cgroup.c

	 * reading; hence we check if it's not null only in that case.
	 */
	l = ((struct seq_file *)file->private_data)->private;
	cgroup_release_pid_array(l);
	return seq_release(inode, file);
}

static const struct file_operations cgroup_pidlist_operations = {
	.read = seq_read,
	.llseek = seq_lseek,
	.write = cgroup_file_write,
	.release = cgroup_pidlist_release,
};

/*
 * The following functions handle opens on a file that displays a pidlist
 * (tasks or procs). Prepare an array of the process/thread IDs of whoever's
 * in the cgroup.
 */
/* helper function for the two below it */
static int cgroup_pidlist_open(struct file *file, enum cgroup_filetype type)
{
	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
	struct cgroup_pidlist *l;
	int retval;

	/* Nothing to do for write-only files */
	if (!(file->f_mode & FMODE_READ))
		return 0;

	/* have the array populated */
	retval = pidlist_array_load(cgrp, type, &l);
	if (retval)
		return retval;
	/* configure file information */
	file->f_op = &cgroup_pidlist_operations;

	retval = seq_open(file, &cgroup_pidlist_seq_operations);
	if (retval) {
		cgroup_release_pid_array(l);
		return retval;
	}
	((struct seq_file *)file->private_data)->private = l;
	return 0;
}
static int cgroup_tasks_open(struct inode *unused, struct file *file)
{
	return cgroup_pidlist_open(file, CGROUP_FILE_TASKS);
}
static int cgroup_procs_open(struct inode *unused, struct file *file)
{
	return cgroup_pidlist_open(file, CGROUP_FILE_PROCS);
}

static u64 cgroup_read_notify_on_release(struct cgroup *cgrp,
					    struct cftype *cft)
{
	return notify_on_release(cgrp);
}

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

/*
 * Unregister event and free resources.
 *
 * Gets called from workqueue.
 */
static void cgroup_event_remove(struct work_struct *work)
{
	struct cgroup_event *event = container_of(work, struct cgroup_event,
			remove);
	struct cgroup *cgrp = event->cgrp;

	event->cft->unregister_event(cgrp, event->cft, event->eventfd);

	eventfd_ctx_put(event->eventfd);
	kfree(event);
	dput(cgrp->dentry);
}

/*
 * Gets called on POLLHUP on eventfd when user closes it.
 *
 * Called with wqh->lock held and interrupts disabled.
 */
static int cgroup_event_wake(wait_queue_t *wait, unsigned mode,
		int sync, void *key)
{
	struct cgroup_event *event = container_of(wait,
			struct cgroup_event, wait);
	struct cgroup *cgrp = event->cgrp;
	unsigned long flags = (unsigned long)key;

	if (flags & POLLHUP) {
		__remove_wait_queue(event->wqh, &event->wait);
		spin_lock(&cgrp->event_list_lock);
		list_del(&event->list);
		spin_unlock(&cgrp->event_list_lock);
		/*
		 * We are in atomic context, but cgroup_event_remove() may
		 * sleep, so we have to call it in workqueue.
		 */
		schedule_work(&event->remove);
	}

	return 0;
}

static void cgroup_event_ptable_queue_proc(struct file *file,
		wait_queue_head_t *wqh, poll_table *pt)
{
	struct cgroup_event *event = container_of(pt,
			struct cgroup_event, pt);

	event->wqh = wqh;
	add_wait_queue(wqh, &event->wait);
}

/*
 * Parse input and register new cgroup event handler.
 *
 * Input must be in format '<event_fd> <control_fd> <args>'.
 * Interpretation of args is defined by control file implementation.
 */
static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft,
				      const char *buffer)
{
	struct cgroup_event *event = NULL;
	unsigned int efd, cfd;
	struct file *efile = NULL;
	struct file *cfile = NULL;
	char *endp;
	int ret;

	efd = simple_strtoul(buffer, &endp, 10);
	if (*endp != ' ')
		return -EINVAL;
	buffer = endp + 1;

	cfd = simple_strtoul(buffer, &endp, 10);
	if ((*endp != ' ') && (*endp != '\0'))
		return -EINVAL;
	buffer = endp + 1;

	event = kzalloc(sizeof(*event), GFP_KERNEL);
	if (!event)
		return -ENOMEM;
	event->cgrp = cgrp;
	INIT_LIST_HEAD(&event->list);
	init_poll_funcptr(&event->pt, cgroup_event_ptable_queue_proc);
	init_waitqueue_func_entry(&event->wait, cgroup_event_wake);
	INIT_WORK(&event->remove, cgroup_event_remove);

	efile = eventfd_fget(efd);
	if (IS_ERR(efile)) {
		ret = PTR_ERR(efile);
		goto fail;
	}

	event->eventfd = eventfd_ctx_fileget(efile);
	if (IS_ERR(event->eventfd)) {
		ret = PTR_ERR(event->eventfd);
		goto fail;
	}

	cfile = fget(cfd);
	if (!cfile) {
		ret = -EBADF;
		goto fail;
	}

	/* the process need read permission on control file */
	ret = file_permission(cfile, MAY_READ);
	if (ret < 0)
		goto fail;

	event->cft = __file_cft(cfile);
	if (IS_ERR(event->cft)) {
		ret = PTR_ERR(event->cft);
		goto fail;
	}

	if (!event->cft->register_event || !event->cft->unregister_event) {
		ret = -EINVAL;
		goto fail;
	}

	ret = event->cft->register_event(cgrp, event->cft,
			event->eventfd, buffer);
	if (ret)
		goto fail;

	if (efile->f_op->poll(efile, &event->pt) & POLLHUP) {
		event->cft->unregister_event(cgrp, event->cft, event->eventfd);
		ret = 0;
		goto fail;
	}

	/*
	 * Events should be removed after rmdir of cgroup directory, but before
	 * destroying subsystem state objects. Let's take reference to cgroup
	 * directory dentry to do that.
	 */
	dget(cgrp->dentry);

	spin_lock(&cgrp->event_list_lock);
	list_add(&event->list, &cgrp->event_list);
	spin_unlock(&cgrp->event_list_lock);

	fput(cfile);
	fput(efile);

	return 0;

fail:
	if (cfile)
		fput(cfile);

	if (event && event->eventfd && !IS_ERR(event->eventfd))
		eventfd_ctx_put(event->eventfd);

	if (!IS_ERR_OR_NULL(efile))
		fput(efile);

	kfree(event);

	return ret;
}

static u64 cgroup_clone_children_read(struct cgroup *cgrp,
				    struct cftype *cft)
{
	return clone_children(cgrp);
}

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

/*
 * for the common functions, 'private' gives the type of file
 */
/* for hysterical raisins, we can't put this on the older files */
#define CGROUP_FILE_GENERIC_PREFIX "cgroup."
static struct cftype files[] = {
	{
		.name = "tasks",
		.open = cgroup_tasks_open,
		.write_u64 = cgroup_tasks_write,
		.release = cgroup_pidlist_release,
		.mode = S_IRUGO | S_IWUSR,
	},
	{
		.name = CGROUP_FILE_GENERIC_PREFIX "procs",
		.open = cgroup_procs_open,
		/* .write_u64 = cgroup_procs_write, TODO */
		.release = cgroup_pidlist_release,
		.mode = S_IRUGO,
	},
	{
		.name = "notify_on_release",
		.read_u64 = cgroup_read_notify_on_release,
		.write_u64 = cgroup_write_notify_on_release,
	},
	{
		.name = CGROUP_FILE_GENERIC_PREFIX "event_control",
		.write_string = cgroup_write_event_control,
		.mode = S_IWUGO,
	},
	{
		.name = "cgroup.clone_children",
		.read_u64 = cgroup_clone_children_read,
		.write_u64 = cgroup_clone_children_write,
	},
};

static struct cftype cft_release_agent = {
	.name = "release_agent",
	.read_seq_string = cgroup_release_agent_show,
	.write_string = cgroup_release_agent_write,
	.max_write_len = PATH_MAX,
};

static int cgroup_populate_dir(struct cgroup *cgrp)
{
	int err;
	struct cgroup_subsys *ss;

	/* First clear out any existing files */
	cgroup_clear_directory(cgrp->dentry);

	err = cgroup_add_files(cgrp, NULL, files, ARRAY_SIZE(files));
	if (err < 0)
		return err;

	if (cgrp == cgrp->top_cgroup) {
		if ((err = cgroup_add_file(cgrp, NULL, &cft_release_agent)) < 0)
			return err;
	}

	for_each_subsys(cgrp->root, ss) {
		if (ss->populate && (err = ss->populate(ss, cgrp)) < 0)
			return err;
	}
	/* This cgroup is ready now */
	for_each_subsys(cgrp->root, ss) {
		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
		/*
		 * Update id->css pointer and make this css visible from
		 * CSS ID functions. This pointer will be dereferened
		 * from RCU-read-side without locks.
		 */
		if (css->id)
			rcu_assign_pointer(css->id->css, css);
	}

	return 0;
}

static void init_cgroup_css(struct cgroup_subsys_state *css,
			       struct cgroup_subsys *ss,
			       struct cgroup *cgrp)
{
	css->cgroup = cgrp;
	atomic_set(&css->refcnt, 1);
	css->flags = 0;
	css->id = NULL;
	if (cgrp == dummytop)
		set_bit(CSS_ROOT, &css->flags);
	BUG_ON(cgrp->subsys[ss->subsys_id]);
	cgrp->subsys[ss->subsys_id] = css;
}

static void cgroup_lock_hierarchy(struct cgroupfs_root *root)
{
	/* We need to take each hierarchy_mutex in a consistent order */
	int i;

	/*
	 * No worry about a race with rebind_subsystems that might mess up the
	 * locking order, since both parties are under cgroup_mutex.
	 */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		if (ss == NULL)
			continue;
		if (ss->root == root)
			mutex_lock(&ss->hierarchy_mutex);
	}
}

static void cgroup_unlock_hierarchy(struct cgroupfs_root *root)
{
	int i;

	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		if (ss == NULL)
			continue;
		if (ss->root == root)
			mutex_unlock(&ss->hierarchy_mutex);
	}
}

/*
 * cgroup_create - create a cgroup
 * @parent: cgroup that will be parent of the new cgroup
 * @dentry: dentry of the new cgroup
 * @mode: mode to set on new inode
 *
 * Must be called with the mutex on the parent inode held
 */
static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
			     mode_t mode)
{
	struct cgroup *cgrp;
	struct cgroupfs_root *root = parent->root;
	int err = 0;
	struct cgroup_subsys *ss;
	struct super_block *sb = root->sb;

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

	/* 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);

	mutex_lock(&cgroup_mutex);

	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 = ss->create(ss, 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(ss, cgrp);
	}

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

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

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

	err = cgroup_populate_dir(cgrp);
	/* 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:

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

 err_destroy:

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

	mutex_unlock(&cgroup_mutex);

	/* Release the reference count that we took on the superblock */
	deactivate_super(sb);

	kfree(cgrp);
	return err;
}

static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int 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);
}

static int cgroup_has_css_refs(struct cgroup *cgrp)
{
	/* 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 */
	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 && (atomic_read(&css->refcnt) > 1))
			return 1;
	}
	return 0;
}

/*
 * Atomically mark all (or else none) of the cgroup's CSS objects as
 * CSS_REMOVED. Return true on success, or false if the cgroup has
 * busy subsystems. Call with cgroup_mutex held
 */

static int cgroup_clear_css_refs(struct cgroup *cgrp)
{
	struct cgroup_subsys *ss;
	unsigned long flags;
	bool failed = false;
	local_irq_save(flags);
	for_each_subsys(cgrp->root, ss) {
		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
		int refcnt;
		while (1) {
			/* We can only remove a CSS with a refcnt==1 */
			refcnt = atomic_read(&css->refcnt);
			if (refcnt > 1) {
				failed = true;
				goto done;
			}
			BUG_ON(!refcnt);
			/*
			 * Drop the refcnt to 0 while we check other
			 * subsystems. This will cause any racing
			 * css_tryget() to spin until we set the
			 * CSS_REMOVED bits or abort
			 */
			if (atomic_cmpxchg(&css->refcnt, refcnt, 0) == refcnt)
				break;
			cpu_relax();
		}
	}
 done:
	for_each_subsys(cgrp->root, ss) {
		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
		if (failed) {
			/*
			 * Restore old refcnt if we previously managed
			 * to clear it from 1 to 0
			 */
			if (!atomic_read(&css->refcnt))
				atomic_set(&css->refcnt, 1);
		} else {
			/* Commit the fact that the CSS is removed */
			set_bit(CSS_REMOVED, &css->flags);
		}
	}
	local_irq_restore(flags);
	return !failed;
}

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;
	int ret;

	/* the vfs holds both inode->i_mutex already */
again:
	mutex_lock(&cgroup_mutex);
	if (atomic_read(&cgrp->count) != 0) {
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}
	if (!list_empty(&cgrp->children)) {
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}
	mutex_unlock(&cgroup_mutex);

	/*
	 * In general, subsystem has no css->refcnt after pre_destroy(). But
	 * in racy cases, subsystem may have to get css->refcnt after
	 * pre_destroy() and it makes rmdir return with -EBUSY. This sometimes
	 * make rmdir return -EBUSY too often. To avoid that, we use waitqueue
	 * for cgroup's rmdir. CGRP_WAIT_ON_RMDIR is for synchronizing rmdir
	 * and subsystem's reference count handling. Please see css_get/put
	 * and css_tryget() and cgroup_wakeup_rmdir_waiter() implementation.
	 */
	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_init(&cgrp->release_list);
	spin_unlock(&release_list_lock);

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

	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 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;

	/* 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 few sanity checks */
		BUG_ON(ss->subsys_id >= CGROUP_BUILTIN_SUBSYS_COUNT);
		BUG_ON(subsys[ss->subsys_id] != ss);
		return 0;
	}

	/*
	 * need to register a subsys id before anything else - for example,
	 * init_cgroup_css needs it.
	 */
	mutex_lock(&cgroup_mutex);
	/* find the first empty slot in the array */
	for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) {
		if (subsys[i] == NULL)
			break;
	}
	if (i == CGROUP_SUBSYS_COUNT) {
		/* maximum number of subsystems already registered! */
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}
	/* assign ourselves the subsys_id */
	ss->subsys_id = i;
	subsys[i] = 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(ss, dummytop);
	if (IS_ERR(css)) {
		/* failure case - need to deassign the subsys[] slot. */
		subsys[i] = 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(ss, dummytop);
			subsys[i] = 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);

	mutex_init(&ss->hierarchy_mutex);
	lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
	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 */
	BUG_ON(ss->subsys_id < CGROUP_BUILTIN_SUBSYS_COUNT);
	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(ss, 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]);

	/* at bootup time, we don't worry about modular subsystems */
	for (i = 0; i < CGROUP_BUILTIN_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;

	/* at bootup time, we don't worry about modular subsystems */
	for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		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);