1 files changed, 165 insertions, 64 deletions

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index f604dae7131..ce514afd78f 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -73,6 +73,8 @@ unsigned int sysctl_sched_wakeup_granularity = 5000000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
 
+static const struct sched_class fair_sched_class;
+
 /**************************************************************
  * CFS operations on generic schedulable entities:
  */
@@ -141,6 +143,49 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
 	return se->parent;
 }
 
+/* return depth at which a sched entity is present in the hierarchy */
+static inline int depth_se(struct sched_entity *se)
+{
+	int depth = 0;
+
+	for_each_sched_entity(se)
+		depth++;
+
+	return depth;
+}
+
+static void
+find_matching_se(struct sched_entity **se, struct sched_entity **pse)
+{
+	int se_depth, pse_depth;
+
+	/*
+	 * preemption test can be made between sibling entities who are in the
+	 * same cfs_rq i.e who have a common parent. Walk up the hierarchy of
+	 * both tasks until we find their ancestors who are siblings of common
+	 * parent.
+	 */
+
+	/* First walk up until both entities are at same depth */
+	se_depth = depth_se(*se);
+	pse_depth = depth_se(*pse);
+
+	while (se_depth > pse_depth) {
+		se_depth--;
+		*se = parent_entity(*se);
+	}
+
+	while (pse_depth > se_depth) {
+		pse_depth--;
+		*pse = parent_entity(*pse);
+	}
+
+	while (!is_same_group(*se, *pse)) {
+		*se = parent_entity(*se);
+		*pse = parent_entity(*pse);
+	}
+}
+
 #else	/* CONFIG_FAIR_GROUP_SCHED */
 
 static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
@@ -191,6 +236,11 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
 	return NULL;
 }
 
+static inline void
+find_matching_se(struct sched_entity **se, struct sched_entity **pse)
+{
+}
+
 #endif	/* CONFIG_FAIR_GROUP_SCHED */
 
 
@@ -221,6 +271,27 @@ static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	return se->vruntime - cfs_rq->min_vruntime;
 }
 
+static void update_min_vruntime(struct cfs_rq *cfs_rq)
+{
+	u64 vruntime = cfs_rq->min_vruntime;
+
+	if (cfs_rq->curr)
+		vruntime = cfs_rq->curr->vruntime;
+
+	if (cfs_rq->rb_leftmost) {
+		struct sched_entity *se = rb_entry(cfs_rq->rb_leftmost,
+						   struct sched_entity,
+						   run_node);
+
+		if (vruntime == cfs_rq->min_vruntime)
+			vruntime = se->vruntime;
+		else
+			vruntime = min_vruntime(vruntime, se->vruntime);
+	}
+
+	cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
+}
+
 /*
  * Enqueue an entity into the rb-tree:
  */
@@ -254,15 +325,8 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 * Maintain a cache of leftmost tree entries (it is frequently
 	 * used):
 	 */
-	if (leftmost) {
+	if (leftmost)
 		cfs_rq->rb_leftmost = &se->run_node;
-		/*
-		 * maintain cfs_rq->min_vruntime to be a monotonic increasing
-		 * value tracking the leftmost vruntime in the tree.
-		 */
-		cfs_rq->min_vruntime =
-			max_vruntime(cfs_rq->min_vruntime, se->vruntime);
-	}
 
 	rb_link_node(&se->run_node, parent, link);
 	rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
@@ -272,18 +336,9 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	if (cfs_rq->rb_leftmost == &se->run_node) {
 		struct rb_node *next_node;
-		struct sched_entity *next;
 
 		next_node = rb_next(&se->run_node);
 		cfs_rq->rb_leftmost = next_node;
-
-		if (next_node) {
-			next = rb_entry(next_node,
-					struct sched_entity, run_node);
-			cfs_rq->min_vruntime =
-				max_vruntime(cfs_rq->min_vruntime,
-					     next->vruntime);
-		}
 	}
 
 	if (cfs_rq->next == se)
@@ -334,7 +389,7 @@ int sched_nr_latency_handler(struct ctl_table *table, int write,
 #endif
 
 /*
- * delta *= w / rw
+ * delta *= P[w / rw]
  */
 static inline unsigned long
 calc_delta_weight(unsigned long delta, struct sched_entity *se)
@@ -348,15 +403,13 @@ calc_delta_weight(unsigned long delta, struct sched_entity *se)
 }
 
 /*
- * delta *= rw / w
+ * delta /= w
  */
 static inline unsigned long
 calc_delta_fair(unsigned long delta, struct sched_entity *se)
 {
-	for_each_sched_entity(se) {
-		delta = calc_delta_mine(delta,
-				cfs_rq_of(se)->load.weight, &se->load);
-	}
+	if (unlikely(se->load.weight != NICE_0_LOAD))
+		delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load);
 
 	return delta;
 }
@@ -386,26 +439,26 @@ static u64 __sched_period(unsigned long nr_running)
  * We calculate the wall-time slice from the period by taking a part
  * proportional to the weight.
  *
- * s = p*w/rw
+ * s = p*P[w/rw]
  */
 static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	return calc_delta_weight(__sched_period(cfs_rq->nr_running), se);
+	unsigned long nr_running = cfs_rq->nr_running;
+
+	if (unlikely(!se->on_rq))
+		nr_running++;
+
+	return calc_delta_weight(__sched_period(nr_running), se);
 }
 
 /*
  * We calculate the vruntime slice of a to be inserted task
  *
- * vs = s*rw/w = p
+ * vs = s/w
  */
-static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	unsigned long nr_running = cfs_rq->nr_running;
-
-	if (!se->on_rq)
-		nr_running++;
-
-	return __sched_period(nr_running);
+	return calc_delta_fair(sched_slice(cfs_rq, se), se);
 }
 
 /*
@@ -424,6 +477,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 	schedstat_add(cfs_rq, exec_clock, delta_exec);
 	delta_exec_weighted = calc_delta_fair(delta_exec, curr);
 	curr->vruntime += delta_exec_weighted;
+	update_min_vruntime(cfs_rq);
 }
 
 static void update_curr(struct cfs_rq *cfs_rq)
@@ -613,13 +667,7 @@ static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static void
 place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 {
-	u64 vruntime;
-
-	if (first_fair(cfs_rq)) {
-		vruntime = min_vruntime(cfs_rq->min_vruntime,
-				__pick_next_entity(cfs_rq)->vruntime);
-	} else
-		vruntime = cfs_rq->min_vruntime;
+	u64 vruntime = cfs_rq->min_vruntime;
 
 	/*
 	 * The 'current' period is already promised to the current tasks,
@@ -628,7 +676,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 	 * stays open at the end.
 	 */
 	if (initial && sched_feat(START_DEBIT))
-		vruntime += sched_vslice_add(cfs_rq, se);
+		vruntime += sched_vslice(cfs_rq, se);
 
 	if (!initial) {
 		/* sleeps upto a single latency don't count. */
@@ -696,6 +744,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 	if (se != cfs_rq->curr)
 		__dequeue_entity(cfs_rq, se);
 	account_entity_dequeue(cfs_rq, se);
+	update_min_vruntime(cfs_rq);
 }
 
 /*
@@ -742,16 +791,14 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	se->prev_sum_exec_runtime = se->sum_exec_runtime;
 }
 
+static int
+wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
+
 static struct sched_entity *
 pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	struct rq *rq = rq_of(cfs_rq);
-	u64 pair_slice = rq->clock - cfs_rq->pair_start;
-
-	if (!cfs_rq->next || pair_slice > sched_slice(cfs_rq, cfs_rq->next)) {
-		cfs_rq->pair_start = rq->clock;
+	if (!cfs_rq->next || wakeup_preempt_entity(cfs_rq->next, se) == 1)
 		return se;
-	}
 
 	return cfs_rq->next;
 }
@@ -849,11 +896,31 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 		hrtick_start(rq, delta);
 	}
 }
+
+/*
+ * called from enqueue/dequeue and updates the hrtick when the
+ * current task is from our class and nr_running is low enough
+ * to matter.
+ */
+static void hrtick_update(struct rq *rq)
+{
+	struct task_struct *curr = rq->curr;
+
+	if (curr->sched_class != &fair_sched_class)
+		return;
+
+	if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency)
+		hrtick_start_fair(rq, curr);
+}
 #else /* !CONFIG_SCHED_HRTICK */
 static inline void
 hrtick_start_fair(struct rq *rq, struct task_struct *p)
 {
 }
+
+static inline void hrtick_update(struct rq *rq)
+{
+}
 #endif
 
 /*
@@ -874,7 +941,7 @@ static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
 		wakeup = 1;
 	}
 
-	hrtick_start_fair(rq, rq->curr);
+	hrtick_update(rq);
 }
 
 /*
@@ -896,7 +963,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
 		sleep = 1;
 	}
 
-	hrtick_start_fair(rq, rq->curr);
+	hrtick_update(rq);
 }
 
 /*
@@ -1002,8 +1069,6 @@ static inline int wake_idle(int cpu, struct task_struct *p)
 
 #ifdef CONFIG_SMP
 
-static const struct sched_class fair_sched_class;
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 /*
  * effective_load() calculates the load change as seen from the root_task_group
@@ -1104,10 +1169,9 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
 	if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
 		return 0;
 
-	if (!sync && sched_feat(SYNC_WAKEUPS) &&
-	    curr->se.avg_overlap < sysctl_sched_migration_cost &&
-	    p->se.avg_overlap < sysctl_sched_migration_cost)
-		sync = 1;
+	if (sync && (curr->se.avg_overlap > sysctl_sched_migration_cost ||
+			p->se.avg_overlap > sysctl_sched_migration_cost))
+		sync = 0;
 
 	/*
 	 * If sync wakeup then subtract the (maximum possible)
@@ -1226,13 +1290,42 @@ static unsigned long wakeup_gran(struct sched_entity *se)
 	 * More easily preempt - nice tasks, while not making it harder for
 	 * + nice tasks.
 	 */
-	if (sched_feat(ASYM_GRAN))
-		gran = calc_delta_mine(gran, NICE_0_LOAD, &se->load);
+	if (!sched_feat(ASYM_GRAN) || se->load.weight > NICE_0_LOAD)
+		gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se);
 
 	return gran;
 }
 
 /*
+ * Should 'se' preempt 'curr'.
+ *
+ *             |s1
+ *        |s2
+ *   |s3
+ *         g
+ *      |<--->|c
+ *
+ *  w(c, s1) = -1
+ *  w(c, s2) =  0
+ *  w(c, s3) =  1
+ *
+ */
+static int
+wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
+{
+	s64 gran, vdiff = curr->vruntime - se->vruntime;
+
+	if (vdiff <= 0)
+		return -1;
+
+	gran = wakeup_gran(curr);
+	if (vdiff > gran)
+		return 1;
+
+	return 0;
+}
+
+/*
  * Preempt the current task with a newly woken task if needed:
  */
 static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
@@ -1240,7 +1333,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 	struct task_struct *curr = rq->curr;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 	struct sched_entity *se = &curr->se, *pse = &p->se;
-	s64 delta_exec;
 
 	if (unlikely(rt_prio(p->prio))) {
 		update_rq_clock(rq);
@@ -1278,9 +1370,19 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 		return;
 	}
 
-	delta_exec = se->sum_exec_runtime - se->prev_sum_exec_runtime;
-	if (delta_exec > wakeup_gran(pse))
-		resched_task(curr);
+	find_matching_se(&se, &pse);
+
+	while (se) {
+		BUG_ON(!pse);
+
+		if (wakeup_preempt_entity(se, pse) == 1) {
+			resched_task(curr);
+			break;
+		}
+
+		se = parent_entity(se);
+		pse = parent_entity(pse);
+	}
 }
 
 static struct task_struct *pick_next_task_fair(struct rq *rq)
@@ -1576,9 +1678,6 @@ static const struct sched_class fair_sched_class = {
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
-#ifdef CONFIG_SMP
-	.select_task_rq		= select_task_rq_fair,
-#endif /* CONFIG_SMP */
 
 	.check_preempt_curr	= check_preempt_wakeup,
 
@@ -1586,6 +1685,8 @@ static const struct sched_class fair_sched_class = {
 	.put_prev_task		= put_prev_task_fair,
 
 #ifdef CONFIG_SMP
+	.select_task_rq		= select_task_rq_fair,
+
 	.load_balance		= load_balance_fair,
 	.move_one_task		= move_one_task_fair,
 #endif