linux_dsm_epyc7002/drivers
Chris Wilson 751b01cb07 drm/i915/ppgtt: Pin page directories before allocation
Commit e2b763caa6 ("drm/i915: Remove bitmap tracking for used-pdpes")
believed that because it did not insert its freshly allocated page
directory into the pd tree, it was safe from the shrinker. I failed to
heed the lesson learnt from commit dd19674bac ("drm/i915: Remove bitmap
tracking for used-ptes") that we need to pin all the levels in the tree
before hitting the shrinker or else the shrinker may free an upper layer
as we proceed to allocate the tree. Thus leaving dangling pointers
everywhere and a GPF should we hit direct reclaim at just the wrong
moment.

CPU: 0 PID: 7374 Comm: chromium Tainted: P           O    4.14.13-1-ARCH #1
Hardware name: Apple Inc. MacBookPro12,1/Mac-E43C1C25D4880AD6, BIOS MBP121.88Z.0167.B33.1706181928 06/18/2017
task: ffff994f696c2c40 task.stack: ffffb1a789d4c000
RIP: 0010:gen8_ppgtt_set_pde.isra.40+0x48/0x70 [i915]
RSP: 0018:ffffb1a789d4f940 EFLAGS: 00010206
RAX: 81c1788cc4f68138 RBX: ffff994f54db8000 RCX: ffff994f696c2c40
RDX: 000000023bc73003 RSI: ffff994d598b6b80 RDI: ffff994f54db8000
RBP: ffff994d598b6b80 R08: 0000000000000000 R09: 0000000000000000
R10: ffffb1a789d4f550 R11: ffff994eaf3c3208 R12: 0000000000000027
R13: 0000000000005000 R14: 0000000004e8f000 R15: ffff994f54dba000
FS:  00007f585886aa00(0000) GS:ffff994faec00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000004ac8e8 CR3: 00000002552c8004 CR4: 00000000003606f0
Call Trace:
 gen8_ppgtt_alloc_pdp+0x178/0x320 [i915]
 gen8_ppgtt_alloc_4lvl+0x5f/0x150 [i915]
 ppgtt_bind_vma+0x30/0x70 [i915]
 i915_vma_bind+0x68/0xd0 [i915]
 __i915_vma_do_pin+0x2d6/0x3a0 [i915]
 eb_lookup_vmas+0x7a2/0xb50 [i915]
 i915_gem_do_execbuffer+0x4d7/0x10e0 [i915]
 ? sock_wfree+0x34/0x60
 ? unix_stream_read_generic+0x1f9/0x7e0
 ? import_iovec+0x37/0xd0
 ? i915_gem_execbuffer2+0x5d/0x390 [i915]
 i915_gem_execbuffer2+0x1b7/0x390 [i915]
 ? i915_gem_execbuffer+0x2d0/0x2d0 [i915]
 drm_ioctl_kernel+0x59/0xb0 [drm]
 drm_ioctl+0x2d5/0x370 [drm]
 ? i915_gem_execbuffer+0x2d0/0x2d0 [i915]
 ? __seccomp_filter+0x3b/0x260
 do_vfs_ioctl+0xa1/0x610
 ? syscall_trace_enter+0xdb/0x2b0
 SyS_ioctl+0x74/0x80
 do_syscall_64+0x55/0x110
 entry_SYSCALL64_slow_path+0x25/0x25
RIP: 0033:0x7f584fa82d27
RSP: 002b:00007ffee14a7828 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 000003b0126a1030 RCX: 00007f584fa82d27
RDX: 00007ffee14a7870 RSI: 0000000040406469 RDI: 0000000000000080
RBP: 00007ffee14a7870 R08: 0000000000000002 R09: 0000000000000077
R10: 00007f5839f2b780 R11: 0000000000000246 R12: 0000000040406469
R13: 0000000000000080 R14: 00007f5842b00040 R15: 0000000000000000
Code: 01 00 83 81 58 0a 00 00 01 48 2b 05 13 9d fd c9 48 c1 f8 06 48 c1 e0 0c 48 8d 04 d0 48 8b 56 08 48 03 05 0c 9d fd c9 48 83 ca 03 <48> 89 10 83 a9 58 0a 00 00 01 65 ff 0d 37 03 fb 3e 74 02 f3 c3
RIP: gen8_ppgtt_set_pde.isra.40+0x48/0x70 [i915] RSP: ffffb1a789d4f940

Reported-by: Eric Blau <eblau@eblau.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104773
Fixes: e2b763caa6 ("drm/i915: Remove bitmap tracking for used-pdpes")
References: dd19674bac ("drm/i915: Remove bitmap tracking for used-ptes")
Testcase: igt/drv_selftest/live_gtt (igt_ppgtt_shrink_boom)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180131214440.7141-1-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
(cherry picked from commit b715a2f0c7)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2018-02-01 07:33:04 -08:00
..
accessibility
acpi Merge branch 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm 2017-12-23 13:47:22 -08:00
amba
android binder: fix proc->files use-after-free 2017-12-18 15:47:12 +01:00
ata
atm
auxdisplay
base Linux 4.15-rc8 2018-01-18 09:32:15 +10:00
bcma
block Two rbd fixes for 4.12 and 4.2 issues respectively, marked for stable. 2018-01-11 16:57:32 -08:00
bluetooth
bus Allwinner fixes for 4.15 2018-01-04 17:06:25 +01:00
cdrom
char - Fix documentation build issues (Randy, Markus) 2017-12-21 11:08:30 +10:00
clk clk: use atomic runtime pm api in clk_core_is_enabled 2017-12-26 17:34:03 -08:00
clocksource
connector
cpufreq cpufreq: governor: Ensure sufficiently large sampling intervals 2017-12-18 12:09:39 +01:00
cpuidle
crypto crypto: inside-secure - do not use areq->result for partial results 2017-12-22 19:48:01 +11:00
dax
dca
devfreq
dio
dma dmaengine: fsl-edma: disable clks on all error paths 2017-12-15 09:53:04 +05:30
dma-buf dma-buf: fix reservation_object_wait_timeout_rcu once more v2 2018-01-23 10:46:39 -05:00
edac
eisa
extcon
firewire
firmware efi/capsule-loader: Reinstate virtual capsule mapping 2018-01-03 13:54:31 +01:00
fmc
fpga
fsi
gpio gpio: Add missing open drain/source handling to gpiod_set_value_cansleep() 2018-01-10 14:17:17 +01:00
gpu drm/i915/ppgtt: Pin page directories before allocation 2018-02-01 07:33:04 -08:00
hid Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid 2017-12-30 10:16:51 -08:00
hsi
hv vmbus: unregister device_obj->channels_kset 2017-12-18 15:47:12 +01:00
hwmon hwmon: Deal with errors from the thermal subsystem 2017-12-26 11:53:24 -08:00
hwspinlock
hwtracing
i2c i2c: piix4: Fix port number check on release 2017-12-12 23:27:04 +01:00
ide
idle
iio
infiniband Fourth pull request for 4.15-rc 2018-01-08 16:17:31 -08:00
input Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input 2018-01-05 16:45:06 -08:00
iommu iommu/arm-smmu-v3: Cope with duplicated Stream IDs 2018-01-02 16:45:51 +00:00
ipack
irqchip genirq/irqdomain: Rename early argument of irq_domain_activate_irq() 2017-12-29 21:13:04 +01:00
isdn
leds leds: core: Fix regression caused by commit 2b83ff96f5 2018-01-07 13:27:07 +01:00
lightnvm
macintosh
mailbox
mcb
md locking/barriers: Convert users of lockless_dereference() to READ_ONCE() 2017-12-17 13:57:15 +01:00
media Linux 4.15-rc4 2017-12-19 21:37:24 +10:00
memory
memstick
message
mfd mfd: rtsx: Release IRQ during shutdown 2018-01-05 11:14:57 +00:00
misc Merge branch 'WIP.x86-pti.base.prep-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2017-12-17 13:54:31 -08:00
mmc mmc: s3mci: mark debug_regs[] as static 2018-01-04 12:42:31 +01:00
mtd mtd: nand: pxa3xx: Fix READOOB implementation 2018-01-06 23:06:58 +01:00
mux mux: core: fix double get_device() 2018-01-09 14:19:41 +01:00
net mlxsw: spectrum_qdisc: Don't use variable array in mlxsw_sp_tclass_congestion_enable 2018-01-10 15:58:23 -05:00
nfc
ntb
nubus
nvdimm libnvdimm, btt: Fix an incompatibility in the log layout 2017-12-21 14:59:27 -08:00
nvme nvme-fabrics: initialize default host->id in nvmf_host_default() 2018-01-08 10:52:03 +01:00
nvmem nvmem: meson-mx-efuse: fix reading from an offset other than 0 2017-12-23 16:46:23 +01:00
of of_mdio: avoid MDIO bus removal when a PHY is missing 2018-01-10 15:07:47 -05:00
opp
oprofile
parisc parisc: Show unhashed EISA EEPROM address 2018-01-02 21:01:02 +01:00
parport
pci Merge branch 'x86/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2017-12-31 13:13:56 -08:00
pcmcia
perf
phy phy: rcar-gen3-usb2: select USB_COMMON 2017-12-15 16:00:41 +05:30
pinctrl genirq/irqdomain: Rename early argument of irq_domain_activate_irq() 2017-12-29 21:13:04 +01:00
platform platform/x86: wmi: Call acpi_wmi_init() later 2018-01-08 10:47:48 -08:00
pnp
power
powercap
pps
ps3
ptp
pwm
rapidio
ras
regulator
remoteproc
reset
rpmsg
rtc
s390 Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux 2018-01-05 12:17:33 -08:00
sbus
scsi SCSI fixes on 20171230 2017-12-30 14:31:30 -08:00
sfi
sh
sn
soc
spi Merge remote-tracking branches 'spi/fix/armada', 'spi/fix/atmel', 'spi/fix/doc', 'spi/fix/imx', 'spi/fix/rspi', 'spi/fix/sun4i' and 'spi/fix/xilinx' into spi-linus 2017-12-19 11:07:00 +00:00
spmi
ssb
staging Linux 4.15-rc8 2018-01-18 09:32:15 +10:00
target block: fix blk_rq_append_bio 2017-12-18 13:55:43 -07:00
tc
tee
thermal
thunderbolt thunderbolt: Mask ring interrupt properly when polling starts 2017-12-16 16:37:51 +01:00
tty n_tty: fix EXTPROC vs ICANON interaction with TIOCINQ (aka FIONREAD) 2017-12-21 11:19:22 +01:00
uio
usb usb: misc: usb3503: make sure reset is low for at least 100us 2018-01-11 18:39:52 +01:00
uwb
vfio
vhost
video omapdrm: panel: td028ttec1: replace MODULE_ALIAS by MODULE_DEVICE_TABLE 2017-12-19 10:32:00 +02:00
virt
virtio virtio_mmio: fix devm cleanup 2017-12-14 21:01:40 +02:00
vlynq
vme
w1
watchdog
xen xen: fixes for 4.15-rc8 2018-01-12 10:00:15 -08:00
zorro
Kconfig
Makefile