From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: tip-bot for Thomas Gleixner <tipbot@zytor.com>
Cc: linux-tip-commits@vger.kernel.org, hpa@zytor.com,
linux-kernel@vger.kernel.org, peterz@infradead.org,
tglx@linutronix.de, mingo@kernel.org
Subject: Re: [tip:smp/hotplug] cpu/hotplug: Plug death reporting race
Date: Thu, 3 Mar 2016 06:11:18 -0800 [thread overview]
Message-ID: <20160303141118.GF3577@linux.vnet.ibm.com> (raw)
In-Reply-To: <tip-71f87b2fc64c2e9b6d53cb817f28711b959d3dfe@git.kernel.org>
On Thu, Mar 03, 2016 at 02:03:35AM -0800, tip-bot for Thomas Gleixner wrote:
> Commit-ID: 71f87b2fc64c2e9b6d53cb817f28711b959d3dfe
> Gitweb: http://git.kernel.org/tip/71f87b2fc64c2e9b6d53cb817f28711b959d3dfe
> Author: Thomas Gleixner <tglx@linutronix.de>
> AuthorDate: Thu, 3 Mar 2016 10:52:10 +0100
> Committer: Thomas Gleixner <tglx@linutronix.de>
> CommitDate: Thu, 3 Mar 2016 10:52:10 +0100
>
> cpu/hotplug: Plug death reporting race
>
> Paul noticed that the conversion of the death reporting introduced a race
> where the outgoing cpu might be delayed after waking the controll processor,
> so it might not be able to call rcu_report_dead() before being physically
> removed, leading to RCU stalls.
>
> We cant call complete after rcu_report_dead(), so instead of going back to
> busy polling, simply issue a function call to do the completion.
>
> Fixes: 27d50c7eeb0f "rcu: Make CPU_DYING_IDLE an explicit call"
> Reported-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> Link: http://lkml.kernel.org/r/20160302201127.GA23440@linux.vnet.ibm.com
> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
> Acked-by: Peter Zijlstra <peterz@infradead.org>
There are some possible issues with printk()s from WARN_ON() calls
using RCU from within smp_call_function_single(), but in normal
execution this should be OK. Besides, the WARN_ON() contains a
cpu_online(this_cpu), so it simply won't fire in this case.
So nice fix!!!
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> ---
> kernel/cpu.c | 16 ++++++++++++++--
> 1 file changed, 14 insertions(+), 2 deletions(-)
>
> diff --git a/kernel/cpu.c b/kernel/cpu.c
> index ff8059b..93e9d89 100644
> --- a/kernel/cpu.c
> +++ b/kernel/cpu.c
> @@ -755,14 +755,26 @@ static int notify_dead(unsigned int cpu)
> return 0;
> }
>
> +static void cpuhp_complete_idle_dead(void *arg)
> +{
> + struct cpuhp_cpu_state *st = arg;
> +
> + complete(&st->done);
> +}
> +
> void cpuhp_report_idle_dead(void)
> {
> struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
>
> BUG_ON(st->state != CPUHP_AP_OFFLINE);
> - st->state = CPUHP_AP_IDLE_DEAD;
> - complete(&st->done);
> rcu_report_dead(smp_processor_id());
> + st->state = CPUHP_AP_IDLE_DEAD;
> + /*
> + * We cannot call complete after rcu_report_dead() so we delegate it
> + * to an online cpu.
> + */
> + smp_call_function_single(cpumask_first(cpu_online_mask),
> + cpuhp_complete_idle_dead, st, 0);
> }
>
> #else
>
prev parent reply other threads:[~2016-03-03 14:11 UTC|newest]
Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-02-26 18:43 [patch 00/20] cpu/hotplug: Core infrastructure for cpu hotplug rework Thomas Gleixner
2016-02-26 18:43 ` [patch 01/20] idle: Move x86ism out of generic code Thomas Gleixner
2016-02-27 20:29 ` Brian Gerst
2016-02-29 19:35 ` Thomas Gleixner
2016-02-29 19:48 ` Will Deacon
2016-02-29 20:06 ` Thomas Gleixner
2016-02-26 18:43 ` [patch 02/20] cpu/hotplug: Restructure FROZEN state handling Thomas Gleixner
2016-03-01 19:51 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-03-02 22:35 ` Srivatsa S. Bhat
2016-03-02 23:43 ` Srivatsa S. Bhat
2016-02-26 18:43 ` [patch 03/20] cpu/hotplug: Restructure cpu_up code Thomas Gleixner
2016-03-01 19:52 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-03-02 22:36 ` Srivatsa S. Bhat
2016-02-26 18:43 ` [patch 04/20] cpu/hotplug: Split out cpu down functions Thomas Gleixner
2016-03-01 19:52 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-03-02 22:37 ` Srivatsa S. Bhat
2016-02-26 18:43 ` [patch 05/20] cpu/hotplug: Add tracepoints Thomas Gleixner
2016-03-01 19:52 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-02-26 18:43 ` [patch 06/20] cpu/hotplug: Convert to a state machine for the control processor Thomas Gleixner
2016-03-01 19:53 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-03-02 11:23 ` Peter Zijlstra
2016-02-26 18:43 ` [patch 07/20] cpu/hotplug: Convert the hotplugged cpu work to a state machine Thomas Gleixner
2016-03-01 19:53 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-02-26 18:43 ` [patch 08/20] cpu/hotplug: Hand in target state to _cpu_up/down Thomas Gleixner
2016-03-01 19:54 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-02-26 18:43 ` [patch 09/20] cpu/hotplug: Add sysfs state interface Thomas Gleixner
2016-03-01 19:54 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-03-02 12:40 ` Peter Zijlstra
2016-02-26 18:43 ` [patch 10/20] cpu/hotplug: Make target state writeable Thomas Gleixner
2016-02-26 23:46 ` Rafael J. Wysocki
2016-02-27 7:39 ` Thomas Gleixner
2016-02-27 14:43 ` Rafael J. Wysocki
2016-02-28 14:49 ` Thomas Gleixner
2016-02-29 15:49 ` Thomas Gleixner
2016-03-01 1:53 ` Rafael J. Wysocki
2016-03-01 19:55 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-03-02 12:41 ` Peter Zijlstra
2016-03-02 19:57 ` Thomas Gleixner
2016-02-26 18:43 ` [patch 11/20] cpu/hotplug: Implement setup/removal interface Thomas Gleixner
2016-03-01 19:55 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-02-26 18:43 ` [patch 12/20] cpu/hotplug: Move scheduler cpu_online notifier to hotplug core Thomas Gleixner
2016-03-01 19:55 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-02-26 18:43 ` [patch 13/20] cpu/hotplug: Unpark smpboot threads from the state machine Thomas Gleixner
2016-03-01 19:56 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-02-26 18:43 ` [patch 14/20] cpu/hotplug: Split out the state walk into functions Thomas Gleixner
2016-03-01 19:56 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-02-26 18:43 ` [patch 15/20] cpu/hotplug: Create hotplug threads Thomas Gleixner
2016-03-01 19:57 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-02-26 18:43 ` [patch 16/20] cpu/hotplug: Move online calls to hotplugged cpu Thomas Gleixner
2016-03-01 19:57 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-02-26 18:43 ` [patch 17/20] arch/hotplug: Call into idle with a proper state Thomas Gleixner
2016-03-01 19:57 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-02-26 18:43 ` [patch 18/20] cpu/hotplug: Let upcoming cpu bring itself fully up Thomas Gleixner
2016-03-01 19:58 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-03-02 17:28 ` [patch 18/20] " Richard Cochran
2016-02-26 18:43 ` [patch 19/20] cpu/hotplug: Make wait for dead cpu completion based Thomas Gleixner
2016-03-01 19:58 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-02-26 18:43 ` [patch 20/20] rcu: Make CPU_DYING_IDLE an explicit call Thomas Gleixner
2016-02-27 2:14 ` Paul E. McKenney
2016-02-27 2:23 ` Paul E. McKenney
2016-02-27 7:47 ` Thomas Gleixner
2016-02-27 11:05 ` Paul E. McKenney
2016-02-27 11:30 ` Thomas Gleixner
2016-02-27 16:33 ` Paul E. McKenney
2016-03-01 19:58 ` [tip:smp/hotplug] " tip-bot for Thomas Gleixner
2016-03-02 20:11 ` Paul E. McKenney
2016-03-03 7:31 ` Thomas Gleixner
2016-03-03 10:03 ` [tip:smp/hotplug] cpu/hotplug: Plug death reporting race tip-bot for Thomas Gleixner
2016-03-03 14:11 ` Paul E. McKenney [this message]
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=20160303141118.GF3577@linux.vnet.ibm.com \
--to=paulmck@linux.vnet.ibm.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-tip-commits@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=tipbot@zytor.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).