sched/fair: Account update_blocked_averages in newidle_balance cost

The time spent to update the blocked load can be significant depending of
the complexity fo the cgroup hierarchy. Take this time into account in
the cost of the 1st load balance of a newly idle cpu.

Also reduce the number of call to sched_clock_cpu() and track more actual
work.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Link: https://lore.kernel.org/r/20211019123537.17146-2-vincent.guittot@linaro.org

kernel/sched/fair.c

@@ -10840,9 +10840,9 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 {
 	unsigned long next_balance = jiffies + HZ;
 	int this_cpu = this_rq->cpu;
+	u64 t0, t1, curr_cost = 0;
 	struct sched_domain *sd;
 	int pulled_task = 0;
-	u64 curr_cost = 0;
 
 	update_misfit_status(NULL, this_rq);
 
@@ -10887,11 +10887,13 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 
 	raw_spin_rq_unlock(this_rq);
 
+	t0 = sched_clock_cpu(this_cpu);
 	update_blocked_averages(this_cpu);
+
 	rcu_read_lock();
 	for_each_domain(this_cpu, sd) {
 		int continue_balancing = 1;
-		u64 t0, domain_cost;
+		u64 domain_cost;
 
 		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) {
 			update_next_balance(sd, &next_balance);
@@ -10899,17 +10901,18 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 		}
 
 		if (sd->flags & SD_BALANCE_NEWIDLE) {
-			t0 = sched_clock_cpu(this_cpu);
 
 			pulled_task = load_balance(this_cpu, this_rq,
 						   sd, CPU_NEWLY_IDLE,
 						   &continue_balancing);
 
-			domain_cost = sched_clock_cpu(this_cpu) - t0;
+			t1 = sched_clock_cpu(this_cpu);
+			domain_cost = t1 - t0;
 			if (domain_cost > sd->max_newidle_lb_cost)
 				sd->max_newidle_lb_cost = domain_cost;
 
 			curr_cost += domain_cost;
+			t0 = t1;
 		}
 
 		update_next_balance(sd, &next_balance);