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

Needed to properly flush the read caches for fences.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index ad99bae..3dce370 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2706,14 +2706,17 @@
 			  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 @@
 	} 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 */