drm/radeon: set the full cache bit for fences on r7xx+

Needed to properly flush the read caches for fences.
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

drivers/gpu/drm/radeon/r600.c

@@ -2706,14 +2706,17 @@ void r600_fence_ring_emit(struct radeon_device *rdev,
 			  struct radeon_fence *fence)
 {
 	struct radeon_ring *ring = &rdev->ring[fence->ring];
+	u32 cp_coher_cntl = PACKET3_TC_ACTION_ENA | PACKET3_VC_ACTION_ENA |
+		PACKET3_SH_ACTION_ENA;
+
+	if (rdev->family >= CHIP_RV770)
+		cp_coher_cntl |= PACKET3_FULL_CACHE_ENA;
 
 	if (rdev->wb.use_event) {
 		u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
 		/* flush read cache over gart */
 		radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
-		radeon_ring_write(ring, PACKET3_TC_ACTION_ENA |
-					PACKET3_VC_ACTION_ENA |
-					PACKET3_SH_ACTION_ENA);
+		radeon_ring_write(ring, cp_coher_cntl);
 		radeon_ring_write(ring, 0xFFFFFFFF);
 		radeon_ring_write(ring, 0);
 		radeon_ring_write(ring, 10); /* poll interval */
@@ -2727,9 +2730,7 @@ void r600_fence_ring_emit(struct radeon_device *rdev,
 	} else {
 		/* flush read cache over gart */
 		radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
-		radeon_ring_write(ring, PACKET3_TC_ACTION_ENA |
-					PACKET3_VC_ACTION_ENA |
-					PACKET3_SH_ACTION_ENA);
+		radeon_ring_write(ring, cp_coher_cntl);
 		radeon_ring_write(ring, 0xFFFFFFFF);
 		radeon_ring_write(ring, 0);
 		radeon_ring_write(ring, 10); /* poll interval */

drivers/gpu/drm/radeon/r600d.h

@@ -1582,6 +1582,7 @@
 #              define PACKET3_CP_DMA_CMD_DAIC      (1 << 29)
 #define	PACKET3_SURFACE_SYNC				0x43
 #              define PACKET3_CB0_DEST_BASE_ENA    (1 << 6)
+#              define PACKET3_FULL_CACHE_ENA       (1 << 20) /* r7xx+ only */
 #              define PACKET3_TC_ACTION_ENA        (1 << 23)
 #              define PACKET3_VC_ACTION_ENA        (1 << 24)
 #              define PACKET3_CB_ACTION_ENA        (1 << 25)