sched: Feature to disable APERF/MPERF cpu_power

I suspect a feed-back loop between cpuidle and the aperf/mperf
cpu_power bits, where when we have idle C-states lower the ratio,
which leads to lower cpu_power and then less load, which generates
more idle time, etc..

Put in a knob to disable it.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

kernel/sched.c

@@ -3602,11 +3602,19 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
 	unsigned long power = SCHED_LOAD_SCALE;
 	struct sched_group *sdg = sd->groups;
 
-	power *= arch_scale_freq_power(sd, cpu);
+	if (sched_feat(ARCH_POWER))
+		power *= arch_scale_freq_power(sd, cpu);
+	else
+		power *= default_scale_freq_power(sd, cpu);
+
 	power >>= SCHED_LOAD_SHIFT;
 
 	if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
-		power *= arch_scale_smt_power(sd, cpu);
+		if (sched_feat(ARCH_POWER))
+			power *= arch_scale_smt_power(sd, cpu);
+		else
+			power *= default_scale_smt_power(sd, cpu);
+
 		power >>= SCHED_LOAD_SHIFT;
 	}
 

kernel/sched_features.h

@@ -82,6 +82,11 @@ SCHED_FEAT(LAST_BUDDY, 1)
  */
 SCHED_FEAT(CACHE_HOT_BUDDY, 1)
 
+/*
+ * Use arch dependent cpu power functions
+ */
+SCHED_FEAT(ARCH_POWER, 0)
+
 SCHED_FEAT(HRTICK, 0)
 SCHED_FEAT(DOUBLE_TICK, 0)
 SCHED_FEAT(LB_BIAS, 1)