sched/fair: Do not compute NUMA Balancing stats unnecessarily during lb

Aggregate nr_numa_running and nr_preferred_running when load balancing
at NUMA domains only. While at it, also move the aggregation below the
idle_cpu() check since an idle CPU cannot have any preferred tasks.

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

Author: kudureranganath

kernel/sched/fair.c

@@ -10409,7 +10409,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 				      bool *sg_overloaded,
 				      bool *sg_overutilized)
 {
-	int i, nr_running, local_group;
+	int i, nr_running, local_group, sd_flags = env->sd->flags;
 
 	memset(sgs, 0, sizeof(*sgs));
 
@@ -10433,10 +10433,6 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		if (cpu_overutilized(i))
 			*sg_overutilized = 1;
 
-#ifdef CONFIG_NUMA_BALANCING
-		sgs->nr_numa_running += rq->nr_numa_running;
-		sgs->nr_preferred_running += rq->nr_preferred_running;
-#endif
 		/*
 		 * No need to call idle_cpu() if nr_running is not 0
 		 */
@@ -10446,10 +10442,17 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			continue;
 		}
 
+#ifdef CONFIG_NUMA_BALANCING
+		/* Only fbq_classify_group() uses this to classify NUMA groups */
+		if (sd_flags & SD_NUMA) {
+			sgs->nr_numa_running += rq->nr_numa_running;
+			sgs->nr_preferred_running += rq->nr_preferred_running;
+		}
+#endif
 		if (local_group)
 			continue;
 
-		if (env->sd->flags & SD_ASYM_CPUCAPACITY) {
+		if (sd_flags & SD_ASYM_CPUCAPACITY) {
 			/* Check for a misfit task on the cpu */
 			if (sgs->group_misfit_task_load < rq->misfit_task_load) {
 				sgs->group_misfit_task_load = rq->misfit_task_load;