io_uring: fix wqe->lock/completion_lock deadlock

Joseph reports following deadlock:

CPU0:
...
io_kill_linked_timeout  // &ctx->completion_lock
io_commit_cqring
__io_queue_deferred
__io_queue_async_work
io_wq_enqueue
io_wqe_enqueue  // &wqe->lock

CPU1:
...
__io_uring_files_cancel
io_wq_cancel_cb
io_wqe_cancel_pending_work  // &wqe->lock
io_cancel_task_cb  // &ctx->completion_lock

Only __io_queue_deferred() calls queue_async_work() while holding
ctx->completion_lock, enqueue drained requests via io_req_task_queue()
instead.

Cc: stable@vger.kernel.org # 5.9+
Reported-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Tested-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

fs/io_uring.c

@@ -1026,6 +1026,7 @@ static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
 			     const struct iovec *fast_iov,
 			     struct iov_iter *iter, bool force);
 static void io_req_drop_files(struct io_kiocb *req);
+static void io_req_task_queue(struct io_kiocb *req);
 
 static struct kmem_cache *req_cachep;
 
@@ -1634,18 +1635,11 @@ static void __io_queue_deferred(struct io_ring_ctx *ctx)
 	do {
 		struct io_defer_entry *de = list_first_entry(&ctx->defer_list,
 						struct io_defer_entry, list);
-		struct io_kiocb *link;
 
 		if (req_need_defer(de->req, de->seq))
 			break;
 		list_del_init(&de->list);
-		/* punt-init is done before queueing for defer */
-		link = __io_queue_async_work(de->req);
-		if (link) {
-			__io_queue_linked_timeout(link);
-			/* drop submission reference */
-			io_put_req_deferred(link, 1);
-		}
+		io_req_task_queue(de->req);
 		kfree(de);
 	} while (!list_empty(&ctx->defer_list));
 }