Re: [PATCH v2 1/2] arch_topology: seed capacity_freq_ref with boost-aware max freq

[Vincent Guittot]

On Tue, 8 Sept 2026 at 10:31, Ananthu C V <ananthu.cv@xxxxxxxxxxxxxxxx> wrote:
>
> capacity_freq_ref, the per-CPU frequency-invariance reference used by
> schedutil, is seeded from policy->cpuinfo.max_freq at policy creation.
> If boost frequencies are filtered out of the frequency table because
> boost isn't yet enabled at boot, max_freq only reflects the non-boost
> ceiling, so capacity_freq_ref never learns about boost frequencies for
> the policy's lifetime. Enabling boost later raises policy->max, but
> capacity_freq_ref stays stale, leaving schedutil unable to scale
> utilization or target a frequency above the non-boost maximum.
>
> Track the highest frequency in the table regardless of boost state
> (max_table_freq) and seed capacity_freq_ref with max(cpuinfo.max_freq,
> max_table_freq), so the invariance reference is boost-aware from boot
> regardless of whether boost is currently enabled. Runtime enforcement,
> still handled by policy->max, is unaffected.
>
> Suggested-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
> Signed-off-by: Ananthu C V <ananthu.cv@xxxxxxxxxxxxxxxx>
> ---
>  drivers/base/arch_topology.c | 3 ++-
>  drivers/cpufreq/freq_table.c | 6 ++++++
>  include/linux/cpufreq.h      | 1 +
>  3 files changed, 9 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
> index 8c5e47c28d9a..da94f77441da 100644
> --- a/drivers/base/arch_topology.c
> +++ b/drivers/base/arch_topology.c
> @@ -404,7 +404,8 @@ init_cpu_capacity_callback(struct notifier_block *nb,
>         cpumask_andnot(cpus_to_visit, cpus_to_visit, policy->related_cpus);
>
>         for_each_cpu(cpu, policy->related_cpus) {
> -               per_cpu(capacity_freq_ref, cpu) = policy->cpuinfo.max_freq;
> +               per_cpu(capacity_freq_ref, cpu) = max(policy->cpuinfo.max_freq,
> +                                                     policy->cpuinfo.max_table_freq);

I will let cpufreq maintainer comment about the need for a
policy->cpuinfo.max_table_freq field or not but otherwise you can use
something similar to [1] to find your max table freq:
[1] https://lore.kernel.org/all/CAKfTPtBji8dkr5ixhtZjkyrWLA68TF-KHLrNYWoewPWLyuUd4A@xxxxxxxxxxxxxx/

diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index da94f77441da..92966be712d5 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -405,7 +405,7 @@ init_cpu_capacity_callback(struct notifier_block *nb,

        for_each_cpu(cpu, policy->related_cpus) {
                per_cpu(capacity_freq_ref, cpu) = max(policy->cpuinfo.max_freq,
-
policy->cpuinfo.max_table_freq);
+
cpufreq_frequency_table_max(policy));
                freq_inv_set_max_ratio(cpu,
                                       per_cpu(capacity_freq_ref, cpu)
* HZ_PER_KHZ);
        }
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 419c71ccff7c..e40f915b7119 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -1109,6 +1109,17 @@ static inline int
cpufreq_frequency_table_target(struct cpufreq_policy *policy,
        return idx;
 }

+static inline unsigned int cpufreq_frequency_table_max(struct
cpufreq_policy *policy)
+{
+       int idx;
+
+       if (!policy->freq_table)
+               return policy->cpuinfo.max_freq;
+
+       idx = cpufreq_frequency_table_target(policy, UINT_MAX, 0,
UINT_MAX, CPUFREQ_RELATION_H);
+       return policy->freq_table[idx].frequency;
+}
+
 static inline int cpufreq_table_count_valid_entries(const struct
cpufreq_policy *policy)
 {
        struct cpufreq_frequency_table *pos;

>                 freq_inv_set_max_ratio(cpu,
>                                        per_cpu(capacity_freq_ref, cpu) * HZ_PER_KHZ);
>         }
> diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
> index ea994647abc8..4984142dc08a 100644
> --- a/drivers/cpufreq/freq_table.c
> +++ b/drivers/cpufreq/freq_table.c
> @@ -33,11 +33,15 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy)
>         struct cpufreq_frequency_table *pos, *table = policy->freq_table;
>         unsigned int min_freq = ~0;
>         unsigned int max_freq = 0;
> +       unsigned int max_table_freq = 0;
>         unsigned int freq, i;
>
>         cpufreq_for_each_valid_entry_idx(pos, table, i) {
>                 freq = pos->frequency;
>
> +               if (freq > max_table_freq)
> +                       max_table_freq = freq;
> +
>                 if ((!cpufreq_boost_enabled() || !policy->boost_enabled)
>                     && (pos->flags & CPUFREQ_BOOST_FREQ))
>                         continue;
> @@ -57,6 +61,8 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy)
>         if (policy->cpuinfo.max_freq < max_freq)
>                 policy->cpuinfo.max_freq = max_freq;
>
> +       policy->cpuinfo.max_table_freq = max_table_freq;
> +
>         if (min_freq == ~0)
>                 return -EINVAL;
>         else
> diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
> index 35ce665edfd8..3f3b1380251a 100644
> --- a/include/linux/cpufreq.h
> +++ b/include/linux/cpufreq.h
> @@ -45,6 +45,7 @@ enum cpufreq_table_sorting {
>  struct cpufreq_cpuinfo {
>         unsigned int            max_freq;
>         unsigned int            min_freq;
> +       unsigned int            max_table_freq; /* Highest valid frequency in the table */
>
>         /* in 10^(-9) s = nanoseconds */
>         unsigned int            transition_latency;
>
> --
> 2.43.0
>