Bug 76308 - [BDW Regression]igt/kms_flip/flip-vs-fences fails with OOM killer
Summary: [BDW Regression]igt/kms_flip/flip-vs-fences fails with OOM killer
Status: CLOSED FIXED
Alias: None
Product: DRI
Classification: Unclassified
Component: DRM/Intel (show other bugs)
Version: unspecified
Hardware: All Linux (All)
: high major
Assignee: Jesse Barnes
QA Contact: Intel GFX Bugs mailing list
URL:
Whiteboard:
Keywords:
Depends on: 72742
Blocks:
  Show dependency treegraph
 
Reported: 2014-03-18 08:56 UTC by lu hua
Modified: 2017-10-06 14:39 UTC (History)
1 user (show)

See Also:
i915 platform:
i915 features:


Attachments
dmesg (124.99 KB, text/plain)
2014-03-18 08:56 UTC, lu hua
no flags Details
dmesg (122.19 KB, text/plain)
2014-03-28 06:15 UTC, lu hua
no flags Details

Description lu hua 2014-03-18 08:56:51 UTC
Created attachment 95991 [details]
dmesg

System Environment:
--------------------------
Platform: Broadwell
kernel: (drm-intel-nightly)b1859622badb7509586987af5269aa525a0c112f

Bug detailed description:
-------------------------
It fails with OOM killer on Broadwell with -nightly kernel, and doesn't happen on -fixes, -queued, drm-next, drm-fixes and core-stuff branch.
igt/kms_flip/flip-vs-fences-interruptible also fails.

It doesn't happen on commit: 32faf6da913d67a4a3fcddd810305ec3445ed581(-nightly branch)

output:
IGT-Version: 1.6-g10571b8 (x86_64) (Linux: 3.14.0-rc6_drm-intel-nightly_b18596_20140314+ x86_64)
Using monotonic timestamps
Beginning flip-vs-fences on crtc 3, connector 10
  1920x1080 60 1920 1966 1996 2080 1080 1082 1086 1112 0xa 0x48 138780
...............................................................................................................................
flip-vs-fences on crtc 3, connector 10: PASSED

Beginning flip-vs-fences on crtc 5, connector 10
  1920x1080 60 1920 1966 1996 2080 1080 1082 1086 1112 0xa 0x48 138780
..............................Killed

[  158.480224] Call Trace:
[  158.480237]  [<ffffffff817170e3>] ? dump_stack+0x41/0x51
[  158.480244]  [<ffffffff817143b1>] ? dump_header.isra.8+0x69/0x191
[  158.480253]  [<ffffffff8107225e>] ? ktime_get_ts+0x49/0xab
[  158.480262]  [<ffffffff812d6cf2>] ? ___ratelimit+0xae/0xc8
[  158.480271]  [<ffffffff810a7244>] ? oom_kill_process+0x76/0x32c
[  158.480278]  [<ffffffff810a7009>] ? find_lock_task_mm+0x22/0x6e
[  158.480288]  [<ffffffff8103af8a>] ? has_ns_capability_noaudit+0xe/0x15
[  158.480295]  [<ffffffff810a7a79>] ? out_of_memory+0x41c/0x44f
[  158.480301]  [<ffffffff810ab2bd>] ? __alloc_pages_nodemask+0x680/0x78d
[  158.480310]  [<ffffffff810d4a2b>] ? alloc_pages_current+0xbf/0xdc
[  158.480317]  [<ffffffff810a6196>] ? filemap_fault+0x25c/0x381
[  158.480325]  [<ffffffff810bc2a1>] ? __do_fault+0xac/0x3bf
[  158.480332]  [<ffffffff810bfa31>] ? handle_mm_fault+0x1e7/0x7e2
[  158.480341]  [<ffffffff8171f4bd>] ? __do_page_fault+0x42e/0x47b
[  158.480348]  [<ffffffff81038055>] ? timespec_add_safe+0x1e/0x4d
[  158.480353]  [<ffffffff810f08e8>] ? dput+0x16/0xeb
[  158.480359]  [<ffffffff8107225e>] ? ktime_get_ts+0x49/0xab
[  158.480368]  [<ffffffff810edcfa>] ? poll_select_copy_remaining+0xe0/0xf6
[  158.480374]  [<ffffffff8171ca72>] ? page_fault+0x22/0x30
[  158.480377] Mem-Info:
[  158.480380] Node 0 DMA per-cpu:
[  158.480385] CPU    0: hi:    0, btch:   1 usd:   0
[  158.480389] CPU    1: hi:    0, btch:   1 usd:   0
[  158.480392] CPU    2: hi:    0, btch:   1 usd:   0
[  158.480396] CPU    3: hi:    0, btch:   1 usd:   0
[  158.480398] Node 0 DMA32 per-cpu:
[  158.480403] CPU    0: hi:  186, btch:  31 usd:   0
[  158.480407] CPU    1: hi:  186, btch:  31 usd:   0
[  158.480410] CPU    2: hi:  186, btch:  31 usd:   0
[  158.480413] CPU    3: hi:  186, btch:  31 usd:   0
[  158.480436] Node 0 Normal per-cpu:
[  158.480440] CPU    0: hi:  186, btch:  31 usd:   0
[  158.480443] CPU    1: hi:  186, btch:  31 usd:   0
[  158.480446] CPU    2: hi:  186, btch:  31 usd:   0
[  158.480449] CPU    3: hi:  186, btch:  31 usd:   0


Reproduce steps:
---------------------------- 
1. ./kms_flip --run-subtest flip-vs-fences
Comment 1 Daniel Vetter 2014-03-27 09:16:38 UTC
Wut ... Is this still an issue on latest -nightly?
Comment 2 lu hua 2014-03-28 06:14:40 UTC
It still happens on latest -nightly kernel.
Comment 3 lu hua 2014-03-28 06:15:03 UTC
Created attachment 96510 [details]
dmesg
Comment 4 Guang Yang 2014-05-17 01:18:18 UTC
Hua, can you help to retest this issue.
Comment 5 Daniel Vetter 2014-05-19 09:04:33 UTC
Sounds like a dupe of the filp leak ... Please retest and reopen if it still happens.

Also we'd need the bisect result here ...
Comment 6 lu hua 2014-05-21 05:40:27 UTC
Verified.Fixed.
Comment 7 Elizabeth 2017-10-06 14:39:15 UTC
Closing old verified.


Use of freedesktop.org services, including Bugzilla, is subject to our Code of Conduct. How we collect and use information is described in our Privacy Policy.