Revert "radeon: just don't map VRAM buffers at all"

This reverts commit 96e8b916

.
In the case of VCE encoding with raw YUV file, CPU load directly
to VRAM is faster than combination of CPU writing to GTT and
then blit to VRAM with GPU.
Reviewed-by: Christian König <christian.koenig@amd.com>

src/gallium/drivers/radeon/r600_texture.c

@@ -928,8 +928,8 @@ static void *r600_texture_transfer_map(struct pipe_context *ctx,
 	if (rtex->surface.level[level].mode >= RADEON_SURF_MODE_1D)
 		use_staging_texture = TRUE;
 
-	/* Untiled buffers in VRAM, which is slow for CPU reads and writes */
-	if (!(usage & PIPE_TRANSFER_MAP_DIRECTLY) &&
+	/* Untiled buffers in VRAM, which is slow for CPU reads */
+	if ((usage & PIPE_TRANSFER_READ) && !(usage & PIPE_TRANSFER_MAP_DIRECTLY) &&
 	    (rtex->resource.domains == RADEON_DOMAIN_VRAM)) {
 		use_staging_texture = TRUE;
 	}