Bug 96323 - [SKL] GPU HANG: ecode 9:0:0x84dffff8, in Xorg [902], reason: Ring hung, action: reset
Summary: [SKL] GPU HANG: ecode 9:0:0x84dffff8, in Xorg [902], reason: Ring hung, actio...
Status: CLOSED FIXED
Alias: None
Product: Mesa
Classification: Unclassified
Component: Drivers/DRI/i965 (show other bugs)
Version: 11.2
Hardware: Other Linux (All)
: medium normal
Assignee: Ian Romanick
QA Contact:
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2016-06-02 12:13 UTC by CircleCode
Modified: 2016-11-10 10:45 UTC (History)
2 users (show)

See Also:
i915 platform: SKL
i915 features: GPU hang


Attachments
gpu crash dump (377.10 KB, text/plain)
2016-06-02 12:13 UTC, CircleCode
Details

Description CircleCode 2016-06-02 12:13:23 UTC
Created attachment 124265 [details]
gpu crash dump

Bug description:

the screen hang up for ~15 seconds, then came back.

journalctl extract:

juin 02 13:59:05 R2D2-X1 kernel: [drm] stuck on render ring
juin 02 13:59:05 R2D2-X1 kernel: [drm] GPU HANG: ecode 9:0:0x84dffff8, in Xorg [902], reason: Ring hung, action: reset
juin 02 13:59:05 R2D2-X1 kernel: [drm] GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.
juin 02 13:59:05 R2D2-X1 kernel: [drm] Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel
juin 02 13:59:05 R2D2-X1 kernel: [drm] drm/i915 developers can then reassign to the right component if it's not a kernel issue.
juin 02 13:59:05 R2D2-X1 kernel: [drm] The gpu crash dump is required to analyze gpu hangs, so please always attach it.
juin 02 13:59:05 R2D2-X1 kernel: [drm] GPU crash dump saved to /sys/class/drm/card0/error
juin 02 13:59:05 R2D2-X1 kernel: drm/i915: Resetting chip after gpu hang

System environment:

-- chipset: Intel(R) Core(TM) i7-6600U CPU @ 2.60GHz
-- system architecture: 64-bit
-- xf86-video-intel: xf86-video-intel 1:2.99.917+654+ga508b11-1
-- xserver: xorg-server 1.18.3-1
-- mesa: mesa 11.2.2-1
-- libdrm: libdrm 2.4.68-1
-- kernel: Linux R2D2-X1 4.5.4-1-ARCH #1 SMP PREEMPT Wed May 11 22:21:28 CEST 2016 x86_64 GNU/Linux
-- Linux distribution: arch linux
-- Machine or mobo model: Thinkpad X1 carbon (model 20FB)
-- Display connector: none (integrated screen)
Comment 1 CircleCode 2016-06-02 12:14:20 UTC
maybe related to #95145, but in my case, I'm not using eclipse, but phpstorm (although it is also java based), and was not able to reproduce it for now
Comment 2 yann 2016-09-01 12:57:38 UTC
Assigning to Mesa product.

From this error dump, hung is happening in render ring batch with active head
at 0xfe1ee994, with 0x7b000005 (3DPRIMITIVE) as IPEHR.

Batch extract (around 0xfe1ee994):

0xfe1ee974:      0x78090005: 3DSTATE_VERTEX_ELEMENTS
0xfe1ee978:      0x02000000:    buffer 0: invalid, type 0x0000, src offset 0x0000 bytes
0xfe1ee97c:      0x22220000:    (0.0, 0.0, 0.0, 0.0), dst offset 0x00 bytes
0xfe1ee980:      0x02f60000:    buffer 0: invalid, type 0x00f6, src offset 0x0000 bytes
0xfe1ee984:      0x11230000:    (X, Y, 0.0, 1.0), dst offset 0x00 bytes
0xfe1ee988:      0x02f60004:    buffer 0: invalid, type 0x00f6, src offset 0x0004 bytes
0xfe1ee98c:      0x11230000:    (X, Y, 0.0, 1.0), dst offset 0x00 bytes
Bad length 7 in (null), expected 6-6
0xfe1ee990:      0x7b000005: 3DPRIMITIVE: fail sequential
0xfe1ee994:      0x00000000:    vertex count
0xfe1ee998:      0x00000003:    start vertex
0xfe1ee99c:      0x00000018:    instance count
0xfe1ee9a0:      0x00000001:    start instance
0xfe1ee9a4:      0x00000000:    index bias
0xfe1ee9a8:      0x00000000: MI_NOOP
0xfe1ee9ac:      0x05000000: MI_BATCH_BUFFER_END
Comment 3 yann 2016-11-04 15:07:43 UTC
Please test a new version of Mesa (12 or 13) and mark as REOPENED
if you can reproduce and RESOLVED/* if you cannot reproduce.
Comment 4 CircleCode 2016-11-10 10:42:17 UTC
this has not happened to me anymore since several time.

current config is
-- chipset: Intel(R) Core(TM) i7-6600U CPU @ 2.60GHz
-- system architecture: 64-bit
-- xf86-video-intel: xf86-video-intel 1:2.99.917+654+ga508b11-1
-- xserver: xorg-server 1.18.4-1
-- mesa: mesa 13.0.0-1
-- libdrm: libdrm 2.4.71-1
-- kernel: Linux R2D2-X1 4.8.6-1-ARCH #1 SMP PREEMPT Mon Oct 31 18:51:30 CET 2016 x86_64 GNU/Linux
-- Linux distribution: arch linux
-- Machine or mobo model: Thinkpad X1 carbon (model 20FB)
-- Display connector: none (integrated screen)

Since I was not able to detect when this occurs exactly, I was not able to reproduce it systematically so I can not confirm it is really resolved, but I won't oppose if you consider it is resolved.
Comment 5 yann 2016-11-10 10:45:11 UTC
(In reply to CircleCode from comment #4)
> this has not happened to me anymore since several time.
> 
> current config is
> -- chipset: Intel(R) Core(TM) i7-6600U CPU @ 2.60GHz
> -- system architecture: 64-bit
> -- xf86-video-intel: xf86-video-intel 1:2.99.917+654+ga508b11-1
> -- xserver: xorg-server 1.18.4-1
> -- mesa: mesa 13.0.0-1
> -- libdrm: libdrm 2.4.71-1
> -- kernel: Linux R2D2-X1 4.8.6-1-ARCH #1 SMP PREEMPT Mon Oct 31 18:51:30 CET
> 2016 x86_64 GNU/Linux
> -- Linux distribution: arch linux
> -- Machine or mobo model: Thinkpad X1 carbon (model 20FB)
> -- Display connector: none (integrated screen)
> 
> Since I was not able to detect when this occurs exactly, I was not able to
> reproduce it systematically so I can not confirm it is really resolved, but
> I won't oppose if you consider it is resolved.

Thanks for your feedback. Then closing it, but if it occurs again please reopen it


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.