mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Jie Zhan <zhanjie9@hisilicon.com>
To: Penghe Geng <pgeng@nvidia.com>
Cc: Viresh Kumar <viresh.kumar@linaro.org>,
	Ionela Voinescu <ionela.voinescu@arm.com>,
	<linux-pm@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
	<stable@vger.kernel.org>, "Rafael J. Wysocki" <rafael@kernel.org>
Subject: Re: [PATCH] cpufreq: cppc: drop invariance when FIE is disabled
Date: Wed, 25 Feb 2026 12:08:06 +0800	[thread overview]
Message-ID: <a9cbeebf-4029-4eb0-b486-9615b03b3c93@hisilicon.com> (raw)
In-Reply-To: <20260220224920.416602-1-pgeng@nvidia.com>


On 2/21/2026 6:49 AM, Penghe Geng wrote:
> CONFIG_ACPI_CPPC_CPUFREQ_FIE gates CPPC counter-based frequency
> invariance support. When FIE is disabled, the CPPC driver does not
> register a frequency scale source, but cpufreq_register_driver() still
> enables cpufreq_freq_invariance for target/fast-switch drivers.
> 
> Disable cpufreq frequency invariance after CPPC driver registration when
> FIE is disabled. This avoids scheduler behavior mismatch when no
> invariance updates are provided, which can cause major performance
> regressions on sensitive platforms.
Hi Penghe,

IIUC, even if CPPC FIE is not there, cpufreq still updates frequency scales
in cpufreq_freq_transition_end() and cpufreq_driver_fast_switch(), so the
frequency scale number is still somewhat meaningful and the
'cpufreq_freq_invariance' static key reflects that correctly.

Any numbers or evidence of that "performance regressions" so that we can
understand the issue better?

Thanks,
Jie
> 
> Export cpufreq_disable_freq_invariance() so modular cppc_cpufreq can call
> it.
> 
> Fixes: 1eb5dde674f5 ("cpufreq: CPPC: Add support for frequency invariance")
> Cc: stable@vger.kernel.org
> Signed-off-by: Penghe Geng <pgeng@nvidia.com>
> ---
>  drivers/cpufreq/cppc_cpufreq.c | 4 ++++
>  drivers/cpufreq/cpufreq.c      | 8 ++++++++
>  include/linux/cpufreq.h        | 3 +++
>  3 files changed, 15 insertions(+)
> 
...

      reply	other threads:[~2026-02-25  4:08 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-20 22:49 Penghe Geng
2026-02-25  4:08 ` Jie Zhan [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=a9cbeebf-4029-4eb0-b486-9615b03b3c93@hisilicon.com \
    --to=zhanjie9@hisilicon.com \
    --cc=ionela.voinescu@arm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=pgeng@nvidia.com \
    --cc=rafael@kernel.org \
    --cc=stable@vger.kernel.org \
    --cc=viresh.kumar@linaro.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

all inboxes | Powered by JetHome®