[Intel-gfx] ✗ Fi.CI.IGT: failure for drm/i915: Flush all user surfaces prior to first use (rev2)

[Chris Wilson]

Quoting Patchwork (2019-07-18 14:18:45)
> == Series Details ==
> 
> Series: drm/i915: Flush all user surfaces prior to first use (rev2)
> URL   : https://patchwork.freedesktop.org/series/63871/
> State : failure
> 
> == Summary ==
> 
> CI Bug Log - changes from CI_DRM_6503_full -> Patchwork_13683_full
> ====================================================
> 
> Summary
> -------
> 
>   **FAILURE**
> 
>   Serious unknown changes coming with Patchwork_13683_full absolutely need to be
>   verified manually.
>   
>   If you think the reported changes have nothing to do with the changes
>   introduced in Patchwork_13683_full, please notify your bug team to allow them
>   to document this new failure mode, which will reduce false positives in CI.
> 
>   
> 
> Possible new issues
> -------------------
> 
>   Here are the unknown changes that may have been introduced in Patchwork_13683_full:
> 
> ### IGT changes ###
> 
> #### Possible regressions ####
> 
>   * igt at gem_pwrite@big-cpu-fbr:
>     - shard-iclb:         [PASS][1] -> [FAIL][2] +11 similar issues
>    [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6503/shard-iclb3/igt@gem_pwrite@big-cpu-fbr.html
>    [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_13683/shard-iclb6/igt@gem_pwrite@big-cpu-fbr.html

Oh dear, icl is behaving strangely. Yay for finding a new feature.
-Chris