public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Roman Gushchin <klamm@yandex-team.ru>
Cc: bsegall@google.com, linux-kernel@vger.kernel.org, pjt@google.com,
	chris.j.arges@canonical.com, gregkh@linuxfoundation.org
Subject: Re: [PATCH] sched: tg_set_cfs_bandwidth() causes rq->lock deadlock
Date: Mon, 19 May 2014 12:32:47 +0200	[thread overview]
Message-ID: <20140519103247.GX30445@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <87lhu215ky.wl%klamm@yandex-team.ru>

[-- Attachment #1: Type: text/plain, Size: 830 bytes --]

On Fri, May 16, 2014 at 12:38:21PM +0400, Roman Gushchin wrote:

> I still think, there is a deadlock. I'll try to explain.
> Three CPUs must be involved:
> CPU0				CPU1				CPU2
> take rq->lock			period timer fired		
> ...				take cfs_b lock
> ...				...				tg_set_cfs_bandwidth()
> throttle_cfs_rq()		release cfs_b lock		take cfs_b lock
> ...				distribute_cfs_runtime()	timer_active = 0
> take cfs_b->lock		wait for rq->lock		...
> __start_cfs_bandwidth()	
> {wait for timer callback
>  break if timer_active == 1}
> 
> So, CPU0 and CPU1 are deadlocked.

OK, so can someone explain this ->timer_active thing? esp. what's the
'obvious' difference with hrtimer_active()?


Ideally we'd change the lot to not have this, but if we have to keep it
we'll need to make it lockdep visible because all this stinks

[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]

  parent reply	other threads:[~2014-05-19 10:32 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-05-15 16:58 [PATCH] sched: tg_set_cfs_bandwidth() causes rq->lock deadlock Roman Gushchin
2014-05-15 17:43 ` bsegall
2014-05-16  8:38   ` Roman Gushchin
2014-05-16 17:57     ` bsegall
2014-05-19 11:10       ` Roman Gushchin
2014-05-19 17:40         ` bsegall
2014-05-19 10:32     ` Peter Zijlstra [this message]
2014-05-19 11:37       ` Roman Gushchin
2014-05-19 17:35         ` bsegall
2014-05-19 17:30       ` bsegall
2014-05-20 13:15         ` Peter Zijlstra
2014-05-20 14:01           ` Peter Zijlstra
2014-05-20 14:55             ` Peter Zijlstra
2014-05-20 14:21           ` Roman Gushchin
2014-05-20 14:28             ` Peter Zijlstra
2014-05-20 14:34               ` Roman Gushchin
2014-05-20 19:08           ` bsegall
2014-05-21  7:58             ` Peter Zijlstra
2014-05-19 10:40   ` Peter Zijlstra

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=20140519103247.GX30445@twins.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=bsegall@google.com \
    --cc=chris.j.arges@canonical.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=klamm@yandex-team.ru \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pjt@google.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