[Intel-gfx] [PATCH] drm/i915: Only clear write-domains after a successful wait-seqno

[Chris Wilson]

On Fri, Jun 28, 2013 at 06:30:39PM +0200, Daniel Vetter wrote:
> On Fri, Jun 28, 2013 at 04:54:08PM +0100, Chris Wilson wrote:
> > In the introduction of the non-blocking wait, I cut'n'pasted the wait
> > completion code from normal locked path. Unfortunately, this neglected
> > that the normal path returned early if the wait returned early. The
> > result is that read-only waits may return whilst the GPU is still
> > writing to the bo.
> > 
> > Fixes regression from
> > commit 3236f57a0162391f84b93f39fc1882c49a8998c7 [v3.7]
> > Author: Chris Wilson <chris at chris-wilson.co.uk>
> > Date:   Fri Aug 24 09:35:09 2012 +0100
> > 
> >     drm/i915: Use a non-blocking wait for set-to-domain ioctl
> > 
> > Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> > Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=66163
> > Cc: stable at vger.kernel.org
> 
> Queued for -next, thanks for the patch. And do we have an igt for this?
> The usual combinaition of some blt busy work with the drmtest interrupt
> should be fairly effective I guess ...

On the third attempt, I seem to have successfully reproduced the bug
using the gem_cpu_concurrent_blit and gem_gtt_concurrent_blit tests.
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre