Re: [Intel-gfx] [PATCH] drm/i915: Always call fence-lost prior to removing the fence

From: Daniel Vetter <daniel@ffwll.ch>
To: Imre Deak <imre.deak@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>,
	intel-gfx@lists.freedesktop.org,
	Daniel Vetter <daniel.vetter@ffwll.ch>,
	stable@vger.kernel.org
Subject: Re: [Intel-gfx] [PATCH] drm/i915: Always call fence-lost prior to removing the fence
Date: Tue, 26 Mar 2013 20:21:24 +0100	[thread overview]
Message-ID: <20130326192123.GX9021@phenom.ffwll.local> (raw)
In-Reply-To: <1364307958.2358.3.camel@intelbox>

On Tue, Mar 26, 2013 at 04:25:58PM +0200, Imre Deak wrote:
> On Tue, 2013-03-26 at 11:29 +0000, Chris Wilson wrote:
> > There is a minute window for a race between put-fence removing the fence
> > and for a new transaction by an external party on the GTT mmap. That is
> > we must zap the mmap prior to removing the fence and not afterwards.
> > 
> > Fixes regression from
> > commit 61050808bb019ebea966b7b5bfd357aaf219fb51
> > Author: Chris Wilson <chris@chris-wilson.co.uk>
> > Date:   Tue Apr 17 15:31:31 2012 +0100
> > 
> >     drm/i915: Refactor put_fence() to use the common fence writing routine
> > 
> > v2: Remember the fence to remove with a local variable (gcc)
> > 
> > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> > Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
> > Cc: stable@vger.kernel.org # regression introduced in v3.5
> 
> Reviewed-by: Imre Deak <imre.deak@intel.com>

stable rules say "no theoretical races", and I think we don't even have a
testcase for this. Hence queued for -next and dropped cc: stable, thanks
for the patch.
-Daniel
-- 
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch