sched.c

Kernel code of linux kernel

		hrtick_clear(cpu_rq(cpu));
		return NOTIFY_OK;
	}

	return NOTIFY_DONE;
}

static __init void init_hrtick(void)
{
	hotcpu_notifier(hotplug_hrtick, 0);
}
#else
/*
 * Called to set the hrtick timer state.
 *
 * called with rq->lock held and irqs disabled
 */
static void hrtick_start(struct rq *rq, u64 delay)
{
	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL);
}

static void init_hrtick(void)
{
}
#endif /* CONFIG_SMP */

static void init_rq_hrtick(struct rq *rq)
{
#ifdef CONFIG_SMP
	rq->hrtick_csd_pending = 0;

	rq->hrtick_csd.flags = 0;
	rq->hrtick_csd.func = __hrtick_start;
	rq->hrtick_csd.info = rq;
#endif

	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
	rq->hrtick_timer.function = hrtick;
	rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
}
#else
static inline void hrtick_clear(struct rq *rq)
{
}

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

static inline void init_hrtick(void)
{
}
#endif

/*
 * resched_task - mark a task 'to be rescheduled now'.
 *
 * On UP this means the setting of the need_resched flag, on SMP it
 * might also involve a cross-CPU call to trigger the scheduler on
 * the target CPU.
 */
#ifdef CONFIG_SMP

#ifndef tsk_is_polling
#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
#endif

static void resched_task(struct task_struct *p)
{
	int cpu;

	assert_spin_locked(&task_rq(p)->lock);

	if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
		return;

	set_tsk_thread_flag(p, TIF_NEED_RESCHED);

	cpu = task_cpu(p);
	if (cpu == smp_processor_id())
		return;

	/* NEED_RESCHED must be visible before we test polling */
	smp_mb();
	if (!tsk_is_polling(p))
		smp_send_reschedule(cpu);
}

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

	if (!spin_trylock_irqsave(&rq->lock, flags))
		return;
	resched_task(cpu_curr(cpu));
	spin_unlock_irqrestore(&rq->lock, flags);
}

#ifdef CONFIG_NO_HZ
/*
 * When add_timer_on() enqueues a timer into the timer wheel of an
 * idle CPU then this timer might expire before the next timer event
 * which is scheduled to wake up that CPU. In case of a completely
 * idle system the next event might even be infinite time into the
 * future. wake_up_idle_cpu() ensures that the CPU is woken up and
 * leaves the inner idle loop so the newly added timer is taken into
 * account when the CPU goes back to idle and evaluates the timer
 * wheel for the next timer event.
 */
void wake_up_idle_cpu(int cpu)
{
	struct rq *rq = cpu_rq(cpu);

	if (cpu == smp_processor_id())
		return;

	/*
	 * This is safe, as this function is called with the timer
	 * wheel base lock of (cpu) held. When the CPU is on the way
	 * to idle and has not yet set rq->curr to idle then it will
	 * be serialized on the timer wheel base lock and take the new
	 * timer into account automatically.
	 */
	if (rq->curr != rq->idle)
		return;

	/*
	 * We can set TIF_RESCHED on the idle task of the other CPU
	 * lockless. The worst case is that the other CPU runs the
	 * idle task through an additional NOOP schedule()
	 */
	set_tsk_thread_flag(rq->idle, TIF_NEED_RESCHED);

	/* NEED_RESCHED must be visible before we test polling */
	smp_mb();
	if (!tsk_is_polling(rq->idle))
		smp_send_reschedule(cpu);
}
#endif /* CONFIG_NO_HZ */

#else /* !CONFIG_SMP */
static void resched_task(struct task_struct *p)
{
	assert_spin_locked(&task_rq(p)->lock);
	set_tsk_need_resched(p);
}
#endif /* CONFIG_SMP */

#if BITS_PER_LONG == 32
# define WMULT_CONST	(~0UL)
#else
# define WMULT_CONST	(1UL << 32)
#endif

#define WMULT_SHIFT	32

/*
 * Shift right and round:
 */
#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))

/*
 * delta *= weight / lw
 */
static unsigned long
calc_delta_mine(unsigned long delta_exec, unsigned long weight,
		struct load_weight *lw)
{
	u64 tmp;

	if (!lw->inv_weight) {
		if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST))
			lw->inv_weight = 1;
		else
			lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)
				/ (lw->weight+1);
	}

	tmp = (u64)delta_exec * weight;
	/*
	 * Check whether we'd overflow the 64-bit multiplication:
	 */
	if (unlikely(tmp > WMULT_CONST))
		tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
			WMULT_SHIFT/2);
	else
		tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT);

	return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
}

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;
}

/*
 * To aid in avoiding the subversion of "niceness" due to uneven distribution
 * of tasks with abnormal "nice" values across CPUs the contribution that
 * each task makes to its run queue's load is weighted according to its
 * scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a
 * scaled version of the new time slice allocation that they receive on time
 * slice expiry etc.
 */

#define WEIGHT_IDLEPRIO		2
#define WMULT_IDLEPRIO		(1 << 31)

/*
 * Nice levels are multiplicative, with a gentle 10% change for every
 * nice level changed. I.e. when a CPU-bound task goes from nice 0 to
 * nice 1, it will get ~10% less CPU time than another CPU-bound task
 * that remained on nice 0.
 *
 * The "10% effect" is relative and cumulative: from _any_ nice level,
 * if you go up 1 level, it's -10% CPU usage, if you go down 1 level
 * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
 * If a task goes up by ~10% and another task goes down by ~10% then
 * the relative distance between them is ~25%.)
 */
static const int prio_to_weight[40] = {
 /* -20 */     88761,     71755,     56483,     46273,     36291,
 /* -15 */     29154,     23254,     18705,     14949,     11916,
 /* -10 */      9548,      7620,      6100,      4904,      3906,
 /*  -5 */      3121,      2501,      1991,      1586,      1277,
 /*   0 */      1024,       820,       655,       526,       423,
 /*   5 */       335,       272,       215,       172,       137,
 /*  10 */       110,        87,        70,        56,        45,
 /*  15 */        36,        29,        23,        18,        15,
};

/*
 * Inverse (2^32/x) values of the prio_to_weight[] array, precalculated.
 *
 * In cases where the weight does not change often, we can use the
 * precalculated inverse to speed up arithmetics by turning divisions
 * into multiplications:
 */
static const u32 prio_to_wmult[40] = {
 /* -20 */     48388,     59856,     76040,     92818,    118348,
 /* -15 */    147320,    184698,    229616,    287308,    360437,
 /* -10 */    449829,    563644,    704093,    875809,   1099582,
 /*  -5 */   1376151,   1717300,   2157191,   2708050,   3363326,
 /*   0 */   4194304,   5237765,   6557202,   8165337,  10153587,
 /*   5 */  12820798,  15790321,  19976592,  24970740,  31350126,
 /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
 /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
};

static void activate_task(struct rq *rq, struct task_struct *p, int wakeup);

/*
 * runqueue iterator, to support SMP load-balancing between different
 * scheduling classes, without having to expose their internal data
 * structures to the load-balancing proper:
 */
struct rq_iterator {
	void *arg;
	struct task_struct *(*start)(void *);
	struct task_struct *(*next)(void *);
};

#ifdef CONFIG_SMP
static unsigned long
balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
	      unsigned long max_load_move, struct sched_domain *sd,
	      enum cpu_idle_type idle, int *all_pinned,
	      int *this_best_prio, struct rq_iterator *iterator);

static int
iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
		   struct sched_domain *sd, enum cpu_idle_type idle,
		   struct rq_iterator *iterator);
#endif

#ifdef CONFIG_CGROUP_CPUACCT
static void cpuacct_charge(struct task_struct *tsk, u64 cputime);
#else
static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
#endif

static inline void inc_cpu_load(struct rq *rq, unsigned long load)
{
	update_load_add(&rq->load, load);
}

static inline void dec_cpu_load(struct rq *rq, unsigned long load)
{
	update_load_sub(&rq->load, load);
}

#ifdef CONFIG_SMP
static unsigned long source_load(int cpu, int type);
static unsigned long target_load(int cpu, int type);
static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);

static unsigned long cpu_avg_load_per_task(int cpu)
{
	struct rq *rq = cpu_rq(cpu);

	if (rq->nr_running)
		rq->avg_load_per_task = rq->load.weight / rq->nr_running;

	return rq->avg_load_per_task;
}

#ifdef CONFIG_FAIR_GROUP_SCHED

typedef void (*tg_visitor)(struct task_group *, int, struct sched_domain *);

/*
 * Iterate the full tree, calling @down when first entering a node and @up when
 * leaving it for the final time.
 */
static void
walk_tg_tree(tg_visitor down, tg_visitor up, int cpu, struct sched_domain *sd)
{
	struct task_group *parent, *child;

	rcu_read_lock();
	parent = &root_task_group;
down:
	(*down)(parent, cpu, sd);
	list_for_each_entry_rcu(child, &parent->children, siblings) {
		parent = child;
		goto down;

up:
		continue;
	}
	(*up)(parent, cpu, sd);

	child = parent;
	parent = parent->parent;
	if (parent)
		goto up;
	rcu_read_unlock();
}

static void __set_se_shares(struct sched_entity *se, unsigned long shares);

/*
 * Calculate and set the cpu's group shares.
 */
static void
__update_group_shares_cpu(struct task_group *tg, int cpu,
			  unsigned long sd_shares, unsigned long sd_rq_weight)
{
	int boost = 0;
	unsigned long shares;
	unsigned long rq_weight;

	if (!tg->se[cpu])
		return;

	rq_weight = tg->cfs_rq[cpu]->load.weight;

	/*
	 * If there are currently no tasks on the cpu pretend there is one of
	 * average load so that when a new task gets to run here it will not
	 * get delayed by group starvation.
	 */
	if (!rq_weight) {
		boost = 1;
		rq_weight = NICE_0_LOAD;
	}

	if (unlikely(rq_weight > sd_rq_weight))
		rq_weight = sd_rq_weight;

	/*
	 *           \Sum shares * rq_weight
	 * shares =  -----------------------
	 *               \Sum rq_weight
	 *
	 */
	shares = (sd_shares * rq_weight) / (sd_rq_weight + 1);

	/*
	 * record the actual number of shares, not the boosted amount.
	 */
	tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
	tg->cfs_rq[cpu]->rq_weight = rq_weight;

	if (shares < MIN_SHARES)
		shares = MIN_SHARES;
	else if (shares > MAX_SHARES)
		shares = MAX_SHARES;

	__set_se_shares(tg->se[cpu], shares);
}

/*
 * Re-compute the task group their per cpu shares over the given domain.
 * This needs to be done in a bottom-up fashion because the rq weight of a
 * parent group depends on the shares of its child groups.
 */
static void
tg_shares_up(struct task_group *tg, int cpu, struct sched_domain *sd)
{
	unsigned long rq_weight = 0;
	unsigned long shares = 0;
	int i;

	for_each_cpu_mask(i, sd->span) {
		rq_weight += tg->cfs_rq[i]->load.weight;
		shares += tg->cfs_rq[i]->shares;
	}

	if ((!shares && rq_weight) || shares > tg->shares)
		shares = tg->shares;

	if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE))
		shares = tg->shares;

	if (!rq_weight)
		rq_weight = cpus_weight(sd->span) * NICE_0_LOAD;

	for_each_cpu_mask(i, sd->span) {
		struct rq *rq = cpu_rq(i);
		unsigned long flags;

		spin_lock_irqsave(&rq->lock, flags);
		__update_group_shares_cpu(tg, i, shares, rq_weight);
		spin_unlock_irqrestore(&rq->lock, flags);
	}
}

/*
 * Compute the cpu's hierarchical load factor for each task group.
 * 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
tg_load_down(struct task_group *tg, int cpu, struct sched_domain *sd)
{
	unsigned long load;

	if (!tg->parent) {
		load = cpu_rq(cpu)->load.weight;
	} else {
		load = tg->parent->cfs_rq[cpu]->h_load;
		load *= tg->cfs_rq[cpu]->shares;
		load /= tg->parent->cfs_rq[cpu]->load.weight + 1;
	}

	tg->cfs_rq[cpu]->h_load = load;
}

static void
tg_nop(struct task_group *tg, int cpu, struct sched_domain *sd)
{
}

static void update_shares(struct sched_domain *sd)
{
	u64 now = cpu_clock(raw_smp_processor_id());
	s64 elapsed = now - sd->last_update;

	if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
		sd->last_update = now;
		walk_tg_tree(tg_nop, tg_shares_up, 0, sd);
	}
}

static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
{
	spin_unlock(&rq->lock);
	update_shares(sd);
	spin_lock(&rq->lock);
}

static void update_h_load(int cpu)
{
	walk_tg_tree(tg_load_down, tg_nop, cpu, NULL);
}

#else

static inline void update_shares(struct sched_domain *sd)
{
}

static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd)
{
}

#endif

#endif

#ifdef CONFIG_FAIR_GROUP_SCHED
static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
{
#ifdef CONFIG_SMP
	cfs_rq->shares = shares;
#endif
}
#endif

#include "sched_stats.h"
#include "sched_idletask.c"
#include "sched_fair.c"
#include "sched_rt.c"
#ifdef CONFIG_SCHED_DEBUG
# include "sched_debug.c"
#endif

#define sched_class_highest (&rt_sched_class)
#define for_each_class(class) \
   for (class = sched_class_highest; class; class = class->next)

static void inc_nr_running(struct rq *rq)
{
	rq->nr_running++;
}

static void dec_nr_running(struct rq *rq)
{
	rq->nr_running--;
}

static void set_load_weight(struct task_struct *p)
{
	if (task_has_rt_policy(p)) {
		p->se.load.weight = prio_to_weight[0] * 2;
		p->se.load.inv_weight = prio_to_wmult[0] >> 1;
		return;
	}

	/*
	 * SCHED_IDLE tasks get minimal weight: