cgroup.c

	/*
	 * The effective csses of all the descendants (excluding @cgrp) may
	 * have changed.  Subsystems can optionally subscribe to this event
	 * by implementing ->css_e_css_changed() which is invoked if any of
	 * the effective csses seen from the css's cgroup may have changed.
	 */
	for_each_subsys(ss, ssid) {
		struct cgroup_subsys_state *this_css = cgroup_css(cgrp, ss);
		struct cgroup_subsys_state *css;

		if (!ss->css_e_css_changed || !this_css)
			continue;

		css_for_each_descendant_pre(css, this_css)
			if (css != this_css)
				ss->css_e_css_changed(css);
	}

	kernfs_activate(cgrp->kn);
	ret = 0;
out_unlock:
	cgroup_kn_unlock(of->kn);
	return ret ?: nbytes;

err_undo_css:
	cgrp->subtree_control = old_sc;
	cgrp->child_subsys_mask = old_ss;

	for_each_subsys(ss, ssid) {
		if (!(enable & (1 << ssid)))
			continue;

		cgroup_for_each_live_child(child, cgrp) {
			struct cgroup_subsys_state *css = cgroup_css(child, ss);

			if (!css)
				continue;

			if (css_enable & (1 << ssid))
				kill_css(css);
			else
				cgroup_clear_dir(child, 1 << ssid);
		}
	}
	goto out_unlock;
}

static int cgroup_populated_show(struct seq_file *seq, void *v)
{
	seq_printf(seq, "%d\n", (bool)seq_css(seq)->cgroup->populated_cnt);
	return 0;
}

static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
				 size_t nbytes, loff_t off)
{
	struct cgroup *cgrp = of->kn->parent->priv;
	struct cftype *cft = of->kn->priv;
	struct cgroup_subsys_state *css;
	int ret;

	if (cft->write)
		return cft->write(of, buf, nbytes, off);

	/*
	 * kernfs guarantees that a file isn't deleted with operations in
	 * flight, which means that the matching css is and stays alive and
	 * doesn't need to be pinned.  The RCU locking is not necessary
	 * either.  It's just for the convenience of using cgroup_css().
	 */
	rcu_read_lock();
	css = cgroup_css(cgrp, cft->ss);
	rcu_read_unlock();

	if (cft->write_u64) {
		unsigned long long v;
		ret = kstrtoull(buf, 0, &v);
		if (!ret)
			ret = cft->write_u64(css, cft, v);
	} else if (cft->write_s64) {
		long long v;
		ret = kstrtoll(buf, 0, &v);
		if (!ret)
			ret = cft->write_s64(css, cft, v);
	} else {
		ret = -EINVAL;
	}

	return ret ?: nbytes;
}

static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos)
{
	return seq_cft(seq)->seq_start(seq, ppos);
}

static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos)
{
	return seq_cft(seq)->seq_next(seq, v, ppos);
}

static void cgroup_seqfile_stop(struct seq_file *seq, void *v)
{
	seq_cft(seq)->seq_stop(seq, v);
}

static int cgroup_seqfile_show(struct seq_file *m, void *arg)
{
	struct cftype *cft = seq_cft(m);
	struct cgroup_subsys_state *css = seq_css(m);

	if (cft->seq_show)
		return cft->seq_show(m, arg);

	if (cft->read_u64)
		seq_printf(m, "%llu\n", cft->read_u64(css, cft));
	else if (cft->read_s64)
		seq_printf(m, "%lld\n", cft->read_s64(css, cft));
	else
		return -EINVAL;
	return 0;
}

static struct kernfs_ops cgroup_kf_single_ops = {
	.atomic_write_len	= PAGE_SIZE,
	.write			= cgroup_file_write,
	.seq_show		= cgroup_seqfile_show,
};

static struct kernfs_ops cgroup_kf_ops = {
	.atomic_write_len	= PAGE_SIZE,
	.write			= cgroup_file_write,
	.seq_start		= cgroup_seqfile_start,
	.seq_next		= cgroup_seqfile_next,
	.seq_stop		= cgroup_seqfile_stop,
	.seq_show		= cgroup_seqfile_show,
};

/*
 * cgroup_rename - Only allow simple rename of directories in place.
 */
static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
			 const char *new_name_str)
{
	struct cgroup *cgrp = kn->priv;
	int ret;

	if (kernfs_type(kn) != KERNFS_DIR)
		return -ENOTDIR;
	if (kn->parent != new_parent)
		return -EIO;

	/*
	 * This isn't a proper migration and its usefulness is very
	 * limited.  Disallow on the default hierarchy.
	 */
	if (cgroup_on_dfl(cgrp))
		return -EPERM;

	/*
	 * We're gonna grab cgroup_mutex which nests outside kernfs
	 * active_ref.  kernfs_rename() doesn't require active_ref
	 * protection.  Break them before grabbing cgroup_mutex.
	 */
	kernfs_break_active_protection(new_parent);
	kernfs_break_active_protection(kn);

	mutex_lock(&cgroup_mutex);

	ret = kernfs_rename(kn, new_parent, new_name_str);

	mutex_unlock(&cgroup_mutex);

	kernfs_unbreak_active_protection(kn);
	kernfs_unbreak_active_protection(new_parent);
	return ret;
}

/* set uid and gid of cgroup dirs and files to that of the creator */
static int cgroup_kn_set_ugid(struct kernfs_node *kn)
{
	struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
			       .ia_uid = current_fsuid(),
			       .ia_gid = current_fsgid(), };

	if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
	    gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
		return 0;

	return kernfs_setattr(kn, &iattr);
}

static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft)
{
	char name[CGROUP_FILE_NAME_MAX];
	struct kernfs_node *kn;
	struct lock_class_key *key = NULL;
	int ret;

#ifdef CONFIG_DEBUG_LOCK_ALLOC
	key = &cft->lockdep_key;
#endif
	kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name),
				  cgroup_file_mode(cft), 0, cft->kf_ops, cft,
				  NULL, key);
	if (IS_ERR(kn))
		return PTR_ERR(kn);

	ret = cgroup_kn_set_ugid(kn);
	if (ret) {
		kernfs_remove(kn);
		return ret;
	}

	if (cft->write == cgroup_procs_write)
		cgrp->procs_kn = kn;
	else if (cft->seq_show == cgroup_populated_show)
		cgrp->populated_kn = kn;
	return 0;
}

/**
 * cgroup_addrm_files - add or remove files to a cgroup directory
 * @cgrp: the target cgroup
 * @cfts: array of cftypes to be added
 * @is_add: whether to add or remove
 *
 * Depending on @is_add, add or remove files defined by @cfts on @cgrp.
 * For removals, this function never fails.  If addition fails, this
 * function doesn't remove files already added.  The caller is responsible
 * for cleaning up.
 */
static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
			      bool is_add)
{
	struct cftype *cft;
	int ret;

	lockdep_assert_held(&cgroup_mutex);

	for (cft = cfts; cft->name[0] != '\0'; cft++) {
		/* does cft->flags tell us to skip this file on @cgrp? */
		if ((cft->flags & __CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp))
			continue;
		if ((cft->flags & __CFTYPE_NOT_ON_DFL) && cgroup_on_dfl(cgrp))
			continue;
		if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgroup_parent(cgrp))
			continue;
		if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp))
			continue;

		if (is_add) {
			ret = cgroup_add_file(cgrp, cft);
			if (ret) {
				pr_warn("%s: failed to add %s, err=%d\n",
					__func__, cft->name, ret);
				return ret;
			}
		} else {
			cgroup_rm_file(cgrp, cft);
		}
	}
	return 0;
}

static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add)
{
	LIST_HEAD(pending);
	struct cgroup_subsys *ss = cfts[0].ss;
	struct cgroup *root = &ss->root->cgrp;
	struct cgroup_subsys_state *css;
	int ret = 0;

	lockdep_assert_held(&cgroup_mutex);

	/* add/rm files for all cgroups created before */
	css_for_each_descendant_pre(css, cgroup_css(root, ss)) {
		struct cgroup *cgrp = css->cgroup;

		if (cgroup_is_dead(cgrp))
			continue;

		ret = cgroup_addrm_files(cgrp, cfts, is_add);
		if (ret)
			break;
	}

	if (is_add && !ret)
		kernfs_activate(root->kn);
	return ret;
}

static void cgroup_exit_cftypes(struct cftype *cfts)
{
	struct cftype *cft;

	for (cft = cfts; cft->name[0] != '\0'; cft++) {
		/* free copy for custom atomic_write_len, see init_cftypes() */
		if (cft->max_write_len && cft->max_write_len != PAGE_SIZE)
			kfree(cft->kf_ops);
		cft->kf_ops = NULL;
		cft->ss = NULL;

		/* revert flags set by cgroup core while adding @cfts */
		cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL);
	}
}

static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
	struct cftype *cft;

	for (cft = cfts; cft->name[0] != '\0'; cft++) {
		struct kernfs_ops *kf_ops;

		WARN_ON(cft->ss || cft->kf_ops);

		if (cft->seq_start)
			kf_ops = &cgroup_kf_ops;
		else
			kf_ops = &cgroup_kf_single_ops;

		/*
		 * 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.
 */
static int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
	int ret;

	if (!cgroup_ssid_enabled(ss->id))
		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_add_dfl_cftypes - add an array of cftypes for default hierarchy
 * @ss: target cgroup subsystem
 * @cfts: zero-length name terminated array of cftypes
 *
 * Similar to cgroup_add_cftypes() but the added files are only used for
 * the default hierarchy.
 */
int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
	struct cftype *cft;

	for (cft = cfts; cft && cft->name[0] != '\0'; cft++)
		cft->flags |= __CFTYPE_ONLY_ON_DFL;
	return cgroup_add_cftypes(ss, cfts);
}

/**
 * cgroup_add_legacy_cftypes - add an array of cftypes for legacy hierarchies
 * @ss: target cgroup subsystem
 * @cfts: zero-length name terminated array of cftypes
 *
 * Similar to cgroup_add_cftypes() but the added files are only used for
 * the legacy hierarchies.
 */
int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
{
	struct cftype *cft;

	/*
	 * If legacy_flies_on_dfl, we want to show the legacy files on the
	 * dfl hierarchy but iff the target subsystem hasn't been updated
	 * for the dfl hierarchy yet.
	 */
	if (!cgroup_legacy_files_on_dfl ||
	    ss->dfl_cftypes != ss->legacy_cftypes) {
		for (cft = cfts; cft && cft->name[0] != '\0'; cft++)
			cft->flags |= __CFTYPE_NOT_ON_DFL;
	}

	return cgroup_add_cftypes(ss, cfts);
}

/**
 * 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 (child->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)
{
	kvfree(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;