From: Pavel Begunkov <[email protected]>
To: Jens Axboe <[email protected]>, [email protected]
Subject: [PATCH 09/13] io_uring: remove dependency on ring->sq/cq_entries
Date: Sun, 16 May 2021 22:58:08 +0100 [thread overview]
Message-ID: <745d31bc2da41283ddd0489ef784af5c8d6310e9.1621201931.git.asml.silence@gmail.com> (raw)
In-Reply-To: <[email protected]>
We have numbers of {sq,cq} entries cached in ctx, don't look up them in
user-shared rings as 1) it may fetch additional cacheline 2) user may
change it and so it's always error prone.
Signed-off-by: Pavel Begunkov <[email protected]>
---
fs/io_uring.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 10970ed32f27..f06bd4123a98 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1351,7 +1351,7 @@ static inline bool io_sqring_full(struct io_ring_ctx *ctx)
{
struct io_rings *r = ctx->rings;
- return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == r->sq_ring_entries;
+ return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == ctx->sq_entries;
}
static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx)
@@ -1369,7 +1369,7 @@ static inline struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
* control dependency is enough as we're using WRITE_ONCE to
* fill the cq entry
*/
- if (__io_cqring_events(ctx) == rings->cq_ring_entries)
+ if (__io_cqring_events(ctx) == ctx->cq_entries)
return NULL;
tail = ctx->cached_cq_tail++;
@@ -1422,11 +1422,10 @@ static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
/* Returns true if there are no backlogged entries after the flush */
static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
{
- struct io_rings *rings = ctx->rings;
unsigned long flags;
bool all_flushed, posted;
- if (!force && __io_cqring_events(ctx) == rings->cq_ring_entries)
+ if (!force && __io_cqring_events(ctx) == ctx->cq_entries)
return false;
posted = false;
--
2.31.1
next prev parent reply other threads:[~2021-05-16 21:58 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-05-16 21:57 [PATCH for-next 00/13] 5.14 cleanups Pavel Begunkov
2021-05-16 21:58 ` [PATCH 01/13] io_uring: improve sqpoll event/state handling Pavel Begunkov
2021-05-16 21:58 ` [PATCH 02/13] io_uring: improve sq_thread waiting check Pavel Begunkov
2021-05-16 21:58 ` [PATCH 03/13] io_uring: remove unused park_task_work Pavel Begunkov
2021-05-16 21:58 ` [PATCH 04/13] io_uring: simplify waking sqo_sq_wait Pavel Begunkov
2021-05-16 21:58 ` [PATCH 05/13] io_uring: get rid of files in exit cancel Pavel Begunkov
2021-05-16 21:58 ` [PATCH 06/13] io_uring: make fail flag not link specific Pavel Begunkov
2021-05-16 21:58 ` [PATCH 07/13] io_uring: shuffle rarely used ctx fields Pavel Begunkov
2021-05-16 21:58 ` [PATCH 08/13] io_uring: better locality for rsrc fields Pavel Begunkov
2021-05-16 21:58 ` Pavel Begunkov [this message]
2021-05-16 21:58 ` [PATCH 10/13] io_uring: deduce cq_mask from cq_entries Pavel Begunkov
2021-05-16 21:58 ` [PATCH 11/13] io_uring: kill cached_cq_overflow Pavel Begunkov
2021-05-16 21:58 ` [PATCH 12/13] io_uring: rename io_get_cqring Pavel Begunkov
2021-05-16 21:58 ` [PATCH 13/13] io_uring: don't bounce submit_state cachelines Pavel Begunkov
2021-05-24 17:41 ` [PATCH for-next 00/13] 5.14 cleanups Jens Axboe
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=745d31bc2da41283ddd0489ef784af5c8d6310e9.1621201931.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