drm/vc4: Make sure to emit a tile coordinates between two MSAA loads.

The HW only executes a load once the tile coordinates packet happens,
and only tracks one at a time, so by emitting our two MSAA loads back
to back we would end up with an undefined color or Z buffer.

Fixes dEQP-EGL.functional.render.multi_context.gles2.rgb888_window

Signed-off-by: Eric Anholt <[e-mail]>
Reviewed-by: Paul Kocialkowski <[e-mail]>
Cc: Maxime Ripard <[e-mail]>
Link: https://patchwork.freedesktop.org/patch/msgid/[e-mail]

drivers/gpu/drm/vc4/vc4_render_cl.c

···
 	}
 
 	if (setup->zs_read) {
+		if (setup->color_read) {
+			/* Exec previous load. */
+			vc4_tile_coordinates(setup, x, y);
+			vc4_store_before_load(setup);
+		}
+
 		if (args->zs_read.flags &
 		    VC4_SUBMIT_RCL_SURFACE_READ_IS_FULL_RES) {
 			rcl_u8(setup, VC4_PACKET_LOAD_FULL_RES_TILE_BUFFER);
···
 						    &args->zs_read, x, y) |
 				VC4_LOADSTORE_FULL_RES_DISABLE_COLOR);
 		} else {
-			if (setup->color_read) {
-				/* Exec previous load. */
-				vc4_tile_coordinates(setup, x, y);
-				vc4_store_before_load(setup);
-			}
-
 			rcl_u8(setup, VC4_PACKET_LOAD_TILE_BUFFER_GENERAL);
 			rcl_u16(setup, args->zs_read.bits);
 			rcl_u32(setup, setup->zs_read->paddr +
···
 		}
 	}
 	if (setup->zs_read) {
+		if (setup->color_read) {
+			loop_body_size += VC4_PACKET_TILE_COORDINATES_SIZE;
+			loop_body_size += VC4_PACKET_STORE_TILE_BUFFER_GENERAL_SIZE;
+		}
+
 		if (args->zs_read.flags &
 		    VC4_SUBMIT_RCL_SURFACE_READ_IS_FULL_RES) {
 			loop_body_size += VC4_PACKET_LOAD_FULL_RES_TILE_BUFFER_SIZE;
 		} else {
-			if (setup->color_read &&
-			    !(args->color_read.flags &
-			      VC4_SUBMIT_RCL_SURFACE_READ_IS_FULL_RES)) {
-				loop_body_size += VC4_PACKET_TILE_COORDINATES_SIZE;
-				loop_body_size += VC4_PACKET_STORE_TILE_BUFFER_GENERAL_SIZE;
-			}
 			loop_body_size += VC4_PACKET_LOAD_TILE_BUFFER_GENERAL_SIZE;
 		}
 	}