drm/radeon: fix surface sync in fence on cayman (v2)

We need to set the engine bit to select the ME and
also set the full cache bit.  Should help stability
on TN and cayman.

V2: fix up surface sync in ib execute as well

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

drivers/gpu/drm/radeon/ni.c

@@ -1331,13 +1331,12 @@ void cayman_fence_ring_emit(struct radeon_device *rdev,
 {
 	struct radeon_ring *ring = &rdev->ring[fence->ring];
 	u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
+	u32 cp_coher_cntl = PACKET3_FULL_CACHE_ENA | PACKET3_TC_ACTION_ENA |
+		PACKET3_SH_ACTION_ENA;
 
 	/* flush read cache over gart for this vmid */
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
-	radeon_ring_write(ring, (CP_COHER_CNTL2 - PACKET3_SET_CONFIG_REG_START) >> 2);
-	radeon_ring_write(ring, 0);
 	radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
-	radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | PACKET3_SH_ACTION_ENA);
+	radeon_ring_write(ring, PACKET3_ENGINE_ME | cp_coher_cntl);
 	radeon_ring_write(ring, 0xFFFFFFFF);
 	radeon_ring_write(ring, 0);
 	radeon_ring_write(ring, 10); /* poll interval */
@@ -1353,6 +1352,8 @@ void cayman_fence_ring_emit(struct radeon_device *rdev,
 void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 {
 	struct radeon_ring *ring = &rdev->ring[ib->ring];
+	u32 cp_coher_cntl = PACKET3_FULL_CACHE_ENA | PACKET3_TC_ACTION_ENA |
+		PACKET3_SH_ACTION_ENA;
 
 	/* set to DX10/11 mode */
 	radeon_ring_write(ring, PACKET3(PACKET3_MODE_CONTROL, 0));
@@ -1377,14 +1378,11 @@ void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 			  (ib->vm ? (ib->vm->id << 24) : 0));
 
 	/* flush read cache over gart for this vmid */
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
-	radeon_ring_write(ring, (CP_COHER_CNTL2 - PACKET3_SET_CONFIG_REG_START) >> 2);
-	radeon_ring_write(ring, ib->vm ? ib->vm->id : 0);
 	radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
-	radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | PACKET3_SH_ACTION_ENA);
+	radeon_ring_write(ring, PACKET3_ENGINE_ME | cp_coher_cntl);
 	radeon_ring_write(ring, 0xFFFFFFFF);
 	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, 10); /* poll interval */
+	radeon_ring_write(ring, ((ib->vm ? ib->vm->id : 0) << 24) | 10); /* poll interval */
 }
 
 static void cayman_cp_enable(struct radeon_device *rdev, bool enable)

drivers/gpu/drm/radeon/nid.h

@@ -1154,6 +1154,7 @@
 #              define PACKET3_DB_ACTION_ENA        (1 << 26)
 #              define PACKET3_SH_ACTION_ENA        (1 << 27)
 #              define PACKET3_SX_ACTION_ENA        (1 << 28)
+#              define PACKET3_ENGINE_ME            (1 << 31)
 #define	PACKET3_ME_INITIALIZE				0x44
 #define		PACKET3_ME_INITIALIZE_DEVICE_ID(x) ((x) << 16)
 #define	PACKET3_COND_WRITE				0x45