linux/drivers
Chris Wilson 4fc788f5ee drm/i915: Flush delayed fence releases after reset
What I never hit in testing, but Mika immediately did, was a GPU hang
with a pending fence release (where a tiled object has been changed by
the user to be untiled, and the update has not yet been committed to the
fence register). As the stride/tiling is 0, this causes a divide-by-zero
error when trying to write the new fence parameters:

[   28.784518] drm/i915: Resetting chip after gpu hang
[   28.784551] divide error: 0000 [#1] PREEMPT SMP
[   28.784565] Modules linked in: nls_iso8859_1 nls_cp437 vfat fat mxm_wmi x86_pkg_temp_thermal snd_hda_codec_hdmi kvm irqbypass snd_hda_codec_realtek snd_hda_codec_generic snd_hda_intel snd_hda_codec serio_raw snd_hwdep snd_hda_core snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq snd_timer snd_seq_device snd soundcore mac_hid wmi efivarfs autofs4 raid10 raid456 libcrc32c async_raid6_recov async_memcpy async_pq raid6_pq async_xor xor async_tx raid0 multipath linear psmouse e1000e ptp pps_core nvme nvme_core i915 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm video
[   28.784738] CPU: 0 PID: 1692 Comm: kworker/0:2 Not tainted 4.8.0-rc2+ #895
[   28.784752] Hardware name: System manufacturer System Product Name/Z170M-PLUS, BIOS 1803 05/09/2016
[   28.784786] Workqueue: events_long i915_hangcheck_elapsed [i915]
[   28.784814] task: ffff923c18f59d40 task.stack: ffff923c1b7e4000
[   28.784827] RIP: 0010:[<ffffffffc0475b5f>]  [<ffffffffc0475b5f>] fence_write+0x9f/0x3b0 [i915]
[   28.784854] RSP: 0018:ffff923c1b7e7b30  EFLAGS: 00010246
[   28.784866] RAX: 00000000008ca000 RBX: ffff923c18540000 RCX: 0000000000000020
[   28.784880] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 000000000596d000
[   28.784894] RBP: ffff923c1b7e7b68 R08: 0000000000000000 R09: 0000000000000000
[   28.784908] R10: 0000000000000000 R11: 00000000008ca000 R12: ffff923c1ef9d600
[   28.784921] R13: 0000000000100040 R14: 0000000000100044 R15: ffff923c18549908
[   28.784935] FS:  0000000000000000(0000) GS:ffff923c36c00000(0000) knlGS:0000000000000000
[   28.784951] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   28.784962] CR2: 00007f193373c893 CR3: 0000000419c78000 CR4: 00000000003406f0
[   28.784976] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   28.784990] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   28.785004] Stack:
[   28.785009]  000000000596c03b ffff923c1b7e7b68 ffff923c18549938 0000000000000009
[   28.785026]  ffff923c18540000 ffff923c18549280 ffff923c18547ce8 ffff923c1b7e7b90
[   28.785044]  ffffffffc04761f9 ffff923c18540000 ffff923c18547d00 ffff923c18548ff8
[   28.785062] Call Trace:
[   28.785078]  [<ffffffffc04761f9>] i915_gem_restore_fences+0x39/0x50 [i915]
[   28.785102]  [<ffffffffc047fe89>] i915_gem_reset+0x179/0x300 [i915]

Reported-by: Mika Kuoppala <mika.kuoppala@intel.com>
Fixes: 49ef5294cd ("drm/i915: Move fence tracking from object to vma")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160819155428.1670-1-chris@chris-wilson.co.uk
2016-08-19 16:59:22 +01:00
..
accessibility
acpi libnvdimm, nd_blk: mask off reserved status bits 2016-08-08 09:26:13 -07:00
amba
android
ata New LED class driver: 2016-07-27 14:03:52 -07:00
atm drivers: atm: nicstar: Use the correct function to free some resources 2016-07-19 11:30:26 -07:00
auxdisplay
base More power management updates for v4.8-rc1 2016-08-05 23:26:16 -04:00
bcma wireless-drivers-next patches for 4.8 2016-07-25 11:09:19 -07:00
block virtio/vhost: fixes and cleanups for 4.8 2016-08-11 14:10:23 -07:00
bluetooth Bluetooth: btmrvl: reset is_suspending flag in failure path 2016-07-18 10:13:02 +02:00
bus ARM: SoC driver updates for v4.8 2016-08-01 18:36:01 -04:00
cdrom cdrom: support read sub-channel command in LBA format 2016-07-12 08:24:50 -07:00
char agp/intel: Flush chipset writes after updating a single PTE 2016-08-18 22:36:23 +01:00
clk treewide: replace obsolete _refok by __ref 2016-08-02 17:31:41 -04:00
clocksource Merge branch 'linus' into timers/urgent, to pick up fixes 2016-08-10 14:36:23 +02:00
connector
cpufreq Merge branches 'pm-sleep' and 'pm-cpufreq' 2016-08-12 22:53:58 +02:00
cpuidle powerpc updates for 4.8 # 1 2016-07-30 21:01:36 -07:00
crypto Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 2016-08-01 14:28:42 -04:00
dax
dca
devfreq
dio
dma dmaengine updates for 4.8-rc1 2016-07-28 15:45:17 -07:00
dma-buf dma-buf/sync_file: only enable fence signalling on poll() 2016-08-11 15:39:38 +05:30
edac * Altera Arria10 ethernet FIFO buffer support (Thor Thayer) 2016-07-27 13:40:47 -07:00
eisa
extcon
firewire
firmware efi/capsule: Allocate whole capsule into virtual memory 2016-08-11 13:55:36 +02:00
fmc
fpga drivers/fpga/Kconfig: fix build failure 2016-08-04 08:50:07 -04:00
gpio This is the bulk of GPIO changes for the v4.8 kernel cycle. 2016-07-26 19:16:01 -07:00
gpu drm/i915: Flush delayed fence releases after reset 2016-08-19 16:59:22 +01:00
hid Merge branch 'for-4.8/hid-led' into for-linus 2016-07-28 10:49:23 +02:00
hsi
hv
hwmon hwmon updates for v4.8 (take 2) 2016-08-01 16:49:13 -04:00
hwspinlock
hwtracing Merge branch 'smp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-07-29 13:55:30 -07:00
i2c powerpc updates for 4.8 # 1 2016-07-30 21:01:36 -07:00
ide Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/ide 2016-07-29 13:29:06 -07:00
idle Merge branch 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-07-30 12:56:26 -07:00
iio Third set of IIO new device support, features and cleanups for the 4.8 cycle. 2016-07-14 12:05:29 +09:00
infiniband Second round of merge items for 4.8 2016-08-04 20:26:31 -04:00
input Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input 2016-08-05 23:24:15 -04:00
iommu dma-mapping: use unsigned long for dma_attrs 2016-08-04 08:50:07 -04:00
ipack
irqchip tree-wide: replace config_enabled() with IS_ENABLED() 2016-08-04 08:50:07 -04:00
isdn
leds powerpc updates for 4.8 # 1 2016-07-30 21:01:36 -07:00
lguest
lightnvm block: get rid of bio_rw and READA 2016-07-20 17:37:01 -06:00
macintosh powerpc updates for 4.8 # 1 2016-07-30 21:01:36 -07:00
mailbox mailbox: Fix format and type mismatches in Broadcom PDC driver 2016-07-28 21:27:31 +05:30
mcb
md block: rename bio bi_rw to bi_opf 2016-08-07 14:41:02 -06:00
media media updates for v4.8-rc1 2016-08-04 09:59:37 -04:00
memory MTD updates for v4.8: 2016-08-02 17:05:11 -04:00
memstick memstick: don't allocate unused major for ms_block 2016-08-02 17:31:41 -04:00
message
mfd ARM: SoC driver updates for v4.8 2016-08-01 18:36:01 -04:00
misc powerpc fixes for 4.8 #3 2016-08-12 12:09:44 -07:00
mmc MMC core: 2016-07-31 21:36:58 -04:00
mtd This pull request contains mostly cleanups and minor 2016-08-04 19:51:49 -04:00
net virtio/vhost: new features for 4.8 2016-08-06 09:20:13 -04:00
nfc NFC 4.8 pull request 2016-07-20 23:39:36 -07:00
ntb NTB: ntb_hw_intel: use local variable pdev 2016-08-05 10:34:13 -04:00
nubus
nvdimm nvdimm, btt: add a size attribute for BTTs 2016-08-08 09:26:14 -07:00
nvme nvme: Suspend all queues before deletion 2016-08-11 09:35:57 -06:00
nvmem
of ramoops: use DT reserved-memory bindings 2016-08-05 11:21:36 -07:00
oprofile
parisc dma-mapping: use unsigned long for dma_attrs 2016-08-04 08:50:07 -04:00
parport
pci genirq/msi: Make sure PCI MSIs are activated early 2016-08-09 09:19:32 +02:00
pcmcia
perf drivers/perf: arm-pmu: Fix handling of SPI lacking "interrupt-affinity" property 2016-08-09 17:57:39 +01:00
phy MMC core: 2016-07-31 21:36:58 -04:00
pinctrl This is the bulk of pin control changes for the v4.8 kernel cycle. 2016-07-28 17:06:51 -07:00
platform dell-wmi: Ignore WMI event 0xe00e 2016-08-08 11:00:21 -07:00
pnp PNP: pnpbios: add header file to fix build errors 2016-07-27 18:52:54 +02:00
power ARM: SoC driver updates for v4.8 2016-08-01 18:36:01 -04:00
powercap
pps pps: do not crash when failed to register 2016-07-23 10:25:54 +09:00
ps3
ptp
pwm pwm: Changes for v4.8-rc1 2016-08-06 00:01:33 -04:00
rapidio rapidio: dereferencing an error pointer 2016-08-10 16:40:56 -07:00
ras
regulator pwm: Changes for v4.8-rc1 2016-08-06 00:01:33 -04:00
remoteproc dma-mapping: use unsigned long for dma_attrs 2016-08-04 08:50:07 -04:00
reset
rpmsg
rtc RTC for 4.8 2016-08-05 09:48:22 -04:00
s390 virtio/s390: deprecate old transport 2016-08-09 13:42:41 +03:00
sbus
scsi ipr: Fix sync scsi scan 2016-08-09 10:17:42 -07:00
sfi
sh
sn
soc ARM: SoC driver updates for v4.8 2016-08-01 18:36:01 -04:00
spi ARM: DT updates for v4.8 2016-08-01 18:37:45 -04:00
spmi
ssb
staging dma-buf/sync_file: refactor fence storage in struct sync_file 2016-08-11 15:33:24 +05:30
target target: iblock_execute_sync_cache() should use bio_set_op_attrs() 2016-08-07 14:41:02 -06:00
tc
thermal Merge branches 'thermal-intel' and 'thermal-core' into next 2016-08-08 10:59:35 +08:00
thunderbolt
tty tree-wide: replace config_enabled() with IS_ENABLED() 2016-08-04 08:50:07 -04:00
uio
usb More USB patches for 4.8-rc1 2016-08-05 23:07:43 -04:00
uwb
vfio vfio/pci: Fix NULL pointer oops in error interrupt setup handling 2016-08-08 16:16:23 -06:00
vhost vhost/vsock: fix vhost virtio_vsock_pkt use-after-free 2016-08-09 13:42:37 +03:00
video dma-mapping: use unsigned long for dma_attrs 2016-08-04 08:50:07 -04:00
virt
virtio virtio: fix error handling for debug builds 2016-08-09 13:42:35 +03:00
vlynq
vme
w1 w1:omap_hdq: fix regression 2016-08-02 19:35:40 -04:00
watchdog watchdog: gpio_wdt: Fix missing platform_set_drvdata() in gpio_wdt_probe() 2016-07-27 10:47:43 +02:00
xen dma-mapping: use unsigned long for dma_attrs 2016-08-04 08:50:07 -04:00
zorro
Kconfig
Makefile virtio/vhost: new features for 4.8 2016-08-06 09:20:13 -04:00