radeonsi: flush TC L2 cache for indirect draw data

This fixes a bug when indirect draw data is generated by transform
feedback.

Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>

src/gallium/drivers/radeonsi/si_descriptors.c

@@ -1242,10 +1242,10 @@ static void si_set_streamout_targets(struct pipe_context *ctx,
 		 * and most other clients can use TC L2 as well, we don't need
 		 * to flush it.
 		 *
-		 * The only case which requires flushing it is VGT DMA index
-		 * fetching, which is a rare case. Thus, flag the TC L2
-		 * dirtiness in the resource and handle it when index fetching
-		 * is used.
+		 * The only cases which requires flushing it is VGT DMA index
+		 * fetching (on <= CIK) and indirect draw data, which are rare
+		 * cases. Thus, flag the TC L2 dirtiness in the resource and
+		 * handle it at draw call time.
 		 */
 		for (i = 0; i < sctx->b.streamout.num_targets; i++)
 			if (sctx->b.streamout.targets[i])

src/gallium/drivers/radeonsi/si_state_draw.c

@@ -967,6 +967,11 @@ void si_draw_vbo(struct pipe_context *ctx, const struct pipe_draw_info *info)
 		r600_resource(ib.buffer)->TC_L2_dirty = false;
 	}
 
+	if (info->indirect && r600_resource(info->indirect)->TC_L2_dirty) {
+		sctx->b.flags |= SI_CONTEXT_INV_GLOBAL_L2;
+		r600_resource(info->indirect)->TC_L2_dirty = false;
+	}
+
 	/* Check flush flags. */
 	if (sctx->b.flags)
 		si_mark_atom_dirty(sctx, sctx->atoms.s.cache_flush);