[Bug 78328] New: [SNB Regression]igt/gem_evict_everything/forked-swapping-mempressure-normal causes OOM Killer

[bugzilla-daemon at freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=78328

          Priority: high
            Bug ID: 78328
                CC: intel-gfx-bugs at lists.freedesktop.org
          Assignee: intel-gfx-bugs at lists.freedesktop.org
           Summary: [SNB
                    Regression]igt/gem_evict_everything/forked-swapping-me
                    mpressure-normal causes OOM Killer
        QA Contact: intel-gfx-bugs at lists.freedesktop.org
          Severity: normal
    Classification: Unclassified
                OS: All
          Reporter: jinxianx.guo at intel.com
          Hardware: Other
            Status: NEW
           Version: unspecified
         Component: DRM/Intel
           Product: DRI

Created attachment 98544
  --> https://bugs.freedesktop.org/attachment.cgi?id=98544&action=edit
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 at 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 at intel.com>
    Cc: Chris Wilson <chris at chris-wilson.co.uk>
    Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
    Reviewed-by: Chris Wilson <chris at chris-wilson.co.uk>
    Signed-off-by: Daniel Vetter <daniel.vetter at ffwll.ch>


-fixes: 9bbfd20abe5025adbb0ac75160bd2e41158a9e83 (works)
    Author: Paulo Zanoni <paulo.r.zanoni at 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 at redhat.com>
    Signed-off-by: Paulo Zanoni <paulo.r.zanoni at intel.com>
    Signed-off-by: Jani Nikula <jani.nikula at 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

-- 
You are receiving this mail because:
You are the QA Contact for the bug.
You are on the CC list for the bug.
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.freedesktop.org/archives/intel-gfx-bugs/attachments/20140506/543bc6b2/attachment.html>