From: Dietmar Eggemann <dietmar.eggemann@arm.com>
To: Viresh Kumar <viresh.kumar@linaro.org>,
Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>,
"Rafael J. Wysocki" <rafael@kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Linux PM <linux-pm@vger.kernel.org>,
Russell King - ARM Linux <linux@arm.linux.org.uk>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Russell King <rmk+kernel@armlinux.org.uk>,
Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will.deacon@arm.com>,
Juri Lelli <juri.lelli@arm.com>,
Vincent Guittot <vincent.guittot@linaro.org>,
Morten Rasmussen <morten.rasmussen@arm.com>
Subject: Re: [PATCH v2 02/10] cpufreq: provide data for frequency-invariant load-tracking support
Date: Mon, 10 Jul 2017 11:31:35 +0100 [thread overview]
Message-ID: <5879943c-00f4-6148-411d-a71acced5eaa@arm.com> (raw)
In-Reply-To: <20170710094209.GJ2928@vireshk-i7>
On 10/07/17 10:42, Viresh Kumar wrote:
> On 10-07-17, 11:30, Peter Zijlstra wrote:
>> On Sat, Jul 08, 2017 at 02:09:37PM +0200, Rafael J. Wysocki wrote:
>>> Anyway, if everyone agrees that doing it in the core is the way to go (Peter?),
>>> why don't you introduce a __weak function for setting policy->cur and
>>> override it from your arch so as to call arch_set_freq_scale() from there?
>>>
>>
>> So I'm terminally backlogged and my recent break didn't help any with
>> that.
>>
>> I'm at a total loss as to what is proposed here and why we need it. I
>> tried reading both the Changelog and patch but came up empty.
>
> Dietmar is proposing the implementation of arch_set_freq_scale() for ARM (32/64)
> platforms here with following equation in drivers/base/arch_topology.c:
>
> scale = (cur_freq << SCHED_CAPACITY_SHIFT) / max_freq
>
> The only variable part here is "cur_freq" and he is looking for sane ways to get
> that value in the arch_topology.c file, so he can use that in the above
> equation. He tried to use cpufreq transition notifiers earlier but they block us
> from using fast switching.
>
> What he is proposing now is a function:
>
> void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
> unsigned long max_freq);
>
> which has to be called by someone after the frequency of the CPU is changed.
>
> Dietmar proposed that this be called by cpufreq core and Rafael was wondering if
> the cpufreq drivers should call it. Dietmar's argument is that it will be used
> for the entire ARM architecture this way and wouldn't lead to redundant core
> across drivers.
>
> Hope I didn't confuse you more with this :)
>
Perfect summary, thanks Viresh!
This is required for architectures (like arm/arm64) which do not have
any other way to know about the current CPU frequency.
X86 can do the frequency invariance support based on APERF/MPERF already
today so it does not need the support from cpufreq.
next prev parent reply other threads:[~2017-07-10 10:31 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-07-06 9:49 [PATCH v2 00/10] arm, arm64: frequency- and cpu-invariant accounting support for task scheduler Dietmar Eggemann
2017-07-06 9:49 ` [PATCH v2 01/10] drivers base/arch_topology: free cpumask cpus_to_visit Dietmar Eggemann
2017-07-06 10:22 ` Viresh Kumar
2017-07-06 10:59 ` Juri Lelli
2017-07-06 11:15 ` Viresh Kumar
2017-07-07 15:50 ` Dietmar Eggemann
2017-07-06 9:49 ` [PATCH v2 02/10] cpufreq: provide data for frequency-invariant load-tracking support Dietmar Eggemann
2017-07-06 10:40 ` Viresh Kumar
2017-07-06 22:38 ` Rafael J. Wysocki
2017-07-07 16:01 ` Dietmar Eggemann
2017-07-07 16:18 ` Rafael J. Wysocki
2017-07-07 17:06 ` Dietmar Eggemann
2017-07-08 12:09 ` Rafael J. Wysocki
2017-07-10 6:54 ` Viresh Kumar
2017-07-10 12:46 ` Rafael J. Wysocki
2017-07-11 6:39 ` Viresh Kumar
2017-07-11 15:21 ` Dietmar Eggemann
2017-07-13 12:40 ` Sudeep Holla
2017-07-13 13:08 ` Dietmar Eggemann
2017-07-13 14:06 ` Sudeep Holla
2017-07-10 9:30 ` Peter Zijlstra
2017-07-10 9:42 ` Viresh Kumar
2017-07-10 10:31 ` Dietmar Eggemann [this message]
2017-07-10 12:02 ` Dietmar Eggemann
2017-07-11 6:01 ` Viresh Kumar
2017-07-11 15:06 ` Dietmar Eggemann
2017-07-11 14:59 ` Rafael J. Wysocki
2017-07-11 15:12 ` Dietmar Eggemann
2017-07-12 4:09 ` Viresh Kumar
2017-07-12 8:31 ` Peter Zijlstra
2017-07-12 9:27 ` Viresh Kumar
2017-07-12 11:14 ` Peter Zijlstra
2017-07-12 23:13 ` Rafael J. Wysocki
2017-07-13 7:49 ` Peter Zijlstra
2017-07-13 8:48 ` Viresh Kumar
2017-07-13 11:15 ` Peter Zijlstra
2017-07-13 14:04 ` Sudeep Holla
2017-07-13 14:42 ` Peter Zijlstra
2017-07-13 15:00 ` Sudeep Holla
2017-07-13 12:54 ` Sudeep Holla
2017-07-13 12:49 ` Sudeep Holla
2017-07-10 6:40 ` Viresh Kumar
2017-07-06 9:49 ` [PATCH v2 03/10] drivers base/arch_topology: " Dietmar Eggemann
2017-07-06 10:45 ` Viresh Kumar
2017-07-07 16:51 ` Dietmar Eggemann
2017-07-06 9:49 ` [PATCH v2 04/10] arm: wire cpufreq input data for frequency-invariant accounting up to the arch Dietmar Eggemann
2017-07-06 10:42 ` Viresh Kumar
2017-07-10 15:13 ` Dietmar Eggemann
2017-07-11 6:32 ` Viresh Kumar
2017-07-06 9:49 ` [PATCH v2 05/10] arm: wire frequency-invariant accounting support up to the task scheduler Dietmar Eggemann
2017-07-06 10:46 ` Viresh Kumar
2017-07-06 9:49 ` [PATCH v2 06/10] arm: wire cpu-invariant " Dietmar Eggemann
2017-07-06 10:47 ` Viresh Kumar
2017-07-06 9:49 ` [PATCH v2 07/10] arm64: wire cpufreq input data for frequency-invariant accounting up to the arch Dietmar Eggemann
2017-07-06 10:48 ` Viresh Kumar
2017-07-06 9:49 ` [PATCH v2 08/10] arm64: wire frequency-invariant accounting support up to the task scheduler Dietmar Eggemann
2017-07-06 10:48 ` Viresh Kumar
2017-07-06 9:49 ` [PATCH v2 09/10] arm64: wire cpu-invariant " Dietmar Eggemann
2017-07-06 10:49 ` Viresh Kumar
2017-07-06 9:49 ` [PATCH v2 10/10] drivers base/arch_topology: inline cpu- and frequency-invariant accounting Dietmar Eggemann
2017-07-06 10:57 ` Viresh Kumar
2017-07-10 15:17 ` Dietmar Eggemann
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=5879943c-00f4-6148-411d-a71acced5eaa@arm.com \
--to=dietmar.eggemann@arm.com \
--cc=catalin.marinas@arm.com \
--cc=gregkh@linuxfoundation.org \
--cc=juri.lelli@arm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=linux@arm.linux.org.uk \
--cc=morten.rasmussen@arm.com \
--cc=peterz@infradead.org \
--cc=rafael@kernel.org \
--cc=rjw@rjwysocki.net \
--cc=rmk+kernel@armlinux.org.uk \
--cc=vincent.guittot@linaro.org \
--cc=viresh.kumar@linaro.org \
--cc=will.deacon@arm.com \
/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).