kernel_xiaomi_raphael/kernel/sched/fair.c

// SPDX-License-Identifier: GPL-2.0
/*
 * 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
 */

#include <linux/sched/mm.h>
#include <linux/sched/topology.h>

#include <linux/latencytop.h>
#include <linux/cpumask.h>
#include <linux/cpuidle.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 <linux/rbtree_augmented.h>

#include <trace/events/sched.h>

#include "sched.h"
#include "tune.h"
#include "walt.h"

#ifdef CONFIG_SMP
static inline bool task_fits_max(struct task_struct *p, int cpu);
#endif /* CONFIG_SMP */

#ifdef CONFIG_SCHED_WALT

static void walt_fixup_sched_stats_fair(struct rq *rq, struct task_struct *p,
					u16 updated_demand_scaled,
					u16 updated_pred_demand_scaled);
static void walt_fixup_nr_big_tasks(struct rq *rq, struct task_struct *p,
					int delta, bool inc);
#endif /* CONFIG_SCHED_WALT */

#if defined(CONFIG_SCHED_WALT) && defined(CONFIG_CFS_BANDWIDTH)

static void walt_init_cfs_rq_stats(struct cfs_rq *cfs_rq);
static void walt_inc_cfs_rq_stats(struct cfs_rq *cfs_rq,
				  struct task_struct *p);
static void walt_dec_cfs_rq_stats(struct cfs_rq *cfs_rq,
				  struct task_struct *p);
static void walt_inc_throttled_cfs_rq_stats(struct walt_sched_stats *stats,
					    struct cfs_rq *cfs_rq);
static void walt_dec_throttled_cfs_rq_stats(struct walt_sched_stats *stats,
					    struct cfs_rq *cfs_rq);
#else
static inline void walt_init_cfs_rq_stats(struct cfs_rq *cfs_rq) {}
static inline void
walt_inc_cfs_rq_stats(struct cfs_rq *cfs_rq, struct task_struct *p) {}
static inline void
walt_dec_cfs_rq_stats(struct cfs_rq *cfs_rq, struct task_struct *p) {}

#define walt_inc_throttled_cfs_rq_stats(...)
#define walt_dec_throttled_cfs_rq_stats(...)

#endif

/*
 * Enable/disable honoring sync flag in energy-aware wakeups.
 */
unsigned int sysctl_sched_sync_hint_enable = 1;
/*
 * Enable/disable using cstate knowledge in idle sibling selection
 */
unsigned int sysctl_sched_cstate_aware = 1;

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

/*
 * Minimal preemption granularity for CPU-bound tasks:
 *
 * (default: 2.8 msec * (1 + ilog(ncpus)), units: nanoseconds)
 */
unsigned int sysctl_sched_base_slice			= 2800000ULL;
static unsigned int normalized_sysctl_sched_base_slice	= 2800000ULL;

/*
 * To enable/disable energy aware feature.
 */
unsigned int __read_mostly sysctl_sched_energy_aware = 1;

const_debug unsigned int sysctl_sched_migration_cost	= 500000UL;
DEFINE_PER_CPU_READ_MOSTLY(int, sched_load_boost);

#ifdef CONFIG_SCHED_WALT
unsigned int sysctl_sched_use_walt_cpu_util = 1;
unsigned int sysctl_sched_use_walt_task_util = 1;
__read_mostly unsigned int sysctl_sched_walt_cpu_high_irqload =
    (10 * NSEC_PER_MSEC);
#endif

int sched_thermal_decay_shift;
static int __init setup_sched_thermal_decay_shift(char *str)
{
	int _shift = 0;

	if (kstrtoint(str, 0, &_shift))
		pr_warn("Unable to set scheduler thermal pressure decay shift parameter\n");

	sched_thermal_decay_shift = clamp(_shift, 0, 10);
	return 1;
}
__setup("sched_thermal_decay_shift=", setup_sched_thermal_decay_shift);

#ifdef CONFIG_SMP
/*
 * For asym packing, by default the lower numbered cpu has higher priority.
 */
int __weak arch_asym_cpu_priority(int cpu)
{
	return -arch_scale_cpu_capacity(cpu);
}

/*
 * The margin used when comparing CPU capacities.
 * is 'cap1' noticeably greater than 'cap2'
 *
 * (default: ~5%)
 */
#define capacity_greater(cap1, cap2) ((cap1) * 1024 > (cap2) * 1078)
#endif

#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

/*
 * The margin used when comparing utilization with CPU capacity.
 *
 * (default: ~20%)
 */
#define fits_capacity(cap, max)	((cap) * 1280 < (max) * 1024)

unsigned int capacity_margin				= 1280;

/* Migration margins */
unsigned int sysctl_sched_capacity_margin_up[MAX_MARGIN_LEVELS] = {
			[0 ... MAX_MARGIN_LEVELS-1] = 1078}; /* ~5% margin */
unsigned int sysctl_sched_capacity_margin_down[MAX_MARGIN_LEVELS] = {
			[0 ... MAX_MARGIN_LEVELS-1] = 1205}; /* ~15% margin */
unsigned int sched_capacity_margin_up[NR_CPUS] = {
			[0 ... NR_CPUS-1] = 1078}; /* ~5% margin */
unsigned int sched_capacity_margin_down[NR_CPUS] = {
			[0 ... NR_CPUS-1] = 1205}; /* ~15% margin */

#ifdef CONFIG_SCHED_WALT
/* 1ms default for 20ms window size scaled to 1024 */
unsigned int sysctl_sched_min_task_util_for_boost = 51;
/* 0.68ms default for 20ms window size scaled to 1024 */
unsigned int sysctl_sched_min_task_util_for_colocation = 35;
#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 unsigned int get_update_sysctl_factor(void)
{
	unsigned int cpus = min_t(unsigned 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_base_slice);
#undef SET_SYSCTL
}

void sched_init_granularity(void)
{
	update_sysctl();
}

#define WMULT_CONST	(~0U)
#define WMULT_SHIFT	32

static void __update_inv_weight(struct load_weight *lw)
{
	unsigned long w;

	if (likely(lw->inv_weight))
		return;

	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;
}

/*
 * delta_exec * weight / lw.weight
 *   OR
 * (delta_exec * (weight * lw->inv_weight)) >> WMULT_SHIFT
 *
 * Either weight := NICE_0_LOAD and lw \e sched_prio_to_wmult[], in which case
 * we're guaranteed shift stays positive because inv_weight is guaranteed to
 * fit 32 bits, and NICE_0_LOAD gives another 10 bits; therefore shift >= 22.
 *
 * Or, weight =< lw.weight (because lw.weight is the runqueue weight), thus
 * weight/lw.weight <= 1, and therefore our shift will also be positive.
 */
static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw)
{
	u64 fact = scale_load_down(weight);
	u32 fact_hi = (u32)(fact >> 32);
	int shift = WMULT_SHIFT;
	int fs;

	__update_inv_weight(lw);

	if (unlikely(fact_hi)) {
		fs = fls(fact_hi);
		shift -= fs;
		fact >>= fs;
	}

	/* hint to use a 32x32->64 mul */
	fact = (u64)(u32)fact * lw->inv_weight;

	fact_hi = (u32)(fact >> 32);
	if (fact_hi) {
		fs = fls(fact_hi);
		shift -= fs;
		fact >>= fs;
	}

	return mul_u64_u32_shr(delta_exec, fact, shift);
}

/*
 * delta /= w
 */
static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se)
{
	if (unlikely(se->load.weight != NICE_0_LOAD))
		delta = __calc_delta(delta, NICE_0_LOAD, &se->load);

	return delta;
}

const struct sched_class fair_sched_class;

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

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

/* Walk up scheduling entities hierarchy */
#define for_each_sched_entity(se) \
		for (; se; se = se->parent)

static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
	return p->se.cfs_rq;
}

/* runqueue on which this entity is (to be) queued */
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
{
	return se->cfs_rq;
}

/* runqueue "owned" by this group */
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
	return grp->my_q;
}

static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
	struct rq *rq = rq_of(cfs_rq);
	int cpu = cpu_of(rq);

	if (cfs_rq->on_list)
		return rq->tmp_alone_branch == &rq->leaf_cfs_rq_list;

	cfs_rq->on_list = 1;

	/*
	 * 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 and a special case for the root
	 * cfs_rq. Furthermore, it also means that we will always reset
	 * tmp_alone_branch either when the branch is connected
	 * to a tree or when we reach the top of the tree
	 */
	if (cfs_rq->tg->parent &&
	    cfs_rq->tg->parent->cfs_rq[cpu]->on_list) {
		/*
		 * If parent is already on the list, we add the child
		 * just before. Thanks to circular linked property of
		 * the list, this means to put the child at the tail
		 * of the list that starts by parent.
		 */
		list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
			&(cfs_rq->tg->parent->cfs_rq[cpu]->leaf_cfs_rq_list));
		/*
		 * The branch is now connected to its tree so we can
		 * reset tmp_alone_branch to the beginning of the
		 * list.
		 */
		rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
		return true;
	}

	if (!cfs_rq->tg->parent) {
		/*
		 * cfs rq without parent should be put
		 * at the tail of the list.
		 */
		list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
			&rq->leaf_cfs_rq_list);
		/*
		 * We have reach the top of a tree so we can reset
		 * tmp_alone_branch to the beginning of the list.
		 */
		rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
		return true;
	}

	/*
	 * The parent has not already been added so we want to
	 * make sure that it will be put after us.
	 * tmp_alone_branch points to the begin of the branch
	 * where we will add parent.
	 */
	list_add_rcu(&cfs_rq->leaf_cfs_rq_list, rq->tmp_alone_branch);
	/*
	 * update tmp_alone_branch to points to the new begin
	 * of the branch
	 */
	rq->tmp_alone_branch = &cfs_rq->leaf_cfs_rq_list;
	return false;
}

static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
	if (cfs_rq->on_list) {
		struct rq *rq = rq_of(cfs_rq);

		/*
		 * With cfs_rq being unthrottled/throttled during an enqueue,
		 * it can happen the tmp_alone_branch points the a leaf that
		 * we finally want to del. In this case, tmp_alone_branch moves
		 * to the prev element but it will point to rq->leaf_cfs_rq_list
		 * at the end of the enqueue.
		 */
		if (rq->tmp_alone_branch == &cfs_rq->leaf_cfs_rq_list)
			rq->tmp_alone_branch = cfs_rq->leaf_cfs_rq_list.prev;

		list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
		cfs_rq->on_list = 0;
	}
}

static inline void assert_list_leaf_cfs_rq(struct rq *rq)
{
	SCHED_WARN_ON(rq->tmp_alone_branch != &rq->leaf_cfs_rq_list);
}

/* Iterate thr' all leaf cfs_rq's on a runqueue */
#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)			\
	list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list,	\
				 leaf_cfs_rq_list)

/* Do the two (enqueued) entities belong to the same group ? */
static inline struct cfs_rq *
is_same_group(struct sched_entity *se, struct sched_entity *pse)
{
	if (se->cfs_rq == pse->cfs_rq)
		return se->cfs_rq;

	return NULL;
}

static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
	return se->parent;
}

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 = (*se)->depth;
	pse_depth = (*pse)->depth;

	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);
}

#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 bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
	return true;
}

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

static inline void assert_list_leaf_cfs_rq(struct rq *rq)
{
}

#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)	\
		for (cfs_rq = &rq->cfs, pos = NULL; cfs_rq; cfs_rq = pos)

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, u64 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 bool entity_before(struct sched_entity *a,
				struct sched_entity *b)
{
	/*
	 * Tiebreak on vruntime seems unnecessary since it can
	 * hardly happen.
	 */
	return (s64)(a->deadline - b->deadline) < 0;
}

static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	return (s64)(se->vruntime - cfs_rq->min_vruntime);
}

#define __node_2_se(node) \
	rb_entry((node), struct sched_entity, run_node)

/*
 * Compute virtual time from the per-task service numbers:
 *
 * Fair schedulers conserve lag:
 *
 *   \Sum lag_i = 0
 *
 * Where lag_i is given by:
 *
 *   lag_i = S - s_i = w_i * (V - v_i)
 *
 * Where S is the ideal service time and V is it's virtual time counterpart.
 * Therefore:
 *
 *   \Sum lag_i = 0
 *   \Sum w_i * (V - v_i) = 0
 *   \Sum w_i * V - w_i * v_i = 0
 *
 * From which we can solve an expression for V in v_i (which we have in
 * se->vruntime):
 *
 *       \Sum v_i * w_i   \Sum v_i * w_i
 *   V = -------------- = --------------
 *          \Sum w_i            W
 *
 * Specifically, this is the weighted average of all entity virtual runtimes.
 *
 * [[ NOTE: this is only equal to the ideal scheduler under the condition
 *          that join/leave operations happen at lag_i = 0, otherwise the
 *          virtual time has non-continguous motion equivalent to:
 *
 *	      V +-= lag_i / W
 *
 *	    Also see the comment in place_entity() that deals with this. ]]
 *
 * However, since v_i is u64, and the multiplcation could easily overflow
 * transform it into a relative form that uses smaller quantities:
 *
 * Substitute: v_i == (v_i - v0) + v0
 *
 *     \Sum ((v_i - v0) + v0) * w_i   \Sum (v_i - v0) * w_i
 * V = ---------------------------- = --------------------- + v0
 *                  W                            W
 *
 * Which we track using:
 *
 *                    v0 := cfs_rq->min_vruntime
 * \Sum (v_i - v0) * w_i := cfs_rq->avg_vruntime
 *              \Sum w_i := cfs_rq->avg_load
 *
 * Since min_vruntime is a monotonic increasing variable that closely tracks
 * the per-task service, these deltas: (v_i - v), will be in the order of the
 * maximal (virtual) lag induced in the system due to quantisation.
 *
 * Also, we use scale_load_down() to reduce the size.
 *
 * As measured, the max (key * weight) value was ~44 bits for a kernel build.
 */
static void
avg_vruntime_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	unsigned long weight = scale_load_down(se->load.weight);
	s64 key = entity_key(cfs_rq, se);

	cfs_rq->avg_vruntime += key * weight;
	cfs_rq->avg_load += weight;
}

static void
avg_vruntime_sub(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	unsigned long weight = scale_load_down(se->load.weight);
	s64 key = entity_key(cfs_rq, se);

	cfs_rq->avg_vruntime -= key * weight;
	cfs_rq->avg_load -= weight;
}

static inline
void avg_vruntime_update(struct cfs_rq *cfs_rq, s64 delta)
{
	/*
	 * v' = v + d ==> avg_vruntime' = avg_runtime - d*avg_load
	 */
	cfs_rq->avg_vruntime -= cfs_rq->avg_load * delta;
}

/*
 * Specifically: avg_runtime() + 0 must result in entity_eligible() := true
 * For this to be so, the result of this function must have a left bias.
 */
u64 avg_vruntime(struct cfs_rq *cfs_rq)
{
	struct sched_entity *curr = cfs_rq->curr;
	s64 avg = cfs_rq->avg_vruntime;
	long load = cfs_rq->avg_load;

	if (curr && curr->on_rq) {
		unsigned long weight = scale_load_down(curr->load.weight);

		avg += entity_key(cfs_rq, curr) * weight;
		load += weight;
	}

	if (load) {
		/* sign flips effective floor / ceil */
		if (avg < 0)
			avg -= (load - 1);
		avg = div_s64(avg, load);
	}

	return cfs_rq->min_vruntime + avg;
}

/*
 * lag_i = S - s_i = w_i * (V - v_i)
 *
 * However, since V is approximated by the weighted average of all entities it
 * is possible -- by addition/removal/reweight to the tree -- to move V around
 * and end up with a larger lag than we started with.
 *
 * Limit this to either double the slice length with a minimum of TICK_NSEC
 * since that is the timing granularity.
 *
 * EEVDF gives the following limit for a steady state system:
 *
 *   -r_max < lag < max(r_max, q)
 *
 * XXX could add max_slice to the augmented data to track this.
 */
s64 entity_lag(u64 avruntime, struct sched_entity *se)
{
	s64 vlag, limit;

	vlag = avruntime - se->vruntime;
	limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);

	return clamp(vlag, -limit, limit);
}

void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	SCHED_WARN_ON(!se->on_rq);

	se->vlag = entity_lag(avg_vruntime(cfs_rq), se);
}

/*
 * Entity is eligible once it received less service than it ought to have,
 * eg. lag >= 0.
 *
 * lag_i = S - s_i = w_i*(V - v_i)
 *
 * lag_i >= 0 -> V >= v_i
 *
 *     \Sum (v_i - v)*w_i
 * V = ------------------ + v
 *          \Sum w_i
 *
 * lag_i >= 0 -> \Sum (v_i - v)*w_i >= (v_i - v)*(\Sum w_i)
 *
 * Note: using 'avg_vruntime() > se->vruntime' is inacurate due
 *       to the loss in precision caused by the division.
 */
static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime)
{
	struct sched_entity *curr = cfs_rq->curr;
	s64 avg = cfs_rq->avg_vruntime;
	long load = cfs_rq->avg_load;

	if (curr && curr->on_rq) {
		unsigned long weight = scale_load_down(curr->load.weight);

		avg += entity_key(cfs_rq, curr) * weight;
		load += weight;
	}

	return avg >= (s64)(vruntime - cfs_rq->min_vruntime) * load;
}

int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	if (!sched_feat(ENFORCE_ELIGIBILITY))
		return 1;

	return vruntime_eligible(cfs_rq, se->vruntime);
}

static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime)
{
	u64 min_vruntime = cfs_rq->min_vruntime;
	/*
	 * open coded max_vruntime() to allow updating avg_vruntime
	 */
	s64 delta = (s64)(vruntime - min_vruntime);
	if (delta > 0) {
		avg_vruntime_update(cfs_rq, delta);
		min_vruntime = vruntime;
	}
	return min_vruntime;
}

static void update_min_vruntime(struct cfs_rq *cfs_rq)
{
	struct sched_entity *se = __pick_root_entity(cfs_rq);
	struct sched_entity *curr = cfs_rq->curr;
	u64 vruntime = cfs_rq->min_vruntime;

	if (curr) {
		if (curr->on_rq)
			vruntime = curr->vruntime;
		else
			curr = NULL;
	}

	if (se) {
		if (!curr)
			vruntime = se->min_vruntime;
		else
			vruntime = min_vruntime(vruntime, se->min_vruntime);
	}

	/* ensure we never gain time by being placed backwards. */
	u64_u32_store(cfs_rq->min_vruntime,
		      __update_min_vruntime(cfs_rq, vruntime));
}

static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
{
	return entity_before(__node_2_se(a), __node_2_se(b));
}

#define vruntime_gt(field, lse, rse) ({ (s64)((lse)->field - (rse)->field) > 0; })

static inline void __min_vruntime_update(struct sched_entity *se, struct rb_node *node)
{
	if (node) {
		struct sched_entity *rse = __node_2_se(node);
		if (vruntime_gt(min_vruntime, se, rse))
			se->min_vruntime = rse->min_vruntime;
	}
}

/*
 * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime)
 */
static inline bool min_vruntime_update(struct sched_entity *se, bool exit)
{
	u64 old_min_vruntime = se->min_vruntime;
	struct rb_node *node = &se->run_node;

	se->min_vruntime = se->vruntime;
	__min_vruntime_update(se, node->rb_right);
	__min_vruntime_update(se, node->rb_left);

	return se->min_vruntime == old_min_vruntime;
}

RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
		     run_node, min_vruntime, min_vruntime_update);

/*
 * Enqueue an entity into the rb-tree:
 */
static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	avg_vruntime_add(cfs_rq, se);
	se->min_vruntime = se->vruntime;
	rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
				__entity_less, &min_vruntime_cb);
}

static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
				  &min_vruntime_cb);
	avg_vruntime_sub(cfs_rq, se);
}

struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq)
{
	struct rb_node *root = cfs_rq->tasks_timeline.rb_root.rb_node;

	if (!root)
		return NULL;

	return __node_2_se(root);
}

struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
{
	struct rb_node *left = rb_first_cached(&cfs_rq->tasks_timeline);

	if (!left)
		return NULL;

	return __node_2_se(left);
}

/*
 * Earliest Eligible Virtual Deadline First
 *
 * In order to provide latency guarantees for different request sizes
 * EEVDF selects the best runnable task from two criteria:
 *
 *  1) the task must be eligible (must be owed service)
 *
 *  2) from those tasks that meet 1), we select the one
 *     with the earliest virtual deadline.
 *
 * We can do this in O(log n) time due to an augmented RB-tree. The
 * tree keeps the entries sorted on deadline, but also functions as a
 * heap based on the vruntime by keeping:
 *
 *  se->min_vruntime = min(se->vruntime, se->{left,right}->min_vruntime)
 *
 * Which allows tree pruning through eligibility.
 */
static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
{
	struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
	struct sched_entity *se = __pick_first_entity(cfs_rq);
	struct sched_entity *curr = cfs_rq->curr;
	struct sched_entity *best = NULL;

	/*
	 * We can safely skip eligibility check if there is only one entity
	 * in this cfs_rq, saving some cycles.
	 */
	if (cfs_rq->nr_running == 1)
		return curr && curr->on_rq ? curr : se;

	if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
		curr = NULL;

	/*
	 * Once selected, run a task until it either becomes non-eligible or
	 * until it gets a new slice. See the HACK in set_next_entity().
	 */
	if (sched_feat(RUN_TO_PARITY) && curr && curr->vlag == curr->deadline)
		return curr;

	/* Pick the leftmost entity if it's eligible */
	if (se && entity_eligible(cfs_rq, se)) {
		best = se;
		goto found;
	}

	/* Heap search for the EEVD entity */
	while (node) {
		struct rb_node *left = node->rb_left;

		/*
		 * Eligible entities in left subtree are always better
		 * choices, since they have earlier deadlines.
		 */
		if (left && vruntime_eligible(cfs_rq,
					__node_2_se(left)->min_vruntime)) {
			node = left;
			continue;
		}

		se = __node_2_se(node);

		/*
		 * The left subtree either is empty or has no eligible
		 * entity, so check the current node since it is the one
		 * with earliest deadline that might be eligible.
		 */
		if (entity_eligible(cfs_rq, se)) {
			best = se;
			break;
		}

		node = node->rb_right;
	}
found:
	if (!best || (curr && entity_before(curr, best)))
		best = curr;

	return best;
}

#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.rb_root);

	if (!last)
		return NULL;

	return __node_2_se(last);
}

/**************************************************************
 * 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);
	unsigned int factor = get_update_sysctl_factor();

	if (ret || !write)
		return ret;

#define WRT_SYSCTL(name) \
	(normalized_sysctl_##name = sysctl_##name / (factor))
	WRT_SYSCTL(sched_base_slice);
#undef WRT_SYSCTL

	return 0;
}
#endif

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

/*
 * XXX: strictly: vd_i += N*r_i/w_i such that: vd_i > ve_i
 * this is probably good enough.
 */
static void update_deadline(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	if ((s64)(se->vruntime - se->deadline) < 0)
		return;

	/*
	 * For EEVDF the virtual time slope is determined by w_i (iow.
	 * nice) while the request time r_i is determined by
	 * sysctl_sched_base_slice.
	 */
	se->slice = sysctl_sched_base_slice;

	/*
	 * EEVDF: vd_i = ve_i + r_i / w_i
	 */
	se->deadline = se->vruntime + calc_delta_fair(se->slice, se);

	/*
	 * The task has consumed its request, reschedule.
	 */
	if (cfs_rq->nr_running > 1) {
		resched_curr(rq_of(cfs_rq));
		clear_buddies(cfs_rq, se);
	}
}

#include "pelt.h"
#ifdef CONFIG_SMP

static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
static unsigned long task_h_load(struct task_struct *p);
static unsigned long capacity_of(int cpu);

/* Give new sched_entity start runnable values to heavy its load in infant time */
void init_entity_runnable_average(struct sched_entity *se)
{
	struct sched_avg *sa = &se->avg;

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

	/*
	 * Tasks are intialized with full load to be seen as heavy tasks until
	 * they get a chance to stabilize to their real load level.
	 * Group entities are intialized with zero load to reflect the fact that
	 * nothing has been attached to the task group yet.
	 */
	if (entity_is_task(se))
		sa->runnable_load_avg = sa->load_avg = scale_load_down(se->load.weight);

	se->runnable_weight = se->load.weight;
	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
}

static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
static void attach_entity_cfs_rq(struct sched_entity *se);

/*
 * With new tasks being created, their initial util_avgs are extrapolated
 * based on the cfs_rq's current util_avg:
 *
 *   util_avg = cfs_rq->avg.util_avg / (cfs_rq->avg.load_avg + 1)
 *		* se_weight(se)
 *
 * However, in many cases, the above util_avg does not give a desired
 * value. Moreover, the sum of the util_avgs may be divergent, such
 * as when the series is a harmonic series.
 *
 * To solve this problem, we also cap the util_avg of successive tasks to
 * only 1/2 of the left utilization budget:
 *
 *   util_avg_cap = (cpu_scale - cfs_rq->avg.util_avg) / 2^n
 *
 * where n denotes the nth task and cpu_scale the CPU capacity.
 *
 * For example, for a CPU with 1024 of capacity, a simplest series from
 * the beginning would be like:
 *
 *  task  util_avg: 512, 256, 128,  64,  32,   16,    8, ...
 * cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ...
 *
 * Finally, that extrapolated util_avg is clamped to the cap (util_avg_cap)
 * if util_avg > util_avg_cap.
 */
void post_init_entity_util_avg(struct sched_entity *se)
{
	struct cfs_rq *cfs_rq = cfs_rq_of(se);
	struct sched_avg *sa = &se->avg;
	long cpu_scale = arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq)));
	long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2;

	if (cap > 0) {
		if (cfs_rq->avg.util_avg != 0) {
			sa->util_avg  = cfs_rq->avg.util_avg * se_weight(se);
			sa->util_avg /= (cfs_rq->avg.load_avg + 1);

			if (sa->util_avg > cap)
				sa->util_avg = cap;
		} else {
			sa->util_avg = cap;
		}
	}

	if (entity_is_task(se)) {
		struct task_struct *p = task_of(se);
		if (p->sched_class != &fair_sched_class) {
			/*
			 * For !fair tasks do:
			 *
			update_cfs_rq_load_avg(now, cfs_rq);
			attach_entity_load_avg(cfs_rq, se);
			switched_from_fair(rq, p);
			 *
			 * such that the next switched_to_fair() has the
			 * expected state.
			 */
			se->avg.last_update_time = cfs_rq_clock_pelt(cfs_rq);
			return;
		}
	}

	attach_entity_cfs_rq(se);
}

#else /* !CONFIG_SMP */
void init_entity_runnable_average(struct sched_entity *se)
{
}
void post_init_entity_util_avg(struct sched_entity *se)
{
}
static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
{
}
#endif /* CONFIG_SMP */

/*
 * Update the current task's runtime statistics.
 */
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));
	u64 delta_exec;

	if (unlikely(!curr))
		return;

	delta_exec = now - curr->exec_start;
	if (unlikely((s64)delta_exec <= 0))
		return;

	curr->exec_start = now;

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

	curr->sum_exec_runtime += delta_exec;
	schedstat_add(cfs_rq->exec_clock, delta_exec);

	curr->vruntime += calc_delta_fair(delta_exec, curr);
	update_deadline(cfs_rq, curr);
	update_min_vruntime(cfs_rq);

	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 void update_curr_fair(struct rq *rq)
{
	update_curr(cfs_rq_of(&rq->curr->se));
}

static inline void
update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	u64 wait_start, prev_wait_start;

	if (!schedstat_enabled())
		return;

	wait_start = rq_clock(rq_of(cfs_rq));
	prev_wait_start = schedstat_val(se->statistics.wait_start);

	if (entity_is_task(se) && task_on_rq_migrating(task_of(se)) &&
	    likely(wait_start > prev_wait_start))
		wait_start -= prev_wait_start;

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

static inline void
update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	struct task_struct *p;
	u64 delta;

	if (!schedstat_enabled())
		return;

	delta = rq_clock(rq_of(cfs_rq)) - schedstat_val(se->statistics.wait_start);

	if (entity_is_task(se)) {
		p = task_of(se);
		if (task_on_rq_migrating(p)) {
			/*
			 * Preserve migrating task's wait time so wait_start
			 * time stamp can be adjusted to accumulate wait time
			 * prior to migration.
			 */
			schedstat_set(se->statistics.wait_start, delta);
			return;
		}
		trace_sched_stat_wait(p, delta);
	}

	schedstat_set(se->statistics.wait_max,
		      max(schedstat_val(se->statistics.wait_max), delta));
	schedstat_inc(se->statistics.wait_count);
	schedstat_add(se->statistics.wait_sum, delta);
	schedstat_set(se->statistics.wait_start, 0);
}

static inline void
update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	struct task_struct *tsk = NULL;
	u64 sleep_start, block_start;

	if (!schedstat_enabled())
		return;

	sleep_start = schedstat_val(se->statistics.sleep_start);
	block_start = schedstat_val(se->statistics.block_start);

	if (entity_is_task(se))
		tsk = task_of(se);

	if (sleep_start) {
		u64 delta = rq_clock(rq_of(cfs_rq)) - sleep_start;

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

		if (unlikely(delta > schedstat_val(se->statistics.sleep_max)))
			schedstat_set(se->statistics.sleep_max, delta);

		schedstat_set(se->statistics.sleep_start, 0);
		schedstat_add(se->statistics.sum_sleep_runtime, delta);

		if (tsk) {
			account_scheduler_latency(tsk, delta >> 10, 1);
			trace_sched_stat_sleep(tsk, delta);
		}
	}
	if (block_start) {
		u64 delta = rq_clock(rq_of(cfs_rq)) - block_start;

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

		if (unlikely(delta > schedstat_val(se->statistics.block_max)))
			schedstat_set(se->statistics.block_max, delta);

		schedstat_set(se->statistics.block_start, 0);
		schedstat_add(se->statistics.sum_sleep_runtime, delta);

		if (tsk) {
			if (tsk->in_iowait) {
				schedstat_add(se->statistics.iowait_sum, delta);
				schedstat_inc(se->statistics.iowait_count);
				trace_sched_stat_iowait(tsk, delta);
			}

			trace_sched_stat_blocked(tsk, delta);
			trace_sched_blocked_reason(tsk);

			/*
			 * 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);
		}
	}
}

/*
 * Task is being enqueued - update stats:
 */
static inline void
update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{
	if (!schedstat_enabled())
		return;

	/*
	 * 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);

	if (flags & ENQUEUE_WAKEUP)
		update_stats_enqueue_sleeper(cfs_rq, se);
}

static inline void
update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{

	if (!schedstat_enabled())
		return;

	/*
	 * Mark the end of the wait period if dequeueing a
	 * waiting task:
	 */
	if (se != cfs_rq->curr)
		update_stats_wait_end(cfs_rq, se);

	if ((flags & DEQUEUE_SLEEP) && entity_is_task(se)) {
		struct task_struct *tsk = task_of(se);

		if (tsk->state & TASK_INTERRUPTIBLE)
			schedstat_set(se->statistics.sleep_start,
				      rq_clock(rq_of(cfs_rq)));
		if (tsk->state & TASK_UNINTERRUPTIBLE)
			schedstat_set(se->statistics.block_start,
				      rq_clock(rq_of(cfs_rq)));
	}
}

/*
 * 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;

struct numa_group {
	atomic_t refcount;

	spinlock_t lock; /* nr_tasks, tasks */
	int nr_tasks;
	pid_t gid;
	int active_nodes;

	struct rcu_head rcu;
	unsigned long total_faults;
	unsigned long max_faults_cpu;
	/*
	 * Faults_cpu is used to decide whether memory should move
	 * towards the CPU. As a consequence, these stats are weighted
	 * more by CPU use than by memory faults.
	 */
	unsigned long *faults_cpu;
	unsigned long faults[0];
};

static inline unsigned long group_faults_priv(struct numa_group *ng);
static inline unsigned long group_faults_shared(struct numa_group *ng);

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_size = READ_ONCE(sysctl_numa_balancing_scan_size);
	unsigned int scan, floor;
	unsigned int windows = 1;

	if (scan_size < MAX_SCAN_WINDOW)
		windows = MAX_SCAN_WINDOW / 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_start(struct task_struct *p)
{
	unsigned long smin = task_scan_min(p);
	unsigned long period = smin;

	/* Scale the maximum scan period with the amount of shared memory. */
	if (p->numa_group) {
		struct numa_group *ng = p->numa_group;
		unsigned long shared = group_faults_shared(ng);
		unsigned long private = group_faults_priv(ng);

		period *= atomic_read(&ng->refcount);
		period *= shared + 1;
		period /= private + shared + 1;
	}

	return max(smin, period);
}

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

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

	/* Scale the maximum scan period with the amount of shared memory. */
	if (p->numa_group) {
		struct numa_group *ng = p->numa_group;
		unsigned long shared = group_faults_shared(ng);
		unsigned long private = group_faults_priv(ng);
		unsigned long period = smax;

		period *= atomic_read(&ng->refcount);
		period *= shared + 1;
		period /= private + shared + 1;

		smax = max(smax, period);
	}

	return max(smin, smax);
}

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));
}

/* Shared or private faults. */
#define NR_NUMA_HINT_FAULT_TYPES 2

/* Memory and CPU locality */
#define NR_NUMA_HINT_FAULT_STATS (NR_NUMA_HINT_FAULT_TYPES * 2)

/* Averaged statistics, and temporary buffers. */
#define NR_NUMA_HINT_FAULT_BUCKETS (NR_NUMA_HINT_FAULT_STATS * 2)

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

/*
 * The averaged statistics, shared & private, memory & cpu,
 * occupy the first half of the array. The second half of the
 * array is for current counters, which are averaged into the
 * first set by task_numa_placement.
 */
static inline int task_faults_idx(enum numa_faults_stats s, int nid, int priv)
{
	return NR_NUMA_HINT_FAULT_TYPES * (s * nr_node_ids + 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(NUMA_MEM, nid, 0)] +
		p->numa_faults[task_faults_idx(NUMA_MEM, 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[task_faults_idx(NUMA_MEM, nid, 0)] +
		p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)];
}

static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
{
	return group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 0)] +
		group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)];
}

static inline unsigned long group_faults_priv(struct numa_group *ng)
{
	unsigned long faults = 0;
	int node;

	for_each_online_node(node) {
		faults += ng->faults[task_faults_idx(NUMA_MEM, node, 1)];
	}

	return faults;
}

static inline unsigned long group_faults_shared(struct numa_group *ng)
{
	unsigned long faults = 0;
	int node;

	for_each_online_node(node) {
		faults += ng->faults[task_faults_idx(NUMA_MEM, node, 0)];
	}

	return faults;
}

/*
 * A node triggering more than 1/3 as many NUMA faults as the maximum is
 * considered part of a numa group's pseudo-interleaving set. Migrations
 * between these nodes are slowed down, to allow things to settle down.
 */
#define ACTIVE_NODE_FRACTION 3

static bool numa_is_active_node(int nid, struct numa_group *ng)
{
	return group_faults_cpu(ng, nid) * ACTIVE_NODE_FRACTION > ng->max_faults_cpu;
}

/* Handle placement on systems where not all nodes are directly connected. */
static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
					int maxdist, bool task)
{
	unsigned long score = 0;
	int node;

	/*
	 * All nodes are directly connected, and the same distance
	 * from each other. No need for fancy placement algorithms.
	 */
	if (sched_numa_topology_type == NUMA_DIRECT)
		return 0;

	/*
	 * This code is called for each node, introducing N^2 complexity,
	 * which should be ok given the number of nodes rarely exceeds 8.
	 */
	for_each_online_node(node) {
		unsigned long faults;
		int dist = node_distance(nid, node);

		/*
		 * The furthest away nodes in the system are not interesting
		 * for placement; nid was already counted.
		 */
		if (dist == sched_max_numa_distance || node == nid)
			continue;

		/*
		 * On systems with a backplane NUMA topology, compare groups
		 * of nodes, and move tasks towards the group with the most
		 * memory accesses. When comparing two nodes at distance
		 * "hoplimit", only nodes closer by than "hoplimit" are part
		 * of each group. Skip other nodes.
		 */
		if (sched_numa_topology_type == NUMA_BACKPLANE &&
					dist > maxdist)
			continue;

		/* Add up the faults from nearby nodes. */
		if (task)
			faults = task_faults(p, node);
		else
			faults = group_faults(p, node);

		/*
		 * On systems with a glueless mesh NUMA topology, there are
		 * no fixed "groups of nodes". Instead, nodes that are not
		 * directly connected bounce traffic through intermediate
		 * nodes; a numa_group can occupy any set of nodes.
		 * The further away a node is, the less the faults count.
		 * This seems to result in good task placement.
		 */
		if (sched_numa_topology_type == NUMA_GLUELESS_MESH) {
			faults *= (sched_max_numa_distance - dist);
			faults /= (sched_max_numa_distance - LOCAL_DISTANCE);
		}

		score += faults;
	}

	return score;
}

/*
 * 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,
					int dist)
{
	unsigned long faults, total_faults;

	if (!p->numa_faults)
		return 0;

	total_faults = p->total_numa_faults;

	if (!total_faults)
		return 0;

	faults = task_faults(p, nid);
	faults += score_nearby_nodes(p, nid, dist, true);

	return 1000 * faults / total_faults;
}

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

	if (!p->numa_group)
		return 0;

	total_faults = p->numa_group->total_faults;

	if (!total_faults)
		return 0;

	faults = group_faults(p, nid);
	faults += score_nearby_nodes(p, nid, dist, false);

	return 1000 * faults / total_faults;
}

bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
				int src_nid, int dst_cpu)
{
	struct numa_group *ng = p->numa_group;
	int dst_nid = cpu_to_node(dst_cpu);
	int last_cpupid, this_cpupid;

	this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);

	/*
	 * Multi-stage node selection is used in conjunction with a periodic
	 * migration fault to build a temporal task<->page relation. By using
	 * a two-stage filter we remove short/unlikely relations.
	 *
	 * Using P(p) ~ n_p / n_t as per frequentist probability, we can equate
	 * a task's usage of a particular page (n_p) per total usage of this
	 * page (n_t) (in a given time-span) to a probability.
	 *
	 * Our periodic faults will sample this probability and getting the
	 * same result twice in a row, given these samples are fully
	 * independent, is then given by P(n)^2, provided our sample period
	 * is sufficiently short compared to the usage pattern.
	 *
	 * This quadric squishes small probabilities, making it less likely we
	 * act on an unlikely task<->page relation.
	 */
	last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
	if (!cpupid_pid_unset(last_cpupid) &&
				cpupid_to_nid(last_cpupid) != dst_nid)
		return false;

	/* Always allow migrate on private faults */
	if (cpupid_match_pid(p, last_cpupid))
		return true;

	/* A shared fault, but p->numa_group has not been set up yet. */
	if (!ng)
		return true;

	/*
	 * Destination node is much more heavily used than the source
	 * node? Allow migration.
	 */
	if (group_faults_cpu(ng, dst_nid) > group_faults_cpu(ng, src_nid) *
					ACTIVE_NODE_FRACTION)
		return true;

	/*
	 * Distribute memory according to CPU & memory use on each node,
	 * with 3/4 hysteresis to avoid unnecessary memory migrations:
	 *
	 * faults_cpu(dst)   3   faults_cpu(src)
	 * --------------- * - > ---------------
	 * faults_mem(dst)   4   faults_mem(src)
	 */
	return group_faults_cpu(ng, dst_nid) * group_faults(p, src_nid) * 3 >
	       group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4;
}

static unsigned long weighted_cpuload(struct rq *rq);

/* 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 compute_capacity;

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

/*
 * XXX borrowed from update_sg_lb_stats
 */
static void update_numa_stats(struct numa_stats *ns, int nid)
{
	int smt, cpu, cpus = 0;
	unsigned long capacity;

	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(rq);
		ns->compute_capacity += capacity_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_free_capacity, or we'll detect a huge
	 * imbalance and bail there.
	 */
	if (!cpus)
		return;

	/* smt := ceil(cpus / capacity), assumes: 1 < smt_power < 2 */
	smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity);
	capacity = cpus / smt; /* cores */

	ns->task_capacity = min_t(unsigned, capacity,
		DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE));
	ns->has_free_capacity = (ns->nr_running < ns->task_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;
	int dist;

	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;
}

static bool load_too_imbalanced(long src_load, long dst_load,
				struct task_numa_env *env)
{
	long imb, old_imb;
	long orig_src_load, orig_dst_load;
	long src_capacity, dst_capacity;

	/*
	 * The load is corrected for the CPU capacity available on each node.
	 *
	 * src_load        dst_load
	 * ------------ vs ---------
	 * src_capacity    dst_capacity
	 */
	src_capacity = env->src_stats.compute_capacity;
	dst_capacity = env->dst_stats.compute_capacity;

	/* We care about the slope of the imbalance, not the direction. */
	if (dst_load < src_load)
		swap(dst_load, src_load);

	/* Is the difference below the threshold? */
	imb = dst_load * src_capacity * 100 -
	      src_load * dst_capacity * env->imbalance_pct;
	if (imb <= 0)
		return false;

	/*
	 * The imbalance is above the allowed threshold.
	 * Compare it with the old imbalance.
	 */
	orig_src_load = env->src_stats.load;
	orig_dst_load = env->dst_stats.load;

	if (orig_dst_load < orig_src_load)
		swap(orig_dst_load, orig_src_load);

	old_imb = orig_dst_load * src_capacity * 100 -
		  orig_src_load * dst_capacity * env->imbalance_pct;

	/* Would this change make things worse? */
	return (imb > old_imb);
}

/*
 * 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 src_load, dst_load;
	long load;
	long imp = env->p->numa_group ? groupimp : taskimp;
	long moveimp = imp;
	int dist = env->dist;

	rcu_read_lock();
	cur = task_rcu_dereference(&dst_rq->curr);
	if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur)))
		cur = NULL;

	/*
	 * Because we have preemption enabled we can get migrated around and
	 * end try selecting ourselves (current == env->p) as a swap candidate.
	 */
	if (cur == env->p)
		goto unlock;

	/*
	 * "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, cur->cpus_ptr))
			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, dist) -
			      task_weight(cur, env->dst_nid, dist);
			/*
			 * 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 (cur->numa_group)
				imp += group_weight(cur, env->src_nid, dist) -
				       group_weight(cur, env->dst_nid, dist);
			else
				imp += task_weight(cur, env->src_nid, dist) -
				       task_weight(cur, env->dst_nid, dist);
		}
	}

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

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

		goto balance;
	}

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

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

	if (moveimp > imp && moveimp > env->best_imp) {
		/*
		 * If the improvement from just moving env->p direction is
		 * better than swapping tasks around, check if a move is
		 * possible. Store a slightly smaller score than moveimp,
		 * so an actually idle CPU will win.
		 */
		if (!load_too_imbalanced(src_load, dst_load, env)) {
			imp = moveimp - 1;
			cur = NULL;
			goto assign;
		}
	}

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

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

	if (load_too_imbalanced(src_load, dst_load, env))
		goto unlock;

	/*
	 * One idle CPU per node is evaluated for a task numa move.
	 * Call select_idle_sibling to maybe find a better one.
	 */
	if (!cur) {
		/*
		 * select_idle_siblings() uses an per-cpu cpumask that
		 * can be used from IRQ context.
		 */
		local_irq_disable();
		env->dst_cpu = select_idle_sibling(env->p, env->src_cpu,
						   env->dst_cpu);
		local_irq_enable();
	}

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, env->p->cpus_ptr))
			continue;

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

/* Only move tasks to a NUMA node less busy than the current node. */
static bool numa_has_capacity(struct task_numa_env *env)
{
	struct numa_stats *src = &env->src_stats;
	struct numa_stats *dst = &env->dst_stats;

	if (src->has_free_capacity && !dst->has_free_capacity)
		return false;

	/*
	 * Only consider a task move if the source has a higher load
	 * than the destination, corrected for CPU capacity on each node.
	 *
	 *      src->load                dst->load
	 * --------------------- vs ---------------------
	 * src->compute_capacity    dst->compute_capacity
	 */
	if (src->load * dst->compute_capacity * env->imbalance_pct >

	    dst->load * src->compute_capacity * 100)
		return true;

	return false;
}

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, dist;
	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 = task_node(p);
		return -EINVAL;
	}

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

	/* Try to find a spot on the preferred nid. */
	if (numa_has_capacity(&env))
		task_numa_find_cpu(&env, taskimp, groupimp);

	/*
	 * Look at other nodes in these cases:
	 * - there is no space available on the preferred_nid
	 * - the task is part of a numa_group that is interleaved across
	 *   multiple NUMA nodes; in order to better consolidate the group,
	 *   we need to check other locations.
	 */
	if (env.best_cpu == -1 || (p->numa_group && p->numa_group->active_nodes > 1)) {
		for_each_online_node(nid) {
			if (nid == env.src_nid || nid == p->numa_preferred_nid)
				continue;

			dist = node_distance(env.src_nid, env.dst_nid);
			if (sched_numa_topology_type == NUMA_BACKPLANE &&
						dist != env.dist) {
				taskweight = task_weight(p, env.src_nid, dist);
				groupweight = group_weight(p, env.src_nid, dist);
			}

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

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

	/*
	 * If the task is part of a workload that spans multiple NUMA nodes,
	 * and is migrating into one of the workload's active nodes, remember
	 * this node as the task's preferred numa node, so the workload can
	 * settle down.
	 * A task that migrated to a second choice node will be better off
	 * trying for a better one later. Do not set the preferred node here.
	 */
	if (p->numa_group) {
		struct numa_group *ng = p->numa_group;

		if (env.best_cpu == -1)
			nid = env.src_nid;
		else
			nid = env.dst_nid;

		if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng))
			sched_setnuma(p, env.dst_nid);
	}

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

	/*
	 * 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_start(p);

	if (env.best_task == NULL) {
		ret = migrate_task_to(p, env.best_cpu);
		if (ret != 0)
			trace_sched_stick_numa(p, env.src_cpu, env.best_cpu);
		return ret;
	}

	ret = migrate_swap(p, env.best_task);
	if (ret != 0)
		trace_sched_stick_numa(p, env.src_cpu, task_cpu(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)
{
	unsigned long interval = HZ;

	/* 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 */
	interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16);
	p->numa_migrate_retry = jiffies + interval;

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

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

/*
 * Find out how many nodes on the workload is actively running on. Do this by
 * tracking the nodes from which NUMA hinting faults are triggered. This can
 * be different from the set of nodes where the workload's memory is currently
 * located.
 */
static void numa_group_count_active_nodes(struct numa_group *numa_group)
{
	unsigned long faults, max_faults = 0;
	int nid, active_nodes = 0;

	for_each_online_node(nid) {
		faults = group_faults_cpu(numa_group, nid);
		if (faults > max_faults)
			max_faults = faults;
	}

	for_each_online_node(nid) {
		faults = group_faults_cpu(numa_group, nid);
		if (faults * ACTIVE_NODE_FRACTION > max_faults)
			active_nodes++;
	}

	numa_group->max_faults_cpu = max_faults;
	numa_group->active_nodes = active_nodes;
}

/*
 * 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/(local+remote) ratio is
 * below NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS)
 * the scan period will decrease. Aim for 70% local accesses.
 */
#define NUMA_PERIOD_SLOTS 10
#define NUMA_PERIOD_THRESHOLD 7

/*
 * 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 lr_ratio, ps_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. Related to that, if there were failed
	 * migration then it implies we are migrating too quickly or the local
	 * node is overloaded. In either case, scan slower
	 */
	if (local + shared == 0 || p->numa_faults_locality[2]) {
		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);
	lr_ratio = (local * NUMA_PERIOD_SLOTS) / (local + remote);
	ps_ratio = (private * NUMA_PERIOD_SLOTS) / (private + shared);

	if (ps_ratio >= NUMA_PERIOD_THRESHOLD) {
		/*
		 * Most memory accesses are local. There is no need to
		 * do fast NUMA scanning, since memory is already local.
		 */
		int slot = ps_ratio - NUMA_PERIOD_THRESHOLD;
		if (!slot)
			slot = 1;
		diff = slot * period_slot;
	} else if (lr_ratio >= NUMA_PERIOD_THRESHOLD) {
		/*
		 * Most memory accesses are shared with other tasks.
		 * There is no point in continuing fast NUMA scanning,
		 * since other tasks may just move the memory elsewhere.
		 */
		int slot = lr_ratio - NUMA_PERIOD_THRESHOLD;
		if (!slot)
			slot = 1;
		diff = slot * period_slot;
	} else {
		/*
		 * Private memory faults exceed (SLOTS-THRESHOLD)/SLOTS,
		 * yet they are not on the local NUMA node. Speed up
		 * NUMA scanning to get the memory moved over.
		 */
		int ratio = max(lr_ratio, ps_ratio);
		diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot;
	}

	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));
}

/*
 * Get the fraction of time the task has been running since the last
 * NUMA placement cycle. The scheduler keeps similar statistics, but
 * decays those on a 32ms period, which is orders of magnitude off
 * from the dozens-of-seconds NUMA balancing period. Use the scheduler
 * stats only if the task is so new there are no NUMA statistics yet.
 */
static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
{
	u64 runtime, delta, now;
	/* Use the start of this time slice to avoid calculations. */
	now = p->se.exec_start;
	runtime = p->se.sum_exec_runtime;

	if (p->last_task_numa_placement) {
		delta = runtime - p->last_sum_exec_runtime;
		*period = now - p->last_task_numa_placement;

		/* Avoid time going backwards, prevent potential divide error: */
		if (unlikely((s64)*period < 0))
			*period = 0;
	} else {
		delta = p->se.avg.load_sum;
		*period = LOAD_AVG_MAX;
	}

	p->last_sum_exec_runtime = runtime;
	p->last_task_numa_placement = now;

	return delta;
}

/*
 * Determine the preferred nid for a task in a numa_group. This needs to
 * be done in a way that produces consistent results with group_weight,
 * otherwise workloads might not converge.
 */
static int preferred_group_nid(struct task_struct *p, int nid)
{
	nodemask_t nodes;
	int dist;

	/* Direct connections between all NUMA nodes. */
	if (sched_numa_topology_type == NUMA_DIRECT)
		return nid;

	/*
	 * On a system with glueless mesh NUMA topology, group_weight
	 * scores nodes according to the number of NUMA hinting faults on
	 * both the node itself, and on nearby nodes.
	 */
	if (sched_numa_topology_type == NUMA_GLUELESS_MESH) {
		unsigned long score, max_score = 0;
		int node, max_node = nid;

		dist = sched_max_numa_distance;

		for_each_online_node(node) {
			score = group_weight(p, node, dist);
			if (score > max_score) {
				max_score = score;
				max_node = node;
			}
		}
		return max_node;
	}

	/*
	 * Finding the preferred nid in a system with NUMA backplane
	 * interconnect topology is more involved. The goal is to locate
	 * tasks from numa_groups near each other in the system, and
	 * untangle workloads from different sides of the system. This requires
	 * searching down the hierarchy of node groups, recursively searching
	 * inside the highest scoring group of nodes. The nodemask tricks
	 * keep the complexity of the search down.
	 */
	nodes = node_online_map;
	for (dist = sched_max_numa_distance; dist > LOCAL_DISTANCE; dist--) {
		unsigned long max_faults = 0;
		nodemask_t max_group = NODE_MASK_NONE;
		int a, b;

		/* Are there nodes at this distance from each other? */
		if (!find_numa_distance(dist))
			continue;

		for_each_node_mask(a, nodes) {
			unsigned long faults = 0;
			nodemask_t this_group;
			nodes_clear(this_group);

			/* Sum group's NUMA faults; includes a==b case. */
			for_each_node_mask(b, nodes) {
				if (node_distance(a, b) < dist) {
					faults += group_faults(p, b);
					node_set(b, this_group);
					node_clear(b, nodes);
				}
			}

			/* Remember the top group. */
			if (faults > max_faults) {
				max_faults = faults;
				max_group = this_group;
				/*
				 * subtle: at the smallest distance there is
				 * just one node left in each "group", the
				 * winner is the preferred nid.
				 */
				nid = a;
			}
		}
		/* Next round, evaluate the nodes within max_group. */
		if (!max_faults)
			break;
		nodes = max_group;
	}
	return nid;
}

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 };
	unsigned long total_faults;
	u64 runtime, period;
	spinlock_t *group_lock = NULL;

	/*
	 * The p->mm->numa_scan_seq field gets updated without
	 * exclusive access. Use READ_ONCE() here to ensure
	 * that the field is read in a single access:
	 */
	seq = READ_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);

	total_faults = p->numa_faults_locality[0] +
		       p->numa_faults_locality[1];
	runtime = numa_get_avg_runtime(p, &period);

	/* 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_irq(group_lock);
	}

	/* Find the node with the highest number of faults */
	for_each_online_node(nid) {
		/* Keep track of the offsets in numa_faults array */
		int mem_idx, membuf_idx, cpu_idx, cpubuf_idx;
		unsigned long faults = 0, group_faults = 0;
		int priv;

		for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) {
			long diff, f_diff, f_weight;

			mem_idx = task_faults_idx(NUMA_MEM, nid, priv);
			membuf_idx = task_faults_idx(NUMA_MEMBUF, nid, priv);
			cpu_idx = task_faults_idx(NUMA_CPU, nid, priv);
			cpubuf_idx = task_faults_idx(NUMA_CPUBUF, nid, priv);

			/* Decay existing window, copy faults since last scan */
			diff = p->numa_faults[membuf_idx] - p->numa_faults[mem_idx] / 2;
			fault_types[priv] += p->numa_faults[membuf_idx];
			p->numa_faults[membuf_idx] = 0;

			/*
			 * Normalize the faults_from, so all tasks in a group
			 * count according to CPU use, instead of by the raw
			 * number of faults. Tasks with little runtime have
			 * little over-all impact on throughput, and thus their
			 * faults are less important.
			 */
			f_weight = div64_u64(runtime << 16, period + 1);
			f_weight = (f_weight * p->numa_faults[cpubuf_idx]) /
				   (total_faults + 1);
			f_diff = f_weight - p->numa_faults[cpu_idx] / 2;
			p->numa_faults[cpubuf_idx] = 0;

			p->numa_faults[mem_idx] += diff;
			p->numa_faults[cpu_idx] += f_diff;
			faults += p->numa_faults[mem_idx];
			p->total_numa_faults += diff;
			if (p->numa_group) {
				/*
				 * safe because we can only change our own group
				 *
				 * mem_idx represents the offset for a given
				 * nid and priv in a specific region because it
				 * is at the beginning of the numa_faults array.
				 */
				p->numa_group->faults[mem_idx] += diff;
				p->numa_group->faults_cpu[mem_idx] += f_diff;
				p->numa_group->total_faults += diff;
				group_faults += p->numa_group->faults[mem_idx];
			}
		}

		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) {
		numa_group_count_active_nodes(p->numa_group);
		spin_unlock_irq(group_lock);
		max_nid = preferred_group_nid(p, max_group_nid);
	}

	if (max_faults) {
		/* Set the new preferred node */
		if (max_nid != p->numa_preferred_nid)
			sched_setnuma(p, max_nid);

		if (task_node(p) != p->numa_preferred_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) +
				    4*nr_node_ids*sizeof(unsigned long);

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

		atomic_set(&grp->refcount, 1);
		grp->active_nodes = 1;
		grp->max_faults_cpu = 0;
		spin_lock_init(&grp->lock);
		grp->gid = p->pid;
		/* Second half of the array tracks nids where faults happen */
		grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES *
						nr_node_ids;

		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
			grp->faults[i] = p->numa_faults[i];

		grp->total_faults = p->total_numa_faults;

		grp->nr_tasks++;
		rcu_assign_pointer(p->numa_group, grp);
	}

	rcu_read_lock();
	tsk = READ_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;

	BUG_ON(irqs_disabled());
	double_lock_irq(&my_grp->lock, &grp->lock);

	for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * 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;

	my_grp->nr_tasks--;
	grp->nr_tasks++;

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

	rcu_assign_pointer(p->numa_group, grp);

	put_numa_group(my_grp);
	return;

no_join:
	rcu_read_unlock();
	return;
}

/*
 * Get rid of NUMA staticstics associated with a task (either current or dead).
 * If @final is set, the task is dead and has reached refcount zero, so we can
 * safely free all relevant data structures. Otherwise, there might be
 * concurrent reads from places like load balancing and procfs, and we should
 * reset the data back to default state without freeing ->numa_faults.
 */
void task_numa_free(struct task_struct *p, bool final)
{
	struct numa_group *grp = p->numa_group;
	unsigned long *numa_faults = p->numa_faults;
	unsigned long flags;
	int i;

	if (!numa_faults)
		return;

	if (grp) {
		spin_lock_irqsave(&grp->lock, flags);
		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
			grp->faults[i] -= p->numa_faults[i];
		grp->total_faults -= p->total_numa_faults;

		grp->nr_tasks--;
		spin_unlock_irqrestore(&grp->lock, flags);
		RCU_INIT_POINTER(p->numa_group, NULL);
		put_numa_group(grp);
	}

	if (final) {
		p->numa_faults = NULL;
		kfree(numa_faults);
	} else {
		p->total_numa_faults = 0;
		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
			numa_faults[i] = 0;
	}
}

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

	if (!IS_ENABLED(CONFIG_NUMA_BALANCING) ||
	    !static_branch_likely(&sched_numa_balancing))
		return;

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

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

		p->numa_faults = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
		if (!p->numa_faults)
			return;

		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);
	}

	/*
	 * If a workload spans multiple NUMA nodes, a shared fault that
	 * occurs wholly within the set of nodes that the workload is
	 * actively using should be counted as local. This allows the
	 * scan rate to slow down when a workload has settled down.
	 */
	ng = p->numa_group;
	if (!priv && !local && ng && ng->active_nodes > 1 &&
				numa_is_active_node(cpu_node, ng) &&
				numa_is_active_node(mem_node, ng))
		local = 1;

	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;
	if (flags & TNF_MIGRATE_FAIL)
		p->numa_faults_locality[2] += pages;

	p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages;
	p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages;
	p->numa_faults_locality[local] += pages;
}

static void reset_ptenuma_scan(struct task_struct *p)
{
	/*
	 * We only did a read acquisition of the mmap sem, so
	 * p->mm->numa_scan_seq is written to without exclusive access
	 * and the update is not guaranteed to be atomic. That's not
	 * much of an issue though, since this is just used for
	 * statistical sampling. Use READ_ONCE/WRITE_ONCE, which are not
	 * expensive, to avoid any form of compiler optimizations:
	 */
	WRITE_ONCE(p->mm->numa_scan_seq, READ_ONCE(p->mm->numa_scan_seq) + 1);
	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;
	u64 runtime = p->se.sum_exec_runtime;
	struct vm_area_struct *vma;
	unsigned long start, end;
	unsigned long nr_pte_updates = 0;
	long pages, virtpages;

	SCHED_WARN_ON(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_start(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 */
	virtpages = pages * 8;	   /* Scan up to this much virtual space */
	if (!pages)
		return;


	if (!down_read_trylock(&mm->mmap_sem))
		return;
	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(vma) ||
			is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) {
			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;

		/*
		 * Skip inaccessible VMAs to avoid any confusion between
		 * PROT_NONE and NUMA hinting ptes
		 */
		if (!vma_is_accessible(vma))
			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);

			/*
			 * Try to scan sysctl_numa_balancing_size worth of
			 * hpages that have at least one present PTE that
			 * is not already pte-numa. If the VMA contains
			 * areas that are unused or already full of prot_numa
			 * PTEs, scan up to virtpages, to skip through those
			 * areas faster.
			 */
			if (nr_pte_updates)
				pages -= (end - start) >> PAGE_SHIFT;
			virtpages -= (end - start) >> PAGE_SHIFT;

			start = end;
			if (pages <= 0 || virtpages <= 0)
				goto out;

			cond_resched();
		} 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);

	/*
	 * Make sure tasks use at least 32x as much time to run other code
	 * than they used here, to limit NUMA PTE scanning overhead to 3% max.
	 * Usually update_task_scan_period slows down scanning enough; on an
	 * overloaded system we need to limit overhead on a per task basis.
	 */
	if (unlikely(p->se.sum_exec_runtime != runtime)) {
		u64 diff = p->se.sum_exec_runtime - runtime;
		p->node_stamp += 32 * diff;
	}
}

/*
 * 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->flags & (PF_EXITING | PF_KTHREAD)) || 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_start(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);
#ifdef CONFIG_SMP
	if (entity_is_task(se)) {
		account_numa_dequeue(rq_of(cfs_rq), task_of(se));
		list_del_init(&se->group_node);
	}
#endif
	cfs_rq->nr_running--;
}

/*
 * Signed add and clamp on underflow.
 *
 * Explicitly do a load-store to ensure the intermediate value never hits
 * memory. This allows lockless observations without ever seeing the negative
 * values.
 */
#define add_positive(_ptr, _val) do {                           \
	typeof(_ptr) ptr = (_ptr);                              \
	typeof(_val) val = (_val);                              \
	typeof(*ptr) res, var = READ_ONCE(*ptr);                \
								\
	res = var + val;                                        \
								\
	if (val < 0 && res > var)                               \
		res = 0;                                        \
								\
	WRITE_ONCE(*ptr, res);                                  \
} while (0)

/*
 * Unsigned subtract and clamp on underflow.
 *
 * Explicitly do a load-store to ensure the intermediate value never hits
 * memory. This allows lockless observations without ever seeing the negative
 * values.
 */
#define sub_positive(_ptr, _val) do {				\
	typeof(_ptr) ptr = (_ptr);				\
	typeof(*ptr) val = (_val);				\
	typeof(*ptr) res, var = READ_ONCE(*ptr);		\
	res = var - val;					\
	if (res > var)						\
		res = 0;					\
	WRITE_ONCE(*ptr, res);					\
} while (0)

#ifdef CONFIG_SMP
static inline void
enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	cfs_rq->runnable_weight += se->runnable_weight;

	cfs_rq->avg.runnable_load_avg += se->avg.runnable_load_avg;
	cfs_rq->avg.runnable_load_sum += se_runnable(se) * se->avg.runnable_load_sum;
}

static inline void
dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	cfs_rq->runnable_weight -= se->runnable_weight;

	sub_positive(&cfs_rq->avg.runnable_load_avg, se->avg.runnable_load_avg);
	sub_positive(&cfs_rq->avg.runnable_load_sum,
		     se_runnable(se) * se->avg.runnable_load_sum);
}

static inline void
enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	cfs_rq->avg.load_avg += se->avg.load_avg;
	cfs_rq->avg.load_sum += se_weight(se) * se->avg.load_sum;
}

static inline void
dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
	sub_positive(&cfs_rq->avg.load_sum, se_weight(se) * se->avg.load_sum);
}
#else
static inline void
enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
static inline void
dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
static inline void
enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
static inline void
dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
#endif

static void reweight_eevdf(struct sched_entity *se, u64 avruntime,
			   unsigned long weight)
{
	unsigned long old_weight = se->load.weight;
	s64 vlag, vslice;

	/*
	 * VRUNTIME
	 * ========
	 *
	 * COROLLARY #1: The virtual runtime of the entity needs to be
	 * adjusted if re-weight at !0-lag point.
	 *
	 * Proof: For contradiction assume this is not true, so we can
	 * re-weight without changing vruntime at !0-lag point.
	 *
	 *             Weight	VRuntime   Avg-VRuntime
	 *     before    w          v            V
	 *      after    w'         v'           V'
	 *
	 * Since lag needs to be preserved through re-weight:
	 *
	 *	lag = (V - v)*w = (V'- v')*w', where v = v'
	 *	==>	V' = (V - v)*w/w' + v		(1)
	 *
	 * Let W be the total weight of the entities before reweight,
	 * since V' is the new weighted average of entities:
	 *
	 *	V' = (WV + w'v - wv) / (W + w' - w)	(2)
	 *
	 * by using (1) & (2) we obtain:
	 *
	 *	(WV + w'v - wv) / (W + w' - w) = (V - v)*w/w' + v
	 *	==> (WV-Wv+Wv+w'v-wv)/(W+w'-w) = (V - v)*w/w' + v
	 *	==> (WV - Wv)/(W + w' - w) + v = (V - v)*w/w' + v
	 *	==>	(V - v)*W/(W + w' - w) = (V - v)*w/w' (3)
	 *
	 * Since we are doing at !0-lag point which means V != v, we
	 * can simplify (3):
	 *
	 *	==>	W / (W + w' - w) = w / w'
	 *	==>	Ww' = Ww + ww' - ww
	 *	==>	W * (w' - w) = w * (w' - w)
	 *	==>	W = w	(re-weight indicates w' != w)
	 *
	 * So the cfs_rq contains only one entity, hence vruntime of
	 * the entity @v should always equal to the cfs_rq's weighted
	 * average vruntime @V, which means we will always re-weight
	 * at 0-lag point, thus breach assumption. Proof completed.
	 *
	 *
	 * COROLLARY #2: Re-weight does NOT affect weighted average
	 * vruntime of all the entities.
	 *
	 * Proof: According to corollary #1, Eq. (1) should be:
	 *
	 *	(V - v)*w = (V' - v')*w'
	 *	==>    v' = V' - (V - v)*w/w'		(4)
	 *
	 * According to the weighted average formula, we have:
	 *
	 *	V' = (WV - wv + w'v') / (W - w + w')
	 *	   = (WV - wv + w'(V' - (V - v)w/w')) / (W - w + w')
	 *	   = (WV - wv + w'V' - Vw + wv) / (W - w + w')
	 *	   = (WV + w'V' - Vw) / (W - w + w')
	 *
	 *	==>  V'*(W - w + w') = WV + w'V' - Vw
	 *	==>	V' * (W - w) = (W - w) * V	(5)
	 *
	 * If the entity is the only one in the cfs_rq, then reweight
	 * always occurs at 0-lag point, so V won't change. Or else
	 * there are other entities, hence W != w, then Eq. (5) turns
	 * into V' = V. So V won't change in either case, proof done.
	 *
	 *
	 * So according to corollary #1 & #2, the effect of re-weight
	 * on vruntime should be:
	 *
	 *	v' = V' - (V - v) * w / w'		(4)
	 *	   = V  - (V - v) * w / w'
	 *	   = V  - vl * w / w'
	 *	   = V  - vl'
	 */
	if (avruntime != se->vruntime) {
		vlag = entity_lag(avruntime, se);
		vlag = div_s64(vlag * old_weight, weight);
		se->vruntime = avruntime - vlag;
	}

	/*
	 * DEADLINE
	 * ========
	 *
	 * When the weight changes, the virtual time slope changes and
	 * we should adjust the relative virtual deadline accordingly.
	 *
	 *	d' = v' + (d - v)*w/w'
	 *	   = V' - (V - v)*w/w' + (d - v)*w/w'
	 *	   = V  - (V - v)*w/w' + (d - v)*w/w'
	 *	   = V  + (d - V)*w/w'
	 */
	vslice = (s64)(se->deadline - avruntime);
	vslice = div_s64(vslice * old_weight, weight);
	se->deadline = avruntime + vslice;
}

static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
			    unsigned long weight, unsigned long runnable)
{
	bool curr = cfs_rq->curr == se;
	u64 avruntime;

	if (se->on_rq) {
		/* commit outstanding execution time */
		update_curr(cfs_rq);
		avruntime = avg_vruntime(cfs_rq);
		if (!curr)
			__dequeue_entity(cfs_rq, se);
                update_load_sub(&cfs_rq->load, se->load.weight);
		dequeue_runnable_load_avg(cfs_rq, se);
	}
	dequeue_load_avg(cfs_rq, se);

	se->runnable_weight = runnable;

	if (se->on_rq) {
		reweight_eevdf(se, avruntime, weight);
	} else {
		/*
		 * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i),
		 * we need to scale se->vlag when w_i changes.
		 */
		se->vlag = div_s64(se->vlag * se->load.weight, weight);
	}

	update_load_set(&se->load, weight);

#ifdef CONFIG_SMP
	do {
		u32 divider = get_pelt_divider(&se->avg);

		se->avg.load_avg = div_u64(se_weight(se) * se->avg.load_sum, divider);
		se->avg.runnable_load_avg =
			div_u64(se_runnable(se) * se->avg.runnable_load_sum, divider);
	} while (0);
#endif

	enqueue_load_avg(cfs_rq, se);
	if (se->on_rq) {
                update_load_add(&cfs_rq->load, se->load.weight);
		enqueue_runnable_load_avg(cfs_rq, se);
		if (!curr)
			__enqueue_entity(cfs_rq, se);

		/*
		 * The entity's vruntime has been adjusted, so let's check
		 * whether the rq-wide min_vruntime needs updated too. Since
		 * the calculations above require stable min_vruntime rather
		 * than up-to-date one, we do the update at the end of the
		 * reweight process.
		 */
		update_min_vruntime(cfs_rq);
	}
}

void reweight_task(struct task_struct *p, int prio)
{
	struct sched_entity *se = &p->se;
	struct cfs_rq *cfs_rq = cfs_rq_of(se);
	struct load_weight *load = &se->load;
	unsigned long weight = scale_load(sched_prio_to_weight[prio]);

	reweight_entity(cfs_rq, se, weight, weight);
	load->inv_weight = sched_prio_to_wmult[prio];
}

#ifdef CONFIG_FAIR_GROUP_SCHED
# ifdef CONFIG_SMP
/*
 * All this does is approximate the hierarchical proportion which includes that
 * global sum we all love to hate.
 *
 * That is, the weight of a group entity, is the proportional share of the
 * group weight based on the group runqueue weights. That is:
 *
 *                     tg->weight * grq->load.weight
 *   ge->load.weight = -----------------------------               (1)
 *			  \Sum grq->load.weight
 *
 * Now, because computing that sum is prohibitively expensive to compute (been
 * there, done that) we approximate it with this average stuff. The average
 * moves slower and therefore the approximation is cheaper and more stable.
 *
 * So instead of the above, we substitute:
 *
 *   grq->load.weight -> grq->avg.load_avg                         (2)
 *
 * which yields the following:
 *
 *                     tg->weight * grq->avg.load_avg
 *   ge->load.weight = ------------------------------              (3)
 *				tg->load_avg
 *
 * Where: tg->load_avg ~= \Sum grq->avg.load_avg
 *
 * That is shares_avg, and it is right (given the approximation (2)).
 *
 * The problem with it is that because the average is slow -- it was designed
 * to be exactly that of course -- this leads to transients in boundary
 * conditions. In specific, the case where the group was idle and we start the
 * one task. It takes time for our CPU's grq->avg.load_avg to build up,
 * yielding bad latency etc..
 *
 * Now, in that special case (1) reduces to:
 *
 *                     tg->weight * grq->load.weight
 *   ge->load.weight = ----------------------------- = tg->weight   (4)
 *			    grp->load.weight
 *
 * That is, the sum collapses because all other CPUs are idle; the UP scenario.
 *
 * So what we do is modify our approximation (3) to approach (4) in the (near)
 * UP case, like:
 *
 *   ge->load.weight =
 *
 *              tg->weight * grq->load.weight
 *     ---------------------------------------------------         (5)
 *     tg->load_avg - grq->avg.load_avg + grq->load.weight
 *
 * But because grq->load.weight can drop to 0, resulting in a divide by zero,
 * we need to use grq->avg.load_avg as its lower bound, which then gives:
 *
 *
 *                     tg->weight * grq->load.weight
 *   ge->load.weight = -----------------------------		   (6)
 *				tg_load_avg'
 *
 * Where:
 *
 *   tg_load_avg' = tg->load_avg - grq->avg.load_avg +
 *                  max(grq->load.weight, grq->avg.load_avg)
 *
 * And that is shares_weight and is icky. In the (near) UP case it approaches
 * (4) while in the normal case it approaches (3). It consistently
 * overestimates the ge->load.weight and therefore:
 *
 *   \Sum ge->load.weight >= tg->weight
 *
 * hence icky!
 */
static long calc_group_shares(struct cfs_rq *cfs_rq)
{
	long tg_weight, tg_shares, load, shares;
	struct task_group *tg = cfs_rq->tg;

	tg_shares = READ_ONCE(tg->shares);

	load = max(scale_load_down(cfs_rq->load.weight), cfs_rq->avg.load_avg);

	tg_weight = atomic_long_read(&tg->load_avg);

	/* Ensure tg_weight >= load */
	tg_weight -= cfs_rq->tg_load_avg_contrib;
	tg_weight += load;

	shares = (tg_shares * load);
	if (tg_weight)
		shares /= tg_weight;

	/*
	 * MIN_SHARES has to be unscaled here to support per-CPU partitioning
	 * of a group with small tg->shares value. It is a floor value which is
	 * assigned as a minimum load.weight to the sched_entity representing
	 * the group on a CPU.
	 *
	 * E.g. on 64-bit for a group with tg->shares of scale_load(15)=15*1024
	 * on an 8-core system with 8 tasks each runnable on one CPU shares has
	 * to be 15*1024*1/8=1920 instead of scale_load(MIN_SHARES)=2*1024. In
	 * case no task is runnable on a CPU MIN_SHARES=2 should be returned
	 * instead of 0.
	 */
	return clamp_t(long, shares, MIN_SHARES, tg_shares);
}

/*
 * This calculates the effective runnable weight for a group entity based on
 * the group entity weight calculated above.
 *
 * Because of the above approximation (2), our group entity weight is
 * an load_avg based ratio (3). This means that it includes blocked load and
 * does not represent the runnable weight.
 *
 * Approximate the group entity's runnable weight per ratio from the group
 * runqueue:
 *
 *					     grq->avg.runnable_load_avg
 *   ge->runnable_weight = ge->load.weight * -------------------------- (7)
 *						 grq->avg.load_avg
 *
 * However, analogous to above, since the avg numbers are slow, this leads to
 * transients in the from-idle case. Instead we use:
 *
 *   ge->runnable_weight = ge->load.weight *
 *
 *		max(grq->avg.runnable_load_avg, grq->runnable_weight)
 *		-----------------------------------------------------	(8)
 *		      max(grq->avg.load_avg, grq->load.weight)
 *
 * Where these max() serve both to use the 'instant' values to fix the slow
 * from-idle and avoid the /0 on to-idle, similar to (6).
 */
static long calc_group_runnable(struct cfs_rq *cfs_rq, long shares)
{
	long runnable, load_avg;

	load_avg = max(cfs_rq->avg.load_avg,
		       scale_load_down(cfs_rq->load.weight));

	runnable = max(cfs_rq->avg.runnable_load_avg,
		       scale_load_down(cfs_rq->runnable_weight));

	runnable *= shares;
	if (load_avg)
		runnable /= load_avg;

	return clamp_t(long, runnable, MIN_SHARES, shares);
}
# endif /* CONFIG_SMP */

static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);

/*
 * Recomputes the group entity based on the current state of its group
 * runqueue.
 */
static void update_cfs_group(struct sched_entity *se)
{
	struct cfs_rq *gcfs_rq = group_cfs_rq(se);
	long shares, runnable;

	if (!gcfs_rq)
		return;

	if (throttled_hierarchy(gcfs_rq))
		return;

#ifndef CONFIG_SMP
	runnable = shares = READ_ONCE(gcfs_rq->tg->shares);

#else
	shares = calc_group_shares(gcfs_rq);
	runnable = calc_group_runnable(gcfs_rq, shares);
#endif

	if (unlikely(se->load.weight != shares))
		reweight_entity(cfs_rq_of(se), se, shares, runnable);
}

#else /* CONFIG_FAIR_GROUP_SCHED */
static inline void update_cfs_group(struct sched_entity *se)
{
}
#endif /* CONFIG_FAIR_GROUP_SCHED */

static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
{
	struct rq *rq = rq_of(cfs_rq);

	if (&rq->cfs == cfs_rq) {
		/*
		 * There are a few boundary cases this might miss but it should
		 * get called often enough that that should (hopefully) not be
		 * a real problem -- added to that it only calls on the local
		 * CPU, so if we enqueue remotely we'll miss an update, but
		 * the next tick/schedule should update.
		 *
		 * It will not get called when we go idle, because the idle
		 * thread is a different class (!fair), nor will the utilization
		 * number include things like RT tasks.
		 *
		 * As is, the util number is not freq-invariant (we'd have to
		 * implement arch_scale_freq_capacity() for that).
		 *
		 * See cpu_util().
		 */
		cpufreq_update_util(rq, 0);
	}
}

#ifdef CONFIG_SMP

#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)

static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
{
	return u64_u32_load_copy(cfs_rq->avg.last_update_time,
				 cfs_rq->last_update_time_copy);
}
#ifdef CONFIG_FAIR_GROUP_SCHED
/**
 * update_tg_load_avg - update the tg's load avg
 * @cfs_rq: the cfs_rq whose avg changed
 * @force: update regardless of how small the difference
 *
 * This function 'ensures': tg->load_avg := \Sum tg->cfs_rq[]->avg.load.
 * However, because tg->load_avg is a global value there are performance
 * considerations.
 *
 * In order to avoid having to look at the other cfs_rq's, we use a
 * differential update where we store the last value we propagated. This in
 * turn allows skipping updates if the differential is 'small'.
 *
 * Updating tg's load_avg is necessary before update_cfs_share().
 */
static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
{
	long delta;
	u64 now;

	/*
	 * No need to update load_avg for root_task_group as it is not used.
	 */
	if (cfs_rq->tg == &root_task_group)
		return;

	/*
	 * For migration heavy workloads, access to tg->load_avg can be
	 * unbound. Limit the update rate to at most once per ms.
	 */
	now = sched_clock_cpu(cpu_of(rq_of(cfs_rq)));
	if (now - cfs_rq->last_update_tg_load_avg < NSEC_PER_MSEC)
		return;

	delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib;
	if (abs(delta) > cfs_rq->tg_load_avg_contrib / 64) {
		atomic_long_add(delta, &cfs_rq->tg->load_avg);
		cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg;
		cfs_rq->last_update_tg_load_avg = now;
	}

	trace_sched_load_tg(cfs_rq);
}

/*
 * Called within set_task_rq() right before setting a task's cpu. The
 * caller only guarantees p->pi_lock is held; no other assumptions,
 * including the state of rq->lock, should be made.
 */
void set_task_rq_fair(struct sched_entity *se,
		      struct cfs_rq *prev, struct cfs_rq *next)
{
	u64 p_last_update_time;
	u64 n_last_update_time;

	if (!sched_feat(ATTACH_AGE_LOAD))
		return;

	/*
	 * We are supposed to update the task to "current" time, then its up to
	 * date and ready to go to new CPU/cfs_rq. But we have difficulty in
	 * getting what current time is, so simply throw away the out-of-date
	 * time. This will result in the wakee task is less decayed, but giving
	 * the wakee more load sounds not bad.
	 */
	if (!(se->avg.last_update_time && prev))
		return;

	p_last_update_time = cfs_rq_last_update_time(prev);
	n_last_update_time = cfs_rq_last_update_time(next);

	__update_load_avg_blocked_se(p_last_update_time, se);
	se->avg.last_update_time = n_last_update_time;
}


/*
 * When on migration a sched_entity joins/leaves the PELT hierarchy, we need to
 * propagate its contribution. The key to this propagation is the invariant
 * that for each group:
 *
 *   ge->avg == grq->avg						(1)
 *
 * _IFF_ we look at the pure running and runnable sums. Because they
 * represent the very same entity, just at different points in the hierarchy.
 *
 * Per the above update_tg_cfs_util() is trivial and simply copies the running
 * sum over (but still wrong, because the group entity and group rq do not have
 * their PELT windows aligned).
 *
 * However, update_tg_cfs_runnable() is more complex. So we have:
 *
 *   ge->avg.load_avg = ge->load.weight * ge->avg.runnable_avg		(2)
 *
 * And since, like util, the runnable part should be directly transferable,
 * the following would _appear_ to be the straight forward approach:
 *
 *   grq->avg.load_avg = grq->load.weight * grq->avg.runnable_avg	(3)
 *
 * And per (1) we have:
 *
 *   ge->avg.runnable_avg == grq->avg.runnable_avg
 *
 * Which gives:
 *
 *                      ge->load.weight * grq->avg.load_avg
 *   ge->avg.load_avg = -----------------------------------		(4)
 *                               grq->load.weight
 *
 * Except that is wrong!
 *
 * Because while for entities historical weight is not important and we
 * really only care about our future and therefore can consider a pure
 * runnable sum, runqueues can NOT do this.
 *
 * We specifically want runqueues to have a load_avg that includes
 * historical weights. Those represent the blocked load, the load we expect
 * to (shortly) return to us. This only works by keeping the weights as
 * integral part of the sum. We therefore cannot decompose as per (3).
 *
 * Another reason this doesn't work is that runnable isn't a 0-sum entity.
 * Imagine a rq with 2 tasks that each are runnable 2/3 of the time. Then the
 * rq itself is runnable anywhere between 2/3 and 1 depending on how the
 * runnable section of these tasks overlap (or not). If they were to perfectly
 * align the rq as a whole would be runnable 2/3 of the time. If however we
 * always have at least 1 runnable task, the rq as a whole is always runnable.
 *
 * So we'll have to approximate.. :/
 *
 * Given the constraint:
 *
 *   ge->avg.running_sum <= ge->avg.runnable_sum <= LOAD_AVG_MAX
 *
 * We can construct a rule that adds runnable to a rq by assuming minimal
 * overlap.
 *
 * On removal, we'll assume each task is equally runnable; which yields:
 *
 *   grq->avg.runnable_sum = grq->avg.load_sum / grq->load.weight
 *
 * XXX: only do this for the part of runnable > running ?
 *
 */

static inline void
update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
{
	long delta = gcfs_rq->avg.util_avg - se->avg.util_avg;

	/* Nothing to update */
	if (!delta)
		return;

	/*
	 * The relation between sum and avg is:
	 *
	 *   LOAD_AVG_MAX - 1024 + sa->period_contrib
	 *
	 * however, the PELT windows are not aligned between grq and gse.
	 */

	/* Set new sched_entity's utilization */
	se->avg.util_avg = gcfs_rq->avg.util_avg;
	se->avg.util_sum = se->avg.util_avg * LOAD_AVG_MAX;

	/* Update parent cfs_rq utilization */
	add_positive(&cfs_rq->avg.util_avg, delta);
	cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * LOAD_AVG_MAX;
}

static inline void
update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
{
	long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum;
	unsigned long runnable_load_avg, load_avg;
	u64 runnable_load_sum, load_sum = 0;
	s64 delta_sum;

	if (!runnable_sum)
		return;

	gcfs_rq->prop_runnable_sum = 0;

	if (runnable_sum >= 0) {
		/*
		 * Add runnable; clip at LOAD_AVG_MAX. Reflects that until
		 * the CPU is saturated running == runnable.
		 */
		runnable_sum += se->avg.load_sum;
		runnable_sum = min(runnable_sum, (long)LOAD_AVG_MAX);
	} else {
		/*
		 * Estimate the new unweighted runnable_sum of the gcfs_rq by
		 * assuming all tasks are equally runnable.
		 */
		if (scale_load_down(gcfs_rq->load.weight)) {
			load_sum = div_s64(gcfs_rq->avg.load_sum,
				scale_load_down(gcfs_rq->load.weight));
		}

		/* But make sure to not inflate se's runnable */
		runnable_sum = min(se->avg.load_sum, load_sum);
	}

	/*
	 * runnable_sum can't be lower than running_sum
	 * Rescale running sum to be in the same range as runnable sum
	 * running_sum is in [0 : LOAD_AVG_MAX <<  SCHED_CAPACITY_SHIFT]
	 * runnable_sum is in [0 : LOAD_AVG_MAX]
	 */
	running_sum = se->avg.util_sum >> SCHED_CAPACITY_SHIFT;
	runnable_sum = max(runnable_sum, running_sum);

	load_sum = (s64)se_weight(se) * runnable_sum;
	load_avg = div_s64(load_sum, LOAD_AVG_MAX);

	delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum;
	delta_avg = load_avg - se->avg.load_avg;

	se->avg.load_sum = runnable_sum;
	se->avg.load_avg = load_avg;
	add_positive(&cfs_rq->avg.load_avg, delta_avg);
	add_positive(&cfs_rq->avg.load_sum, delta_sum);

	runnable_load_sum = (s64)se_runnable(se) * runnable_sum;
	runnable_load_avg = div_s64(runnable_load_sum, LOAD_AVG_MAX);
	delta_sum = runnable_load_sum - se_weight(se) * se->avg.runnable_load_sum;
	delta_avg = runnable_load_avg - se->avg.runnable_load_avg;

	se->avg.runnable_load_sum = runnable_sum;
	se->avg.runnable_load_avg = runnable_load_avg;

	if (se->on_rq) {
		add_positive(&cfs_rq->avg.runnable_load_avg, delta_avg);
		add_positive(&cfs_rq->avg.runnable_load_sum, delta_sum);
	}
}

static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum)
{
	cfs_rq->propagate = 1;
	cfs_rq->prop_runnable_sum += runnable_sum;
}

/* Update task and its cfs_rq load average */
static inline int propagate_entity_load_avg(struct sched_entity *se)
{
	struct cfs_rq *cfs_rq, *gcfs_rq;

	if (entity_is_task(se))
		return 0;

	gcfs_rq = group_cfs_rq(se);
	if (!gcfs_rq->propagate)
		return 0;

	gcfs_rq->propagate = 0;

	cfs_rq = cfs_rq_of(se);

	add_tg_cfs_propagate(cfs_rq, gcfs_rq->prop_runnable_sum);

	update_tg_cfs_util(cfs_rq, se, gcfs_rq);
	update_tg_cfs_runnable(cfs_rq, se, gcfs_rq);

	trace_sched_load_cfs_rq(cfs_rq);
	trace_sched_load_se(se);

	return 1;
}

/*
 * Check if we need to update the load and the utilization of a blocked
 * group_entity:
 */
static inline bool skip_blocked_update(struct sched_entity *se)
{
	struct cfs_rq *gcfs_rq = group_cfs_rq(se);

	/*
	 * If sched_entity still have not zero load or utilization, we have to
	 * decay it:
	 */
	if (se->avg.load_avg || se->avg.util_avg)
		return false;

	/*
	 * If there is a pending propagation, we have to update the load and
	 * the utilization of the sched_entity:
	 */
	if (gcfs_rq->propagate)
		return false;

	/*
	 * Otherwise, the load and the utilization of the sched_entity is
	 * already zero and there is no pending propagation, so it will be a
	 * waste of time to try to decay it:
	 */
	return true;
}

#else /* CONFIG_FAIR_GROUP_SCHED */

static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}

static inline int propagate_entity_load_avg(struct sched_entity *se)
{
	return 0;
}

static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum) {}

#endif /* CONFIG_FAIR_GROUP_SCHED */

/*
 * Remove and clamp on negative, from a local variable.
 *
 * A variant of sub_positive(), which does not use explicit load-store
 * and is thus optimized for local variable updates.
 */
#define lsub_positive(_ptr, _val) do {				\
	typeof(_ptr) ptr = (_ptr);				\
	*ptr -= min_t(typeof(*ptr), *ptr, _val);		\
} while (0)

/**
 * update_cfs_rq_load_avg - update the cfs_rq's load/util averages
 * @now: current time, as per cfs_rq_clock_pelt()
 * @cfs_rq: cfs_rq to update
 *
 * The cfs_rq avg is the direct sum of all its entities (blocked and runnable)
 * avg. The immediate corollary is that all (fair) tasks must be attached, see
 * post_init_entity_util_avg().
 *
 * cfs_rq->avg is used for task_h_load() and update_cfs_share() for example.
 *
 * Returns true if the load decayed or we removed load.
 *
 * Since both these conditions indicate a changed cfs_rq->avg.load we should
 * call update_tg_load_avg() when this function returns true.
 */
static inline int
update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
{
	unsigned long removed_load = 0, removed_util = 0, removed_runnable_sum = 0;
	struct sched_avg *sa = &cfs_rq->avg;
	int decayed = 0;

	if (cfs_rq->removed.nr) {
		unsigned long r;
		u32 divider = get_pelt_divider(&cfs_rq->avg);

		raw_spin_lock(&cfs_rq->removed.lock);
		swap(cfs_rq->removed.util_avg, removed_util);
		swap(cfs_rq->removed.load_avg, removed_load);
		swap(cfs_rq->removed.runnable_sum, removed_runnable_sum);
		cfs_rq->removed.nr = 0;
		raw_spin_unlock(&cfs_rq->removed.lock);

		r = removed_load;
		sub_positive(&sa->load_avg, r);
		sub_positive(&sa->load_sum, r * divider);

		r = removed_util;
		sub_positive(&sa->util_avg, r);
		sub_positive(&sa->util_sum, r * divider);

		add_tg_cfs_propagate(cfs_rq, -(long)removed_runnable_sum);

		decayed = 1;
	}

	decayed |= __update_load_avg_cfs_rq(now, cfs_rq);
	u64_u32_store_copy(sa->last_update_time,
			   cfs_rq->last_update_time_copy,
			   sa->last_update_time);

	if (decayed)
		cfs_rq_util_change(cfs_rq);

	return decayed;
}

/**
 * attach_entity_load_avg - attach this entity to its cfs_rq load avg
 * @cfs_rq: cfs_rq to attach to
 * @se: sched_entity to attach
 *
 * Must call update_cfs_rq_load_avg() before this, since we rely on
 * cfs_rq->avg.last_update_time being current.
 */
static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	/*
	 * cfs_rq->avg.period_contrib can be used for both cfs_rq and se.
	 * See ___update_load_avg() for details.
	 */
	u32 divider = get_pelt_divider(&cfs_rq->avg);

	/*
	 * When we attach the @se to the @cfs_rq, we must align the decay
	 * window because without that, really weird and wonderful things can
	 * happen.
	 *
	 * XXX illustrate
	 */
	se->avg.last_update_time = cfs_rq->avg.last_update_time;
	se->avg.period_contrib = cfs_rq->avg.period_contrib;

	/*
	 * Hell(o) Nasty stuff.. we need to recompute _sum based on the new
	 * period_contrib. This isn't strictly correct, but since we're
	 * entirely outside of the PELT hierarchy, nobody cares if we truncate
	 * _sum a little.
	 */
	se->avg.util_sum = se->avg.util_avg * divider;

	se->avg.load_sum = divider;
	if (se_weight(se)) {
		se->avg.load_sum =
			div_u64(se->avg.load_avg * se->avg.load_sum, se_weight(se));
	}

	se->avg.runnable_load_sum = se->avg.load_sum;

	enqueue_load_avg(cfs_rq, se);
	cfs_rq->avg.util_avg += se->avg.util_avg;
	cfs_rq->avg.util_sum += se->avg.util_sum;

	add_tg_cfs_propagate(cfs_rq, se->avg.load_sum);

	cfs_rq_util_change(cfs_rq);

	trace_sched_load_cfs_rq(cfs_rq);
}

/**
 * detach_entity_load_avg - detach this entity from its cfs_rq load avg
 * @cfs_rq: cfs_rq to detach from
 * @se: sched_entity to detach
 *
 * Must call update_cfs_rq_load_avg() before this, since we rely on
 * cfs_rq->avg.last_update_time being current.
 */
static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	dequeue_load_avg(cfs_rq, se);
	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);

	add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum);

	cfs_rq_util_change(cfs_rq);

	trace_sched_load_cfs_rq(cfs_rq);
}

/*
 * Optional action to be done while updating the load average
 */
#define UPDATE_TG	0x1
#define SKIP_AGE_LOAD	0x2
#define DO_ATTACH	0x4
#define DO_DETACH	0x8

/* Update task and its cfs_rq load average */
static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{
	u64 now = cfs_rq_clock_pelt(cfs_rq);
	int decayed;

	/*
	 * Track task load average for carrying it to new CPU after migrated, and
	 * track group sched_entity load average for task_h_load calc in migration
	 */
	if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD))
		__update_load_avg_se(now, cfs_rq, se);

	decayed  = update_cfs_rq_load_avg(now, cfs_rq);
	decayed |= propagate_entity_load_avg(se);

	if (!se->avg.last_update_time && (flags & DO_ATTACH)) {

		attach_entity_load_avg(cfs_rq, se);
		update_tg_load_avg(cfs_rq, 0);

	} else if (flags & DO_DETACH) {
		/*
		 * DO_DETACH means we're here from dequeue_entity()
		 * and we are migrating task out of the CPU.
		 */
		detach_entity_load_avg(cfs_rq, se);
		update_tg_load_avg(cfs_rq, 0);
	} else if (decayed && (flags & UPDATE_TG))
		update_tg_load_avg(cfs_rq, 0);
}

/*
 * Synchronize entity load avg of dequeued entity without locking
 * the previous rq.
 */
void sync_entity_load_avg(struct sched_entity *se)
{
	struct cfs_rq *cfs_rq = cfs_rq_of(se);
	u64 last_update_time;

	last_update_time = cfs_rq_last_update_time(cfs_rq);
	__update_load_avg_blocked_se(last_update_time, se);
}

/*
 * Task first catches up with cfs_rq, and then subtract
 * itself from the cfs_rq (task must be off the queue now).
 */
void remove_entity_load_avg(struct sched_entity *se)
{
	struct cfs_rq *cfs_rq = cfs_rq_of(se);
	unsigned long flags;

	/*
	 * tasks cannot exit without having gone through wake_up_new_task() ->
	 * post_init_entity_util_avg() which will have added things to the
	 * cfs_rq, so we can remove unconditionally.
	 *
	 * Similarly for groups, they will have passed through
	 * post_init_entity_util_avg() before unregister_sched_fair_group()
	 * calls this.
	 */

	sync_entity_load_avg(se);

	raw_spin_lock_irqsave(&cfs_rq->removed.lock, flags);
	++cfs_rq->removed.nr;
	cfs_rq->removed.util_avg	+= se->avg.util_avg;
	cfs_rq->removed.load_avg	+= se->avg.load_avg;
	cfs_rq->removed.runnable_sum	+= se->avg.load_sum; /* == runnable_sum */
	raw_spin_unlock_irqrestore(&cfs_rq->removed.lock, flags);
}

static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq)
{
	return cfs_rq->avg.runnable_load_avg;
}

static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
{
	return cfs_rq->avg.load_avg;
}

static int idle_balance(struct rq *this_rq, struct rq_flags *rf);

static inline bool task_fits_capacity(struct task_struct *p, long capacity);

static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
{
	if (!static_branch_unlikely(&sched_asym_cpucapacity))
		return;

	if (!p) {
		rq->misfit_task_load = 0;
		return;
	}

	if (task_fits_max(p, cpu_of(rq))) {
		rq->misfit_task_load = 0;
		return;
	}

	rq->misfit_task_load = task_h_load(p);
}

static inline unsigned long _task_util_est(struct task_struct *p)
{
	struct util_est ue = READ_ONCE(p->se.avg.util_est);

	return (max(ue.ewma, ue.enqueued) | UTIL_AVG_UNCHANGED);
}

unsigned long task_util_est(struct task_struct *p)
{
#ifdef CONFIG_SCHED_WALT
	if (likely(!walt_disabled && sysctl_sched_use_walt_task_util))
		return p->ravg.demand_scaled;
#endif
	return max(task_util(p), _task_util_est(p));
}

#ifdef CONFIG_UCLAMP_TASK
static inline unsigned long uclamp_task_util(struct task_struct *p)
{
	return clamp(task_util_est(p),
		     uclamp_eff_value(p, UCLAMP_MIN),
		     uclamp_eff_value(p, UCLAMP_MAX));
}
#else
static inline unsigned long uclamp_task_util(struct task_struct *p)
{
	return task_util_est(p);
}
#endif

static inline void util_est_enqueue(struct cfs_rq *cfs_rq,
				    struct task_struct *p)
{
	unsigned int enqueued;

	if (!sched_feat(UTIL_EST))
		return;

	/* Update root cfs_rq's estimated utilization */
	enqueued  = cfs_rq->avg.util_est.enqueued;
	enqueued += _task_util_est(p);
	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued);

	trace_sched_util_est_task(p, &p->se.avg);
	trace_sched_util_est_cpu(cpu_of(rq_of(cfs_rq)), cfs_rq);
}

#define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100)

/*
 * Check if a (signed) value is within a specified (unsigned) margin,
 * based on the observation that:
 *
 *     abs(x) < y := (unsigned)(x + y - 1) < (2 * y - 1)
 *
 * NOTE: this only works when value + maring < INT_MAX.
 */
static inline bool within_margin(int value, int margin)
{
	return ((unsigned int)(value + margin - 1) < (2 * margin - 1));
}

static void
util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
{
	long last_ewma_diff, last_enqueued_diff;
	struct util_est ue;
	int cpu;

	if (!sched_feat(UTIL_EST))
		return;

	/* Update root cfs_rq's estimated utilization */
	ue.enqueued  = cfs_rq->avg.util_est.enqueued;
	ue.enqueued -= min_t(unsigned int, ue.enqueued, _task_util_est(p));
	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued);

	trace_sched_util_est_cpu(cpu_of(rq_of(cfs_rq)), cfs_rq);

	/*
	 * Skip update of task's estimated utilization when the task has not
	 * yet completed an activation, e.g. being migrated.
	 */
	if (!task_sleep)
		return;

	/*
	 * If the PELT values haven't changed since enqueue time,
	 * skip the util_est update.
	 */
	ue = p->se.avg.util_est;
	if (ue.enqueued & UTIL_AVG_UNCHANGED)
		return;

	last_enqueued_diff = ue.enqueued;

	/*
	 * Reset EWMA on utilization increases, the moving average is used only
	 * to smooth utilization decreases.
	 */
	ue.enqueued = (task_util(p) | UTIL_AVG_UNCHANGED);
	if (sched_feat(UTIL_EST_FASTUP)) {
		if (ue.ewma < ue.enqueued) {
			ue.ewma = ue.enqueued;
			goto done;
		}
	}

	/*
	 * Skip update of task's estimated utilization when its members are
	 * already ~1% close to its last activation value.
	 */
	last_ewma_diff = ue.enqueued - ue.ewma;
	last_enqueued_diff -= ue.enqueued;
	if (within_margin(last_ewma_diff, UTIL_EST_MARGIN)) {
		if (!within_margin(last_enqueued_diff, UTIL_EST_MARGIN))
			goto done;

		return;
	}

	/*
	 * To avoid overestimation of actual task utilization, skip updates if
	 * we cannot grant there is idle time in this CPU.
	 */
	cpu = cpu_of(rq_of(cfs_rq));
	if (task_util(p) > capacity_orig_of(cpu))
		return;

	/*
	 * Update Task's estimated utilization
	 *
	 * When *p completes an activation we can consolidate another sample
	 * of the task size. This is done by storing the current PELT value
	 * as ue.enqueued and by using this value to update the Exponential
	 * Weighted Moving Average (EWMA):
	 *
	 *  ewma(t) = w *  task_util(p) + (1-w) * ewma(t-1)
	 *          = w *  task_util(p) +         ewma(t-1)  - w * ewma(t-1)
	 *          = w * (task_util(p) -         ewma(t-1)) +     ewma(t-1)
	 *          = w * (      last_ewma_diff            ) +     ewma(t-1)
	 *          = w * (last_ewma_diff  +  ewma(t-1) / w)
	 *
	 * Where 'w' is the weight of new samples, which is configured to be
	 * 0.25, thus making w=1/4 ( >>= UTIL_EST_WEIGHT_SHIFT)
	 */
	ue.ewma <<= UTIL_EST_WEIGHT_SHIFT;
	ue.ewma  += last_ewma_diff;
	ue.ewma >>= UTIL_EST_WEIGHT_SHIFT;
done:
	WRITE_ONCE(p->se.avg.util_est, ue);

	trace_sched_util_est_task(p, &p->se.avg);
}

#else /* CONFIG_SMP */

#define UPDATE_TG	0x0
#define SKIP_AGE_LOAD	0x0
#define DO_ATTACH	0x0
#define DO_DETACH	0x0

static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int not_used1)
{
	cfs_rq_util_change(cfs_rq);
}

static inline void remove_entity_load_avg(struct sched_entity *se) {}

static inline void
attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
static inline void
detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}

static inline int idle_balance(struct rq *rq, struct rq_flags *rf)
{
	return 0;
}

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

static inline void
util_est_enqueue(struct cfs_rq *cfs_rq, struct task_struct *p) {}

static inline void
util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p,
		 bool task_sleep) {}

#endif /* CONFIG_SMP */

static inline bool entity_is_long_sleeper(struct sched_entity *se)
{
	struct cfs_rq *cfs_rq;
	u64 sleep_time;

	if (se->exec_start == 0)
		return false;

	cfs_rq = cfs_rq_of(se);

	sleep_time = rq_clock_task(rq_of(cfs_rq));

	/* Happen while migrating because of clock task divergence */
	if (sleep_time <= se->exec_start)
		return false;

	sleep_time -= se->exec_start;
	if (sleep_time > ((1ULL << 63) / scale_load_down(NICE_0_LOAD)))
		return true;

	return false;
}

static void
place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{
	u64 vslice, vruntime = avg_vruntime(cfs_rq);
	s64 lag = 0;

	se->slice = sysctl_sched_base_slice;
	vslice = calc_delta_fair(se->slice, se);

	/*
	 * Due to how V is constructed as the weighted average of entities,
	 * adding tasks with positive lag, or removing tasks with negative lag
	 * will move 'time' backwards, this can screw around with the lag of
	 * other tasks.
	 *
	 * EEVDF: placement strategy #1 / #2
	 */
	if (sched_feat(PLACE_LAG) && cfs_rq->nr_running) {
		struct sched_entity *curr = cfs_rq->curr;
		unsigned long load;

		lag = se->vlag;

		/*
		 * If we want to place a task and preserve lag, we have to
		 * consider the effect of the new entity on the weighted
		 * average and compensate for this, otherwise lag can quickly
		 * evaporate.
		 *
		 * Lag is defined as:
		 *
		 *   lag_i = S - s_i = w_i * (V - v_i)
		 *
		 * To avoid the 'w_i' term all over the place, we only track
		 * the virtual lag:
		 *
		 *   vl_i = V - v_i <=> v_i = V - vl_i
		 *
		 * And we take V to be the weighted average of all v:
		 *
		 *   V = (\Sum w_j*v_j) / W
		 *
		 * Where W is: \Sum w_j
		 *
		 * Then, the weighted average after adding an entity with lag
		 * vl_i is given by:
		 *
		 *   V' = (\Sum w_j*v_j + w_i*v_i) / (W + w_i)
		 *      = (W*V + w_i*(V - vl_i)) / (W + w_i)
		 *      = (W*V + w_i*V - w_i*vl_i) / (W + w_i)
		 *      = (V*(W + w_i) - w_i*l) / (W + w_i)
		 *      = V - w_i*vl_i / (W + w_i)
		 *
		 * And the actual lag after adding an entity with vl_i is:
		 *
		 *   vl'_i = V' - v_i
		 *         = V - w_i*vl_i / (W + w_i) - (V - vl_i)
		 *         = vl_i - w_i*vl_i / (W + w_i)
		 *
		 * Which is strictly less than vl_i. So in order to preserve lag
		 * we should inflate the lag before placement such that the
		 * effective lag after placement comes out right.
		 *
		 * As such, invert the above relation for vl'_i to get the vl_i
		 * we need to use such that the lag after placement is the lag
		 * we computed before dequeue.
		 *
		 *   vl'_i = vl_i - w_i*vl_i / (W + w_i)
		 *         = ((W + w_i)*vl_i - w_i*vl_i) / (W + w_i)
		 *
		 *   (W + w_i)*vl'_i = (W + w_i)*vl_i - w_i*vl_i
		 *                   = W*vl_i
		 *
		 *   vl_i = (W + w_i)*vl'_i / W
		 */
		load = cfs_rq->avg_load;
		if (curr && curr->on_rq)
			load += scale_load_down(curr->load.weight);

		lag *= load + scale_load_down(se->load.weight);
		if (WARN_ON_ONCE(!load))
			load = 1;
		lag = div_s64(lag, load);
	}

	se->vruntime = vruntime - lag;

	/*
	 * When joining the competition; the exisiting tasks will be,
	 * on average, halfway through their slice, as such start tasks
	 * off with half a slice to ease into the competition.
	 */
	if (sched_feat(PLACE_DEADLINE_INITIAL) && (flags & ENQUEUE_INITIAL))
		vslice /= 2;

	/*
	 * EEVDF: vd_i = ve_i + r_i/w_i
	 */
	se->deadline = se->vruntime + vslice;
}

static void check_enqueue_throttle(struct cfs_rq *cfs_rq);

static inline void check_schedstat_required(void)
{
#ifdef CONFIG_SCHEDSTATS
	if (schedstat_enabled())
		return;

	/* Force schedstat enabled if a dependent tracepoint is active */
	if (trace_sched_stat_wait_enabled()    ||
			trace_sched_stat_sleep_enabled()   ||
			trace_sched_stat_iowait_enabled()  ||
			trace_sched_stat_blocked_enabled() ||
			trace_sched_stat_runtime_enabled())  {
		printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, "
			     "stat_blocked and stat_runtime require the "
			     "kernel parameter schedstats=enable or "
			     "kernel.sched_schedstats=1\n");
	}
#endif
}


static void
enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{
	bool curr = cfs_rq->curr == se;

	/*
	 * If we're the current task, we must renormalise before calling
	 * update_curr().
	 */
	if (curr)
		place_entity(cfs_rq, se, flags);

	update_curr(cfs_rq);

	/*
	 * When enqueuing a sched_entity, we must:
	 *   - Update loads to have both entity and cfs_rq synced with now.
	 *   - Add its load to cfs_rq->runnable_avg
	 *   - For group_entity, update its weight to reflect the new share of
	 *     its group cfs_rq
	 *   - Add its new weight to cfs_rq->load.weight
	 */
	update_load_avg(cfs_rq, se, UPDATE_TG | DO_ATTACH);
	enqueue_runnable_load_avg(cfs_rq, se);
	/*
	 * XXX update_load_avg() above will have attached us to the pelt sum;
	 * but update_cfs_group() here will re-adjust the weight and have to
	 * undo/redo all that. Seems wasteful.
	 */
	update_cfs_group(se);

	/*
	 * XXX now that the entity has been re-weighted, and it's lag adjusted,
	 * we can place the entity.
	 */
	if (!curr)
		place_entity(cfs_rq, se, flags);

	account_entity_enqueue(cfs_rq, se);

	if (flags & ENQUEUE_WAKEUP)
		place_entity(cfs_rq, se, 0);
	/* Entity has migrated, no longer consider this task hot */
	if (flags & ENQUEUE_MIGRATED)
		se->exec_start = 0;

	check_schedstat_required();
	update_stats_enqueue(cfs_rq, se, flags);
	if (!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_next(struct sched_entity *se)
{
	for_each_sched_entity(se) {
		struct cfs_rq *cfs_rq = cfs_rq_of(se);
		if (cfs_rq->next != se)
			break;

		cfs_rq->next = NULL;
	}
}

static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	if (cfs_rq->next == se)
		__clear_buddies_next(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)
{
	int action = UPDATE_TG;

	if (entity_is_task(se) && task_on_rq_migrating(task_of(se)))
		action |= DO_DETACH;

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

	/*
	 * When dequeuing a sched_entity, we must:
	 *   - Update loads to have both entity and cfs_rq synced with now.
	 *   - Substract its load from the cfs_rq->runnable_avg.
	 *   - Substract its previous weight from cfs_rq->load.weight.
	 *   - For group entity, update its weight to reflect the new share
	 *     of its group cfs_rq.
	 */
        update_load_avg(cfs_rq, se, action);
	dequeue_runnable_load_avg(cfs_rq, se);

	update_stats_dequeue(cfs_rq, se, flags);

	clear_buddies(cfs_rq, se);

	update_entity_lag(cfs_rq, se);
	if (se != cfs_rq->curr)
		__dequeue_entity(cfs_rq, se);
	se->on_rq = 0;
	account_entity_dequeue(cfs_rq, se);

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

	update_cfs_group(se);

	/*
	 * Now advance min_vruntime if @se was the entity holding it back,
	 * except when: DEQUEUE_SAVE && !DEQUEUE_MOVE, in this case we'll be
	 * put back on, and if we advance min_vruntime, we'll be placed back
	 * further than we started -- ie. we'll be penalized.
	 */
	if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE)
		update_min_vruntime(cfs_rq);
}

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

	/* 'current' is not kept within the tree. */
	if (se->on_rq) {
		/*
		 * Any task has to be enqueued before it get to execute on
		 * a CPU. So account for the time it spent waiting on the
		 * runqueue.
		 */
		update_stats_wait_end(cfs_rq, se);
		__dequeue_entity(cfs_rq, se);
		update_load_avg(cfs_rq, se, UPDATE_TG);
		/*
		 * HACK, stash a copy of deadline at the point of pick in vlag,
		 * which isn't used until dequeue.
		 */
		se->vlag = se->deadline;
	}

	update_stats_curr_start(cfs_rq, se);
	cfs_rq->curr = se;

	/*
	 * 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 (schedstat_enabled() && rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
		schedstat_set(se->statistics.slice_max,
			max((u64)schedstat_val(se->statistics.slice_max),
			    se->sum_exec_runtime - se->prev_sum_exec_runtime));
	}

	se->prev_sum_exec_runtime = se->sum_exec_runtime;
}

/*
 * 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)
{
	/*
	 * Enabling NEXT_BUDDY will affect latency but not fairness.
	 */
	if (sched_feat(NEXT_BUDDY) &&
	    cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next))
		return cfs_rq->next;

	return pick_eevdf(cfs_rq);
}

static bool 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);

	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_load_avg(cfs_rq, prev, 0);
	}
	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_load_avg(cfs_rq, curr, UPDATE_TG);
	update_cfs_group(curr);

#ifdef CONFIG_SCHED_HRTICK
	/*
	 * queued ticks are scheduled to match the slice, so don't bother
	 * validating it and just reschedule.
	 */
	if (queued) {
		resched_curr(rq_of(cfs_rq));
		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
}


/**************************************************
 * 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_cpuslocked(&__cfs_bandwidth_used);
}

void cfs_bandwidth_usage_dec(void)
{
	static_key_slow_dec_cpuslocked(&__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. 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)
{
	if (cfs_b->quota != RUNTIME_INF)
		cfs_b->runtime = cfs_b->quota;
}

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_pelt - cfs_rq->throttled_clock_pelt_time;

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

/* returns 0 on failure to allocate runtime */
static int __assign_cfs_rq_runtime(struct cfs_bandwidth *cfs_b,
				   struct cfs_rq *cfs_rq, u64 target_runtime)
{
	u64 min_amount, amount = 0;

	lockdep_assert_held(&cfs_b->lock);

	/* note: this is a positive sum as runtime_remaining <= 0 */
	min_amount = target_runtime - cfs_rq->runtime_remaining;

	if (cfs_b->quota == RUNTIME_INF)
		amount = min_amount;
	else {
		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;
		}
	}

	cfs_rq->runtime_remaining += amount;

	return cfs_rq->runtime_remaining > 0;
}

/* returns 0 on failure to allocate runtime */
static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
	int ret;

	raw_spin_lock(&cfs_b->lock);
	ret = __assign_cfs_rq_runtime(cfs_b, cfs_rq, sched_cfs_bandwidth_slice());
	raw_spin_unlock(&cfs_b->lock);

	return ret;
}

static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
{
	/* dock delta_exec before expiring quota (as it could span periods) */
	cfs_rq->runtime_remaining -= delta_exec;

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

	if (cfs_rq->throttled)
		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_curr(rq_of(cfs_rq));
}

static __always_inline
void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 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--;
	if (!cfs_rq->throttle_count) {
		/* adjust cfs_rq_clock_task() */
		cfs_rq->throttled_clock_pelt_time += rq_clock_pelt(rq) -
					     cfs_rq->throttled_clock_pelt;

		/* Add cfs_rq with already running entity in the list */
		if (cfs_rq->nr_running >= 1)
			list_add_leaf_cfs_rq(cfs_rq);
	}

	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_pelt = rq_clock_pelt(rq);
		list_del_leaf_cfs_rq(cfs_rq);
	}
	cfs_rq->throttle_count++;

	return 0;
}

static bool 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, idle_task_delta, dequeue = 1;

	raw_spin_lock(&cfs_b->lock);
	/* This will start the period timer if necessary */
	if (__assign_cfs_rq_runtime(cfs_b, cfs_rq, 1)) {
		/*
		 * We have raced with bandwidth becoming available, and if we
		 * actually throttled the timer might not unthrottle us for an
		 * entire period. We additionally needed to make sure that any
		 * subsequent check_cfs_rq_runtime calls agree not to throttle
		 * us, as we may commit to do cfs put_prev+pick_next, so we ask
		 * for 1ns of runtime rather than just check cfs_b.
		 */
		dequeue = 0;
	} else {
		list_add_tail_rcu(&cfs_rq->throttled_list,
				  &cfs_b->throttled_cfs_rq);
	}
	raw_spin_unlock(&cfs_b->lock);

	if (!dequeue)
		return false;  /* Throttle no longer required. */

	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;
	idle_task_delta = cfs_rq->idle_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;
                qcfs_rq->idle_h_nr_running -= idle_task_delta;
		walt_dec_throttled_cfs_rq_stats(&qcfs_rq->walt_stats, cfs_rq);

		if (qcfs_rq->load.weight)
			dequeue = 0;
	}

	if (!se) {
		sub_nr_running(rq, task_delta);
		walt_dec_throttled_cfs_rq_stats(&rq->walt_stats, cfs_rq);
	}

	/*
	 * Note: distribution will already see us throttled via the
	 * throttled-list.  rq->lock protects completion.
	 */
	cfs_rq->throttled = 1;
	cfs_rq->throttled_clock = rq_clock(rq);
	return true;
}

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;
	long task_delta, idle_task_delta;
	struct cfs_rq *tcfs_rq __maybe_unused = cfs_rq;

	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;
	idle_task_delta = cfs_rq->idle_h_nr_running;
	for_each_sched_entity(se) {
		if (se->on_rq)
			break;
		cfs_rq = cfs_rq_of(se);
		enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);

		cfs_rq->h_nr_running += task_delta;
                cfs_rq->idle_h_nr_running += idle_task_delta;
		walt_inc_throttled_cfs_rq_stats(&cfs_rq->walt_stats, tcfs_rq);

		/* end evaluation on encountering a throttled cfs_rq */
		if (cfs_rq_throttled(cfs_rq))
			goto unthrottle_throttle;
	}

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

		update_load_avg(cfs_rq, se, UPDATE_TG);
		se_update_runnable(se);

		cfs_rq->h_nr_running += task_delta;
		cfs_rq->idle_h_nr_running += idle_task_delta;


		/* end evaluation on encountering a throttled cfs_rq */
		if (cfs_rq_throttled(cfs_rq))
			goto unthrottle_throttle;

		/*
		 * One parent has been throttled and cfs_rq removed from the
		 * list. Add it back to not break the leaf list.
		 */
		if (throttled_hierarchy(cfs_rq))
			list_add_leaf_cfs_rq(cfs_rq);
	}

	/* At this point se is NULL and we are at root level*/
	add_nr_running(rq, task_delta);

unthrottle_throttle:
	/*
	 * The cfs_rq_throttled() breaks in the above iteration can result in
	 * incomplete leaf list maintenance, resulting in triggering the
	 * assertion below.
	 */
	for_each_sched_entity(se) {
		cfs_rq = cfs_rq_of(se);

		if (list_add_leaf_cfs_rq(cfs_rq))
			break;
	}

	assert_list_leaf_cfs_rq(rq);

	if (!se) {
		add_nr_running(rq, task_delta);
		walt_inc_throttled_cfs_rq_stats(&rq->walt_stats, tcfs_rq);
	}

	/* determine whether we need to wake up potentially idle cpu */
	if (rq->curr == rq->idle && rq->cfs.nr_running)
		resched_curr(rq);
}

static void distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
{
	struct cfs_rq *cfs_rq;
	u64 runtime, remaining = 1;

	rcu_read_lock();
	list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq,
				throttled_list) {
		struct rq *rq = rq_of(cfs_rq);
		struct rq_flags rf;

		rq_lock(rq, &rf);
		if (!cfs_rq_throttled(cfs_rq))
			goto next;

		/* By the above check, this should never be true */
		SCHED_WARN_ON(cfs_rq->runtime_remaining > 0);

		raw_spin_lock(&cfs_b->lock);
		runtime = -cfs_rq->runtime_remaining + 1;
		if (runtime > cfs_b->runtime)
			runtime = cfs_b->runtime;
		cfs_b->runtime -= runtime;
		remaining = cfs_b->runtime;
		raw_spin_unlock(&cfs_b->lock);

		cfs_rq->runtime_remaining += runtime;

		/* we check whether we're throttled above */
		if (cfs_rq->runtime_remaining > 0)
			unthrottle_cfs_rq(cfs_rq);

next:
		rq_unlock(rq, &rf);

		if (!remaining)
			break;
	}
	rcu_read_unlock();
}

/*
 * 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)
{
	int throttled;

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

	throttled = !list_empty(&cfs_b->throttled_cfs_rq);
	cfs_b->nr_periods += overrun;

	/*
	 * idle depends on !throttled (for the case of a large deficit), and if
	 * we're going inactive then everything else can be deferred
	 */
	if (cfs_b->idle && !throttled)
		goto out_deactivate;

	__refill_cfs_bandwidth_runtime(cfs_b);

	if (!throttled) {
		/* mark as potentially idle for the upcoming period */
		cfs_b->idle = 1;
		return 0;
	}

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

	/*
	 * This check is repeated as we release cfs_b->lock while we unthrottle.
	 */
	while (throttled && cfs_b->runtime > 0) {
		raw_spin_unlock(&cfs_b->lock);
		/* we can't nest cfs_b->lock while distributing bandwidth */
		distribute_cfs_runtime(cfs_b);
		raw_spin_lock(&cfs_b->lock);

		throttled = !list_empty(&cfs_b->throttled_cfs_rq);
	}

	/*
	 * 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;

	return 0;

out_deactivate:
	return 1;
}

/* 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?
 *
 * Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the
 * hrtimer base being cleared by hrtimer_start. In the case of
 * migrate_hrtimers, base is never cleared, so we are fine.
 */
static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
{
	struct hrtimer *refresh_timer = &cfs_b->period_timer;
	s64 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 < (s64)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;

	/* don't push forwards an existing deferred unthrottle */
	if (cfs_b->slack_started)
		return;
	cfs_b->slack_started = true;

	hrtimer_start(&cfs_b->slack_timer,
			ns_to_ktime(cfs_bandwidth_slack_period),
			HRTIMER_MODE_REL);
}

/* 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_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();

	/* confirm we're still not at a refresh boundary */
	raw_spin_lock(&cfs_b->lock);
	cfs_b->slack_started = false;

	if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
		raw_spin_unlock(&cfs_b->lock);
		return;
	}

	if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice)
		runtime = cfs_b->runtime;

	raw_spin_unlock(&cfs_b->lock);

	if (!runtime)
		return;

	distribute_cfs_runtime(cfs_b);

	raw_spin_lock(&cfs_b->lock);
	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);
}

static void sync_throttle(struct task_group *tg, int cpu)
{
	struct cfs_rq *pcfs_rq, *cfs_rq;

	if (!cfs_bandwidth_used())
		return;

	if (!tg->parent)
		return;

	cfs_rq = tg->cfs_rq[cpu];
	pcfs_rq = tg->parent->cfs_rq[cpu];

	cfs_rq->throttle_count = pcfs_rq->throttle_count;
	cfs_rq->throttled_clock_pelt = rq_clock_pelt(cpu_rq(cpu));
}

/* conditionally throttle active cfs_rq's from put_prev_entity() */
static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
	if (!cfs_bandwidth_used())
		return false;

	if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0))
		return false;

	/*
	 * 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 true;

	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;
}

extern const u64 max_cfs_quota_period;

static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
{
	struct cfs_bandwidth *cfs_b =
		container_of(timer, struct cfs_bandwidth, period_timer);
	int overrun;
	int idle = 0;
	int count = 0;

	raw_spin_lock(&cfs_b->lock);
	for (;;) {
		overrun = hrtimer_forward_now(timer, cfs_b->period);
		if (!overrun)
			break;

		if (++count > 3) {
			u64 new, old = ktime_to_ns(cfs_b->period);

			/*
			 * Grow period by a factor of 2 to avoid losing precision.
			 * Precision loss in the quota/period ratio can cause __cfs_schedulable
			 * to fail.
			 */
			new = old * 2;
			if (new < max_cfs_quota_period) {
				cfs_b->period = ns_to_ktime(new);
				cfs_b->quota *= 2;

				pr_warn_ratelimited(
	"cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us = %lld, cfs_quota_us = %lld)\n",
					smp_processor_id(),
					div_u64(new, NSEC_PER_USEC),
					div_u64(cfs_b->quota, NSEC_PER_USEC));
			} else {
				pr_warn_ratelimited(
	"cfs_period_timer[cpu%d]: period too short, but cannot scale up without losing precision (cfs_period_us = %lld, cfs_quota_us = %lld)\n",
					smp_processor_id(),
					div_u64(old, NSEC_PER_USEC),
					div_u64(cfs_b->quota, NSEC_PER_USEC));
			}

			/* reset count so we don't come right back in here */
			count = 0;
		}

		idle = do_sched_cfs_period_timer(cfs_b, overrun);
	}
	if (idle)
		cfs_b->period_active = 0;
	raw_spin_unlock(&cfs_b->lock);

	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_ABS_PINNED);
	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;
	cfs_b->slack_started = false;
}

static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
	cfs_rq->runtime_enabled = 0;
	INIT_LIST_HEAD(&cfs_rq->throttled_list);
	walt_init_cfs_rq_stats(cfs_rq);
}

void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
	u64 overrun;

	lockdep_assert_held(&cfs_b->lock);

	if (cfs_b->period_active)
		return;

	cfs_b->period_active = 1;
	overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
	cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period);
	cfs_b->expires_seq++;
	hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
}

static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
	/* init_cfs_bandwidth() was not called */
	if (!cfs_b->throttled_cfs_rq.next)
		return;

	hrtimer_cancel(&cfs_b->period_timer);
	hrtimer_cancel(&cfs_b->slack_timer);
}

/*
 * Both these cpu hotplug callbacks race against unregister_fair_sched_group()
 *
 * The race is harmless, since modifying bandwidth settings of unhooked group
 * bits doesn't do much.
 */

/* cpu online calback */
static void __maybe_unused update_runtime_enabled(struct rq *rq)
{
	struct task_group *tg;

	lockdep_assert_held(&rq->lock);

	rcu_read_lock();
	list_for_each_entry_rcu(tg, &task_groups, list) {
		struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];

		raw_spin_lock(&cfs_b->lock);
		cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF;
		raw_spin_unlock(&cfs_b->lock);
	}
	rcu_read_unlock();
}

/* cpu offline callback */
static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
{
	struct task_group *tg;

	lockdep_assert_held(&rq->lock);

	rcu_read_lock();
	list_for_each_entry_rcu(tg, &task_groups, list) {
		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];

		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 = 1;
		/*
		 * Offline rq is schedulable till cpu is completely disabled
		 * in take_cpu_down(), so we prevent new cfs throttling here.
		 */
		cfs_rq->runtime_enabled = 0;

		if (cfs_rq_throttled(cfs_rq))
			unthrottle_cfs_rq(cfs_rq);
	}
	rcu_read_unlock();
}

#else /* CONFIG_CFS_BANDWIDTH */

static inline bool cfs_bandwidth_used(void)
{
	return false;
}

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, u64 delta_exec) {}
static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; }
static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
static inline void sync_throttle(struct task_group *tg, int cpu) {}
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 update_runtime_enabled(struct rq *rq) {}
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;

	SCHED_WARN_ON(task_rq(p) != rq);

	if (rq->cfs.h_nr_running > 1) {
		u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime;
		u64 slice = se->slice;
		s64 delta = slice - ran;

		if (delta < 0) {
			if (rq->curr == p)
				resched_curr(rq);
			return;
		}
		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;

	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

#ifdef CONFIG_SMP
static bool sd_overutilized(struct sched_domain *sd)
{
	return sd->shared->overutilized;
}

static void set_sd_overutilized(struct sched_domain *sd)
{
	trace_sched_overutilized(sd, sd->shared->overutilized, true);
	sd->shared->overutilized = true;
}

static void clear_sd_overutilized(struct sched_domain *sd)
{
	trace_sched_overutilized(sd, sd->shared->overutilized, false);
	sd->shared->overutilized = false;
}

static inline void update_overutilized_status(struct rq *rq)
{
	struct sched_domain *sd;

	rcu_read_lock();
	sd = rcu_dereference(rq->sd);
	if (cpu_overutilized(rq->cpu)) {
		if (sd && (sd->flags & SD_LOAD_BALANCE))
			set_sd_overutilized(sd);
		else if (sd && sd->parent)
			set_sd_overutilized(sd->parent);
	}
	rcu_read_unlock();
}
#else

#define update_overutilized_status(rq) do {} while (0)

#endif /* CONFIG_SMP */

/* Runqueue only has SCHED_IDLE tasks enqueued */
static int sched_idle_rq(struct rq *rq)
{
	return unlikely(rq->nr_running == rq->cfs.idle_h_nr_running &&
			rq->nr_running);
}

static int sched_idle_cpu(int cpu)
{
	return sched_idle_rq(cpu_rq(cpu));
}

/*
 * 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;
	int task_new = !(flags & ENQUEUE_WAKEUP);
	int idle_h_nr_running = task_has_idle_policy(p);
	bool prefer_idle = sched_feat(EAS_PREFER_IDLE) ?
				(uclamp_latency_sensitive(p) > 0) : 0;

#ifdef CONFIG_SCHED_WALT
	p->misfit = !task_fits_max(p, rq->cpu);
#endif
	/*
	 * The code below (indirectly) updates schedutil which looks at
	 * the cfs_rq utilization to select a frequency.
	 * Let's add the task's estimated utilization to the cfs_rq's
	 * estimated utilization, before we update schedutil.
	 */
	util_est_enqueue(&rq->cfs, p);

	/*
	 * The code below (indirectly) updates schedutil which looks at
	 * the cfs_rq utilization to select a frequency.
	 * Let's update schedtune here to ensure the boost value of the
	 * current task is accounted for in the selection of the OPP.
	 *
	 * We do it also in the case where we enqueue a throttled task;
	 * we could argue that a throttled task should not boost a CPU,
	 * however:
	 * a) properly implementing CPU boosting considering throttled
	 *    tasks will increase a lot the complexity of the solution
	 * b) it's not easy to quantify the benefits introduced by
	 *    such a more complex solution.
	 * Thus, for the time being we go for the simple solution and boost
	 * also for throttled RQs.
	 */
	schedtune_enqueue_task(p, cpu_of(rq));

	/*
	 * If in_iowait is set, the code below may not trigger any cpufreq
	 * utilization updates, so do it here explicitly with the IOWAIT flag
	 * passed.
	 */
	if (p->in_iowait && prefer_idle)
		cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT);

	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++;
                cfs_rq->idle_h_nr_running += idle_h_nr_running;
		walt_inc_cfs_rq_stats(cfs_rq, p);

		flags = ENQUEUE_WAKEUP;
	}

	for_each_sched_entity(se) {
		cfs_rq = cfs_rq_of(se);
		cfs_rq->h_nr_running++;
                cfs_rq->idle_h_nr_running += idle_h_nr_running;
		walt_inc_cfs_rq_stats(cfs_rq, p);

		if (cfs_rq_throttled(cfs_rq))
			break;

		update_load_avg(cfs_rq, se, UPDATE_TG);
		update_cfs_group(se);
	}

	if (!se) {
		add_nr_running(rq, 1);
		inc_rq_walt_stats(rq, p);
		/*
		 * If the task prefers idle cpu, and it also is the first
		 * task enqueued in this runqueue, then we don't check
		 * overutilized. Hopefully the cpu util will be back to
		 * normal before next overutilized check.
		 */
		if (!task_new &&
			!(prefer_idle && rq->nr_running == 1))
			update_overutilized_status(rq);
	}

	if (cfs_bandwidth_used()) {
		/*
		 * When bandwidth control is enabled; the cfs_rq_throttled()
		 * breaks in the above iteration can result in incomplete
		 * leaf list maintenance, resulting in triggering the assertion
		 * below.
		 */
		for_each_sched_entity(se) {
			cfs_rq = cfs_rq_of(se);

			if (list_add_leaf_cfs_rq(cfs_rq))
				break;
		}
	}

	assert_list_leaf_cfs_rq(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;
	int idle_h_nr_running = task_has_idle_policy(p);
	bool was_sched_idle = sched_idle_rq(rq);

	/*
	 * The code below (indirectly) updates schedutil which looks at
	 * the cfs_rq utilization to select a frequency.
	 * Let's update schedtune here to ensure the boost value of the
	 * current task is not more accounted for in the selection of the OPP.
	 */
	schedtune_dequeue_task(p, cpu_of(rq));

	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--;
                cfs_rq->idle_h_nr_running -= idle_h_nr_running;
		walt_dec_cfs_rq_stats(cfs_rq, p);

		/* Don't dequeue parent if it has other entities besides us */
		if (cfs_rq->load.weight) {
			/* Avoid re-evaluating load for this entity: */
			se = parent_entity(se);
			/*
			 * 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 && se && !throttled_hierarchy(cfs_rq))
				set_next_buddy(se);
			break;
		}
		flags |= DEQUEUE_SLEEP;
	}

	for_each_sched_entity(se) {
		cfs_rq = cfs_rq_of(se);
		cfs_rq->h_nr_running--;
                cfs_rq->idle_h_nr_running -= idle_h_nr_running;
		walt_dec_cfs_rq_stats(cfs_rq, p);

		if (cfs_rq_throttled(cfs_rq))
			break;

		update_load_avg(cfs_rq, se, UPDATE_TG);
		update_cfs_group(se);
	}

	if (!se) {
		sub_nr_running(rq, 1);
		dec_rq_walt_stats(rq, p);
	}

	/* balance early to pull high priority tasks */
	if (unlikely(!was_sched_idle && sched_idle_rq(rq)))
		rq->next_balance = jiffies;

	util_est_dequeue(&rq->cfs, p, task_sleep);
	hrtick_update(rq);
}

#ifdef CONFIG_SMP

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

static unsigned long weighted_cpuload(struct rq *rq)
{
	return cfs_rq_runnable_load_avg(&rq->cfs);
}

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

	if (nr_running)
		return load_avg / nr_running;

	return 0;
}

static void record_wakee(struct task_struct *p)
{
	/*
	 * Only decay a single time; tasks that have less then 1 wakeup per
	 * jiffy will not have built up many flips.
	 */
	if (time_after(jiffies, current->wakee_flip_decay_ts + HZ)) {
		current->wakee_flips >>= 1;
		current->wakee_flip_decay_ts = jiffies;
	}

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

/*
 * Returns the current capacity of cpu after applying both
 * cpu and freq scaling.
 */
unsigned long capacity_curr_of(int cpu)
{
	unsigned long max_cap = cpu_rq(cpu)->cpu_capacity_orig;
	unsigned long scale_freq = arch_scale_freq_capacity(cpu);

	return cap_scale(max_cap, scale_freq);
}

inline bool energy_aware(void)
{
	return sysctl_sched_energy_aware;
}

/*
 * Externally visible function. Let's keep the one above
 * so that the check is inlined/optimized in the sched paths.
 */
bool sched_is_energy_aware(void)
{
	return energy_aware();
}

/*
 * __cpu_norm_util() returns the cpu util relative to a specific capacity,
 * i.e. it's busy ratio, in the range [0..SCHED_CAPACITY_SCALE] which is useful
 * for energy calculations. Using the scale-invariant util returned by
 * cpu_util() and approximating scale-invariant util by:
 *
 *   util ~ (curr_freq/max_freq)*1024 * capacity_orig/1024 * running_time/time
 *
 * the normalized util can be found using the specific capacity.
 *
 *   capacity = capacity_orig * curr_freq/max_freq
 *
 *   norm_util = running_time/time ~ util/capacity
 */
static unsigned long __cpu_norm_util(unsigned long util, unsigned long capacity)
{
	if (util >= capacity)
		return SCHED_CAPACITY_SCALE;

	return (util << SCHED_CAPACITY_SHIFT)/capacity;
}

/*
 * Check whether cpu is in the fastest set of cpu's that p should run on.
 * If p is boosted, prefer that p runs on a faster cpu; otherwise, allow p
 * to run on any cpu.
 */
static inline bool
cpu_is_in_target_set(struct task_struct *p, int cpu)
{
	struct root_domain *rd = cpu_rq(cpu)->rd;
	int first_cpu = (uclamp_boosted(p)) ?
		rd->mid_cap_orig_cpu : rd->min_cap_orig_cpu;
	int next_usable_cpu = cpumask_next(first_cpu - 1, p->cpus_ptr);
	return cpu >= next_usable_cpu || next_usable_cpu >= nr_cpu_ids;
}

static inline bool
bias_to_waker_cpu(struct task_struct *p, int cpu, struct cpumask *rtg_target)
{
	bool base_test = cpumask_test_cpu(cpu, p->cpus_ptr) &&
			cpu_active(cpu) && task_fits_max(p, cpu) &&
			!__cpu_overutilized(cpu, task_util(p)) &&
			cpu_is_in_target_set(p, cpu);
	bool rtg_test = rtg_target && cpumask_test_cpu(cpu, rtg_target);

	return base_test && (!rtg_target || rtg_test);
}

/*
 * CPU candidates.
 *
 * These are labels to reference CPU candidates for an energy_diff.
 * Currently we support only two possible candidates: the task's previous CPU
 * and another candiate CPU.
 * More advanced/aggressive EAS selection policies can consider more
 * candidates.
 */
#define EAS_CPU_PRV	0
#define EAS_CPU_NXT	1
#define EAS_CPU_BKP	2

/*
 * energy_diff - supports the computation of the estimated energy impact in
 * moving a "task"'s "util_delta" between different CPU candidates.
 */
/*
 * NOTE: When using or examining WALT task signals, all wakeup
 * latency is included as busy time for task util.
 *
 * This is relevant here because:
 * When debugging is enabled, it can take as much as 1ms to
 * write the output to the trace buffer for each eenv
 * scenario. For periodic tasks where the sleep time is of
 * a similar order, the WALT task util can be inflated.
 *
 * Further, and even without debugging enabled,
 * task wakeup latency changes depending upon the EAS
 * wakeup algorithm selected - FIND_BEST_TARGET only does
 * energy calculations for up to 2 candidate CPUs. When
 * NO_FIND_BEST_TARGET is configured, we can potentially
 * do an energy calculation across all CPUS in the system.
 *
 * The impact to WALT task util on a Juno board
 * running a periodic task which only sleeps for 200usec
 * between 1ms activations has been measured.
 * (i.e. the wakeup latency induced by energy calculation
 * and debug output is double the desired sleep time and
 * almost equivalent to the runtime which is more-or-less
 * the worst case possible for this test)
 *
 * In this scenario, a task which has a PELT util of around
 * 220 is inflated under WALT to have util around 400.
 *
 * This is simply a property of the way WALT includes
 * wakeup latency in busy time while PELT does not.
 *
 * Hence - be careful when enabling DEBUG_EENV_DECISIONS
 * expecially if WALT is the task signal.
 */
/*#define DEBUG_EENV_DECISIONS*/

#ifdef DEBUG_EENV_DECISIONS
/* max of 8 levels of sched groups traversed */
#define EAS_EENV_DEBUG_LEVELS 16

struct _eenv_debug {
	unsigned long cap;
	unsigned long norm_util;
	unsigned long cap_energy;
	unsigned long idle_energy;
	unsigned long this_energy;
	unsigned long this_busy_energy;
	unsigned long this_idle_energy;
	cpumask_t group_cpumask;
	unsigned long cpu_util[1];
};
#endif

struct eenv_cpu {
	/* CPU ID, must be in cpus_mask */
	int     cpu_id;

	/*
	 * Index (into sched_group_energy::cap_states) of the OPP the
	 * CPU needs to run at if the task is placed on it.
	 * This includes the both active and blocked load, due to
	 * other tasks on this CPU,  as well as the task's own
	 * utilization.
	*/
	int     cap_idx;
	int     cap;

	/* Estimated system energy */
	unsigned long energy;

	/* Estimated energy variation wrt EAS_CPU_PRV */
	long nrg_delta;

#ifdef DEBUG_EENV_DECISIONS
	struct _eenv_debug *debug;
	int debug_idx;
#endif /* DEBUG_EENV_DECISIONS */
};

struct energy_env {
	/* Utilization to move */
	struct task_struct	*p;
	unsigned long		util_delta;
	unsigned long		util_delta_boosted;

	/* Mask of CPUs candidates to evaluate */
	cpumask_t		cpus_mask;

	/* CPU candidates to evaluate */
	struct eenv_cpu *cpu;
	int eenv_cpu_count;

#ifdef DEBUG_EENV_DECISIONS
	/* pointer to the memory block reserved
	 * for debug on this CPU - there will be
	 * sizeof(struct _eenv_debug) *
	 *  (EAS_CPU_CNT * EAS_EENV_DEBUG_LEVELS)
	 * bytes allocated here.
	 */
	struct _eenv_debug *debug;
#endif
	/*
	 * Index (into energy_env::cpu) of the morst energy efficient CPU for
	 * the specified energy_env::task
	 */
	int	next_idx;
	int	max_cpu_count;

	/* Support data */
	struct sched_group	*sg_top;
	struct sched_group	*sg_cap;
	struct sched_group	*sg;
};

/*
 * cpu_util_without: compute cpu utilization without any contributions from *p
 * @cpu: the CPU which utilization is requested
 * @p: the task which utilization should be discounted
 *
 * The utilization of a CPU is defined by the utilization of tasks currently
 * enqueued on that CPU as well as tasks which are currently sleeping after an
 * execution on that CPU.
 *
 * This method returns the utilization of the specified CPU by discounting the
 * utilization of the specified task, whenever the task is currently
 * contributing to the CPU utilization.
 */
static unsigned long cpu_util_without(int cpu, struct task_struct *p)
{
	struct cfs_rq *cfs_rq;
	unsigned int util;

#ifdef CONFIG_SCHED_WALT
	/*
	 * WALT does not decay idle tasks in the same manner
	 * as PELT, so it makes little sense to subtract task
	 * utilization from cpu utilization. Instead just use
	 * cpu_util for this case.
	 */
	if (likely(!walt_disabled && sysctl_sched_use_walt_cpu_util) &&
						p->state == TASK_WAKING)
		return cpu_util(cpu);
#endif

	/* Task has no contribution or is new */
	if (cpu != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time))
		return cpu_util(cpu);

#ifdef CONFIG_SCHED_WALT
	util = max_t(long, cpu_util(cpu) - task_util(p), 0);
#else

	cfs_rq = &cpu_rq(cpu)->cfs;
	util = READ_ONCE(cfs_rq->avg.util_avg);

	/* Discount task's util from CPU's util */
	lsub_positive(&util, task_util(p));

	/*
	 * Covered cases:
	 *
	 * a) if *p is the only task sleeping on this CPU, then:
	 *      cpu_util (== task_util) > util_est (== 0)
	 *    and thus we return:
	 *      cpu_util_without = (cpu_util - task_util) = 0
	 *
	 * b) if other tasks are SLEEPING on this CPU, which is now exiting
	 *    IDLE, then:
	 *      cpu_util >= task_util
	 *      cpu_util > util_est (== 0)
	 *    and thus we discount *p's blocked utilization to return:
	 *      cpu_util_without = (cpu_util - task_util) >= 0
	 *
	 * c) if other tasks are RUNNABLE on that CPU and
	 *      util_est > cpu_util
	 *    then we use util_est since it returns a more restrictive
	 *    estimation of the spare capacity on that CPU, by just
	 *    considering the expected utilization of tasks already
	 *    runnable on that CPU.
	 *
	 * Cases a) and b) are covered by the above code, while case c) is
	 * covered by the following code when estimated utilization is
	 * enabled.
	 */
	if (sched_feat(UTIL_EST)) {
		unsigned int estimated =
			READ_ONCE(cfs_rq->avg.util_est.enqueued);

		/*
		 * Despite the following checks we still have a small window
		 * for a possible race, when an execl's select_task_rq_fair()
		 * races with LB's detach_task():
		 *
		 *   detach_task()
		 *     p->on_rq = TASK_ON_RQ_MIGRATING;
		 *     ---------------------------------- A
		 *     deactivate_task()                   \
		 *       dequeue_task()                     + RaceTime
		 *         util_est_dequeue()              /
		 *     ---------------------------------- B
		 *
		 * The additional check on "current == p" it's required to
		 * properly fix the execl regression and it helps in further
		 * reducing the chances for the above race.
		 */
		if (unlikely(task_on_rq_queued(p) || current == p))
			lsub_positive(&estimated, _task_util_est(p));

		util = max(util, estimated);
	}
#endif

	/*
	 * Utilization (estimated) can exceed the CPU capacity, thus let's
	 * clamp to the maximum CPU capacity to ensure consistency with
	 * the cpu_util call.
	 */
	return min_t(unsigned long, util, capacity_orig_of(cpu));
}

static unsigned long group_max_util(struct energy_env *eenv, int cpu_idx)
{
	unsigned long max_util = 0;
	unsigned long util;
	int cpu;

	for_each_cpu(cpu, sched_group_span(eenv->sg_cap)) {
		util = cpu_util_without(cpu, eenv->p);

		/*
		 * If we are looking at the target CPU specified by the eenv,
		 * then we should add the (estimated) utilization of the task
		 * assuming we will wake it up on that CPU.
		 */
		if (unlikely(cpu == eenv->cpu[cpu_idx].cpu_id))
			util += eenv->util_delta_boosted;

		max_util = max(max_util, util);
	}

	return max_util;
}

/*
 * group_norm_util() returns the approximated group util relative to it's
 * current capacity (busy ratio) in the range [0..SCHED_CAPACITY_SCALE] for use
 * in energy calculations. Since task executions may or may not overlap in time
 * in the group the true normalized util is between max(cpu_norm_util(i)) and
 * sum(cpu_norm_util(i)) when iterating over all cpus in the group, i. The
 * latter is used as the estimate as it leads to a more pessimistic energy
 * estimate (more busy).
 */
static unsigned
long group_norm_util(struct energy_env *eenv, int cpu_idx)
{
	unsigned long capacity = eenv->cpu[cpu_idx].cap;
	unsigned long util, util_sum = 0;
	int cpu;

	for_each_cpu(cpu, sched_group_span(eenv->sg)) {
		util = cpu_util_without(cpu, eenv->p);

		/*
		 * If we are looking at the target CPU specified by the eenv,
		 * then we should add the (estimated) utilization of the task
		 * assuming we will wake it up on that CPU.
		 */
		if (unlikely(cpu == eenv->cpu[cpu_idx].cpu_id))
			util += eenv->util_delta;

		util_sum += __cpu_norm_util(util, capacity);
	}

	if (util_sum > SCHED_CAPACITY_SCALE)
		return SCHED_CAPACITY_SCALE;
	return util_sum;
}

static int find_new_capacity(struct energy_env *eenv, int cpu_idx)
{
	const struct sched_group_energy *sge = eenv->sg_cap->sge;
	unsigned long util = group_max_util(eenv, cpu_idx);
	int idx, cap_idx;

	cap_idx = sge->nr_cap_states - 1;

	for (idx = 0; idx < sge->nr_cap_states; idx++) {
		if (sge->cap_states[idx].cap >= util) {
			cap_idx = idx;
			break;
		}
	}
	/* Keep track of SG's capacity */
	eenv->cpu[cpu_idx].cap = sge->cap_states[cap_idx].cap;
	eenv->cpu[cpu_idx].cap_idx = cap_idx;

	return cap_idx;
}

static int group_idle_state(struct energy_env *eenv, int cpu_idx)
{
	struct sched_group *sg = eenv->sg;
	int src_in_grp, dst_in_grp;
	int i, state = INT_MAX;
	int max_idle_state_idx;
	long grp_util = 0;
	int new_state;

	/* Find the shallowest idle state in the sched group. */
	for_each_cpu(i, sched_group_span(sg))
		state = min(state, idle_get_state_idx(cpu_rq(i)));

	if (unlikely(state == INT_MAX))
		return -EINVAL;

	/* Take non-cpuidle idling into account (active idle/arch_cpu_idle()) */
	state++;
	/*
	 * Try to estimate if a deeper idle state is
	 * achievable when we move the task.
	 */
	for_each_cpu(i, sched_group_span(sg))
		grp_util += cpu_util(i);

	src_in_grp = cpumask_test_cpu(eenv->cpu[EAS_CPU_PRV].cpu_id,
				      sched_group_span(sg));
	dst_in_grp = cpumask_test_cpu(eenv->cpu[cpu_idx].cpu_id,
				      sched_group_span(sg));
	if (src_in_grp == dst_in_grp) {
		/*
		 * both CPUs under consideration are in the same group or not in
		 * either group, migration should leave idle state the same.
		 */
		return state;
	}
	/*
	 * add or remove util as appropriate to indicate what group util
	 * will be (worst case - no concurrent execution) after moving the task
	 */
	grp_util += src_in_grp ? -eenv->util_delta : eenv->util_delta;

	if (grp_util >
		((long)sg->sgc->max_capacity * (int)sg->group_weight)) {
		/*
		 * After moving, the group will be fully occupied
		 * so assume it will not be idle at all.
		 */
		return 0;
	}

	/*
	 * after moving, this group is at most partly
	 * occupied, so it should have some idle time.
	 */
	max_idle_state_idx = sg->sge->nr_idle_states - 2;
	new_state = grp_util * max_idle_state_idx;
	if (grp_util <= 0) {
		/* group will have no util, use lowest state */
		new_state = max_idle_state_idx + 1;
	} else {
		/*
		 * for partially idle, linearly map util to idle
		 * states, excluding the lowest one. This does not
		 * correspond to the state we expect to enter in
		 * reality, but an indication of what might happen.
		 */
		new_state = min_t(int, max_idle_state_idx,
				  new_state / sg->sgc->max_capacity);
		new_state = max_idle_state_idx - new_state;
	}
	return new_state;
}

#ifdef DEBUG_EENV_DECISIONS
static struct _eenv_debug *eenv_debug_entry_ptr(struct _eenv_debug *base, int idx);

static void store_energy_calc_debug_info(struct energy_env *eenv, int cpu_idx, int cap_idx, int idle_idx)
{
	int debug_idx = eenv->cpu[cpu_idx].debug_idx;
	unsigned long sg_util, busy_energy, idle_energy;
	const struct sched_group_energy *sge;
	struct _eenv_debug *dbg;
	int cpu;

	if (debug_idx < EAS_EENV_DEBUG_LEVELS) {
		sge = eenv->sg->sge;
		sg_util = group_norm_util(eenv, cpu_idx);
		busy_energy   = sge->cap_states[cap_idx].power;
		busy_energy  *= sg_util;
		idle_energy   = SCHED_CAPACITY_SCALE - sg_util;
		idle_energy  *= sge->idle_states[idle_idx].power;
		/* should we use sg_cap or sg? */
		dbg = eenv_debug_entry_ptr(eenv->cpu[cpu_idx].debug, debug_idx);
		dbg->cap = sge->cap_states[cap_idx].cap;
		dbg->norm_util = sg_util;
		dbg->cap_energy = sge->cap_states[cap_idx].power;
		dbg->idle_energy = sge->idle_states[idle_idx].power;
		dbg->this_energy = busy_energy + idle_energy;
		dbg->this_busy_energy = busy_energy;
		dbg->this_idle_energy = idle_energy;

		cpumask_copy(&dbg->group_cpumask,
				sched_group_span(eenv->sg));

		for_each_cpu(cpu, &dbg->group_cpumask)
			dbg->cpu_util[cpu] = cpu_util(cpu);

		eenv->cpu[cpu_idx].debug_idx = debug_idx+1;
	}
}
#else
#define store_energy_calc_debug_info(a,b,c,d) {}
#endif /* DEBUG_EENV_DECISIONS */

/*
 * calc_sg_energy: compute energy for the eenv's SG (i.e. eenv->sg).
 *
 * This works in iterations to compute the SG's energy for each CPU
 * candidate defined by the energy_env's cpu array.
 */
static int calc_sg_energy(struct energy_env *eenv)
{
	struct sched_group *sg = eenv->sg;
	unsigned long busy_energy, idle_energy;
	unsigned int busy_power, idle_power;
	unsigned long total_energy = 0;
	unsigned long sg_util;
	int cap_idx, idle_idx;
	int cpu_idx;

	for (cpu_idx = EAS_CPU_PRV; cpu_idx < eenv->max_cpu_count; ++cpu_idx) {
		if (eenv->cpu[cpu_idx].cpu_id == -1)
			continue;

		/* Compute ACTIVE energy */
		cap_idx = find_new_capacity(eenv, cpu_idx);
		busy_power = sg->sge->cap_states[cap_idx].power;
		sg_util = group_norm_util(eenv, cpu_idx);
		busy_energy   = sg_util * busy_power;

		/* Compute IDLE energy */
		idle_idx = group_idle_state(eenv, cpu_idx);
		if (unlikely(idle_idx < 0))
			return idle_idx;

		if (idle_idx > sg->sge->nr_idle_states - 1)
			idle_idx = sg->sge->nr_idle_states - 1;

		idle_power = sg->sge->idle_states[idle_idx].power;
		idle_energy   = SCHED_CAPACITY_SCALE - sg_util;
		idle_energy  *= idle_power;

		total_energy = busy_energy + idle_energy;
		eenv->cpu[cpu_idx].energy += total_energy;

		store_energy_calc_debug_info(eenv, cpu_idx, cap_idx, idle_idx);
	}

	return 0;
}

/*
 * compute_energy() computes the absolute variation in energy consumption by
 * moving eenv.util_delta from EAS_CPU_PRV to EAS_CPU_NXT.
 *
 * NOTE: compute_energy() may fail when racing with sched_domain updates, in
 *       which case we abort by returning -EINVAL.
 */
static int compute_energy(struct energy_env *eenv)
{
	struct sched_domain *sd;
	int cpu;
	struct cpumask visit_cpus;
	struct sched_group *sg;
	int cpu_count;

	WARN_ON(!eenv->sg_top->sge);

	cpumask_copy(&visit_cpus, sched_group_span(eenv->sg_top));

	/* If a cpu is hotplugged in while we are in this function, it does
	 * not appear in the existing visit_cpus mask which came from the
	 * sched_group pointer of the sched_domain pointed at by sd_ea for
	 * either the prev or next cpu and was dereferenced in
	 * select_energy_cpu_idx.
	 * Since we will dereference sd_scs later as we iterate through the
	 * CPUs we expect to visit, new CPUs can be present which are not in
	 * the visit_cpus mask. Guard this with cpu_count.
	 */
	cpu_count = cpumask_weight(&visit_cpus);

	while (!cpumask_empty(&visit_cpus)) {
		struct sched_group *sg_shared_cap = NULL;
		cpu = cpumask_first(&visit_cpus);

		/*
		 * Is the group utilization affected by cpus outside this
		 * sched_group?
		 * This sd may have groups with cpus which were not present
		 * when we took visit_cpus.
		 */
		sd = rcu_dereference(per_cpu(sd_scs, cpu));
		if (sd) {
			if (sd->parent)
				sg_shared_cap = sd->parent->groups;
			else /* single cluster system */
				sg_shared_cap = sd->groups;
		}
		for_each_domain(cpu, sd) {
			sg = sd->groups;
			/* Has this sched_domain already been visited? */
			if (sd->child && group_first_cpu(sg) != cpu)
				break;

			do {
				eenv->sg_cap = sg;
				if (sg_shared_cap && sg_shared_cap->group_weight >= sg->group_weight)
					eenv->sg_cap = sg_shared_cap;

				/*
				 * Compute the energy for all the candidate
				 * CPUs in the current visited SG.
				 */
				eenv->sg = sg;
				if (calc_sg_energy(eenv))
					return -EINVAL;

				/* remove CPUs we have just visited */
				if (!sd->child) {
					/*
					 * cpu_count here is the number of
					 * cpus we expect to visit in this
					 * calculation. If we race against
					 * hotplug, we can have extra cpus
					 * added to the groups we are
					 * iterating which do not appear in
					 * the visit_cpus mask. In that case
					 * we are not able to calculate energy
					 * without restarting so we will bail
					 * out and use prev_cpu this time.
					 */
					if (!cpu_count)
						return -EINVAL;
					cpumask_xor(&visit_cpus, &visit_cpus, sched_group_span(sg));
					cpu_count--;
				}

				if (cpumask_equal(sched_group_span(sg), sched_group_span(eenv->sg_top)) &&
					sd->child)
					goto next_cpu;

			} while (sg = sg->next, sg != sd->groups);
		}
next_cpu:
		cpumask_clear_cpu(cpu, &visit_cpus);
		continue;
	}

	return 0;
}

static inline bool cpu_in_sg(struct sched_group *sg, int cpu)
{
	return cpu != -1 && cpumask_test_cpu(cpu, sched_group_span(sg));
}

#ifdef DEBUG_EENV_DECISIONS
static void dump_eenv_debug(struct energy_env *eenv)
{
	int cpu_idx, grp_idx;
	char cpu_utils[(NR_CPUS*12)+10]="cpu_util: ";
	char cpulist[64];

	trace_printk("eenv scenario: task=%p %s task_util=%lu prev_cpu=%d",
			eenv->p, eenv->p->comm, eenv->util_delta, eenv->cpu[EAS_CPU_PRV].cpu_id);

	for (cpu_idx=EAS_CPU_PRV; cpu_idx < eenv->max_cpu_count; cpu_idx++) {
		if (eenv->cpu[cpu_idx].cpu_id == -1)
			continue;
		trace_printk("---Scenario %d: Place task on cpu %d energy=%lu (%d debug logs at %p)",
				cpu_idx+1, eenv->cpu[cpu_idx].cpu_id,
				eenv->cpu[cpu_idx].energy >> SCHED_CAPACITY_SHIFT,
				eenv->cpu[cpu_idx].debug_idx,
				eenv->cpu[cpu_idx].debug);
		for (grp_idx = 0; grp_idx < eenv->cpu[cpu_idx].debug_idx; grp_idx++) {
			struct _eenv_debug *debug;
			int cpu, written=0;

			debug = eenv_debug_entry_ptr(eenv->cpu[cpu_idx].debug, grp_idx);
			cpu = scnprintf(cpulist, sizeof(cpulist), "%*pbl", cpumask_pr_args(&debug->group_cpumask));

			cpu_utils[0] = 0;
			/* print out the relevant cpu_util */
			for_each_cpu(cpu, &(debug->group_cpumask)) {
				char tmp[64];
				if (written > sizeof(cpu_utils)-10) {
					cpu_utils[written]=0;
					break;
				}
				written += snprintf(tmp, sizeof(tmp), "cpu%d(%lu) ", cpu, debug->cpu_util[cpu]);
				strcat(cpu_utils, tmp);
			}
			/* trace the data */
			trace_printk("  | %s : cap=%lu nutil=%lu, cap_nrg=%lu, idle_nrg=%lu energy=%lu busy_energy=%lu idle_energy=%lu %s",
					cpulist, debug->cap, debug->norm_util,
					debug->cap_energy, debug->idle_energy,
					debug->this_energy >> SCHED_CAPACITY_SHIFT,
					debug->this_busy_energy >> SCHED_CAPACITY_SHIFT,
					debug->this_idle_energy >> SCHED_CAPACITY_SHIFT,
					cpu_utils);

		}
		trace_printk("---");
	}
	trace_printk("----- done");
	return;
}
#else
#define dump_eenv_debug(a) {}
#endif /* DEBUG_EENV_DECISIONS */
/*
 * select_energy_cpu_idx(): estimate the energy impact of changing the
 * utilization distribution.
 *
 * The eenv parameter specifies the changes: utilization amount and a
 * collection of possible CPU candidates. The number of candidates
 * depends upon the selection algorithm used.
 *
 * If find_best_target was used to select candidate CPUs, there will
 * be at most 3 including prev_cpu. If not, we used a brute force
 * selection which will provide the union of:
 *  * CPUs belonging to the highest sd which is not overutilized
 *  * CPUs the task is allowed to run on
 *  * online CPUs
 *
 * This function returns the index of a CPU candidate specified by the
 * energy_env which corresponds to the most energy efficient CPU.
 * Thus, 0 (EAS_CPU_PRV) means that non of the CPU candidate is more energy
 * efficient than running on prev_cpu. This is also the value returned in case
 * of abort due to error conditions during the computations. The only
 * exception to this if we fail to access the energy model via sd_ea, where
 * we return -1 with the intent of asking the system to use a different
 * wakeup placement algorithm.
 *
 * A value greater than zero means that the most energy efficient CPU is the
 * one represented by eenv->cpu[eenv->next_idx].cpu_id.
 */
static inline int select_energy_cpu_idx(struct energy_env *eenv)
{
	int last_cpu_idx = eenv->max_cpu_count - 1;
	struct sched_domain *sd;
	struct sched_group *sg;
	int sd_cpu = -1;
	int cpu_idx;
	int margin;

	sd_cpu = eenv->cpu[EAS_CPU_PRV].cpu_id;
	sd = rcu_dereference(per_cpu(sd_ea, sd_cpu));
	if (!sd)
		return -1;

	cpumask_clear(&eenv->cpus_mask);
	for (cpu_idx = EAS_CPU_PRV; cpu_idx < eenv->max_cpu_count; ++cpu_idx) {
		int cpu = eenv->cpu[cpu_idx].cpu_id;

		if (cpu < 0)
			continue;
		cpumask_set_cpu(cpu, &eenv->cpus_mask);
	}

	sg = sd->groups;
	do {
		/* Skip SGs which do not contains a candidate CPU */
		if (!cpumask_intersects(&eenv->cpus_mask, sched_group_span(sg)))
			continue;

		eenv->sg_top = sg;
		if (compute_energy(eenv) == -EINVAL)
			return EAS_CPU_PRV;
	} while (sg = sg->next, sg != sd->groups);
	/* remember - eenv energy values are unscaled */

	/*
	 * Compute the dead-zone margin used to prevent too many task
	 * migrations with negligible energy savings.
	 * An energy saving is considered meaningful if it reduces the energy
	 * consumption of EAS_CPU_PRV CPU candidate by at least ~1.56%
	 */
	margin = eenv->cpu[EAS_CPU_PRV].energy >> 6;

	/*
	 * By default the EAS_CPU_PRV CPU is considered the most energy
	 * efficient, with a 0 energy variation.
	 */
	eenv->next_idx = EAS_CPU_PRV;
	eenv->cpu[EAS_CPU_PRV].nrg_delta = 0;

	dump_eenv_debug(eenv);

	trace_sched_energy_diff(eenv->p, eenv->cpu[EAS_CPU_PRV].cpu_id,
				eenv->cpu[EAS_CPU_PRV].energy,
				eenv->cpu[EAS_CPU_NXT].cpu_id,
				eenv->cpu[EAS_CPU_NXT].energy,
				eenv->cpu[EAS_CPU_BKP].cpu_id,
				eenv->cpu[EAS_CPU_BKP].energy);
	/*
	 * Compare the other CPU candidates to find a CPU which can be
	 * more energy efficient then EAS_CPU_PRV
	 */
	if (sched_feat(FBT_STRICT_ORDER))
		last_cpu_idx = EAS_CPU_BKP;

	for(cpu_idx = EAS_CPU_NXT; cpu_idx <= last_cpu_idx; cpu_idx++) {
		if (eenv->cpu[cpu_idx].cpu_id < 0)
			continue;
		eenv->cpu[cpu_idx].nrg_delta =
			eenv->cpu[cpu_idx].energy -
			eenv->cpu[EAS_CPU_PRV].energy;

		/* filter energy variations within the dead-zone margin */
		if (abs(eenv->cpu[cpu_idx].nrg_delta) < margin)
			eenv->cpu[cpu_idx].nrg_delta = 0;
		/* update the schedule candidate with min(nrg_delta) */
		if (eenv->cpu[cpu_idx].nrg_delta <
		    eenv->cpu[eenv->next_idx].nrg_delta) {
			eenv->next_idx = cpu_idx;
			/* break out if we want to stop on first saving candidate */
			if (sched_feat(FBT_STRICT_ORDER))
				break;
		}
	}

	return eenv->next_idx;
}

/*
 * Detect M:N waker/wakee relationships via a switching-frequency heuristic.
 *
 * A waker of many should wake a different task than the one last awakened
 * at a frequency roughly N times higher than one of its wakees.
 *
 * In order to determine whether we should let the load spread vs consolidating
 * to shared cache, we look for a minimum 'flip' frequency of llc_size in one
 * partner, and a factor of lls_size higher frequency in the other.
 *
 * With both conditions met, we can be relatively sure that the relationship is
 * non-monogamous, with partner count exceeding socket size.
 *
 * Waker/wakee being client/server, worker/dispatcher, interrupt source or
 * whatever is irrelevant, spread criteria is apparent partner count exceeds
 * socket size.
 */
__maybe_unused static int wake_wide(struct task_struct *p)
{
	unsigned int master = current->wakee_flips;
	unsigned int slave = p->wakee_flips;
	int factor = this_cpu_read(sd_llc_size);

	if (master < slave)
		swap(master, slave);
	if (slave < factor || master < slave * factor)
		return 0;
	return 1;
}

/*
 * The purpose of wake_affine() is to quickly determine on which CPU we can run
 * soonest. For the purpose of speed we only consider the waking and previous
 * CPU.
 *
 * wake_affine_idle() - only considers 'now', it check if the waking CPU is
 *			cache-affine and is (or	will be) idle.
 *
 * wake_affine_weight() - considers the weight to reflect the average
 *			  scheduling latency of the CPUs. This seems to work
 *			  for the overloaded case.
 */

static int
wake_affine_idle(int this_cpu, int prev_cpu, int sync)
{
	/*
	 * If this_cpu is idle, it implies the wakeup is from interrupt
	 * context. Only allow the move if cache is shared. Otherwise an
	 * interrupt intensive workload could force all tasks onto one
	 * node depending on the IO topology or IRQ affinity settings.
	 *
	 * If the prev_cpu is idle and cache affine then avoid a migration.
	 * There is no guarantee that the cache hot data from an interrupt
	 * is more important than cache hot data on the prev_cpu and from
	 * a cpufreq perspective, it's better to have higher utilisation
	 * on one CPU.
	 */
	if (available_idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu))
		return available_idle_cpu(prev_cpu) ? prev_cpu : this_cpu;

	if (sync && cpu_rq(this_cpu)->nr_running == 1)
		return this_cpu;

	return nr_cpumask_bits;
}

static int
wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
		   int this_cpu, int prev_cpu, int sync)
{
	s64 this_eff_load, prev_eff_load;
	unsigned long task_load;

	this_eff_load = weighted_cpuload(cpu_rq(this_cpu));

	if (sync) {
		unsigned long current_load = task_h_load(current);

		if (current_load > this_eff_load)
			return this_cpu;

		this_eff_load -= current_load;
	}

	task_load = task_h_load(p);

	this_eff_load += task_load;
	if (sched_feat(WA_BIAS))
		this_eff_load *= 100;
	this_eff_load *= capacity_of(prev_cpu);

	prev_eff_load = weighted_cpuload(cpu_rq(prev_cpu));
	prev_eff_load -= task_load;
	if (sched_feat(WA_BIAS))
		prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2;
	prev_eff_load *= capacity_of(this_cpu);

	/*
	 * If sync, adjust the weight of prev_eff_load such that if
	 * prev_eff == this_eff that select_idle_sibling() will consider
	 * stacking the wakee on top of the waker if no other CPU is
	 * idle.
	 */
	if (sync)
		prev_eff_load += 1;

	return this_eff_load < prev_eff_load ? this_cpu : nr_cpumask_bits;
}

static int wake_affine(struct sched_domain *sd, struct task_struct *p,
		       int prev_cpu, int sync)
{
	int this_cpu = smp_processor_id();
	int target = nr_cpumask_bits;

	if (sched_feat(WA_IDLE))
		target = wake_affine_idle(this_cpu, prev_cpu, sync);

	if (sched_feat(WA_WEIGHT) && target == nr_cpumask_bits)
		target = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync);

	schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts);
	if (target == nr_cpumask_bits)
		return prev_cpu;

	schedstat_inc(sd->ttwu_move_affine);
	schedstat_inc(p->se.statistics.nr_wakeups_affine);
	return target;
}

#ifdef CONFIG_SCHED_TUNE
struct reciprocal_value schedtune_spc_rdiv;

static long
schedtune_margin(unsigned long signal, long boost, long capacity)
{
	long long margin = 0;

	/*
	 * Signal proportional compensation (SPC)
	 *
	 * The Boost (B) value is used to compute a Margin (M) which is
	 * proportional to the complement of the original Signal (S):
	 *   M = B * (capacity - S)
	 * The obtained M could be used by the caller to "boost" S.
	 */
	if (boost >= 0) {
		if (capacity > signal) {
			margin  = capacity - signal;
			margin *= boost;
		}
	} else
		margin = -signal * boost;

	margin  = reciprocal_divide(margin, schedtune_spc_rdiv);

	if (boost < 0)
		margin *= -1;
	return margin;
}

inline long
schedtune_cpu_margin_with(unsigned long util, int cpu, struct task_struct *p)
{
	int boost = schedtune_cpu_boost_with(cpu, p);
	long margin;

	if (boost == 0)
		margin = 0;
	else
		margin = schedtune_margin(util, boost);

	trace_sched_boost_cpu(cpu, util, margin);

	return margin;
}

long schedtune_task_margin(struct task_struct *task)
{
	int boost = schedtune_task_boost(task);
	unsigned long util;
	long margin;

	if (boost == 0)
		return 0;

	util = task_util_est(task);
	margin = schedtune_margin(util, boost, SCHED_CAPACITY_SCALE);

	return margin;
}

#else /* CONFIG_SCHED_TUNE */

inline long
schedtune_cpu_margin_with(unsigned long util, int cpu, struct task_struct *p)
{
	return 0;
}

#endif /* CONFIG_SCHED_TUNE */

static unsigned long cpu_util_without(int cpu, struct task_struct *p);

static unsigned long capacity_spare_without(int cpu, struct task_struct *p)
{
	return max_t(long, capacity_of(cpu) - cpu_util_without(cpu, p), 0);
}

/*
 * find_idlest_group finds and returns the least busy CPU group within the
 * domain.
 *
 * Assumes p is allowed on at least one CPU in sd.
 */
static struct sched_group *
find_idlest_group(struct sched_domain *sd, struct task_struct *p,
		  int this_cpu, int sd_flag)
{
	struct sched_group *idlest = NULL, *group = sd->groups;
	struct sched_group *most_spare_sg = NULL;
	unsigned long min_runnable_load = ULONG_MAX;
	unsigned long this_runnable_load = ULONG_MAX;
	unsigned long min_avg_load = ULONG_MAX, this_avg_load = ULONG_MAX;
	unsigned long most_spare = 0, this_spare = 0;
	int imbalance_scale = 100 + (sd->imbalance_pct-100)/2;
	unsigned long imbalance = scale_load_down(NICE_0_LOAD) *
				(sd->imbalance_pct-100) / 100;

	do {
		unsigned long load, avg_load, runnable_load;
		unsigned long spare_cap, max_spare_cap;
		int local_group;
		int i;

		/* Skip over this group if it has no CPUs allowed */
		if (!cpumask_intersects(sched_group_span(group), p->cpus_ptr))
			continue;

		local_group = cpumask_test_cpu(this_cpu,
					       sched_group_span(group));

		/*
		 * Tally up the load of all CPUs in the group and find
		 * the group containing the CPU with most spare capacity.
		 */
		avg_load = 0;
		runnable_load = 0;
		max_spare_cap = 0;

		for_each_cpu(i, sched_group_span(group)) {
			load = weighted_cpuload(cpu_rq(i));
			runnable_load += load;

			avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs);

			spare_cap = capacity_spare_without(i, p);

			if (spare_cap > max_spare_cap)
				max_spare_cap = spare_cap;
		}

		/* Adjust by relative CPU capacity of the group */
		avg_load = (avg_load * SCHED_CAPACITY_SCALE) /
					group->sgc->capacity;
		runnable_load = (runnable_load * SCHED_CAPACITY_SCALE) /
					group->sgc->capacity;

		if (local_group) {
			this_runnable_load = runnable_load;
			this_avg_load = avg_load;
			this_spare = max_spare_cap;
		} else {
			if (min_runnable_load > (runnable_load + imbalance)) {
				/*
				 * The runnable load is significantly smaller
				 * so we can pick this new cpu
				 */
				min_runnable_load = runnable_load;
				min_avg_load = avg_load;
				idlest = group;
			} else if ((runnable_load < (min_runnable_load + imbalance)) &&
				   (100*min_avg_load > imbalance_scale*avg_load)) {
				/*
				 * The runnable loads are close so take the
				 * blocked load into account through avg_load.
				 */
				min_avg_load = avg_load;
				idlest = group;
			}

			if (most_spare < max_spare_cap) {
				most_spare = max_spare_cap;
				most_spare_sg = group;
			}
		}
	} while (group = group->next, group != sd->groups);

	/*
	 * The cross-over point between using spare capacity or least load
	 * is too conservative for high utilization tasks on partially
	 * utilized systems if we require spare_capacity > task_util(p),
	 * so we allow for some task stuffing by using
	 * spare_capacity > task_util(p)/2.
	 *
	 * Spare capacity can't be used for fork because the utilization has
	 * not been set yet, we must first select a rq to compute the initial
	 * utilization.
	 */
	if (sd_flag & SD_BALANCE_FORK)
		goto skip_spare;

	if (this_spare > task_util(p) / 2 &&
	    imbalance_scale*this_spare > 100*most_spare)
		return NULL;

	if (most_spare > task_util(p) / 2)
		return most_spare_sg;

skip_spare:
	if (!idlest)
		return NULL;

	if (min_runnable_load > (this_runnable_load + imbalance))
		return NULL;

	if ((this_runnable_load < (min_runnable_load + imbalance)) &&
	     (100*this_avg_load < imbalance_scale*min_avg_load))
		return NULL;

	return idlest;
}

/*
 * find_idlest_group_cpu - find the idlest cpu among the cpus in group.
 */
static int
find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
{
	unsigned long load, min_load = ULONG_MAX;
	unsigned int min_exit_latency = UINT_MAX;
	u64 latest_idle_timestamp = 0;
	int least_loaded_cpu = this_cpu;
	int shallowest_idle_cpu = -1, si_cpu = -1;
	int i;

	/* Check if we have any choice: */
	if (group->group_weight == 1)
		return cpumask_first(sched_group_span(group));

	/* Traverse only the allowed CPUs */
	for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) {
		if (available_idle_cpu(i)) {
			struct rq *rq = cpu_rq(i);
			struct cpuidle_state *idle = idle_get_state(rq);
			if (idle && idle->exit_latency < min_exit_latency) {
				/*
				 * We give priority to a CPU whose idle state
				 * has the smallest exit latency irrespective
				 * of any idle timestamp.
				 */
				min_exit_latency = idle->exit_latency;
				latest_idle_timestamp = rq->idle_stamp;
				shallowest_idle_cpu = i;
			} else if ((!idle || idle->exit_latency == min_exit_latency) &&
				   rq->idle_stamp > latest_idle_timestamp) {
				/*
				 * If equal or no active idle state, then
				 * the most recently idled CPU might have
				 * a warmer cache.
				 */
				latest_idle_timestamp = rq->idle_stamp;
				shallowest_idle_cpu = i;
			}
		} else if (shallowest_idle_cpu == -1 && si_cpu == -1) {
			if (sched_idle_cpu(i)) {
				si_cpu = i;
				continue;
			}

			load = weighted_cpuload(cpu_rq(i));
			if (load < min_load) {
				min_load = load;
				least_loaded_cpu = i;
			}
		}
	}

	if (shallowest_idle_cpu != -1)
		return shallowest_idle_cpu;
	if (si_cpu != -1)
		return si_cpu;
	return least_loaded_cpu;
}

static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p,
				  int cpu, int prev_cpu, int sd_flag)
{
	int new_cpu = cpu;

	if (!cpumask_intersects(sched_domain_span(sd), p->cpus_ptr))
		return prev_cpu;

	/*
	 * We need task's util for capacity_spare_wake, sync it up to prev_cpu's
	 * last_update_time.
	 */
	if (sd && !(sd_flag & SD_BALANCE_FORK))
		sync_entity_load_avg(&p->se);

	while (sd) {
		struct sched_group *group;
		struct sched_domain *tmp;
		int weight;

		if (!(sd->flags & sd_flag)) {
			sd = sd->child;
			continue;
		}

		group = find_idlest_group(sd, p, cpu, sd_flag);
		if (!group) {
			sd = sd->child;
			continue;
		}

		new_cpu = find_idlest_group_cpu(group, p, cpu);
		if (new_cpu == cpu) {
			/* Now try balancing at a lower domain level of cpu */
			sd = sd->child;
			continue;
		}

		/* Now try balancing at a lower domain level of new_cpu */
		cpu = new_cpu;
		weight = sd->span_weight;
		sd = NULL;
		for_each_domain(cpu, tmp) {
			if (weight <= tmp->span_weight)
				break;
			if (tmp->flags & sd_flag)
				sd = tmp;
		}
		/* while loop will break here if sd == NULL */
	}

	return new_cpu;
}

#ifdef CONFIG_SCHED_SMT
DEFINE_STATIC_KEY_FALSE(sched_smt_present);
EXPORT_SYMBOL_GPL(sched_smt_present);

static inline void set_idle_cores(int cpu, int val)
{
	struct sched_domain_shared *sds;

	sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
	if (sds)
		WRITE_ONCE(sds->has_idle_cores, val);
}

static inline bool test_idle_cores(int cpu, bool def)
{
	struct sched_domain_shared *sds;

	sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
	if (sds)
		return READ_ONCE(sds->has_idle_cores);

	return def;
}

/*
 * Scans the local SMT mask to see if the entire core is idle, and records this
 * information in sd_llc_shared->has_idle_cores.
 *
 * Since SMT siblings share all cache levels, inspecting this limited remote
 * state should be fairly cheap.
 */
void __update_idle_core(struct rq *rq)
{
	int core = cpu_of(rq);
	int cpu;

	rcu_read_lock();
	if (test_idle_cores(core, true))
		goto unlock;

	for_each_cpu(cpu, cpu_smt_mask(core)) {
		if (cpu == core)
			continue;

		if (!available_idle_cpu(cpu))
			goto unlock;
	}

	set_idle_cores(core, 1);
unlock:
	rcu_read_unlock();
}

/*
 * Scan the entire LLC domain for idle cores; this dynamically switches off if
 * there are no idle cores left in the system; tracked through
 * sd_llc->shared->has_idle_cores and enabled through update_idle_core() above.
 */
static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target)
{
	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
	int core, cpu;

	if (!static_branch_likely(&sched_smt_present))
		return -1;

	if (!test_idle_cores(target, false))
		return -1;

	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);

	for_each_cpu_wrap(core, cpus, target) {
		bool idle = true;

		for_each_cpu(cpu, cpu_smt_mask(core)) {
			cpumask_clear_cpu(cpu, cpus);
			if (!available_idle_cpu(cpu))
				idle = false;
		}

		if (idle)
			return core;
	}

	/*
	 * Failed to find an idle core; stop looking for one.
	 */
	set_idle_cores(target, 0);

	return -1;
}

/*
 * Scan the local SMT mask for idle CPUs.
 */
static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
{
	int cpu, si_cpu = -1;

	if (!static_branch_likely(&sched_smt_present))
		return -1;

	for_each_cpu(cpu, cpu_smt_mask(target)) {
		if (!cpumask_test_cpu(cpu, p->cpus_ptr))
			continue;
		if (available_idle_cpu(cpu))
			return cpu;
		if (si_cpu == -1 && sched_idle_cpu(cpu))
			si_cpu = cpu;
	}

	return si_cpu;
}

#else /* CONFIG_SCHED_SMT */

static inline int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target)
{
	return -1;
}

static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
{
	return -1;
}

#endif /* CONFIG_SCHED_SMT */

/*
 * Scan the LLC domain for idle CPUs; this is dynamically regulated by
 * comparing the average scan cost (tracked in sd->avg_scan_cost) against the
 * average idle time for this rq (as found in rq->avg_idle).
 */
static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
{
	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
	struct sched_domain *this_sd;
	u64 avg_cost, avg_idle;
	u64 time, cost;
	s64 delta;
	int cpu, nr = INT_MAX, si_cpu = -1;

	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
	if (!this_sd)
		return -1;

	/*
	 * Due to large variance we need a large fuzz factor; hackbench in
	 * particularly is sensitive here.
	 */
	avg_idle = this_rq()->avg_idle / 512;
	avg_cost = this_sd->avg_scan_cost + 1;

	if (sched_feat(SIS_AVG_CPU) && avg_idle < avg_cost)
		return -1;

	if (sched_feat(SIS_PROP)) {
		u64 span_avg = sd->span_weight * avg_idle;
		if (span_avg > 4*avg_cost)
			nr = div_u64(span_avg, avg_cost);
		else
			nr = 4;
	}

	time = local_clock();

	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);

	for_each_cpu_wrap(cpu, cpus, target) {
		if (!--nr)
			return si_cpu;
		if (cpu_isolated(cpu))
			continue;
		if (available_idle_cpu(cpu))
			break;
		if (si_cpu == -1 && sched_idle_cpu(cpu))
			si_cpu = cpu;
	}

	time = local_clock() - time;
	cost = this_sd->avg_scan_cost;
	delta = (s64)(time - cost) / 8;
	this_sd->avg_scan_cost += delta;

	return cpu;
}

/*
 * Try and locate an idle core/thread in the LLC cache domain.
 */
static inline int __select_idle_sibling(struct task_struct *p, int prev, int target)
{
	struct sched_domain *sd;
	int i, recent_used_cpu;

	if ((available_idle_cpu(target) && !cpu_isolated(target)) || sched_idle_cpu(target))
		return target;

	/*
	 * If the previous cpu is cache affine and idle, don't be stupid.
	 */
	if ((prev != target && cpus_share_cache(prev, target) && available_idle_cpu(prev) && !cpu_isolated(prev)) || sched_idle_cpu(prev))
		return prev;

	/* Check a recently used CPU as a potential idle candidate */
	recent_used_cpu = p->recent_used_cpu;
	if (recent_used_cpu != prev &&
	    recent_used_cpu != target &&
	    cpus_share_cache(recent_used_cpu, target) &&
	    available_idle_cpu(recent_used_cpu) &&
	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) {
		/*
		 * Replace recent_used_cpu with prev as it is a potential
		 * candidate for the next wake.
		 */
		p->recent_used_cpu = prev;
		return recent_used_cpu;
	}

	sd = rcu_dereference(per_cpu(sd_llc, target));
	if (!sd)
		return target;

	i = select_idle_core(p, sd, target);
	if ((unsigned)i < nr_cpumask_bits)
		return i;

	i = select_idle_cpu(p, sd, target);
	if ((unsigned)i < nr_cpumask_bits)
		return i;

	i = select_idle_smt(p, sd, target);
	if ((unsigned)i < nr_cpumask_bits)
		return i;

	return target;
}

static inline int select_idle_sibling_cstate_aware(struct task_struct *p, int prev, int target)
{
	struct sched_domain *sd;
	struct sched_group *sg;
	int best_idle_cpu = -1;
	int best_idle_cstate = -1;
	int best_idle_capacity = INT_MAX;
	int i;

	/*
	 * 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_span(sg), p->cpus_ptr))
				goto next;

			for_each_cpu_and(i, p->cpus_ptr, sched_group_span(sg)) {
				int idle_idx;
				unsigned long new_usage;
				unsigned long capacity_orig;

				if (!idle_cpu(i))
					goto next;

				if (cpu_isolated(i))
					continue;

				/* figure out if the task can fit here at all */
				new_usage = uclamp_task(p);
				capacity_orig = capacity_orig_of(i);

				if (new_usage > capacity_orig)
					goto next;

				/* if the task fits without changing OPP and we
				 * intended to use this CPU, just proceed
				 */
				if (i == target && new_usage <= capacity_curr_of(target)) {
					return target;
				}

				/* otherwise select CPU with shallowest idle state
				 * to reduce wakeup latency.
				 */
				idle_idx = idle_get_state_idx(cpu_rq(i));

				if (idle_idx < best_idle_cstate &&
					capacity_orig <= best_idle_capacity) {
					best_idle_cpu = i;
					best_idle_cstate = idle_idx;
					best_idle_capacity = capacity_orig;
				}
			}
	next:
			sg = sg->next;
		} while (sg != sd->groups);
	}

	if (best_idle_cpu >= 0)
		target = best_idle_cpu;

	return target;
}

static int select_idle_sibling(struct task_struct *p, int prev, int target)
{
	if (!sysctl_sched_cstate_aware)
		return __select_idle_sibling(p, prev, target);

	return select_idle_sibling_cstate_aware(p, prev, target);
}

static inline bool task_fits_capacity(struct task_struct *p,
					long capacity)
{
	return fits_capacity(task_util_est(p), capacity);
}

static inline bool task_fits_max(struct task_struct *p, int cpu)
{
	unsigned long capacity = capacity_orig_of(cpu);
	unsigned long max_capacity = cpu_rq(cpu)->rd->max_cpu_capacity.val;

	if (capacity == max_capacity)
		return true;

	if ((task_boost_policy(p) == SCHED_BOOST_ON_BIG ||
			uclamp_boosted(p) > 0) &&
			is_min_capacity_cpu(cpu))
		return false;

	return task_fits_capacity(p, capacity);
}

struct find_best_target_env {
	struct cpumask *rtg_target;
	int placement_boost;
	bool need_idle;
	int fastpath;
};

static bool is_packing_eligible(struct task_struct *p, int target_cpu,
				struct find_best_target_env *fbt_env,
				unsigned int target_cpus_count,
				int best_idle_cstate, bool boosted)
{
	unsigned long tutil, estimated_capacity;

	if (task_placement_boost_enabled(p) || fbt_env->need_idle || boosted)
		return false;

	if (best_idle_cstate == -1)
		return false;

	if (target_cpus_count != 1)
		return true;

	if (task_in_cum_window_demand(cpu_rq(target_cpu), p))
		tutil = 0;
	else
		tutil = task_util(p);

	estimated_capacity = cpu_util_cum(target_cpu, tutil);
	estimated_capacity = add_capacity_margin(estimated_capacity,
						target_cpu);

	/*
	 * If there is only one active CPU and it is already above its current
	 * capacity, avoid placing additional task on the CPU.
	 */
	return (estimated_capacity <= capacity_curr_of(target_cpu));
}

static int start_cpu(struct task_struct *p, bool boosted,
		     bool sync_boost, struct cpumask *rtg_target)
{
	struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
	int start_cpu = -1;

	if (boosted) {
		if (rd->mid_cap_orig_cpu != -1 &&
		    task_fits_max(p, rd->mid_cap_orig_cpu))
			return rd->mid_cap_orig_cpu;
		return rd->max_cap_orig_cpu;
	}

	if (sync_boost && rd->mid_cap_orig_cpu != -1)
		return rd->mid_cap_orig_cpu;

	/* A task always fits on its rtg_target */
	if (rtg_target) {
		int rtg_target_cpu = cpumask_first_and(rtg_target,
						cpu_online_mask);

		if (rtg_target_cpu < nr_cpu_ids)
			return rtg_target_cpu;
	}

	/* Where the task should land based on its demand */
	if (rd->min_cap_orig_cpu != -1
			&& task_fits_max(p, rd->min_cap_orig_cpu))
		start_cpu = rd->min_cap_orig_cpu;
	else if (rd->mid_cap_orig_cpu != -1
				&& task_fits_max(p, rd->mid_cap_orig_cpu))
		start_cpu = rd->mid_cap_orig_cpu;
	else
		start_cpu = rd->max_cap_orig_cpu;

	return start_cpu;
}

enum fastpaths {
	NONE = 0,
	SYNC_WAKEUP,
	PREV_CPU_FASTPATH,
};

static inline int find_best_target(struct task_struct *p, int *backup_cpu,
				   bool boosted, bool sync_boost,
				   bool prefer_idle,
				   struct find_best_target_env *fbt_env)
{
	unsigned long min_util = uclamp_task(p);
	unsigned long target_capacity = ULONG_MAX;
	unsigned long min_wake_util = ULONG_MAX;
	unsigned long target_max_spare_cap = 0;
	unsigned long target_util = ULONG_MAX;
	unsigned long best_active_util = ULONG_MAX;
	unsigned long best_active_cuml_util = ULONG_MAX;
	unsigned long best_idle_cuml_util = ULONG_MAX;
	unsigned long best_idle_util = ULONG_MAX;
	int best_idle_cstate = INT_MAX;
	struct sched_domain *sd;
	struct sched_group *sg;
	int best_active_cpu = -1;
	int best_idle_cpu = -1;
	int target_cpu = -1;
	int cpu, i;
	long spare_wake_cap, most_spare_wake_cap = 0;
	int most_spare_cap_cpu = -1;
	unsigned int active_cpus_count = 0;
	int prev_cpu = task_cpu(p);
	bool next_group_higher_cap = false;
	int isolated_candidate = -1;
	int mid_cap_orig_cpu = cpu_rq(smp_processor_id())->rd->mid_cap_orig_cpu;
	struct task_struct *curr_tsk;

	*backup_cpu = -1;

	/*
	 * In most cases, target_capacity tracks capacity_orig of the most
	 * energy efficient CPU candidate, thus requiring to minimise
	 * target_capacity. For these cases target_capacity is already
	 * initialized to ULONG_MAX.
	 * However, for prefer_idle and boosted tasks we look for a high
	 * performance CPU, thus requiring to maximise target_capacity. In this
	 * case we initialise target_capacity to 0.
	 */
	if (prefer_idle && boosted)
		target_capacity = 0;

	/* Find start CPU based on boost value */
	cpu = start_cpu(p, boosted, sync_boost, fbt_env->rtg_target);
	if (cpu < 0)
		return -1;

	/* Find SD for the start CPU */
	sd = rcu_dereference(per_cpu(sd_ea, cpu));
	if (!sd)
		return -1;

	/* fast path for prev_cpu */
	if ((capacity_orig_of(prev_cpu) == capacity_orig_of(cpu)) &&
		!cpu_isolated(prev_cpu) && cpu_online(prev_cpu) &&
		idle_cpu(prev_cpu)) {

		if (idle_get_state_idx(cpu_rq(prev_cpu)) <= 1) {
			/*
			 * Since target_cpu and backup_cpu are both -1s the
			 * caller will choose prev_cpu and importantly skip
			 * energy evaluation
			 */
			target_cpu = -1;

			fbt_env->fastpath = PREV_CPU_FASTPATH;
			trace_sched_find_best_target(p, prefer_idle, min_util,
					cpu, -1, -1, -1, target_cpu, -1);
			goto out;
		}
	}

	/* Scan CPUs in all SDs */
	sg = sd->groups;
	do {
		for_each_cpu_and(i, p->cpus_ptr, sched_group_span(sg)) {
			unsigned long capacity_curr = capacity_curr_of(i);
			unsigned long capacity_orig = capacity_orig_of(i);
			unsigned long wake_util, new_util, new_util_cuml;
			long spare_cap;
			int idle_idx = INT_MAX;

			trace_sched_cpu_util(i);

			if (!cpu_online(i) || cpu_isolated(i))
				continue;

			if (isolated_candidate == -1)
				isolated_candidate = i;
			/*
			 * This CPU is the target of an active migration that's
			 * yet to complete. Avoid placing another task on it.
			 * See check_for_migration()
			 */
			if (is_reserved(i))
				continue;

			if (sched_cpu_high_irqload(i))
				continue;

			/*
			 * p's blocked utilization is still accounted for on prev_cpu
			 * so prev_cpu will receive a negative bias due to the double
			 * accounting. However, the blocked utilization may be zero.
			 */
			wake_util = cpu_util_without(i, p);
			new_util = wake_util + uclamp_task_util(p);
			spare_wake_cap = capacity_orig_of(i) - wake_util;

			if (spare_wake_cap > most_spare_wake_cap) {
				most_spare_wake_cap = spare_wake_cap;
				most_spare_cap_cpu = i;
			}

			/*
			 * Cumulative demand may already be accounting for the
			 * task. If so, add just the boost-utilization to
			 * the cumulative demand of the cpu.
			 */
			if (task_in_cum_window_demand(cpu_rq(i), p))
				new_util_cuml = cpu_util_cum(i, 0) +
					       min_util - task_util(p);
			else
				new_util_cuml = cpu_util_cum(i, 0) + min_util;

			/*
			 * Ensure minimum capacity to grant the required boost.
			 * The target CPU can be already at a capacity level higher
			 * than the one required to boost the task.
			 * However, if the task prefers idle cpu and that
			 * cpu is idle, skip this check.
			 */
			new_util = max(min_util, new_util);
			if (!(prefer_idle && idle_cpu(i))
				&& new_util > capacity_orig)
				continue;

			/*
			 * Pre-compute the maximum possible capacity we expect
			 * to have available on this CPU once the task is
			 * enqueued here.
			 */
			spare_cap = capacity_orig - new_util;

			if (idle_cpu(i))
				idle_idx = idle_get_state_idx(cpu_rq(i));


			/*
			 * Case A) Latency sensitive tasks
			 *
			 * Unconditionally favoring tasks that prefer idle CPU to
			 * improve latency.
			 *
			 * Looking for:
			 * - an idle CPU, whatever its idle_state is, since
			 *   the first CPUs we explore are more likely to be
			 *   reserved for latency sensitive tasks.
			 * - a non idle CPU where the task fits in its current
			 *   capacity and has the maximum spare capacity.
			 * - a non idle CPU with lower contention from other
			 *   tasks and running at the lowest possible OPP.
			 *
			 * The last two goals tries to favor a non idle CPU
			 * where the task can run as if it is "almost alone".
			 * A maximum spare capacity CPU is favoured since
			 * the task already fits into that CPU's capacity
			 * without waiting for an OPP chance.
			 *
			 * The following code path is the only one in the CPUs
			 * exploration loop which is always used by
			 * prefer_idle tasks. It exits the loop with wither a
			 * best_active_cpu or a target_cpu which should
			 * represent an optimal choice for latency sensitive
			 * tasks.
			 */
			if (prefer_idle) {

				/*
				 * Case A.1: IDLE CPU
				 * Return the best IDLE CPU we find:
				 * - for boosted tasks: if the task fits in mid
				 * cluster, prefer the first mid cluster cpu
				 * due to cpuset design, then other mid cluster
				 * cpus. Otherwise, choose max cluster cpu.
				 * - for !boosted tasks: the most energy
				 * efficient CPU (i.e. smallest capacity_orig)
				 */
				if (boosted && mid_cap_orig_cpu != -1 &&
					best_idle_cpu == mid_cap_orig_cpu)
					break;
				if (idle_cpu(i)) {
					if (boosted &&
					    capacity_orig < target_capacity)
						continue;
					if (!boosted &&
					    capacity_orig > target_capacity)
						continue;
					if (capacity_orig == target_capacity &&
					    sysctl_sched_cstate_aware) {
						if (best_idle_cstate < idle_idx)
							continue;
						/*
						 * If idle state of cpu is the
						 * same, select least utilized.
						 */
						else if (best_idle_cstate ==
						    idle_idx &&
						    best_idle_util <= new_util)
							continue;
					}

					target_capacity = capacity_orig;
					best_idle_cstate = idle_idx;
					best_idle_util = new_util;
					best_idle_cpu = i;
					continue;
				}
				if (best_idle_cpu != -1)
					continue;

				/* Skip CPUs which do not fit task requirements */
				if (capacity_orig < uclamp_task_util(p))
					continue;

				/*
				 * Case A.2: Target ACTIVE CPU
				 * Favor CPUs with max spare capacity.
				 */
				if (capacity_curr > new_util &&
				    spare_cap > target_max_spare_cap) {
					target_max_spare_cap = spare_cap;
					target_cpu = i;
					continue;
				}
				if (target_cpu != -1)
					continue;


				/*
				 * Case A.3: Backup ACTIVE CPU
				 * Favor CPUs with:
				 * - lower utilization due to other tasks
				 * - lower utilization with the task in
				 */
				if (wake_util > min_wake_util)
					continue;
				if (new_util > best_active_util)
					continue;

				/*
				 * If utilization is the same between CPUs,
				 * break the ties with cumulative demand,
				 * also prefer lower order cpu.
				 */
				if (new_util == best_active_util &&
					new_util_cuml >= best_active_cuml_util)
					continue;
				min_wake_util = wake_util;
				best_active_util = new_util;
				best_active_cuml_util = new_util_cuml;
				best_active_cpu = i;
				continue;
			}

			/*
			 * Skip processing placement further if we are visiting
			 * cpus with lower capacity than start cpu
			 */
			if (capacity_orig < capacity_orig_of(cpu))
				continue;




			/*
			 * Case B) Non latency sensitive tasks on IDLE CPUs.
			 *
			 * Find an optimal backup IDLE CPU for non latency
			 * sensitive tasks.
			 *
			 * Looking for:
			 * - minimizing the capacity_orig,
			 *   i.e. preferring LITTLE CPUs
			 * - favoring shallowest idle states
			 *   i.e. avoid to wakeup deep-idle CPUs
			 *
			 * The following code path is used by non latency
			 * sensitive tasks if IDLE CPUs are available. If at
			 * least one of such CPUs are available it sets the
			 * best_idle_cpu to the most suitable idle CPU to be
			 * selected.
			 *
			 * If idle CPUs are available, favour these CPUs to
			 * improve performances by spreading tasks.
			 * Indeed, the energy_diff() computed by the caller
			 * will take care to ensure the minimization of energy
			 * consumptions without affecting performance.
			 */
			if (idle_cpu(i)) {
				/*
				 * Skip CPUs in deeper idle state, but only
				 * if they are also less energy efficient.
				 * IOW, prefer a deep IDLE LITTLE CPU vs a
				 * shallow idle big CPU.
				 */
				if (capacity_orig >= target_capacity &&
				    sysctl_sched_cstate_aware &&
				    best_idle_cstate < idle_idx)
					continue;

				if (best_idle_cstate == idle_idx &&
					(best_idle_cpu == prev_cpu ||
					(i != prev_cpu &&
					new_util_cuml > best_idle_cuml_util)))
					continue;

				target_capacity = capacity_orig;
				best_idle_cstate = idle_idx;
				best_idle_cuml_util = new_util_cuml;
				best_idle_cpu = i;
				continue;
			}

#ifdef CONFIG_SCHED_WALT
			/*
			 * Consider only idle CPUs for active migration.
			 */
			if (p->state == TASK_RUNNING)
				continue;
#endif

			/*
			 * Case C) Non latency sensitive tasks on ACTIVE CPUs.
			 *
			 * Pack tasks in the most energy efficient capacities.
			 *
			 * This task packing strategy prefers more energy
			 * efficient CPUs (i.e. pack on smaller maximum
			 * capacity CPUs) while also trying to spread tasks to
			 * run them all at the lower OPP.
			 *
			 * This assumes for example that it's more energy
			 * efficient to run two tasks on two CPUs at a lower
			 * OPP than packing both on a single CPU but running
			 * that CPU at an higher OPP.
			 *
			 * Thus, this case keep track of the CPU with the
			 * smallest maximum capacity and highest spare maximum
			 * capacity.
			 */

			active_cpus_count++;

			/* Favor CPUs with maximum spare capacity */
			if (spare_cap < target_max_spare_cap)
				continue;

			target_max_spare_cap = spare_cap;
			target_capacity = capacity_orig;
			target_util = new_util;
			target_cpu = i;
		}

		next_group_higher_cap = (capacity_orig_of(group_first_cpu(sg)) <
			capacity_orig_of(group_first_cpu(sg->next)));

		/*
		 * If we've found a cpu, but the boost is ON_ALL we continue
		 * visiting other clusters. If the boost is ON_BIG we visit
		 * next cluster if they are higher in capacity. If we are
		 * not in any kind of boost, we break.
		 */
		if (!prefer_idle && !boosted &&
			(target_cpu != -1 || best_idle_cpu != -1) &&
			(fbt_env->placement_boost == SCHED_BOOST_NONE ||
			sched_boost() != FULL_THROTTLE_BOOST ||
			(fbt_env->placement_boost == SCHED_BOOST_ON_BIG &&
				!next_group_higher_cap)))
			break;

		/*
		 * if we are in prefer_idle and have found an idle cpu,
		 * break from searching more groups based on the stune.boost and
		 * group cpu capacity. For !prefer_idle && boosted case, don't
		 * iterate lower capacity CPUs unless the task can't be
		 * accommodated in the higher capacity CPUs.
		 */
		if ((prefer_idle && best_idle_cpu != -1) ||
		    (boosted && (best_idle_cpu != -1 || target_cpu != -1))) {
			if (boosted) {
				/*
				 * For boosted task, stop searching when an idle
				 * cpu is found in mid cluster.
				 */
				if ((mid_cap_orig_cpu != -1 &&
					best_idle_cpu >= mid_cap_orig_cpu) ||
					!next_group_higher_cap)
					break;
			} else {
				if (next_group_higher_cap)
					break;
			}
		}

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

	if (prefer_idle && (best_idle_cpu != -1)) {
		trace_sched_find_best_target(p, prefer_idle, min_util, cpu,
					     best_idle_cpu, best_active_cpu,
					     -1, best_idle_cpu, -1);

		return best_idle_cpu;
	}

	if (best_idle_cpu != -1 && !is_packing_eligible(p, target_cpu, fbt_env,
					active_cpus_count, best_idle_cstate,
					boosted)) {
		target_cpu = best_idle_cpu;
		best_idle_cpu = -1;
	}

	/*
	 * For non latency sensitive tasks, cases B and C in the previous loop,
	 * we pick the best IDLE CPU only if we was not able to find a target
	 * ACTIVE CPU.
	 *
	 * Policies priorities:
	 *
	 * - prefer_idle tasks:
	 *
	 *   a) IDLE CPU available: best_idle_cpu
	 *   b) ACTIVE CPU where task fits and has the bigger maximum spare
	 *      capacity (i.e. target_cpu)
	 *   c) ACTIVE CPU with less contention due to other tasks
	 *      (i.e. best_active_cpu)
	 *
	 * - NON prefer_idle tasks:
	 *
	 *   a) ACTIVE CPU: target_cpu
	 *   b) IDLE CPU: best_idle_cpu
	 */
	if (target_cpu != -1 && !idle_cpu(target_cpu) &&
			best_idle_cpu != -1) {
		curr_tsk = READ_ONCE(cpu_rq(target_cpu)->curr);
		if (curr_tsk && uclamp_boosted(curr_tsk)) {
			target_cpu = best_idle_cpu;
		}
	}

	if (target_cpu == -1)
		target_cpu = prefer_idle
			? best_active_cpu
			: best_idle_cpu;
	else
		*backup_cpu = prefer_idle
		? best_active_cpu
		: best_idle_cpu;

#ifdef CONFIG_SCHED_WALT
	if (target_cpu == -1 && most_spare_cap_cpu != -1 &&
		/* ensure we use active cpu for active migration */
		!(p->state == TASK_RUNNING && !idle_cpu(most_spare_cap_cpu)))
		target_cpu = most_spare_cap_cpu;
#endif

	trace_sched_find_best_target(p, prefer_idle, min_util, cpu,
				     best_idle_cpu, best_active_cpu,
				     most_spare_cap_cpu,
				     target_cpu,
				     *backup_cpu);

	/* it is possible for target and backup
	 * to select same CPU - if so, drop backup
	 */
	if (*backup_cpu == target_cpu)
		*backup_cpu = -1;

	/*
	 * The next step of energy evaluation includes
	 * prev_cpu. Drop target or backup if it is
	 * same as prev_cpu
	 */
	if (*backup_cpu == prev_cpu)
		*backup_cpu = -1;

	if (target_cpu == prev_cpu) {
		target_cpu = *backup_cpu;
		*backup_cpu = -1;
	}

	if (target_cpu == -1 && isolated_candidate != -1 &&
	    cpu_isolated(prev_cpu))
		target_cpu = isolated_candidate;

out:
	return target_cpu;
}

/*
 * Disable WAKE_AFFINE in the case where task @p doesn't fit in the
 * capacity of either the waking CPU @cpu or the previous CPU @prev_cpu.
 *
 * In that case WAKE_AFFINE doesn't make sense and we'll let
 * BALANCE_WAKE sort things out.
 */
static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
{
	long min_cap, max_cap;

	if (!static_branch_unlikely(&sched_asym_cpucapacity))
		return 0;

	min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu));
	max_cap = cpu_rq(cpu)->rd->max_cpu_capacity.val;

	/* Minimum capacity is close to max, no need to abort wake_affine */
	if (max_cap - min_cap < max_cap >> 3)
		return 0;

	/* Bring task utilization in sync with prev_cpu */
	sync_entity_load_avg(&p->se);

	return !task_fits_max(p, cpu);
}

bool __cpu_overutilized(int cpu, int delta)
{
	return (capacity_orig_of(cpu) * 1024) <
		((cpu_util(cpu) + delta) * sched_capacity_margin_up[cpu]);
}

bool cpu_overutilized(int cpu)
{
	return __cpu_overutilized(cpu, 0);
}

DEFINE_PER_CPU(struct energy_env, eenv_cache);

/* kernels often have NR_CPUS defined to be much
 * larger than exist in practise on booted systems.
 * Allocate the cpu array for eenv calculations
 * at boot time to avoid massive overprovisioning.
 */
#ifdef DEBUG_EENV_DECISIONS
static inline int eenv_debug_size_per_dbg_entry(void)
{
	return sizeof(struct _eenv_debug) + (sizeof(unsigned long) * num_possible_cpus());
}

static inline int eenv_debug_size_per_cpu_entry(void)
{
	/* each cpu struct has an array of _eenv_debug structs
	 * which have an array of unsigned longs at the end -
	 * the allocation should be extended so that there are
	 * at least 'num_possible_cpus' entries in the array.
	 */
	return EAS_EENV_DEBUG_LEVELS * eenv_debug_size_per_dbg_entry();
}
/* given a per-_eenv_cpu debug env ptr, get the ptr for a given index */
static inline struct _eenv_debug *eenv_debug_entry_ptr(struct _eenv_debug *base, int idx)
{
	char *ptr = (char *)base;
	ptr += (idx * eenv_debug_size_per_dbg_entry());
	return (struct _eenv_debug *)ptr;
}
/* given a pointer to the per-cpu global copy of _eenv_debug, get
 * a pointer to the specified _eenv_cpu debug env.
 */
static inline struct _eenv_debug *eenv_debug_percpu_debug_env_ptr(struct _eenv_debug *base, int cpu_idx)
{
	char *ptr = (char *)base;
	ptr += (cpu_idx * eenv_debug_size_per_cpu_entry());
	return (struct _eenv_debug *)ptr;
}

static inline int eenv_debug_size(void)
{
	return num_possible_cpus() * eenv_debug_size_per_cpu_entry();
}
#endif

static inline void alloc_eenv(void)
{
	int cpu;
	int cpu_count = num_possible_cpus();

	for_each_possible_cpu(cpu) {
		struct energy_env *eenv = &per_cpu(eenv_cache, cpu);
		eenv->cpu = kmalloc_array(cpu_count, sizeof(struct eenv_cpu),
					  GFP_KERNEL);
		eenv->eenv_cpu_count = cpu_count;
#ifdef DEBUG_EENV_DECISIONS
		eenv->debug = (struct _eenv_debug *)kmalloc(eenv_debug_size(), GFP_KERNEL);
#endif
	}
}

static inline void reset_eenv(struct energy_env *eenv)
{
	int cpu_count;
	struct eenv_cpu *cpu;
#ifdef DEBUG_EENV_DECISIONS
	struct _eenv_debug *debug;
	int cpu_idx;
	debug = eenv->debug;
#endif

	cpu_count = eenv->eenv_cpu_count;
	cpu = eenv->cpu;
	memset(eenv, 0, sizeof(struct energy_env));
	eenv->cpu = cpu;
	memset(eenv->cpu, 0, sizeof(struct eenv_cpu)*cpu_count);
	eenv->eenv_cpu_count = cpu_count;

#ifdef DEBUG_EENV_DECISIONS
	memset(debug, 0, eenv_debug_size());
	eenv->debug = debug;
	for(cpu_idx = 0; cpu_idx < eenv->eenv_cpu_count; cpu_idx++)
		eenv->cpu[cpu_idx].debug = eenv_debug_percpu_debug_env_ptr(debug, cpu_idx);
#endif
}
/*
 * get_eenv - reset the eenv struct cached for this CPU
 *
 * When the eenv is returned, it is configured to do
 * energy calculations for the maximum number of CPUs
 * the task can be placed on. The prev_cpu entry is
 * filled in here. Callers are responsible for adding
 * other CPU candidates up to eenv->max_cpu_count.
 */
static inline struct energy_env *get_eenv(struct task_struct *p, int prev_cpu)
{
	struct energy_env *eenv;
	cpumask_t cpumask_possible_cpus;
	int cpu = smp_processor_id();
	int i;

	eenv = &(per_cpu(eenv_cache, cpu));
	reset_eenv(eenv);

	/* populate eenv */
	eenv->p = p;
	/* use boosted task util for capacity selection
	 * during energy calculation, but unboosted task
	 * util for group utilization calculations
	 */
	eenv->util_delta = task_util_est(p);
	eenv->util_delta_boosted = uclamp_task(p);

	cpumask_and(&cpumask_possible_cpus, p->cpus_ptr, cpu_online_mask);
	eenv->max_cpu_count = cpumask_weight(&cpumask_possible_cpus);

	for (i=0; i < eenv->max_cpu_count; i++)
		eenv->cpu[i].cpu_id = -1;
	eenv->cpu[EAS_CPU_PRV].cpu_id = prev_cpu;
	eenv->next_idx = EAS_CPU_PRV;

	return eenv;
}

static inline int wake_to_idle(struct task_struct *p)
{
	return (current->flags & PF_WAKE_UP_IDLE) ||
		 (p->flags & PF_WAKE_UP_IDLE);
}

#ifdef CONFIG_SCHED_WALT
static inline bool is_task_util_above_min_thresh(struct task_struct *p)
{
	unsigned int threshold = (sched_boost() == CONSERVATIVE_BOOST) ?
			sysctl_sched_min_task_util_for_boost :
			sysctl_sched_min_task_util_for_colocation;

	return task_util(p) > threshold;
}

static inline struct cpumask *find_rtg_target(struct task_struct *p)
{
	struct related_thread_group *grp;
	struct cpumask *rtg_target;

	rcu_read_lock();

	grp = task_related_thread_group(p);
	if (grp && grp->preferred_cluster && is_task_util_above_min_thresh(p)) {
		rtg_target = &grp->preferred_cluster->cpus;
		if (!task_fits_max(p, cpumask_first(rtg_target)))
			rtg_target = NULL;
	} else {
		rtg_target = NULL;
	}

	rcu_read_unlock();

	return rtg_target;
}
#else
static inline struct cpumask *find_rtg_target(struct task_struct *p)
{
	return NULL;
}
#endif

/*
 * Needs to be called inside rcu_read_lock critical section.
 * sd is a pointer to the sched domain we wish to use for an
 * energy-aware placement option.
 */
static int find_energy_efficient_cpu(struct sched_domain *sd,
				     struct task_struct *p,
				     int cpu, int prev_cpu,
				     int sync, bool sync_boost)
{
	int use_fbt = sched_feat(FIND_BEST_TARGET);
	int cpu_iter, eas_cpu_idx = EAS_CPU_NXT;
	int delta = 0;
	int target_cpu = -1;
	struct energy_env *eenv;
	struct cpumask *rtg_target = find_rtg_target(p);
	struct find_best_target_env fbt_env;
	bool need_idle = wake_to_idle(p) || uclamp_latency_sensitive(p);
	int placement_boost = task_boost_policy(p);
	u64 start_t = 0;
	int next_cpu = -1, backup_cpu = -1;
	int boosted = (uclamp_boosted(p) > 0);

	fbt_env.fastpath = 0;

	if (trace_sched_task_util_enabled())
		start_t = sched_clock();

	if (need_idle)
		sync = 0;

	if (sysctl_sched_sync_hint_enable && sync &&
				bias_to_waker_cpu(p, cpu, rtg_target)) {
		target_cpu = cpu;
		fbt_env.fastpath = SYNC_WAKEUP;
		goto out;
	}

	/* prepopulate energy diff environment */
	eenv = get_eenv(p, prev_cpu);
	if (eenv->max_cpu_count < 2)
		goto out;

	if(!use_fbt) {
		/*
		 * using this function outside wakeup balance will not supply
		 * an sd ptr. Instead, fetch the highest level with energy data.
		 */
		if (!sd)
			sd = rcu_dereference(per_cpu(sd_ea, prev_cpu));

		for_each_cpu_and(cpu_iter, p->cpus_ptr, sched_domain_span(sd)) {
			unsigned long spare;

			/* prev_cpu already in list */
			if (cpu_iter == prev_cpu)
				continue;

			/*
			 * Consider only CPUs where the task is expected to
			 * fit without making the CPU overutilized.
			 */
			spare = capacity_spare_without(cpu_iter, p);
			if (spare * 1024 < sched_capacity_margin_up[cpu_iter] *
							task_util_est(p))
				continue;

			/* Add CPU candidate */
			eenv->cpu[eas_cpu_idx++].cpu_id = cpu_iter;
			eenv->max_cpu_count = eas_cpu_idx;

			/* stop adding CPUs if we have no space left */
			if (eas_cpu_idx >= eenv->eenv_cpu_count)
				break;
		}
	} else {
		int prefer_idle;

		/*
		 * give compiler a hint that if sched_features
		 * cannot be changed, it is safe to optimise out
		 * all if(prefer_idle) blocks.
		 */
		prefer_idle = sched_feat(EAS_PREFER_IDLE) ?
				(uclamp_latency_sensitive(p) > 0) : 0;

		eenv->max_cpu_count = EAS_CPU_BKP + 1;

		fbt_env.rtg_target = rtg_target;
		fbt_env.placement_boost = placement_boost;
		fbt_env.need_idle = need_idle;

		/* Find a cpu with sufficient capacity */
		target_cpu = find_best_target(p, &eenv->cpu[EAS_CPU_BKP].cpu_id,
					      boosted, sync_boost, prefer_idle,
					      &fbt_env);
		if (target_cpu < 0)
			goto out;

		/* Immediately return a found idle CPU for a prefer_idle task */
		if (prefer_idle && idle_cpu(target_cpu))
			goto out;

#ifdef CONFIG_SCHED_WALT
		if (!walt_disabled && sysctl_sched_use_walt_cpu_util &&
		    p->state == TASK_WAKING)
			delta = task_util(p);
#endif
		if (task_placement_boost_enabled(p) || need_idle || boosted ||
		    (rtg_target && (!cpumask_test_cpu(prev_cpu, rtg_target) ||
		    cpumask_test_cpu(target_cpu, rtg_target))) ||
		    __cpu_overutilized(prev_cpu, delta) ||
		    !task_fits_max(p, prev_cpu) || cpu_isolated(prev_cpu))
			goto out;

		/* Place target into NEXT slot */
		eenv->cpu[EAS_CPU_NXT].cpu_id = target_cpu;

		next_cpu = eenv->cpu[EAS_CPU_NXT].cpu_id;
		backup_cpu = eenv->cpu[EAS_CPU_BKP].cpu_id;

		/* take note if no backup was found */
		if (eenv->cpu[EAS_CPU_BKP].cpu_id < 0)
			eenv->max_cpu_count = EAS_CPU_BKP;
	}

	if (eenv->max_cpu_count == EAS_CPU_NXT) {
		/*
		 * we did not find any energy-awareness
		 * candidates beyond prev_cpu, so we will
		 * fall-back to the regular slow-path.
		 */
		goto out;
	}

	/* find most energy-efficient CPU */
	target_cpu = select_energy_cpu_idx(eenv) < 0 ? prev_cpu :
					eenv->cpu[eenv->next_idx].cpu_id;

out:
	if (target_cpu < 0)
		target_cpu = prev_cpu;

	trace_sched_task_util(p, next_cpu, backup_cpu, target_cpu, sync,
			need_idle, fbt_env.fastpath, placement_boost,
			rtg_target ? cpumask_first(rtg_target) : -1, start_t,
			boosted);
	return target_cpu;
}

static inline bool nohz_kick_needed(struct rq *rq, bool only_update);
static void nohz_balancer_kick(bool only_update);

/*
 * wake_energy: Make the decision if we want to use an energy-aware
 * wakeup task placement or not. This is limited to situations where
 * we cannot use energy-awareness right now.
 *
 * Returns TRUE if we should attempt energy-aware wakeup, FALSE if not.
 *
 * Should only be called from select_task_rq_fair inside the RCU
 * read-side critical section.
 */
static inline int wake_energy(struct task_struct *p, int prev_cpu,
			      int sd_flag, int wake_flags)
{
	struct sched_domain *sd = NULL;
	int sync = wake_flags & WF_SYNC;

	sd = rcu_dereference_sched(cpu_rq(prev_cpu)->sd);

	/*
	 * Check all definite no-energy-awareness conditions
	 */
	if (!sd)
		return false;

	if (!energy_aware())
		return false;

	if (sd_overutilized(sd))
		return false;

	/*
	 * we cannot do energy-aware wakeup placement sensibly
	 * for tasks with 0 utilization, so let them be placed
	 * according to the normal strategy.
	 * However if fbt is in use we may still benefit from
	 * the heuristics we use there in selecting candidate
	 * CPUs.
	 */
	if (unlikely(!sched_feat(FIND_BEST_TARGET) && !task_util_est(p)))
		return false;

	if(!sched_feat(EAS_PREFER_IDLE)){
		/*
		 * Force prefer-idle tasks into the slow path, this may not happen
		 * if none of the sd flags matched.
		 */
		if (uclamp_latency_sensitive(p) > 0 && !sync)
			return false;
	}
	return true;
}

/*
 * select_task_rq_fair: Select target runqueue for the waking task in domains
 * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
 * SD_BALANCE_FORK, or SD_BALANCE_EXEC.
 *
 * Balances load by selecting the idlest cpu in the idlest group, or under
 * certain conditions an idle sibling cpu if the domain has SD_WAKE_AFFINE set.
 *
 * Returns the target cpu number.
 *
 * 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;
	struct sched_domain *sd = NULL, *energy_sd = NULL;
	int cpu = smp_processor_id();
	int new_cpu = prev_cpu;
	int want_affine = 0;
	int want_energy = 0;
	int sync = (wake_flags & WF_SYNC) && !(current->flags & PF_EXITING);

	rcu_read_lock();

	if (sd_flag & SD_BALANCE_WAKE) {
		int _wake_cap = wake_cap(p, cpu, prev_cpu);
		int _cpus_allowed = cpumask_test_cpu(cpu, p->cpus_ptr);

		if (sysctl_sched_sync_hint_enable && sync &&
				_cpus_allowed && !_wake_cap &&
				wake_affine_idle(cpu, prev_cpu, sync) &&
				cpu_is_in_target_set(p, cpu)) {
			rcu_read_unlock();
			return cpu;
		}

		record_wakee(p);
		want_energy = wake_energy(p, prev_cpu, sd_flag, wake_flags);
		want_affine = !want_energy &&
			      !_wake_cap &&
			      _cpus_allowed;
	}

	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 we are able to try an energy-aware wakeup,
		 * select the highest non-overutilized sched domain
		 * which includes this cpu and prev_cpu
		 *
		 * maybe want to not test prev_cpu and only consider
		 * the current one?
		 */
		if (want_energy &&
		    !sd_overutilized(tmp) &&
		    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp)))
			energy_sd = tmp;

		if (tmp->flags & sd_flag)
			sd = tmp;
		else if (!(want_affine || want_energy))
			break;
	}

	if (affine_sd) {
		sd = NULL; /* Prefer wake_affine over balance flags */
		if (cpu == prev_cpu)
			goto pick_cpu;

		new_cpu = wake_affine(affine_sd, p, prev_cpu, sync);
	}

	if (!sd) {
pick_cpu:
		if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */
			new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);

			if (want_affine)
				current->recent_used_cpu = cpu;
		}
	} else {
		if (energy_sd) {
			/*
			 * If the sync flag is set but ignored, prefer to
			 * select cpu in the same or nearest cluster as current.
			 * So if current is a big or big+ cpu and sync is set,
			 * indicate that the selection algorithm from mid
			 * capacity cpu should be used.
			*/
			bool sync_boost = sync &&
				      cpu >= cpu_rq(cpu)->rd->mid_cap_orig_cpu;

			new_cpu = find_energy_efficient_cpu(energy_sd, p, cpu,
						    prev_cpu, sync, sync_boost);
		}

		/* if we did an energy-aware placement and had no choices available
		 * then fall back to the default find_idlest_cpu choice
		 */
		if (!energy_sd || (energy_sd && new_cpu == -1))
			new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag);
	}

	rcu_read_unlock();

#ifdef CONFIG_NO_HZ_COMMON
	if (nohz_kick_needed(cpu_rq(new_cpu), true))
		nohz_balancer_kick(true);
#endif

	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. The caller guarantees p->pi_lock or task_rq(p)->lock is held.
 */
static void migrate_task_rq_fair(struct task_struct *p)
{
	struct sched_entity *se = &p->se;

	if (!task_on_rq_migrating(p)) {
		remove_entity_load_avg(se);

		/*
		 * We are supposed to update the task to "current" time, then
		 * its up to date and ready to go to new CPU/cfs_rq. But we
		 * have difficulty in getting what current time is, so simply
		 * throw away the out-of-date time. This will result in the
		 * wakee task is less decayed, but giving the wakee more load
		 * sounds not bad.
		 */
		remove_entity_load_avg(&p->se);
	}

	/* Tell new CPU we are migrated */
	p->se.avg.last_update_time = 0;
}

static void task_dead_fair(struct task_struct *p)
{
	remove_entity_load_avg(&p->se);
}
#endif /* CONFIG_SMP */

static void set_next_buddy(struct sched_entity *se)
{
	if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se))))
		return;

	for_each_sched_entity(se) {
		if (SCHED_WARN_ON(!se->on_rq))
			return;
		cfs_rq_of(se)->next = se;
	}
}

/*
 * Preempt the current task with a newly woken task if needed:
 */
static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
{
	struct task_struct *curr = rq->curr;
	struct sched_entity *se = &curr->se, *pse = &p->se;
	struct cfs_rq *cfs_rq = task_cfs_rq(curr);

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

	/*
	 * This is possible from callers such as attach_tasks(), 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) && !(wake_flags & WF_FORK)) {
		set_next_buddy(pse);
	}

	/*
	 * 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(task_has_idle_policy(curr)) &&
	    likely(!task_has_idle_policy(p)))
		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);
	BUG_ON(!pse);

	cfs_rq = cfs_rq_of(se);
	update_curr(cfs_rq);

	/*
	 * XXX pick_eevdf(cfs_rq) != se ?
	 */
	if (pick_eevdf(cfs_rq) == pse)
		goto preempt;

	return;

preempt:
	resched_curr(rq);
}

static struct task_struct *
pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
	struct cfs_rq *cfs_rq = &rq->cfs;
	struct sched_entity *se;
	struct task_struct *p;
	int new_tasks;

again:
	if (!cfs_rq->nr_running)
		goto idle;

#ifdef CONFIG_FAIR_GROUP_SCHED
	if (prev->sched_class != &fair_sched_class)
		goto simple;

	/*
	 * Because of the set_next_buddy() in dequeue_task_fair() it is rather
	 * likely that a next task is from the same cgroup as the current.
	 *
	 * Therefore attempt to avoid putting and setting the entire cgroup
	 * hierarchy, only change the part that actually changes.
	 */

	do {
		struct sched_entity *curr = cfs_rq->curr;

		/*
		 * Since we got here without doing put_prev_entity() we also
		 * have to consider cfs_rq->curr. If it is still a runnable
		 * entity, update_curr() will update its vruntime, otherwise
		 * forget we've ever seen it.
		 */
		if (curr) {
			if (curr->on_rq)
				update_curr(cfs_rq);
			else
				curr = NULL;

			/*
			 * This call to check_cfs_rq_runtime() will do the
			 * throttle and dequeue its entity in the parent(s).
			 * Therefore the nr_running test will indeed
			 * be correct.
			 */
			if (unlikely(check_cfs_rq_runtime(cfs_rq))) {
				cfs_rq = &rq->cfs;

				if (!cfs_rq->nr_running)
					goto idle;

				goto simple;
			}
		}

		se = pick_next_entity(cfs_rq);
		cfs_rq = group_cfs_rq(se);
	} while (cfs_rq);

	p = task_of(se);

	/*
	 * Since we haven't yet done put_prev_entity and if the selected task
	 * is a different task than we started out with, try and touch the
	 * least amount of cfs_rqs.
	 */
	if (prev != p) {
		struct sched_entity *pse = &prev->se;

		while (!(cfs_rq = is_same_group(se, pse))) {
			int se_depth = se->depth;
			int pse_depth = pse->depth;

			if (se_depth <= pse_depth) {
				put_prev_entity(cfs_rq_of(pse), pse);
				pse = parent_entity(pse);
			}
			if (se_depth >= pse_depth) {
				set_next_entity(cfs_rq_of(se), se);
				se = parent_entity(se);
			}
		}

		put_prev_entity(cfs_rq, pse);
		set_next_entity(cfs_rq, se);
	}

	goto done;
simple:
#endif

	put_prev_task(rq, prev);

	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);

done: __maybe_unused
#ifdef CONFIG_SMP
	/*
	 * Move the next running task to the front of
	 * the list, so our cfs_tasks list becomes MRU
	 * one.
	 */
	list_move(&p->se.group_node, &rq->cfs_tasks);
#endif

	if (hrtick_enabled(rq))
		hrtick_start_fair(rq, p);

	update_misfit_status(p, rq);

	return p;

idle:
	update_misfit_status(NULL, rq);
	new_tasks = idle_balance(rq, rf);

	/*
	 * Because idle_balance() releases (and re-acquires) rq->lock, it is
	 * possible for any higher priority task to appear. In that case we
	 * must re-start the pick_next_entity() loop.
	 */
	if (new_tasks < 0)
		return RETRY_TASK;

	if (new_tasks > 0)
		goto again;

	/*
	 * rq is about to be idle, check if we need to update the
	 * lost_idle_time of clock_pelt
	 */
	update_idle_rq_clock_pelt(rq);

	return NULL;
}

/*
 * 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
 */
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);

	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_clock_skip_update(rq, true);

	se->deadline += calc_delta_fair(se->slice, 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 sched_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)
 *
 * C_i is the 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/C), W_i/C_i } - min{ avg(W/C), W_j/C_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;

enum fbq_type { regular, remote, all };

enum group_type {
	group_other = 0,
	group_misfit_task,
	group_imbalanced,
	group_overloaded,
};

#define LBF_ALL_PINNED	0x01
#define LBF_NEED_BREAK	0x02
#define LBF_DST_PINNED  0x04
#define LBF_SOME_PINNED	0x08
#define LBF_ACTIVE_LB   0x40
#define LBF_IGNORE_BIG_TASKS 0x100
#define LBF_IGNORE_PREFERRED_CLUSTER_TASKS 0x200

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;
	unsigned int		src_grp_nr_running;
	/* 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;

	enum fbq_type		fbq_type;
	enum group_type		src_grp_type;
	struct list_head	tasks;
};

/*
 * Is this task likely cache-hot:
 */
static int task_hot(struct task_struct *p, struct lb_env *env)
{
	s64 delta;

	lockdep_assert_held(&env->src_rq->lock);

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

	if (unlikely(task_has_idle_policy(p)))
		return 0;

	/* SMT siblings share cache */
	if (env->sd->flags & SD_SHARE_CPUCAPACITY)
		return 0;

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

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

	delta = rq_clock_task(env->src_rq) - p->se.exec_start;

	return delta < (s64)sysctl_sched_migration_cost;
}

#ifdef CONFIG_NUMA_BALANCING
/*
 * Returns 1, if task migration degrades locality
 * Returns 0, if task migration improves locality i.e migration preferred.
 * Returns -1, if task migration is not affected by locality.
 */
static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
{
	struct numa_group *numa_group = rcu_dereference(p->numa_group);
	unsigned long src_faults, dst_faults;
	int src_nid, dst_nid;

	if (!static_branch_likely(&sched_numa_balancing))
		return -1;

	if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
		return -1;

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

	if (src_nid == dst_nid)
		return -1;

	/* Migrating away from the preferred node is always bad. */
	if (src_nid == p->numa_preferred_nid) {
		if (env->src_rq->nr_running > env->src_rq->nr_preferred_running)
			return 1;
		else
			return -1;
	}

	/* Encourage migration to the preferred node. */
	if (dst_nid == p->numa_preferred_nid)
		return 0;

	/* Leaving a core idle is often worse than degrading locality. */
	if (env->idle != CPU_NOT_IDLE)
		return -1;

	if (numa_group) {
		src_faults = group_faults(p, src_nid);
		dst_faults = group_faults(p, dst_nid);
	} else {
		src_faults = task_faults(p, src_nid);
		dst_faults = task_faults(p, dst_nid);
	}

	return dst_faults < src_faults;
}

#else
static inline int migrate_degrades_locality(struct task_struct *p,
					     struct lb_env *env)
{
	return -1;
}
#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;

	lockdep_assert_held(&env->src_rq->lock);

	/*
	 * 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;

	/* Disregard pcpu kthreads; they are where they need to be. */
	if ((p->flags & PF_KTHREAD) && kthread_is_per_cpu(p))
		return 0;

	if (!cpumask_test_cpu(env->dst_cpu, p->cpus_ptr)) {
		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.
		 *
		 * Avoid computing new_dst_cpu
		 * - for NEWLY_IDLE
		 * - if we have already computed one in current iteration
		 * - if it's an active balance
		 */
		if (env->idle == CPU_NEWLY_IDLE ||
		    env->flags & (LBF_DST_PINNED | LBF_ACTIVE_LB))
			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, p->cpus_ptr)) {
				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 (energy_aware() && !sd_overutilized(env->sd) &&
	    env->idle == CPU_NEWLY_IDLE &&
	    !task_in_related_thread_group(p)) {
		long util_cum_dst, util_cum_src;
		unsigned long demand;

		demand = task_util(p);
		util_cum_dst = cpu_util_cum(env->dst_cpu, 0) + demand;
		util_cum_src = cpu_util_cum(env->src_cpu, 0) - demand;

		if (util_cum_dst > util_cum_src)
			return 0;
	}

#ifdef CONFIG_SCHED_WALT
	if (env->flags & LBF_IGNORE_PREFERRED_CLUSTER_TASKS &&
			 !preferred_cluster(cpu_rq(env->dst_cpu)->cluster, p))
		return 0;
#endif

	/* Don't detach task if it doesn't fit on the destination */
	if (env->flags & LBF_IGNORE_BIG_TASKS &&
		!task_fits_max(p, env->dst_cpu))
		return 0;

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

	/* Don't detach task if it is under active migration */
	if (env->src_rq->push_task == p)
		return 0;

	/*
	 * Aggressive migration if:
	 * 1) active balance
	 * 2) IDLE or NEWLY_IDLE balance.
	 * 3) destination numa is preferred
	 * 4) task is cache cold, or
	 * 5) too many balance attempts have failed.
	 */

	if (env->flags & LBF_ACTIVE_LB)
		return 1;

	tsk_cache_hot = migrate_degrades_locality(p, env);
	if (tsk_cache_hot == -1)
		tsk_cache_hot = task_hot(p, env);

	if (env->idle != CPU_NOT_IDLE || tsk_cache_hot <= 0 ||
	    env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
		if (tsk_cache_hot == 1) {
			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;
}

/*
 * detach_task() -- detach the task for the migration specified in env
 */
static void detach_task(struct task_struct *p, struct lb_env *env)
{
	lockdep_assert_held(&env->src_rq->lock);

	p->on_rq = TASK_ON_RQ_MIGRATING;
	deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK);
#ifdef CONFIG_SCHED_WALT
	double_lock_balance(env->src_rq, env->dst_rq);
	if (!(env->src_rq->clock_update_flags & RQCF_UPDATED))
		update_rq_clock(env->src_rq);
	set_task_cpu(p, env->dst_cpu);
	double_unlock_balance(env->src_rq, env->dst_rq);
	lockdep_on();
#else
	set_task_cpu(p, env->dst_cpu);
#endif
}

/*
 * detach_one_task() -- tries to dequeue exactly one task from env->src_rq, as
 * part of active balancing operations within "domain".
 *
 * Returns a task if successful and NULL otherwise.
 */
static struct task_struct *detach_one_task(struct lb_env *env)
{
	struct task_struct *p;

	lockdep_assert_held(&env->src_rq->lock);

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

		detach_task(p, env);

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

static const unsigned int sched_nr_migrate_break = 32;

/*
 * detach_tasks() -- tries to detach up to imbalance weighted load from
 * busiest_rq, as part of a balancing operation within domain "sd".
 *
 * Returns number of detached tasks if successful and 0 otherwise.
 */
static int detach_tasks(struct lb_env *env)
{
	struct list_head *tasks = &env->src_rq->cfs_tasks;
	struct task_struct *p;
	unsigned long load = 0;
	int detached = 0;
	int orig_loop = env->loop;

	lockdep_assert_held(&env->src_rq->lock);

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

	if (!same_cluster(env->dst_cpu, env->src_cpu))
		env->flags |= LBF_IGNORE_PREFERRED_CLUSTER_TASKS;

	if (cpu_capacity(env->dst_cpu) < cpu_capacity(env->src_cpu))
		env->flags |= LBF_IGNORE_BIG_TASKS;

redo:
	while (!list_empty(tasks)) {
		/*
		 * We don't want to steal all, otherwise we may be treated likewise,
		 * which could at worst lead to a livelock crash.
		 */
		if (env->idle != CPU_NOT_IDLE && env->src_rq->nr_running <= 1)
			break;

		p = list_last_entry(tasks, struct task_struct, se.group_node);

		env->loop++;
		/*
		 * We've more or less seen every task there is, call it quits
		 * unless we haven't found any movable task yet.
		 */
		if (env->loop > env->loop_max &&
		    !(env->flags & LBF_ALL_PINNED))
			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;

		/*
		 * Depending of the number of CPUs and tasks and the
		 * cgroup hierarchy, task_h_load() can return a null
		 * value. Make sure that env->imbalance decreases
		 * otherwise detach_tasks() will stop only after
		 * detaching up to loop_max tasks.
		 */
		load = max_t(unsigned long, task_h_load(p), 1);


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

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

		detach_task(p, env);
		list_add(&p->se.group_node, &env->tasks);

		detached++;
		env->imbalance -= load;

#ifdef CONFIG_PREEMPT
		/*
		 * NEWIDLE balancing is a source of latency, so preemptible
		 * kernels will stop after the first task is detached 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:
		trace_sched_load_balance_skip_tasks(env->src_cpu, env->dst_cpu,
				env->src_grp_type, p->pid, load, task_util(p),
				cpumask_bits(&p->cpus_ptr)[0], env->flags );
		list_move(&p->se.group_node, tasks);
	}

	if (env->flags & (LBF_IGNORE_BIG_TASKS |
			LBF_IGNORE_PREFERRED_CLUSTER_TASKS) && !detached) {
		tasks = &env->src_rq->cfs_tasks;
		env->flags &= ~(LBF_IGNORE_BIG_TASKS |
				LBF_IGNORE_PREFERRED_CLUSTER_TASKS);
		env->loop = orig_loop;
		goto redo;
	}

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

	return detached;
}

/*
 * attach_task() -- attach the task detached by detach_task() to its new rq.
 */
static void attach_task(struct rq *rq, struct task_struct *p)
{
	lockdep_assert_held(&rq->lock);

	BUG_ON(task_rq(p) != rq);
	activate_task(rq, p, ENQUEUE_NOCLOCK);
	p->on_rq = TASK_ON_RQ_QUEUED;
	check_preempt_curr(rq, p, 0);
}

/*
 * attach_one_task() -- attaches the task returned from detach_one_task() to
 * its new rq.
 */
static void attach_one_task(struct rq *rq, struct task_struct *p)
{
	struct rq_flags rf;

	rq_lock(rq, &rf);
	update_rq_clock(rq);
	attach_task(rq, p);
	update_overutilized_status(rq);
	rq_unlock(rq, &rf);
}

/*
 * attach_tasks() -- attaches all tasks detached by detach_tasks() to their
 * new rq.
 */
static void attach_tasks(struct lb_env *env)
{
	struct list_head *tasks = &env->tasks;
	struct task_struct *p;
	struct rq_flags rf;

	rq_lock(env->dst_rq, &rf);
	update_rq_clock(env->dst_rq);

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

		attach_task(env->dst_rq, p);
	}

	/*
	 * The enqueue_task_fair only updates the overutilized status
	 * for the waking tasks. Since multiple tasks may get migrated
	 * from load balancer, instead of doing it there, update the
	 * overutilized status here at the end.
	 */
	update_overutilized_status(env->dst_rq);
	rq_unlock(env->dst_rq, &rf);
}

static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq)
{
	if (cfs_rq->avg.load_avg)
		return true;

	if (cfs_rq->avg.util_avg)
		return true;

	return false;
}

static inline bool others_have_blocked(struct rq *rq)
{
	if (READ_ONCE(rq->avg_rt.util_avg))
		return true;

	if (READ_ONCE(rq->avg_dl.util_avg))
		return true;

	if (thermal_load_avg(rq))
		return true;

#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
	if (READ_ONCE(rq->avg_irq.util_avg))
		return true;
#endif

	return false;
}

#ifdef CONFIG_FAIR_GROUP_SCHED

static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
{
	if (cfs_rq->load.weight)
		return false;

	if (cfs_rq->avg.load_sum)
		return false;

	if (cfs_rq->avg.util_sum)
		return false;

	if (cfs_rq->avg.runnable_load_sum)
		return false;

	return true;
}

static void update_blocked_averages(int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	struct cfs_rq *cfs_rq, *pos;
	const struct sched_class *curr_class;
	struct rq_flags rf;
	unsigned long thermal_pressure;

	rq_lock_irqsave(rq, &rf);
	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_safe(rq, cfs_rq, pos) {
		struct sched_entity *se;

		if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq))
			update_tg_load_avg(cfs_rq, 0);

		/* Propagate pending load changes to the parent, if any: */
		se = cfs_rq->tg->se[cpu];
		if (se && !skip_blocked_update(se))
			update_load_avg(cfs_rq_of(se), se, 0);

		/*
		 * There can be a lot of idle CPU cgroups.  Don't let fully
		 * decayed cfs_rqs linger on the list.
		 */
		if (cfs_rq_is_decayed(cfs_rq))
			list_del_leaf_cfs_rq(cfs_rq);
	}

	curr_class = rq->curr->sched_class;
	
	thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
	
	update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
	update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
	update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure);
	update_irq_load_avg(rq, 0);
#ifdef CONFIG_NO_HZ_COMMON
	rq->last_blocked_load_update_tick = jiffies;
#endif
	rq_unlock_irqrestore(rq, &rf);
}

/*
 * 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;

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

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

	while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) {
		load = cfs_rq->h_load;
		load = div64_ul(load * se->avg.load_avg,
			cfs_rq_load_avg(cfs_rq) + 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 * cfs_rq->h_load,
			cfs_rq_load_avg(cfs_rq) + 1);
}
#else
static inline void update_blocked_averages(int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	struct cfs_rq *cfs_rq = &rq->cfs;
	const struct sched_class *curr_class;
	struct rq_flags rf;

	rq_lock_irqsave(rq, &rf);
	update_rq_clock(rq);
	update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);

	curr_class = rq->curr->sched_class;
	update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
	update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
	update_irq_load_avg(rq, 0);
#ifdef CONFIG_NO_HZ_COMMON
	rq->last_blocked_load_update_tick = jiffies;
#endif
	rq_unlock_irqrestore(rq, &rf);
}

static unsigned long task_h_load(struct task_struct *p)
{
	return p->se.avg.load_avg;
}
#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_capacity;
	unsigned long group_util; /* Total utilization of the group */
	unsigned int sum_nr_running; /* Nr tasks running in the group */
	unsigned int idle_cpus;
	unsigned int group_weight;
	enum group_type group_type;
	int group_no_capacity;
	/* A cpu has a task too big for its capacity */
	unsigned long group_misfit_task_load;
#ifdef CONFIG_NUMA_BALANCING
	unsigned int nr_numa_running;
	unsigned int nr_preferred_running;
#endif
};

/*
 * 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_running;
	unsigned long total_load;	/* Total load of all groups in sd */
	unsigned long total_capacity;	/* Total capacity of all groups in sd */
	unsigned long total_util;	/* Total util 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_running = 0UL,
		.total_load = 0UL,
		.total_capacity = 0UL,
		.total_util = 0UL,
		.busiest_stat = {
			.avg_load = 0UL,
			.sum_nr_running = 0,
			.group_type = group_other,
		},
	};
}

static unsigned long scale_rt_capacity(int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long max = arch_scale_cpu_capacity(cpu);
	unsigned long used, free;
	unsigned long irq;

	irq = cpu_util_irq(rq);

	if (unlikely(irq >= max))
		return 1;

	used = READ_ONCE(rq->avg_rt.util_avg);
	used += READ_ONCE(rq->avg_dl.util_avg);

	if (unlikely(used >= max))
		return 1;

	free = max - used;

	return scale_irq_capacity(free, irq, max);
}

void init_max_cpu_capacity(struct max_cpu_capacity *mcc)
{
	raw_spin_lock_init(&mcc->lock);
	mcc->val = 0;
	mcc->cpu = -1;
}

static void update_cpu_capacity(struct sched_domain *sd, int cpu)
{
	unsigned long capacity = scale_rt_capacity(cpu);
	struct sched_group *sdg = sd->groups;
	struct max_cpu_capacity *mcc;
	unsigned long max_capacity;
	int max_cap_cpu;
	unsigned long flags;
	__maybe_unused bool update = false;

	cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu);

	capacity *= arch_scale_max_freq_capacity(sd, cpu);
	capacity >>= SCHED_CAPACITY_SHIFT;

	mcc = &cpu_rq(cpu)->rd->max_cpu_capacity;

	raw_spin_lock_irqsave(&mcc->lock, flags);
	max_capacity = mcc->val;
	max_cap_cpu = mcc->cpu;

	if ((max_capacity > capacity && max_cap_cpu == cpu) ||
	    max_capacity < capacity) {
		mcc->val = capacity;
		mcc->cpu = cpu;
#ifdef CONFIG_SCHED_DEBUG
		raw_spin_unlock_irqrestore(&mcc->lock, flags);
		printk_deferred(KERN_INFO "CPU%d: update max cpu_capacity %lu\n",
				cpu, capacity);
		goto skip_unlock;
#endif
	}
	raw_spin_unlock_irqrestore(&mcc->lock, flags);

skip_unlock: __attribute__ ((unused));
	if (!capacity)
		capacity = 1;

	cpu_rq(cpu)->cpu_capacity = capacity;
	sdg->sgc->capacity = capacity;
	sdg->sgc->min_capacity = capacity;
	sdg->sgc->max_capacity = capacity;
}

void update_group_capacity(struct sched_domain *sd, int cpu)
{
	struct sched_domain *child = sd->child;
	struct sched_group *group, *sdg = sd->groups;
	unsigned long capacity, min_capacity, max_capacity;

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

	capacity = 0;
	min_capacity = ULONG_MAX;
	max_capacity = 0;

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

		for_each_cpu(cpu, sched_group_span(sdg)) {
			unsigned long cpu_cap = capacity_of(cpu);

			if (cpumask_test_cpu(cpu, cpu_isolated_mask))
			capacity += cpu_cap;
			min_capacity = min(cpu_cap, min_capacity);
			max_capacity = max(cpu_cap, max_capacity);
		}
	} else  {
		/*
		 * !SD_OVERLAP domains can assume that child groups
		 * span the current group.
		 */

		group = child->groups;
		do {
			struct sched_group_capacity *sgc = group->sgc;
			cpumask_t *cpus = sched_group_span(group);

			if (!cpu_isolated(cpumask_first(cpus))) {
				capacity += sgc->capacity;
				min_capacity = min(sgc->min_capacity,
							min_capacity);
				max_capacity = max(sgc->max_capacity,
							max_capacity);
			}
			group = group->next;
		} while (group != child->groups);
	}

	sdg->sgc->capacity = capacity;
	sdg->sgc->min_capacity = min_capacity;
	sdg->sgc->max_capacity = max_capacity;
}

/*
 * Check whether the capacity of the rq has been noticeably reduced by side
 * activity. The imbalance_pct is used for the threshold.
 * Return true is the capacity is reduced
 */
static inline int
check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
{
	return ((rq->cpu_capacity * sd->imbalance_pct) <
				(rq->cpu_capacity_orig * 100));
}

/*
 * Group imbalance indicates (and tries to solve) the problem where balancing
 * groups is inadequate due to ->cpus_ptr 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 calculate_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->sgc->imbalance;
}

/*
 * group_has_capacity returns true if the group has spare capacity that could
 * be used by some tasks.
 * We consider that a group has spare capacity if the  * number of task is
 * smaller than the number of CPUs or if the utilization is lower than the
 * available capacity for CFS tasks.
 * For the latter, we use a threshold to stabilize the state, to take into
 * account the variance of the tasks' load and to return true if the available
 * capacity in meaningful for the load balancer.
 * As an example, an available capacity of 1% can appear but it doesn't make
 * any benefit for the load balance.
 */
static inline bool
group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs)
{
	if (sgs->sum_nr_running < sgs->group_weight)
		return true;

	if ((sgs->group_capacity * 100) >
			(sgs->group_util * env->sd->imbalance_pct))
		return true;

	return false;
}

/*
 *  group_is_overloaded returns true if the group has more tasks than it can
 *  handle.
 *  group_is_overloaded is not equals to !group_has_capacity because a group
 *  with the exact right number of tasks, has no more spare capacity but is not
 *  overloaded so both group_has_capacity and group_is_overloaded return
 *  false.
 */
static inline bool
group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
{
	if (sgs->sum_nr_running <= sgs->group_weight)
		return false;

#ifdef CONFIG_SCHED_WALT
	if (env->idle != CPU_NOT_IDLE && walt_rotation_enabled)
		return true;
#endif

	if ((sgs->group_capacity * 100) <
			(sgs->group_util * env->sd->imbalance_pct))
		return true;

	return false;
}

static inline enum
group_type group_classify(struct sched_group *group,
			  struct sg_lb_stats *sgs)
{
	if (sgs->group_no_capacity)
		return group_overloaded;

	if (sg_imbalanced(group))
		return group_imbalanced;

	if (sgs->group_misfit_task_load)
		return group_misfit_task;

	return group_other;
}

/**
 * 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.
 * @sgs: variable to hold the statistics for this group.
 * @sg_status: Holds flag indicating the status of the sched_group
 * @overutilized: Indicate overutilization for any CPU.
 */
static inline void update_sg_lb_stats(struct lb_env *env,
			struct sched_group *group,
			struct sg_lb_stats *sgs,
			int *sg_status, bool *overutilized, bool *misfit_task)
{
	int i, nr_running;

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

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

		if (cpu_isolated(i))
			continue;

		sgs->group_load += weighted_cpuload(rq);
		sgs->group_util += cpu_util(i);

		nr_running = rq->nr_running;
		sgs->sum_nr_running += nr_running;

		if (nr_running > 1)
			*sg_status |= SG_OVERLOAD;

#ifdef CONFIG_NUMA_BALANCING
		sgs->nr_numa_running += rq->nr_numa_running;
		sgs->nr_preferred_running += rq->nr_preferred_running;
#endif
		sgs->sum_weighted_load += weighted_cpuload(rq);
		/*
		 * No need to call idle_cpu() if nr_running is not 0
		 */
		if (!nr_running && idle_cpu(i))
			sgs->idle_cpus++;

		if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
		    sgs->group_misfit_task_load < rq->misfit_task_load) {
			sgs->group_misfit_task_load = rq->misfit_task_load;
			*sg_status |= SG_OVERLOAD;
		}


		if (cpu_overutilized(i)) {
			*overutilized = true;

			if (rq->misfit_task_load)
				*misfit_task = true;
		}
	}

	/* Isolated CPU has no weight */
	if (!group->group_weight) {
		sgs->group_capacity = 0;
		sgs->avg_load = 0;
		sgs->group_no_capacity = 1;
		sgs->group_type = group_other;
		sgs->group_weight = group->group_weight;
	} else {
		/* Adjust by relative CPU capacity of the group */
		sgs->group_capacity = group->sgc->capacity;
		sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) /
							sgs->group_capacity;

		sgs->group_weight = group->group_weight;

		sgs->group_no_capacity = group_is_overloaded(env, sgs);
		sgs->group_type = group_classify(group, sgs);
	}

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

/**
 * 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)
{
	struct sg_lb_stats *busiest = &sds->busiest_stat;

	/*
	 * Don't try to pull misfit tasks we can't help.
	 * We can use max_capacity here as reduction in capacity on some
	 * cpus in the group should either be possible to resolve
	 * internally or be covered by avg_load imbalance (eventually).
	 */
	if (sgs->group_type == group_misfit_task &&
	    (!capacity_greater(capacity_of(env->dst_cpu), sg->sgc->max_capacity) ||
	     !group_has_capacity(env, &sds->local_stat)))
		return false;

	if (sgs->group_type > busiest->group_type)
		return true;

	if (sgs->group_type < busiest->group_type)
		return false;

	if (sgs->avg_load <= busiest->avg_load)
		return false;

	if (!(env->sd->flags & SD_ASYM_CPUCAPACITY))
		goto asym_packing;

	/*
	 * If we have more than one misfit sg go with the biggest misfit.
	 */
	if (sgs->group_type == group_misfit_task &&
	    sgs->group_misfit_task_load < busiest->group_misfit_task_load)
		return false;

asym_packing:
	/* This is the busiest node in its class. */
	if (!(env->sd->flags & SD_ASYM_PACKING))
		return true;

	/* No ASYM_PACKING if target cpu is already busy */
	if (env->idle == CPU_NOT_IDLE)
		return true;
	/*
	 * ASYM_PACKING needs to move all the work to the highest
	 * prority CPUs in the group, therefore mark all groups
	 * of lower priority than ourself as busy.
	 */
	if (sgs->sum_nr_running &&
	    sched_asym_prefer(env->dst_cpu, sg->asym_prefer_cpu)) {
		if (!sds->busiest)
			return true;

		/* Prefer to move from lowest priority cpu's work */
		if (sched_asym_prefer(sds->busiest->asym_prefer_cpu,
				      sg->asym_prefer_cpu))
			return true;
	}

	return false;
}

#ifdef CONFIG_NUMA_BALANCING
static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs)
{
	if (sgs->sum_nr_running > sgs->nr_numa_running)
		return regular;
	if (sgs->sum_nr_running > sgs->nr_preferred_running)
		return remote;
	return all;
}

static inline enum fbq_type fbq_classify_rq(struct rq *rq)
{
	if (rq->nr_running > rq->nr_numa_running)
		return regular;
	if (rq->nr_running > rq->nr_preferred_running)
		return remote;
	return all;
}
#else
static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs)
{
	return all;
}

static inline enum fbq_type fbq_classify_rq(struct rq *rq)
{
	return regular;
}
#endif /* CONFIG_NUMA_BALANCING */

#ifdef CONFIG_NO_HZ_COMMON
static struct {
	cpumask_var_t idle_cpus_mask;
	atomic_t nr_cpus;
	unsigned long next_balance;     /* in jiffy units */
	unsigned long next_update;     /* in jiffy units */
} nohz ____cacheline_aligned;
#endif

#define lb_sd_parent(sd) \
	(sd->parent && sd->parent->groups != sd->parent->groups->next)

/**
 * update_sd_lb_stats - Update sched_domain's statistics for load balancing.
 * @env: The load balancing environment.
 * @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 *local = &sds->local_stat;
	struct sg_lb_stats tmp_sgs;
	bool overutilized = false, misfit_task = false;
	bool prefer_sibling = child && child->flags & SD_PREFER_SIBLING;
	int sg_status = 0;

#ifdef CONFIG_NO_HZ_COMMON
	if (env->idle == CPU_NEWLY_IDLE) {
		int cpu;

		/* Update the stats of NOHZ idle CPUs in the sd */
		for_each_cpu_and(cpu, sched_domain_span(env->sd),
				 nohz.idle_cpus_mask) {
			struct rq *rq = cpu_rq(cpu);

			/* ... Unless we've already done since the last tick */
			if (time_after(jiffies,
                                       rq->last_blocked_load_update_tick))
				update_blocked_averages(cpu);
		}
	}
	/*
	 * If we've just updated all of the NOHZ idle CPUs, then we can push
	 * back the next nohz.next_update, which will prevent an unnecessary
	 * wakeup for the nohz stats kick
	 */
	if (cpumask_subset(nohz.idle_cpus_mask, sched_domain_span(env->sd)))
		nohz.next_update = jiffies + LOAD_AVG_PERIOD;
#endif

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

		local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(sg));
		if (local_group) {
			sds->local = sg;
			sgs = local;
			update_group_capacity(env->sd, env->dst_cpu);
		}

		update_sg_lb_stats(env, sg, sgs,
				   &sg_status, &overutilized,
				   &misfit_task);

		if (local_group)
			goto next_group;

		/*
		 * In case the child domain prefers tasks go to siblings
		 * first, lower the sg capacity 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. 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 &&
		    group_has_capacity(env, local) &&
		    (sgs->sum_nr_running > local->sum_nr_running + 1)) {
			sgs->group_no_capacity = 1;
			sgs->group_type = group_classify(sg, sgs);
		}

		/*
		 * Disallow moving tasks from asym cap sibling CPUs to other
		 * CPUs (lower capacity) unless the asym cap sibling group has
		 * no capacity to manage the current load.
		 */
		if ((env->sd->flags & SD_ASYM_CPUCAPACITY) &&
			sgs->group_no_capacity &&
			asym_cap_sibling_group_has_capacity(env->dst_cpu,
						env->sd->imbalance_pct)) {
			sgs->group_no_capacity = 0;
			sgs->group_type = group_classify(sg, sgs);
		}

		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_running += sgs->sum_nr_running;
		sds->total_load += sgs->group_load;
		sds->total_capacity += sgs->group_capacity;
		sds->total_util += sgs->group_util;

		trace_sched_load_balance_sg_stats(sg->cpumask[0], sgs->group_type,
					sgs->idle_cpus, sgs->sum_nr_running,
					sgs->group_load, sgs->group_capacity,
					sgs->group_util, sgs->group_no_capacity,
					sgs->load_per_task,
					sgs->group_misfit_task_load,
					sds->busiest ? sds->busiest->cpumask[0] : 0);

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

	if (env->sd->flags & SD_NUMA)
		env->fbq_type = fbq_classify_group(&sds->busiest_stat);

	env->src_grp_nr_running = sds->busiest_stat.sum_nr_running;

	if (!lb_sd_parent(env->sd)) {
		/* update overload indicator if we are at root domain */
		WRITE_ONCE(env->dst_rq->rd->overload, sg_status & SG_OVERLOAD);
	}

	if (overutilized)
		set_sd_overutilized(env->sd);
	else
		clear_sd_overutilized(env->sd);

	/*
	 * If there is a misfit task in one cpu in this sched_domain
	 * it is likely that the imbalance cannot be sorted out among
	 * the cpu's in this sched_domain. In this case set the
	 * overutilized flag at the parent sched_domain.
	 */
	if (misfit_task) {
		struct sched_domain *sd = env->sd->parent;

		/*
		 * In case of a misfit task, load balance at the parent
		 * sched domain level will make sense only if the the cpus
		 * have a different capacity. If cpus at a domain level have
		 * the same capacity, the misfit task cannot be well
		 * accomodated	in any of the cpus and there in no point in
		 * trying a load balance at this level
		 */
		while (sd) {
			if (sd->flags & SD_ASYM_CPUCAPACITY) {
				set_sd_overutilized(sd);
				break;
			}
			sd = sd->parent;
		}
	}

	/*
	 * If the domain util is greater that domain capacity, load balancing
	 * needs to be done at the next sched domain level as well.
	 */
	if (lb_sd_parent(env->sd) &&
	    sds->total_capacity * 1024 < sds->total_util *
			sched_capacity_margin_up[group_first_cpu(sds->local)])
		set_sd_overutilized(env->sd->parent);
}

/**
 * check_asym_packing - Check to see if the group is packed into the
 *			sched domain.
 *
 * 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 env->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 (env->idle == CPU_NOT_IDLE)
		return 0;

	if (!sds->busiest)
		return 0;

	busiest_cpu = sds->busiest->asym_prefer_cpu;
	if (sched_asym_prefer(busiest_cpu, env->dst_cpu))
		return 0;

	env->imbalance = DIV_ROUND_CLOSEST(
		sds->busiest_stat.avg_load * sds->busiest_stat.group_capacity,
		SCHED_CAPACITY_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, capa_now = 0, capa_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_CAPACITY_SCALE) /
		busiest->group_capacity;

	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 capacity used by
	 * moving them.
	 */

	capa_now += busiest->group_capacity *
			min(busiest->load_per_task, busiest->avg_load);
	capa_now += local->group_capacity *
			min(local->load_per_task, local->avg_load);
	capa_now /= SCHED_CAPACITY_SCALE;

	/* Amount of load we'd subtract */
	if (busiest->avg_load > scaled_busy_load_per_task) {
		capa_move += busiest->group_capacity *
			    min(busiest->load_per_task,
				busiest->avg_load - scaled_busy_load_per_task);
	}

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

	/* Move if we gain throughput */
	if (capa_move > capa_now) {
		env->imbalance = busiest->load_per_task;
		return;
	}

	/* We can't see throughput improvement with the load-based
	 * method, but it is possible depending upon group size and
	 * capacity range that there might still be an underutilized
	 * cpu available in an asymmetric capacity system. Do one last
	 * check just in case.
	 */
	if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
		busiest->group_type == group_overloaded &&
		busiest->sum_nr_running > busiest->group_weight &&
		local->sum_nr_running < local->group_weight &&
		local->group_capacity < busiest->group_capacity)
		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;
	bool no_imbalance = false;

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

	if (busiest->group_type == group_imbalanced) {
		/*
		 * 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);
	}

	/*
	 * Avg load of busiest sg can be less and avg load of local sg can
	 * be greater than avg load across all sgs of sd because avg load
	 * factors in sg capacity and sgs with smaller group_type are
	 * skipped when updating the busiest sg:
	 */
	if (busiest->avg_load <= sds->avg_load ||
	    local->avg_load >= sds->avg_load)
		no_imbalance = true;

	if (busiest->group_type != group_misfit_task && no_imbalance) {
		env->imbalance = 0;
		if (busiest->group_type == group_overloaded &&
				local->group_type <= group_misfit_task) {
			env->imbalance = busiest->load_per_task;
			return;
		}
		return fix_small_imbalance(env, sds);
	}

	/*
	 * If there aren't any idle cpus, avoid creating some.
	 */
	if (busiest->group_type == group_overloaded &&
	    local->group_type   == group_overloaded) {
		load_above_capacity = busiest->sum_nr_running * SCHED_CAPACITY_SCALE;
		if (load_above_capacity > busiest->group_capacity) {
			load_above_capacity -= busiest->group_capacity;
			load_above_capacity *= scale_load_down(NICE_0_LOAD);
			load_above_capacity /= busiest->group_capacity;
		} else
			load_above_capacity = ~0UL;
	}

	/*
	 * In case of a misfit task, independent of avg loads we do load balance
	 * at the parent sched domain level for B.L systems, so it is possible
	 * that busiest group avg load can be less than sd avg load.
	 * So skip calculating load based imbalance between groups.
	 */
	if (!no_imbalance) {
		/*
		 * 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.
		 * 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_capacity,
				     (sds->avg_load - local->avg_load) *
				     local->group_capacity) /
				     SCHED_CAPACITY_SCALE;
	} else {
		/*
		 * Skipped load based imbalance calculations, but let's find
		 * imbalance based on busiest group type or fix small imbalance.
		 */
		env->imbalance = 0;
	}

	/* Boost imbalance to allow misfit task to be balanced.
	 * Always do this if we are doing a NEWLY_IDLE balance
	 * on the assumption that any tasks we have must not be
	 * long-running (and hence we cannot rely upon load).
	 * However if we are not idle, we should assume the tasks
	 * we have are longer running and not override load-based
	 * calculations above unless we are sure that the local
	 * group is underutilized.
	 */
	if (busiest->group_type == group_misfit_task &&
	    (env->idle == CPU_NEWLY_IDLE ||
	     local->sum_nr_running < local->group_weight)) {
		env->imbalance = max_t(long, env->imbalance,
				       busiest->group_misfit_task_load);
	}

	/*
	 * 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) {
		/*
		 * The busiest group is overloaded so it could use help
		 * from the other groups. If the local group has idle CPUs
		 * and it is not overloaded and has no imbalance with in
		 * the group, allow the load balance by bumping the
		 * imbalance.
		 */
		if (busiest->group_type == group_overloaded &&
			local->group_type <= group_misfit_task &&
			env->idle != CPU_NOT_IDLE) {
			env->imbalance = busiest->load_per_task;
			return;
		}

		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.
 *
 * 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.
 */
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);

	if (energy_aware() && !sd_overutilized(env->sd)) {
		int cpu_local, cpu_busiest;
		unsigned long capacity_local, capacity_busiest;

		if (env->idle != CPU_NEWLY_IDLE)
			goto out_balanced;

		if (!sds.local || !sds.busiest)
			goto out_balanced;

		cpu_local = group_first_cpu(sds.local);
		cpu_busiest = group_first_cpu(sds.busiest);

		/* TODO: don't assume same cap cpus are in same domain */
		capacity_local = capacity_orig_of(cpu_local);
		capacity_busiest = capacity_orig_of(cpu_busiest);
		if (capacity_local > capacity_busiest) {
			goto out_balanced;
		} else if (capacity_local == capacity_busiest) {
			if (cpu_rq(cpu_busiest)->nr_running < 2)
				goto out_balanced;
		}
	}

	local = &sds.local_stat;
	busiest = &sds.busiest_stat;

	/* ASYM feature bypasses nice load balance check */
	if (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;

	/* XXX broken for overlapping NUMA groups */
	sds.avg_load = (SCHED_CAPACITY_SCALE * sds.total_load)
						/ sds.total_capacity;

	/*
	 * 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_type == group_imbalanced)
		goto force_balance;

	/*
	 * When dst_cpu is idle, prevent SMP nice and/or asymmetric group
	 * capacities from resulting in underutilization due to avg_load.
	 */
	if (env->idle != CPU_NOT_IDLE && group_has_capacity(env, local) &&
	    busiest->group_no_capacity)
		goto force_balance;

	/* Misfit tasks should be dealt with regardless of the avg load */
	if (busiest->group_type == group_misfit_task)
		goto force_balance;

	/*
	 * If the local group is busier 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 is not overloaded
		 * and there is no imbalance between this and busiest group
		 * wrt idle cpus, it is balanced. The imbalance becomes
		 * significant if the diff is greater than 1 otherwise we
		 * might end up to just move the imbalance on another group
		 */
		if ((busiest->group_type != group_overloaded) &&
				(local->idle_cpus <= (busiest->idle_cpus + 1)))
			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 */
	env->src_grp_type = busiest->group_type;
	calculate_imbalance(env, &sds);
	trace_sched_load_balance_stats(sds.busiest->cpumask[0], busiest->group_type,
				busiest->avg_load, busiest->load_per_task,
				sds.local->cpumask[0], local->group_type,
				local->avg_load, local->load_per_task,
				sds.avg_load, env->imbalance);
	return env->imbalance ? sds.busiest : NULL;

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_capacity = 1;
	int i;

	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
		unsigned long capacity, wl;
		enum fbq_type rt;

		rq = cpu_rq(i);
		rt = fbq_classify_rq(rq);

		/*
		 * We classify groups/runqueues into three groups:
		 *  - regular: there are !numa tasks
		 *  - remote:  there are numa tasks that run on the 'wrong' node
		 *  - all:     there is no distinction
		 *
		 * In order to avoid migrating ideally placed numa tasks,
		 * ignore those when there's better options.
		 *
		 * If we ignore the actual busiest queue to migrate another
		 * task, the next balance pass can still reduce the busiest
		 * queue by moving tasks around inside the node.
		 *
		 * If we cannot move enough load due to this classification
		 * the next pass will adjust the group classification and
		 * allow migration of more tasks.
		 *
		 * Both cases only affect the total convergence complexity.
		 */
		if (rt > env->fbq_type)
			continue;

		/*
		 * For ASYM_CPUCAPACITY domains with misfit tasks we simply
		 * seek the "biggest" misfit task.
		 */
		if (env->src_grp_type == group_misfit_task) {
			if (rq->misfit_task_load > busiest_load) {
				busiest_load = rq->misfit_task_load;
				busiest = rq;
			}
			continue;
		}

		/*
		 * Ignore cpu, which is undergoing active_balance and doesn't
		 * have more than 2 tasks.
		 */
		if (rq->active_balance && rq->nr_running <= 2)
			continue;

		capacity = capacity_of(i);

		/*
		 * For ASYM_CPUCAPACITY domains, don't pick a cpu that could
		 * eventually lead to active_balancing high->low capacity.
		 * Higher per-cpu capacity is considered better than balancing
		 * average load.
		 */
		if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
		    !capacity_greater(capacity_of(env->dst_cpu), capacity) &&
		    rq->nr_running == 1)
			continue;

		wl = weighted_cpuload(rq);

		/*
		 * When comparing with imbalance, use weighted_cpuload()
		 * which is not scaled with the cpu capacity.
		 */

		if (rq->nr_running == 1 && wl > env->imbalance &&
		    !check_cpu_capacity(rq, env->sd))
			continue;

		/*
		 * For the load comparisons with the other cpu's, consider
		 * the weighted_cpuload() scaled with the cpu capacity, 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 / capacity_i), crosswise
		 * multiplication to rid ourselves of the division works out
		 * to: wl_i * capacity_j > wl_j * capacity_i;  where j is
		 * our previous maximum.
		 */
		if (wl * busiest_capacity > busiest_load * capacity) {
			busiest_load = wl;
			busiest_capacity = capacity;
			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
#define NEED_ACTIVE_BALANCE_THRESHOLD 10

static inline bool
asym_active_balance(struct lb_env *env)
{
	/*
	 * ASYM_PACKING needs to force migrate tasks from busy but
	 * lower priority CPUs in order to pack all tasks in the
	 * highest priority CPUs.
	 */
	return env->idle != CPU_NOT_IDLE && (env->sd->flags & SD_ASYM_PACKING) &&
	       sched_asym_prefer(env->dst_cpu, env->src_cpu);
}

static inline bool
voluntary_active_balance(struct lb_env *env)
{
	struct sched_domain *sd = env->sd;
	if (asym_active_balance(env))
		return 1;

	if (env->src_grp_type == group_overloaded &&
	    env->src_rq->misfit_task_load)
		return 1;

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

static int group_balance_cpu_not_isolated(struct sched_group *sg)
{
	cpumask_t cpus;

	cpumask_and(&cpus, sched_group_span(sg), group_balance_mask(sg));
	cpumask_andnot(&cpus, &cpus, cpu_isolated_mask);
	return cpumask_first(&cpus);
}

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

	if (voluntary_active_balance(env))
		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;
	int cpu, balance_cpu = -1;

	/*
	 * Ensure the balancing environment is consistent; can happen
	 * when the softirq triggers 'during' hotplug.
	 */
	if (!cpumask_test_cpu(env->dst_cpu, env->cpus))
		return 0;

	/*
	 * Ensure the balancing environment is consistent; can happen
	 * when the softirq triggers 'during' hotplug.
	 */
	if (!cpumask_test_cpu(env->dst_cpu, env->cpus))
		return 0;

	/*
	 * Ensure the balancing environment is consistent; can happen
	 * when the softirq triggers 'during' hotplug.
	 */
	if (!cpumask_test_cpu(env->dst_cpu, env->cpus))
		return 0;

	/*
	 * In the newly idle case, we will allow all the cpu's
	 * to do the newly idle load balance.
	 *
	 * However, we bail out if we already have tasks or a wakeup pending,
	 * to optimize wakeup latency.
	 */
	if (env->idle == CPU_NEWLY_IDLE) {
#if SCHED_FEAT_TTWU_QUEUE
		if (env->dst_rq->nr_running > 0 || !llist_empty(&env->dst_rq->wake_list))
			return 0;
#else
		if (env->dst_rq->nr_running > 0)
			return 0;
#endif
		return 1;
	}

	/* Try to find first idle cpu */
	for_each_cpu_and(cpu, group_balance_mask(sg), env->cpus) {
		if (!idle_cpu(cpu) || cpu_isolated(cpu))
			continue;

		balance_cpu = cpu;
		break;
	}

	if (balance_cpu == -1)
		balance_cpu = group_balance_cpu_not_isolated(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 = 0, cur_ld_moved, active_balance = 0;
	struct sched_domain *sd_parent = lb_sd_parent(sd) ? sd->parent : NULL;
	struct sched_group *group = NULL;
	struct rq *busiest = NULL;
	struct rq_flags rf;
	struct cpumask *cpus = this_cpu_cpumask_var_ptr(load_balance_mask);

	struct lb_env env = {
		.sd		= sd,
		.dst_cpu	= this_cpu,
		.dst_rq		= this_rq,
		.dst_grpmask    = group_balance_mask(sd->groups),
		.idle		= idle,
		.loop_break	= sched_nr_migrate_break,
		.cpus		= cpus,
		.fbq_type	= all,
		.tasks		= LIST_HEAD_INIT(env.tasks),
		.imbalance		= 0,
		.flags			= 0,
		.loop			= 0,
	};

	cpumask_and(cpus, sched_domain_span(sd), 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);

	env.src_cpu = busiest->cpu;
	env.src_rq = busiest;

	ld_moved = 0;
	/* Clear this flag as soon as we find a pullable task */
	env.flags |= LBF_ALL_PINNED;
	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.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);

more_balance:
		rq_lock_irqsave(busiest, &rf);

		/*
		 * The world might have changed. Validate assumptions.
		 * And also, if the busiest cpu is undergoing active_balance,
		 * it doesn't need help if it has less than 2 tasks on it.
		 */

		if (busiest->nr_running <= 1 ||
		    (busiest->active_balance && busiest->nr_running <= 2)) {
			rq_unlock_irqrestore(busiest, &rf);
			env.flags &= ~LBF_ALL_PINNED;
			goto no_move;
		}

		update_rq_clock(busiest);

		/*
		 * cur_ld_moved - load moved in current iteration
		 * ld_moved     - cumulative load moved across iterations
		 */
		cur_ld_moved = detach_tasks(&env);

		/*
		 * We've detached some tasks from busiest_rq. Every
		 * task is masked "TASK_ON_RQ_MIGRATING", so we can safely
		 * unlock busiest->lock, and we are able to be sure
		 * that nobody can manipulate the tasks in parallel.
		 * See task_rq_lock() family for the details.
		 */

		rq_unlock(busiest, &rf);

		if (cur_ld_moved) {
			attach_tasks(&env);
			ld_moved += cur_ld_moved;
		}

		local_irq_restore(rf.flags);

		if (env.flags & LBF_NEED_BREAK) {
			env.flags &= ~LBF_NEED_BREAK;
			/* Stop if we tried all running tasks */
			if (env.loop < busiest->nr_running)
				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->sgc->imbalance;

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

		/* All tasks on this runqueue were pinned by CPU affinity */
		if (unlikely(env.flags & LBF_ALL_PINNED)) {
			cpumask_clear_cpu(cpu_of(busiest), cpus);
			/*
			 * Attempting to continue load balancing at the current
			 * sched_domain level only makes sense if there are
			 * active CPUs remaining as possible busiest CPUs to
			 * pull load from which are not contained within the
			 * destination group that is receiving any migrated
			 * load.
			 */
			if (!cpumask_subset(cpus, env.dst_grpmask)) {
				env.loop = 0;
				env.loop_break = sched_nr_migrate_break;
				goto redo;
			}
			goto out_all_pinned;
		}
	}

no_move:
	if (!ld_moved) {
		/*
		 * 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) {
			if (env.src_grp_nr_running > 1)
				sd->nr_balance_failed++;
		}

		if (need_active_balance(&env)) {
			unsigned long flags;

			raw_spin_lock_irqsave(&busiest->lock, flags);

			/*
			 * The CPUs are marked as reserved if tasks
			 * are pushed/pulled from other CPUs. In that case,
			 * bail out from the load balancer.
			 */
			if (is_reserved(this_cpu) ||
			    is_reserved(cpu_of(busiest))) {
				raw_spin_unlock_irqrestore(&busiest->lock,
							   flags);
				*continue_balancing = 0;
				goto out;
			}

			/* 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, busiest->curr->cpus_ptr)) {
				raw_spin_unlock_irqrestore(&busiest->lock,
							    flags);
				goto out_one_pinned;
			}

			/* Record that we found at least one task that could run on this_cpu */
			env.flags &= ~LBF_ALL_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 &&
			    !cpu_isolated(cpu_of(busiest))) {
				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);
				*continue_balancing = 0;
			}
		}
	} else
		sd->nr_balance_failed = 0;

	if (likely(!active_balance) || voluntary_active_balance(&env)) {
		/* 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
		 * detach_tasks).
		 */
		if (sd->balance_interval < sd->max_interval)
			sd->balance_interval *= 2;
	}

	goto out;

out_balanced:
	/*
	 * We reach balance although we may have faced some affinity
	 * constraints. Clear the imbalance flag only if other tasks got
	 * a chance to move and fix the imbalance.
	 */
	if (sd_parent && !(env.flags & LBF_ALL_PINNED)) {
		int *group_imbalance = &sd_parent->groups->sgc->imbalance;

		if (*group_imbalance)
			*group_imbalance = 0;
	}

out_all_pinned:
	/*
	 * We reach balance because all tasks are pinned at this level so
	 * we can't migrate them. Let the imbalance flag set so parent level
	 * can try to migrate them.
	 */
	schedstat_inc(sd->lb_balanced[idle]);

	sd->nr_balance_failed = 0;

out_one_pinned:
	ld_moved = 0;

	/*
	 * idle_balance() disregards balance intervals, so we could repeatedly
	 * reach this code, which would lead to balance_interval skyrocketting
	 * in a short amount of time. Skip the balance_interval increase logic
	 * to avoid that.
	 */
	if (env.idle == CPU_NEWLY_IDLE)
		goto out;

	/* 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;
out:
	trace_sched_load_balance(this_cpu, idle, *continue_balancing,
				 group ? group->cpumask[0] : 0,
				 busiest ? busiest->nr_running : 0,
				 env.imbalance, env.flags, ld_moved,
				 sd->balance_interval, active_balance);
	return ld_moved;
}

static inline unsigned long
get_sd_balance_interval(struct sched_domain *sd, int cpu_busy)
{
	unsigned long interval = sd->balance_interval;
	unsigned int cpu;

	if (cpu_busy)
		interval *= sd->busy_factor;

	/* scale ms to jiffies */
	interval = msecs_to_jiffies(interval);

	/*
	 * Reduce likelihood of busy balancing at higher domains racing with
	 * balancing at lower domains by preventing their balancing periods
	 * from being multiples of each other.
	 */
	if (cpu_busy)
		interval -= 1;

	interval = clamp(interval, 1UL, max_load_balance_interval);

	/*
	 * check if sched domain is marked as overutilized
	 * we ought to only do this on systems which have SD_ASYMCAPACITY
	 * but we want to do it for all sched domains in those systems
	 * So for now, just check if overutilized as a proxy.
	 */
	/*
	 * If we are overutilized and we have a misfit task, then
	 * we want to balance as soon as practically possible, so
	 * we return an interval of zero.
	 */
	if (energy_aware() && sd_overutilized(sd)) {
		/* we know the root is overutilized, let's check for a misfit task */
		for_each_cpu(cpu, sched_domain_span(sd)) {
			if (cpu_rq(cpu)->misfit_task_load)
				return 1;
		}
	}
	return interval;
}

static inline void
update_next_balance(struct sched_domain *sd, unsigned long *next_balance)
{
	unsigned long interval, next;

	/* used by idle balance, so cpu_busy = 0 */
	interval = get_sd_balance_interval(sd, 0);
	next = sd->last_balance + interval;

	if (time_after(*next_balance, next))
		*next_balance = next;
}

#ifdef CONFIG_SCHED_WALT
static inline bool min_cap_cluster_has_misfit_task(void)
{
	int cpu;

	for_each_possible_cpu(cpu) {
		if (!is_min_capacity_cpu(cpu))
			break;
		if (cpu_rq(cpu)->walt_stats.nr_big_tasks)
			return true;
	}

	return false;
}
#else
static inline bool min_cap_cluster_has_misfit_task(void)
{
	return false;
}
#endif

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

	if (cpu_isolated(this_cpu))
		return 0;

	/*
	 * We must set idle_stamp _before_ calling idle_balance(), such that we
	 * measure the duration of idle_balance() as idle time.
	 */
	this_rq->idle_stamp = rq_clock(this_rq);

	/*
	 * Do not pull tasks towards !active CPUs...
	 */
	if (!cpu_active(this_cpu))
		return 0;

	/*
	 * Force higher capacity CPUs doing load balance, when the lower
	 * capacity CPUs has some misfit tasks.
	 */
	if (!is_min_capacity_cpu(this_cpu) && min_cap_cluster_has_misfit_task())
		force_lb = true;

	/*
	 * This is OK, because current is on_cpu, which avoids it being picked
	 * for load-balance and preemption/IRQs are still disabled avoiding
	 * further scheduler activity on it and we're being very careful to
	 * re-start the picking loop.
	 */
	rq_unpin_lock(this_rq, rf);

	if (!force_lb && (this_rq->avg_idle < sysctl_sched_migration_cost ||
	    !READ_ONCE(this_rq->rd->overload))) {
		rcu_read_lock();
		sd = rcu_dereference_check_sched_domain(this_rq->sd);
		if (sd)
			update_next_balance(sd, &next_balance);
		rcu_read_unlock();

		goto out;
	}

	raw_spin_unlock(&this_rq->lock);

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

		if (!(sd->flags & SD_LOAD_BALANCE)) {
			update_group_capacity(sd, this_cpu);
			continue;
		}

		if (!force_lb &&
		    this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) {
			update_next_balance(sd, &next_balance);
			break;
		}

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

			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;
		}

		update_next_balance(sd, &next_balance);

		/*
		 * Stop searching for tasks to pull if there are
		 * now runnable tasks on this rq.
		 */
		if (pulled_task || this_rq->nr_running > 0)
			break;
	}
	rcu_read_unlock();

	raw_spin_lock(&this_rq->lock);

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

out:
	/*
	 * While browsing the domains, we released the rq lock, a task could
	 * have been enqueued in the meantime. Since we're not going idle,
	 * pretend we pulled a task.
	 */
	if (this_rq->cfs.h_nr_running && !pulled_task)
		pulled_task = 1;

	/* Move the next balance forward */
	if (time_after(this_rq->next_balance, next_balance))
		this_rq->next_balance = next_balance;

	/* Is there a task of a high priority class? */
	if (this_rq->nr_running != this_rq->cfs.h_nr_running)
		pulled_task = -1;

	if (pulled_task)
		this_rq->idle_stamp = 0;

	rq_repin_lock(this_rq, rf);

	return pulled_task;
}

/*
 * 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 = NULL;
	struct task_struct *p = NULL;
	struct rq_flags rf;
	struct task_struct *push_task;
	int push_task_detached = 0;
	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,
		.flags			= 0,
		.loop			= 0,
	};
	bool moved = false;

	rq_lock_irq(busiest_rq, &rf);
	/*
	 * Between queueing the stop-work and running it is a hole in which
	 * CPUs can become inactive. We should not move tasks from or to
	 * inactive CPUs.
	 */
	if (!cpu_active(busiest_cpu) || !cpu_active(target_cpu))
		goto out_unlock;

	/* 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);

	push_task = busiest_rq->push_task;
	target_cpu = busiest_rq->push_cpu;
	if (push_task) {
		if (task_on_rq_queued(push_task) &&
			push_task->state == TASK_RUNNING &&
			task_cpu(push_task) == busiest_cpu &&
					cpu_online(target_cpu)) {
			update_rq_clock(busiest_rq);
			detach_task(push_task, &env);
			push_task_detached = 1;
			moved = true;
		}
		goto out_unlock;
	}

	/* 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,
			.flags		= LBF_ACTIVE_LB,
		};

		schedstat_inc(sd->alb_count);
		update_rq_clock(busiest_rq);

		p = detach_one_task(&env);
		if (p) {
			schedstat_inc(sd->alb_pushed);
			/* Active balancing done, reset the failure counter. */
			sd->nr_balance_failed = 0;
			moved = true;
		} else {
			schedstat_inc(sd->alb_failed);
		}
	}
	rcu_read_unlock();
out_unlock:
	busiest_rq->active_balance = 0;
	push_task = busiest_rq->push_task;
	target_cpu = busiest_rq->push_cpu;

	if (push_task)
		busiest_rq->push_task = NULL;

	rq_unlock(busiest_rq, &rf);

	if (push_task) {
		if (push_task_detached)
			attach_one_task(target_rq, push_task);
		put_task_struct(push_task);
		clear_reserved(target_cpu);
	}

	if (p)
		attach_one_task(target_rq, p);

	local_irq_enable();

	return 0;
}

static inline int on_null_domain(struct rq *rq)
{
	return unlikely(!rcu_dereference_sched(rq->sd));
}

#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 inline int find_new_ilb(void)
{
	int ilb = nr_cpu_ids;
	struct sched_domain *sd;
	int cpu = raw_smp_processor_id();
	struct rq *rq = cpu_rq(cpu);
	cpumask_t cpumask;

	rcu_read_lock();
	sd = rcu_dereference_check_sched_domain(rq->sd);
	if (sd) {
		cpumask_and(&cpumask, nohz.idle_cpus_mask,
				sched_domain_span(sd));
		cpumask_andnot(&cpumask, &cpumask,
				cpu_isolated_mask);
		ilb = cpumask_first(&cpumask);
	}
	rcu_read_unlock();

	if (sd && (ilb >= nr_cpu_ids || !idle_cpu(ilb))) {
		if (!energy_aware() ||
				(capacity_orig_of(cpu) ==
				cpu_rq(cpu)->rd->max_cpu_capacity.val ||
				cpu_overutilized(cpu))) {
			cpumask_andnot(&cpumask, nohz.idle_cpus_mask,
					cpu_isolated_mask);
			ilb = cpumask_first(&cpumask);
		}
	}

	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(bool only_update)
{
	int ilb_cpu;

	nohz.next_balance++;

	ilb_cpu = find_new_ilb();

	if (ilb_cpu >= nr_cpu_ids)
		return;

	if (test_and_set_bit(NOHZ_BALANCE_KICK, nohz_flags(ilb_cpu)))
		return;

	if (only_update)
		set_bit(NOHZ_STATS_KICK, nohz_flags(ilb_cpu));

	/*
	 * 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.
	 */
	trace_sched_load_balance_nohz_kick(smp_processor_id(), ilb_cpu);
	smp_send_reschedule(ilb_cpu);
	return;
}

void nohz_balance_exit_idle(unsigned int cpu)
{
	if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) {
		/*
		 * Completely isolated CPUs don't ever set, so we must test.
		 */
		if (likely(cpumask_test_cpu(cpu, nohz.idle_cpus_mask))) {
			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;
	int cpu = smp_processor_id();

	rcu_read_lock();
	sd = rcu_dereference(per_cpu(sd_llc, cpu));

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

	atomic_inc(&sd->shared->nr_busy_cpus);
unlock:
	rcu_read_unlock();
}

void set_cpu_sd_state_idle(void)
{
	struct sched_domain *sd;
	int cpu = smp_processor_id();

	rcu_read_lock();
	sd = rcu_dereference(per_cpu(sd_llc, cpu));

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

	atomic_dec(&sd->shared->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 (!cpu_active(cpu)) {	
		/*
		 * A CPU can be paused while it is idle with it's tick
		 * stopped. nohz_balance_exit_idle() should be called
		 * from the local CPU, so it can't be called during
		 * pause. This results in paused CPU participating in
		 * the nohz idle balance, which should be avoided.
		 * When the paused CPU exits idle and enters again,
		 * exempt the paused CPU from nohz_balance_exit_idle.
		 */
		nohz_balance_exit_idle(cpu);
		return;
	}

	/* Spare idle load balancing on CPUs that don't want to be disturbed: */
	if (!is_housekeeping_cpu(cpu))
		return;

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

	/*
	 * If we're a completely isolated CPU, we don't play.
	 */
	if (on_null_domain(cpu_rq(cpu)) || cpu_isolated(cpu))
		return;

	cpumask_set_cpu(cpu, nohz.idle_cpus_mask);
	atomic_inc(&nohz.nr_cpus);
	set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
}
#else
static inline void nohz_balancer_kick(bool only_update) {}
#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)
{
	cpumask_t avail_mask;
	unsigned int available_cpus;

	cpumask_andnot(&avail_mask, cpu_online_mask, cpu_isolated_mask);
	available_cpus = cpumask_weight(&avail_mask);

	max_load_balance_interval = HZ*available_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(struct rq *rq, enum cpu_idle_type idle)
{
	int continue_balancing = 1;
	int cpu = rq->cpu;
	int busy = idle != CPU_IDLE && !sched_idle_cpu(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;

	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 (energy_aware() && !sd_overutilized(sd))
			continue;

		if (!(sd->flags & SD_LOAD_BALANCE)) {
			update_group_capacity(sd, cpu);
			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 = get_sd_balance_interval(sd, busy);

		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;
				busy = idle != CPU_IDLE && !sched_idle_cpu(cpu);
			}
			sd->last_balance = jiffies;
			interval = get_sd_balance_interval(sd, busy);
		}
		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
		/*
		 * If this CPU has been elected to perform the nohz idle
		 * balance. Other idle CPUs have already rebalanced with
		 * nohz_idle_balance() and nohz.next_balance has been
		 * updated accordingly. This CPU is now running the idle load
		 * balance for itself and we need to update the
		 * nohz.next_balance accordingly.
		 */
		if ((idle == CPU_IDLE) && time_after(nohz.next_balance, rq->next_balance))
			nohz.next_balance = rq->next_balance;
#endif
	}
}

#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(struct rq *this_rq, enum cpu_idle_type idle)
{
	int this_cpu = this_rq->cpu;
	struct rq *rq;
	struct sched_domain *sd;
	int balance_cpu;
	/* Earliest time when we have to do rebalance again */
	unsigned long next_balance = jiffies + 60*HZ;
	int update_next_balance = 0;
	cpumask_t cpus;

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

	/*
	 * This cpu is going to update the blocked load of idle CPUs either
	 * before doing a rebalancing or just to keep metrics up to date. we
	 * can safely update the next update timestamp
	 */
	rcu_read_lock();
	sd = rcu_dereference(this_rq->sd);
	/*
	 * Check whether there is a sched_domain available for this cpu.
	 * The last other cpu can have been unplugged since the ILB has been
	 * triggered and the sched_domain can now be null. The idle balance
	 * sequence will quickly be aborted as there is no more idle CPUs
	 */
	if (sd)
		nohz.next_update = jiffies + msecs_to_jiffies(LOAD_AVG_PERIOD);
	rcu_read_unlock();

	cpumask_andnot(&cpus, nohz.idle_cpus_mask, cpu_isolated_mask);

	for_each_cpu(balance_cpu, &cpus) {
		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);

		/*
		 * If time for next balance is due,
		 * do the balance.
		 */
		if (time_after_eq(jiffies, rq->next_balance)) {
			struct rq_flags rf;

			rq_lock_irq(rq, &rf);
			update_rq_clock(rq);
			rq_unlock_irq(rq, &rf);

			update_blocked_averages(balance_cpu);
			/*
			 * This idle load balance softirq may have been
			 * triggered only to update the blocked load and shares
			 * of idle CPUs (which we have just done for
			 * balance_cpu). In that case skip the actual balance.
			 */
			if (!test_bit(NOHZ_STATS_KICK, nohz_flags(this_cpu)))
				rebalance_domains(rq, idle);
		}

		if (time_after(next_balance, rq->next_balance)) {
			next_balance = rq->next_balance;
			update_next_balance = 1;
		}
	}

	/*
	 * 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))
		nohz.next_balance = 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 in the system.
 *   - This rq has more than one task.
 *   - This rq has at least one CFS task and the capacity of the CPU is
 *     significantly reduced because of RT tasks or IRQs.
 *   - At parent of LLC scheduler domain level, this cpu's scheduler group has
 *     multiple busy cpu.
 *   - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler
 *     domain span are idle.
 */
static inline bool nohz_kick_needed(struct rq *rq, bool only_update)
{
	unsigned long now = jiffies;
	struct sched_domain_shared *sds;
	struct sched_domain *sd;
	int nr_busy, i, cpu = rq->cpu;
	bool kick = false;
	cpumask_t cpumask;

	if (unlikely(rq->idle_balance) && !only_update)
		return false;

       /*
	* 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.
	 */
	cpumask_andnot(&cpumask, nohz.idle_cpus_mask, cpu_isolated_mask);
	if (cpumask_empty(&cpumask))
		return false;

	if (only_update) {
		if (time_before(now, nohz.next_update))
			return false;
		else
			return true;
	}

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

	/*
	 * If energy aware is enabled, do idle load balance if runqueue has
	 * at least 2 tasks and cpu is overutilized
	 */
	if (rq->nr_running >= 2 &&
	    (!energy_aware() || cpu_overutilized(cpu)))
		return true;

	if (energy_aware())
		return rq->misfit_task_load > 0;

	rcu_read_lock();
	sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
	if (sds && !energy_aware()) {
		/*
		 * XXX: write a coherent comment on why we do this.
		 * See also: http://lkml.kernel.org/r/20111202010832.602203411@sbsiddha-desk.sc.intel.com
		 */
		nr_busy = atomic_read(&sds->nr_busy_cpus);
		if (nr_busy > 1) {
			kick = true;
			goto unlock;
		}

	}

	sd = rcu_dereference(per_cpu(sd_asym, cpu));
	if (sd) {
		for_each_cpu(i, sched_domain_span(sd)) {
			if (i == cpu ||
			    !cpumask_test_cpu(i, &cpumask))
				continue;

			if (sched_asym_prefer(i, cpu)) {
				kick = true;
				goto unlock;
			}
		}
	}
unlock:
	rcu_read_unlock();
	return kick;
}
#else
static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { }
static inline bool nohz_kick_needed(struct rq *rq, bool only_update) { return false; }
#endif

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

	/*
	 * Since core isolation doesn't update nohz.idle_cpus_mask, there
	 * is a possibility this nohz kicked cpu could be isolated. Hence
	 * return if the cpu is isolated.
	 */
	if (cpu_isolated(this_rq->cpu))
		return;
	/*
	 * If this cpu has a pending nohz_balance_kick, then do the
	 * balancing on behalf of the other idle cpus whose ticks are
	 * stopped. Do nohz_idle_balance *before* rebalance_domains to
	 * give the idle cpus a chance to load balance. Else we may
	 * load balance only within the local sched_domain hierarchy
	 * and abort nohz_idle_balance altogether if we pull some load.
	 */
	nohz_idle_balance(this_rq, idle);
	update_blocked_averages(this_rq->cpu);
#ifdef CONFIG_NO_HZ_COMMON
	if (!test_bit(NOHZ_STATS_KICK, nohz_flags(this_rq->cpu)))
		rebalance_domains(this_rq, idle);
	clear_bit(NOHZ_STATS_KICK, nohz_flags(this_rq->cpu));
#else
	rebalance_domains(this_rq, idle);
#endif
}

/*
 * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
 */
void trigger_load_balance(struct rq *rq)
{
	/* Don't need to rebalance while attached to NULL domain or
	 * cpu is isolated.
	 */
	if (unlikely(on_null_domain(rq)) || cpu_isolated(cpu_of(rq)))
		return;

	if (time_after_eq(jiffies, rq->next_balance))
		raise_softirq(SCHED_SOFTIRQ);
#ifdef CONFIG_NO_HZ_COMMON
	if (nohz_kick_needed(rq, false))
		nohz_balancer_kick(false);
#endif
}

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

	update_runtime_enabled(rq);
}

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;
#ifdef CONFIG_SCHED_WALT
	bool old_misfit = curr->misfit;
	bool misfit;
#endif

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

	if (IS_ENABLED(CONFIG_NUMA_BALANCING) &&
	    static_branch_unlikely(&sched_numa_balancing))
		task_tick_numa(rq, curr);

	update_misfit_status(curr, rq);

#ifdef CONFIG_SCHED_WALT
	misfit = rq->misfit_task_load;

	if (old_misfit != misfit) {
		walt_fixup_nr_big_tasks(rq, curr, 1, misfit);
		curr->misfit = misfit;
	}
#endif

	update_overutilized_status(rq);
}

/*
 * 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 sched_entity *se = &p->se, *curr;
	struct cfs_rq *cfs_rq;
	struct rq *rq = this_rq();
	struct rq_flags rf;

	rq_lock(rq, &rf);
	update_rq_clock(rq);

	cfs_rq = task_cfs_rq(current);
	curr = cfs_rq->curr;
	if (curr)
		update_curr(cfs_rq);
	place_entity(cfs_rq, se, ENQUEUE_INITIAL);
	rq_unlock(rq, &rf);
}

/*
 * 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 (!task_on_rq_queued(p))
		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_curr(rq);
	} else
		check_preempt_curr(rq, p, 0);
}

#ifdef CONFIG_FAIR_GROUP_SCHED
/*
 * Propagate the changes of the sched_entity across the tg tree to make it
 * visible to the root
 */
static void propagate_entity_cfs_rq(struct sched_entity *se)
{
	struct cfs_rq *cfs_rq;

	/* Start to propagate at parent */
	se = se->parent;

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

		if (cfs_rq_throttled(cfs_rq))
			break;

		update_load_avg(cfs_rq, se, UPDATE_TG);
	}
}
#else
static void propagate_entity_cfs_rq(struct sched_entity *se) { }
#endif

static void detach_entity_cfs_rq(struct sched_entity *se)
{
	struct cfs_rq *cfs_rq = cfs_rq_of(se);

#ifdef CONFIG_SMP
	/*
	 * In case the task sched_avg hasn't been attached:
	 * - A forked task which hasn't been woken up by wake_up_new_task().
	 * - A task which has been woken up by try_to_wake_up() but is
	 *   waiting for actually being woken up by sched_ttwu_pending().
	 */
	if (!se->avg.last_update_time)
		return;
#endif

	/* Catch up with the cfs_rq and remove our load when we leave */
	update_load_avg(cfs_rq, se, 0);
	detach_entity_load_avg(cfs_rq, se);
	update_tg_load_avg(cfs_rq, false);
	propagate_entity_cfs_rq(se);
}

static void attach_entity_cfs_rq(struct sched_entity *se)
{
	struct cfs_rq *cfs_rq = cfs_rq_of(se);

#ifdef CONFIG_FAIR_GROUP_SCHED
	/*
	 * Since the real-depth could have been changed (only FAIR
	 * class maintain depth value), reset depth properly.
	 */
	se->depth = se->parent ? se->parent->depth + 1 : 0;
#endif

	/* Synchronize entity with its cfs_rq */
	update_load_avg(cfs_rq, se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD);
	attach_entity_load_avg(cfs_rq, se);
	update_tg_load_avg(cfs_rq, false);
	propagate_entity_cfs_rq(se);
}

static void detach_task_cfs_rq(struct task_struct *p)
{
	struct sched_entity *se = &p->se;

	detach_entity_cfs_rq(se);
}

static void attach_task_cfs_rq(struct task_struct *p)
{
	struct sched_entity *se = &p->se;

	attach_entity_cfs_rq(se);
}

static void switched_from_fair(struct rq *rq, struct task_struct *p)
{
	detach_task_cfs_rq(p);
}

static void switched_to_fair(struct rq *rq, struct task_struct *p)
{
	attach_task_cfs_rq(p);

	if (task_on_rq_queued(p)) {
		/*
		 * 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_curr(rq);
		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_CACHED;
	u64_u32_store(cfs_rq->min_vruntime, (u64)(-(1LL << 20)));
#ifdef CONFIG_SMP
	raw_spin_lock_init(&cfs_rq->removed.lock);
#endif
}

#ifdef CONFIG_FAIR_GROUP_SCHED
static void task_set_group_fair(struct task_struct *p)
{
	struct sched_entity *se = &p->se;

	set_task_rq(p, task_cpu(p));
	se->depth = se->parent ? se->parent->depth + 1 : 0;
}

static void task_move_group_fair(struct task_struct *p)
{
	detach_task_cfs_rq(p);
	set_task_rq(p, task_cpu(p));

#ifdef CONFIG_SMP
	/* Tell se's cfs_rq has been changed -- migrated */
	p->se.avg.last_update_time = 0;
#endif
	attach_task_cfs_rq(p);
}

static void task_change_group_fair(struct task_struct *p, int type)
{
	switch (type) {
	case TASK_SET_GROUP:
		task_set_group_fair(p);
		break;

	case TASK_MOVE_GROUP:
		task_move_group_fair(p);
		break;
	}
}

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

	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 sched_entity *se;
	struct cfs_rq *cfs_rq;
	int i;

	tg->cfs_rq = kcalloc(nr_cpu_ids, sizeof(cfs_rq), GFP_KERNEL);
	if (!tg->cfs_rq)
		goto err;
	tg->se = kcalloc(nr_cpu_ids, sizeof(se), 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]);
		init_entity_runnable_average(se);
	}

	return 1;

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

void online_fair_sched_group(struct task_group *tg)
{
	struct sched_entity *se;
	struct rq_flags rf;
	struct rq *rq;
	int i;

	for_each_possible_cpu(i) {
		rq = cpu_rq(i);
		se = tg->se[i];
		rq_lock_irq(rq, &rf);
		update_rq_clock(rq);
		attach_entity_cfs_rq(se);
		sync_throttle(tg, i);
		rq_unlock_irq(rq, &rf);
	}
}

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

	destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));

	for_each_possible_cpu(cpu) {
		if (tg->se[cpu])
			remove_entity_load_avg(tg->se[cpu]);

		/*
		 * 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)
			continue;

		rq = cpu_rq(cpu);

		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;
		se->depth = 0;
	} else {
		se->cfs_rq = parent->my_q;
		se->depth = parent->depth + 1;
	}

	se->my_q = cfs_rq;
	/* guarantee group entities always have weight */
	update_load_set(&se->load, NICE_0_LOAD);
	se->parent = parent;
}

static DEFINE_MUTEX(shares_mutex);

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

	/*
	 * 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 = tg->se[i];
		struct rq_flags rf;

		/* Propagate contribution to hierarchy */
		rq_lock_irqsave(rq, &rf);
		update_rq_clock(rq);
		for_each_sched_entity(se) {
			update_load_avg(cfs_rq_of(se), se, UPDATE_TG);
			update_cfs_group(se);
		}
		rq_unlock_irqrestore(rq, &rf);
	}

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 online_fair_sched_group(struct task_group *tg) { }

void unregister_fair_sched_group(struct task_group *tg) { }

#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(se->slice);

	return rr_interval;
}

#ifdef CONFIG_SCHED_CASS
#include "cass.c"

/* Use CASS. A dummy wrapper ensures the replaced function is still "used". */
static inline void *select_task_rq_fair_dummy(void)
{
	return (void *)select_task_rq_fair;
}
#define select_task_rq_fair cass_select_task_rq_fair
#endif /* CONFIG_SCHED_CASS */

/*
 * 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_dead		= task_dead_fair,
	.set_cpus_allowed	= set_cpus_allowed_common,
#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,

	.update_curr		= update_curr_fair,

#ifdef CONFIG_FAIR_GROUP_SCHED
	.task_change_group	= task_change_group_fair,
#endif

#ifdef CONFIG_SCHED_WALT
	.fixup_walt_sched_stats	= walt_fixup_sched_stats_fair,
#endif

#ifdef CONFIG_UCLAMP_TASK
	.uclamp_enabled		= 1,
#endif
};

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

	rcu_read_lock();
	for_each_leaf_cfs_rq_safe(cpu_rq(cpu), cfs_rq, pos)
		print_cfs_rq(m, cpu, cfs_rq);
	rcu_read_unlock();
}

#ifdef CONFIG_NUMA_BALANCING
void show_numa_stats(struct task_struct *p, struct seq_file *m)
{
	int node;
	unsigned long tsf = 0, tpf = 0, gsf = 0, gpf = 0;

	for_each_online_node(node) {
		if (p->numa_faults) {
			tsf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 0)];
			tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)];
		}
		if (p->numa_group) {
			gsf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 0)],
			gpf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 1)];
		}
		print_numa_stats(m, node, tsf, tpf, gsf, gpf);
	}
}
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_SCHED_DEBUG */

__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;
	nohz.next_update = jiffies;
	zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
#endif

	alloc_eenv();
#endif /* SMP */

}

/* WALT sched implementation begins here */
#ifdef CONFIG_SCHED_WALT

#ifdef CONFIG_CFS_BANDWIDTH

static void walt_init_cfs_rq_stats(struct cfs_rq *cfs_rq)
{
	cfs_rq->walt_stats.nr_big_tasks = 0;
	cfs_rq->walt_stats.cumulative_runnable_avg_scaled = 0;
	cfs_rq->walt_stats.pred_demands_sum_scaled = 0;
}

static void walt_inc_cfs_rq_stats(struct cfs_rq *cfs_rq, struct task_struct *p)
{
	inc_nr_big_task(&cfs_rq->walt_stats, p);
	fixup_cumulative_runnable_avg(&cfs_rq->walt_stats,
				      p->ravg.demand_scaled,
				      p->ravg.pred_demand_scaled);
}

static void walt_dec_cfs_rq_stats(struct cfs_rq *cfs_rq, struct task_struct *p)
{
	dec_nr_big_task(&cfs_rq->walt_stats, p);
	fixup_cumulative_runnable_avg(&cfs_rq->walt_stats,
				      -(s64)p->ravg.demand_scaled,
				      -(s64)p->ravg.pred_demand_scaled);
}

static void walt_inc_throttled_cfs_rq_stats(struct walt_sched_stats *stats,
					    struct cfs_rq *tcfs_rq)
{
	struct rq *rq = rq_of(tcfs_rq);

	stats->nr_big_tasks += tcfs_rq->walt_stats.nr_big_tasks;
	fixup_cumulative_runnable_avg(stats,
			tcfs_rq->walt_stats.cumulative_runnable_avg_scaled,
			tcfs_rq->walt_stats.pred_demands_sum_scaled);

	if (stats == &rq->walt_stats)
		walt_fixup_cum_window_demand(rq,
			tcfs_rq->walt_stats.cumulative_runnable_avg_scaled);

}

static void walt_dec_throttled_cfs_rq_stats(struct walt_sched_stats *stats,
					    struct cfs_rq *tcfs_rq)
{
	struct rq *rq = rq_of(tcfs_rq);

	stats->nr_big_tasks -= tcfs_rq->walt_stats.nr_big_tasks;
	fixup_cumulative_runnable_avg(stats,
			-tcfs_rq->walt_stats.cumulative_runnable_avg_scaled,
			-tcfs_rq->walt_stats.pred_demands_sum_scaled);

	/*
	 * We remove the throttled cfs_rq's tasks's contribution from the
	 * cumulative window demand so that the same can be added
	 * unconditionally when the cfs_rq is unthrottled.
	 */
	if (stats == &rq->walt_stats)
		walt_fixup_cum_window_demand(rq,
			-tcfs_rq->walt_stats.cumulative_runnable_avg_scaled);
}

static void walt_fixup_sched_stats_fair(struct rq *rq, struct task_struct *p,
					u16 updated_demand_scaled,
					u16 updated_pred_demand_scaled)
{
	struct cfs_rq *cfs_rq;
	struct sched_entity *se = &p->se;
	s64 task_load_delta = (s64)updated_demand_scaled -
			      p->ravg.demand_scaled;
	s64 pred_demand_delta = (s64)updated_pred_demand_scaled -
				p->ravg.pred_demand_scaled;

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

		fixup_cumulative_runnable_avg(&cfs_rq->walt_stats,
					      task_load_delta,
					      pred_demand_delta);
		if (cfs_rq_throttled(cfs_rq))
			break;
	}

	/* Fix up rq->walt_stats only if we didn't find any throttled cfs_rq */
	if (!se) {
		fixup_cumulative_runnable_avg(&rq->walt_stats,
					      task_load_delta,
					      pred_demand_delta);
		walt_fixup_cum_window_demand(rq, task_load_delta);
	}
}

static void walt_fixup_nr_big_tasks(struct rq *rq, struct task_struct *p,
							int delta, bool inc)
{
	struct cfs_rq *cfs_rq;
	struct sched_entity *se = &p->se;

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

		cfs_rq->walt_stats.nr_big_tasks += inc ? delta : -delta;
		BUG_ON(cfs_rq->walt_stats.nr_big_tasks < 0);

		if (cfs_rq_throttled(cfs_rq))
			break;
	}

	/* Fix up rq->walt_stats only if we didn't find any throttled cfs_rq */
	if (!se)
		walt_adjust_nr_big_tasks(rq, delta, inc);
}

/*
 * Check if task is part of a hierarchy where some cfs_rq does not have any
 * runtime left.
 *
 * We can't rely on throttled_hierarchy() to do this test, as
 * cfs_rq->throttle_count will not be updated yet when this function is called
 * from scheduler_tick()
 */
static int task_will_be_throttled(struct task_struct *p)
{
	struct sched_entity *se = &p->se;
	struct cfs_rq *cfs_rq;

	if (!cfs_bandwidth_used())
		return 0;

	for_each_sched_entity(se) {
		cfs_rq = cfs_rq_of(se);
		if (!cfs_rq->runtime_enabled)
			continue;
		if (cfs_rq->runtime_remaining <= 0)
			return 1;
	}

	return 0;
}

#else /* CONFIG_CFS_BANDWIDTH */

static void walt_fixup_sched_stats_fair(struct rq *rq, struct task_struct *p,
					u16 updated_demand_scaled,
					u16 updated_pred_demand_scaled)
{
	fixup_walt_sched_stats_common(rq, p, updated_demand_scaled,
				      updated_pred_demand_scaled);
}

static void walt_fixup_nr_big_tasks(struct rq *rq, struct task_struct *p,
							int delta, bool inc)
{
	walt_adjust_nr_big_tasks(rq, delta, inc);
}

static int task_will_be_throttled(struct task_struct *p)
{
	return false;
}

#endif /* CONFIG_CFS_BANDWIDTH */

static inline int
kick_active_balance(struct rq *rq, struct task_struct *p, int new_cpu)
{
	unsigned long flags;
	int rc = 0;

	/* Invoke active balance to force migrate currently running task */
	raw_spin_lock_irqsave(&rq->lock, flags);
	if (!rq->active_balance) {
		rq->active_balance = 1;
		rq->push_cpu = new_cpu;
		get_task_struct(p);
		rq->push_task = p;
		rc = 1;
	}
	raw_spin_unlock_irqrestore(&rq->lock, flags);

	return rc;
}

#ifdef CONFIG_SCHED_WALT
struct walt_rotate_work {
	struct work_struct w;
	struct task_struct *src_task;
	struct task_struct *dst_task;
	int src_cpu;
	int dst_cpu;
};

static DEFINE_PER_CPU(struct walt_rotate_work, walt_rotate_works);

static void walt_rotate_work_func(struct work_struct *work)
{
	struct walt_rotate_work *wr = container_of(work,
				struct walt_rotate_work, w);

	migrate_swap(wr->src_task, wr->dst_task);

	put_task_struct(wr->src_task);
	put_task_struct(wr->dst_task);

	clear_reserved(wr->src_cpu);
	clear_reserved(wr->dst_cpu);
}

void walt_rotate_work_init(void)
{
	int i;

	for_each_possible_cpu(i) {
		struct walt_rotate_work *wr = &per_cpu(walt_rotate_works, i);

		INIT_WORK(&wr->w, walt_rotate_work_func);
	}
}

#define WALT_ROTATION_THRESHOLD_NS	16000000
static void walt_check_for_rotation(struct rq *src_rq)
{
	u64 wc, wait, max_wait = 0, run, max_run = 0;
	int deserved_cpu = nr_cpu_ids, dst_cpu = nr_cpu_ids;
	int i, src_cpu = cpu_of(src_rq);
	struct rq *dst_rq;
	struct walt_rotate_work *wr = NULL;

	if (!walt_rotation_enabled)
		return;

	if (!is_min_capacity_cpu(src_cpu))
		return;

	wc = sched_ktime_clock();
	for_each_possible_cpu(i) {
		struct rq *rq = cpu_rq(i);

		if (!is_min_capacity_cpu(i))
			break;

		if (is_reserved(i))
			continue;

		if (!rq->misfit_task_load || rq->curr->sched_class !=
						&fair_sched_class)
			continue;

		wait = wc - rq->curr->last_enqueued_ts;
		if (wait > max_wait) {
			max_wait = wait;
			deserved_cpu = i;
		}
	}

	if (deserved_cpu != src_cpu)
		return;

	for_each_possible_cpu(i) {
		struct rq *rq = cpu_rq(i);

		if (is_min_capacity_cpu(i))
			continue;

		if (is_reserved(i))
			continue;

		if (rq->curr->sched_class != &fair_sched_class)
			continue;

		if (rq->nr_running > 1)
			continue;

		run = wc - rq->curr->last_enqueued_ts;

		if (run < WALT_ROTATION_THRESHOLD_NS)
			continue;

		if (run > max_run) {
			max_run = run;
			dst_cpu = i;
		}
	}

	if (dst_cpu == nr_cpu_ids)
		return;

	dst_rq = cpu_rq(dst_cpu);

	double_rq_lock(src_rq, dst_rq);
	if (dst_rq->curr->sched_class == &fair_sched_class) {
		get_task_struct(src_rq->curr);
		get_task_struct(dst_rq->curr);

		mark_reserved(src_cpu);
		mark_reserved(dst_cpu);
		wr = &per_cpu(walt_rotate_works, src_cpu);

		wr->src_task = src_rq->curr;
		wr->dst_task = dst_rq->curr;

		wr->src_cpu = src_cpu;
		wr->dst_cpu = dst_cpu;
	}
	double_rq_unlock(src_rq, dst_rq);

	if (wr)
		queue_work_on(src_cpu, system_highpri_wq, &wr->w);
}
#else
static inline void walt_check_for_rotation(struct rq *rq)
{
}
#endif

static DEFINE_RAW_SPINLOCK(migration_lock);
void check_for_migration(struct rq *rq, struct task_struct *p)
{
	int active_balance;
	int new_cpu = -1;
	int cpu = smp_processor_id();
	int prev_cpu = task_cpu(p);
	struct sched_domain *sd = NULL;

	if (IS_ENABLED(CONFIG_SCHED_CASS))
		return;

	if (rq->misfit_task_load) {
		if (rq->curr->state != TASK_RUNNING ||
		    rq->curr->nr_cpus_allowed == 1)
			return;

		if (task_will_be_throttled(p))
			return;

		raw_spin_lock(&migration_lock);
		rcu_read_lock();
		new_cpu = find_energy_efficient_cpu(sd, p, cpu, prev_cpu,
						    0, false);
		rcu_read_unlock();
		if ((new_cpu != -1) &&
			(capacity_orig_of(new_cpu) > capacity_orig_of(cpu))) {
			active_balance = kick_active_balance(rq, p, new_cpu);
			if (active_balance) {
				mark_reserved(new_cpu);
				raw_spin_unlock(&migration_lock);
				stop_one_cpu_nowait(cpu,
					active_load_balance_cpu_stop, rq,
					&rq->active_balance_work);
				return;
			}
		} else {
			walt_check_for_rotation(rq);
		}
		raw_spin_unlock(&migration_lock);
	}
}

#endif /* CONFIG_SCHED_WALT */