<html>
    <head>
      <base href="https://bugs.freedesktop.org/" />
    </head>
    <body>
      <p>
        <div>
            <b><a class="bz_bug_link 
          bz_status_NEW "
   title="NEW --- - [GM45 regression] GPU hang during disk io"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=57136#c42">Comment # 42</a>
              on <a class="bz_bug_link 
          bz_status_NEW "
   title="NEW --- - [GM45 regression] GPU hang during disk io"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=57136">bug 57136</a>
              from <span class="vcard"><a class="email" href="mailto:selinux@gmail.com" title="Tom London <selinux@gmail.com>"> <span class="fn">Tom London</span></a>
</span></b>
        <pre>Created <span class=""><a href="attachment.cgi?id=72801" name="attach_72801" title="tar.gz included 'dmesg', i915_error_state, etc.">attachment 72801</a> <a href="attachment.cgi?id=72801&action=edit" title="tar.gz included 'dmesg', i915_error_state, etc.">[details]</a></span>
tar.gz included 'dmesg', i915_error_state, etc.

kernel with just the one patch (remove-MI_FLUSH) hangs/crashes under my "cat
big-files >/dev/null" test.

Here is the dmesg spew:

[  178.704031] [drm:i915_hangcheck_hung] *ERROR* Hangcheck timer elapsed... GPU
hung
[  178.704039] [drm] capturing error event; look for more information in
/debug/dri/0/i915_error_state
[  188.704040] [drm:i915_hangcheck_hung] *ERROR* Hangcheck timer elapsed... GPU
hung
[  188.757040] [drm:init_ring_common] *ERROR* render ring initialization failed
ctl 0001f001 head 00003000 tail 00000000 start 00003000
[  190.704040] [drm:i915_hangcheck_hung] *ERROR* Hangcheck timer elapsed... GPU
hung
[  190.704160] [drm:i915_reset] *ERROR* GPU hanging too fast, declaring wedged!
[  190.704163] [drm:i915_reset] *ERROR* Failed to reset chip.
[  201.972860] gnome-shell[1927]: segfault at 230 ip 00007fbcbf78989f sp
00007fff8ae7ac00 error 4 in i965_dri.so[7fbcbf737000+b3000]

Here are the first few lines from i915_error_state:

Time: 1357847009 s 606144 us
PCI ID: 0x2a42
EIR: 0x00000000
IER: 0x02028c53
PGTBL_ER: 0x00000000
CCID: 0x00000000
  fence[0] = 00000000
  fence[1] = 00000000
  fence[2] = 00000000

Hope this helps....</pre>
        </div>
      </p>
      <hr>
      <span>You are receiving this mail because:</span>
      
      <ul>
          <li>You are the QA Contact for the bug.</li>
      </ul>
    </body>
</html>