From: Ming Lei <ming.lei@redhat.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>,
dennis@kernel.org, tj@kernel.org, cl@linux.com,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
zhouchengming@bytedance.com, songmuchun@bytedance.com
Subject: Re: [PATCH] percpu_ref: call wake_up_all() after percpu_ref_put() completes
Date: Fri, 8 Apr 2022 09:40:49 +0800 [thread overview]
Message-ID: <Yk+SoZrwUGnQ3cI4@T590> (raw)
In-Reply-To: <20220407155752.769632b737f79b038cf83742@linux-foundation.org>
On Thu, Apr 07, 2022 at 03:57:52PM -0700, Andrew Morton wrote:
> (cc Ming Lei)
>
> On Thu, 7 Apr 2022 18:33:35 +0800 Qi Zheng <zhengqi.arch@bytedance.com> wrote:
>
> > In the percpu_ref_call_confirm_rcu(), we call the wake_up_all()
> > before calling percpu_ref_put(), which will cause the value of
> > percpu_ref to be unstable when percpu_ref_switch_to_atomic_sync()
> > returns.
> >
> > CPU0 CPU1
> >
> > percpu_ref_switch_to_atomic_sync(&ref)
> > --> percpu_ref_switch_to_atomic(&ref)
> > --> percpu_ref_get(ref); /* put after confirmation */
> > call_rcu(&ref->data->rcu, percpu_ref_switch_to_atomic_rcu);
> >
> > percpu_ref_switch_to_atomic_rcu
> > --> percpu_ref_call_confirm_rcu
> > --> data->confirm_switch = NULL;
> > wake_up_all(&percpu_ref_switch_waitq);
> >
> > /* here waiting to wake up */
> > wait_event(percpu_ref_switch_waitq, !ref->data->confirm_switch);
> > (A)percpu_ref_put(ref);
> > /* The value of &ref is unstable! */
> > percpu_ref_is_zero(&ref)
> > (B)percpu_ref_put(ref);
> >
> > As shown above, assuming that the counts on each cpu add up to 0 before
> > calling percpu_ref_switch_to_atomic_sync(), we expect that after switching
> > to atomic mode, percpu_ref_is_zero() can return true. But actually it will
Looks all current users expect the refcount is stable after percpu_ref_switch_to_atomic_sync
returns, even though the API itself doesn't mention the point explicitly.
> > return different values in the two cases of A and B, which is not what
> > we expected.
> >
> > Maybe the original purpose of percpu_ref_switch_to_atomic_sync() is
> > just to ensure that the conversion to atomic mode is completed, but it
> > should not return with an extra reference count.
> >
> > Calling wake_up_all() after percpu_ref_put() ensures that the value of
> > percpu_ref is stable after percpu_ref_switch_to_atomic_sync() returns.
> > So just do it.
>
> Thanks. I'll grab this, but shall await input from others before doing
> anything else with it.
>
> > Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
> > +++ b/lib/percpu-refcount.c
> > @@ -154,13 +154,14 @@ static void percpu_ref_call_confirm_rcu(struct rcu_head *rcu)
> >
> > data->confirm_switch(ref);
> > data->confirm_switch = NULL;
> > - wake_up_all(&percpu_ref_switch_waitq);
> >
> > if (!data->allow_reinit)
> > __percpu_ref_exit(ref);
> >
> > /* drop ref from percpu_ref_switch_to_atomic() */
> > percpu_ref_put(ref);
> > +
> > + wake_up_all(&percpu_ref_switch_waitq);
> > }
Looks fine:
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Thanks,
Ming
next prev parent reply other threads:[~2022-04-08 1:41 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-04-07 10:33 [PATCH] percpu_ref: call wake_up_all() after percpu_ref_put() completes Qi Zheng
2022-04-07 22:57 ` Andrew Morton
2022-04-08 0:39 ` Dennis Zhou
2022-04-08 1:40 ` Ming Lei [this message]
2022-04-08 2:54 ` Muchun Song
2022-04-08 3:50 ` Qi Zheng
2022-04-08 3:54 ` Andrew Morton
2022-04-08 4:06 ` Qi Zheng
2022-04-08 4:10 ` Andrew Morton
2022-04-08 4:14 ` Qi Zheng
2022-04-08 4:16 ` Qi Zheng
2022-04-08 5:57 ` Dennis Zhou
2022-04-08 6:28 ` Qi Zheng
2022-04-08 17:41 ` Tejun Heo
2022-04-08 19:19 ` Dennis Zhou
2022-04-09 0:40 ` Qi Zheng
2022-04-11 7:19 ` Qi Zheng
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=Yk+SoZrwUGnQ3cI4@T590 \
--to=ming.lei@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=dennis@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=songmuchun@bytedance.com \
--cc=tj@kernel.org \
--cc=zhengqi.arch@bytedance.com \
--cc=zhouchengming@bytedance.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).