drm/i915: Add the WaCsStallBeforeStateCacheInvalidate:bdw workaround.

On Broadwell, any PIPE_CONTROL with the "State Cache Invalidate" bit set
must be preceded by a PIPE_CONTROL with the "CS Stall" bit set.

Documented on the BSpec 3D workarounds page.
Reviewed-by: Rafael Barbalho <rafael.barbalho@intel.com>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
[vsyrjala: add chv w/a note too]
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -406,6 +406,7 @@ gen8_render_ring_flush(struct intel_engine_cs *ring,
 {
 	u32 flags = 0;
 	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+	int ret;
 
 	flags |= PIPE_CONTROL_CS_STALL;
 
@@ -422,6 +423,14 @@ gen8_render_ring_flush(struct intel_engine_cs *ring,
 		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_QW_WRITE;
 		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+
+		/* WaCsStallBeforeStateCacheInvalidate:bdw,chv */
+		ret = gen8_emit_pipe_control(ring,
+					     PIPE_CONTROL_CS_STALL |
+					     PIPE_CONTROL_STALL_AT_SCOREBOARD,
+					     0);
+		if (ret)
+			return ret;
 	}
 
 	return gen8_emit_pipe_control(ring, flags, scratch_addr);