cpufreq/schedutil: Take time spent in interrupts into account

The time spent executing IRQ handlers can be significant but it is not reflected
in the utilization of CPU when deciding to choose an OPP. Now that we have
access to this metric, schedutil can take it into account when selecting
the OPP for a CPU.

RQS utilization don't see the time spend under interrupt context and report
their value in the normal context time window. We need to compensate this when
adding interrupt utilization

The CPU utilization is:

  IRQ util_avg + (1 - IRQ util_avg / max capacity ) * /Sum rq util_avg

A test with iperf on hikey (octo arm64) gives the following speedup:

 iperf -c server_address -r -t 5

 w/o patch		w/ patch
 Tx 276 Mbits/sec	304 Mbits/sec +10%
 Rx 299 Mbits/sec	328 Mbits/sec  +9%

 8 iterations
 stdev is lower than 1%

Only WFI idle state is enabled (shallowest idle state).

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: claudio@evidence.eu.com
Cc: daniel.lezcano@linaro.org
Cc: dietmar.eggemann@arm.com
Cc: joel@joelfernandes.org
Cc: juri.lelli@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: patrick.bellasi@arm.com
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: valentin.schneider@arm.com
Link: http://lkml.kernel.org/r/1530200714-4504-8-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/cpufreq_schedutil.c

@@ -58,6 +58,7 @@ struct sugov_cpu {
 	unsigned long		util_dl;
 	unsigned long		bw_dl;
 	unsigned long		util_rt;
+	unsigned long		util_irq;
 	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
@@ -190,21 +191,30 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu)
 	sg_cpu->util_dl  = cpu_util_dl(rq);
 	sg_cpu->bw_dl    = cpu_bw_dl(rq);
 	sg_cpu->util_rt  = cpu_util_rt(rq);
+	sg_cpu->util_irq = cpu_util_irq(rq);
 }
 
 static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
-	unsigned long util;
+	unsigned long util, max = sg_cpu->max;
 
 	if (rt_rq_is_runnable(&rq->rt))
 		return sg_cpu->max;
 
+	if (unlikely(sg_cpu->util_irq >= max))
+		return max;
+
+	/* Sum rq utilization */
 	util = sg_cpu->util_cfs;
 	util += sg_cpu->util_rt;
 
-	if ((util + sg_cpu->util_dl) >= sg_cpu->max)
-		return sg_cpu->max;
+	/*
+	 * Interrupt time is not seen by RQS utilization so we can compare
+	 * them with the CPU capacity
+	 */
+	if ((util + sg_cpu->util_dl) >= max)
+		return max;
 
 	/*
 	 * As there is still idle time on the CPU, we need to compute the
@@ -220,10 +230,17 @@ static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
 	 * ready for such an interface. So, we only do the latter for now.
 	 */
 
+	/* Weight RQS utilization to normal context window */
+	util *= (max - sg_cpu->util_irq);
+	util /= max;
+
+	/* Add interrupt utilization */
+	util += sg_cpu->util_irq;
+
 	/* Add DL bandwidth requirement */
 	util += sg_cpu->bw_dl;
 
-	return min(sg_cpu->max, util);
+	return min(max, util);
 }
 
 /**

kernel/sched/sched.h

@@ -2228,4 +2228,17 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
 {
 	return rq->avg_rt.util_avg;
 }
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+static inline unsigned long cpu_util_irq(struct rq *rq)
+{
+	return rq->avg_irq.util_avg;
+}
+#else
+static inline unsigned long cpu_util_irq(struct rq *rq)
+{
+	return 0;
+}
+
+#endif
 #endif