[Bug 110848] Everything using GPU gets stuck after running+killing parallel Media loads (after running 3D benchmarks)

[bugzilla-daemon at freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=110848

--- Comment #29 from Chris Wilson <chris at chris-wilson.co.uk> ---
This is the only process of interest that is active

[ 3810.865923] h264parse0:sink R  running task        0 10012      1 0x00004004
[ 3810.865928] Call Trace:
[ 3810.865931]  ? mark_held_locks+0x49/0x70
[ 3810.865936]  ? trace_hardirqs_on_thunk+0x1a/0x1c
[ 3810.865939]  ? lockdep_hardirqs_on+0xeb/0x180
[ 3810.865943]  ? trace_hardirqs_on_thunk+0x1a/0x1c
[ 3810.865950]  ? retint_kernel+0x2b/0x2b
[ 3810.866009]  ? i915_gem_evict_something+0x2df/0x4e0 [i915]
[ 3810.866054]  ? i915_gem_evict_something+0x2fc/0x4e0 [i915]
[ 3810.866105]  ? i915_gem_gtt_insert+0x1ce/0x270 [i915]
[ 3810.866152]  ? __i915_vma_do_pin+0x40c/0x530 [i915]
[ 3810.866200]  ? i915_gem_object_ggtt_pin+0x11f/0x1e0 [i915]
[ 3810.866241]  ? i915_gem_fault+0x291/0x6d0 [i915]
[ 3810.866245]  ? __lock_acquire+0x2bf/0x22e0
[ 3810.866255]  ? __do_fault+0x31/0xb0
[ 3810.866262]  ? __handle_mm_fault+0x9ab/0xfc0
[ 3810.866274]  ? handle_mm_fault+0x15a/0x350
[ 3810.866280]  ? __do_page_fault+0x24d/0x500
[ 3810.866287]  ? page_fault+0x8/0x30
[ 3810.866291]  ? page_fault+0x1e/0x30

What does the profiler say is going on? From the above, it seems the system is
still running, just struggling? That eviction is going to struggle to clear
context objects...

-- 
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/20190719/29721e64/attachment.html>