[Bug 109823] [CI][DRMTIP] igt at gem_ppgtt@blt-vs-render-ctx0 - dmesg-fail - BUG: unable to handle kernel paging request at ffffa08d71663ee0

[bugzilla-daemon at freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=109823

--- Comment #4 from Chris Wilson <chris at chris-wilson.co.uk> ---
If it's stray memcorruption (honestly more likely than a bug in the swap code),
then 

commit e781a7a3235e9ff68095d2cd4d9c1e039a0516d7
Author: Chris Wilson <chris at chris-wilson.co.uk>
Date:   Mon Mar 4 11:41:13 2019 +0000

    drm/i915: Acquire breadcrumb ref before cancelling

    We may race the interrupt signaling with retirement, in which case the
    order in which we acquire the reference inside the interrupt is vital to
    provide the correct barrier against the request being freed in
    retirement, i.e. we need to acquire our reference before marking the
    breadcrumb as cancelled (as soon as the breadcrumb is cancelled
    retirement may drop its reference to the request without serialisation
    with the interrupt handler).

is definitely a possible fix. But without definite proof, the only thing we can
do is read the code while waiting for a pattern.

-- 
You are receiving this mail because:
You are the assignee for the bug.
You are the QA Contact for the bug.
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/intel-gfx-bugs/attachments/20190307/613496bd/attachment.html>