linux-kernel - Re: [PATCH v2 12/17] PM: EM: Add argument to get

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: <18b1a981-79a0-13d7-bfba-2f1c0e554da9@arm.com>
Date:   Mon, 3 Jul 2023 16:30:13 +0100
From:   Lukasz Luba <lukasz.luba@....com>
To:     Dietmar Eggemann <dietmar.eggemann@....com>
Cc:     rui.zhang@...el.com, amit.kucheria@...durent.com,
        amit.kachhap@...il.com, daniel.lezcano@...aro.org,
        viresh.kumar@...aro.org, len.brown@...el.com, pavel@....cz,
        Pierre.Gondois@....com, ionela.voinescu@....com,
        rostedt@...dmis.org, mhiramat@...nel.org,
        linux-kernel@...r.kernel.org, linux-pm@...r.kernel.org,
        rafael@...nel.org
Subject: Re: [PATCH v2 12/17] PM: EM: Add argument to get_cost() for runtime
 modification



On 5/30/23 10:53, Dietmar Eggemann wrote:
> On 12/05/2023 11:57, Lukasz Luba wrote:
>> The Energy Model (EM) supports runtime modifications. Let also the
>> artificial EM use this new feature and allow to update the 'cost' values
>> at runtime. When the artificial EM is used there is a need to provide
>> two callbacks: get_cost() and update_power(), not only the last one.
>>
>> Update also CPPC driver code, since the new argument is needed there
>> to compile properly and register EM.
> 
> Is there a real use case behind this? It can't be mobile which IMHO
> drivers the rest of the 'Runtime modifiable EM' feature.

Correct, CPPC+EM is not for mobile phones, but notebooks. For now
the notebooks are not tested with that feature and were not in
requirement scope.

> 
> Do we know of any machine using the artificial EM. And do they care
> about EM matching workload or static power?
> 
> [...]

For now we don't know about such notebook which uses CPPC + EM
and if it's a candidate for this feature.

I thought, since it's just one patch w/ small change, it would be
consistent to not 'forget' about that notebooks angle. I know
that there are some folks who 'run'/'are willing to run' Arm laptop with
CPPC w/ artificial EM. They might pick that feature as well.