io_uring: clusterise ki_flags access in rw_prep

ioprio setup doesn't depend on other fields that are modified in
io_prep_rw() and we can move it down in the function without worrying
about performance. It's useful as it makes iocb->ki_flags
accesses/modifications closer together, so it's more likely the compiler
will cache it in a register and avoid extra reloads.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/8ee98779c06f1b59f6039b1e292db4332efd664b.1634987320.git.asml.silence@gmail.comSigned-off-by: Jens Axboe <axboe@kernel.dk>

fs/io_uring.c

@@ -2840,16 +2840,6 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	    ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
 		req->flags |= REQ_F_NOWAIT;
 
-	ioprio = READ_ONCE(sqe->ioprio);
-	if (ioprio) {
-		ret = ioprio_check_cap(ioprio);
-		if (ret)
-			return ret;
-
-		kiocb->ki_ioprio = ioprio;
-	} else
-		kiocb->ki_ioprio = get_current_ioprio();
-
 	if (ctx->flags & IORING_SETUP_IOPOLL) {
 		if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
 			return -EOPNOTSUPP;
@@ -2863,6 +2853,17 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		kiocb->ki_complete = io_complete_rw;
 	}
 
+	ioprio = READ_ONCE(sqe->ioprio);
+	if (ioprio) {
+		ret = ioprio_check_cap(ioprio);
+		if (ret)
+			return ret;
+
+		kiocb->ki_ioprio = ioprio;
+	} else {
+		kiocb->ki_ioprio = get_current_ioprio();
+	}
+
 	req->imu = NULL;
 	req->rw.addr = READ_ONCE(sqe->addr);
 	req->rw.len = READ_ONCE(sqe->len);