Imagine this
resource_copy_region(ctx, dst, ..., src, ...);
transfer_map(ctx, src, 0, PIPE_TRANSFER_WRITE, ...);
at the beginning of a cmdbuf. We need to flush in transfer_map so
that the transfer is not reordered before the resource copy. The
check for "vctx->num_draws == 0 && vctx->num_compute == 0" is not
enough. Removing the optimization entirely.
Because of the more precise resource tracking in the previous
commit, I hope the performance impact is minimized. We will have to
go with perfect resource tracking, or attempt a more limited
optimization, if there are specific cases we really need to optimize
for.
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Gurchetan Singh <gurchetansingh@chromium.org>
*
* - synchronization is disabled
* - the resource is not referenced by the current cmdbuf
- * - the current cmdbuf has no draw/compute command that accesses the
- * resource (XXX there are also clear or blit commands)
*/
static bool virgl_res_needs_flush(struct virgl_context *vctx,
struct virgl_transfer *trans)
if (!vws->res_is_referenced(vws, vctx->cbuf, res->hw_res))
return false;
- if (res->clean_mask & (1 << trans->base.level)) {
- /* XXX Consider
- *
- * glCopyBufferSubData(src, dst, ...);
- * glBufferSubData(src, ...);
- *
- * at the beginning of a cmdbuf. glBufferSubData will be incorrectly
- * reordered before glCopyBufferSubData.
- */
- if (vctx->num_draws == 0 && vctx->num_compute == 0)
- return false;
- }
-
return true;
}