[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <bbbc09e9-4719-4a8a-b368-1b5aa67b6e76@amd.com>
Date: Wed, 5 Feb 2025 11:45:30 -0600
From: Mario Limonciello <mario.limonciello@....com>
To: Dhananjay Ugwekar <dhananjay.ugwekar@....com>
Cc: linux-kernel@...r.kernel.org, linux-pm@...r.kernel.org,
gautham.shenoy@....com, rafael@...nel.org, viresh.kumar@...aro.org
Subject: Re: [PATCH 03/12] cpufreq/amd-pstate: Modify the min_perf calculation
in adjust_perf callback
On 2/5/2025 05:25, Dhananjay Ugwekar wrote:
> Instead of setting a fixed floor at lowest_nonlinear_perf, use the
> min_limit_perf value, so that it gives the user the freedom to lower the
> floor further.
>
> There are two minimum frequency/perf limits that we need to consider in
> the adjust_perf callback. One provided by schedutil i.e. the sg_cpu->bw_min
> value passed in _min_perf arg, another is the effective value of
> min_freq_qos request that is updated in cpudata->min_limit_perf. Modify the
> code to use the bigger of these two values.
>
> Signed-off-by: Dhananjay Ugwekar <dhananjay.ugwekar@....com>
Reviewed-by: Mario Limonciello <mario.limonciello@....com>
I'll queue this for 6.15.
> ---
> drivers/cpufreq/amd-pstate.c | 12 ++++++------
> 1 file changed, 6 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index 9dc3933bc326..a23fb78a442b 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -672,7 +672,7 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
> unsigned long capacity)
> {
> unsigned long max_perf, min_perf, des_perf,
> - cap_perf, lowest_nonlinear_perf;
> + cap_perf, min_limit_perf;
> struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
> struct amd_cpudata *cpudata;
>
> @@ -684,20 +684,20 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
> if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq)
> amd_pstate_update_min_max_limit(policy);
>
> -
> cap_perf = READ_ONCE(cpudata->highest_perf);
> - lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
> + min_limit_perf = READ_ONCE(cpudata->min_limit_perf);
>
> des_perf = cap_perf;
> if (target_perf < capacity)
> des_perf = DIV_ROUND_UP(cap_perf * target_perf, capacity);
>
> - min_perf = READ_ONCE(cpudata->lowest_perf);
> if (_min_perf < capacity)
> min_perf = DIV_ROUND_UP(cap_perf * _min_perf, capacity);
> + else
> + min_perf = cap_perf;
>
> - if (min_perf < lowest_nonlinear_perf)
> - min_perf = lowest_nonlinear_perf;
> + if (min_perf < min_limit_perf)
> + min_perf = min_limit_perf;
>
> max_perf = cpudata->max_limit_perf;
> if (max_perf < min_perf)
Powered by blists - more mailing lists