[RFCv4 PATCH 23/34] sched: Extend sched_group_energy to test load-balancing decisions

[Morten Rasmussen <morten.rasmussen@arm.com>]

Extended sched_group_energy() to support energy prediction with usage
(tasks) added/removed from a specific cpu or migrated between a pair of
cpus. Useful for load-balancing decision making.

cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>

Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
---
 kernel/sched/fair.c | 86 +++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 60 insertions(+), 26 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2677ca6..52403e9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4810,15 +4810,17 @@ static unsigned long capacity_curr_of(int cpu)
  * capacity_curr (but not capacity_orig) as it useful for predicting the
  * capacity required after task migrations (scheduler-driven DVFS).
  */
-
-static unsigned long get_cpu_usage(int cpu)
+static unsigned long __get_cpu_usage(int cpu, int delta)
 {
 	int sum;
 	unsigned long usage = cpu_rq(cpu)->cfs.utilization_load_avg;
 	unsigned long blocked = cpu_rq(cpu)->cfs.utilization_blocked_avg;
 	unsigned long capacity_orig = capacity_orig_of(cpu);
 
-	sum = usage + blocked;
+	sum = usage + blocked + delta;
+
+	if (sum < 0)
+		return 0;
 
 	if (sum >= capacity_orig)
 		return capacity_orig;
@@ -4826,13 +4828,28 @@ static unsigned long get_cpu_usage(int cpu)
 	return sum;
 }
 
+static unsigned long get_cpu_usage(int cpu)
+{
+	return __get_cpu_usage(cpu, 0);
+}
+
 static inline bool energy_aware(void)
 {
 	return sched_feat(ENERGY_AWARE);
 }
 
+struct energy_env {
+	struct sched_group	*sg_top;
+	struct sched_group	*sg_cap;
+	int			cap_idx;
+	int			usage_delta;
+	int			src_cpu;
+	int			dst_cpu;
+	int			energy;
+};
+
 /*
- * cpu_norm_usage() returns the cpu usage relative to a specific capacity,
+ * __cpu_norm_usage() returns the cpu usage relative to a specific capacity,
  * i.e. it's busy ratio, in the range [0..SCHED_LOAD_SCALE] which is useful for
  * energy calculations. Using the scale-invariant usage returned by
  * get_cpu_usage() and approximating scale-invariant usage by:
@@ -4845,9 +4862,9 @@ static inline bool energy_aware(void)
  *
  *   norm_usage = running_time/time ~ usage/capacity
  */
-static unsigned long cpu_norm_usage(int cpu, unsigned long capacity)
+static unsigned long __cpu_norm_usage(int cpu, unsigned long capacity, int delta)
 {
-	int usage = __get_cpu_usage(cpu);
+	int usage = __get_cpu_usage(cpu, delta);
 
 	if (usage >= capacity)
 		return SCHED_CAPACITY_SCALE;
@@ -4855,13 +4872,25 @@ static unsigned long cpu_norm_usage(int cpu, unsigned long capacity)
 	return (usage << SCHED_CAPACITY_SHIFT)/capacity;
 }
 
-static unsigned long group_max_usage(struct sched_group *sg)
+static int calc_usage_delta(struct energy_env *eenv, int cpu)
 {
-	int i;
+	if (cpu == eenv->src_cpu)
+		return -eenv->usage_delta;
+	if (cpu == eenv->dst_cpu)
+		return eenv->usage_delta;
+	return 0;
+}
+
+static
+unsigned long group_max_usage(struct energy_env *eenv, struct sched_group *sg)
+{
+	int i, delta;
 	unsigned long max_usage = 0;
 
-	for_each_cpu(i, sched_group_cpus(sg))
-		max_usage = max(max_usage, get_cpu_usage(i));
+	for_each_cpu(i, sched_group_cpus(sg)) {
+		delta = calc_usage_delta(eenv, i);
+		max_usage = max(max_usage, __get_cpu_usage(i, delta));
+	}
 
 	return max_usage;
 }
@@ -4875,31 +4904,36 @@ static unsigned long group_max_usage(struct sched_group *sg)
  * latter is used as the estimate as it leads to a more pessimistic energy
  * estimate (more busy).
  */
-static unsigned long group_norm_usage(struct sched_group *sg, int cap_idx)
+static unsigned
+long group_norm_usage(struct energy_env *eenv, struct sched_group *sg)
 {
-	int i;
+	int i, delta;
 	unsigned long usage_sum = 0;
-	unsigned long capacity = sg->sge->cap_states[cap_idx].cap;
+	unsigned long capacity = sg->sge->cap_states[eenv->cap_idx].cap;
 
-	for_each_cpu(i, sched_group_cpus(sg))
-		usage_sum += cpu_norm_usage(i, capacity);
+	for_each_cpu(i, sched_group_cpus(sg)) {
+		delta = calc_usage_delta(eenv, i);
+		usage_sum += __cpu_norm_usage(i, capacity, delta);
+	}
 
 	if (usage_sum > SCHED_CAPACITY_SCALE)
 		return SCHED_CAPACITY_SCALE;
 	return usage_sum;
 }
 
-static int find_new_capacity(struct sched_group *sg,
+static int find_new_capacity(struct energy_env *eenv,
 		struct sched_group_energy *sge)
 {
 	int idx;
-	unsigned long util = group_max_usage(sg);
+	unsigned long util = group_max_usage(eenv, eenv->sg_cap);
 
 	for (idx = 0; idx < sge->nr_cap_states; idx++) {
 		if (sge->cap_states[idx].cap >= util)
 			return idx;
 	}
 
+	eenv->cap_idx = idx;
+
 	return idx;
 }
 
@@ -4912,16 +4946,16 @@ static int find_new_capacity(struct sched_group *sg,
  * gather the same usage statistics multiple times. This can probably be done in
  * a faster but more complex way.
  */
-static unsigned int sched_group_energy(struct sched_group *sg_top)
+static unsigned int sched_group_energy(struct energy_env *eenv)
 {
 	struct sched_domain *sd;
 	int cpu, total_energy = 0;
 	struct cpumask visit_cpus;
 	struct sched_group *sg;
 
-	WARN_ON(!sg_top->sge);
+	WARN_ON(!eenv->sg_top->sge);
 
-	cpumask_copy(&visit_cpus, sched_group_cpus(sg_top));
+	cpumask_copy(&visit_cpus, sched_group_cpus(eenv->sg_top));
 
 	while (!cpumask_empty(&visit_cpus)) {
 		struct sched_group *sg_shared_cap = NULL;
@@ -4944,17 +4978,16 @@ static unsigned int sched_group_energy(struct sched_group *sg_top)
 				break;
 
 			do {
-				struct sched_group *sg_cap_util;
 				unsigned long group_util;
 				int sg_busy_energy, sg_idle_energy, cap_idx;
 
 				if (sg_shared_cap && sg_shared_cap->group_weight >= sg->group_weight)
-					sg_cap_util = sg_shared_cap;
+					eenv->sg_cap = sg_shared_cap;
 				else
-					sg_cap_util = sg;
+					eenv->sg_cap = sg;
 
-				cap_idx = find_new_capacity(sg_cap_util, sg->sge);
-				group_util = group_norm_usage(sg, cap_idx);
+				cap_idx = find_new_capacity(eenv, sg->sge);
+				group_util = group_norm_usage(eenv, sg);
 				sg_busy_energy = (group_util * sg->sge->cap_states[cap_idx].power)
 										>> SCHED_CAPACITY_SHIFT;
 				sg_idle_energy = ((SCHED_LOAD_SCALE-group_util) * sg->sge->idle_states[0].power)
@@ -4965,7 +4998,7 @@ static unsigned int sched_group_energy(struct sched_group *sg_top)
 				if (!sd->child)
 					cpumask_xor(&visit_cpus, &visit_cpus, sched_group_cpus(sg));
 
-				if (cpumask_equal(sched_group_cpus(sg), sched_group_cpus(sg_top)))
+				if (cpumask_equal(sched_group_cpus(sg), sched_group_cpus(eenv->sg_top)))
 					goto next_cpu;
 
 			} while (sg = sg->next, sg != sd->groups);
@@ -4974,6 +5007,7 @@ static unsigned int sched_group_energy(struct sched_group *sg_top)
 		continue;
 	}
 
+	eenv->energy = total_energy;
 	return total_energy;
 }
 
-- 
1.9.1