cpuidle: menu: Remove get_loadavg() from the performance multiplier

The function get_loadavg() returns almost always zero. To be more
precise, statistically speaking for a total of 1023379 times passing
in the function, the load is equal to zero 1020728 times, greater than
100, 610 times, the remaining is between 0 and 5.

In 2011, the get_loadavg() was removed from the Android tree because
of the above [1]. At this time, the load was:

unsigned long this_cpu_load(void)
{
        struct rq *this = this_rq();
        return this->cpu_load[0];
}

In 2014, the code was changed by commit 372ba8cb (cpuidle: menu: Lookup CPU
runqueues less) and the load is:

void get_iowait_load(unsigned long *nr_waiters, unsigned long *load)
{
        struct rq *rq = this_rq();
        *nr_waiters = atomic_read(&rq->nr_iowait);
        *load = rq->load.weight;
}

with the same result.

Both measurements show using the load in this code path does no matter
anymore. Removing it.

[1] https://android.googlesource.com/kernel/common/+/4dedd9f124703207895777ac6e91dacde0f7cc17Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

drivers/cpuidle/governors/menu.c

@@ -134,11 +134,6 @@ struct menu_device {
 #define LOAD_INT(x) ((x) >> FSHIFT)
 #define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
 
-static inline int get_loadavg(unsigned long load)
-{
-	return LOAD_INT(load) * 10 + LOAD_FRAC(load) / 10;
-}
-
 static inline int which_bucket(unsigned int duration, unsigned long nr_iowaiters)
 {
 	int bucket = 0;
@@ -172,18 +167,10 @@ static inline int which_bucket(unsigned int duration, unsigned long nr_iowaiters
  * to be, the higher this multiplier, and thus the higher
  * the barrier to go to an expensive C state.
  */
-static inline int performance_multiplier(unsigned long nr_iowaiters, unsigned long load)
+static inline int performance_multiplier(unsigned long nr_iowaiters)
 {
-	int mult = 1;
-
-	/* for higher loadavg, we are more reluctant */
-
-	mult += 2 * get_loadavg(load);
-
-	/* for IO wait tasks (per cpu!) we add 5x each */
-	mult += 10 * nr_iowaiters;
-
-	return mult;
+	/* for IO wait tasks (per cpu!) we add 10x each */
+	return 1 + 10 * nr_iowaiters;
 }
 
 static DEFINE_PER_CPU(struct menu_device, menu_devices);
@@ -301,7 +288,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	int idx;
 	unsigned int interactivity_req;
 	unsigned int predicted_us;
-	unsigned long nr_iowaiters, cpu_load;
+	unsigned long nr_iowaiters;
 	ktime_t delta_next;
 
 	if (data->needs_update) {
@@ -312,7 +299,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	/* determine the expected residency time, round up */
 	data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length(&delta_next));
 
-	get_iowait_load(&nr_iowaiters, &cpu_load);
+	nr_iowaiters = nr_iowait_cpu(dev->cpu);
 	data->bucket = which_bucket(data->next_timer_us, nr_iowaiters);
 
 	if (unlikely(drv->state_count <= 1 || latency_req == 0) ||
@@ -356,7 +343,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		 * Use the performance multiplier and the user-configurable
 		 * latency_req to determine the maximum exit latency.
 		 */
-		interactivity_req = predicted_us / performance_multiplier(nr_iowaiters, cpu_load);
+		interactivity_req = predicted_us / performance_multiplier(nr_iowaiters);
 		if (latency_req > interactivity_req)
 			latency_req = interactivity_req;
 	}

include/linux/sched/stat.h

@@ -20,7 +20,6 @@ extern unsigned long nr_running(void);
 extern bool single_task_running(void);
 extern unsigned long nr_iowait(void);
 extern unsigned long nr_iowait_cpu(int cpu);
-extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
 
 static inline int sched_info_on(void)
 {

kernel/sched/core.c

@@ -2887,13 +2887,6 @@ unsigned long nr_iowait_cpu(int cpu)
 	return atomic_read(&cpu_rq(cpu)->nr_iowait);
 }
 
-void get_iowait_load(unsigned long *nr_waiters, unsigned long *load)
-{
-	struct rq *rq = this_rq();
-	*nr_waiters = atomic_read(&rq->nr_iowait);
-	*load = rq->load.weight;
-}
-
 /*
  * IO-wait accounting, and how its mostly bollocks (on SMP).
  *