sched/fair: Only compute base_energy_pd if necessary

find_energy_efficient_cpu() searches the best energy CPU
to place a task on. To do so, the energy of each performance domain
(pd) is computed w/ and w/o the task placed on it.

The energy of a pd w/o the task (base_energy_pd) is computed prior
knowing whether a CPU is available in the pd.

Move the base_energy_pd computation after looping through the CPUs
of a pd and only compute it if at least one CPU is available.
Suggested-by: Xuewen Yan <xuewen.yan@unisoc.com>
Signed-off-by: Pierre Gondois <Pierre.Gondois@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reviewed-by: Vincent Donnefort <vincent.donnefort@arm.com>
Link: https://lkml.kernel.org/r/20210504090743.9688-2-Pierre.Gondois@arm.com

kernel/sched/fair.c

@@ -6687,13 +6687,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 
 	for (; pd; pd = pd->next) {
 		unsigned long cur_delta, spare_cap, max_spare_cap = 0;
+		bool compute_prev_delta = false;
 		unsigned long base_energy_pd;
 		int max_spare_cap_cpu = -1;
 
-		/* Compute the 'base' energy of the pd, without @p */
-		base_energy_pd = compute_energy(p, -1, pd);
-		base_energy += base_energy_pd;
-
 		for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) {
 			if (!cpumask_test_cpu(cpu, p->cpus_ptr))
 				continue;
@@ -6714,25 +6711,35 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			if (!fits_capacity(util, cpu_cap))
 				continue;
 
-			/* Always use prev_cpu as a candidate. */
 			if (cpu == prev_cpu) {
-				prev_delta = compute_energy(p, prev_cpu, pd);
-				prev_delta -= base_energy_pd;
-				best_delta = min(best_delta, prev_delta);
-			}
-
-			/*
-			 * Find the CPU with the maximum spare capacity in
-			 * the performance domain
-			 */
-			if (spare_cap > max_spare_cap) {
+				/* Always use prev_cpu as a candidate. */
+				compute_prev_delta = true;
+			} else if (spare_cap > max_spare_cap) {
+				/*
+				 * Find the CPU with the maximum spare capacity
+				 * in the performance domain.
+				 */
 				max_spare_cap = spare_cap;
 				max_spare_cap_cpu = cpu;
 			}
 		}
 
-		/* Evaluate the energy impact of using this CPU. */
-		if (max_spare_cap_cpu >= 0 && max_spare_cap_cpu != prev_cpu) {
+		if (max_spare_cap_cpu < 0 && !compute_prev_delta)
+			continue;
+
+		/* Compute the 'base' energy of the pd, without @p */
+		base_energy_pd = compute_energy(p, -1, pd);
+		base_energy += base_energy_pd;
+
+		/* Evaluate the energy impact of using prev_cpu. */
+		if (compute_prev_delta) {
+			prev_delta = compute_energy(p, prev_cpu, pd);
+			prev_delta -= base_energy_pd;
+			best_delta = min(best_delta, prev_delta);
+		}
+
+		/* Evaluate the energy impact of using max_spare_cap_cpu. */
+		if (max_spare_cap_cpu >= 0) {
 			cur_delta = compute_energy(p, max_spare_cap_cpu, pd);
 			cur_delta -= base_energy_pd;
 			if (cur_delta < best_delta) {