ANDROID: sched/fair: Bias EAS placement for latencyexperimental/eas-dev

Add to find_energy_efficient_cpu() a latency sensitive case which mimics
what was done for prefer-idle in android-4.19 and before (see [1] for
reference).

This isn't strictly equivalent to the legacy algorithm but comes real
close, and isn't very invasive. Overall, the idea is to select the
biggest idle CPU we can find for latency-sensitive boosted tasks, and
the smallest CPU where the can fit for latency-sensitive non-boosted
tasks.

The main differences with the legacy behaviour are the following:

 1. the policy for 'prefer idle' when there isn't a single idle CPU in
    the system is simpler now. We just pick the CPU with the highest
    spare capacity;

 2. the cstate awareness is implemented by minimizing the exit latency
    rather than the idle state index. This is how it is done in the slow
    path (find_idlest_group_cpu()), it doesn't require us to keep hooks
    into CPUIdle, and should actually be better because what we want is
    a CPU that can wake up quickly;

 3. non-latency-sensitive tasks just use the standard mainline
    energy-aware wake-up path, which decides the placement using the
    Energy Model;

 4. the 'boosted' and 'latency_sensitive' attributes of a task come from
    util_clamp (which now replaces schedtune).

[1] https://android.googlesource.com/kernel/common.git/+/c27c56105dcaaae54ecc39ef33fbfac87a1486fc

Change-Id: Ia58516906e9cb5abe08385a8cd088097043d8703
Signed-off-by: Quentin Perret <quentin.perret@arm.com>

1 files changed, 38 insertions, 2 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ec7565ad589e..f6b6f4b251be 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6348,8 +6348,13 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu, int sy
 {
 	unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX;
 	struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
+	int max_spare_cap_cpu_ls = prev_cpu, best_idle_cpu = -1;
+	unsigned long max_spare_cap_ls = 0, target_cap;
 	unsigned long cpu_cap, util, base_energy = 0;
+	bool boosted, latency_sensitive = false;
+	unsigned int min_exit_lat = UINT_MAX;
 	int cpu, best_energy_cpu = prev_cpu;
+	struct cpuidle_state *idle;
 	struct sched_domain *sd;
 	struct perf_domain *pd;
 
@@ -6378,6 +6383,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu, int sy
 	if (!task_util_est(p))
 		goto unlock;
 
+	latency_sensitive = uclamp_latency_sensitive(p);
+	boosted = uclamp_boosted(p);
+	target_cap = boosted ? 0 : ULONG_MAX;
+
 	for (; pd; pd = pd->next) {
 		unsigned long cur_delta, spare_cap, max_spare_cap = 0;
 		unsigned long base_energy_pd;
@@ -6398,7 +6407,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu, int sy
 				continue;
 
 			/* Always use prev_cpu as a candidate. */
-			if (cpu == prev_cpu) {
+			if (!latency_sensitive && cpu == prev_cpu) {
 				prev_delta = compute_energy(p, prev_cpu, pd);
 				prev_delta -= base_energy_pd;
 				best_delta = min(best_delta, prev_delta);
@@ -6413,10 +6422,34 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu, int sy
 				max_spare_cap = spare_cap;
 				max_spare_cap_cpu = cpu;
 			}
+
+			if (!latency_sensitive)
+				continue;
+
+			if (idle_cpu(cpu)) {
+				cpu_cap = capacity_orig_of(cpu);
+				if (boosted && cpu_cap < target_cap)
+					continue;
+				if (!boosted && cpu_cap > target_cap)
+					continue;
+				idle = idle_get_state(cpu_rq(cpu));
+				if (idle && idle->exit_latency > min_exit_lat &&
+						cpu_cap == target_cap)
+					continue;
+
+				if (idle)
+					min_exit_lat = idle->exit_latency;
+				target_cap = cpu_cap;
+				best_idle_cpu = cpu;
+			} else if (spare_cap > max_spare_cap_ls) {
+				max_spare_cap_ls = spare_cap;
+				max_spare_cap_cpu_ls = cpu;
+			}
 		}
 
 		/* Evaluate the energy impact of using this CPU. */
-		if (max_spare_cap_cpu >= 0 && max_spare_cap_cpu != prev_cpu) {
+		if (!latency_sensitive && max_spare_cap_cpu >= 0 &&
+						max_spare_cap_cpu != prev_cpu) {
 			cur_delta = compute_energy(p, max_spare_cap_cpu, pd);
 			cur_delta -= base_energy_pd;
 			if (cur_delta < best_delta) {
@@ -6428,6 +6461,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu, int sy
 unlock:
 	rcu_read_unlock();
 
+	if (latency_sensitive)
+		return best_idle_cpu >= 0 ? best_idle_cpu : max_spare_cap_cpu_ls;
+
 	/*
 	 * Pick the best CPU if prev_cpu cannot be used, or if it saves at
 	 * least 6% of the energy used by prev_cpu.