drm/radeon: use WRITE_DATA packets for vm flush on SI

This is the preferred packet for writing data to memory
or registers on SI.
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/radeon/si.c

@@ -2797,21 +2797,35 @@ void si_vm_flush(struct radeon_device *rdev, struct radeon_ib *ib)
 	if (vm == NULL)
 		return;
 
+	/* write new base address */
+	radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
+	radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
+				 WRITE_DATA_DST_SEL(0)));
+
 	if (vm->id < 8) {
-		radeon_ring_write(ring, PACKET0(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR
-						+ (vm->id << 2), 0));
+		radeon_ring_write(ring,
+				  (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2);
 	} else {
-		radeon_ring_write(ring, PACKET0(VM_CONTEXT8_PAGE_TABLE_BASE_ADDR
-						+ ((vm->id - 8) << 2), 0));
+		radeon_ring_write(ring,
+				  (VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm->id - 8) << 2)) >> 2);
 	}
+	radeon_ring_write(ring, 0);
 	radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
 
 	/* flush hdp cache */
-	radeon_ring_write(ring, PACKET0(HDP_MEM_COHERENCY_FLUSH_CNTL, 0));
+	radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
+	radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
+				 WRITE_DATA_DST_SEL(0)));
+	radeon_ring_write(ring, HDP_MEM_COHERENCY_FLUSH_CNTL >> 2);
+	radeon_ring_write(ring, 0);
 	radeon_ring_write(ring, 0x1);
 
-	/* bits 0-7 are the VM contexts0-7 */
-	radeon_ring_write(ring, PACKET0(VM_INVALIDATE_REQUEST, 0));
+	/* bits 0-15 are the VM contexts0-15 */
+	radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
+	radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
+				 WRITE_DATA_DST_SEL(0)));
+	radeon_ring_write(ring, VM_INVALIDATE_REQUEST >> 2);
+	radeon_ring_write(ring, 0);
 	radeon_ring_write(ring, 1 << ib->vm->id);
 }
 

drivers/gpu/drm/radeon/sid.h

@@ -812,6 +812,21 @@
 #define	PACKET3_DRAW_INDEX_OFFSET_2			0x35
 #define	PACKET3_DRAW_INDEX_MULTI_ELEMENT		0x36
 #define	PACKET3_WRITE_DATA				0x37
+#define		WRITE_DATA_DST_SEL(x)                   ((x) << 8)
+                /* 0 - register
+		 * 1 - memory (sync - via GRBM)
+		 * 2 - tc/l2
+		 * 3 - gds
+		 * 4 - reserved
+		 * 5 - memory (async - direct)
+		 */
+#define		WR_ONE_ADDR                             (1 << 16)
+#define		WR_CONFIRM                              (1 << 20)
+#define		WRITE_DATA_ENGINE_SEL(x)                ((x) << 30)
+                /* 0 - me
+		 * 1 - pfp
+		 * 2 - ce
+		 */
 #define	PACKET3_DRAW_INDEX_INDIRECT_MULTI		0x38
 #define	PACKET3_MEM_SEMAPHORE				0x39
 #define	PACKET3_MPEG_INDEX				0x3A