Bug 100521 - [drm] GPU HANG: ecode 7:0:0xf3cffffe, in opera-developer [2458], reason: Hang on render ring, action: reset
Summary: [drm] GPU HANG: ecode 7:0:0xf3cffffe, in opera-developer [2458], reason: Hang...
Status: CLOSED DUPLICATE of bug 100181
Alias: None
Product: DRI
Classification: Unclassified
Component: DRM/Intel (show other bugs)
Version: XOrg git
Hardware: Other All
: medium normal
Assignee: Intel GFX Bugs mailing list
QA Contact: Intel GFX Bugs mailing list
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2017-03-31 19:32 UTC by mikhail.v.gavrilov
Modified: 2017-07-24 23:15 UTC (History)
1 user (show)

See Also:
i915 platform:
i915 features:


Attachments
dmesg (117.97 KB, text/plain)
2017-03-31 19:32 UTC, mikhail.v.gavrilov
no flags Details
/sys/class/drm/card0/error (40.52 KB, text/plain)
2017-03-31 19:33 UTC, mikhail.v.gavrilov
no flags Details
lspci (27.52 KB, text/plain)
2017-03-31 19:33 UTC, mikhail.v.gavrilov
no flags Details
lshw (30.41 KB, text/plain)
2017-03-31 19:33 UTC, mikhail.v.gavrilov
no flags Details

Description mikhail.v.gavrilov 2017-03-31 19:32:38 UTC
Created attachment 130624 [details]
dmesg

[38795.987195] [drm] GPU HANG: ecode 7:0:0xf3cffffe, in opera-developer [2458], reason: Hang on render ring, action: reset
[38795.987287] [drm] GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
[38795.987290] [drm] Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel
[38795.987292] [drm] drm/i915 developers can then reassign to the right component if it's not a kernel issue.
[38795.987294] [drm] The gpu crash dump is required to analyze gpu hangs, so please always attach it.
[38795.987296] [drm] GPU crash dump saved to /sys/class/drm/card0/error
[38795.987891] drm/i915: Resetting chip after gpu hang
[38804.046176] drm/i915: Resetting chip after gpu hang
[38812.046676] drm/i915: Resetting chip after gpu hang
[38822.031184] drm/i915: Resetting chip after gpu hang
[38830.031712] drm/i915: Resetting chip after gpu hang
[38838.032212] drm/i915: Resetting chip after gpu hang
[38846.032608] drm/i915: Resetting chip after gpu hang
[38854.033169] drm/i915: Resetting chip after gpu hang
[38864.017723] drm/i915: Resetting chip after gpu hang
Comment 1 mikhail.v.gavrilov 2017-03-31 19:33:15 UTC
Created attachment 130625 [details]
/sys/class/drm/card0/error
Comment 2 mikhail.v.gavrilov 2017-03-31 19:33:26 UTC
Created attachment 130626 [details]
lspci
Comment 3 mikhail.v.gavrilov 2017-03-31 19:33:38 UTC
Created attachment 130627 [details]
lshw
Comment 4 mikhail.v.gavrilov 2017-03-31 19:35:10 UTC
Why recent times I see very often GPU HANG which I never seen before?
Comment 5 mikhail.v.gavrilov 2017-03-31 19:36:00 UTC
And in which kernel version it will be fixed?
Comment 6 Chris Wilson 2017-03-31 19:40:12 UTC
commit 5d4bac5503fcc67dd7999571e243cee49371aef7
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date:   Wed Mar 22 20:59:30 2017 +0000

    drm/i915: Restore marking context objects as dirty on pinning

v4.11. The fix is in a pull request to Linus, it will be in place before v4.11 is released.

*** This bug has been marked as a duplicate of bug 100181 ***


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.