode *inode, struct file *file) */ err = -ENOENT; if (configfs_dirent_is_ready(parent_sd)) { - file->private_data = configfs_new_dirent(parent_sd, NULL, 0); + file->private_data = configfs_new_dirent(parent_sd, NULL, 0, NULL); if (IS_ERR(file->private_data)) err = PTR_ERR(file->private_data); else @@ -1743,8 +1787,13 @@ int configfs_register_group(struct config_group *parent_group, { struct configfs_subsystem *subsys = parent_group->cg_subsys; struct dentry *parent; + struct configfs_fragment *frag; int ret; + frag = new_fragment(); + if (!frag) + return -ENOMEM; + mutex_lock(&subsys->su_mutex); link_group(parent_group, group); mutex_unlock(&subsys->su_mutex); @@ -1752,7 +1801,7 @@ int configfs_register_group(struct config_group *parent_group, parent = parent_group->cg_item.ci_dentry; inode_lock_nested(d_inode(parent), I_MUTEX_PARENT); - ret = create_default_group(parent_group, group); + ret = create_default_group(parent_group, group, frag); if (ret) goto err_out; @@ -1760,12 +1809,14 @@ int configfs_register_group(struct config_group *parent_group, configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata); spin_unlock(&configfs_dirent_lock); inode_unlock(d_inode(parent)); + put_fragment(frag); return 0; err_out: inode_unlock(d_inode(parent)); mutex_lock(&subsys->su_mutex); unlink_group(group); mutex_unlock(&subsys->su_mutex); + put_fragment(frag); return ret; } EXPORT_SYMBOL(configfs_register_group); @@ -1852,10 +1903,17 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys) struct dentry *dentry; struct dentry *root; struct configfs_dirent *sd; + struct configfs_fragment *frag; + + frag = new_fragment(); + if (!frag) + return -ENOMEM; root = configfs_pin_fs(); - if (IS_ERR(root)) + if (IS_ERR(root)) { + put_fragment(frag); return PTR_ERR(root); + } if (!group->cg_item.ci_name) group->cg_item.ci_name = group->cg_item.ci_namebuf; @@ -1871,7 +1929,7 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys) d_add(dentry, NULL); err = configfs_attach_group(sd->s_element, &group->cg_item, - dentry); + dentry, frag); if (err) { BUG_ON(d_inode(dentry)); d_drop(dentry); @@ -1889,6 +1947,7 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys) unlink_group(group); configfs_release_fs(); } + put_fragment(frag); return err; } diff --git a/fs/configfs/file.c b/fs/configfs/file.c index bab13084fa73..e8caa2c44aac 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -502,7 +502,7 @@ int configfs_create_file(struct config_item * item, const struct configfs_attrib inode_lock_nested(d_inode(dir), I_MUTEX_NORMAL); error = configfs_make_dirent(parent_sd, NULL, (void *) attr, mode, - CONFIGFS_ITEM_ATTR); + CONFIGFS_ITEM_ATTR, parent_sd->s_frag); inode_unlock(d_inode(dir)); return error; @@ -524,7 +524,7 @@ int configfs_create_bin_file(struct config_item *item, inode_lock_nested(dir->d_inode, I_MUTEX_NORMAL); error = configfs_make_dirent(parent_sd, NULL, (void *) bin_attr, mode, - CONFIGFS_ITEM_BIN_ATTR); + CONFIGFS_ITEM_BIN_ATTR, parent_sd->s_frag); inode_unlock(dir->d_inode); return error; From 49824b5c875087a52672b0c8e8ecbefe6f773532 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 31 Aug 2019 09:43:43 +0200 Subject: [PATCH 30/93] configfs: provide exclusion between IO and removals commit b0841eefd9693827afb9888235e26ddd098f9cef upstream. Make sure that attribute methods are not called after the item has been removed from the tree. To do so, we * at the point of no return in removals, grab ->frag_sem exclusive and mark the fragment dead. * call the methods of attributes with ->frag_sem taken shared and only after having verified that the fragment is still alive. The main benefit is for method instances - they are guaranteed that the objects they are accessing *and* all ancestors are still there. Another win is that we don't need to bother with extra refcount on config_item when opening a file - the item will be alive for as long as it stays in the tree, and we won't touch it/attributes/any associated data after it's been removed from the tree. Signed-off-by: Al Viro Signed-off-by: Christoph Hellwig Signed-off-by: Greg Kroah-Hartman --- fs/configfs/dir.c | 23 ++++++++++++++ fs/configfs/file.c | 77 ++++++++++++++++++++++++++++++++++------------ 2 files changed, 81 insertions(+), 19 deletions(-) diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 1362208a8618..c2ef617d2f97 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1474,6 +1474,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry) struct config_item *item; struct configfs_subsystem *subsys; struct configfs_dirent *sd; + struct configfs_fragment *frag; struct module *subsys_owner = NULL, *dead_item_owner = NULL; int ret; @@ -1531,6 +1532,16 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry) } } while (ret == -EAGAIN); + frag = sd->s_frag; + if (down_write_killable(&frag->frag_sem)) { + spin_lock(&configfs_dirent_lock); + configfs_detach_rollback(dentry); + spin_unlock(&configfs_dirent_lock); + return -EINTR; + } + frag->frag_dead = true; + up_write(&frag->frag_sem); + /* Get a working ref for the duration of this function */ item = configfs_get_config_item(dentry); @@ -1832,6 +1843,12 @@ void configfs_unregister_group(struct config_group *group) struct configfs_subsystem *subsys = group->cg_subsys; struct dentry *dentry = group->cg_item.ci_dentry; struct dentry *parent = group->cg_item.ci_parent->ci_dentry; + struct configfs_dirent *sd = dentry->d_fsdata; + struct configfs_fragment *frag = sd->s_frag; + + down_write(&frag->frag_sem); + frag->frag_dead = true; + up_write(&frag->frag_sem); inode_lock_nested(d_inode(parent), I_MUTEX_PARENT); spin_lock(&configfs_dirent_lock); @@ -1957,12 +1974,18 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys) struct config_group *group = &subsys->su_group; struct dentry *dentry = group->cg_item.ci_dentry; struct dentry *root = dentry->d_sb->s_root; + struct configfs_dirent *sd = dentry->d_fsdata; + struct configfs_fragment *frag = sd->s_frag; if (dentry->d_parent != root) { pr_err("Tried to unregister non-subsystem!\n"); return; } + down_write(&frag->frag_sem); + frag->frag_dead = true; + up_write(&frag->frag_sem); + inode_lock_nested(d_inode(root), I_MUTEX_PARENT); inode_lock_nested(d_inode(dentry), I_MUTEX_CHILD); diff --git a/fs/configfs/file.c b/fs/configfs/file.c index e8caa2c44aac..7285440bc62e 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -62,22 +62,32 @@ struct configfs_buffer { }; }; - -static int fill_read_buffer(struct configfs_buffer * buffer) +static inline struct configfs_fragment *to_frag(struct file *file) { - ssize_t count; + struct configfs_dirent *sd = file->f_path.dentry->d_fsdata; + + return sd->s_frag; +} + +static int fill_read_buffer(struct file *file, struct configfs_buffer *buffer) +{ + struct configfs_fragment *frag = to_frag(file); + ssize_t count = -ENOENT; if (!buffer->page) buffer->page = (char *) get_zeroed_page(GFP_KERNEL); if (!buffer->page) return -ENOMEM; - count = buffer->attr->show(buffer->item, buffer->page); + down_read(&frag->frag_sem); + if (!frag->frag_dead) + count = buffer->attr->show(buffer->item, buffer->page); + up_read(&frag->frag_sem); + if (count < 0) return count; if (WARN_ON_ONCE(count > (ssize_t)SIMPLE_ATTR_SIZE)) return -EIO; - buffer->needs_read_fill = 0; buffer->count = count; return 0; @@ -110,7 +120,7 @@ configfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *pp mutex_lock(&buffer->mutex); if (buffer->needs_read_fill) { - retval = fill_read_buffer(buffer); + retval = fill_read_buffer(file, buffer); if (retval) goto out; } @@ -147,6 +157,7 @@ static ssize_t configfs_read_bin_file(struct file *file, char __user *buf, size_t count, loff_t *ppos) { + struct configfs_fragment *frag = to_frag(file); struct configfs_buffer *buffer = file->private_data; ssize_t retval = 0; ssize_t len = min_t(size_t, count, PAGE_SIZE); @@ -162,7 +173,12 @@ configfs_read_bin_file(struct file *file, char __user *buf, if (buffer->needs_read_fill) { /* perform first read with buf == NULL to get extent */ - len = buffer->bin_attr->read(buffer->item, NULL, 0); + down_read(&frag->frag_sem); + if (!frag->frag_dead) + len = buffer->bin_attr->read(buffer->item, NULL, 0); + else + len = -ENOENT; + up_read(&frag->frag_sem); if (len <= 0) { retval = len; goto out; @@ -182,8 +198,13 @@ configfs_read_bin_file(struct file *file, char __user *buf, buffer->bin_buffer_size = len; /* perform second read to fill buffer */ - len = buffer->bin_attr->read(buffer->item, - buffer->bin_buffer, len); + down_read(&frag->frag_sem); + if (!frag->frag_dead) + len = buffer->bin_attr->read(buffer->item, + buffer->bin_buffer, len); + else + len = -ENOENT; + up_read(&frag->frag_sem); if (len < 0) { retval = len; vfree(buffer->bin_buffer); @@ -234,9 +255,16 @@ fill_write_buffer(struct configfs_buffer * buffer, const char __user * buf, size } static int -flush_write_buffer(struct configfs_buffer *buffer, size_t count) +flush_write_buffer(struct file *file, struct configfs_buffer *buffer, size_t count) { - return buffer->attr->store(buffer->item, buffer->page, count); + struct configfs_fragment *frag = to_frag(file); + int res = -ENOENT; + + down_read(&frag->frag_sem); + if (!frag->frag_dead) + res = buffer->attr->store(buffer->item, buffer->page, count); + up_read(&frag->frag_sem); + return res; } @@ -266,7 +294,7 @@ configfs_write_file(struct file *file, const char __user *buf, size_t count, lof mutex_lock(&buffer->mutex); len = fill_write_buffer(buffer, buf, count); if (len > 0) - len = flush_write_buffer(buffer, len); + len = flush_write_buffer(file, buffer, len); if (len > 0) *ppos += len; mutex_unlock(&buffer->mutex); @@ -342,6 +370,7 @@ out: static int __configfs_open_file(struct inode *inode, struct file *file, int type) { struct dentry *dentry = file->f_path.dentry; + struct configfs_fragment *frag = to_frag(file); struct configfs_attribute *attr; struct configfs_buffer *buffer; int error; @@ -351,8 +380,13 @@ static int __configfs_open_file(struct inode *inode, struct file *file, int type if (!buffer) goto out; + error = -ENOENT; + down_read(&frag->frag_sem); + if (unlikely(frag->frag_dead)) + goto out_free_buffer; + error = -EINVAL; - buffer->item = configfs_get_config_item(dentry->d_parent); + buffer->item = to_item(dentry->d_parent); if (!buffer->item) goto out_free_buffer; @@ -410,6 +444,7 @@ static int __configfs_open_file(struct inode *inode, struct file *file, int type buffer->read_in_progress = false; buffer->write_in_progress = false; file->private_data = buffer; + up_read(&frag->frag_sem); return 0; out_put_module: @@ -417,6 +452,7 @@ out_put_module: out_put_item: config_item_put(buffer->item); out_free_buffer: + up_read(&frag->frag_sem); kfree(buffer); out: return error; @@ -426,8 +462,6 @@ static int configfs_release(struct inode *inode, struct file *filp) { struct configfs_buffer *buffer = filp->private_data; - if (buffer->item) - config_item_put(buffer->item); module_put(buffer->owner); if (buffer->page) free_page((unsigned long)buffer->page); @@ -453,12 +487,17 @@ static int configfs_release_bin_file(struct inode *inode, struct file *file) buffer->read_in_progress = false; if (buffer->write_in_progress) { + struct configfs_fragment *frag = to_frag(file); buffer->write_in_progress = false; - /* result of ->release() is ignored */ - buffer->bin_attr->write(buffer->item, buffer->bin_buffer, - buffer->bin_buffer_size); - + down_read(&frag->frag_sem); + if (!frag->frag_dead) { + /* result of ->release() is ignored */ + buffer->bin_attr->write(buffer->item, + buffer->bin_buffer, + buffer->bin_buffer_size); + } + up_read(&frag->frag_sem); /* vfree on NULL is safe */ vfree(buffer->bin_buffer); buffer->bin_buffer = NULL; From fa33be192ea775c7bf77dca0562f05c2cbf06f5e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 3 Aug 2019 11:51:18 -0400 Subject: [PATCH 31/93] configfs: fix a deadlock in configfs_symlink() commit 351e5d869e5ac10cb40c78b5f2d7dfc816ad4587 upstream. Configfs abuses symlink(2). Unlike the normal filesystems, it wants the target resolved at symlink(2) time, like link(2) would've done. The problem is that ->symlink() is called with the parent directory locked exclusive, so resolving the target inside the ->symlink() is easily deadlocked. Short of really ugly games in sys_symlink() itself, all we can do is to unlock the parent before resolving the target and relock it after. However, that invalidates the checks done by the caller of ->symlink(), so we have to * check that dentry is still where it used to be (it couldn't have been moved, but it could've been unhashed) * recheck that it's still negative (somebody else might've successfully created a symlink with the same name while we were looking the target up) * recheck the permissions on the parent directory. Cc: stable@vger.kernel.org Signed-off-by: Al Viro Signed-off-by: Christoph Hellwig Signed-off-by: Greg Kroah-Hartman --- fs/configfs/symlink.c | 33 ++++++++++++++++++++++++++++++++- 1 file changed, 32 insertions(+), 1 deletion(-) diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index fea6db1ee065..afd79a1a34b3 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -157,11 +157,42 @@ int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symna !type->ct_item_ops->allow_link) goto out_put; + /* + * This is really sick. What they wanted was a hybrid of + * link(2) and symlink(2) - they wanted the target resolved + * at syscall time (as link(2) would've done), be a directory + * (which link(2) would've refused to do) *AND* be a deep + * fucking magic, making the target busy from rmdir POV. + * symlink(2) is nothing of that sort, and the locking it + * gets matches the normal symlink(2) semantics. Without + * attempts to resolve the target (which might very well + * not even exist yet) done prior to locking the parent + * directory. This perversion, OTOH, needs to resolve + * the target, which would lead to obvious deadlocks if + * attempted with any directories locked. + * + * Unfortunately, that garbage is userland ABI and we should've + * said "no" back in 2005. Too late now, so we get to + * play very ugly games with locking. + * + * Try *ANYTHING* of that sort in new code, and you will + * really regret it. Just ask yourself - what could a BOFH + * do to me and do I want to find it out first-hand? + * + * AV, a thoroughly annoyed bastard. + */ + inode_unlock(dir); ret = get_target(symname, &path, &target_item, dentry->d_sb); + inode_lock(dir); if (ret) goto out_put; - ret = type->ct_item_ops->allow_link(parent_item, target_item); + if (dentry->d_inode || d_unhashed(dentry)) + ret = -EEXIST; + else + ret = inode_permission(dir, MAY_WRITE | MAY_EXEC); + if (!ret) + ret = type->ct_item_ops->allow_link(parent_item, target_item); if (!ret) { mutex_lock(&configfs_symlink_mutex); ret = create_link(parent_item, target_item, dentry); From d645d6934d08761d75070c9e6ce51792d6791880 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Fri, 15 Dec 2017 10:05:15 -0700 Subject: [PATCH 32/93] usbip: stub_rx: fix static checker warning on unnecessary checks commit 10c90120930628e8b959bf58d4a0aaef3ae5d945 upstream. Fix the following static checker warnings: The patch c6688ef9f297: "usbip: fix stub_rx: harden CMD_SUBMIT path to handle malicious input" from Dec 7, 2017, leads to the following static checker warning: drivers/usb/usbip/stub_rx.c:346 get_pipe() warn: impossible condition '(pdu->u.cmd_submit.transfer_buffer_length > ((~0 >> 1))) => (s32min-s32max > s32max)' drivers/usb/usbip/stub_rx.c:486 stub_recv_cmd_submit() warn: always true condition '(pdu->u.cmd_submit.transfer_buffer_length <= ((~0 >> 1))) => (s32min-s32max <= s32max)' Reported-by: Dan Carpenter Signed-off-by: Shuah Khan Signed-off-by: Greg Kroah-Hartman --- drivers/usb/usbip/stub_rx.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c index 777a4058c407..d47176f9c310 100644 --- a/drivers/usb/usbip/stub_rx.c +++ b/drivers/usb/usbip/stub_rx.c @@ -353,14 +353,6 @@ static int get_pipe(struct stub_device *sdev, struct usbip_header *pdu) epd = &ep->desc; - /* validate transfer_buffer_length */ - if (pdu->u.cmd_submit.transfer_buffer_length > INT_MAX) { - dev_err(&sdev->udev->dev, - "CMD_SUBMIT: -EMSGSIZE transfer_buffer_length %d\n", - pdu->u.cmd_submit.transfer_buffer_length); - return -1; - } - if (usb_endpoint_xfer_control(epd)) { if (dir == USBIP_DIR_OUT) return usb_sndctrlpipe(udev, epnum); @@ -487,8 +479,7 @@ static void stub_recv_cmd_submit(struct stub_device *sdev, } /* allocate urb transfer buffer, if needed */ - if (pdu->u.cmd_submit.transfer_buffer_length > 0 && - pdu->u.cmd_submit.transfer_buffer_length <= INT_MAX) { + if (pdu->u.cmd_submit.transfer_buffer_length > 0) { priv->urb->transfer_buffer = kzalloc(pdu->u.cmd_submit.transfer_buffer_length, GFP_KERNEL); From e2aae1a99c7e24a891a579aba2cb245a291c39fc Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Thu, 24 Jan 2019 14:46:42 -0700 Subject: [PATCH 33/93] usbip: Fix vhci_urb_enqueue() URB null transfer buffer error path commit 2c904963b1dd2acd4bc785b6c72e10a6283c2081 upstream. Fix vhci_urb_enqueue() to print debug msg and return error instead of failing with BUG_ON. Signed-off-by: Shuah Khan Signed-off-by: Greg Kroah-Hartman --- drivers/usb/usbip/vhci_hcd.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c index 9936a2f199b1..ae2f56689537 100644 --- a/drivers/usb/usbip/vhci_hcd.c +++ b/drivers/usb/usbip/vhci_hcd.c @@ -512,8 +512,10 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, } vdev = &vhci->vdev[portnum-1]; - /* patch to usb_sg_init() is in 2.5.60 */ - BUG_ON(!urb->transfer_buffer && urb->transfer_buffer_length); + if (!urb->transfer_buffer && urb->transfer_buffer_length) { + dev_dbg(dev, "Null URB transfer buffer\n"); + return -EINVAL; + } spin_lock_irqsave(&vhci->lock, flags); From d43b763e7b7ec835c95bbd7624288ad80e48c92f Mon Sep 17 00:00:00 2001 From: Nobuo Iwata Date: Thu, 13 Oct 2016 12:49:02 +0900 Subject: [PATCH 34/93] usbip: fix possibility of dereference by NULLL pointer in vhci_hcd.c commit d79cda045e3bacb7e754a5324cd3d4ce80708eb1 upstream. This patch fixes possibility of dereference by NULLL pointer in "[PATCH v5 1/3] usbip: vhci extension: modifications to vhci driver" which has been merged to 4.9-rc1. It occurs when a URB with pointer to invalid USB/IP device is enqueued in race condition against detach operation. A pointer was passed to vdev_to_vhci() before NULL check. In vdev_to_vhci(), there's a dereference by the pointer. This patch moves vdev_to_vhci() after NULL check of the pointer. Signed-off-by: Nobuo Iwata Signed-off-by: Greg Kroah-Hartman --- drivers/usb/usbip/vhci_hcd.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c index ae2f56689537..5108ca50b2e6 100644 --- a/drivers/usb/usbip/vhci_hcd.c +++ b/drivers/usb/usbip/vhci_hcd.c @@ -465,13 +465,14 @@ static void vhci_tx_urb(struct urb *urb) { struct vhci_device *vdev = get_vdev(urb->dev); struct vhci_priv *priv; - struct vhci_hcd *vhci = vdev_to_vhci(vdev); + struct vhci_hcd *vhci; unsigned long flags; if (!vdev) { pr_err("could not get virtual device"); return; } + vhci = vdev_to_vhci(vdev); priv = kzalloc(sizeof(struct vhci_priv), GFP_ATOMIC); if (!priv) { From 0e216dbf7d7c56b866e264cea9a746ec9083d9ae Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 9 Feb 2017 01:49:56 -0600 Subject: [PATCH 35/93] drivers: usb: usbip: Add missing break statement to switch commit 7c92e5fbf4dac0dd4dd41a0383adc54f16f403e2 upstream. Add missing break statement to prevent the code for case USB_PORT_FEAT_C_RESET falling through to the default case. Addresses-Coverity-ID: 143155 Signed-off-by: Gustavo A. R. Silva Signed-off-by: Greg Kroah-Hartman --- drivers/usb/usbip/vhci_hcd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c index 5108ca50b2e6..8bda6455dfcb 100644 --- a/drivers/usb/usbip/vhci_hcd.c +++ b/drivers/usb/usbip/vhci_hcd.c @@ -318,6 +318,7 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, default: break; } + break; default: usbip_dbg_vhci_rh(" ClearPortFeature: default %x\n", wValue); From f7f886b51bf6ff8b2a621669e1b4c306177a6e5f Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Thu, 4 Jul 2019 20:34:28 +0530 Subject: [PATCH 36/93] PCI: tegra: Enable Relaxed Ordering only for Tegra20 & Tegra30 commit 7be142caabc4780b13a522c485abc806de5c4114 upstream. The PCI Tegra controller conversion to a device tree configurable driver in commit d1523b52bff3 ("PCI: tegra: Move PCIe driver to drivers/pci/host") implied that code for the driver can be compiled in for a kernel supporting multiple platforms. Unfortunately, a blind move of the code did not check that some of the quirks that were applied in arch/arm (eg enabling Relaxed Ordering on all PCI devices - since the quirk hook erroneously matches PCI_ANY_ID for both Vendor-ID and Device-ID) are now applied in all kernels that compile the PCI Tegra controlled driver, DT and ACPI alike. This is completely wrong, in that enablement of Relaxed Ordering is only required by default in Tegra20 platforms as described in the Tegra20 Technical Reference Manual (available at https://developer.nvidia.com/embedded/downloads#?search=tegra%202 in Section 34.1, where it is mentioned that Relaxed Ordering bit needs to be enabled in its root ports to avoid deadlock in hardware) and in the Tegra30 platforms for the same reasons (unfortunately not documented in the TRM). There is no other strict requirement on PCI devices Relaxed Ordering enablement on any other Tegra platforms or PCI host bridge driver. Fix this quite upsetting situation by limiting the vendor and device IDs to which the Relaxed Ordering quirk applies to the root ports in question, reported above. Signed-off-by: Vidya Sagar [lorenzo.pieralisi@arm.com: completely rewrote the commit log/fixes tag] Signed-off-by: Lorenzo Pieralisi Acked-by: Thierry Reding Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-tegra.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c index 8e101b19c4d6..90be00c1bab9 100644 --- a/drivers/pci/host/pci-tegra.c +++ b/drivers/pci/host/pci-tegra.c @@ -603,12 +603,15 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0bf1, tegra_pcie_fixup_class); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0e1c, tegra_pcie_fixup_class); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0e1d, tegra_pcie_fixup_class); -/* Tegra PCIE requires relaxed ordering */ +/* Tegra20 and Tegra30 PCIE requires relaxed ordering */ static void tegra_pcie_relax_enable(struct pci_dev *dev) { pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_RELAX_EN); } -DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, tegra_pcie_relax_enable); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0bf0, tegra_pcie_relax_enable); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0bf1, tegra_pcie_relax_enable); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0e1c, tegra_pcie_relax_enable); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0e1d, tegra_pcie_relax_enable); static int tegra_pcie_setup(int nr, struct pci_sys_data *sys) { From 35614acc10ff2d04f5fd1ad019d0cec708294d6b Mon Sep 17 00:00:00 2001 From: Radhey Shyam Pandey Date: Thu, 26 Sep 2019 16:20:58 +0530 Subject: [PATCH 37/93] dmaengine: xilinx_dma: Fix control reg update in vdma_channel_set_config [ Upstream commit 6c6de1ddb1be3840f2ed5cc9d009a622720940c9 ] In vdma_channel_set_config clear the delay, frame count and master mask before updating their new values. It avoids programming incorrect state when input parameters are different from default. Signed-off-by: Radhey Shyam Pandey Acked-by: Appana Durga Kedareswara rao Signed-off-by: Michal Simek Link: https://lore.kernel.org/r/1569495060-18117-3-git-send-email-radhey.shyam.pandey@xilinx.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/xilinx/xilinx_dma.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index 8288fe4d17c3..cd271f782605 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -72,6 +72,9 @@ #define XILINX_DMA_DMACR_CIRC_EN BIT(1) #define XILINX_DMA_DMACR_RUNSTOP BIT(0) #define XILINX_DMA_DMACR_FSYNCSRC_MASK GENMASK(6, 5) +#define XILINX_DMA_DMACR_DELAY_MASK GENMASK(31, 24) +#define XILINX_DMA_DMACR_FRAME_COUNT_MASK GENMASK(23, 16) +#define XILINX_DMA_DMACR_MASTER_MASK GENMASK(11, 8) #define XILINX_DMA_REG_DMASR 0x0004 #define XILINX_DMA_DMASR_EOL_LATE_ERR BIT(15) @@ -2054,8 +2057,10 @@ int xilinx_vdma_channel_set_config(struct dma_chan *dchan, chan->config.gen_lock = cfg->gen_lock; chan->config.master = cfg->master; + dmacr &= ~XILINX_DMA_DMACR_GENLOCK_EN; if (cfg->gen_lock && chan->genlock) { dmacr |= XILINX_DMA_DMACR_GENLOCK_EN; + dmacr &= ~XILINX_DMA_DMACR_MASTER_MASK; dmacr |= cfg->master << XILINX_DMA_DMACR_MASTER_SHIFT; } @@ -2069,11 +2074,13 @@ int xilinx_vdma_channel_set_config(struct dma_chan *dchan, chan->config.delay = cfg->delay; if (cfg->coalesc <= XILINX_DMA_DMACR_FRAME_COUNT_MAX) { + dmacr &= ~XILINX_DMA_DMACR_FRAME_COUNT_MASK; dmacr |= cfg->coalesc << XILINX_DMA_DMACR_FRAME_COUNT_SHIFT; chan->config.coalesc = cfg->coalesc; } if (cfg->delay <= XILINX_DMA_DMACR_DELAY_MAX) { + dmacr &= ~XILINX_DMA_DMACR_DELAY_MASK; dmacr |= cfg->delay << XILINX_DMA_DMACR_DELAY_SHIFT; chan->config.delay = cfg->delay; } From 5af2eb2ffa62b5f27aeb609bbd46e88674f14c1f Mon Sep 17 00:00:00 2001 From: Zhang Lixu Date: Wed, 16 Oct 2019 08:15:59 +0800 Subject: [PATCH 38/93] HID: intel-ish-hid: fix wrong error handling in ishtp_cl_alloc_tx_ring() [ Upstream commit 16ff7bf6dbcc6f77d2eec1ac9120edf44213c2f1 ] When allocating tx ring buffers failed, should free tx buffers, not rx buffers. Signed-off-by: Zhang Lixu Acked-by: Srinivas Pandruvada Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/intel-ish-hid/ishtp/client-buffers.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/intel-ish-hid/ishtp/client-buffers.c b/drivers/hid/intel-ish-hid/ishtp/client-buffers.c index b9b917d2d50d..c41dbb167c91 100644 --- a/drivers/hid/intel-ish-hid/ishtp/client-buffers.c +++ b/drivers/hid/intel-ish-hid/ishtp/client-buffers.c @@ -90,7 +90,7 @@ int ishtp_cl_alloc_tx_ring(struct ishtp_cl *cl) return 0; out: dev_err(&cl->device->dev, "error in allocating Tx pool\n"); - ishtp_cl_free_rx_ring(cl); + ishtp_cl_free_tx_ring(cl); return -ENOMEM; } From 59e736bab849c2db967eb01c3847042779417a2c Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Fri, 18 Oct 2019 16:04:58 +0200 Subject: [PATCH 39/93] scsi: qla2xxx: fixup incorrect usage of host_byte [ Upstream commit 66cf50e65b183c863825f5c28a818e3f47a72e40 ] DRIVER_ERROR is a a driver byte setting, not a host byte. The qla2xxx driver should rather return DID_ERROR here to be in line with the other drivers. Link: https://lore.kernel.org/r/20191018140458.108278-1-hare@suse.de Signed-off-by: Hannes Reinecke Acked-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qla2xxx/qla_bsg.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c index 4a6e086279f9..33e4dceb895f 100644 --- a/drivers/scsi/qla2xxx/qla_bsg.c +++ b/drivers/scsi/qla2xxx/qla_bsg.c @@ -252,7 +252,7 @@ qla2x00_process_els(struct fc_bsg_job *bsg_job) srb_t *sp; const char *type; int req_sg_cnt, rsp_sg_cnt; - int rval = (DRIVER_ERROR << 16); + int rval = (DID_ERROR << 16); uint16_t nextlid = 0; if (bsg_job->request->msgcode == FC_BSG_RPT_ELS) { @@ -426,7 +426,7 @@ qla2x00_process_ct(struct fc_bsg_job *bsg_job) struct Scsi_Host *host = bsg_job->shost; scsi_qla_host_t *vha = shost_priv(host); struct qla_hw_data *ha = vha->hw; - int rval = (DRIVER_ERROR << 16); + int rval = (DID_ERROR << 16); int req_sg_cnt, rsp_sg_cnt; uint16_t loop_id; struct fc_port *fcport; @@ -1911,7 +1911,7 @@ qlafx00_mgmt_cmd(struct fc_bsg_job *bsg_job) struct Scsi_Host *host = bsg_job->shost; scsi_qla_host_t *vha = shost_priv(host); struct qla_hw_data *ha = vha->hw; - int rval = (DRIVER_ERROR << 16); + int rval = (DID_ERROR << 16); struct qla_mt_iocb_rqst_fx00 *piocb_rqst; srb_t *sp; int req_sg_cnt = 0, rsp_sg_cnt = 0; From 21ed3ef92556bf616d6aa905c4473086139cee90 Mon Sep 17 00:00:00 2001 From: Daniel Wagner Date: Tue, 22 Oct 2019 09:21:12 +0200 Subject: [PATCH 40/93] scsi: lpfc: Honor module parameter lpfc_use_adisc [ Upstream commit 0fd103ccfe6a06e40e2d9d8c91d96332cc9e1239 ] The initial lpfc_desc_set_adisc implementation in commit dea3101e0a5c ("lpfc: add Emulex FC driver version 8.0.28") enabled ADISC if cfg_use_adisc && RSCN_MODE && FCP_2_DEVICE In commit 92d7f7b0cde3 ("[SCSI] lpfc: NPIV: add NPIV support on top of SLI-3") this changed to (cfg_use_adisc && RSC_MODE) || FCP_2_DEVICE and later in commit ffc954936b13 ("[SCSI] lpfc 8.3.13: FC Discovery Fixes and enhancements.") to (cfg_use_adisc && RSC_MODE) || (FCP_2_DEVICE && FCP_TARGET) A customer reports that after a devloss, an ADISC failure is logged. It turns out the ADISC flag is set even the user explicitly set lpfc_use_adisc = 0. [Sat Dec 22 22:55:58 2018] lpfc 0000:82:00.0: 2:(0):0203 Devloss timeout on WWPN 50:01:43:80:12:8e:40:20 NPort x05df00 Data: x82000000 x8 xa [Sat Dec 22 23:08:20 2018] lpfc 0000:82:00.0: 2:(0):2755 ADISC failure DID:05DF00 Status:x9/x70000 [mkp: fixed Hannes' email] Fixes: 92d7f7b0cde3 ("[SCSI] lpfc: NPIV: add NPIV support on top of SLI-3") Cc: Dick Kennedy Cc: James Smart Link: https://lore.kernel.org/r/20191022072112.132268-1-dwagner@suse.de Reviewed-by: Hannes Reinecke Reviewed-by: James Smart Signed-off-by: Daniel Wagner Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/lpfc/lpfc_nportdisc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c index 56a3df4fddb0..21ec7b5b6c85 100644 --- a/drivers/scsi/lpfc/lpfc_nportdisc.c +++ b/drivers/scsi/lpfc/lpfc_nportdisc.c @@ -759,9 +759,9 @@ lpfc_disc_set_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) if (!(vport->fc_flag & FC_PT2PT)) { /* Check config parameter use-adisc or FCP-2 */ - if ((vport->cfg_use_adisc && (vport->fc_flag & FC_RSCN_MODE)) || + if (vport->cfg_use_adisc && ((vport->fc_flag & FC_RSCN_MODE) || ((ndlp->nlp_fcp_info & NLP_FCP_2_DEVICE) && - (ndlp->nlp_type & NLP_FCP_TARGET))) { + (ndlp->nlp_type & NLP_FCP_TARGET)))) { spin_lock_irq(shost->host_lock); ndlp->nlp_flag |= NLP_NPR_ADISC; spin_unlock_irq(shost->host_lock); From a4b012c648780b19fea13c1601ba091713f84f58 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 23 Oct 2019 09:53:03 -0700 Subject: [PATCH 41/93] ipvs: move old_secure_tcp into struct netns_ipvs [ Upstream commit c24b75e0f9239e78105f81c5f03a751641eb07ef ] syzbot reported the following issue : BUG: KCSAN: data-race in update_defense_level / update_defense_level read to 0xffffffff861a6260 of 4 bytes by task 3006 on cpu 1: update_defense_level+0x621/0xb30 net/netfilter/ipvs/ip_vs_ctl.c:177 defense_work_handler+0x3d/0xd0 net/netfilter/ipvs/ip_vs_ctl.c:225 process_one_work+0x3d4/0x890 kernel/workqueue.c:2269 worker_thread+0xa0/0x800 kernel/workqueue.c:2415 kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352 write to 0xffffffff861a6260 of 4 bytes by task 7333 on cpu 0: update_defense_level+0xa62/0xb30 net/netfilter/ipvs/ip_vs_ctl.c:205 defense_work_handler+0x3d/0xd0 net/netfilter/ipvs/ip_vs_ctl.c:225 process_one_work+0x3d4/0x890 kernel/workqueue.c:2269 worker_thread+0xa0/0x800 kernel/workqueue.c:2415 kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 7333 Comm: kworker/0:5 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: events defense_work_handler Indeed, old_secure_tcp is currently a static variable, while it needs to be a per netns variable. Fixes: a0840e2e165a ("IPVS: netns, ip_vs_ctl local vars moved to ipvs struct.") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: Simon Horman Signed-off-by: Sasha Levin --- include/net/ip_vs.h | 1 + net/netfilter/ipvs/ip_vs_ctl.c | 15 +++++++-------- 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index cd6018a9ee24..a26165744d98 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -887,6 +887,7 @@ struct netns_ipvs { struct delayed_work defense_work; /* Work handler */ int drop_rate; int drop_counter; + int old_secure_tcp; atomic_t dropentry; /* locks in ctl.c */ spinlock_t dropentry_lock; /* drop entry handling */ diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 8037b25ddb76..33125fc009cf 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -97,7 +97,6 @@ static bool __ip_vs_addr_is_local_v6(struct net *net, static void update_defense_level(struct netns_ipvs *ipvs) { struct sysinfo i; - static int old_secure_tcp = 0; int availmem; int nomem; int to_change = -1; @@ -178,35 +177,35 @@ static void update_defense_level(struct netns_ipvs *ipvs) spin_lock(&ipvs->securetcp_lock); switch (ipvs->sysctl_secure_tcp) { case 0: - if (old_secure_tcp >= 2) + if (ipvs->old_secure_tcp >= 2) to_change = 0; break; case 1: if (nomem) { - if (old_secure_tcp < 2) + if (ipvs->old_secure_tcp < 2) to_change = 1; ipvs->sysctl_secure_tcp = 2; } else { - if (old_secure_tcp >= 2) + if (ipvs->old_secure_tcp >= 2) to_change = 0; } break; case 2: if (nomem) { - if (old_secure_tcp < 2) + if (ipvs->old_secure_tcp < 2) to_change = 1; } else { - if (old_secure_tcp >= 2) + if (ipvs->old_secure_tcp >= 2) to_change = 0; ipvs->sysctl_secure_tcp = 1; } break; case 3: - if (old_secure_tcp < 2) + if (ipvs->old_secure_tcp < 2) to_change = 1; break; } - old_secure_tcp = ipvs->sysctl_secure_tcp; + ipvs->old_secure_tcp = ipvs->sysctl_secure_tcp; if (to_change >= 0) ip_vs_protocol_timeout_change(ipvs, ipvs->sysctl_secure_tcp > 1); From c368df30c8331b83ea3e7802d16cea4cfae92ee3 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 21 Oct 2019 18:47:52 +0000 Subject: [PATCH 42/93] bonding: fix unexpected IFF_BONDING bit unset [ Upstream commit 65de65d9033750d2cf1b336c9d6e9da3a8b5cc6e ] The IFF_BONDING means bonding master or bonding slave device. ->ndo_add_slave() sets IFF_BONDING flag and ->ndo_del_slave() unsets IFF_BONDING flag. bond0<--bond1 Both bond0 and bond1 are bonding device and these should keep having IFF_BONDING flag until they are removed. But bond1 would lose IFF_BONDING at ->ndo_del_slave() because that routine do not check whether the slave device is the bonding type or not. This patch adds the interface type check routine before removing IFF_BONDING flag. Test commands: ip link add bond0 type bond ip link add bond1 type bond ip link set bond1 master bond0 ip link set bond1 nomaster ip link del bond1 type bond ip link add bond1 type bond Splat looks like: [ 226.665555] proc_dir_entry 'bonding/bond1' already registered [ 226.666440] WARNING: CPU: 0 PID: 737 at fs/proc/generic.c:361 proc_register+0x2a9/0x3e0 [ 226.667571] Modules linked in: bonding af_packet sch_fq_codel ip_tables x_tables unix [ 226.668662] CPU: 0 PID: 737 Comm: ip Not tainted 5.4.0-rc3+ #96 [ 226.669508] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 226.670652] RIP: 0010:proc_register+0x2a9/0x3e0 [ 226.671612] Code: 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 39 01 00 00 48 8b 04 24 48 89 ea 48 c7 c7 a0 0b 14 9f 48 8b b0 e 0 00 00 00 e8 07 e7 88 ff <0f> 0b 48 c7 c7 40 2d a5 9f e8 59 d6 23 01 48 8b 4c 24 10 48 b8 00 [ 226.675007] RSP: 0018:ffff888050e17078 EFLAGS: 00010282 [ 226.675761] RAX: dffffc0000000008 RBX: ffff88805fdd0f10 RCX: ffffffff9dd344e2 [ 226.676757] RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffff88806c9f6b8c [ 226.677751] RBP: ffff8880507160f3 R08: ffffed100d940019 R09: ffffed100d940019 [ 226.678761] R10: 0000000000000001 R11: ffffed100d940018 R12: ffff888050716008 [ 226.679757] R13: ffff8880507160f2 R14: dffffc0000000000 R15: ffffed100a0e2c1e [ 226.680758] FS: 00007fdc217cc0c0(0000) GS:ffff88806c800000(0000) knlGS:0000000000000000 [ 226.681886] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 226.682719] CR2: 00007f49313424d0 CR3: 0000000050e46001 CR4: 00000000000606f0 [ 226.683727] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 226.684725] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 226.685681] Call Trace: [ 226.687089] proc_create_seq_private+0xb3/0xf0 [ 226.687778] bond_create_proc_entry+0x1b3/0x3f0 [bonding] [ 226.691458] bond_netdev_event+0x433/0x970 [bonding] [ 226.692139] ? __module_text_address+0x13/0x140 [ 226.692779] notifier_call_chain+0x90/0x160 [ 226.693401] register_netdevice+0x9b3/0xd80 [ 226.694010] ? alloc_netdev_mqs+0x854/0xc10 [ 226.694629] ? netdev_change_features+0xa0/0xa0 [ 226.695278] ? rtnl_create_link+0x2ed/0xad0 [ 226.695849] bond_newlink+0x2a/0x60 [bonding] [ 226.696422] __rtnl_newlink+0xb9f/0x11b0 [ 226.696968] ? rtnl_link_unregister+0x220/0x220 [ ... ] Fixes: 0b680e753724 ("[PATCH] bonding: Add priv_flag to avoid event mishandling") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/bonding/bond_main.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c1971bca62fb..d52fd842ef1f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1759,7 +1759,8 @@ err_detach: slave_disable_netpoll(new_slave); err_close: - slave_dev->priv_flags &= ~IFF_BONDING; + if (!netif_is_bond_master(slave_dev)) + slave_dev->priv_flags &= ~IFF_BONDING; dev_close(slave_dev); err_restore_mac: @@ -1960,7 +1961,8 @@ static int __bond_release_one(struct net_device *bond_dev, dev_set_mtu(slave_dev, slave->original_mtu); - slave_dev->priv_flags &= ~IFF_BONDING; + if (!netif_is_bond_master(slave_dev)) + slave_dev->priv_flags &= ~IFF_BONDING; bond_free_slave(slave); From 954d05646f68e36a18451fe208f2dc39be7c46e3 Mon Sep 17 00:00:00 2001 From: Nikhil Badola Date: Mon, 21 Oct 2019 18:21:51 +0800 Subject: [PATCH 43/93] usb: fsl: Check memory resource before releasing it [ Upstream commit bc1e3a2dd0c9954fd956ac43ca2876bbea018c01 ] Check memory resource existence before releasing it to avoid NULL pointer dereference Signed-off-by: Nikhil Badola Reviewed-by: Ran Wang Reviewed-by: Peter Chen Signed-off-by: Felipe Balbi Signed-off-by: Sasha Levin --- drivers/usb/gadget/udc/fsl_udc_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c index 8991a4070792..bd98557caa28 100644 --- a/drivers/usb/gadget/udc/fsl_udc_core.c +++ b/drivers/usb/gadget/udc/fsl_udc_core.c @@ -2570,7 +2570,7 @@ static int fsl_udc_remove(struct platform_device *pdev) dma_pool_destroy(udc_controller->td_pool); free_irq(udc_controller->irq, udc_controller); iounmap(dr_regs); - if (pdata->operating_mode == FSL_USB2_DR_DEVICE) + if (res && (pdata->operating_mode == FSL_USB2_DR_DEVICE)) release_mem_region(res->start, resource_size(res)); /* free udc --wait for the release() finished */ From 76e7146038b21f02d29343216f3a9c42995fddcf Mon Sep 17 00:00:00 2001 From: Cristian Birsan Date: Fri, 4 Oct 2019 20:10:54 +0300 Subject: [PATCH 44/93] usb: gadget: udc: atmel: Fix interrupt storm in FIFO mode. [ Upstream commit ba3a1a915c49cc3023e4ddfc88f21e7514e82aa4 ] Fix interrupt storm generated by endpoints when working in FIFO mode. The TX_COMPLETE interrupt is used only by control endpoints processing. Do not enable it for other types of endpoints. Fixes: 914a3f3b3754 ("USB: add atmel_usba_udc driver") Signed-off-by: Cristian Birsan Signed-off-by: Felipe Balbi Signed-off-by: Sasha Levin --- drivers/usb/gadget/udc/atmel_usba_udc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c index 9705bcdbc577..57dd3bad9539 100644 --- a/drivers/usb/gadget/udc/atmel_usba_udc.c +++ b/drivers/usb/gadget/udc/atmel_usba_udc.c @@ -403,9 +403,11 @@ static void submit_request(struct usba_ep *ep, struct usba_request *req) next_fifo_transaction(ep, req); if (req->last_transaction) { usba_ep_writel(ep, CTL_DIS, USBA_TX_PK_RDY); - usba_ep_writel(ep, CTL_ENB, USBA_TX_COMPLETE); + if (ep_is_control(ep)) + usba_ep_writel(ep, CTL_ENB, USBA_TX_COMPLETE); } else { - usba_ep_writel(ep, CTL_DIS, USBA_TX_COMPLETE); + if (ep_is_control(ep)) + usba_ep_writel(ep, CTL_DIS, USBA_TX_COMPLETE); usba_ep_writel(ep, CTL_ENB, USBA_TX_PK_RDY); } } From 1dd7015a9b09cda42af3922427508c4b9c9c5bb1 Mon Sep 17 00:00:00 2001 From: Chandana Kishori Chiluveru Date: Tue, 1 Oct 2019 13:16:48 +0530 Subject: [PATCH 45/93] usb: gadget: composite: Fix possible double free memory bug [ Upstream commit 1c20c89b0421b52b2417bb0f62a611bc669eda1d ] composite_dev_cleanup call from the failure of configfs_composite_bind frees up the cdev->os_desc_req and cdev->req. If the previous calls of bind and unbind is successful these will carry stale values. Consider the below sequence of function calls: configfs_composite_bind() composite_dev_prepare() - Allocate cdev->req, cdev->req->buf composite_os_desc_req_prepare() - Allocate cdev->os_desc_req, cdev->os_desc_req->buf configfs_composite_unbind() composite_dev_cleanup() - free the cdev->os_desc_req->buf and cdev->req->buf Next composition switch configfs_composite_bind() - If it fails goto err_comp_cleanup will call the composite_dev_cleanup() function composite_dev_cleanup() - calls kfree up with the stale values of cdev->req->buf and cdev->os_desc_req from the previous configfs_composite_bind call. The free call on these stale values leads to double free. Hence, Fix this issue by setting request and buffer pointer to NULL after kfree. Signed-off-by: Chandana Kishori Chiluveru Signed-off-by: Felipe Balbi Signed-off-by: Sasha Levin --- drivers/usb/gadget/composite.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 9fa168af847b..854c4ec0af2c 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -2179,14 +2179,18 @@ void composite_dev_cleanup(struct usb_composite_dev *cdev) usb_ep_dequeue(cdev->gadget->ep0, cdev->os_desc_req); kfree(cdev->os_desc_req->buf); + cdev->os_desc_req->buf = NULL; usb_ep_free_request(cdev->gadget->ep0, cdev->os_desc_req); + cdev->os_desc_req = NULL; } if (cdev->req) { if (cdev->setup_pending) usb_ep_dequeue(cdev->gadget->ep0, cdev->req); kfree(cdev->req->buf); + cdev->req->buf = NULL; usb_ep_free_request(cdev->gadget->ep0, cdev->req); + cdev->req = NULL; } cdev->next_string_id = 0; device_remove_file(&cdev->gadget->dev, &dev_attr_suspended); From aa919ef9a34b29e79b7a3fef79df7165376a4cf1 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Mon, 26 Aug 2019 15:10:55 -0400 Subject: [PATCH 46/93] usb: gadget: configfs: fix concurrent issue between composite APIs [ Upstream commit 1a1c851bbd706ea9f3a9756c2d3db28523506d3b ] We meet several NULL pointer issues if configfs_composite_unbind and composite_setup (or composite_disconnect) are running together. These issues occur when do the function switch stress test, the configfs_compsoite_unbind is called from user mode by echo "" to /sys/../UDC entry, and meanwhile, the setup interrupt or disconnect interrupt occurs by hardware. The composite_setup will get the cdev from get_gadget_data, but configfs_composite_unbind will set gadget data as NULL, so the NULL pointer issue occurs. This concurrent is hard to reproduce by native kernel, but can be reproduced by android kernel. In this commit, we introduce one spinlock belongs to structure gadget_info since we can't use the same spinlock in usb_composite_dev due to exclusive running together between composite_setup and configfs_composite_unbind. And one bit flag 'unbind' to indicate the code is at unbind routine, this bit is needed due to we release the lock at during configfs_composite_unbind sometimes, and composite_setup may be run at that time. Several oops: oops 1: android_work: sent uevent USB_STATE=CONNECTED configfs-gadget gadget: super-speed config #1: b android_work: sent uevent USB_STATE=CONFIGURED init: Received control message 'start' for 'adbd' from pid: 3515 (system_server) Unable to handle kernel NULL pointer dereference at virtual address 0000002a init: Received control message 'stop' for 'adbd' from pid: 3375 (/vendor/bin/hw/android.hardware.usb@1.1-servic) Mem abort info: Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 user pgtable: 4k pages, 48-bit VAs, pgd = ffff8008f1b7f000 [000000000000002a] *pgd=0000000000000000 Internal error: Oops: 96000004 [#1] PREEMPT SMP Modules linked in: CPU: 4 PID: 2457 Comm: irq/125-5b11000 Not tainted 4.14.98-07846-g0b40a9b-dirty #16 Hardware name: Freescale i.MX8QM MEK (DT) task: ffff8008f2a98000 task.stack: ffff00000b7b8000 PC is at composite_setup+0x44/0x1508 LR is at android_setup+0xb8/0x13c pc : [] lr : [] pstate: 800001c5 sp : ffff00000b7bbb80 x29: ffff00000b7bbb80 x28: ffff8008f2a3c010 x27: 0000000000000001 x26: 0000000000000000 [1232/1897] audit: audit_lost=25791 audit_rate_limit=5 audit_backlog_limit=64 x25: 00000000ffffffa1 x24: ffff8008f2a3c010 audit: rate limit exceeded x23: 0000000000000409 x22: ffff000009c8e000 x21: ffff8008f7a8b428 x20: ffff00000afae000 x19: ffff0000089ff000 x18: 0000000000000000 x17: 0000000000000000 x16: ffff0000082b7c9c x15: 0000000000000000 x14: f1866f5b952aca46 x13: e35502e30d44349c x12: 0000000000000008 x11: 0000000000000008 x10: 0000000000000a30 x9 : ffff00000b7bbd00 x8 : ffff8008f2a98a90 x7 : ffff8008f27a9c90 x6 : 0000000000000001 x5 : 0000000000000000 x4 : 0000000000000001 x3 : 0000000000000000 x2 : 0000000000000006 x1 : ffff0000089ff8d0 x0 : 732a010310b9ed00 X7: 0xffff8008f27a9c10: 9c10 00000002 00000000 00000001 00000000 13110000 ffff0000 00000002 00208040 9c30 00000000 00000000 00000000 00000000 00000000 00000005 00000029 00000000 9c50 00051778 00000001 f27a8e00 ffff8008 00000005 00000000 00000078 00000078 9c70 00000078 00000000 09031d48 ffff0000 00100000 00000000 00400000 00000000 9c90 00000001 00000000 00000000 00000000 00000000 00000000 ffefb1a0 ffff8008 9cb0 f27a9ca8 ffff8008 00000000 00000000 b9d88037 00000173 1618a3eb 00000001 9cd0 870a792a 0000002e 16188fe6 00000001 0000242b 00000000 00000000 00000000 using random self ethernet address 9cf0 019a4646 00000000 000547f3 00000000 ecfd6c33 00000002 00000000 using random host ethernet address 00000000 X8: 0xffff8008f2a98a10: 8a10 00000000 00000000 f7788d00 ffff8008 00000001 00000000 00000000 00000000 8a30 eb218000 ffff8008 f2a98000 ffff8008 f2a98000 ffff8008 09885000 ffff0000 8a50 f34df480 ffff8008 00000000 00000000 f2a98648 ffff8008 09c8e000 ffff0000 8a70 fff2c800 ffff8008 09031d48 ffff0000 0b7bbd00 ffff0000 0b7bbd00 ffff0000 8a90 080861bc ffff0000 00000000 00000000 00000000 00000000 00000000 00000000 8ab0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 8ad0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 8af0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 X21: 0xffff8008f7a8b3a8: b3a8 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 b3c8 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 b3e8 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 b408 00000000 00000000 00000000 00000000 00000000 00000000 00000001 00000000 b428 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 b448 0053004d 00540046 00300031 00010030 eb07b520 ffff8008 20011201 00000003 b468 e418d109 0104404e 00010302 00000000 eb07b558 ffff8008 eb07b558 ffff8008 b488 f7a8b488 ffff8008 f7a8b488 ffff8008 f7a8b300 ffff8008 00000000 00000000 X24: 0xffff8008f2a3bf90: bf90 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 bfb0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 bfd0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 bff0 00000000 00000000 00000000 00000000 f76c8010 ffff8008 f76c8010 ffff8008 c010 00000000 00000000 f2a3c018 ffff8008 f2a3c018 ffff8008 08a067dc ffff0000 c030 f2a5a000 ffff8008 091c3650 ffff0000 f716fd18 ffff8008 f716fe30 ffff8008 c050 f2ce4a30 ffff8008 00000000 00000005 00000000 00000000 095d1568 ffff0000 c070 f76c8010 ffff8008 f2ce4b00 ffff8008 095cac68 ffff0000 f2a5a028 ffff8008 X28: 0xffff8008f2a3bf90: bf90 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 bfb0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 bfd0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 bff0 00000000 00000000 00000000 00000000 f76c8010 ffff8008 f76c8010 ffff8008 c010 00000000 00000000 f2a3c018 ffff8008 f2a3c018 ffff8008 08a067dc ffff0000 c030 f2a5a000 ffff8008 091c3650 ffff0000 f716fd18 ffff8008 f716fe30 ffff8008 c050 f2ce4a30 ffff8008 00000000 00000005 00000000 00000000 095d1568 ffff0000 c070 f76c8010 ffff8008 f2ce4b00 ffff8008 095cac68 ffff0000 f2a5a028 ffff8008 Process irq/125-5b11000 (pid: 2457, stack limit = 0xffff00000b7b8000) Call trace: Exception stack(0xffff00000b7bba40 to 0xffff00000b7bbb80) ba40: 732a010310b9ed00 ffff0000089ff8d0 0000000000000006 0000000000000000 ba60: 0000000000000001 0000000000000000 0000000000000001 ffff8008f27a9c90 ba80: ffff8008f2a98a90 ffff00000b7bbd00 0000000000000a30 0000000000000008 baa0: 0000000000000008 e35502e30d44349c f1866f5b952aca46 0000000000000000 bac0: ffff0000082b7c9c 0000000000000000 0000000000000000 ffff0000089ff000 bae0: ffff00000afae000 ffff8008f7a8b428 ffff000009c8e000 0000000000000409 bb00: ffff8008f2a3c010 00000000ffffffa1 0000000000000000 0000000000000001 bb20: ffff8008f2a3c010 ffff00000b7bbb80 ffff000008a032fc ffff00000b7bbb80 bb40: ffff0000089ffb3c 00000000800001c5 ffff00000b7bbb80 732a010310b9ed00 bb60: ffffffffffffffff ffff0000080f777c ffff00000b7bbb80 ffff0000089ffb3c [] composite_setup+0x44/0x1508 [] android_setup+0xb8/0x13c [] cdns3_ep0_delegate_req+0x44/0x70 [] cdns3_check_ep0_interrupt_proceed+0x33c/0x654 [] cdns3_device_thread_irq_handler+0x4b0/0x4bc [] cdns3_thread_irq+0x48/0x68 [] irq_thread_fn+0x28/0x88 [] irq_thread+0x13c/0x228 [] kthread+0x104/0x130 [] ret_from_fork+0x10/0x18 oops2: composite_disconnect: Calling disconnect on a Gadget that is not connected android_work: did not send uevent (0 0 (null)) init: Received control message 'stop' for 'adbd' from pid: 3359 (/vendor/bin/hw/android.hardware.usb@1.1-service.imx) init: Sending signal 9 to service 'adbd' (pid 22343) process group... ------------[ cut here ]------------ audit: audit_lost=180038 audit_rate_limit=5 audit_backlog_limit=64 audit: rate limit exceeded WARNING: CPU: 0 PID: 3468 at kernel_imx/drivers/usb/gadget/composite.c:2009 composite_disconnect+0x80/0x88 Modules linked in: CPU: 0 PID: 3468 Comm: HWC-UEvent-Thre Not tainted 4.14.98-07846-g0b40a9b-dirty #16 Hardware name: Freescale i.MX8QM MEK (DT) task: ffff8008f2349c00 task.stack: ffff00000b0a8000 PC is at composite_disconnect+0x80/0x88 LR is at composite_disconnect+0x80/0x88 pc : [] lr : [] pstate: 600001c5 sp : ffff000008003dd0 x29: ffff000008003dd0 x28: ffff8008f2349c00 x27: ffff000009885018 x26: ffff000008004000 Timeout for IPC response! x25: ffff000009885018 x24: ffff000009c8e280 x23: ffff8008f2d98010 x22: 00000000000001c0 x21: ffff8008f2d98394 x20: ffff8008f2d98010 x19: 0000000000000000 x18: 0000e3956f4f075a fxos8700 4-001e: i2c block read acc failed x17: 0000e395735727e8 x16: ffff00000829f4d4 x15: ffffffffffffffff x14: 7463656e6e6f6320 x13: 746f6e2009090920 x12: 7369207461687420 x11: 7465676461472061 x10: 206e6f207463656e x9 : 6e6f637369642067 x8 : ffff000009c8e280 x7 : ffff0000086ca6cc x6 : ffff000009f15e78 x5 : 0000000000000000 x4 : 0000000000000000 x3 : ffffffffffffffff x2 : c3f28b86000c3900 x1 : c3f28b86000c3900 x0 : 000000000000004e X20: 0xffff8008f2d97f90: 7f90 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 7fb0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 libprocessgroup: Failed to kill process cgroup uid 0 pid 22343 in 215ms, 1 processes remain 7fd0 Timeout for IPC response! 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 using random self ethernet address 7ff0 00000000 00000000 00000000 00000000 f76c8010 ffff8008 f76c8010 ffff8008 8010 00000100 00000000 f2d98018 ffff8008 f2d98018 ffff8008 08a067dc using random host ethernet address ffff0000 8030 f206d800 ffff8008 091c3650 ffff0000 f7957b18 ffff8008 f7957730 ffff8008 8050 f716a630 ffff8008 00000000 00000005 00000000 00000000 095d1568 ffff0000 8070 f76c8010 ffff8008 f716a800 ffff8008 095cac68 ffff0000 f206d828 ffff8008 X21: 0xffff8008f2d98314: 8314 ffff8008 00000000 00000000 00000000 00000000 00000000 00000000 00000000 8334 00000000 00000000 00000000 00000000 00000000 08a04cf4 ffff0000 00000000 8354 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 8374 00000000 00000000 00000000 00001001 00000000 00000000 00000000 00000000 8394 e4bbe4bb 0f230000 ffff0000 0afae000 ffff0000 ae001000 00000000 f206d400 Timeout for IPC response! 83b4 ffff8008 00000000 00000000 f7957b18 ffff8008 f7957718 ffff8008 f7957018 83d4 ffff8008 f7957118 ffff8008 f7957618 ffff8008 f7957818 ffff8008 f7957918 83f4 ffff8008 f7957d18 ffff8008 00000000 00000000 00000000 00000000 00000000 X23: 0xffff8008f2d97f90: 7f90 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 7fb0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 7fd0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 7ff0 00000000 00000000 00000000 00000000 f76c8010 ffff8008 f76c8010 ffff8008 8010 00000100 00000000 f2d98018 ffff8008 f2d98018 ffff8008 08a067dc ffff0000 8030 f206d800 ffff8008 091c3650 ffff0000 f7957b18 ffff8008 f7957730 ffff8008 8050 f716a630 ffff8008 00000000 00000005 00000000 00000000 095d1568 ffff0000 8070 f76c8010 ffff8008 f716a800 ffff8008 095cac68 ffff0000 f206d828 ffff8008 X28: 0xffff8008f2349b80: 9b80 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 9ba0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 9bc0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 9be0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 9c00 00000022 00000000 ffffffff ffffffff 00010001 00000000 00000000 00000000 9c20 0b0a8000 ffff0000 00000002 00404040 00000000 00000000 00000000 00000000 9c40 00000001 00000000 00000001 00000000 001ebd44 00000001 f390b800 ffff8008 9c60 00000000 00000001 00000070 00000070 00000070 00000000 09031d48 ffff0000 Call trace: Exception stack(0xffff000008003c90 to 0xffff000008003dd0) 3c80: 000000000000004e c3f28b86000c3900 3ca0: c3f28b86000c3900 ffffffffffffffff 0000000000000000 0000000000000000 3cc0: ffff000009f15e78 ffff0000086ca6cc ffff000009c8e280 6e6f637369642067 3ce0: 206e6f207463656e 7465676461472061 7369207461687420 746f6e2009090920 3d00: 7463656e6e6f6320 ffffffffffffffff ffff00000829f4d4 0000e395735727e8 3d20: 0000e3956f4f075a 0000000000000000 ffff8008f2d98010 ffff8008f2d98394 3d40: 00000000000001c0 ffff8008f2d98010 ffff000009c8e280 ffff000009885018 3d60: ffff000008004000 ffff000009885018 ffff8008f2349c00 ffff000008003dd0 3d80: ffff0000089ff9b0 ffff000008003dd0 ffff0000089ff9b0 00000000600001c5 3da0: ffff8008f33f2cd8 0000000000000000 0000ffffffffffff 0000000000000000 init: Received control message 'start' for 'adbd' from pid: 3359 (/vendor/bin/hw/android.hardware.usb@1.1-service.imx) 3dc0: ffff000008003dd0 ffff0000089ff9b0 [] composite_disconnect+0x80/0x88 [] android_disconnect+0x3c/0x68 [] cdns3_device_irq_handler+0xfc/0x2c8 [] cdns3_irq+0x44/0x94 [] __handle_irq_event_percpu+0x60/0x24c [] handle_irq_event+0x58/0xc0 [] handle_fasteoi_irq+0x98/0x180 [] generic_handle_irq+0x24/0x38 [] __handle_domain_irq+0x60/0xac [] gic_handle_irq+0xd4/0x17c Signed-off-by: Peter Chen Signed-off-by: Felipe Balbi Signed-off-by: Sasha Levin --- drivers/usb/gadget/configfs.c | 110 ++++++++++++++++++++++++++++++++-- 1 file changed, 105 insertions(+), 5 deletions(-) diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index a5ca409dc97e..b5315a47f0b9 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -60,6 +60,8 @@ struct gadget_info { bool use_os_desc; char b_vendor_code; char qw_sign[OS_STRING_QW_SIGN_LEN]; + spinlock_t spinlock; + bool unbind; }; static inline struct gadget_info *to_gadget_info(struct config_item *item) @@ -1241,6 +1243,7 @@ static int configfs_composite_bind(struct usb_gadget *gadget, int ret; /* the gi->lock is hold by the caller */ + gi->unbind = 0; cdev->gadget = gadget; set_gadget_data(gadget, cdev); ret = composite_dev_prepare(composite, cdev); @@ -1373,31 +1376,128 @@ static void configfs_composite_unbind(struct usb_gadget *gadget) { struct usb_composite_dev *cdev; struct gadget_info *gi; + unsigned long flags; /* the gi->lock is hold by the caller */ cdev = get_gadget_data(gadget); gi = container_of(cdev, struct gadget_info, cdev); + spin_lock_irqsave(&gi->spinlock, flags); + gi->unbind = 1; + spin_unlock_irqrestore(&gi->spinlock, flags); kfree(otg_desc[0]); otg_desc[0] = NULL; purge_configs_funcs(gi); composite_dev_cleanup(cdev); usb_ep_autoconfig_reset(cdev->gadget); + spin_lock_irqsave(&gi->spinlock, flags); cdev->gadget = NULL; set_gadget_data(gadget, NULL); + spin_unlock_irqrestore(&gi->spinlock, flags); +} + +static int configfs_composite_setup(struct usb_gadget *gadget, + const struct usb_ctrlrequest *ctrl) +{ + struct usb_composite_dev *cdev; + struct gadget_info *gi; + unsigned long flags; + int ret; + + cdev = get_gadget_data(gadget); + if (!cdev) + return 0; + + gi = container_of(cdev, struct gadget_info, cdev); + spin_lock_irqsave(&gi->spinlock, flags); + cdev = get_gadget_data(gadget); + if (!cdev || gi->unbind) { + spin_unlock_irqrestore(&gi->spinlock, flags); + return 0; + } + + ret = composite_setup(gadget, ctrl); + spin_unlock_irqrestore(&gi->spinlock, flags); + return ret; +} + +static void configfs_composite_disconnect(struct usb_gadget *gadget) +{ + struct usb_composite_dev *cdev; + struct gadget_info *gi; + unsigned long flags; + + cdev = get_gadget_data(gadget); + if (!cdev) + return; + + gi = container_of(cdev, struct gadget_info, cdev); + spin_lock_irqsave(&gi->spinlock, flags); + cdev = get_gadget_data(gadget); + if (!cdev || gi->unbind) { + spin_unlock_irqrestore(&gi->spinlock, flags); + return; + } + + composite_disconnect(gadget); + spin_unlock_irqrestore(&gi->spinlock, flags); +} + +static void configfs_composite_suspend(struct usb_gadget *gadget) +{ + struct usb_composite_dev *cdev; + struct gadget_info *gi; + unsigned long flags; + + cdev = get_gadget_data(gadget); + if (!cdev) + return; + + gi = container_of(cdev, struct gadget_info, cdev); + spin_lock_irqsave(&gi->spinlock, flags); + cdev = get_gadget_data(gadget); + if (!cdev || gi->unbind) { + spin_unlock_irqrestore(&gi->spinlock, flags); + return; + } + + composite_suspend(gadget); + spin_unlock_irqrestore(&gi->spinlock, flags); +} + +static void configfs_composite_resume(struct usb_gadget *gadget) +{ + struct usb_composite_dev *cdev; + struct gadget_info *gi; + unsigned long flags; + + cdev = get_gadget_data(gadget); + if (!cdev) + return; + + gi = container_of(cdev, struct gadget_info, cdev); + spin_lock_irqsave(&gi->spinlock, flags); + cdev = get_gadget_data(gadget); + if (!cdev || gi->unbind) { + spin_unlock_irqrestore(&gi->spinlock, flags); + return; + } + + composite_resume(gadget); + spin_unlock_irqrestore(&gi->spinlock, flags); } static const struct usb_gadget_driver configfs_driver_template = { .bind = configfs_composite_bind, .unbind = configfs_composite_unbind, - .setup = composite_setup, - .reset = composite_disconnect, - .disconnect = composite_disconnect, + .setup = configfs_composite_setup, + .reset = configfs_composite_disconnect, + .disconnect = configfs_composite_disconnect, - .suspend = composite_suspend, - .resume = composite_resume, + .suspend = configfs_composite_suspend, + .resume = configfs_composite_resume, .max_speed = USB_SPEED_SUPER, .driver = { From 74df2be6a7efd73201800111797732ccdbe0e2a2 Mon Sep 17 00:00:00 2001 From: Yinbo Zhu Date: Mon, 29 Jul 2019 14:46:07 +0800 Subject: [PATCH 47/93] usb: dwc3: remove the call trace of USBx_GFLADJ [ Upstream commit a7d9874c6f3fbc8d25cd9ceba35b6822612c4ebf ] layerscape board sometimes reported some usb call trace, that is due to kernel sent LPM tokerns automatically when it has no pending transfers and think that the link is idle enough to enter L1, which procedure will ask usb register has a recovery,then kernel will compare USBx_GFLADJ and set GFLADJ_30MHZ, GFLADJ_30MHZ_REG until GFLADJ_30MHZ is equal 0x20, if the conditions were met then issue occur, but whatever the conditions whether were met that usb is all need keep GFLADJ_30MHZ of value is 0x20 (xhci spec ask use GFLADJ_30MHZ to adjust any offset from clock source that generates the clock that drives the SOF counter, 0x20 is default value of it)That is normal logic, so need remove the call trace. Signed-off-by: Yinbo Zhu Signed-off-by: Felipe Balbi Signed-off-by: Sasha Levin --- drivers/usb/dwc3/core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 73dc5a6c6108..7154a93f0114 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -227,8 +227,7 @@ static void dwc3_frame_length_adjustment(struct dwc3 *dwc) reg = dwc3_readl(dwc->regs, DWC3_GFLADJ); dft = reg & DWC3_GFLADJ_30MHZ_MASK; - if (!dev_WARN_ONCE(dwc->dev, dft == dwc->fladj, - "request value same as default, ignoring\n")) { + if (dft != dwc->fladj) { reg &= ~DWC3_GFLADJ_30MHZ_MASK; reg |= DWC3_GFLADJ_30MHZ_SDBND_SEL | dwc->fladj; dwc3_writel(dwc->regs, DWC3_GFLADJ, reg); From 59d550d2ae22573d79439cec71a8cb490a73bea6 Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Wed, 23 Oct 2019 10:09:54 -0500 Subject: [PATCH 48/93] perf/x86/amd/ibs: Fix reading of the IBS OpData register and thus precise RIP validity [ Upstream commit 317b96bb14303c7998dbcd5bc606bd8038fdd4b4 ] The loop that reads all the IBS MSRs into *buf stopped one MSR short of reading the IbsOpData register, which contains the RipInvalid status bit. Fix the offset_max assignment so the MSR gets read, so the RIP invalid evaluation is based on what the IBS h/w output, instead of what was left in memory. Signed-off-by: Kim Phillips Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Jiri Olsa Cc: Linus Torvalds Cc: Mark Rutland Cc: Namhyung Kim Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: d47e8238cd76 ("perf/x86-ibs: Take instruction pointer from ibs sample") Link: https://lkml.kernel.org/r/20191023150955.30292-1-kim.phillips@amd.com Signed-off-by: Ingo Molnar Signed-off-by: Sasha Levin --- arch/x86/events/amd/ibs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 112e3c4636b4..a8317d384773 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -624,7 +624,7 @@ fail: if (event->attr.sample_type & PERF_SAMPLE_RAW) offset_max = perf_ibs->offset_max; else if (check_rip) - offset_max = 2; + offset_max = 3; else offset_max = 1; do { From ba7c1d43f9aeebda66e51dcedbd1bd0d6e6ad918 Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Wed, 23 Oct 2019 10:09:55 -0500 Subject: [PATCH 49/93] perf/x86/amd/ibs: Handle erratum #420 only on the affected CPU family (10h) [ Upstream commit e431e79b60603079d269e0c2a5177943b95fa4b6 ] This saves us writing the IBS control MSR twice when disabling the event. I searched revision guides for all families since 10h, and did not find occurrence of erratum #420, nor anything remotely similar: so we isolate the secondary MSR write to family 10h only. Also unconditionally update the count mask for IBS Op implementations that have read & writeable current count (CurCnt) fields in addition to the MaxCnt field. These bits were reserved on prior implementations, and therefore shouldn't have negative impact. Signed-off-by: Kim Phillips Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Jiri Olsa Cc: Linus Torvalds Cc: Mark Rutland Cc: Namhyung Kim Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: c9574fe0bdb9 ("perf/x86-ibs: Implement workaround for IBS erratum #420") Link: https://lkml.kernel.org/r/20191023150955.30292-2-kim.phillips@amd.com Signed-off-by: Ingo Molnar Signed-off-by: Sasha Levin --- arch/x86/events/amd/ibs.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index a8317d384773..5f72b473f3ed 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -388,7 +388,8 @@ static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs, struct hw_perf_event *hwc, u64 config) { config &= ~perf_ibs->cnt_mask; - wrmsrl(hwc->config_base, config); + if (boot_cpu_data.x86 == 0x10) + wrmsrl(hwc->config_base, config); config &= ~perf_ibs->enable_mask; wrmsrl(hwc->config_base, config); } @@ -563,7 +564,8 @@ static struct perf_ibs perf_ibs_op = { }, .msr = MSR_AMD64_IBSOPCTL, .config_mask = IBS_OP_CONFIG_MASK, - .cnt_mask = IBS_OP_MAX_CNT, + .cnt_mask = IBS_OP_MAX_CNT | IBS_OP_CUR_CNT | + IBS_OP_CUR_CNT_RAND, .enable_mask = IBS_OP_ENABLE, .valid_mask = IBS_OP_VAL, .max_period = IBS_OP_MAX_CNT << 4, From 3cbc8867d76ca61e4cf6b73ced0156442eddc4d7 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 28 Oct 2019 10:52:35 -0400 Subject: [PATCH 50/93] USB: Skip endpoints with 0 maxpacket length [ Upstream commit d482c7bb0541d19dea8bff437a9f3c5563b5b2d2 ] Endpoints with a maxpacket length of 0 are probably useless. They can't transfer any data, and it's not at all unlikely that an HCD will crash or hang when trying to handle an URB for such an endpoint. Currently the USB core does not check for endpoints having a maxpacket value of 0. This patch adds a check, printing a warning and skipping over any endpoints it catches. Now, the USB spec does not rule out endpoints having maxpacket = 0. But since they wouldn't have any practical use, there doesn't seem to be any good reason for us to accept them. Signed-off-by: Alan Stern Link: https://lore.kernel.org/r/Pine.LNX.4.44L0.1910281050420.1485-100000@iolanthe.rowland.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/core/config.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 94ec2dc27748..e8061b02b7e3 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -343,6 +343,11 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum, /* Validate the wMaxPacketSize field */ maxp = usb_endpoint_maxp(&endpoint->desc); + if (maxp == 0) { + dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has wMaxPacketSize 0, skipping\n", + cfgno, inum, asnum, d->bEndpointAddress); + goto skip_to_next_endpoint_or_interface_descriptor; + } /* Find the highest legal maxpacket size for this endpoint */ i = 0; /* additional transactions per microframe */ From 51def7114ea3637befa4d4d744fdc8cf91ac4772 Mon Sep 17 00:00:00 2001 From: Potnuri Bharat Teja Date: Fri, 25 Oct 2019 18:04:40 +0530 Subject: [PATCH 51/93] RDMA/iw_cxgb4: Avoid freeing skb twice in arp failure case [ Upstream commit d4934f45693651ea15357dd6c7c36be28b6da884 ] _put_ep_safe() and _put_pass_ep_safe() free the skb before it is freed by process_work(). fix double free by freeing the skb only in process_work(). Fixes: 1dad0ebeea1c ("iw_cxgb4: Avoid touch after free error in ARP failure handlers") Link: https://lore.kernel.org/r/1572006880-5800-1-git-send-email-bharat@chelsio.com Signed-off-by: Dakshaja Uppalapati Signed-off-by: Potnuri Bharat Teja Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/cxgb4/cm.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index e5752352e0fb..605d50ad123c 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -490,7 +490,6 @@ static int _put_ep_safe(struct c4iw_dev *dev, struct sk_buff *skb) ep = *((struct c4iw_ep **)(skb->cb + 2 * sizeof(void *))); release_ep_resources(ep); - kfree_skb(skb); return 0; } @@ -501,7 +500,6 @@ static int _put_pass_ep_safe(struct c4iw_dev *dev, struct sk_buff *skb) ep = *((struct c4iw_ep **)(skb->cb + 2 * sizeof(void *))); c4iw_put_ep(&ep->parent_ep->com); release_ep_resources(ep); - kfree_skb(skb); return 0; } From 89ffe62db51459262b7144b60bfda62f350d3fe1 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 24 Oct 2019 16:38:04 +1000 Subject: [PATCH 52/93] scsi: qla2xxx: stop timer in shutdown path [ Upstream commit d3566abb1a1e7772116e4d50fb6a58d19c9802e5 ] In shutdown/reboot paths, the timer is not stopped: qla2x00_shutdown pci_device_shutdown device_shutdown kernel_restart_prepare kernel_restart sys_reboot This causes lockups (on powerpc) when firmware config space access calls are interrupted by smp_send_stop later in reboot. Fixes: e30d1756480dc ("[SCSI] qla2xxx: Addition of shutdown callback handler.") Link: https://lore.kernel.org/r/20191024063804.14538-1-npiggin@gmail.com Signed-off-by: Nicholas Piggin Acked-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qla2xxx/qla_os.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index c813c9b75a10..3bae56b202f8 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3077,6 +3077,10 @@ qla2x00_shutdown(struct pci_dev *pdev) /* Stop currently executing firmware. */ qla2x00_try_to_stop_firmware(vha); + /* Disable timer */ + if (vha->timer_active) + qla2x00_stop_timer(vha); + /* Turn adapter off line */ vha->flags.online = 0; From 76e62b04f78f6ae3f13dfbebf1f49b78e8cc938b Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 25 Oct 2019 12:06:02 +0100 Subject: [PATCH 53/93] fjes: Handle workqueue allocation failure [ Upstream commit 85ac30fa2e24f628e9f4f9344460f4015d33fd7d ] In the highly unlikely event that we fail to allocate either of the "/txrx" or "/control" workqueues, we should bail cleanly rather than blindly march on with NULL queue pointer(s) installed in the 'fjes_adapter' instance. Cc: "David S. Miller" Reported-by: Nicolas Waisman Link: https://lore.kernel.org/lkml/CADJ_3a8WFrs5NouXNqS5WYe7rebFP+_A5CheeqAyD_p7DFJJcg@mail.gmail.com/ Signed-off-by: Will Deacon Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/fjes/fjes_main.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c index 7ea8ead4fd1c..bbc983b04561 100644 --- a/drivers/net/fjes/fjes_main.c +++ b/drivers/net/fjes/fjes_main.c @@ -1187,8 +1187,17 @@ static int fjes_probe(struct platform_device *plat_dev) adapter->open_guard = false; adapter->txrx_wq = alloc_workqueue(DRV_NAME "/txrx", WQ_MEM_RECLAIM, 0); + if (unlikely(!adapter->txrx_wq)) { + err = -ENOMEM; + goto err_free_netdev; + } + adapter->control_wq = alloc_workqueue(DRV_NAME "/control", WQ_MEM_RECLAIM, 0); + if (unlikely(!adapter->control_wq)) { + err = -ENOMEM; + goto err_free_txrx_wq; + } INIT_WORK(&adapter->tx_stall_task, fjes_tx_stall_task); INIT_WORK(&adapter->raise_intr_rxdata_task, @@ -1205,7 +1214,7 @@ static int fjes_probe(struct platform_device *plat_dev) hw->hw_res.irq = platform_get_irq(plat_dev, 0); err = fjes_hw_init(&adapter->hw); if (err) - goto err_free_netdev; + goto err_free_control_wq; /* setup MAC address (02:00:00:00:00:[epid])*/ netdev->dev_addr[0] = 2; @@ -1225,6 +1234,10 @@ static int fjes_probe(struct platform_device *plat_dev) err_hw_exit: fjes_hw_exit(&adapter->hw); +err_free_control_wq: + destroy_workqueue(adapter->control_wq); +err_free_txrx_wq: + destroy_workqueue(adapter->txrx_wq); err_free_netdev: free_netdev(netdev); err_out: From 4a8b8c7f00420482389a72b40c531b2ea0e8559f Mon Sep 17 00:00:00 2001 From: Jiangfeng Xiao Date: Fri, 25 Oct 2019 21:48:22 +0800 Subject: [PATCH 54/93] net: hisilicon: Fix "Trying to free already-free IRQ" [ Upstream commit 63a41746827cb16dc6ad0d4d761ab4e7dda7a0c3 ] When rmmod hip04_eth.ko, we can get the following warning: Task track: rmmod(1623)>bash(1591)>login(1581)>init(1) ------------[ cut here ]------------ WARNING: CPU: 0 PID: 1623 at kernel/irq/manage.c:1557 __free_irq+0xa4/0x2ac() Trying to free already-free IRQ 200 Modules linked in: ping(O) pramdisk(O) cpuinfo(O) rtos_snapshot(O) interrupt_ctrl(O) mtdblock mtd_blkdevrtfs nfs_acl nfs lockd grace sunrpc xt_tcpudp ipt_REJECT iptable_filter ip_tables x_tables nf_reject_ipv CPU: 0 PID: 1623 Comm: rmmod Tainted: G O 4.4.193 #1 Hardware name: Hisilicon A15 [] (rtos_unwind_backtrace) from [] (show_stack+0x10/0x14) [] (show_stack) from [] (dump_stack+0xa0/0xd8) [] (dump_stack) from [] (warn_slowpath_common+0x84/0xb0) [] (warn_slowpath_common) from [] (warn_slowpath_fmt+0x3c/0x68) [] (warn_slowpath_fmt) from [] (__free_irq+0xa4/0x2ac) [] (__free_irq) from [] (free_irq+0x60/0x7c) [] (free_irq) from [] (release_nodes+0x1c4/0x1ec) [] (release_nodes) from [] (__device_release_driver+0xa8/0x104) [] (__device_release_driver) from [] (driver_detach+0xd0/0xf8) [] (driver_detach) from [] (bus_remove_driver+0x64/0x8c) [] (bus_remove_driver) from [] (SyS_delete_module+0x198/0x1e0) [] (SyS_delete_module) from [] (__sys_trace_return+0x0/0x10) ---[ end trace bb25d6123d849b44 ]--- Currently "rmmod hip04_eth.ko" call free_irq more than once as devres_release_all and hip04_remove both call free_irq. This results in a 'Trying to free already-free IRQ' warning. To solve the problem free_irq has been moved out of hip04_remove. Signed-off-by: Jiangfeng Xiao Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hip04_eth.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 407e1177d9d1..4436a0307f32 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -953,7 +953,6 @@ static int hip04_remove(struct platform_device *pdev) hip04_free_ring(ndev, d); unregister_netdev(ndev); - free_irq(ndev->irq, ndev); of_node_put(priv->phy_node); cancel_work_sync(&priv->tx_timeout_task); free_netdev(ndev); From 7fe8d1529b604d88bd0e293a7081ad75be1b23bc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 31 Oct 2019 18:40:32 -0400 Subject: [PATCH 55/93] NFSv4: Don't allow a cached open with a revoked delegation [ Upstream commit be3df3dd4c70ee020587a943a31b98a0fb4b6424 ] If the delegation is marked as being revoked, we must not use it for cached opens. Fixes: 869f9dfa4d6d ("NFSv4: Fix races between nfs_remove_bad_delegation() and delegation return") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/delegation.c | 10 ++++++++++ fs/nfs/delegation.h | 1 + fs/nfs/nfs4proc.c | 7 ++----- 3 files changed, 13 insertions(+), 5 deletions(-) diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index dff600ae0d74..46afd7cdcc37 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -52,6 +52,16 @@ nfs4_is_valid_delegation(const struct nfs_delegation *delegation, return false; } +struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode) +{ + struct nfs_delegation *delegation; + + delegation = rcu_dereference(NFS_I(inode)->delegation); + if (nfs4_is_valid_delegation(delegation, 0)) + return delegation; + return NULL; +} + static int nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark) { diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index e9d555796873..2c6cb7fb7d5e 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -62,6 +62,7 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid); bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, struct rpc_cred **cred); +struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode); void nfs_mark_delegation_referenced(struct nfs_delegation *delegation); int nfs4_have_delegation(struct inode *inode, fmode_t flags); int nfs4_check_delegation(struct inode *inode, fmode_t flags); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 8354dfae7038..ca4249ae644f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1368,8 +1368,6 @@ static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode, return 0; if ((delegation->type & fmode) != fmode) return 0; - if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) - return 0; switch (claim) { case NFS4_OPEN_CLAIM_NULL: case NFS4_OPEN_CLAIM_FH: @@ -1628,7 +1626,6 @@ static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmo static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata) { struct nfs4_state *state = opendata->state; - struct nfs_inode *nfsi = NFS_I(state->inode); struct nfs_delegation *delegation; int open_mode = opendata->o_arg.open_flags; fmode_t fmode = opendata->o_arg.fmode; @@ -1645,7 +1642,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata) } spin_unlock(&state->owner->so_lock); rcu_read_lock(); - delegation = rcu_dereference(nfsi->delegation); + delegation = nfs4_get_valid_delegation(state->inode); if (!can_open_delegated(delegation, fmode, claim)) { rcu_read_unlock(); break; @@ -2142,7 +2139,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) if (can_open_cached(data->state, data->o_arg.fmode, data->o_arg.open_flags)) goto out_no_action; rcu_read_lock(); - delegation = rcu_dereference(NFS_I(data->state->inode)->delegation); + delegation = nfs4_get_valid_delegation(data->state->inode); if (can_open_delegated(delegation, data->o_arg.fmode, claim)) goto unlock_no_action; rcu_read_unlock(); From 0e63ae78bcc78220fe282cfed99bee14711be3be Mon Sep 17 00:00:00 2001 From: Chuhong Yuan Date: Fri, 1 Nov 2019 20:17:25 +0800 Subject: [PATCH 56/93] net: ethernet: arc: add the missed clk_disable_unprepare [ Upstream commit 4202e219edd6cc164c042e16fa327525410705ae ] The remove misses to disable and unprepare priv->macclk like what is done when probe fails. Add the missed call in remove. Signed-off-by: Chuhong Yuan Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/arc/emac_rockchip.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/arc/emac_rockchip.c b/drivers/net/ethernet/arc/emac_rockchip.c index c770ca37c9b2..a7d30731d376 100644 --- a/drivers/net/ethernet/arc/emac_rockchip.c +++ b/drivers/net/ethernet/arc/emac_rockchip.c @@ -261,6 +261,9 @@ static int emac_rockchip_remove(struct platform_device *pdev) if (priv->regulator) regulator_disable(priv->regulator); + if (priv->soc_data->need_div_macclk) + clk_disable_unprepare(priv->macclk); + free_netdev(ndev); return err; } From d0844089e3e2ae95865e8526b4f48d9acdeb72b7 Mon Sep 17 00:00:00 2001 From: Manfred Rudigier Date: Thu, 15 Aug 2019 13:55:20 -0700 Subject: [PATCH 57/93] igb: Fix constant media auto sense switching when no cable is connected [ Upstream commit 8d5cfd7f76a2414e23c74bb8858af7540365d985 ] At least on the i350 there is an annoying behavior that is maybe also present on 82580 devices, but was probably not noticed yet as MAS is not widely used. If no cable is connected on both fiber/copper ports the media auto sense code will constantly swap between them as part of the watchdog task and produce many unnecessary kernel log messages. The swap code responsible for this behavior (switching to fiber) should not be executed if the current media type is copper and there is no signal detected on the fiber port. In this case we can safely wait until the AUTOSENSE_EN bit is cleared. Signed-off-by: Manfred Rudigier Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igb/igb_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 7956176c2c73..7e35bd665630 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1677,7 +1677,8 @@ static void igb_check_swap_media(struct igb_adapter *adapter) if ((hw->phy.media_type == e1000_media_type_copper) && (!(connsw & E1000_CONNSW_AUTOSENSE_EN))) { swap_now = true; - } else if (!(connsw & E1000_CONNSW_SERDESD)) { + } else if ((hw->phy.media_type != e1000_media_type_copper) && + !(connsw & E1000_CONNSW_SERDESD)) { /* copper signal takes time to appear */ if (adapter->copper_tries < 4) { adapter->copper_tries++; From 18372c98cf9ebc696ac6ccef904592ab30fc2d3d Mon Sep 17 00:00:00 2001 From: Wenwen Wang Date: Mon, 12 Aug 2019 00:59:21 -0500 Subject: [PATCH 58/93] e1000: fix memory leaks [ Upstream commit 8472ba62154058b64ebb83d5f57259a352d28697 ] In e1000_set_ringparam(), 'tx_old' and 'rx_old' are not deallocated if e1000_up() fails, leading to memory leaks. Refactor the code to fix this issue. Signed-off-by: Wenwen Wang Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/e1000/e1000_ethtool.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index 2a81f6d72140..8936f19e9325 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -628,6 +628,7 @@ static int e1000_set_ringparam(struct net_device *netdev, for (i = 0; i < adapter->num_rx_queues; i++) rxdr[i].count = rxdr->count; + err = 0; if (netif_running(adapter->netdev)) { /* Try to get new resources before deleting old */ err = e1000_setup_all_rx_resources(adapter); @@ -648,14 +649,13 @@ static int e1000_set_ringparam(struct net_device *netdev, adapter->rx_ring = rxdr; adapter->tx_ring = txdr; err = e1000_up(adapter); - if (err) - goto err_setup; } kfree(tx_old); kfree(rx_old); clear_bit(__E1000_RESETTING, &adapter->flags); - return 0; + return err; + err_setup_tx: e1000_free_all_rx_resources(adapter); err_setup_rx: @@ -667,7 +667,6 @@ err_alloc_rx: err_alloc_tx: if (netif_running(adapter->netdev)) e1000_up(adapter); -err_setup: clear_bit(__E1000_RESETTING, &adapter->flags); return err; } From 3bbebab1715235100b68b0617fb70cfe2f07e35d Mon Sep 17 00:00:00 2001 From: Dou Liyang Date: Thu, 1 Mar 2018 13:59:28 +0800 Subject: [PATCH 59/93] x86/apic: Move pending interrupt check code into it's own function [ Upstream commit 9b217f33017715903d0956dfc58f82d2a2d00e63 ] The pending interrupt check code is mixed with the local APIC setup code, that looks messy. Extract the related code, move it into a new function named apic_pending_intr_clear(). Signed-off-by: Dou Liyang Signed-off-by: Thomas Gleixner Reviewed-by: Andy Shevchenko Cc: bhe@redhat.com Cc: ebiederm@xmission.com Link: https://lkml.kernel.org/r/20180301055930.2396-2-douly.fnst@cn.fujitsu.com Signed-off-by: Sasha Levin --- arch/x86/kernel/apic/apic.c | 100 ++++++++++++++++++++---------------- 1 file changed, 55 insertions(+), 45 deletions(-) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 232350519062..264daf1f4991 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1281,6 +1281,56 @@ static void lapic_setup_esr(void) oldvalue, value); } +static void apic_pending_intr_clear(void) +{ + long long max_loops = cpu_khz ? cpu_khz : 1000000; + unsigned long long tsc = 0, ntsc; + unsigned int value, queued; + int i, j, acked = 0; + + if (boot_cpu_has(X86_FEATURE_TSC)) + tsc = rdtsc(); + /* + * After a crash, we no longer service the interrupts and a pending + * interrupt from previous kernel might still have ISR bit set. + * + * Most probably by now CPU has serviced that pending interrupt and + * it might not have done the ack_APIC_irq() because it thought, + * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it + * does not clear the ISR bit and cpu thinks it has already serivced + * the interrupt. Hence a vector might get locked. It was noticed + * for timer irq (vector 0x31). Issue an extra EOI to clear ISR. + */ + do { + queued = 0; + for (i = APIC_ISR_NR - 1; i >= 0; i--) + queued |= apic_read(APIC_IRR + i*0x10); + + for (i = APIC_ISR_NR - 1; i >= 0; i--) { + value = apic_read(APIC_ISR + i*0x10); + for (j = 31; j >= 0; j--) { + if (value & (1< 256) { + printk(KERN_ERR "LAPIC pending interrupts after %d EOI\n", + acked); + break; + } + if (queued) { + if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) { + ntsc = rdtsc(); + max_loops = (cpu_khz << 10) - (ntsc - tsc); + } else + max_loops--; + } + } while (queued && max_loops > 0); + WARN_ON(max_loops <= 0); +} + /** * setup_local_APIC - setup the local APIC * @@ -1290,13 +1340,11 @@ static void lapic_setup_esr(void) void setup_local_APIC(void) { int cpu = smp_processor_id(); - unsigned int value, queued; - int i, j, acked = 0; - unsigned long long tsc = 0, ntsc; - long long max_loops = cpu_khz ? cpu_khz : 1000000; + unsigned int value; +#ifdef CONFIG_X86_32 + int i; +#endif - if (boot_cpu_has(X86_FEATURE_TSC)) - tsc = rdtsc(); if (disable_apic) { disable_ioapic_support(); @@ -1356,45 +1404,7 @@ void setup_local_APIC(void) value &= ~APIC_TPRI_MASK; apic_write(APIC_TASKPRI, value); - /* - * After a crash, we no longer service the interrupts and a pending - * interrupt from previous kernel might still have ISR bit set. - * - * Most probably by now CPU has serviced that pending interrupt and - * it might not have done the ack_APIC_irq() because it thought, - * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it - * does not clear the ISR bit and cpu thinks it has already serivced - * the interrupt. Hence a vector might get locked. It was noticed - * for timer irq (vector 0x31). Issue an extra EOI to clear ISR. - */ - do { - queued = 0; - for (i = APIC_ISR_NR - 1; i >= 0; i--) - queued |= apic_read(APIC_IRR + i*0x10); - - for (i = APIC_ISR_NR - 1; i >= 0; i--) { - value = apic_read(APIC_ISR + i*0x10); - for (j = 31; j >= 0; j--) { - if (value & (1< 256) { - printk(KERN_ERR "LAPIC pending interrupts after %d EOI\n", - acked); - break; - } - if (queued) { - if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) { - ntsc = rdtsc(); - max_loops = (cpu_khz << 10) - (ntsc - tsc); - } else - max_loops--; - } - } while (queued && max_loops > 0); - WARN_ON(max_loops <= 0); + apic_pending_intr_clear(); /* * Now that we are all set up, enable the APIC From 122134fa8c08e0a033f1b92b8fcacf4e769b5635 Mon Sep 17 00:00:00 2001 From: Dou Liyang Date: Thu, 1 Mar 2018 13:59:30 +0800 Subject: [PATCH 60/93] x86/apic: Drop logical_smp_processor_id() inline [ Upstream commit 8f1561680f42a5491b371b513f1ab8197f31fd62 ] The logical_smp_processor_id() inline which is only called in setup_local_APIC() on x86_32 systems has no real value. Drop it and directly use GET_APIC_LOGICAL_ID() at the call site and use a more suitable variable name for readability Signed-off-by: Dou Liyang Signed-off-by: Thomas Gleixner Cc: andy.shevchenko@gmail.com Cc: bhe@redhat.com Cc: ebiederm@xmission.com Link: https://lkml.kernel.org/r/20180301055930.2396-4-douly.fnst@cn.fujitsu.com Signed-off-by: Sasha Levin --- arch/x86/include/asm/smp.h | 10 ---------- arch/x86/kernel/apic/apic.c | 10 +++++----- 2 files changed, 5 insertions(+), 15 deletions(-) diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index d25fb6beb2f0..dcaf7100b69c 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -177,16 +177,6 @@ extern int safe_smp_processor_id(void); #endif #ifdef CONFIG_X86_LOCAL_APIC - -#ifndef CONFIG_X86_64 -static inline int logical_smp_processor_id(void) -{ - /* we don't want to mark this access volatile - bad code generation */ - return GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); -} - -#endif - extern int hard_smp_processor_id(void); #else /* CONFIG_X86_LOCAL_APIC */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 264daf1f4991..ad2a220a4a7f 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1342,7 +1342,7 @@ void setup_local_APIC(void) int cpu = smp_processor_id(); unsigned int value; #ifdef CONFIG_X86_32 - int i; + int logical_apicid, ldr_apicid; #endif @@ -1389,11 +1389,11 @@ void setup_local_APIC(void) * initialized during get_smp_config(), make sure it matches the * actual value. */ - i = early_per_cpu(x86_cpu_to_logical_apicid, cpu); - WARN_ON(i != BAD_APICID && i != logical_smp_processor_id()); + logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); + ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); + WARN_ON(logical_apicid != BAD_APICID && logical_apicid != ldr_apicid); /* always use the value from LDR */ - early_per_cpu(x86_cpu_to_logical_apicid, cpu) = - logical_smp_processor_id(); + early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; #endif /* From 818226c0625e5dda5ae32e959764c55912104fca Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 29 Oct 2019 10:34:19 +0100 Subject: [PATCH 61/93] x86/apic/32: Avoid bogus LDR warnings [ Upstream commit fe6f85ca121e9c74e7490fe66b0c5aae38e332c3 ] The removal of the LDR initialization in the bigsmp_32 APIC code unearthed a problem in setup_local_APIC(). The code checks unconditionally for a mismatch of the logical APIC id by comparing the early APIC id which was initialized in get_smp_config() with the actual LDR value in the APIC. Due to the removal of the bogus LDR initialization the check now can trigger on bigsmp_32 APIC systems emitting a warning for every booting CPU. This is of course a false positive because the APIC is not using logical destination mode. Restrict the check and the possibly resulting fixup to systems which are actually using the APIC in logical destination mode. [ tglx: Massaged changelog and added Cc stable ] Fixes: bae3a8d3308 ("x86/apic: Do not initialize LDR and DFR for bigsmp") Signed-off-by: Jan Beulich Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/666d8f91-b5a8-1afd-7add-821e72a35f03@suse.com Signed-off-by: Sasha Levin --- arch/x86/kernel/apic/apic.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index ad2a220a4a7f..722a76b88bcc 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1341,9 +1341,6 @@ void setup_local_APIC(void) { int cpu = smp_processor_id(); unsigned int value; -#ifdef CONFIG_X86_32 - int logical_apicid, ldr_apicid; -#endif if (disable_apic) { @@ -1384,16 +1381,21 @@ void setup_local_APIC(void) apic->init_apic_ldr(); #ifdef CONFIG_X86_32 - /* - * APIC LDR is initialized. If logical_apicid mapping was - * initialized during get_smp_config(), make sure it matches the - * actual value. - */ - logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); - ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); - WARN_ON(logical_apicid != BAD_APICID && logical_apicid != ldr_apicid); - /* always use the value from LDR */ - early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; + if (apic->dest_logical) { + int logical_apicid, ldr_apicid; + + /* + * APIC LDR is initialized. If logical_apicid mapping was + * initialized during get_smp_config(), make sure it matches + * the actual value. + */ + logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); + ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); + if (logical_apicid != BAD_APICID) + WARN_ON(logical_apicid != ldr_apicid); + /* Always use the value from LDR. */ + early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; + } #endif /* From d6b15585bca178ec6faec6a076e4b133ee3a010d Mon Sep 17 00:00:00 2001 From: Joakim Zhang Date: Thu, 15 Aug 2019 08:00:26 +0000 Subject: [PATCH 62/93] can: flexcan: disable completely the ECC mechanism [ Upstream commit 5e269324db5adb2f5f6ec9a93a9c7b0672932b47 ] The ECC (memory error detection and correction) mechanism can be activated or not, controlled by the ECCDIS bit in CAN_MECR. When disabled, updates on indications and reporting registers are stopped. So if want to disable ECC completely, had better assert ECCDIS bit, not just mask the related interrupts. Fixes: cdce844865be ("can: flexcan: add vf610 support for FlexCAN") Signed-off-by: Joakim Zhang Cc: linux-stable Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- drivers/net/can/flexcan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index baef09b9449f..6b866d0451b2 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -923,6 +923,7 @@ static int flexcan_chip_start(struct net_device *dev) reg_mecr = flexcan_read(®s->mecr); reg_mecr &= ~FLEXCAN_MECR_ECRWRDIS; flexcan_write(reg_mecr, ®s->mecr); + reg_mecr |= FLEXCAN_MECR_ECCDIS; reg_mecr &= ~(FLEXCAN_MECR_NCEFAFRZ | FLEXCAN_MECR_HANCEI_MSK | FLEXCAN_MECR_FANCEI_MSK); flexcan_write(reg_mecr, ®s->mecr); From 063620bbbc41572c8e0ee6f258f70b052153eba9 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Mon, 23 Sep 2019 15:34:45 -0700 Subject: [PATCH 63/93] mm/filemap.c: don't initiate writeback if mapping has no dirty pages commit c3aab9a0bd91b696a852169479b7db1ece6cbf8c upstream. Functions like filemap_write_and_wait_range() should do nothing if inode has no dirty pages or pages currently under writeback. But they anyway construct struct writeback_control and this does some atomic operations if CONFIG_CGROUP_WRITEBACK=y - on fast path it locks inode->i_lock and updates state of writeback ownership, on slow path might be more work. Current this path is safely avoided only when inode mapping has no pages. For example generic_file_read_iter() calls filemap_write_and_wait_range() at each O_DIRECT read - pretty hot path. This patch skips starting new writeback if mapping has no dirty tags set. If writeback is already in progress filemap_write_and_wait_range() will wait for it. Link: http://lkml.kernel.org/r/156378816804.1087.8607636317907921438.stgit@buzz Signed-off-by: Konstantin Khlebnikov Reviewed-by: Jan Kara Cc: Tejun Heo Cc: Jens Axboe Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/filemap.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/filemap.c b/mm/filemap.c index 6d2f561d517c..b046d8f147e2 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -383,7 +383,8 @@ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, .range_end = end, }; - if (!mapping_cap_writeback_dirty(mapping)) + if (!mapping_cap_writeback_dirty(mapping) || + !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) return 0; wbc_attach_fdatawrite_inode(&wbc, mapping->host); From d92f4f02d46f7fe990fffb64987200443de3014a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 8 Nov 2019 12:18:29 -0800 Subject: [PATCH 64/93] cgroup,writeback: don't switch wbs immediately on dead wbs if the memcg is dead commit 65de03e251382306a4575b1779c57c87889eee49 upstream. cgroup writeback tries to refresh the associated wb immediately if the current wb is dead. This is to avoid keeping issuing IOs on the stale wb after memcg - blkcg association has changed (ie. when blkcg got disabled / enabled higher up in the hierarchy). Unfortunately, the logic gets triggered spuriously on inodes which are associated with dead cgroups. When the logic is triggered on dead cgroups, the attempt fails only after doing quite a bit of work allocating and initializing a new wb. While c3aab9a0bd91 ("mm/filemap.c: don't initiate writeback if mapping has no dirty pages") alleviated the issue significantly as it now only triggers when the inode has dirty pages. However, the condition can still be triggered before the inode is switched to a different cgroup and the logic simply doesn't make sense. Skip the immediate switching if the associated memcg is dying. This is a simplified version of the following two patches: * https://lore.kernel.org/linux-mm/20190513183053.GA73423@dennisz-mbp/ * http://lkml.kernel.org/r/156355839560.2063.5265687291430814589.stgit@buzz Cc: Konstantin Khlebnikov Fixes: e8a7abf5a5bd ("writeback: disassociate inodes from dying bdi_writebacks") Acked-by: Dennis Zhou Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- fs/fs-writeback.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index baaed9369ab4..882e9d6830df 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -582,10 +582,13 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, spin_unlock(&inode->i_lock); /* - * A dying wb indicates that the memcg-blkcg mapping has changed - * and a new wb is already serving the memcg. Switch immediately. + * A dying wb indicates that either the blkcg associated with the + * memcg changed or the associated memcg is dying. In the first + * case, a replacement wb should already be available and we should + * refresh the wb immediately. In the second case, trying to + * refresh will keep failing. */ - if (unlikely(wb_dying(wbc->wb))) + if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css))) inode_switch_wbs(inode, wbc->wb_id); } From 4e8e9fd6a3a1c733ee9f0879fa4a3b2589406205 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 4 Nov 2019 21:38:43 -0800 Subject: [PATCH 65/93] net: prevent load/store tearing on sk->sk_stamp [ Upstream commit f75359f3ac855940c5718af10ba089b8977bf339 ] Add a couple of READ_ONCE() and WRITE_ONCE() to prevent load-tearing and store-tearing in sock_read_timestamp() and sock_write_timestamp() This might prevent another KCSAN report. Fixes: 3a0ed3e96197 ("sock: Make sock->sk_stamp thread-safe") Signed-off-by: Eric Dumazet Cc: Deepa Dinamani Acked-by: Deepa Dinamani Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/sock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 469c012a6d01..d8d14ae8892a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2142,7 +2142,7 @@ static inline ktime_t sock_read_timestamp(struct sock *sk) return kt; #else - return sk->sk_stamp; + return READ_ONCE(sk->sk_stamp); #endif } @@ -2153,7 +2153,7 @@ static inline void sock_write_timestamp(struct sock *sk, ktime_t kt) sk->sk_stamp = kt; write_sequnlock(&sk->sk_stamp_seq); #else - sk->sk_stamp = kt; + WRITE_ONCE(sk->sk_stamp, kt); #endif } From f9154aba2fbc836555cd87b91c9ff5ace3ca600f Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Wed, 23 Nov 2016 23:02:27 +0000 Subject: [PATCH 66/93] drm/i915: kick out cmd_parser specific structs from i915_drv.h commit 007873b30b9001348c0dfc96deb9db220a3be116 upstream. No sense in keeping the cmd_descriptor and cmd_table structs in i915_drv.h, now that they are no longer referenced externally. Cc: Chris Wilson Signed-off-by: Matthew Auld Reviewed-by: Joonas Lahtinen Signed-off-by: Joonas Lahtinen Signed-off-by: Jon Bloomfield Link: http://patchwork.freedesktop.org/patch/msgid/1479942147-9837-1-git-send-email-matthew.auld@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 96 ++++++++++++++++++++++++++ drivers/gpu/drm/i915/i915_drv.h | 96 -------------------------- 2 files changed, 96 insertions(+), 96 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 70980f82a15b..193d15e947e0 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -86,6 +86,102 @@ * general bitmasking mechanism. */ +/* + * A command that requires special handling by the command parser. + */ +struct drm_i915_cmd_descriptor { + /* + * Flags describing how the command parser processes the command. + * + * CMD_DESC_FIXED: The command has a fixed length if this is set, + * a length mask if not set + * CMD_DESC_SKIP: The command is allowed but does not follow the + * standard length encoding for the opcode range in + * which it falls + * CMD_DESC_REJECT: The command is never allowed + * CMD_DESC_REGISTER: The command should be checked against the + * register whitelist for the appropriate ring + * CMD_DESC_MASTER: The command is allowed if the submitting process + * is the DRM master + */ + u32 flags; +#define CMD_DESC_FIXED (1<<0) +#define CMD_DESC_SKIP (1<<1) +#define CMD_DESC_REJECT (1<<2) +#define CMD_DESC_REGISTER (1<<3) +#define CMD_DESC_BITMASK (1<<4) +#define CMD_DESC_MASTER (1<<5) + + /* + * The command's unique identification bits and the bitmask to get them. + * This isn't strictly the opcode field as defined in the spec and may + * also include type, subtype, and/or subop fields. + */ + struct { + u32 value; + u32 mask; + } cmd; + + /* + * The command's length. The command is either fixed length (i.e. does + * not include a length field) or has a length field mask. The flag + * CMD_DESC_FIXED indicates a fixed length. Otherwise, the command has + * a length mask. All command entries in a command table must include + * length information. + */ + union { + u32 fixed; + u32 mask; + } length; + + /* + * Describes where to find a register address in the command to check + * against the ring's register whitelist. Only valid if flags has the + * CMD_DESC_REGISTER bit set. + * + * A non-zero step value implies that the command may access multiple + * registers in sequence (e.g. LRI), in that case step gives the + * distance in dwords between individual offset fields. + */ + struct { + u32 offset; + u32 mask; + u32 step; + } reg; + +#define MAX_CMD_DESC_BITMASKS 3 + /* + * Describes command checks where a particular dword is masked and + * compared against an expected value. If the command does not match + * the expected value, the parser rejects it. Only valid if flags has + * the CMD_DESC_BITMASK bit set. Only entries where mask is non-zero + * are valid. + * + * If the check specifies a non-zero condition_mask then the parser + * only performs the check when the bits specified by condition_mask + * are non-zero. + */ + struct { + u32 offset; + u32 mask; + u32 expected; + u32 condition_offset; + u32 condition_mask; + } bits[MAX_CMD_DESC_BITMASKS]; +}; + +/* + * A table of commands requiring special handling by the command parser. + * + * Each engine has an array of tables. Each table consists of an array of + * command descriptors, which must be sorted with command opcodes in + * ascending order. + */ +struct drm_i915_cmd_table { + const struct drm_i915_cmd_descriptor *table; + int count; +}; + #define STD_MI_OPCODE_SHIFT (32 - 9) #define STD_3D_OPCODE_SHIFT (32 - 16) #define STD_2D_OPCODE_SHIFT (32 - 10) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index e23748cca0c0..9320f8265cc6 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2476,102 +2476,6 @@ static inline struct scatterlist *__sg_next(struct scatterlist *sg) (((__iter).curr += PAGE_SIZE) < (__iter).max) || \ ((__iter) = __sgt_iter(__sg_next((__iter).sgp), false), 0)) -/* - * A command that requires special handling by the command parser. - */ -struct drm_i915_cmd_descriptor { - /* - * Flags describing how the command parser processes the command. - * - * CMD_DESC_FIXED: The command has a fixed length if this is set, - * a length mask if not set - * CMD_DESC_SKIP: The command is allowed but does not follow the - * standard length encoding for the opcode range in - * which it falls - * CMD_DESC_REJECT: The command is never allowed - * CMD_DESC_REGISTER: The command should be checked against the - * register whitelist for the appropriate ring - * CMD_DESC_MASTER: The command is allowed if the submitting process - * is the DRM master - */ - u32 flags; -#define CMD_DESC_FIXED (1<<0) -#define CMD_DESC_SKIP (1<<1) -#define CMD_DESC_REJECT (1<<2) -#define CMD_DESC_REGISTER (1<<3) -#define CMD_DESC_BITMASK (1<<4) -#define CMD_DESC_MASTER (1<<5) - - /* - * The command's unique identification bits and the bitmask to get them. - * This isn't strictly the opcode field as defined in the spec and may - * also include type, subtype, and/or subop fields. - */ - struct { - u32 value; - u32 mask; - } cmd; - - /* - * The command's length. The command is either fixed length (i.e. does - * not include a length field) or has a length field mask. The flag - * CMD_DESC_FIXED indicates a fixed length. Otherwise, the command has - * a length mask. All command entries in a command table must include - * length information. - */ - union { - u32 fixed; - u32 mask; - } length; - - /* - * Describes where to find a register address in the command to check - * against the ring's register whitelist. Only valid if flags has the - * CMD_DESC_REGISTER bit set. - * - * A non-zero step value implies that the command may access multiple - * registers in sequence (e.g. LRI), in that case step gives the - * distance in dwords between individual offset fields. - */ - struct { - u32 offset; - u32 mask; - u32 step; - } reg; - -#define MAX_CMD_DESC_BITMASKS 3 - /* - * Describes command checks where a particular dword is masked and - * compared against an expected value. If the command does not match - * the expected value, the parser rejects it. Only valid if flags has - * the CMD_DESC_BITMASK bit set. Only entries where mask is non-zero - * are valid. - * - * If the check specifies a non-zero condition_mask then the parser - * only performs the check when the bits specified by condition_mask - * are non-zero. - */ - struct { - u32 offset; - u32 mask; - u32 expected; - u32 condition_offset; - u32 condition_mask; - } bits[MAX_CMD_DESC_BITMASKS]; -}; - -/* - * A table of commands requiring special handling by the command parser. - * - * Each engine has an array of tables. Each table consists of an array of - * command descriptors, which must be sorted with command opcodes in - * ascending order. - */ -struct drm_i915_cmd_table { - const struct drm_i915_cmd_descriptor *table; - int count; -}; - /* Note that the (struct drm_i915_private *) cast is just to shut up gcc. */ #define __I915__(p) ({ \ struct drm_i915_private *__p; \ From 5ead0580734bad351694445fa7db9eb8d49f716d Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Mon, 14 Nov 2016 22:39:34 +0000 Subject: [PATCH 67/93] drm/i915: cleanup use of INSTR_CLIENT_MASK commit e3f51ece02f877d2ce9619aa8d5919db56f39582 upstream. Doing cmd_header >> 29 to extract our 3-bit client value where we know cmd_header is a u32 shouldn't then also require the use of a mask. So remove the redundant operation and get rid of INSTR_CLIENT_MASK now that there are no longer any users. Cc: Chris Wilson Signed-off-by: Matthew Auld Reviewed-by: Chris Wilson Signed-off-by: Joonas Lahtinen Signed-off-by: Jon Bloomfield Link: http://patchwork.freedesktop.org/patch/msgid/1479163174-29686-1-git-send-email-matthew.auld@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 6 +++--- drivers/gpu/drm/i915/i915_reg.h | 1 - 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 193d15e947e0..429a249acc0c 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -655,7 +655,7 @@ static const struct drm_i915_reg_table hsw_blt_reg_tables[] = { static u32 gen7_render_get_cmd_length_mask(u32 cmd_header) { - u32 client = (cmd_header & INSTR_CLIENT_MASK) >> INSTR_CLIENT_SHIFT; + u32 client = cmd_header >> INSTR_CLIENT_SHIFT; u32 subclient = (cmd_header & INSTR_SUBCLIENT_MASK) >> INSTR_SUBCLIENT_SHIFT; @@ -674,7 +674,7 @@ static u32 gen7_render_get_cmd_length_mask(u32 cmd_header) static u32 gen7_bsd_get_cmd_length_mask(u32 cmd_header) { - u32 client = (cmd_header & INSTR_CLIENT_MASK) >> INSTR_CLIENT_SHIFT; + u32 client = cmd_header >> INSTR_CLIENT_SHIFT; u32 subclient = (cmd_header & INSTR_SUBCLIENT_MASK) >> INSTR_SUBCLIENT_SHIFT; u32 op = (cmd_header & INSTR_26_TO_24_MASK) >> INSTR_26_TO_24_SHIFT; @@ -697,7 +697,7 @@ static u32 gen7_bsd_get_cmd_length_mask(u32 cmd_header) static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header) { - u32 client = (cmd_header & INSTR_CLIENT_MASK) >> INSTR_CLIENT_SHIFT; + u32 client = cmd_header >> INSTR_CLIENT_SHIFT; if (client == INSTR_MI_CLIENT) return 0x3F; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 70d96162def6..a94caae05cc3 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -295,7 +295,6 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) * Instruction field definitions used by the command parser */ #define INSTR_CLIENT_SHIFT 29 -#define INSTR_CLIENT_MASK 0xE0000000 #define INSTR_MI_CLIENT 0x0 #define INSTR_BC_CLIENT 0x2 #define INSTR_RC_CLIENT 0x3 From eda2e0a12af1030f95ce224ae23eeb01fcc695c0 Mon Sep 17 00:00:00 2001 From: Robert Bragg Date: Mon, 7 Nov 2016 19:49:49 +0000 Subject: [PATCH 68/93] drm/i915: return EACCES for check_cmd() failures commit 9bbeaedb664a6d3e1cfbe6b0c2f07bf667512456 upstream. check_cmd() is checking whether a command adheres to certain restrictions that ensure it's safe to execute within a privileged batch buffer. Returning false implies a privilege problem, not that the command is invalid. The distinction makes the difference between allowing the buffer to be executed as an unprivileged batch buffer or returning an EINVAL error to userspace without executing anything. In a case where userspace may want to test whether it can successfully write to a register that needs privileges the distinction may be important and an EINVAL error may be considered fatal. In particular this is currently true for Mesa, which includes a test for whether OACONTROL can be written too, but Mesa treats any error when flushing a batch buffer as fatal, calling exit(1). As it is currently Mesa can gracefully handle a failure to write to OACONTROL if the command parser is disabled, but if we were to remove OACONTROL from the parser's whitelist then the returned EINVAL would break Mesa applications as they attempt an OACONTROL write. This bumps the command parser version from 7 to 8, as the change is visible to userspace. Signed-off-by: Robert Bragg Reviewed-by: Matthew Auld Reviewed-by: Sourab Gupta Signed-off-by: Daniel Vetter Signed-off-by: Jon Bloomfield Link: http://patchwork.freedesktop.org/patch/msgid/20161107194957.3385-4-robert@sixbynine.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 429a249acc0c..a62b05e87160 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1368,7 +1368,7 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, if (!check_cmd(engine, desc, cmd, length, is_master, &oacontrol_set)) { - ret = -EINVAL; + ret = -EACCES; break; } @@ -1428,6 +1428,9 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv) * 5. GPGPU dispatch compute indirect registers. * 6. TIMESTAMP register and Haswell CS GPR registers * 7. Allow MI_LOAD_REGISTER_REG between whitelisted registers. + * 8. Don't report cmd_check() failures as EINVAL errors to userspace; + * rely on the HW to NOOP disallowed commands as it would without + * the parser enabled. */ - return 7; + return 8; } From 91ff7fa70345e1b137df968808be48739c9c2251 Mon Sep 17 00:00:00 2001 From: Robert Bragg Date: Tue, 8 Nov 2016 12:51:48 +0000 Subject: [PATCH 69/93] drm/i915: don't whitelist oacontrol in cmd parser commit 10ff401df041e57afc2b1619cd252b86d0ae5f30 upstream. Being able to program OACONTROL from a non-privileged batch buffer is not sufficient to be able to configure the OA unit. This was originally allowed to help enable Mesa to expose OA counters via the INTEL_performance_query extension, but the current implementation based on programming OACONTROL via a batch buffer isn't able to report useable data without a more complete OA unit configuration. Mesa handles the possibility that writes to OACONTROL may not be allowed and so only advertises the extension after explicitly testing that a write to OACONTROL succeeds. Based on this; removing OACONTROL from the whitelist should be ok for userspace. Removing this simplifies adding a new kernel api for configuring the OA unit without needing to consider the possibility that userspace might trample on OACONTROL state which we'd like to start managing within the kernel instead. In particular running any Mesa based GL application currently results in clearing OACONTROL when initializing which would disable the capturing of metrics. v2: This bumps the command parser version from 8 to 9, as the change is visible to userspace. Signed-off-by: Robert Bragg Reviewed-by: Matthew Auld Reviewed-by: Sourab Gupta Signed-off-by: Daniel Vetter Signed-off-by: Jon Bloomfield Link: http://patchwork.freedesktop.org/patch/msgid/20161108125148.25007-1-robert@sixbynine.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 42 +++----------------------- 1 file changed, 5 insertions(+), 37 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index a62b05e87160..2e3e9cd6c53c 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -546,7 +546,6 @@ static const struct drm_i915_reg_descriptor gen7_render_regs[] = { REG64(PS_INVOCATION_COUNT), REG64(PS_DEPTH_COUNT), REG64_IDX(RING_TIMESTAMP, RENDER_RING_BASE), - REG32(OACONTROL), /* Only allowed for LRI and SRM. See below. */ REG64(MI_PREDICATE_SRC0), REG64(MI_PREDICATE_SRC1), REG32(GEN7_3DPRIM_END_OFFSET), @@ -1156,8 +1155,7 @@ bool intel_engine_needs_cmd_parser(struct intel_engine_cs *engine) static bool check_cmd(const struct intel_engine_cs *engine, const struct drm_i915_cmd_descriptor *desc, const u32 *cmd, u32 length, - const bool is_master, - bool *oacontrol_set) + const bool is_master) { if (desc->flags & CMD_DESC_SKIP) return true; @@ -1194,31 +1192,6 @@ static bool check_cmd(const struct intel_engine_cs *engine, return false; } - /* - * OACONTROL requires some special handling for - * writes. We want to make sure that any batch which - * enables OA also disables it before the end of the - * batch. The goal is to prevent one process from - * snooping on the perf data from another process. To do - * that, we need to check the value that will be written - * to the register. Hence, limit OACONTROL writes to - * only MI_LOAD_REGISTER_IMM commands. - */ - if (reg_addr == i915_mmio_reg_offset(OACONTROL)) { - if (desc->cmd.value == MI_LOAD_REGISTER_MEM) { - DRM_DEBUG_DRIVER("CMD: Rejected LRM to OACONTROL\n"); - return false; - } - - if (desc->cmd.value == MI_LOAD_REGISTER_REG) { - DRM_DEBUG_DRIVER("CMD: Rejected LRR to OACONTROL\n"); - return false; - } - - if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1)) - *oacontrol_set = (cmd[offset + 1] != 0); - } - /* * Check the value written to the register against the * allowed mask/value pair given in the whitelist entry. @@ -1310,7 +1283,6 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, u32 *cmd, *batch_end; struct drm_i915_cmd_descriptor default_desc = noop_desc; const struct drm_i915_cmd_descriptor *desc = &default_desc; - bool oacontrol_set = false; /* OACONTROL tracking. See check_cmd() */ bool needs_clflush_after = false; int ret = 0; @@ -1366,8 +1338,7 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, break; } - if (!check_cmd(engine, desc, cmd, length, is_master, - &oacontrol_set)) { + if (!check_cmd(engine, desc, cmd, length, is_master)) { ret = -EACCES; break; } @@ -1375,11 +1346,6 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, cmd += length; } - if (oacontrol_set) { - DRM_DEBUG_DRIVER("CMD: batch set OACONTROL but did not clear it\n"); - ret = -EINVAL; - } - if (cmd >= batch_end) { DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n"); ret = -EINVAL; @@ -1431,6 +1397,8 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv) * 8. Don't report cmd_check() failures as EINVAL errors to userspace; * rely on the HW to NOOP disallowed commands as it would without * the parser enabled. + * 9. Don't whitelist or handle oacontrol specially, as ownership + * for oacontrol state is moving to i915-perf. */ - return 8; + return 9; } From ba8ba9898c27b57acefcc46a1b63b20d0187b4de Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 24 Nov 2016 12:58:51 +0000 Subject: [PATCH 70/93] drm/i915: Use the precomputed value for whether to enable command parsing commit 41736a8e3331a67445b271e73be39536c498659e upstream. As i915.enable_cmd_parser is an unsafe option, make it read-only at runtime. Now that it is constant, we can use the value determined during initialisation as to whether we need the cmdparser at execbuffer time. v2: Remove the inline for its single user, it is clear enough (and shorter) without! Signed-off-by: Chris Wilson Reviewed-by: Joonas Lahtinen Signed-off-by: Jon Bloomfield Link: http://patchwork.freedesktop.org/patch/msgid/20161124125851.6615-1-chris@chris-wilson.co.uk Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 23 +--------------------- drivers/gpu/drm/i915/i915_drv.h | 1 - drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +- drivers/gpu/drm/i915/i915_params.c | 6 +++--- drivers/gpu/drm/i915/i915_params.h | 2 +- 5 files changed, 6 insertions(+), 28 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 2e3e9cd6c53c..bdfdb4595a9e 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1131,27 +1131,6 @@ unpin_src: return dst; } -/** - * intel_engine_needs_cmd_parser() - should a given engine use software - * command parsing? - * @engine: the engine in question - * - * Only certain platforms require software batch buffer command parsing, and - * only when enabled via module parameter. - * - * Return: true if the engine requires software command parsing - */ -bool intel_engine_needs_cmd_parser(struct intel_engine_cs *engine) -{ - if (!engine->needs_cmd_parser) - return false; - - if (!USES_PPGTT(engine->i915)) - return false; - - return (i915.enable_cmd_parser == 1); -} - static bool check_cmd(const struct intel_engine_cs *engine, const struct drm_i915_cmd_descriptor *desc, const u32 *cmd, u32 length, @@ -1374,7 +1353,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv) /* If the command parser is not enabled, report 0 - unsupported */ for_each_engine(engine, dev_priv) { - if (intel_engine_needs_cmd_parser(engine)) { + if (engine->needs_cmd_parser) { active = true; break; } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 9320f8265cc6..54b768618bea 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -3455,7 +3455,6 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type); int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv); void intel_engine_init_cmd_parser(struct intel_engine_cs *engine); void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine); -bool intel_engine_needs_cmd_parser(struct intel_engine_cs *engine); int intel_engine_cmd_parser(struct intel_engine_cs *engine, struct drm_i915_gem_object *batch_obj, struct drm_i915_gem_object *shadow_batch_obj, diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 2117f172d7a2..4e66f99a771c 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -1711,7 +1711,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, } params->args_batch_start_offset = args->batch_start_offset; - if (intel_engine_needs_cmd_parser(engine) && args->batch_len) { + if (engine->needs_cmd_parser && args->batch_len) { struct i915_vma *vma; vma = i915_gem_execbuffer_parse(engine, &shadow_exec_entry, diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c index 768ad89d9cd4..9d9dfe194b9b 100644 --- a/drivers/gpu/drm/i915/i915_params.c +++ b/drivers/gpu/drm/i915/i915_params.c @@ -49,7 +49,7 @@ struct i915_params i915 __read_mostly = { .reset = true, .invert_brightness = 0, .disable_display = 0, - .enable_cmd_parser = 1, + .enable_cmd_parser = true, .use_mmio_flip = 0, .mmio_debug = 0, .verbose_state_checks = 1, @@ -178,9 +178,9 @@ MODULE_PARM_DESC(invert_brightness, module_param_named(disable_display, i915.disable_display, bool, 0400); MODULE_PARM_DESC(disable_display, "Disable display (default: false)"); -module_param_named_unsafe(enable_cmd_parser, i915.enable_cmd_parser, int, 0600); +module_param_named_unsafe(enable_cmd_parser, i915.enable_cmd_parser, bool, 0400); MODULE_PARM_DESC(enable_cmd_parser, - "Enable command parsing (1=enabled [default], 0=disabled)"); + "Enable command parsing (true=enabled [default], false=disabled)"); module_param_named_unsafe(use_mmio_flip, i915.use_mmio_flip, int, 0600); MODULE_PARM_DESC(use_mmio_flip, diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h index 3a0dd78ddb38..82ac6e886eed 100644 --- a/drivers/gpu/drm/i915/i915_params.h +++ b/drivers/gpu/drm/i915/i915_params.h @@ -44,7 +44,6 @@ struct i915_params { int disable_power_well; int enable_ips; int invert_brightness; - int enable_cmd_parser; int enable_guc_loading; int enable_guc_submission; int guc_log_level; @@ -53,6 +52,7 @@ struct i915_params { int edp_vswing; unsigned int inject_load_failure; /* leave bools at the end to not create holes */ + bool enable_cmd_parser; bool enable_hangcheck; bool fastboot; bool prefault_disable; From 1414193e7db55a0fd9292e16b2fe630b46a543a7 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 10 Mar 2017 11:55:18 +0000 Subject: [PATCH 71/93] drm/i915/cmdparser: Limit clflush to active cachelines commit 504ae4024131c5a01c3ce8382d49b801375e039c upstream. We only need to clflush those cachelines that we have validated to be read by the GPU. Userspace typically fills the batch length in correctly, the exceptions tend to be explicit tests within igt. v2: Use ptr_mask_bits() to make Mika happy v3: cmd is not advanced on MI_BBE, so make sure to include an extra dword in the clflush. Signed-off-by: Chris Wilson Cc: Mika Kuoppala Link: http://patchwork.freedesktop.org/patch/msgid/20170310115518.13832-1-chris@chris-wilson.co.uk Signed-off-by: Jon Bloomfield Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index bdfdb4595a9e..cd124df3e005 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1279,11 +1279,17 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, * space. Parsing should be faster in some cases this way. */ batch_end = cmd + (batch_len / sizeof(*batch_end)); - while (cmd < batch_end) { + do { u32 length; - if (*cmd == MI_BATCH_BUFFER_END) + if (*cmd == MI_BATCH_BUFFER_END) { + if (needs_clflush_after) { + void *ptr = ptr_mask_bits(shadow_batch_obj->mapping); + drm_clflush_virt_range(ptr, + (void *)(cmd + 1) - ptr); + } break; + } desc = find_cmd(engine, *cmd, desc, &default_desc); if (!desc) { @@ -1323,17 +1329,14 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, } cmd += length; - } + if (cmd >= batch_end) { + DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n"); + ret = -EINVAL; + break; + } + } while (1); - if (cmd >= batch_end) { - DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n"); - ret = -EINVAL; - } - - if (ret == 0 && needs_clflush_after) - drm_clflush_virt_range(shadow_batch_obj->mapping, batch_len); i915_gem_object_unpin_map(shadow_batch_obj); - return ret; } From bebb6a49fd662b312448c152ccf162e9f283e221 Mon Sep 17 00:00:00 2001 From: Jon Bloomfield Date: Thu, 12 Jul 2018 19:53:10 +0100 Subject: [PATCH 72/93] drm/i915/gtt: Add read only pages to gen8_pte_encode commit 25dda4dabeeb12af5209b0183c788ef2a88dabbe upstream. We can set a bit inside the ppGTT PTE to indicate a page is read-only; writes from the GPU will be discarded. We can use this to protect pages and in particular support read-only userptr mappings (necessary for importing PROT_READ vma). Signed-off-by: Jon Bloomfield Signed-off-by: Chris Wilson Cc: Joonas Lahtinen Cc: Matthew Auld Reviewed-by: Joonas Lahtinen Reviewed-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20180712185315.3288-1-chris@chris-wilson.co.uk Reviewed-by: Jon Bloomfield Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_gem_gtt.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 0bb4232f66bc..088f9c03cbb4 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -197,11 +197,14 @@ static void ppgtt_unbind_vma(struct i915_vma *vma) static gen8_pte_t gen8_pte_encode(dma_addr_t addr, enum i915_cache_level level, - bool valid) + bool valid, u32 flags) { gen8_pte_t pte = valid ? _PAGE_PRESENT | _PAGE_RW : 0; pte |= addr; + if (unlikely(flags & PTE_READ_ONLY)) + pte &= ~_PAGE_RW; + switch (level) { case I915_CACHE_NONE: pte |= PPAT_UNCACHED_INDEX; @@ -472,7 +475,7 @@ static void gen8_initialize_pt(struct i915_address_space *vm, gen8_pte_t scratch_pte; scratch_pte = gen8_pte_encode(vm->scratch_page.daddr, - I915_CACHE_LLC, true); + I915_CACHE_LLC, true, 0); fill_px(vm->dev, pt, scratch_pte); } @@ -769,7 +772,7 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm, { struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm); gen8_pte_t scratch_pte = gen8_pte_encode(vm->scratch_page.daddr, - I915_CACHE_LLC, use_scratch); + I915_CACHE_LLC, use_scratch, 0); if (!USES_FULL_48BIT_PPGTT(vm->dev)) { gen8_ppgtt_clear_pte_range(vm, &ppgtt->pdp, start, length, @@ -809,7 +812,7 @@ gen8_ppgtt_insert_pte_entries(struct i915_address_space *vm, pt_vaddr[pte] = gen8_pte_encode(sg_page_iter_dma_address(sg_iter), - cache_level, true); + cache_level, true, 0); if (++pte == GEN8_PTES) { kunmap_px(ppgtt, pt_vaddr); pt_vaddr = NULL; @@ -1452,7 +1455,7 @@ static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m) uint64_t start = ppgtt->base.start; uint64_t length = ppgtt->base.total; gen8_pte_t scratch_pte = gen8_pte_encode(vm->scratch_page.daddr, - I915_CACHE_LLC, true); + I915_CACHE_LLC, true, 0); if (!USES_FULL_48BIT_PPGTT(vm->dev)) { gen8_dump_pdp(&ppgtt->pdp, start, length, scratch_pte, m); @@ -2321,7 +2324,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm, rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv); - gen8_set_pte(pte, gen8_pte_encode(addr, level, true)); + gen8_set_pte(pte, gen8_pte_encode(addr, level, true, 0)); I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN); POSTING_READ(GFX_FLSH_CNTL_GEN6); @@ -2348,7 +2351,7 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm, gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm + (start >> PAGE_SHIFT); for_each_sgt_dma(addr, sgt_iter, st) { - gtt_entry = gen8_pte_encode(addr, level, true); + gtt_entry = gen8_pte_encode(addr, level, true, 0); gen8_set_pte(>t_entries[i++], gtt_entry); } @@ -2499,7 +2502,7 @@ static void gen8_ggtt_clear_range(struct i915_address_space *vm, scratch_pte = gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, - use_scratch); + use_scratch, 0); for (i = 0; i < num_entries; i++) gen8_set_pte(>t_base[i], scratch_pte); readl(gtt_base); From 85e04705c9ea7a68ad0dd0c06abea6bd8fc2cc10 Mon Sep 17 00:00:00 2001 From: Jon Bloomfield Date: Mon, 6 Aug 2018 14:10:48 -0700 Subject: [PATCH 73/93] drm/i915/gtt: Read-only pages for insert_entries on bdw+ commit 250f8c8140ac0a5e5acb91891d6813f12778b224 upstream. Hook up the flags to allow read-only ppGTT mappings for gen8+ v2: Include a selftest to check that writes to a readonly PTE are dropped v3: Don't duplicate cpu_check() as we can just reuse it, and even worse don't wholesale copy the theory-of-operation comment from igt_ctx_exec without changing it to explain the intention behind the new test! v4: Joonas really likes magic mystery values Signed-off-by: Jon Bloomfield Cc: Joonas Lahtinen Cc: Matthew Auld Reviewed-by: Joonas Lahtinen Reviewed-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20180712185315.3288-2-chris@chris-wilson.co.uk Signed-off-by: Jon Bloomfield Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_gem_gtt.c | 28 ++++++++++++++++++------- drivers/gpu/drm/i915/i915_gem_gtt.h | 3 +++ drivers/gpu/drm/i915/intel_ringbuffer.c | 11 +++++++--- 3 files changed, 31 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 088f9c03cbb4..acff88447bd6 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -177,7 +177,7 @@ static int ppgtt_bind_vma(struct i915_vma *vma, vma->pages = vma->obj->pages; - /* Currently applicable only to VLV */ + /* Applicable to VLV, and gen8+ */ if (vma->obj->gt_ro) pte_flags |= PTE_READ_ONLY; @@ -793,7 +793,8 @@ gen8_ppgtt_insert_pte_entries(struct i915_address_space *vm, struct i915_page_directory_pointer *pdp, struct sg_page_iter *sg_iter, uint64_t start, - enum i915_cache_level cache_level) + enum i915_cache_level cache_level, + u32 flags) { struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm); gen8_pte_t *pt_vaddr; @@ -812,7 +813,7 @@ gen8_ppgtt_insert_pte_entries(struct i915_address_space *vm, pt_vaddr[pte] = gen8_pte_encode(sg_page_iter_dma_address(sg_iter), - cache_level, true, 0); + cache_level, true, flags); if (++pte == GEN8_PTES) { kunmap_px(ppgtt, pt_vaddr); pt_vaddr = NULL; @@ -833,7 +834,7 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, struct sg_table *pages, uint64_t start, enum i915_cache_level cache_level, - u32 unused) + u32 flags) { struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm); struct sg_page_iter sg_iter; @@ -842,7 +843,7 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, if (!USES_FULL_48BIT_PPGTT(vm->dev)) { gen8_ppgtt_insert_pte_entries(vm, &ppgtt->pdp, &sg_iter, start, - cache_level); + cache_level, flags); } else { struct i915_page_directory_pointer *pdp; uint64_t pml4e; @@ -850,7 +851,7 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, gen8_for_each_pml4e(pdp, &ppgtt->pml4, start, length, pml4e) { gen8_ppgtt_insert_pte_entries(vm, pdp, &sg_iter, - start, cache_level); + start, cache_level, flags); } } } @@ -1523,6 +1524,10 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt) ppgtt->base.clear_range = gen8_ppgtt_clear_range; ppgtt->base.unbind_vma = ppgtt_unbind_vma; ppgtt->base.bind_vma = ppgtt_bind_vma; + + /* From bdw, there is support for read-only pages in the PPGTT */ + ppgtt->base.has_read_only = true; + ppgtt->debug_dump = gen8_dump_ppgtt; if (USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) { @@ -2335,7 +2340,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm, static void gen8_ggtt_insert_entries(struct i915_address_space *vm, struct sg_table *st, uint64_t start, - enum i915_cache_level level, u32 unused) + enum i915_cache_level level, u32 flags) { struct drm_i915_private *dev_priv = to_i915(vm->dev); struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm); @@ -2346,6 +2351,9 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm, int rpm_atomic_seq; int i = 0; + /* The GTT does not support read-only mappings */ + GEM_BUG_ON(flags & PTE_READ_ONLY); + rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv); gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm + (start >> PAGE_SHIFT); @@ -2607,7 +2615,7 @@ static int ggtt_bind_vma(struct i915_vma *vma, if (ret) return ret; - /* Currently applicable only to VLV */ + /* Applicable to VLV (gen8+ do not support RO in the GGTT) */ if (obj->gt_ro) pte_flags |= PTE_READ_ONLY; @@ -3196,6 +3204,10 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv) ggtt->base.total -= PAGE_SIZE; i915_address_space_init(&ggtt->base, dev_priv); ggtt->base.total += PAGE_SIZE; + + /* Only VLV supports read-only GGTT mappings */ + ggtt->base.has_read_only = IS_VALLEYVIEW(dev_priv); + if (!HAS_LLC(dev_priv)) ggtt->base.mm.color_adjust = i915_gtt_color_adjust; diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index ec78be2f8c77..43a0192242eb 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -392,6 +392,9 @@ struct i915_address_space { */ struct list_head unbound_list; + /* Some systems support read-only mappings for GGTT and/or PPGTT */ + bool has_read_only:1; + /* FIXME: Need a more generic return type */ gen6_pte_t (*pte_encode)(dma_addr_t addr, enum i915_cache_level level, diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 8babfe0ce4e3..418d1d142067 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -1951,6 +1951,7 @@ void intel_ring_unpin(struct intel_ring *ring) static struct i915_vma * intel_ring_create_vma(struct drm_i915_private *dev_priv, int size) { + struct i915_address_space *vm = &dev_priv->ggtt.base; struct drm_i915_gem_object *obj; struct i915_vma *vma; @@ -1960,10 +1961,14 @@ intel_ring_create_vma(struct drm_i915_private *dev_priv, int size) if (IS_ERR(obj)) return ERR_CAST(obj); - /* mark ring buffers as read-only from GPU side by default */ - obj->gt_ro = 1; + /* + * Mark ring buffers as read-only from GPU side (so no stray overwrites) + * if supported by the platform's GGTT. + */ + if (vm->has_read_only) + obj->gt_ro = 1; - vma = i915_vma_create(obj, &dev_priv->ggtt.base, NULL); + vma = i915_vma_create(obj, vm, NULL); if (IS_ERR(vma)) goto err; From 9c37932bf60fc7ccf8b0a6a5a49763e33ae24d6e Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 12 Jul 2018 19:53:12 +0100 Subject: [PATCH 74/93] drm/i915/gtt: Disable read-only support under GVT commit c9e666880de5a1fed04dc412b046916d542b72dd upstream. GVT is not propagating the PTE bits, and is always setting the read-write bit, thus breaking read-only support. Signed-off-by: Chris Wilson Cc: Zhenyu Wang Cc: Jon Bloomfield Cc: Joonas Lahtinen Cc: Matthew Auld Reviewed-by: Jon Bloomfield Link: https://patchwork.freedesktop.org/patch/msgid/20180712185315.3288-3-chris@chris-wilson.co.uk Signed-off--by: Jon Bloomfield Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_gem_gtt.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index acff88447bd6..83c7497e9aa7 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -1525,8 +1525,12 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt) ppgtt->base.unbind_vma = ppgtt_unbind_vma; ppgtt->base.bind_vma = ppgtt_bind_vma; - /* From bdw, there is support for read-only pages in the PPGTT */ - ppgtt->base.has_read_only = true; + /* + * From bdw, there is support for read-only pages in the PPGTT. + * + * XXX GVT is not honouring the lack of RW in the PTE bits. + */ + ppgtt->base.has_read_only = !intel_vgpu_active(to_i915(ppgtt->base.dev)); ppgtt->debug_dump = gen8_dump_ppgtt; From 91b712cffa4e7be02706ea92368cc0cdb930a56c Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 12 Jul 2018 19:53:13 +0100 Subject: [PATCH 75/93] drm/i915: Prevent writing into a read-only object via a GGTT mmap commit 3e977ac6179b39faa3c0eda5fce4f00663ae298d upstream. If the user has created a read-only object, they should not be allowed to circumvent the write protection by using a GGTT mmapping. Deny it. Also most machines do not support read-only GGTT PTEs, so again we have to reject attempted writes. Fortunately, this is known a priori, so we can at least reject in the call to create the mmap (with a sanity check in the fault handler). v2: Check the vma->vm_flags during mmap() to allow readonly access. v3: Remove VM_MAYWRITE to curtail mprotect() Testcase: igt/gem_userptr_blits/readonly_mmap* Signed-off-by: Chris Wilson Cc: Jon Bloomfield Cc: Joonas Lahtinen Cc: Matthew Auld Cc: David Herrmann Reviewed-by: Matthew Auld #v1 Reviewed-by: Joonas Lahtinen Link: https://patchwork.freedesktop.org/patch/msgid/20180712185315.3288-4-chris@chris-wilson.co.uk Signed-off-by: Rodrigo Vivi Reviewed-by: Jon Bloomfield Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_gem.c | 9 +++++++++ drivers/gpu/drm/i915/i915_drv.h | 12 ++++++++++++ drivers/gpu/drm/i915/i915_gem.c | 4 ++++ drivers/gpu/drm/i915/i915_gem_gtt.c | 11 ++++++++--- drivers/gpu/drm/i915/intel_ringbuffer.c | 2 +- include/drm/drm_vma_manager.h | 1 + 6 files changed, 35 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 48e99ab525c3..ae5c0952a7a3 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -996,6 +996,15 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma) return -EACCES; } + if (node->readonly) { + if (vma->vm_flags & VM_WRITE) { + drm_gem_object_unreference_unlocked(obj); + return -EINVAL; + } + + vma->vm_flags &= ~VM_MAYWRITE; + } + ret = drm_gem_mmap_obj(obj, drm_vma_node_size(node) << PAGE_SHIFT, vma); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 54b768618bea..eb740997f143 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2339,6 +2339,18 @@ i915_gem_object_put_unlocked(struct drm_i915_gem_object *obj) __deprecated extern void drm_gem_object_unreference_unlocked(struct drm_gem_object *); +static inline void +i915_gem_object_set_readonly(struct drm_i915_gem_object *obj) +{ + obj->base.vma_node.readonly = true; +} + +static inline bool +i915_gem_object_is_readonly(const struct drm_i915_gem_object *obj) +{ + return obj->base.vma_node.readonly; +} + static inline bool i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj) { diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 26c4befcd234..f1c4e95baa28 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1773,6 +1773,10 @@ int i915_gem_fault(struct vm_area_struct *area, struct vm_fault *vmf) unsigned int flags; int ret; + /* Sanity check that we allow writing into this object */ + if (i915_gem_object_is_readonly(obj) && write) + return VM_FAULT_SIGBUS; + /* We don't use vmf->pgoff since that has the fake offset */ page_offset = ((unsigned long)vmf->virtual_address - area->vm_start) >> PAGE_SHIFT; diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 83c7497e9aa7..bfe40d9e5ac9 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -178,7 +178,7 @@ static int ppgtt_bind_vma(struct i915_vma *vma, vma->pages = vma->obj->pages; /* Applicable to VLV, and gen8+ */ - if (vma->obj->gt_ro) + if (i915_gem_object_is_readonly(vma->obj)) pte_flags |= PTE_READ_ONLY; vma->vm->insert_entries(vma->vm, vma->pages, vma->node.start, @@ -2360,6 +2360,11 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm, rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv); + /* + * Note that we ignore PTE_READ_ONLY here. The caller must be careful + * not to allow the user to override access to a read only page. + */ + gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm + (start >> PAGE_SHIFT); for_each_sgt_dma(addr, sgt_iter, st) { @@ -2620,7 +2625,7 @@ static int ggtt_bind_vma(struct i915_vma *vma, return ret; /* Applicable to VLV (gen8+ do not support RO in the GGTT) */ - if (obj->gt_ro) + if (i915_gem_object_is_readonly(obj)) pte_flags |= PTE_READ_ONLY; vma->vm->insert_entries(vma->vm, vma->pages, vma->node.start, @@ -2649,7 +2654,7 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma, /* Currently applicable only to VLV */ pte_flags = 0; - if (vma->obj->gt_ro) + if (i915_gem_object_is_readonly(vma->obj)) pte_flags |= PTE_READ_ONLY; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 418d1d142067..29c3123840ae 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -1966,7 +1966,7 @@ intel_ring_create_vma(struct drm_i915_private *dev_priv, int size) * if supported by the platform's GGTT. */ if (vm->has_read_only) - obj->gt_ro = 1; + i915_gem_object_set_readonly(obj); vma = i915_vma_create(obj, vm, NULL); if (IS_ERR(vma)) diff --git a/include/drm/drm_vma_manager.h b/include/drm/drm_vma_manager.h index 9c03895dc479..72bf408f887f 100644 --- a/include/drm/drm_vma_manager.h +++ b/include/drm/drm_vma_manager.h @@ -42,6 +42,7 @@ struct drm_vma_offset_node { rwlock_t vm_lock; struct drm_mm_node vm_node; struct rb_root vm_files; + bool readonly:1; }; struct drm_vma_offset_manager { From eaae4e6ef12d324a87f82561c570d48e5de98182 Mon Sep 17 00:00:00 2001 From: Michal Srb Date: Mon, 5 Feb 2018 16:04:37 +0000 Subject: [PATCH 76/93] drm/i915/cmdparser: Check reg_table_count before derefencing. commit 2f265fad9756a40c09e3f4dcc62d5d7fa73a9fb2 upstream. The find_reg function was assuming that there is always at least one table in reg_tables. It is not always true. In case of VCS or VECS, the reg_tables is NULL and reg_table_count is 0, implying that no register-accessing commands are allowed. However, the command tables include commands such as MI_STORE_REGISTER_MEM. When trying to check such command, the find_reg would dereference NULL pointer. Now it will just return NULL meaning that the register was not found and the command will be rejected. Fixes: 76ff480ec963 ("drm/i915/cmdparser: Use binary search for faster register lookup") Signed-off-by: Michal Srb Link: https://patchwork.freedesktop.org/patch/msgid/20180205142916.27092-2-msrb@suse.com Cc: Chris Wilson Cc: Matthew Auld Reviewed-by: Chris Wilson Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20180205160438.3267-1-chris@chris-wilson.co.uk register lookup") Reviewed-by: Jon Bloomfield Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index cd124df3e005..d844ab00be69 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1038,7 +1038,7 @@ find_reg(const struct intel_engine_cs *engine, bool is_master, u32 addr) const struct drm_i915_reg_table *table = engine->reg_tables; int count = engine->reg_table_count; - do { + for (; count > 0; ++table, --count) { if (!table->master || is_master) { const struct drm_i915_reg_descriptor *reg; @@ -1046,7 +1046,7 @@ find_reg(const struct intel_engine_cs *engine, bool is_master, u32 addr) if (reg != NULL) return reg; } - } while (table++, --count); + } return NULL; } From ce3748042e268a2be3c1397923424799c20ccd00 Mon Sep 17 00:00:00 2001 From: Michal Srb Date: Mon, 5 Feb 2018 16:04:38 +0000 Subject: [PATCH 77/93] drm/i915/cmdparser: Do not check past the cmd length. commit b3ad99ed45917f42884fee731fa3cf9b8229a26c upstream. The command MEDIA_VFE_STATE checks bits at offset +2 dwords. However, it is possible to have MEDIA_VFE_STATE command with length = 0 + LENGTH_BIAS = 2. In that case check_cmd will read bits from the following command, or even past the end of the buffer. If the offset ends up outside of the command length, reject the command. Fixes: 351e3db2b363 ("drm/i915: Implement command buffer parsing logic") Signed-off-by: Michal Srb Link: https://patchwork.freedesktop.org/patch/msgid/20180205151745.29292-1-msrb@suse.com Reviewed-by: Chris Wilson Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20180205160438.3267-2-chris@chris-wilson.co.uk Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index d844ab00be69..0ea7a4e71f9a 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1218,6 +1218,12 @@ static bool check_cmd(const struct intel_engine_cs *engine, continue; } + if (desc->bits[i].offset >= length) { + DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X, too short to check bitmask (%s)\n", + *cmd, engine->name); + return false; + } + dword = cmd[desc->bits[i].offset] & desc->bits[i].mask; From b3c37ff5fe6faf534aeffe246d67577acd316c9f Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 7 Nov 2017 15:40:55 +0000 Subject: [PATCH 78/93] drm/i915: Silence smatch for cmdparser commit 0ffba1fc98e8ec35caae8d50b657296ebb9a9a51 upstream. drivers/gpu/drm/i915/i915_cmd_parser.c:808:23: error: not an lvalue drivers/gpu/drm/i915/i915_cmd_parser.c:811:23: error: not an lvalue drivers/gpu/drm/i915/i915_cmd_parser.c:814:23: error: not an lvalue drivers/gpu/drm/i915/i915_cmd_parser.c:808:23: error: not an lvalue drivers/gpu/drm/i915/i915_cmd_parser.c:811:23: error: not an lvalue drivers/gpu/drm/i915/i915_cmd_parser.c:814:23: error: not an lvalue drivers/gpu/drm/i915/i915_cmd_parser.c:808:23: error: not an lvalue drivers/gpu/drm/i915/i915_cmd_parser.c:811:23: error: not an lvalue drivers/gpu/drm/i915/i915_cmd_parser.c:814:23: error: not an lvalue drivers/gpu/drm/i915/i915_cmd_parser.c:808:23: error: not an lvalue drivers/gpu/drm/i915/i915_cmd_parser.c:811:23: error: not an lvalue drivers/gpu/drm/i915/i915_cmd_parser.c:814:23: error: not an lvalue If we move the shift into each case not only do we kill the warning from smatch, but we shrink the code slightly: text data bss dec hex filename 1267906 20587 3168 1291661 13b58d before 1267890 20587 3168 1291645 13b57d after Signed-off-by: Chris Wilson Cc: Joonas Lahtinen Cc: Mika Kuoppala Cc: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20171107154055.19460-1-chris@chris-wilson.co.uk Reviewed-by: Matthew Auld Reviewed-by: Gabriel Krisman Bertazi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 0ea7a4e71f9a..d50d4a4d5e00 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -798,22 +798,15 @@ struct cmd_node { */ static inline u32 cmd_header_key(u32 x) { - u32 shift; - switch (x >> INSTR_CLIENT_SHIFT) { default: case INSTR_MI_CLIENT: - shift = STD_MI_OPCODE_SHIFT; - break; + return x >> STD_MI_OPCODE_SHIFT; case INSTR_RC_CLIENT: - shift = STD_3D_OPCODE_SHIFT; - break; + return x >> STD_3D_OPCODE_SHIFT; case INSTR_BC_CLIENT: - shift = STD_2D_OPCODE_SHIFT; - break; + return x >> STD_2D_OPCODE_SHIFT; } - - return x >> shift; } static int init_hash_table(struct intel_engine_cs *engine, From fd8e74276ccd58e44b7130178d9ec76cd6f704b6 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Wed, 29 Nov 2017 08:24:09 +0000 Subject: [PATCH 79/93] drm/i915: Move engine->needs_cmd_parser to engine->flags commit 439e2ee4ca520e72870e4fa44aa0076060ad6857 upstream. Will be adding a new per-engine flags shortly so it makes sense to consolidate. v2: Keep the original code flow in intel_engine_cleanup_cmd_parser. (Joonas Lahtinen) Signed-off-by: Tvrtko Ursulin Suggested-by: Chris Wilson Reviewed-by: Chris Wilson Reviewed-by: Sagar Arun Kamble Reviewed-by: Joonas Lahtinen Link: https://patchwork.freedesktop.org/patch/msgid/20171129082409.18189-1-tvrtko.ursulin@linux.intel.com Signed-off-by: Jon Bloomfield Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 7 ++++--- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +- drivers/gpu/drm/i915/intel_ringbuffer.h | 10 ++++++++-- 3 files changed, 13 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index d50d4a4d5e00..e365f5358959 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -26,6 +26,7 @@ */ #include "i915_drv.h" +#include "intel_ringbuffer.h" /** * DOC: batch buffer command parser @@ -940,7 +941,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) return; } - engine->needs_cmd_parser = true; + engine->flags |= I915_ENGINE_NEEDS_CMD_PARSER; } /** @@ -952,7 +953,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) */ void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine) { - if (!engine->needs_cmd_parser) + if (!intel_engine_needs_cmd_parser(engine)) return; fini_hash_table(engine); @@ -1355,7 +1356,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv) /* If the command parser is not enabled, report 0 - unsupported */ for_each_engine(engine, dev_priv) { - if (engine->needs_cmd_parser) { + if (intel_engine_needs_cmd_parser(engine)) { active = true; break; } diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 4e66f99a771c..2117f172d7a2 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -1711,7 +1711,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, } params->args_batch_start_offset = args->batch_start_offset; - if (engine->needs_cmd_parser && args->batch_len) { + if (intel_engine_needs_cmd_parser(engine) && args->batch_len) { struct i915_vma *vma; vma = i915_gem_execbuffer_parse(engine, &shadow_exec_entry, diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index ec0b4a0c605d..e24d1324f094 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -341,7 +341,8 @@ struct intel_engine_cs { struct intel_engine_hangcheck hangcheck; - bool needs_cmd_parser; +#define I915_ENGINE_NEEDS_CMD_PARSER BIT(0) + unsigned int flags; /* * Table of commands the command parser needs to know about @@ -374,7 +375,12 @@ intel_engine_initialized(const struct intel_engine_cs *engine) return engine->i915 != NULL; } -static inline unsigned +static inline bool intel_engine_needs_cmd_parser(struct intel_engine_cs *engine) +{ + return engine->flags & I915_ENGINE_NEEDS_CMD_PARSER; +} + +static inline unsigned int intel_engine_flag(const struct intel_engine_cs *engine) { return 1 << engine->id; From 64003d092ec9b9ecf03984513aee106c15b411e7 Mon Sep 17 00:00:00 2001 From: Jon Bloomfield Date: Fri, 20 Apr 2018 14:26:01 -0700 Subject: [PATCH 80/93] drm/i915: Rename gen7 cmdparser tables commit 0a2f661b6c21815a7fa60e30babe975fee8e73c6 upstream. We're about to introduce some new tables for later gens, and the current naming for the gen7 tables will no longer make sense. v2: rebase Signed-off-by: Jon Bloomfield Cc: Tony Luck Cc: Dave Airlie Cc: Takashi Iwai Cc: Tyler Hicks Signed-off-by: Mika Kuoppala Reviewed-by: Chris Wilson Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 70 +++++++++++++------------- 1 file changed, 35 insertions(+), 35 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index e365f5358959..e93d6b63d489 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -211,7 +211,7 @@ struct drm_i915_cmd_table { /* Command Mask Fixed Len Action ---------------------------------------------------------- */ -static const struct drm_i915_cmd_descriptor common_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_common_cmds[] = { CMD( MI_NOOP, SMI, F, 1, S ), CMD( MI_USER_INTERRUPT, SMI, F, 1, R ), CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, M ), @@ -244,7 +244,7 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = { CMD( MI_BATCH_BUFFER_START, SMI, !F, 0xFF, S ), }; -static const struct drm_i915_cmd_descriptor render_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_render_cmds[] = { CMD( MI_FLUSH, SMI, F, 1, S ), CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), CMD( MI_PREDICATE, SMI, F, 1, S ), @@ -328,7 +328,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = { CMD( GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS, S3D, !F, 0x1FF, S ), }; -static const struct drm_i915_cmd_descriptor video_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_video_cmds[] = { CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), CMD( MI_SET_APPID, SMI, F, 1, S ), CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B, @@ -372,7 +372,7 @@ static const struct drm_i915_cmd_descriptor video_cmds[] = { CMD( MFX_WAIT, SMFX, F, 1, S ), }; -static const struct drm_i915_cmd_descriptor vecs_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_vecs_cmds[] = { CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), CMD( MI_SET_APPID, SMI, F, 1, S ), CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B, @@ -410,7 +410,7 @@ static const struct drm_i915_cmd_descriptor vecs_cmds[] = { }}, ), }; -static const struct drm_i915_cmd_descriptor blt_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_blt_cmds[] = { CMD( MI_DISPLAY_FLIP, SMI, !F, 0xFF, R ), CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3FF, B, .bits = {{ @@ -463,35 +463,35 @@ static const struct drm_i915_cmd_descriptor noop_desc = #undef B #undef M -static const struct drm_i915_cmd_table gen7_render_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { render_cmds, ARRAY_SIZE(render_cmds) }, +static const struct drm_i915_cmd_table gen7_render_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) }, }; -static const struct drm_i915_cmd_table hsw_render_ring_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { render_cmds, ARRAY_SIZE(render_cmds) }, +static const struct drm_i915_cmd_table hsw_render_ring_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) }, { hsw_render_cmds, ARRAY_SIZE(hsw_render_cmds) }, }; -static const struct drm_i915_cmd_table gen7_video_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { video_cmds, ARRAY_SIZE(video_cmds) }, +static const struct drm_i915_cmd_table gen7_video_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_video_cmds, ARRAY_SIZE(gen7_video_cmds) }, }; -static const struct drm_i915_cmd_table hsw_vebox_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { vecs_cmds, ARRAY_SIZE(vecs_cmds) }, +static const struct drm_i915_cmd_table hsw_vebox_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_vecs_cmds, ARRAY_SIZE(gen7_vecs_cmds) }, }; -static const struct drm_i915_cmd_table gen7_blt_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { blt_cmds, ARRAY_SIZE(blt_cmds) }, +static const struct drm_i915_cmd_table gen7_blt_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) }, }; -static const struct drm_i915_cmd_table hsw_blt_ring_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { blt_cmds, ARRAY_SIZE(blt_cmds) }, +static const struct drm_i915_cmd_table hsw_blt_ring_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) }, { hsw_blt_cmds, ARRAY_SIZE(hsw_blt_cmds) }, }; @@ -871,12 +871,12 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) switch (engine->id) { case RCS: if (IS_HASWELL(engine->i915)) { - cmd_tables = hsw_render_ring_cmds; + cmd_tables = hsw_render_ring_cmd_table; cmd_table_count = - ARRAY_SIZE(hsw_render_ring_cmds); + ARRAY_SIZE(hsw_render_ring_cmd_table); } else { - cmd_tables = gen7_render_cmds; - cmd_table_count = ARRAY_SIZE(gen7_render_cmds); + cmd_tables = gen7_render_cmd_table; + cmd_table_count = ARRAY_SIZE(gen7_render_cmd_table); } if (IS_HASWELL(engine->i915)) { @@ -890,17 +890,17 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) engine->get_cmd_length_mask = gen7_render_get_cmd_length_mask; break; case VCS: - cmd_tables = gen7_video_cmds; - cmd_table_count = ARRAY_SIZE(gen7_video_cmds); + cmd_tables = gen7_video_cmd_table; + cmd_table_count = ARRAY_SIZE(gen7_video_cmd_table); engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask; break; case BCS: if (IS_HASWELL(engine->i915)) { - cmd_tables = hsw_blt_ring_cmds; - cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds); + cmd_tables = hsw_blt_ring_cmd_table; + cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmd_table); } else { - cmd_tables = gen7_blt_cmds; - cmd_table_count = ARRAY_SIZE(gen7_blt_cmds); + cmd_tables = gen7_blt_cmd_table; + cmd_table_count = ARRAY_SIZE(gen7_blt_cmd_table); } if (IS_HASWELL(engine->i915)) { @@ -914,8 +914,8 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask; break; case VECS: - cmd_tables = hsw_vebox_cmds; - cmd_table_count = ARRAY_SIZE(hsw_vebox_cmds); + cmd_tables = hsw_vebox_cmd_table; + cmd_table_count = ARRAY_SIZE(hsw_vebox_cmd_table); /* VECS can use the same length_mask function as VCS */ engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask; break; From 52306d4210bce70455ab80a598e1658a41ec569e Mon Sep 17 00:00:00 2001 From: Jon Bloomfield Date: Fri, 8 Jun 2018 08:53:46 -0700 Subject: [PATCH 81/93] drm/i915: Disable Secure Batches for gen6+ commit 44157641d448cbc0c4b73c5231d2b911f0cb0427 upstream. Retroactively stop reporting support for secure batches through the api for gen6+ so that older binaries trigger the fallback path instead. Older binaries use secure batches pre gen6 to access resources that are not available to normal usermode processes. However, all known userspace explicitly checks for HAS_SECURE_BATCHES before relying on the secure batch feature. Since there are no known binaries relying on this for newer gens we can kill secure batches from gen6, via I915_PARAM_HAS_SECURE_BATCHES. v2: rebase (Mika) v3: rebase (Mika) Signed-off-by: Jon Bloomfield Cc: Tony Luck Cc: Dave Airlie Cc: Takashi Iwai Cc: Tyler Hicks Signed-off-by: Mika Kuoppala Reviewed-by: Chris Wilson Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_drv.c | 2 +- drivers/gpu/drm/i915/i915_drv.h | 2 ++ drivers/gpu/drm/i915/i915_gem_execbuffer.c | 9 ++++++++- 3 files changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index bae62cf934cf..56b8aacc2d76 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -280,7 +280,7 @@ static int i915_getparam(struct drm_device *dev, void *data, value = i915.semaphores; break; case I915_PARAM_HAS_SECURE_BATCHES: - value = capable(CAP_SYS_ADMIN); + value = HAS_SECURE_BATCHES(dev_priv) && capable(CAP_SYS_ADMIN); break; case I915_PARAM_CMD_PARSER_VERSION: value = i915_cmd_parser_get_version(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index eb740997f143..916fd13d53ba 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2661,6 +2661,8 @@ static inline struct scatterlist *__sg_next(struct scatterlist *sg) #define HAS_BLT(dev_priv) HAS_ENGINE(dev_priv, BCS) #define HAS_VEBOX(dev_priv) HAS_ENGINE(dev_priv, VECS) +#define HAS_SECURE_BATCHES(dev_priv) (INTEL_GEN(dev_priv) < 6) + #define HAS_LLC(dev) (INTEL_INFO(dev)->has_llc) #define HAS_SNOOP(dev) (INTEL_INFO(dev)->has_snoop) #define HAS_EDRAM(dev) (!!(__I915__(dev)->edram_cap & EDRAM_ENABLED)) diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 2117f172d7a2..9e8b052bd5d9 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -1601,8 +1601,15 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, dispatch_flags = 0; if (args->flags & I915_EXEC_SECURE) { + if (INTEL_GEN(dev_priv) >= 11) + return -ENODEV; + + /* Return -EPERM to trigger fallback code on old binaries. */ + if (!HAS_SECURE_BATCHES(dev_priv)) + return -EPERM; + if (!drm_is_current_master(file) || !capable(CAP_SYS_ADMIN)) - return -EPERM; + return -EPERM; dispatch_flags |= I915_DISPATCH_SECURE; } From 44f0f8d44b3771270657bc7b2372d995350752d4 Mon Sep 17 00:00:00 2001 From: Jon Bloomfield Date: Fri, 8 Jun 2018 10:05:26 -0700 Subject: [PATCH 82/93] drm/i915: Remove Master tables from cmdparser commit 66d8aba1cd6db34af10de465c0d52af679288cb6 upstream. The previous patch has killed support for secure batches on gen6+, and hence the cmdparsers master tables are now dead code. Remove them. Signed-off-by: Jon Bloomfield Cc: Tony Luck Cc: Dave Airlie Cc: Takashi Iwai Cc: Tyler Hicks Signed-off-by: Mika Kuoppala Reviewed-by: Chris Wilson Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 84 ++++++---------------- drivers/gpu/drm/i915/i915_drv.h | 3 +- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 9 +-- 3 files changed, 26 insertions(+), 70 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index e93d6b63d489..462d0f700a8c 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -51,13 +51,11 @@ * granting userspace undue privileges. There are three categories of privilege. * * First, commands which are explicitly defined as privileged or which should - * only be used by the kernel driver. The parser generally rejects such - * commands, though it may allow some from the drm master process. + * only be used by the kernel driver. The parser rejects such commands * * Second, commands which access registers. To support correct/enhanced * userspace functionality, particularly certain OpenGL extensions, the parser - * provides a whitelist of registers which userspace may safely access (for both - * normal and drm master processes). + * provides a whitelist of registers which userspace may safely access * * Third, commands which access privileged memory (i.e. GGTT, HWS page, etc). * The parser always rejects such commands. @@ -82,9 +80,9 @@ * in the per-engine command tables. * * Other command table entries map fairly directly to high level categories - * mentioned above: rejected, master-only, register whitelist. The parser - * implements a number of checks, including the privileged memory checks, via a - * general bitmasking mechanism. + * mentioned above: rejected, register whitelist. The parser implements a number + * of checks, including the privileged memory checks, via a general bitmasking + * mechanism. */ /* @@ -102,8 +100,6 @@ struct drm_i915_cmd_descriptor { * CMD_DESC_REJECT: The command is never allowed * CMD_DESC_REGISTER: The command should be checked against the * register whitelist for the appropriate ring - * CMD_DESC_MASTER: The command is allowed if the submitting process - * is the DRM master */ u32 flags; #define CMD_DESC_FIXED (1<<0) @@ -111,7 +107,6 @@ struct drm_i915_cmd_descriptor { #define CMD_DESC_REJECT (1<<2) #define CMD_DESC_REGISTER (1<<3) #define CMD_DESC_BITMASK (1<<4) -#define CMD_DESC_MASTER (1<<5) /* * The command's unique identification bits and the bitmask to get them. @@ -207,14 +202,13 @@ struct drm_i915_cmd_table { #define R CMD_DESC_REJECT #define W CMD_DESC_REGISTER #define B CMD_DESC_BITMASK -#define M CMD_DESC_MASTER /* Command Mask Fixed Len Action ---------------------------------------------------------- */ static const struct drm_i915_cmd_descriptor gen7_common_cmds[] = { CMD( MI_NOOP, SMI, F, 1, S ), CMD( MI_USER_INTERRUPT, SMI, F, 1, R ), - CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, M ), + CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, R ), CMD( MI_ARB_CHECK, SMI, F, 1, S ), CMD( MI_REPORT_HEAD, SMI, F, 1, S ), CMD( MI_SUSPEND_FLUSH, SMI, F, 1, S ), @@ -311,7 +305,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = { CMD( MI_URB_ATOMIC_ALLOC, SMI, F, 1, S ), CMD( MI_SET_APPID, SMI, F, 1, S ), CMD( MI_RS_CONTEXT, SMI, F, 1, S ), - CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, M ), + CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, R ), CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, R ), CMD( MI_LOAD_REGISTER_REG, SMI, !F, 0xFF, W, .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 } ), @@ -444,7 +438,7 @@ static const struct drm_i915_cmd_descriptor gen7_blt_cmds[] = { }; static const struct drm_i915_cmd_descriptor hsw_blt_cmds[] = { - CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, M ), + CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, R ), CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, R ), }; @@ -461,7 +455,6 @@ static const struct drm_i915_cmd_descriptor noop_desc = #undef R #undef W #undef B -#undef M static const struct drm_i915_cmd_table gen7_render_cmd_table[] = { { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, @@ -610,47 +603,29 @@ static const struct drm_i915_reg_descriptor gen7_blt_regs[] = { REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE), }; -static const struct drm_i915_reg_descriptor ivb_master_regs[] = { - REG32(FORCEWAKE_MT), - REG32(DERRMR), - REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_A)), - REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_B)), - REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_C)), -}; - -static const struct drm_i915_reg_descriptor hsw_master_regs[] = { - REG32(FORCEWAKE_MT), - REG32(DERRMR), -}; - #undef REG64 #undef REG32 struct drm_i915_reg_table { const struct drm_i915_reg_descriptor *regs; int num_regs; - bool master; }; static const struct drm_i915_reg_table ivb_render_reg_tables[] = { - { gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false }, - { ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true }, + { gen7_render_regs, ARRAY_SIZE(gen7_render_regs) }, }; static const struct drm_i915_reg_table ivb_blt_reg_tables[] = { - { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false }, - { ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true }, + { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) }, }; static const struct drm_i915_reg_table hsw_render_reg_tables[] = { - { gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false }, - { hsw_render_regs, ARRAY_SIZE(hsw_render_regs), false }, - { hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true }, + { gen7_render_regs, ARRAY_SIZE(gen7_render_regs) }, + { hsw_render_regs, ARRAY_SIZE(hsw_render_regs) }, }; static const struct drm_i915_reg_table hsw_blt_reg_tables[] = { - { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false }, - { hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true }, + { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) }, }; static u32 gen7_render_get_cmd_length_mask(u32 cmd_header) @@ -1027,22 +1002,16 @@ __find_reg(const struct drm_i915_reg_descriptor *table, int count, u32 addr) } static const struct drm_i915_reg_descriptor * -find_reg(const struct intel_engine_cs *engine, bool is_master, u32 addr) +find_reg(const struct intel_engine_cs *engine, u32 addr) { const struct drm_i915_reg_table *table = engine->reg_tables; + const struct drm_i915_reg_descriptor *reg = NULL; int count = engine->reg_table_count; - for (; count > 0; ++table, --count) { - if (!table->master || is_master) { - const struct drm_i915_reg_descriptor *reg; + for (; !reg && (count > 0); ++table, --count) + reg = __find_reg(table->regs, table->num_regs, addr); - reg = __find_reg(table->regs, table->num_regs, addr); - if (reg != NULL) - return reg; - } - } - - return NULL; + return reg; } /* Returns a vmap'd pointer to dst_obj, which the caller must unmap */ @@ -1127,8 +1096,7 @@ unpin_src: static bool check_cmd(const struct intel_engine_cs *engine, const struct drm_i915_cmd_descriptor *desc, - const u32 *cmd, u32 length, - const bool is_master) + const u32 *cmd, u32 length) { if (desc->flags & CMD_DESC_SKIP) return true; @@ -1138,12 +1106,6 @@ static bool check_cmd(const struct intel_engine_cs *engine, return false; } - if ((desc->flags & CMD_DESC_MASTER) && !is_master) { - DRM_DEBUG_DRIVER("CMD: Rejected master-only command: 0x%08X\n", - *cmd); - return false; - } - if (desc->flags & CMD_DESC_REGISTER) { /* * Get the distance between individual register offset @@ -1157,7 +1119,7 @@ static bool check_cmd(const struct intel_engine_cs *engine, offset += step) { const u32 reg_addr = cmd[offset] & desc->reg.mask; const struct drm_i915_reg_descriptor *reg = - find_reg(engine, is_master, reg_addr); + find_reg(engine, reg_addr); if (!reg) { DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (exec_id=%d)\n", @@ -1244,7 +1206,6 @@ static bool check_cmd(const struct intel_engine_cs *engine, * @shadow_batch_obj: copy of the batch buffer in question * @batch_start_offset: byte offset in the batch at which execution starts * @batch_len: length of the commands in batch_obj - * @is_master: is the submitting process the drm master? * * Parses the specified batch buffer looking for privilege violations as * described in the overview. @@ -1256,8 +1217,7 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, struct drm_i915_gem_object *batch_obj, struct drm_i915_gem_object *shadow_batch_obj, u32 batch_start_offset, - u32 batch_len, - bool is_master) + u32 batch_len) { u32 *cmd, *batch_end; struct drm_i915_cmd_descriptor default_desc = noop_desc; @@ -1323,7 +1283,7 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, break; } - if (!check_cmd(engine, desc, cmd, length, is_master)) { + if (!check_cmd(engine, desc, cmd, length)) { ret = -EACCES; break; } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 916fd13d53ba..73b88da64127 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -3473,8 +3473,7 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, struct drm_i915_gem_object *batch_obj, struct drm_i915_gem_object *shadow_batch_obj, u32 batch_start_offset, - u32 batch_len, - bool is_master); + u32 batch_len); /* i915_suspend.c */ extern int i915_save_state(struct drm_device *dev); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 9e8b052bd5d9..1f5e64190fff 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -1407,8 +1407,7 @@ i915_gem_execbuffer_parse(struct intel_engine_cs *engine, struct drm_i915_gem_object *batch_obj, struct eb_vmas *eb, u32 batch_start_offset, - u32 batch_len, - bool is_master) + u32 batch_len) { struct drm_i915_gem_object *shadow_batch_obj; struct i915_vma *vma; @@ -1423,8 +1422,7 @@ i915_gem_execbuffer_parse(struct intel_engine_cs *engine, batch_obj, shadow_batch_obj, batch_start_offset, - batch_len, - is_master); + batch_len); if (ret) { if (ret == -EACCES) /* unhandled chained batch */ vma = NULL; @@ -1725,8 +1723,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, params->batch->obj, eb, args->batch_start_offset, - args->batch_len, - drm_is_current_master(file)); + args->batch_len); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto err; From 943ccd0cc6c6febe23018776e65a3a56aea9968c Mon Sep 17 00:00:00 2001 From: Jon Bloomfield Date: Wed, 1 Aug 2018 09:33:59 -0700 Subject: [PATCH 83/93] drm/i915: Add support for mandatory cmdparsing commit 311a50e76a33d1e029563c24b2ff6db0c02b5afe upstream. The existing cmdparser for gen7 can be bypassed by specifying batch_len=0 in the execbuf call. This is safe because bypassing simply reduces the cmd-set available. In a later patch we will introduce cmdparsing for gen9, as a security measure, which must be strictly enforced since without it we are vulnerable to DoS attacks. Introduce the concept of 'required' cmd parsing that cannot be bypassed by submitting zero-length bb's. v2: rebase (Mika) v2: rebase (Mika) v3: fix conflict on engine flags (Mika) Signed-off-by: Jon Bloomfield Cc: Tony Luck Cc: Dave Airlie Cc: Takashi Iwai Cc: Tyler Hicks Signed-off-by: Mika Kuoppala Reviewed-by: Chris Wilson Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 6 +++--- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 ++- drivers/gpu/drm/i915/intel_ringbuffer.h | 14 +++++++++++--- 3 files changed, 16 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 462d0f700a8c..da91d3650dea 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -916,7 +916,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) return; } - engine->flags |= I915_ENGINE_NEEDS_CMD_PARSER; + engine->flags |= I915_ENGINE_USING_CMD_PARSER; } /** @@ -928,7 +928,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) */ void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine) { - if (!intel_engine_needs_cmd_parser(engine)) + if (!intel_engine_using_cmd_parser(engine)) return; fini_hash_table(engine); @@ -1316,7 +1316,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv) /* If the command parser is not enabled, report 0 - unsupported */ for_each_engine(engine, dev_priv) { - if (intel_engine_needs_cmd_parser(engine)) { + if (intel_engine_using_cmd_parser(engine)) { active = true; break; } diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 1f5e64190fff..069f26a3f3ba 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -1716,7 +1716,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, } params->args_batch_start_offset = args->batch_start_offset; - if (intel_engine_needs_cmd_parser(engine) && args->batch_len) { + if (intel_engine_requires_cmd_parser(engine) || + (intel_engine_using_cmd_parser(engine) && args->batch_len)) { struct i915_vma *vma; vma = i915_gem_execbuffer_parse(engine, &shadow_exec_entry, diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index e24d1324f094..ce14cd8495e8 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -341,7 +341,8 @@ struct intel_engine_cs { struct intel_engine_hangcheck hangcheck; -#define I915_ENGINE_NEEDS_CMD_PARSER BIT(0) +#define I915_ENGINE_USING_CMD_PARSER BIT(0) +#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(3) unsigned int flags; /* @@ -375,9 +376,16 @@ intel_engine_initialized(const struct intel_engine_cs *engine) return engine->i915 != NULL; } -static inline bool intel_engine_needs_cmd_parser(struct intel_engine_cs *engine) +static inline bool +intel_engine_using_cmd_parser(const struct intel_engine_cs *engine) { - return engine->flags & I915_ENGINE_NEEDS_CMD_PARSER; + return engine->flags & I915_ENGINE_USING_CMD_PARSER; +} + +static inline bool +intel_engine_requires_cmd_parser(const struct intel_engine_cs *engine) +{ + return engine->flags & I915_ENGINE_REQUIRES_CMD_PARSER; } static inline unsigned int From 9f5fb6f2e59e65d51e8b77a4f958db4c8c1a51ac Mon Sep 17 00:00:00 2001 From: Jon Bloomfield Date: Tue, 22 May 2018 13:59:06 -0700 Subject: [PATCH 84/93] drm/i915: Support ro ppgtt mapped cmdparser shadow buffers commit 4f7af1948abcb18b4772fe1bcd84d7d27d96258c upstream. For Gen7, the original cmdparser motive was to permit limited use of register read/write instructions in unprivileged BB's. This worked by copying the user supplied bb to a kmd owned bb, and running it in secure mode, from the ggtt, only if the scanner finds no unsafe commands or registers. For Gen8+ we can't use this same technique because running bb's from the ggtt also disables access to ppgtt space. But we also do not actually require 'secure' execution since we are only trying to reduce the available command/register set. Instead we will copy the user buffer to a kmd owned read-only bb in ppgtt, and run in the usual non-secure mode. Note that ro pages are only supported by ppgtt (not ggtt), but luckily that's exactly what we need. Add the required paths to map the shadow buffer to ppgtt ro for Gen8+ v2: IS_GEN7/IS_GEN (Mika) v3: rebase v4: rebase v5: rebase Signed-off-by: Jon Bloomfield Cc: Tony Luck Cc: Dave Airlie Cc: Takashi Iwai Cc: Tyler Hicks Signed-off-by: Mika Kuoppala Reviewed-by: Chris Wilson Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_drv.h | 14 ++++++ drivers/gpu/drm/i915/i915_gem.c | 15 ++++++- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 50 ++++++++++++++++------ 3 files changed, 65 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 73b88da64127..88f4d270d656 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2645,6 +2645,12 @@ static inline struct scatterlist *__sg_next(struct scatterlist *sg) #define IS_GEN8(dev) (!!(INTEL_INFO(dev)->gen_mask & BIT(7))) #define IS_GEN9(dev) (!!(INTEL_INFO(dev)->gen_mask & BIT(8))) +/* + * The Gen7 cmdparser copies the scanned buffer to the ggtt for execution + * All later gens can run the final buffer from the ppgtt + */ +#define CMDPARSER_USES_GGTT(dev_priv) IS_GEN7(dev_priv) + #define ENGINE_MASK(id) BIT(id) #define RENDER_RING ENGINE_MASK(RCS) #define BSD_RING ENGINE_MASK(VCS) @@ -3016,6 +3022,14 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, u64 alignment, u64 flags); +struct i915_vma * __must_check +i915_gem_object_pin(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, + const struct i915_ggtt_view *view, + u64 size, + u64 alignment, + u64 flags); + int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level, u32 flags); void __i915_vma_set_map_and_fenceable(struct i915_vma *vma); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index f1c4e95baa28..dff3eabd674f 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -3826,6 +3826,19 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, u64 flags) { struct i915_address_space *vm = &to_i915(obj->base.dev)->ggtt.base; + + return i915_gem_object_pin(obj, vm, view, size, alignment, + flags | PIN_GLOBAL); +} + +struct i915_vma * +i915_gem_object_pin(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, + const struct i915_ggtt_view *view, + u64 size, + u64 alignment, + u64 flags) +{ struct i915_vma *vma; int ret; @@ -3850,7 +3863,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, return ERR_PTR(ret); } - ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL); + ret = i915_vma_pin(vma, size, alignment, flags); if (ret) return ERR_PTR(ret); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 069f26a3f3ba..dbfab0b66c63 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -1401,11 +1401,36 @@ i915_reset_gen7_sol_offsets(struct drm_i915_gem_request *req) return 0; } +static struct i915_vma* +shadow_batch_pin(struct drm_i915_gem_object *obj, struct i915_address_space *vm) +{ + struct drm_i915_private *dev_priv = to_i915(obj->base.dev); + u64 flags; + + /* + * PPGTT backed shadow buffers must be mapped RO, to prevent + * post-scan tampering + */ + if (CMDPARSER_USES_GGTT(dev_priv)) { + flags = PIN_GLOBAL; + vm = &dev_priv->ggtt.base; + } else if (vm->has_read_only) { + flags = PIN_USER; + i915_gem_object_set_readonly(obj); + } else { + DRM_DEBUG("Cannot prevent post-scan tampering without RO capable vm\n"); + return ERR_PTR(-EINVAL); + } + + return i915_gem_object_pin(obj, vm, NULL, 0, 0, flags); +} + static struct i915_vma * i915_gem_execbuffer_parse(struct intel_engine_cs *engine, struct drm_i915_gem_exec_object2 *shadow_exec_entry, struct drm_i915_gem_object *batch_obj, struct eb_vmas *eb, + struct i915_address_space *vm, u32 batch_start_offset, u32 batch_len) { @@ -1424,14 +1449,21 @@ i915_gem_execbuffer_parse(struct intel_engine_cs *engine, batch_start_offset, batch_len); if (ret) { - if (ret == -EACCES) /* unhandled chained batch */ + /* + * Unsafe GGTT-backed buffers can still be submitted safely + * as non-secure. + * For PPGTT backing however, we have no choice but to forcibly + * reject unsafe buffers + */ + if (CMDPARSER_USES_GGTT(eb->i915) && (ret == -EACCES)) + /* Execute original buffer non-secure */ vma = NULL; else vma = ERR_PTR(ret); goto out; } - vma = i915_gem_object_ggtt_pin(shadow_batch_obj, NULL, 0, 0, 0); + vma = shadow_batch_pin(shadow_batch_obj, vm); if (IS_ERR(vma)) goto out; @@ -1722,7 +1754,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, vma = i915_gem_execbuffer_parse(engine, &shadow_exec_entry, params->batch->obj, - eb, + eb, vm, args->batch_start_offset, args->batch_len); if (IS_ERR(vma)) { @@ -1731,16 +1763,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, } if (vma) { - /* - * Batch parsed and accepted: - * - * Set the DISPATCH_SECURE bit to remove the NON_SECURE - * bit from MI_BATCH_BUFFER_START commands issued in - * the dispatch_execbuffer implementations. We - * specifically don't want that set on batches the - * command parser has accepted. - */ - dispatch_flags |= I915_DISPATCH_SECURE; + if (CMDPARSER_USES_GGTT(dev_priv)) + dispatch_flags |= I915_DISPATCH_SECURE; params->args_batch_start_offset = 0; params->batch = vma; } From 05e5cf18ae4189c0a13dc1e704c78bed79a1b0f9 Mon Sep 17 00:00:00 2001 From: Jon Bloomfield Date: Wed, 1 Aug 2018 09:45:50 -0700 Subject: [PATCH 85/93] drm/i915: Allow parsing of unsized batches commit 435e8fc059dbe0eec823a75c22da2972390ba9e0 upstream. In "drm/i915: Add support for mandatory cmdparsing" we introduced the concept of mandatory parsing. This allows the cmdparser to be invoked even when user passes batch_len=0 to the execbuf ioctl's. However, the cmdparser needs to know the extents of the buffer being scanned. Refactor the code to ensure the cmdparser uses the actual object size, instead of the incoming length, if user passes 0. Signed-off-by: Jon Bloomfield Cc: Tony Luck Cc: Dave Airlie Cc: Takashi Iwai Cc: Tyler Hicks Reviewed-by: Chris Wilson Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index dbfab0b66c63..2240aba5f7ab 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -55,6 +55,7 @@ struct i915_execbuffer_params { struct i915_vma *batch; u32 dispatch_flags; u32 args_batch_start_offset; + u64 args_batch_len; struct intel_engine_cs *engine; struct i915_gem_context *ctx; struct drm_i915_gem_request *request; @@ -1506,13 +1507,10 @@ execbuf_submit(struct i915_execbuffer_params *params, return ret; } - exec_len = args->batch_len; + exec_len = params->args_batch_len; exec_start = params->batch->node.start + params->args_batch_start_offset; - if (exec_len == 0) - exec_len = params->batch->size - params->args_batch_start_offset; - ret = params->engine->emit_bb_start(params->request, exec_start, exec_len, params->dispatch_flags); @@ -1748,6 +1746,10 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, } params->args_batch_start_offset = args->batch_start_offset; + params->args_batch_len = args->batch_len; + if (args->batch_len == 0) + params->args_batch_len = params->batch->size - params->args_batch_start_offset; + if (intel_engine_requires_cmd_parser(engine) || (intel_engine_using_cmd_parser(engine) && args->batch_len)) { struct i915_vma *vma; @@ -1755,8 +1757,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, vma = i915_gem_execbuffer_parse(engine, &shadow_exec_entry, params->batch->obj, eb, vm, - args->batch_start_offset, - args->batch_len); + params->args_batch_start_offset, + params->args_batch_len); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto err; From a6ba2df10d64d6d113ac3e033e3c4b80a3febd66 Mon Sep 17 00:00:00 2001 From: Jon Bloomfield Date: Mon, 23 Apr 2018 11:12:15 -0700 Subject: [PATCH 86/93] drm/i915: Add gen9 BCS cmdparsing commit 0f2f39758341df70202ae1c42d5a1e4ee392b6d3 upstream. For gen9 we enable cmdparsing on the BCS ring, specifically to catch inadvertent accesses to sensitive registers Unlike gen7/hsw, we use the parser only to block certain registers. We can rely on h/w to block restricted commands, so the command tables only provide enough info to allow the parser to delineate each command, and identify commands that access registers. Note: This patch deliberately ignores checkpatch issues in favour of matching the style of the surrounding code. We'll correct the entire file in one go in a later patch. v3: rebase (Mika) v4: Add RING_TIMESTAMP registers to whitelist (Jon) Signed-off-by: Jon Bloomfield Cc: Tony Luck Cc: Dave Airlie Cc: Takashi Iwai Cc: Tyler Hicks Signed-off-by: Mika Kuoppala Reviewed-by: Chris Wilson Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 116 ++++++++++++++++++++++--- drivers/gpu/drm/i915/i915_gem_gtt.c | 3 +- drivers/gpu/drm/i915/i915_reg.h | 4 + 3 files changed, 112 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index da91d3650dea..c662cd534432 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -442,6 +442,47 @@ static const struct drm_i915_cmd_descriptor hsw_blt_cmds[] = { CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, R ), }; +/* + * For Gen9 we can still rely on the h/w to enforce cmd security, and only + * need to re-enforce the register access checks. We therefore only need to + * teach the cmdparser how to find the end of each command, and identify + * register accesses. The table doesn't need to reject any commands, and so + * the only commands listed here are: + * 1) Those that touch registers + * 2) Those that do not have the default 8-bit length + * + * Note that the default MI length mask chosen for this table is 0xFF, not + * the 0x3F used on older devices. This is because the vast majority of MI + * cmds on Gen9 use a standard 8-bit Length field. + * All the Gen9 blitter instructions are standard 0xFF length mask, and + * none allow access to non-general registers, so in fact no BLT cmds are + * included in the table at all. + * + */ +static const struct drm_i915_cmd_descriptor gen9_blt_cmds[] = { + CMD( MI_NOOP, SMI, F, 1, S ), + CMD( MI_USER_INTERRUPT, SMI, F, 1, S ), + CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, S ), + CMD( MI_FLUSH, SMI, F, 1, S ), + CMD( MI_ARB_CHECK, SMI, F, 1, S ), + CMD( MI_REPORT_HEAD, SMI, F, 1, S ), + CMD( MI_ARB_ON_OFF, SMI, F, 1, S ), + CMD( MI_SUSPEND_FLUSH, SMI, F, 1, S ), + CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, S ), + CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, S ), + CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3FF, S ), + CMD( MI_LOAD_REGISTER_IMM(1), SMI, !F, 0xFF, W, + .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 } ), + CMD( MI_UPDATE_GTT, SMI, !F, 0x3FF, S ), + CMD( MI_STORE_REGISTER_MEM_GEN8, SMI, F, 4, W, + .reg = { .offset = 1, .mask = 0x007FFFFC } ), + CMD( MI_FLUSH_DW, SMI, !F, 0x3F, S ), + CMD( MI_LOAD_REGISTER_MEM_GEN8, SMI, F, 4, W, + .reg = { .offset = 1, .mask = 0x007FFFFC } ), + CMD( MI_LOAD_REGISTER_REG, SMI, !F, 0xFF, W, + .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 } ), +}; + static const struct drm_i915_cmd_descriptor noop_desc = CMD(MI_NOOP, SMI, F, 1, S); @@ -488,6 +529,11 @@ static const struct drm_i915_cmd_table hsw_blt_ring_cmd_table[] = { { hsw_blt_cmds, ARRAY_SIZE(hsw_blt_cmds) }, }; +static const struct drm_i915_cmd_table gen9_blt_cmd_table[] = { + { gen9_blt_cmds, ARRAY_SIZE(gen9_blt_cmds) }, +}; + + /* * Register whitelists, sorted by increasing register offset. */ @@ -603,6 +649,29 @@ static const struct drm_i915_reg_descriptor gen7_blt_regs[] = { REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE), }; +static const struct drm_i915_reg_descriptor gen9_blt_regs[] = { + REG64_IDX(RING_TIMESTAMP, RENDER_RING_BASE), + REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE), + REG32(BCS_SWCTRL), + REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE), + REG64_IDX(BCS_GPR, 0), + REG64_IDX(BCS_GPR, 1), + REG64_IDX(BCS_GPR, 2), + REG64_IDX(BCS_GPR, 3), + REG64_IDX(BCS_GPR, 4), + REG64_IDX(BCS_GPR, 5), + REG64_IDX(BCS_GPR, 6), + REG64_IDX(BCS_GPR, 7), + REG64_IDX(BCS_GPR, 8), + REG64_IDX(BCS_GPR, 9), + REG64_IDX(BCS_GPR, 10), + REG64_IDX(BCS_GPR, 11), + REG64_IDX(BCS_GPR, 12), + REG64_IDX(BCS_GPR, 13), + REG64_IDX(BCS_GPR, 14), + REG64_IDX(BCS_GPR, 15), +}; + #undef REG64 #undef REG32 @@ -628,6 +697,10 @@ static const struct drm_i915_reg_table hsw_blt_reg_tables[] = { { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) }, }; +static const struct drm_i915_reg_table gen9_blt_reg_tables[] = { + { gen9_blt_regs, ARRAY_SIZE(gen9_blt_regs) }, +}; + static u32 gen7_render_get_cmd_length_mask(u32 cmd_header) { u32 client = cmd_header >> INSTR_CLIENT_SHIFT; @@ -683,6 +756,17 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header) return 0; } +static u32 gen9_blt_get_cmd_length_mask(u32 cmd_header) +{ + u32 client = cmd_header >> INSTR_CLIENT_SHIFT; + + if (client == INSTR_MI_CLIENT || client == INSTR_BC_CLIENT) + return 0xFF; + + DRM_DEBUG_DRIVER("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header); + return 0; +} + static bool validate_cmds_sorted(const struct intel_engine_cs *engine, const struct drm_i915_cmd_table *cmd_tables, int cmd_table_count) @@ -840,7 +924,8 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) int cmd_table_count; int ret; - if (!IS_GEN7(engine->i915)) + if (!IS_GEN7(engine->i915) && !(IS_GEN9(engine->i915) && + engine->id == BCS)) return; switch (engine->id) { @@ -861,7 +946,6 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) engine->reg_tables = ivb_render_reg_tables; engine->reg_table_count = ARRAY_SIZE(ivb_render_reg_tables); } - engine->get_cmd_length_mask = gen7_render_get_cmd_length_mask; break; case VCS: @@ -870,7 +954,16 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask; break; case BCS: - if (IS_HASWELL(engine->i915)) { + engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask; + if (IS_GEN9(engine->i915)) { + cmd_tables = gen9_blt_cmd_table; + cmd_table_count = ARRAY_SIZE(gen9_blt_cmd_table); + engine->get_cmd_length_mask = + gen9_blt_get_cmd_length_mask; + + /* BCS Engine unsafe without parser */ + engine->flags |= I915_ENGINE_REQUIRES_CMD_PARSER; + } else if (IS_HASWELL(engine->i915)) { cmd_tables = hsw_blt_ring_cmd_table; cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmd_table); } else { @@ -878,15 +971,17 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) cmd_table_count = ARRAY_SIZE(gen7_blt_cmd_table); } - if (IS_HASWELL(engine->i915)) { + if (IS_GEN9(engine->i915)) { + engine->reg_tables = gen9_blt_reg_tables; + engine->reg_table_count = + ARRAY_SIZE(gen9_blt_reg_tables); + } else if (IS_HASWELL(engine->i915)) { engine->reg_tables = hsw_blt_reg_tables; engine->reg_table_count = ARRAY_SIZE(hsw_blt_reg_tables); } else { engine->reg_tables = ivb_blt_reg_tables; engine->reg_table_count = ARRAY_SIZE(ivb_blt_reg_tables); } - - engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask; break; case VECS: cmd_tables = hsw_vebox_cmd_table; @@ -1260,9 +1355,9 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, } /* - * If the batch buffer contains a chained batch, return an - * error that tells the caller to abort and dispatch the - * workload as a non-secure batch. + * We don't try to handle BATCH_BUFFER_START because it adds + * non-trivial complexity. Instead we abort the scan and return + * and error to indicate that the batch is unsafe. */ if (desc->cmd.value == MI_BATCH_BUFFER_START) { ret = -EACCES; @@ -1341,6 +1436,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv) * the parser enabled. * 9. Don't whitelist or handle oacontrol specially, as ownership * for oacontrol state is moving to i915-perf. + * 10. Support for Gen9 BCS Parsing */ - return 9; + return 10; } diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index bfe40d9e5ac9..16f56f14f4d0 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -140,7 +140,8 @@ int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv, if (enable_ppgtt == 0 && INTEL_GEN(dev_priv) < 9) return 0; - if (enable_ppgtt == 1) + /* Full PPGTT is required by the Gen9 cmdparser */ + if (enable_ppgtt == 1 && INTEL_GEN(dev_priv) != 9) return 1; if (enable_ppgtt == 2 && has_full_ppgtt) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index a94caae05cc3..31c92f86e43d 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -568,6 +568,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) */ #define BCS_SWCTRL _MMIO(0x22200) +/* There are 16 GPR registers */ +#define BCS_GPR(n) _MMIO(0x22600 + (n) * 8) +#define BCS_GPR_UDW(n) _MMIO(0x22600 + (n) * 8 + 4) + #define GPGPU_THREADS_DISPATCHED _MMIO(0x2290) #define GPGPU_THREADS_DISPATCHED_UDW _MMIO(0x2290 + 4) #define HS_INVOCATION_COUNT _MMIO(0x2300) From 81848cc9c57295e05c8ba81fa2b2b4b8a3962c3c Mon Sep 17 00:00:00 2001 From: Jon Bloomfield Date: Thu, 27 Sep 2018 10:23:17 -0700 Subject: [PATCH 87/93] drm/i915/cmdparser: Use explicit goto for error paths commit 0546a29cd884fb8184731c79ab008927ca8859d0 upstream. In the next patch we will be adding a second valid termination condition which will require a small amount of refactoring to share logic with the BB_END case. Refactor all error conditions to jump to a dedicated exit path, with 'break' reserved only for a successful parse. Signed-off-by: Jon Bloomfield Cc: Tony Luck Cc: Dave Airlie Cc: Takashi Iwai Cc: Tyler Hicks Signed-off-by: Mika Kuoppala Reviewed-by: Chris Wilson Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index c662cd534432..21451e8ca985 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1337,21 +1337,15 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, do { u32 length; - if (*cmd == MI_BATCH_BUFFER_END) { - if (needs_clflush_after) { - void *ptr = ptr_mask_bits(shadow_batch_obj->mapping); - drm_clflush_virt_range(ptr, - (void *)(cmd + 1) - ptr); - } + if (*cmd == MI_BATCH_BUFFER_END) break; - } desc = find_cmd(engine, *cmd, desc, &default_desc); if (!desc) { DRM_DEBUG_DRIVER("CMD: Unrecognized command: 0x%08X\n", *cmd); ret = -EINVAL; - break; + goto err; } /* @@ -1361,7 +1355,7 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, */ if (desc->cmd.value == MI_BATCH_BUFFER_START) { ret = -EACCES; - break; + goto err; } if (desc->flags & CMD_DESC_FIXED) @@ -1375,22 +1369,29 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, length, batch_end - cmd); ret = -EINVAL; - break; + goto err; } if (!check_cmd(engine, desc, cmd, length)) { ret = -EACCES; - break; + goto err; } cmd += length; if (cmd >= batch_end) { DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n"); ret = -EINVAL; - break; + goto err; } } while (1); + if (needs_clflush_after) { + void *ptr = ptr_mask_bits(shadow_batch_obj->mapping); + drm_clflush_virt_range(ptr, + (void *)(cmd + 1) - ptr); + } + +err: i915_gem_object_unpin_map(shadow_batch_obj); return ret; } From a7a1a3e368b5f42e75e14da66c6c9f9825d3217c Mon Sep 17 00:00:00 2001 From: Jon Bloomfield Date: Thu, 20 Sep 2018 09:58:36 -0700 Subject: [PATCH 88/93] drm/i915/cmdparser: Add support for backward jumps commit f8c08d8faee5567803c8c533865296ca30286bbf upstream. To keep things manageable, the pre-gen9 cmdparser does not attempt to track any form of nested BB_START's. This did not prevent usermode from using nested starts, or even chained batches because the cmdparser is not strictly enforced pre gen9. Instead, the existence of a nested BB_START would cause the batch to be emitted in insecure mode, and any privileged capabilities would not be available. For Gen9, the cmdparser becomes mandatory (for BCS at least), and so not providing any form of nested BB_START support becomes overly restrictive. Any such batch will simply not run. We make heavy use of backward jumps in igt, and it is much easier to add support for this restricted subset of nested jumps, than to rewrite the whole of our test suite to avoid them. Add the required logic to support limited backward jumps, to instructions that have already been validated by the parser. Note that it's not sufficient to simply approve any BB_START that jumps backwards in the buffer because this would allow an attacker to embed a rogue instruction sequence within the operand words of a harmless instruction (say LRI) and jump to that. We introduce a bit array to track every instr offset successfully validated, and test the target of BB_START against this. If the target offset hits, it is re-written to the same offset in the shadow buffer and the BB_START cmd is allowed. Note: This patch deliberately ignores checkpatch issues in the cmdtables, in order to match the style of the surrounding code. We'll correct the entire file in one go in a later patch. v2: set dispatch secure late (Mika) v3: rebase (Mika) v4: Clear whitelist on each parse Minor review updates (Chris) v5: Correct backward jump batching v6: fix compilation error due to struct eb shuffle (Mika) Cc: Tony Luck Cc: Dave Airlie Cc: Takashi Iwai Cc: Tyler Hicks Signed-off-by: Jon Bloomfield Signed-off-by: Mika Kuoppala Reviewed-by: Chris Wilson Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 151 +++++++++++++++++++-- drivers/gpu/drm/i915/i915_drv.h | 16 ++- drivers/gpu/drm/i915/i915_gem_context.c | 5 + drivers/gpu/drm/i915/i915_gem_execbuffer.c | 43 +++--- 4 files changed, 181 insertions(+), 34 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 21451e8ca985..8885c03f16c1 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -481,6 +481,19 @@ static const struct drm_i915_cmd_descriptor gen9_blt_cmds[] = { .reg = { .offset = 1, .mask = 0x007FFFFC } ), CMD( MI_LOAD_REGISTER_REG, SMI, !F, 0xFF, W, .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 } ), + + /* + * We allow BB_START but apply further checks. We just sanitize the + * basic fields here. + */ +#define MI_BB_START_OPERAND_MASK GENMASK(SMI-1, 0) +#define MI_BB_START_OPERAND_EXPECT (MI_BATCH_PPGTT_HSW | 1) + CMD( MI_BATCH_BUFFER_START_GEN8, SMI, !F, 0xFF, B, + .bits = {{ + .offset = 0, + .mask = MI_BB_START_OPERAND_MASK, + .expected = MI_BB_START_OPERAND_EXPECT, + }}, ), }; static const struct drm_i915_cmd_descriptor noop_desc = @@ -1292,15 +1305,113 @@ static bool check_cmd(const struct intel_engine_cs *engine, return true; } +static int check_bbstart(const struct i915_gem_context *ctx, + u32 *cmd, u32 offset, u32 length, + u32 batch_len, + u64 batch_start, + u64 shadow_batch_start) +{ + u64 jump_offset, jump_target; + u32 target_cmd_offset, target_cmd_index; + + /* For igt compatibility on older platforms */ + if (CMDPARSER_USES_GGTT(ctx->i915)) { + DRM_DEBUG("CMD: Rejecting BB_START for ggtt based submission\n"); + return -EACCES; + } + + if (length != 3) { + DRM_DEBUG("CMD: Recursive BB_START with bad length(%u)\n", + length); + return -EINVAL; + } + + jump_target = *(u64*)(cmd+1); + jump_offset = jump_target - batch_start; + + /* + * Any underflow of jump_target is guaranteed to be outside the range + * of a u32, so >= test catches both too large and too small + */ + if (jump_offset >= batch_len) { + DRM_DEBUG("CMD: BB_START to 0x%llx jumps out of BB\n", + jump_target); + return -EINVAL; + } + + /* + * This cannot overflow a u32 because we already checked jump_offset + * is within the BB, and the batch_len is a u32 + */ + target_cmd_offset = lower_32_bits(jump_offset); + target_cmd_index = target_cmd_offset / sizeof(u32); + + *(u64*)(cmd + 1) = shadow_batch_start + target_cmd_offset; + + if (target_cmd_index == offset) + return 0; + + if (ctx->jump_whitelist_cmds <= target_cmd_index) { + DRM_DEBUG("CMD: Rejecting BB_START - truncated whitelist array\n"); + return -EINVAL; + } else if (!test_bit(target_cmd_index, ctx->jump_whitelist)) { + DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n", + jump_target); + return -EINVAL; + } + + return 0; +} + +static void init_whitelist(struct i915_gem_context *ctx, u32 batch_len) +{ + const u32 batch_cmds = DIV_ROUND_UP(batch_len, sizeof(u32)); + const u32 exact_size = BITS_TO_LONGS(batch_cmds); + u32 next_size = BITS_TO_LONGS(roundup_pow_of_two(batch_cmds)); + unsigned long *next_whitelist; + + if (CMDPARSER_USES_GGTT(ctx->i915)) + return; + + if (batch_cmds <= ctx->jump_whitelist_cmds) { + memset(ctx->jump_whitelist, 0, exact_size * sizeof(u32)); + return; + } + +again: + next_whitelist = kcalloc(next_size, sizeof(long), GFP_KERNEL); + if (next_whitelist) { + kfree(ctx->jump_whitelist); + ctx->jump_whitelist = next_whitelist; + ctx->jump_whitelist_cmds = + next_size * BITS_PER_BYTE * sizeof(long); + return; + } + + if (next_size > exact_size) { + next_size = exact_size; + goto again; + } + + DRM_DEBUG("CMD: Failed to extend whitelist. BB_START may be disallowed\n"); + memset(ctx->jump_whitelist, 0, + BITS_TO_LONGS(ctx->jump_whitelist_cmds) * sizeof(u32)); + + return; +} + #define LENGTH_BIAS 2 /** * i915_parse_cmds() - parse a submitted batch buffer for privilege violations + * @ctx: the context in which the batch is to execute * @engine: the engine on which the batch is to execute * @batch_obj: the batch buffer in question - * @shadow_batch_obj: copy of the batch buffer in question + * @batch_start: Canonical base address of batch * @batch_start_offset: byte offset in the batch at which execution starts * @batch_len: length of the commands in batch_obj + * @shadow_batch_obj: copy of the batch buffer in question + * @shadow_batch_start: Canonical base address of shadow_batch_obj * * Parses the specified batch buffer looking for privilege violations as * described in the overview. @@ -1308,13 +1419,17 @@ static bool check_cmd(const struct intel_engine_cs *engine, * Return: non-zero if the parser finds violations or otherwise fails; -EACCES * if the batch appears legal but should use hardware parsing */ -int intel_engine_cmd_parser(struct intel_engine_cs *engine, + +int intel_engine_cmd_parser(struct i915_gem_context *ctx, + struct intel_engine_cs *engine, struct drm_i915_gem_object *batch_obj, - struct drm_i915_gem_object *shadow_batch_obj, + u64 batch_start, u32 batch_start_offset, - u32 batch_len) + u32 batch_len, + struct drm_i915_gem_object *shadow_batch_obj, + u64 shadow_batch_start) { - u32 *cmd, *batch_end; + u32 *cmd, *batch_end, offset = 0; struct drm_i915_cmd_descriptor default_desc = noop_desc; const struct drm_i915_cmd_descriptor *desc = &default_desc; bool needs_clflush_after = false; @@ -1328,6 +1443,8 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, return PTR_ERR(cmd); } + init_whitelist(ctx, batch_len); + /* * We use the batch length as size because the shadow object is as * large or larger and copy_batch() will write MI_NOPs to the extra @@ -1348,16 +1465,6 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, goto err; } - /* - * We don't try to handle BATCH_BUFFER_START because it adds - * non-trivial complexity. Instead we abort the scan and return - * and error to indicate that the batch is unsafe. - */ - if (desc->cmd.value == MI_BATCH_BUFFER_START) { - ret = -EACCES; - goto err; - } - if (desc->flags & CMD_DESC_FIXED) length = desc->length.fixed; else @@ -1377,7 +1484,21 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, goto err; } + if (desc->cmd.value == MI_BATCH_BUFFER_START) { + ret = check_bbstart(ctx, cmd, offset, length, + batch_len, batch_start, + shadow_batch_start); + + if (ret) + goto err; + break; + } + + if (ctx->jump_whitelist_cmds > offset) + set_bit(offset, ctx->jump_whitelist); + cmd += length; + offset += length; if (cmd >= batch_end) { DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n"); ret = -EINVAL; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 88f4d270d656..6193369fdbc1 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -943,6 +943,13 @@ struct i915_gem_context { struct list_head link; u8 remap_slice; + + /** jump_whitelist: Bit array for tracking cmds during cmdparsing */ + unsigned long *jump_whitelist; + + /** jump_whitelist_cmds: No of cmd slots available */ + u32 jump_whitelist_cmds; + bool closed:1; }; @@ -3483,11 +3490,14 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type); int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv); void intel_engine_init_cmd_parser(struct intel_engine_cs *engine); void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine); -int intel_engine_cmd_parser(struct intel_engine_cs *engine, +int intel_engine_cmd_parser(struct i915_gem_context *cxt, + struct intel_engine_cs *engine, struct drm_i915_gem_object *batch_obj, - struct drm_i915_gem_object *shadow_batch_obj, + u64 user_batch_start, u32 batch_start_offset, - u32 batch_len); + u32 batch_len, + struct drm_i915_gem_object *shadow_batch_obj, + u64 shadow_batch_start); /* i915_suspend.c */ extern int i915_save_state(struct drm_device *dev); diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index df10f4e95736..5d55cd159e89 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -158,6 +158,8 @@ void i915_gem_context_free(struct kref *ctx_ref) i915_vma_put(ce->state); } + kfree(ctx->jump_whitelist); + put_pid(ctx->pid); list_del(&ctx->link); @@ -327,6 +329,9 @@ __create_hw_context(struct drm_device *dev, GEN8_CTX_ADDRESSING_MODE_SHIFT; ATOMIC_INIT_NOTIFIER_HEAD(&ctx->status_notifier); + ctx->jump_whitelist = NULL; + ctx->jump_whitelist_cmds = 0; + return ctx; err_out: diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 2240aba5f7ab..4548d89abcdc 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -1429,27 +1429,44 @@ shadow_batch_pin(struct drm_i915_gem_object *obj, struct i915_address_space *vm) static struct i915_vma * i915_gem_execbuffer_parse(struct intel_engine_cs *engine, struct drm_i915_gem_exec_object2 *shadow_exec_entry, - struct drm_i915_gem_object *batch_obj, + struct i915_execbuffer_params *params, struct eb_vmas *eb, - struct i915_address_space *vm, - u32 batch_start_offset, - u32 batch_len) + struct i915_address_space *vm) { + struct drm_i915_gem_object *batch_obj = params->batch->obj; struct drm_i915_gem_object *shadow_batch_obj; struct i915_vma *vma; + u64 batch_start; + u32 batch_start_offset = params->args_batch_start_offset; + u32 batch_len = params->args_batch_len; + u64 shadow_batch_start; int ret; + shadow_batch_obj = i915_gem_batch_pool_get(&engine->batch_pool, PAGE_ALIGN(batch_len)); if (IS_ERR(shadow_batch_obj)) return ERR_CAST(shadow_batch_obj); - ret = intel_engine_cmd_parser(engine, + vma = shadow_batch_pin(shadow_batch_obj, vm); + if (IS_ERR(vma)) + goto out; + + batch_start = gen8_canonical_addr(params->batch->node.start) + + batch_start_offset; + shadow_batch_start = gen8_canonical_addr(vma->node.start); + + ret = intel_engine_cmd_parser(params->ctx, + engine, batch_obj, - shadow_batch_obj, + batch_start, batch_start_offset, - batch_len); + batch_len, + shadow_batch_obj, + shadow_batch_start); if (ret) { + i915_vma_unpin(vma); + /* * Unsafe GGTT-backed buffers can still be submitted safely * as non-secure. @@ -1461,13 +1478,10 @@ i915_gem_execbuffer_parse(struct intel_engine_cs *engine, vma = NULL; else vma = ERR_PTR(ret); + goto out; } - vma = shadow_batch_pin(shadow_batch_obj, vm); - if (IS_ERR(vma)) - goto out; - memset(shadow_exec_entry, 0, sizeof(*shadow_exec_entry)); vma->exec_entry = shadow_exec_entry; @@ -1745,6 +1759,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, goto err; } + params->ctx = ctx; params->args_batch_start_offset = args->batch_start_offset; params->args_batch_len = args->batch_len; if (args->batch_len == 0) @@ -1755,10 +1770,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, struct i915_vma *vma; vma = i915_gem_execbuffer_parse(engine, &shadow_exec_entry, - params->batch->obj, - eb, vm, - params->args_batch_start_offset, - params->args_batch_len); + params, eb, vm); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto err; @@ -1829,7 +1841,6 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, params->file = file; params->engine = engine; params->dispatch_flags = dispatch_flags; - params->ctx = ctx; ret = execbuf_submit(params, args, &eb->vmas); err_request: From bd671d06b6232107943ec93cf587aa00ece495af Mon Sep 17 00:00:00 2001 From: Jon Bloomfield Date: Thu, 20 Sep 2018 09:45:10 -0700 Subject: [PATCH 89/93] drm/i915/cmdparser: Ignore Length operands during command matching commit 926abff21a8f29ef159a3ac893b05c6e50e043c3 upstream. Some of the gen instruction macros (e.g. MI_DISPLAY_FLIP) have the length directly encoded in them. Since these are used directly in the tables, the Length becomes part of the comparison used for matching during parsing. Thus, if the cmd being parsed has a different length to that in the table, it is not matched and the cmd is accepted via the default variable length path. Fix by masking out everything except the Opcode in the cmd tables Cc: Tony Luck Cc: Dave Airlie Cc: Takashi Iwai Cc: Tyler Hicks Signed-off-by: Jon Bloomfield Reviewed-by: Chris Wilson Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 8885c03f16c1..7f1e2c5e113f 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -187,7 +187,7 @@ struct drm_i915_cmd_table { #define CMD(op, opm, f, lm, fl, ...) \ { \ .flags = (fl) | ((f) ? CMD_DESC_FIXED : 0), \ - .cmd = { (op), ~0u << (opm) }, \ + .cmd = { (op & ~0u << (opm)), ~0u << (opm) }, \ .length = { (lm) }, \ __VA_ARGS__ \ } From ebd6ded190ed0920c16eb63f274b50ca050e46fb Mon Sep 17 00:00:00 2001 From: Uma Shankar Date: Tue, 7 Aug 2018 21:15:35 +0530 Subject: [PATCH 90/93] drm/i915: Lower RM timeout to avoid DSI hard hangs commit 1d85a299c4db57c55e0229615132c964d17aa765 upstream. In BXT/APL, device 2 MMIO reads from MIPI controller requires its PLL to be turned ON. When MIPI PLL is turned off (MIPI Display is not active or connected), and someone (host or GT engine) tries to read MIPI registers, it causes hard hang. This is a hardware restriction or limitation. Driver by itself doesn't read MIPI registers when MIPI display is off. But any userspace application can submit unprivileged batch buffer for execution. In that batch buffer there can be mmio reads. And these reads are allowed even for unprivileged applications. If these register reads are for MIPI DSI controller and MIPI display is not active during that time, then the MMIO read operation causes system hard hang and only way to recover is hard reboot. A genuine process/application won't submit batch buffer like this and doesn't cause any issue. But on a compromised system, a malign userspace process/app can generate such batch buffer and can trigger system hard hang (denial of service attack). The fix is to lower the internal MMIO timeout value to an optimum value of 950us as recommended by hardware team. If the timeout is beyond 1ms (which will hit for any value we choose if MMIO READ on a DSI specific register is performed without PLL ON), it causes the system hang. But if the timeout value is lower than it will be below the threshold (even if timeout happens) and system will not get into a hung state. This will avoid a system hang without losing any programming or GT interrupts, taking the worst case of lowest CDCLK frequency and early DC5 abort into account. Signed-off-by: Uma Shankar Reviewed-by: Jon Bloomfield Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_reg.h | 4 ++++ drivers/gpu/drm/i915/intel_pm.c | 7 +++++++ 2 files changed, 11 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 31c92f86e43d..cd504bc31e74 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -5939,6 +5939,10 @@ enum { #define SKL_CSR_DC5_DC6_COUNT _MMIO(0x8002C) #define BXT_CSR_DC3_DC5_COUNT _MMIO(0x80038) +/* Display Internal Timeout Register */ +#define RM_TIMEOUT _MMIO(0x42060) +#define MMIO_TIMEOUT_US(us) ((us) << 0) + /* interrupts */ #define DE_MASTER_IRQ_CONTROL (1 << 31) #define DE_SPRITEB_FLIP_DONE (1 << 29) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 05427d292457..39147d40dcc0 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -105,6 +105,13 @@ static void bxt_init_clock_gating(struct drm_device *dev) if (IS_BXT_REVID(dev_priv, BXT_REVID_B0, REVID_FOREVER)) I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) | PWM1_GATING_DIS | PWM2_GATING_DIS); + /* + * Lower the display internal timeout. + * This is needed to avoid any hard hangs when DSI port PLL + * is off and a MMIO access is attempted by any privilege + * application, using batch buffers or any other means. + */ + I915_WRITE(RM_TIMEOUT, MMIO_TIMEOUT_US(950)); } static void i915_pineview_get_mem_freq(struct drm_device *dev) From 00194ecfb32cab5bc20ce1308c681c47094015bd Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Mon, 9 Jul 2018 18:24:27 +0300 Subject: [PATCH 91/93] drm/i915/gen8+: Add RC6 CTX corruption WA commit 7e34f4e4aad3fd34c02b294a3cf2321adf5b4438 upstream. In some circumstances the RC6 context can get corrupted. We can detect this and take the required action, that is disable RC6 and runtime PM. The HW recovers from the corrupted state after a system suspend/resume cycle, so detect the recovery and re-enable RC6 and runtime PM. v2: rebase (Mika) v3: - Move intel_suspend_gt_powersave() to the end of the GEM suspend sequence. - Add commit message. v4: - Rebased on intel_uncore_forcewake_put(i915->uncore, ...) API change. v5: - Rebased on latest upstream gt_pm refactoring. Signed-off-by: Imre Deak Signed-off-by: Mika Kuoppala Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_drv.c | 3 + drivers/gpu/drm/i915/i915_drv.h | 7 +- drivers/gpu/drm/i915/i915_gem.c | 6 + drivers/gpu/drm/i915/i915_gem_request.c | 4 + drivers/gpu/drm/i915/i915_reg.h | 2 + drivers/gpu/drm/i915/intel_drv.h | 3 + drivers/gpu/drm/i915/intel_pm.c | 153 +++++++++++++++++++++--- 7 files changed, 159 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 56b8aacc2d76..ff61229d963b 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1470,6 +1470,7 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation) disable_rpm_wakeref_asserts(dev_priv); intel_display_set_init_power(dev_priv, false); + i915_rc6_ctx_wa_suspend(dev_priv); fw_csr = !IS_BROXTON(dev_priv) && suspend_to_idle(dev_priv) && dev_priv->csr.dmc_payload; @@ -1706,6 +1707,8 @@ static int i915_drm_resume_early(struct drm_device *dev) else intel_display_set_init_power(dev_priv, true); + i915_rc6_ctx_wa_resume(dev_priv); + enable_rpm_wakeref_asserts(dev_priv); out: diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 6193369fdbc1..c4f155663ca9 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1228,6 +1228,7 @@ struct intel_gen6_power_mgmt { bool client_boost; bool enabled; + bool ctx_corrupted; struct delayed_work autoenable_work; unsigned boosts; @@ -2695,11 +2696,13 @@ static inline struct scatterlist *__sg_next(struct scatterlist *sg) /* Early gen2 have a totally busted CS tlb and require pinned batches. */ #define HAS_BROKEN_CS_TLB(dev) (IS_I830(dev) || IS_845G(dev)) +#define NEEDS_RC6_CTX_CORRUPTION_WA(dev_priv) \ + (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) == 9) + /* WaRsDisableCoarsePowerGating:skl,bxt */ #define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \ (IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1) || \ - IS_SKL_GT3(dev_priv) || \ - IS_SKL_GT4(dev_priv)) + (INTEL_GEN(dev_priv) == 9)) /* * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index dff3eabd674f..3fb4f9acacba 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2763,6 +2763,12 @@ i915_gem_idle_work_handler(struct work_struct *work) if (INTEL_GEN(dev_priv) >= 6) gen6_rps_idle(dev_priv); + + if (NEEDS_RC6_CTX_CORRUPTION_WA(dev_priv)) { + i915_rc6_ctx_wa_check(dev_priv); + intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); + } + intel_runtime_pm_put(dev_priv); out_unlock: mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c index 8832f8ec1583..f597261c264f 100644 --- a/drivers/gpu/drm/i915/i915_gem_request.c +++ b/drivers/gpu/drm/i915/i915_gem_request.c @@ -558,6 +558,10 @@ static void i915_gem_mark_busy(const struct intel_engine_cs *engine) return; intel_runtime_pm_get_noresume(dev_priv); + + if (NEEDS_RC6_CTX_CORRUPTION_WA(dev_priv)) + intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); + dev_priv->gt.awake = true; intel_enable_gt_powersave(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index cd504bc31e74..5468e69bf520 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -223,6 +223,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN8_CONFIG0 _MMIO(0xD00) #define GEN9_DEFAULT_FIXES (1 << 3 | 1 << 2 | 1 << 1) +#define GEN8_RC6_CTX_INFO _MMIO(0x8504) + #define GAC_ECO_BITS _MMIO(0x14090) #define ECOBITS_SNB_BIT (1<<13) #define ECOBITS_PPGTT_CACHE64B (3<<8) diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 8aafb9601540..b3af565b7027 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1730,6 +1730,9 @@ void intel_enable_gt_powersave(struct drm_i915_private *dev_priv); void intel_autoenable_gt_powersave(struct drm_i915_private *dev_priv); void intel_disable_gt_powersave(struct drm_i915_private *dev_priv); void intel_suspend_gt_powersave(struct drm_i915_private *dev_priv); +bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915); +void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915); +void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915); void gen6_rps_busy(struct drm_i915_private *dev_priv); void gen6_rps_reset_ei(struct drm_i915_private *dev_priv); void gen6_rps_idle(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 39147d40dcc0..07d2a8e7f78c 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -5156,19 +5156,23 @@ static void gen9_disable_rps(struct drm_i915_private *dev_priv) I915_WRITE(GEN6_RP_CONTROL, 0); } -static void gen6_disable_rps(struct drm_i915_private *dev_priv) +static void gen6_disable_rc6(struct drm_i915_private *dev_priv) { I915_WRITE(GEN6_RC_CONTROL, 0); +} + +static void gen6_disable_rps(struct drm_i915_private *dev_priv) +{ I915_WRITE(GEN6_RPNSWREQ, 1 << 31); I915_WRITE(GEN6_RP_CONTROL, 0); } -static void cherryview_disable_rps(struct drm_i915_private *dev_priv) +static void cherryview_disable_rc6(struct drm_i915_private *dev_priv) { I915_WRITE(GEN6_RC_CONTROL, 0); } -static void valleyview_disable_rps(struct drm_i915_private *dev_priv) +static void valleyview_disable_rc6(struct drm_i915_private *dev_priv) { /* we're doing forcewake before Disabling RC6, * This what the BIOS expects when going into suspend */ @@ -5433,7 +5437,8 @@ static void gen9_enable_rc6(struct drm_i915_private *dev_priv) I915_WRITE(GEN9_RENDER_PG_IDLE_HYSTERESIS, 25); /* 3a: Enable RC6 */ - if (intel_enable_rc6() & INTEL_RC6_ENABLE) + if (!dev_priv->rps.ctx_corrupted && + intel_enable_rc6() & INTEL_RC6_ENABLE) rc6_mask = GEN6_RC_CTL_RC6_ENABLE; DRM_INFO("RC6 %s\n", onoff(rc6_mask & GEN6_RC_CTL_RC6_ENABLE)); /* WaRsUseTimeoutMode */ @@ -5491,7 +5496,8 @@ static void gen8_enable_rps(struct drm_i915_private *dev_priv) I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */ /* 3: Enable RC6 */ - if (intel_enable_rc6() & INTEL_RC6_ENABLE) + if (!dev_priv->rps.ctx_corrupted && + intel_enable_rc6() & INTEL_RC6_ENABLE) rc6_mask = GEN6_RC_CTL_RC6_ENABLE; intel_print_rc6_info(dev_priv, rc6_mask); if (IS_BROADWELL(dev_priv)) @@ -6662,6 +6668,95 @@ static void intel_init_emon(struct drm_i915_private *dev_priv) dev_priv->ips.corr = (lcfuse & LCFUSE_HIV_MASK); } +static bool i915_rc6_ctx_corrupted(struct drm_i915_private *dev_priv) +{ + return !I915_READ(GEN8_RC6_CTX_INFO); +} + +static void i915_rc6_ctx_wa_init(struct drm_i915_private *i915) +{ + if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915)) + return; + + if (i915_rc6_ctx_corrupted(i915)) { + DRM_INFO("RC6 context corrupted, disabling runtime power management\n"); + i915->rps.ctx_corrupted = true; + intel_runtime_pm_get(i915); + } +} + +static void i915_rc6_ctx_wa_cleanup(struct drm_i915_private *i915) +{ + if (i915->rps.ctx_corrupted) { + intel_runtime_pm_put(i915); + i915->rps.ctx_corrupted = false; + } +} + +/** + * i915_rc6_ctx_wa_suspend - system suspend sequence for the RC6 CTX WA + * @i915: i915 device + * + * Perform any steps needed to clean up the RC6 CTX WA before system suspend. + */ +void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915) +{ + if (i915->rps.ctx_corrupted) + intel_runtime_pm_put(i915); +} + +/** + * i915_rc6_ctx_wa_resume - system resume sequence for the RC6 CTX WA + * @i915: i915 device + * + * Perform any steps needed to re-init the RC6 CTX WA after system resume. + */ +void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915) +{ + if (!i915->rps.ctx_corrupted) + return; + + if (i915_rc6_ctx_corrupted(i915)) { + intel_runtime_pm_get(i915); + return; + } + + DRM_INFO("RC6 context restored, re-enabling runtime power management\n"); + i915->rps.ctx_corrupted = false; +} + +static void intel_disable_rc6(struct drm_i915_private *dev_priv); + +/** + * i915_rc6_ctx_wa_check - check for a new RC6 CTX corruption + * @i915: i915 device + * + * Check if an RC6 CTX corruption has happened since the last check and if so + * disable RC6 and runtime power management. + * + * Return false if no context corruption has happened since the last call of + * this function, true otherwise. +*/ +bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915) +{ + if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915)) + return false; + + if (i915->rps.ctx_corrupted) + return false; + + if (!i915_rc6_ctx_corrupted(i915)) + return false; + + DRM_NOTE("RC6 context corruption, disabling runtime power management\n"); + + intel_disable_rc6(i915); + i915->rps.ctx_corrupted = true; + intel_runtime_pm_get_noresume(i915); + + return true; +} + void intel_init_gt_powersave(struct drm_i915_private *dev_priv) { /* @@ -6676,6 +6771,8 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv) mutex_lock(&dev_priv->drm.struct_mutex); mutex_lock(&dev_priv->rps.hw_lock); + i915_rc6_ctx_wa_init(dev_priv); + /* Initialize RPS limits (for userspace) */ if (IS_CHERRYVIEW(dev_priv)) cherryview_init_gt_powersave(dev_priv); @@ -6725,6 +6822,8 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv) if (IS_VALLEYVIEW(dev_priv)) valleyview_cleanup_gt_powersave(dev_priv); + i915_rc6_ctx_wa_cleanup(dev_priv); + if (!i915.enable_rc6) intel_runtime_pm_put(dev_priv); } @@ -6756,6 +6855,35 @@ void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv) gen6_reset_rps_interrupts(dev_priv); } +static void __intel_disable_rc6(struct drm_i915_private *dev_priv) +{ + if (INTEL_GEN(dev_priv) >= 9) + gen9_disable_rc6(dev_priv); + else if (IS_CHERRYVIEW(dev_priv)) + cherryview_disable_rc6(dev_priv); + else if (IS_VALLEYVIEW(dev_priv)) + valleyview_disable_rc6(dev_priv); + else if (INTEL_GEN(dev_priv) >= 6) + gen6_disable_rc6(dev_priv); +} + +static void intel_disable_rc6(struct drm_i915_private *dev_priv) +{ + mutex_lock(&dev_priv->rps.hw_lock); + __intel_disable_rc6(dev_priv); + mutex_unlock(&dev_priv->rps.hw_lock); +} + +static void intel_disable_rps(struct drm_i915_private *dev_priv) +{ + if (INTEL_GEN(dev_priv) >= 9) + gen9_disable_rps(dev_priv); + else if (INTEL_GEN(dev_priv) >= 6) + gen6_disable_rps(dev_priv); + else if (IS_IRONLAKE_M(dev_priv)) + ironlake_disable_drps(dev_priv); +} + void intel_disable_gt_powersave(struct drm_i915_private *dev_priv) { if (!READ_ONCE(dev_priv->rps.enabled)) @@ -6763,20 +6891,11 @@ void intel_disable_gt_powersave(struct drm_i915_private *dev_priv) mutex_lock(&dev_priv->rps.hw_lock); - if (INTEL_GEN(dev_priv) >= 9) { - gen9_disable_rc6(dev_priv); - gen9_disable_rps(dev_priv); - } else if (IS_CHERRYVIEW(dev_priv)) { - cherryview_disable_rps(dev_priv); - } else if (IS_VALLEYVIEW(dev_priv)) { - valleyview_disable_rps(dev_priv); - } else if (INTEL_GEN(dev_priv) >= 6) { - gen6_disable_rps(dev_priv); - } else if (IS_IRONLAKE_M(dev_priv)) { - ironlake_disable_drps(dev_priv); - } + __intel_disable_rc6(dev_priv); + intel_disable_rps(dev_priv); dev_priv->rps.enabled = false; + mutex_unlock(&dev_priv->rps.hw_lock); } From 139bb57b355ed8bef2dc619ea9e63923c245557a Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 11 Nov 2019 08:13:24 -0800 Subject: [PATCH 92/93] drm/i915/cmdparser: Fix jump whitelist clearing commit ea0b163b13ffc52818c079adb00d55e227a6da6f upstream. When a jump_whitelist bitmap is reused, it needs to be cleared. Currently this is done with memset() and the size calculation assumes bitmaps are made of 32-bit words, not longs. So on 64-bit architectures, only the first half of the bitmap is cleared. If some whitelist bits are carried over between successive batches submitted on the same context, this will presumably allow embedding the rogue instructions that we're trying to reject. Use bitmap_zero() instead, which gets the calculation right. Fixes: f8c08d8faee5 ("drm/i915/cmdparser: Add support for backward jumps") Signed-off-by: Ben Hutchings Signed-off-by: Jon Bloomfield Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_cmd_parser.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 7f1e2c5e113f..1e104518192d 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1374,7 +1374,7 @@ static void init_whitelist(struct i915_gem_context *ctx, u32 batch_len) return; if (batch_cmds <= ctx->jump_whitelist_cmds) { - memset(ctx->jump_whitelist, 0, exact_size * sizeof(u32)); + bitmap_zero(ctx->jump_whitelist, batch_cmds); return; } @@ -1394,8 +1394,7 @@ again: } DRM_DEBUG("CMD: Failed to extend whitelist. BB_START may be disallowed\n"); - memset(ctx->jump_whitelist, 0, - BITS_TO_LONGS(ctx->jump_whitelist_cmds) * sizeof(u32)); + bitmap_zero(ctx->jump_whitelist, ctx->jump_whitelist_cmds); return; } From 9829ecfd824adba0396cf5fa8dcc813f4c0ff754 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 12 Nov 2019 19:16:25 +0100 Subject: [PATCH 93/93] Linux 4.9.201 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 84410351b27c..4741bbdfaa10 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 9 -SUBLEVEL = 200 +SUBLEVEL = 201 EXTRAVERSION = NAME = Roaring Lionus