linux-kernel - Re: [PATCH] nohz_full: Make sched_should_stop

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: <571E8C6F.8010701@mellanox.com>
Date:	Mon, 25 Apr 2016 17:30:23 -0400
From:	Chris Metcalf <cmetcalf@...lanox.com>
To:	Peter Zijlstra <peterz@...radead.org>,
	Wanpeng Li <kernellwp@...il.com>
CC:	Rik van Riel <riel@...hat.com>,
	Frederic Weisbecker <fweisbec@...il.com>,
	Christoph Lameter <cl@...ux.com>,
	Ingo Molnar <mingo@...nel.org>,
	Luiz Capitulino <lcapitulino@...hat.com>,
	Thomas Gleixner <tglx@...utronix.de>,
	Viresh Kumar <viresh.kumar@...aro.org>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] nohz_full: Make sched_should_stop_tick() more
 conservative

On 4/21/2016 12:03 PM, Peter Zijlstra wrote:
> On Thu, Apr 21, 2016 at 04:42:13PM +0200, Peter Zijlstra wrote:
>
>> So I think that is indeed the right thing here. But looking at this
>> function I think there's more problems with it.
>>
>> It seems to assume that if there's FIFO tasks, those will run. This is
>> incorrect. The FIFO task can have a lower prio than an RR task, in which
>> case the RR task will run.
>>
>> So the whole fifo_nr_running test seems misplaced, it should go after
>> the rr_nr_running tests. That is, only if !rr_nr_running, can we use
>> fifo_nr_running like this.
> A little something like so perhaps; can anybody test?

Tested-by: Chris Metcalf <cmetcalf@...lanox.com>

To be clear, I only tested that it fixed my original bug, where we weren't
kicking a remote cpu when we should have been; I have not tested that
it works properly in the presence of RR or FIFO scheduled tasks.

But this or something like it should definitely go into 4.6 before it's done.

-- 
Chris Metcalf, Mellanox Technologies
http://www.mellanox.com