sched: fair-group: de-couple load-balancing from the rb-trees

De-couple load-balancing from the rb-trees, so that I can change their
organization.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

include/linux/init_task.h

@@ -151,6 +151,9 @@ extern struct group_info init_groups;
 	.cpus_allowed	= CPU_MASK_ALL,					\
 	.mm		= NULL,						\
 	.active_mm	= &init_mm,					\
+	.se		= {						\
+		.group_node 	= LIST_HEAD_INIT(tsk.se.group_node),	\
+	},								\
 	.rt		= {						\
 		.run_list	= LIST_HEAD_INIT(tsk.rt.run_list),	\
 		.time_slice	= HZ, 					\

include/linux/sched.h

@@ -946,6 +946,7 @@ struct load_weight {
 struct sched_entity {
 	struct load_weight	load;		/* for load-balancing */
 	struct rb_node		run_node;
+	struct list_head	group_node;
 	unsigned int		on_rq;
 
 	u64			exec_start;

kernel/sched.c

@@ -384,8 +384,12 @@ struct cfs_rq {
 
 	struct rb_root tasks_timeline;
 	struct rb_node *rb_leftmost;
-	struct rb_node *rb_load_balance_curr;
-	/* 'curr' points to currently running entity on this cfs_rq.
+
+	struct list_head tasks;
+	struct list_head *balance_iterator;
+
+	/*
+	 * 'curr' points to currently running entity on this cfs_rq.
 	 * It is set to NULL otherwise (i.e when none are currently running).
 	 */
 	struct sched_entity *curr, *next;
@@ -2525,6 +2529,7 @@ static void __sched_fork(struct task_struct *p)
 
 	INIT_LIST_HEAD(&p->rt.run_list);
 	p->se.on_rq = 0;
+	INIT_LIST_HEAD(&p->se.group_node);
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
@@ -7898,6 +7903,7 @@ int in_sched_functions(unsigned long addr)
 static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
 {
 	cfs_rq->tasks_timeline = RB_ROOT;
+	INIT_LIST_HEAD(&cfs_rq->tasks);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	cfs_rq->rq = rq;
 #endif

kernel/sched_fair.c

@@ -533,6 +533,7 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		add_cfs_task_weight(cfs_rq, se->load.weight);
 	cfs_rq->nr_running++;
 	se->on_rq = 1;
+	list_add(&se->group_node, &cfs_rq->tasks);
 }
 
 static void
@@ -545,6 +546,7 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		add_cfs_task_weight(cfs_rq, -se->load.weight);
 	cfs_rq->nr_running--;
 	se->on_rq = 0;
+	list_del_init(&se->group_node);
 }
 
 static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -1289,21 +1291,24 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
  * the current task:
  */
 static struct task_struct *
-__load_balance_iterator(struct cfs_rq *cfs_rq, struct rb_node *curr)
+__load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
 {
 	struct task_struct *p = NULL;
 	struct sched_entity *se;
 
-	if (!curr)
+	if (next == &cfs_rq->tasks)
 		return NULL;
 
 	/* Skip over entities that are not tasks */
 	do {
-		se = rb_entry(curr, struct sched_entity, run_node);
-		curr = rb_next(curr);
-	} while (curr && !entity_is_task(se));
+		se = list_entry(next, struct sched_entity, group_node);
+		next = next->next;
+	} while (next != &cfs_rq->tasks && !entity_is_task(se));
 
-	cfs_rq->rb_load_balance_curr = curr;
+	if (next == &cfs_rq->tasks)
+		return NULL;
+
+	cfs_rq->balance_iterator = next;
 
 	if (entity_is_task(se))
 		p = task_of(se);
@@ -1315,14 +1320,14 @@ static struct task_struct *load_balance_start_fair(void *arg)
 {
 	struct cfs_rq *cfs_rq = arg;
 
-	return __load_balance_iterator(cfs_rq, first_fair(cfs_rq));
+	return __load_balance_iterator(cfs_rq, cfs_rq->tasks.next);
 }
 
 static struct task_struct *load_balance_next_fair(void *arg)
 {
 	struct cfs_rq *cfs_rq = arg;
 
-	return __load_balance_iterator(cfs_rq, cfs_rq->rb_load_balance_curr);
+	return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator);
 }
 
 static unsigned long