mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: Kent Overstreet <koverstreet@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>,
	srivatsa.bhat@linux.vnet.ibm.com, rusty@rustcorp.com.au,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH] generic dynamic per cpu refcounting
Date: Mon, 28 Jan 2013 13:18:32 -0800	[thread overview]
Message-ID: <20130128211832.GK22465@mtj.dyndns.org> (raw)
In-Reply-To: <20130128205540.GE26407@google.com>

Hello, Kent.

On Mon, Jan 28, 2013 at 12:55:40PM -0800, Kent Overstreet wrote:
> > I don't understand why we need two stages. What prevents the killing
> > thread from fetching percpu counters after dying passes one
> > synchronize_sched()?
> 
> It does. The second synchronize_sched() is needed after we set state :=
> dead, and before we drop the initial ref. Otherwise the ref could hit 0
> before percpu_ref_put knows to check for it.

Still a bit confused.  Why do we need to make the two steps separate?
What prevents us from doing the following?

	set dying;
	synchronize_sched();
	collect percpu refs into global atomic_t;
	put the base ref;

Thanks.

-- 
tejun

  reply	other threads:[~2013-01-28 21:18 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20130124232024.GA584@google.com>
2013-01-25 18:09 ` Oleg Nesterov
2013-01-25 18:29   ` Oleg Nesterov
2013-01-28 18:10     ` Kent Overstreet
2013-01-28 18:50       ` Oleg Nesterov
2013-01-25 19:11   ` Oleg Nesterov
2013-01-28 18:15     ` Kent Overstreet
2013-01-28 18:27       ` Tejun Heo
2013-01-28 18:49         ` Kent Overstreet
2013-01-28 18:55           ` Tejun Heo
2013-01-28 20:22             ` Kent Overstreet
2013-01-28 20:27               ` Tejun Heo
2013-01-28 20:55                 ` Kent Overstreet
2013-01-28 21:18                   ` Tejun Heo [this message]
2013-01-28 21:24                     ` Kent Overstreet
2013-01-28 21:28                       ` Tejun Heo
2013-01-28 21:36                         ` Tejun Heo
2013-01-28 21:48                           ` Kent Overstreet
2013-01-28 21:45                         ` Kent Overstreet
2013-01-28 21:50                           ` Tejun Heo
2013-01-29 16:39                             ` Kent Overstreet
2013-01-29 19:29                               ` Tejun Heo
2013-01-29 19:51                                 ` Kent Overstreet
2013-01-29 20:02                                   ` Tejun Heo
2013-01-29 21:45                                     ` Kent Overstreet
2013-01-29 22:06                                       ` Tejun Heo
2013-01-29 18:04                             ` [PATCH] module: Convert to generic percpu refcounts Kent Overstreet
2013-01-28 18:07   ` [PATCH] generic dynamic per cpu refcounting Kent Overstreet

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=20130128211832.GK22465@mtj.dyndns.org \
    --to=tj@kernel.org \
    --cc=koverstreet@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=oleg@redhat.com \
    --cc=rusty@rustcorp.com.au \
    --cc=srivatsa.bhat@linux.vnet.ibm.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
all inboxes | Powered by JetHome®