sched/fair: Make sched-idle CPU selection consistent throughout

There are instances where we keep searching for an idle CPU despite
already having a sched-idle CPU (in find_idlest_group_cpu(),
select_idle_smt() and select_idle_cpu() and then there are places where
we don't necessarily do that and return a sched-idle CPU as soon as we
find one (in select_idle_sibling()). This looks a bit inconsistent and
it may be worth having the same policy everywhere.

On the other hand, choosing a sched-idle CPU over a idle one shall be
beneficial from performance and power point of view as well, as we don't
need to get the CPU online from a deep idle state which wastes quite a
lot of time and energy and delays the scheduling of the newly woken up
task.

This patch tries to simplify code around sched-idle CPU selection and
make it consistent throughout.

Testing is done with the help of rt-app on hikey board (ARM64 octa-core,
2 clusters, 0-3 and 4-7). The cpufreq governor was set to performance to
avoid any side affects from CPU frequency. Following are the tests
performed:

Test 1: 1-cfs-task:

 A single SCHED_NORMAL task is pinned to CPU5 which runs for 2333 us
 out of 7777 us (so gives time for the cluster to go in deep idle
 state).

Test 2: 1-cfs-1-idle-task:

 A single SCHED_NORMAL task is pinned on CPU5 and single SCHED_IDLE
 task is pinned on CPU6 (to make sure cluster 1 doesn't go in deep idle
 state).

Test 3: 1-cfs-8-idle-task:

 A single SCHED_NORMAL task is pinned on CPU5 and eight SCHED_IDLE
 tasks are created which run forever (not pinned anywhere, so they run
 on all CPUs). Checked with kernelshark that as soon as NORMAL task
 sleeps, the SCHED_IDLE task starts running on CPU5.

And here are the results on mean latency (in us), using the "st" tool.

  $ st 1-cfs-task/rt-app-cfs_thread-0.log
  N       min     max     sum     mean    stddev
  642     90      592     197180  307.134 109.906

  $ st 1-cfs-1-idle-task/rt-app-cfs_thread-0.log
  N       min     max     sum     mean    stddev
  642     67      311     113850  177.336 41.4251

  $ st 1-cfs-8-idle-task/rt-app-cfs_thread-0.log
  N       min     max     sum     mean    stddev
  643     29      173     41364   64.3297 13.2344

The mean latency when we need to:

 - wakeup from deep idle state is 307 us.
 - wakeup from shallow idle state is 177 us.
 - preempt a SCHED_IDLE task is 64 us.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/b90cbcce608cef4e02a7bbfe178335f76d201bab.1573728344.git.viresh.kumar@linaro.orgSigned-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/fair.c

@@ -5588,7 +5588,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
 	unsigned int min_exit_latency = UINT_MAX;
 	u64 latest_idle_timestamp = 0;
 	int least_loaded_cpu = this_cpu;
-	int shallowest_idle_cpu = -1, si_cpu = -1;
+	int shallowest_idle_cpu = -1;
 	int i;
 
 	/* Check if we have any choice: */
@@ -5597,6 +5597,9 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
 
 	/* Traverse only the allowed CPUs */
 	for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) {
+		if (sched_idle_cpu(i))
+			return i;
+
 		if (available_idle_cpu(i)) {
 			struct rq *rq = cpu_rq(i);
 			struct cpuidle_state *idle = idle_get_state(rq);
@@ -5619,12 +5622,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
 				latest_idle_timestamp = rq->idle_stamp;
 				shallowest_idle_cpu = i;
 			}
-		} else if (shallowest_idle_cpu == -1 && si_cpu == -1) {
-			if (sched_idle_cpu(i)) {
-				si_cpu = i;
-				continue;
-			}
-
+		} else if (shallowest_idle_cpu == -1) {
 			load = cpu_load(cpu_rq(i));
 			if (load < min_load) {
 				min_load = load;
@@ -5633,11 +5631,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
 		}
 	}
 
-	if (shallowest_idle_cpu != -1)
-		return shallowest_idle_cpu;
-	if (si_cpu != -1)
-		return si_cpu;
-	return least_loaded_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,
@@ -5790,7 +5784,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
  */
 static int select_idle_smt(struct task_struct *p, int target)
 {
-	int cpu, si_cpu = -1;
+	int cpu;
 
 	if (!static_branch_likely(&sched_smt_present))
 		return -1;
@@ -5798,13 +5792,11 @@ static int select_idle_smt(struct task_struct *p, int target)
 	for_each_cpu(cpu, cpu_smt_mask(target)) {
 		if (!cpumask_test_cpu(cpu, p->cpus_ptr))
 			continue;
-		if (available_idle_cpu(cpu))
+		if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
 			return cpu;
-		if (si_cpu == -1 && sched_idle_cpu(cpu))
-			si_cpu = cpu;
 	}
 
-	return si_cpu;
+	return -1;
 }
 
 #else /* CONFIG_SCHED_SMT */
@@ -5834,7 +5826,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 	u64 time, cost;
 	s64 delta;
 	int this = smp_processor_id();
-	int cpu, nr = INT_MAX, si_cpu = -1;
+	int cpu, nr = INT_MAX;
 
 	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
 	if (!this_sd)
@@ -5864,11 +5856,9 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 
 	for_each_cpu_wrap(cpu, cpus, target) {
 		if (!--nr)
-			return si_cpu;
-		if (available_idle_cpu(cpu))
+			return -1;
+		if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
 			break;
-		if (si_cpu == -1 && sched_idle_cpu(cpu))
-			si_cpu = cpu;
 	}
 
 	time = cpu_clock(this) - time;