cgroup.c

	/*
	 * We aren't being called from kernfs and there's no guarantee on
	 * @kn->priv's validity.  For this and css_tryget_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->dummy_css, &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);
}

/*
 * seq_operations functions for iterating on pidlists through seq_file -
 * independent of whether it's tasks or procs
 */
static const struct seq_operations cgroup_pidlist_seq_operations = {
	.start = cgroup_pidlist_start,
	.stop = cgroup_pidlist_stop,
	.next = cgroup_pidlist_next,
	.show = cgroup_pidlist_show,
};

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;
}

static struct cftype cgroup_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_u64 = cgroup_procs_write,
		.mode = S_IRUGO | S_IWUSR,
	},
	{
		.name = "cgroup.clone_children",
		.flags = CFTYPE_INSANE,
		.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,
	},

	/*
	 * Historical crazy stuff.  These don't have "cgroup."  prefix and
	 * don't exist if sane_behavior.  If you're depending on these, be
	 * prepared to be burned.
	 */
	{
		.name = "tasks",
		.flags = CFTYPE_INSANE,		/* use "procs" instead */
		.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_u64 = cgroup_tasks_write,
		.mode = S_IRUGO | S_IWUSR,
	},
	{
		.name = "notify_on_release",
		.flags = CFTYPE_INSANE,
		.read_u64 = cgroup_read_notify_on_release,
		.write_u64 = cgroup_write_notify_on_release,
	},
	{
		.name = "release_agent",
		.flags = CFTYPE_INSANE | CFTYPE_ONLY_ON_ROOT,
		.seq_show = cgroup_release_agent_show,
		.write_string = 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 long subsys_mask)
{
	struct cgroup_subsys *ss;
	int i, ret = 0;

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

		if (!test_bit(i, &subsys_mask))
			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() 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;

	if (css->parent)
		css_put(css->parent);

	css->ss->css_free(css);
	cgroup_put(cgrp);
}

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

	rcu_assign_pointer(css->cgroup->subsys[css->ss->id], NULL);
	call_rcu(&css->rcu_head, css_free_rcu_fn);
}

static void init_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss,
		     struct cgroup *cgrp)
{
	css->cgroup = cgrp;
	css->ss = ss;
	css->flags = 0;

	if (cgrp->parent)
		css->parent = cgroup_css(cgrp->parent, ss);
	else
		css->flags |= CSS_ROOT;

	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_tree_mutex);
	lockdep_assert_held(&cgroup_mutex);

	if (ss->css_online)
		ret = ss->css_online(css);
	if (!ret) {
		css->flags |= CSS_ONLINE;
		css->cgroup->nr_css++;
		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_tree_mutex);
	lockdep_assert_held(&cgroup_mutex);

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

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

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

/**
 * create_css - create a cgroup_subsys_state
 * @cgrp: the cgroup new css will be associated with
 * @ss: the subsys of new css
 *
 * 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.
 * Returns 0 on success, -errno on failure.
 */
static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
{
	struct cgroup *parent = cgrp->parent;
	struct cgroup_subsys_state *css;
	int err;

	lockdep_assert_held(&cgroup_mutex);

	css = ss->css_alloc(cgroup_css(parent, ss));
	if (IS_ERR(css))
		return PTR_ERR(css);

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

	init_css(css, ss, cgrp);

	err = cgroup_populate_dir(cgrp, 1 << ss->id);
	if (err)
		goto err_free;

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

	cgroup_get(cgrp);
	css_get(css->parent);

	if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
	    parent->parent) {
		pr_warning("cgroup: %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_warning("cgroup: \"memory\" requires setting use_hierarchy to 1 on the root.\n");
		ss->warned_broken_hierarchy = true;
	}

	return 0;

err_free:
	percpu_ref_cancel_init(&css->refcnt);
	ss->css_free(css);
	return err;
}

/**
 * cgroup_create - create a cgroup
 * @parent: cgroup that will be parent of the new cgroup
 * @name: name of the new cgroup
 * @mode: mode to set on new cgroup
 */
static long cgroup_create(struct cgroup *parent, const char *name,
			  umode_t mode)
{
	struct cgroup *cgrp;
	struct cgroupfs_root *root = parent->root;
	int ssid, err;
	struct cgroup_subsys *ss;
	struct kernfs_node *kn;

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

	mutex_lock(&cgroup_tree_mutex);

	/*
	 * Only live parents can have children.  Note that the liveliness
	 * check isn't strictly necessary because cgroup_mkdir() and
	 * cgroup_rmdir() are fully synchronized by i_mutex; however, do it
	 * anyway so that locking is contained inside cgroup proper and we
	 * don't get nasty surprises if we ever grow another caller.
	 */
	if (!cgroup_lock_live_group(parent)) {
		err = -ENODEV;
		goto err_unlock_tree;
	}

	/*
	 * Temporarily set the pointer to NULL, so idr_find() won't return
	 * a half-baked cgroup.
	 */
	cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
	if (cgrp->id < 0) {
		err = -ENOMEM;
		goto err_unlock;
	}

	init_cgroup_housekeeping(cgrp);

	cgrp->parent = parent;
	cgrp->dummy_css.parent = &parent->dummy_css;
	cgrp->root = parent->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)) {
		err = PTR_ERR(kn);
		goto err_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->serial_nr = cgroup_serial_nr_next++;

	/* allocation complete, commit to creation */
	list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->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.
	 */
	idr_replace(&root->cgroup_idr, cgrp, cgrp->id);

	err = cgroup_addrm_files(cgrp, cgroup_base_files, true);
	if (err)
		goto err_destroy;

	/* let's create and online css's */
	for_each_subsys(ss, ssid) {
		if (root->subsys_mask & (1 << ssid)) {
			err = create_css(cgrp, ss);
			if (err)
				goto err_destroy;
		}
	}

	kernfs_activate(kn);

	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&cgroup_tree_mutex);

	return 0;

err_free_id:
	idr_remove(&root->cgroup_idr, cgrp->id);
err_unlock:
	mutex_unlock(&cgroup_mutex);
err_unlock_tree:
	mutex_unlock(&cgroup_tree_mutex);
	kfree(cgrp);
	return err;

err_destroy:
	cgroup_destroy_locked(cgrp);
	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&cgroup_tree_mutex);
	return err;
}

static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
			umode_t mode)
{
	struct cgroup *parent = parent_kn->priv;

	return cgroup_create(parent, name, mode);
}

/*
 * This is called when the refcnt of a css is confirmed to be killed.
 * css_tryget() is now guaranteed to fail.
 */
static void css_killed_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;

	mutex_lock(&cgroup_tree_mutex);
	mutex_lock(&cgroup_mutex);

	/*
	 * css_tryget() is guaranteed to fail now.  Tell subsystems to
	 * initate destruction.
	 */
	offline_css(css);

	/*
	 * If @cgrp is marked dead, it's waiting for refs of all css's to
	 * be disabled before proceeding to the second phase of cgroup
	 * destruction.  If we are the last one, kick it off.
	 */
	if (!cgrp->nr_css && cgroup_is_dead(cgrp))
		cgroup_destroy_css_killed(cgrp);

	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&cgroup_tree_mutex);

	/*
	 * Put the css refs from kill_css().  Each css holds an extra
	 * reference to the cgroup's dentry and cgroup removal proceeds
	 * regardless of css refs.  On the last put of each css, whenever
	 * that may be, the extra dentry ref is put so that dentry
	 * destruction happens only after all css's are released.
	 */
	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() is guaranteed to fail and when the
 * reference count reaches zero, @css will be released.
 */
static void kill_css(struct cgroup_subsys_state *css)
{
	/*
	 * 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().  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() 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 *child;
	struct cgroup_subsys_state *css;
	bool empty;
	int ssid;

	lockdep_assert_held(&cgroup_tree_mutex);
	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 ->children
	 * emptiness as dead children linger on it while being destroyed;
	 * otherwise, "rmdir parent/child parent" may fail with -EBUSY.
	 */
	empty = true;
	rcu_read_lock();
	list_for_each_entry_rcu(child, &cgrp->children, sibling) {
		empty = cgroup_is_dead(child);
		if (!empty)
			break;
	}
	rcu_read_unlock();
	if (!empty)
		return -EBUSY;

	/*
	 * Initiate massacre of all css's.  cgroup_destroy_css_killed()
	 * will be invoked to perform the rest of destruction once the
	 * percpu refs of all css's are confirmed to be killed.  This
	 * involves removing the subsystem's files, drop cgroup_mutex.
	 */
	mutex_unlock(&cgroup_mutex);
	for_each_css(css, ssid, cgrp)
		kill_css(css);
	mutex_lock(&cgroup_mutex);

	/*
	 * Mark @cgrp dead.  This prevents further task migration and child
	 * creation by disabling cgroup_lock_live_group().  Note that
	 * CGRP_DEAD assertion is depended upon by css_next_child() to
	 * resume iteration after dropping RCU read lock.  See
	 * css_next_child() for details.
	 */
	set_bit(CGRP_DEAD, &cgrp->flags);

	/* CGRP_DEAD is set, 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);

	/*
	 * If @cgrp has css's attached, the second stage of cgroup
	 * destruction is kicked off from css_killed_work_fn() after the
	 * refs of all attached css's are killed.  If @cgrp doesn't have
	 * any css, we kick it off here.
	 */
	if (!cgrp->nr_css)
		cgroup_destroy_css_killed(cgrp);

	/* remove @cgrp directory along with the base files */
	mutex_unlock(&cgroup_mutex);

	/*
	 * There are two control paths which try to determine cgroup from
	 * dentry without going through kernfs - cgroupstats_build() and
	 * css_tryget_from_dir().  Those are supported by RCU protecting
	 * clearing of cgrp->kn->priv backpointer, which should happen
	 * after all files under it have been removed.
	 */
	kernfs_remove(cgrp->kn);	/* @cgrp has an extra ref on its kn */
	RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL);

	mutex_lock(&cgroup_mutex);

	return 0;
};

/**
 * cgroup_destroy_css_killed - the second step of cgroup destruction
 * @work: cgroup->destroy_free_work
 *
 * This function is invoked from a work item for a cgroup which is being
 * destroyed after all css's are offlined and performs the rest of
 * destruction.  This is the second step of destruction described in the
 * comment above cgroup_destroy_locked().
 */
static void cgroup_destroy_css_killed(struct cgroup *cgrp)
{
	struct cgroup *parent = cgrp->parent;

	lockdep_assert_held(&cgroup_tree_mutex);
	lockdep_assert_held(&cgroup_mutex);

	/* delete this cgroup from parent->children */
	list_del_rcu(&cgrp->sibling);

	cgroup_put(cgrp);

	set_bit(CGRP_RELEASABLE, &parent->flags);
	check_for_release(parent);
}

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

	/*
	 * This is self-destruction but @kn can't be removed while this
	 * callback is in progress.  Let's break active protection.  Once
	 * the protection is broken, @cgrp can be destroyed at any point.
	 * Pin it so that it stays accessible.
	 */
	cgroup_get(cgrp);
	kernfs_break_active_protection(kn);

	mutex_lock(&cgroup_tree_mutex);
	mutex_lock(&cgroup_mutex);

	/*
	 * @cgrp might already have been destroyed while we're trying to
	 * grab the mutexes.
	 */
	if (!cgroup_is_dead(cgrp))
		ret = cgroup_destroy_locked(cgrp);

	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&cgroup_tree_mutex);

	kernfs_unbreak_active_protection(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)
{
	struct cgroup_subsys_state *css;

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

	mutex_lock(&cgroup_tree_mutex);
	mutex_lock(&cgroup_mutex);

	INIT_LIST_HEAD(&ss->cfts);

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

	/* 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 top 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);
	mutex_unlock(&cgroup_tree_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)
{
	struct cgroup_subsys *ss;
	int i;

	atomic_set(&init_css_set.refcount, 1);
	INIT_LIST_HEAD(&init_css_set.cgrp_links);
	INIT_LIST_HEAD(&init_css_set.tasks);
	INIT_HLIST_NODE(&init_css_set.hlist);
	css_set_count = 1;
	init_cgroup_root(&cgroup_dummy_root);
	cgroup_root_count = 1;
	RCU_INIT_POINTER(init_task.cgroups, &init_css_set);

	init_cgrp_cset_link.cset = &init_css_set;
	init_cgrp_cset_link.cgrp = cgroup_dummy_top;
	list_add(&init_cgrp_cset_link.cset_link, &cgroup_dummy_top->cset_links);
	list_add(&init_cgrp_cset_link.cgrp_link, &init_css_set.cgrp_links);

	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);
	}
	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 i, err;

	BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files));

	for_each_subsys(ss, i) {
		if (!ss->early_init)
			cgroup_init_subsys(ss);

		/*
		 * cftype registration needs kmalloc and can't be done
		 * during early_init.  Register base cftypes separately.
		 */
		if (ss->base_cftypes)
			WARN_ON(cgroup_add_cftypes(ss, ss->base_cftypes));
	}

	/* allocate id for the dummy hierarchy */
	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_init_root_id(&cgroup_dummy_root, 0, 1));

	err = idr_alloc(&cgroup_dummy_root.cgroup_idr, cgroup_dummy_top,
			0, 1, GFP_KERNEL);
	BUG_ON(err < 0);

	mutex_unlock(&cgroup_mutex);

	cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
	if (!cgroup_kobj)
		return -ENOMEM;

	err = register_filesystem(&cgroup_fs_type);
	if (err < 0) {
		kobject_put(cgroup_kobj);
		return err;
	}

	proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations);
	return 0;
}

static int __init cgroup_wq_init(void)
{
	/*
	 * There isn't much point in executing destruction path in
	 * parallel.  Good chunk is serialized with cgroup_mutex anyway.
	 *
	 * XXX: Must be ordered to make sure parent is offlined after
	 * children.  The ordering requirement is for memcg where a
	 * parent's offline may wait for a child's leading to deadlock.  In
	 * the long term, this should be fixed from memcg side.
	 *
	 * We would prefer to do this in cgroup_init() above, but that
	 * is called before init_workqueues(): so leave this until after.
	 */
	cgroup_destroy_wq = alloc_ordered_workqueue("cgroup_destroy", 0);
	BUG_ON(!cgroup_destroy_wq);

	/*
	 * Used to destroy pidlists and separate to serve as flush domain.
	 * Cap @max_active to 1 too.
	 */
	cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy",
						    0, 1);
	BUG_ON(!cgroup_pidlist_destroy_wq);

	return 0;
}
core_initcall(cgroup_wq_init);

/*
 * proc_cgroup_show()
 *  - Print task's cgroup paths into seq_file, one line for each hierarchy
 *  - Used for /proc/<pid>/cgroup.
 *  - No need to task_lock(tsk) on this tsk->cgroup reference, as it
 *    doesn't really matter if tsk->cgroup changes after we read it,
 *    and we take cgroup_mutex, keeping cgroup_attach_task() from changing it
 *    anyway.  No need to check that tsk->cgroup != NULL, thanks to
 *    the_top_cgroup_hack in cgroup_exit(), which sets an exiting tasks