From: Esben Nielsen <simlo@phys.au.dk>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>, <linux-kernel@vger.kernel.org>,
<robustmutexes@lists.osdl.org>, <dino@in.ibm.com>,
David Singleton <dsingleton@mvista.com>
Subject: Re: robust futex deadlock detection patch
Date: Mon, 9 Jan 2006 22:19:08 +0100 (MET) [thread overview]
Message-ID: <Pine.LNX.4.44L0.0601092213580.19569-100000@lifa01.phys.au.dk> (raw)
In-Reply-To: <1136840886.6197.14.camel@localhost.localdomain>
On Mon, 9 Jan 2006, Steven Rostedt wrote:
> On Mon, 2006-01-09 at 21:16 +0100, Esben Nielsen wrote:
>
> > You only take the spinlocks corresponding to the current lock. What about
> > the next locks in the chain? Remember those locks might not be
> > futexes but a lock inside the kernel, taken in system calls. I.e. the
> > robust_sem might not protect you.
> > If there are n locks you need to lock n lock->wait_lock and n
> > owner->task->pi_lock as you traverse the locks. That is what I tried to
> > sketch in the examble below.
>
> The thing about this is that you can't (if the kernel is not buggy)
> deadlock on the kernel spin locks. As long as you protect the locks in
> the futex from deadlocking you are fine. This is because you don't grab
> a futex after grabbing a kernel spin lock. All kernel spin locks
> __must__ be released before going back to user land, and that's where
> you grab the futexes.
>
Yes, but the deadlock-detect code doesn't know what is a futex and what
isn't. Therefore when it starts to traverse rt_mutexes which aren't
futexes it has to be _very_ carefull taking the right spinlocks. On the
other hand when traversing the futexes it has to be carefull not to
deadlocks on those very same spinlocks.
And yes, you _can_ traverse the lock chain without deadlocking the kernel.
The code I sketched in the previouse mail should do it.
Anyway, I am trying to rewrite rt_mutex to remove the spinlock deadlock
altogether. My girlfriend is away with our daugther a few days so I might
get time to do finish it :-)
> -- Steve
>
>
Esben
prev parent reply other threads:[~2006-01-09 21:19 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-12-14 22:39 Recursion bug in -rt Dinakar Guniguntala
2005-12-15 1:03 ` david singleton
2005-12-15 19:44 ` Dinakar Guniguntala
2005-12-15 20:40 ` David Singleton
2005-12-16 0:02 ` david singleton
2005-12-16 18:42 ` Dinakar Guniguntala
2005-12-16 21:26 ` David Singleton
2005-12-19 11:56 ` Dinakar Guniguntala
2005-12-19 20:11 ` David Singleton
2005-12-15 19:00 ` David Singleton
2005-12-15 19:52 ` Dinakar Guniguntala
2005-12-20 13:19 ` Ingo Molnar
2005-12-20 15:50 ` Dinakar Guniguntala
2005-12-20 17:43 ` Esben Nielsen
2005-12-20 19:33 ` Steven Rostedt
2005-12-20 20:42 ` Esben Nielsen
2005-12-20 21:20 ` Steven Rostedt
2005-12-20 21:55 ` david singleton
2005-12-20 22:56 ` Esben Nielsen
2005-12-20 23:12 ` Steven Rostedt
2005-12-20 23:55 ` Esben Nielsen
2005-12-22 4:37 ` david singleton
2005-12-20 22:43 ` Esben Nielsen
2005-12-20 22:59 ` Steven Rostedt
2006-01-03 1:54 ` david singleton
2006-01-05 2:14 ` david singleton
2006-01-05 9:43 ` Esben Nielsen
2006-01-05 17:11 ` david singleton
2006-01-05 17:47 ` Esben Nielsen
2006-01-05 18:26 ` david singleton
2006-01-07 2:40 ` robust futex deadlock detection patch david singleton
[not found] ` <a36005b50601071145y7e2ead9an4a4ca7896f35a85e@mail.gmail.com>
2006-01-07 19:49 ` Ulrich Drepper
2006-01-09 9:23 ` Esben Nielsen
2006-01-09 20:01 ` David Singleton
2006-01-09 20:16 ` Esben Nielsen
2006-01-09 21:08 ` Steven Rostedt
2006-01-09 21:19 ` Esben Nielsen [this message]
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=Pine.LNX.4.44L0.0601092213580.19569-100000@lifa01.phys.au.dk \
--to=simlo@phys.au.dk \
--cc=dino@in.ibm.com \
--cc=dsingleton@mvista.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=robustmutexes@lists.osdl.org \
--cc=rostedt@goodmis.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
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).