sched/fair: Do not compute overloaded status unnecessarily during lb

Only set sg_overloaded when computing sg_lb_stats() at the highest sched
domain since rd->overloaded status is updated only when load balancing
at the highest domain. While at it, move setting of sg_overloaded below
idle_cpu() check since an idle CPU can never be overloaded.

Signed-off-by: K Prateek Nayak <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Vincent Guittot <[email protected]>
Reviewed-by: Shrikanth Hegde <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: kudureranganath

kernel/sched/fair.c

@@ -10410,6 +10410,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 				      bool *sg_overutilized)
 {
 	int i, nr_running, local_group, sd_flags = env->sd->flags;
+	bool balancing_at_rd = !env->sd->parent;
 
 	memset(sgs, 0, sizeof(*sgs));
 
@@ -10427,9 +10428,6 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		nr_running = rq->nr_running;
 		sgs->sum_nr_running += nr_running;
 
-		if (nr_running > 1)
-			*sg_overloaded = 1;
-
 		if (cpu_overutilized(i))
 			*sg_overutilized = 1;
 
@@ -10442,6 +10440,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			continue;
 		}
 
+		/* Overload indicator is only updated at root domain */
+		if (balancing_at_rd && nr_running > 1)
+			*sg_overloaded = 1;
+
 #ifdef CONFIG_NUMA_BALANCING
 		/* Only fbq_classify_group() uses this to classify NUMA groups */
 		if (sd_flags & SD_NUMA) {