Bug 101041 - [i965] GPU HANG: ecode 4:0:0x8644f8fe, in chrome [1674], reason: Hang on render ring, action: reset
Summary: [i965] GPU HANG: ecode 4:0:0x8644f8fe, in chrome [1674], reason: Hang on rend...
Status: RESOLVED INVALID
Alias: None
Product: Mesa
Classification: Unclassified
Component: Drivers/DRI/i965 (show other bugs)
Version: unspecified
Hardware: x86-64 (AMD64) Linux (All)
: medium normal
Assignee: Intel 3D Bugs Mailing List
QA Contact: Intel 3D Bugs Mailing List
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2017-05-14 20:59 UTC by Chris Douglass
Modified: 2019-01-17 19:46 UTC (History)
1 user (show)

See Also:
i915 platform: I965GM
i915 features:


Attachments
/sys/class/drm/card0/error (105.45 KB, application/x-bzip)
2017-05-14 20:59 UTC, Chris Douglass
Details
Xorg.0.log (59.51 KB, text/plain)
2017-05-14 21:02 UTC, Chris Douglass
Details
dmesg.log (68.14 KB, text/x-log)
2017-05-14 21:03 UTC, Chris Douglass
Details
intel_error_decode log (1.60 MB, text/x-log)
2017-05-14 21:09 UTC, Chris Douglass
Details

Note You need to log in before you can comment on or make changes to this bug.
Description Chris Douglass 2017-05-14 20:59:10 UTC
Created attachment 131354 [details]
/sys/class/drm/card0/error

I encounter a hang during which X does not respond to key or mouse events and recovery some seconds later. The following messages are from a tail of dmesg.

```
[ 1204.829037] [drm] GPU HANG: ecode 4:0:0x8644f8fe, in chrome [1674], reason: Hang on render ring, action: reset
[ 1204.829040] [drm] GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
[ 1204.829041] [drm] Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel
[ 1204.829042] [drm] drm/i915 developers can then reassign to the right component if it's not a kernel issue.
[ 1204.829043] [drm] The gpu crash dump is required to analyze gpu hangs, so please always attach it.
[ 1204.829044] [drm] GPU crash dump saved to /sys/class/drm/card0/error
[ 1205.136582] drm/i915: Resetting chip after gpu hang
[ 1215.140428] drm/i915: Resetting chip after gpu hang
[ 1413.363513] perf: interrupt took too long (4910 > 4908), lowering kernel.perf_event_max_sample_rate to 40500
[ 1425.134080] drm/i915: Resetting chip after gpu hang
[ 1437.128358] drm/i915: Resetting chip after gpu hang
[ 1449.123365] drm/i915: Resetting chip after gpu hang
[ 1459.143450] drm/i915: Resetting chip after gpu hang
[ 1462.794884] [drm] HPD interrupt storm detected on connector VGA-1: switching from hotplug detection to polling

```

Thinkpad R16

uname -a
Linux thicky 4.9.0-0.bpo.2-rt-amd64 #1 SMP PREEMPT RT Debian 4.9.18-1~bpo8+1 (2017-04-10) x86_64 GNU/Linux
Comment 1 Chris Douglass 2017-05-14 21:02:24 UTC
Created attachment 131355 [details]
Xorg.0.log
Comment 2 Chris Douglass 2017-05-14 21:03:03 UTC
Created attachment 131356 [details]
dmesg.log
Comment 3 Chris Douglass 2017-05-14 21:04:56 UTC
intel_stepping 
Vendor: 0x8086, Device: 0x2a02, Revision: 0x0c (>C0)
render clock: 500 Mhz  sampler clock: 533 Mhz
Comment 4 Chris Douglass 2017-05-14 21:06:23 UTC
intel_reg_checker 
MI_MODE (0x209c): 0x00000040
  (bit 14) OK:   Async Flip Performance mode
  (bit 13) OK:   Flush Performance Mode
  (bit  7) OK:   Vertex Shader Cache Mode
  (bit  6) OK:   Vertex Shader Timer Dispatch Enable
CACHE_MODE_0 (0x2120): 0x00006820
  (bit 15) OK:   Sampler L2 Disable
  (bit  9) PERF: Sampler L2 TLB Prefetch Enable should be set
  (bit  8) OK:   Depth Related Cache Pipelined Flush Disable
  (bit  5) FAIL: STC LRA Eviction Policy must be unset
  (bit  3) OK:   Hierarchical Z Disable
  (bit  0) OK:   Render Cache Operational Flush
CACHE_MODE_1 (0x2124): 0x00000180
  (bit 12) OK:   HIZ LRA Eviction Policy
  (bit 11) OK:   DAP Instruction and State Cache Invalidate
  (bit 10) OK:   Instruction L1 Cache and In-Flight Queue Disable
  (bit  9) OK:   Instruction L2 Cache Fill Buffers Disable
  (bit  4) OK:   Data Disable
  (bit  1) OK:   Instruction and State L2 Cache Disable
  (bit  0) OK:   Instruction and State L1 Cache Disable
3D_CHICKEN (0x2084): 0x00000000
           OK:   chicken bits unset
3D_CHICKEN2 (0x208c): 0x00000000
           OK:   chicken bits unset
ECOSKPD (0x21d0): 0x00000307
           WARN: chicken bits set
Comment 5 Chris Douglass 2017-05-14 21:07:18 UTC
inteltool 
Intel CPU: Family 6, Model f
Intel Northbridge: 8086:2a00 (PM965)
Intel Southbridge: 8086:2811 (unknown)
Comment 6 Chris Douglass 2017-05-14 21:09:00 UTC
Created attachment 131357 [details]
intel_error_decode log
Comment 7 Mark Janes 2017-05-15 18:20:51 UTC
Is there a specific website that triggers this hang?
Comment 8 Chris Douglass 2019-01-17 19:46:45 UTC
I no longer have access to hardware to replicate.


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.