Re: [RFC PATCH] sched/cpufreq/schedutil: handling urgent frequency requests

[Joel Fernandes <joel@joelfernandes.org>]

On Wed, May 09, 2018 at 08:45:30AM +0200, Juri Lelli wrote:
> On 08/05/18 21:54, Joel Fernandes wrote:
> 
> [...]
> 
> > Just for discussion sake, is there any need for work_in_progress? If we can
> > queue multiple work say kthread_queue_work can handle it, then just queuing
> > works whenever they are available should be Ok and the kthread loop can
> > handle them. __cpufreq_driver_target is also protected by the work lock if
> > there is any concern that can have races... only thing is rate-limiting of
> > the requests, but we are doing a rate limiting, just not for the "DL
> > increased utilization" type requests (which I don't think we are doing at the
> > moment for urgent DL requests anyway).
> > 
> > Following is an untested diff to show the idea. What do you think?
> > 
> > thanks,
> > 
> > - Joel
> > 
> > ----8<---
> > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > index d2c6083304b4..862634ff4bf3 100644
> > --- a/kernel/sched/cpufreq_schedutil.c
> > +++ b/kernel/sched/cpufreq_schedutil.c
> > @@ -38,7 +38,6 @@ struct sugov_policy {
> >  	struct			mutex work_lock;
> >  	struct			kthread_worker worker;
> >  	struct task_struct	*thread;
> > -	bool			work_in_progress;
> >  
> >  	bool			need_freq_update;
> >  };
> > @@ -92,16 +91,8 @@ 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;
> > -		/*
> > -		 * This happens when limits change, so forget the previous
> > -		 * next_freq value and force an update.
> > -		 */
> > -		sg_policy->next_freq = UINT_MAX;
> >  		return true;
> >  	}
> >  
> > @@ -129,7 +120,6 @@ 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 {
> > -		sg_policy->work_in_progress = true;
> >  		irq_work_queue(&sg_policy->irq_work);
> 
> Isn't this potentially introducing unneeded irq pressure (and doing the
> whole wakeup the kthread thing), while the already active kthread could
> simply handle multiple back-to-back requests before going to sleep?

How about this? Will use the latest request, and also doesn't do unnecessary
irq_work_queue:

(untested)
-----8<--------
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index d2c6083304b4..6a3e42b01f52 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -38,7 +38,7 @@ struct sugov_policy {
 	struct			mutex work_lock;
 	struct			kthread_worker worker;
 	struct task_struct	*thread;
-	bool			work_in_progress;
+	bool			work_in_progress; /* Has kthread been kicked */
 
 	bool			need_freq_update;
 };
@@ -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;
 		/*
@@ -129,8 +126,11 @@ 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 {
-		sg_policy->work_in_progress = true;
-		irq_work_queue(&sg_policy->irq_work);
+		/* work_in_progress helps us not queue unnecessarily */
+		if (!sg_policy->work_in_progress) {
+			sg_policy->work_in_progress = true;
+			irq_work_queue(&sg_policy->irq_work);
+		}
 	}
 }
 
@@ -381,13 +381,23 @@ 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;
+
+	/*
+	 * Hold sg_policy->update_lock just enough to handle the case where:
+	 * if sg_policy->next_freq is updated before work_in_progress is set to
+	 * false, we may miss queueing the new update request since
+	 * work_in_progress would appear to be true.
+	 */
+	raw_spin_lock(&sg_policy->update_lock);
+	freq = sg_policy->next_freq;
+	sg_policy->work_in_progress = false;
+	raw_spin_unlock(&sg_policy->update_lock);
 
 	mutex_lock(&sg_policy->work_lock);
-	__cpufreq_driver_target(sg_policy->policy, sg_policy->next_freq,
+	__cpufreq_driver_target(sg_policy->policy, freq,
 				CPUFREQ_RELATION_L);
 	mutex_unlock(&sg_policy->work_lock);
-
-	sg_policy->work_in_progress = false;
 }
 
 static void sugov_irq_work(struct irq_work *irq_work)