Re: [PATCH] sched/cpufreq: Reevaluate frequency before tickless idle

[Christian Loehle]

On 8/24/26 14:18, Christian Loehle wrote:
> sugov_hold_freq() can preserve a UCLAMP_MIN-driven high frequency when
> the runqueue goes idle. If cpuidle then stops the tick, no later
> utilization update is guaranteed and a CPU using WFI can remain at an
> unnecessarily high voltage for the entire idle period.
> 
> Issue a final cpufreq update when the idle tick actually transitions to
> stopped and force single-policy schedutil past its rate limit. Keep the
> existing hold behavior when the tick is retained.
> 
> Signed-off-by: Christian Loehle <christian.loehle@xxxxxxx>
> ---
>  include/linux/sched/cpufreq.h    |  1 +
>  kernel/sched/cpufreq_schedutil.c |  5 ++++-
>  kernel/sched/idle.c              | 29 +++++++++++++++++++++++++++--
>  3 files changed, 32 insertions(+), 3 deletions(-)
> 
> diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h
> index bdd31ab93bc5..0814f6c79315 100644
> --- a/include/linux/sched/cpufreq.h
> +++ b/include/linux/sched/cpufreq.h
> @@ -9,6 +9,7 @@
>   */
>  
>  #define SCHED_CPUFREQ_IOWAIT	(1U << 0)
> +#define SCHED_CPUFREQ_IDLE	(1U << 1)
>  
>  #ifdef CONFIG_CPU_FREQ
>  struct cpufreq_policy;
> diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> index a1782755efcc..90bf8d8bffb7 100644
> --- a/kernel/sched/cpufreq_schedutil.c
> +++ b/kernel/sched/cpufreq_schedutil.c
> @@ -100,7 +100,7 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
>  
>  		return true;
>  	} else if (sg_policy->need_freq_update) {
> -		/* ignore_dl_rate_limit() wants a new frequency to be found. */
> +		/* A forced update needs a new frequency to be found. */
>  		return true;
>  	}
>  
> @@ -407,6 +407,9 @@ static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
>  	sugov_iowait_boost(sg_cpu, time, flags);
>  	sg_cpu->last_update = time;
>  
> +	if (flags & SCHED_CPUFREQ_IDLE)
> +		sg_cpu->sg_policy->need_freq_update = true;
> +
>  	ignore_dl_rate_limit(sg_cpu);
>  
>  	if (!sugov_should_update_freq(sg_cpu->sg_policy, time))
> diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
> index eb73b65ce6c4..36f8840d0562 100644
> --- a/kernel/sched/idle.c
> +++ b/kernel/sched/idle.c
> @@ -161,10 +161,35 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
>  	return cpuidle_enter(drv, dev, next_state);
>  }
>  
> +static void idle_stop_tick(void)
> +{
> +#ifdef CONFIG_CPU_FREQ
> +	bool was_stopped = tick_nohz_tick_stopped();
> +#endif
> +
> +	tick_nohz_idle_stop_tick();
> +
> +#ifdef CONFIG_CPU_FREQ
> +	/*
> +	 * Run one last cpufreq update before entering idle with the tick
> +	 * stopped, because no later update is guaranteed.
> +	 */
> +	if (!was_stopped && tick_nohz_tick_stopped()) {
> +		struct rq *rq = this_rq();
> +		struct rq_flags rf;
> +
> +		rq_lock(rq, &rf);
> +		update_rq_clock(rq);
> +		cpufreq_update_util(rq, SCHED_CPUFREQ_IDLE);

Sashiko correctly noted that this may lead to an infinite loop on
slow-switch platforms where the pre-idle update results in another
sugov kthread wakeup which in turn will result in a new pre-idle
cpufreq update.

I will just track if sugov actually held a frequency and gate
the update on that in v2.