X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=kernel%2Fsched_fair.c;h=08ae848b71d4643429f67ef312a7bfd78a32aa0a;hb=1b7558e457ed0de61023cfc913d2c342c7c3d9f2;hp=b89fec93a2371cab354f944c2fec29edda4c9859;hpb=18d95a2832c1392a2d63227a7a6d433cb9f2037e;p=linux-2.6

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index b89fec93a2..08ae848b71 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -362,29 +362,47 @@ static u64 __sched_period(unsigned long nr_running)
  */
 static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	return calc_delta_mine(__sched_period(cfs_rq->nr_running),
-			       se->load.weight, &cfs_rq->load);
+	u64 slice = __sched_period(cfs_rq->nr_running);
+
+	for_each_sched_entity(se) {
+		cfs_rq = cfs_rq_of(se);
+
+		slice *= se->load.weight;
+		do_div(slice, cfs_rq->load.weight);
+	}
+
+
+	return slice;
 }
 
 /*
- * We calculate the vruntime slice.
+ * We calculate the vruntime slice of a to be inserted task
  *
  * vs = s/w = p/rw
  */
-static u64 __sched_vslice(unsigned long rq_weight, unsigned long nr_running)
+static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	u64 vslice = __sched_period(nr_running);
+	unsigned long nr_running = cfs_rq->nr_running;
+	unsigned long weight;
+	u64 vslice;
 
-	vslice *= NICE_0_LOAD;
-	do_div(vslice, rq_weight);
+	if (!se->on_rq)
+		nr_running++;
 
-	return vslice;
-}
+	vslice = __sched_period(nr_running);
 
-static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	return __sched_vslice(cfs_rq->load.weight + se->load.weight,
-			cfs_rq->nr_running + 1);
+	for_each_sched_entity(se) {
+		cfs_rq = cfs_rq_of(se);
+
+		weight = cfs_rq->load.weight;
+		if (!se->on_rq)
+			weight += se->load.weight;
+
+		vslice *= NICE_0_LOAD;
+		do_div(vslice, weight);
+	}
+
+	return vslice;
 }
 
 /*
@@ -492,41 +510,22 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * Scheduling class queueing methods:
  */
 
-#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
-static void
-add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
-{
-	cfs_rq->task_weight += weight;
-}
-#else
-static inline void
-add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
-{
-}
-#endif
-
 static void
 account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	update_load_add(&cfs_rq->load, se->load.weight);
-	if (!parent_entity(se))
-		inc_cpu_load(rq_of(cfs_rq), se->load.weight);
-	if (entity_is_task(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
 account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	update_load_sub(&cfs_rq->load, se->load.weight);
-	if (!parent_entity(se))
-		dec_cpu_load(rq_of(cfs_rq), se->load.weight);
-	if (entity_is_task(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)
@@ -610,13 +609,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 	if (!initial) {
 		/* sleeps upto a single latency don't count. */
-		if (sched_feat(NEW_FAIR_SLEEPERS)) {
-			if (sched_feat(NORMALIZED_SLEEPER))
-				vruntime -= calc_delta_fair(sysctl_sched_latency,
-						&cfs_rq->load);
-			else
-				vruntime -= sysctl_sched_latency;
-		}
+		if (sched_feat(NEW_FAIR_SLEEPERS))
+			vruntime -= sysctl_sched_latency;
 
 		/* ensure we never gain time by being placed backwards. */
 		vruntime = max_vruntime(se->vruntime, vruntime);
@@ -632,6 +626,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
 	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
+	account_entity_enqueue(cfs_rq, se);
 
 	if (wakeup) {
 		place_entity(cfs_rq, se, 0);
@@ -642,7 +637,6 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
 	check_spread(cfs_rq, se);
 	if (se != cfs_rq->curr)
 		__enqueue_entity(cfs_rq, se);
-	account_entity_enqueue(cfs_rq, se);
 }
 
 static void update_avg(u64 *avg, u64 sample)
@@ -791,8 +785,10 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	 * queued ticks are scheduled to match the slice, so don't bother
 	 * validating it and just reschedule.
 	 */
-	if (queued)
-		return resched_task(rq_of(cfs_rq)->curr);
+	if (queued) {
+		resched_task(rq_of(cfs_rq)->curr);
+		return;
+	}
 	/*
 	 * don't let the period tick interfere with the hrtick preemption
 	 */
@@ -907,7 +903,7 @@ static void yield_task_fair(struct rq *rq)
 		return;
 
 	if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
-		__update_rq_clock(rq);
+		update_rq_clock(rq);
 		/*
 		 * Update run-time statistics of the 'current'.
 		 */
@@ -957,7 +953,7 @@ static int wake_idle(int cpu, struct task_struct *p)
 	 * sibling runqueue info. This will avoid the checks and cache miss
 	 * penalities associated with that.
 	 */
-	if (idle_cpu(cpu) || cpu_rq(cpu)->nr_running > 1)
+	if (idle_cpu(cpu) || cpu_rq(cpu)->cfs.nr_running > 1)
 		return cpu;
 
 	for_each_domain(cpu, sd) {
@@ -1000,16 +996,27 @@ wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
 	struct task_struct *curr = this_rq->curr;
 	unsigned long tl = this_load;
 	unsigned long tl_per_task;
+	int balanced;
 
-	if (!(this_sd->flags & SD_WAKE_AFFINE))
+	if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
 		return 0;
 
+	/*
+	 * If sync wakeup then subtract the (maximum possible)
+	 * effect of the currently running task from the load
+	 * of the current CPU:
+	 */
+	if (sync)
+		tl -= current->se.load.weight;
+
+	balanced = 100*(tl + p->se.load.weight) <= imbalance*load;
+
 	/*
 	 * If the currently running task will sleep within
 	 * a reasonable amount of time then attract this newly
 	 * woken task:
 	 */
-	if (sync && curr->sched_class == &fair_sched_class) {
+	if (sync && balanced && curr->sched_class == &fair_sched_class) {
 		if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
 				p->se.avg_overlap < sysctl_sched_migration_cost)
 			return 1;
@@ -1018,16 +1025,8 @@ wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
 	schedstat_inc(p, se.nr_wakeups_affine_attempts);
 	tl_per_task = cpu_avg_load_per_task(this_cpu);
 
-	/*
-	 * If sync wakeup then subtract the (maximum possible)
-	 * effect of the currently running task from the load
-	 * of the current CPU:
-	 */
-	if (sync)
-		tl -= current->se.load.weight;
-
 	if ((tl <= load && tl + target_load(prev_cpu, idx) <= tl_per_task) ||
-			100*(tl + p->se.load.weight) <= imbalance*load) {
+			balanced) {
 		/*
 		 * This domain has SD_WAKE_AFFINE and
 		 * p is cache cold in this domain, and
@@ -1271,21 +1270,24 @@ 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);
@@ -1297,100 +1299,85 @@ 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
-__load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		unsigned long max_load_move, struct sched_domain *sd,
-		enum cpu_idle_type idle, int *all_pinned, int *this_best_prio,
-		struct cfs_rq *cfs_rq)
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static int cfs_rq_best_prio(struct cfs_rq *cfs_rq)
 {
-	struct rq_iterator cfs_rq_iterator;
+	struct sched_entity *curr;
+	struct task_struct *p;
 
-	cfs_rq_iterator.start = load_balance_start_fair;
-	cfs_rq_iterator.next = load_balance_next_fair;
-	cfs_rq_iterator.arg = cfs_rq;
+	if (!cfs_rq->nr_running || !first_fair(cfs_rq))
+		return MAX_PRIO;
 
-	return balance_tasks(this_rq, this_cpu, busiest,
-			max_load_move, sd, idle, all_pinned,
-			this_best_prio, &cfs_rq_iterator);
+	curr = cfs_rq->curr;
+	if (!curr)
+		curr = __pick_next_entity(cfs_rq);
+
+	p = task_of(curr);
+
+	return p->prio;
 }
+#endif
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
 static unsigned long
 load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		  unsigned long max_load_move,
 		  struct sched_domain *sd, enum cpu_idle_type idle,
 		  int *all_pinned, int *this_best_prio)
 {
+	struct cfs_rq *busy_cfs_rq;
 	long rem_load_move = max_load_move;
-	int busiest_cpu = cpu_of(busiest);
-	struct task_group *tg;
-
-	rcu_read_lock();
-	list_for_each_entry(tg, &task_groups, list) {
-		long imbalance;
-		unsigned long this_weight, busiest_weight;
-		long rem_load, max_load, moved_load;
-
-		/*
-		 * empty group
-		 */
-		if (!aggregate(tg, sd)->task_weight)
-			continue;
-
-		rem_load = rem_load_move * aggregate(tg, sd)->rq_weight;
-		rem_load /= aggregate(tg, sd)->load + 1;
-
-		this_weight = tg->cfs_rq[this_cpu]->task_weight;
-		busiest_weight = tg->cfs_rq[busiest_cpu]->task_weight;
+	struct rq_iterator cfs_rq_iterator;
 
-		imbalance = (busiest_weight - this_weight) / 2;
+	cfs_rq_iterator.start = load_balance_start_fair;
+	cfs_rq_iterator.next = load_balance_next_fair;
 
-		if (imbalance < 0)
-			imbalance = busiest_weight;
+	for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
+#ifdef CONFIG_FAIR_GROUP_SCHED
+		struct cfs_rq *this_cfs_rq;
+		long imbalance;
+		unsigned long maxload;
 
-		max_load = max(rem_load, imbalance);
-		moved_load = __load_balance_fair(this_rq, this_cpu, busiest,
-				max_load, sd, idle, all_pinned, this_best_prio,
-				tg->cfs_rq[busiest_cpu]);
+		this_cfs_rq = cpu_cfs_rq(busy_cfs_rq, this_cpu);
 
-		if (!moved_load)
+		imbalance = busy_cfs_rq->load.weight - this_cfs_rq->load.weight;
+		/* Don't pull if this_cfs_rq has more load than busy_cfs_rq */
+		if (imbalance <= 0)
 			continue;
 
-		move_group_shares(tg, sd, busiest_cpu, this_cpu);
+		/* Don't pull more than imbalance/2 */
+		imbalance /= 2;
+		maxload = min(rem_load_move, imbalance);
 
-		moved_load *= aggregate(tg, sd)->load;
-		moved_load /= aggregate(tg, sd)->rq_weight + 1;
+		*this_best_prio = cfs_rq_best_prio(this_cfs_rq);
+#else
+# define maxload rem_load_move
+#endif
+		/*
+		 * pass busy_cfs_rq argument into
+		 * load_balance_[start|next]_fair iterators
+		 */
+		cfs_rq_iterator.arg = busy_cfs_rq;
+		rem_load_move -= balance_tasks(this_rq, this_cpu, busiest,
+					       maxload, sd, idle, all_pinned,
+					       this_best_prio,
+					       &cfs_rq_iterator);
 
-		rem_load_move -= moved_load;
-		if (rem_load_move < 0)
+		if (rem_load_move <= 0)
 			break;
 	}
-	rcu_read_unlock();
 
 	return max_load_move - rem_load_move;
 }
-#else
-static unsigned long
-load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		  unsigned long max_load_move,
-		  struct sched_domain *sd, enum cpu_idle_type idle,
-		  int *all_pinned, int *this_best_prio)
-{
-	return __load_balance_fair(this_rq, this_cpu, busiest,
-			max_load_move, sd, idle, all_pinned,
-			this_best_prio, &busiest->cfs);
-}
-#endif
 
 static int
 move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,