linux-kernel - Re: [PATCH RFC] x86 / CPU: Add cpu isolation flag for avoiding disturbance from aperfmperf IPI

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:   Thu, 25 Apr 2019 14:38:04 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Konstantin Khlebnikov <khlebnikov@...dex-team.ru>
Cc:     linux-kernel@...r.kernel.org, Len Brown <len.brown@...el.com>,
        Frederic Weisbecker <frederic@...nel.org>,
        "Rafael J. Wysocki" <rafael.j.wysocki@...el.com>,
        Ingo Molnar <mingo@...hat.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
Subject: Re: [PATCH RFC] x86 / CPU: Add cpu isolation flag for avoiding
 disturbance from aperfmperf IPI

On Thu, Apr 25, 2019 at 03:27:12PM +0300, Konstantin Khlebnikov wrote:
> On 25.04.2019 14:45, Peter Zijlstra wrote:
> > On Thu, Apr 25, 2019 at 01:46:51PM +0300, Konstantin Khlebnikov wrote:
> > > Sensitive workloads like DPDK polling do not like any interrupts.
> > > 
> > > This patch adds flag 'freq' for boot option 'isolcpu': isolcpu=freq,<cpus>.
> > > 
> > > Users like show_cpuinfo() fallback to frequency from generic cpufreq
> > > policy if arch-specific requesting method returns 0.
> > 
> > Then don't touch that sysfs file?
> 
> What sysfs file?

/sys/devices/system/cpu/cpu*/cpufreq/scaling_cur_freq

> I mean many applications read /proc/cpuinfo and this triggers IPI to all cpus.

Argh, I missed it was wired into that too :/

> > I really hate having an option for just this.
> > 
> 
> This could be generalized to 'isolate cpu from unnecessary IPI'.
> Something like mm pagevec drain also could be avoided.

Well, that should be a default feature of nohz full, no additional flags
required.