X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fsched_fair.c;h=e2a530515619ee8f3b42b1ca246cd18ae05f5544;hb=8d039bc7f3d2330787eaa7a392f5e6489f1544d5;hp=568e922255c6946f98f5981e6db5ab77d05f0d4a;hpb=f6b53205e17c8ca481c69ed579a35a650a4b481a;p=safe%2Fjmp%2Flinux-2.6

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 568e922..e2a5305 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -20,33 +20,38 @@
  *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
  */
 
+#include <linux/latencytop.h>
+
 /*
  * Targeted preemption latency for CPU-bound tasks:
- * (default: 20ms, units: nanoseconds)
+ * (default: 20ms * (1 + ilog(ncpus)), units: nanoseconds)
  *
  * NOTE: this latency value is not the same as the concept of
- * 'timeslice length' - timeslices in CFS are of variable length.
- * (to see the precise effective timeslice length of your workload,
- *  run vmstat and monitor the context-switches field)
+ * 'timeslice length' - timeslices in CFS are of variable length
+ * and have no persistent notion like in traditional, time-slice
+ * based scheduling concepts.
  *
- * On SMP systems the value of this is multiplied by the log2 of the
- * number of CPUs. (i.e. factor 2x on 2-way systems, 3x on 4-way
- * systems, 4x on 8-way systems, 5x on 16-way systems, etc.)
- * Targeted preemption latency for CPU-bound tasks:
+ * (to see the precise effective timeslice length of your workload,
+ *  run vmstat and monitor the context-switches (cs) field)
  */
-const_debug unsigned int sysctl_sched_latency = 20000000ULL;
+unsigned int sysctl_sched_latency = 20000000ULL;
 
 /*
- * After fork, child runs first. (default) If set to 0 then
- * parent will (try to) run first.
+ * Minimal preemption granularity for CPU-bound tasks:
+ * (default: 4 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-const_debug unsigned int sysctl_sched_child_runs_first = 1;
+unsigned int sysctl_sched_min_granularity = 4000000ULL;
 
 /*
- * Minimal preemption granularity for CPU-bound tasks:
- * (default: 2 msec, units: nanoseconds)
+ * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
  */
-unsigned int sysctl_sched_min_granularity __read_mostly = 2000000ULL;
+static unsigned int sched_nr_latency = 5;
+
+/*
+ * After fork, child runs first. (default) If set to 0 then
+ * parent will (try to) run first.
+ */
+const_debug unsigned int sysctl_sched_child_runs_first = 1;
 
 /*
  * sys_sched_yield() compat mode
@@ -58,27 +63,25 @@ unsigned int __read_mostly sysctl_sched_compat_yield;
 
 /*
  * SCHED_BATCH wake-up granularity.
- * (default: 25 msec, units: nanoseconds)
+ * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds)
  *
  * This option delays the preemption effects of decoupled workloads
  * and reduces their over-scheduling. Synchronous workloads will still
  * have immediate wakeup/sleep latencies.
  */
-const_debug unsigned int sysctl_sched_batch_wakeup_granularity = 25000000UL;
+unsigned int sysctl_sched_batch_wakeup_granularity = 10000000UL;
 
 /*
  * SCHED_OTHER wake-up granularity.
- * (default: 1 msec, units: nanoseconds)
+ * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds)
  *
  * This option delays the preemption effects of decoupled workloads
  * and reduces their over-scheduling. Synchronous workloads will still
  * have immediate wakeup/sleep latencies.
  */
-const_debug unsigned int sysctl_sched_wakeup_granularity = 2000000UL;
-
-unsigned int sysctl_sched_runtime_limit __read_mostly;
+unsigned int sysctl_sched_wakeup_granularity = 10000000UL;
 
-extern struct sched_class fair_sched_class;
+const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
 
 /**************************************************************
  * CFS operations on generic schedulable entities:
@@ -116,28 +119,25 @@ static inline struct task_struct *task_of(struct sched_entity *se)
  * Scheduling class tree data structure manipulation methods:
  */
 
-static inline u64
-max_vruntime(u64 min_vruntime, u64 vruntime)
+static inline u64 max_vruntime(u64 min_vruntime, u64 vruntime)
 {
-	if ((vruntime > min_vruntime) ||
-	    (min_vruntime > (1ULL << 61) && vruntime < (1ULL << 50)))
+	s64 delta = (s64)(vruntime - min_vruntime);
+	if (delta > 0)
 		min_vruntime = vruntime;
 
 	return min_vruntime;
 }
 
-static inline void
-set_leftmost(struct cfs_rq *cfs_rq, struct rb_node *leftmost)
+static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
 {
-	struct sched_entity *se;
+	s64 delta = (s64)(vruntime - min_vruntime);
+	if (delta < 0)
+		min_vruntime = vruntime;
 
-	cfs_rq->rb_leftmost = leftmost;
-	if (leftmost)
-		se = rb_entry(leftmost, struct sched_entity, run_node);
+	return min_vruntime;
 }
 
-static inline s64
-entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	return se->vruntime - cfs_rq->min_vruntime;
 }
@@ -145,8 +145,7 @@ entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
 /*
  * Enqueue an entity into the rb-tree:
  */
-static void
-__enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
 	struct rb_node *parent = NULL;
@@ -177,17 +176,16 @@ __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 * used):
 	 */
 	if (leftmost)
-		set_leftmost(cfs_rq, &se->run_node);
+		cfs_rq->rb_leftmost = &se->run_node;
 
 	rb_link_node(&se->run_node, parent, link);
 	rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
 }
 
-static void
-__dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	if (cfs_rq->rb_leftmost == &se->run_node)
-		set_leftmost(cfs_rq, rb_next(&se->run_node));
+		cfs_rq->rb_leftmost = rb_next(&se->run_node);
 
 	rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
 }
@@ -204,45 +202,96 @@ static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
 
 static inline struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 {
-	struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
-	struct sched_entity *se = NULL;
-	struct rb_node *parent;
+	struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
 
-	while (*link) {
-		parent = *link;
-		se = rb_entry(parent, struct sched_entity, run_node);
-		link = &parent->rb_right;
-	}
+	if (!last)
+		return NULL;
 
-	return se;
+	return rb_entry(last, struct sched_entity, run_node);
 }
 
 /**************************************************************
  * Scheduling class statistics methods:
  */
 
+#ifdef CONFIG_SCHED_DEBUG
+int sched_nr_latency_handler(struct ctl_table *table, int write,
+		struct file *filp, void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+
+	if (ret || !write)
+		return ret;
+
+	sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency,
+					sysctl_sched_min_granularity);
+
+	return 0;
+}
+#endif
+
+/*
+ * The idea is to set a period in which each task runs once.
+ *
+ * When there are too many tasks (sysctl_sched_nr_latency) we have to stretch
+ * this period because otherwise the slices get too small.
+ *
+ * p = (nr <= nl) ? l : l*nr/nl
+ */
 static u64 __sched_period(unsigned long nr_running)
 {
 	u64 period = sysctl_sched_latency;
-	unsigned long nr_latency =
-		sysctl_sched_latency / sysctl_sched_min_granularity;
+	unsigned long nr_latency = sched_nr_latency;
 
 	if (unlikely(nr_running > nr_latency)) {
+		period = sysctl_sched_min_granularity;
 		period *= nr_running;
-		do_div(period, nr_latency);
 	}
 
 	return period;
 }
 
+/*
+ * We calculate the wall-time slice from the period by taking a part
+ * proportional to the weight.
+ *
+ * s = p*w/rw
+ */
 static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	u64 period = __sched_period(cfs_rq->nr_running);
+	u64 slice = __sched_period(cfs_rq->nr_running);
 
-	period *= se->load.weight;
-	do_div(period, cfs_rq->load.weight);
+	slice *= se->load.weight;
+	do_div(slice, cfs_rq->load.weight);
 
-	return period;
+	return slice;
+}
+
+/*
+ * We calculate the vruntime slice.
+ *
+ * vs = s/w = p/rw
+ */
+static u64 __sched_vslice(unsigned long rq_weight, unsigned long nr_running)
+{
+	u64 vslice = __sched_period(nr_running);
+
+	vslice *= NICE_0_LOAD;
+	do_div(vslice, rq_weight);
+
+	return vslice;
+}
+
+static u64 sched_vslice(struct cfs_rq *cfs_rq)
+{
+	return __sched_vslice(cfs_rq->load.weight, cfs_rq->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);
 }
 
 /*
@@ -254,7 +303,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 	      unsigned long delta_exec)
 {
 	unsigned long delta_exec_weighted;
-	u64 next_vruntime, min_vruntime;
+	u64 vruntime;
 
 	schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
 
@@ -272,19 +321,13 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 	 * value tracking the leftmost vruntime in the tree.
 	 */
 	if (first_fair(cfs_rq)) {
-		next_vruntime = __pick_next_entity(cfs_rq)->vruntime;
-
-		/* min_vruntime() := !max_vruntime() */
-		min_vruntime = max_vruntime(curr->vruntime, next_vruntime);
-		if (min_vruntime == next_vruntime)
-			min_vruntime = curr->vruntime;
-		else
-			min_vruntime = next_vruntime;
+		vruntime = min_vruntime(curr->vruntime,
+				__pick_next_entity(cfs_rq)->vruntime);
 	} else
-		min_vruntime = curr->vruntime;
+		vruntime = curr->vruntime;
 
 	cfs_rq->min_vruntime =
-		max_vruntime(cfs_rq->min_vruntime, min_vruntime);
+		max_vruntime(cfs_rq->min_vruntime, vruntime);
 }
 
 static void update_curr(struct cfs_rq *cfs_rq)
@@ -305,6 +348,12 @@ static void update_curr(struct cfs_rq *cfs_rq)
 
 	__update_curr(cfs_rq, curr, delta_exec);
 	curr->exec_start = now;
+
+	if (entity_is_task(curr)) {
+		struct task_struct *curtask = task_of(curr);
+
+		cpuacct_charge(curtask, delta_exec);
+	}
 }
 
 static inline void
@@ -313,17 +362,6 @@ update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	schedstat_set(se->wait_start, rq_of(cfs_rq)->clock);
 }
 
-static inline unsigned long
-calc_weighted(unsigned long delta, struct sched_entity *se)
-{
-	unsigned long weight = se->load.weight;
-
-	if (unlikely(weight != NICE_0_LOAD))
-		return (u64)delta * se->load.weight >> NICE_0_SHIFT;
-	else
-		return delta;
-}
-
 /*
  * Task is being enqueued - update stats:
  */
@@ -342,13 +380,15 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	schedstat_set(se->wait_max, max(se->wait_max,
 			rq_of(cfs_rq)->clock - se->wait_start));
+	schedstat_set(se->wait_count, se->wait_count + 1);
+	schedstat_set(se->wait_sum, se->wait_sum +
+			rq_of(cfs_rq)->clock - se->wait_start);
 	schedstat_set(se->wait_start, 0);
 }
 
 static inline void
 update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	update_curr(cfs_rq);
 	/*
 	 * Mark the end of the wait period if dequeueing a
 	 * waiting task:
@@ -369,15 +409,6 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	se->exec_start = rq_of(cfs_rq)->clock;
 }
 
-/*
- * We are descheduling a task - update its stats:
- */
-static inline void
-update_stats_curr_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	se->exec_start = 0;
-}
-
 /**************************************************
  * Scheduling class queueing methods:
  */
@@ -403,6 +434,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 #ifdef CONFIG_SCHEDSTATS
 	if (se->sleep_start) {
 		u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
+		struct task_struct *tsk = task_of(se);
 
 		if ((s64)delta < 0)
 			delta = 0;
@@ -412,9 +444,12 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 		se->sleep_start = 0;
 		se->sum_sleep_runtime += delta;
+
+		account_scheduler_latency(tsk, delta >> 10, 1);
 	}
 	if (se->block_start) {
 		u64 delta = rq_of(cfs_rq)->clock - se->block_start;
+		struct task_struct *tsk = task_of(se);
 
 		if ((s64)delta < 0)
 			delta = 0;
@@ -431,62 +466,70 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		 * time that the task spent sleeping:
 		 */
 		if (unlikely(prof_on == SLEEP_PROFILING)) {
-			struct task_struct *tsk = task_of(se);
 
 			profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
 				     delta >> 20);
 		}
+		account_scheduler_latency(tsk, delta >> 10, 0);
 	}
 #endif
 }
 
+static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+#ifdef CONFIG_SCHED_DEBUG
+	s64 d = se->vruntime - cfs_rq->min_vruntime;
+
+	if (d < 0)
+		d = -d;
+
+	if (d > 3*sysctl_sched_latency)
+		schedstat_inc(cfs_rq, nr_spread_over);
+#endif
+}
+
 static void
 place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 {
-	u64 min_runtime, latency;
+	u64 vruntime;
 
-	min_runtime = cfs_rq->min_vruntime;
+	vruntime = cfs_rq->min_vruntime;
 
-	if (sched_feat(USE_TREE_AVG)) {
+	if (sched_feat(TREE_AVG)) {
 		struct sched_entity *last = __pick_last_entity(cfs_rq);
 		if (last) {
-			min_runtime = __pick_next_entity(cfs_rq)->vruntime;
-			min_runtime += last->vruntime;
-			min_runtime >>= 1;
+			vruntime += last->vruntime;
+			vruntime >>= 1;
 		}
-	} else if (sched_feat(APPROX_AVG))
-		min_runtime += sysctl_sched_latency/2;
+	} else if (sched_feat(APPROX_AVG) && cfs_rq->nr_running)
+		vruntime += sched_vslice(cfs_rq)/2;
 
+	/*
+	 * The 'current' period is already promised to the current tasks,
+	 * however the extra weight of the new task will slow them down a
+	 * little, place the new task so that it fits in the slot that
+	 * stays open at the end.
+	 */
 	if (initial && sched_feat(START_DEBIT))
-		min_runtime += sched_slice(cfs_rq, se);
-
-	if (!initial && sched_feat(NEW_FAIR_SLEEPERS)) {
-		latency = sysctl_sched_latency;
-		if (min_runtime > latency)
-			min_runtime -= latency;
-		else
-			min_runtime = 0;
+		vruntime += sched_vslice_add(cfs_rq, se);
+
+	if (!initial) {
+		/* sleeps upto a single latency don't count. */
+		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);
 	}
 
-	se->vruntime = max(se->vruntime, min_runtime);
+	se->vruntime = vruntime;
 }
 
 static void
-enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
-		int wakeup, int set_curr)
+enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
 {
 	/*
- 	 * In case of the 'current'.
- 	 */
-	if (unlikely(set_curr)) {
-		update_stats_curr_start(cfs_rq, se);
-		cfs_rq->curr = se;
-		account_entity_enqueue(cfs_rq, se);
-		return;
-	}
-
-	/*
-	 * Update the fair clock.
+	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
 
@@ -496,16 +539,23 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 	}
 
 	update_stats_enqueue(cfs_rq, se);
-	__enqueue_entity(cfs_rq, se);
+	check_spread(cfs_rq, se);
+	if (se != cfs_rq->curr)
+		__enqueue_entity(cfs_rq, se);
 	account_entity_enqueue(cfs_rq, se);
 }
 
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 {
+	/*
+	 * Update run-time statistics of the 'current'.
+	 */
+	update_curr(cfs_rq);
+
 	update_stats_dequeue(cfs_rq, se);
-#ifdef CONFIG_SCHEDSTATS
 	if (sleep) {
+#ifdef CONFIG_SCHEDSTATS
 		if (entity_is_task(se)) {
 			struct task_struct *tsk = task_of(se);
 
@@ -514,14 +564,11 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 			if (tsk->state & TASK_UNINTERRUPTIBLE)
 				se->block_start = rq_of(cfs_rq)->clock;
 		}
-	}
 #endif
-	if (likely(se != cfs_rq->curr))
-		__dequeue_entity(cfs_rq, se);
-	else {
-		update_stats_curr_end(cfs_rq, se);
-		cfs_rq->curr = NULL;
 	}
+
+	if (se != cfs_rq->curr)
+		__dequeue_entity(cfs_rq, se);
 	account_entity_dequeue(cfs_rq, se);
 }
 
@@ -539,15 +586,20 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 		resched_task(rq_of(cfs_rq)->curr);
 }
 
-static inline void
+static void
 set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	/*
-	 * Any task has to be enqueued before it get to execute on
-	 * a CPU. So account for the time it spent waiting on the
-	 * runqueue.
-	 */
-	update_stats_wait_end(cfs_rq, se);
+	/* 'current' is not kept within the tree. */
+	if (se->on_rq) {
+		/*
+		 * Any task has to be enqueued before it get to execute on
+		 * a CPU. So account for the time it spent waiting on the
+		 * runqueue.
+		 */
+		update_stats_wait_end(cfs_rq, se);
+		__dequeue_entity(cfs_rq, se);
+	}
+
 	update_stats_curr_start(cfs_rq, se);
 	cfs_rq->curr = se;
 #ifdef CONFIG_SCHEDSTATS
@@ -566,13 +618,12 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
-	struct sched_entity *se = __pick_next_entity(cfs_rq);
-
-	/* 'current' is not kept within the tree. */
-	if (se)
-		__dequeue_entity(cfs_rq, se);
+	struct sched_entity *se = NULL;
 
-	set_next_entity(cfs_rq, se);
+	if (first_fair(cfs_rq)) {
+		se = __pick_next_entity(cfs_rq);
+		set_next_entity(cfs_rq, se);
+	}
 
 	return se;
 }
@@ -586,8 +637,7 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 	if (prev->on_rq)
 		update_curr(cfs_rq);
 
-	update_stats_curr_end(cfs_rq, prev);
-
+	check_spread(cfs_rq, prev);
 	if (prev->on_rq) {
 		update_stats_wait_start(cfs_rq, prev);
 		/* Put 'current' back into the tree. */
@@ -596,14 +646,30 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 	cfs_rq->curr = NULL;
 }
 
-static void entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
+static void
+entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 {
 	/*
 	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
 
-	if (cfs_rq->nr_running > 1)
+#ifdef CONFIG_SCHED_HRTICK
+	/*
+	 * 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);
+	/*
+	 * don't let the period tick interfere with the hrtick preemption
+	 */
+	if (!sched_feat(DOUBLE_TICK) &&
+			hrtimer_active(&rq_of(cfs_rq)->hrtick_timer))
+		return;
+#endif
+
+	if (cfs_rq->nr_running > 1 || !sched_feat(WAKEUP_PREEMPT))
 		check_preempt_tick(cfs_rq, curr);
 }
 
@@ -644,17 +710,23 @@ static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
 
 /* Iterate thr' all leaf cfs_rq's on a runqueue */
 #define for_each_leaf_cfs_rq(rq, cfs_rq) \
-	list_for_each_entry(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
+	list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
 
-/* Do the two (enqueued) tasks belong to the same group ? */
-static inline int is_same_group(struct task_struct *curr, struct task_struct *p)
+/* Do the two (enqueued) entities belong to the same group ? */
+static inline int
+is_same_group(struct sched_entity *se, struct sched_entity *pse)
 {
-	if (curr->se.cfs_rq == p->se.cfs_rq)
+	if (se->cfs_rq == pse->cfs_rq)
 		return 1;
 
 	return 0;
 }
 
+static inline struct sched_entity *parent_entity(struct sched_entity *se)
+{
+	return se->parent;
+}
+
 #else	/* CONFIG_FAIR_GROUP_SCHED */
 
 #define for_each_sched_entity(se) \
@@ -687,13 +759,56 @@ static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
 #define for_each_leaf_cfs_rq(rq, cfs_rq) \
 		for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
 
-static inline int is_same_group(struct task_struct *curr, struct task_struct *p)
+static inline int
+is_same_group(struct sched_entity *se, struct sched_entity *pse)
 {
 	return 1;
 }
 
+static inline struct sched_entity *parent_entity(struct sched_entity *se)
+{
+	return NULL;
+}
+
 #endif	/* CONFIG_FAIR_GROUP_SCHED */
 
+#ifdef CONFIG_SCHED_HRTICK
+static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
+{
+	int requeue = rq->curr == p;
+	struct sched_entity *se = &p->se;
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+	WARN_ON(task_rq(p) != rq);
+
+	if (hrtick_enabled(rq) && cfs_rq->nr_running > 1) {
+		u64 slice = sched_slice(cfs_rq, se);
+		u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+		s64 delta = slice - ran;
+
+		if (delta < 0) {
+			if (rq->curr == p)
+				resched_task(p);
+			return;
+		}
+
+		/*
+		 * Don't schedule slices shorter than 10000ns, that just
+		 * doesn't make sense. Rely on vruntime for fairness.
+		 */
+		if (!requeue)
+			delta = max(10000LL, delta);
+
+		hrtick_start(rq, delta, requeue);
+	}
+}
+#else
+static inline void
+hrtick_start_fair(struct rq *rq, struct task_struct *p)
+{
+}
+#endif
+
 /*
  * The enqueue_task method is called before nr_running is
  * increased. Here we update the fair scheduling stats and
@@ -703,18 +818,16 @@ 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;
-	int set_curr = 0;
-
-	/* Are we enqueuing the current task? */
-	if (unlikely(task_running(rq, p)))
-		set_curr = 1;
 
 	for_each_sched_entity(se) {
 		if (se->on_rq)
 			break;
 		cfs_rq = cfs_rq_of(se);
-		enqueue_entity(cfs_rq, se, wakeup, set_curr);
+		enqueue_entity(cfs_rq, se, wakeup);
+		wakeup = 1;
 	}
+
+	hrtick_start_fair(rq, rq->curr);
 }
 
 /*
@@ -733,7 +846,10 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight)
 			break;
+		sleep = 1;
 	}
+
+	hrtick_start_fair(rq, rq->curr);
 }
 
 /*
@@ -743,10 +859,9 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
  */
 static void yield_task_fair(struct rq *rq)
 {
-	struct cfs_rq *cfs_rq = &rq->cfs;
-	struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
-	struct sched_entity *rightmost, *se = &rq->curr->se;
-	struct rb_node *parent;
+	struct task_struct *curr = rq->curr;
+	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+	struct sched_entity *rightmost, *se = &curr->se;
 
 	/*
 	 * Are we the only task in the tree?
@@ -754,46 +869,180 @@ static void yield_task_fair(struct rq *rq)
 	if (unlikely(cfs_rq->nr_running == 1))
 		return;
 
-	if (likely(!sysctl_sched_compat_yield)) {
+	if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
 		__update_rq_clock(rq);
 		/*
-		 * Dequeue and enqueue the task to update its
-		 * position within the tree:
+		 * Update run-time statistics of the 'current'.
 		 */
-		dequeue_entity(cfs_rq, se, 0);
-		enqueue_entity(cfs_rq, se, 0, 1);
+		update_curr(cfs_rq);
 
 		return;
 	}
 	/*
 	 * Find the rightmost entry in the rbtree:
 	 */
-	do {
-		parent = *link;
-		link = &parent->rb_right;
-	} while (*link);
-
-	rightmost = rb_entry(parent, struct sched_entity, run_node);
+	rightmost = __pick_last_entity(cfs_rq);
 	/*
 	 * Already in the rightmost position?
 	 */
-	if (unlikely(rightmost == se))
+	if (unlikely(rightmost->vruntime < se->vruntime))
 		return;
 
 	/*
 	 * Minimally necessary key value to be last in the tree:
+	 * Upon rescheduling, sched_class::put_prev_task() will place
+	 * 'current' within the tree based on its new key value.
 	 */
 	se->vruntime = rightmost->vruntime + 1;
+}
+
+/*
+ * wake_idle() will wake a task on an idle cpu if task->cpu is
+ * not idle and an idle cpu is available.  The span of cpus to
+ * search starts with cpus closest then further out as needed,
+ * so we always favor a closer, idle cpu.
+ *
+ * Returns the CPU we should wake onto.
+ */
+#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
+static int wake_idle(int cpu, struct task_struct *p)
+{
+	cpumask_t tmp;
+	struct sched_domain *sd;
+	int i;
 
-	if (cfs_rq->rb_leftmost == &se->run_node)
-		cfs_rq->rb_leftmost = rb_next(&se->run_node);
 	/*
-	 * Relink the task to the rightmost position:
+	 * If it is idle, then it is the best cpu to run this task.
+	 *
+	 * This cpu is also the best, if it has more than one task already.
+	 * Siblings must be also busy(in most cases) as they didn't already
+	 * pickup the extra load from this cpu and hence we need not check
+	 * sibling runqueue info. This will avoid the checks and cache miss
+	 * penalities associated with that.
 	 */
-	rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
-	rb_link_node(&se->run_node, parent, link);
-	rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
+	if (idle_cpu(cpu) || cpu_rq(cpu)->nr_running > 1)
+		return cpu;
+
+	for_each_domain(cpu, sd) {
+		if (sd->flags & SD_WAKE_IDLE) {
+			cpus_and(tmp, sd->span, p->cpus_allowed);
+			for_each_cpu_mask(i, tmp) {
+				if (idle_cpu(i)) {
+					if (i != task_cpu(p)) {
+						schedstat_inc(p,
+						       se.nr_wakeups_idle);
+					}
+					return i;
+				}
+			}
+		} else {
+			break;
+		}
+	}
+	return cpu;
+}
+#else
+static inline int wake_idle(int cpu, struct task_struct *p)
+{
+	return cpu;
 }
+#endif
+
+#ifdef CONFIG_SMP
+static int select_task_rq_fair(struct task_struct *p, int sync)
+{
+	int cpu, this_cpu;
+	struct rq *rq;
+	struct sched_domain *sd, *this_sd = NULL;
+	int new_cpu;
+
+	cpu      = task_cpu(p);
+	rq       = task_rq(p);
+	this_cpu = smp_processor_id();
+	new_cpu  = cpu;
+
+	if (cpu == this_cpu)
+		goto out_set_cpu;
+
+	for_each_domain(this_cpu, sd) {
+		if (cpu_isset(cpu, sd->span)) {
+			this_sd = sd;
+			break;
+		}
+	}
+
+	if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
+		goto out_set_cpu;
+
+	/*
+	 * Check for affine wakeup and passive balancing possibilities.
+	 */
+	if (this_sd) {
+		int idx = this_sd->wake_idx;
+		unsigned int imbalance;
+		unsigned long load, this_load;
+
+		imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
+
+		load = source_load(cpu, idx);
+		this_load = target_load(this_cpu, idx);
+
+		new_cpu = this_cpu; /* Wake to this CPU if we can */
+
+		if (this_sd->flags & SD_WAKE_AFFINE) {
+			unsigned long tl = this_load;
+			unsigned long tl_per_task;
+
+			/*
+			 * Attract cache-cold tasks on sync wakeups:
+			 */
+			if (sync && !task_hot(p, rq->clock, this_sd))
+				goto out_set_cpu;
+
+			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(cpu, idx) <= tl_per_task) ||
+			       100*(tl + p->se.load.weight) <= imbalance*load) {
+				/*
+				 * This domain has SD_WAKE_AFFINE and
+				 * p is cache cold in this domain, and
+				 * there is no bad imbalance.
+				 */
+				schedstat_inc(this_sd, ttwu_move_affine);
+				schedstat_inc(p, se.nr_wakeups_affine);
+				goto out_set_cpu;
+			}
+		}
+
+		/*
+		 * Start passive balancing when half the imbalance_pct
+		 * limit is reached.
+		 */
+		if (this_sd->flags & SD_WAKE_BALANCE) {
+			if (imbalance*this_load <= 100*load) {
+				schedstat_inc(this_sd, ttwu_move_balance);
+				schedstat_inc(p, se.nr_wakeups_passive);
+				goto out_set_cpu;
+			}
+		}
+	}
+
+	new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
+out_set_cpu:
+	return wake_idle(new_cpu, p);
+}
+#endif /* CONFIG_SMP */
+
 
 /*
  * Preempt the current task with a newly woken task if needed:
@@ -802,6 +1051,8 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
 {
 	struct task_struct *curr = rq->curr;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+	struct sched_entity *se = &curr->se, *pse = &p->se;
+	unsigned long gran;
 
 	if (unlikely(rt_prio(p->prio))) {
 		update_rq_clock(rq);
@@ -809,16 +1060,36 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
 		resched_task(curr);
 		return;
 	}
-	if (is_same_group(curr, p)) {
-		s64 delta = curr->se.vruntime - p->se.vruntime;
+	/*
+	 * Batch tasks do not preempt (their preemption is driven by
+	 * the tick):
+	 */
+	if (unlikely(p->policy == SCHED_BATCH))
+		return;
+
+	if (!sched_feat(WAKEUP_PREEMPT))
+		return;
 
-		if (delta > (s64)sysctl_sched_wakeup_granularity)
-			resched_task(curr);
+	while (!is_same_group(se, pse)) {
+		se = parent_entity(se);
+		pse = parent_entity(pse);
 	}
+
+	gran = sysctl_sched_wakeup_granularity;
+	/*
+	 * More easily preempt - nice tasks, while not making
+	 * it harder for + nice tasks.
+	 */
+	if (unlikely(se->load.weight > NICE_0_LOAD))
+		gran = calc_delta_fair(gran, &se->load);
+
+	if (pse->vruntime + gran < se->vruntime)
+		resched_task(curr);
 }
 
 static struct task_struct *pick_next_task_fair(struct rq *rq)
 {
+	struct task_struct *p;
 	struct cfs_rq *cfs_rq = &rq->cfs;
 	struct sched_entity *se;
 
@@ -830,7 +1101,10 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);
 
-	return task_of(se);
+	p = task_of(se);
+	hrtick_start_fair(rq, p);
+
+	return p;
 }
 
 /*
@@ -847,6 +1121,7 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
 	}
 }
 
+#ifdef CONFIG_SMP
 /**************************************************
  * Fair scheduling class load-balancing methods:
  */
@@ -858,7 +1133,7 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
  * achieve that by always pre-iterating before returning
  * the current task:
  */
-static inline struct task_struct *
+static struct task_struct *
 __load_balance_iterator(struct cfs_rq *cfs_rq, struct rb_node *curr)
 {
 	struct task_struct *p;
@@ -892,10 +1167,13 @@ static int cfs_rq_best_prio(struct cfs_rq *cfs_rq)
 	struct sched_entity *curr;
 	struct task_struct *p;
 
-	if (!cfs_rq->nr_running)
+	if (!cfs_rq->nr_running || !first_fair(cfs_rq))
 		return MAX_PRIO;
 
-	curr = __pick_next_entity(cfs_rq);
+	curr = cfs_rq->curr;
+	if (!curr)
+		curr = __pick_next_entity(cfs_rq);
+
 	p = task_of(curr);
 
 	return p->prio;
@@ -904,12 +1182,11 @@ static int cfs_rq_best_prio(struct cfs_rq *cfs_rq)
 
 static unsigned long
 load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		  unsigned long max_nr_move, unsigned long max_load_move,
+		  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;
-	unsigned long load_moved, total_nr_moved = 0, nr_moved;
 	long rem_load_move = max_load_move;
 	struct rq_iterator cfs_rq_iterator;
 
@@ -937,40 +1214,63 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 #else
 # define maxload rem_load_move
 #endif
-		/* pass busy_cfs_rq argument into
+		/*
+		 * pass busy_cfs_rq argument into
 		 * load_balance_[start|next]_fair iterators
 		 */
 		cfs_rq_iterator.arg = busy_cfs_rq;
-		nr_moved = balance_tasks(this_rq, this_cpu, busiest,
-				max_nr_move, maxload, sd, idle, all_pinned,
-				&load_moved, this_best_prio, &cfs_rq_iterator);
-
-		total_nr_moved += nr_moved;
-		max_nr_move -= nr_moved;
-		rem_load_move -= load_moved;
+		rem_load_move -= balance_tasks(this_rq, this_cpu, busiest,
+					       maxload, sd, idle, all_pinned,
+					       this_best_prio,
+					       &cfs_rq_iterator);
 
-		if (max_nr_move <= 0 || rem_load_move <= 0)
+		if (rem_load_move <= 0)
 			break;
 	}
 
 	return max_load_move - rem_load_move;
 }
 
+static int
+move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		   struct sched_domain *sd, enum cpu_idle_type idle)
+{
+	struct cfs_rq *busy_cfs_rq;
+	struct rq_iterator cfs_rq_iterator;
+
+	cfs_rq_iterator.start = load_balance_start_fair;
+	cfs_rq_iterator.next = load_balance_next_fair;
+
+	for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
+		/*
+		 * pass busy_cfs_rq argument into
+		 * load_balance_[start|next]_fair iterators
+		 */
+		cfs_rq_iterator.arg = busy_cfs_rq;
+		if (iter_move_one_task(this_rq, this_cpu, busiest, sd, idle,
+				       &cfs_rq_iterator))
+		    return 1;
+	}
+
+	return 0;
+}
+#endif
+
 /*
  * scheduler tick hitting a task of our scheduling class:
  */
-static void task_tick_fair(struct rq *rq, struct task_struct *curr)
+static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &curr->se;
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		entity_tick(cfs_rq, se);
+		entity_tick(cfs_rq, se, queued);
 	}
 }
 
-#define swap(a,b) do { typeof(a) tmp = (a); (a) = (b); (b) = tmp; } while (0)
+#define swap(a, b) do { typeof(a) tmp = (a); (a) = (b); (b) = tmp; } while (0)
 
 /*
  * Share the fairness runtime between parent and child, thus the
@@ -983,44 +1283,118 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
 {
 	struct cfs_rq *cfs_rq = task_cfs_rq(p);
 	struct sched_entity *se = &p->se, *curr = cfs_rq->curr;
+	int this_cpu = smp_processor_id();
 
 	sched_info_queued(p);
 
 	update_curr(cfs_rq);
 	place_entity(cfs_rq, se, 1);
 
-	if (sysctl_sched_child_runs_first &&
-			curr->vruntime < se->vruntime) {
+	/* 'curr' will be NULL if the child belongs to a different group */
+	if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) &&
+			curr && curr->vruntime < se->vruntime) {
 		/*
- 		 * Upon rescheduling, sched_class::put_prev_task() will place
- 		 * 'current' within the tree based on its new key value.
- 		 */
+		 * Upon rescheduling, sched_class::put_prev_task() will place
+		 * 'current' within the tree based on its new key value.
+		 */
 		swap(curr->vruntime, se->vruntime);
 	}
 
-	update_stats_enqueue(cfs_rq, se);
-	__enqueue_entity(cfs_rq, se);
-	account_entity_enqueue(cfs_rq, se);
+	enqueue_task_fair(rq, p, 0);
 	resched_task(rq->curr);
 }
 
 /*
+ * Priority of the task has changed. Check to see if we preempt
+ * the current task.
+ */
+static void prio_changed_fair(struct rq *rq, struct task_struct *p,
+			      int oldprio, int running)
+{
+	/*
+	 * Reschedule if we are currently running on this runqueue and
+	 * our priority decreased, or if we are not currently running on
+	 * this runqueue and our priority is higher than the current's
+	 */
+	if (running) {
+		if (p->prio > oldprio)
+			resched_task(rq->curr);
+	} else
+		check_preempt_curr(rq, p);
+}
+
+/*
+ * We switched to the sched_fair class.
+ */
+static void switched_to_fair(struct rq *rq, struct task_struct *p,
+			     int running)
+{
+	/*
+	 * We were most likely switched from sched_rt, so
+	 * kick off the schedule if running, otherwise just see
+	 * if we can still preempt the current task.
+	 */
+	if (running)
+		resched_task(rq->curr);
+	else
+		check_preempt_curr(rq, p);
+}
+
+/* Account for a task changing its policy or group.
+ *
+ * This routine is mostly called to set cfs_rq->curr field when a task
+ * migrates between groups/classes.
+ */
+static void set_curr_task_fair(struct rq *rq)
+{
+	struct sched_entity *se = &rq->curr->se;
+
+	for_each_sched_entity(se)
+		set_next_entity(cfs_rq_of(se), se);
+}
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static void moved_group_fair(struct task_struct *p)
+{
+	struct cfs_rq *cfs_rq = task_cfs_rq(p);
+
+	update_curr(cfs_rq);
+	place_entity(cfs_rq, &p->se, 1);
+}
+#endif
+
+/*
  * All the scheduling class methods:
  */
-struct sched_class fair_sched_class __read_mostly = {
+static const struct sched_class fair_sched_class = {
+	.next			= &idle_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,
 
 	.pick_next_task		= pick_next_task_fair,
 	.put_prev_task		= put_prev_task_fair,
 
+#ifdef CONFIG_SMP
 	.load_balance		= load_balance_fair,
+	.move_one_task		= move_one_task_fair,
+#endif
 
+	.set_curr_task          = set_curr_task_fair,
 	.task_tick		= task_tick_fair,
 	.task_new		= task_new_fair,
+
+	.prio_changed		= prio_changed_fair,
+	.switched_to		= switched_to_fair,
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	.moved_group		= moved_group_fair,
+#endif
 };
 
 #ifdef CONFIG_SCHED_DEBUG
@@ -1028,7 +1402,12 @@ static void print_cfs_stats(struct seq_file *m, int cpu)
 {
 	struct cfs_rq *cfs_rq;
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	print_cfs_rq(m, cpu, &cpu_rq(cpu)->cfs);
+#endif
+	rcu_read_lock();
 	for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
 		print_cfs_rq(m, cpu, cfs_rq);
+	rcu_read_unlock();
 }
 #endif