sched/core: Use PELT for scale_rt_capacity()

The utilization of the CPU by RT, DL and IRQs are now tracked with
PELT so we can use these metrics instead of rt_avg to evaluate the remaining
capacity available for CFS class.

scale_rt_capacity() behavior has been changed and now returns the remaining
capacity available for CFS instead of a scaling factor because RT, DL and
IRQ provide now absolute utilization value.

The same formula as schedutil is used:

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

but the implementation is different because it doesn't return the same value
and doesn't benefit of the same optimization.

Signed-off-by: Vincent Guittot <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: [email protected]
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

kernel/sched/deadline.c

@@ -1180,8 +1180,6 @@ static void update_curr_dl(struct rq *rq)
 	curr->se.exec_start = now;
 	cgroup_account_cputime(curr, delta_exec);
 
-	sched_rt_avg_update(rq, delta_exec);
-
 	if (dl_entity_is_special(dl_se))
 		return;
 

kernel/sched/fair.c

@@ -7551,39 +7551,39 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 static unsigned long scale_rt_capacity(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	u64 total, used, age_stamp, avg;
-	s64 delta;
-
-	/*
-	 * Since we're reading these variables without serialization make sure
-	 * we read them once before doing sanity checks on them.
-	 */
-	age_stamp = READ_ONCE(rq->age_stamp);
-	avg = READ_ONCE(rq->rt_avg);
-	delta = __rq_clock_broken(rq) - age_stamp;
+	unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+	unsigned long used, free;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	unsigned long irq;
+#endif
 
-	if (unlikely(delta < 0))
-		delta = 0;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	irq = READ_ONCE(rq->avg_irq.util_avg);
 
-	total = sched_avg_period() + delta;
+	if (unlikely(irq >= max))
+		return 1;
+#endif
 
-	used = div_u64(avg, total);
+	used = READ_ONCE(rq->avg_rt.util_avg);
+	used += READ_ONCE(rq->avg_dl.util_avg);
 
-	if (likely(used < SCHED_CAPACITY_SCALE))
-		return SCHED_CAPACITY_SCALE - used;
+	if (unlikely(used >= max))
+		return 1;
 
-	return 1;
+	free = max - used;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	free *= (max - irq);
+	free /= max;
+#endif
+	return free;
 }
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-	unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
+	unsigned long capacity = scale_rt_capacity(cpu);
 	struct sched_group *sdg = sd->groups;
 
-	cpu_rq(cpu)->cpu_capacity_orig = capacity;
-
-	capacity *= scale_rt_capacity(cpu);
-	capacity >>= SCHED_CAPACITY_SHIFT;
+	cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu);
 
 	if (!capacity)
 		capacity = 1;

kernel/sched/pelt.c

@@ -237,7 +237,7 @@ ___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runna
 	 */
 	sa->load_avg = div_u64(load * sa->load_sum, divider);
 	sa->runnable_load_avg =	div_u64(runnable * sa->runnable_load_sum, divider);
-	sa->util_avg = sa->util_sum / divider;
+	WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
 }
 
 /*

kernel/sched/rt.c

@@ -973,8 +973,6 @@ static void update_curr_rt(struct rq *rq)
 	curr->se.exec_start = now;
 	cgroup_account_cputime(curr, delta_exec);
 
-	sched_rt_avg_update(rq, delta_exec);
-
 	if (!rt_bandwidth_enabled())
 		return;