From: Pavel Begunkov <[email protected]>
To: [email protected]
Cc: Jens Axboe <[email protected]>, [email protected]
Subject: [PATCH for-next v2 13/25] io_uring: remove check_cq checking from hot paths
Date: Tue, 14 Jun 2022 15:37:03 +0100 [thread overview]
Message-ID: <9ab7e307e77ffeb92ec788694c87beff27d55c05.1655213915.git.asml.silence@gmail.com> (raw)
In-Reply-To: <[email protected]>
All ctx->check_cq events are slow path, don't test every single flag one
by one in the hot path, but add a common guarding if.
Signed-off-by: Pavel Begunkov <[email protected]>
---
io_uring/io_uring.c | 34 +++++++++++++++++++---------------
1 file changed, 19 insertions(+), 15 deletions(-)
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 0f6edf82f262..e43eccf173ff 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1807,24 +1807,25 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
int ret = 0;
unsigned long check_cq;
+ check_cq = READ_ONCE(ctx->check_cq);
+ if (unlikely(check_cq)) {
+ if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT))
+ __io_cqring_overflow_flush(ctx, false);
+ /*
+ * Similarly do not spin if we have not informed the user of any
+ * dropped CQE.
+ */
+ if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))
+ return -EBADR;
+ }
/*
* Don't enter poll loop if we already have events pending.
* If we do, we can potentially be spinning for commands that
* already triggered a CQE (eg in error).
*/
- check_cq = READ_ONCE(ctx->check_cq);
- if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT))
- __io_cqring_overflow_flush(ctx, false);
if (io_cqring_events(ctx))
return 0;
- /*
- * Similarly do not spin if we have not informed the user of any
- * dropped CQE.
- */
- if (unlikely(check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT)))
- return -EBADR;
-
do {
/*
* If a submit got punted to a workqueue, we can have the
@@ -2752,12 +2753,15 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
ret = io_run_task_work_sig();
if (ret || io_should_wake(iowq))
return ret;
+
check_cq = READ_ONCE(ctx->check_cq);
- /* let the caller flush overflows, retry */
- if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT))
- return 1;
- if (unlikely(check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT)))
- return -EBADR;
+ if (unlikely(check_cq)) {
+ /* let the caller flush overflows, retry */
+ if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT))
+ return 1;
+ if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))
+ return -EBADR;
+ }
if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS))
return -ETIME;
return 1;
--
2.36.1
next prev parent reply other threads:[~2022-06-14 14:38 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-06-14 14:36 [PATCH for-next v2 00/25] 5.20 cleanups and poll optimisations Pavel Begunkov
2022-06-14 14:36 ` [PATCH for-next v2 01/25] io_uring: make reg buf init consistent Pavel Begunkov
2022-06-14 14:36 ` [PATCH for-next v2 02/25] io_uring: move defer_list to slow data Pavel Begunkov
2022-06-14 14:36 ` [PATCH for-next v2 03/25] io_uring: better caching for ctx timeout fields Pavel Begunkov
2022-06-14 14:36 ` [PATCH for-next v2 04/25] io_uring: refactor ctx slow data placement Pavel Begunkov
2022-06-14 14:36 ` [PATCH for-next v2 05/25] io_uring: move small helpers to headers Pavel Begunkov
2022-06-14 14:36 ` [PATCH for-next v2 06/25] io_uring: explain io_wq_work::cancel_seq placement Pavel Begunkov
2022-06-14 14:36 ` [PATCH for-next v2 07/25] io_uring: inline ->registered_rings Pavel Begunkov
2022-06-14 14:36 ` [PATCH for-next v2 08/25] io_uring: don't set REQ_F_COMPLETE_INLINE in tw Pavel Begunkov
2022-06-14 14:36 ` [PATCH for-next v2 09/25] io_uring: never defer-complete multi-apoll Pavel Begunkov
2022-06-14 14:37 ` [PATCH for-next v2 10/25] io_uring: kill REQ_F_COMPLETE_INLINE Pavel Begunkov
2022-06-15 8:20 ` Hao Xu
2022-06-14 14:37 ` [PATCH for-next v2 11/25] io_uring: refactor io_req_task_complete() Pavel Begunkov
2022-06-14 17:45 ` Hao Xu
2022-06-14 17:52 ` Pavel Begunkov
2022-06-14 14:37 ` [PATCH for-next v2 12/25] io_uring: don't inline io_put_kbuf Pavel Begunkov
2022-06-14 14:37 ` Pavel Begunkov [this message]
2022-06-14 14:37 ` [PATCH for-next v2 14/25] io_uring: poll: remove unnecessary req->ref set Pavel Begunkov
2022-06-14 14:37 ` [PATCH for-next v2 15/25] io_uring: switch cancel_hash to use per entry spinlock Pavel Begunkov
2022-06-14 14:37 ` [PATCH for-next v2 16/25] io_uring: pass poll_find lock back Pavel Begunkov
2022-06-14 14:37 ` [PATCH for-next v2 17/25] io_uring: clean up io_try_cancel Pavel Begunkov
2022-06-14 14:37 ` [PATCH for-next v2 18/25] io_uring: limit number hash buckets Pavel Begunkov
2022-06-14 14:37 ` [PATCH for-next v2 19/25] io_uring: clean up io_ring_ctx_alloc Pavel Begunkov
2022-06-14 14:37 ` [PATCH for-next v2 20/25] io_uring: use state completion infra for poll reqs Pavel Begunkov
2022-06-14 14:37 ` [PATCH for-next v2 21/25] io_uring: add IORING_SETUP_SINGLE_ISSUER Pavel Begunkov
2022-06-14 14:37 ` [PATCH for-next v2 22/25] io_uring: pass hash table into poll_find Pavel Begunkov
2022-06-14 14:37 ` [PATCH for-next v2 23/25] io_uring: introduce a struct for hash table Pavel Begunkov
2022-06-14 14:37 ` [PATCH for-next v2 24/25] io_uring: propagate locking state to poll cancel Pavel Begunkov
2022-06-14 14:37 ` [PATCH for-next v2 25/25] io_uring: mutex locked poll hashing Pavel Begunkov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=9ab7e307e77ffeb92ec788694c87beff27d55c05.1655213915.git.asml.silence@gmail.com \
[email protected] \
[email protected] \
[email protected] \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox