cgroup.c

	 */
	set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);

	/*
	 * Call pre_destroy handlers of subsys. Notify subsystems
	 * that rmdir() request comes.
	 */
	ret = cgroup_call_pre_destroy(cgrp);
	if (ret) {
		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
		return ret;
	}

	mutex_lock(&cgroup_mutex);
	parent = cgrp->parent;
	if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}
	prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE);
	if (!cgroup_clear_css_refs(cgrp)) {
		mutex_unlock(&cgroup_mutex);
		/*
		 * Because someone may call cgroup_wakeup_rmdir_waiter() before
		 * prepare_to_wait(), we need to check this flag.
		 */
		if (test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags))
			schedule();
		finish_wait(&cgroup_rmdir_waitq, &wait);
		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
		if (signal_pending(current))
			return -EINTR;
		goto again;
	}
	/* NO css_tryget() can success after here. */
	finish_wait(&cgroup_rmdir_waitq, &wait);
	clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);

	spin_lock(&release_list_lock);
	set_bit(CGRP_REMOVED, &cgrp->flags);
	if (!list_empty(&cgrp->release_list))
		list_del(&cgrp->release_list);
	spin_unlock(&release_list_lock);

	cgroup_lock_hierarchy(cgrp->root);
	/* delete this cgroup from parent->children */
	list_del(&cgrp->sibling);
	cgroup_unlock_hierarchy(cgrp->root);

	spin_lock(&cgrp->dentry->d_lock);
	d = dget(cgrp->dentry);
	spin_unlock(&d->d_lock);

	cgroup_d_remove_dir(d);
	dput(d);

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

	mutex_unlock(&cgroup_mutex);
	return 0;
}

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);

	/* Create the top cgroup state for this subsystem */
	list_add(&ss->sibling, &rootnode.subsys_list);
	ss->root = &rootnode;
	css = ss->create(ss, 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));

	mutex_init(&ss->hierarchy_mutex);
	lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
	ss->active = 1;
}

/**
 * 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];

		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];
		if (!ss->early_init)
			cgroup_init_subsys(ss);
		if (ss->use_id)
			cgroup_subsys_init_idr(ss);
	}

	/* 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));
	err = register_filesystem(&cgroup_fs_type);
	if (err < 0)
		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);
}

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");
	mutex_lock(&cgroup_mutex);
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		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 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_fork_callbacks - run fork callbacks
 * @child: the new task
 *
 * Called on a new task very soon before adding it to the
 * tasklist. No need to take any locks since no-one can
 * be operating on this task.
 */
void cgroup_fork_callbacks(struct task_struct *child)
{
	if (need_forkexit_callback) {
		int i;
		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
			struct cgroup_subsys *ss = subsys[i];
			if (ss->fork)
				ss->fork(ss, child);
		}
	}
}

/**
 * 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.
 * 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)
{
	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);
	}
}
/**
 * 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)
{
	int i;
	struct css_set *cg;

	if (run_callbacks && need_forkexit_callback) {
		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
			struct cgroup_subsys *ss = subsys[i];
			if (ss->exit)
				ss->exit(ss, tsk);
		}
	}

	/*
	 * 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(&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;
	task_unlock(tsk);
	if (cg)
		put_css_set_taskexit(cg);
}

/**
 * cgroup_clone - clone the cgroup the given subsystem is attached to
 * @tsk: the task to be moved
 * @subsys: the given subsystem
 * @nodename: the name for the new cgroup
 *
 * Duplicate the current cgroup in the hierarchy that the given
 * subsystem is attached to, and move this task into the new
 * child.
 */
int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
							char *nodename)
{
	struct dentry *dentry;
	int ret = 0;
	struct cgroup *parent, *child;
	struct inode *inode;
	struct css_set *cg;
	struct cgroupfs_root *root;
	struct cgroup_subsys *ss;

	/* We shouldn't be called by an unregistered subsystem */
	BUG_ON(!subsys->active);

	/* First figure out what hierarchy and cgroup we're dealing
	 * with, and pin them so we can drop cgroup_mutex */
	mutex_lock(&cgroup_mutex);
 again:
	root = subsys->root;
	if (root == &rootnode) {
		mutex_unlock(&cgroup_mutex);
		return 0;
	}

	/* Pin the hierarchy */
	if (!atomic_inc_not_zero(&root->sb->s_active)) {
		/* We race with the final deactivate_super() */
		mutex_unlock(&cgroup_mutex);
		return 0;
	}

	/* Keep the cgroup alive */
	task_lock(tsk);
	parent = task_cgroup(tsk, subsys->subsys_id);
	cg = tsk->cgroups;
	get_css_set(cg);
	task_unlock(tsk);

	mutex_unlock(&cgroup_mutex);

	/* Now do the VFS work to create a cgroup */
	inode = parent->dentry->d_inode;

	/* Hold the parent directory mutex across this operation to
	 * stop anyone else deleting the new cgroup */
	mutex_lock(&inode->i_mutex);
	dentry = lookup_one_len(nodename, parent->dentry, strlen(nodename));
	if (IS_ERR(dentry)) {
		printk(KERN_INFO
		       "cgroup: Couldn't allocate dentry for %s: %ld\n", nodename,
		       PTR_ERR(dentry));
		ret = PTR_ERR(dentry);
		goto out_release;
	}

	/* Create the cgroup directory, which also creates the cgroup */
	ret = vfs_mkdir(inode, dentry, 0755);
	child = __d_cgrp(dentry);
	dput(dentry);
	if (ret) {
		printk(KERN_INFO
		       "Failed to create cgroup %s: %d\n", nodename,
		       ret);
		goto out_release;
	}

	/* The cgroup now exists. Retake cgroup_mutex and check
	 * that we're still in the same state that we thought we
	 * were. */
	mutex_lock(&cgroup_mutex);
	if ((root != subsys->root) ||
	    (parent != task_cgroup(tsk, subsys->subsys_id))) {
		/* Aargh, we raced ... */
		mutex_unlock(&inode->i_mutex);
		put_css_set(cg);

		deactivate_super(root->sb);
		/* The cgroup is still accessible in the VFS, but
		 * we're not going to try to rmdir() it at this
		 * point. */
		printk(KERN_INFO
		       "Race in cgroup_clone() - leaking cgroup %s\n",
		       nodename);
		goto again;
	}

	/* do any required auto-setup */
	for_each_subsys(root, ss) {
		if (ss->post_clone)
			ss->post_clone(ss, child);
	}

	/* All seems fine. Finish by moving the task into the new cgroup */
	ret = cgroup_attach_task(child, tsk);
	mutex_unlock(&cgroup_mutex);

 out_release:
	mutex_unlock(&inode->i_mutex);

	mutex_lock(&cgroup_mutex);
	put_css_set(cg);
	mutex_unlock(&cgroup_mutex);
	deactivate_super(root->sb);
	return ret;
}

/**
 * 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;
		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;
		}
		spin_unlock(&release_list_lock);
		if (need_schedule_work)
			schedule_work(&release_agent_work);
	}
}

void __css_put(struct cgroup_subsys_state *css)
{
	struct cgroup *cgrp = css->cgroup;
	rcu_read_lock();
	if (atomic_dec_return(&css->refcnt) == 1) {
		if (notify_on_release(cgrp)) {
			set_bit(CGRP_RELEASABLE, &cgrp->flags);
			check_for_release(cgrp);
		}
		cgroup_wakeup_rmdir_waiter(cgrp);
	}
	rcu_read_unlock();
}

/*
 * 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);
	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);
		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);
		spin_lock(&release_list_lock);
	}
	spin_unlock(&release_list_lock);
	mutex_unlock(&cgroup_mutex);
}

static int __init cgroup_disable(char *str)
{
	int i;
	char *token;

	while ((token = strsep(&str, ",")) != NULL) {
		if (!*token)
			continue;

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

			if (!strcmp(token, ss->name)) {
				ss->disabled = 1;
				printk(KERN_INFO "Disabling %s control group"
					" subsystem\n", ss->name);
				break;
			}
		}
	}
	return 1;
}
__setup("cgroup_disable=", cgroup_disable);

/*
 * Functons for CSS ID.
 */

/*
 *To get ID other than 0, this should be called when !cgroup_is_removed().
 */
unsigned short css_id(struct cgroup_subsys_state *css)
{
	struct css_id *cssid = rcu_dereference(css->id);

	if (cssid)
		return cssid->id;
	return 0;
}

unsigned short css_depth(struct cgroup_subsys_state *css)
{
	struct css_id *cssid = rcu_dereference(css->id);

	if (cssid)
		return cssid->depth;
	return 0;
}

bool css_is_ancestor(struct cgroup_subsys_state *child,
		    const struct cgroup_subsys_state *root)
{
	struct css_id *child_id = rcu_dereference(child->id);
	struct css_id *root_id = rcu_dereference(root->id);

	if (!child_id || !root_id || (child_id->depth < root_id->depth))
		return false;
	return child_id->stack[root_id->depth] == root_id->id;
}

static void __free_css_id_cb(struct rcu_head *head)
{
	struct css_id *id;

	id = container_of(head, struct css_id, rcu_head);
	kfree(id);
}

void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
{
	struct css_id *id = css->id;
	/* When this is called before css_id initialization, id can be NULL */
	if (!id)
		return;

	BUG_ON(!ss->use_id);

	rcu_assign_pointer(id->css, NULL);
	rcu_assign_pointer(css->id, NULL);
	spin_lock(&ss->id_lock);
	idr_remove(&ss->idr, id->id);
	spin_unlock(&ss->id_lock);
	call_rcu(&id->rcu_head, __free_css_id_cb);
}

/*
 * This is called by init or create(). Then, calls to this function are
 * always serialized (By cgroup_mutex() at create()).
 */

static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth)
{
	struct css_id *newid;
	int myid, error, size;

	BUG_ON(!ss->use_id);

	size = sizeof(*newid) + sizeof(unsigned short) * (depth + 1);
	newid = kzalloc(size, GFP_KERNEL);
	if (!newid)
		return ERR_PTR(-ENOMEM);
	/* get id */
	if (unlikely(!idr_pre_get(&ss->idr, GFP_KERNEL))) {
		error = -ENOMEM;
		goto err_out;
	}
	spin_lock(&ss->id_lock);
	/* Don't use 0. allocates an ID of 1-65535 */
	error = idr_get_new_above(&ss->idr, newid, 1, &myid);
	spin_unlock(&ss->id_lock);

	/* Returns error when there are no free spaces for new ID.*/
	if (error) {
		error = -ENOSPC;
		goto err_out;
	}
	if (myid > CSS_ID_MAX)
		goto remove_idr;

	newid->id = myid;
	newid->depth = depth;
	return newid;
remove_idr:
	error = -ENOSPC;
	spin_lock(&ss->id_lock);
	idr_remove(&ss->idr, myid);
	spin_unlock(&ss->id_lock);
err_out:
	kfree(newid);
	return ERR_PTR(error);

}

static int __init cgroup_subsys_init_idr(struct cgroup_subsys *ss)
{
	struct css_id *newid;
	struct cgroup_subsys_state *rootcss;

	spin_lock_init(&ss->id_lock);
	idr_init(&ss->idr);

	rootcss = init_css_set.subsys[ss->subsys_id];
	newid = get_new_cssid(ss, 0);
	if (IS_ERR(newid))
		return PTR_ERR(newid);

	newid->stack[0] = newid->id;
	newid->css = rootcss;
	rootcss->id = newid;
	return 0;
}

static int alloc_css_id(struct cgroup_subsys *ss, struct cgroup *parent,
			struct cgroup *child)
{
	int subsys_id, i, depth = 0;
	struct cgroup_subsys_state *parent_css, *child_css;
	struct css_id *child_id, *parent_id = NULL;

	subsys_id = ss->subsys_id;
	parent_css = parent->subsys[subsys_id];
	child_css = child->subsys[subsys_id];
	depth = css_depth(parent_css) + 1;
	parent_id = parent_css->id;

	child_id = get_new_cssid(ss, depth);
	if (IS_ERR(child_id))
		return PTR_ERR(child_id);

	for (i = 0; i < depth; i++)
		child_id->stack[i] = parent_id->stack[i];
	child_id->stack[depth] = child_id->id;
	/*
	 * child_id->css pointer will be set after this cgroup is available
	 * see cgroup_populate_dir()
	 */
	rcu_assign_pointer(child_css->id, child_id);

	return 0;
}

/**
 * css_lookup - lookup css by id
 * @ss: cgroup subsys to be looked into.
 * @id: the id
 *
 * Returns pointer to cgroup_subsys_state if there is valid one with id.
 * NULL if not. Should be called under rcu_read_lock()
 */
struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id)
{
	struct css_id *cssid = NULL;

	BUG_ON(!ss->use_id);
	cssid = idr_find(&ss->idr, id);

	if (unlikely(!cssid))
		return NULL;

	return rcu_dereference(cssid->css);
}

/**
 * css_get_next - lookup next cgroup under specified hierarchy.
 * @ss: pointer to subsystem
 * @id: current position of iteration.
 * @root: pointer to css. search tree under this.
 * @foundid: position of found object.
 *
 * Search next css under the specified hierarchy of rootid. Calling under
 * rcu_read_lock() is necessary. Returns NULL if it reaches the end.
 */
struct cgroup_subsys_state *
css_get_next(struct cgroup_subsys *ss, int id,
	     struct cgroup_subsys_state *root, int *foundid)
{
	struct cgroup_subsys_state *ret = NULL;
	struct css_id *tmp;
	int tmpid;
	int rootid = css_id(root);
	int depth = css_depth(root);

	if (!rootid)
		return NULL;

	BUG_ON(!ss->use_id);
	/* fill start point for scan */
	tmpid = id;
	while (1) {
		/*
		 * scan next entry from bitmap(tree), tmpid is updated after
		 * idr_get_next().
		 */
		spin_lock(&ss->id_lock);
		tmp = idr_get_next(&ss->idr, &tmpid);
		spin_unlock(&ss->id_lock);

		if (!tmp)
			break;
		if (tmp->depth >= depth && tmp->stack[depth] == rootid) {
			ret = rcu_dereference(tmp->css);
			if (ret) {
				*foundid = tmpid;
				break;
			}
		}
		/* continue to scan from next id */
		tmpid = tmpid + 1;
	}
	return ret;
}

#ifdef CONFIG_CGROUP_DEBUG
static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
						   struct cgroup *cont)
{
	struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);

	if (!css)
		return ERR_PTR(-ENOMEM);

	return css;
}

static void debug_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
{
	kfree(cont->subsys[debug_subsys_id]);
}

static u64 cgroup_refcount_read(struct cgroup *cont, struct cftype *cft)
{
	return atomic_read(&cont->count);
}

static u64 debug_taskcount_read(struct cgroup *cont, struct cftype *cft)
{
	return cgroup_task_count(cont);
}

static u64 current_css_set_read(struct cgroup *cont, struct cftype *cft)
{
	return (u64)(unsigned long)current->cgroups;
}

static u64 current_css_set_refcount_read(struct cgroup *cont,
					   struct cftype *cft)
{
	u64 count;

	rcu_read_lock();
	count = atomic_read(&current->cgroups->refcount);
	rcu_read_unlock();
	return count;
}

static int current_css_set_cg_links_read(struct cgroup *cont,
					 struct cftype *cft,
					 struct seq_file *seq)
{
	struct cg_cgroup_link *link;
	struct css_set *cg;

	read_lock(&css_set_lock);
	rcu_read_lock();
	cg = rcu_dereference(current->cgroups);
	list_for_each_entry(link, &cg->cg_links, cg_link_list) {
		struct cgroup *c = link->cgrp;
		const char *name;

		if (c->dentry)
			name = c->dentry->d_name.name;
		else
			name = "?";
		seq_printf(seq, "Root %d group %s\n",
			   c->root->hierarchy_id, name);
	}
	rcu_read_unlock();
	read_unlock(&css_set_lock);
	return 0;
}

#define MAX_TASKS_SHOWN_PER_CSS 25
static int cgroup_css_links_read(struct cgroup *cont,