io_uring: fix lockup in io_fail_links()

to #29608102

commit 4ae6dbd683860b9edc254ea8acf5e04b5ae242e5 upstream.

io_fail_links() doesn't consider REQ_F_COMP_LOCKED leading to nested
spin_lock(completion_lock) and lockup.

[  197.680409] rcu: INFO: rcu_preempt detected expedited stalls on
	CPUs/tasks: { 6-... } 18239 jiffies s: 1421 root: 0x40/.
[  197.680411] rcu: blocking rcu_node structures:
[  197.680412] Task dump for CPU 6:
[  197.680413] link-timeout    R  running task        0  1669
	1 0x8000008a
[  197.680414] Call Trace:
[  197.680420]  ? io_req_find_next+0xa0/0x200
[  197.680422]  ? io_put_req_find_next+0x2a/0x50
[  197.680423]  ? io_poll_task_func+0xcf/0x140
[  197.680425]  ? task_work_run+0x67/0xa0
[  197.680426]  ? do_exit+0x35d/0xb70
[  197.680429]  ? syscall_trace_enter+0x187/0x2c0
[  197.680430]  ? do_group_exit+0x43/0xa0
[  197.680448]  ? __x64_sys_exit_group+0x18/0x20
[  197.680450]  ? do_syscall_64+0x52/0xa0
[  197.680452]  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NJiufei Xue <jiufei.xue@linux.alibaba.com>
Reviewed-by: NJoseph Qi <joseph.qi@linux.alibaba.com>

fs/io_uring.c

@@ -4161,10 +4161,9 @@ static void io_poll_task_handler(struct io_kiocb *req, struct io_kiocb **nxt)
 
 	hash_del(&req->hash_node);
 	io_poll_complete(req, req->result, 0);
-	req->flags |= REQ_F_COMP_LOCKED;
-	io_put_req_find_next(req, nxt);
 	spin_unlock_irq(&ctx->completion_lock);
 
+	io_put_req_find_next(req, nxt);
 	io_cqring_ev_posted(ctx);
 }