From: "Gautham R. Shenoy" <gautham.shenoy@amd.com>
To: Mario Limonciello <mario.limonciello@amd.com>
Cc: Perry Yuan <perry.yuan@amd.com>,
linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org,
Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com>,
Peter Jung <ptr1337@cachyos.org>
Subject: Re: [PATCH 1/4] cpufreq/amd-pstate: Use nominal perf for limits when boost is disabled
Date: Wed, 16 Oct 2024 09:40:40 +0530 [thread overview]
Message-ID: <Zw88wPX6WqCRYyRt@BLRRASHENOY1.amd.com> (raw)
In-Reply-To: <20241012174519.897-1-mario.limonciello@amd.com>
Hello Mario,
On Sat, Oct 12, 2024 at 12:45:16PM -0500, Mario Limonciello wrote:
> When boost has been disabled the limit for perf should be nominal perf not
> the highest perf. Using the latter to do calculations will lead to
> incorrect values that are still above nominal.
>
> Fixes: ad4caad58d91 ("cpufreq: amd-pstate: Merge amd_pstate_highest_perf_set() into amd_get_boost_ratio_numerator()")
> Reported-by: Peter Jung <ptr1337@cachyos.org>
> Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219348
> Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
The patch looks good to me.
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
--
Thanks and Regards
gautham.
> ---
> drivers/cpufreq/amd-pstate.c | 20 ++++++++++++++------
> 1 file changed, 14 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index 30415c30d8b4..dfa9a146769b 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -536,11 +536,16 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy)
>
> static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
> {
> - u32 max_limit_perf, min_limit_perf, lowest_perf;
> + u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf;
> struct amd_cpudata *cpudata = policy->driver_data;
>
> - max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
> - min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
> + if (cpudata->boost_supported && !policy->boost_enabled)
> + max_perf = READ_ONCE(cpudata->nominal_perf);
> + else
> + max_perf = READ_ONCE(cpudata->highest_perf);
> +
> + max_limit_perf = div_u64(policy->max * max_perf, policy->cpuinfo.max_freq);
> + min_limit_perf = div_u64(policy->min * max_perf, policy->cpuinfo.max_freq);
>
> lowest_perf = READ_ONCE(cpudata->lowest_perf);
> if (min_limit_perf < lowest_perf)
> @@ -1506,10 +1511,13 @@ static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
> u64 value;
> s16 epp;
>
> - max_perf = READ_ONCE(cpudata->highest_perf);
> + if (cpudata->boost_supported && !policy->boost_enabled)
> + max_perf = READ_ONCE(cpudata->nominal_perf);
> + else
> + max_perf = READ_ONCE(cpudata->highest_perf);
> min_perf = READ_ONCE(cpudata->lowest_perf);
> - max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
> - min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
> + max_limit_perf = div_u64(policy->max * max_perf, policy->cpuinfo.max_freq);
> + min_limit_perf = div_u64(policy->min * max_perf, policy->cpuinfo.max_freq);
>
> if (min_limit_perf < min_perf)
> min_limit_perf = min_perf;
> --
> 2.43.0
>
next prev parent reply other threads:[~2024-10-16 4:10 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-12 17:45 [PATCH 1/4] cpufreq/amd-pstate: Use nominal perf for limits when boost is disabled Mario Limonciello
2024-10-12 17:45 ` [PATCH 2/4] cpufreq/amd-pstate: Don't update CPPC request in amd_pstate_cpu_boost_update() Mario Limonciello
2024-10-16 4:42 ` Yuan, Perry
2024-10-16 9:50 ` Gautham R. Shenoy
2024-10-12 17:45 ` [PATCH 3/4] cpufreq/amd-pstate: Use amd_pstate_update_min_max_limit() for EPP limits Mario Limonciello
2024-10-16 4:38 ` Yuan, Perry
2024-10-16 10:14 ` Gautham R. Shenoy
2024-10-12 17:45 ` [PATCH 4/4] cpufreq/amd-pstate: Drop needless EPP initialization Mario Limonciello
2024-10-15 9:07 ` Dhananjay Ugwekar
2024-10-16 4:33 ` Yuan, Perry
2024-10-16 10:33 ` Gautham R. Shenoy
2024-10-16 4:10 ` Gautham R. Shenoy [this message]
2024-10-16 4:45 ` [PATCH 1/4] cpufreq/amd-pstate: Use nominal perf for limits when boost is disabled Yuan, Perry
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=Zw88wPX6WqCRYyRt@BLRRASHENOY1.amd.com \
--to=gautham.shenoy@amd.com \
--cc=Dhananjay.Ugwekar@amd.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=mario.limonciello@amd.com \
--cc=perry.yuan@amd.com \
--cc=ptr1337@cachyos.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