linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Viresh Kumar <viresh.kumar@linaro.org>
To: Bjorn Andersson <bjorn.andersson@linaro.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>,
	linux-arm-msm@vger.kernel.org, linux-pm@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH] cpufreq: qcom-hw: Add support for per-core-dcvs
Date: Thu, 24 Feb 2022 10:00:07 +0530	[thread overview]
Message-ID: <20220224043007.2s3jrwork4zxxlsq@vireshk-i7> (raw)
In-Reply-To: <20220210050117.747569-1-bjorn.andersson@linaro.org>

On 09-02-22, 21:01, Bjorn Andersson wrote:
> The OSM and EPSS hardware controls the frequency of each cluster in the
> system based on requests from the OS and various limiting factors, such
> as input from LMH.
> 
> In most systems the vote from the OS is done using a single register per
> cluster, but some systems are configured to instead take one request per
> core.  In this configuration a set of consecutive registers are used for
> the OS to request the frequency of each of the cores within the cluster.
> The information is then aggregated in the hardware and the frequency for
> the cluster is determined.
> 
> As the current implementation ends up only requesting a frequency for
> the first core in each cluster and only the vote of non-idle cores are
> considered it's often the case that the cluster will be clocked (much)
> lower than expected.
> 
> It's possible that there are benefits of performing the per-core
> requests from the OS, but more investigation of the outcome is needed
> before introducing such support. As such this patch extends the request
> for the cluster to be written to all the cores.
> 
> The weight of the policy's related_cpus is used to determine how many
> cores, and hence consecutive registers, each cluster has.
> 
> The OS is not permitted to disable the per-core dcvs feature.
> 
> Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
> ---
>  drivers/cpufreq/qcom-cpufreq-hw.c | 18 ++++++++++++++++++
>  1 file changed, 18 insertions(+)

Applied. Thanks.

-- 
viresh

      reply	other threads:[~2022-02-24  4:30 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-02-10  5:01 [PATCH] cpufreq: qcom-hw: Add support for per-core-dcvs Bjorn Andersson
2022-02-24  4:30 ` Viresh Kumar [this message]

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=20220224043007.2s3jrwork4zxxlsq@vireshk-i7 \
    --to=viresh.kumar@linaro.org \
    --cc=bjorn.andersson@linaro.org \
    --cc=linux-arm-msm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=rafael@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).