kernel/sched/fair.c

/*
 * 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 <linux/mempolicy.h>
#include <linux/migrate.h>
#include <linux/task_work.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

static inline void update_load_add(struct load_weight *lw, unsigned long inc)
{
	lw->weight += inc;
	lw->inv_weight = 0;
}

static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
{
	lw->weight -= dec;
	lw->inv_weight = 0;
}

static inline void update_load_set(struct load_weight *lw, unsigned long w)
{
	lw->weight = w;
	lw->inv_weight = 0;
}

/*
 * 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 void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq,
				       int force_update);

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;
		/* We should have no load, but we need to update last_decay. */
		update_cfs_rq_blocked_load(cfs_rq, 0);
	}
}

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 __always_inline
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 max_vruntime, u64 vruntime)
{
	s64 delta = (s64)(vruntime - max_vruntime);
	if (delta > 0)
		max_vruntime = vruntime;

	return max_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);
	}

	/* ensure we never gain time by being placed backwards. */
	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 (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);
}

#ifdef CONFIG_SMP
static unsigned long task_h_load(struct task_struct *p);

static inline void __update_task_entity_contrib(struct sched_entity *se);

/* Give new task start runnable values to heavy its load in infant time */
void init_task_runnable_average(struct task_struct *p)
{
	u32 slice;

	p->se.avg.decay_count = 0;
	slice = sched_slice(task_cfs_rq(p), &p->se) >> 10;
	p->se.avg.runnable_avg_sum = slice;
	p->se.avg.runnable_avg_period = slice;
	__update_task_entity_contrib(&p->se);
}
#else
void init_task_runnable_average(struct task_struct *p)
{
}
#endif

/*
 * 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_clock_task(rq_of(cfs_rq));
	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_clock(rq_of(cfs_rq)));
}

/*
 * 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_clock(rq_of(cfs_rq)) - 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_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
#ifdef CONFIG_SCHEDSTATS
	if (entity_is_task(se)) {
		trace_sched_stat_wait(task_of(se),
			rq_clock(rq_of(cfs_rq)) - 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_clock_task(rq_of(cfs_rq));
}

/**************************************************
 * Scheduling class queueing methods:
 */

#ifdef CONFIG_NUMA_BALANCING
/*
 * Approximate time to scan a full NUMA task in ms. The task scan period is
 * calculated based on the tasks virtual memory size and
 * numa_balancing_scan_size.
 */
unsigned int sysctl_numa_balancing_scan_period_min = 1000;
unsigned int sysctl_numa_balancing_scan_period_max = 60000;
unsigned int sysctl_numa_balancing_scan_period_reset = 60000;

/* Portion of address space to scan in MB */
unsigned int sysctl_numa_balancing_scan_size = 256;

/* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
unsigned int sysctl_numa_balancing_scan_delay = 1000;

static unsigned int task_nr_scan_windows(struct task_struct *p)
{
	unsigned long rss = 0;
	unsigned long nr_scan_pages;

	/*
	 * Calculations based on RSS as non-present and empty pages are skipped
	 * by the PTE scanner and NUMA hinting faults should be trapped based
	 * on resident pages
	 */
	nr_scan_pages = sysctl_numa_balancing_scan_size << (20 - PAGE_SHIFT);
	rss = get_mm_rss(p->mm);
	if (!rss)
		rss = nr_scan_pages;

	rss = round_up(rss, nr_scan_pages);
	return rss / nr_scan_pages;
}

/* For sanitys sake, never scan more PTEs than MAX_SCAN_WINDOW MB/sec. */
#define MAX_SCAN_WINDOW 2560

static unsigned int task_scan_min(struct task_struct *p)
{
	unsigned int scan, floor;
	unsigned int windows = 1;

	if (sysctl_numa_balancing_scan_size < MAX_SCAN_WINDOW)
		windows = MAX_SCAN_WINDOW / sysctl_numa_balancing_scan_size;
	floor = 1000 / windows;

	scan = sysctl_numa_balancing_scan_period_min / task_nr_scan_windows(p);
	return max_t(unsigned int, floor, scan);
}

static unsigned int task_scan_max(struct task_struct *p)
{
	unsigned int smin = task_scan_min(p);
	unsigned int smax;

	/* Watch for min being lower than max due to floor calculations */
	smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p);
	return max(smin, smax);
}

/*
 * Once a preferred node is selected the scheduler balancer will prefer moving
 * a task to that node for sysctl_numa_balancing_settle_count number of PTE
 * scans. This will give the process the chance to accumulate more faults on
 * the preferred node but still allow the scheduler to move the task again if
 * the nodes CPUs are overloaded.
 */
unsigned int sysctl_numa_balancing_settle_count __read_mostly = 4;

struct numa_group {
	atomic_t refcount;

	spinlock_t lock; /* nr_tasks, tasks */
	int nr_tasks;
	pid_t gid;
	struct list_head task_list;

	struct rcu_head rcu;
	atomic_long_t total_faults;
	atomic_long_t faults[0];
};

pid_t task_numa_group_id(struct task_struct *p)
{
	return p->numa_group ? p->numa_group->gid : 0;
}

static inline int task_faults_idx(int nid, int priv)
{
	return 2 * nid + priv;
}

static inline unsigned long task_faults(struct task_struct *p, int nid)
{
	if (!p->numa_faults)
		return 0;

	return p->numa_faults[task_faults_idx(nid, 0)] +
		p->numa_faults[task_faults_idx(nid, 1)];
}

static inline unsigned long group_faults(struct task_struct *p, int nid)
{
	if (!p->numa_group)
		return 0;

	return atomic_long_read(&p->numa_group->faults[2*nid]) +
	       atomic_long_read(&p->numa_group->faults[2*nid+1]);
}

/*
 * These return the fraction of accesses done by a particular task, or
 * task group, on a particular numa node.  The group weight is given a
 * larger multiplier, in order to group tasks together that are almost
 * evenly spread out between numa nodes.
 */
static inline unsigned long task_weight(struct task_struct *p, int nid)
{
	unsigned long total_faults;

	if (!p->numa_faults)
		return 0;

	total_faults = p->total_numa_faults;

	if (!total_faults)
		return 0;

	return 1000 * task_faults(p, nid) / total_faults;
}

static inline unsigned long group_weight(struct task_struct *p, int nid)
{
	unsigned long total_faults;

	if (!p->numa_group)
		return 0;

	total_faults = atomic_long_read(&p->numa_group->total_faults);

	if (!total_faults)
		return 0;

	return 1200 * group_faults(p, nid) / total_faults;
}

static unsigned long weighted_cpuload(const int cpu);
static unsigned long source_load(int cpu, int type);
static unsigned long target_load(int cpu, int type);
static unsigned long power_of(int cpu);
static long effective_load(struct task_group *tg, int cpu, long wl, long wg);

/* Cached statistics for all CPUs within a node */
struct numa_stats {
	unsigned long nr_running;
	unsigned long load;

	/* Total compute capacity of CPUs on a node */
	unsigned long power;

	/* Approximate capacity in terms of runnable tasks on a node */
	unsigned long capacity;
	int has_capacity;
};

/*
 * XXX borrowed from update_sg_lb_stats
 */
static void update_numa_stats(struct numa_stats *ns, int nid)
{
	int cpu;

	memset(ns, 0, sizeof(*ns));
	for_each_cpu(cpu, cpumask_of_node(nid)) {
		struct rq *rq = cpu_rq(cpu);

		ns->nr_running += rq->nr_running;
		ns->load += weighted_cpuload(cpu);
		ns->power += power_of(cpu);
	}

	ns->load = (ns->load * SCHED_POWER_SCALE) / ns->power;
	ns->capacity = DIV_ROUND_CLOSEST(ns->power, SCHED_POWER_SCALE);
	ns->has_capacity = (ns->nr_running < ns->capacity);
}

struct task_numa_env {
	struct task_struct *p;

	int src_cpu, src_nid;
	int dst_cpu, dst_nid;

	struct numa_stats src_stats, dst_stats;

	int imbalance_pct, idx;

	struct task_struct *best_task;
	long best_imp;
	int best_cpu;
};

static void task_numa_assign(struct task_numa_env *env,
			     struct task_struct *p, long imp)
{
	if (env->best_task)
		put_task_struct(env->best_task);
	if (p)
		get_task_struct(p);

	env->best_task = p;
	env->best_imp = imp;
	env->best_cpu = env->dst_cpu;
}

/*
 * This checks if the overall compute and NUMA accesses of the system would
 * be improved if the source tasks was migrated to the target dst_cpu taking
 * into account that it might be best if task running on the dst_cpu should
 * be exchanged with the source task
 */
static void task_numa_compare(struct task_numa_env *env,
			      long taskimp, long groupimp)
{
	struct rq *src_rq = cpu_rq(env->src_cpu);
	struct rq *dst_rq = cpu_rq(env->dst_cpu);
	struct task_struct *cur;
	long dst_load, src_load;
	long load;
	long imp = (groupimp > 0) ? groupimp : taskimp;

	rcu_read_lock();
	cur = ACCESS_ONCE(dst_rq->curr);
	if (cur->pid == 0) /* idle */
		cur = NULL;

	/*
	 * "imp" is the fault differential for the source task between the
	 * source and destination node. Calculate the total differential for
	 * the source task and potential destination task. The more negative
	 * the value is, the more rmeote accesses that would be expected to
	 * be incurred if the tasks were swapped.
	 */
	if (cur) {
		/* Skip this swap candidate if cannot move to the source cpu */
		if (!cpumask_test_cpu(env->src_cpu, tsk_cpus_allowed(cur)))
			goto unlock;

		/*
		 * If dst and source tasks are in the same NUMA group, or not
		 * in any group then look only at task weights otherwise give
		 * priority to the group weights.
		 */
		if (!cur->numa_group || !env->p->numa_group ||
		    cur->numa_group == env->p->numa_group) {
			imp = taskimp + task_weight(cur, env->src_nid) -
			      task_weight(cur, env->dst_nid);
		} else {
			imp = groupimp + group_weight(cur, env->src_nid) -
			       group_weight(cur, env->dst_nid);
		}
	}

	if (imp < env->best_imp)
		goto unlock;

	if (!cur) {
		/* Is there capacity at our destination? */
		if (env->src_stats.has_capacity &&
		    !env->dst_stats.has_capacity)
			goto unlock;

		goto balance;
	}

	/* Balance doesn't matter much if we're running a task per cpu */
	if (src_rq->nr_running == 1 && dst_rq->nr_running == 1)
		goto assign;

	/*
	 * In the overloaded case, try and keep the load balanced.
	 */
balance:
	dst_load = env->dst_stats.load;
	src_load = env->src_stats.load;

	/* XXX missing power terms */
	load = task_h_load(env->p);
	dst_load += load;
	src_load -= load;

	if (cur) {
		load = task_h_load(cur);
		dst_load -= load;
		src_load += load;
	}

	/* make src_load the smaller */
	if (dst_load < src_load)
		swap(dst_load, src_load);

	if (src_load * env->imbalance_pct < dst_load * 100)
		goto unlock;

assign:
	task_numa_assign(env, cur, imp);
unlock:
	rcu_read_unlock();
}

static void task_numa_find_cpu(struct task_numa_env *env,
				long taskimp, long groupimp)
{
	int cpu;

	for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
		/* Skip this CPU if the source task cannot migrate */
		if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(env->p)))
			continue;

		env->dst_cpu = cpu;
		task_numa_compare(env, taskimp, groupimp);
	}
}

static int task_numa_migrate(struct task_struct *p)
{
	struct task_numa_env env = {
		.p = p,

		.src_cpu = task_cpu(p),
		.src_nid = task_node(p),

		.imbalance_pct = 112,

		.best_task = NULL,
		.best_imp = 0,
		.best_cpu = -1
	};
	struct sched_domain *sd;
	unsigned long taskweight, groupweight;
	int nid, ret;
	long taskimp, groupimp;

	/*
	 * Pick the lowest SD_NUMA domain, as that would have the smallest
	 * imbalance and would be the first to start moving tasks about.
	 *
	 * And we want to avoid any moving of tasks about, as that would create
	 * random movement of tasks -- counter the numa conditions we're trying
	 * to satisfy here.
	 */
	rcu_read_lock();
	sd = rcu_dereference(per_cpu(sd_numa, env.src_cpu));
	env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2;
	rcu_read_unlock();

	taskweight = task_weight(p, env.src_nid);
	groupweight = group_weight(p, env.src_nid);
	update_numa_stats(&env.src_stats, env.src_nid);
	env.dst_nid = p->numa_preferred_nid;
	taskimp = task_weight(p, env.dst_nid) - taskweight;
	groupimp = group_weight(p, env.dst_nid) - groupweight;
	update_numa_stats(&env.dst_stats, env.dst_nid);

	/* If the preferred nid has capacity, try to use it. */
	if (env.dst_stats.has_capacity)
		task_numa_find_cpu(&env, taskimp, groupimp);

	/* No space available on the preferred nid. Look elsewhere. */
	if (env.best_cpu == -1) {
		for_each_online_node(nid) {
			if (nid == env.src_nid || nid == p->numa_preferred_nid)
				continue;

			/* Only consider nodes where both task and groups benefit */
			taskimp = task_weight(p, nid) - taskweight;
			groupimp = group_weight(p, nid) - groupweight;
			if (taskimp < 0 && groupimp < 0)
				continue;

			env.dst_nid = nid;
			update_numa_stats(&env.dst_stats, env.dst_nid);
			task_numa_find_cpu(&env, taskimp, groupimp);
		}
	}

	/* No better CPU than the current one was found. */
	if (env.best_cpu == -1)
		return -EAGAIN;

	if (env.best_task == NULL) {
		int ret = migrate_task_to(p, env.best_cpu);
		return ret;
	}

	ret = migrate_swap(p, env.best_task);
	put_task_struct(env.best_task);
	return ret;
}

/* Attempt to migrate a task to a CPU on the preferred node. */
static void numa_migrate_preferred(struct task_struct *p)
{
	/* Success if task is already running on preferred CPU */
	p->numa_migrate_retry = 0;
	if (cpu_to_node(task_cpu(p)) == p->numa_preferred_nid) {
		/*
		 * If migration is temporarily disabled due to a task migration
		 * then re-enable it now as the task is running on its
		 * preferred node and memory should migrate locally
		 */
		if (!p->numa_migrate_seq)
			p->numa_migrate_seq++;
		return;
	}

	/* This task has no NUMA fault statistics yet */
	if (unlikely(p->numa_preferred_nid == -1))
		return;

	/* Otherwise, try migrate to a CPU on the preferred node */
	if (task_numa_migrate(p) != 0)
		p->numa_migrate_retry = jiffies + HZ*5;
}

static void task_numa_placement(struct task_struct *p)
{
	int seq, nid, max_nid = -1, max_group_nid = -1;
	unsigned long max_faults = 0, max_group_faults = 0;
	spinlock_t *group_lock = NULL;

	seq = ACCESS_ONCE(p->mm->numa_scan_seq);
	if (p->numa_scan_seq == seq)
		return;
	p->numa_scan_seq = seq;
	p->numa_migrate_seq++;
	p->numa_scan_period_max = task_scan_max(p);

	/* If the task is part of a group prevent parallel updates to group stats */
	if (p->numa_group) {
		group_lock = &p->numa_group->lock;
		spin_lock(group_lock);
	}

	/* Find the node with the highest number of faults */
	for_each_online_node(nid) {
		unsigned long faults = 0, group_faults = 0;
		int priv, i;

		for (priv = 0; priv < 2; priv++) {
			long diff;

			i = task_faults_idx(nid, priv);
			diff = -p->numa_faults[i];

			/* Decay existing window, copy faults since last scan */
			p->numa_faults[i] >>= 1;
			p->numa_faults[i] += p->numa_faults_buffer[i];
			p->numa_faults_buffer[i] = 0;

			faults += p->numa_faults[i];
			diff += p->numa_faults[i];
			p->total_numa_faults += diff;
			if (p->numa_group) {
				/* safe because we can only change our own group */
				atomic_long_add(diff, &p->numa_group->faults[i]);
				atomic_long_add(diff, &p->numa_group->total_faults);
				group_faults += atomic_long_read(&p->numa_group->faults[i]);
			}
		}

		if (faults > max_faults) {
			max_faults = faults;
			max_nid = nid;
		}

		if (group_faults > max_group_faults) {
			max_group_faults = group_faults;
			max_group_nid = nid;
		}
	}

	if (p->numa_group) {
		/*
		 * If the preferred task and group nids are different,
		 * iterate over the nodes again to find the best place.
		 */
		if (max_nid != max_group_nid) {
			unsigned long weight, max_weight = 0;

			for_each_online_node(nid) {
				weight = task_weight(p, nid) + group_weight(p, nid);
				if (weight > max_weight) {
					max_weight = weight;
					max_nid = nid;
				}
			}
		}

		spin_unlock(group_lock);
	}

	/* Preferred node as the node with the most faults */
	if (max_faults && max_nid != p->numa_preferred_nid) {
		/* Update the preferred nid and migrate task if possible */
		p->numa_preferred_nid = max_nid;
		p->numa_migrate_seq = 1;
		numa_migrate_preferred(p);
	}
}

static inline int get_numa_group(struct numa_group *grp)
{
	return atomic_inc_not_zero(&grp->refcount);
}

static inline void put_numa_group(struct numa_group *grp)
{
	if (atomic_dec_and_test(&grp->refcount))
		kfree_rcu(grp, rcu);
}

static void double_lock(spinlock_t *l1, spinlock_t *l2)
{
	if (l1 > l2)
		swap(l1, l2);

	spin_lock(l1);
	spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
}

static void task_numa_group(struct task_struct *p, int cpupid)
{
	struct numa_group *grp, *my_grp;
	struct task_struct *tsk;
	bool join = false;
	int cpu = cpupid_to_cpu(cpupid);
	int i;

	if (unlikely(!p->numa_group)) {
		unsigned int size = sizeof(struct numa_group) +
				    2*nr_node_ids*sizeof(atomic_long_t);

		grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
		if (!grp)
			return;

		atomic_set(&grp->refcount, 1);
		spin_lock_init(&grp->lock);
		INIT_LIST_HEAD(&grp->task_list);
		grp->gid = p->pid;

		for (i = 0; i < 2*nr_node_ids; i++)
			atomic_long_set(&grp->faults[i], p->numa_faults[i]);

		atomic_long_set(&grp->total_faults, p->total_numa_faults);

		list_add(&p->numa_entry, &grp->task_list);
		grp->nr_tasks++;
		rcu_assign_pointer(p->numa_group, grp);
	}

	rcu_read_lock();
	tsk = ACCESS_ONCE(cpu_rq(cpu)->curr);

	if (!cpupid_match_pid(tsk, cpupid))
		goto unlock;

	grp = rcu_dereference(tsk->numa_group);
	if (!grp)
		goto unlock;

	my_grp = p->numa_group;
	if (grp == my_grp)
		goto unlock;

	/*
	 * Only join the other group if its bigger; if we're the bigger group,
	 * the other task will join us.
	 */
	if (my_grp->nr_tasks > grp->nr_tasks)
		goto unlock;

	/*
	 * Tie-break on the grp address.
	 */
	if (my_grp->nr_tasks == grp->nr_tasks && my_grp > grp)
		goto unlock;

	if (!get_numa_group(grp))
		goto unlock;

	join = true;

unlock:
	rcu_read_unlock();

	if (!join)
		return;

	for (i = 0; i < 2*nr_node_ids; i++) {
		atomic_long_sub(p->numa_faults[i], &my_grp->faults[i]);
		atomic_long_add(p->numa_faults[i], &grp->faults[i]);
	}
	atomic_long_sub(p->total_numa_faults, &my_grp->total_faults);
	atomic_long_add(p->total_numa_faults, &grp->total_faults);

	double_lock(&my_grp->lock, &grp->lock);

	list_move(&p->numa_entry, &grp->task_list);
	my_grp->nr_tasks--;
	grp->nr_tasks++;

	spin_unlock(&my_grp->lock);
	spin_unlock(&grp->lock);

	rcu_assign_pointer(p->numa_group, grp);

	put_numa_group(my_grp);
}

void task_numa_free(struct task_struct *p)
{
	struct numa_group *grp = p->numa_group;
	int i;
	void *numa_faults = p->numa_faults;

	if (grp) {
		for (i = 0; i < 2*nr_node_ids; i++)
			atomic_long_sub(p->numa_faults[i], &grp->faults[i]);

		atomic_long_sub(p->total_numa_faults, &grp->total_faults);

		spin_lock(&grp->lock);
		list_del(&p->numa_entry);
		grp->nr_tasks--;
		spin_unlock(&grp->lock);
		rcu_assign_pointer(p->numa_group, NULL);
		put_numa_group(grp);
	}

	p->numa_faults = NULL;
	p->numa_faults_buffer = NULL;
	kfree(numa_faults);
}

/*
 * Got a PROT_NONE fault for a page on @node.
 */
void task_numa_fault(int last_cpupid, int node, int pages, int flags)
{
	struct task_struct *p = current;
	bool migrated = flags & TNF_MIGRATED;
	int priv;

	if (!numabalancing_enabled)
		return;

	/* for example, ksmd faulting in a user's mm */
	if (!p->mm)
		return;

	/* Do not worry about placement if exiting */
	if (p->state == TASK_DEAD)
		return;

	/* Allocate buffer to track faults on a per-node basis */
	if (unlikely(!p->numa_faults)) {
		int size = sizeof(*p->numa_faults) * 2 * nr_node_ids;

		/* numa_faults and numa_faults_buffer share the allocation */
		p->numa_faults = kzalloc(size * 2, GFP_KERNEL|__GFP_NOWARN);
		if (!p->numa_faults)
			return;

		BUG_ON(p->numa_faults_buffer);
		p->numa_faults_buffer = p->numa_faults + (2 * nr_node_ids);
		p->total_numa_faults = 0;
	}

	/*
	 * First accesses are treated as private, otherwise consider accesses
	 * to be private if the accessing pid has not changed
	 */
	if (unlikely(last_cpupid == (-1 & LAST_CPUPID_MASK))) {
		priv = 1;
	} else {
		priv = cpupid_match_pid(p, last_cpupid);
		if (!priv && !(flags & TNF_NO_GROUP))
			task_numa_group(p, last_cpupid);
	}

	/*
	 * If pages are properly placed (did not migrate) then scan slower.
	 * This is reset periodically in case of phase changes
	 */
	if (!migrated) {
		/* Initialise if necessary */
		if (!p->numa_scan_period_max)
			p->numa_scan_period_max = task_scan_max(p);

		p->numa_scan_period = min(p->numa_scan_period_max,
			p->numa_scan_period + 10);
	}

	task_numa_placement(p);

	/* Retry task to preferred node migration if it previously failed */
	if (p->numa_migrate_retry && time_after(jiffies, p->numa_migrate_retry))
		numa_migrate_preferred(p);

	if (migrated)
		p->numa_pages_migrated += pages;

	p->numa_faults_buffer[task_faults_idx(node, priv)] += pages;
}

static void reset_ptenuma_scan(struct task_struct *p)
{
	ACCESS_ONCE(p->mm->numa_scan_seq)++;
	p->mm->numa_scan_offset = 0;
}

/*
 * The expensive part of numa migration is done from task_work context.
 * Triggered from task_tick_numa().
 */
void task_numa_work(struct callback_head *work)
{
	unsigned long migrate, next_scan, now = jiffies;
	struct task_struct *p = current;
	struct mm_struct *mm = p->mm;
	struct vm_area_struct *vma;
	unsigned long start, end;
	unsigned long nr_pte_updates = 0;
	long pages;

	WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));

	work->next = work; /* protect against double add */
	/*
	 * Who cares about NUMA placement when they're dying.
	 *
	 * NOTE: make sure not to dereference p->mm before this check,
	 * exit_task_work() happens _after_ exit_mm() so we could be called
	 * without p->mm even though we still had it when we enqueued this
	 * work.
	 */
	if (p->flags & PF_EXITING)
		return;

	if (!mm->numa_next_reset || !mm->numa_next_scan) {
		mm->numa_next_scan = now +
			msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
		mm->numa_next_reset = now +
			msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset);
	}

	/*
	 * Reset the scan period if enough time has gone by. Objective is that
	 * scanning will be reduced if pages are properly placed. As tasks
	 * can enter different phases this needs to be re-examined. Lacking
	 * proper tracking of reference behaviour, this blunt hammer is used.
	 */
	migrate = mm->numa_next_reset;
	if (time_after(now, migrate)) {
		p->numa_scan_period = task_scan_min(p);
		next_scan = now + msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset);
		xchg(&mm->numa_next_reset, next_scan);
	}

	/*
	 * Enforce maximal scan/migration frequency..
	 */
	migrate = mm->numa_next_scan;
	if (time_before(now, migrate))
		return;

	if (p->numa_scan_period == 0) {
		p->numa_scan_period_max = task_scan_max(p);
		p->numa_scan_period = task_scan_min(p);
	}

	next_scan = now + msecs_to_jiffies(p->numa_scan_period);
	if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate)
		return;

	/*
	 * Delay this task enough that another task of this mm will likely win
	 * the next time around.
	 */
	p->node_stamp += 2 * TICK_NSEC;

	start = mm->numa_scan_offset;
	pages = sysctl_numa_balancing_scan_size;
	pages <<= 20 - PAGE_SHIFT; /* MB in pages */
	if (!pages)
		return;

	down_read(&mm->mmap_sem);
	vma = find_vma(mm, start);
	if (!vma) {
		reset_ptenuma_scan(p);
		start = 0;
		vma = mm->mmap;
	}
	for (; vma; vma = vma->vm_next) {
		if (!vma_migratable(vma) || !vma_policy_mof(p, vma))
			continue;

		/*
		 * Shared library pages mapped by multiple processes are not
		 * migrated as it is expected they are cache replicated. Avoid
		 * hinting faults in read-only file-backed mappings or the vdso
		 * as migrating the pages will be of marginal benefit.
		 */
		if (!vma->vm_mm ||
		    (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ)))
			continue;

		do {
			start = max(start, vma->vm_start);
			end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
			end = min(end, vma->vm_end);
			nr_pte_updates += change_prot_numa(vma, start, end);

			/*
			 * Scan sysctl_numa_balancing_scan_size but ensure that
			 * at least one PTE is updated so that unused virtual
			 * address space is quickly skipped.
			 */
			if (nr_pte_updates)
				pages -= (end - start) >> PAGE_SHIFT;

			start = end;
			if (pages <= 0)
				goto out;
		} while (end != vma->vm_end);
	}

out:
	/*
	 * If the whole process was scanned without updates then no NUMA
	 * hinting faults are being recorded and scan rate should be lower.
	 */
	if (mm->numa_scan_offset == 0 && !nr_pte_updates) {
		p->numa_scan_period = min(p->numa_scan_period_max,
			p->numa_scan_period << 1);

		next_scan = now + msecs_to_jiffies(p->numa_scan_period);
		mm->numa_next_scan = next_scan;
	}

	/*
	 * It is possible to reach the end of the VMA list but the last few
	 * VMAs are not guaranteed to the vma_migratable. If they are not, we
	 * would find the !migratable VMA on the next scan but not reset the
	 * scanner to the start so check it now.
	 */
	if (vma)
		mm->numa_scan_offset = start;
	else
		reset_ptenuma_scan(p);
	up_read(&mm->mmap_sem);
}

/*
 * Drive the periodic memory faults..
 */
void task_tick_numa(struct rq *rq, struct task_struct *curr)
{
	struct callback_head *work = &curr->numa_work;
	u64 period, now;

	/*
	 * We don't care about NUMA placement if we don't have memory.
	 */
	if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work)
		return;

	/*
	 * Using runtime rather than walltime has the dual advantage that
	 * we (mostly) drive the selection from busy threads and that the
	 * task needs to have done some actual work before we bother with
	 * NUMA placement.
	 */
	now = curr->se.sum_exec_runtime;
	period = (u64)curr->numa_scan_period * NSEC_PER_MSEC;

	if (now - curr->node_stamp > period) {
		if (!curr->node_stamp)
			curr->numa_scan_period = task_scan_min(curr);
		curr->node_stamp += period;

		if (!time_before(jiffies, curr->mm->numa_next_scan)) {
			init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */
			task_work_add(curr, work, true);
		}
	}
}
#else
static void task_tick_numa(struct rq *rq, struct task_struct *curr)
{
}
#endif /* CONFIG_NUMA_BALANCING */

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);
#ifdef CONFIG_SMP
	if (entity_is_task(se))
		list_add(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
#endif
	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))
		list_del_init(&se->group_node);
	cfs_rq->nr_running--;
}

#ifdef CONFIG_FAIR_GROUP_SCHED
# ifdef CONFIG_SMP
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_long_read(&tg->load_avg);
	tg_weight -= cfs_rq->tg_load_contrib;
	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;
}
# else /* CONFIG_SMP */
static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
	return tg->shares;
}
# 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 inline int throttled_hierarchy(struct cfs_rq *cfs_rq);

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 inline void update_cfs_shares(struct cfs_rq *cfs_rq)
{
}
#endif /* CONFIG_FAIR_GROUP_SCHED */

#ifdef CONFIG_SMP
/*
 * We choose a half-life close to 1 scheduling period.
 * Note: The tables below are dependent on this value.
 */
#define LOAD_AVG_PERIOD 32
#define LOAD_AVG_MAX 47742 /* maximum possible load avg */
#define LOAD_AVG_MAX_N 345 /* number of full periods to produce LOAD_MAX_AVG */

/* Precomputed fixed inverse multiplies for multiplication by y^n */
static const u32 runnable_avg_yN_inv[] = {
	0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6,
	0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85,
	0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581,
	0xad583ee9, 0xa9a15ab4, 0xa5fed6a9, 0xa2704302, 0x9ef5325f, 0x9b8d39b9,
	0x9837f050, 0x94f4efa8, 0x91c3d373, 0x8ea4398a, 0x8b95c1e3, 0x88980e80,
	0x85aac367, 0x82cd8698,
};

/*
 * Precomputed \Sum y^k { 1<=k<=n }.  These are floor(true_value) to prevent
 * over-estimates when re-combining.
 */
static const u32 runnable_avg_yN_sum[] = {
	    0, 1002, 1982, 2941, 3880, 4798, 5697, 6576, 7437, 8279, 9103,
	 9909,10698,11470,12226,12966,13690,14398,15091,15769,16433,17082,
	17718,18340,18949,19545,20128,20698,21256,21802,22336,22859,23371,
};

/*
 * Approximate:
 *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
 */
static __always_inline u64 decay_load(u64 val, u64 n)
{
	unsigned int local_n;

	if (!n)
		return val;
	else if (unlikely(n > LOAD_AVG_PERIOD * 63))
		return 0;

	/* after bounds checking we can collapse to 32-bit */
	local_n = n;

	/*
	 * As y^PERIOD = 1/2, we can combine
	 *    y^n = 1/2^(n/PERIOD) * k^(n%PERIOD)
	 * With a look-up table which covers k^n (n<PERIOD)
	 *
	 * To achieve constant time decay_load.
	 */
	if (unlikely(local_n >= LOAD_AVG_PERIOD)) {
		val >>= local_n / LOAD_AVG_PERIOD;
		local_n %= LOAD_AVG_PERIOD;
	}

	val *= runnable_avg_yN_inv[local_n];
	/* We don't use SRR here since we always want to round down. */
	return val >> 32;
}

/*
 * For updates fully spanning n periods, the contribution to runnable
 * average will be: \Sum 1024*y^n
 *
 * We can compute this reasonably efficiently by combining:
 *   y^PERIOD = 1/2 with precomputed \Sum 1024*y^n {for  n <PERIOD}
 */
static u32 __compute_runnable_contrib(u64 n)
{
	u32 contrib = 0;

	if (likely(n <= LOAD_AVG_PERIOD))
		return runnable_avg_yN_sum[n];
	else if (unlikely(n >= LOAD_AVG_MAX_N))
		return LOAD_AVG_MAX;

	/* Compute \Sum k^n combining precomputed values for k^i, \Sum k^j */
	do {
		contrib /= 2; /* y^LOAD_AVG_PERIOD = 1/2 */
		contrib += runnable_avg_yN_sum[LOAD_AVG_PERIOD];

		n -= LOAD_AVG_PERIOD;
	} while (n > LOAD_AVG_PERIOD);

	contrib = decay_load(contrib, n);
	return contrib + runnable_avg_yN_sum[n];
}

/*
 * We can represent the historical contribution to runnable average as the
 * coefficients of a geometric series.  To do this we sub-divide our runnable
 * history into segments of approximately 1ms (1024us); label the segment that
 * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
 *
 * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
 *      p0            p1           p2
 *     (now)       (~1ms ago)  (~2ms ago)
 *
 * Let u_i denote the fraction of p_i that the entity was runnable.
 *
 * We then designate the fractions u_i as our co-efficients, yielding the
 * following representation of historical load:
 *   u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
 *
 * We choose y based on the with of a reasonably scheduling period, fixing:
 *   y^32 = 0.5
 *
 * This means that the contribution to load ~32ms ago (u_32) will be weighted
 * approximately half as much as the contribution to load within the last ms
 * (u_0).
 *
 * When a period "rolls over" and we have new u_0`, multiplying the previous
 * sum again by y is sufficient to update:
 *   load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
 *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
 */
static __always_inline int __update_entity_runnable_avg(u64 now,
							struct sched_avg *sa,
							int runnable)
{
	u64 delta, periods;
	u32 runnable_contrib;
	int delta_w, decayed = 0;

	delta = now - sa->last_runnable_update;
	/*
	 * This should only happen when time goes backwards, which it
	 * unfortunately does during sched clock init when we swap over to TSC.
	 */
	if ((s64)delta < 0) {
		sa->last_runnable_update = now;
		return 0;
	}

	/*
	 * Use 1024ns as the unit of measurement since it's a reasonable
	 * approximation of 1us and fast to compute.
	 */
	delta >>= 10;
	if (!delta)
		return 0;
	sa->last_runnable_update = now;

	/* delta_w is the amount already accumulated against our next period */
	delta_w = sa->runnable_avg_period % 1024;
	if (delta + delta_w >= 1024) {
		/* period roll-over */
		decayed = 1;

		/*
		 * Now that we know we're crossing a period boundary, figure
		 * out how much from delta we need to complete the current
		 * period and accrue it.
		 */
		delta_w = 1024 - delta_w;
		if (runnable)
			sa->runnable_avg_sum += delta_w;
		sa->runnable_avg_period += delta_w;

		delta -= delta_w;

		/* Figure out how many additional periods this update spans */
		periods = delta / 1024;
		delta %= 1024;

		sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum,
						  periods + 1);
		sa->runnable_avg_period = decay_load(sa->runnable_avg_period,
						     periods + 1);

		/* Efficiently calculate \sum (1..n_period) 1024*y^i */
		runnable_contrib = __compute_runnable_contrib(periods);
		if (runnable)
			sa->runnable_avg_sum += runnable_contrib;
		sa->runnable_avg_period += runnable_contrib;
	}

	/* Remainder of delta accrued against u_0` */
	if (runnable)
		sa->runnable_avg_sum += delta;
	sa->runnable_avg_period += delta;

	return decayed;
}

/* Synchronize an entity's decay with its parenting cfs_rq.*/
static inline u64 __synchronize_entity_decay(struct sched_entity *se)
{
	struct cfs_rq *cfs_rq = cfs_rq_of(se);
	u64 decays = atomic64_read(&cfs_rq->decay_counter);

	decays -= se->avg.decay_count;
	if (!decays)
		return 0;

	se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays);
	se->avg.decay_count = 0;

	return decays;
}

#ifdef CONFIG_FAIR_GROUP_SCHED
static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
						 int force_update)
{
	struct task_group *tg = cfs_rq->tg;
	long tg_contrib;

	tg_contrib = cfs_rq->runnable_load_avg + cfs_rq->blocked_load_avg;
	tg_contrib -= cfs_rq->tg_load_contrib;

	if (force_update || abs(tg_contrib) > cfs_rq->tg_load_contrib / 8) {
		atomic_long_add(tg_contrib, &tg->load_avg);
		cfs_rq->tg_load_contrib += tg_contrib;
	}
}

/*
 * Aggregate cfs_rq runnable averages into an equivalent task_group
 * representation for computing load contributions.
 */
static inline void __update_tg_runnable_avg(struct sched_avg *sa,
						  struct cfs_rq *cfs_rq)
{
	struct task_group *tg = cfs_rq->tg;
	long contrib;

	/* The fraction of a cpu used by this cfs_rq */
	contrib = div_u64(sa->runnable_avg_sum << NICE_0_SHIFT,
			  sa->runnable_avg_period + 1);
	contrib -= cfs_rq->tg_runnable_contrib;

	if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) {
		atomic_add(contrib, &tg->runnable_avg);
		cfs_rq->tg_runnable_contrib += contrib;
	}
}

static inline void __update_group_entity_contrib(struct sched_entity *se)
{
	struct cfs_rq *cfs_rq = group_cfs_rq(se);
	struct task_group *tg = cfs_rq->tg;
	int runnable_avg;

	u64 contrib;

	contrib = cfs_rq->tg_load_contrib * tg->shares;
	se->avg.load_avg_contrib = div_u64(contrib,
				     atomic_long_read(&tg->load_avg) + 1);

	/*
	 * For group entities we need to compute a correction term in the case
	 * that they are consuming <1 cpu so that we would contribute the same
	 * load as a task of equal weight.
	 *
	 * Explicitly co-ordinating this measurement would be expensive, but
	 * fortunately the sum of each cpus contribution forms a usable
	 * lower-bound on the true value.
	 *
	 * Consider the aggregate of 2 contributions.  Either they are disjoint
	 * (and the sum represents true value) or they are disjoint and we are
	 * understating by the aggregate of their overlap.
	 *
	 * Extending this to N cpus, for a given overlap, the maximum amount we
	 * understand is then n_i(n_i+1)/2 * w_i where n_i is the number of
	 * cpus that overlap for this interval and w_i is the interval width.
	 *
	 * On a small machine; the first term is well-bounded which bounds the
	 * total error since w_i is a subset of the period.  Whereas on a
	 * larger machine, while this first term can be larger, if w_i is the
	 * of consequential size guaranteed to see n_i*w_i quickly converge to
	 * our upper bound of 1-cpu.
	 */
	runnable_avg = atomic_read(&tg->runnable_avg);
	if (runnable_avg < NICE_0_LOAD) {
		se->avg.load_avg_contrib *= runnable_avg;
		se->avg.load_avg_contrib >>= NICE_0_SHIFT;
	}
}
#else
static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
						 int force_update) {}
static inline void __update_tg_runnable_avg(struct sched_avg *sa,
						  struct cfs_rq *cfs_rq) {}
static inline void __update_group_entity_contrib(struct sched_entity *se) {}
#endif

static inline void __update_task_entity_contrib(struct sched_entity *se)
{
	u32 contrib;

	/* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */
	contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight);
	contrib /= (se->avg.runnable_avg_period + 1);
	se->avg.load_avg_contrib = scale_load(contrib);
}

/* Compute the current contribution to load_avg by se, return any delta */
static long __update_entity_load_avg_contrib(struct sched_entity *se)
{
	long old_contrib = se->avg.load_avg_contrib;

	if (entity_is_task(se)) {
		__update_task_entity_contrib(se);
	} else {
		__update_tg_runnable_avg(&se->avg, group_cfs_rq(se));
		__update_group_entity_contrib(se);
	}

	return se->avg.load_avg_contrib - old_contrib;
}

static inline void subtract_blocked_load_contrib(struct cfs_rq *cfs_rq,
						 long load_contrib)
{
	if (likely(load_contrib < cfs_rq->blocked_load_avg))
		cfs_rq->blocked_load_avg -= load_contrib;
	else
		cfs_rq->blocked_load_avg = 0;
}

static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);

/* Update a sched_entity's runnable average */
static inline void update_entity_load_avg(struct sched_entity *se,
					  int update_cfs_rq)
{
	struct cfs_rq *cfs_rq = cfs_rq_of(se);
	long contrib_delta;
	u64 now;

	/*
	 * For a group entity we need to use their owned cfs_rq_clock_task() in
	 * case they are the parent of a throttled hierarchy.
	 */
	if (entity_is_task(se))
		now = cfs_rq_clock_task(cfs_rq);
	else
		now = cfs_rq_clock_task(group_cfs_rq(se));

	if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq))
		return;

	contrib_delta = __update_entity_load_avg_contrib(se);

	if (!update_cfs_rq)
		return;

	if (se->on_rq)
		cfs_rq->runnable_load_avg += contrib_delta;
	else
		subtract_blocked_load_contrib(cfs_rq, -contrib_delta);
}

/*
 * Decay the load contributed by all blocked children and account this so that
 * their contribution may appropriately discounted when they wake up.
 */
static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
{
	u64 now = cfs_rq_clock_task(cfs_rq) >> 20;
	u64 decays;

	decays = now - cfs_rq->last_decay;
	if (!decays && !force_update)
		return;

	if (atomic_long_read(&cfs_rq->removed_load)) {
		unsigned long removed_load;
		removed_load = atomic_long_xchg(&cfs_rq->removed_load, 0);
		subtract_blocked_load_contrib(cfs_rq, removed_load);
	}

	if (decays) {
		cfs_rq->blocked_load_avg = decay_load(cfs_rq->blocked_load_avg,
						      decays);
		atomic64_add(decays, &cfs_rq->decay_counter);
		cfs_rq->last_decay = now;
	}

	__update_cfs_rq_tg_load_contrib(cfs_rq, force_update);
}

static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
{
	__update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
	__update_tg_runnable_avg(&rq->avg, &rq->cfs);
}

/* Add the load generated by se into cfs_rq's child load-average */
static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
						  struct sched_entity *se,
						  int wakeup)
{
	/*
	 * We track migrations using entity decay_count <= 0, on a wake-up
	 * migration we use a negative decay count to track the remote decays
	 * accumulated while sleeping.
	 *
	 * Newly forked tasks are enqueued with se->avg.decay_count == 0, they
	 * are seen by enqueue_entity_load_avg() as a migration with an already
	 * constructed load_avg_contrib.
	 */
	if (unlikely(se->avg.decay_count <= 0)) {
		se->avg.last_runnable_update = rq_clock_task(rq_of(cfs_rq));
		if (se->avg.decay_count) {
			/*
			 * In a wake-up migration we have to approximate the
			 * time sleeping.  This is because we can't synchronize
			 * clock_task between the two cpus, and it is not
			 * guaranteed to be read-safe.  Instead, we can
			 * approximate this using our carried decays, which are
			 * explicitly atomically readable.
			 */
			se->avg.last_runnable_update -= (-se->avg.decay_count)
							<< 20;
			update_entity_load_avg(se, 0);
			/* Indicate that we're now synchronized and on-rq */
			se->avg.decay_count = 0;
		}
		wakeup = 0;
	} else {
		/*
		 * Task re-woke on same cpu (or else migrate_task_rq_fair()
		 * would have made count negative); we must be careful to avoid
		 * double-accounting blocked time after synchronizing decays.
		 */
		se->avg.last_runnable_update += __synchronize_entity_decay(se)
							<< 20;
	}

	/* migrated tasks did not contribute to our blocked load */
	if (wakeup) {
		subtract_blocked_load_contrib(cfs_rq, se->avg.load_avg_contrib);
		update_entity_load_avg(se, 0);
	}

	cfs_rq->runnable_load_avg += se->avg.load_avg_contrib;
	/* we force update consideration on load-balancer moves */
	update_cfs_rq_blocked_load(cfs_rq, !wakeup);
}

/*
 * Remove se's load from this cfs_rq child load-average, if the entity is
 * transitioning to a blocked state we track its projected decay using
 * blocked_load_avg.
 */
static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
						  struct sched_entity *se,
						  int sleep)
{
	update_entity_load_avg(se, 1);
	/* we force update consideration on load-balancer moves */
	update_cfs_rq_blocked_load(cfs_rq, !sleep);

	cfs_rq->runnable_load_avg -= se->avg.load_avg_contrib;
	if (sleep) {
		cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
		se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
	} /* migrations, e.g. sleep=0 leave decay_count == 0 */
}

/*
 * Update the rq's load with the elapsed running time before entering
 * idle. if the last scheduled task is not a CFS task, idle_enter will
 * be the only way to update the runnable statistic.
 */
void idle_enter_fair(struct rq *this_rq)
{
	update_rq_runnable_avg(this_rq, 1);
}

/*
 * Update the rq's load with the elapsed idle time before a task is
 * scheduled. if the newly scheduled task is not a CFS task, idle_exit will
 * be the only way to update the runnable statistic.
 */
void idle_exit_fair(struct rq *this_rq)
{
	update_rq_runnable_avg(this_rq, 0);
}

#else
static inline void update_entity_load_avg(struct sched_entity *se,
					  int update_cfs_rq) {}
static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {}
static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
					   struct sched_entity *se,
					   int wakeup) {}
static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
					   struct sched_entity *se,
					   int sleep) {}
static inline void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq,
					      int force_update) {}
#endif

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_clock(rq_of(cfs_rq)) - 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_clock(rq_of(cfs_rq)) - 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);
			}

			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. */
	se->vruntime = max_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 calling 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);
	enqueue_entity_load_avg(cfs_rq, se, flags & ENQUEUE_WAKEUP);
	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 __always_inline 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);
	dequeue_entity_load_avg(cfs_rq, se, flags & DEQUEUE_SLEEP);

	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_clock(rq_of(cfs_rq));
			if (tsk->state & TASK_UNINTERRUPTIBLE)
				se->statistics.block_start = rq_clock(rq_of(cfs_rq));
		}
#endif
	}

	clear_buddies(cfs_rq, se);

	if (se != cfs_rq->curr)
		__dequeue_entity(cfs_rq, se);
	se->on_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);
		/* in !on_rq case, update occurred at dequeue */
		update_entity_load_avg(prev, 1);
	}
	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);

	/*
	 * Ensure that runnable average is periodically updated.
	 */
	update_entity_load_avg(curr, 1);
	update_cfs_rq_blocked_load(cfs_rq, 1);
	update_cfs_shares(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 static_key __cfs_bandwidth_used;

static inline bool cfs_bandwidth_used(void)
{
	return static_key_false(&__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)
		static_key_slow_inc(&__cfs_bandwidth_used);
	else if (!enabled && was_enabled)
		static_key_slow_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;
}

/* rq->task_clock normalized against any time this cfs_rq has spent throttled */
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
{
	if (unlikely(cfs_rq->throttle_count))
		return cfs_rq->throttled_clock_task;

	return rq_clock_task(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time;
}

/* 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);

	/* if the deadline is ahead of our clock, nothing to do */
	if (likely((s64)(rq_clock(rq_of(cfs_rq)) - 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) {
		/* adjust cfs_rq_clock_task() */
		cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
					     cfs_rq->throttled_clock_task;
	}
#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, stop time */
	if (!cfs_rq->throttle_count)
		cfs_rq->throttled_clock_task = rq_clock_task(rq);
	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))];

	/* freeze hierarchy runnable averages while throttled */
	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_clock = rq_clock(rq);
	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)];

	cfs_rq->throttled = 0;

	update_rq_clock(rq);

	raw_spin_lock(&cfs_b->lock);
	cfs_b->throttled_time += rq_clock(rq) - cfs_rq->throttled_clock;
	list_del_rcu(&cfs_rq->throttled_list);
	raw_spin_unlock(&cfs_b->lock);

	/* 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 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);
}

static void __maybe_unused 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 inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
{
	return rq_clock_task(rq_of(cfs_rq));
}

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 __always_inline 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) {}
static inline 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_shares(cfs_rq);
		update_entity_load_avg(se, 1);
	}

	if (!se) {
		update_rq_runnable_avg(rq, rq->nr_running);
		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_shares(cfs_rq);
		update_entity_load_avg(se, 1);
	}

	if (!se) {
		dec_nr_running(rq);
		update_rq_runnable_avg(rq, 1);
	}
	hrtick_update(rq);
}

#ifdef CONFIG_SMP
/* Used instead of source_load when we know the type == 0 */
static unsigned long weighted_cpuload(const int cpu)
{
	return cpu_rq(cpu)->cfs.runnable_load_avg;
}

/*
 * Return a low guess at the load of a migration-source cpu weighted
 * according to the scheduling class and "nice" value.
 *
 * We want to under-estimate the load of migration sources, to
 * balance conservatively.
 */
static unsigned long source_load(int cpu, int type)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long total = weighted_cpuload(cpu);

	if (type == 0 || !sched_feat(LB_BIAS))
		return total;

	return min(rq->cpu_load[type-1], total);
}

/*
 * Return a high guess at the load of a migration-target cpu weighted
 * according to the scheduling class and "nice" value.
 */
static unsigned long target_load(int cpu, int type)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long total = weighted_cpuload(cpu);

	if (type == 0 || !sched_feat(LB_BIAS))
		return total;

	return max(rq->cpu_load[type-1], total);
}

static unsigned long power_of(int cpu)
{
	return cpu_rq(cpu)->cpu_power;
}

static unsigned long cpu_avg_load_per_task(int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long nr_running = ACCESS_ONCE(rq->nr_running);
	unsigned long load_avg = rq->cfs.runnable_load_avg;

	if (nr_running)
		return load_avg / nr_running;

	return 0;
}

static void record_wakee(struct task_struct *p)
{
	/*
	 * Rough decay (wiping) for cost saving, don't worry
	 * about the boundary, really active task won't care
	 * about the loss.
	 */
	if (jiffies > current->wakee_flip_decay_ts + HZ) {
		current->wakee_flips = 0;
		current->wakee_flip_decay_ts = jiffies;
	}

	if (current->last_wakee != p) {
		current->last_wakee = p;
		current->wakee_flips++;
	}
}

static void task_waking_fair(struct task_struct *p)
{
	struct sched_entity *se = &p->se;
	struct cfs_rq *cfs_rq = cfs_rq_of(se);
	u64 min_vruntime;

#ifndef CONFIG_64BIT
	u64 min_vruntime_copy;

	do {
		min_vruntime_copy = cfs_rq->min_vruntime_copy;
		smp_rmb();
		min_vruntime = cfs_rq->min_vruntime;
	} while (min_vruntime != min_vruntime_copy);
#else
	min_vruntime = cfs_rq->min_vruntime;
#endif

	se->vruntime -= min_vruntime;
	record_wakee(p);
}

#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.
 *
 * Calculate the effective load difference if @wl is added (subtracted) to @tg
 * on this @cpu and results in a total addition (subtraction) of @wg to the
 * total group weight.
 *
 * Given a runqueue weight distribution (rw_i) we can compute a shares
 * distribution (s_i) using:
 *
 *   s_i = rw_i / \Sum rw_j						(1)
 *
 * Suppose we have 4 CPUs and our @tg is a direct child of the root group and
 * has 7 equal weight tasks, distributed as below (rw_i), with the resulting
 * shares distribution (s_i):
 *
 *   rw_i = {   2,   4,   1,   0 }
 *   s_i  = { 2/7, 4/7, 1/7,   0 }
 *
 * As per wake_affine() we're interested in the load of two CPUs (the CPU the
 * task used to run on and the CPU the waker is running on), we need to
 * compute the effect of waking a task on either CPU and, in case of a sync
 * wakeup, compute the effect of the current task going to sleep.
 *
 * So for a change of @wl to the local @cpu with an overall group weight change
 * of @wl we can compute the new shares distribution (s'_i) using:
 *
 *   s'_i = (rw_i + @wl) / (@wg + \Sum rw_j)				(2)
 *
 * Suppose we're interested in CPUs 0 and 1, and want to compute the load
 * differences in waking a task to CPU 0. The additional task changes the
 * weight and shares distributions like:
 *
 *   rw'_i = {   3,   4,   1,   0 }
 *   s'_i  = { 3/8, 4/8, 1/8,   0 }
 *
 * We can then compute the difference in effective weight by using:
 *
 *   dw_i = S * (s'_i - s_i)						(3)
 *
 * Where 'S' is the group weight as seen by its parent.
 *
 * Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7)
 * times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 -
 * 4/7) times the weight of the group.
 */
static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
{
	struct sched_entity *se = tg->se[cpu];

	if (!tg->parent || !wl)	/* the trivial, non-cgroup case */
		return wl;

	for_each_sched_entity(se) {
		long w, W;

		tg = se->my_q->tg;

		/*
		 * W = @wg + \Sum rw_j
		 */
		W = wg + calc_tg_weight(tg, se->my_q);

		/*
		 * w = rw_i + @wl
		 */
		w = se->my_q->load.weight + wl;

		/*
		 * wl = S * s'_i; see (2)
		 */
		if (W > 0 && w < W)
			wl = (w * tg->shares) / W;
		else
			wl = tg->shares;

		/*
		 * Per the above, wl is the new se->load.weight value; since
		 * those are clipped to [MIN_SHARES, ...) do so now. See
		 * calc_cfs_shares().
		 */
		if (wl < MIN_SHARES)
			wl = MIN_SHARES;

		/*
		 * wl = dw_i = S * (s'_i - s_i); see (3)
		 */
		wl -= se->load.weight;

		/*
		 * Recursively apply this logic to all parent groups to compute
		 * the final effective load change on the root group. Since
		 * only the @tg group gets extra weight, all parent groups can
		 * only redistribute existing shares. @wl is the shift in shares
		 * resulting from this level per the above.
		 */
		wg = 0;
	}

	return wl;
}
#else

static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
{
	return wl;
}

#endif

static int wake_wide(struct task_struct *p)
{
	int factor = this_cpu_read(sd_llc_size);

	/*
	 * Yeah, it's the switching-frequency, could means many wakee or
	 * rapidly switch, use factor here will just help to automatically
	 * adjust the loose-degree, so bigger node will lead to more pull.
	 */
	if (p->wakee_flips > factor) {
		/*
		 * wakee is somewhat hot, it needs certain amount of cpu
		 * resource, so if waker is far more hot, prefer to leave
		 * it alone.
		 */
		if (current->wakee_flips > (factor * p->wakee_flips))
			return 1;
	}

	return 0;
}

static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
{
	s64 this_load, load;
	int idx, this_cpu, prev_cpu;
	unsigned long tl_per_task;
	struct task_group *tg;
	unsigned long weight;
	int balanced;

	/*
	 * If we wake multiple tasks be careful to not bounce
	 * ourselves around too much.
	 */
	if (wake_wide(p))
		return 0;

	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:
	 */
	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 > 0) {
		s64 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;

	/*
	 * 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),
					tsk_cpus_allowed(p)))
			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_POWER_SCALE) / group->sgp->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), tsk_cpus_allowed(p)) {
		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)
{
	struct sched_domain *sd;
	struct sched_group *sg;
	int i = task_cpu(p);

	if (idle_cpu(target))
		return target;

	/*
	 * If the prevous cpu is cache affine and idle, don't be stupid.
	 */
	if (i != target && cpus_share_cache(i, target) && idle_cpu(i))
		return i;

	/*
	 * Otherwise, iterate the domains and find an elegible idle cpu.
	 */
	sd = rcu_dereference(per_cpu(sd_llc, target));
	for_each_lower_domain(sd) {
		sg = sd->groups;
		do {
			if (!cpumask_intersects(sched_group_cpus(sg),
						tsk_cpus_allowed(p)))
				goto next;

			for_each_cpu(i, sched_group_cpus(sg)) {
				if (i == target || !idle_cpu(i))
					goto next;
			}

			target = cpumask_first_and(sched_group_cpus(sg),
					tsk_cpus_allowed(p));
			goto done;
next:
			sg = sg->next;
		} while (sg != sd->groups);
	}
done:
	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 task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
{
	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
	int cpu = smp_processor_id();
	int new_cpu = cpu;
	int want_affine = 0;
	int sync = wake_flags & WF_SYNC;

	if (p->nr_cpus_allowed == 1)
		return prev_cpu;

	if (sd_flag & SD_BALANCE_WAKE) {
		if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
			want_affine = 1;
		new_cpu = prev_cpu;
	}

	rcu_read_lock();
	for_each_domain(cpu, tmp) {
		if (!(tmp->flags & SD_LOAD_BALANCE))
			continue;

		/*
		 * 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;
			break;
		}

		if (tmp->flags & sd_flag)
			sd = tmp;
	}

	if (affine_sd) {
		if (cpu != prev_cpu && wake_affine(affine_sd, p, sync))
			prev_cpu = cpu;

		new_cpu = select_idle_sibling(p, prev_cpu);
		goto unlock;
	}

	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 */
	}
unlock:
	rcu_read_unlock();

	return new_cpu;
}

/*
 * Called immediately before a task is migrated to a new cpu; task_cpu(p) and
 * cfs_rq_of(p) references at time of call are still valid and identify the
 * previous cpu.  However, the caller only guarantees p->pi_lock is held; no
 * other assumptions, including the state of rq->lock, should be made.
 */
static void
migrate_task_rq_fair(struct task_struct *p, int next_cpu)
{
	struct sched_entity *se = &p->se;
	struct cfs_rq *cfs_rq = cfs_rq_of(se);

	/*
	 * Load tracking: accumulate removed load so that it can be processed
	 * when we next update owning cfs_rq under rq->lock.  Tasks contribute
	 * to blocked load iff they have a positive decay-count.  It can never
	 * be negative here since on-rq tasks have decay-count == 0.
	 */
	if (se->avg.decay_count) {
		se->avg.decay_count = -__synchronize_entity_decay(se);
		atomic_long_add(se->avg.load_avg_contrib,
						&cfs_rq->removed_load);
	}
}
#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.
	 */
	return calc_delta_fair(gran, se);
}

/*
 * 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 (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
		return;

	for_each_sched_entity(se)
		cfs_rq_of(se)->last = se;
}

static void set_next_buddy(struct sched_entity *se)
{
	if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
		return;

	for_each_sched_entity(se)
		cfs_rq_of(se)->next = se;
}

static void set_skip_buddy(struct sched_entity *se)
{
	for_each_sched_entity(se)
		cfs_rq_of(se)->skip = 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;
	int next_buddy_marked = 0;

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

	/*
	 * This is possible from callers such as move_task(), in which we
	 * unconditionally check_prempt_curr() after an enqueue (which may have
	 * lead to a throttle).  This both saves work and prevents false
	 * next-buddy nomination below.
	 */
	if (unlikely(throttled_hierarchy(cfs_rq_of(pse))))
		return;

	if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) {
		set_next_buddy(pse);
		next_buddy_marked = 1;
	}

	/*
	 * We can come here with TIF_NEED_RESCHED already set from new task
	 * wake up path.
	 *
	 * Note: this also catches the edge-case of curr being in a throttled
	 * group (e.g. via set_curr_task), since update_curr() (in the
	 * enqueue of curr) will have resulted in resched being set.  This
	 * prevents us from potentially nominating it as a false LAST_BUDDY
	 * below.
	 */
	if (test_tsk_need_resched(curr))
		return;

	/* Idle tasks are by definition preempted by non-idle tasks. */
	if (unlikely(curr->policy == SCHED_IDLE) &&
	    likely(p->policy != SCHED_IDLE))
		goto preempt;

	/*
	 * Batch and idle tasks do not preempt non-idle tasks (their preemption
	 * is driven by the tick):
	 */
	if (unlikely(p->policy != SCHED_NORMAL) || !sched_feat(WAKEUP_PREEMPTION))
		return;

	find_matching_se(&se, &pse);
	update_curr(cfs_rq_of(se));
	BUG_ON(!pse);
	if (wakeup_preempt_entity(se, pse) == 1) {
		/*
		 * Bias pick_next to pick the sched entity that is
		 * triggering this preemption.
		 */
		if (!next_buddy_marked)
			set_next_buddy(pse);
		goto preempt;
	}

	return;

preempt:
	resched_task(curr);
	/*
	 * Only set the backward buddy when the current task is still
	 * on the rq. This can happen when a wakeup gets interleaved
	 * with schedule on the ->pre_schedule() or idle_balance()
	 * point, either of which can * drop the rq lock.
	 *
	 * Also, during early boot the idle thread is in the fair class,
	 * for obvious reasons its a bad idea to schedule back to it.
	 */
	if (unlikely(!se->on_rq || curr == rq->idle))
		return;

	if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
		set_last_buddy(se);
}

static struct task_struct *pick_next_task_fair(struct rq *rq)
{
	struct task_struct *p;
	struct cfs_rq *cfs_rq = &rq->cfs;
	struct sched_entity *se;

	if (!cfs_rq->nr_running)
		return NULL;

	do {
		se = pick_next_entity(cfs_rq);
		set_next_entity(cfs_rq, se);
		cfs_rq = group_cfs_rq(se);
	} while (cfs_rq);

	p = task_of(se);
	if (hrtick_enabled(rq))
		hrtick_start_fair(rq, p);

	return p;
}

/*
 * Account for a descheduled task:
 */
static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
{
	struct sched_entity *se = &prev->se;
	struct cfs_rq *cfs_rq;

	for_each_sched_entity(se) {
		cfs_rq = cfs_rq_of(se);
		put_prev_entity(cfs_rq, se);
	}
}

/*
 * sched_yield() is very simple
 *
 * The magic of dealing with the ->skip buddy is in pick_next_entity.
 */
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 *se = &curr->se;

	/*
	 * Are we the only task in the tree?
	 */
	if (unlikely(rq->nr_running == 1))
		return;

	clear_buddies(cfs_rq, se);

	if (curr->policy != SCHED_BATCH) {
		update_rq_clock(rq);
		/*
		 * Update run-time statistics of the 'current'.
		 */
		update_curr(cfs_rq);
		/*
		 * Tell update_rq_clock() that we've just updated,
		 * so we don't do microscopic update in schedule()
		 * and double the fastpath cost.
		 */
		 rq->skip_clock_update = 1;
	}

	set_skip_buddy(se);
}

static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt)
{
	struct sched_entity *se = &p->se;

	/* throttled hierarchies are not runnable */
	if (!se->on_rq || throttled_hierarchy(cfs_rq_of(se)))
		return false;

	/* Tell the scheduler that we'd really like pse to run next. */
	set_next_buddy(se);

	yield_task_fair(rq);

	return true;
}

#ifdef CONFIG_SMP
/**************************************************
 * Fair scheduling class load-balancing methods.
 *
 * BASICS
 *
 * The purpose of load-balancing is to achieve the same basic fairness the
 * per-cpu scheduler provides, namely provide a proportional amount of compute
 * time to each task. This is expressed in the following equation:
 *
 *   W_i,n/P_i == W_j,n/P_j for all i,j                               (1)
 *
 * Where W_i,n is the n-th weight average for cpu i. The instantaneous weight
 * W_i,0 is defined as:
 *
 *   W_i,0 = \Sum_j w_i,j                                             (2)
 *
 * Where w_i,j is the weight of the j-th runnable task on cpu i. This weight
 * is derived from the nice value as per prio_to_weight[].
 *
 * The weight average is an exponential decay average of the instantaneous
 * weight:
 *
 *   W'_i,n = (2^n - 1) / 2^n * W_i,n + 1 / 2^n * W_i,0               (3)
 *
 * P_i is the cpu power (or compute capacity) of cpu i, typically it is the
 * fraction of 'recent' time available for SCHED_OTHER task execution. But it
 * can also include other factors [XXX].
 *
 * To achieve this balance we define a measure of imbalance which follows
 * directly from (1):
 *
 *   imb_i,j = max{ avg(W/P), W_i/P_i } - min{ avg(W/P), W_j/P_j }    (4)
 *
 * We them move tasks around to minimize the imbalance. In the continuous
 * function space it is obvious this converges, in the discrete case we get
 * a few fun cases generally called infeasible weight scenarios.
 *
 * [XXX expand on:
 *     - infeasible weights;
 *     - local vs global optima in the discrete case. ]
 *
 *
 * SCHED DOMAINS
 *
 * In order to solve the imbalance equation (4), and avoid the obvious O(n^2)
 * for all i,j solution, we create a tree of cpus that follows the hardware
 * topology where each level pairs two lower groups (or better). This results
 * in O(log n) layers. Furthermore we reduce the number of cpus going up the
 * tree to only the first of the previous level and we decrease the frequency
 * of load-balance at each level inv. proportional to the number of cpus in
 * the groups.
 *
 * This yields:
 *
 *     log_2 n     1     n
 *   \Sum       { --- * --- * 2^i } = O(n)                            (5)
 *     i = 0      2^i   2^i
 *                               `- size of each group
 *         |         |     `- number of cpus doing load-balance
 *         |         `- freq
 *         `- sum over all levels
 *
 * Coupled with a limit on how many tasks we can migrate every balance pass,
 * this makes (5) the runtime complexity of the balancer.
 *
 * An important property here is that each CPU is still (indirectly) connected
 * to every other cpu in at most O(log n) steps:
 *
 * The adjacency matrix of the resulting graph is given by:
 *
 *             log_2 n     
 *   A_i,j = \Union     (i % 2^k == 0) && i / 2^(k+1) == j / 2^(k+1)  (6)
 *             k = 0
 *
 * And you'll find that:
 *
 *   A^(log_2 n)_i,j != 0  for all i,j                                (7)
 *
 * Showing there's indeed a path between every cpu in at most O(log n) steps.
 * The task movement gives a factor of O(m), giving a convergence complexity
 * of:
 *
 *   O(nm log n),  n := nr_cpus, m := nr_tasks                        (8)
 *
 *
 * WORK CONSERVING
 *
 * In order to avoid CPUs going idle while there's still work to do, new idle
 * balancing is more aggressive and has the newly idle cpu iterate up the domain
 * tree itself instead of relying on other CPUs to bring it work.
 *
 * This adds some complexity to both (5) and (8) but it reduces the total idle
 * time.
 *
 * [XXX more?]
 *
 *
 * CGROUPS
 *
 * Cgroups make a horror show out of (2), instead of a simple sum we get:
 *
 *                                s_k,i
 *   W_i,0 = \Sum_j \Prod_k w_k * -----                               (9)
 *                                 S_k
 *
 * Where
 *
 *   s_k,i = \Sum_j w_i,j,k  and  S_k = \Sum_i s_k,i                 (10)
 *
 * w_i,j,k is the weight of the j-th runnable task in the k-th cgroup on cpu i.
 *
 * The big problem is S_k, its a global sum needed to compute a local (W_i)
 * property.
 *
 * [XXX write more on how we solve this.. _after_ merging pjt's patches that
 *      rewrite all of this once again.]
 */ 

static unsigned long __read_mostly max_load_balance_interval = HZ/10;

#define LBF_ALL_PINNED	0x01
#define LBF_NEED_BREAK	0x02
#define LBF_DST_PINNED  0x04
#define LBF_SOME_PINNED	0x08

struct lb_env {
	struct sched_domain	*sd;

	struct rq		*src_rq;
	int			src_cpu;

	int			dst_cpu;
	struct rq		*dst_rq;

	struct cpumask		*dst_grpmask;
	int			new_dst_cpu;
	enum cpu_idle_type	idle;
	long			imbalance;
	/* The set of CPUs under consideration for load-balancing */
	struct cpumask		*cpus;

	unsigned int		flags;

	unsigned int		loop;
	unsigned int		loop_break;
	unsigned int		loop_max;
};

/*
 * move_task - move a task from one runqueue to another runqueue.
 * Both runqueues must be locked.
 */
static void move_task(struct task_struct *p, struct lb_env *env)
{
	deactivate_task(env->src_rq, p, 0);
	set_task_cpu(p, env->dst_cpu);
	activate_task(env->dst_rq, p, 0);
	check_preempt_curr(env->dst_rq, p, 0);
#ifdef CONFIG_NUMA_BALANCING
	if (p->numa_preferred_nid != -1) {
		int src_nid = cpu_to_node(env->src_cpu);
		int dst_nid = cpu_to_node(env->dst_cpu);

		/*
		 * If the load balancer has moved the task then limit
		 * migrations from taking place in the short term in
		 * case this is a short-lived migration.
		 */
		if (src_nid != dst_nid && dst_nid != p->numa_preferred_nid)
			p->numa_migrate_seq = 0;
	}
#endif
}

/*
 * Is this task likely cache-hot:
 */
static int
task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
{
	s64 delta;

	if (p->sched_class != &fair_sched_class)
		return 0;

	if (unlikely(p->policy == SCHED_IDLE))
		return 0;

	/*
	 * Buddy candidates are cache hot:
	 */
	if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
			(&p->se == cfs_rq_of(&p->se)->next ||
			 &p->se == cfs_rq_of(&p->se)->last))
		return 1;

	if (sysctl_sched_migration_cost == -1)
		return 1;
	if (sysctl_sched_migration_cost == 0)
		return 0;

	delta = now - p->se.exec_start;

	return delta < (s64)sysctl_sched_migration_cost;
}

#ifdef CONFIG_NUMA_BALANCING
/* Returns true if the destination node has incurred more faults */
static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
{
	int src_nid, dst_nid;

	if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
	    !(env->sd->flags & SD_NUMA)) {
		return false;
	}

	src_nid = cpu_to_node(env->src_cpu);
	dst_nid = cpu_to_node(env->dst_cpu);

	if (src_nid == dst_nid)
		return false;

	/* Always encourage migration to the preferred node. */
	if (dst_nid == p->numa_preferred_nid)
		return true;

	/* If both task and group weight improve, this move is a winner. */
	if (task_weight(p, dst_nid) > task_weight(p, src_nid) &&
	    group_weight(p, dst_nid) > group_weight(p, src_nid))
		return true;

	return false;
}


static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
{
	int src_nid, dst_nid;

	if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
		return false;

	if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
		return false;

	src_nid = cpu_to_node(env->src_cpu);
	dst_nid = cpu_to_node(env->dst_cpu);

	if (src_nid == dst_nid)
		return false;

	/* Migrating away from the preferred node is always bad. */
	if (src_nid == p->numa_preferred_nid)
		return true;

	/* If either task or group weight get worse, don't do it. */
	if (task_weight(p, dst_nid) < task_weight(p, src_nid) ||
	    group_weight(p, dst_nid) < group_weight(p, src_nid))
		return true;

	return false;
}

#else
static inline bool migrate_improves_locality(struct task_struct *p,
					     struct lb_env *env)
{
	return false;
}

static inline bool migrate_degrades_locality(struct task_struct *p,
					     struct lb_env *env)
{
	return false;
}
#endif

/*
 * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
 */
static
int can_migrate_task(struct task_struct *p, struct lb_env *env)
{
	int tsk_cache_hot = 0;
	/*
	 * We do not migrate tasks that are:
	 * 1) throttled_lb_pair, or
	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
	 * 3) running (obviously), or
	 * 4) are cache-hot on their current CPU.
	 */
	if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
		return 0;

	if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) {
		int cpu;

		schedstat_inc(p, se.statistics.nr_failed_migrations_affine);

		env->flags |= LBF_SOME_PINNED;

		/*
		 * Remember if this task can be migrated to any other cpu in
		 * our sched_group. We may want to revisit it if we couldn't
		 * meet load balance goals by pulling other tasks on src_cpu.
		 *
		 * Also avoid computing new_dst_cpu if we have already computed
		 * one in current iteration.
		 */
		if (!env->dst_grpmask || (env->flags & LBF_DST_PINNED))
			return 0;

		/* Prevent to re-select dst_cpu via env's cpus */
		for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) {
			if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) {
				env->flags |= LBF_DST_PINNED;
				env->new_dst_cpu = cpu;
				break;
			}
		}

		return 0;
	}

	/* Record that we found atleast one task that could run on dst_cpu */
	env->flags &= ~LBF_ALL_PINNED;

	if (task_running(env->src_rq, p)) {
		schedstat_inc(p, se.statistics.nr_failed_migrations_running);
		return 0;
	}

	/*
	 * Aggressive migration if:
	 * 1) destination numa is preferred
	 * 2) task is cache cold, or
	 * 3) too many balance attempts have failed.
	 */
	tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd);
	if (!tsk_cache_hot)
		tsk_cache_hot = migrate_degrades_locality(p, env);

	if (migrate_improves_locality(p, env)) {
#ifdef CONFIG_SCHEDSTATS
		if (tsk_cache_hot) {
			schedstat_inc(env->sd, lb_hot_gained[env->idle]);
			schedstat_inc(p, se.statistics.nr_forced_migrations);
		}
#endif
		return 1;
	}

	if (!tsk_cache_hot ||
		env->sd->nr_balance_failed > env->sd->cache_nice_tries) {

		if (tsk_cache_hot) {
			schedstat_inc(env->sd, lb_hot_gained[env->idle]);
			schedstat_inc(p, se.statistics.nr_forced_migrations);
		}

		return 1;
	}

	schedstat_inc(p, se.statistics.nr_failed_migrations_hot);
	return 0;
}

/*
 * move_one_task tries to move exactly one task from busiest to this_rq, as
 * part of active balancing operations within "domain".
 * Returns 1 if successful and 0 otherwise.
 *
 * Called with both runqueues locked.
 */
static int move_one_task(struct lb_env *env)
{
	struct task_struct *p, *n;

	list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) {
		if (!can_migrate_task(p, env))
			continue;

		move_task(p, env);
		/*
		 * Right now, this is only the second place move_task()
		 * is called, so we can safely collect move_task()
		 * stats here rather than inside move_task().
		 */
		schedstat_inc(env->sd, lb_gained[env->idle]);
		return 1;
	}
	return 0;
}

static const unsigned int sched_nr_migrate_break = 32;

/*
 * move_tasks tries to move up to imbalance weighted load from busiest to
 * this_rq, as part of a balancing operation within domain "sd".
 * Returns 1 if successful and 0 otherwise.
 *
 * Called with both runqueues locked.
 */
static int move_tasks(struct lb_env *env)
{
	struct list_head *tasks = &env->src_rq->cfs_tasks;
	struct task_struct *p;
	unsigned long load;
	int pulled = 0;

	if (env->imbalance <= 0)
		return 0;

	while (!list_empty(tasks)) {
		p = list_first_entry(tasks, struct task_struct, se.group_node);

		env->loop++;
		/* We've more or less seen every task there is, call it quits */
		if (env->loop > env->loop_max)
			break;

		/* take a breather every nr_migrate tasks */
		if (env->loop > env->loop_break) {
			env->loop_break += sched_nr_migrate_break;
			env->flags |= LBF_NEED_BREAK;
			break;
		}

		if (!can_migrate_task(p, env))
			goto next;

		load = task_h_load(p);

		if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
			goto next;

		if ((load / 2) > env->imbalance)
			goto next;

		move_task(p, env);
		pulled++;
		env->imbalance -= load;

#ifdef CONFIG_PREEMPT
		/*
		 * NEWIDLE balancing is a source of latency, so preemptible
		 * kernels will stop after the first task is pulled to minimize
		 * the critical section.
		 */
		if (env->idle == CPU_NEWLY_IDLE)
			break;
#endif

		/*
		 * We only want to steal up to the prescribed amount of
		 * weighted load.
		 */
		if (env->imbalance <= 0)
			break;

		continue;
next:
		list_move_tail(&p->se.group_node, tasks);
	}

	/*
	 * Right now, this is one of only two places move_task() is called,
	 * so we can safely collect move_task() stats here rather than
	 * inside move_task().
	 */
	schedstat_add(env->sd, lb_gained[env->idle], pulled);

	return pulled;
}

#ifdef CONFIG_FAIR_GROUP_SCHED
/*
 * update tg->load_weight by folding this cpu's load_avg
 */
static void __update_blocked_averages_cpu(struct task_group *tg, int cpu)
{
	struct sched_entity *se = tg->se[cpu];
	struct cfs_rq *cfs_rq = tg->cfs_rq[cpu];

	/* throttled entities do not contribute to load */
	if (throttled_hierarchy(cfs_rq))
		return;

	update_cfs_rq_blocked_load(cfs_rq, 1);

	if (se) {
		update_entity_load_avg(se, 1);
		/*
		 * We pivot on our runnable average having decayed to zero for
		 * list removal.  This generally implies that all our children
		 * have also been removed (modulo rounding error or bandwidth
		 * control); however, such cases are rare and we can fix these
		 * at enqueue.
		 *
		 * TODO: fix up out-of-order children on enqueue.
		 */
		if (!se->avg.runnable_avg_sum && !cfs_rq->nr_running)
			list_del_leaf_cfs_rq(cfs_rq);
	} else {
		struct rq *rq = rq_of(cfs_rq);
		update_rq_runnable_avg(rq, rq->nr_running);
	}
}

static void update_blocked_averages(int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	struct cfs_rq *cfs_rq;
	unsigned long flags;

	raw_spin_lock_irqsave(&rq->lock, flags);
	update_rq_clock(rq);
	/*
	 * Iterates the task_group tree in a bottom up fashion, see
	 * list_add_leaf_cfs_rq() for details.
	 */
	for_each_leaf_cfs_rq(rq, cfs_rq) {
		/*
		 * Note: We may want to consider periodically releasing
		 * rq->lock about these updates so that creating many task
		 * groups does not result in continually extending hold time.
		 */
		__update_blocked_averages_cpu(cfs_rq->tg, rq->cpu);
	}

	raw_spin_unlock_irqrestore(&rq->lock, flags);
}

/*
 * Compute the hierarchical load factor for cfs_rq and all its ascendants.
 * This needs to be done in a top-down fashion because the load of a child
 * group is a fraction of its parents load.
 */
static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
{
	struct rq *rq = rq_of(cfs_rq);
	struct sched_entity *se = cfs_rq->tg->se[cpu_of(rq)];
	unsigned long now = jiffies;
	unsigned long load;

	if (cfs_rq->last_h_load_update == now)
		return;

	cfs_rq->h_load_next = NULL;
	for_each_sched_entity(se) {
		cfs_rq = cfs_rq_of(se);
		cfs_rq->h_load_next = se;
		if (cfs_rq->last_h_load_update == now)
			break;
	}

	if (!se) {
		cfs_rq->h_load = cfs_rq->runnable_load_avg;
		cfs_rq->last_h_load_update = now;
	}

	while ((se = cfs_rq->h_load_next) != NULL) {
		load = cfs_rq->h_load;
		load = div64_ul(load * se->avg.load_avg_contrib,
				cfs_rq->runnable_load_avg + 1);
		cfs_rq = group_cfs_rq(se);
		cfs_rq->h_load = load;
		cfs_rq->last_h_load_update = now;
	}
}

static unsigned long task_h_load(struct task_struct *p)
{
	struct cfs_rq *cfs_rq = task_cfs_rq(p);

	update_cfs_rq_h_load(cfs_rq);
	return div64_ul(p->se.avg.load_avg_contrib * cfs_rq->h_load,
			cfs_rq->runnable_load_avg + 1);
}
#else
static inline void update_blocked_averages(int cpu)
{
}

static unsigned long task_h_load(struct task_struct *p)
{
	return p->se.avg.load_avg_contrib;
}
#endif

/********** Helpers for find_busiest_group ************************/
/*
 * sg_lb_stats - stats of a sched_group required for load_balancing
 */
struct sg_lb_stats {
	unsigned long avg_load; /*Avg load across the CPUs of the group */
	unsigned long group_load; /* Total load over the CPUs of the group */
	unsigned long sum_weighted_load; /* Weighted load of group's tasks */
	unsigned long load_per_task;
	unsigned long group_power;
	unsigned int sum_nr_running; /* Nr tasks running in the group */
	unsigned int group_capacity;
	unsigned int idle_cpus;
	unsigned int group_weight;
	int group_imb; /* Is there an imbalance in the group ? */
	int group_has_capacity; /* Is there extra capacity in the group? */
};

/*
 * sd_lb_stats - Structure to store the statistics of a sched_domain
 *		 during load balancing.
 */
struct sd_lb_stats {
	struct sched_group *busiest;	/* Busiest group in this sd */
	struct sched_group *local;	/* Local group in this sd */
	unsigned long total_load;	/* Total load of all groups in sd */
	unsigned long total_pwr;	/* Total power of all groups in sd */
	unsigned long avg_load;	/* Average load across all groups in sd */

	struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */
	struct sg_lb_stats local_stat;	/* Statistics of the local group */
};

static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
{
	/*
	 * Skimp on the clearing to avoid duplicate work. We can avoid clearing
	 * local_stat because update_sg_lb_stats() does a full clear/assignment.
	 * We must however clear busiest_stat::avg_load because
	 * update_sd_pick_busiest() reads this before assignment.
	 */
	*sds = (struct sd_lb_stats){
		.busiest = NULL,
		.local = NULL,
		.total_load = 0UL,
		.total_pwr = 0UL,
		.busiest_stat = {
			.avg_load = 0UL,
		},
	};
}

/**
 * get_sd_load_idx - Obtain the load index for a given sched domain.
 * @sd: The sched_domain whose load_idx is to be obtained.
 * @idle: The Idle status of the CPU for whose sd load_icx is obtained.
 *
 * Return: The load index.
 */
static inline int get_sd_load_idx(struct sched_domain *sd,
					enum cpu_idle_type idle)
{
	int load_idx;

	switch (idle) {
	case CPU_NOT_IDLE:
		load_idx = sd->busy_idx;
		break;

	case CPU_NEWLY_IDLE:
		load_idx = sd->newidle_idx;
		break;
	default:
		load_idx = sd->idle_idx;
		break;
	}

	return load_idx;
}

static unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu)
{
	return SCHED_POWER_SCALE;
}

unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu)
{
	return default_scale_freq_power(sd, cpu);
}

static unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu)
{
	unsigned long weight = sd->span_weight;
	unsigned long smt_gain = sd->smt_gain;

	smt_gain /= weight;

	return smt_gain;
}

unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
{
	return default_scale_smt_power(sd, cpu);
}

static unsigned long scale_rt_power(int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	u64 total, available, age_stamp, avg;

	/*
	 * Since we're reading these variables without serialization make sure
	 * we read them once before doing sanity checks on them.
	 */
	age_stamp = ACCESS_ONCE(rq->age_stamp);
	avg = ACCESS_ONCE(rq->rt_avg);

	total = sched_avg_period() + (rq_clock(rq) - age_stamp);

	if (unlikely(total < avg)) {
		/* Ensures that power won't end up being negative */
		available = 0;
	} else {
		available = total - avg;
	}

	if (unlikely((s64)total < SCHED_POWER_SCALE))
		total = SCHED_POWER_SCALE;

	total >>= SCHED_POWER_SHIFT;

	return div_u64(available, total);
}

static void update_cpu_power(struct sched_domain *sd, int cpu)
{
	unsigned long weight = sd->span_weight;
	unsigned long power = SCHED_POWER_SCALE;
	struct sched_group *sdg = sd->groups;

	if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
		if (sched_feat(ARCH_POWER))
			power *= arch_scale_smt_power(sd, cpu);
		else
			power *= default_scale_smt_power(sd, cpu);

		power >>= SCHED_POWER_SHIFT;
	}

	sdg->sgp->power_orig = power;

	if (sched_feat(ARCH_POWER))
		power *= arch_scale_freq_power(sd, cpu);
	else
		power *= default_scale_freq_power(sd, cpu);

	power >>= SCHED_POWER_SHIFT;

	power *= scale_rt_power(cpu);
	power >>= SCHED_POWER_SHIFT;

	if (!power)
		power = 1;

	cpu_rq(cpu)->cpu_power = power;
	sdg->sgp->power = power;
}

void update_group_power(struct sched_domain *sd, int cpu)
{
	struct sched_domain *child = sd->child;
	struct sched_group *group, *sdg = sd->groups;
	unsigned long power, power_orig;
	unsigned long interval;

	interval = msecs_to_jiffies(sd->balance_interval);
	interval = clamp(interval, 1UL, max_load_balance_interval);
	sdg->sgp->next_update = jiffies + interval;

	if (!child) {
		update_cpu_power(sd, cpu);
		return;
	}

	power_orig = power = 0;

	if (child->flags & SD_OVERLAP) {
		/*
		 * SD_OVERLAP domains cannot assume that child groups
		 * span the current group.
		 */

		for_each_cpu(cpu, sched_group_cpus(sdg)) {
			struct sched_group *sg = cpu_rq(cpu)->sd->groups;

			power_orig += sg->sgp->power_orig;
			power += sg->sgp->power;
		}
	} else  {
		/*
		 * !SD_OVERLAP domains can assume that child groups
		 * span the current group.
		 */ 

		group = child->groups;
		do {
			power_orig += group->sgp->power_orig;
			power += group->sgp->power;
			group = group->next;
		} while (group != child->groups);
	}

	sdg->sgp->power_orig = power_orig;
	sdg->sgp->power = power;
}

/*
 * Try and fix up capacity for tiny siblings, this is needed when
 * things like SD_ASYM_PACKING need f_b_g to select another sibling
 * which on its own isn't powerful enough.
 *
 * See update_sd_pick_busiest() and check_asym_packing().
 */
static inline int
fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
{
	/*
	 * Only siblings can have significantly less than SCHED_POWER_SCALE
	 */
	if (!(sd->flags & SD_SHARE_CPUPOWER))
		return 0;

	/*
	 * If ~90% of the cpu_power is still there, we're good.
	 */
	if (group->sgp->power * 32 > group->sgp->power_orig * 29)
		return 1;

	return 0;
}

/*
 * Group imbalance indicates (and tries to solve) the problem where balancing
 * groups is inadequate due to tsk_cpus_allowed() constraints.
 *
 * Imagine a situation of two groups of 4 cpus each and 4 tasks each with a
 * cpumask covering 1 cpu of the first group and 3 cpus of the second group.
 * Something like:
 *
 * 	{ 0 1 2 3 } { 4 5 6 7 }
 * 	        *     * * *
 *
 * If we were to balance group-wise we'd place two tasks in the first group and
 * two tasks in the second group. Clearly this is undesired as it will overload
 * cpu 3 and leave one of the cpus in the second group unused.
 *
 * The current solution to this issue is detecting the skew in the first group
 * by noticing the lower domain failed to reach balance and had difficulty
 * moving tasks due to affinity constraints.
 *
 * When this is so detected; this group becomes a candidate for busiest; see
 * update_sd_pick_busiest(). And calculcate_imbalance() and
 * find_busiest_group() avoid some of the usual balance conditions to allow it
 * to create an effective group imbalance.
 *
 * This is a somewhat tricky proposition since the next run might not find the
 * group imbalance and decide the groups need to be balanced again. A most
 * subtle and fragile situation.
 */

static inline int sg_imbalanced(struct sched_group *group)
{
	return group->sgp->imbalance;
}

/*
 * Compute the group capacity.
 *
 * Avoid the issue where N*frac(smt_power) >= 1 creates 'phantom' cores by
 * first dividing out the smt factor and computing the actual number of cores
 * and limit power unit capacity with that.
 */
static inline int sg_capacity(struct lb_env *env, struct sched_group *group)
{
	unsigned int capacity, smt, cpus;
	unsigned int power, power_orig;

	power = group->sgp->power;
	power_orig = group->sgp->power_orig;
	cpus = group->group_weight;

	/* smt := ceil(cpus / power), assumes: 1 < smt_power < 2 */
	smt = DIV_ROUND_UP(SCHED_POWER_SCALE * cpus, power_orig);
	capacity = cpus / smt; /* cores */

	capacity = min_t(unsigned, capacity, DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE));
	if (!capacity)
		capacity = fix_small_capacity(env->sd, group);

	return capacity;
}

/**
 * update_sg_lb_stats - Update sched_group's statistics for load balancing.
 * @env: The load balancing environment.
 * @group: sched_group whose statistics are to be updated.
 * @load_idx: Load index of sched_domain of this_cpu for load calc.
 * @local_group: Does group contain this_cpu.
 * @sgs: variable to hold the statistics for this group.
 */
static inline void update_sg_lb_stats(struct lb_env *env,
			struct sched_group *group, int load_idx,
			int local_group, struct sg_lb_stats *sgs)
{
	unsigned long nr_running;
	unsigned long load;
	int i;

	memset(sgs, 0, sizeof(*sgs));

	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
		struct rq *rq = cpu_rq(i);

		nr_running = rq->nr_running;

		/* Bias balancing toward cpus of our domain */
		if (local_group)
			load = target_load(i, load_idx);
		else
			load = source_load(i, load_idx);

		sgs->group_load += load;
		sgs->sum_nr_running += nr_running;
		sgs->sum_weighted_load += weighted_cpuload(i);
		if (idle_cpu(i))
			sgs->idle_cpus++;
	}

	/* Adjust by relative CPU power of the group */
	sgs->group_power = group->sgp->power;
	sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / sgs->group_power;

	if (sgs->sum_nr_running)
		sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;

	sgs->group_weight = group->group_weight;

	sgs->group_imb = sg_imbalanced(group);
	sgs->group_capacity = sg_capacity(env, group);

	if (sgs->group_capacity > sgs->sum_nr_running)
		sgs->group_has_capacity = 1;
}

/**
 * update_sd_pick_busiest - return 1 on busiest group
 * @env: The load balancing environment.
 * @sds: sched_domain statistics
 * @sg: sched_group candidate to be checked for being the busiest
 * @sgs: sched_group statistics
 *
 * Determine if @sg is a busier group than the previously selected
 * busiest group.
 *
 * Return: %true if @sg is a busier group than the previously selected
 * busiest group. %false otherwise.
 */
static bool update_sd_pick_busiest(struct lb_env *env,
				   struct sd_lb_stats *sds,
				   struct sched_group *sg,
				   struct sg_lb_stats *sgs)
{
	if (sgs->avg_load <= sds->busiest_stat.avg_load)
		return false;

	if (sgs->sum_nr_running > sgs->group_capacity)
		return true;

	if (sgs->group_imb)
		return true;

	/*
	 * ASYM_PACKING needs to move all the work to the lowest
	 * numbered CPUs in the group, therefore mark all groups
	 * higher than ourself as busy.
	 */
	if ((env->sd->flags & SD_ASYM_PACKING) && sgs->sum_nr_running &&
	    env->dst_cpu < group_first_cpu(sg)) {
		if (!sds->busiest)
			return true;

		if (group_first_cpu(sds->busiest) > group_first_cpu(sg))
			return true;
	}

	return false;
}

/**
 * update_sd_lb_stats - Update sched_domain's statistics for load balancing.
 * @env: The load balancing environment.
 * @balance: Should we balance.
 * @sds: variable to hold the statistics for this sched_domain.
 */
static inline void update_sd_lb_stats(struct lb_env *env,
					struct sd_lb_stats *sds)
{
	struct sched_domain *child = env->sd->child;
	struct sched_group *sg = env->sd->groups;
	struct sg_lb_stats tmp_sgs;
	int load_idx, prefer_sibling = 0;

	if (child && child->flags & SD_PREFER_SIBLING)
		prefer_sibling = 1;

	load_idx = get_sd_load_idx(env->sd, env->idle);

	do {
		struct sg_lb_stats *sgs = &tmp_sgs;
		int local_group;

		local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
		if (local_group) {
			sds->local = sg;
			sgs = &sds->local_stat;

			if (env->idle != CPU_NEWLY_IDLE ||
			    time_after_eq(jiffies, sg->sgp->next_update))
				update_group_power(env->sd, env->dst_cpu);
		}

		update_sg_lb_stats(env, sg, load_idx, local_group, sgs);

		if (local_group)
			goto next_group;

		/*
		 * In case the child domain prefers tasks go to siblings
		 * first, lower the sg capacity to one so that we'll try
		 * and move all the excess tasks away. We lower the capacity
		 * of a group only if the local group has the capacity to fit
		 * these excess tasks, i.e. nr_running < group_capacity. The
		 * extra check prevents the case where you always pull from the
		 * heaviest group when it is already under-utilized (possible
		 * with a large weight task outweighs the tasks on the system).
		 */
		if (prefer_sibling && sds->local &&
		    sds->local_stat.group_has_capacity)
			sgs->group_capacity = min(sgs->group_capacity, 1U);

		if (update_sd_pick_busiest(env, sds, sg, sgs)) {
			sds->busiest = sg;
			sds->busiest_stat = *sgs;
		}

next_group:
		/* Now, start updating sd_lb_stats */
		sds->total_load += sgs->group_load;
		sds->total_pwr += sgs->group_power;

		sg = sg->next;
	} while (sg != env->sd->groups);
}

/**
 * check_asym_packing - Check to see if the group is packed into the
 *			sched doman.
 *
 * This is primarily intended to used at the sibling level.  Some
 * cores like POWER7 prefer to use lower numbered SMT threads.  In the
 * case of POWER7, it can move to lower SMT modes only when higher
 * threads are idle.  When in lower SMT modes, the threads will
 * perform better since they share less core resources.  Hence when we
 * have idle threads, we want them to be the higher ones.
 *
 * This packing function is run on idle threads.  It checks to see if
 * the busiest CPU in this domain (core in the P7 case) has a higher
 * CPU number than the packing function is being run on.  Here we are
 * assuming lower CPU number will be equivalent to lower a SMT thread
 * number.
 *
 * Return: 1 when packing is required and a task should be moved to
 * this CPU.  The amount of the imbalance is returned in *imbalance.
 *
 * @env: The load balancing environment.
 * @sds: Statistics of the sched_domain which is to be packed
 */
static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
{
	int busiest_cpu;

	if (!(env->sd->flags & SD_ASYM_PACKING))
		return 0;

	if (!sds->busiest)
		return 0;

	busiest_cpu = group_first_cpu(sds->busiest);
	if (env->dst_cpu > busiest_cpu)
		return 0;

	env->imbalance = DIV_ROUND_CLOSEST(
		sds->busiest_stat.avg_load * sds->busiest_stat.group_power,
		SCHED_POWER_SCALE);

	return 1;
}

/**
 * fix_small_imbalance - Calculate the minor imbalance that exists
 *			amongst the groups of a sched_domain, during
 *			load balancing.
 * @env: The load balancing environment.
 * @sds: Statistics of the sched_domain whose imbalance is to be calculated.
 */
static inline
void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
{
	unsigned long tmp, pwr_now = 0, pwr_move = 0;
	unsigned int imbn = 2;
	unsigned long scaled_busy_load_per_task;
	struct sg_lb_stats *local, *busiest;

	local = &sds->local_stat;
	busiest = &sds->busiest_stat;

	if (!local->sum_nr_running)
		local->load_per_task = cpu_avg_load_per_task(env->dst_cpu);
	else if (busiest->load_per_task > local->load_per_task)
		imbn = 1;

	scaled_busy_load_per_task =
		(busiest->load_per_task * SCHED_POWER_SCALE) /
		busiest->group_power;

	if (busiest->avg_load + scaled_busy_load_per_task >=
	    local->avg_load + (scaled_busy_load_per_task * imbn)) {
		env->imbalance = busiest->load_per_task;
		return;
	}

	/*
	 * OK, we don't have enough imbalance to justify moving tasks,
	 * however we may be able to increase total CPU power used by
	 * moving them.
	 */

	pwr_now += busiest->group_power *
			min(busiest->load_per_task, busiest->avg_load);
	pwr_now += local->group_power *
			min(local->load_per_task, local->avg_load);
	pwr_now /= SCHED_POWER_SCALE;

	/* Amount of load we'd subtract */
	tmp = (busiest->load_per_task * SCHED_POWER_SCALE) /
		busiest->group_power;
	if (busiest->avg_load > tmp) {
		pwr_move += busiest->group_power *
			    min(busiest->load_per_task,
				busiest->avg_load - tmp);
	}

	/* Amount of load we'd add */
	if (busiest->avg_load * busiest->group_power <
	    busiest->load_per_task * SCHED_POWER_SCALE) {
		tmp = (busiest->avg_load * busiest->group_power) /
		      local->group_power;
	} else {
		tmp = (busiest->load_per_task * SCHED_POWER_SCALE) /
		      local->group_power;
	}
	pwr_move += local->group_power *
		    min(local->load_per_task, local->avg_load + tmp);
	pwr_move /= SCHED_POWER_SCALE;

	/* Move if we gain throughput */
	if (pwr_move > pwr_now)
		env->imbalance = busiest->load_per_task;
}

/**
 * calculate_imbalance - Calculate the amount of imbalance present within the
 *			 groups of a given sched_domain during load balance.
 * @env: load balance environment
 * @sds: statistics of the sched_domain whose imbalance is to be calculated.
 */
static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
{
	unsigned long max_pull, load_above_capacity = ~0UL;
	struct sg_lb_stats *local, *busiest;

	local = &sds->local_stat;
	busiest = &sds->busiest_stat;

	if (busiest->group_imb) {
		/*
		 * In the group_imb case we cannot rely on group-wide averages
		 * to ensure cpu-load equilibrium, look at wider averages. XXX
		 */
		busiest->load_per_task =
			min(busiest->load_per_task, sds->avg_load);
	}

	/*
	 * In the presence of smp nice balancing, certain scenarios can have
	 * max load less than avg load(as we skip the groups at or below
	 * its cpu_power, while calculating max_load..)
	 */
	if (busiest->avg_load <= sds->avg_load ||
	    local->avg_load >= sds->avg_load) {
		env->imbalance = 0;
		return fix_small_imbalance(env, sds);
	}

	if (!busiest->group_imb) {
		/*
		 * Don't want to pull so many tasks that a group would go idle.
		 * Except of course for the group_imb case, since then we might
		 * have to drop below capacity to reach cpu-load equilibrium.
		 */
		load_above_capacity =
			(busiest->sum_nr_running - busiest->group_capacity);

		load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_POWER_SCALE);
		load_above_capacity /= busiest->group_power;
	}

	/*
	 * We're trying to get all the cpus to the average_load, so we don't
	 * want to push ourselves above the average load, nor do we wish to
	 * reduce the max loaded cpu below the average load. At the same time,
	 * we also don't want to reduce the group load below the group capacity
	 * (so that we can implement power-savings policies etc). Thus we look
	 * for the minimum possible imbalance.
	 */
	max_pull = min(busiest->avg_load - sds->avg_load, load_above_capacity);

	/* How much load to actually move to equalise the imbalance */
	env->imbalance = min(
		max_pull * busiest->group_power,
		(sds->avg_load - local->avg_load) * local->group_power
	) / SCHED_POWER_SCALE;

	/*
	 * if *imbalance is less than the average load per runnable task
	 * there is no guarantee that any tasks will be moved so we'll have
	 * a think about bumping its value to force at least one task to be
	 * moved
	 */
	if (env->imbalance < busiest->load_per_task)
		return fix_small_imbalance(env, sds);
}

/******* find_busiest_group() helpers end here *********************/

/**
 * find_busiest_group - Returns the busiest group within the sched_domain
 * if there is an imbalance. If there isn't an imbalance, and
 * the user has opted for power-savings, it returns a group whose
 * CPUs can be put to idle by rebalancing those tasks elsewhere, if
 * such a group exists.
 *
 * Also calculates the amount of weighted load which should be moved
 * to restore balance.
 *
 * @env: The load balancing environment.
 *
 * Return:	- The busiest group if imbalance exists.
 *		- If no imbalance and user has opted for power-savings balance,
 *		   return the least loaded group whose CPUs can be
 *		   put to idle by rebalancing its tasks onto our group.
 */
static struct sched_group *find_busiest_group(struct lb_env *env)
{
	struct sg_lb_stats *local, *busiest;
	struct sd_lb_stats sds;

	init_sd_lb_stats(&sds);

	/*
	 * Compute the various statistics relavent for load balancing at
	 * this level.
	 */
	update_sd_lb_stats(env, &sds);
	local = &sds.local_stat;
	busiest = &sds.busiest_stat;

	if ((env->idle == CPU_IDLE || env->idle == CPU_NEWLY_IDLE) &&
	    check_asym_packing(env, &sds))
		return sds.busiest;

	/* There is no busy sibling group to pull tasks from */
	if (!sds.busiest || busiest->sum_nr_running == 0)
		goto out_balanced;

	sds.avg_load = (SCHED_POWER_SCALE * sds.total_load) / sds.total_pwr;

	/*
	 * If the busiest group is imbalanced the below checks don't
	 * work because they assume all things are equal, which typically
	 * isn't true due to cpus_allowed constraints and the like.
	 */
	if (busiest->group_imb)
		goto force_balance;

	/* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
	if (env->idle == CPU_NEWLY_IDLE && local->group_has_capacity &&
	    !busiest->group_has_capacity)
		goto force_balance;

	/*
	 * If the local group is more busy than the selected busiest group
	 * don't try and pull any tasks.
	 */
	if (local->avg_load >= busiest->avg_load)
		goto out_balanced;

	/*
	 * Don't pull any tasks if this group is already above the domain
	 * average load.
	 */
	if (local->avg_load >= sds.avg_load)
		goto out_balanced;

	if (env->idle == CPU_IDLE) {
		/*
		 * This cpu is idle. If the busiest group load doesn't
		 * have more tasks than the number of available cpu's and
		 * there is no imbalance between this and busiest group
		 * wrt to idle cpu's, it is balanced.
		 */
		if ((local->idle_cpus < busiest->idle_cpus) &&
		    busiest->sum_nr_running <= busiest->group_weight)
			goto out_balanced;
	} else {
		/*
		 * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use
		 * imbalance_pct to be conservative.
		 */
		if (100 * busiest->avg_load <=
				env->sd->imbalance_pct * local->avg_load)
			goto out_balanced;
	}

force_balance:
	/* Looks like there is an imbalance. Compute it */
	calculate_imbalance(env, &sds);
	return sds.busiest;

out_balanced:
	env->imbalance = 0;
	return NULL;
}

/*
 * find_busiest_queue - find the busiest runqueue among the cpus in group.
 */
static struct rq *find_busiest_queue(struct lb_env *env,
				     struct sched_group *group)
{
	struct rq *busiest = NULL, *rq;
	unsigned long busiest_load = 0, busiest_power = 1;
	int i;

	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
		unsigned long power = power_of(i);
		unsigned long capacity = DIV_ROUND_CLOSEST(power,
							   SCHED_POWER_SCALE);
		unsigned long wl;

		if (!capacity)
			capacity = fix_small_capacity(env->sd, group);

		rq = cpu_rq(i);
		wl = weighted_cpuload(i);

		/*
		 * When comparing with imbalance, use weighted_cpuload()
		 * which is not scaled with the cpu power.
		 */
		if (capacity && rq->nr_running == 1 && wl > env->imbalance)
			continue;

		/*
		 * For the load comparisons with the other cpu's, consider
		 * the weighted_cpuload() scaled with the cpu power, so that
		 * the load can be moved away from the cpu that is potentially
		 * running at a lower capacity.
		 *
		 * Thus we're looking for max(wl_i / power_i), crosswise
		 * multiplication to rid ourselves of the division works out
		 * to: wl_i * power_j > wl_j * power_i;  where j is our
		 * previous maximum.
		 */
		if (wl * busiest_power > busiest_load * power) {
			busiest_load = wl;
			busiest_power = power;
			busiest = rq;
		}
	}

	return busiest;
}

/*
 * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
 * so long as it is large enough.
 */
#define MAX_PINNED_INTERVAL	512

/* Working cpumask for load_balance and load_balance_newidle. */
DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);

static int need_active_balance(struct lb_env *env)
{
	struct sched_domain *sd = env->sd;

	if (env->idle == CPU_NEWLY_IDLE) {

		/*
		 * ASYM_PACKING needs to force migrate tasks from busy but
		 * higher numbered CPUs in order to pack all tasks in the
		 * lowest numbered CPUs.
		 */
		if ((sd->flags & SD_ASYM_PACKING) && env->src_cpu > env->dst_cpu)
			return 1;
	}

	return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
}

static int active_load_balance_cpu_stop(void *data);

static int should_we_balance(struct lb_env *env)
{
	struct sched_group *sg = env->sd->groups;
	struct cpumask *sg_cpus, *sg_mask;
	int cpu, balance_cpu = -1;

	/*
	 * In the newly idle case, we will allow all the cpu's
	 * to do the newly idle load balance.
	 */
	if (env->idle == CPU_NEWLY_IDLE)
		return 1;

	sg_cpus = sched_group_cpus(sg);
	sg_mask = sched_group_mask(sg);
	/* Try to find first idle cpu */
	for_each_cpu_and(cpu, sg_cpus, env->cpus) {
		if (!cpumask_test_cpu(cpu, sg_mask) || !idle_cpu(cpu))
			continue;

		balance_cpu = cpu;
		break;
	}

	if (balance_cpu == -1)
		balance_cpu = group_balance_cpu(sg);

	/*
	 * First idle cpu or the first cpu(busiest) in this sched group
	 * is eligible for doing load balancing at this and above domains.
	 */
	return balance_cpu == env->dst_cpu;
}

/*
 * Check this_cpu to ensure it is balanced within domain. Attempt to move
 * tasks if there is an imbalance.
 */
static int load_balance(int this_cpu, struct rq *this_rq,
			struct sched_domain *sd, enum cpu_idle_type idle,
			int *continue_balancing)
{
	int ld_moved, cur_ld_moved, active_balance = 0;
	struct sched_domain *sd_parent = sd->parent;
	struct sched_group *group;
	struct rq *busiest;
	unsigned long flags;
	struct cpumask *cpus = __get_cpu_var(load_balance_mask);

	struct lb_env env = {
		.sd		= sd,
		.dst_cpu	= this_cpu,
		.dst_rq		= this_rq,
		.dst_grpmask    = sched_group_cpus(sd->groups),
		.idle		= idle,
		.loop_break	= sched_nr_migrate_break,
		.cpus		= cpus,
	};

	/*
	 * For NEWLY_IDLE load_balancing, we don't need to consider
	 * other cpus in our group
	 */
	if (idle == CPU_NEWLY_IDLE)
		env.dst_grpmask = NULL;

	cpumask_copy(cpus, cpu_active_mask);

	schedstat_inc(sd, lb_count[idle]);

redo:
	if (!should_we_balance(&env)) {
		*continue_balancing = 0;
		goto out_balanced;
	}

	group = find_busiest_group(&env);
	if (!group) {
		schedstat_inc(sd, lb_nobusyg[idle]);
		goto out_balanced;
	}

	busiest = find_busiest_queue(&env, group);
	if (!busiest) {
		schedstat_inc(sd, lb_nobusyq[idle]);
		goto out_balanced;
	}

	BUG_ON(busiest == env.dst_rq);

	schedstat_add(sd, lb_imbalance[idle], env.imbalance);

	ld_moved = 0;
	if (busiest->nr_running > 1) {
		/*
		 * Attempt to move tasks. If find_busiest_group has found
		 * an imbalance but busiest->nr_running <= 1, the group is
		 * still unbalanced. ld_moved simply stays zero, so it is
		 * correctly treated as an imbalance.
		 */
		env.flags |= LBF_ALL_PINNED;
		env.src_cpu   = busiest->cpu;
		env.src_rq    = busiest;
		env.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);

more_balance:
		local_irq_save(flags);
		double_rq_lock(env.dst_rq, busiest);

		/*
		 * cur_ld_moved - load moved in current iteration
		 * ld_moved     - cumulative load moved across iterations
		 */
		cur_ld_moved = move_tasks(&env);
		ld_moved += cur_ld_moved;
		double_rq_unlock(env.dst_rq, busiest);
		local_irq_restore(flags);

		/*
		 * some other cpu did the load balance for us.
		 */
		if (cur_ld_moved && env.dst_cpu != smp_processor_id())
			resched_cpu(env.dst_cpu);

		if (env.flags & LBF_NEED_BREAK) {
			env.flags &= ~LBF_NEED_BREAK;
			goto more_balance;
		}

		/*
		 * Revisit (affine) tasks on src_cpu that couldn't be moved to
		 * us and move them to an alternate dst_cpu in our sched_group
		 * where they can run. The upper limit on how many times we
		 * iterate on same src_cpu is dependent on number of cpus in our
		 * sched_group.
		 *
		 * This changes load balance semantics a bit on who can move
		 * load to a given_cpu. In addition to the given_cpu itself
		 * (or a ilb_cpu acting on its behalf where given_cpu is
		 * nohz-idle), we now have balance_cpu in a position to move
		 * load to given_cpu. In rare situations, this may cause
		 * conflicts (balance_cpu and given_cpu/ilb_cpu deciding
		 * _independently_ and at _same_ time to move some load to
		 * given_cpu) causing exceess load to be moved to given_cpu.
		 * This however should not happen so much in practice and
		 * moreover subsequent load balance cycles should correct the
		 * excess load moved.
		 */
		if ((env.flags & LBF_DST_PINNED) && env.imbalance > 0) {

			/* Prevent to re-select dst_cpu via env's cpus */
			cpumask_clear_cpu(env.dst_cpu, env.cpus);

			env.dst_rq	 = cpu_rq(env.new_dst_cpu);
			env.dst_cpu	 = env.new_dst_cpu;
			env.flags	&= ~LBF_DST_PINNED;
			env.loop	 = 0;
			env.loop_break	 = sched_nr_migrate_break;

			/*
			 * Go back to "more_balance" rather than "redo" since we
			 * need to continue with same src_cpu.
			 */
			goto more_balance;
		}

		/*
		 * We failed to reach balance because of affinity.
		 */
		if (sd_parent) {
			int *group_imbalance = &sd_parent->groups->sgp->imbalance;

			if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) {
				*group_imbalance = 1;
			} else if (*group_imbalance)
				*group_imbalance = 0;
		}

		/* All tasks on this runqueue were pinned by CPU affinity */
		if (unlikely(env.flags & LBF_ALL_PINNED)) {
			cpumask_clear_cpu(cpu_of(busiest), cpus);
			if (!cpumask_empty(cpus)) {
				env.loop = 0;
				env.loop_break = sched_nr_migrate_break;
				goto redo;
			}
			goto out_balanced;
		}
	}

	if (!ld_moved) {
		schedstat_inc(sd, lb_failed[idle]);
		/*
		 * Increment the failure counter only on periodic balance.
		 * We do not want newidle balance, which can be very
		 * frequent, pollute the failure counter causing
		 * excessive cache_hot migrations and active balances.
		 */
		if (idle != CPU_NEWLY_IDLE)
			sd->nr_balance_failed++;

		if (need_active_balance(&env)) {
			raw_spin_lock_irqsave(&busiest->lock, flags);

			/* don't kick the active_load_balance_cpu_stop,
			 * if the curr task on busiest cpu can't be
			 * moved to this_cpu
			 */
			if (!cpumask_test_cpu(this_cpu,
					tsk_cpus_allowed(busiest->curr))) {
				raw_spin_unlock_irqrestore(&busiest->lock,
							    flags);
				env.flags |= LBF_ALL_PINNED;
				goto out_one_pinned;
			}

			/*
			 * ->active_balance synchronizes accesses to
			 * ->active_balance_work.  Once set, it's cleared
			 * only after active load balance is finished.
			 */
			if (!busiest->active_balance) {
				busiest->active_balance = 1;
				busiest->push_cpu = this_cpu;
				active_balance = 1;
			}
			raw_spin_unlock_irqrestore(&busiest->lock, flags);

			if (active_balance) {
				stop_one_cpu_nowait(cpu_of(busiest),
					active_load_balance_cpu_stop, busiest,
					&busiest->active_balance_work);
			}

			/*
			 * We've kicked active balancing, reset the failure
			 * counter.
			 */
			sd->nr_balance_failed = sd->cache_nice_tries+1;
		}
	} else
		sd->nr_balance_failed = 0;

	if (likely(!active_balance)) {
		/* We were unbalanced, so reset the balancing interval */
		sd->balance_interval = sd->min_interval;
	} else {
		/*
		 * If we've begun active balancing, start to back off. This
		 * case may not be covered by the all_pinned logic if there
		 * is only 1 task on the busy runqueue (because we don't call
		 * move_tasks).
		 */
		if (sd->balance_interval < sd->max_interval)
			sd->balance_interval *= 2;
	}

	goto out;

out_balanced:
	schedstat_inc(sd, lb_balanced[idle]);

	sd->nr_balance_failed = 0;

out_one_pinned:
	/* tune up the balancing interval */
	if (((env.flags & LBF_ALL_PINNED) &&
			sd->balance_interval < MAX_PINNED_INTERVAL) ||
			(sd->balance_interval < sd->max_interval))
		sd->balance_interval *= 2;

	ld_moved = 0;
out:
	return ld_moved;
}

/*
 * idle_balance is called by schedule() if this_cpu is about to become
 * idle. Attempts to pull tasks from other CPUs.
 */
void idle_balance(int this_cpu, struct rq *this_rq)
{
	struct sched_domain *sd;
	int pulled_task = 0;
	unsigned long next_balance = jiffies + HZ;
	u64 curr_cost = 0;

	this_rq->idle_stamp = rq_clock(this_rq);

	if (this_rq->avg_idle < sysctl_sched_migration_cost)
		return;

	/*
	 * Drop the rq->lock, but keep IRQ/preempt disabled.
	 */
	raw_spin_unlock(&this_rq->lock);

	update_blocked_averages(this_cpu);
	rcu_read_lock();
	for_each_domain(this_cpu, sd) {
		unsigned long interval;
		int continue_balancing = 1;
		u64 t0, domain_cost;

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

		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost)
			break;

		if (sd->flags & SD_BALANCE_NEWIDLE) {
			t0 = sched_clock_cpu(this_cpu);

			/* If we've pulled tasks over stop searching: */
			pulled_task = load_balance(this_cpu, this_rq,
						   sd, CPU_NEWLY_IDLE,
						   &continue_balancing);

			domain_cost = sched_clock_cpu(this_cpu) - t0;
			if (domain_cost > sd->max_newidle_lb_cost)
				sd->max_newidle_lb_cost = domain_cost;

			curr_cost += domain_cost;
		}

		interval = msecs_to_jiffies(sd->balance_interval);
		if (time_after(next_balance, sd->last_balance + interval))
			next_balance = sd->last_balance + interval;
		if (pulled_task) {
			this_rq->idle_stamp = 0;
			break;
		}
	}
	rcu_read_unlock();

	raw_spin_lock(&this_rq->lock);

	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
		/*
		 * We are going idle. next_balance may be set based on
		 * a busy processor. So reset next_balance.
		 */
		this_rq->next_balance = next_balance;
	}

	if (curr_cost > this_rq->max_idle_balance_cost)
		this_rq->max_idle_balance_cost = curr_cost;
}

/*
 * active_load_balance_cpu_stop is run by cpu stopper. It pushes
 * running tasks off the busiest CPU onto idle CPUs. It requires at
 * least 1 task to be running on each physical CPU where possible, and
 * avoids physical / logical imbalances.
 */
static int active_load_balance_cpu_stop(void *data)
{
	struct rq *busiest_rq = data;
	int busiest_cpu = cpu_of(busiest_rq);
	int target_cpu = busiest_rq->push_cpu;
	struct rq *target_rq = cpu_rq(target_cpu);
	struct sched_domain *sd;

	raw_spin_lock_irq(&busiest_rq->lock);

	/* make sure the requested cpu hasn't gone down in the meantime */
	if (unlikely(busiest_cpu != smp_processor_id() ||
		     !busiest_rq->active_balance))
		goto out_unlock;

	/* Is there any task to move? */
	if (busiest_rq->nr_running <= 1)
		goto out_unlock;

	/*
	 * This condition is "impossible", if it occurs
	 * we need to fix it. Originally reported by
	 * Bjorn Helgaas on a 128-cpu setup.
	 */
	BUG_ON(busiest_rq == target_rq);

	/* move a task from busiest_rq to target_rq */
	double_lock_balance(busiest_rq, target_rq);

	/* Search for an sd spanning us and the target CPU. */
	rcu_read_lock();
	for_each_domain(target_cpu, sd) {
		if ((sd->flags & SD_LOAD_BALANCE) &&
		    cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
				break;
	}

	if (likely(sd)) {
		struct lb_env env = {
			.sd		= sd,
			.dst_cpu	= target_cpu,
			.dst_rq		= target_rq,
			.src_cpu	= busiest_rq->cpu,
			.src_rq		= busiest_rq,
			.idle		= CPU_IDLE,
		};

		schedstat_inc(sd, alb_count);

		if (move_one_task(&env))
			schedstat_inc(sd, alb_pushed);
		else
			schedstat_inc(sd, alb_failed);
	}
	rcu_read_unlock();
	double_unlock_balance(busiest_rq, target_rq);
out_unlock:
	busiest_rq->active_balance = 0;
	raw_spin_unlock_irq(&busiest_rq->lock);
	return 0;
}

#ifdef CONFIG_NO_HZ_COMMON
/*
 * idle load balancing details
 * - When one of the busy CPUs notice that there may be an idle rebalancing
 *   needed, they will kick the idle load balancer, which then does idle
 *   load balancing for all the idle CPUs.
 */
static struct {
	cpumask_var_t idle_cpus_mask;
	atomic_t nr_cpus;
	unsigned long next_balance;     /* in jiffy units */
} nohz ____cacheline_aligned;

static inline int find_new_ilb(int call_cpu)
{
	int ilb = cpumask_first(nohz.idle_cpus_mask);

	if (ilb < nr_cpu_ids && idle_cpu(ilb))
		return ilb;

	return nr_cpu_ids;
}

/*
 * Kick a CPU to do the nohz balancing, if it is time for it. We pick the
 * nohz_load_balancer CPU (if there is one) otherwise fallback to any idle
 * CPU (if there is one).
 */
static void nohz_balancer_kick(int cpu)
{
	int ilb_cpu;

	nohz.next_balance++;

	ilb_cpu = find_new_ilb(cpu);

	if (ilb_cpu >= nr_cpu_ids)
		return;

	if (test_and_set_bit(NOHZ_BALANCE_KICK, nohz_flags(ilb_cpu)))
		return;
	/*
	 * Use smp_send_reschedule() instead of resched_cpu().
	 * This way we generate a sched IPI on the target cpu which
	 * is idle. And the softirq performing nohz idle load balance
	 * will be run before returning from the IPI.
	 */
	smp_send_reschedule(ilb_cpu);
	return;
}

static inline void nohz_balance_exit_idle(int cpu)
{
	if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) {
		cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
		atomic_dec(&nohz.nr_cpus);
		clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
	}
}

static inline void set_cpu_sd_state_busy(void)
{
	struct sched_domain *sd;

	rcu_read_lock();
	sd = rcu_dereference_check_sched_domain(this_rq()->sd);

	if (!sd || !sd->nohz_idle)
		goto unlock;
	sd->nohz_idle = 0;

	for (; sd; sd = sd->parent)
		atomic_inc(&sd->groups->sgp->nr_busy_cpus);
unlock:
	rcu_read_unlock();
}

void set_cpu_sd_state_idle(void)
{
	struct sched_domain *sd;

	rcu_read_lock();
	sd = rcu_dereference_check_sched_domain(this_rq()->sd);

	if (!sd || sd->nohz_idle)
		goto unlock;
	sd->nohz_idle = 1;

	for (; sd; sd = sd->parent)
		atomic_dec(&sd->groups->sgp->nr_busy_cpus);
unlock:
	rcu_read_unlock();
}

/*
 * This routine will record that the cpu is going idle with tick stopped.
 * This info will be used in performing idle load balancing in the future.
 */
void nohz_balance_enter_idle(int cpu)
{
	/*
	 * If this cpu is going down, then nothing needs to be done.
	 */
	if (!cpu_active(cpu))
		return;

	if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
		return;

	cpumask_set_cpu(cpu, nohz.idle_cpus_mask);
	atomic_inc(&nohz.nr_cpus);
	set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
}

static int sched_ilb_notifier(struct notifier_block *nfb,
					unsigned long action, void *hcpu)
{
	switch (action & ~CPU_TASKS_FROZEN) {
	case CPU_DYING:
		nohz_balance_exit_idle(smp_processor_id());
		return NOTIFY_OK;
	default:
		return NOTIFY_DONE;
	}
}
#endif

static DEFINE_SPINLOCK(balancing);

/*
 * Scale the max load_balance interval with the number of CPUs in the system.
 * This trades load-balance latency on larger machines for less cross talk.
 */
void update_max_interval(void)
{
	max_load_balance_interval = HZ*num_online_cpus()/10;
}

/*
 * It checks each scheduling domain to see if it is due to be balanced,
 * and initiates a balancing operation if so.
 *
 * Balancing parameters are set up in init_sched_domains.
 */
static void rebalance_domains(int cpu, enum cpu_idle_type idle)
{
	int continue_balancing = 1;
	struct rq *rq = cpu_rq(cpu);
	unsigned long interval;
	struct sched_domain *sd;
	/* Earliest time when we have to do rebalance again */
	unsigned long next_balance = jiffies + 60*HZ;
	int update_next_balance = 0;
	int need_serialize, need_decay = 0;
	u64 max_cost = 0;

	update_blocked_averages(cpu);

	rcu_read_lock();
	for_each_domain(cpu, sd) {
		/*
		 * Decay the newidle max times here because this is a regular
		 * visit to all the domains. Decay ~1% per second.
		 */
		if (time_after(jiffies, sd->next_decay_max_lb_cost)) {
			sd->max_newidle_lb_cost =
				(sd->max_newidle_lb_cost * 253) / 256;
			sd->next_decay_max_lb_cost = jiffies + HZ;
			need_decay = 1;
		}
		max_cost += sd->max_newidle_lb_cost;

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

		/*
		 * Stop the load balance at this level. There is another
		 * CPU in our sched group which is doing load balancing more
		 * actively.
		 */
		if (!continue_balancing) {
			if (need_decay)
				continue;
			break;
		}

		interval = sd->balance_interval;
		if (idle != CPU_IDLE)
			interval *= sd->busy_factor;

		/* scale ms to jiffies */
		interval = msecs_to_jiffies(interval);
		interval = clamp(interval, 1UL, max_load_balance_interval);

		need_serialize = sd->flags & SD_SERIALIZE;

		if (need_serialize) {
			if (!spin_trylock(&balancing))
				goto out;
		}

		if (time_after_eq(jiffies, sd->last_balance + interval)) {
			if (load_balance(cpu, rq, sd, idle, &continue_balancing)) {
				/*
				 * The LBF_DST_PINNED logic could have changed
				 * env->dst_cpu, so we can't know our idle
				 * state even if we migrated tasks. Update it.
				 */
				idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE;
			}
			sd->last_balance = jiffies;
		}
		if (need_serialize)
			spin_unlock(&balancing);
out:
		if (time_after(next_balance, sd->last_balance + interval)) {
			next_balance = sd->last_balance + interval;
			update_next_balance = 1;
		}
	}
	if (need_decay) {
		/*
		 * Ensure the rq-wide value also decays but keep it at a
		 * reasonable floor to avoid funnies with rq->avg_idle.
		 */
		rq->max_idle_balance_cost =
			max((u64)sysctl_sched_migration_cost, max_cost);
	}
	rcu_read_unlock();

	/*
	 * next_balance will be updated only when there is a need.
	 * When the cpu is attached to null domain for ex, it will not be
	 * updated.
	 */
	if (likely(update_next_balance))
		rq->next_balance = next_balance;
}

#ifdef CONFIG_NO_HZ_COMMON
/*
 * In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the
 * rebalancing for all the cpus for whom scheduler ticks are stopped.
 */
static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle)
{
	struct rq *this_rq = cpu_rq(this_cpu);
	struct rq *rq;
	int balance_cpu;

	if (idle != CPU_IDLE ||
	    !test_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu)))
		goto end;

	for_each_cpu(balance_cpu, nohz.idle_cpus_mask) {
		if (balance_cpu == this_cpu || !idle_cpu(balance_cpu))
			continue;

		/*
		 * If this cpu gets work to do, stop the load balancing
		 * work being done for other cpus. Next load
		 * balancing owner will pick it up.
		 */
		if (need_resched())
			break;

		rq = cpu_rq(balance_cpu);

		raw_spin_lock_irq(&rq->lock);
		update_rq_clock(rq);
		update_idle_cpu_load(rq);
		raw_spin_unlock_irq(&rq->lock);

		rebalance_domains(balance_cpu, CPU_IDLE);

		if (time_after(this_rq->next_balance, rq->next_balance))
			this_rq->next_balance = rq->next_balance;
	}
	nohz.next_balance = this_rq->next_balance;
end:
	clear_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu));
}

/*
 * Current heuristic for kicking the idle load balancer in the presence
 * of an idle cpu is the system.
 *   - This rq has more than one task.
 *   - At any scheduler domain level, this cpu's scheduler group has multiple
 *     busy cpu's exceeding the group's power.
 *   - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler
 *     domain span are idle.
 */
static inline int nohz_kick_needed(struct rq *rq, int cpu)
{
	unsigned long now = jiffies;
	struct sched_domain *sd;

	if (unlikely(idle_cpu(cpu)))
		return 0;

       /*
	* We may be recently in ticked or tickless idle mode. At the first
	* busy tick after returning from idle, we will update the busy stats.
	*/
	set_cpu_sd_state_busy();
	nohz_balance_exit_idle(cpu);

	/*
	 * None are in tickless mode and hence no need for NOHZ idle load
	 * balancing.
	 */
	if (likely(!atomic_read(&nohz.nr_cpus)))
		return 0;

	if (time_before(now, nohz.next_balance))
		return 0;

	if (rq->nr_running >= 2)
		goto need_kick;

	rcu_read_lock();
	for_each_domain(cpu, sd) {
		struct sched_group *sg = sd->groups;
		struct sched_group_power *sgp = sg->sgp;
		int nr_busy = atomic_read(&sgp->nr_busy_cpus);

		if (sd->flags & SD_SHARE_PKG_RESOURCES && nr_busy > 1)
			goto need_kick_unlock;

		if (sd->flags & SD_ASYM_PACKING && nr_busy != sg->group_weight
		    && (cpumask_first_and(nohz.idle_cpus_mask,
					  sched_domain_span(sd)) < cpu))
			goto need_kick_unlock;

		if (!(sd->flags & (SD_SHARE_PKG_RESOURCES | SD_ASYM_PACKING)))
			break;
	}
	rcu_read_unlock();
	return 0;

need_kick_unlock:
	rcu_read_unlock();
need_kick:
	return 1;
}
#else
static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { }
#endif

/*
 * run_rebalance_domains is triggered when needed from the scheduler tick.
 * Also triggered for nohz idle balancing (with nohz_balancing_kick set).
 */
static void run_rebalance_domains(struct softirq_action *h)
{
	int this_cpu = smp_processor_id();
	struct rq *this_rq = cpu_rq(this_cpu);
	enum cpu_idle_type idle = this_rq->idle_balance ?
						CPU_IDLE : CPU_NOT_IDLE;

	rebalance_domains(this_cpu, idle);

	/*
	 * If this cpu has a pending nohz_balance_kick, then do the
	 * balancing on behalf of the other idle cpus whose ticks are
	 * stopped.
	 */
	nohz_idle_balance(this_cpu, idle);
}

static inline int on_null_domain(int cpu)
{
	return !rcu_dereference_sched(cpu_rq(cpu)->sd);
}

/*
 * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
 */
void trigger_load_balance(struct rq *rq, int cpu)
{
	/* Don't need to rebalance while attached to NULL domain */
	if (time_after_eq(jiffies, rq->next_balance) &&
	    likely(!on_null_domain(cpu)))
		raise_softirq(SCHED_SOFTIRQ);
#ifdef CONFIG_NO_HZ_COMMON
	if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu)))
		nohz_balancer_kick(cpu);
#endif
}

static void rq_online_fair(struct rq *rq)
{
	update_sysctl();
}

static void rq_offline_fair(struct rq *rq)
{
	update_sysctl();

	/* Ensure any throttled groups are reachable by pick_next_task */
	unthrottle_offline_cfs_rqs(rq);
}

#endif /* CONFIG_SMP */

/*
 * scheduler tick hitting a task of our scheduling class:
 */
static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
{
	struct cfs_rq *cfs_rq;
	struct sched_entity *se = &curr->se;

	for_each_sched_entity(se) {
		cfs_rq = cfs_rq_of(se);
		entity_tick(cfs_rq, se, queued);
	}

	if (numabalancing_enabled)
		task_tick_numa(rq, curr);

	update_rq_runnable_avg(rq, 1);
}

/*
 * called on fork with the child task as argument from the parent's context
 *  - child not yet on the tasklist
 *  - preemption disabled
 */
static void task_fork_fair(struct task_struct *p)
{
	struct cfs_rq *cfs_rq;
	struct sched_entity *se = &p->se, *curr;
	int this_cpu = smp_processor_id();
	struct rq *rq = this_rq();
	unsigned long flags;

	raw_spin_lock_irqsave(&rq->lock, flags);

	update_rq_clock(rq);

	cfs_rq = task_cfs_rq(current);
	curr = cfs_rq->curr;

	/*
	 * Not only the cpu but also the task_group of the parent might have
	 * been changed after parent->se.parent,cfs_rq were copied to
	 * child->se.parent,cfs_rq. So call __set_task_cpu() to make those
	 * of child point to valid ones.
	 */
	rcu_read_lock();
	__set_task_cpu(p, this_cpu);
	rcu_read_unlock();

	update_curr(cfs_rq);

	if (curr)
		se->vruntime = curr->vruntime;
	place_entity(cfs_rq, se, 1);

	if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) {
		/*
		 * Upon rescheduling, sched_class::put_prev_task() will place
		 * 'current' within the tree based on its new key value.
		 */
		swap(curr->vruntime, se->vruntime);
		resched_task(rq->curr);
	}

	se->vruntime -= cfs_rq->min_vruntime;

	raw_spin_unlock_irqrestore(&rq->lock, flags);
}

/*
 * Priority of the task has changed. Check to see if we preempt
 * the current task.
 */
static void
prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
{
	if (!p->se.on_rq)
		return;

	/*
	 * Reschedule if we are currently running on this runqueue and
	 * our priority decreased, or if we are not currently running on
	 * this runqueue and our priority is higher than the current's
	 */
	if (rq->curr == p) {
		if (p->prio > oldprio)
			resched_task(rq->curr);
	} else
		check_preempt_curr(rq, p, 0);
}

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

	/*
	 * Ensure the task's vruntime is normalized, so that when its
	 * switched back to the fair class the enqueue_entity(.flags=0) will
	 * do the right thing.
	 *
	 * If it was on_rq, then the dequeue_entity(.flags=0) will already
	 * have normalized the vruntime, if it was !on_rq, then only when
	 * the task is sleeping will it still have non-normalized vruntime.
	 */
	if (!se->on_rq && p->state != TASK_RUNNING) {
		/*
		 * Fix up our vruntime so that the current sleep doesn't
		 * cause 'unlimited' sleep bonus.
		 */
		place_entity(cfs_rq, se, 0);
		se->vruntime -= cfs_rq->min_vruntime;
	}

#ifdef CONFIG_SMP
	/*
	* Remove our load from contribution when we leave sched_fair
	* and ensure we don't carry in an old decay_count if we
	* switch back.
	*/
	if (se->avg.decay_count) {
		__synchronize_entity_decay(se);
		subtract_blocked_load_contrib(cfs_rq, se->avg.load_avg_contrib);
	}
#endif
}

/*
 * We switched to the sched_fair class.
 */
static void switched_to_fair(struct rq *rq, struct task_struct *p)
{
	if (!p->se.on_rq)
		return;

	/*
	 * We were most likely switched from sched_rt, so
	 * kick off the schedule if running, otherwise just see
	 * if we can still preempt the current task.
	 */
	if (rq->curr == p)
		resched_task(rq->curr);
	else
		check_preempt_curr(rq, p, 0);
}

/* Account for a task changing its policy or group.
 *
 * This routine is mostly called to set cfs_rq->curr field when a task
 * migrates between groups/classes.
 */
static void set_curr_task_fair(struct rq *rq)
{
	struct sched_entity *se = &rq->curr->se;

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

		set_next_entity(cfs_rq, se);
		/* ensure bandwidth has been allocated on our new cfs_rq */
		account_cfs_rq_runtime(cfs_rq, 0);
	}
}

void init_cfs_rq(struct cfs_rq *cfs_rq)
{
	cfs_rq->tasks_timeline = RB_ROOT;
	cfs_rq->min_vruntime = (u64)(-(1LL << 20));
#ifndef CONFIG_64BIT
	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
#endif
#ifdef CONFIG_SMP
	atomic64_set(&cfs_rq->decay_counter, 1);
	atomic_long_set(&cfs_rq->removed_load, 0);
#endif
}

#ifdef CONFIG_FAIR_GROUP_SCHED
static void task_move_group_fair(struct task_struct *p, int on_rq)
{
	struct cfs_rq *cfs_rq;
	/*
	 * If the task was not on the rq at the time of this cgroup movement
	 * it must have been asleep, sleeping tasks keep their ->vruntime
	 * absolute on their old rq until wakeup (needed for the fair sleeper
	 * bonus in place_entity()).
	 *
	 * If it was on the rq, we've just 'preempted' it, which does convert
	 * ->vruntime to a relative base.
	 *
	 * Make sure both cases convert their relative position when migrating
	 * to another cgroup's rq. This does somewhat interfere with the
	 * fair sleeper stuff for the first placement, but who cares.
	 */
	/*
	 * When !on_rq, vruntime of the task has usually NOT been normalized.
	 * But there are some cases where it has already been normalized:
	 *
	 * - Moving a forked child which is waiting for being woken up by
	 *   wake_up_new_task().
	 * - Moving a task which has been woken up by try_to_wake_up() and
	 *   waiting for actually being woken up by sched_ttwu_pending().
	 *
	 * To prevent boost or penalty in the new cfs_rq caused by delta
	 * min_vruntime between the two cfs_rqs, we skip vruntime adjustment.
	 */
	if (!on_rq && (!p->se.sum_exec_runtime || p->state == TASK_WAKING))
		on_rq = 1;

	if (!on_rq)
		p->se.vruntime -= cfs_rq_of(&p->se)->min_vruntime;
	set_task_rq(p, task_cpu(p));
	if (!on_rq) {
		cfs_rq = cfs_rq_of(&p->se);
		p->se.vruntime += cfs_rq->min_vruntime;
#ifdef CONFIG_SMP
		/*
		 * migrate_task_rq_fair() will have removed our previous
		 * contribution, but we must synchronize for ongoing future
		 * decay.
		 */
		p->se.avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
		cfs_rq->blocked_load_avg += p->se.avg.load_avg_contrib;
#endif
	}
}

void free_fair_sched_group(struct task_group *tg)
{
	int i;

	destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));

	for_each_possible_cpu(i) {
		if (tg->cfs_rq)
			kfree(tg->cfs_rq[i]);
		if (tg->se)
			kfree(tg->se[i]);
	}

	kfree(tg->cfs_rq);
	kfree(tg->se);
}

int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
	struct cfs_rq *cfs_rq;
	struct sched_entity *se;
	int i;

	tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
	if (!tg->cfs_rq)
		goto err;
	tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL);
	if (!tg->se)
		goto err;

	tg->shares = NICE_0_LOAD;

	init_cfs_bandwidth(tg_cfs_bandwidth(tg));

	for_each_possible_cpu(i) {
		cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
				      GFP_KERNEL, cpu_to_node(i));
		if (!cfs_rq)
			goto err;

		se = kzalloc_node(sizeof(struct sched_entity),
				  GFP_KERNEL, cpu_to_node(i));
		if (!se)
			goto err_free_rq;

		init_cfs_rq(cfs_rq);
		init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
	}

	return 1;

err_free_rq:
	kfree(cfs_rq);
err:
	return 0;
}

void unregister_fair_sched_group(struct task_group *tg, int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long flags;

	/*
	* Only empty task groups can be destroyed; so we can speculatively
	* check on_list without danger of it being re-added.
	*/
	if (!tg->cfs_rq[cpu]->on_list)
		return;

	raw_spin_lock_irqsave(&rq->lock, flags);
	list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
	raw_spin_unlock_irqrestore(&rq->lock, flags);
}

void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
			struct sched_entity *se, int cpu,
			struct sched_entity *parent)
{
	struct rq *rq = cpu_rq(cpu);

	cfs_rq->tg = tg;
	cfs_rq->rq = rq;
	init_cfs_rq_runtime(cfs_rq);

	tg->cfs_rq[cpu] = cfs_rq;
	tg->se[cpu] = se;

	/* se could be NULL for root_task_group */
	if (!se)
		return;

	if (!parent)
		se->cfs_rq = &rq->cfs;
	else
		se->cfs_rq = parent->my_q;

	se->my_q = cfs_rq;
	update_load_set(&se->load, 0);
	se->parent = parent;
}

static DEFINE_MUTEX(shares_mutex);

int sched_group_set_shares(struct task_group *tg, unsigned long shares)
{
	int i;
	unsigned long flags;

	/*
	 * We can't change the weight of the root cgroup.
	 */
	if (!tg->se[0])
		return -EINVAL;

	shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES));

	mutex_lock(&shares_mutex);
	if (tg->shares == shares)
		goto done;

	tg->shares = shares;
	for_each_possible_cpu(i) {
		struct rq *rq = cpu_rq(i);
		struct sched_entity *se;

		se = tg->se[i];
		/* Propagate contribution to hierarchy */
		raw_spin_lock_irqsave(&rq->lock, flags);

		/* Possible calls to update_curr() need rq clock */
		update_rq_clock(rq);
		for_each_sched_entity(se)
			update_cfs_shares(group_cfs_rq(se));
		raw_spin_unlock_irqrestore(&rq->lock, flags);
	}

done:
	mutex_unlock(&shares_mutex);
	return 0;
}
#else /* CONFIG_FAIR_GROUP_SCHED */

void free_fair_sched_group(struct task_group *tg) { }

int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
	return 1;
}

void unregister_fair_sched_group(struct task_group *tg, int cpu) { }

#endif /* CONFIG_FAIR_GROUP_SCHED */


static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task)
{
	struct sched_entity *se = &task->se;
	unsigned int rr_interval = 0;

	/*
	 * Time slice is 0 for SCHED_OTHER tasks that are on an otherwise
	 * idle runqueue:
	 */
	if (rq->cfs.load.weight)
		rr_interval = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se));

	return rr_interval;
}

/*
 * All the scheduling class methods:
 */
const struct sched_class fair_sched_class = {
	.next			= &idle_sched_class,
	.enqueue_task		= enqueue_task_fair,
	.dequeue_task		= dequeue_task_fair,
	.yield_task		= yield_task_fair,
	.yield_to_task		= yield_to_task_fair,

	.check_preempt_curr	= check_preempt_wakeup,

	.pick_next_task		= pick_next_task_fair,
	.put_prev_task		= put_prev_task_fair,

#ifdef CONFIG_SMP
	.select_task_rq		= select_task_rq_fair,
	.migrate_task_rq	= migrate_task_rq_fair,

	.rq_online		= rq_online_fair,
	.rq_offline		= rq_offline_fair,

	.task_waking		= task_waking_fair,
#endif

	.set_curr_task          = set_curr_task_fair,
	.task_tick		= task_tick_fair,
	.task_fork		= task_fork_fair,

	.prio_changed		= prio_changed_fair,
	.switched_from		= switched_from_fair,
	.switched_to		= switched_to_fair,

	.get_rr_interval	= get_rr_interval_fair,

#ifdef CONFIG_FAIR_GROUP_SCHED
	.task_move_group	= task_move_group_fair,
#endif
};

#ifdef CONFIG_SCHED_DEBUG
void print_cfs_stats(struct seq_file *m, int cpu)
{
	struct cfs_rq *cfs_rq;

	rcu_read_lock();
	for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
		print_cfs_rq(m, cpu, cfs_rq);
	rcu_read_unlock();
}
#endif

__init void init_sched_fair_class(void)
{
#ifdef CONFIG_SMP
	open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);

#ifdef CONFIG_NO_HZ_COMMON
	nohz.next_balance = jiffies;
	zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
	cpu_notifier(sched_ilb_notifier, 0);
#endif
#endif /* SMP */

}