cgroup.c

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 test_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
}

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

static struct cftype cgroup_base_files[] = {
	{
		.name = "cgroup.procs",
		.open = cgroup_procs_open,
		.write_u64 = cgroup_procs_write,
		.release = cgroup_pidlist_release,
		.mode = S_IRUGO | S_IWUSR,
	},
	{
		.name = "cgroup.event_control",
		.write_string = cgroup_write_event_control,
		.mode = S_IWUGO,
	},
	{
		.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,
		.read_seq_string = 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 */
		.open = cgroup_tasks_open,
		.write_u64 = cgroup_tasks_write,
		.release = cgroup_pidlist_release,
		.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,
		.read_seq_string = cgroup_release_agent_show,
		.write_string = cgroup_release_agent_write,
		.max_write_len = PATH_MAX,
	},
	{ }	/* terminate */
};

/**
 * cgroup_populate_dir - selectively creation of files in a directory
 * @cgrp: target cgroup
 * @base_files: true if the base files should be added
 * @subsys_mask: mask of the subsystem ids whose files should be added
 */
static int cgroup_populate_dir(struct cgroup *cgrp, bool base_files,
			       unsigned long subsys_mask)
{
	int err;
	struct cgroup_subsys *ss;

	if (base_files) {
		err = cgroup_addrm_files(cgrp, NULL, cgroup_base_files, true);
		if (err < 0)
			return err;
	}

	/* process cftsets of each subsystem */
	for_each_subsys(cgrp->root, ss) {
		struct cftype_set *set;
		if (!test_bit(ss->subsys_id, &subsys_mask))
			continue;

		list_for_each_entry(set, &ss->cftsets, node)
			cgroup_addrm_files(cgrp, ss, set->cfts, true);
	}

	/* 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 css_dput_fn(struct work_struct *work)
{
	struct cgroup_subsys_state *css =
		container_of(work, struct cgroup_subsys_state, dput_work);
	struct dentry *dentry = css->cgroup->dentry;
	struct super_block *sb = dentry->d_sb;

	atomic_inc(&sb->s_active);
	dput(dentry);
	deactivate_super(sb);
}

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)
		css->flags |= CSS_ROOT;
	BUG_ON(cgrp->subsys[ss->subsys_id]);
	cgrp->subsys[ss->subsys_id] = css;

	/*
	 * css holds an extra ref to @cgrp->dentry which is put on the last
	 * css_put().  dput() requires process context, which css_put() may
	 * be called without.  @css->dput_work will be used to invoke
	 * dput() asynchronously from css_put().
	 */
	INIT_WORK(&css->dput_work, css_dput_fn);
}

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

	lockdep_assert_held(&cgroup_mutex);

	if (ss->css_online)
		ret = ss->css_online(cgrp);
	if (!ret)
		cgrp->subsys[ss->subsys_id]->flags |= CSS_ONLINE;
	return ret;
}

/* if the CSS is online, invoke ->pre_destory() on it and mark it offline */
static void offline_css(struct cgroup_subsys *ss, struct cgroup *cgrp)
	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
{
	struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];

	lockdep_assert_held(&cgroup_mutex);

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

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

	cgrp->subsys[ss->subsys_id]->flags &= ~CSS_ONLINE;
}

/*
 * 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,
			     umode_t mode)
{
	static atomic64_t serial_nr_cursor = ATOMIC64_INIT(0);
	struct cgroup *cgrp;
	struct cgroup_name *name;
	struct cgroupfs_root *root = parent->root;
	int err = 0;
	struct cgroup_subsys *ss;
	struct super_block *sb = root->sb;

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

	name = cgroup_alloc_name(dentry);
	if (!name)
		goto err_free_cgrp;
	rcu_assign_pointer(cgrp->name, name);

	cgrp->id = ida_simple_get(&root->cgroup_ida, 1, 0, GFP_KERNEL);
	if (cgrp->id < 0)
		goto err_free_name;

	/*
	 * 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_free_id;
	}

	/* 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);

	dentry->d_fsdata = cgrp;
	cgrp->dentry = dentry;

	cgrp->parent = parent;
	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);

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

		css = ss->css_alloc(cgrp);
		if (IS_ERR(css)) {
			err = PTR_ERR(css);
			goto err_free_all;
		}
		init_cgroup_css(css, ss, cgrp);
		if (ss->use_id) {
			err = alloc_css_id(ss, parent, cgrp);
			if (err)
				goto err_free_all;
		}
	}

	/*
	 * Create directory.  cgroup_create_file() returns with the new
	 * directory locked on success so that it can be populated without
	 * dropping cgroup_mutex.
	 */
	err = cgroup_create_file(dentry, S_IFDIR | mode, sb);
	if (err < 0)
		goto err_free_all;
	lockdep_assert_held(&dentry->d_inode->i_mutex);

	/*
	 * Assign a monotonically increasing serial number.  With the list
	 * appending below, it guarantees that sibling cgroups are always
	 * sorted in the ascending serial number order on the parent's
	 * ->children.
	 */
	cgrp->serial_nr = atomic64_inc_return(&serial_nr_cursor);

	/* allocation complete, commit to creation */
	list_add_tail(&cgrp->allcg_node, &root->allcg_list);
	list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
	root->number_of_cgroups++;

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

	/* hold a ref to the parent's dentry */
	dget(parent->dentry);

	/* creation succeeded, notify subsystems */
	for_each_subsys(root, ss) {
		err = online_css(ss, cgrp);
		if (err)
			goto err_destroy;

		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;
		}
	}

	err = cgroup_populate_dir(cgrp, true, root->subsys_mask);
	if (err)
		goto err_destroy;

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

	return 0;

err_free_all:
	for_each_subsys(root, ss) {
		if (cgrp->subsys[ss->subsys_id])
			ss->css_free(cgrp);
	}
	mutex_unlock(&cgroup_mutex);
	/* Release the reference count that we took on the superblock */
	deactivate_super(sb);
err_free_id:
	ida_simple_remove(&root->cgroup_ida, cgrp->id);
err_free_name:
	kfree(rcu_dereference_raw(cgrp->name));
err_free_cgrp:
	kfree(cgrp);
	return err;

err_destroy:
	cgroup_destroy_locked(cgrp);
	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&dentry->d_inode->i_mutex);
	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);
}

static int cgroup_destroy_locked(struct cgroup *cgrp)
	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
{
	struct dentry *d = cgrp->dentry;
	struct cgroup_event *event, *tmp;
	struct cgroup_subsys *ss;
	bool empty;

	lockdep_assert_held(&d->d_inode->i_mutex);
	lockdep_assert_held(&cgroup_mutex);

	/*
	 * css_set_lock synchronizes access to ->cset_links and prevents
	 * @cgrp from being removed while __put_css_set() is in progress.
	 */
	read_lock(&css_set_lock);
	empty = list_empty(&cgrp->cset_links) && list_empty(&cgrp->children);
	read_unlock(&css_set_lock);
	if (!empty)
		return -EBUSY;

	/*
	 * Block new css_tryget() by deactivating refcnt and mark @cgrp
	 * removed.  This makes future css_tryget() attempts fail which we
	 * guarantee to ->css_offline() callbacks.
	 */
	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);
	}

	/*
	 * 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 cgroup_next_sibling() to
	 * resume iteration after dropping RCU read lock.  See
	 * cgroup_next_sibling() 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);

	/*
	 * Remove @cgrp directory.  The removal puts the base ref but we
	 * aren't quite done with @cgrp yet, so hold onto it.
	 */
	dget(d);
	cgroup_d_remove_dir(d);

	/*
	 * 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_init(&event->list);
		schedule_work(&event->remove);
	}
	spin_unlock(&cgrp->event_list_lock);

	INIT_WORK(&cgrp->destroy_work, cgroup_offline_fn);
	schedule_work(&cgrp->destroy_work);

	return 0;
};

static void cgroup_offline_fn(struct work_struct *work)
{
	struct cgroup *cgrp = container_of(work, struct cgroup, destroy_work);
	struct cgroup *parent = cgrp->parent;
	struct dentry *d = cgrp->dentry;
	struct cgroup_subsys *ss;

	mutex_lock(&cgroup_mutex);

	/* tell subsystems to initate destruction */
	for_each_subsys(cgrp->root, ss)
		offline_css(ss, cgrp);

	/*
	 * 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]);

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

	dput(d);

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

	mutex_unlock(&cgroup_mutex);
}

static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
{
	int ret;

	mutex_lock(&cgroup_mutex);
	ret = cgroup_destroy_locked(dentry->d_fsdata);
	mutex_unlock(&cgroup_mutex);

	return ret;
}

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);

	mutex_lock(&cgroup_mutex);

	/* 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->css_alloc(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] = 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(ss, dummytop));

	mutex_unlock(&cgroup_mutex);

	/* 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)
{
	struct cgroup_subsys_state *css;
	int i, ret;
	struct hlist_node *tmp;
	struct css_set *cset;
	unsigned long key;

	/* check name and function validity */
	if (ss->name == NULL || strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN ||
	    ss->css_alloc == NULL || ss->css_free == 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->css_alloc seems to need anything important in the ss
	 * struct, so this can happen first (i.e. before the rootnode
	 * attachment).
	 */
	css = ss->css_alloc(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) {
		ret = cgroup_init_idr(ss, css);
		if (ret)
			goto err_unload;
	}

	/*
	 * 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);
	hash_for_each_safe(css_set_table, i, tmp, cset, hlist) {
		/* skip entries that we already rehashed */
		if (cset->subsys[ss->subsys_id])
			continue;
		/* remove existing entry */
		hash_del(&cset->hlist);
		/* set new value */
		cset->subsys[ss->subsys_id] = css;
		/* recompute hash and restore entry */
		key = css_set_hash(cset->subsys);
		hash_add(css_set_table, &cset->hlist, key);
	}
	write_unlock(&css_set_lock);

	ret = online_css(ss, dummytop);
	if (ret)
		goto err_unload;

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

err_unload:
	mutex_unlock(&cgroup_mutex);
	/* @ss can't be mounted here as try_module_get() would fail */
	cgroup_unload_subsys(ss);
	return ret;
}
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 cgrp_cset_link *link;

	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);

	offline_css(ss, dummytop);

	if (ss->use_id)
		idr_destroy(&ss->idr);

	/* 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->cset_links, cset_link) {
		struct css_set *cset = link->cset;
		unsigned long key;

		hash_del(&cset->hlist);
		cset->subsys[ss->subsys_id] = NULL;
		key = css_set_hash(cset->subsys);
		hash_add(css_set_table, &cset->hlist, key);
	}
	write_unlock(&css_set_lock);

	/*
	 * remove subsystem's css from the dummytop and free it - need to
	 * free before marking as null because ss->css_free needs the
	 * cgrp->subsys pointer to find their state. note that this also
	 * takes care of freeing the css_id.
	 */
	ss->css_free(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.cgrp_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_cgrp_cset_link.cset = &init_css_set;
	init_cgrp_cset_link.cgrp = dummytop;
	list_add(&init_cgrp_cset_link.cset_link, &rootnode.top_cgroup.cset_links);
	list_add(&init_cgrp_cset_link.cgrp_link, &init_css_set.cgrp_links);

	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->css_alloc);
		BUG_ON(!ss->css_free);
		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;
	unsigned long key;

	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 */
	key = css_set_hash(init_css_set.subsys);
	hash_add(css_set_table, &init_css_set.hlist, key);

	/* allocate id for the dummy hierarchy */
	mutex_lock(&cgroup_mutex);
	mutex_lock(&cgroup_root_mutex);

	BUG_ON(cgroup_init_root_id(&rootnode));

	mutex_unlock(&cgroup_root_mutex);
	mutex_unlock(&cgroup_mutex);

	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 */
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;
}

/* 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) {
		/*
		 * fork/exit callbacks are supported only for builtin
		 * subsystems, and the builtin section of the subsys
		 * array is immutable, so we don't need to lock the
		 * subsys array here. On the other hand, modular section
		 * of the array can be freed at module unload, so we
		 * can't touch that.
		 */
		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
			struct cgroup_subsys *ss = subsys[i];

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