cgroup.c

	 * don't get nasty surprises if we ever grow another caller.
	 */
	if (!cgroup_lock_live_group(parent)) {
		err = -ENODEV;
		goto err_free;
	}

	/* Grab a reference on the superblock so the hierarchy doesn't
	 * get deleted on unmount if there are child cgroups.  This
	 * can be done outside cgroup_mutex, since the sb can't
	 * disappear while someone has an open control file on the
	 * fs */
	atomic_inc(&sb->s_active);

	init_cgroup_housekeeping(cgrp);

	cgrp->parent = parent;
	cgrp->root = parent->root;
	cgrp->top_cgroup = parent->top_cgroup;

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

	if (clone_children(parent))
		set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);

	for_each_subsys(root, ss) {
		struct cgroup_subsys_state *css;

		css = ss->create(cgrp);
		if (IS_ERR(css)) {
			err = PTR_ERR(css);
			goto err_destroy;
		}
		init_cgroup_css(css, ss, cgrp);
		if (ss->use_id) {
			err = alloc_css_id(ss, parent, cgrp);
			if (err)
				goto err_destroy;
		}
		/* At error, ->destroy() callback has to free assigned ID. */
		if (clone_children(parent) && ss->post_clone)
			ss->post_clone(cgrp);

		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;
		}
	}

	list_add(&cgrp->sibling, &cgrp->parent->children);
	root->number_of_cgroups++;

	err = cgroup_create_dir(cgrp, dentry, mode);
	if (err < 0)
		goto err_remove;

	/* each css holds a ref to the cgroup's dentry */
	for_each_subsys(root, ss)
		dget(dentry);

	/* The cgroup directory was pre-locked for us */
	BUG_ON(!mutex_is_locked(&cgrp->dentry->d_inode->i_mutex));

	list_add_tail(&cgrp->allcg_node, &root->allcg_list);

	err = cgroup_populate_dir(cgrp, true, root->subsys_mask);
	/* If err < 0, we have a half-filled directory - oh well ;) */

	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);

	return 0;

 err_remove:

	list_del(&cgrp->sibling);
	root->number_of_cgroups--;

 err_destroy:

	for_each_subsys(root, ss) {
		if (cgrp->subsys[ss->subsys_id])
			ss->destroy(cgrp);
	}

	mutex_unlock(&cgroup_mutex);

	/* Release the reference count that we took on the superblock */
	deactivate_super(sb);
err_free:
	kfree(cgrp);
	return err;
}

static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
	struct cgroup *c_parent = dentry->d_parent->d_fsdata;

	/* the vfs holds inode->i_mutex already */
	return cgroup_create(c_parent, dentry, mode | S_IFDIR);
}

/*
 * Check the reference count on each subsystem. Since we already
 * established that there are no tasks in the cgroup, if the css refcount
 * is also 1, then there should be no outstanding references, so the
 * subsystem is safe to destroy. We scan across all subsystems rather than
 * using the per-hierarchy linked list of mounted subsystems since we can
 * be called via check_for_release() with no synchronization other than
 * RCU, and the subsystem linked list isn't RCU-safe.
 */
static int cgroup_has_css_refs(struct cgroup *cgrp)
{
	int i;

	/*
	 * We won't need to lock the subsys array, because the subsystems
	 * we're concerned about aren't going anywhere since our cgroup root
	 * has a reference on them.
	 */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		struct cgroup_subsys_state *css;

		/* Skip subsystems not present or not in this hierarchy */
		if (ss == NULL || ss->root != cgrp->root)
			continue;

		css = cgrp->subsys[ss->subsys_id];
		/*
		 * When called from check_for_release() it's possible
		 * that by this point the cgroup has been removed
		 * and the css deleted. But a false-positive doesn't
		 * matter, since it can only happen if the cgroup
		 * has been deleted and hence no longer needs the
		 * release agent to be called anyway.
		 */
		if (css && css_refcnt(css) > 1)
			return 1;
	}
	return 0;
}

static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
{
	struct cgroup *cgrp = dentry->d_fsdata;
	struct dentry *d;
	struct cgroup *parent;
	DEFINE_WAIT(wait);
	struct cgroup_event *event, *tmp;
	struct cgroup_subsys *ss;

	/* the vfs holds both inode->i_mutex already */
	mutex_lock(&cgroup_mutex);
	parent = cgrp->parent;
	if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}

	/*
	 * Block new css_tryget() by deactivating refcnt and mark @cgrp
	 * removed.  This makes future css_tryget() and child creation
	 * attempts fail thus maintaining the removal conditions verified
	 * above.
	 */
	for_each_subsys(cgrp->root, ss) {
		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];

		WARN_ON(atomic_read(&css->refcnt) < 0);
		atomic_add(CSS_DEACT_BIAS, &css->refcnt);
	}
	set_bit(CGRP_REMOVED, &cgrp->flags);

	/*
	 * Tell subsystems to initate destruction.  pre_destroy() should be
	 * called with cgroup_mutex unlocked.  See 3fa59dfbc3 ("cgroup: fix
	 * potential deadlock in pre_destroy") for details.
	 */
	mutex_unlock(&cgroup_mutex);
	for_each_subsys(cgrp->root, ss)
		if (ss->pre_destroy)
			ss->pre_destroy(cgrp);
	mutex_lock(&cgroup_mutex);

	/*
	 * Put all the base refs.  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.
	 */
	for_each_subsys(cgrp->root, ss)
		css_put(cgrp->subsys[ss->subsys_id]);

	raw_spin_lock(&release_list_lock);
	if (!list_empty(&cgrp->release_list))
		list_del_init(&cgrp->release_list);
	raw_spin_unlock(&release_list_lock);

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

	list_del_init(&cgrp->allcg_node);

	d = dget(cgrp->dentry);

	cgroup_d_remove_dir(d);
	dput(d);

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

	/*
	 * Unregister events and notify userspace.
	 * Notify userspace about cgroup removing only after rmdir of cgroup
	 * directory to avoid race between userspace and kernelspace
	 */
	spin_lock(&cgrp->event_list_lock);
	list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
		list_del(&event->list);
		remove_wait_queue(event->wqh, &event->wait);
		eventfd_signal(event->eventfd, 1);
		schedule_work(&event->remove);
	}
	spin_unlock(&cgrp->event_list_lock);

	mutex_unlock(&cgroup_mutex);
	return 0;
}

static void __init_or_module cgroup_init_cftsets(struct cgroup_subsys *ss)
{
	INIT_LIST_HEAD(&ss->cftsets);

	/*
	 * base_cftset is embedded in subsys itself, no need to worry about
	 * deregistration.
	 */
	if (ss->base_cftypes) {
		ss->base_cftset.cfts = ss->base_cftypes;
		list_add_tail(&ss->base_cftset.node, &ss->cftsets);
	}
}

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);

	/* init base cftset */
	cgroup_init_cftsets(ss);

	/* Create the top cgroup state for this subsystem */
	list_add(&ss->sibling, &rootnode.subsys_list);
	ss->root = &rootnode;
	css = ss->create(dummytop);
	/* We don't handle early failures gracefully */
	BUG_ON(IS_ERR(css));
	init_cgroup_css(css, ss, dummytop);

	/* 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->subsys_id] = dummytop->subsys[ss->subsys_id];

	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));

	ss->active = 1;

	/* this function shouldn't be used with modular subsystems, since they
	 * need to register a subsys_id, among other things */
	BUG_ON(ss->module);
}

/**
 * cgroup_load_subsys: load and register a modular subsystem at runtime
 * @ss: the subsystem to load
 *
 * This function should be called in a modular subsystem's initcall. If the
 * subsystem is built as a module, it will be assigned a new subsys_id and set
 * up for use. If the subsystem is built-in anyway, work is delegated to the
 * simpler cgroup_init_subsys.
 */
int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
{
	int i;
	struct cgroup_subsys_state *css;

	/* check name and function validity */
	if (ss->name == NULL || strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN ||
	    ss->create == NULL || ss->destroy == NULL)
		return -EINVAL;

	/*
	 * we don't support callbacks in modular subsystems. this check is
	 * before the ss->module check for consistency; a subsystem that could
	 * be a module should still have no callbacks even if the user isn't
	 * compiling it as one.
	 */
	if (ss->fork || ss->exit)
		return -EINVAL;

	/*
	 * an optionally modular subsystem is built-in: we want to do nothing,
	 * since cgroup_init_subsys will have already taken care of it.
	 */
	if (ss->module == NULL) {
		/* a sanity check */
		BUG_ON(subsys[ss->subsys_id] != ss);
		return 0;
	}

	/* init base cftset */
	cgroup_init_cftsets(ss);

	mutex_lock(&cgroup_mutex);
	subsys[ss->subsys_id] = ss;

	/*
	 * no ss->create seems to need anything important in the ss struct, so
	 * this can happen first (i.e. before the rootnode attachment).
	 */
	css = ss->create(dummytop);
	if (IS_ERR(css)) {
		/* failure case - need to deassign the subsys[] slot. */
		subsys[ss->subsys_id] = NULL;
		mutex_unlock(&cgroup_mutex);
		return PTR_ERR(css);
	}

	list_add(&ss->sibling, &rootnode.subsys_list);
	ss->root = &rootnode;

	/* our new subsystem will be attached to the dummy hierarchy. */
	init_cgroup_css(css, ss, dummytop);
	/* init_idr must be after init_cgroup_css because it sets css->id. */
	if (ss->use_id) {
		int ret = cgroup_init_idr(ss, css);
		if (ret) {
			dummytop->subsys[ss->subsys_id] = NULL;
			ss->destroy(dummytop);
			subsys[ss->subsys_id] = NULL;
			mutex_unlock(&cgroup_mutex);
			return ret;
		}
	}

	/*
	 * Now we need to entangle the css into the existing css_sets. unlike
	 * in cgroup_init_subsys, there are now multiple css_sets, so each one
	 * will need a new pointer to it; done by iterating the css_set_table.
	 * furthermore, modifying the existing css_sets will corrupt the hash
	 * table state, so each changed css_set will need its hash recomputed.
	 * this is all done under the css_set_lock.
	 */
	write_lock(&css_set_lock);
	for (i = 0; i < CSS_SET_TABLE_SIZE; i++) {
		struct css_set *cg;
		struct hlist_node *node, *tmp;
		struct hlist_head *bucket = &css_set_table[i], *new_bucket;

		hlist_for_each_entry_safe(cg, node, tmp, bucket, hlist) {
			/* skip entries that we already rehashed */
			if (cg->subsys[ss->subsys_id])
				continue;
			/* remove existing entry */
			hlist_del(&cg->hlist);
			/* set new value */
			cg->subsys[ss->subsys_id] = css;
			/* recompute hash and restore entry */
			new_bucket = css_set_hash(cg->subsys);
			hlist_add_head(&cg->hlist, new_bucket);
		}
	}
	write_unlock(&css_set_lock);

	ss->active = 1;

	/* success! */
	mutex_unlock(&cgroup_mutex);
	return 0;
}
EXPORT_SYMBOL_GPL(cgroup_load_subsys);

/**
 * cgroup_unload_subsys: unload a modular subsystem
 * @ss: the subsystem to unload
 *
 * This function should be called in a modular subsystem's exitcall. When this
 * function is invoked, the refcount on the subsystem's module will be 0, so
 * the subsystem will not be attached to any hierarchy.
 */
void cgroup_unload_subsys(struct cgroup_subsys *ss)
{
	struct cg_cgroup_link *link;
	struct hlist_head *hhead;

	BUG_ON(ss->module == NULL);

	/*
	 * we shouldn't be called if the subsystem is in use, and the use of
	 * try_module_get in parse_cgroupfs_options should ensure that it
	 * doesn't start being used while we're killing it off.
	 */
	BUG_ON(ss->root != &rootnode);

	mutex_lock(&cgroup_mutex);
	/* deassign the subsys_id */
	subsys[ss->subsys_id] = NULL;

	/* remove subsystem from rootnode's list of subsystems */
	list_del_init(&ss->sibling);

	/*
	 * disentangle the css from all css_sets attached to the dummytop. as
	 * in loading, we need to pay our respects to the hashtable gods.
	 */
	write_lock(&css_set_lock);
	list_for_each_entry(link, &dummytop->css_sets, cgrp_link_list) {
		struct css_set *cg = link->cg;

		hlist_del(&cg->hlist);
		BUG_ON(!cg->subsys[ss->subsys_id]);
		cg->subsys[ss->subsys_id] = NULL;
		hhead = css_set_hash(cg->subsys);
		hlist_add_head(&cg->hlist, hhead);
	}
	write_unlock(&css_set_lock);

	/*
	 * remove subsystem's css from the dummytop and free it - need to free
	 * before marking as null because ss->destroy needs the cgrp->subsys
	 * pointer to find their state. note that this also takes care of
	 * freeing the css_id.
	 */
	ss->destroy(dummytop);
	dummytop->subsys[ss->subsys_id] = NULL;

	mutex_unlock(&cgroup_mutex);
}
EXPORT_SYMBOL_GPL(cgroup_unload_subsys);

/**
 * 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)
{
	int i;
	atomic_set(&init_css_set.refcount, 1);
	INIT_LIST_HEAD(&init_css_set.cg_links);
	INIT_LIST_HEAD(&init_css_set.tasks);
	INIT_HLIST_NODE(&init_css_set.hlist);
	css_set_count = 1;
	init_cgroup_root(&rootnode);
	root_count = 1;
	init_task.cgroups = &init_css_set;

	init_css_set_link.cg = &init_css_set;
	init_css_set_link.cgrp = dummytop;
	list_add(&init_css_set_link.cgrp_link_list,
		 &rootnode.top_cgroup.css_sets);
	list_add(&init_css_set_link.cg_link_list,
		 &init_css_set.cg_links);

	for (i = 0; i < CSS_SET_TABLE_SIZE; i++)
		INIT_HLIST_HEAD(&css_set_table[i]);

	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];

		/* at bootup time, we don't worry about modular subsystems */
		if (!ss || ss->module)
			continue;

		BUG_ON(!ss->name);
		BUG_ON(strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN);
		BUG_ON(!ss->create);
		BUG_ON(!ss->destroy);
		if (ss->subsys_id != i) {
			printk(KERN_ERR "cgroup: Subsys %s id == %d\n",
			       ss->name, ss->subsys_id);
			BUG();
		}

		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)
{
	int err;
	int i;
	struct hlist_head *hhead;

	err = bdi_init(&cgroup_backing_dev_info);
	if (err)
		return err;

	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];

		/* at bootup time, we don't worry about modular subsystems */
		if (!ss || ss->module)
			continue;
		if (!ss->early_init)
			cgroup_init_subsys(ss);
		if (ss->use_id)
			cgroup_init_idr(ss, init_css_set.subsys[ss->subsys_id]);
	}

	/* Add init_css_set to the hash table */
	hhead = css_set_hash(init_css_set.subsys);
	hlist_add_head(&init_css_set.hlist, hhead);
	BUG_ON(!init_root_id(&rootnode));

	cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
	if (!cgroup_kobj) {
		err = -ENOMEM;
		goto out;
	}

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

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

out:
	if (err)
		bdi_destroy(&cgroup_backing_dev_info);

	return err;
}

/*
 * 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
 *    cgroup to top_cgroup.
 */

/* TODO: Use a proper seq_file iterator */
static int proc_cgroup_show(struct seq_file *m, void *v)
{
	struct pid *pid;
	struct task_struct *tsk;
	char *buf;
	int retval;
	struct cgroupfs_root *root;

	retval = -ENOMEM;
	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
	if (!buf)
		goto out;

	retval = -ESRCH;
	pid = m->private;
	tsk = get_pid_task(pid, PIDTYPE_PID);
	if (!tsk)
		goto out_free;

	retval = 0;

	mutex_lock(&cgroup_mutex);

	for_each_active_root(root) {
		struct cgroup_subsys *ss;
		struct cgroup *cgrp;
		int count = 0;

		seq_printf(m, "%d:", root->hierarchy_id);
		for_each_subsys(root, ss)
			seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
		if (strlen(root->name))
			seq_printf(m, "%sname=%s", count ? "," : "",
				   root->name);
		seq_putc(m, ':');
		cgrp = task_cgroup_from_root(tsk, root);
		retval = cgroup_path(cgrp, buf, PAGE_SIZE);
		if (retval < 0)
			goto out_unlock;
		seq_puts(m, buf);
		seq_putc(m, '\n');
	}

out_unlock:
	mutex_unlock(&cgroup_mutex);
	put_task_struct(tsk);
out_free:
	kfree(buf);
out:
	return retval;
}

static int cgroup_open(struct inode *inode, struct file *file)
{
	struct pid *pid = PROC_I(inode)->pid;
	return single_open(file, proc_cgroup_show, pid);
}

const struct file_operations proc_cgroup_operations = {
	.open		= cgroup_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
};

/* Display information about each subsystem and each hierarchy */
static int proc_cgroupstats_show(struct seq_file *m, void *v)
{
	int i;

	seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n");
	/*
	 * ideally we don't want subsystems moving around while we do this.
	 * cgroup_mutex is also necessary to guarantee an atomic snapshot of
	 * subsys/hierarchy state.
	 */
	mutex_lock(&cgroup_mutex);
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		if (ss == NULL)
			continue;
		seq_printf(m, "%s\t%d\t%d\t%d\n",
			   ss->name, ss->root->hierarchy_id,
			   ss->root->number_of_cgroups, !ss->disabled);
	}
	mutex_unlock(&cgroup_mutex);
	return 0;
}

static int cgroupstats_open(struct inode *inode, struct file *file)
{
	return single_open(file, proc_cgroupstats_show, NULL);
}

static const struct file_operations proc_cgroupstats_operations = {
	.open = cgroupstats_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = single_release,
};

/**
 * cgroup_fork - attach newly forked task to its parents cgroup.
 * @child: pointer to task_struct of forking parent process.
 *
 * Description: A task inherits its parent's cgroup at fork().
 *
 * A pointer to the shared css_set was automatically copied in
 * fork.c by dup_task_struct().  However, we ignore that copy, since
 * it was not made under the protection of RCU or cgroup_mutex, so
 * might no longer be a valid cgroup pointer.  cgroup_attach_task() might
 * have already changed current->cgroups, allowing the previously
 * referenced cgroup group to be removed and freed.
 *
 * At the point that cgroup_fork() is called, 'current' is the parent
 * task, and the passed argument 'child' points to the child task.
 */
void cgroup_fork(struct task_struct *child)
{
	task_lock(current);
	child->cgroups = current->cgroups;
	get_css_set(child->cgroups);
	task_unlock(current);
	INIT_LIST_HEAD(&child->cg_list);
}

/**
 * cgroup_post_fork - called on a new task after adding it to the task list
 * @child: the task in question
 *
 * Adds the task to the list running through its css_set if necessary and
 * call the subsystem fork() callbacks.  Has to be after the task is
 * visible on the task list in case we race with the first call to
 * cgroup_iter_start() - to guarantee that the new task ends up on its
 * list.
 */
void cgroup_post_fork(struct task_struct *child)
{
	int i;

	/*
	 * use_task_css_set_links is set to 1 before we walk the tasklist
	 * under the tasklist_lock and we read it here after we added the child
	 * to the tasklist under the tasklist_lock as well. If the child wasn't
	 * yet in the tasklist when we walked through it from
	 * cgroup_enable_task_cg_lists(), then use_task_css_set_links value
	 * should be visible now due to the paired locking and barriers implied
	 * by LOCK/UNLOCK: it is written before the tasklist_lock unlock
	 * in cgroup_enable_task_cg_lists() and read here after the tasklist_lock
	 * lock on fork.
	 */
	if (use_task_css_set_links) {
		write_lock(&css_set_lock);
		task_lock(child);
		if (list_empty(&child->cg_list))
			list_add(&child->cg_list, &child->cgroups->tasks);
		task_unlock(child);
		write_unlock(&css_set_lock);
	}

	/*
	 * Call ss->fork().  This must happen after @child is linked on
	 * css_set; otherwise, @child might change state between ->fork()
	 * and addition to css_set.
	 */
	if (need_forkexit_callback) {
		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
			struct cgroup_subsys *ss = subsys[i];

			/*
			 * fork/exit callbacks are supported only for
			 * builtin subsystems and we don't need further
			 * synchronization as they never go away.
			 */
			if (!ss || ss->module)
				continue;

			if (ss->fork)
				ss->fork(child);
		}
	}
}

/**
 * cgroup_exit - detach cgroup from exiting task
 * @tsk: pointer to task_struct of exiting process
 * @run_callback: run exit callbacks?
 *
 * Description: Detach cgroup from @tsk and release it.
 *
 * Note that cgroups marked notify_on_release force every task in
 * them to take the global cgroup_mutex mutex when exiting.
 * This could impact scaling on very large systems.  Be reluctant to
 * use notify_on_release cgroups where very high task exit scaling
 * is required on large systems.
 *
 * the_top_cgroup_hack:
 *
 *    Set the exiting tasks cgroup to the root cgroup (top_cgroup).
 *
 *    We call cgroup_exit() while the task is still competent to
 *    handle notify_on_release(), then leave the task attached to the
 *    root cgroup in each hierarchy for the remainder of its exit.
 *
 *    To do this properly, we would increment the reference count on
 *    top_cgroup, and near the very end of the kernel/exit.c do_exit()
 *    code we would add a second cgroup function call, to drop that
 *    reference.  This would just create an unnecessary hot spot on
 *    the top_cgroup reference count, to no avail.
 *
 *    Normally, holding a reference to a cgroup without bumping its
 *    count is unsafe.   The cgroup could go away, or someone could
 *    attach us to a different cgroup, decrementing the count on
 *    the first cgroup that we never incremented.  But in this case,
 *    top_cgroup isn't going away, and either task has PF_EXITING set,
 *    which wards off any cgroup_attach_task() attempts, or task is a failed
 *    fork, never visible to cgroup_attach_task.
 */
void cgroup_exit(struct task_struct *tsk, int run_callbacks)
{
	struct css_set *cg;
	int i;

	/*
	 * Unlink from the css_set task list if necessary.
	 * Optimistically check cg_list before taking
	 * css_set_lock
	 */
	if (!list_empty(&tsk->cg_list)) {
		write_lock(&css_set_lock);
		if (!list_empty(&tsk->cg_list))
			list_del_init(&tsk->cg_list);
		write_unlock(&css_set_lock);
	}

	/* Reassign the task to the init_css_set. */
	task_lock(tsk);
	cg = tsk->cgroups;
	tsk->cgroups = &init_css_set;

	if (run_callbacks && need_forkexit_callback) {
		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
			struct cgroup_subsys *ss = subsys[i];

			/* modular subsystems can't use callbacks */
			if (!ss || ss->module)
				continue;

			if (ss->exit) {
				struct cgroup *old_cgrp =
					rcu_dereference_raw(cg->subsys[i])->cgroup;
				struct cgroup *cgrp = task_cgroup(tsk, i);
				ss->exit(cgrp, old_cgrp, tsk);
			}
		}
	}
	task_unlock(tsk);

	if (cg)
		put_css_set_taskexit(cg);
}

/**
 * cgroup_is_descendant - see if @cgrp is a descendant of @task's cgrp
 * @cgrp: the cgroup in question
 * @task: the task in question
 *
 * See if @cgrp is a descendant of @task's cgroup in the appropriate
 * hierarchy.
 *
 * If we are sending in dummytop, then presumably we are creating
 * the top cgroup in the subsystem.
 *
 * Called only by the ns (nsproxy) cgroup.
 */
int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task)
{
	int ret;
	struct cgroup *target;

	if (cgrp == dummytop)
		return 1;

	target = task_cgroup_from_root(task, cgrp->root);
	while (cgrp != target && cgrp!= cgrp->top_cgroup)
		cgrp = cgrp->parent;
	ret = (cgrp == target);
	return ret;
}

static void check_for_release(struct cgroup *cgrp)
{
	/* All of these checks rely on RCU to keep the cgroup
	 * structure alive */
	if (cgroup_is_releasable(cgrp) && !atomic_read(&cgrp->count)
	    && list_empty(&cgrp->children) && !cgroup_has_css_refs(cgrp)) {
		/* Control Group is currently removeable. If it's not
		 * already queued for a userspace notification, queue
		 * it now */
		int need_schedule_work = 0;
		raw_spin_lock(&release_list_lock);
		if (!cgroup_is_removed(cgrp) &&
		    list_empty(&cgrp->release_list)) {
			list_add(&cgrp->release_list, &release_list);
			need_schedule_work = 1;
		}
		raw_spin_unlock(&release_list_lock);
		if (need_schedule_work)
			schedule_work(&release_agent_work);
	}
}

/* Caller must verify that the css is not for root cgroup */
bool __css_tryget(struct cgroup_subsys_state *css)
{
	while (true) {
		int t, v;

		v = css_refcnt(css);
		t = atomic_cmpxchg(&css->refcnt, v, v + 1);
		if (likely(t == v))
			return true;
		else if (t < 0)
			return false;
		cpu_relax();
	}
}
EXPORT_SYMBOL_GPL(__css_tryget);

/* Caller must verify that the css is not for root cgroup */
void __css_put(struct cgroup_subsys_state *css)
{
	struct cgroup *cgrp = css->cgroup;
	int v;

	rcu_read_lock();
	v = css_unbias_refcnt(atomic_dec_return(&css->refcnt));

	switch (v) {
	case 1:
		if (notify_on_release(cgrp)) {
			set_bit(CGRP_RELEASABLE, &cgrp->flags);
			check_for_release(cgrp);
		}
		break;
	case 0:
		schedule_work(&css->dput_work);
		break;
	}
	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(__css_put);

/*
 * Notify userspace when a cgroup is released, by running the
 * configured release agent with the name of the cgroup (path
 * relative to the root of cgroup file system) as the argument.
 *
 * Most likely, this user command will try to rmdir this cgroup.
 *
 * This races with the possibility that some other task will be
 * attached to this cgroup before it is removed, or that some other
 * user task will 'mkdir' a child cgroup of this cgroup.  That's ok.
 * The presumed 'rmdir' will fail quietly if this cgroup is no longer
 * unused, and this cgroup will be reprieved from its death sentence,
 * to continue to serve a useful existence.  Next time it's released,
 * we will get notified again, if it still has 'notify_on_release' set.
 *
 * The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which
 * means only wait until the task is successfully execve()'d.  The
 * separate release agent task is forked by call_usermodehelper(),
 * then control in this thread returns here, without waiting for the
 * release agent task.  We don't bother to wait because the caller of
 * this routine has no use for the exit status of the release agent
 * task, so no sense holding our caller up for that.
 */
static void cgroup_release_agent(struct work_struct *work)
{
	BUG_ON(work != &release_agent_work);
	mutex_lock(&cgroup_mutex);
	raw_spin_lock(&release_list_lock);
	while (!list_empty(&release_list)) {
		char *argv[3], *envp[3];
		int i;
		char *pathbuf = NULL, *agentbuf = NULL;
		struct cgroup *cgrp = list_entry(release_list.next,
						    struct cgroup,
						    release_list);
		list_del_init(&cgrp->release_list);
		raw_spin_unlock(&release_list_lock);
		pathbuf = kmalloc(PAGE_SIZE, GFP_KERNEL);
		if (!pathbuf)
			goto continue_free;
		if (cgroup_path(cgrp, pathbuf, PAGE_SIZE) < 0)
			goto continue_free;
		agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
		if (!agentbuf)
			goto continue_free;

		i = 0;
		argv[i++] = agentbuf;
		argv[i++] = pathbuf;
		argv[i] = NULL;

		i = 0;
		/* minimal command environment */
		envp[i++] = "HOME=/";
		envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
		envp[i] = NULL;

		/* Drop the lock while we invoke the usermode helper,
		 * since the exec could involve hitting disk and hence
		 * be a slow process */
		mutex_unlock(&cgroup_mutex);
		call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
		mutex_lock(&cgroup_mutex);
 continue_free:
		kfree(pathbuf);
		kfree(agentbuf);
		raw_spin_lock(&release_list_lock);
	}
	raw_spin_unlock(&release_list_lock);
	mutex_unlock(&cgroup_mutex);
}

static int __init cgroup_disable(char *str)
{