diff options
| author | Pavel Begunkov <asml.silence@gmail.com> | 2022-08-24 13:07:41 +0100 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2022-08-24 08:57:28 -0600 |
| commit | 53bdc88aac9a21aae937452724fa4738cd843795 (patch) | |
| tree | 9f3c2b3ecf2c84631b305b29328e348ef61fbbb2 /io_uring/notif.c | |
| parent | 986e263def32eec89153babf469859d837507d34 (diff) | |
io_uring/notif: order notif vs send CQEs
Currently, there is no ordering between notification CQEs and
completions of the send flushing it, this quite complicates the
userspace, especially since we don't flush notification when the
send(+flush) request fails, i.e. there will be only one CQE. What we
can do is to make sure that notification completions come only after
sends.
The easiest way to achieve this is to not try to complete a notification
inline from io_sendzc() but defer it to task_work, considering that
io-wq sendzc is disallowed CQEs will be naturally ordered because
task_works will only be executed after we're done with submission and so
inline completion.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/cddfd1c2bf91f22b9fe08e13b7dffdd8f858a151.1661342812.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'io_uring/notif.c')
| -rw-r--r-- | io_uring/notif.c | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/io_uring/notif.c b/io_uring/notif.c index 568ff17dc552..96f076b175e0 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -81,8 +81,10 @@ void io_notif_slot_flush(struct io_notif_slot *slot) slot->notif = NULL; /* drop slot's master ref */ - if (refcount_dec_and_test(&nd->uarg.refcnt)) - io_notif_complete(notif); + if (refcount_dec_and_test(&nd->uarg.refcnt)) { + notif->io_task_work.func = __io_notif_complete_tw; + io_req_task_work_add(notif); + } } __cold int io_notif_unregister(struct io_ring_ctx *ctx) |