io_uring: simplify fallback execution

Lock the ring with uring_lock in io_fallback_req_func(), which should
make it a bit safer and easier. With that we also don't need refs
pinning as io_ring_exit_work() will wait until uring_lock is freed.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/56170e6a0cbfc8edee2794c6613e8f6f1d76d276.1673887636.git.asml.silence@gmail.comSigned-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/io_uring.c

@@ -245,17 +245,15 @@ static __cold void io_fallback_req_func(struct work_struct *work)
 						fallback_work.work);
 	struct llist_node *node = llist_del_all(&ctx->fallback_llist);
 	struct io_kiocb *req, *tmp;
-	bool locked = false;
+	bool locked = true;
 
-	percpu_ref_get(&ctx->refs);
+	mutex_lock(&ctx->uring_lock);
 	llist_for_each_entry_safe(req, tmp, node, io_task_work.node)
 		req->io_task_work.func(req, &locked);
-
-	if (locked) {
-		io_submit_flush_completions(ctx);
-		mutex_unlock(&ctx->uring_lock);
-	}
-	percpu_ref_put(&ctx->refs);
+	if (WARN_ON_ONCE(!locked))
+		return;
+	io_submit_flush_completions(ctx);
+	mutex_unlock(&ctx->uring_lock);
 }
 
 static int io_alloc_hash_table(struct io_hash_table *table, unsigned bits)