Re: [PATCH 07/10] cpufreq: ondemand: queue work for policy->cpus together

[Preeti U Murthy <preeti@linux.vnet.ibm.com>]

On 06/22/2015 01:32 PM, Viresh Kumar wrote:
> Currently update_sampling_rate() runs over each online CPU and
> cancels/queues work on it. Its very inefficient for the case where a
> single policy manages multiple CPUs, as they can be processed together.
> 
> Also drop the unnecessary cancel_delayed_work_sync() as we are doing a
> mod_delayed_work_on() in gov_queue_work(), which will take care of
> pending works for us.

This looks fine, except for one point. See below:
> 
> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
> ---
>  drivers/cpufreq/cpufreq_ondemand.c | 32 ++++++++++++++++++++------------
>  1 file changed, 20 insertions(+), 12 deletions(-)
> 
> diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
> index 841e1fa96ee7..cfecd3b67cb3 100644
> --- a/drivers/cpufreq/cpufreq_ondemand.c
> +++ b/drivers/cpufreq/cpufreq_ondemand.c
> @@ -247,40 +247,48 @@ static void update_sampling_rate(struct dbs_data *dbs_data,
>  		unsigned int new_rate)
>  {
>  	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
> +	struct cpufreq_policy *policy;
> +	struct od_cpu_dbs_info_s *dbs_info;
> +	unsigned long next_sampling, appointed_at;
> +	struct cpumask cpumask;
>  	int cpu;
> 
> +	cpumask_copy(&cpumask, cpu_online_mask);
> +
>  	od_tuners->sampling_rate = new_rate = max(new_rate,
>  			dbs_data->min_sampling_rate);
> 
> -	for_each_online_cpu(cpu) {
> -		struct cpufreq_policy *policy;
> -		struct od_cpu_dbs_info_s *dbs_info;
> -		unsigned long next_sampling, appointed_at;
> -
> +	for_each_cpu(cpu, &cpumask) {
>  		policy = cpufreq_cpu_get(cpu);
>  		if (!policy)
>  			continue;
> +
> +		/* clear all CPUs of this policy */
> +		cpumask_andnot(&cpumask, &cpumask, policy->cpus);
> +
>  		if (policy->governor != &cpufreq_gov_ondemand) {
>  			cpufreq_cpu_put(policy);
>  			continue;
>  		}
> +
>  		dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
>  		cpufreq_cpu_put(policy);
> 
> +		/*
> +		 * Checking this for any CPU of the policy is fine. As either
> +		 * all would have queued work or none.

Are you sure that the state of the work will be the same across all
policy cpus ? 'Pending' only refers to twork awaiting for the timer to
fire and then queue itself on the runqueue right ? On some of the
policy->cpus, timers may be yet to fire, while on others it might
already have ?

> +		 */
>  		if (!delayed_work_pending(&dbs_info->cdbs.dwork))
>  			continue;
> 
>  		next_sampling = jiffies + usecs_to_jiffies(new_rate);
>  		appointed_at = dbs_info->cdbs.dwork.timer.expires;
> 
> -		if (time_before(next_sampling, appointed_at)) {
> -			cancel_delayed_work_sync(&dbs_info->cdbs.dwork);
> -
> -			gov_queue_work(dbs_data, policy,
> -				       usecs_to_jiffies(new_rate),
> -				       cpumask_of(cpu));
> +		if (!time_before(next_sampling, appointed_at))
> +			continue;
> 
> -		}
> +		gov_queue_work(dbs_data, policy, usecs_to_jiffies(new_rate),
> +			       policy->cpus);
>  	}
>  }
> 

Regards
Preeti U Murthy