Bug 107128 - [CI] SKL-IOMMU igt@drv_selftest@live_coherency failed with error -5
Summary: [CI] SKL-IOMMU igt@drv_selftest@live_coherency failed with error -5
Status: CLOSED FIXED
Alias: None
Product: DRI
Classification: Unclassified
Component: DRM/Intel (show other bugs)
Version: DRI git
Hardware: Other All
: medium normal
Assignee: Intel GFX Bugs mailing list
QA Contact: Intel GFX Bugs mailing list
URL:
Whiteboard:
Keywords:
Depends on:
Blocks:
 
Reported: 2018-07-05 14:18 UTC by Tomi Sarvela
Modified: 2018-07-10 11:53 UTC (History)
1 user (show)

See Also:
i915 platform:
i915 features:


Attachments

Description Tomi Sarvela 2018-07-05 14:18:58 UTC
CI hosts are starting to run i915 selftests, and this bug is part of the series "Initial findings"

On SKL with IOMMU not disabled, selftest igt@drv_selftest@live_coherency fails with message

[  387.755935] i915 0000:00:02.0: GPU recovery failed
[  387.798444] Failed to set value[0/1] in object using gpu, err=-5
[  387.798468] i915/i915_gem_coherency_live_selftests: igt_gem_coherency failed with error -5
[  387.900210] i915: probe of 0000:00:02.0 failed with error -5

Full trace at

https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_4432/fi-skl-iommu/igt@drv_selftest@live_coherency.html
Comment 1 Chris Wilson 2018-07-05 14:21:12 UTC
Rotflmao.

I suppose we need to preface such tests with "is the GPU irrevocably broken?"
Comment 2 Chris Wilson 2018-07-06 15:21:15 UTC
commit b5f6e53d4cd58043e2c4e1b60fd446924cf56cbe
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date:   Fri Jul 6 07:53:08 2018 +0100

    drm/i915/selftests: Skip using the GPU if wedged
    
    If the GPU is irrecoverably broken, we can not use it to dirty memory
    and check for cache coherency with the CPU. All we can do is simply skip
    over the GPU subtests and focus on the CPU domains (WC, WB) cache
    management.
    
    Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107127
    Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
    Reviewed-by: Matthew Auld <matthew.auld@intel.com>
    Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-3-c
hris@chris-wilson.co.uk
Comment 3 Martin Peres 2018-07-10 11:53:58 UTC
(In reply to Chris Wilson from comment #2)
> commit b5f6e53d4cd58043e2c4e1b60fd446924cf56cbe
> Author: Chris Wilson <chris@chris-wilson.co.uk>
> Date:   Fri Jul 6 07:53:08 2018 +0100
> 
>     drm/i915/selftests: Skip using the GPU if wedged
>     
>     If the GPU is irrecoverably broken, we can not use it to dirty memory
>     and check for cache coherency with the CPU. All we can do is simply skip
>     over the GPU subtests and focus on the CPU domains (WC, WB) cache
>     management.
>     
>     Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107127
>     Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
>     Reviewed-by: Matthew Auld <matthew.auld@intel.com>
>     Link:
> https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-3-c
> hris@chris-wilson.co.uk

It did the trick, thanks!


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.