Bug 78328 - [SNB Regression]igt/gem_evict_everything/forked-swapping-mempressure-normal causes OOM Killer
Summary: [SNB Regression]igt/gem_evict_everything/forked-swapping-mempressure-normal c...
Status: CLOSED WORKSFORME
Alias: None
Product: DRI
Classification: Unclassified
Component: DRM/Intel (show other bugs)
Version: unspecified
Hardware: Other All
: high normal
Assignee: Intel GFX Bugs mailing list
QA Contact: Intel GFX Bugs mailing list
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2014-05-06 08:45 UTC by Guo Jinxian
Modified: 2017-08-14 08:30 UTC (History)
1 user (show)

See Also:
i915 platform:
i915 features:


Attachments
dmesg (96.33 KB, text/plain)
2014-05-06 08:45 UTC, Guo Jinxian
no flags Details

Description Guo Jinxian 2014-05-06 08:45:53 UTC
Created attachment 98544 [details]
dmesg

*System Environment:
--------------------------
Regression: Yes.  
good commit on -queued(bb8786a44c6042ec8a85370466a8bd400a079bdc)

Non-working platforms: SNB

 *kernel: 
--------------------------
-nightly: 5e83a7964e9530e6f693a3d49adccceb7a4b86e1 (fails)
-queued: d9ceb957fd97836c7fb0e403062e68ad2f737021 (fails)
    Author: Ben Widawsky <benjamin.widawsky@intel.com>
    Date:   Mon Apr 28 17:18:28 2014 -0700

    drm/i915: Support 64b relocations

    All the rest of the code to enable this is in my branch. Without my
    branch, hitting > 32b offsets is impossible. The code has always
    "supported" 64b, but it's never actually been run of tested. This change
    doesn't actually fix anything. [1] I am not sure why X won't work yet. I
    do not get hangs or obvious errors.

    There are 3 fixes grouped together here. First is to remove the
    hardcoded 0 for the upper dword of the relocation. The next fix is to
    use a 64b value for target_offset. The final fix is to not directly
    apply target_offset to reloc->delta. reloc->delta is part of ABI, and so
    we cannot change it. As it stands, 32b is enough to represent everything
    we're interested in representing anyway. The main problem is, we cannot
    add greater than 32b values to it directly.

    [1] Almost all of intel-gpu-tools is not yet ready to test 64b
    relocations. There are a few places that expect 32b values for offsets
    and these all won't work.

    Cc: Rafael Barbalho <rafael.barbalho@intel.com>
    Cc: Chris Wilson <chris@chris-wilson.co.uk>
    Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
    Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
    Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>


-fixes: 9bbfd20abe5025adbb0ac75160bd2e41158a9e83 (works)
    Author: Paulo Zanoni <paulo.r.zanoni@intel.com>
    Date:   Tue Apr 29 11:00:22 2014 -0300

    drm/i915: don't try DP_LINK_BW_5_4 on HSW ULX

    Because the docs say ULX doesn't support it on HSW.

    Reviewed-by: Dave Airlie <airlied@redhat.com>
    Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
    Signed-off-by: Jani Nikula <jani.nikula@intel.com>

 *Bug detailed description:
-----------------------------
igt/gem_evict_everything/forked-swapping-mempressure-normal causes OOM Killer

Output:
 date;./gem_evict_everything --run-subtest forked-swapping-mempressure-normal;date
Tue May  6 15:58:20 CST 2014
IGT-Version: 1.6-gc864279 (i686) (Linux: 3.15.0-rc3_drm-intel-nightly_5e83a7_20140506+ i686)
child 8 died with signal 9, Killed
Subtest forked-swapping-mempressure-normal: FAIL
gem_evict_everything: igt_core.c:832: children_exit_handler: Assertion `ret == 0' failed.
Aborted (core dumped)
Tue May  6 16:06:49 CST 2014

 *Reproduce steps:
---------------------------- 
1. ./gem_evict_everything --run-subtest forked-swapping-mempressure-normal
Comment 1 Chris Wilson 2014-05-06 12:25:11 UTC
Well that's curious. Please bisect.
Comment 2 Guo Jinxian 2014-05-08 07:09:44 UTC
(In reply to comment #1)
> Well that's curious. Please bisect.

I can't reproduce this issue now, whether exchange previous kernel or previous igt.
Comment 3 Daniel Vetter 2014-05-15 21:27:23 UTC
Closing again since the bug refuses to reproduce. Please reopen if it shows up again.
Comment 4 Chris Wilson 2014-05-16 06:34:59 UTC
It's likely to be the same shrinker fallout anyway.
Comment 5 liulei 2014-05-26 08:23:16 UTC
Verified 
[root@x-sgb opt]# ./gem_evict_everything --run-subtest forked-swapping-mempressure-normal
IGT-Version: 1.6-gff3c122 (x86_64) (Linux: 3.15.0-rc3_drm-intel-next-queued_f83d65_20140526+ x86_64)
Subtest forked-swapping-mempressure-normal: SUCCESS
Comment 6 Jari Tahvanainen 2017-08-14 08:30:49 UTC
Moving old bug from Verified to Closed.


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.