Bug 41184 - glxgears hang GPU on Sandy Bridge
Summary: glxgears hang GPU on Sandy Bridge
Status: RESOLVED FIXED
Alias: None
Product: Mesa
Classification: Unclassified
Component: Drivers/DRI/i965 (show other bugs)
Version: 7.11
Hardware: x86-64 (AMD64) Linux (All)
: medium normal
Assignee: Ian Romanick
QA Contact:
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2011-09-25 08:20 UTC by Lukas Hejtmanek
Modified: 2012-05-04 09:06 UTC (History)
2 users (show)

See Also:
i915 platform:
i915 features:

Attachments
i915_error_state (2.14 MB, text/plain)
2011-09-25 08:20 UTC, Lukas Hejtmanek 		Details
View All

Description Lukas Hejtmanek 2011-09-25 08:20:05 UTC 
Created attachment 51590 [details]
i915_error_state

Running glxgears for more than 10 secs causes GPU hang:
[125537.901951] [drm:i915_hangcheck_elapsed] *ERROR* Hangcheck timer elapsed... GPU hung
[125537.901959] [drm] capturing error event; look for more information in /debug/dri/0/i915_error_state
[125537.917763] [drm:i915_wait_request] *ERROR* i915_wait_request returns -11 (awaiting 3472039 at 3472038, next 3472041)

I use kernel 3.1.0-rc7+. I got Mesa 7.11 from Ubuntu/unstable distro as well as glxgears. 

This bug seems to be reproducible.

I attached i915_error_state.
Comment 1 Joel 2011-10-26 00:51:47 UTC 
I cannot reproduce this using current master (commit 20a20c781ac2143e92807fa8dfab086a5b7c1d53 ), 

This is on Fedora
kernel 3.1.0-0.rc10.git0.1.fc16.x86_64
intel_drv.so from git commit a18f559961135fa288dda3b94207abb0b6d4d302
Comment 2 Lukas Hejtmanek 2011-10-26 01:35:48 UTC 
(In reply to comment #1)
> I cannot reproduce this using current master (commit
> 20a20c781ac2143e92807fa8dfab086a5b7c1d53 ), 

this is commit of what? MESA?
Comment 3 Joel 2011-10-27 08:14:59 UTC 
Sorry. Yes, current mesa master.
Comment 4 Kenneth Graunke 2011-11-16 13:46:15 UTC 
Hi Lukas,

We fixed this in Mesa master with

commit 3cc0a7be23ab603ed40d602595f673a44e079885
Author: Kenneth Graunke <kenneth@whitecape.org>
Date:   Fri Oct 21 01:03:37 2011 -0700

    i965: Apply post-sync non-zero workaround to homebrew workaround.
    
    In commit 3e5d3626, Eric added a homebrew workaround to fix GPU hangs in
    the Mesa "engine" demo and oglc's api-texcoord test.
    
    Unfortunately, his PIPE_CONTROL contains a Depth Stall, which
    necessitates the post-sync non-zero workaround,
    
    Fixes GPU hangs in Civilization 4, PlaneShift, and 3DMMES.
    Hopefully Heroes of Newerth as well, though I haven't tested that.
    
    NOTE: This is candidate for the 7.11 branch.
    
    Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=40324
    Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=41096
    Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
    Reviewed-and-tested-by: Eric Anholt <eric@anholt.net>

Or in the 7.11 branch as commit 439628318bfd4596d0d8129a0792d2c3ea849bb7 (which will be released as 7.11.1 shortly.)

Could you grab either the latest 7.11 branch or master and see if that fixes the issue for you?  Thanks, and sorry for the trouble.
Comment 5 Kenneth Graunke 2012-05-04 09:06:46 UTC 
No response, closing as fixed (since I claimed to have fixed it a while ago).

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.