Merge branch 'upstream-runnable-load-avg-in-load-balance-v2' into big-LITTLE-MP-upstream-v2

Conflicts:
	include/linux/sched.h

3 files changed, 49 insertions, 17 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index e2ed2d217f6..fbca8583f06 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1041,6 +1041,7 @@ struct sched_domain;
 #else
 #define ENQUEUE_WAKING		0
 #endif
+#define ENQUEUE_NEWTASK		8
 
 #define DEQUEUE_SLEEP		1
 
@@ -1166,8 +1167,8 @@ struct sched_entity {
 	/* rq "owned" by this entity/group: */
 	struct cfs_rq		*my_q;
 #endif
+
 #ifdef CONFIG_SMP
-	/* Per-entity load-tracking */
 	struct sched_avg	avg;
 #endif
 };
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f166474e435..d16b9635441 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1564,6 +1564,8 @@ static void __sched_fork(struct task_struct *p)
 #ifdef CONFIG_SMP
 	p->se.avg.runnable_avg_period = 0;
 	p->se.avg.runnable_avg_sum = 0;
+	p->se.avg.decay_count = 0;
+	p->se.avg.load_avg_contrib = 0;
 #endif
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
@@ -1709,7 +1711,7 @@ void wake_up_new_task(struct task_struct *p)
 #endif
 
 	rq = __task_rq_lock(p);
-	activate_task(rq, p, 0);
+	activate_task(rq, p, ENQUEUE_NEWTASK);
 	p->on_rq = 1;
 	trace_sched_wakeup_new(p, true);
 	check_preempt_curr(rq, p, WF_FORK);
@@ -2528,7 +2530,7 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
 void update_idle_cpu_load(struct rq *this_rq)
 {
 	unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
-	unsigned long load = this_rq->load.weight;
+	unsigned long load = (unsigned long)this_rq->cfs.runnable_load_avg;
 	unsigned long pending_updates;
 
 	/*
@@ -2578,7 +2580,7 @@ static void update_cpu_load_active(struct rq *this_rq)
 	 * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
 	 */
 	this_rq->last_load_update_tick = jiffies;
-	__update_cpu_load(this_rq, this_rq->load.weight, 1);
+	__update_cpu_load(this_rq, this_rq->cfs.runnable_load_avg, 1);
 
 	calc_load_account_active(this_rq);
 }
@@ -2684,8 +2686,8 @@ void scheduler_tick(void)
 
 	raw_spin_lock(&rq->lock);
 	update_rq_clock(rq);
-	update_cpu_load_active(rq);
 	curr->sched_class->task_tick(rq, curr, 0);
+	update_cpu_load_active(rq);
 	raw_spin_unlock(&rq->lock);
 
 	perf_event_task_tick();
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 01b3806e385..d66fa87ebdb 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1572,8 +1572,9 @@ static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
 /* Add the load generated by se into cfs_rq's child load-average */
 static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 						  struct sched_entity *se,
-						  int wakeup)
+						  int flags)
 {
+	int wakeup = flags & ENQUEUE_WAKEUP;
 	/*
 	 * We track migrations using entity decay_count <= 0, on a wake-up
 	 * migration we use a negative decay count to track the remote decays
@@ -1607,6 +1608,12 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 		update_entity_load_avg(se, 0);
 	}
 
+	/*
+	 * set the initial load avg of new task same as its load
+	 * in order to avoid brust fork make few cpu too heavier
+	 */
+	if (flags & ENQUEUE_NEWTASK)
+		se->avg.load_avg_contrib = se->load.weight;
 	cfs_rq->runnable_load_avg += se->avg.load_avg_contrib;
 	/* we force update consideration on load-balancer moves */
 	update_cfs_rq_blocked_load(cfs_rq, !wakeup);
@@ -1778,7 +1785,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
-	enqueue_entity_load_avg(cfs_rq, se, flags & ENQUEUE_WAKEUP);
+	enqueue_entity_load_avg(cfs_rq, se, flags);
 	account_entity_enqueue(cfs_rq, se);
 	update_cfs_shares(cfs_rq);
 
@@ -2976,7 +2983,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 /* Used instead of source_load when we know the type == 0 */
 static unsigned long weighted_cpuload(const int cpu)
 {
-	return cpu_rq(cpu)->load.weight;
+	return (unsigned long)cpu_rq(cpu)->cfs.runnable_load_avg;
 }
 
 /*
@@ -3023,7 +3030,7 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 	unsigned long nr_running = ACCESS_ONCE(rq->nr_running);
 
 	if (nr_running)
-		return rq->load.weight / nr_running;
+		return (unsigned long)rq->cfs.runnable_load_avg / nr_running;
 
 	return 0;
 }
@@ -3052,7 +3059,8 @@ static void task_waking_fair(struct task_struct *p)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 /*
- * effective_load() calculates the load change as seen from the root_task_group
+ * effective_load() calculates the runnable load average change as seen from
+ * the root_task_group
  *
  * Adding load to a group doesn't make a group heavier, but can cause movement
  * of group shares between cpus. Assuming the shares were perfectly aligned one
@@ -3100,6 +3108,9 @@ static void task_waking_fair(struct task_struct *p)
  * Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7)
  * times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 -
  * 4/7) times the weight of the group.
+ *
+ * After get effective_load of the load moving, will engaged the sched entity's
+ * runnable avg.
  */
 static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 {
@@ -3174,6 +3185,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 	struct task_group *tg;
 	unsigned long weight;
 	int balanced;
+	int runnable_avg;
 
 	idx	  = sd->wake_idx;
 	this_cpu  = smp_processor_id();
@@ -3189,13 +3201,19 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 	if (sync) {
 		tg = task_group(current);
 		weight = current->se.load.weight;
+		runnable_avg = current->se.avg.runnable_avg_sum * NICE_0_LOAD
+				/ (current->se.avg.runnable_avg_period + 1);
 
-		this_load += effective_load(tg, this_cpu, -weight, -weight);
-		load += effective_load(tg, prev_cpu, 0, -weight);
+		this_load += effective_load(tg, this_cpu, -weight, -weight)
+				* runnable_avg >> NICE_0_SHIFT;
+		load += effective_load(tg, prev_cpu, 0, -weight)
+				* runnable_avg >> NICE_0_SHIFT;
 	}
 
 	tg = task_group(p);
 	weight = p->se.load.weight;
+	runnable_avg = p->se.avg.runnable_avg_sum * NICE_0_LOAD
+				/ (p->se.avg.runnable_avg_period + 1);
 
 	/*
 	 * In low-load situations, where prev_cpu is idle and this_cpu is idle
@@ -3207,16 +3225,18 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 	 * task to be woken on this_cpu.
 	 */
 	if (this_load > 0) {
-		s64 this_eff_load, prev_eff_load;
+		s64 this_eff_load, prev_eff_load, tmp_eff_load;
 
 		this_eff_load = 100;
 		this_eff_load *= power_of(prev_cpu);
-		this_eff_load *= this_load +
-			effective_load(tg, this_cpu, weight, weight);
+		tmp_eff_load = effective_load(tg, this_cpu, weight, weight)
+				* runnable_avg >> NICE_0_SHIFT;
+		this_eff_load *= this_load + tmp_eff_load;
 
 		prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
 		prev_eff_load *= power_of(this_cpu);
-		prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight);
+		prev_eff_load *= load + (effective_load(tg, prev_cpu, 0, weight)
+						* runnable_avg >> NICE_0_SHIFT);
 
 		balanced = this_eff_load <= prev_eff_load;
 	} else
@@ -4090,6 +4110,15 @@ static unsigned long task_h_load(struct task_struct *p);
 
 static const unsigned int sched_nr_migrate_break = 32;
 
+static unsigned long task_h_load_avg(struct task_struct *p)
+{
+	u32 period = p->se.avg.runnable_avg_period;
+	if (!period)
+		return 0;
+
+	return task_h_load(p) * p->se.avg.runnable_avg_sum / period;
+}
+
 /*
  * move_tasks tries to move up to imbalance weighted load from busiest to
  * this_rq, as part of a balancing operation within domain "sd".
@@ -4125,7 +4154,7 @@ static int move_tasks(struct lb_env *env)
 		if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
 			goto next;
 
-		load = task_h_load(p);
+		load = task_h_load_avg(p);
 
 		if (sched_feat(LB_MIN) && load < 204 && !env->sd->nr_balance_failed)
 			goto next;