sched/fair: Add 'group_misfit_task' load-balance type

To maximize throughput in systems with asymmetric CPU capacities (e.g.
ARM big.LITTLE) load-balancing has to consider task and CPU utilization
as well as per-CPU compute capacity when load-balancing in addition to
the current average load based load-balancing policy. Tasks with high
utilization that are scheduled on a lower capacity CPU need to be
identified and migrated to a higher capacity CPU if possible to maximize
throughput.

To implement this additional policy an additional group_type
(load-balance scenario) is added: 'group_misfit_task'. This represents
scenarios where a sched_group has one or more tasks that are not
suitable for its per-CPU capacity. 'group_misfit_task' is only considered
if the system is not overloaded or imbalanced ('group_imbalanced' or
'group_overloaded').

Identifying misfit tasks requires the rq lock to be held. To avoid
taking remote rq locks to examine source sched_groups for misfit tasks,
each CPU is responsible for tracking misfit tasks themselves and update
the rq->misfit_task flag. This means checking task utilization when
tasks are scheduled and on sched_tick.

Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dietmar.eggemann@arm.com
Cc: gaku.inami.xh@renesas.com
Cc: valentin.schneider@arm.com
Cc: vincent.guittot@linaro.org
Link: http://lkml.kernel.org/r/1530699470-29808-3-git-send-email-morten.rasmussen@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/fair.c

@@ -693,6 +693,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
 static unsigned long task_h_load(struct task_struct *p);
+static unsigned long capacity_of(int cpu);
 
 /* Give new sched_entity start runnable values to heavy its load in infant time */
 void init_entity_runnable_average(struct sched_entity *se)
@@ -1446,7 +1447,6 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 static unsigned long weighted_cpuload(struct rq *rq);
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
-static unsigned long capacity_of(int cpu);
 
 /* Cached statistics for all CPUs within a node */
 struct numa_stats {
@@ -3647,6 +3647,29 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 	WRITE_ONCE(p->se.avg.util_est, ue);
 }
 
+static inline int task_fits_capacity(struct task_struct *p, long capacity)
+{
+	return capacity * 1024 > task_util_est(p) * capacity_margin;
+}
+
+static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
+{
+	if (!static_branch_unlikely(&sched_asym_cpucapacity))
+		return;
+
+	if (!p) {
+		rq->misfit_task_load = 0;
+		return;
+	}
+
+	if (task_fits_capacity(p, capacity_of(cpu_of(rq)))) {
+		rq->misfit_task_load = 0;
+		return;
+	}
+
+	rq->misfit_task_load = task_h_load(p);
+}
+
 #else /* CONFIG_SMP */
 
 #define UPDATE_TG	0x0
@@ -3676,6 +3699,7 @@ util_est_enqueue(struct cfs_rq *cfs_rq, struct task_struct *p) {}
 static inline void
 util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p,
 		 bool task_sleep) {}
+static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {}
 
 #endif /* CONFIG_SMP */
 
@@ -6201,7 +6225,7 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
 	/* Bring task utilization in sync with prev_cpu */
 	sync_entity_load_avg(&p->se);
 
-	return min_cap * 1024 < task_util(p) * capacity_margin;
+	return !task_fits_capacity(p, min_cap);
 }
 
 /*
@@ -6618,9 +6642,12 @@ done: __maybe_unused;
 	if (hrtick_enabled(rq))
 		hrtick_start_fair(rq, p);
 
+	update_misfit_status(p, rq);
+
 	return p;
 
 idle:
+	update_misfit_status(NULL, rq);
 	new_tasks = idle_balance(rq, rf);
 
 	/*
@@ -6826,6 +6853,13 @@ static unsigned long __read_mostly max_load_balance_interval = HZ/10;
 
 enum fbq_type { regular, remote, all };
 
+enum group_type {
+	group_other = 0,
+	group_misfit_task,
+	group_imbalanced,
+	group_overloaded,
+};
+
 #define LBF_ALL_PINNED	0x01
 #define LBF_NEED_BREAK	0x02
 #define LBF_DST_PINNED  0x04
@@ -7399,12 +7433,6 @@ static unsigned long task_h_load(struct task_struct *p)
 
 /********** Helpers for find_busiest_group ************************/
 
-enum group_type {
-	group_other = 0,
-	group_imbalanced,
-	group_overloaded,
-};
-
 /*
  * sg_lb_stats - stats of a sched_group required for load_balancing
  */
@@ -7420,6 +7448,7 @@ struct sg_lb_stats {
 	unsigned int group_weight;
 	enum group_type group_type;
 	int group_no_capacity;
+	unsigned long group_misfit_task_load; /* A CPU has a task too big for its capacity */
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int nr_numa_running;
 	unsigned int nr_preferred_running;
@@ -7712,6 +7741,9 @@ group_type group_classify(struct sched_group *group,
 	if (sg_imbalanced(group))
 		return group_imbalanced;
 
+	if (sgs->group_misfit_task_load)
+		return group_misfit_task;
+
 	return group_other;
 }
 
@@ -7786,6 +7818,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		 */
 		if (!nr_running && idle_cpu(i))
 			sgs->idle_cpus++;
+
+		if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
+		    sgs->group_misfit_task_load < rq->misfit_task_load)
+			sgs->group_misfit_task_load = rq->misfit_task_load;
 	}
 
 	/* Adjust by relative CPU capacity of the group */
@@ -9567,6 +9603,8 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 
 	if (static_branch_unlikely(&sched_numa_balancing))
 		task_tick_numa(rq, curr);
+
+	update_misfit_status(curr, rq);
 }
 
 /*

kernel/sched/sched.h

@@ -842,6 +842,8 @@ struct rq {
 
 	unsigned char		idle_balance;
 
+	unsigned long		misfit_task_load;
+
 	/* For active balancing */
 	int			active_balance;
 	int			push_cpu;