sched_fair.c

Kernel code of linux kernel

{
}
#endif

static void
account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	update_load_add(&cfs_rq->load, se->load.weight);
	if (!parent_entity(se))
		inc_cpu_load(rq_of(cfs_rq), se->load.weight);
	if (entity_is_task(se))
		add_cfs_task_weight(cfs_rq, se->load.weight);
	cfs_rq->nr_running++;
	se->on_rq = 1;
	list_add(&se->group_node, &cfs_rq->tasks);
}

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))
		dec_cpu_load(rq_of(cfs_rq), se->load.weight);
	if (entity_is_task(se))
		add_cfs_task_weight(cfs_rq, -se->load.weight);
	cfs_rq->nr_running--;
	se->on_rq = 0;
	list_del_init(&se->group_node);
}

static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_SCHEDSTATS
	if (se->sleep_start) {
		u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
		struct task_struct *tsk = task_of(se);

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

		if (unlikely(delta > se->sleep_max))
			se->sleep_max = delta;

		se->sleep_start = 0;
		se->sum_sleep_runtime += delta;

		account_scheduler_latency(tsk, delta >> 10, 1);
	}
	if (se->block_start) {
		u64 delta = rq_of(cfs_rq)->clock - se->block_start;
		struct task_struct *tsk = task_of(se);

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

		if (unlikely(delta > se->block_max))
			se->block_max = delta;

		se->block_start = 0;
		se->sum_sleep_runtime += delta;

		/*
		 * Blocking time is in units of nanosecs, so shift by 20 to
		 * get a milliseconds-range estimation of the amount of
		 * time that the task spent sleeping:
		 */
		if (unlikely(prof_on == SLEEP_PROFILING)) {

			profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
				     delta >> 20);
		}
		account_scheduler_latency(tsk, delta >> 10, 0);
	}
#endif
}

static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_SCHED_DEBUG
	s64 d = se->vruntime - cfs_rq->min_vruntime;

	if (d < 0)
		d = -d;

	if (d > 3*sysctl_sched_latency)
		schedstat_inc(cfs_rq, nr_spread_over);
#endif
}

static void
place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
{
	u64 vruntime;

	if (first_fair(cfs_rq)) {
		vruntime = min_vruntime(cfs_rq->min_vruntime,
				__pick_next_entity(cfs_rq)->vruntime);
	} else
		vruntime = cfs_rq->min_vruntime;

	/*
	 * The 'current' period is already promised to the current tasks,
	 * however the extra weight of the new task will slow them down a
	 * little, place the new task so that it fits in the slot that
	 * stays open at the end.
	 */
	if (initial && sched_feat(START_DEBIT))
		vruntime += sched_vslice_add(cfs_rq, se);

	if (!initial) {
		/* sleeps upto a single latency don't count. */
		if (sched_feat(NEW_FAIR_SLEEPERS)) {
			unsigned long thresh = sysctl_sched_latency;

			/*
			 * convert the sleeper threshold into virtual time
			 */
			if (sched_feat(NORMALIZED_SLEEPER))
				thresh = calc_delta_fair(thresh, se);

			vruntime -= thresh;
		}

		/* ensure we never gain time by being placed backwards. */
		vruntime = max_vruntime(se->vruntime, vruntime);
	}

	se->vruntime = vruntime;
}

static void
enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
{
	/*
	 * Update run-time statistics of the 'current'.
	 */
	update_curr(cfs_rq);
	account_entity_enqueue(cfs_rq, se);

	if (wakeup) {
		place_entity(cfs_rq, se, 0);
		enqueue_sleeper(cfs_rq, se);
	}

	update_stats_enqueue(cfs_rq, se);
	check_spread(cfs_rq, se);
	if (se != cfs_rq->curr)
		__enqueue_entity(cfs_rq, se);
}

static void
dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
{
	/*
	 * Update run-time statistics of the 'current'.
	 */
	update_curr(cfs_rq);

	update_stats_dequeue(cfs_rq, se);
	if (sleep) {
#ifdef CONFIG_SCHEDSTATS
		if (entity_is_task(se)) {
			struct task_struct *tsk = task_of(se);

			if (tsk->state & TASK_INTERRUPTIBLE)
				se->sleep_start = rq_of(cfs_rq)->clock;
			if (tsk->state & TASK_UNINTERRUPTIBLE)
				se->block_start = rq_of(cfs_rq)->clock;
		}
#endif
	}

	if (se != cfs_rq->curr)
		__dequeue_entity(cfs_rq, se);
	account_entity_dequeue(cfs_rq, se);
}

/*
 * Preempt the current task with a newly woken task if needed:
 */
static void
check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
	unsigned long ideal_runtime, delta_exec;

	ideal_runtime = sched_slice(cfs_rq, curr);
	delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
	if (delta_exec > ideal_runtime)
		resched_task(rq_of(cfs_rq)->curr);
}

static void
set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	/* 'current' is not kept within the tree. */
	if (se->on_rq) {
		/*
		 * Any task has to be enqueued before it get to execute on
		 * a CPU. So account for the time it spent waiting on the
		 * runqueue.
		 */
		update_stats_wait_end(cfs_rq, se);
		__dequeue_entity(cfs_rq, se);
	}

	update_stats_curr_start(cfs_rq, se);
	cfs_rq->curr = se;
#ifdef CONFIG_SCHEDSTATS
	/*
	 * Track our maximum slice length, if the CPU's load is at
	 * least twice that of our own weight (i.e. dont track it
	 * when there are only lesser-weight tasks around):
	 */
	if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
		se->slice_max = max(se->slice_max,
			se->sum_exec_runtime - se->prev_sum_exec_runtime);
	}
#endif
	se->prev_sum_exec_runtime = se->sum_exec_runtime;
}

static struct sched_entity *
pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	struct rq *rq = rq_of(cfs_rq);
	u64 pair_slice = rq->clock - cfs_rq->pair_start;

	if (!cfs_rq->next || pair_slice > sched_slice(cfs_rq, cfs_rq->next)) {
		cfs_rq->pair_start = rq->clock;
		return se;
	}

	return cfs_rq->next;
}

static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
	struct sched_entity *se = NULL;

	if (first_fair(cfs_rq)) {
		se = __pick_next_entity(cfs_rq);
		se = pick_next(cfs_rq, se);
		set_next_entity(cfs_rq, se);
	}

	return se;
}

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);

	check_spread(cfs_rq, prev);
	if (prev->on_rq) {
		update_stats_wait_start(cfs_rq, prev);
		/* Put 'current' back into the tree. */
		__enqueue_entity(cfs_rq, prev);
	}
	cfs_rq->curr = NULL;
}

static void
entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
{
	/*
	 * Update run-time statistics of the 'current'.
	 */
	update_curr(cfs_rq);

#ifdef CONFIG_SCHED_HRTICK
	/*
	 * queued ticks are scheduled to match the slice, so don't bother
	 * validating it and just reschedule.
	 */
	if (queued) {
		resched_task(rq_of(cfs_rq)->curr);
		return;
	}
	/*
	 * don't let the period tick interfere with the hrtick preemption
	 */
	if (!sched_feat(DOUBLE_TICK) &&
			hrtimer_active(&rq_of(cfs_rq)->hrtick_timer))
		return;
#endif

	if (cfs_rq->nr_running > 1 || !sched_feat(WAKEUP_PREEMPT))
		check_preempt_tick(cfs_rq, curr);
}

/**************************************************
 * CFS operations on tasks:
 */

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

	WARN_ON(task_rq(p) != rq);

	if (hrtick_enabled(rq) && cfs_rq->nr_running > 1) {
		u64 slice = sched_slice(cfs_rq, se);
		u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime;
		s64 delta = slice - ran;

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

		/*
		 * Don't schedule slices shorter than 10000ns, that just
		 * doesn't make sense. Rely on vruntime for fairness.
		 */
		if (rq->curr != p)
			delta = max_t(s64, 10000LL, delta);

		hrtick_start(rq, delta);
	}
}
#else /* !CONFIG_SCHED_HRTICK */
static inline void
hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
}
#endif

/*
 * The enqueue_task method is called before nr_running is
 * increased. Here we update the fair scheduling stats and
 * then put the task into the rbtree:
 */
static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
{
	struct cfs_rq *cfs_rq;
	struct sched_entity *se = &p->se;

	for_each_sched_entity(se) {
		if (se->on_rq)
			break;
		cfs_rq = cfs_rq_of(se);
		enqueue_entity(cfs_rq, se, wakeup);
		wakeup = 1;
	}

	hrtick_start_fair(rq, rq->curr);
}

/*
 * 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 sleep)
{
	struct cfs_rq *cfs_rq;
	struct sched_entity *se = &p->se;

	for_each_sched_entity(se) {
		cfs_rq = cfs_rq_of(se);
		dequeue_entity(cfs_rq, se, sleep);
		/* Don't dequeue parent if it has other entities besides us */
		if (cfs_rq->load.weight)
			break;
		sleep = 1;
	}

	hrtick_start_fair(rq, rq->curr);
}

/*
 * sched_yield() support is very simple - we dequeue and enqueue.
 *
 * If compat_yield is turned on then we requeue to the end of the tree.
 */
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 *rightmost, *se = &curr->se;

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

	if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
		update_rq_clock(rq);
		/*
		 * Update run-time statistics of the 'current'.
		 */
		update_curr(cfs_rq);

		return;
	}
	/*
	 * Find the rightmost entry in the rbtree:
	 */
	rightmost = __pick_last_entity(cfs_rq);
	/*
	 * Already in the rightmost position?
	 */
	if (unlikely(!rightmost || rightmost->vruntime < se->vruntime))
		return;

	/*
	 * Minimally necessary key value to be last in the tree:
	 * Upon rescheduling, sched_class::put_prev_task() will place
	 * 'current' within the tree based on its new key value.
	 */
	se->vruntime = rightmost->vruntime + 1;
}

/*
 * wake_idle() will wake a task on an idle cpu if task->cpu is
 * not idle and an idle cpu is available.  The span of cpus to
 * search starts with cpus closest then further out as needed,
 * so we always favor a closer, idle cpu.
 * Domains may include CPUs that are not usable for migration,
 * hence we need to mask them out (cpu_active_map)
 *
 * Returns the CPU we should wake onto.
 */
#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
static int wake_idle(int cpu, struct task_struct *p)
{
	cpumask_t tmp;
	struct sched_domain *sd;
	int i;

	/*
	 * If it is idle, then it is the best cpu to run this task.
	 *
	 * This cpu is also the best, if it has more than one task already.
	 * Siblings must be also busy(in most cases) as they didn't already
	 * pickup the extra load from this cpu and hence we need not check
	 * sibling runqueue info. This will avoid the checks and cache miss
	 * penalities associated with that.
	 */
	if (idle_cpu(cpu) || cpu_rq(cpu)->cfs.nr_running > 1)
		return cpu;

	for_each_domain(cpu, sd) {
		if ((sd->flags & SD_WAKE_IDLE)
		    || ((sd->flags & SD_WAKE_IDLE_FAR)
			&& !task_hot(p, task_rq(p)->clock, sd))) {
			cpus_and(tmp, sd->span, p->cpus_allowed);
			cpus_and(tmp, tmp, cpu_active_map);
			for_each_cpu_mask_nr(i, tmp) {
				if (idle_cpu(i)) {
					if (i != task_cpu(p)) {
						schedstat_inc(p,
						       se.nr_wakeups_idle);
					}
					return i;
				}
			}
		} else {
			break;
		}
	}
	return cpu;
}
#else /* !ARCH_HAS_SCHED_WAKE_IDLE*/
static inline int wake_idle(int cpu, struct task_struct *p)
{
	return cpu;
}
#endif

#ifdef CONFIG_SMP

static const struct sched_class fair_sched_class;

#ifdef CONFIG_FAIR_GROUP_SCHED
/*
 * effective_load() calculates the load change as seen from the root_task_group
 *
 * Adding load to a group doesn't make a group heavier, but can cause movement
 * of group shares between cpus. Assuming the shares were perfectly aligned one
 * can calculate the shift in shares.
 *
 * The problem is that perfectly aligning the shares is rather expensive, hence
 * we try to avoid doing that too often - see update_shares(), which ratelimits
 * this change.
 *
 * We compensate this by not only taking the current delta into account, but
 * also considering the delta between when the shares were last adjusted and
 * now.
 *
 * We still saw a performance dip, some tracing learned us that between
 * cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased
 * significantly. Therefore try to bias the error in direction of failing
 * the affine wakeup.
 *
 */
static long effective_load(struct task_group *tg, int cpu,
		long wl, long wg)
{
	struct sched_entity *se = tg->se[cpu];
	long more_w;

	if (!tg->parent)
		return wl;

	/*
	 * By not taking the decrease of shares on the other cpu into
	 * account our error leans towards reducing the affine wakeups.
	 */
	if (!wl && sched_feat(ASYM_EFF_LOAD))
		return wl;

	/*
	 * Instead of using this increment, also add the difference
	 * between when the shares were last updated and now.
	 */
	more_w = se->my_q->load.weight - se->my_q->rq_weight;
	wl += more_w;
	wg += more_w;

	for_each_sched_entity(se) {
#define D(n) (likely(n) ? (n) : 1)

		long S, rw, s, a, b;

		S = se->my_q->tg->shares;
		s = se->my_q->shares;
		rw = se->my_q->rq_weight;

		a = S*(rw + wl);
		b = S*rw + s*wg;

		wl = s*(a-b)/D(b);
		/*
		 * Assume the group is already running and will
		 * thus already be accounted for in the weight.
		 *
		 * That is, moving shares between CPUs, does not
		 * alter the group weight.
		 */
		wg = 0;
#undef D
	}

	return wl;
}

#else

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

#endif

static int
wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
	    struct task_struct *p, int prev_cpu, int this_cpu, int sync,
	    int idx, unsigned long load, unsigned long this_load,
	    unsigned int imbalance)
{
	struct task_struct *curr = this_rq->curr;
	struct task_group *tg;
	unsigned long tl = this_load;
	unsigned long tl_per_task;
	unsigned long weight;
	int balanced;