cpu子系统的组调度

组调度属于cgroup中的cpu子系统
cpu子系统的所有操作都在cpu_cgrp_subsys 中有定义
struct cgroup_subsys cpu_cgrp_subsys = {
	.css_alloc	= cpu_cgroup_css_alloc,
	.css_online	= cpu_cgroup_css_online,
	.css_released	= cpu_cgroup_css_released,
	.css_free	= cpu_cgroup_css_free,
	.css_extra_stat_show = cpu_extra_stat_show,
	.fork		= cpu_cgroup_fork,
	.can_attach	= cpu_cgroup_can_attach,
	.attach		= cpu_cgroup_attach,
	.legacy_cftypes	= cpu_legacy_files,
	.dfl_cftypes	= cpu_files,
	.early_init	= true,
	.threaded	= true,
};
我们这里以css_alloc 为例
static struct cgroup_subsys_state *
cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
	struct task_group *parent = css_tg(parent_css);
	struct task_group *tg;

	if (!parent) {
		/* This is early initialization for the top cgroup */
		return &root_task_group.css;
	}
	#创建调度组
	tg = sched_create_group(parent);
	if (IS_ERR(tg))
		return ERR_PTR(-ENOMEM);

	return &tg->css;
}
struct task_group *sched_create_group(struct task_group *parent)
{
	struct task_group *tg;
	
	tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO);
	if (!tg)
		return ERR_PTR(-ENOMEM);
	#可见这里分别为fair和rt申请调度组
	if (!alloc_fair_sched_group(tg, parent))
		goto err;

	if (!alloc_rt_sched_group(tg, parent))
		goto err;

	return tg;

err:
	sched_free_group(tg);
	return ERR_PTR(-ENOMEM);
}
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
	struct sched_entity *se;
	struct cfs_rq *cfs_rq;
	int i;
	#分别问cfs_rq和se申请内存
	tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
	if (!tg->cfs_rq)
		goto err;
	tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL);
	if (!tg->se)
		goto err;

	tg->shares = NICE_0_LOAD;

	init_cfs_bandwidth(tg_cfs_bandwidth(tg));
	#为每个cpu 初始化cfs_rq和se
	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;
		#主要是初始化
		init_cfs_rq(cfs_rq);
		init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
		init_entity_runnable_average(se);
	}

}
当进程要加入组调度是会调用attach
static void cpu_cgroup_attach(struct cgroup_taskset *tset)
{
	struct task_struct *task;
	struct cgroup_subsys_state *css;
	#将cgroup_taskset 中的所有task通过sched_move_task 将进程迁移到组调度中
	cgroup_taskset_for_each(task, css, tset)
		sched_move_task(task);
}
void sched_move_task(struct task_struct *tsk)
{
#分别调用调度器的dequeue_task函数迁出task，然后在调用enqueue_task加入调度组
	if (queued)
		dequeue_task(rq, tsk, queue_flags);
	if (running)
		put_prev_task(rq, tsk);

	sched_change_group(tsk, TASK_MOVE_GROUP);

	if (queued)
		enqueue_task(rq, tsk, queue_flags);
	if (running)
		set_curr_task(rq, tsk);
}
这里以enqueue_task 为例
static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
{
	if (!(flags & ENQUEUE_NOCLOCK))
		update_rq_clock(rq);

	if (!(flags & ENQUEUE_RESTORE))
		sched_info_queued(rq, p);
	#这里最终调用fair的enqueue_task_fair 来加入组调度的fair的rq中
	p->sched_class->enqueue_task(rq, p, flags);
}