From: Eric Wong <normalperson@yhbt.net>
To: "Arve Hjønnevåg" <arve@android.com>
Cc: NeilBrown <neilb@suse.de>, "Rafael J. Wysocki" <rjw@sisk.pl>,
linux-kernel@vger.kernel.org,
Davide Libenzi <davidel@xmailserver.org>,
Alexander Viro <viro@zeniv.linux.org.uk>,
linux-fsdevel@vger.kernel.org,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: epoll: possible bug from wakeup_source activation
Date: Sat, 9 Mar 2013 07:10:37 +0000 [thread overview]
Message-ID: <20130309071037.GA13360@dcvr.yhbt.net> (raw)
In-Reply-To: <CAMP5Xgc4-oX=-V57Mu5PARCWdfpkjck0VnZNAXH-JisvKi5tAg@mail.gmail.com>
Arve Hjønnevåg <arve@android.com> wrote:
> On Fri, Mar 8, 2013 at 12:49 PM, Eric Wong <normalperson@yhbt.net> wrote:
> > What happens if ep_modify calls ep_destroy_wakeup_source
> > while __pm_stay_awake is running on the same epi->ws?
>
> Yes, that looks like a problem. I think calling
> ep_destroy_wakeup_source with ep->lock held should fix that. It is not
> clear how useful changing EPOLLWAKEUP in ep_modify is, so
> alternatively we could remove that feature and instead only allow it
> to be set in ep_insert.
ep->lock would work, but ep->lock is already a source of heavy
contention in my multithreaded+epoll webservers.
Perhaps RCU can be used? I've no experience with RCU, but I've been
meaning to get acquainted with RCU.
Another possible solution is to only use ep->ws and add an atomic
counter to ep; so __pm_relax(ep->ws) is only called when the atomic
counter reaches zero.
next prev parent reply other threads:[~2013-03-09 7:10 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-03-07 11:26 epoll: possible bug from wakeup_source activation Eric Wong
2013-03-08 1:30 ` Eric Wong
2013-03-08 4:56 ` Arve Hjønnevåg
2013-03-08 20:49 ` Eric Wong
2013-03-09 4:09 ` Arve Hjønnevåg
2013-03-09 7:10 ` Eric Wong [this message]
2013-03-10 1:11 ` Eric Wong
2013-03-10 4:59 ` Eric Dumazet
2013-03-10 11:50 ` [PATCH] epoll: use RCU protect wakeup_source in epitem Eric Wong
2013-03-14 3:09 ` [PATCH mm] epoll: lock ep->mtx in ep_free to silence lockdep Eric Wong
2013-03-11 23:37 ` epoll: possible bug from wakeup_source activation Arve Hjønnevåg
2013-03-12 0:17 ` Eric Wong
2013-03-12 0:29 ` Arve Hjønnevåg
2013-03-12 0:44 ` Eric Wong
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=20130309071037.GA13360@dcvr.yhbt.net \
--to=normalperson@yhbt.net \
--cc=akpm@linux-foundation.org \
--cc=arve@android.com \
--cc=davidel@xmailserver.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=neilb@suse.de \
--cc=rjw@sisk.pl \
--cc=viro@zeniv.linux.org.uk \
/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