Bug 64661 - [HSW]I-G-T [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout when run gem_fence_thrash/bo-write-verify-threaded-x
Summary: [HSW]I-G-T [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal time...
Status: CLOSED FIXED
Alias: None
Product: DRI
Classification: Unclassified
Component: DRM/Intel (show other bugs)
Version: unspecified
Hardware: All Linux (All)
: medium normal
Assignee: Intel GFX Bugs mailing list
QA Contact: Intel GFX Bugs mailing list
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2013-05-16 06:04 UTC by lu hua
Modified: 2016-10-03 09:11 UTC (History)
1 user (show)

See Also:
i915 platform:
i915 features:

Attachments
dmesg (125.24 KB, text/plain)
2013-05-16 06:04 UTC, lu hua 		no flags Details
View All

Description lu hua 2013-05-16 06:04:42 UTC 
Created attachment 79378 [details]
dmesg

System Environment:
--------------------------
Arch:             x86_64
Platform:         Haswell
Kernel:	(drm-intel-fixes) e6c6992522d3f74341f032bda2c76266057cc53b

Bug detailed description:
-------------------------
It happens on haswell with drm-intel-fixes kernel and drm-intel-next-queued kernel.
It happens 3 times in 5 runs.
igt/gem_fence_thrash/bo-write-verify-threaded-y also has this issue.

output:
write-verify: threads 64, fences 32, tiling 1, surfaces per thread 2
write-verify: threads 160, fences 32, tiling 1, surfaces per thread 2
write-verify: threads 320, fences 32, tiling 1, surfaces per thread 2
write-verify: threads 640, fences 32, tiling 1, surfaces per thread 2

ERROR in dmesg:
<3>[  841.280866] [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout (has irq: 1)!
<3>[  841.280916] [drm:intel_dp_aux_ch] *ERROR* dp_aux_ch not done status 0xa145004a
<3>[  863.359327] [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout (has irq: 1)!
<3>[  867.474189] [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout (has irq: 1)!
<3>[  878.394119] [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout (has irq: 1)!
<3>[  881.852162] [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout (has irq: 1)!
<3>[  889.526997] [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout (has irq: 1)!
<3>[  892.958625] [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout (has irq: 1)!
<3>[  900.478867] [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout (has irq: 1)!
<3>[  904.527499] [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout (has irq: 1)!
<3>[  904.542026] [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout (has irq: 1)!
<3>[  907.930553] [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout (has irq: 1)!
<3>[  934.148787] [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout (has irq: 1)!
<3>[  934.149825] [drm:intel_dp_aux_ch] *ERROR* dp_aux_ch not done status 0xa145004a
<3>[  937.528233] [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout (has irq: 1)!
<3>[  940.999809] [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout (has irq: 1)!
<3>[  941.030577] [drm:intel_dp_aux_wait_done] *ERROR* dp aux hw did not signal timeout (has irq: 1)!

Reproduce steps:
----------------
1. ./gem_fence_thrash --run-subtest bo-write-verify-threaded-x
2. dmesg -r | egrep "<[1-6]>" |grep drm
Comment 1 Imre Deak 2013-05-16 07:26:18 UTC 
This may be a duplicate of Bug 64133. Could you check if the 'fix false timeouts due to higher scheduling latencies' patch there gets rid of the problem?
Comment 2 lu hua 2013-05-16 09:00:42 UTC 
(In reply to comment #1)
> This may be a duplicate of Bug 64133. Could you check if the 'fix false
> timeouts due to higher scheduling latencies' patch there gets rid of the
> problem?

Test with the patch 'fix false timeouts due to higher scheduling latencies', This issue goes away. I run it 5 cycles, It works well.
Comment 3 Imre Deak 2013-05-16 09:21:37 UTC 
(In reply to comment #2)
> (In reply to comment #1)
> > This may be a duplicate of Bug 64133. Could you check if the 'fix false
> > timeouts due to higher scheduling latencies' patch there gets rid of the
> > problem?
> 
> Test with the patch 'fix false timeouts due to higher scheduling latencies',
> This issue goes away. I run it 5 cycles, It works well.

Thanks. Setting as a duplicate based on this.

*** This bug has been marked as a duplicate of bug 64133 ***
Comment 4 Jari Tahvanainen 2016-10-03 09:11:34 UTC 
Closing as duplicate of Closed+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.