devicetree.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Viresh Kumar <viresh.kumar@linaro.org>
To: Lukasz Luba <lukasz.luba@arm.com>
Cc: Nicola Mazzucato <nicola.mazzucato@arm.com>,
	linux-kernel@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org, linux-pm@vger.kernel.org,
	devicetree@vger.kernel.org, sudeep.holla@arm.com,
	rjw@rjwysocki.net, vireshk@kernel.org, robh+dt@kernel.org,
	sboyd@kernel.org, nm@ti.com, daniel.lezcano@linaro.org,
	morten.rasmussen@arm.com, chris.redpath@arm.com
Subject: Re: [PATCH v3 3/3] [RFC] CPUFreq: Add support for cpu-perf-dependencies
Date: Fri, 6 Nov 2020 16:25:14 +0530	[thread overview]
Message-ID: <20201106105514.bhtdklyhn7goml64@vireshk-i7> (raw)
In-Reply-To: <0a334a73-45ef-58ff-7dfd-9df6f4ff290a@arm.com>

On 06-11-20, 10:37, Lukasz Luba wrote:
> Good question.
> 
> How about a different interface for those cpufreq drivers?
> That new registration API would allow to specify the cpumask.
> Or rely on EM cpumask: em_span_cpus(em)
> 
> Currently we have two ways to register cooling device:
> 1. when the cpufreq driver set a flag CPUFREQ_IS_COOLING_DEV, the core
> will register cooling device
> 2. cpufreq driver can explicitly call the registration function:
> cpufreq_cooling_register() with 'policy' as argument
> 
> That would need substantial change to the cpufreq cooling code, from
> policy oriented to custom driver's cpumask (like EM registration).

I am even wondering if we should really make that change. Why do we
need the combined load of the CPUs to be sent back to the IPA governor
? Why shouldn't they all do that (they == cdev) ?

This is a bit confusing to me, sorry about that. The cpufreq governors
take a look at all the CPUs utilization and set the frequency based on
the highest utilization (and not the total util).

While in this case we present the total load of the CPUs to the IPA
(based on the current frequency of the CPUs), in response to which it
tells us the frequency at which all the CPUs of the policy can run at
(I am not even sure if it is the right thing to do as the CPUs have
different loads). And how do we fit this dependent_cpus thing into
this.

Sorry, I am not sure what's the right way of doing thing here.

-- 
viresh

  reply	other threads:[~2020-11-06 10:55 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-02 12:01 [PATCH v3 0/3] CPUFreq: Add support for cpu performance dependencies Nicola Mazzucato
2020-11-02 12:01 ` [PATCH v3 1/3] dt-bindings/opp: Update documentation for opp-shared Nicola Mazzucato
2020-11-02 12:01 ` [PATCH v3 2/3] opp/of: Allow empty opp-table with opp-shared Nicola Mazzucato
2020-11-03  5:01   ` Viresh Kumar
2020-11-04 17:54     ` Nicola Mazzucato
2020-11-05  4:41       ` Viresh Kumar
2020-11-16 11:45         ` Nicola Mazzucato
2020-11-02 12:01 ` [PATCH v3 3/3] [RFC] CPUFreq: Add support for cpu-perf-dependencies Nicola Mazzucato
2020-11-06  9:20   ` Viresh Kumar
2020-11-06 10:37     ` Lukasz Luba
2020-11-06 10:55       ` Viresh Kumar [this message]
2020-11-06 11:14         ` Lukasz Luba
2020-11-09  6:57           ` Viresh Kumar
2020-11-16 11:33             ` Lukasz Luba
2020-11-17 10:11               ` Viresh Kumar
2020-11-17 10:47                 ` Nicola Mazzucato
2020-11-17 10:53                   ` Viresh Kumar
2020-11-17 13:06                     ` Rafael J. Wysocki
2020-11-18  4:42                       ` Viresh Kumar
2020-11-18 12:00                         ` Rafael J. Wysocki
2020-11-19  6:40                           ` Viresh Kumar
2020-11-17 10:47                 ` Lukasz Luba
2020-11-17 10:55                   ` Viresh Kumar
2020-11-06  9:24   ` Viresh Kumar
2020-11-19  6:43   ` Viresh Kumar
2020-11-03 10:18 ` [PATCH v3 0/3] CPUFreq: Add support for cpu performance dependencies Viresh Kumar
2020-11-04 18:04   ` Nicola Mazzucato
2020-11-05 14:25     ` Vincent Guittot
2020-11-05 15:46       ` Ionela Voinescu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20201106105514.bhtdklyhn7goml64@vireshk-i7 \
    --to=viresh.kumar@linaro.org \
    --cc=chris.redpath@arm.com \
    --cc=daniel.lezcano@linaro.org \
    --cc=devicetree@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=lukasz.luba@arm.com \
    --cc=morten.rasmussen@arm.com \
    --cc=nicola.mazzucato@arm.com \
    --cc=nm@ti.com \
    --cc=rjw@rjwysocki.net \
    --cc=robh+dt@kernel.org \
    --cc=sboyd@kernel.org \
    --cc=sudeep.holla@arm.com \
    --cc=vireshk@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).