From: Pavel Begunkov <[email protected]>
To: Usama Arif <[email protected]>,
[email protected], [email protected],
[email protected]
Cc: [email protected]
Subject: Re: [PATCH v5 2/4] io_uring: avoid ring quiesce while registering/unregistering eventfd
Date: Thu, 3 Feb 2022 23:54:46 +0000 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
On 2/3/22 23:46, Pavel Begunkov wrote:
> On 2/3/22 23:34, Usama Arif wrote:
>> This is done by creating a new RCU data structure (io_ev_fd) as part of
>> io_ring_ctx that holds the eventfd_ctx.
>>
>> The function io_eventfd_signal is executed under rcu_read_lock with a
>> single rcu_dereference to io_ev_fd so that if another thread unregisters
>> the eventfd while io_eventfd_signal is still being executed, the
>> eventfd_signal for which io_eventfd_signal was called completes
>> successfully.
>>
>> The process of registering/unregistering eventfd is done under a lock
>> so multiple threads don't enter a race condition while
>> registering/unregistering eventfd.
>>
>> With the above approach ring quiesce can be avoided which is much more
>> expensive then using RCU lock. On the system tested, io_uring_reigster with
>> IORING_REGISTER_EVENTFD takes less than 1ms with RCU lock, compared to 15ms
>> before with ring quiesce.
>>
>> Signed-off-by: Usama Arif <[email protected]>
>> ---
>> fs/io_uring.c | 116 ++++++++++++++++++++++++++++++++++++++++----------
>> 1 file changed, 93 insertions(+), 23 deletions(-)
>>
[...]
>> +
>> +static void io_eventfd_put(struct rcu_head *rcu)
>> +{
>> + struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu);
>> + struct io_ring_ctx *ctx = ev_fd->ctx;
>> +
>> + eventfd_ctx_put(ev_fd->cq_ev_fd);
>> + kfree(ev_fd);
>> + rcu_assign_pointer(ctx->io_ev_fd, NULL);
>> }
>
> Emm, it happens after the grace period, so you have a gap where a
> request may read a freed eventfd... What I think you wanted to do
> is more like below:
>
>
> io_eventfd_put() {
> evfd = ...;
> eventfd_ctx_put(evfd->evfd);
> kfree(io_ev_fd);
> }
>
> register() {
s/register/unregister/
> mutex_lock();
> ev_fd = rcu_deref();
> if (ev_fd) {
> rcu_assign_pointer(ctx->evfd, NULL);
> call_rcu(&ev_fd->evfd, io_eventfd_put);
> }
> mutex_unlock();
> }
>
>
> Note, there's no need in ->unregistering. I also doubt you need
> ->ev_fd_lock, how about just using already taken ->uring_lock?
--
Pavel Begunkov
next prev parent reply other threads:[~2022-02-03 23:59 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-03 23:34 [PATCH v5 0/4] io_uring: remove ring quiesce in io_uring_register Usama Arif
2022-02-03 23:34 ` [PATCH v5 1/4] io_uring: remove trace for eventfd Usama Arif
2022-02-03 23:34 ` [PATCH v5 2/4] io_uring: avoid ring quiesce while registering/unregistering eventfd Usama Arif
2022-02-03 23:46 ` Pavel Begunkov
2022-02-03 23:54 ` Pavel Begunkov [this message]
2022-02-04 0:12 ` Jens Axboe
2022-02-03 23:34 ` [PATCH v5 3/4] io_uring: avoid ring quiesce for IORING_REGISTER_EVENTFD_ASYNC Usama Arif
2022-02-03 23:34 ` [PATCH v5 4/4] io_uring: remove ring quiesce for io_uring_register Usama Arif
2022-02-03 23:47 ` Pavel Begunkov
2022-02-04 0:28 ` Pavel Begunkov
2022-02-04 0:02 ` [PATCH v5 0/4] io_uring: remove ring quiesce in io_uring_register Pavel Begunkov
2022-02-04 0:15 ` Jens Axboe
2022-02-04 0:24 ` 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 \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[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