From: Pavel Begunkov <asml.silence@xxxxxxxxx> commit 4c979eaefa4356d385b7c7d2877dc04d7fe88969 upstream. msg_ring will fail the request if it can't lock rings, instead punt it to io-wq as was originally intended. Cc: stable@xxxxxxxxxxxxxxx Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx> Link: https://lore.kernel.org/r/4697f05afcc37df5c8f89e2fe6d9c7c19f0241f9.1670384893.git.asml.silence@xxxxxxxxx Signed-off-by: Jens Axboe <axboe@xxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- io_uring/msg_ring.c | 2 ++ 1 file changed, 2 insertions(+) --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -164,6 +164,8 @@ int io_msg_ring(struct io_kiocb *req, un } done: + if (ret == -EAGAIN) + return -EAGAIN; if (ret < 0) req_set_fail(req); io_req_set_res(req, ret, 0);
