cgroup.c

 * cgroupstats_build - build and fill cgroupstats
 * @stats: cgroupstats to fill information into
 * @dentry: A dentry entry belonging to the cgroup for which stats have
 * been requested.
 *
 * Build and fill cgroupstats so that taskstats can export it to user
 * space.
 */
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
{
	struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
	struct cgroup *cgrp;
	struct css_task_iter it;
	struct task_struct *tsk;

	/* it should be kernfs_node belonging to cgroupfs and is a directory */
	if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
	    kernfs_type(kn) != KERNFS_DIR)
		return -EINVAL;

	mutex_lock(&cgroup_mutex);

	/*
	 * We aren't being called from kernfs and there's no guarantee on
	 * @kn->priv's validity.  For this and css_tryget_online_from_dir(),
	 * @kn->priv is RCU safe.  Let's do the RCU dancing.
	 */
	rcu_read_lock();
	cgrp = rcu_dereference(kn->priv);
	if (!cgrp || cgroup_is_dead(cgrp)) {
		rcu_read_unlock();
		mutex_unlock(&cgroup_mutex);
		return -ENOENT;
	}
	rcu_read_unlock();

	css_task_iter_start(&cgrp->self, &it);
	while ((tsk = css_task_iter_next(&it))) {
		switch (tsk->state) {
		case TASK_RUNNING:
			stats->nr_running++;
			break;
		case TASK_INTERRUPTIBLE:
			stats->nr_sleeping++;
			break;
		case TASK_UNINTERRUPTIBLE:
			stats->nr_uninterruptible++;
			break;
		case TASK_STOPPED:
			stats->nr_stopped++;
			break;
		default:
			if (delayacct_is_task_waiting_on_io(tsk))
				stats->nr_io_wait++;
			break;
		}
	}
	css_task_iter_end(&it);

	mutex_unlock(&cgroup_mutex);
	return 0;
}


/*
 * seq_file methods for the tasks/procs files. The seq_file position is the
 * next pid to display; the seq_file iterator is a pointer to the pid
 * in the cgroup->l->list array.
 */

static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
{
	/*
	 * Initially we receive a position value that corresponds to
	 * one more than the last pid shown (or 0 on the first call or
	 * after a seek to the start). Use a binary-search to find the
	 * next pid to display, if any
	 */
	struct kernfs_open_file *of = s->private;
	struct cgroup *cgrp = seq_css(s)->cgroup;
	struct cgroup_pidlist *l;
	enum cgroup_filetype type = seq_cft(s)->private;
	int index = 0, pid = *pos;
	int *iter, ret;

	mutex_lock(&cgrp->pidlist_mutex);

	/*
	 * !NULL @of->priv indicates that this isn't the first start()
	 * after open.  If the matching pidlist is around, we can use that.
	 * Look for it.  Note that @of->priv can't be used directly.  It
	 * could already have been destroyed.
	 */
	if (of->priv)
		of->priv = cgroup_pidlist_find(cgrp, type);

	/*
	 * Either this is the first start() after open or the matching
	 * pidlist has been destroyed inbetween.  Create a new one.
	 */
	if (!of->priv) {
		ret = pidlist_array_load(cgrp, type,
					 (struct cgroup_pidlist **)&of->priv);
		if (ret)
			return ERR_PTR(ret);
	}
	l = of->priv;

	if (pid) {
		int end = l->length;

		while (index < end) {
			int mid = (index + end) / 2;
			if (cgroup_pid_fry(cgrp, l->list[mid]) == pid) {
				index = mid;
				break;
			} else if (cgroup_pid_fry(cgrp, l->list[mid]) <= pid)
				index = mid + 1;
			else
				end = mid;
		}
	}
	/* If we're off the end of the array, we're done */
	if (index >= l->length)
		return NULL;
	/* Update the abstract position to be the actual pid that we found */
	iter = l->list + index;
	*pos = cgroup_pid_fry(cgrp, *iter);
	return iter;
}

static void cgroup_pidlist_stop(struct seq_file *s, void *v)
{
	struct kernfs_open_file *of = s->private;
	struct cgroup_pidlist *l = of->priv;

	if (l)
		mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork,
				 CGROUP_PIDLIST_DESTROY_DELAY);
	mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex);
}

static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
{
	struct kernfs_open_file *of = s->private;
	struct cgroup_pidlist *l = of->priv;
	pid_t *p = v;
	pid_t *end = l->list + l->length;
	/*
	 * Advance to the next pid in the array. If this goes off the
	 * end, we're done
	 */
	p++;
	if (p >= end) {
		return NULL;
	} else {
		*pos = cgroup_pid_fry(seq_css(s)->cgroup, *p);
		return p;
	}
}

static int cgroup_pidlist_show(struct seq_file *s, void *v)
{
	return seq_printf(s, "%d\n", *(int *)v);
}

static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css,
					 struct cftype *cft)
{
	return notify_on_release(css->cgroup);
}

static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css,
					  struct cftype *cft, u64 val)
{
	clear_bit(CGRP_RELEASABLE, &css->cgroup->flags);
	if (val)
		set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags);
	else
		clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags);
	return 0;
}

static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css,
				      struct cftype *cft)
{
	return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags);
}

static int cgroup_clone_children_write(struct cgroup_subsys_state *css,
				       struct cftype *cft, u64 val)
{
	if (val)
		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags);
	else
		clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags);
	return 0;
}

/* cgroup core interface files for the default hierarchy */
static struct cftype cgroup_dfl_base_files[] = {
	{
		.name = "cgroup.procs",
		.seq_start = cgroup_pidlist_start,
		.seq_next = cgroup_pidlist_next,
		.seq_stop = cgroup_pidlist_stop,
		.seq_show = cgroup_pidlist_show,
		.private = CGROUP_FILE_PROCS,
		.write = cgroup_procs_write,
		.mode = S_IRUGO | S_IWUSR,
	},
	{
		.name = "cgroup.controllers",
		.flags = CFTYPE_ONLY_ON_ROOT,
		.seq_show = cgroup_root_controllers_show,
	},
	{
		.name = "cgroup.controllers",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = cgroup_controllers_show,
	},
	{
		.name = "cgroup.subtree_control",
		.seq_show = cgroup_subtree_control_show,
		.write = cgroup_subtree_control_write,
	},
	{
		.name = "cgroup.populated",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = cgroup_populated_show,
	},
	{ }	/* terminate */
};

/* cgroup core interface files for the legacy hierarchies */
static struct cftype cgroup_legacy_base_files[] = {
	{
		.name = "cgroup.procs",
		.seq_start = cgroup_pidlist_start,
		.seq_next = cgroup_pidlist_next,
		.seq_stop = cgroup_pidlist_stop,
		.seq_show = cgroup_pidlist_show,
		.private = CGROUP_FILE_PROCS,
		.write = cgroup_procs_write,
		.mode = S_IRUGO | S_IWUSR,
	},
	{
		.name = "cgroup.clone_children",
		.read_u64 = cgroup_clone_children_read,
		.write_u64 = cgroup_clone_children_write,
	},
	{
		.name = "cgroup.sane_behavior",
		.flags = CFTYPE_ONLY_ON_ROOT,
		.seq_show = cgroup_sane_behavior_show,
	},
	{
		.name = "tasks",
		.seq_start = cgroup_pidlist_start,
		.seq_next = cgroup_pidlist_next,
		.seq_stop = cgroup_pidlist_stop,
		.seq_show = cgroup_pidlist_show,
		.private = CGROUP_FILE_TASKS,
		.write = cgroup_tasks_write,
		.mode = S_IRUGO | S_IWUSR,
	},
	{
		.name = "notify_on_release",
		.read_u64 = cgroup_read_notify_on_release,
		.write_u64 = cgroup_write_notify_on_release,
	},
	{
		.name = "release_agent",
		.flags = CFTYPE_ONLY_ON_ROOT,
		.seq_show = cgroup_release_agent_show,
		.write = cgroup_release_agent_write,
		.max_write_len = PATH_MAX - 1,
	},
	{ }	/* terminate */
};

/**
 * cgroup_populate_dir - create subsys files in a cgroup directory
 * @cgrp: target cgroup
 * @subsys_mask: mask of the subsystem ids whose files should be added
 *
 * On failure, no file is added.
 */
static int cgroup_populate_dir(struct cgroup *cgrp, unsigned int subsys_mask)
{
	struct cgroup_subsys *ss;
	int i, ret = 0;

	/* process cftsets of each subsystem */
	for_each_subsys(ss, i) {
		struct cftype *cfts;

		if (!(subsys_mask & (1 << i)))
			continue;

		list_for_each_entry(cfts, &ss->cfts, node) {
			ret = cgroup_addrm_files(cgrp, cfts, true);
			if (ret < 0)
				goto err;
		}
	}
	return 0;
err:
	cgroup_clear_dir(cgrp, subsys_mask);
	return ret;
}

/*
 * css destruction is four-stage process.
 *
 * 1. Destruction starts.  Killing of the percpu_ref is initiated.
 *    Implemented in kill_css().
 *
 * 2. When the percpu_ref is confirmed to be visible as killed on all CPUs
 *    and thus css_tryget_online() is guaranteed to fail, the css can be
 *    offlined by invoking offline_css().  After offlining, the base ref is
 *    put.  Implemented in css_killed_work_fn().
 *
 * 3. When the percpu_ref reaches zero, the only possible remaining
 *    accessors are inside RCU read sections.  css_release() schedules the
 *    RCU callback.
 *
 * 4. After the grace period, the css can be freed.  Implemented in
 *    css_free_work_fn().
 *
 * It is actually hairier because both step 2 and 4 require process context
 * and thus involve punting to css->destroy_work adding two additional
 * steps to the already complex sequence.
 */
static void css_free_work_fn(struct work_struct *work)
{
	struct cgroup_subsys_state *css =
		container_of(work, struct cgroup_subsys_state, destroy_work);
	struct cgroup *cgrp = css->cgroup;

	percpu_ref_exit(&css->refcnt);

	if (css->ss) {
		/* css free path */
		if (css->parent)
			css_put(css->parent);

		css->ss->css_free(css);
		cgroup_put(cgrp);
	} else {
		/* cgroup free path */
		atomic_dec(&cgrp->root->nr_cgrps);
		cgroup_pidlist_destroy_all(cgrp);

		if (cgroup_parent(cgrp)) {
			/*
			 * We get a ref to the parent, and put the ref when
			 * this cgroup is being freed, so it's guaranteed
			 * that the parent won't be destroyed before its
			 * children.
			 */
			cgroup_put(cgroup_parent(cgrp));
			kernfs_put(cgrp->kn);
			kfree(cgrp);
		} else {
			/*
			 * This is root cgroup's refcnt reaching zero,
			 * which indicates that the root should be
			 * released.
			 */
			cgroup_destroy_root(cgrp->root);
		}
	}
}

static void css_free_rcu_fn(struct rcu_head *rcu_head)
{
	struct cgroup_subsys_state *css =
		container_of(rcu_head, struct cgroup_subsys_state, rcu_head);

	INIT_WORK(&css->destroy_work, css_free_work_fn);
	queue_work(cgroup_destroy_wq, &css->destroy_work);
}

static void css_release_work_fn(struct work_struct *work)
{
	struct cgroup_subsys_state *css =
		container_of(work, struct cgroup_subsys_state, destroy_work);
	struct cgroup_subsys *ss = css->ss;
	struct cgroup *cgrp = css->cgroup;

	mutex_lock(&cgroup_mutex);

	css->flags |= CSS_RELEASED;
	list_del_rcu(&css->sibling);

	if (ss) {
		/* css release path */
		cgroup_idr_remove(&ss->css_idr, css->id);
	} else {
		/* cgroup release path */
		cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
		cgrp->id = -1;

		/*
		 * There are two control paths which try to determine
		 * cgroup from dentry without going through kernfs -
		 * cgroupstats_build() and css_tryget_online_from_dir().
		 * Those are supported by RCU protecting clearing of
		 * cgrp->kn->priv backpointer.
		 */
		RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL);
	}

	mutex_unlock(&cgroup_mutex);

	call_rcu(&css->rcu_head, css_free_rcu_fn);
}

static void css_release(struct percpu_ref *ref)
{
	struct cgroup_subsys_state *css =
		container_of(ref, struct cgroup_subsys_state, refcnt);

	INIT_WORK(&css->destroy_work, css_release_work_fn);
	queue_work(cgroup_destroy_wq, &css->destroy_work);
}

static void init_and_link_css(struct cgroup_subsys_state *css,
			      struct cgroup_subsys *ss, struct cgroup *cgrp)
{
	lockdep_assert_held(&cgroup_mutex);

	cgroup_get(cgrp);

	memset(css, 0, sizeof(*css));
	css->cgroup = cgrp;
	css->ss = ss;
	INIT_LIST_HEAD(&css->sibling);
	INIT_LIST_HEAD(&css->children);
	css->serial_nr = css_serial_nr_next++;

	if (cgroup_parent(cgrp)) {
		css->parent = cgroup_css(cgroup_parent(cgrp), ss);
		css_get(css->parent);
	}

	BUG_ON(cgroup_css(cgrp, ss));
}

/* invoke ->css_online() on a new CSS and mark it online if successful */
static int online_css(struct cgroup_subsys_state *css)
{
	struct cgroup_subsys *ss = css->ss;
	int ret = 0;

	lockdep_assert_held(&cgroup_mutex);

	if (ss->css_online)
		ret = ss->css_online(css);
	if (!ret) {
		css->flags |= CSS_ONLINE;
		rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
	}
	return ret;
}

/* if the CSS is online, invoke ->css_offline() on it and mark it offline */
static void offline_css(struct cgroup_subsys_state *css)
{
	struct cgroup_subsys *ss = css->ss;

	lockdep_assert_held(&cgroup_mutex);

	if (!(css->flags & CSS_ONLINE))
		return;

	if (ss->css_offline)
		ss->css_offline(css);

	css->flags &= ~CSS_ONLINE;
	RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL);

	wake_up_all(&css->cgroup->offline_waitq);
}

/**
 * create_css - create a cgroup_subsys_state
 * @cgrp: the cgroup new css will be associated with
 * @ss: the subsys of new css
 * @visible: whether to create control knobs for the new css or not
 *
 * Create a new css associated with @cgrp - @ss pair.  On success, the new
 * css is online and installed in @cgrp with all interface files created if
 * @visible.  Returns 0 on success, -errno on failure.
 */
static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss,
		      bool visible)
{
	struct cgroup *parent = cgroup_parent(cgrp);
	struct cgroup_subsys_state *parent_css = cgroup_css(parent, ss);
	struct cgroup_subsys_state *css;
	int err;

	lockdep_assert_held(&cgroup_mutex);

	css = ss->css_alloc(parent_css);
	if (IS_ERR(css))
		return PTR_ERR(css);

	init_and_link_css(css, ss, cgrp);

	err = percpu_ref_init(&css->refcnt, css_release, GFP_KERNEL);
	if (err)
		goto err_free_css;

	err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_NOWAIT);
	if (err < 0)
		goto err_free_percpu_ref;
	css->id = err;

	if (visible) {
		err = cgroup_populate_dir(cgrp, 1 << ss->id);
		if (err)
			goto err_free_id;
	}

	/* @css is ready to be brought online now, make it visible */
	list_add_tail_rcu(&css->sibling, &parent_css->children);
	cgroup_idr_replace(&ss->css_idr, css, css->id);

	err = online_css(css);
	if (err)
		goto err_list_del;

	if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
	    cgroup_parent(parent)) {
		pr_warn("%s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
			current->comm, current->pid, ss->name);
		if (!strcmp(ss->name, "memory"))
			pr_warn("\"memory\" requires setting use_hierarchy to 1 on the root\n");
		ss->warned_broken_hierarchy = true;
	}

	return 0;

err_list_del:
	list_del_rcu(&css->sibling);
	cgroup_clear_dir(css->cgroup, 1 << css->ss->id);
err_free_id:
	cgroup_idr_remove(&ss->css_idr, css->id);
err_free_percpu_ref:
	percpu_ref_exit(&css->refcnt);
err_free_css:
	call_rcu(&css->rcu_head, css_free_rcu_fn);
	return err;
}

static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
			umode_t mode)
{
	struct cgroup *parent, *cgrp;
	struct cgroup_root *root;
	struct cgroup_subsys *ss;
	struct kernfs_node *kn;
	struct cftype *base_files;
	int ssid, 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);
	if (!parent)
		return -ENODEV;
	root = parent->root;

	/* allocate the cgroup and its ID, 0 is reserved for the root */
	cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
	if (!cgrp) {
		ret = -ENOMEM;
		goto out_unlock;
	}

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

	/*
	 * 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_NOWAIT);
	if (cgrp->id < 0) {
		ret = -ENOMEM;
		goto out_cancel_ref;
	}

	init_cgroup_housekeeping(cgrp);

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

	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);

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

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

	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);
	atomic_inc(&root->nr_cgrps);
	cgroup_get(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);

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

	if (cgroup_on_dfl(cgrp))
		base_files = cgroup_dfl_base_files;
	else
		base_files = cgroup_legacy_base_files;

	ret = cgroup_addrm_files(cgrp, base_files, true);
	if (ret)
		goto out_destroy;

	/* let's create and online css's */
	for_each_subsys(ss, ssid) {
		if (parent->child_subsys_mask & (1 << ssid)) {
			ret = create_css(cgrp, ss,
					 parent->subtree_control & (1 << ssid));
			if (ret)
				goto out_destroy;
		}
	}

	/*
	 * 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 = parent->subtree_control;
		cgroup_refresh_child_subsys_mask(cgrp);
	}

	kernfs_activate(kn);

	ret = 0;
	goto out_unlock;

out_free_id:
	cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
out_cancel_ref:
	percpu_ref_exit(&cgrp->self.refcnt);
out_free_cgrp:
	kfree(cgrp);
out_unlock:
	cgroup_kn_unlock(parent_kn);
	return ret;

out_destroy:
	cgroup_destroy_locked(cgrp);
	goto out_unlock;
}

/*
 * This is called when the refcnt of a css is confirmed to be killed.
 * css_tryget_online() is now guaranteed to fail.  Tell the subsystem to
 * initate destruction and put the css ref from kill_css().
 */
static void css_killed_work_fn(struct work_struct *work)
{
	struct cgroup_subsys_state *css =
		container_of(work, struct cgroup_subsys_state, destroy_work);

	mutex_lock(&cgroup_mutex);
	offline_css(css);
	mutex_unlock(&cgroup_mutex);

	css_put(css);
}

/* css kill confirmation processing requires process context, bounce */
static void css_killed_ref_fn(struct percpu_ref *ref)
{
	struct cgroup_subsys_state *css =
		container_of(ref, struct cgroup_subsys_state, refcnt);

	INIT_WORK(&css->destroy_work, css_killed_work_fn);
	queue_work(cgroup_destroy_wq, &css->destroy_work);
}

/**
 * kill_css - destroy a css
 * @css: css to destroy
 *
 * This function initiates destruction of @css by removing cgroup interface
 * files and putting its base reference.  ->css_offline() will be invoked
 * asynchronously once css_tryget_online() is guaranteed to fail and when
 * the reference count reaches zero, @css will be released.
 */
static void kill_css(struct cgroup_subsys_state *css)
{
	lockdep_assert_held(&cgroup_mutex);

	/*
	 * This must happen before css is disassociated with its cgroup.
	 * See seq_css() for details.
	 */
	cgroup_clear_dir(css->cgroup, 1 << css->ss->id);

	/*
	 * Killing would put the base ref, but we need to keep it alive
	 * until after ->css_offline().
	 */
	css_get(css);

	/*
	 * cgroup core guarantees that, by the time ->css_offline() is
	 * invoked, no new css reference will be given out via
	 * css_tryget_online().  We can't simply call percpu_ref_kill() and
	 * proceed to offlining css's because percpu_ref_kill() doesn't
	 * guarantee that the ref is seen as killed on all CPUs on return.
	 *
	 * Use percpu_ref_kill_and_confirm() to get notifications as each
	 * css is confirmed to be seen as killed on all CPUs.
	 */
	percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn);
}

/**
 * cgroup_destroy_locked - the first stage of cgroup destruction
 * @cgrp: cgroup to be destroyed
 *
 * css's make use of percpu refcnts whose killing latency shouldn't be
 * exposed to userland and are RCU protected.  Also, cgroup core needs to
 * guarantee that css_tryget_online() won't succeed by the time
 * ->css_offline() is invoked.  To satisfy all the requirements,
 * destruction is implemented in the following two steps.
 *
 * s1. Verify @cgrp can be destroyed and mark it dying.  Remove all
 *     userland visible parts and start killing the percpu refcnts of
 *     css's.  Set up so that the next stage will be kicked off once all
 *     the percpu refcnts are confirmed to be killed.
 *
 * s2. Invoke ->css_offline(), mark the cgroup dead and proceed with the
 *     rest of destruction.  Once all cgroup references are gone, the
 *     cgroup is RCU-freed.
 *
 * This function implements s1.  After this step, @cgrp is gone as far as
 * the userland is concerned and a new cgroup with the same name may be
 * created.  As cgroup doesn't care about the names internally, this
 * doesn't cause any problem.
 */
static int cgroup_destroy_locked(struct cgroup *cgrp)
	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
{
	struct cgroup_subsys_state *css;
	bool empty;
	int ssid;

	lockdep_assert_held(&cgroup_mutex);

	/*
	 * css_set_rwsem synchronizes access to ->cset_links and prevents
	 * @cgrp from being removed while put_css_set() is in progress.
	 */
	down_read(&css_set_rwsem);
	empty = list_empty(&cgrp->cset_links);
	up_read(&css_set_rwsem);
	if (!empty)
		return -EBUSY;

	/*
	 * Make sure there's no live children.  We can't test emptiness of
	 * ->self.children as dead children linger on it while being
	 * drained; otherwise, "rmdir parent/child parent" may fail.
	 */
	if (css_has_online_children(&cgrp->self))
		return -EBUSY;

	/*
	 * Mark @cgrp dead.  This prevents further task migration and child
	 * creation by disabling cgroup_lock_live_group().
	 */
	cgrp->self.flags &= ~CSS_ONLINE;

	/* initiate massacre of all css's */
	for_each_css(css, ssid, cgrp)
		kill_css(css);

	/* CSS_ONLINE is clear, remove from ->release_list for the last time */
	raw_spin_lock(&release_list_lock);
	if (!list_empty(&cgrp->release_list))
		list_del_init(&cgrp->release_list);
	raw_spin_unlock(&release_list_lock);

	/*
	 * Remove @cgrp directory along with the base files.  @cgrp has an
	 * extra ref on its kn.
	 */
	kernfs_remove(cgrp->kn);

	set_bit(CGRP_RELEASABLE, &cgroup_parent(cgrp)->flags);
	check_for_release(cgroup_parent(cgrp));

	/* put the base reference */
	percpu_ref_kill(&cgrp->self.refcnt);

	return 0;
};

static int cgroup_rmdir(struct kernfs_node *kn)
{
	struct cgroup *cgrp;
	int ret = 0;

	cgrp = cgroup_kn_lock_live(kn);
	if (!cgrp)
		return 0;
	cgroup_get(cgrp);	/* for @kn->priv clearing */

	ret = cgroup_destroy_locked(cgrp);

	cgroup_kn_unlock(kn);

	cgroup_put(cgrp);
	return ret;
}

static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
	.remount_fs		= cgroup_remount,
	.show_options		= cgroup_show_options,
	.mkdir			= cgroup_mkdir,
	.rmdir			= cgroup_rmdir,
	.rename			= cgroup_rename,
};

static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
{
	struct cgroup_subsys_state *css;

	printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name);

	mutex_lock(&cgroup_mutex);

	idr_init(&ss->css_idr);
	INIT_LIST_HEAD(&ss->cfts);

	/* Create the root cgroup state for this subsystem */
	ss->root = &cgrp_dfl_root;
	css = ss->css_alloc(cgroup_css(&cgrp_dfl_root.cgrp, ss));
	/* We don't handle early failures gracefully */
	BUG_ON(IS_ERR(css));
	init_and_link_css(css, ss, &cgrp_dfl_root.cgrp);

	/*
	 * Root csses are never destroyed and we can't initialize
	 * percpu_ref during early init.  Disable refcnting.
	 */
	css->flags |= CSS_NO_REF;

	if (early) {
		/* allocation can't be done safely during early init */
		css->id = 1;
	} else {
		css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL);
		BUG_ON(css->id < 0);
	}

	/* Update the init_css_set to contain a subsys
	 * pointer to this state - since the subsystem is
	 * newly registered, all tasks and hence the
	 * init_css_set is in the subsystem's root cgroup. */
	init_css_set.subsys[ss->id] = css;

	need_forkexit_callback |= ss->fork || ss->exit;

	/* At system boot, before all subsystems have been
	 * registered, no tasks have been forked, so we don't
	 * need to invoke fork callbacks here. */
	BUG_ON(!list_empty(&init_task.tasks));

	BUG_ON(online_css(css));

	mutex_unlock(&cgroup_mutex);
}

/**
 * cgroup_init_early - cgroup initialization at system boot
 *
 * Initialize cgroups at system boot, and initialize any
 * subsystems that request early init.
 */
int __init cgroup_init_early(void)
{
	static struct cgroup_sb_opts __initdata opts;
	struct cgroup_subsys *ss;
	int i;

	init_cgroup_root(&cgrp_dfl_root, &opts);
	cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF;

	RCU_INIT_POINTER(init_task.cgroups, &init_css_set);

	for_each_subsys(ss, i) {
		WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id,
		     "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p name:id=%d:%s\n",
		     i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free,
		     ss->id, ss->name);
		WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN,
		     "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]);

		ss->id = i;
		ss->name = cgroup_subsys_name[i];

		if (ss->early_init)
			cgroup_init_subsys(ss, true);
	}
	return 0;
}

/**
 * cgroup_init - cgroup initialization
 *
 * Register cgroup filesystem and /proc file, and initialize
 * any subsystems that didn't request early init.
 */
int __init cgroup_init(void)
{
	struct cgroup_subsys *ss;
	unsigned long key;
	int ssid, err;

	BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
	BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));

	mutex_lock(&cgroup_mutex);

	/* Add init_css_set to the hash table */
	key = css_set_hash(init_css_set.subsys);
	hash_add(css_set_table, &init_css_set.hlist, key);

	BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));

	mutex_unlock(&cgroup_mutex);

	for_each_subsys(ss, ssid) {
		if (ss->early_init) {
			struct cgroup_subsys_state *css =
				init_css_set.subsys[ss->id];

			css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2,
						   GFP_KERNEL);
			BUG_ON(css->id < 0);
		} else {
			cgroup_init_subsys(ss, false);
		}

		list_add_tail(&init_css_set.e_cset_node[ssid],
			      &cgrp_dfl_root.cgrp.e_csets[ssid]);

		/*
		 * Setting dfl_root subsys_mask needs to consider the
		 * disabled flag and cftype registration needs kmalloc,
		 * both of which aren't available during early_init.
		 */
		if (ss->disabled)
			continue;

		cgrp_dfl_root.subsys_mask |= 1 << ss->id;

		if (cgroup_legacy_files_on_dfl && !ss->dfl_cftypes)
			ss->dfl_cftypes = ss->legacy_cftypes;

		if (!ss->dfl_cftypes)