BACKPORT: sched/fair: Move select_task_rq_fair slow-path into its own function

In preparation for changes that would otherwise require adding a new
level of indentation to the while(sd) loop, create a new function
find_idlest_cpu() which contains this loop, and rename the existing
find_idlest_cpu() to find_idlest_group_cpu().

Code inside the while(sd) loop is unchanged. @new_cpu is added as a
variable in the new function, with the same initial value as the
@new_cpu in select_task_rq_fair().

Change-Id: I9842308cab00dc9cd6c513fc38c609089a1aaaaf
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20171005114516.18617-2-brendan.jackman@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
(reworked for eas/cas schedstats added in Android)
(cherry-picked commit 18bd1b4bd53a from tip:sched/core)
Signed-off-by: Chris Redpath <chris.redpath@arm.com>

Author: Brendan Jackman

kernel/sched/fair.c

@@ -6072,10 +6072,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 }
 
 /*
- * find_idlest_cpu - find the idlest cpu among the cpus in group.
+ * find_idlest_group_cpu - find the idlest cpu among the cpus in group.
  */
 static int
-find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
+find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 {
 	unsigned long load, min_load = ULONG_MAX;
 	unsigned int min_exit_latency = UINT_MAX;
@@ -6122,6 +6122,65 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 	}
 
 	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
+ }
+
+static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p,
+				  int cpu, int prev_cpu, int sd_flag)
+{
+	int new_cpu = prev_cpu;
+	int wu = sd_flag & SD_BALANCE_WAKE;
+	int cas_cpu = -1;
+
+	if (wu) {
+		schedstat_inc(p, se.statistics.nr_wakeups_cas_attempts);
+		schedstat_inc(this_rq(), eas_stats.cas_attempts);
+	}
+
+	while (sd) {
+		struct sched_group *group;
+		struct sched_domain *tmp;
+		int weight;
+
+		if (wu)
+			schedstat_inc(sd, eas_stats.cas_attempts);
+
+		if (!(sd->flags & sd_flag)) {
+			sd = sd->child;
+			continue;
+		}
+
+		group = find_idlest_group(sd, p, cpu, sd_flag);
+		if (!group) {
+			sd = sd->child;
+			continue;
+		}
+
+		new_cpu = find_idlest_group_cpu(group, p, cpu);
+		if (new_cpu == -1 || new_cpu == cpu) {
+			/* Now try balancing at a lower domain level of cpu */
+			sd = sd->child;
+			continue;
+		}
+
+		/* Now try balancing at a lower domain level of new_cpu */
+		cpu = cas_cpu = new_cpu;
+		weight = sd->span_weight;
+		sd = NULL;
+		for_each_domain(cpu, tmp) {
+			if (weight <= tmp->span_weight)
+				break;
+			if (tmp->flags & sd_flag)
+				sd = tmp;
+		}
+		/* while loop will break here if sd == NULL */
+	}
+
+	if (wu && (cas_cpu >= 0)) {
+		schedstat_inc(p, se.statistics.nr_wakeups_cas_count);
+		schedstat_inc(this_rq(), eas_stats.cas_count);
+	}
+
+	return new_cpu;
 }
 
 /*
@@ -6698,56 +6757,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 			new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
 
 	} else {
-		int wu = sd_flag & SD_BALANCE_WAKE;
-		int cas_cpu = -1;
-
-		if (wu) {
-			schedstat_inc(p, se.statistics.nr_wakeups_cas_attempts);
-			schedstat_inc(this_rq(), eas_stats.cas_attempts);
-		}
-
-		while (sd) {
-			struct sched_group *group;
-			int weight;
-
-			if (wu)
-				schedstat_inc(sd, eas_stats.cas_attempts);
-
-			if (!(sd->flags & sd_flag)) {
-				sd = sd->child;
-				continue;
-			}
-
-			group = find_idlest_group(sd, p, cpu, sd_flag);
-			if (!group) {
-				sd = sd->child;
-				continue;
-			}
-
-			new_cpu = find_idlest_cpu(group, p, cpu);
-			if (new_cpu == -1 || new_cpu == cpu) {
-				/* Now try balancing at a lower domain level of cpu */
-				sd = sd->child;
-				continue;
-			}
-
-			/* Now try balancing at a lower domain level of new_cpu */
-			cpu = cas_cpu = new_cpu;
-			weight = sd->span_weight;
-			sd = NULL;
-			for_each_domain(cpu, tmp) {
-				if (weight <= tmp->span_weight)
-					break;
-				if (tmp->flags & sd_flag)
-					sd = tmp;
-			}
-			/* while loop will break here if sd == NULL */
-		}
-
-		if (wu && (cas_cpu >= 0)) {
-			schedstat_inc(p, se.statistics.nr_wakeups_cas_count);
-			schedstat_inc(this_rq(), eas_stats.cas_count);
-		}
+		new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag);
 	}
 	rcu_read_unlock();