io_uring: optimise io_free_batch_list

We do several req->flags checks in the fast path of
io_free_batch_list(). One explicit check of REQ_F_REFCOUNT, and two
other hidden in io_queue_next() and io_dismantle_req(). Moreover, there
is a io_req_put_rsrc_locked() call in between, so there is no hope
req->flags will be preserved in registers.

All those flags if not a slow path than definitely a slower path, so
put them all under a single flags mask check and save several mem
reloads and ifs.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/0fb493f73f2009aea395c570c2932fecaa4e1244.1647897811.git.asml.silence@gmail.comSigned-off-by: Jens Axboe <axboe@kernel.dk>

fs/io_uring.c

@@ -113,6 +113,9 @@
 #define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
 				REQ_F_POLLED | REQ_F_CREDS | REQ_F_ASYNC_DATA)
 
+#define IO_REQ_CLEAN_SLOW_FLAGS (REQ_F_REFCOUNT | REQ_F_LINK | REQ_F_HARDLINK |\
+				 IO_REQ_CLEAN_FLAGS)
+
 #define IO_TCTX_REFS_CACHE_NR	(1U << 10)
 
 struct io_uring {
@@ -2626,15 +2629,20 @@ static void io_free_batch_list(struct io_ring_ctx *ctx,
 		struct io_kiocb *req = container_of(node, struct io_kiocb,
 						    comp_list);
 
-		if (unlikely(req->flags & REQ_F_REFCOUNT)) {
-			node = req->comp_list.next;
-			if (!req_ref_put_and_test(req))
-				continue;
+		if (unlikely(req->flags & IO_REQ_CLEAN_SLOW_FLAGS)) {
+			if (req->flags & REQ_F_REFCOUNT) {
+				node = req->comp_list.next;
+				if (!req_ref_put_and_test(req))
+					continue;
+			}
+			io_queue_next(req);
+			if (unlikely(req->flags & IO_REQ_CLEAN_FLAGS))
+				io_clean_op(req);
 		}
+		if (!(req->flags & REQ_F_FIXED_FILE))
+			io_put_file(req->file);
 
 		io_req_put_rsrc_locked(req, ctx);
-		io_queue_next(req);
-		io_dismantle_req(req);
 
 		if (req->task != task) {
 			if (task)