From: Frederic Weisbecker <frederic@kernel.org>
To: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Pingfan Liu <kernelfans@gmail.com>,
rcu@vger.kernel.org, David Woodhouse <dwmw@amazon.co.uk>,
Neeraj Upadhyay <quic_neeraju@quicinc.com>,
Josh Triplett <josh@joshtriplett.org>,
Steven Rostedt <rostedt@goodmis.org>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Lai Jiangshan <jiangshanlai@gmail.com>,
Joel Fernandes <joel@joelfernandes.org>,
"Jason A. Donenfeld" <Jason@zx2c4.com>
Subject: Re: [PATCHv2 3/3] rcu: coordinate tick dependency during concurrent offlining
Date: Sat, 24 Sep 2022 00:13:49 +0200 [thread overview]
Message-ID: <20220923221349.GA161211@lothringen> (raw)
In-Reply-To: <20220922135442.GH4196@paulmck-ThinkPad-P17-Gen-1>
On Thu, Sep 22, 2022 at 06:54:42AM -0700, Paul E. McKenney wrote:
> On Thu, Sep 22, 2022 at 05:29:32PM +0800, Pingfan Liu wrote:
> > My understanding is after removing the tick dep by
> > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > index 79aea7df4345..cbfc884f04a4 100644
> > --- a/kernel/rcu/tree.c
> > +++ b/kernel/rcu/tree.c
> > @@ -2171,8 +2171,6 @@ int rcutree_dead_cpu(unsigned int cpu)
> > WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
> > /* Adjust any no-longer-needed kthreads. */
> > rcu_boost_kthread_setaffinity(rnp, -1);
> > - // Stop-machine done, so allow nohz_full to disable tick.
> > - tick_dep_clear(TICK_DEP_BIT_RCU);
> > return 0;
> > }
> >
> > @@ -4008,8 +4006,6 @@ int rcutree_online_cpu(unsigned int cpu)
> > sync_sched_exp_online_cleanup(cpu);
> > rcutree_affinity_setting(cpu, -1);
> >
> > - // Stop-machine done, so allow nohz_full to disable tick.
> > - tick_dep_clear(TICK_DEP_BIT_RCU);
> > return 0;
> > }
> >
> > @@ -4031,8 +4027,6 @@ int rcutree_offline_cpu(unsigned int cpu)
> >
> > rcutree_affinity_setting(cpu, cpu);
> >
> > - // nohz_full CPUs need the tick for stop-machine to work quickly
> > - tick_dep_set(TICK_DEP_BIT_RCU);
> > return 0;
> > }
> >
> > If the TREE04 can success, then move on to revert the commit(s)
> > identified by Frederic, and do test again.
> >
> > At this time, a TREE04 failure is expected.
> >
> > If the above two results are observed, TICK_DEP_BIT_RCU can be
> > removed.
> >
> > Is my understanding right?
>
> Seems plausible to me, but I again defer to Frederic.
Right, more precisely the commit to revert is:
96926686deab ("rcu: Make CPU-hotplug removal operations enable tick")
which is the diff Pingfan Liu proposed above. The other uses of TICK_DEP_BIT_RCU
will still be needed though.
Thanks.
next prev parent reply other threads:[~2022-09-23 22:13 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-15 5:58 [PATCHv2 0/3] rcu: Enhance the capability to cope with concurrent cpu offlining/onlining Pingfan Liu
2022-09-15 5:58 ` [PATCHv2 1/3] rcu: Keep qsmaskinitnext fresh when rcutree_online_cpu() Pingfan Liu
2022-09-15 6:11 ` Pingfan Liu
2022-09-16 14:52 ` Frederic Weisbecker
2022-09-19 10:24 ` Pingfan Liu
2022-09-19 10:51 ` Frederic Weisbecker
2022-09-20 3:45 ` Pingfan Liu
2022-09-20 9:23 ` Frederic Weisbecker
2022-10-01 2:26 ` Joel Fernandes
2022-10-02 12:34 ` Pingfan Liu
2022-10-02 15:52 ` Joel Fernandes
2022-09-20 10:31 ` Frederic Weisbecker
2022-09-21 11:56 ` Pingfan Liu
2022-09-15 5:58 ` [PATCHv2 2/3] rcu: Resort to cpu_dying_mask for affinity when offlining Pingfan Liu
2022-09-16 14:23 ` Frederic Weisbecker
2022-09-19 4:33 ` Pingfan Liu
2022-09-19 10:34 ` Frederic Weisbecker
2022-09-20 3:16 ` Pingfan Liu
2022-09-20 9:00 ` Frederic Weisbecker
2022-09-20 9:38 ` Frederic Weisbecker
2022-09-21 11:48 ` Pingfan Liu
2022-09-15 5:58 ` [PATCHv2 3/3] rcu: coordinate tick dependency during concurrent offlining Pingfan Liu
2022-09-16 13:42 ` Frederic Weisbecker
2022-09-20 7:26 ` Pingfan Liu
2022-09-20 9:46 ` Frederic Weisbecker
2022-09-20 19:13 ` Paul E. McKenney
2022-09-22 9:29 ` Pingfan Liu
2022-09-22 13:54 ` Paul E. McKenney
2022-09-23 22:13 ` Frederic Weisbecker [this message]
2022-09-26 6:34 ` Pingfan Liu
2022-09-26 22:23 ` Paul E. McKenney
2022-09-27 9:59 ` Pingfan Liu
2022-09-29 8:19 ` Pingfan Liu
2022-09-29 8:20 ` Pingfan Liu
2022-09-30 13:04 ` Joel Fernandes
2022-10-02 14:06 ` Pingfan Liu
2022-10-02 16:11 ` Joel Fernandes
2022-10-02 16:24 ` Paul E. McKenney
2022-10-02 16:30 ` Joel Fernandes
2022-10-02 16:57 ` Paul E. McKenney
2022-10-02 16:59 ` Joel Fernandes
2022-09-30 15:44 ` Paul E. McKenney
2022-10-02 13:29 ` Pingfan Liu
2022-10-02 15:08 ` Frederic Weisbecker
2022-10-02 16:20 ` Paul E. McKenney
2022-10-02 16:20 ` Paul E. McKenney
[not found] ` <CAFgQCTtgLfc0NeYqyWk4Ew-pA9rMREjRjWSnQhYLv-V5117s9Q@mail.gmail.com>
2022-10-27 17:46 ` Paul E. McKenney
2022-10-31 3:24 ` Pingfan Liu
2022-11-03 16:51 ` Paul E. McKenney
2022-11-07 16:07 ` Paul E. McKenney
2022-11-09 18:55 ` Joel Fernandes
2022-11-18 12:08 ` Pingfan Liu
2022-11-18 23:30 ` Paul E. McKenney
2022-11-21 3:48 ` Pingfan Liu
2022-11-21 17:14 ` Paul E. McKenney
2022-11-17 14:39 ` Frederic Weisbecker
2022-11-18 1:45 ` Pingfan Liu
[not found] ` <CAFgQCTtNetv7v_Law=abPtngC8Gv6OGcGz9M_wWMxz_GAEWDUQ@mail.gmail.com>
2022-10-27 18:13 ` Paul E. McKenney
2022-10-31 2:10 ` Pingfan Liu
2022-09-26 16:13 ` Joel Fernandes
2022-09-27 9:42 ` Pingfan Liu
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=20220923221349.GA161211@lothringen \
--to=frederic@kernel.org \
--cc=Jason@zx2c4.com \
--cc=dwmw@amazon.co.uk \
--cc=jiangshanlai@gmail.com \
--cc=joel@joelfernandes.org \
--cc=josh@joshtriplett.org \
--cc=kernelfans@gmail.com \
--cc=mathieu.desnoyers@efficios.com \
--cc=paulmck@kernel.org \
--cc=quic_neeraju@quicinc.com \
--cc=rcu@vger.kernel.org \
--cc=rostedt@goodmis.org \
/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