1 files changed, 61 insertions, 3 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 036600fd70b..ab532b5de40 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -627,6 +627,9 @@ struct rq {
 
 	struct task_struct *migration_thread;
 	struct list_head migration_queue;
+
+	u64 rt_avg;
+	u64 age_stamp;
 #endif
 
 	/* calc_load related fields */
@@ -863,6 +866,14 @@ unsigned int sysctl_sched_shares_ratelimit = 250000;
 unsigned int sysctl_sched_shares_thresh = 4;
 
 /*
+ * period over which we average the RT time consumption, measured
+ * in ms.
+ *
+ * default: 1s
+ */
+const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
+
+/*
  * period over which we measure -rt task cpu usage in us.
  * default: 1s
  */
@@ -1280,12 +1291,37 @@ void wake_up_idle_cpu(int cpu)
 }
 #endif /* CONFIG_NO_HZ */
 
+static u64 sched_avg_period(void)
+{
+	return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
+}
+
+static void sched_avg_update(struct rq *rq)
+{
+	s64 period = sched_avg_period();
+
+	while ((s64)(rq->clock - rq->age_stamp) > period) {
+		rq->age_stamp += period;
+		rq->rt_avg /= 2;
+	}
+}
+
+static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
+{
+	rq->rt_avg += rt_delta;
+	sched_avg_update(rq);
+}
+
 #else /* !CONFIG_SMP */
 static void resched_task(struct task_struct *p)
 {
 	assert_spin_locked(&task_rq(p)->lock);
 	set_tsk_need_resched(p);
 }
+
+static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
+{
+}
 #endif /* CONFIG_SMP */
 
 #if BITS_PER_LONG == 32
@@ -3699,7 +3735,7 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
 }
 #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
-unsigned long __weak arch_smt_gain(struct sched_domain *sd, int cpu)
+unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
 {
 	unsigned long weight = cpumask_weight(sched_domain_span(sd));
 	unsigned long smt_gain = sd->smt_gain;
@@ -3709,6 +3745,24 @@ unsigned long __weak arch_smt_gain(struct sched_domain *sd, int cpu)
 	return smt_gain;
 }
 
+unsigned long scale_rt_power(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	u64 total, available;
+
+	sched_avg_update(rq);
+
+	total = sched_avg_period() + (rq->clock - rq->age_stamp);
+	available = total - rq->rt_avg;
+
+	if (unlikely((s64)total < SCHED_LOAD_SCALE))
+		total = SCHED_LOAD_SCALE;
+
+	total >>= SCHED_LOAD_SHIFT;
+
+	return div_u64(available, total);
+}
+
 static void update_cpu_power(struct sched_domain *sd, int cpu)
 {
 	unsigned long weight = cpumask_weight(sched_domain_span(sd));
@@ -3719,11 +3773,15 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
 	/* here we could scale based on cpufreq */
 
 	if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
-		power *= arch_smt_gain(sd, cpu);
+		power *= arch_scale_smt_power(sd, cpu);
 		power >>= SCHED_LOAD_SHIFT;
 	}
 
-	/* here we could scale based on RT time */
+	power *= scale_rt_power(cpu);
+	power >>= SCHED_LOAD_SHIFT;
+
+	if (!power)
+		power = 1;
 
 	if (power != old) {
 		sdg->__cpu_power = power;