LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Kirill Tkhai <tkhai@yandex.ru>
To: Juri Lelli <juri.lelli@gmail.com>, Peter Zijlstra <peterz@infradead.org>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"mingo@redhat.com" <mingo@redhat.com>,
	"stable@vger.kernel.org" <stable@vger.kernel.org>
Subject: Re: [PATCH] sched/dl: Fix race between dl_task_timer() and sched_setaffinity()
Date: Tue, 20 May 2014 13:33:42 +0400
Message-ID: <3056991400578422@web14g.yandex.ru> (raw)
In-Reply-To: <20140520101730.ab593e41d5ee5949740de52e@gmail.com>

20.05.2014, 12:16, "Juri Lelli" <juri.lelli@gmail.com>:
> Hi,
>
> On Tue, 20 May 2014 09:53:15 +0200
> Peter Zijlstra <peterz@infradead.org> wrote:
>
>>  On Tue, May 20, 2014 at 09:08:53AM +0400, Kirill Tkhai wrote:
>>>  20.05.2014, 04:00, "Peter Zijlstra" <peterz@infradead.org>:
>>>>  On Mon, May 19, 2014 at 11:31:19PM +0400, Kirill Tkhai wrote:
>>>>>   @@ -513,9 +513,17 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
>>>>>                                                         struct sched_dl_entity,
>>>>>                                                         dl_timer);
>>>>>            struct task_struct *p = dl_task_of(dl_se);
>>>>>   - struct rq *rq = task_rq(p);
>>>>>   + struct rq *rq;
>>>>>   +again:
>>>>>   + rq = task_rq(p);
>>>>>            raw_spin_lock(&rq->lock);
>>>>>
>>>>>   + if (unlikely(rq != task_rq(p))) {
>>>>>   + /* Task was moved, retrying. */
>>>>>   + raw_spin_unlock(&rq->lock);
>>>>>   + goto again;
>>>>>   + }
>>>>>   +
>>>>  That thing is called: rq = __task_rq_lock(p);
>>>  But p->pi_lock is not held. The problem is __task_rq_lock() has lockdep assert.
>>>  Should we change it?
>>  Ok, so now that I'm awake ;-)
>>
>>  So the trivial problem as described by your initial changelog isn't
>>  right, because we cannot call sched_setaffinity() on deadline tasks, or
>>  rather we can, but we can't actually change the affinity mask.
>
> Well, if we disable AC we can. And I was able to recreate that race in
> that case.
>
>>  Now I suppose the problem can still actually happen when you change the
>>  root domain and trigger a effective affinity change that way.
>
> Yeah, I think here too.
>
>>  That said, no leave it as you proposed, adding a *task_rq_lock() variant
>>  without lockdep assert in will only confuse things, as normally we
>>  really should be also taking ->pi_lock.
>>
>>  The only reason we don't strictly need ->pi_lock now is because we're
>>  guaranteed to have p->state == TASK_RUNNING here and are thus free of
>>  ttwu races.
>
> Maybe we could add this as part of the comment.

Peter, Juri, thanks for comment. Hope, I understood you right :)

[PATCH] sched/dl: Fix race in dl_task_timer()

Throttled task is still on rq, and it may be moved to other cpu
if user is playing with sched_setaffinity(). Therefore, unlocked
task_rq() access makes the race.

Juri Lelli reports he got this race when dl_bandwidth_enabled()
was not set.

Other thing, pointed by Peter Zijlstra:

   "Now I suppose the problem can still actually happen when
    you change the root domain and trigger a effective affinity
    change that way".

To fix that we do the same as made in __task_rq_lock(). We do not
use __task_rq_lock() itself, because it has a useful lockdep check,
which is not correct in case of dl_task_timer(). We do not need
pi_lock locked here. This case is an exception (PeterZ):

   "The only reason we don't strictly need ->pi_lock now is because
    we're guaranteed to have p->state == TASK_RUNNING here and are
    thus free of ttwu races".

Signed-off-by: Kirill Tkhai <tkhai@yandex.ru>
CC: Juri Lelli <juri.lelli@gmail.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Ingo Molnar <mingo@redhat.com>
Cc: <stable@vger.kernel.org> # v3.14
---
 kernel/sched/deadline.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 800e99b..14bc348 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -513,9 +513,17 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 						     struct sched_dl_entity,
 						     dl_timer);
 	struct task_struct *p = dl_task_of(dl_se);
-	struct rq *rq = task_rq(p);
+	struct rq *rq;
+again:
+	rq = task_rq(p);
 	raw_spin_lock(&rq->lock);
 
+	if (rq != task_rq(p)) {
+		/* Task was moved, retrying. */
+		raw_spin_unlock(&rq->lock);
+		goto again;
+	}
+
 	/*
 	 * We need to take care of a possible races here. In fact, the
 	 * task might have changed its scheduling policy to something

  reply index

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-05-16 21:30 Kirill Tkhai
2014-05-19 13:12 ` Juri Lelli
2014-05-19 19:31   ` Kirill Tkhai
2014-05-20  0:00     ` Peter Zijlstra
2014-05-20  5:08       ` Kirill Tkhai
2014-05-20  6:07         ` Kirill Tkhai
2014-05-20  7:53         ` Peter Zijlstra
2014-05-20  8:17           ` Juri Lelli
2014-05-20  9:33             ` Kirill Tkhai [this message]
2014-05-21  7:29               ` Peter Zijlstra
2014-06-05 14:33               ` [tip:sched/urgent] sched/dl: Fix race in dl_task_timer() tip-bot for Kirill Tkhai

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=3056991400578422@web14g.yandex.ru \
    --to=tkhai@yandex.ru \
    --cc=juri.lelli@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=stable@vger.kernel.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git