sched: Add group_misfit_task load-balance type

To maximize throughput in systems with reduced capacity cpus (e.g.
high RT/IRQ load and/or 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 that are scheduled on a reduced capacity
cpu need to be identified and migrated to a higher capacity cpu if
possible.

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 tasks that are not suitable for its
per-cpu capacity. group_misfit_task is only considered if the system is
not overloaded in any other way (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>

2 files changed, 23 insertions, 7 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9762288ee47b..b16e1b7878f6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5739,6 +5739,8 @@ again:
 	if (hrtick_enabled(rq))
 		hrtick_start_fair(rq, p);
 
+	rq->misfit_task = !task_fits_max(p, rq->cpu);
+
 	return p;
 simple:
 	cfs_rq = &rq->cfs;
@@ -5760,9 +5762,12 @@ simple:
 	if (hrtick_enabled(rq))
 		hrtick_start_fair(rq, p);
 
+	rq->misfit_task = !task_fits_max(p, rq->cpu);
+
 	return p;
 
 idle:
+	rq->misfit_task = 0;
 	/*
 	 * This is OK, because current is on_cpu, which avoids it being picked
 	 * for load-balance and preemption/IRQs are still disabled avoiding
@@ -5975,6 +5980,13 @@ 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
@@ -6446,12 +6458,6 @@ 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
  */
@@ -6467,6 +6473,7 @@ struct sg_lb_stats {
 	unsigned int group_weight;
 	enum group_type group_type;
 	int group_no_capacity;
+	int group_misfit_task; /* A cpu has a task too big for its capacity */
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int nr_numa_running;
 	unsigned int nr_preferred_running;
@@ -6783,6 +6790,9 @@ group_type group_classify(struct sched_group *group,
 	if (sg_imbalanced(group))
 		return group_imbalanced;
 
+	if (sgs->group_misfit_task)
+		return group_misfit_task;
+
 	return group_other;
 }
 
@@ -6830,8 +6840,11 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		if (idle_cpu(i))
 			sgs->idle_cpus++;
 
-		if (cpu_overutilized(i))
+		if (cpu_overutilized(i)) {
 			*overutilized = true;
+			if (!sgs->group_misfit_task && rq->misfit_task)
+				sgs->group_misfit_task = capacity_of(i);
+		}
 	}
 
 	/* Adjust by relative CPU capacity of the group */
@@ -8412,6 +8425,8 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 
 	if (!rq->rd->overutilized && cpu_overutilized(task_cpu(curr)))
 		rq->rd->overutilized = true;
+
+	rq->misfit_task = !task_fits_max(curr, rq->cpu);
 }
 
 /*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 967d70d49af9..fcbb3e07accc 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -584,6 +584,7 @@ struct rq {
 	#define CPU_LOAD_IDX_MAX 5
 	unsigned long cpu_load[CPU_LOAD_IDX_MAX];
 	unsigned long last_load_update_tick;
+	unsigned int misfit_task;
 #ifdef CONFIG_NO_HZ_COMMON
 	u64 nohz_stamp;
 	unsigned long nohz_flags;