Re: [PATCH v2] schedutil: Allow cpufreq requests to be made even when kthread kicked

[Rafael J. Wysocki]

On Tuesday, May 22, 2018 12:50:06 PM CEST Viresh Kumar wrote:
> On 22-05-18, 16:04, Viresh Kumar wrote:
> > Okay, me and Rafael were discussing this patch, locking and races around this.
> > 
> > On 18-05-18, 11:55, Joel Fernandes (Google.) wrote:
> > > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > > index e13df951aca7..5c482ec38610 100644
> > > --- a/kernel/sched/cpufreq_schedutil.c
> > > +++ b/kernel/sched/cpufreq_schedutil.c
> > > @@ -92,9 +92,6 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
> > >  	    !cpufreq_can_do_remote_dvfs(sg_policy->policy))
> > >  		return false;
> > >  
> > > -	if (sg_policy->work_in_progress)
> > > -		return false;
> > > -
> > >  	if (unlikely(sg_policy->need_freq_update)) {
> > >  		sg_policy->need_freq_update = false;
> > >  		/*
> > > @@ -128,7 +125,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
> > >  
> > >  		policy->cur = next_freq;
> > >  		trace_cpu_frequency(next_freq, smp_processor_id());
> > > -	} else {
> > > +	} else if (!sg_policy->work_in_progress) {
> > >  		sg_policy->work_in_progress = true;
> > >  		irq_work_queue(&sg_policy->irq_work);
> > >  	}
> > > @@ -291,6 +288,13 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
> > >  
> > >  	ignore_dl_rate_limit(sg_cpu, sg_policy);
> > >  
> > > +	/*
> > > +	 * For slow-switch systems, single policy requests can't run at the
> > > +	 * moment if update is in progress, unless we acquire update_lock.
> > > +	 */
> > > +	if (sg_policy->work_in_progress)
> > > +		return;
> > > +
> > >  	if (!sugov_should_update_freq(sg_policy, time))
> > >  		return;
> > >  
> > > @@ -382,13 +386,27 @@ sugov_update_shared(struct update_util_data *hook, u64 time, unsigned int flags)
> > >  static void sugov_work(struct kthread_work *work)
> > >  {
> > >  	struct sugov_policy *sg_policy = container_of(work, struct sugov_policy, work);
> > > +	unsigned int freq;
> > > +	unsigned long flags;
> > > +
> > > +	/*
> > > +	 * Hold sg_policy->update_lock shortly to handle the case where:
> > > +	 * incase sg_policy->next_freq is read here, and then updated by
> > > +	 * sugov_update_shared just before work_in_progress is set to false
> > > +	 * here, we may miss queueing the new update.
> > > +	 *
> > > +	 * Note: If a work was queued after the update_lock is released,
> > > +	 * sugov_work will just be called again by kthread_work code; and the
> > > +	 * request will be proceed before the sugov thread sleeps.
> > > +	 */
> > > +	raw_spin_lock_irqsave(&sg_policy->update_lock, flags);
> > > +	freq = sg_policy->next_freq;
> > > +	sg_policy->work_in_progress = false;
> > > +	raw_spin_unlock_irqrestore(&sg_policy->update_lock, flags);
> > >  
> > >  	mutex_lock(&sg_policy->work_lock);
> > > -	__cpufreq_driver_target(sg_policy->policy, sg_policy->next_freq,
> > > -				CPUFREQ_RELATION_L);
> > > +	__cpufreq_driver_target(sg_policy->policy, freq, CPUFREQ_RELATION_L);
> > >  	mutex_unlock(&sg_policy->work_lock);
> > > -
> > > -	sg_policy->work_in_progress = false;
> > >  }
> > 
> > And I do see a race here for single policy systems doing slow switching.
> > 
> > Kthread                                                 Sched update
> > 
> > sugov_work()                                            sugov_update_single()
> > 
> >         lock();
> >         // The CPU is free to rearrange below           
> >         // two in any order, so it may clear
> >         // the flag first and then read next
> >         // freq. Lets assume it does.
> >         work_in_progress = false
> > 
> >                                                         if (work_in_progress)
> >                                                                 return;
> > 
> >                                                         sg_policy->next_freq = 0;
> >         freq = sg_policy->next_freq;
> >                                                         sg_policy->next_freq = real-next-freq;
> >         unlock();
> > 
> > 
> > 
> > Is the above theory right or am I day dreaming ? :)
> 
> And here comes the ugly fix:
> 
> diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> index 35826f4ec43c..1665da31862e 100644
> --- a/kernel/sched/cpufreq_schedutil.c
> +++ b/kernel/sched/cpufreq_schedutil.c
> @@ -283,6 +283,9 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
>  
>         ignore_dl_rate_limit(sg_cpu, sg_policy);
>  
> +       if (!policy->fast_switch_enabled)
> +               raw_spin_lock(&sg_policy->update_lock);
> +
>         /*
>          * For slow-switch systems, single policy requests can't run at the
>          * moment if update is in progress, unless we acquire update_lock.
> @@ -312,6 +315,9 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
>         }
>  
>         sugov_update_commit(sg_policy, time, next_f);
> +
> +       if (!policy->fast_switch_enabled)
> +               raw_spin_unlock(&sg_policy->update_lock);
>  }
>  
>  static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
> 
> 
> 

Ugly indeed.