linux-kernel - Re: [tip:core/locking] x86/smp: Move waiting on contended ticket lock out of line

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: <512FC89B.6030507@redhat.com>
Date:	Thu, 28 Feb 2013 16:14:03 -0500
From:	Rik van Riel <riel@...hat.com>
To:	Linus Torvalds <torvalds@...ux-foundation.org>
CC:	Davidlohr Bueso <davidlohr.bueso@...com>,
	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
	Thomas Gleixner <tglx@...utronix.de>,
	Steven Rostedt <rostedt@...dmis.org>,
	"Vinod, Chegu" <chegu_vinod@...com>,
	"Low, Jason" <jason.low2@...com>,
	linux-tip-commits@...r.kernel.org,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	"H. Peter Anvin" <hpa@...or.com>,
	Andrew Morton <akpm@...ux-foundation.org>, aquini@...hat.com,
	Michel Lespinasse <walken@...gle.com>,
	Ingo Molnar <mingo@...nel.org>,
	Larry Woodman <lwoodman@...hat.com>
Subject: Re: [tip:core/locking] x86/smp: Move waiting on contended ticket
 lock out of line

On 02/28/2013 03:26 PM, Linus Torvalds wrote:
> On Thu, Feb 28, 2013 at 10:22 AM, Linus Torvalds
> <torvalds@...ux-foundation.org> wrote:
>>
>> I'm sure there are other things we could do to improve ipc lock times
>> even if we don't actually split the lock, but the security one might
>> be a good first step.
>
> Btw, if somebody has a benchmark for threads using multiple ipc
> semaphores (from the same semget() allocation) concurrently, and we
> could have a simple way to see the contention without having to run
> some big DB thing, that would also be nice. Maybe there is something
> out there already? Google didn't find any, and the normal benchmarks
> I'm aware of all just do one single (private) ipc semaphore per
> process.
>
> Nothing gets some people going like just having a nice benchmark to
> show the effect.

I have modified one of the semop tests to use multiple semaphores.

To run the test, specify the number of threads.  If you want the
number of semaphores to be different from the number of threads,
specify a second commandline argument.

$ ./semop-multi
usage: ./semop-multi <threads> [nsems]


View attachment "semop-multi.c" of type "text/x-csrc" (4047 bytes)