Re: futex question

From: Thomas Gleixner <tglx@linutronix.de>
To: Anirban Sinha <ani@anirban.org>
Cc: Ingo Molnar <mingo@elte.hu>,
	linux-kernel@vger.kernel.org, Darren Hart <dvhltc@us.ibm.com>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Kaz Kylheku <kaz@zeugmasystems.com>,
	Anirban Sinha <asinha@zeugmasystems.com>
Subject: Re: futex question
Date: Sun, 4 Oct 2009 18:59:46 +0200 (CEST)	[thread overview]
Message-ID: <alpine.LFD.2.00.0910041853180.2646@localhost.localdomain> (raw)
In-Reply-To: <4AC8CF32.8060108@anirban.org>

On Sun, 4 Oct 2009, Anirban Sinha wrote:

> >> 1) What caused you to instrument this path in the first place?  Were you
> >> seeing some unexpected behavior?
> >>
> >> 2) I wonder why we would need to clear the robust list, but I don't see other
> >> things like pi_blocked_on, etc. in execve being cleared.  I'm looking into
> >> this now (perhaps we don't do the same cleanup, need to check).... have to get
> >> on the plane...
> > 
> > Hmm, just setting the robust list pointer to NULL fixes the problem at
> > hand, but I wonder whether we need to call exit_robust_list() as
> > well. 

> hmm. That is an interesting thought. But I wonder if acquiring a
> lock and then exec()ing in the critical section is a legal thing to

It's definitely legal. There is no law which forbids to do that. :)

> do. It does not feel right. Currently, with or without my change,
> such a thing would indefinitely block other waiters on the same
> futex.

Right. Which completely defeats the purpose of the robust list. Will
have a look tomorrow.

Thanks,

	tglx