Bug 89936 - [BSW Regression]Run Cairo Performance case will result GPU HANG: ecode 8:0:0x85dffffb, in X [4370], reason: Ring hung
Summary: [BSW Regression]Run Cairo Performance case will result GPU HANG: ecode 8:0:0x...
Status: CLOSED FIXED
Alias: None
Product: DRI
Classification: Unclassified
Component: DRM/Intel (show other bugs)
Version: unspecified
Hardware: Other All
: high major
Assignee: Intel GFX Bugs mailing list
QA Contact: Intel GFX Bugs mailing list
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2015-04-07 11:31 UTC by wendy.wang
Modified: 2017-10-06 14:30 UTC (History)
3 users (show)

See Also:
i915 platform:
i915 features:


Attachments
GPU_HANG_dmesg_cairo_case (123.46 KB, text/plain)
2015-04-07 11:31 UTC, wendy.wang
no flags Details

Description wendy.wang 2015-04-07 11:31:34 UTC
Created attachment 114914 [details]
GPU_HANG_dmesg_cairo_case

System Environment:       
--------------------
Failed Platform: Braswell
Kernel Regression: Yes, 
but cannot bisect because of the bug between the good and bad commit.
89350 [BSW bisected] kernel fails to start up

Kernel:
Good commit: drm-intel-nightly branch 2015-02-10 kernel
Bad commit: drm-intel-nightly branch from 2015-03-10 to the latest kernel commit

Description:
Run cairo performance, check dmesg will see GPU HANG error message:
GPU HANG: ecode 8:0:0x85dffffb, in X [4370], reason: Ring hung, action: reset
[  119.815835] [drm:i915_reset_and_wakeup] resetting chip
[  119.815956] [drm:i915_context_is_banned [i915]] *ERROR* gpu hanging too fast, banning!
[  119.817187] drm/i915: Resetting chip after gpu hang

Dmesg file has been attached.

Reproduce Steps:
1. cd /home/cairo/perf 
2. vblank_mode=0 CAIRO_TEST_TARGET=xlib ./cairo-perf-trace /home/cairo-traces/benchmark/firefox-chalkboard.trace
Comment 1 Ander Conselvan de Oliveira 2015-06-02 08:12:48 UTC
Error state is missing. (/sys/class/drm/card0/error)
Comment 2 wendy.wang 2015-06-17 01:44:02 UTC
This issue cannot reproduce in recently GFX SW stack on BSW test machine:

Libdrm:		(master)libdrm-2.4.61-13-g97be70b45eccc37e98a1cecf360593f36956ea42
 Mesa:		(master)9538902c4f0e94e57228f939489d31676c43a778
 Xserver:		(master)xorg-server-1.17.0-158-gfa12f2c150b2f50de9dac4a2b09265f13af353af
 Xf86_video_intel:		(master)2.99.917-342-g46d74edf991f315319236ba81c6e357e0cb0dddc
 Cairo:		(master)2cf2d8e340a325adb205baf8e4bd64e1d1858008
 Libva:		(master)50d936cb527ba6da82ff9ee482f64e1ac070e1df
 Libva_intel_driver:		(master)d0c22df7094788a58d3282a2c25483d26a3cca54
 Kernel:   (drm-intel-nightly)d4f412886ec9694658ab17092c3f70569a0405f9

so close this issue as fixed.
Comment 3 Elizabeth 2017-10-06 14:30:41 UTC
Closing old verified.


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.