/*
   * 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>

  #include <linux/cpumask.h>

  #include <linux/slab.h>
  #include <linux/profile.h>
  #include <linux/interrupt.h>
  
  #include <trace/events/sched.h>
  
  #include "sched.h"

  /*

   * Targeted preemption latency for CPU-bound tasks:

   * (default: 6ms * (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: 0.75 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;

  
  /*

   * 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;

  /*
   * The exponential sliding  window over which load is averaged for shares
   * distribution.
   * (default: 10msec)
   */
  unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;

  #ifdef CONFIG_CFS_BANDWIDTH
  /*
   * Amount of runtime to allocate from global (tg) to local (per-cfs_rq) pool
   * each time a cfs_rq requests quota.
   *
   * Note: in the case that the slice exceeds the runtime remaining (either due
   * to consumption or the quota being specified to be smaller than the slice)
   * we will always only issue the remaining available time.
   *
   * default: 5 msec, units: microseconds
    */
  unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
  #endif

  /*
   * Increase the granularity value when there are more CPUs,
   * because with more CPUs the 'effective latency' as visible
   * to users decreases. But the relationship is not linear,
   * so pick a second-best guess by going with the log2 of the
   * number of CPUs.
   *
   * This idea comes from the SD scheduler of Con Kolivas:
   */
  static int get_update_sysctl_factor(void)
  {
  	unsigned int cpus = min_t(int, num_online_cpus(), 8);
  	unsigned int factor;
  
  	switch (sysctl_sched_tunable_scaling) {
  	case SCHED_TUNABLESCALING_NONE:
  		factor = 1;
  		break;
  	case SCHED_TUNABLESCALING_LINEAR:
  		factor = cpus;
  		break;
  	case SCHED_TUNABLESCALING_LOG:
  	default:
  		factor = 1 + ilog2(cpus);
  		break;
  	}
  
  	return factor;
  }
  
  static void update_sysctl(void)
  {
  	unsigned int factor = get_update_sysctl_factor();
  
  #define SET_SYSCTL(name) \
  	(sysctl_##name = (factor) * normalized_sysctl_##name)
  	SET_SYSCTL(sched_min_granularity);
  	SET_SYSCTL(sched_latency);
  	SET_SYSCTL(sched_wakeup_granularity);
  #undef SET_SYSCTL
  }
  
  void sched_init_granularity(void)
  {
  	update_sysctl();
  }
  
  #if BITS_PER_LONG == 32
  # define WMULT_CONST	(~0UL)
  #else
  # define WMULT_CONST	(1UL << 32)
  #endif
  
  #define WMULT_SHIFT	32
  
  /*
   * Shift right and round:
   */
  #define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
  
  /*
   * delta *= weight / lw
   */
  static unsigned long
  calc_delta_mine(unsigned long delta_exec, unsigned long weight,
  		struct load_weight *lw)
  {
  	u64 tmp;
  
  	/*
  	 * weight can be less than 2^SCHED_LOAD_RESOLUTION for task group sched
  	 * entities since MIN_SHARES = 2. Treat weight as 1 if less than
  	 * 2^SCHED_LOAD_RESOLUTION.
  	 */
  	if (likely(weight > (1UL << SCHED_LOAD_RESOLUTION)))
  		tmp = (u64)delta_exec * scale_load_down(weight);
  	else
  		tmp = (u64)delta_exec;
  
  	if (!lw->inv_weight) {
  		unsigned long w = scale_load_down(lw->weight);
  
  		if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST))
  			lw->inv_weight = 1;
  		else if (unlikely(!w))
  			lw->inv_weight = WMULT_CONST;
  		else
  			lw->inv_weight = WMULT_CONST / w;
  	}
  
  	/*
  	 * Check whether we'd overflow the 64-bit multiplication:
  	 */
  	if (unlikely(tmp > WMULT_CONST))
  		tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
  			WMULT_SHIFT/2);
  	else
  		tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT);
  
  	return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
  }
  
  
  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;
  }

  static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
  {
  	if (!cfs_rq->on_list) {

  		/*
  		 * Ensure we either appear before our parent (if already
  		 * enqueued) or force our parent to appear after us when it is
  		 * enqueued.  The fact that we always enqueue bottom-up
  		 * reduces this to two cases.
  		 */
  		if (cfs_rq->tg->parent &&
  		    cfs_rq->tg->parent->cfs_rq[cpu_of(rq_of(cfs_rq))]->on_list) {
  			list_add_rcu(&cfs_rq->leaf_cfs_rq_list,
  				&rq_of(cfs_rq)->leaf_cfs_rq_list);
  		} else {
  			list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,

  				&rq_of(cfs_rq)->leaf_cfs_rq_list);

  		}

  
  		cfs_rq->on_list = 1;
  	}
  }
  
  static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
  {
  	if (cfs_rq->on_list) {
  		list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
  		cfs_rq->on_list = 0;
  	}
  }

  /* 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 void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
  {
  }
  
  static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
  {
  }

  #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 */

  static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
  				   unsigned long delta_exec);

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

  #ifndef CONFIG_64BIT
  	smp_wmb();
  	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
  #endif

  }

  /*
   * 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;

  	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 (entity_before(se, 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);

  }

  struct sched_entity *__pick_first_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_next_entity(struct sched_entity *se)
  {
  	struct rb_node *next = rb_next(&se->run_node);
  
  	if (!next)
  		return NULL;
  
  	return rb_entry(next, struct sched_entity, run_node);
  }
  
  #ifdef CONFIG_SCHED_DEBUG

  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:
   */

  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);

  #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);

  }

  static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update);

  static void update_cfs_shares(struct cfs_rq *cfs_rq);

  /*

   * 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);

  #if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED

  	cfs_rq->load_unacc_exec_time += delta_exec;

  #endif

  }

  static void update_curr(struct cfs_rq *cfs_rq)

  {

  	struct sched_entity *curr = cfs_rq->curr;

  	u64 now = rq_of(cfs_rq)->clock_task;

  	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);

  	}

  
  	account_cfs_rq_runtime(cfs_rq, 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_task;

  }

  /**************************************************
   * 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))

  		update_load_add(&rq_of(cfs_rq)->load, 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++;

  }
  
  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))

  		update_load_sub(&rq_of(cfs_rq)->load, 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--;

  }

  #ifdef CONFIG_FAIR_GROUP_SCHED

  /* we need this in update_cfs_load and load-balance functions below */
  static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);

  # ifdef CONFIG_SMP

  static void update_cfs_rq_load_contribution(struct cfs_rq *cfs_rq,
  					    int global_update)
  {
  	struct task_group *tg = cfs_rq->tg;
  	long load_avg;
  
  	load_avg = div64_u64(cfs_rq->load_avg, cfs_rq->load_period+1);
  	load_avg -= cfs_rq->load_contribution;
  
  	if (global_update || abs(load_avg) > cfs_rq->load_contribution / 8) {
  		atomic_add(load_avg, &tg->load_weight);
  		cfs_rq->load_contribution += load_avg;
  	}
  }
  
  static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)

  {

  	u64 period = sysctl_sched_shares_window;

  	u64 now, delta;

  	unsigned long load = cfs_rq->load.weight;

  	if (cfs_rq->tg == &root_task_group || throttled_hierarchy(cfs_rq))

  		return;

  	now = rq_of(cfs_rq)->clock_task;

  	delta = now - cfs_rq->load_stamp;

  	/* truncate load history at 4 idle periods */
  	if (cfs_rq->load_stamp > cfs_rq->load_last &&
  	    now - cfs_rq->load_last > 4 * period) {
  		cfs_rq->load_period = 0;
  		cfs_rq->load_avg = 0;

  		delta = period - 1;

  	}

  	cfs_rq->load_stamp = now;

  	cfs_rq->load_unacc_exec_time = 0;

  	cfs_rq->load_period += delta;

  	if (load) {
  		cfs_rq->load_last = now;
  		cfs_rq->load_avg += delta * load;
  	}

  	/* consider updating load contribution on each fold or truncate */
  	if (global_update || cfs_rq->load_period > period
  	    || !cfs_rq->load_period)
  		update_cfs_rq_load_contribution(cfs_rq, global_update);

  	while (cfs_rq->load_period > period) {
  		/*
  		 * Inline assembly required to prevent the compiler
  		 * optimising this loop into a divmod call.
  		 * See __iter_div_u64_rem() for another example of this.
  		 */
  		asm("" : "+rm" (cfs_rq->load_period));
  		cfs_rq->load_period /= 2;
  		cfs_rq->load_avg /= 2;
  	}

  	if (!cfs_rq->curr && !cfs_rq->nr_running && !cfs_rq->load_avg)
  		list_del_leaf_cfs_rq(cfs_rq);

  }

  static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
  {
  	long tg_weight;
  
  	/*
  	 * Use this CPU's actual weight instead of the last load_contribution
  	 * to gain a more accurate current total weight. See
  	 * update_cfs_rq_load_contribution().
  	 */
  	tg_weight = atomic_read(&tg->load_weight);
  	tg_weight -= cfs_rq->load_contribution;
  	tg_weight += cfs_rq->load.weight;
  
  	return tg_weight;
  }

  static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)

  {

  	long tg_weight, load, shares;

  	tg_weight = calc_tg_weight(tg, cfs_rq);

  	load = cfs_rq->load.weight;

  	shares = (tg->shares * load);

  	if (tg_weight)
  		shares /= tg_weight;

  
  	if (shares < MIN_SHARES)
  		shares = MIN_SHARES;
  	if (shares > tg->shares)
  		shares = tg->shares;
  
  	return shares;
  }
  
  static void update_entity_shares_tick(struct cfs_rq *cfs_rq)
  {
  	if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) {
  		update_cfs_load(cfs_rq, 0);

  		update_cfs_shares(cfs_rq);

  	}
  }
  # else /* CONFIG_SMP */
  static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
  {
  }

  static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)

  {
  	return tg->shares;
  }
  
  static inline void update_entity_shares_tick(struct cfs_rq *cfs_rq)
  {
  }
  # endif /* CONFIG_SMP */

  static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
  			    unsigned long weight)
  {

  	if (se->on_rq) {
  		/* commit outstanding execution time */
  		if (cfs_rq->curr == se)
  			update_curr(cfs_rq);

  		account_entity_dequeue(cfs_rq, se);

  	}

  
  	update_load_set(&se->load, weight);
  
  	if (se->on_rq)
  		account_entity_enqueue(cfs_rq, se);
  }

  static void update_cfs_shares(struct cfs_rq *cfs_rq)

  {
  	struct task_group *tg;
  	struct sched_entity *se;

  	long shares;

  	tg = cfs_rq->tg;
  	se = tg->se[cpu_of(rq_of(cfs_rq))];

  	if (!se || throttled_hierarchy(cfs_rq))

  		return;

  #ifndef CONFIG_SMP
  	if (likely(se->load.weight == tg->shares))
  		return;
  #endif

  	shares = calc_cfs_shares(cfs_rq, tg);

  
  	reweight_entity(cfs_rq_of(se), se, shares);
  }
  #else /* CONFIG_FAIR_GROUP_SCHED */

  static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)

  {
  }

  static inline void update_cfs_shares(struct cfs_rq *cfs_rq)

  {
  }

  
  static inline void update_entity_shares_tick(struct cfs_rq *cfs_rq)
  {
  }

  #endif /* CONFIG_FAIR_GROUP_SCHED */

  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.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.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);

  			}

  			trace_sched_stat_blocked(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 check_enqueue_throttle(struct cfs_rq *cfs_rq);

  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);

  	update_cfs_load(cfs_rq, 0);

  	account_entity_enqueue(cfs_rq, se);

  	update_cfs_shares(cfs_rq);

  	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);

  	se->on_rq = 1;

  	if (cfs_rq->nr_running == 1) {

  		list_add_leaf_cfs_rq(cfs_rq);

  		check_enqueue_throttle(cfs_rq);
  	}

  }

  static void __clear_buddies_last(struct sched_entity *se)

  {

  	for_each_sched_entity(se) {
  		struct cfs_rq *cfs_rq = cfs_rq_of(se);
  		if (cfs_rq->last == se)
  			cfs_rq->last = NULL;
  		else
  			break;
  	}
  }

  static void __clear_buddies_next(struct sched_entity *se)
  {
  	for_each_sched_entity(se) {
  		struct cfs_rq *cfs_rq = cfs_rq_of(se);
  		if (cfs_rq->next == se)
  			cfs_rq->next = NULL;
  		else
  			break;
  	}

  }

  static void __clear_buddies_skip(struct sched_entity *se)
  {
  	for_each_sched_entity(se) {
  		struct cfs_rq *cfs_rq = cfs_rq_of(se);
  		if (cfs_rq->skip == se)
  			cfs_rq->skip = NULL;
  		else
  			break;
  	}
  }

  static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
  {

  	if (cfs_rq->last == se)
  		__clear_buddies_last(se);
  
  	if (cfs_rq->next == se)
  		__clear_buddies_next(se);

  
  	if (cfs_rq->skip == se)
  		__clear_buddies_skip(se);

  }

  static void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);

  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);

  	se->on_rq = 0;

  	update_cfs_load(cfs_rq, 0);

  	account_entity_dequeue(cfs_rq, se);

  
  	/*
  	 * 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;

  	/* return excess runtime on last dequeue */
  	return_cfs_rq_runtime(cfs_rq);

  	update_min_vruntime(cfs_rq);
  	update_cfs_shares(cfs_rq);

  }
  
  /*
   * 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;

  	struct sched_entity *se;
  	s64 delta;

  	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 (delta_exec < sysctl_sched_min_granularity)
  		return;

  	se = __pick_first_entity(cfs_rq);
  	delta = curr->vruntime - se->vruntime;

  	if (delta < 0)
  		return;

  	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);

  /*
   * Pick the next process, keeping these things in mind, in this order:
   * 1) keep things fair between processes/task groups
   * 2) pick the "next" process, since someone really wants that to run
   * 3) pick the "last" process, for cache locality
   * 4) do not run the "skip" process, if something else is available
   */

  static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)

  {

  	struct sched_entity *se = __pick_first_entity(cfs_rq);

  	struct sched_entity *left = se;

  	/*
  	 * Avoid running the skip buddy, if running something else can
  	 * be done without getting too unfair.
  	 */
  	if (cfs_rq->skip == se) {
  		struct sched_entity *second = __pick_next_entity(se);
  		if (second && wakeup_preempt_entity(second, left) < 1)
  			se = second;
  	}

  	/*
  	 * 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;

  	/*
  	 * Someone really wants this to run. If it's not unfair, run it.
  	 */
  	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
  		se = cfs_rq->next;

  	clear_buddies(cfs_rq, se);

  
  	return se;

  }

  static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq);

  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);

  	/* throttle cfs_rqs exceeding runtime */
  	check_cfs_rq_runtime(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);

  	/*
  	 * Update share accounting for long-running entities.
  	 */
  	update_entity_shares_tick(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)

  		check_preempt_tick(cfs_rq, curr);

  }

  
  /**************************************************
   * CFS bandwidth control machinery
   */
  
  #ifdef CONFIG_CFS_BANDWIDTH

  
  #ifdef HAVE_JUMP_LABEL
  static struct jump_label_key __cfs_bandwidth_used;
  
  static inline bool cfs_bandwidth_used(void)
  {
  	return static_branch(&__cfs_bandwidth_used);
  }
  
  void account_cfs_bandwidth_used(int enabled, int was_enabled)
  {
  	/* only need to count groups transitioning between enabled/!enabled */
  	if (enabled && !was_enabled)
  		jump_label_inc(&__cfs_bandwidth_used);
  	else if (!enabled && was_enabled)
  		jump_label_dec(&__cfs_bandwidth_used);
  }
  #else /* HAVE_JUMP_LABEL */
  static bool cfs_bandwidth_used(void)
  {
  	return true;
  }
  
  void account_cfs_bandwidth_used(int enabled, int was_enabled) {}
  #endif /* HAVE_JUMP_LABEL */

  /*
   * default period for cfs group bandwidth.
   * default: 0.1s, units: nanoseconds
   */
  static inline u64 default_cfs_period(void)
  {
  	return 100000000ULL;
  }

  
  static inline u64 sched_cfs_bandwidth_slice(void)
  {
  	return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC;
  }

  /*
   * Replenish runtime according to assigned quota and update expiration time.
   * We use sched_clock_cpu directly instead of rq->clock to avoid adding
   * additional synchronization around rq->lock.
   *
   * requires cfs_b->lock
   */

  void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)

  {
  	u64 now;
  
  	if (cfs_b->quota == RUNTIME_INF)
  		return;
  
  	now = sched_clock_cpu(smp_processor_id());
  	cfs_b->runtime = cfs_b->quota;
  	cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period);
  }

  static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
  {
  	return &tg->cfs_bandwidth;
  }

  /* returns 0 on failure to allocate runtime */
  static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)

  {
  	struct task_group *tg = cfs_rq->tg;
  	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);

  	u64 amount = 0, min_amount, expires;

  
  	/* note: this is a positive sum as runtime_remaining <= 0 */
  	min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
  
  	raw_spin_lock(&cfs_b->lock);
  	if (cfs_b->quota == RUNTIME_INF)
  		amount = min_amount;

  	else {

  		/*
  		 * If the bandwidth pool has become inactive, then at least one
  		 * period must have elapsed since the last consumption.
  		 * Refresh the global state and ensure bandwidth timer becomes
  		 * active.
  		 */
  		if (!cfs_b->timer_active) {
  			__refill_cfs_bandwidth_runtime(cfs_b);

  			__start_cfs_bandwidth(cfs_b);

  		}

  
  		if (cfs_b->runtime > 0) {
  			amount = min(cfs_b->runtime, min_amount);
  			cfs_b->runtime -= amount;
  			cfs_b->idle = 0;
  		}

  	}

  	expires = cfs_b->runtime_expires;

  	raw_spin_unlock(&cfs_b->lock);
  
  	cfs_rq->runtime_remaining += amount;

  	/*
  	 * we may have advanced our local expiration to account for allowed
  	 * spread between our sched_clock and the one on which runtime was
  	 * issued.
  	 */
  	if ((s64)(expires - cfs_rq->runtime_expires) > 0)
  		cfs_rq->runtime_expires = expires;

  
  	return cfs_rq->runtime_remaining > 0;

  }

  /*
   * Note: This depends on the synchronization provided by sched_clock and the
   * fact that rq->clock snapshots this value.
   */
  static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)

  {

  	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
  	struct rq *rq = rq_of(cfs_rq);
  
  	/* if the deadline is ahead of our clock, nothing to do */
  	if (likely((s64)(rq->clock - cfs_rq->runtime_expires) < 0))

  		return;

  	if (cfs_rq->runtime_remaining < 0)
  		return;
  
  	/*
  	 * If the local deadline has passed we have to consider the
  	 * possibility that our sched_clock is 'fast' and the global deadline
  	 * has not truly expired.
  	 *
  	 * Fortunately we can check determine whether this the case by checking
  	 * whether the global deadline has advanced.
  	 */
  
  	if ((s64)(cfs_rq->runtime_expires - cfs_b->runtime_expires) >= 0) {
  		/* extend local deadline, drift is bounded above by 2 ticks */
  		cfs_rq->runtime_expires += TICK_NSEC;
  	} else {
  		/* global deadline is ahead, expiration has passed */
  		cfs_rq->runtime_remaining = 0;
  	}
  }
  
  static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
  				     unsigned long delta_exec)
  {
  	/* dock delta_exec before expiring quota (as it could span periods) */

  	cfs_rq->runtime_remaining -= delta_exec;

  	expire_cfs_rq_runtime(cfs_rq);
  
  	if (likely(cfs_rq->runtime_remaining > 0))

  		return;

  	/*
  	 * if we're unable to extend our runtime we resched so that the active
  	 * hierarchy can be throttled
  	 */
  	if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr))
  		resched_task(rq_of(cfs_rq)->curr);

  }
  
  static __always_inline void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
  						   unsigned long delta_exec)
  {

  	if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled)

  		return;
  
  	__account_cfs_rq_runtime(cfs_rq, delta_exec);
  }

  static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
  {

  	return cfs_bandwidth_used() && cfs_rq->throttled;

  }

  /* check whether cfs_rq, or any parent, is throttled */
  static inline int throttled_hierarchy(struct cfs_rq *cfs_rq)
  {

  	return cfs_bandwidth_used() && cfs_rq->throttle_count;

  }
  
  /*
   * Ensure that neither of the group entities corresponding to src_cpu or
   * dest_cpu are members of a throttled hierarchy when performing group
   * load-balance operations.
   */
  static inline int throttled_lb_pair(struct task_group *tg,
  				    int src_cpu, int dest_cpu)
  {
  	struct cfs_rq *src_cfs_rq, *dest_cfs_rq;
  
  	src_cfs_rq = tg->cfs_rq[src_cpu];
  	dest_cfs_rq = tg->cfs_rq[dest_cpu];
  
  	return throttled_hierarchy(src_cfs_rq) ||
  	       throttled_hierarchy(dest_cfs_rq);
  }
  
  /* updated child weight may affect parent so we have to do this bottom up */
  static int tg_unthrottle_up(struct task_group *tg, void *data)
  {
  	struct rq *rq = data;
  	struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
  
  	cfs_rq->throttle_count--;
  #ifdef CONFIG_SMP
  	if (!cfs_rq->throttle_count) {
  		u64 delta = rq->clock_task - cfs_rq->load_stamp;
  
  		/* leaving throttled state, advance shares averaging windows */
  		cfs_rq->load_stamp += delta;
  		cfs_rq->load_last += delta;
  
  		/* update entity weight now that we are on_rq again */
  		update_cfs_shares(cfs_rq);
  	}
  #endif
  
  	return 0;
  }
  
  static int tg_throttle_down(struct task_group *tg, void *data)
  {
  	struct rq *rq = data;
  	struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
  
  	/* group is entering throttled state, record last load */
  	if (!cfs_rq->throttle_count)
  		update_cfs_load(cfs_rq, 0);
  	cfs_rq->throttle_count++;
  
  	return 0;
  }

  static void throttle_cfs_rq(struct cfs_rq *cfs_rq)

  {
  	struct rq *rq = rq_of(cfs_rq);
  	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
  	struct sched_entity *se;
  	long task_delta, dequeue = 1;
  
  	se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
  
  	/* account load preceding throttle */

  	rcu_read_lock();
  	walk_tg_tree_from(cfs_rq->tg, tg_throttle_down, tg_nop, (void *)rq);
  	rcu_read_unlock();

  
  	task_delta = cfs_rq->h_nr_running;
  	for_each_sched_entity(se) {
  		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
  		/* throttled entity or throttle-on-deactivate */
  		if (!se->on_rq)
  			break;
  
  		if (dequeue)
  			dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
  		qcfs_rq->h_nr_running -= task_delta;
  
  		if (qcfs_rq->load.weight)
  			dequeue = 0;
  	}
  
  	if (!se)
  		rq->nr_running -= task_delta;
  
  	cfs_rq->throttled = 1;

  	cfs_rq->throttled_timestamp = rq->clock;

  	raw_spin_lock(&cfs_b->lock);
  	list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
  	raw_spin_unlock(&cfs_b->lock);
  }

  void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)

  {
  	struct rq *rq = rq_of(cfs_rq);
  	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
  	struct sched_entity *se;
  	int enqueue = 1;
  	long task_delta;
  
  	se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
  
  	cfs_rq->throttled = 0;
  	raw_spin_lock(&cfs_b->lock);

  	cfs_b->throttled_time += rq->clock - cfs_rq->throttled_timestamp;

  	list_del_rcu(&cfs_rq->throttled_list);
  	raw_spin_unlock(&cfs_b->lock);

  	cfs_rq->throttled_timestamp = 0;

  	update_rq_clock(rq);
  	/* update hierarchical throttle state */
  	walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq);

  	if (!cfs_rq->load.weight)
  		return;
  
  	task_delta = cfs_rq->h_nr_running;
  	for_each_sched_entity(se) {
  		if (se->on_rq)
  			enqueue = 0;
  
  		cfs_rq = cfs_rq_of(se);
  		if (enqueue)
  			enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
  		cfs_rq->h_nr_running += task_delta;
  
  		if (cfs_rq_throttled(cfs_rq))
  			break;
  	}
  
  	if (!se)
  		rq->nr_running += task_delta;
  
  	/* determine whether we need to wake up potentially idle cpu */
  	if (rq->curr == rq->idle && rq->cfs.nr_running)
  		resched_task(rq->curr);
  }
  
  static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
  		u64 remaining, u64 expires)
  {
  	struct cfs_rq *cfs_rq;
  	u64 runtime = remaining;
  
  	rcu_read_lock();
  	list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq,
  				throttled_list) {
  		struct rq *rq = rq_of(cfs_rq);
  
  		raw_spin_lock(&rq->lock);
  		if (!cfs_rq_throttled(cfs_rq))
  			goto next;
  
  		runtime = -cfs_rq->runtime_remaining + 1;
  		if (runtime > remaining)
  			runtime = remaining;
  		remaining -= runtime;
  
  		cfs_rq->runtime_remaining += runtime;
  		cfs_rq->runtime_expires = expires;
  
  		/* we check whether we're throttled above */
  		if (cfs_rq->runtime_remaining > 0)
  			unthrottle_cfs_rq(cfs_rq);
  
  next:
  		raw_spin_unlock(&rq->lock);
  
  		if (!remaining)
  			break;
  	}
  	rcu_read_unlock();
  
  	return remaining;
  }

  /*
   * Responsible for refilling a task_group's bandwidth and unthrottling its
   * cfs_rqs as appropriate. If there has been no activity within the last
   * period the timer is deactivated until scheduling resumes; cfs_b->idle is
   * used to track this state.
   */
  static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
  {

  	u64 runtime, runtime_expires;
  	int idle = 1, throttled;

  
  	raw_spin_lock(&cfs_b->lock);
  	/* no need to continue the timer with no bandwidth constraint */
  	if (cfs_b->quota == RUNTIME_INF)
  		goto out_unlock;

  	throttled = !list_empty(&cfs_b->throttled_cfs_rq);
  	/* idle depends on !throttled (for the case of a large deficit) */
  	idle = cfs_b->idle && !throttled;

  	cfs_b->nr_periods += overrun;

  	/* if we're going inactive then everything else can be deferred */
  	if (idle)
  		goto out_unlock;
  
  	__refill_cfs_bandwidth_runtime(cfs_b);

  	if (!throttled) {
  		/* mark as potentially idle for the upcoming period */
  		cfs_b->idle = 1;
  		goto out_unlock;
  	}

  	/* account preceding periods in which throttling occurred */
  	cfs_b->nr_throttled += overrun;

  	/*
  	 * There are throttled entities so we must first use the new bandwidth
  	 * to unthrottle them before making it generally available.  This
  	 * ensures that all existing debts will be paid before a new cfs_rq is
  	 * allowed to run.
  	 */
  	runtime = cfs_b->runtime;
  	runtime_expires = cfs_b->runtime_expires;
  	cfs_b->runtime = 0;
  
  	/*
  	 * This check is repeated as we are holding onto the new bandwidth
  	 * while we unthrottle.  This can potentially race with an unthrottled
  	 * group trying to acquire new bandwidth from the global pool.
  	 */
  	while (throttled && runtime > 0) {
  		raw_spin_unlock(&cfs_b->lock);
  		/* we can't nest cfs_b->lock while distributing bandwidth */
  		runtime = distribute_cfs_runtime(cfs_b, runtime,
  						 runtime_expires);
  		raw_spin_lock(&cfs_b->lock);
  
  		throttled = !list_empty(&cfs_b->throttled_cfs_rq);
  	}

  	/* return (any) remaining runtime */
  	cfs_b->runtime = runtime;
  	/*
  	 * While we are ensured activity in the period following an
  	 * unthrottle, this also covers the case in which the new bandwidth is
  	 * insufficient to cover the existing bandwidth deficit.  (Forcing the
  	 * timer to remain active while there are any throttled entities.)
  	 */
  	cfs_b->idle = 0;

  out_unlock:
  	if (idle)
  		cfs_b->timer_active = 0;
  	raw_spin_unlock(&cfs_b->lock);
  
  	return idle;
  }

  /* a cfs_rq won't donate quota below this amount */
  static const u64 min_cfs_rq_runtime = 1 * NSEC_PER_MSEC;
  /* minimum remaining period time to redistribute slack quota */
  static const u64 min_bandwidth_expiration = 2 * NSEC_PER_MSEC;
  /* how long we wait to gather additional slack before distributing */
  static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC;
  
  /* are we near the end of the current quota period? */
  static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
  {
  	struct hrtimer *refresh_timer = &cfs_b->period_timer;
  	u64 remaining;
  
  	/* if the call-back is running a quota refresh is already occurring */
  	if (hrtimer_callback_running(refresh_timer))
  		return 1;
  
  	/* is a quota refresh about to occur? */
  	remaining = ktime_to_ns(hrtimer_expires_remaining(refresh_timer));
  	if (remaining < min_expire)
  		return 1;
  
  	return 0;
  }
  
  static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b)
  {
  	u64 min_left = cfs_bandwidth_slack_period + min_bandwidth_expiration;
  
  	/* if there's a quota refresh soon don't bother with slack */
  	if (runtime_refresh_within(cfs_b, min_left))
  		return;
  
  	start_bandwidth_timer(&cfs_b->slack_timer,
  				ns_to_ktime(cfs_bandwidth_slack_period));
  }
  
  /* we know any runtime found here is valid as update_curr() precedes return */
  static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
  {
  	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
  	s64 slack_runtime = cfs_rq->runtime_remaining - min_cfs_rq_runtime;
  
  	if (slack_runtime <= 0)
  		return;
  
  	raw_spin_lock(&cfs_b->lock);
  	if (cfs_b->quota != RUNTIME_INF &&
  	    cfs_rq->runtime_expires == cfs_b->runtime_expires) {
  		cfs_b->runtime += slack_runtime;
  
  		/* we are under rq->lock, defer unthrottling using a timer */
  		if (cfs_b->runtime > sched_cfs_bandwidth_slice() &&
  		    !list_empty(&cfs_b->throttled_cfs_rq))
  			start_cfs_slack_bandwidth(cfs_b);
  	}
  	raw_spin_unlock(&cfs_b->lock);
  
  	/* even if it's not valid for return we don't want to try again */
  	cfs_rq->runtime_remaining -= slack_runtime;
  }
  
  static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
  {

  	if (!cfs_bandwidth_used())
  		return;

  	if (!cfs_rq->runtime_enabled || cfs_rq->nr_running)

  		return;
  
  	__return_cfs_rq_runtime(cfs_rq);
  }
  
  /*
   * This is done with a timer (instead of inline with bandwidth return) since
   * it's necessary to juggle rq->locks to unthrottle their respective cfs_rqs.
   */
  static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
  {
  	u64 runtime = 0, slice = sched_cfs_bandwidth_slice();
  	u64 expires;
  
  	/* confirm we're still not at a refresh boundary */
  	if (runtime_refresh_within(cfs_b, min_bandwidth_expiration))
  		return;
  
  	raw_spin_lock(&cfs_b->lock);
  	if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) {
  		runtime = cfs_b->runtime;
  		cfs_b->runtime = 0;
  	}
  	expires = cfs_b->runtime_expires;
  	raw_spin_unlock(&cfs_b->lock);
  
  	if (!runtime)
  		return;
  
  	runtime = distribute_cfs_runtime(cfs_b, runtime, expires);
  
  	raw_spin_lock(&cfs_b->lock);
  	if (expires == cfs_b->runtime_expires)
  		cfs_b->runtime = runtime;
  	raw_spin_unlock(&cfs_b->lock);
  }

  /*
   * When a group wakes up we want to make sure that its quota is not already
   * expired/exceeded, otherwise it may be allowed to steal additional ticks of
   * runtime as update_curr() throttling can not not trigger until it's on-rq.
   */
  static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
  {

  	if (!cfs_bandwidth_used())
  		return;

  	/* an active group must be handled by the update_curr()->put() path */
  	if (!cfs_rq->runtime_enabled || cfs_rq->curr)
  		return;
  
  	/* ensure the group is not already throttled */
  	if (cfs_rq_throttled(cfs_rq))
  		return;
  
  	/* update runtime allocation */
  	account_cfs_rq_runtime(cfs_rq, 0);
  	if (cfs_rq->runtime_remaining <= 0)
  		throttle_cfs_rq(cfs_rq);
  }
  
  /* conditionally throttle active cfs_rq's from put_prev_entity() */
  static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
  {

  	if (!cfs_bandwidth_used())
  		return;

  	if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0))
  		return;
  
  	/*
  	 * it's possible for a throttled entity to be forced into a running
  	 * state (e.g. set_curr_task), in this case we're finished.
  	 */
  	if (cfs_rq_throttled(cfs_rq))
  		return;
  
  	throttle_cfs_rq(cfs_rq);
  }

  
  static inline u64 default_cfs_period(void);
  static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun);
  static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b);
  
  static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
  {
  	struct cfs_bandwidth *cfs_b =
  		container_of(timer, struct cfs_bandwidth, slack_timer);
  	do_sched_cfs_slack_timer(cfs_b);
  
  	return HRTIMER_NORESTART;
  }
  
  static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
  {
  	struct cfs_bandwidth *cfs_b =
  		container_of(timer, struct cfs_bandwidth, period_timer);
  	ktime_t now;
  	int overrun;
  	int idle = 0;
  
  	for (;;) {
  		now = hrtimer_cb_get_time(timer);
  		overrun = hrtimer_forward(timer, now, cfs_b->period);
  
  		if (!overrun)
  			break;
  
  		idle = do_sched_cfs_period_timer(cfs_b, overrun);
  	}
  
  	return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
  }
  
  void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
  {
  	raw_spin_lock_init(&cfs_b->lock);
  	cfs_b->runtime = 0;
  	cfs_b->quota = RUNTIME_INF;
  	cfs_b->period = ns_to_ktime(default_cfs_period());
  
  	INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
  	hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
  	cfs_b->period_timer.function = sched_cfs_period_timer;
  	hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
  	cfs_b->slack_timer.function = sched_cfs_slack_timer;
  }
  
  static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
  {
  	cfs_rq->runtime_enabled = 0;
  	INIT_LIST_HEAD(&cfs_rq->throttled_list);
  }
  
  /* requires cfs_b->lock, may release to reprogram timer */
  void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
  {
  	/*
  	 * The timer may be active because we're trying to set a new bandwidth
  	 * period or because we're racing with the tear-down path
  	 * (timer_active==0 becomes visible before the hrtimer call-back
  	 * terminates).  In either case we ensure that it's re-programmed
  	 */
  	while (unlikely(hrtimer_active(&cfs_b->period_timer))) {
  		raw_spin_unlock(&cfs_b->lock);
  		/* ensure cfs_b->lock is available while we wait */
  		hrtimer_cancel(&cfs_b->period_timer);
  
  		raw_spin_lock(&cfs_b->lock);
  		/* if someone else restarted the timer then we're done */
  		if (cfs_b->timer_active)
  			return;
  	}
  
  	cfs_b->timer_active = 1;
  	start_bandwidth_timer(&cfs_b->period_timer, cfs_b->period);
  }
  
  static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
  {
  	hrtimer_cancel(&cfs_b->period_timer);
  	hrtimer_cancel(&cfs_b->slack_timer);
  }
  
  void unthrottle_offline_cfs_rqs(struct rq *rq)
  {
  	struct cfs_rq *cfs_rq;
  
  	for_each_leaf_cfs_rq(rq, cfs_rq) {
  		struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
  
  		if (!cfs_rq->runtime_enabled)
  			continue;
  
  		/*
  		 * clock_task is not advancing so we just need to make sure
  		 * there's some valid quota amount
  		 */
  		cfs_rq->runtime_remaining = cfs_b->quota;
  		if (cfs_rq_throttled(cfs_rq))
  			unthrottle_cfs_rq(cfs_rq);
  	}
  }
  
  #else /* CONFIG_CFS_BANDWIDTH */

  static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
  				     unsigned long delta_exec) {}

  static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
  static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}

  static void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}

  
  static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
  {
  	return 0;
  }

  
  static inline int throttled_hierarchy(struct cfs_rq *cfs_rq)
  {
  	return 0;
  }
  
  static inline int throttled_lb_pair(struct task_group *tg,
  				    int src_cpu, int dest_cpu)
  {
  	return 0;
  }

  
  void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
  
  #ifdef CONFIG_FAIR_GROUP_SCHED
  static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}

  #endif

  static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
  {
  	return NULL;
  }
  static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
  void unthrottle_offline_cfs_rqs(struct rq *rq) {}
  
  #endif /* CONFIG_CFS_BANDWIDTH */

  /**************************************************
   * 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 (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 (!hrtick_enabled(rq) || 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);

  
  		/*
  		 * end evaluation on encountering a throttled cfs_rq
  		 *
  		 * note: in the case of encountering a throttled cfs_rq we will
  		 * post the final h_nr_running increment below.
  		*/
  		if (cfs_rq_throttled(cfs_rq))
  			break;

  		cfs_rq->h_nr_running++;

  		flags = ENQUEUE_WAKEUP;

  	}

  	for_each_sched_entity(se) {

  		cfs_rq = cfs_rq_of(se);

  		cfs_rq->h_nr_running++;

  		if (cfs_rq_throttled(cfs_rq))
  			break;

  		update_cfs_load(cfs_rq, 0);

  		update_cfs_shares(cfs_rq);

  	}

  	if (!se)
  		inc_nr_running(rq);

  	hrtick_update(rq);

  }

  static void set_next_buddy(struct sched_entity *se);

  /*
   * 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;

  	int task_sleep = flags & DEQUEUE_SLEEP;

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

  		dequeue_entity(cfs_rq, se, flags);

  
  		/*
  		 * end evaluation on encountering a throttled cfs_rq
  		 *
  		 * note: in the case of encountering a throttled cfs_rq we will
  		 * post the final h_nr_running decrement below.
  		*/
  		if (cfs_rq_throttled(cfs_rq))
  			break;

  		cfs_rq->h_nr_running--;

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

  		if (cfs_rq->load.weight) {
  			/*
  			 * Bias pick_next to pick a task from this cfs_rq, as
  			 * p is sleeping when it is within its sched_slice.
  			 */
  			if (task_sleep && parent_entity(se))
  				set_next_buddy(parent_entity(se));

  
  			/* avoid re-evaluating load for this entity */
  			se = parent_entity(se);

  			break;

  		}

  		flags |= DEQUEUE_SLEEP;

  	}

  	for_each_sched_entity(se) {

  		cfs_rq = cfs_rq_of(se);

  		cfs_rq->h_nr_running--;

  		if (cfs_rq_throttled(cfs_rq))
  			break;

  		update_cfs_load(cfs_rq, 0);

  		update_cfs_shares(cfs_rq);

  	}

  	if (!se)
  		dec_nr_running(rq);

  	hrtick_update(rq);

  }