linux-kernel - Re: [PATCH] sched: Do not release current rq lock on non contended double_lock

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] [day] [month] [year] [list]

Date:	Wed, 15 Jun 2016 12:13:53 -0400
From:	Steven Rostedt <rostedt@...dmis.org>
To:	Peter Zijlstra <peterz@...radead.org>
Cc:	LKML <linux-kernel@...r.kernel.org>,
	Ingo Molnar <mingo@...nel.org>,
	Thomas Gleixner <tglx@...utronix.de>,
	Clark Williams <williams@...hat.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Nick Piggin <nickpiggin@...oo.com.au>
Subject: Re: [PATCH] sched: Do not release current rq lock on non contended
 double_lock_balance()

On Wed, 15 Jun 2016 13:14:53 +0200
Peter Zijlstra <peterz@...radead.org> wrote:

> OK, so should not the whole HAVE_RT_PUSH_IPI thing have avoided that
> loop entirely? And therefore made the point moot?

I believe there was another issue that we had in our tests. But I don't
have the trace available with me. I'll rerun the tests when I get back
home and have some more concrete examples for you.

> 
> In any case, can't we add another cpupri for pushable tasks and use that
> to find the highest priority task to pull and avoid the loop thus?

I thought about this too, but I was a bit concerned about complexities
this would add. But I can look into it. Currently I'm in NYC for
personal reasons and will take a look at this when I get back.

-- Steve