sched: Packing support until a frequency threshold

Add another dimension for task packing based on frequency. This patch
adds a per-cpu tunable, rq->mostly_idle_freq, which when set will
result in tasks being packed on a single cpu in cluster as long as
cluster frequency is less than set threshold.

Change-Id: I318e9af6c8788ddf5dfcda407d621449ea5343c0
Signed-off-by: Srivatsa Vaddagiri <vatsa@codeaurora.org>

3 files changed, 64 insertions, 0 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a7324abaeb3f..d43925c6e560 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9134,6 +9134,7 @@ void __init sched_init(void)
 		rq->hmp_flags = 0;
 		rq->mostly_idle_load = pct_to_real(20);
 		rq->mostly_idle_nr_run = 3;
+		rq->mostly_idle_freq = 0;
 #ifdef CONFIG_SCHED_FREQ_INPUT
 		rq->curr_runnable_sum = rq->prev_runnable_sum = 0;
 		rq->old_busy_time = 0;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 087f5e072e35..1238a6825e7f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2703,6 +2703,25 @@ int sched_set_cpu_mostly_idle_load(int cpu, int mostly_idle_pct)
 	return 0;
 }
 
+int sched_set_cpu_mostly_idle_freq(int cpu, unsigned int mostly_idle_freq)
+{
+	struct rq *rq = cpu_rq(cpu);
+
+	if (mostly_idle_freq > rq->max_possible_freq)
+		return -EINVAL;
+
+	rq->mostly_idle_freq = mostly_idle_freq;
+
+	return 0;
+}
+
+unsigned int sched_get_cpu_mostly_idle_freq(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+
+	return rq->mostly_idle_freq;
+}
+
 int sched_get_cpu_mostly_idle_load(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -3109,6 +3128,42 @@ static int skip_cpu(struct task_struct *p, int cpu, int reason)
 	return skip;
 }
 
+/*
+ * Select a single cpu in cluster as target for packing, iff cluster frequency
+ * is less than a threshold level
+ */
+static int select_packing_target(struct task_struct *p, int best_cpu)
+{
+	struct rq *rq = cpu_rq(best_cpu);
+	struct cpumask search_cpus;
+	int i;
+	int min_cost = INT_MAX;
+	int target = best_cpu;
+
+	if (rq->cur_freq >= rq->mostly_idle_freq)
+		return best_cpu;
+
+	/* Don't pack if current freq is low because of throttling */
+	if (rq->max_freq <= rq->mostly_idle_freq)
+		return best_cpu;
+
+	cpumask_and(&search_cpus, tsk_cpus_allowed(p), cpu_online_mask);
+	cpumask_and(&search_cpus, &search_cpus, &rq->freq_domain_cpumask);
+
+	/* Pick the first lowest power cpu as target */
+	for_each_cpu(i, &search_cpus) {
+		int cost = power_cost(p, i);
+
+		if (cost < min_cost) {
+			target = i;
+			min_cost = cost;
+		}
+	}
+
+	return target;
+}
+
+
 /* return cheapest cpu that can fit this task */
 static int select_best_cpu(struct task_struct *p, int target, int reason)
 {
@@ -3220,6 +3275,9 @@ done:
 			best_cpu = fallback_idle_cpu;
 	}
 
+	if (cpu_rq(best_cpu)->mostly_idle_freq)
+		best_cpu = select_packing_target(p, best_cpu);
+
 	return best_cpu;
 }
 
@@ -9286,6 +9344,10 @@ static inline int _nohz_kick_needed_hmp(struct rq *rq, int cpu, int *type)
 	struct sched_domain *sd;
 	int i;
 
+	if (rq->mostly_idle_freq && rq->cur_freq < rq->mostly_idle_freq
+		 && rq->max_freq > rq->mostly_idle_freq)
+			return 0;
+
 	if (rq->nr_running >= 2 && (rq->nr_running - rq->nr_small_tasks >= 2 ||
 	     rq->nr_running > rq->mostly_idle_nr_run ||
 		cpu_load(cpu) > rq->mostly_idle_load)) {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d0193932354f..fcdf4063ac11 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -660,6 +660,7 @@ struct rq {
 	u64 window_start;
 	u32 mostly_idle_load;
 	int mostly_idle_nr_run;
+	int mostly_idle_freq;
 
 #ifdef CONFIG_SCHED_FREQ_INPUT
 	unsigned int old_busy_time;