C++ cpu_rq函数代码示例

void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
		struct sched_rt_entity *rt_se, int cpu,
		struct sched_rt_entity *parent)
{
	struct rq *rq = cpu_rq(cpu);

	rt_rq->highest_prio.curr = MAX_RT_PRIO;
	rt_rq->rt_nr_boosted = 0;
	rt_rq->rq = rq;
	rt_rq->tg = tg;

	tg->rt_rq[cpu] = rt_rq;
	tg->rt_se[cpu] = rt_se;

	if (!rt_se)
		return;

	if (!parent)
		rt_se->rt_rq = &rq->rt;
	else
		rt_se->rt_rq = parent->my_q;

	rt_se->my_q = rt_rq;
	rt_se->parent = parent;
	INIT_LIST_HEAD(&rt_se->run_list);
}

void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
	s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,
		spread, rq0_min_vruntime, spread0;
	struct rq *rq = cpu_rq(cpu);
	struct sched_entity *last;
	unsigned long flags;

	SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "exec_clock",
			SPLIT_NS(cfs_rq->exec_clock));

	raw_spin_lock_irqsave(&rq->lock, flags);
	if (cfs_rq->rb_leftmost)
		MIN_vruntime = (__pick_next_entity(cfs_rq))->vruntime;
	last = __pick_last_entity(cfs_rq);
	if (last)
		max_vruntime = last->vruntime;
	min_vruntime = cfs_rq->min_vruntime;
	rq0_min_vruntime = cpu_rq(0)->cfs.min_vruntime;
	raw_spin_unlock_irqrestore(&rq->lock, flags);
	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "MIN_vruntime",
			SPLIT_NS(MIN_vruntime));
	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "min_vruntime",
			SPLIT_NS(min_vruntime));
	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "max_vruntime",
			SPLIT_NS(max_vruntime));
	spread = max_vruntime - MIN_vruntime;
	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "spread",
			SPLIT_NS(spread));
	spread0 = min_vruntime - rq0_min_vruntime;
	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "spread0",
			SPLIT_NS(spread0));
	SEQ_printf(m, "  .%-30s: %ld\n", "nr_running", cfs_rq->nr_running);
	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);

	SEQ_printf(m, "  .%-30s: %d\n", "nr_spread_over",
			cfs_rq->nr_spread_over);
#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_SMP
	SEQ_printf(m, "  .%-30s: %lu\n", "shares", cfs_rq->shares);
#endif
	print_cfs_group_stats(m, cpu, cfs_rq->tg);
#endif
}

void print_cfs_stats_at_KE(struct seq_file *m, int cpu)
{
	struct cfs_rq *cfs_rq;

	rcu_read_lock();
	for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
		print_cfs_rq_at_KE(m, cpu, cfs_rq);
	rcu_read_unlock();
}

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

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

/*
 * schedule() is the main scheduler function.
 */
asmlinkage void __sched schedule(void)
{
        struct task_struct *prev, *next;
        unsigned long *switch_count;
        struct rq *rq;
        int cpu;

need_resched:
        preempt_disable();
        cpu = smp_processor_id();
        rq = cpu_rq(cpu);
        rcu_sched_qs(cpu);
        prev = rq->curr;
        switch_count = &prev->nivcsw;

        release_kernel_lock(prev);
need_resched_nonpreemptible:

        schedule_debug(prev);

        if (sched_feat(HRTICK))
                hrtick_clear(rq);

        raw_spin_lock_irq(&rq->lock);
        update_rq_clock(rq);
        clear_tsk_need_resched(prev);

	        if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
                if (unlikely(signal_pending_state(prev->state, prev)))
                        prev->state = TASK_RUNNING;
                else
                        deactivate_task(rq, prev, 1);
                switch_count = &prev->nvcsw;
        }

        pre_schedule(rq, prev);

        if (unlikely(!rq->nr_running))
                idle_balance(cpu, rq);

        put_prev_task(rq, prev);
        next = pick_next_task(rq);

        if (likely(prev != next)) {
                sched_info_switch(prev, next);
                perf_event_task_sched_out(prev, next);

                rq->nr_switches++;
                rq->curr = next;
                ++*switch_count;

                context_switch(rq, prev, next); /* unlocks the rq */

/*
 * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
 * hold the hotplug lock.
 */
static void
cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	struct sched_domain *tmp;

	/* Remove the sched domains which do not contribute to scheduling. */
	for (tmp = sd; tmp; ) {
		struct sched_domain *parent = tmp->parent;
		if (!parent)
			break;

		if (sd_parent_degenerate(tmp, parent)) {
			tmp->parent = parent->parent;
			if (parent->parent)
				parent->parent->child = tmp;
			/*
			 * Transfer SD_PREFER_SIBLING down in case of a
			 * degenerate parent; the spans match for this
			 * so the property transfers.
			 */
			if (parent->flags & SD_PREFER_SIBLING)
				tmp->flags |= SD_PREFER_SIBLING;
			destroy_sched_domain(parent);
		} else
			tmp = tmp->parent;
	}

	if (sd && sd_degenerate(sd)) {
		tmp = sd;
		sd = sd->parent;
		destroy_sched_domain(tmp);
		if (sd)
			sd->child = NULL;
	}

	sched_domain_debug(sd, cpu);

	rq_attach_root(rq, rd);
	tmp = rq->sd;
	rcu_assign_pointer(rq->sd, sd);
	dirty_sched_domain_sysctl(cpu);
	destroy_sched_domains(tmp);

	update_top_cache_domain(cpu);
}

static int
hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
	int cpu = (int)(long)hcpu;

	switch (action) {
	case CPU_UP_CANCELED:
	case CPU_UP_CANCELED_FROZEN:
	case CPU_DOWN_PREPARE:
	case CPU_DOWN_PREPARE_FROZEN:
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		hrtick_clear(cpu_rq(cpu));
		return NOTIFY_OK;
	}

	return NOTIFY_DONE;
}

static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
{
	struct sched_entity *se = tg->se[cpu];

#define P(F) \
	SEQ_printf(m, "  .%-30s: %lld\n", #F, (long long)F)
#define PN(F) \
	SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F))

	if (!se) {
		struct sched_avg *avg = &cpu_rq(cpu)->avg;
		P(avg->runnable_avg_sum);
		P(avg->avg_period);
		return;
	}


	PN(se->exec_start);
	PN(se->vruntime);
	PN(se->sum_exec_runtime);
#ifdef CONFIG_SCHEDSTATS
	PN(se->statistics.wait_start);
	PN(se->statistics.sleep_start);
	PN(se->statistics.block_start);
	PN(se->statistics.sleep_max);
	PN(se->statistics.block_max);
	PN(se->statistics.exec_max);
	PN(se->statistics.slice_max);
	PN(se->statistics.wait_max);
	PN(se->statistics.wait_sum);
	P(se->statistics.wait_count);
#endif
	P(se->load.weight);
#ifdef CONFIG_SMP
	P(se->avg.runnable_avg_sum);
	P(se->avg.running_avg_sum);
	P(se->avg.avg_period);
	P(se->avg.load_avg_contrib);
	P(se->avg.utilization_avg_contrib);
	P(se->avg.decay_count);
#endif
#undef PN
#undef P
}

int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
{
	struct rt_rq *rt_rq;
	struct sched_rt_entity *rt_se;
	int i;

	tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL);
	if (!tg->rt_rq)
		goto err;
	tg->rt_se = kzalloc(sizeof(rt_se) * nr_cpu_ids, GFP_KERNEL);
	if (!tg->rt_se)
		goto err_free_rt_rq;

	init_rt_bandwidth(&tg->rt_bandwidth,
			ktime_to_ns(def_rt_bandwidth.rt_period), 0);

	for_each_possible_cpu(i) {
		rt_rq = kzalloc_node(sizeof(struct rt_rq),
				     GFP_KERNEL, cpu_to_node(i));
		if (!rt_rq)
			goto err_free_rt_se;

		rt_se = kzalloc_node(sizeof(struct sched_rt_entity),
				     GFP_KERNEL, cpu_to_node(i));
		if (!rt_se)
			goto err_free_rq;

		init_rt_rq(rt_rq, cpu_rq(i));
		rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
		init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]);
	}

	return 1;

err_free_rq:
	kfree(rt_rq);
err_free_rt_se:
	kfree(tg->rt_se);
err_free_rt_rq:
	kfree(tg->rt_rq);
err:
	return 0;
}

/*
 * schedule() is the main scheduler function.
 */
asmlinkage void __sched schedule(void)
{
    struct task_struct *prev, *next;
    unsigned long *switch_count;
    struct rq *rq;
    int cpu;

need_resched:
    preempt_disable();
    cpu = smp_processor_id();
    rq = cpu_rq(cpu);
    rcu_note_context_switch(cpu);
    prev = rq->curr;

    schedule_debug(prev);

    if (sched_feat(HRTICK))
        hrtick_clear(rq);

    raw_spin_lock_irq(&rq->lock);

    switch_count = &prev->nivcsw;
    if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
        if (unlikely(signal_pending_state(prev->state, prev))) {
            prev->state = TASK_RUNNING;
        } else {
            /*
             * If a worker is going to sleep, notify and
             * ask workqueue whether it wants to wake up a
             * task to maintain concurrency.  If so, wake
             * up the task.
             */
            if (prev->flags & PF_WQ_WORKER) {
                struct task_struct *to_wakeup;

                to_wakeup = wq_worker_sleeping(prev, cpu);
                if (to_wakeup)
                    try_to_wake_up_local(to_wakeup);
            }
            deactivate_task(rq, prev, DEQUEUE_SLEEP);

            /*
             * If we are going to sleep and we have plugged IO queued, make
             * sure to submit it to avoid deadlocks.
             */
            if (blk_needs_flush_plug(prev)) {
                raw_spin_unlock(&rq->lock);
                blk_schedule_flush_plug(prev);
                raw_spin_lock(&rq->lock);
            }
        }
        switch_count = &prev->nvcsw;
    }

    pre_schedule(rq, prev);

    if (unlikely(!rq->nr_running))
        idle_balance(cpu, rq);

    put_prev_task(rq, prev);
    next = pick_next_task(rq);
    clear_tsk_need_resched(prev);
    rq->skip_clock_update = 0;

    if (likely(prev != next)) {
        rq->nr_switches++;
        rq->curr = next;
        ++*switch_count;

        context_switch(rq, prev, next); /* unlocks the rq */
        /*
         * The context switch have flipped the stack from under us
         * and restored the local variables which were saved when
         * this task called schedule() in the past. prev == current
         * is still correct, but it can be moved to another cpu/rq.
         */
        cpu = smp_processor_id();
        rq = cpu_rq(cpu);
    } else
        raw_spin_unlock_irq(&rq->lock);

    post_schedule(rq);

    preempt_enable_no_resched();
    if (need_resched())
        goto need_resched;
}

static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
{
	return &cpu_rq(this_cpu)->cfs;
}

static void __sched notrace __schedule(bool preempt)
{
    struct task_struct *prev, *next;
    unsigned long *switch_count;
    struct rq *rq;
    int cpu;

    /*  ==1==  
        找到当前cpu上的就绪队列rq
        并将正在运行的进程curr保存到prev中  */
    cpu = smp_processor_id();
    rq = cpu_rq(cpu);
    prev = rq->curr;

    /*
     * do_exit() calls schedule() with preemption disabled as an exception;
     * however we must fix that up, otherwise the next task will see an
     * inconsistent (higher) preempt count.
     *
     * It also avoids the below schedule_debug() test from complaining
     * about this.
     */
    if (unlikely(prev->state == TASK_DEAD))
        preempt_enable_no_resched_notrace();
    
    /*  如果禁止内核抢占，而又调用了cond_resched就会出错
     *  这里就是用来捕获该错误的  */
    schedule_debug(prev);

    if (sched_feat(HRTICK))
        hrtick_clear(rq);

    /*  关闭本地中断  */
    local_irq_disable();

    /*  更新全局状态，
     *  标识当前CPU发生上下文的切换  */
    rcu_note_context_switch();

    /*
     * Make sure that signal_pending_state()->signal_pending() below
     * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
     * done by the caller to avoid the race with signal_wake_up().
     */
    smp_mb__before_spinlock();
    /*  锁住该队列  */
    raw_spin_lock(&rq->lock);
    lockdep_pin_lock(&rq->lock);

    rq->clock_skip_update <<= 1; /* promote REQ to ACT */

    /*  切换次数记录, 默认认为非主动调度计数(抢占)  */
    switch_count = &prev->nivcsw;
    
    /*
     *  scheduler检查prev的状态state和内核抢占表示
     *  如果prev是不可运行的, 并且在内核态没有被抢占
     *  
     *  此时当前进程不是处于运行态, 并且不是被抢占
     *  此时不能只检查抢占计数
     *  因为可能某个进程(如网卡轮询)直接调用了schedule
     *  如果不判断prev->stat就可能误认为task进程为RUNNING状态
     *  到达这里，有两种可能，一种是主动schedule, 另外一种是被抢占
     *  被抢占有两种情况, 一种是时间片到点, 一种是时间片没到点
     *  时间片到点后, 主要是置当前进程的need_resched标志
     *  接下来在时钟中断结束后, 会preempt_schedule_irq抢占调度
     *  
     *  那么我们正常应该做的是应该将进程prev从就绪队列rq中删除, 
     *  但是如果当前进程prev有非阻塞等待信号, 
     *  并且它的状态是TASK_INTERRUPTIBLE
     *  我们就不应该从就绪队列总删除它 
     *  而是配置其状态为TASK_RUNNING, 并且把他留在rq中

    /*  如果内核态没有被抢占, 并且内核抢占有效
        即是否同时满足以下条件：
        1  该进程处于停止状态
        2  该进程没有在内核态被抢占 */
    if (!preempt && prev->state)
    {

        /*  如果当前进程有非阻塞等待信号，并且它的状态是TASK_INTERRUPTIBLE  */
        if (unlikely(signal_pending_state(prev->state, prev)))
        {
            /*  将当前进程的状态设为：TASK_RUNNING  */
            prev->state = TASK_RUNNING;
        }
        else   /*  否则需要将prev进程从就绪队列中删除*/
        {
            /*  将当前进程从runqueue(运行队列)中删除  */
            deactivate_task(rq, prev, DEQUEUE_SLEEP);

            /*  标识当前进程不在runqueue中  */
            prev->on_rq = 0;

            /*
             * If a worker went to sleep, notify and ask workqueue
             * whether it wants to wake up a task to maintain
             * concurrency.
             */
            if (prev->flags & PF_WQ_WORKER) {
//.........这里部分代码省略.........

void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
	s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,
		spread, rq0_min_vruntime, spread0;
	struct rq *rq = cpu_rq(cpu);
	struct sched_entity *last;
	unsigned long flags;

#ifdef CONFIG_FAIR_GROUP_SCHED
	SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, task_group_path(cfs_rq->tg));
#else
	SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
#endif
	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "exec_clock",
			SPLIT_NS(cfs_rq->exec_clock));

	raw_spin_lock_irqsave(&rq->lock, flags);
	if (cfs_rq->rb_leftmost)
		MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime;
	last = __pick_last_entity(cfs_rq);
	if (last)
		max_vruntime = last->vruntime;
	min_vruntime = cfs_rq->min_vruntime;
	rq0_min_vruntime = cpu_rq(0)->cfs.min_vruntime;
	raw_spin_unlock_irqrestore(&rq->lock, flags);
	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "MIN_vruntime",
			SPLIT_NS(MIN_vruntime));
	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "min_vruntime",
			SPLIT_NS(min_vruntime));
	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "max_vruntime",
			SPLIT_NS(max_vruntime));
	spread = max_vruntime - MIN_vruntime;
	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "spread",
			SPLIT_NS(spread));
	spread0 = min_vruntime - rq0_min_vruntime;
	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "spread0",
			SPLIT_NS(spread0));
	SEQ_printf(m, "  .%-30s: %d\n", "nr_spread_over",
			cfs_rq->nr_spread_over);
	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_SMP
	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "load_avg",
			SPLIT_NS(cfs_rq->load_avg));
	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "load_period",
			SPLIT_NS(cfs_rq->load_period));
	SEQ_printf(m, "  .%-30s: %ld\n", "load_contrib",
			cfs_rq->load_contribution);
	SEQ_printf(m, "  .%-30s: %d\n", "load_tg",
			atomic_read(&cfs_rq->tg->load_weight));
#endif
#ifdef CONFIG_CFS_BANDWIDTH
	SEQ_printf(m, "  .%-30s: %d\n", "tg->cfs_bandwidth.timer_active",
			cfs_rq->tg->cfs_bandwidth.timer_active);
	SEQ_printf(m, "  .%-30s: %d\n", "throttled",
			cfs_rq->throttled);
	SEQ_printf(m, "  .%-30s: %d\n", "throttle_count",
			cfs_rq->throttle_count);
#endif

	print_cfs_group_stats(m, cpu, cfs_rq->tg);
#endif
}

static void print_cpu(struct seq_file *m, int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long flags;

#ifdef CONFIG_X86
	{
		unsigned int freq = cpu_khz ? : 1;

		SEQ_printf(m, "\ncpu#%d, %u.%03u MHz\n",
			   cpu, freq / 1000, (freq % 1000));
	}
#else
	SEQ_printf(m, "\ncpu#%d\n", cpu);
#endif

#define P(x) \
	SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rq->x))
#define PN(x) \
	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rq->x))

	P(nr_running);
	SEQ_printf(m, "  .%-30s: %lu\n", "load",
		   rq->load.weight);
	P(nr_switches);
	P(nr_load_updates);
	P(nr_uninterruptible);
	PN(next_balance);
	P(curr->pid);
	PN(clock);
	P(cpu_load[0]);
	P(cpu_load[1]);
	P(cpu_load[2]);
	P(cpu_load[3]);
	P(cpu_load[4]);
#undef P
#undef PN

#ifdef CONFIG_SCHEDSTATS
#define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, rq->n);
#define P64(n) SEQ_printf(m, "  .%-30s: %Ld\n", #n, rq->n);

	P(yld_count);

	P(sched_count);
	P(sched_goidle);
#ifdef CONFIG_SMP
	P64(avg_idle);
#endif

	P(ttwu_count);
	P(ttwu_local);

#undef P
#undef P64
#endif
	spin_lock_irqsave(&sched_debug_lock, flags);
	print_cfs_stats(m, cpu);
	print_rt_stats(m, cpu);

	rcu_read_lock();
	print_rq(m, rq, cpu);
	rcu_read_unlock();
	spin_unlock_irqrestore(&sched_debug_lock, flags);
}

static inline cpumask_t sched_rt_period_mask(void)
{
	return cpu_rq(smp_processor_id())->rd->span;
}