linux-kernel - Re: [PATCH 1/4] sched: cpufreq: Rename map_util_perf to apply_dvfs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20230820211307.p6gypri2jztqwf2o@airbuntu>
Date:   Sun, 20 Aug 2023 22:13:07 +0100
From:   Qais Yousef <qyousef@...alina.io>
To:     "Rafael J. Wysocki" <rafael@...nel.org>,
        Viresh Kumar <viresh.kumar@...aro.org>,
        Ingo Molnar <mingo@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>
Cc:     linux-kernel@...r.kernel.org, linux-pm@...r.kernel.org,
        Vincent Guittot <vincent.guittot@...aro.org>,
        Dietmar Eggemann <dietmar.eggemann@....com>,
        Lukasz Luba <lukasz.luba@....com>
Subject: Re: [PATCH 1/4] sched: cpufreq: Rename map_util_perf to
 apply_dvfs_headroom

On 08/20/23 22:06, Qais Yousef wrote:
> We are providing headroom for the utilization to grow until the next
> decision point to pick the next frequency. Give the function a better
> name and give it some documentation. It is not really mapping anything.
> 
> Provide a dummy definition for !CONFIG_CPUFREQ which will be required
> for later patches.
> 
> Signed-off-by: Qais Yousef (Google) <qyousef@...alina.io>
> ---
>  include/linux/energy_model.h     |  2 +-
>  include/linux/sched/cpufreq.h    | 27 ++++++++++++++++++++++++++-
>  kernel/sched/cpufreq_schedutil.c |  6 +++---
>  3 files changed, 30 insertions(+), 5 deletions(-)
> 
> diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
> index b9caa01dfac4..6ebde4e69e98 100644
> --- a/include/linux/energy_model.h
> +++ b/include/linux/energy_model.h
> @@ -243,7 +243,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
>  	scale_cpu = arch_scale_cpu_capacity(cpu);
>  	ps = &pd->table[pd->nr_perf_states - 1];
>  
> -	max_util = map_util_perf(max_util);
> +	max_util = apply_dvfs_headroom(max_util);
>  	max_util = min(max_util, allowed_cpu_cap);
>  	freq = map_util_freq(max_util, ps->frequency, scale_cpu);
>  
> diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h
> index bdd31ab93bc5..f0069b354ac8 100644
> --- a/include/linux/sched/cpufreq.h
> +++ b/include/linux/sched/cpufreq.h
> @@ -29,10 +29,35 @@ static inline unsigned long map_util_freq(unsigned long util,
>  	return freq * util / cap;
>  }
>  
> -static inline unsigned long map_util_perf(unsigned long util)
> +/*
> + * DVFS decision are made at discrete points. If CPU stays busy, the util will
> + * continue to grow, which means it could need to run at a higher frequency
> + * before the next decision point was reached. IOW, we can't follow the util as
> + * it grows immediately, but there's a delay before we issue a request to go to
> + * higher frequency. The headroom caters for this delay so the system continues
> + * to run at adequate performance point.
> + *
> + * This function provides enough headroom to provide adequate performance
> + * assuming the CPU continues to be busy.
> + *
> + * At the moment it is a constant multiplication with 1.25.
> + *
> + * TODO: The headroom should be a function of the delay. 25% is too high
> + * especially on powerful systems. For example, if the delay is 500us, it makes
> + * more sense to give a small headroom as the next decision point is not far
> + * away and will follow the util if it continues to rise. On the other hand if
> + * the delay is 10ms, then we need a bigger headroom so the CPU won't struggle
> + * at a lower frequency if it never goes to idle until then.
> + */

I'm happy to drop this TODO if it is controversial. I already have a series
that works in that effect that I will hopefully get a chance to post soon
enough.


Cheers

--
Qais Yousef

> +static inline unsigned long apply_dvfs_headroom(unsigned long util)
>  {
>  	return util + (util >> 2);
>  }
> +#else
> +static inline unsigned long apply_dvfs_headroom(unsigned long util)
> +{
> +	return util;
> +}
>  #endif /* CONFIG_CPU_FREQ */
>  
>  #endif /* _LINUX_SCHED_CPUFREQ_H */
> diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> index 4492608b7d7f..916c4d3d6192 100644
> --- a/kernel/sched/cpufreq_schedutil.c
> +++ b/kernel/sched/cpufreq_schedutil.c
> @@ -143,7 +143,7 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
>  	unsigned int freq = arch_scale_freq_invariant() ?
>  				policy->cpuinfo.max_freq : policy->cur;
>  
> -	util = map_util_perf(util);
> +	util = apply_dvfs_headroom(util);
>  	freq = map_util_freq(util, freq, max);
>  
>  	if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
> @@ -406,8 +406,8 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
>  	    sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
>  		sg_cpu->util = prev_util;
>  
> -	cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
> -				   map_util_perf(sg_cpu->util), max_cap);
> +	cpufreq_driver_adjust_perf(sg_cpu->cpu, apply_dvfs_headroom(sg_cpu->bw_dl),
> +				   apply_dvfs_headroom(sg_cpu->util), max_cap);
>  
>  	sg_cpu->sg_policy->last_freq_update_time = time;
>  }
> -- 
> 2.34.1
>