diff options
| author |   Pavel Begunkov <asml.silence@gmail.com> | 2021-03-25 19:05:14 +0000 |
|---|---|---|
| committer |   Jens Axboe <axboe@kernel.dk> | 2021-03-25 13:47:03 -0600 |
| commit | 90b8749022bbdd0c94a13182a78f4903b98fd0d7 (patch) | |
| tree | 32a12b3183e89e32bc6da294070eb4340d49e6d3 | |
| parent | io-wq: fix race around pending work on teardown (diff) | |
| download | linux-dev-90b8749022bbdd0c94a13182a78f4903b98fd0d7.tar.xz linux-dev-90b8749022bbdd0c94a13182a78f4903b98fd0d7.zip | |
io_uring: maintain CQE order of a failed link
Arguably we want CQEs of linked requests be in a strict order of
submission as it always was. Now if init of a request fails its CQE may
be posted before all prior linked requests including the head of the
link. Fix it by failing it last.
Fixes: de59bc104c24f ("io_uring: fail links more in io_submit_sqe()")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/b7a96b05832e7ab23ad55f84092a2548c4a888b0.1616699075.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
| -rw-r--r-- | fs/io_uring.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/fs/io_uring.c b/fs/io_uring.c index 8c5789b96dbb..54ea561db4a5 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6480,8 +6480,6 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, ret = io_init_req(ctx, req, sqe); if (unlikely(ret)) { fail_req: - io_put_req(req); - io_req_complete(req, ret); if (link->head) { /* fail even hard links since we don't submit */ link->head->flags |= REQ_F_FAIL_LINK; @@ -6489,6 +6487,8 @@ fail_req: io_req_complete(link->head, -ECANCELED); link->head = NULL; } + io_put_req(req); + io_req_complete(req, ret); return ret; } ret = io_req_prep(req, sqe); |