linux-kernel - Re: [PATCH] futex: avoid race between requeue and wake

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20140408181305.GT10526@twins.programming.kicks-ass.net>
Date:	Tue, 8 Apr 2014 20:13:05 +0200
From:	Peter Zijlstra <peterz@...radead.org>
To:	Linus Torvalds <torvalds@...ux-foundation.org>
Cc:	Jan Stancek <jstancek@...hat.com>,
	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
	Srikar Dronamraju <srikar@...ux.vnet.ibm.com>,
	Davidlohr Bueso <davidlohr@...com>,
	Ingo Molnar <mingo@...nel.org>,
	Larry Woodman <lwoodman@...hat.com>
Subject: Re: [PATCH] futex: avoid race between requeue and wake

On Tue, Apr 08, 2014 at 10:33:55AM -0700, Linus Torvalds wrote:
> Hmm. And let's think about that powerpc race, where "spin_is_locked()"
> can be false when somebody is waiting to get the lock..

Right; so in the original discussion I never really got to why that is a
problem. A pending waiter cannot modify the wait list, so either we see
the current holder, or we see a stable list.

So I had to hop on a plane while that discussion was happening and while
I did briefly task to Davidlohr in Napa his explanation didn't stick in
my jet-leg addled brain.

Afterwards the discussion got lost in the pile of unread mail.

I'll go re-read that discussion and look up this thread to see if
things will start to make sense.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/