[Intel-gfx] [PATCH V2] drm/i915/gt: Add workaround 14016712196

Andi Shyti andi.shyti at linux.intel.com
Wed May 31 12:14:53 UTC 2023


Hi Andrzej,

> > @@ -218,6 +242,16 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
> >   		u32 flags = 0;
> >   		u32 *cs, count;
> > +		/* Wa_14016712196 */
> > +		if (IS_MTL_GRAPHICS_STEP(engine->i915, M, STEP_A0, STEP_B0) ||
> > +		    IS_MTL_GRAPHICS_STEP(engine->i915, P, STEP_A0, STEP_B0)) {
> > +			/* dummy PIPE_CONTROL + depth flush */
> > +			cs = intel_ring_begin(rq, 6);
> > +			err = mtl_dummy_pipe_control(rq, cs);
> > +			if (err)
> > +				return err;
> > +		}
> > +
> 
> In case gen12_emit_flush_rcs is called with EMIT_BARRIER = (EMIT_INVALIDATE
> | EMIT_FLUSH) dummy pipe will be inserted twice, is it OK?

good point... I also meant to ask this, indeed. I assumed that
before the pipe control we needed the dummy pipe. Is that the
case, Tejas?

> >   		flags |= PIPE_CONTROL_COMMAND_CACHE_INVALIDATE;
> >   		flags |= PIPE_CONTROL_TLB_INVALIDATE;
> >   		flags |= PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE;
> > @@ -733,6 +767,13 @@ u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
> >   		     PIPE_CONTROL_DC_FLUSH_ENABLE |
> >   		     PIPE_CONTROL_FLUSH_ENABLE);
> > +	/* Wa_14016712196 */
> > +	if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) ||
> > +	    IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0))
> > +		/* dummy PIPE_CONTROL + depth flush */
> > +		cs = gen12_emit_pipe_control(cs, 0,
> > +					     PIPE_CONTROL_DEPTH_CACHE_FLUSH, 0);
> 
> How do we know there is enough space for dummy pipe?

This should be ensured by intel_ring_begin().

Andi

> Regards
> Andrzej
> 
> > +
> >   	if (GRAPHICS_VER(i915) == 12 && GRAPHICS_VER_FULL(i915) < IP_VER(12, 50))
> >   		/* Wa_1409600907 */
> >   		flags |= PIPE_CONTROL_DEPTH_STALL;


More information about the Intel-gfx mailing list