cgroup.c

			get_task_struct(p);
			put_task_struct(dropped);
		}
		/*
		 * Else the new task was newer than anything already in
		 * the heap and wasn't inserted
		 */
	}
	cgroup_iter_end(scan->cg, &it);

	if (heap->size) {
		for (i = 0; i < heap->size; i++) {
			struct task_struct *q = heap->ptrs[i];
			if (i == 0) {
				latest_time = q->start_time;
				latest_task = q;
			}
			/* Process the task per the caller's callback */
			scan->process_task(q, scan);
			put_task_struct(q);
		}
		/*
		 * If we had to process any tasks at all, scan again
		 * in case some of them were in the middle of forking
		 * children that didn't get processed.
		 * Not the most efficient way to do it, but it avoids
		 * having to take callback_mutex in the fork path
		 */
		goto again;
	}
	if (heap == &tmp_heap)
		heap_free(&tmp_heap);
	return 0;
}

/*
 * Stuff for reading the 'tasks'/'procs' files.
 *
 * Reading this file can return large amounts of data if a cgroup has
 * *lots* of attached tasks. So it may need several calls to read(),
 * but we cannot guarantee that the information we produce is correct
 * unless we produce it entirely atomically.
 *
 */

/*
 * The following two functions "fix" the issue where there are more pids
 * than kmalloc will give memory for; in such cases, we use vmalloc/vfree.
 * TODO: replace with a kernel-wide solution to this problem
 */
#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2))
static void *pidlist_allocate(int count)
{
	if (PIDLIST_TOO_LARGE(count))
		return vmalloc(count * sizeof(pid_t));
	else
		return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
}
static void pidlist_free(void *p)
{
	if (is_vmalloc_addr(p))
		vfree(p);
	else
		kfree(p);
}
static void *pidlist_resize(void *p, int newcount)
{
	void *newlist;
	/* note: if new alloc fails, old p will still be valid either way */
	if (is_vmalloc_addr(p)) {
		newlist = vmalloc(newcount * sizeof(pid_t));
		if (!newlist)
			return NULL;
		memcpy(newlist, p, newcount * sizeof(pid_t));
		vfree(p);
	} else {
		newlist = krealloc(p, newcount * sizeof(pid_t), GFP_KERNEL);
	}
	return newlist;
}

/*
 * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
 * If the new stripped list is sufficiently smaller and there's enough memory
 * to allocate a new buffer, will let go of the unneeded memory. Returns the
 * number of unique elements.
 */
/* is the size difference enough that we should re-allocate the array? */
#define PIDLIST_REALLOC_DIFFERENCE(old, new) ((old) - PAGE_SIZE >= (new))
static int pidlist_uniq(pid_t **p, int length)
{
	int src, dest = 1;
	pid_t *list = *p;
	pid_t *newlist;

	/*
	 * we presume the 0th element is unique, so i starts at 1. trivial
	 * edge cases first; no work needs to be done for either
	 */
	if (length == 0 || length == 1)
		return length;
	/* src and dest walk down the list; dest counts unique elements */
	for (src = 1; src < length; src++) {
		/* find next unique element */
		while (list[src] == list[src-1]) {
			src++;
			if (src == length)
				goto after;
		}
		/* dest always points to where the next unique element goes */
		list[dest] = list[src];
		dest++;
	}
after:
	/*
	 * if the length difference is large enough, we want to allocate a
	 * smaller buffer to save memory. if this fails due to out of memory,
	 * we'll just stay with what we've got.
	 */
	if (PIDLIST_REALLOC_DIFFERENCE(length, dest)) {
		newlist = pidlist_resize(list, dest);
		if (newlist)
			*p = newlist;
	}
	return dest;
}

static int cmppid(const void *a, const void *b)
{
	return *(pid_t *)a - *(pid_t *)b;
}

/*
 * find the appropriate pidlist for our purpose (given procs vs tasks)
 * returns with the lock on that pidlist already held, and takes care
 * of the use count, or returns NULL with no locks held if we're out of
 * memory.
 */
static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
						  enum cgroup_filetype type)
{
	struct cgroup_pidlist *l;
	/* don't need task_nsproxy() if we're looking at ourself */
	struct pid_namespace *ns = current->nsproxy->pid_ns;

	/*
	 * We can't drop the pidlist_mutex before taking the l->mutex in case
	 * the last ref-holder is trying to remove l from the list at the same
	 * time. Holding the pidlist_mutex precludes somebody taking whichever
	 * list we find out from under us - compare release_pid_array().
	 */
	mutex_lock(&cgrp->pidlist_mutex);
	list_for_each_entry(l, &cgrp->pidlists, links) {
		if (l->key.type == type && l->key.ns == ns) {
			/* make sure l doesn't vanish out from under us */
			down_write(&l->mutex);
			mutex_unlock(&cgrp->pidlist_mutex);
			return l;
		}
	}
	/* entry not found; create a new one */
	l = kmalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
	if (!l) {
		mutex_unlock(&cgrp->pidlist_mutex);
		return l;
	}
	init_rwsem(&l->mutex);
	down_write(&l->mutex);
	l->key.type = type;
	l->key.ns = get_pid_ns(ns);
	l->use_count = 0; /* don't increment here */
	l->list = NULL;
	l->owner = cgrp;
	list_add(&l->links, &cgrp->pidlists);
	mutex_unlock(&cgrp->pidlist_mutex);
	return l;
}

/*
 * Load a cgroup's pidarray with either procs' tgids or tasks' pids
 */
static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
			      struct cgroup_pidlist **lp)
{
	pid_t *array;
	int length;
	int pid, n = 0; /* used for populating the array */
	struct cgroup_iter it;
	struct task_struct *tsk;
	struct cgroup_pidlist *l;

	/*
	 * If cgroup gets more users after we read count, we won't have
	 * enough space - tough.  This race is indistinguishable to the
	 * caller from the case that the additional cgroup users didn't
	 * show up until sometime later on.
	 */
	length = cgroup_task_count(cgrp);
	array = pidlist_allocate(length);
	if (!array)
		return -ENOMEM;
	/* now, populate the array */
	cgroup_iter_start(cgrp, &it);
	while ((tsk = cgroup_iter_next(cgrp, &it))) {
		if (unlikely(n == length))
			break;
		/* get tgid or pid for procs or tasks file respectively */
		if (type == CGROUP_FILE_PROCS)
			pid = task_tgid_vnr(tsk);
		else
			pid = task_pid_vnr(tsk);
		if (pid > 0) /* make sure to only use valid results */
			array[n++] = pid;
	}
	cgroup_iter_end(cgrp, &it);
	length = n;
	/* now sort & (if procs) strip out duplicates */
	sort(array, length, sizeof(pid_t), cmppid, NULL);
	if (type == CGROUP_FILE_PROCS)
		length = pidlist_uniq(&array, length);
	l = cgroup_pidlist_find(cgrp, type);
	if (!l) {
		pidlist_free(array);
		return -ENOMEM;
	}
	/* store array, freeing old if necessary - lock already held */
	pidlist_free(l->list);
	l->list = array;
	l->length = length;
	l->use_count++;
	up_write(&l->mutex);
	*lp = l;
	return 0;
}

/**
 * cgroupstats_build - build and fill cgroupstats
 * @stats: cgroupstats to fill information into
 * @dentry: A dentry entry belonging to the cgroup for which stats have
 * been requested.
 *
 * Build and fill cgroupstats so that taskstats can export it to user
 * space.
 */
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
{
	int ret = -EINVAL;
	struct cgroup *cgrp;
	struct cgroup_iter it;
	struct task_struct *tsk;

	/*
	 * Validate dentry by checking the superblock operations,
	 * and make sure it's a directory.
	 */
	if (dentry->d_sb->s_op != &cgroup_ops ||
	    !S_ISDIR(dentry->d_inode->i_mode))
		 goto err;

	ret = 0;
	cgrp = dentry->d_fsdata;

	cgroup_iter_start(cgrp, &it);
	while ((tsk = cgroup_iter_next(cgrp, &it))) {
		switch (tsk->state) {
		case TASK_RUNNING:
			stats->nr_running++;
			break;
		case TASK_INTERRUPTIBLE:
			stats->nr_sleeping++;
			break;
		case TASK_UNINTERRUPTIBLE:
			stats->nr_uninterruptible++;
			break;
		case TASK_STOPPED:
			stats->nr_stopped++;
			break;
		default:
			if (delayacct_is_task_waiting_on_io(tsk))
				stats->nr_io_wait++;
			break;
		}
	}
	cgroup_iter_end(cgrp, &it);

err:
	return ret;
}


/*
 * seq_file methods for the tasks/procs files. The seq_file position is the
 * next pid to display; the seq_file iterator is a pointer to the pid
 * in the cgroup->l->list array.
 */

static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
{
	/*
	 * Initially we receive a position value that corresponds to
	 * one more than the last pid shown (or 0 on the first call or
	 * after a seek to the start). Use a binary-search to find the
	 * next pid to display, if any
	 */
	struct cgroup_pidlist *l = s->private;
	int index = 0, pid = *pos;
	int *iter;

	down_read(&l->mutex);
	if (pid) {
		int end = l->length;

		while (index < end) {
			int mid = (index + end) / 2;
			if (l->list[mid] == pid) {
				index = mid;
				break;
			} else if (l->list[mid] <= pid)
				index = mid + 1;
			else
				end = mid;
		}
	}
	/* If we're off the end of the array, we're done */
	if (index >= l->length)
		return NULL;
	/* Update the abstract position to be the actual pid that we found */
	iter = l->list + index;
	*pos = *iter;
	return iter;
}

static void cgroup_pidlist_stop(struct seq_file *s, void *v)
{
	struct cgroup_pidlist *l = s->private;
	up_read(&l->mutex);
}

static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
{
	struct cgroup_pidlist *l = s->private;
	pid_t *p = v;
	pid_t *end = l->list + l->length;
	/*
	 * Advance to the next pid in the array. If this goes off the
	 * end, we're done
	 */
	p++;
	if (p >= end) {
		return NULL;
	} else {
		*pos = *p;
		return p;
	}
}

static int cgroup_pidlist_show(struct seq_file *s, void *v)
{
	return seq_printf(s, "%d\n", *(int *)v);
}

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

static void cgroup_release_pid_array(struct cgroup_pidlist *l)
{
	/*
	 * the case where we're the last user of this particular pidlist will
	 * have us remove it from the cgroup's list, which entails taking the
	 * mutex. since in pidlist_find the pidlist->lock depends on cgroup->
	 * pidlist_mutex, we have to take pidlist_mutex first.
	 */
	mutex_lock(&l->owner->pidlist_mutex);
	down_write(&l->mutex);
	BUG_ON(!l->use_count);
	if (!--l->use_count) {
		/* we're the last user if refcount is 0; remove and free */
		list_del(&l->links);
		mutex_unlock(&l->owner->pidlist_mutex);
		pidlist_free(l->list);
		put_pid_ns(l->key.ns);
		up_write(&l->mutex);
		kfree(l);
		return;
	}
	mutex_unlock(&l->owner->pidlist_mutex);
	up_write(&l->mutex);
}

static int cgroup_pidlist_release(struct inode *inode, struct file *file)
{
	struct cgroup_pidlist *l;
	if (!(file->f_mode & FMODE_READ))
		return 0;
	/*
	 * the seq_file will only be initialized if the file was opened for
	 * 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 */
	/* AV: shouldn't we check that it's been opened for read instead? */
	ret = inode_permission(cfile->f_path.dentry->d_inode, 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,
		.release = cgroup_pidlist_release,
		.mode = S_IRUGO | S_IWUSR,
	},
	{
		.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,
			     umode_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, 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_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);