Bug 106154 - GPU hangs according to dmesg
Summary: GPU hangs according to dmesg
Status: CLOSED WORKSFORME
Alias: None
Product: DRI
Classification: Unclassified
Component: DRM/Intel (show other bugs)
Version: unspecified
Hardware: x86-64 (AMD64) Linux (All)
: medium normal
Assignee: Intel GFX Bugs mailing list
QA Contact: Intel GFX Bugs mailing list
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2018-04-20 15:44 UTC by Taavetti
Modified: 2018-05-04 12:47 UTC (History)
1 user (show)

See Also:
i915 platform:
i915 features: GPU hang


Attachments

Description Taavetti 2018-04-20 15:44:39 UTC
Laptop freezes when under medium load
Desktop enviroonment is Openbox
I'm currently using a Lenovo Thinkpad T420s


--Dmesg output--
[  147.853631] random: crng init done
[ 1514.691461] perf: interrupt took too long (2579 > 2500), lowering kernel.perf_event_max_sample_rate to 77500
[ 1925.547873] perf: interrupt took too long (3300 > 3223), lowering kernel.perf_event_max_sample_rate to 60500
[ 2607.084105] perf: interrupt took too long (4196 > 4125), lowering kernel.perf_event_max_sample_rate to 47500
[ 2846.913123] perf: interrupt took too long (5258 > 5245), lowering kernel.perf_event_max_sample_rate to 38000
[ 2965.549710] [drm] GPU HANG: ecode 6:0:0x85fffff8, in java [14042], reason: Hang on render ring, action: reset
[ 2965.549711] [drm] GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
[ 2965.549712] [drm] Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel
[ 2965.549712] [drm] drm/i915 developers can then reassign to the right component if it's not a kernel issue.
[ 2965.549713] [drm] The gpu crash dump is required to analyze gpu hangs, so please always attach it.
[ 2965.549713] [drm] GPU crash dump saved to /sys/class/drm/card0/error
[ 2965.549756] drm/i915: Resetting chip after gpu hang
[ 3186.985306] perf: interrupt took too long (6582 > 6572), lowering kernel.perf_event_max_sample_rate to 30250
[ 3204.497050] drm/i915: Resetting chip after gpu hang


--Gpu crash dump--
http://pasted.co/d60f3fed
Comment 1 Jani Saarinen 2018-04-20 19:59:24 UTC
Can you test with drm-tip: https://cgit.freedesktop.org/drm-tip?
Also send whole dmesg with attaching the “dmesg” output taken with drm.debug=0xe.
Comment 2 Jani Saarinen 2018-05-04 12:47:03 UTC
Closing, please re-open if occurs again.


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.