/*
   * Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH)
   *
   *  Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
   *
   *  Interactivity improvements by Mike Galbraith
   *  (C) 2007 Mike Galbraith <efault@gmx.de>
   *
   *  Various enhancements by Dmitry Adamushko.
   *  (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com>
   *
   *  Group scheduling enhancements by Srivatsa Vaddagiri
   *  Copyright IBM Corporation, 2007
   *  Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
   *
   *  Scaled math optimizations by Thomas Gleixner
   *  Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>

   *
   *  Adaptive scheduling granularity, math enhancements by Peter Zijlstra
   *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>

   */

  #include <linux/latencytop.h>

  #include <linux/sched.h>

  /*

   * Targeted preemption latency for CPU-bound tasks:

   * (default: 5ms * (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
   * and have no persistent notion like in traditional, time-slice
   * based scheduling concepts.

   *

   * (to see the precise effective timeslice length of your workload,
   *  run vmstat and monitor the context-switches (cs) field)

   */

  unsigned int sysctl_sched_latency = 6000000ULL;
  unsigned int normalized_sysctl_sched_latency = 6000000ULL;

  
  /*

   * The initial- and re-scaling of tunables is configurable
   * (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus))
   *
   * Options are:
   * SCHED_TUNABLESCALING_NONE - unscaled, always *1
   * SCHED_TUNABLESCALING_LOG - scaled logarithmical, *1+ilog(ncpus)
   * SCHED_TUNABLESCALING_LINEAR - scaled linear, *ncpus
   */
  enum sched_tunable_scaling sysctl_sched_tunable_scaling
  	= SCHED_TUNABLESCALING_LOG;
  
  /*

   * Minimal preemption granularity for CPU-bound tasks:

   * (default: 2 msec * (1 + ilog(ncpus)), units: nanoseconds)

   */

  unsigned int sysctl_sched_min_granularity = 750000ULL;
  unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;

  
  /*

   * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
   */

  static unsigned int sched_nr_latency = 8;

  
  /*

   * After fork, child runs first. If set to 0 (default) then

   * parent will (try to) run first.

   */

  unsigned int sysctl_sched_child_runs_first __read_mostly;

  
  /*

   * sys_sched_yield() compat mode
   *
   * This option switches the agressive yield implementation of the
   * old scheduler back on.
   */
  unsigned int __read_mostly sysctl_sched_compat_yield;
  
  /*

   * SCHED_OTHER wake-up granularity.

   * (default: 1 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.
   */

  unsigned int sysctl_sched_wakeup_granularity = 1000000UL;

  unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL;

  const_debug unsigned int sysctl_sched_migration_cost = 500000UL;

  static const struct sched_class fair_sched_class;

  /**************************************************************
   * CFS operations on generic schedulable entities:
   */

  #ifdef CONFIG_FAIR_GROUP_SCHED

  /* cpu runqueue to which this cfs_rq is attached */

  static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
  {

  	return cfs_rq->rq;

  }

  /* An entity is a task if it doesn't "own" a runqueue */
  #define entity_is_task(se)	(!se->my_q)

  static inline struct task_struct *task_of(struct sched_entity *se)
  {
  #ifdef CONFIG_SCHED_DEBUG
  	WARN_ON_ONCE(!entity_is_task(se));
  #endif
  	return container_of(se, struct task_struct, se);
  }

  /* Walk up scheduling entities hierarchy */
  #define for_each_sched_entity(se) \
  		for (; se; se = se->parent)
  
  static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
  {
  	return p->se.cfs_rq;
  }
  
  /* runqueue on which this entity is (to be) queued */
  static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
  {
  	return se->cfs_rq;
  }
  
  /* runqueue "owned" by this group */
  static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
  {
  	return grp->my_q;
  }
  
  /* Given a group's cfs_rq on one cpu, return its corresponding cfs_rq on
   * another cpu ('this_cpu')
   */
  static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
  {
  	return cfs_rq->tg->cfs_rq[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_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
  
  /* 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 (se->cfs_rq == pse->cfs_rq)
  		return 1;
  
  	return 0;
  }
  
  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 task_struct *task_of(struct sched_entity *se)
  {
  	return container_of(se, struct task_struct, se);
  }

  static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
  {
  	return container_of(cfs_rq, struct rq, cfs);

  }
  
  #define entity_is_task(se)	1

  #define for_each_sched_entity(se) \
  		for (; se; se = NULL)

  static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)

  {

  	return &task_rq(p)->cfs;

  }

  static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
  {
  	struct task_struct *p = task_of(se);
  	struct rq *rq = task_rq(p);
  
  	return &rq->cfs;
  }
  
  /* runqueue "owned" by this group */
  static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
  {
  	return NULL;
  }
  
  static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
  {
  	return &cpu_rq(this_cpu)->cfs;
  }
  
  #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 sched_entity *se, struct sched_entity *pse)
  {
  	return 1;
  }
  
  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 */

  
  /**************************************************************
   * Scheduling class tree data structure manipulation methods:
   */

  static inline u64 max_vruntime(u64 min_vruntime, u64 vruntime)

  {

  	s64 delta = (s64)(vruntime - min_vruntime);
  	if (delta > 0)

  		min_vruntime = vruntime;
  
  	return min_vruntime;
  }

  static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)

  {
  	s64 delta = (s64)(vruntime - min_vruntime);
  	if (delta < 0)
  		min_vruntime = vruntime;
  
  	return min_vruntime;
  }

  static inline int entity_before(struct sched_entity *a,
  				struct sched_entity *b)
  {
  	return (s64)(a->vruntime - b->vruntime) < 0;
  }

  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 (!cfs_rq->curr)

  			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:
   */

  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;
  	struct sched_entity *entry;

  	s64 key = entity_key(cfs_rq, se);

  	int leftmost = 1;
  
  	/*
  	 * Find the right place in the rbtree:
  	 */
  	while (*link) {
  		parent = *link;
  		entry = rb_entry(parent, struct sched_entity, run_node);
  		/*
  		 * We dont care about collisions. Nodes with
  		 * the same key stay together.
  		 */

  		if (key < entity_key(cfs_rq, entry)) {

  			link = &parent->rb_left;
  		} else {
  			link = &parent->rb_right;
  			leftmost = 0;
  		}
  	}
  
  	/*
  	 * Maintain a cache of leftmost tree entries (it is frequently
  	 * used):
  	 */

  	if (leftmost)

  		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)

  {

  	if (cfs_rq->rb_leftmost == &se->run_node) {
  		struct rb_node *next_node;

  
  		next_node = rb_next(&se->run_node);
  		cfs_rq->rb_leftmost = next_node;

  	}

  	rb_erase(&se->run_node, &cfs_rq->tasks_timeline);

  }

  static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
  {

  	struct rb_node *left = cfs_rq->rb_leftmost;
  
  	if (!left)
  		return NULL;
  
  	return rb_entry(left, struct sched_entity, run_node);

  }

  static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)

  {

  	struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);

  	if (!last)
  		return NULL;

  
  	return rb_entry(last, struct sched_entity, run_node);

  }

  /**************************************************************
   * Scheduling class statistics methods:
   */

  #ifdef CONFIG_SCHED_DEBUG

  int sched_proc_update_handler(struct ctl_table *table, int write,

  		void __user *buffer, size_t *lenp,

  		loff_t *ppos)
  {

  	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);

  	int factor = get_update_sysctl_factor();

  
  	if (ret || !write)
  		return ret;
  
  	sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency,
  					sysctl_sched_min_granularity);

  #define WRT_SYSCTL(name) \
  	(normalized_sysctl_##name = sysctl_##name / (factor))
  	WRT_SYSCTL(sched_min_granularity);
  	WRT_SYSCTL(sched_latency);
  	WRT_SYSCTL(sched_wakeup_granularity);
  	WRT_SYSCTL(sched_shares_ratelimit);
  #undef WRT_SYSCTL

  	return 0;
  }
  #endif

  
  /*

   * delta /= w

   */
  static inline unsigned long
  calc_delta_fair(unsigned long delta, struct sched_entity *se)
  {

  	if (unlikely(se->load.weight != NICE_0_LOAD))
  		delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load);

  
  	return delta;
  }
  
  /*

   * 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 = sched_nr_latency;

  
  	if (unlikely(nr_running > nr_latency)) {

  		period = sysctl_sched_min_granularity;

  		period *= nr_running;

  	}
  
  	return period;
  }

  /*
   * We calculate the wall-time slice from the period by taking a part
   * proportional to the weight.
   *

   * s = p*P[w/rw]

   */

  static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)

  {

  	u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq);

  	for_each_sched_entity(se) {

  		struct load_weight *load;

  		struct load_weight lw;

  
  		cfs_rq = cfs_rq_of(se);
  		load = &cfs_rq->load;

  		if (unlikely(!se->on_rq)) {

  			lw = cfs_rq->load;

  
  			update_load_add(&lw, se->load.weight);
  			load = &lw;
  		}
  		slice = calc_delta_mine(slice, se->load.weight, load);
  	}
  	return slice;

  }

  /*

   * We calculate the vruntime slice of a to be inserted task

   *

   * vs = s/w

   */

  static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)

  {

  	return calc_delta_fair(sched_slice(cfs_rq, se), se);

  }
  
  /*

   * Update the current task's runtime statistics. Skip current tasks that
   * are not in our scheduling class.
   */
  static inline void

  __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
  	      unsigned long delta_exec)

  {

  	unsigned long delta_exec_weighted;

  	schedstat_set(curr->statistics.exec_max,
  		      max((u64)delta_exec, curr->statistics.exec_max));

  
  	curr->sum_exec_runtime += delta_exec;

  	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)

  {

  	struct sched_entity *curr = cfs_rq->curr;

  	u64 now = rq_of(cfs_rq)->clock;

  	unsigned long delta_exec;
  
  	if (unlikely(!curr))
  		return;
  
  	/*
  	 * Get the amount of time the current task was running
  	 * since the last time we changed load (this cannot
  	 * overflow on 32 bits):
  	 */

  	delta_exec = (unsigned long)(now - curr->exec_start);

  	if (!delta_exec)
  		return;

  	__update_curr(cfs_rq, curr, delta_exec);
  	curr->exec_start = now;

  
  	if (entity_is_task(curr)) {
  		struct task_struct *curtask = task_of(curr);

  		trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime);

  		cpuacct_charge(curtask, delta_exec);

  		account_group_exec_runtime(curtask, delta_exec);

  	}

  }
  
  static inline void

  update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)

  {

  	schedstat_set(se->statistics.wait_start, rq_of(cfs_rq)->clock);

  }

  /*
   * Task is being enqueued - update stats:
   */

  static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)

  {

  	/*
  	 * Are we enqueueing a waiting task? (for current tasks
  	 * a dequeue/enqueue event is a NOP)
  	 */

  	if (se != cfs_rq->curr)

  		update_stats_wait_start(cfs_rq, se);

  }

  static void

  update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)

  {

  	schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max,
  			rq_of(cfs_rq)->clock - se->statistics.wait_start));
  	schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1);
  	schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum +
  			rq_of(cfs_rq)->clock - se->statistics.wait_start);

  #ifdef CONFIG_SCHEDSTATS
  	if (entity_is_task(se)) {
  		trace_sched_stat_wait(task_of(se),

  			rq_of(cfs_rq)->clock - se->statistics.wait_start);

  	}
  #endif

  	schedstat_set(se->statistics.wait_start, 0);

  }
  
  static inline void

  update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)

  {

  	/*
  	 * Mark the end of the wait period if dequeueing a
  	 * waiting task:
  	 */

  	if (se != cfs_rq->curr)

  		update_stats_wait_end(cfs_rq, se);

  }
  
  /*
   * We are picking a new current task - update its stats:
   */
  static inline void

  update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)

  {
  	/*
  	 * We are starting a new run period:
  	 */

  	se->exec_start = rq_of(cfs_rq)->clock;

  }

  /**************************************************
   * 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);

  		list_add(&se->group_node, &cfs_rq->tasks);
  	}

  	cfs_rq->nr_running++;
  	se->on_rq = 1;
  }
  
  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);

  		list_del_init(&se->group_node);
  	}

  	cfs_rq->nr_running--;
  	se->on_rq = 0;
  }

  static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)

  {

  #ifdef CONFIG_SCHEDSTATS

  	struct task_struct *tsk = NULL;
  
  	if (entity_is_task(se))
  		tsk = task_of(se);

  	if (se->statistics.sleep_start) {
  		u64 delta = rq_of(cfs_rq)->clock - se->statistics.sleep_start;

  
  		if ((s64)delta < 0)
  			delta = 0;

  		if (unlikely(delta > se->statistics.sleep_max))
  			se->statistics.sleep_max = delta;

  		se->statistics.sleep_start = 0;
  		se->statistics.sum_sleep_runtime += delta;

  		if (tsk) {

  			account_scheduler_latency(tsk, delta >> 10, 1);

  			trace_sched_stat_sleep(tsk, delta);
  		}

  	}

  	if (se->statistics.block_start) {
  		u64 delta = rq_of(cfs_rq)->clock - se->statistics.block_start;

  
  		if ((s64)delta < 0)
  			delta = 0;

  		if (unlikely(delta > se->statistics.block_max))
  			se->statistics.block_max = delta;

  		se->statistics.block_start = 0;
  		se->statistics.sum_sleep_runtime += delta;

  		if (tsk) {

  			if (tsk->in_iowait) {

  				se->statistics.iowait_sum += delta;
  				se->statistics.iowait_count++;

  				trace_sched_stat_iowait(tsk, delta);

  			}

  			/*
  			 * Blocking time is in units of nanosecs, so shift by
  			 * 20 to get a milliseconds-range estimation of the
  			 * amount of time that the task spent sleeping:
  			 */
  			if (unlikely(prof_on == SLEEP_PROFILING)) {
  				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 vruntime = cfs_rq->min_vruntime;

  	/*
  	 * 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))

  		vruntime += sched_vslice(cfs_rq, se);

  	/* sleeps up to a single latency don't count. */

  	if (!initial) {

  		unsigned long thresh = sysctl_sched_latency;

  		/*

  		 * Halve their sleep time's effect, to allow
  		 * for a gentler effect of sleepers:
  		 */
  		if (sched_feat(GENTLE_FAIR_SLEEPERS))
  			thresh >>= 1;

  		vruntime -= thresh;

  	}

  	/* ensure we never gain time by being placed backwards. */
  	vruntime = max_vruntime(se->vruntime, vruntime);

  	se->vruntime = vruntime;

  }
  
  static void

  enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)

  {
  	/*

  	 * Update the normalized vruntime before updating min_vruntime
  	 * through callig update_curr().
  	 */

  	if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING))

  		se->vruntime += cfs_rq->min_vruntime;
  
  	/*

  	 * Update run-time statistics of the 'current'.

  	 */

  	update_curr(cfs_rq);

  	account_entity_enqueue(cfs_rq, se);

  	if (flags & ENQUEUE_WAKEUP) {

  		place_entity(cfs_rq, se, 0);

  		enqueue_sleeper(cfs_rq, se);

  	}

  	update_stats_enqueue(cfs_rq, se);

  	check_spread(cfs_rq, se);

  	if (se != cfs_rq->curr)
  		__enqueue_entity(cfs_rq, se);

  }

  static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)

  {

  	if (!se || cfs_rq->last == se)

  		cfs_rq->last = NULL;

  	if (!se || cfs_rq->next == se)

  		cfs_rq->next = NULL;
  }

  static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
  {
  	for_each_sched_entity(se)
  		__clear_buddies(cfs_rq_of(se), se);
  }

  static void

  dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)

  {

  	/*
  	 * Update run-time statistics of the 'current'.
  	 */
  	update_curr(cfs_rq);

  	update_stats_dequeue(cfs_rq, se);

  	if (flags & DEQUEUE_SLEEP) {

  #ifdef CONFIG_SCHEDSTATS

  		if (entity_is_task(se)) {
  			struct task_struct *tsk = task_of(se);
  
  			if (tsk->state & TASK_INTERRUPTIBLE)

  				se->statistics.sleep_start = rq_of(cfs_rq)->clock;

  			if (tsk->state & TASK_UNINTERRUPTIBLE)

  				se->statistics.block_start = rq_of(cfs_rq)->clock;

  		}

  #endif

  	}

  	clear_buddies(cfs_rq, se);

  	if (se != cfs_rq->curr)

  		__dequeue_entity(cfs_rq, se);
  	account_entity_dequeue(cfs_rq, se);

  	update_min_vruntime(cfs_rq);

  
  	/*
  	 * Normalize the entity after updating the min_vruntime because the
  	 * update can refer to the ->curr item and we need to reflect this
  	 * movement in our normalized position.
  	 */

  	if (!(flags & DEQUEUE_SLEEP))

  		se->vruntime -= cfs_rq->min_vruntime;

  }
  
  /*
   * Preempt the current task with a newly woken task if needed:
   */

  static void

  check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)

  {

  	unsigned long ideal_runtime, delta_exec;

  	ideal_runtime = sched_slice(cfs_rq, curr);

  	delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;

  	if (delta_exec > ideal_runtime) {

  		resched_task(rq_of(cfs_rq)->curr);

  		/*
  		 * The current task ran long enough, ensure it doesn't get
  		 * re-elected due to buddy favours.
  		 */
  		clear_buddies(cfs_rq, curr);

  		return;
  	}
  
  	/*
  	 * Ensure that a task that missed wakeup preemption by a
  	 * narrow margin doesn't have to wait for a full slice.
  	 * This also mitigates buddy induced latencies under load.
  	 */
  	if (!sched_feat(WAKEUP_PREEMPT))
  		return;
  
  	if (delta_exec < sysctl_sched_min_granularity)
  		return;
  
  	if (cfs_rq->nr_running > 1) {
  		struct sched_entity *se = __pick_next_entity(cfs_rq);
  		s64 delta = curr->vruntime - se->vruntime;
  
  		if (delta > ideal_runtime)
  			resched_task(rq_of(cfs_rq)->curr);

  	}

  }

  static void

  set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *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
  	/*
  	 * Track our maximum slice length, if the CPU's load is at
  	 * least twice that of our own weight (i.e. dont track it
  	 * when there are only lesser-weight tasks around):
  	 */

  	if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {

  		se->statistics.slice_max = max(se->statistics.slice_max,

  			se->sum_exec_runtime - se->prev_sum_exec_runtime);
  	}
  #endif

  	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_entity(struct cfs_rq *cfs_rq)

  {

  	struct sched_entity *se = __pick_next_entity(cfs_rq);

  	struct sched_entity *left = se;

  	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
  		se = cfs_rq->next;

  	/*
  	 * Prefer last buddy, try to return the CPU to a preempted task.
  	 */
  	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
  		se = cfs_rq->last;
  
  	clear_buddies(cfs_rq, se);

  
  	return se;

  }

  static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)

  {
  	/*
  	 * If still on the runqueue then deactivate_task()
  	 * was not called and update_curr() has to be done:
  	 */
  	if (prev->on_rq)

  		update_curr(cfs_rq);

  	check_spread(cfs_rq, prev);

  	if (prev->on_rq) {

  		update_stats_wait_start(cfs_rq, prev);

  		/* Put 'current' back into the tree. */
  		__enqueue_entity(cfs_rq, prev);
  	}

  	cfs_rq->curr = NULL;

  }

  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);

  #ifdef CONFIG_SCHED_HRTICK
  	/*
  	 * queued ticks are scheduled to match the slice, so don't bother
  	 * validating it and just reschedule.
  	 */

  	if (queued) {
  		resched_task(rq_of(cfs_rq)->curr);
  		return;
  	}

  	/*
  	 * 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);

  }
  
  /**************************************************
   * CFS operations on tasks:
   */

  #ifdef CONFIG_SCHED_HRTICK
  static void hrtick_start_fair(struct rq *rq, struct task_struct *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 (rq->curr != p)

  			delta = max_t(s64, 10000LL, delta);

  		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

  /*
   * The enqueue_task method is called before nr_running is
   * increased. Here we update the fair scheduling stats and
   * then put the task into the rbtree:
   */

  static void

  enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)

  {
  	struct cfs_rq *cfs_rq;

  	struct sched_entity *se = &p->se;

  
  	for_each_sched_entity(se) {

  		if (se->on_rq)

  			break;
  		cfs_rq = cfs_rq_of(se);

  		enqueue_entity(cfs_rq, se, flags);
  		flags = ENQUEUE_WAKEUP;

  	}

  	hrtick_update(rq);

  }
  
  /*
   * The dequeue_task method is called before nr_running is
   * decreased. We remove the task from the rbtree and
   * update the fair scheduling stats:
   */

  static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)

  {
  	struct cfs_rq *cfs_rq;

  	struct sched_entity *se = &p->se;

  
  	for_each_sched_entity(se) {
  		cfs_rq = cfs_rq_of(se);

  		dequeue_entity(cfs_rq, se, flags);

  		/* Don't dequeue parent if it has other entities besides us */

  		if (cfs_rq->load.weight)

  			break;

  		flags |= DEQUEUE_SLEEP;

  	}

  	hrtick_update(rq);

  }
  
  /*

   * sched_yield() support is very simple - we dequeue and enqueue.
   *
   * If compat_yield is turned on then we requeue to the end of the tree.

   */

  static void yield_task_fair(struct rq *rq)

  {

  	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?
  	 */
  	if (unlikely(cfs_rq->nr_running == 1))
  		return;

  	clear_buddies(cfs_rq, se);

  	if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {

  		update_rq_clock(rq);

  		/*

  		 * Update run-time statistics of the 'current'.

  		 */

  		update_curr(cfs_rq);

  
  		return;
  	}
  	/*
  	 * Find the rightmost entry in the rbtree:

  	 */

  	rightmost = __pick_last_entity(cfs_rq);

  	/*
  	 * Already in the rightmost position?
  	 */

  	if (unlikely(!rightmost || entity_before(rightmost, se)))

  		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;

  }

  #ifdef CONFIG_SMP

  static void task_waking_fair(struct rq *rq, struct task_struct *p)
  {
  	struct sched_entity *se = &p->se;
  	struct cfs_rq *cfs_rq = cfs_rq_of(se);
  
  	se->vruntime -= cfs_rq->min_vruntime;
  }

  #ifdef CONFIG_FAIR_GROUP_SCHED

  /*
   * effective_load() calculates the load change as seen from the root_task_group
   *
   * Adding load to a group doesn't make a group heavier, but can cause movement
   * of group shares between cpus. Assuming the shares were perfectly aligned one
   * can calculate the shift in shares.
   *
   * The problem is that perfectly aligning the shares is rather expensive, hence
   * we try to avoid doing that too often - see update_shares(), which ratelimits
   * this change.
   *
   * We compensate this by not only taking the current delta into account, but
   * also considering the delta between when the shares were last adjusted and
   * now.
   *
   * We still saw a performance dip, some tracing learned us that between
   * cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased
   * significantly. Therefore try to bias the error in direction of failing
   * the affine wakeup.
   *
   */

  static long effective_load(struct task_group *tg, int cpu,
  		long wl, long wg)

  {

  	struct sched_entity *se = tg->se[cpu];

  
  	if (!tg->parent)
  		return wl;
  
  	/*

  	 * By not taking the decrease of shares on the other cpu into
  	 * account our error leans towards reducing the affine wakeups.
  	 */
  	if (!wl && sched_feat(ASYM_EFF_LOAD))
  		return wl;

  	for_each_sched_entity(se) {

  		long S, rw, s, a, b;

  		long more_w;
  
  		/*
  		 * Instead of using this increment, also add the difference
  		 * between when the shares were last updated and now.
  		 */
  		more_w = se->my_q->load.weight - se->my_q->rq_weight;
  		wl += more_w;
  		wg += more_w;

  
  		S = se->my_q->tg->shares;
  		s = se->my_q->shares;

  		rw = se->my_q->rq_weight;

  		a = S*(rw + wl);
  		b = S*rw + s*wg;

  		wl = s*(a-b);
  
  		if (likely(b))
  			wl /= b;

  		/*
  		 * Assume the group is already running and will
  		 * thus already be accounted for in the weight.
  		 *
  		 * That is, moving shares between CPUs, does not
  		 * alter the group weight.
  		 */

  		wg = 0;

  	}

  	return wl;

  }

  #else

  static inline unsigned long effective_load(struct task_group *tg, int cpu,
  		unsigned long wl, unsigned long wg)

  {

  	return wl;

  }

  #endif

  static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)

  {

  	unsigned long this_load, load;
  	int idx, this_cpu, prev_cpu;

  	unsigned long tl_per_task;

  	struct task_group *tg;

  	unsigned long weight;

  	int balanced;

  	idx	  = sd->wake_idx;
  	this_cpu  = smp_processor_id();
  	prev_cpu  = task_cpu(p);
  	load	  = source_load(prev_cpu, idx);
  	this_load = target_load(this_cpu, idx);

  
  	/*

  	 * If sync wakeup then subtract the (maximum possible)
  	 * effect of the currently running task from the load
  	 * of the current CPU:
  	 */

  	rcu_read_lock();

  	if (sync) {
  		tg = task_group(current);
  		weight = current->se.load.weight;

  		this_load += effective_load(tg, this_cpu, -weight, -weight);

  		load += effective_load(tg, prev_cpu, 0, -weight);
  	}

  	tg = task_group(p);
  	weight = p->se.load.weight;

  	/*
  	 * In low-load situations, where prev_cpu is idle and this_cpu is idle

  	 * due to the sync cause above having dropped this_load to 0, we'll
  	 * always have an imbalance, but there's really nothing you can do
  	 * about that, so that's good too.

  	 *
  	 * Otherwise check if either cpus are near enough in load to allow this
  	 * task to be woken on this_cpu.
  	 */

  	if (this_load) {
  		unsigned long this_eff_load, prev_eff_load;
  
  		this_eff_load = 100;
  		this_eff_load *= power_of(prev_cpu);
  		this_eff_load *= this_load +
  			effective_load(tg, this_cpu, weight, weight);
  
  		prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
  		prev_eff_load *= power_of(this_cpu);
  		prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight);
  
  		balanced = this_eff_load <= prev_eff_load;
  	} else
  		balanced = true;

  	rcu_read_unlock();

  
  	/*

  	 * If the currently running task will sleep within
  	 * a reasonable amount of time then attract this newly
  	 * woken task:

  	 */

  	if (sync && balanced)
  		return 1;

  	schedstat_inc(p, se.statistics.nr_wakeups_affine_attempts);

  	tl_per_task = cpu_avg_load_per_task(this_cpu);

  	if (balanced ||
  	    (this_load <= load &&
  	     this_load + target_load(prev_cpu, idx) <= tl_per_task)) {

  		/*
  		 * This domain has SD_WAKE_AFFINE and
  		 * p is cache cold in this domain, and
  		 * there is no bad imbalance.
  		 */

  		schedstat_inc(sd, ttwu_move_affine);

  		schedstat_inc(p, se.statistics.nr_wakeups_affine);

  
  		return 1;
  	}
  	return 0;
  }

  /*
   * find_idlest_group finds and returns the least busy CPU group within the
   * domain.
   */
  static struct sched_group *

  find_idlest_group(struct sched_domain *sd, struct task_struct *p,

  		  int this_cpu, int load_idx)

  {

  	struct sched_group *idlest = NULL, *group = sd->groups;

  	unsigned long min_load = ULONG_MAX, this_load = 0;

  	int imbalance = 100 + (sd->imbalance_pct-100)/2;

  	do {
  		unsigned long load, avg_load;
  		int local_group;
  		int i;

  		/* Skip over this group if it has no CPUs allowed */
  		if (!cpumask_intersects(sched_group_cpus(group),
  					&p->cpus_allowed))
  			continue;
  
  		local_group = cpumask_test_cpu(this_cpu,
  					       sched_group_cpus(group));
  
  		/* Tally up the load of all CPUs in the group */
  		avg_load = 0;
  
  		for_each_cpu(i, sched_group_cpus(group)) {
  			/* Bias balancing toward cpus of our domain */
  			if (local_group)
  				load = source_load(i, load_idx);
  			else
  				load = target_load(i, load_idx);
  
  			avg_load += load;
  		}
  
  		/* Adjust by relative CPU power of the group */
  		avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
  
  		if (local_group) {
  			this_load = avg_load;

  		} else if (avg_load < min_load) {
  			min_load = avg_load;
  			idlest = group;
  		}
  	} while (group = group->next, group != sd->groups);
  
  	if (!idlest || 100*this_load < imbalance*min_load)
  		return NULL;
  	return idlest;
  }
  
  /*
   * find_idlest_cpu - find the idlest cpu among the cpus in group.
   */
  static int
  find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
  {
  	unsigned long load, min_load = ULONG_MAX;
  	int idlest = -1;
  	int i;
  
  	/* Traverse only the allowed CPUs */
  	for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) {
  		load = weighted_cpuload(i);
  
  		if (load < min_load || (load == min_load && i == this_cpu)) {
  			min_load = load;
  			idlest = i;

  		}
  	}

  	return idlest;
  }

  /*

   * Try and locate an idle CPU in the sched_domain.
   */

  static int select_idle_sibling(struct task_struct *p, int target)

  {
  	int cpu = smp_processor_id();
  	int prev_cpu = task_cpu(p);

  	struct sched_domain *sd;

  	int i;
  
  	/*

  	 * If the task is going to be woken-up on this cpu and if it is
  	 * already idle, then it is the right target.

  	 */

  	if (target == cpu && idle_cpu(cpu))
  		return cpu;
  
  	/*
  	 * If the task is going to be woken-up on the cpu where it previously
  	 * ran and if it is currently idle, then it the right target.
  	 */
  	if (target == prev_cpu && idle_cpu(prev_cpu))

  		return prev_cpu;

  
  	/*

  	 * Otherwise, iterate the domains and find an elegible idle cpu.

  	 */

  	for_each_domain(target, sd) {
  		if (!(sd->flags & SD_SHARE_PKG_RESOURCES))

  			break;

  
  		for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
  			if (idle_cpu(i)) {
  				target = i;
  				break;
  			}

  		}

  
  		/*
  		 * Lets stop looking for an idle sibling when we reached
  		 * the domain that spans the current cpu and prev_cpu.
  		 */
  		if (cpumask_test_cpu(cpu, sched_domain_span(sd)) &&
  		    cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
  			break;

  	}
  
  	return target;
  }
  
  /*

   * sched_balance_self: balance the current task (running on cpu) in domains
   * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
   * SD_BALANCE_EXEC.
   *
   * Balance, ie. select the least loaded group.
   *
   * Returns the target CPU number, or the same CPU if no balancing is needed.
   *
   * preempt must be disabled.
   */

  static int
  select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags)

  {

  	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;

  	int cpu = smp_processor_id();
  	int prev_cpu = task_cpu(p);
  	int new_cpu = cpu;

  	int want_affine = 0;

  	int want_sd = 1;

  	int sync = wake_flags & WF_SYNC;

  	if (sd_flag & SD_BALANCE_WAKE) {

  		if (cpumask_test_cpu(cpu, &p->cpus_allowed))

  			want_affine = 1;
  		new_cpu = prev_cpu;
  	}

  
  	for_each_domain(cpu, tmp) {

  		if (!(tmp->flags & SD_LOAD_BALANCE))
  			continue;

  		/*

  		 * If power savings logic is enabled for a domain, see if we
  		 * are not overloaded, if so, don't balance wider.

  		 */

  		if (tmp->flags & (SD_POWERSAVINGS_BALANCE|SD_PREFER_LOCAL)) {

  			unsigned long power = 0;
  			unsigned long nr_running = 0;
  			unsigned long capacity;
  			int i;
  
  			for_each_cpu(i, sched_domain_span(tmp)) {
  				power += power_of(i);
  				nr_running += cpu_rq(i)->cfs.nr_running;
  			}
  
  			capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);

  			if (tmp->flags & SD_POWERSAVINGS_BALANCE)
  				nr_running /= 2;
  
  			if (nr_running < capacity)

  				want_sd = 0;

  		}

  		/*

  		 * If both cpu and prev_cpu are part of this domain,
  		 * cpu is a valid SD_WAKE_AFFINE target.

  		 */

  		if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
  		    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
  			affine_sd = tmp;
  			want_affine = 0;

  		}

  		if (!want_sd && !want_affine)
  			break;

  		if (!(tmp->flags & sd_flag))

  			continue;

  		if (want_sd)
  			sd = tmp;
  	}

  #ifdef CONFIG_FAIR_GROUP_SCHED

  	if (sched_feat(LB_SHARES_UPDATE)) {
  		/*
  		 * Pick the largest domain to update shares over
  		 */
  		tmp = sd;

  		if (affine_sd && (!tmp || affine_sd->span_weight > sd->span_weight))

  			tmp = affine_sd;

  		if (tmp) {
  			raw_spin_unlock(&rq->lock);

  			update_shares(tmp);

  			raw_spin_lock(&rq->lock);
  		}

  	}

  #endif

  	if (affine_sd) {

  		if (cpu == prev_cpu || wake_affine(affine_sd, p, sync))
  			return select_idle_sibling(p, cpu);
  		else
  			return select_idle_sibling(p, prev_cpu);

  	}

  	while (sd) {

  		int load_idx = sd->forkexec_idx;

  		struct sched_group *group;

  		int weight;

  		if (!(sd->flags & sd_flag)) {

  			sd = sd->child;
  			continue;
  		}

  		if (sd_flag & SD_BALANCE_WAKE)
  			load_idx = sd->wake_idx;

  		group = find_idlest_group(sd, p, cpu, load_idx);

  		if (!group) {
  			sd = sd->child;
  			continue;
  		}

  		new_cpu = find_idlest_cpu(group, p, cpu);

  		if (new_cpu == -1 || new_cpu == cpu) {
  			/* Now try balancing at a lower domain level of cpu */
  			sd = sd->child;
  			continue;

  		}

  
  		/* Now try balancing at a lower domain level of new_cpu */
  		cpu = new_cpu;

  		weight = sd->span_weight;

  		sd = NULL;
  		for_each_domain(cpu, tmp) {

  			if (weight <= tmp->span_weight)

  				break;

  			if (tmp->flags & sd_flag)

  				sd = tmp;
  		}
  		/* while loop will break here if sd == NULL */

  	}

  	return new_cpu;

  }
  #endif /* CONFIG_SMP */

  static unsigned long
  wakeup_gran(struct sched_entity *curr, struct sched_entity *se)

  {
  	unsigned long gran = sysctl_sched_wakeup_granularity;
  
  	/*

  	 * Since its curr running now, convert the gran from real-time
  	 * to virtual-time in his units.

  	 *
  	 * By using 'se' instead of 'curr' we penalize light tasks, so
  	 * they get preempted easier. That is, if 'se' < 'curr' then
  	 * the resulting gran will be larger, therefore penalizing the
  	 * lighter, if otoh 'se' > 'curr' then the resulting gran will
  	 * be smaller, again penalizing the lighter task.
  	 *
  	 * This is especially important for buddies when the leftmost
  	 * task is higher priority than the buddy.

  	 */

  	if (unlikely(se->load.weight != NICE_0_LOAD))
  		gran = calc_delta_fair(gran, 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, se);

  	if (vdiff > gran)
  		return 1;
  
  	return 0;
  }

  static void set_last_buddy(struct sched_entity *se)
  {

  	if (likely(task_of(se)->policy != SCHED_IDLE)) {
  		for_each_sched_entity(se)
  			cfs_rq_of(se)->last = se;
  	}

  }
  
  static void set_next_buddy(struct sched_entity *se)
  {

  	if (likely(task_of(se)->policy != SCHED_IDLE)) {
  		for_each_sched_entity(se)
  			cfs_rq_of(se)->next = se;
  	}

  }

  /*

   * Preempt the current task with a newly woken task if needed:
   */

  static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)

  {
  	struct task_struct *curr = rq->curr;

  	struct sched_entity *se = &curr->se, *pse = &p->se;

  	struct cfs_rq *cfs_rq = task_cfs_rq(curr);

  	int scale = cfs_rq->nr_running >= sched_nr_latency;

  	if (unlikely(rt_prio(p->prio)))
  		goto preempt;

  	if (unlikely(p->sched_class != &fair_sched_class))
  		return;

  	if (unlikely(se == pse))
  		return;

  	if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK))

  		set_next_buddy(pse);

  	/*
  	 * We can come here with TIF_NEED_RESCHED already set from new task
  	 * wake up path.
  	 */
  	if (test_tsk_need_resched(curr))
  		return;

  	/*

  	 * Batch and idle tasks do not preempt (their preemption is driven by

  	 * the tick):
  	 */

  	if (unlikely(p->policy != SCHED_NORMAL))

  		return;

  	/* Idle tasks are by definition preempted by everybody. */

  	if (unlikely(curr->policy == SCHED_IDLE))
  		goto preempt;

  	if (!sched_feat(WAKEUP_PREEMPT))
  		return;

  	update_curr(cfs_rq);

  	find_matching_se(&se, &pse);