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;

/* 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;

/*
 * After skipping a page migration on a shared page, skip N more numa page
 * migrations unconditionally. This reduces the number of NUMA migrations
 * in shared memory workloads, and has the effect of pulling tasks towards
 * where their memory lives, over pulling the memory towards the task.
 */
unsigned int sysctl_numa_balancing_migrate_deferred = 16;

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;

static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
{
	rq->nr_numa_running += (p->numa_preferred_nid != -1);
	rq->nr_preferred_running += (p->numa_preferred_nid == task_node(p));
}

static void account_numa_dequeue(struct rq *rq, struct task_struct *p)
{
	rq->nr_numa_running -= (p->numa_preferred_nid != -1);
	rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p));
}

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;
	unsigned long total_faults;
	unsigned long 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 p->numa_group->faults[2*nid] + 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)
{
	if (!p->numa_group || !p->numa_group->total_faults)
		return 0;

	return 1000 * group_faults(p, nid) / p->numa_group->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, cpus = 0;

	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);

		cpus++;
	}

	/*
	 * If we raced with hotplug and there are no CPUs left in our mask
	 * the @ns structure is NULL'ed and task_numa_compare() will
	 * not find this node attractive.
	 *
	 * We'll either bail at !has_capacity, or we'll detect a huge imbalance
	 * and bail there.
	 */
	if (!cpus)
		return;

	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.
		 */
		if (cur->numa_group == env->p->numa_group) {
			imp = taskimp + task_weight(cur, env->src_nid) -
			      task_weight(cur, env->dst_nid);
			/*
			 * Add some hysteresis to prevent swapping the
			 * tasks within a group over tiny differences.
			 */
			if (cur->numa_group)
				imp -= imp/16;
		} else {
			/*
			 * Compare the group weights. If a task is all by
			 * itself (not part of a group), use the task weight
			 * instead.
			 */
			if (env->p->numa_group)
				imp = groupimp;
			else
				imp = taskimp;

			if (cur->numa_group)
				imp += group_weight(cur, env->src_nid) -
				       group_weight(cur, env->dst_nid);
			else
				imp += task_weight(cur, env->src_nid) -
				       task_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));
	if (sd)
		env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2;
	rcu_read_unlock();

	/*
	 * Cpusets can break the scheduler domain tree into smaller
	 * balance domains, some of which do not cross NUMA boundaries.
	 * Tasks that are "trapped" in such domains cannot be migrated
	 * elsewhere, so there is no point in (re)trying.
	 */
	if (unlikely(!sd)) {
		p->numa_preferred_nid = cpu_to_node(task_cpu(p));
		return -EINVAL;
	}

	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;

	sched_setnuma(p, env.dst_nid);

	/*
	 * Reset the scan period if the task is being rescheduled on an
	 * alternative node to recheck if the tasks is now properly placed.
	 */
	p->numa_scan_period = task_scan_min(p);

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

	/* Periodically retry migrating the task to the preferred node */
	p->numa_migrate_retry = jiffies + HZ;

	/* Success if task is already running on preferred CPU */
	if (cpu_to_node(task_cpu(p)) == p->numa_preferred_nid)
		return;

	/* Otherwise, try migrate to a CPU on the preferred node */
	task_numa_migrate(p);
}

/*
 * When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS
 * increments. The more local the fault statistics are, the higher the scan
 * period will be for the next scan window. If local/remote ratio is below
 * NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS) the
 * scan period will decrease
 */
#define NUMA_PERIOD_SLOTS 10
#define NUMA_PERIOD_THRESHOLD 3

/*
 * Increase the scan period (slow down scanning) if the majority of
 * our memory is already on our local node, or if the majority of
 * the page accesses are shared with other processes.
 * Otherwise, decrease the scan period.
 */
static void update_task_scan_period(struct task_struct *p,
			unsigned long shared, unsigned long private)
{
	unsigned int period_slot;
	int ratio;
	int diff;

	unsigned long remote = p->numa_faults_locality[0];
	unsigned long local = p->numa_faults_locality[1];

	/*
	 * If there were no record hinting faults then either the task is
	 * completely idle or all activity is areas that are not of interest
	 * to automatic numa balancing. Scan slower
	 */
	if (local + shared == 0) {
		p->numa_scan_period = min(p->numa_scan_period_max,
			p->numa_scan_period << 1);

		p->mm->numa_next_scan = jiffies +
			msecs_to_jiffies(p->numa_scan_period);

		return;
	}

	/*
	 * Prepare to scale scan period relative to the current period.
	 *	 == NUMA_PERIOD_THRESHOLD scan period stays the same
	 *       <  NUMA_PERIOD_THRESHOLD scan period decreases (scan faster)
	 *	 >= NUMA_PERIOD_THRESHOLD scan period increases (scan slower)
	 */
	period_slot = DIV_ROUND_UP(p->numa_scan_period, NUMA_PERIOD_SLOTS);
	ratio = (local * NUMA_PERIOD_SLOTS) / (local + remote);
	if (ratio >= NUMA_PERIOD_THRESHOLD) {
		int slot = ratio - NUMA_PERIOD_THRESHOLD;
		if (!slot)
			slot = 1;
		diff = slot * period_slot;
	} else {
		diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot;

		/*
		 * Scale scan rate increases based on sharing. There is an
		 * inverse relationship between the degree of sharing and
		 * the adjustment made to the scanning period. Broadly
		 * speaking the intent is that there is little point
		 * scanning faster if shared accesses dominate as it may
		 * simply bounce migrations uselessly
		 */
		period_slot = DIV_ROUND_UP(diff, NUMA_PERIOD_SLOTS);
		ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
		diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
	}

	p->numa_scan_period = clamp(p->numa_scan_period + diff,
			task_scan_min(p), task_scan_max(p));
	memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
}

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;
	unsigned long fault_types[2] = { 0, 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_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];
			fault_types[priv] += 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 */
				p->numa_group->faults[i] += diff;
				p->numa_group->total_faults += diff;
				group_faults += 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;
		}
	}

	update_task_scan_period(p, fault_types[0], fault_types[1]);

	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 */
		sched_setnuma(p, max_nid);
		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 task_numa_group(struct task_struct *p, int cpupid, int flags,
			int *priv)
{
	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(unsigned long);

		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++)
			grp->faults[i] = p->numa_faults[i];

		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 no_join;

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

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

	/*
	 * 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 no_join;

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

	/* Always join threads in the same process. */
	if (tsk->mm == current->mm)
		join = true;

	/* Simple filter to avoid false positives due to PID collisions */
	if (flags & TNF_SHARED)
		join = true;

	/* Update priv based on whether false sharing was detected */
	*priv = !join;

	if (join && !get_numa_group(grp))
		goto no_join;

	rcu_read_unlock();

	if (!join)
		return;

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

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

	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);
	return;

no_join:
	rcu_read_unlock();
	return;
}

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) {
		spin_lock(&grp->lock);
		for (i = 0; i < 2*nr_node_ids; i++)
			grp->faults[i] -= p->numa_faults[i];
		grp->total_faults -= p->total_numa_faults;

		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;
		memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
	}

	/*
	 * 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, flags, &priv);
	}

	task_numa_placement(p);

	/*
	 * Retry task to preferred node migration periodically, in case it
	 * case it previously failed, or the scheduler moved us.
	 */
	if (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;
	p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += 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_scan) {
		mm->numa_next_scan = now +
			msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
	}

	/*
	 * 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:
	/*
	 * 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)
{
}

static inline void account_numa_enqueue(struct rq *rq, struct task_struct *p)
{
}

static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p)
{
}
#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)) {
		struct rq *rq = rq_of(cfs_rq);

		account_numa_enqueue(rq, task_of(se));
		list_add(&se->group_node, &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)) {
		account_numa_dequeue(rq_of(cfs_rq), task_of(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((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 cfs_bandwidth_usage_inc(void)
{
	static_key_slow_inc(&__cfs_bandwidth_used);
}

void cfs_bandwidth_usage_dec(void)
{
	static_key_slow_dec(&__cfs_bandwidth_used);
}
#else /* HAVE_JUMP_LABEL */
static bool cfs_bandwidth_used(void)
{
	return true;
}

void cfs_bandwidth_usage_inc(void) {}
void cfs_bandwidth_usage_dec(void) {}
#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);
	if (!cfs_b->timer_active)
		__start_cfs_bandwidth(cfs_b);
	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)