cgroup.c

		/*
		 * Ugh... if @cft wants a custom max_write_len, we need to
		 * make a copy of kf_ops to set its atomic_write_len.
		 */
		if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) {
			kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL);
			if (!kf_ops) {
				cgroup_exit_cftypes(cfts);
				return -ENOMEM;
			}
			kf_ops->atomic_write_len = cft->max_write_len;
		}

		cft->kf_ops = kf_ops;
		cft->ss = ss;
	}

	return 0;
}

static int cgroup_rm_cftypes_locked(struct cftype *cfts)
{
	lockdep_assert_held(&cgroup_mutex);

	if (!cfts || !cfts[0].ss)
		return -ENOENT;

	list_del(&cfts->node);
	cgroup_apply_cftypes(cfts, false);
	cgroup_exit_cftypes(cfts);
	return 0;
}

/**
 * cgroup_rm_cftypes - remove an array of cftypes from a subsystem
 * @cfts: zero-length name terminated array of cftypes
 *
 * Unregister @cfts.  Files described by @cfts are removed from all
 * existing cgroups and all future cgroups won't have them either.  This
 * function can be called anytime whether @cfts' subsys is attached or not.
 *
 * Returns 0 on successful unregistration, -ENOENT if @cfts is not
 * registered.
 */
int cgroup_rm_cftypes(struct cftype *cfts)
{
	int ret;

	mutex_lock(&cgroup_mutex);
	ret = cgroup_rm_cftypes_locked(cfts);
	mutex_unlock(&cgroup_mutex);
	return ret;
}

/**
 * cgroup_add_cftypes - add an array of cftypes to a subsystem
 * @ss: target cgroup subsystem
 * @cfts: zero-length name terminated array of cftypes
 *
 * Register @cfts to @ss.  Files described by @cfts are created for all
 * existing cgroups to which @ss is attached and all future cgroups will
 * have them too.  This function can be called anytime whether @ss is
 * attached or not.
 *
 * Returns 0 on successful registration, -errno on failure.  Note that this
 * function currently returns 0 as long as @cfts registration is successful
 * even if some file creation attempts on existing cgroups fail.
 */
int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
	int ret;

	if (ss->disabled)
		return 0;

	if (!cfts || cfts[0].name[0] == '\0')
		return 0;

	ret = cgroup_init_cftypes(ss, cfts);
	if (ret)
		return ret;

	mutex_lock(&cgroup_mutex);

	list_add_tail(&cfts->node, &ss->cfts);
	ret = cgroup_apply_cftypes(cfts, true);
	if (ret)
		cgroup_rm_cftypes_locked(cfts);

	mutex_unlock(&cgroup_mutex);
	return ret;
}

/**
 * cgroup_task_count - count the number of tasks in a cgroup.
 * @cgrp: the cgroup in question
 *
 * Return the number of tasks in the cgroup.
 */
static int cgroup_task_count(const struct cgroup *cgrp)
{
	int count = 0;
	struct cgrp_cset_link *link;

	down_read(&css_set_rwsem);
	list_for_each_entry(link, &cgrp->cset_links, cset_link)
		count += atomic_read(&link->cset->refcount);
	up_read(&css_set_rwsem);
	return count;
}

/**
 * css_next_child - find the next child of a given css
 * @pos: the current position (%NULL to initiate traversal)
 * @parent: css whose children to walk
 *
 * This function returns the next child of @parent and should be called
 * under either cgroup_mutex or RCU read lock.  The only requirement is
 * that @parent and @pos are accessible.  The next sibling is guaranteed to
 * be returned regardless of their states.
 *
 * If a subsystem synchronizes ->css_online() and the start of iteration, a
 * css which finished ->css_online() is guaranteed to be visible in the
 * future iterations and will stay visible until the last reference is put.
 * A css which hasn't finished ->css_online() or already finished
 * ->css_offline() may show up during traversal.  It's each subsystem's
 * responsibility to synchronize against on/offlining.
 */
struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos,
					   struct cgroup_subsys_state *parent)
{
	struct cgroup_subsys_state *next;

	cgroup_assert_mutex_or_rcu_locked();

	/*
	 * @pos could already have been unlinked from the sibling list.
	 * Once a cgroup is removed, its ->sibling.next is no longer
	 * updated when its next sibling changes.  CSS_RELEASED is set when
	 * @pos is taken off list, at which time its next pointer is valid,
	 * and, as releases are serialized, the one pointed to by the next
	 * pointer is guaranteed to not have started release yet.  This
	 * implies that if we observe !CSS_RELEASED on @pos in this RCU
	 * critical section, the one pointed to by its next pointer is
	 * guaranteed to not have finished its RCU grace period even if we
	 * have dropped rcu_read_lock() inbetween iterations.
	 *
	 * If @pos has CSS_RELEASED set, its next pointer can't be
	 * dereferenced; however, as each css is given a monotonically
	 * increasing unique serial number and always appended to the
	 * sibling list, the next one can be found by walking the parent's
	 * children until the first css with higher serial number than
	 * @pos's.  While this path can be slower, it happens iff iteration
	 * races against release and the race window is very small.
	 */
	if (!pos) {
		next = list_entry_rcu(parent->children.next, struct cgroup_subsys_state, sibling);
	} else if (likely(!(pos->flags & CSS_RELEASED))) {
		next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling);
	} else {
		list_for_each_entry_rcu(next, &parent->children, sibling)
			if (next->serial_nr > pos->serial_nr)
				break;
	}

	/*
	 * @next, if not pointing to the head, can be dereferenced and is
	 * the next sibling.
	 */
	if (&next->sibling != &parent->children)
		return next;
	return NULL;
}

/**
 * css_next_descendant_pre - find the next descendant for pre-order walk
 * @pos: the current position (%NULL to initiate traversal)
 * @root: css whose descendants to walk
 *
 * To be used by css_for_each_descendant_pre().  Find the next descendant
 * to visit for pre-order traversal of @root's descendants.  @root is
 * included in the iteration and the first node to be visited.
 *
 * While this function requires cgroup_mutex or RCU read locking, it
 * doesn't require the whole traversal to be contained in a single critical
 * section.  This function will return the correct next descendant as long
 * as both @pos and @root are accessible and @pos is a descendant of @root.
 *
 * If a subsystem synchronizes ->css_online() and the start of iteration, a
 * css which finished ->css_online() is guaranteed to be visible in the
 * future iterations and will stay visible until the last reference is put.
 * A css which hasn't finished ->css_online() or already finished
 * ->css_offline() may show up during traversal.  It's each subsystem's
 * responsibility to synchronize against on/offlining.
 */
struct cgroup_subsys_state *
css_next_descendant_pre(struct cgroup_subsys_state *pos,
			struct cgroup_subsys_state *root)
{
	struct cgroup_subsys_state *next;

	cgroup_assert_mutex_or_rcu_locked();

	/* if first iteration, visit @root */
	if (!pos)
		return root;

	/* visit the first child if exists */
	next = css_next_child(NULL, pos);
	if (next)
		return next;

	/* no child, visit my or the closest ancestor's next sibling */
	while (pos != root) {
		next = css_next_child(pos, pos->parent);
		if (next)
			return next;
		pos = pos->parent;
	}

	return NULL;
}

/**
 * css_rightmost_descendant - return the rightmost descendant of a css
 * @pos: css of interest
 *
 * Return the rightmost descendant of @pos.  If there's no descendant, @pos
 * is returned.  This can be used during pre-order traversal to skip
 * subtree of @pos.
 *
 * While this function requires cgroup_mutex or RCU read locking, it
 * doesn't require the whole traversal to be contained in a single critical
 * section.  This function will return the correct rightmost descendant as
 * long as @pos is accessible.
 */
struct cgroup_subsys_state *
css_rightmost_descendant(struct cgroup_subsys_state *pos)
{
	struct cgroup_subsys_state *last, *tmp;

	cgroup_assert_mutex_or_rcu_locked();

	do {
		last = pos;
		/* ->prev isn't RCU safe, walk ->next till the end */
		pos = NULL;
		css_for_each_child(tmp, last)
			pos = tmp;
	} while (pos);

	return last;
}

static struct cgroup_subsys_state *
css_leftmost_descendant(struct cgroup_subsys_state *pos)
{
	struct cgroup_subsys_state *last;

	do {
		last = pos;
		pos = css_next_child(NULL, pos);
	} while (pos);

	return last;
}

/**
 * css_next_descendant_post - find the next descendant for post-order walk
 * @pos: the current position (%NULL to initiate traversal)
 * @root: css whose descendants to walk
 *
 * To be used by css_for_each_descendant_post().  Find the next descendant
 * to visit for post-order traversal of @root's descendants.  @root is
 * included in the iteration and the last node to be visited.
 *
 * While this function requires cgroup_mutex or RCU read locking, it
 * doesn't require the whole traversal to be contained in a single critical
 * section.  This function will return the correct next descendant as long
 * as both @pos and @cgroup are accessible and @pos is a descendant of
 * @cgroup.
 *
 * If a subsystem synchronizes ->css_online() and the start of iteration, a
 * css which finished ->css_online() is guaranteed to be visible in the
 * future iterations and will stay visible until the last reference is put.
 * A css which hasn't finished ->css_online() or already finished
 * ->css_offline() may show up during traversal.  It's each subsystem's
 * responsibility to synchronize against on/offlining.
 */
struct cgroup_subsys_state *
css_next_descendant_post(struct cgroup_subsys_state *pos,
			 struct cgroup_subsys_state *root)
{
	struct cgroup_subsys_state *next;

	cgroup_assert_mutex_or_rcu_locked();

	/* if first iteration, visit leftmost descendant which may be @root */
	if (!pos)
		return css_leftmost_descendant(root);

	/* if we visited @root, we're done */
	if (pos == root)
		return NULL;

	/* if there's an unvisited sibling, visit its leftmost descendant */
	next = css_next_child(pos, pos->parent);
	if (next)
		return css_leftmost_descendant(next);

	/* no sibling left, visit parent */
	return pos->parent;
}

/**
 * css_has_online_children - does a css have online children
 * @css: the target css
 *
 * Returns %true if @css has any online children; otherwise, %false.  This
 * function can be called from any context but the caller is responsible
 * for synchronizing against on/offlining as necessary.
 */
bool css_has_online_children(struct cgroup_subsys_state *css)
{
	struct cgroup_subsys_state *child;
	bool ret = false;

	rcu_read_lock();
	css_for_each_child(child, css) {
		if (css->flags & CSS_ONLINE) {
			ret = true;
			break;
		}
	}
	rcu_read_unlock();
	return ret;
}

/**
 * css_advance_task_iter - advance a task itererator to the next css_set
 * @it: the iterator to advance
 *
 * Advance @it to the next css_set to walk.
 */
static void css_advance_task_iter(struct css_task_iter *it)
{
	struct list_head *l = it->cset_pos;
	struct cgrp_cset_link *link;
	struct css_set *cset;

	/* Advance to the next non-empty css_set */
	do {
		l = l->next;
		if (l == it->cset_head) {
			it->cset_pos = NULL;
			return;
		}

		if (it->ss) {
			cset = container_of(l, struct css_set,
					    e_cset_node[it->ss->id]);
		} else {
			link = list_entry(l, struct cgrp_cset_link, cset_link);
			cset = link->cset;
		}
	} while (list_empty(&cset->tasks) && list_empty(&cset->mg_tasks));

	it->cset_pos = l;

	if (!list_empty(&cset->tasks))
		it->task_pos = cset->tasks.next;
	else
		it->task_pos = cset->mg_tasks.next;

	it->tasks_head = &cset->tasks;
	it->mg_tasks_head = &cset->mg_tasks;
}

/**
 * css_task_iter_start - initiate task iteration
 * @css: the css to walk tasks of
 * @it: the task iterator to use
 *
 * Initiate iteration through the tasks of @css.  The caller can call
 * css_task_iter_next() to walk through the tasks until the function
 * returns NULL.  On completion of iteration, css_task_iter_end() must be
 * called.
 *
 * Note that this function acquires a lock which is released when the
 * iteration finishes.  The caller can't sleep while iteration is in
 * progress.
 */
void css_task_iter_start(struct cgroup_subsys_state *css,
			 struct css_task_iter *it)
	__acquires(css_set_rwsem)
{
	/* no one should try to iterate before mounting cgroups */
	WARN_ON_ONCE(!use_task_css_set_links);

	down_read(&css_set_rwsem);

	it->ss = css->ss;

	if (it->ss)
		it->cset_pos = &css->cgroup->e_csets[css->ss->id];
	else
		it->cset_pos = &css->cgroup->cset_links;

	it->cset_head = it->cset_pos;

	css_advance_task_iter(it);
}

/**
 * css_task_iter_next - return the next task for the iterator
 * @it: the task iterator being iterated
 *
 * The "next" function for task iteration.  @it should have been
 * initialized via css_task_iter_start().  Returns NULL when the iteration
 * reaches the end.
 */
struct task_struct *css_task_iter_next(struct css_task_iter *it)
{
	struct task_struct *res;
	struct list_head *l = it->task_pos;

	/* If the iterator cg is NULL, we have no tasks */
	if (!it->cset_pos)
		return NULL;
	res = list_entry(l, struct task_struct, cg_list);

	/*
	 * Advance iterator to find next entry.  cset->tasks is consumed
	 * first and then ->mg_tasks.  After ->mg_tasks, we move onto the
	 * next cset.
	 */
	l = l->next;

	if (l == it->tasks_head)
		l = it->mg_tasks_head->next;

	if (l == it->mg_tasks_head)
		css_advance_task_iter(it);
	else
		it->task_pos = l;

	return res;
}

/**
 * css_task_iter_end - finish task iteration
 * @it: the task iterator to finish
 *
 * Finish task iteration started by css_task_iter_start().
 */
void css_task_iter_end(struct css_task_iter *it)
	__releases(css_set_rwsem)
{
	up_read(&css_set_rwsem);
}

/**
 * cgroup_trasnsfer_tasks - move tasks from one cgroup to another
 * @to: cgroup to which the tasks will be moved
 * @from: cgroup in which the tasks currently reside
 *
 * Locking rules between cgroup_post_fork() and the migration path
 * guarantee that, if a task is forking while being migrated, the new child
 * is guaranteed to be either visible in the source cgroup after the
 * parent's migration is complete or put into the target cgroup.  No task
 * can slip out of migration through forking.
 */
int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
{
	LIST_HEAD(preloaded_csets);
	struct cgrp_cset_link *link;
	struct css_task_iter it;
	struct task_struct *task;
	int ret;

	mutex_lock(&cgroup_mutex);

	/* all tasks in @from are being moved, all csets are source */
	down_read(&css_set_rwsem);
	list_for_each_entry(link, &from->cset_links, cset_link)
		cgroup_migrate_add_src(link->cset, to, &preloaded_csets);
	up_read(&css_set_rwsem);

	ret = cgroup_migrate_prepare_dst(to, &preloaded_csets);
	if (ret)
		goto out_err;

	/*
	 * Migrate tasks one-by-one until @form is empty.  This fails iff
	 * ->can_attach() fails.
	 */
	do {
		css_task_iter_start(&from->self, &it);
		task = css_task_iter_next(&it);
		if (task)
			get_task_struct(task);
		css_task_iter_end(&it);

		if (task) {
			ret = cgroup_migrate(to, task, false);
			put_task_struct(task);
		}
	} while (task && !ret);
out_err:
	cgroup_migrate_finish(&preloaded_csets);
	mutex_unlock(&cgroup_mutex);
	return ret;
}

/*
 * 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.
 *
 */

/* which pidlist file are we talking about? */
enum cgroup_filetype {
	CGROUP_FILE_PROCS,
	CGROUP_FILE_TASKS,
};

/*
 * A pidlist is a list of pids that virtually represents the contents of one
 * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists,
 * a pair (one each for procs, tasks) for each pid namespace that's relevant
 * to the cgroup.
 */
struct cgroup_pidlist {
	/*
	 * used to find which pidlist is wanted. doesn't change as long as
	 * this particular list stays in the list.
	*/
	struct { enum cgroup_filetype type; struct pid_namespace *ns; } key;
	/* array of xids */
	pid_t *list;
	/* how many elements the above list has */
	int length;
	/* each of these stored in a list by its cgroup */
	struct list_head links;
	/* pointer to the cgroup we belong to, for list removal purposes */
	struct cgroup *owner;
	/* for delayed destruction */
	struct delayed_work destroy_dwork;
};

/*
 * 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);
}

/*
 * Used to destroy all pidlists lingering waiting for destroy timer.  None
 * should be left afterwards.
 */
static void cgroup_pidlist_destroy_all(struct cgroup *cgrp)
{
	struct cgroup_pidlist *l, *tmp_l;

	mutex_lock(&cgrp->pidlist_mutex);
	list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links)
		mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0);
	mutex_unlock(&cgrp->pidlist_mutex);

	flush_workqueue(cgroup_pidlist_destroy_wq);
	BUG_ON(!list_empty(&cgrp->pidlists));
}

static void cgroup_pidlist_destroy_work_fn(struct work_struct *work)
{
	struct delayed_work *dwork = to_delayed_work(work);
	struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist,
						destroy_dwork);
	struct cgroup_pidlist *tofree = NULL;

	mutex_lock(&l->owner->pidlist_mutex);

	/*
	 * Destroy iff we didn't get queued again.  The state won't change
	 * as destroy_dwork can only be queued while locked.
	 */
	if (!delayed_work_pending(dwork)) {
		list_del(&l->links);
		pidlist_free(l->list);
		put_pid_ns(l->key.ns);
		tofree = l;
	}

	mutex_unlock(&l->owner->pidlist_mutex);
	kfree(tofree);
}

/*
 * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
 * Returns the number of unique elements.
 */
static int pidlist_uniq(pid_t *list, int length)
{
	int src, dest = 1;

	/*
	 * 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:
	return dest;
}

/*
 * The two pid files - task and cgroup.procs - guaranteed that the result
 * is sorted, which forced this whole pidlist fiasco.  As pid order is
 * different per namespace, each namespace needs differently sorted list,
 * making it impossible to use, for example, single rbtree of member tasks
 * sorted by task pointer.  As pidlists can be fairly large, allocating one
 * per open file is dangerous, so cgroup had to implement shared pool of
 * pidlists keyed by cgroup and namespace.
 *
 * All this extra complexity was caused by the original implementation
 * committing to an entirely unnecessary property.  In the long term, we
 * want to do away with it.  Explicitly scramble sort order if
 * sane_behavior so that no such expectation exists in the new interface.
 *
 * Scrambling is done by swapping every two consecutive bits, which is
 * non-identity one-to-one mapping which disturbs sort order sufficiently.
 */
static pid_t pid_fry(pid_t pid)
{
	unsigned a = pid & 0x55555555;
	unsigned b = pid & 0xAAAAAAAA;

	return (a << 1) | (b >> 1);
}

static pid_t cgroup_pid_fry(struct cgroup *cgrp, pid_t pid)
{
	if (cgroup_sane_behavior(cgrp))
		return pid_fry(pid);
	else
		return pid;
}

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

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

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 = task_active_pid_ns(current);

	lockdep_assert_held(&cgrp->pidlist_mutex);

	list_for_each_entry(l, &cgrp->pidlists, links)
		if (l->key.type == type && l->key.ns == ns)
			return l;
	return NULL;
}

/*
 * 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_create(struct cgroup *cgrp,
						enum cgroup_filetype type)
{
	struct cgroup_pidlist *l;

	lockdep_assert_held(&cgrp->pidlist_mutex);

	l = cgroup_pidlist_find(cgrp, type);
	if (l)
		return l;

	/* entry not found; create a new one */
	l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
	if (!l)
		return l;

	INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn);
	l->key.type = type;
	/* don't need task_nsproxy() if we're looking at ourself */
	l->key.ns = get_pid_ns(task_active_pid_ns(current));
	l->owner = cgrp;
	list_add(&l->links, &cgrp->pidlists);
	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 css_task_iter it;
	struct task_struct *tsk;
	struct cgroup_pidlist *l;

	lockdep_assert_held(&cgrp->pidlist_mutex);

	/*
	 * 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 */
	css_task_iter_start(&cgrp->self, &it);
	while ((tsk = css_task_iter_next(&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;
	}
	css_task_iter_end(&it);
	length = n;
	/* now sort & (if procs) strip out duplicates */
	if (cgroup_sane_behavior(cgrp))
		sort(array, length, sizeof(pid_t), fried_cmppid, NULL);
	else
		sort(array, length, sizeof(pid_t), cmppid, NULL);
	if (type == CGROUP_FILE_PROCS)
		length = pidlist_uniq(array, length);

	l = cgroup_pidlist_find_create(cgrp, type);
	if (!l) {
		mutex_unlock(&cgrp->pidlist_mutex);
		pidlist_free(array);
		return -ENOMEM;
	}

	/* store array, freeing old if necessary */
	pidlist_free(l->list);
	l->list = array;
	l->length = length;
	*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)
{
	struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
	struct cgroup *cgrp;
	struct css_task_iter it;
	struct task_struct *tsk;

	/* it should be kernfs_node belonging to cgroupfs and is a directory */
	if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
	    kernfs_type(kn) != KERNFS_DIR)
		return -EINVAL;

	mutex_lock(&cgroup_mutex);

	/*
	 * We aren't being called from kernfs and there's no guarantee on
	 * @kn->priv's validity.  For this and css_tryget_online_from_dir(),
	 * @kn->priv is RCU safe.  Let's do the RCU dancing.
	 */
	rcu_read_lock();
	cgrp = rcu_dereference(kn->priv);
	if (!cgrp || cgroup_is_dead(cgrp)) {
		rcu_read_unlock();
		mutex_unlock(&cgroup_mutex);
		return -ENOENT;
	}
	rcu_read_unlock();

	css_task_iter_start(&cgrp->self, &it);
	while ((tsk = css_task_iter_next(&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;
		}
	}
	css_task_iter_end(&it);

	mutex_unlock(&cgroup_mutex);
	return 0;
}


/*
 * 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 kernfs_open_file *of = s->private;
	struct cgroup *cgrp = seq_css(s)->cgroup;
	struct cgroup_pidlist *l;
	enum cgroup_filetype type = seq_cft(s)->private;
	int index = 0, pid = *pos;
	int *iter, ret;

	mutex_lock(&cgrp->pidlist_mutex);

	/*
	 * !NULL @of->priv indicates that this isn't the first start()
	 * after open.  If the matching pidlist is around, we can use that.
	 * Look for it.  Note that @of->priv can't be used directly.  It
	 * could already have been destroyed.
	 */
	if (of->priv)
		of->priv = cgroup_pidlist_find(cgrp, type);

	/*
	 * Either this is the first start() after open or the matching
	 * pidlist has been destroyed inbetween.  Create a new one.
	 */
	if (!of->priv) {
		ret = pidlist_array_load(cgrp, type,
					 (struct cgroup_pidlist **)&of->priv);
		if (ret)
			return ERR_PTR(ret);
	}
	l = of->priv;

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

		while (index < end) {
			int mid = (index + end) / 2;
			if (cgroup_pid_fry(cgrp, l->list[mid]) == pid) {
				index = mid;
				break;
			} else if (cgroup_pid_fry(cgrp, 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 = cgroup_pid_fry(cgrp, *iter);
	return iter;
}

static void cgroup_pidlist_stop(struct seq_file *s, void *v)
{
	struct kernfs_open_file *of = s->private;
	struct cgroup_pidlist *l = of->priv;

	if (l)
		mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork,
				 CGROUP_PIDLIST_DESTROY_DELAY);
	mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex);
}

static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
{
	struct kernfs_open_file *of = s->private;
	struct cgroup_pidlist *l = of->priv;
	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 = cgroup_pid_fry(seq_css(s)->cgroup, *p);
		return p;
	}
}

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

static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css,
					 struct cftype *cft)
{
	return notify_on_release(css->cgroup);
}

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

static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css,
				      struct cftype *cft)
{
	return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags);
}

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