linux cgroup (3)----mkdir

kernel :5.0
当在cgroup某个子系统下创建一个目录，此时该目录下会自动生成许多文件，这个过程有cgroup_mkdir完成。可通过ftrace（events/cgroup/cgroup_mkdir)跟踪

cgroup_mkdir

int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode)
{
	struct cgroup *parent, *cgrp;
	struct kernfs_node *kn;
	int ret;

	/* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */
	if (strchr(name, '\n'))
		return -EINVAL;

	parent = cgroup_kn_lock_live(parent_kn, false); //kernfs_node->priv指向一个cgroup
	if (!parent)
		return -ENODEV;

	if (!cgroup_check_hierarchy_limits(parent)) { //对父cgroup的后代数、深度做检查,确保创建新的cgroup后不会超过最大值
		ret = -EAGAIN;
		goto out_unlock;
	}

	cgrp = cgroup_create(parent);
	if (IS_ERR(cgrp)) {
		ret = PTR_ERR(cgrp);
		goto out_unlock;
	}

	/* create the directory */
	kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
	if (IS_ERR(kn)) {
		ret = PTR_ERR(kn);
		goto out_destroy;
	}
	cgrp->kn = kn;

	/*
	 * This extra ref will be put in cgroup_free_fn() and guarantees
	 * that @cgrp->kn is always accessible.
	 */
	kernfs_get(kn);

	ret = cgroup_kn_set_ugid(kn);
	if (ret)
		goto out_destroy;

	ret = css_populate_dir(&cgrp->self);//创建基本属性节点
	if (ret)
		goto out_destroy;

	ret = cgroup_apply_control_enable(cgrp);//根据cgroup_create时赋予的ss_mask填充cgroup的subsys数组，并创建子系统属性节点
	if (ret)
		goto out_destroy;

	TRACE_CGROUP_PATH(mkdir, cgrp);

	/* let's create and online css's */
	kernfs_activate(kn);

	ret = 0;
	goto out_unlock;

out_destroy:
	cgroup_destroy_locked(cgrp);
out_unlock:
	cgroup_kn_unlock(parent_kn);
	return ret;
}

cgroup_create(parent)

当cgroup_create完成后，新创建的cgroup的subsys数组并未填充。

static struct cgroup *cgroup_create(struct cgroup *parent)
{
	struct cgroup_root *root = parent->root;
	struct cgroup *cgrp, *tcgrp;
	int level = parent->level + 1;
	int ret;

	/* allocate the cgroup and its ID, 0 is reserved for the root */
	cgrp = kzalloc(struct_size(cgrp, ancestor_ids, (level + 1)),
		       GFP_KERNEL);
	if (!cgrp)
		return ERR_PTR(-ENOMEM);

	ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL);
	if (ret)
		goto out_free_cgrp;

	if (cgroup_on_dfl(parent)) {
		ret = cgroup_rstat_init(cgrp);
		if (ret)
			goto out_cancel_ref;
	}

	/*
	 * Temporarily set the pointer to NULL, so idr_find() won't return
	 * a half-baked cgroup.
	 */
	cgrp->id = cgroup_idr_alloc(&root->cgroup_idr, NULL, 2, 0, GFP_KERNEL);
	if (cgrp->id < 0) {
		ret = -ENOMEM;
		goto out_stat_exit;
	}

	init_cgroup_housekeeping(cgrp);

	cgrp->self.parent = &parent->self;
	cgrp->root = root;
	cgrp->level = level;

	ret = psi_cgroup_alloc(cgrp);
	if (ret)
		goto out_idr_free;

	ret = cgroup_bpf_inherit(cgrp);
	if (ret)
		goto out_psi_free;

	for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { //使所有祖先的后代数+1
		cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;

		if (tcgrp != cgrp)
			tcgrp->nr_descendants++;
	}

	if (notify_on_release(parent))
		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);

	if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags))
		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);

	cgrp->self.serial_nr = css_serial_nr_next++;

	/* allocation complete, commit to creation */
	list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children); //将子css以sibling为连接件接入父css的children链表
	atomic_inc(&root->nr_cgrps);
	cgroup_get_live(parent);

	/*
	 * @cgrp is now fully operational.  If something fails after this
	 * point, it'll be released via the normal destruction path.
	 */
	cgroup_idr_replace(&root->cgroup_idr, cgrp, cgrp->id);

	/*
	 * On the default hierarchy, a child doesn't automatically inherit
	 * subtree_control from the parent.  Each is configured manually.
	 */
	if (!cgroup_on_dfl(cgrp))
		cgrp->subtree_control = cgroup_control(cgrp); //返回父cgroup的subtree_control

	cgroup_propagate_control(cgrp);//设置cgrp的subsys_mask

	return cgrp;

out_psi_free:
	psi_cgroup_free(cgrp);
out_idr_free:
	cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
out_stat_exit:
	if (cgroup_on_dfl(parent))
		cgroup_rstat_exit(cgrp);
out_cancel_ref:
	percpu_ref_exit(&cgrp->self.refcnt);
out_free_cgrp:
	kfree(cgrp);
	return ERR_PTR(ret);
}

总结

通过这个流程可以看出来，cgroup树的层级关系由cgroup_subsys_state维护，每个cgroup包含一个css用于维护这个树，另外还有数个css，其由对应子系统的css_alloc函数分配，其ss指向对应的子系统。
子系统的css_alloc函数会分配一个各子系统对应的cgroup结构（如mem_cgroup、blkcg等），其第一个成员就是一个css结构。