linux-kernel - Re: [Question]: about 'cpuinfo_cur_freq' shown in sysfs when the CPU is in idle state

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: <20200603104017.GD7259@bogus>
Date:   Wed, 3 Jun 2020 11:40:17 +0100
From:   Sudeep Holla <sudeep.holla@....com>
To:     Viresh Kumar <viresh.kumar@...aro.org>
Cc:     Xiongfeng Wang <wangxiongfeng2@...wei.com>, rjw@...ysocki.net,
        guohanjun@...wei.com, ionela.voinescu@....com,
        linux-pm@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [Question]: about 'cpuinfo_cur_freq' shown in sysfs when the CPU
 is in idle state

On Wed, Jun 03, 2020 at 03:51:59PM +0530, Viresh Kumar wrote:
> On 03-06-20, 11:17, Sudeep Holla wrote:
> > On Wed, Jun 03, 2020 at 03:40:10PM +0530, Viresh Kumar wrote:
> > > On 03-06-20, 11:07, Sudeep Holla wrote:
> > > > But I have another question. If we can detect that CPPC on some platforms
> > > > rely on CPU registers(I assume FFH registers here and not system/io/...
> > > > type of GAS registers), can we set dvfs_on_any_cpu(can't recall exact
> > > > flag name) to false if not already done to prevent such issues. Or I am
> > > > talking non-sense as it may be applicable only for _set operation and
> > >
> > >           Yes, non-sense :)
> > >
> >
> > Thanks for confirming 👍.
>
> Hehe.
>
> So, do you agree that we better do the read from the CPUs themselves ?
>

Yes if that is fine. I thought waking up the core was not a good solution
in terms of power, but I have no objection for that as well as return 0
as IMO it aligns with the AMU counters when CPU is idle.

--
Regards,
Sudeep