Re: [PATCH] drm/i915: Workaround to avoid lite restore with HEAD==TAIL

[Chris Wilson <chris@chris-wilson.co.uk>]

On Fri, Apr 10, 2015 at 12:01:08PM +0200, Daniel Vetter wrote:
> On Fri, Apr 10, 2015 at 10:32:33AM +0100, Michel Thierry wrote:
> > ---
> >  drivers/gpu/drm/i915/i915_gem.c  | 11 +++++++++++
> >  drivers/gpu/drm/i915/intel_lrc.c | 29 +++++++++++++++++++++++++++++
> >  2 files changed, 40 insertions(+)
> > 
> > diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> > index ca522c9..a44070a 100644
> > --- a/drivers/gpu/drm/i915/i915_gem.c
> > +++ b/drivers/gpu/drm/i915/i915_gem.c
> > @@ -2382,6 +2382,17 @@ int __i915_add_request(struct intel_engine_cs *ring,
> >  	request->head = request_start;
> >  	request->tail = intel_ring_get_tail(ringbuf);
> >  
> > +	if (i915.enable_execlists &&
> > +	    (IS_GEN8(ring->dev) || IS_GEN9(ring->dev))) {
> > +		/*
> > +		 * Here we add two extra NOOPs as padding to avoid
> > +		 * lite restore of a context with HEAD==TAIL.
> > +		 */
> > +		intel_logical_ring_emit(ringbuf, MI_NOOP);
> > +		intel_logical_ring_emit(ringbuf, MI_NOOP);
> > +		intel_logical_ring_advance(ringbuf);
> > +	}

Move this to gen8_emit_request() and remove the permanent overallocation
in ring_begin. The tail pointer adjustment can then also be localised.
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx