diff options
| author | Pavel Begunkov <asml.silence@gmail.com> | 2023-08-11 15:53:45 +0300 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2023-08-11 19:42:57 +0300 |
| commit | b6b2bb58a75407660f638a68e6e34a07036146d0 (patch) | |
| tree | e6c9a49099ab2542577003a22c85af3dee481427 /io_uring/poll.c | |
| parent | 056695bffa4beed5668dd4aa11efb696eacb3ed9 (diff) | |
| download | linux-b6b2bb58a75407660f638a68e6e34a07036146d0.tar.xz | |
io_uring: never overflow io_aux_cqe
Now all callers of io_aux_cqe() set allow_overflow to false, remove the
parameter and not allow overflowing auxilary multishot cqes.
When CQ is full the function callers and all multishot requests in
general are expected to complete the request. That prevents indefinite
in-background grows of the overflow list and let's the userspace to
handle the backlog at its own pace.
Resubmitting a request should also be faster than accounting a bunch of
overflows, so it should be better for perf when it happens, but a well
behaving userspace should be trying to avoid overflows in any case.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/bb20d14d708ea174721e58bb53786b0521e4dd6d.1691757663.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'io_uring/poll.c')
| -rw-r--r-- | io_uring/poll.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/io_uring/poll.c b/io_uring/poll.c index 65ec363f6377..4c360ba8793a 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -300,8 +300,8 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts) __poll_t mask = mangle_poll(req->cqe.res & req->apoll_events); - if (!io_aux_cqe(req, ts->locked, mask, - IORING_CQE_F_MORE, false)) { + if (!io_fill_cqe_req_aux(req, ts->locked, mask, + IORING_CQE_F_MORE)) { io_req_set_res(req, mask, 0); return IOU_POLL_REMOVE_POLL_USE_RES; } |