<html>
<head>
<base href="https://bugs.freedesktop.org/">
</head>
<body>
<p>
<div>
<b><a class="bz_bug_link
bz_status_NEW "
title="NEW - ring 0 stalled after bytes_moved_threshold reached - Cap Verde - HD 7770"
href="https://bugs.freedesktop.org/show_bug.cgi?id=100712#c4">Comment # 4</a>
on <a class="bz_bug_link
bz_status_NEW "
title="NEW - ring 0 stalled after bytes_moved_threshold reached - Cap Verde - HD 7770"
href="https://bugs.freedesktop.org/show_bug.cgi?id=100712">bug 100712</a>
from <span class="vcard"><a class="email" href="mailto:michel@daenzer.net" title="Michel Dänzer <michel@daenzer.net>"> <span class="fn">Michel Dänzer</span></a>
</span></b>
<pre>(In reply to Julien Isorce from <a href="show_bug.cgi?id=100712#c0">comment #0</a>)
<span class="quote">> In kernel radeon_object.c::radeon_bo_list_validate, once "bytes_moved >
> bytes_moved_threshold" is reached (this is the case for 850 bo in the same
> list_for_each_entry loop), I can see that radeon_ib_schedule emits a fence
> that it takes more than the radeon.lockup_timeout to be signaled.</span >
radeon_ib_schedule is called for submitting the command stream from userspace,
not for any BO moves directly, right?
How did you determine that this hang is directly related to bytes_moved /
bytes_moved_threshold? Maybe it's only indirectly related, e.g. due to the
threshold preventing a BO from being moved to VRAM despite userspace's
preference.
<span class="quote">> Also it seems the fence is signaled by swapper after more than 10 seconds
> but it is too late. I requires to reduce the "15" param above to 4 to see
> that.</span >
How does "swapper" (what is that exactly?) signal the fence?
<span class="quote">> Is it normal that radeon_bo_list_validate still tries to move the bo if
> bytes_moved_threshold is reached ?</span >
There are circumstances where a BO has to be moved even though the threshold is
reached.
<span class="quote">> Indeed ttm_bo_validate is always called</span >
ttm_bo_validate must be called for every BO referenced by the command stream
from userspace for correct lifetime management of its memory.
<span class="quote">> (it blits from vram to vram).</span >
It might be worth looking into why this happens, though. If domain ==
current_domain == RADEON_GEM_DOMAIN_VRAM, I wouldn't expect ttm_bo_validate to
trigger a blit.</pre>
</div>
</p>
<hr>
<span>You are receiving this mail because:</span>
<ul>
<li>You are the assignee for the bug.</li>
</ul>
</body>
</html>