Bug 94509 - GPU HANG: ecode 8:0:0x85dffffb, in X [1307], reason: Ring hung, action: reset
Summary: GPU HANG: ecode 8:0:0x85dffffb, in X [1307], reason: Ring hung, action: reset
Status: CLOSED INVALID
Alias: None
Product: DRI
Classification: Unclassified
Component: DRM/Intel (show other bugs)
Version: unspecified
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: 2016-03-12 11:47 UTC by Per Jessen
Modified: 2017-02-22 08:18 UTC (History)
2 users (show)

See Also:
i915 platform: BSW/CHT
i915 features: GEM/Other

Attachments
gpu crash dump (413.36 KB, text/plain)
2016-03-12 11:47 UTC, Per Jessen 		no flags Details
The gpu crash dump cuncompressed (2.73 MB, text/plain)
2016-04-21 06:33 UTC, Per Jessen 		no flags Details
View All

Description Per Jessen 2016-03-12 11:47:04 UTC 
Created attachment 122248 [details]
gpu crash dump

[  950.752506] [drm] stuck on render ring
[  950.771990] [drm] GPU HANG: ecode 8:0:0x85dffffb, in X [1307], reason: Ring hung, action: reset
[  950.771999] [drm] GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
[  950.772001] [drm] Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel
[  950.772003] [drm] drm/i915 developers can then reassign to the right component if it's not a kernel issue.
[  950.772004] [drm] The gpu crash dump is required to analyze gpu hangs, so please always attach it.
[  950.772007] [drm] GPU crash dump saved to /sys/class/drm/card0/error
[  950.774335] drm/i915: Resetting chip after gpu hang
Comment 1 an77vo 2016-04-21 04:57:17 UTC 
Comment on attachment 122248 [details]
gpu crash dump

@Per Jessen
Would you send the "gpu crash dump"-file as uncompressed textformat?
Comment 2 Per Jessen 2016-04-21 06:33:11 UTC 
Created attachment 123107 [details]
The gpu crash dump cuncompressed

fyi, the original file is gone, but I took attachment#122248 [details] and decompressed it, seems to have worked.
Comment 3 yann 2016-09-05 10:54:02 UTC 
(In reply to Per Jessen from comment #2)
> Created attachment 123107 [details]
> The gpu crash dump cuncompressed
> 
> fyi, the original file is gone, but I took attachment#122248 [details] and
> decompressed it, seems to have worked.

from your gpu crash dump, one can note that there is an error: 
ERROR: 0x00000001
    TLB page fault error (GTT entry not valid)

Can you upgrade your kernel to benefit of all work done so far and see if you are reproducing ? If this is still the case, please attach fresh gpu crash dump as well as dmesg.
Comment 4 Ricardo 2017-02-21 16:56:18 UTC 
@Per Jessen can you please provide more information requested in pervious comment, if there is no response in 30 days the bug will be closed.
Comment 5 Per Jessen 2017-02-22 08:02:58 UTC 
(In reply to Ricardo from comment #4)
> @Per Jessen can you please provide more information requested in pervious
> comment, if there is no response in 30 days the bug will be closed.

I am closing this as "invalid", I don't have the time to play with this hardware currently.

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.