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
prev parent 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).