From: Stefan Roesch <shr@devkernel.io>
To: Jakub Kicinski <kuba@kernel.org>
Cc: io-uring@vger.kernel.org, kernel-team@fb.com, axboe@kernel.dk,
ammarfaizi2@gnuweeb.org, netdev@vger.kernel.org,
olivier@trillion01.com
Subject: Re: [PATCH v13 1/7] net: split off __napi_busy_poll from napi_busy_poll
Date: Wed, 31 May 2023 12:16:50 -0700 [thread overview]
Message-ID: <qvqwleh41f8x.fsf@devbig1114.prn1.facebook.com> (raw)
In-Reply-To: <20230531103224.17a462cc@kernel.org>
Jakub Kicinski <kuba@kernel.org> writes:
> On Thu, 18 May 2023 14:17:45 -0700 Stefan Roesch wrote:
>> - napi = napi_by_id(napi_id);
>> - if (!napi)
>> + ctx.napi = napi_by_id(napi_id);
>> + if (!ctx.napi)
>> goto out;
>>
>> preempt_disable();
>
> This will conflict with:
>
> https://git.kernel.org/netdev/net-next/c/c857946a4e26
>
> :( Not sure what to do about it..
>
> Maybe we can merge a simpler version to unblock io-uring (just add
> need_resched() to your loop_end callback and you'll get the same
> behavior). Refactor in net-next in parallel. Then once trees converge
> do simple a cleanup and call the _rcu version?
Jakub, I can certainly call need_resched() in the loop_end callback, but
isn't there a potential race? need_resched() in the loop_end callback
might not return true, but the need_resched() call in napi_busy_poll
does?
next prev parent reply other threads:[~2023-05-31 19:18 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-18 21:17 [PATCH v13 0/7] io_uring: add napi busy polling support Stefan Roesch
2023-05-18 21:17 ` [PATCH v13 1/7] net: split off __napi_busy_poll from napi_busy_poll Stefan Roesch
[not found] ` <20230531103224.17a462cc@kernel.org>
2023-05-31 19:16 ` Stefan Roesch [this message]
2023-06-01 4:15 ` Jakub Kicinski
2023-06-02 4:12 ` Stefan Roesch
2023-06-02 4:26 ` Jakub Kicinski
[not found] ` <20230531102644.7f171d48@kernel.org>
2023-06-05 17:47 ` Stefan Roesch
2023-06-05 18:00 ` Jakub Kicinski
2023-05-18 21:17 ` [PATCH v13 2/7] net: introduce napi_busy_loop_rcu() Stefan Roesch
[not found] ` <20230531102915.0afc570b@kernel.org>
2023-06-05 17:45 ` Stefan Roesch
2023-05-18 21:17 ` [PATCH v13 3/7] io-uring: move io_wait_queue definition to header file Stefan Roesch
2023-05-18 21:17 ` [PATCH v13 4/7] io-uring: add napi busy poll support Stefan Roesch
2023-05-19 1:26 ` Jens Axboe
2023-05-19 23:11 ` Stefan Roesch
2023-05-19 9:53 ` Simon Horman
2023-05-19 23:17 ` Stefan Roesch
2023-05-18 21:17 ` [PATCH v13 5/7] io-uring: add sqpoll support for napi busy poll Stefan Roesch
2023-05-19 0:11 ` kernel test robot
2023-05-19 1:13 ` Jens Axboe
2023-05-19 23:29 ` Stefan Roesch
2023-05-19 4:35 ` kernel test robot
2023-05-18 21:17 ` [PATCH v13 6/7] io_uring: add register/unregister napi function Stefan Roesch
2023-05-19 1:30 ` Jens Axboe
2023-05-18 21:17 ` [PATCH v13 7/7] io_uring: add prefer busy poll to register and unregister napi api Stefan Roesch
2023-05-19 1:31 ` [PATCH v13 0/7] io_uring: add napi busy polling support 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=qvqwleh41f8x.fsf@devbig1114.prn1.facebook.com \
--to=shr@devkernel.io \
--cc=ammarfaizi2@gnuweeb.org \
--cc=axboe@kernel.dk \
--cc=io-uring@vger.kernel.org \
--cc=kernel-team@fb.com \
--cc=kuba@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=olivier@trillion01.com \
/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;
as well as URLs for NNTP newsgroup(s).