cgroup.c

	 */
	mutex_unlock(&cgroup_mutex);
	cgroup_clear_dir(cgrp, removed_mask);
	mutex_lock(&cgroup_mutex);

	for_each_subsys(ss, i) {
		unsigned long bit = 1UL << i;

		if (bit & added_mask) {
			/* We're binding this subsystem to this hierarchy */
			BUG_ON(cgroup_css(cgrp, ss));
			BUG_ON(!cgroup_css(cgroup_dummy_top, ss));
			BUG_ON(cgroup_css(cgroup_dummy_top, ss)->cgroup != cgroup_dummy_top);

			rcu_assign_pointer(cgrp->subsys[i],
					   cgroup_css(cgroup_dummy_top, ss));
			cgroup_css(cgrp, ss)->cgroup = cgrp;

			ss->root = root;
			if (ss->bind)
				ss->bind(cgroup_css(cgrp, ss));

			/* refcount was already taken, and we're keeping it */
			root->subsys_mask |= bit;
		} else if (bit & removed_mask) {
			/* We're removing this subsystem */
			BUG_ON(cgroup_css(cgrp, ss) != cgroup_css(cgroup_dummy_top, ss));
			BUG_ON(cgroup_css(cgrp, ss)->cgroup != cgrp);

			if (ss->bind)
				ss->bind(cgroup_css(cgroup_dummy_top, ss));

			cgroup_css(cgroup_dummy_top, ss)->cgroup = cgroup_dummy_top;
			RCU_INIT_POINTER(cgrp->subsys[i], NULL);

			cgroup_subsys[i]->root = &cgroup_dummy_root;
			root->subsys_mask &= ~bit;
		}
	}

	kernfs_activate(cgrp->kn);
	return 0;
}

static int cgroup_show_options(struct seq_file *seq,
			       struct kernfs_root *kf_root)
{
	struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
	struct cgroup_subsys *ss;
	int ssid;

	for_each_subsys(ss, ssid)
		if (root->subsys_mask & (1 << ssid))
			seq_printf(seq, ",%s", ss->name);
	if (root->flags & CGRP_ROOT_SANE_BEHAVIOR)
		seq_puts(seq, ",sane_behavior");
	if (root->flags & CGRP_ROOT_NOPREFIX)
		seq_puts(seq, ",noprefix");
	if (root->flags & CGRP_ROOT_XATTR)
		seq_puts(seq, ",xattr");

	spin_lock(&release_agent_path_lock);
	if (strlen(root->release_agent_path))
		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
	spin_unlock(&release_agent_path_lock);

	if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags))
		seq_puts(seq, ",clone_children");
	if (strlen(root->name))
		seq_printf(seq, ",name=%s", root->name);
	return 0;
}

struct cgroup_sb_opts {
	unsigned long subsys_mask;
	unsigned long flags;
	char *release_agent;
	bool cpuset_clone_children;
	char *name;
	/* User explicitly requested empty subsystem */
	bool none;
};

/*
 * Convert a hierarchy specifier into a bitmask of subsystems and
 * flags. Call with cgroup_mutex held to protect the cgroup_subsys[]
 * array. This function takes refcounts on subsystems to be used, unless it
 * returns error, in which case no refcounts are taken.
 */
static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
{
	char *token, *o = data;
	bool all_ss = false, one_ss = false;
	unsigned long mask = (unsigned long)-1;
	struct cgroup_subsys *ss;
	int i;

	BUG_ON(!mutex_is_locked(&cgroup_mutex));

#ifdef CONFIG_CPUSETS
	mask = ~(1UL << cpuset_cgrp_id);
#endif

	memset(opts, 0, sizeof(*opts));

	while ((token = strsep(&o, ",")) != NULL) {
		if (!*token)
			return -EINVAL;
		if (!strcmp(token, "none")) {
			/* Explicitly have no subsystems */
			opts->none = true;
			continue;
		}
		if (!strcmp(token, "all")) {
			/* Mutually exclusive option 'all' + subsystem name */
			if (one_ss)
				return -EINVAL;
			all_ss = true;
			continue;
		}
		if (!strcmp(token, "__DEVEL__sane_behavior")) {
			opts->flags |= CGRP_ROOT_SANE_BEHAVIOR;
			continue;
		}
		if (!strcmp(token, "noprefix")) {
			opts->flags |= CGRP_ROOT_NOPREFIX;
			continue;
		}
		if (!strcmp(token, "clone_children")) {
			opts->cpuset_clone_children = true;
			continue;
		}
		if (!strcmp(token, "xattr")) {
			opts->flags |= CGRP_ROOT_XATTR;
			continue;
		}
		if (!strncmp(token, "release_agent=", 14)) {
			/* Specifying two release agents is forbidden */
			if (opts->release_agent)
				return -EINVAL;
			opts->release_agent =
				kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL);
			if (!opts->release_agent)
				return -ENOMEM;
			continue;
		}
		if (!strncmp(token, "name=", 5)) {
			const char *name = token + 5;
			/* Can't specify an empty name */
			if (!strlen(name))
				return -EINVAL;
			/* Must match [\w.-]+ */
			for (i = 0; i < strlen(name); i++) {
				char c = name[i];
				if (isalnum(c))
					continue;
				if ((c == '.') || (c == '-') || (c == '_'))
					continue;
				return -EINVAL;
			}
			/* Specifying two names is forbidden */
			if (opts->name)
				return -EINVAL;
			opts->name = kstrndup(name,
					      MAX_CGROUP_ROOT_NAMELEN - 1,
					      GFP_KERNEL);
			if (!opts->name)
				return -ENOMEM;

			continue;
		}

		for_each_subsys(ss, i) {
			if (strcmp(token, ss->name))
				continue;
			if (ss->disabled)
				continue;

			/* Mutually exclusive option 'all' + subsystem name */
			if (all_ss)
				return -EINVAL;
			set_bit(i, &opts->subsys_mask);
			one_ss = true;

			break;
		}
		if (i == CGROUP_SUBSYS_COUNT)
			return -ENOENT;
	}

	/*
	 * If the 'all' option was specified select all the subsystems,
	 * otherwise if 'none', 'name=' and a subsystem name options
	 * were not specified, let's default to 'all'
	 */
	if (all_ss || (!one_ss && !opts->none && !opts->name))
		for_each_subsys(ss, i)
			if (!ss->disabled)
				set_bit(i, &opts->subsys_mask);

	/* Consistency checks */

	if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
		pr_warning("cgroup: sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");

		if ((opts->flags & (CGRP_ROOT_NOPREFIX | CGRP_ROOT_XATTR)) ||
		    opts->cpuset_clone_children || opts->release_agent ||
		    opts->name) {
			pr_err("cgroup: sane_behavior: noprefix, xattr, clone_children, release_agent and name are not allowed\n");
			return -EINVAL;
		}
	}

	/*
	 * Option noprefix was introduced just for backward compatibility
	 * with the old cpuset, so we allow noprefix only if mounting just
	 * the cpuset subsystem.
	 */
	if ((opts->flags & CGRP_ROOT_NOPREFIX) && (opts->subsys_mask & mask))
		return -EINVAL;


	/* Can't specify "none" and some subsystems */
	if (opts->subsys_mask && opts->none)
		return -EINVAL;

	/*
	 * We either have to specify by name or by subsystems. (So all
	 * empty hierarchies must have a name).
	 */
	if (!opts->subsys_mask && !opts->name)
		return -EINVAL;

	return 0;
}

static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
{
	int ret = 0;
	struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
	struct cgroup_sb_opts opts;
	unsigned long added_mask, removed_mask;

	if (root->flags & CGRP_ROOT_SANE_BEHAVIOR) {
		pr_err("cgroup: sane_behavior: remount is not allowed\n");
		return -EINVAL;
	}

	mutex_lock(&cgroup_tree_mutex);
	mutex_lock(&cgroup_mutex);

	/* See what subsystems are wanted */
	ret = parse_cgroupfs_options(data, &opts);
	if (ret)
		goto out_unlock;

	if (opts.subsys_mask != root->subsys_mask || opts.release_agent)
		pr_warning("cgroup: option changes via remount are deprecated (pid=%d comm=%s)\n",
			   task_tgid_nr(current), current->comm);

	added_mask = opts.subsys_mask & ~root->subsys_mask;
	removed_mask = root->subsys_mask & ~opts.subsys_mask;

	/* Don't allow flags or name to change at remount */
	if (((opts.flags ^ root->flags) & CGRP_ROOT_OPTION_MASK) ||
	    (opts.name && strcmp(opts.name, root->name))) {
		pr_err("cgroup: option or name mismatch, new: 0x%lx \"%s\", old: 0x%lx \"%s\"\n",
		       opts.flags & CGRP_ROOT_OPTION_MASK, opts.name ?: "",
		       root->flags & CGRP_ROOT_OPTION_MASK, root->name);
		ret = -EINVAL;
		goto out_unlock;
	}

	/* remounting is not allowed for populated hierarchies */
	if (!list_empty(&root->top_cgroup.children)) {
		ret = -EBUSY;
		goto out_unlock;
	}

	ret = rebind_subsystems(root, added_mask, removed_mask);
	if (ret)
		goto out_unlock;

	if (opts.release_agent) {
		spin_lock(&release_agent_path_lock);
		strcpy(root->release_agent_path, opts.release_agent);
		spin_unlock(&release_agent_path_lock);
	}
 out_unlock:
	kfree(opts.release_agent);
	kfree(opts.name);
	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&cgroup_tree_mutex);
	return ret;
}

/*
 * To reduce the fork() overhead for systems that are not actually using
 * their cgroups capability, we don't maintain the lists running through
 * each css_set to its tasks until we see the list actually used - in other
 * words after the first mount.
 */
static bool use_task_css_set_links __read_mostly;

static void cgroup_enable_task_cg_lists(void)
{
	struct task_struct *p, *g;

	down_write(&css_set_rwsem);

	if (use_task_css_set_links)
		goto out_unlock;

	use_task_css_set_links = true;

	/*
	 * We need tasklist_lock because RCU is not safe against
	 * while_each_thread(). Besides, a forking task that has passed
	 * cgroup_post_fork() without seeing use_task_css_set_links = 1
	 * is not guaranteed to have its child immediately visible in the
	 * tasklist if we walk through it with RCU.
	 */
	read_lock(&tasklist_lock);
	do_each_thread(g, p) {
		task_lock(p);

		WARN_ON_ONCE(!list_empty(&p->cg_list) ||
			     task_css_set(p) != &init_css_set);

		/*
		 * We should check if the process is exiting, otherwise
		 * it will race with cgroup_exit() in that the list
		 * entry won't be deleted though the process has exited.
		 */
		if (!(p->flags & PF_EXITING))
			list_add(&p->cg_list, &task_css_set(p)->tasks);

		task_unlock(p);
	} while_each_thread(g, p);
	read_unlock(&tasklist_lock);
out_unlock:
	up_write(&css_set_rwsem);
}

static void init_cgroup_housekeeping(struct cgroup *cgrp)
{
	atomic_set(&cgrp->refcnt, 1);
	INIT_LIST_HEAD(&cgrp->sibling);
	INIT_LIST_HEAD(&cgrp->children);
	INIT_LIST_HEAD(&cgrp->cset_links);
	INIT_LIST_HEAD(&cgrp->release_list);
	INIT_LIST_HEAD(&cgrp->pidlists);
	mutex_init(&cgrp->pidlist_mutex);
	cgrp->dummy_css.cgroup = cgrp;
}

static void init_cgroup_root(struct cgroupfs_root *root)
{
	struct cgroup *cgrp = &root->top_cgroup;

	INIT_LIST_HEAD(&root->root_list);
	atomic_set(&root->nr_cgrps, 1);
	cgrp->root = root;
	init_cgroup_housekeeping(cgrp);
	idr_init(&root->cgroup_idr);
}

static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
{
	struct cgroupfs_root *root;

	if (!opts->subsys_mask && !opts->none)
		return ERR_PTR(-EINVAL);

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

	init_cgroup_root(root);

	root->flags = opts->flags;
	if (opts->release_agent)
		strcpy(root->release_agent_path, opts->release_agent);
	if (opts->name)
		strcpy(root->name, opts->name);
	if (opts->cpuset_clone_children)
		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags);
	return root;
}

static int cgroup_setup_root(struct cgroupfs_root *root, unsigned long ss_mask)
{
	LIST_HEAD(tmp_links);
	struct cgroup *root_cgrp = &root->top_cgroup;
	struct css_set *cset;
	int i, ret;

	lockdep_assert_held(&cgroup_tree_mutex);
	lockdep_assert_held(&cgroup_mutex);

	ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL);
	if (ret < 0)
		goto out;
	root_cgrp->id = ret;

	/*
	 * We're accessing css_set_count without locking css_set_rwsem here,
	 * but that's OK - it can only be increased by someone holding
	 * cgroup_lock, and that's us. The worst that can happen is that we
	 * have some link structures left over
	 */
	ret = allocate_cgrp_cset_links(css_set_count, &tmp_links);
	if (ret)
		goto out;

	/* ID 0 is reserved for dummy root, 1 for unified hierarchy */
	ret = cgroup_init_root_id(root, 2, 0);
	if (ret)
		goto out;

	root->kf_root = kernfs_create_root(&cgroup_kf_syscall_ops,
					   KERNFS_ROOT_CREATE_DEACTIVATED,
					   root_cgrp);
	if (IS_ERR(root->kf_root)) {
		ret = PTR_ERR(root->kf_root);
		goto exit_root_id;
	}
	root_cgrp->kn = root->kf_root->kn;

	ret = cgroup_addrm_files(root_cgrp, cgroup_base_files, true);
	if (ret)
		goto destroy_root;

	ret = rebind_subsystems(root, ss_mask, 0);
	if (ret)
		goto destroy_root;

	/*
	 * There must be no failure case after here, since rebinding takes
	 * care of subsystems' refcounts, which are explicitly dropped in
	 * the failure exit path.
	 */
	list_add(&root->root_list, &cgroup_roots);
	cgroup_root_count++;

	/*
	 * Link the top cgroup in this hierarchy into all the css_set
	 * objects.
	 */
	down_write(&css_set_rwsem);
	hash_for_each(css_set_table, i, cset, hlist)
		link_css_set(&tmp_links, cset, root_cgrp);
	up_write(&css_set_rwsem);

	BUG_ON(!list_empty(&root_cgrp->children));
	BUG_ON(atomic_read(&root->nr_cgrps) != 1);

	kernfs_activate(root_cgrp->kn);
	ret = 0;
	goto out;

destroy_root:
	kernfs_destroy_root(root->kf_root);
	root->kf_root = NULL;
exit_root_id:
	cgroup_exit_root_id(root);
out:
	free_cgrp_cset_links(&tmp_links);
	return ret;
}

static struct dentry *cgroup_mount(struct file_system_type *fs_type,
			 int flags, const char *unused_dev_name,
			 void *data)
{
	struct cgroupfs_root *root;
	struct cgroup_sb_opts opts;
	struct dentry *dentry;
	int ret;

	/*
	 * The first time anyone tries to mount a cgroup, enable the list
	 * linking each css_set to its tasks and fix up all existing tasks.
	 */
	if (!use_task_css_set_links)
		cgroup_enable_task_cg_lists();
retry:
	mutex_lock(&cgroup_tree_mutex);
	mutex_lock(&cgroup_mutex);

	/* First find the desired set of subsystems */
	ret = parse_cgroupfs_options(data, &opts);
	if (ret)
		goto out_unlock;

	/* look for a matching existing root */
	for_each_active_root(root) {
		bool name_match = false;

		/*
		 * If we asked for a name then it must match.  Also, if
		 * name matches but sybsys_mask doesn't, we should fail.
		 * Remember whether name matched.
		 */
		if (opts.name) {
			if (strcmp(opts.name, root->name))
				continue;
			name_match = true;
		}

		/*
		 * If we asked for subsystems (or explicitly for no
		 * subsystems) then they must match.
		 */
		if ((opts.subsys_mask || opts.none) &&
		    (opts.subsys_mask != root->subsys_mask)) {
			if (!name_match)
				continue;
			ret = -EBUSY;
			goto out_unlock;
		}

		if ((root->flags ^ opts.flags) & CGRP_ROOT_OPTION_MASK) {
			if ((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) {
				pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n");
				ret = -EINVAL;
				goto out_unlock;
			} else {
				pr_warning("cgroup: new mount options do not match the existing superblock, will be ignored\n");
			}
		}

		/*
		 * A root's lifetime is governed by its top cgroup.  Zero
		 * ref indicate that the root is being destroyed.  Wait for
		 * destruction to complete so that the subsystems are free.
		 * We can use wait_queue for the wait but this path is
		 * super cold.  Let's just sleep for a bit and retry.
		 */
		if (!atomic_inc_not_zero(&root->top_cgroup.refcnt)) {
			mutex_unlock(&cgroup_mutex);
			mutex_unlock(&cgroup_tree_mutex);
			kfree(opts.release_agent);
			kfree(opts.name);
			msleep(10);
			goto retry;
		}

		ret = 0;
		goto out_unlock;
	}

	/* no such thing, create a new one */
	root = cgroup_root_from_opts(&opts);
	if (IS_ERR(root)) {
		ret = PTR_ERR(root);
		goto out_unlock;
	}

	ret = cgroup_setup_root(root, opts.subsys_mask);
	if (ret)
		cgroup_free_root(root);

out_unlock:
	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&cgroup_tree_mutex);

	kfree(opts.release_agent);
	kfree(opts.name);

	if (ret)
		return ERR_PTR(ret);

	dentry = kernfs_mount(fs_type, flags, root->kf_root);
	if (IS_ERR(dentry))
		cgroup_put(&root->top_cgroup);
	return dentry;
}

static void cgroup_kill_sb(struct super_block *sb)
{
	struct kernfs_root *kf_root = kernfs_root_from_sb(sb);
	struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);

	cgroup_put(&root->top_cgroup);
	kernfs_kill_sb(sb);
}

static struct file_system_type cgroup_fs_type = {
	.name = "cgroup",
	.mount = cgroup_mount,
	.kill_sb = cgroup_kill_sb,
};

static struct kobject *cgroup_kobj;

/**
 * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
 * @task: target task
 * @buf: the buffer to write the path into
 * @buflen: the length of the buffer
 *
 * Determine @task's cgroup on the first (the one with the lowest non-zero
 * hierarchy_id) cgroup hierarchy and copy its path into @buf.  This
 * function grabs cgroup_mutex and shouldn't be used inside locks used by
 * cgroup controller callbacks.
 *
 * Return value is the same as kernfs_path().
 */
char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
{
	struct cgroupfs_root *root;
	struct cgroup *cgrp;
	int hierarchy_id = 1;
	char *path = NULL;

	mutex_lock(&cgroup_mutex);
	down_read(&css_set_rwsem);

	root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id);

	if (root) {
		cgrp = task_cgroup_from_root(task, root);
		path = cgroup_path(cgrp, buf, buflen);
	} else {
		/* if no hierarchy exists, everyone is in "/" */
		if (strlcpy(buf, "/", buflen) < buflen)
			path = buf;
	}

	up_read(&css_set_rwsem);
	mutex_unlock(&cgroup_mutex);
	return path;
}
EXPORT_SYMBOL_GPL(task_cgroup_path);

/*
 * Control Group taskset
 */
struct task_and_cgroup {
	struct task_struct	*task;
	struct cgroup		*cgrp;
	struct css_set		*cset;
};

struct cgroup_taskset {
	struct task_and_cgroup	single;
	struct flex_array	*tc_array;
	int			tc_array_len;
	int			idx;
};

/**
 * cgroup_taskset_first - reset taskset and return the first task
 * @tset: taskset of interest
 *
 * @tset iteration is initialized and the first task is returned.
 */
struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
{
	if (tset->tc_array) {
		tset->idx = 0;
		return cgroup_taskset_next(tset);
	} else {
		return tset->single.task;
	}
}

/**
 * cgroup_taskset_next - iterate to the next task in taskset
 * @tset: taskset of interest
 *
 * Return the next task in @tset.  Iteration must have been initialized
 * with cgroup_taskset_first().
 */
struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
{
	struct task_and_cgroup *tc;

	if (!tset->tc_array || tset->idx >= tset->tc_array_len)
		return NULL;

	tc = flex_array_get(tset->tc_array, tset->idx++);
	return tc->task;
}

/**
 * cgroup_task_migrate - move a task from one cgroup to another.
 * @old_cgrp; the cgroup @tsk is being migrated from
 * @tsk: the task being migrated
 * @new_cset: the new css_set @tsk is being attached to
 *
 * Must be called with cgroup_mutex, threadgroup and css_set_rwsem locked.
 */
static void cgroup_task_migrate(struct cgroup *old_cgrp,
				struct task_struct *tsk,
				struct css_set *new_cset)
{
	struct css_set *old_cset;

	lockdep_assert_held(&cgroup_mutex);
	lockdep_assert_held(&css_set_rwsem);

	/*
	 * We are synchronized through threadgroup_lock() against PF_EXITING
	 * setting such that we can't race against cgroup_exit() changing the
	 * css_set to init_css_set and dropping the old one.
	 */
	WARN_ON_ONCE(tsk->flags & PF_EXITING);
	old_cset = task_css_set(tsk);

	task_lock(tsk);
	rcu_assign_pointer(tsk->cgroups, new_cset);
	task_unlock(tsk);

	list_move(&tsk->cg_list, &new_cset->tasks);

	/*
	 * We just gained a reference on old_cset by taking it from the
	 * task. As trading it for new_cset is protected by cgroup_mutex,
	 * we're safe to drop it here; it will be freed under RCU.
	 */
	set_bit(CGRP_RELEASABLE, &old_cgrp->flags);
	put_css_set_locked(old_cset, false);
}

/**
 * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup
 * @cgrp: the cgroup to attach to
 * @leader: the task or the leader of the threadgroup to be attached
 * @threadgroup: attach the whole threadgroup?
 *
 * Call holding cgroup_mutex and the group_rwsem of the leader. Will take
 * task_lock of @tsk or each thread in the threadgroup individually in turn.
 */
static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *leader,
			      bool threadgroup)
{
	int ret, i, group_size;
	struct cgroupfs_root *root = cgrp->root;
	struct cgroup_subsys_state *css, *failed_css = NULL;
	/* threadgroup list cursor and array */
	struct task_struct *task;
	struct task_and_cgroup *tc;
	struct flex_array *group;
	struct cgroup_taskset tset = { };

	/*
	 * step 0: in order to do expensive, possibly blocking operations for
	 * every thread, we cannot iterate the thread group list, since it needs
	 * rcu or tasklist locked. instead, build an array of all threads in the
	 * group - group_rwsem prevents new threads from appearing, and if
	 * threads exit, this will just be an over-estimate.
	 */
	if (threadgroup)
		group_size = get_nr_threads(leader);
	else
		group_size = 1;
	/* flex_array supports very large thread-groups better than kmalloc. */
	group = flex_array_alloc(sizeof(*tc), group_size, GFP_KERNEL);
	if (!group)
		return -ENOMEM;
	/* pre-allocate to guarantee space while iterating in rcu read-side. */
	ret = flex_array_prealloc(group, 0, group_size, GFP_KERNEL);
	if (ret)
		goto out_free_group_list;

	i = 0;
	/*
	 * Prevent freeing of tasks while we take a snapshot. Tasks that are
	 * already PF_EXITING could be freed from underneath us unless we
	 * take an rcu_read_lock.
	 */
	down_read(&css_set_rwsem);
	rcu_read_lock();
	task = leader;
	do {
		struct task_and_cgroup ent;

		/* @task either already exited or can't exit until the end */
		if (task->flags & PF_EXITING)
			goto next;

		/* as per above, nr_threads may decrease, but not increase. */
		BUG_ON(i >= group_size);
		ent.task = task;
		ent.cgrp = task_cgroup_from_root(task, root);
		/* nothing to do if this task is already in the cgroup */
		if (ent.cgrp == cgrp)
			goto next;
		/*
		 * saying GFP_ATOMIC has no effect here because we did prealloc
		 * earlier, but it's good form to communicate our expectations.
		 */
		ret = flex_array_put(group, i, &ent, GFP_ATOMIC);
		BUG_ON(ret != 0);
		i++;
	next:
		if (!threadgroup)
			break;
	} while_each_thread(leader, task);
	rcu_read_unlock();
	up_read(&css_set_rwsem);
	/* remember the number of threads in the array for later. */
	group_size = i;
	tset.tc_array = group;
	tset.tc_array_len = group_size;

	/* methods shouldn't be called if no task is actually migrating */
	ret = 0;
	if (!group_size)
		goto out_free_group_list;

	/*
	 * step 1: check that we can legitimately attach to the cgroup.
	 */
	for_each_css(css, i, cgrp) {
		if (css->ss->can_attach) {
			ret = css->ss->can_attach(css, &tset);
			if (ret) {
				failed_css = css;
				goto out_cancel_attach;
			}
		}
	}

	/*
	 * step 2: make sure css_sets exist for all threads to be migrated.
	 * we use find_css_set, which allocates a new one if necessary.
	 */
	for (i = 0; i < group_size; i++) {
		struct css_set *old_cset;

		tc = flex_array_get(group, i);
		old_cset = task_css_set(tc->task);
		tc->cset = find_css_set(old_cset, cgrp);
		if (!tc->cset) {
			ret = -ENOMEM;
			goto out_put_css_set_refs;
		}
	}

	/*
	 * step 3: now that we're guaranteed success wrt the css_sets,
	 * proceed to move all tasks to the new cgroup.  There are no
	 * failure cases after here, so this is the commit point.
	 */
	down_write(&css_set_rwsem);
	for (i = 0; i < group_size; i++) {
		tc = flex_array_get(group, i);
		cgroup_task_migrate(tc->cgrp, tc->task, tc->cset);
	}
	up_write(&css_set_rwsem);
	/* nothing is sensitive to fork() after this point. */

	/*
	 * step 4: do subsystem attach callbacks.
	 */
	for_each_css(css, i, cgrp)
		if (css->ss->attach)
			css->ss->attach(css, &tset);

	/*
	 * step 5: success! and cleanup
	 */
	ret = 0;
out_put_css_set_refs:
	if (ret) {
		for (i = 0; i < group_size; i++) {
			tc = flex_array_get(group, i);
			if (!tc->cset)
				break;
			put_css_set(tc->cset, false);
		}
	}
out_cancel_attach:
	if (ret) {
		for_each_css(css, i, cgrp) {
			if (css == failed_css)
				break;
			if (css->ss->cancel_attach)
				css->ss->cancel_attach(css, &tset);
		}
	}
out_free_group_list:
	flex_array_free(group);
	return ret;
}

/*
 * Find the task_struct of the task to attach by vpid and pass it along to the
 * function to attach either it or all tasks in its threadgroup. Will lock
 * cgroup_mutex and threadgroup; may take task_lock of task.
 */
static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup)
{
	struct task_struct *tsk;
	const struct cred *cred = current_cred(), *tcred;
	int ret;

	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;

retry_find_task:
	rcu_read_lock();
	if (pid) {
		tsk = find_task_by_vpid(pid);
		if (!tsk) {
			rcu_read_unlock();
			ret = -ESRCH;
			goto out_unlock_cgroup;
		}
		/*
		 * even if we're attaching all tasks in the thread group, we
		 * only need to check permissions on one of them.
		 */
		tcred = __task_cred(tsk);
		if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
		    !uid_eq(cred->euid, tcred->uid) &&
		    !uid_eq(cred->euid, tcred->suid)) {
			rcu_read_unlock();
			ret = -EACCES;
			goto out_unlock_cgroup;
		}
	} else
		tsk = current;

	if (threadgroup)
		tsk = tsk->group_leader;

	/*
	 * Workqueue threads may acquire PF_NO_SETAFFINITY and become
	 * trapped in a cpuset, or RT worker may be born in a cgroup
	 * with no rt_runtime allocated.  Just say no.
	 */
	if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
		ret = -EINVAL;
		rcu_read_unlock();
		goto out_unlock_cgroup;
	}

	get_task_struct(tsk);
	rcu_read_unlock();

	threadgroup_lock(tsk);
	if (threadgroup) {
		if (!thread_group_leader(tsk)) {
			/*
			 * a race with de_thread from another thread's exec()
			 * may strip us of our leadership, if this happens,
			 * there is no choice but to throw this task away and
			 * try again; this is
			 * "double-double-toil-and-trouble-check locking".
			 */
			threadgroup_unlock(tsk);
			put_task_struct(tsk);
			goto retry_find_task;
		}
	}

	ret = cgroup_attach_task(cgrp, tsk, threadgroup);

	threadgroup_unlock(tsk);

	put_task_struct(tsk);
out_unlock_cgroup:
	mutex_unlock(&cgroup_mutex);
	return ret;
}

/**
 * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from'
 * @from: attach to all cgroups of a given task
 * @tsk: the task to be attached
 */
int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
{
	struct cgroupfs_root *root;
	int retval = 0;

	mutex_lock(&cgroup_mutex);
	for_each_active_root(root) {
		struct cgroup *from_cgrp;

		down_read(&css_set_rwsem);
		from_cgrp = task_cgroup_from_root(from, root);
		up_read(&css_set_rwsem);

		retval = cgroup_attach_task(from_cgrp, tsk, false);
		if (retval)
			break;
	}
	mutex_unlock(&cgroup_mutex);

	return retval;
}
EXPORT_SYMBOL_GPL(cgroup_attach_task_all);

static int cgroup_tasks_write(struct cgroup_subsys_state *css,
			      struct cftype *cft, u64 pid)