From: Oleg Nesterov <oleg@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>,
Ingo Molnar <mingo@elte.hu>,
Hiroyuki KAMEZAWA <kamezawa.hiroyu@jp.fujitsu.com>,
Motohiro Kosaki <kosaki.motohiro@jp.fujitsu.com>,
Linux Kernel ML <linux-kernel@vger.kernel.org>
Subject: Re: [BUG] TASK_DEAD task is able to be woken up in special condition
Date: Fri, 6 Jan 2012 15:12:58 +0100 [thread overview]
Message-ID: <20120106141258.GB19462@redhat.com> (raw)
In-Reply-To: <1325853838.2442.18.camel@twins>
On 01/06, Peter Zijlstra wrote:
>
> On Fri, 2012-01-06 at 21:01 +0900, Yasunori Goto wrote:
>
> > Do you mean the following patch?
>
> Yes, something like that. At that point ->state should be TASK_RUNNING
> (since we are after all running). The unlock_wait() will synchronize
> against any in-progress ttwu() while its fast path is a non-atomic
> compare. Any ttwu after this will bail since it will either observe
> TASK_RUNNING or TASK_DEAD, neither are a state it will act upon.
>
> Now the only question that remains is if we need the full memory barrier
> or if we can get away with less.
>
> I guess the mb separates the write to ->state (setting TASK_RUNNING)
> from the read of ->pi_lock. The remote CPU must see the TASK_RUNNING,
> and we must see ->pi_lock taken if it is.
Yes, I think we need the full mb, STORE vs LOAD.
> > --- linux-3.2-rc7.orig/kernel/exit.c
> > +++ linux-3.2-rc7/kernel/exit.c
> > @@ -1038,6 +1038,10 @@ NORET_TYPE void do_exit(long code)
> >
> > preempt_disable();
> > exit_rcu();
> > +
> > + smp_mb();
> > + raw_spin_unlock_wait(&tsk->pi_lock);
> > +
> > /* causes final put_task_struct in finish_task_switch(). */
> > tsk->state = TASK_DEAD;
Interesting. Initially I thought this is wrong and we should do
raw_spin_unlock_wait(pi_lock);
mb();
tsk->state = TASK_DEAD;
This "obviously" serializes LOAD(pi_lock) and STORE(state).
But when I re-read your explanation above I think you are right,
mb() before unlock_wait() should work too, just it refers to
state = RUNNING in the past.
But this makes me worry. We are doing a lot of things after
exit_mm(). In particular we take tasklist_lock in exit_notify()
and then do_exit() takes task_lock(). But every unlock + lock
implies mb(). So how it was possible to hit this bug???
Oleg.
next prev parent reply other threads:[~2012-01-06 14:19 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-12-22 0:42 [BUG] TASK_DEAD task is able to be woken up in special condition Yasunori Goto
2011-12-22 2:14 ` KOSAKI Motohiro
2011-12-22 8:22 ` Yasunori Goto
2011-12-22 20:02 ` KOSAKI Motohiro
2011-12-23 9:49 ` Peter Zijlstra
2011-12-23 15:41 ` Oleg Nesterov
2011-12-26 8:23 ` Yasunori Goto
2011-12-26 17:11 ` Oleg Nesterov
2011-12-27 6:48 ` Yasunori Goto
2012-01-06 10:22 ` Yasunori Goto
2012-01-06 11:01 ` Peter Zijlstra
2012-01-06 12:01 ` Yasunori Goto
2012-01-06 12:43 ` Peter Zijlstra
2012-01-06 14:12 ` Oleg Nesterov [this message]
2012-01-06 14:19 ` Oleg Nesterov
2012-01-07 1:31 ` Yasunori Goto
2012-01-16 11:51 ` Yasunori Goto
2012-01-16 13:38 ` Peter Zijlstra
2012-01-17 8:40 ` Yasunori Goto
2012-01-17 9:06 ` Ingo Molnar
2012-01-17 15:12 ` Oleg Nesterov
2012-01-18 9:42 ` Ingo Molnar
2012-01-18 14:20 ` Oleg Nesterov
2012-01-24 10:19 ` Peter Zijlstra
2012-01-24 10:55 ` Peter Zijlstra
2012-01-24 17:25 ` KOSAKI Motohiro
2012-01-25 15:45 ` Oleg Nesterov
2012-01-25 16:51 ` Peter Zijlstra
2012-01-25 17:43 ` Oleg Nesterov
2012-01-26 15:32 ` Peter Zijlstra
2012-01-26 16:26 ` Oleg Nesterov
2012-01-27 8:59 ` Peter Zijlstra
2012-01-24 10:11 ` Peter Zijlstra
2012-01-26 9:39 ` Ingo Molnar
2012-01-28 12:03 ` [tip:sched/core] sched: Fix ancient race in do_exit() tip-bot for Yasunori Goto
2012-01-28 21:12 ` Linus Torvalds
2012-01-29 16:07 ` Oleg Nesterov
2012-01-29 17:44 ` Linus Torvalds
2012-01-29 18:28 ` Linus Torvalds
2012-01-29 18:59 ` Oleg Nesterov
2012-01-30 16:27 ` Linus Torvalds
2012-01-06 13:48 ` [BUG] TASK_DEAD task is able to be woken up in special condition Oleg Nesterov
2011-12-28 21:07 ` KOSAKI Motohiro
2012-01-24 10:23 ` Peter Zijlstra
2012-01-24 18:01 ` KOSAKI Motohiro
2012-01-25 6:15 ` Mike Galbraith
2012-01-26 21:24 ` KOSAKI Motohiro
2012-01-25 10:10 ` Peter Zijlstra
2012-01-26 20:25 ` [tip:sched/urgent] sched: Fix rq->nr_uninterruptible update race tip-bot for Peter Zijlstra
2012-01-27 5:20 ` Rakib Mullick
2012-01-27 8:19 ` Peter Zijlstra
2012-01-27 14:11 ` Rakib Mullick
2012-01-26 21:21 ` [BUG] TASK_DEAD task is able to be woken up in special condition KOSAKI Motohiro
2012-01-27 8:21 ` Peter Zijlstra
2011-12-26 6:52 ` Yasunori Goto
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=20120106141258.GB19462@redhat.com \
--to=oleg@redhat.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=peterz@infradead.org \
--cc=y-goto@jp.fujitsu.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).