linux-kernel - Re: [PATCH] intel-pstate: Update frequencies of policy->cpus only from ->set

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]

Date:	Mon, 22 Feb 2016 13:54:57 +0100
From:	"Rafael J. Wysocki" <rafael@...nel.org>
To:	Viresh Kumar <viresh.kumar@...aro.org>
Cc:	"Chen, Yu C" <yu.c.chen@...el.com>,
	"linaro-kernel@...ts.linaro.org" <linaro-kernel@...ts.linaro.org>,
	"linux-pm@...r.kernel.org" <linux-pm@...r.kernel.org>,
	Joonas Lahtinen <joonas.lahtinen@...ux.intel.com>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	Rafael Wysocki <rjw@...ysocki.net>,
	Srinivas Pandruvada <srinivas.pandruvada@...ux.intel.com>,
	Len Brown <lenb@...nel.org>
Subject: Re: [PATCH] intel-pstate: Update frequencies of policy->cpus only
 from ->set_policy()

On Mon, Feb 22, 2016 at 12:27 PM, Viresh Kumar <viresh.kumar@...aro.org> wrote:
> Hi,
>
> I am not really an intel-pstate driver guy, just wrote the patch based
> on software-review of the stuff :)
>
> On 22-02-16, 10:17, Chen, Yu C wrote:
>> IIRC,
>> 1.HWP is  hardwarely per-package, CPUs inside one package have one shared HWP.
>> 2.Currently all the CPUs share the same HWP settings according to intel_pstate design.
>> 3.  The policy is per-cpu in intel_pstate driver.(policy->cpus only contains one cpu)
>>
>> So with this patch applied,  it is likely CPUs may have different HWP settings?
>
> I think the hardware should be able to cope with that, and should be
> selecting the frequency based on the highest frequency requested for
> the same package. Otherwise, why should there be an option to supply
> per-cpu settings ?

Right.

I can easily imagine a use case in which someone may want to have
different ranges for different CPUs.

>> For example:
>> CPU 0 belongs to package A with policy 0, and CPU 1 belongs to package B with policy 1,
>> If you change the policy 0 from powersave to performance, then only CPU0 will update its
>> min/max freq in HWP, however we should also update CPU 2's min/max in HWP settings?
>> Plz correct me  if I'm wrong..
>
> I will let the official intel-pstate guys reply to that.

My opinion is to do what your patch does until that proves to be a
problem in practice.

Thanks,
Rafael