Bug 97831 - IvyBridge, [drm] GPU HANG: ecode 7:0:0x85fffff8, in chrome [23323], reason: Engine(s) hung, action: reset
Summary: IvyBridge, [drm] GPU HANG: ecode 7:0:0x85fffff8, in chrome [23323], reason: E...
Status: CLOSED FIXED
Alias: None
Product: Mesa
Classification: Unclassified
Component: Drivers/DRI/i915 (show other bugs)
Version: 12.0
Hardware: Other All
: medium normal
Assignee: Ian Romanick
QA Contact:
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2016-09-16 09:39 UTC by Tod Jackson
Modified: 2016-10-14 07:36 UTC (History)
1 user (show)

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


Attachments
gpu crash dump 1 (2.11 MB, text/plain)
2016-09-16 09:39 UTC, Tod Jackson
Details
dmesg 1 (63.69 KB, text/plain)
2016-09-16 09:44 UTC, Tod Jackson
Details

Description Tod Jackson 2016-09-16 09:39:22 UTC
Created attachment 126570 [details]
gpu crash dump 1

I play a Flash game in Chrome all the time (League of Angels II) but this is the first time it's hung the GPU. Upgraded to kernel 4.7.4 this morning. Crash dump is attached.

libdrm 2.4.70
xorg-server 1.18.4
mesa 12.0.2
xf86-video-intel git master, SNA DRI 2 with TearFree enabled, Compton with --backend glx running also.

Temperature was at a reasonable level.
Comment 1 Tod Jackson 2016-09-16 09:44:24 UTC
Created attachment 126571 [details]
dmesg 1
Comment 2 yann 2016-09-16 09:57:53 UTC
Kernel: 4.7.4
Platform: Ivybridge (pci id: 0x0166, revision: 0x09, subsystem: 1043:10fd)
Mesa:12.0.2

Assigning to Mesa product (please let me know if I am mistaken with this GPU Hang).

From this error dump, hung is happening in render ring batch with active head at 0x0f1eebb4, with 0x7a000003 (PIPE_CONTROL) as IPEHR.

Batch extract (around 0x0f1eebb4):

0x0f1eeb84:      0x7b000005: 3DPRIMITIVE:
0x0f1eeb88:      0x00000006:    tri fan sequential
0x0f1eeb8c:      0x00000004:    vertex count
0x0f1eeb90:      0x00000000:    start vertex
0x0f1eeb94:      0x00000001:    instance count
0x0f1eeb98:      0x00000000:    start instance
0x0f1eeb9c:      0x00000000:    index bias
0x0f1eeba0:      0x7a000003: PIPE_CONTROL
0x0f1eeba4:      0x00101001:    no write, cs stall, render target cache flush, depth cache flush,
0x0f1eeba8:      0x00000000:    destination address
0x0f1eebac:      0x00000000:    immediate dword low
0x0f1eebb0:      0x00000000:    immediate dword high
0x0f1eebb4:      0x7a000003: PIPE_CONTROL
0x0f1eebb8:      0x00000c10:    no write, instruction cache invalidate, texture cache invalidate, vf fetch invalidate,
0x0f1eebbc:      0x00000000:    destination address
0x0f1eebc0:      0x00000000:    immediate dword low
0x0f1eebc4:      0x00000000:    immediate dword high
0x0f1eebc8:      0x7a000003: PIPE_CONTROL
0x0f1eebcc:      0x00101001:    no write, cs stall, render target cache flush, depth cache flush,
0x0f1eebd0:      0x00000000:    destination address
0x0f1eebd4:      0x00000000:    immediate dword low
0x0f1eebd8:      0x00000000:    immediate dword high
Comment 3 Tod Jackson 2016-10-14 06:23:28 UTC
There was a Mesa update to 12.0.3 right after I posted this and I haven't seen the issue (or any other GPU hang) since then. I'll close this as fixed.


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.