[Android Cgroup层次关系] 二、mount子系统

        Android将需要mount的子系统和对应路径等信息，放在配置文件/system/core/libprocessgroup/profiles/cgroups.json中。init进程的SecondStage阶段调用函数SetupCgroupsAction()建立各子系统，主要是在ReadDescriptors()中解析配置文件，在SetupCgroup()中调用系统调用mount对应子系统。

int main(int argc, char** argv) {
    .......................................
    if (!strcmp(argv[1], "second_stage") {
        return SecondStageMain(argc, argv);
    }
    .......................................
}

int SecondStageMain(int argc, char** argv) {
    .......................................
    am.QueueBuiltinAction(SetupCgroupsAction, "SetupCgroups");
    .......................................
}

static Result<Success> SecondStageMain(const BuiltinArguments&) {
    make_dir(android::base::Dirname(CGROUPS_RC_PATH), 0711);
    if (!CgroupSetup()) {
        return ErrorError()<<"Failed to setup cgroups";
    }
    return Success();
}

bool CgroupSetup() {
    using namespace android::cgrouprc;
    std::map<std::string, CgroupDescriptor> descriptors;
    ........................................................
    if (!ReadDescriptors(&descriptors)) {           //解析配置文件
        return false;
    }
    for (auto [name, descriptor] : descriptors) {     
        if (SetupCgroup(descriptor)) {            //mount各子系统
        ................................................
	}
        ....................................................
    }
    ........................................................
}

        mount系统调用最终会走到cgroup_mount()，cgroup_mount()有两个重要任务：一是创建cgroup_root并初始化；二是创建子系统根目录。本文重点在Cgroup层次关系，主要分析cgroup_root初始化过程。cgroup_mount()首先为cgroup_root分配内存，然后调用init_cgroup_root()初始化cgroup_root，init_cgroup_root()在《Android Cgroup分析之Cgroup初始化》中已经分析过。

static struct dentry *cgroup_mount(struct file_system_type *fs_type,
			 int flags, const char *unused_dev_name,
			 void *data)
{
	bool is_v2 = fs_type == &cgroup2_fs_type;
	struct super_block *pinned_sb = NULL;
	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
	struct cgroup_subsys *ss;
	struct cgroup_root *root;
	struct cgroup_sb_opts opts;
	struct dentry *dentry;
	int ret;
	int i;
	bool new_sb;
    ...............................................................
	ret = parse_cgroupfs_options(data, &opts);
	...............................................................
	root = kzalloc(sizeof(*root), GFP_KERNEL);
    ...............................................................
	init_cgroup_root(root, &opts);

	ret = cgroup_setup_root(root, opts.subsys_mask);
    ...............................................................
out_mount:
	dentry = kernfs_mount(fs_type, flags, root->kf_root,
			      is_v2 ? CGROUP2_SUPER_MAGIC : CGROUP_SUPER_MAGIC,
			      &new_sb);
    ...............................................................
	return dentry;
}

        mount Cgroup子系统后，在对应文件夹能看到cgroup.procs、tasks等操作Cgroup的节点，这些节点的创建是在cgroup_setup_root()中完成的。首先调用kernfs_create_root()创建kernfs_root，kernfs_root在kernfs文件系统中代表sys文件系统的根，kernfs_node代表一个目录或文件(kernfs_node->mode有标志位S_IFDIR为目录否则为文件)。kernfs_root的成员syscall_ops指向cgroup_kf_syscall_ops，kernfs_root->kn->priv指向cgroup_root包含的struct cgroup。 

static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
{
	LIST_HEAD(tmp_links);
	struct cgroup *root_cgrp = &root->cgrp;
	struct css_set *cset;
	int i, ret;
    ...........................................................
	//创建kf_root
	root->kf_root = kernfs_create_root(&cgroup_kf_syscall_ops,
					   KERNFS_ROOT_CREATE_DEACTIVATED,
					   root_cgrp);
	root_cgrp->kn = root->kf_root->kn;

	ret = css_populate_dir(&root_cgrp->self);
	if (ret)
		goto destroy_root;

	ret = rebind_subsystems(root, ss_mask);
    ......................................................................
	list_add(&root->root_list, &cgroup_roots);
	cgroup_root_count++;
    ...............................................................
}

struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
				       unsigned int flags, void *priv)
{
	struct kernfs_root *root;
	struct kernfs_node *kn;

	root = kzalloc(sizeof(*root), GFP_KERNEL);
	if (!root)
		return ERR_PTR(-ENOMEM);

	ida_init(&root->ino_ida);
	INIT_LIST_HEAD(&root->supers);

	kn = __kernfs_new_node(root, "", S_IFDIR | S_IRUGO | S_IXUGO,
			       KERNFS_DIR);
    ....................................................................
	kn->priv = priv;
	kn->dir.root = root;

	root->syscall_ops = scops;
	root->flags = flags;
	root->kn = kn;
	init_waitqueue_head(&root->deactivate_waitq);
    ....................................................................
	return root;
}

         cgroup_setup_root()创建kernfs_root后，第一次调用css_populate_dir()创建默认节点。此时cgroup_root->cgrp->self->ss为空，故进入if (!css->ss) 分支，创建一些默认节点。Cgroup的参数以及操作接口，抽象为结构体struct cftype，cgroup_addrm_files()以cftype为参数创建kernfs文件节点，以供应用程序操作。

static int css_populate_dir(struct cgroup_subsys_state *css)
{
	struct cgroup *cgrp = css->cgroup;
	struct cftype *cfts, *failed_cfts;
	int ret;
    .................................................................
	if (!css->ss) {
		if (cgroup_on_dfl(cgrp))
			cfts = cgroup_dfl_base_files;
		else
			cfts = cgroup_legacy_base_files;

		return cgroup_addrm_files(&cgrp->self, cgrp, cfts, true);
	}
    ...............................................................
}

static int cgroup_addrm_files(struct cgroup_subsys_state *css,
			      struct cgroup *cgrp, struct cftype cfts[],
			      bool is_add)
{
	struct cftype *cft, *cft_end = NULL;
	int ret = 0;

	lockdep_assert_held(&cgroup_mutex);

restart:
	for (cft = cfts; cft != cft_end && cft->name[0] != '\0'; cft++) {
            ...............................................................
		if (is_add) {
			ret = cgroup_add_file(css, cgrp, cft);
            ...........................................................
		} else {
			cgroup_rm_file(cgrp, cft);
		}
	}
	return ret;
}

         下一步是调用rebind_subsystems()建立与子系统的关系，将子系统的struct cgroup_root *root指向新创建的cgroup_root，struct cgroup_subsys_state的*cgroup成员指向新创建cgroup_root包含的cgroup，从而建立其新创建cgroup与子系统的联系。

static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
{
	struct cgroup *dcgrp = &dst_root->cgrp;
	struct cgroup_subsys *ss;
	int ssid, i, ret;
    ...................................................................
	do_each_subsys_mask(ss, ssid, ss_mask) {
		struct cgroup_root *src_root = ss->root;
		struct cgroup *scgrp = &src_root->cgrp;
		struct cgroup_subsys_state *css = cgroup_css(scgrp, ss);
		struct css_set *cset;

		WARN_ON(!css || cgroup_css(dcgrp, ss));

		/* disable from the source */
		src_root->subsys_mask &= ~(1 << ssid);
		WARN_ON(cgroup_apply_control(scgrp));
		cgroup_finalize_control(scgrp, 0);

		/* rebind */
		RCU_INIT_POINTER(scgrp->subsys[ssid], NULL);
		rcu_assign_pointer(dcgrp->subsys[ssid], css);
		ss->root = dst_root;
		css->cgroup = dcgrp;
        ...............................................................
		ret = cgroup_apply_control(dcgrp);
        ...............................................................
	} while_each_subsys_mask();

	kernfs_activate(dcgrp->kn);
	return 0;
}

         cgroup_apply_control_enable()再次调用css_populate_dir()创建子系统的操作节点。这次调用时，参数css为css_create()所创建，不为空，故会根据子系统成员cfts链表中的cftype来创建节点。

static int cgroup_apply_control_enable(struct cgroup *cgrp)
{
	struct cgroup *dsct;
	struct cgroup_subsys_state *d_css;
	struct cgroup_subsys *ss;
	int ssid, ret;

	cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
		for_each_subsys(ss, ssid) {
			struct cgroup_subsys_state *css = cgroup_css(dsct, ss);

			WARN_ON_ONCE(css && percpu_ref_is_dying(&css->refcnt));

			if (!(cgroup_ss_mask(dsct) & (1 << ss->id)))
				continue;
			if (!css) {
				css = css_create(dsct, ss);
				if (IS_ERR(css))
					return PTR_ERR(css);
			}
			if (css_visible(css)) {
				ret = css_populate_dir(css);
				if (ret)
					return ret;
			}
		}
	}

	return 0;
}

static int css_populate_dir(struct cgroup_subsys_state *css)
{
	struct cgroup *cgrp = css->cgroup;
	struct cftype *cfts, *failed_cfts;
	int ret;

	if ((css->flags & CSS_VISIBLE) || !cgrp->kn)
		return 0;

    .........................................................
	list_for_each_entry(cfts, &css->ss->cfts, node) {
		ret = cgroup_addrm_files(css, cgrp, cfts, true);
		if (ret < 0) {
			failed_cfts = cfts;
			goto err;
		}
	}

	css->flags |= CSS_VISIBLE;
    ..........................................................
}