[Bug 104479] [CI] igt at kms_cursor_legacy@all-pipes-single-move - Incomplete - INFO: task kswapd0:52 blocked for more than 60 seconds

[bugzilla-daemon at freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=104479

--- Comment #1 from Chris Wilson <chris at chris-wilson.co.uk> ---
(In reply to Marta Löfstedt from comment #0)
> https://intel-gfx-ci.01.org/tree/drm-tip/IGT_4109/shard-glkb6/
> igt at kms_cursor_legacy@all-pipes-single-move.html
> 
> <7>[  115.915180] [drm:gen9_set_dc_state [i915]] Setting DC state from 00 to
> 01
> <3>[  123.918946] INFO: task kswapd0:52 blocked for more than 60 seconds.
> <3>[  123.918960]       Tainted: G     U          
> 4.15.0-rc6-CI-CI_DRM_3589+ #1
> <3>[  123.918963] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs"
> disables this message.
> <6>[  123.918967] kswapd0         D    0    52      2 0x80000000
> <4>[  123.918973] Call Trace:
> <4>[  123.918985]  ? __schedule+0x3c3/0xaf0
> <4>[  123.918994]  schedule+0x37/0x90
> <4>[  123.919000]  io_schedule+0xd/0x30
> <4>[  123.919005]  __lock_page+0x107/0x130
> <4>[  123.919011]  ? add_to_page_cache_lru+0xc0/0xc0
> <4>[  123.919019]  deferred_split_scan+0x25a/0x2b0
> <4>[  123.919027]  shrink_slab.part.17+0x201/0x5d0
> <4>[  123.919041]  shrink_node+0x2fd/0x310
> <4>[  123.919050]  kswapd+0x31c/0x910
> <4>[  123.919064]  kthread+0xfb/0x130
> <4>[  123.919067]  ? mem_cgroup_shrink_node+0x300/0x300
> <4>[  123.919070]  ? _kthread_create_on_node+0x30/0x30
> <4>[  123.919075]  ret_from_fork+0x24/0x30
...
> Since igt at gem_tiled_swapping@non-threaded was run before this test, maybe
> this is related to bug 104218.

That seems very likely, the same waiting for deferred_split_scan::lock_page
with nothing on the other cpus that would appear to be keeping a page locked.

-- 
You are receiving this mail because:
You are the QA Contact for the bug.
You are on the CC list for the bug.
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/intel-gfx-bugs/attachments/20180103/1787de4f/attachment.html>