sched: group scheduling, change how cpu load is calculated

This patch changes how the cpu load exerted by fair_sched_class tasks
is calculated. Load exerted by fair_sched_class tasks on a cpu is now
a summation of the group weights, rather than summation of task weights.
Weight exerted by a group on a cpu is dependent on the shares allocated
to it.

This version of patch has a minor impact on code size, but should have
no runtime/functional impact for !CONFIG_FAIR_GROUP_SCHED.

Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 40 insertions, 20 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index cfa695819252..c915f3e6e593 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -886,6 +886,16 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime);
 static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
 #endif
 
+static inline void inc_cpu_load(struct rq *rq, unsigned long load)
+{
+	update_load_add(&rq->load, load);
+}
+
+static inline void dec_cpu_load(struct rq *rq, unsigned long load)
+{
+	update_load_sub(&rq->load, load);
+}
+
 #include "sched_stats.h"
 #include "sched_idletask.c"
 #include "sched_fair.c"
@@ -896,26 +906,14 @@ static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
 
 #define sched_class_highest (&rt_sched_class)
 
-static inline void inc_load(struct rq *rq, const struct task_struct *p)
-{
-	update_load_add(&rq->load, p->se.load.weight);
-}
-
-static inline void dec_load(struct rq *rq, const struct task_struct *p)
-{
-	update_load_sub(&rq->load, p->se.load.weight);
-}
-
 static void inc_nr_running(struct task_struct *p, struct rq *rq)
 {
 	rq->nr_running++;
-	inc_load(rq, p);
 }
 
 static void dec_nr_running(struct task_struct *p, struct rq *rq)
 {
 	rq->nr_running--;
-	dec_load(rq, p);
 }
 
 static void set_load_weight(struct task_struct *p)
@@ -4087,10 +4085,8 @@ void set_user_nice(struct task_struct *p, long nice)
 		goto out_unlock;
 	}
 	on_rq = p->se.on_rq;
-	if (on_rq) {
+	if (on_rq)
 		dequeue_task(rq, p, 0);
-		dec_load(rq, p);
-	}
 
 	p->static_prio = NICE_TO_PRIO(nice);
 	set_load_weight(p);
@@ -4100,7 +4096,6 @@ void set_user_nice(struct task_struct *p, long nice)
 
 	if (on_rq) {
 		enqueue_task(rq, p, 0);
-		inc_load(rq, p);
 		/*
 		 * If the task increased its priority or is running and
 		 * lowered its priority, then reschedule its CPU:
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 0c5fdce67228..30ae9c2a2861 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -760,15 +760,26 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
 static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
 {
 	struct cfs_rq *cfs_rq;
-	struct sched_entity *se = &p->se;
+	struct sched_entity *se = &p->se,
+			    *topse = NULL;	/* Highest schedulable entity */
+	int incload = 1;
 
 	for_each_sched_entity(se) {
-		if (se->on_rq)
+		topse = se;
+		if (se->on_rq) {
+			incload = 0;
 			break;
+		}
 		cfs_rq = cfs_rq_of(se);
 		enqueue_entity(cfs_rq, se, wakeup);
 		wakeup = 1;
 	}
+	/* Increment cpu load if we just enqueued the first task of a group on
+	 * 'rq->cpu'. 'topse' represents the group to which task 'p' belongs
+	 * at the highest grouping level.
+	 */
+	if (incload)
+		inc_cpu_load(rq, topse->load.weight);
 }
 
 /*
@@ -779,16 +790,28 @@ static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
 static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
 {
 	struct cfs_rq *cfs_rq;
-	struct sched_entity *se = &p->se;
+	struct sched_entity *se = &p->se,
+			    *topse = NULL; 	/* Highest schedulable entity */
+	int decload = 1;
 
 	for_each_sched_entity(se) {
+		topse = se;
 		cfs_rq = cfs_rq_of(se);
 		dequeue_entity(cfs_rq, se, sleep);
 		/* Don't dequeue parent if it has other entities besides us */
-		if (cfs_rq->load.weight)
+		if (cfs_rq->load.weight) {
+			if (parent_entity(se))
+				decload = 0;
 			break;
+		}
 		sleep = 1;
 	}
+	/* Decrement cpu load if we just dequeued the last task of a group on
+	 * 'rq->cpu'. 'topse' represents the group to which task 'p' belongs
+	 * at the highest grouping level.
+	 */
+	if (decload)
+		dec_cpu_load(rq, topse->load.weight);
 }
 
 /*
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 9ba3daa03475..cefcd5105146 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -32,6 +32,7 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
 
 	list_add_tail(&p->run_list, array->queue + p->prio);
 	__set_bit(p->prio, array->bitmap);
+	inc_cpu_load(rq, p->se.load.weight);
 }
 
 /*
@@ -46,6 +47,7 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
 	list_del(&p->run_list);
 	if (list_empty(array->queue + p->prio))
 		__clear_bit(p->prio, array->bitmap);
+	dec_cpu_load(rq, p->se.load.weight);
 }
 
 /*