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

static void __sched __schedule(void)
{
        ...
        if (unlikely(!rq->nr_running))
                idle_balance(cpu, rq);

        ...
}

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

	this_rq->idle_stamp = rq_clock(this_rq);

    /* 如果该CPU平均空闲时间小于/proc中的配置值或者该cpu调度域中所有cpu都是idle状态，那么不需要负载均衡了*/
	if (this_rq->avg_idle < sysctl_sched_migration_cost ||
	    !this_rq->rd->overload) {
		rcu_read_lock();
		sd = rcu_dereference_check_sched_domain(this_rq->sd);
		if (sd)
			update_next_balance(sd, 0, &next_balance);
		rcu_read_unlock();

		goto out;
	}

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

	update_blocked_averages(this_cpu);
	rcu_read_lock();
    /* 从底向上遍历调度域，只要迁移成功一个进程就跳出循环*/
	for_each_domain(this_cpu, sd) {
		int should_balance;
		u64 t0, domain_cost;

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

        /* 
         * 如果（当前累积的负载均衡开销时间 + 历史上该层级负载均衡开销最大值）已经大于CPU平均空闲时间了，
         * 那么就没有必要负载均衡了。注意，sd->max_newidle_lb_cost会在load_balance()函数中缓慢减少。
         */
		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) {
			update_next_balance(sd, 0, &next_balance);
			break;
		}

        /* 我的机器上该标记总是设置了SD_BALANCE_NEWIDLE */
		if (sd->flags & SD_BALANCE_NEWIDLE) {
			t0 = sched_clock_cpu(this_cpu);

			pulled_task = load_balance(this_cpu, this_rq,
						   sd, CPU_NEWLY_IDLE,
						   &should_balance);
           
			domain_cost = sched_clock_cpu(this_cpu) - t0;
			if (domain_cost > sd->max_newidle_lb_cost)
				sd->max_newidle_lb_cost = domain_cost;

           /* 记录了当前负载均衡开销累计值 */
			curr_cost += domain_cost;
		}

		update_next_balance(sd, 0, &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) {
			this_rq->idle_stamp = 0;
			break;
		}
	}
	rcu_read_unlock();

	raw_spin_lock(&this_rq->lock);

out:
	/* Move the next balance forward */
	if (time_after(this_rq->next_balance, next_balance))
		this_rq->next_balance = next_balance;

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

/*
 * sched_balance_self: balance the current task (running on cpu) in domains
 * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
 * SD_BALANCE_EXEC.
 *
 * Balance, ie. select the least loaded group.
 *
 * Returns the target CPU number, or the same CPU if no balancing is needed.
 *
 * preempt must be disabled.
 */
/* A进程给自己或者B进程选择一个CPU运行，
 * 1: A唤醒B
 * 2: A fork()出B后让B运行
 * 3: A execute()后重新选择自己将要运行的CPU
 */ 
static int
select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
{
	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
	int cpu = smp_processor_id();
	int new_cpu = cpu;
	int want_affine = 0;
	int sync = wake_flags & WF_SYNC;

    /* 当A进程唤醒B进程时，从try_to_wake_up()进入本函数，这里会置位SD_BALANCE_WAKE。 */
	if (sd_flag & SD_BALANCE_WAKE) {
        /* B进程被唤醒时希望运行的CPU尽可能离A进程所在CPU近一点 */
		if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
			want_affine = 1;
		new_cpu = prev_cpu;
		record_wakee(p);
	}

	rcu_read_lock();
    /* 
     * 如果是A唤醒B模式，则查找同时包含A所在cpu和B睡眠前所在prev_cpu的最低级别的调度域。因为A进程
     * 和B进程大概率会有某种数据交换关系，唤醒B时让它们所在的CPU离的近一点会性能最优。
     * 否则，查找包含了sd_flag的最高调度域。
     */
	for_each_domain(cpu, tmp) {
		if (!(tmp->flags & SD_LOAD_BALANCE))
			continue;

		/*
		 * If both cpu and prev_cpu are part of this domain,
		 * cpu is a valid SD_WAKE_AFFINE target.
		 */        
		if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
		    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
			affine_sd = tmp;
			break;
		}

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

    /* 如果是A唤醒B模式，则在同时包含A所在cpu和B睡眠前所在prev_cpu的最低级别的调度域中寻找合适的CPU */
	if (affine_sd) {
       /* 
        * wake_affine()计算A所在CPU和B睡眠前所在CPU的负载值，判断出B进程唤醒时是否
        * 需要离A近一点。
        */
		if (cpu != prev_cpu && wake_affine(affine_sd, p, sync))
			prev_cpu = cpu;

       /* 在与prev_cpu共享LLC的CPU中寻找空闲CPU，如果没有找到，则返回prev_cpu。这里将确定
        * B进程唤醒后在哪个CPU运行。
        */
		new_cpu = select_idle_sibling(p, prev_cpu);
		goto unlock;
	}

    /* 到这里，A进程和B进程基本是没有啥亲缘关系的。不用考虑两个进程的Cache亲缘性 */
	while (sd) {
		int load_idx = sd->forkexec_idx;
		struct sched_group *group;
		int weight;

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

		if (sd_flag & SD_BALANCE_WAKE)
			load_idx = sd->wake_idx;

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

		new_cpu = find_idlest_cpu(group, p, cpu);
		if (new_cpu == -1 || new_cpu == cpu) {
			/* Now try balancing at a lower domain level of cpu */
			sd = sd->child;
			continue;
		}

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

	return new_cpu;
}

/*
 * Try and locate an idle CPU in the sched_domain.
 */
 /* 寻找离target CPU最近的空闲CPU(Cache或者内存距离最近)*/
static int select_idle_sibling(struct task_struct *p, int target)
{
	struct sched_domain *sd;
	struct sched_group *sg;
	int i = task_cpu(p);
    
    /* target CPU正好空闲，自己跟自己当然最近*/
	if (idle_cpu(target))
		return target;

	/*
	 * If the prevous cpu is cache affine and idle, don't be stupid.
	 */
    /* 
     * p进程所在的CPU跟target CPU有Cache共享关系(SMT,或者MC层才有这个关系)，并且是空闲的，那就用它了。
     * Cache共享说明距离很近了 
     */
	if (i != target && cpus_share_cache(i, target) && idle_cpu(i))
		return i;

	/*
	 * Otherwise, iterate the domains and find an elegible idle cpu.
	 */
    /*
     * 在与target CPU有LLC Cache共享关系的调度域中寻找空闲CPU。注意，在X86体系中只有SMT和MC层的调度域才有Cache共享。
     */
	sd = rcu_dereference(per_cpu(sd_llc, target));    
    /* 在我的机器上是按MC，SMT调度域顺序遍历 */
	for_each_lower_domain(sd) {
		sg = sd->groups;
		do {
			if (!cpumask_intersects(sched_group_cpus(sg),
						tsk_cpus_allowed(p)))
				goto next;

           /* 调度组内所有CPU都是空闲状态，才能选定 */
			for_each_cpu(i, sched_group_cpus(sg)) {
				if (i == target || !idle_cpu(i))
					goto next;
			}

           /* 选择全部CPU都空闲的调度组中第一个CPU*/
			target = cpumask_first_and(sched_group_cpus(sg),
					tsk_cpus_allowed(p));
			goto done;
next:
			sg = sg->next;
		} while (sg != sd->groups);
	}
done:
	return target;
}

/*
 * sched_exec - execve() is a valuable balancing opportunity, because at
 * this point the task has the smallest effective memory and cache footprint.
 */
void sched_exec(void)
{
	struct task_struct *p = current;
	unsigned long flags;
	int dest_cpu;

	raw_spin_lock_irqsave(&p->pi_lock, flags);
    /* 选择最合适的CPU，这里由于进程execve()后，之前的Cache就无意义了，因此选择目标CPU不用考虑Cache距离 */
	dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0);
	if (dest_cpu == smp_processor_id())
		goto unlock;

	if (likely(cpu_active(dest_cpu))) {
		struct migration_arg arg = { p, dest_cpu };

		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
		stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
		return;
	}
unlock:
	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
}

/*
 * wake_up_new_task - wake up a newly created task for the first time.
 *
 * This function will do some initial scheduler statistics housekeeping
 * that must be done for every newly created context, then puts the task
 * on the runqueue and wakes it.
 */
void wake_up_new_task(struct task_struct *p)
{
	unsigned long flags;
	struct rq *rq;

	raw_spin_lock_irqsave(&p->pi_lock, flags);
#ifdef CONFIG_SMP
	/*
	 * Fork balancing, do it here and not earlier because:
	 *  - cpus_allowed can change in the fork path
	 *  - any previously selected cpu might disappear through hotplug
	 */
    /* 选择最合适的CPU，这里由于进程execve()后，之前的Cache就无意义了，因此选择目标CPU不用考虑Cache距离 */
	set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
#endif

	/* Initialize new task's runnable average */
	init_task_runnable_average(p);
	rq = __task_rq_lock(p);
	activate_task(rq, p, 0);
	p->on_rq = TASK_ON_RQ_QUEUED;
	trace_sched_wakeup_new(p, true);
	check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
	if (p->sched_class->task_woken)
		p->sched_class->task_woken(rq, p);
#endif
	task_rq_unlock(rq, p, &flags);
}