cgroup.c

	struct cgroup *cgrp = css->cgroup;

	mutex_lock(&cgroup_mutex);

	css->flags |= CSS_RELEASED;
	list_del_rcu(&css->sibling);

	if (ss) {
		/* css release path */
		cgroup_idr_replace(&ss->css_idr, NULL, css->id);
		if (ss->css_released)
			ss->css_released(css);
	} else {
		/* cgroup release path */
		trace_cgroup_release(cgrp);

		cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
		cgrp->id = -1;

		/*
		 * There are two control paths which try to determine
		 * cgroup from dentry without going through kernfs -
		 * cgroupstats_build() and css_tryget_online_from_dir().
		 * Those are supported by RCU protecting clearing of
		 * cgrp->kn->priv backpointer.
		 */
		if (cgrp->kn)
			RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv,
					 NULL);

		cgroup_bpf_put(cgrp);
	}

	mutex_unlock(&cgroup_mutex);

	call_rcu(&css->rcu_head, css_free_rcu_fn);
}

static void css_release(struct percpu_ref *ref)
{
	struct cgroup_subsys_state *css =
		container_of(ref, struct cgroup_subsys_state, refcnt);

	INIT_WORK(&css->destroy_work, css_release_work_fn);
	queue_work(cgroup_destroy_wq, &css->destroy_work);
}

static void init_and_link_css(struct cgroup_subsys_state *css,
			      struct cgroup_subsys *ss, struct cgroup *cgrp)
{
	lockdep_assert_held(&cgroup_mutex);

	cgroup_get_live(cgrp);

	memset(css, 0, sizeof(*css));
	css->cgroup = cgrp;
	css->ss = ss;
	css->id = -1;
	INIT_LIST_HEAD(&css->sibling);
	INIT_LIST_HEAD(&css->children);
	css->serial_nr = css_serial_nr_next++;
	atomic_set(&css->online_cnt, 0);

	if (cgroup_parent(cgrp)) {
		css->parent = cgroup_css(cgroup_parent(cgrp), ss);
		css_get(css->parent);
	}

	BUG_ON(cgroup_css(cgrp, ss));
}

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

	lockdep_assert_held(&cgroup_mutex);

	if (ss->css_online)
		ret = ss->css_online(css);
	if (!ret) {
		css->flags |= CSS_ONLINE;
		rcu_assign_pointer(css->cgroup->subsys[ss->id], css);

		atomic_inc(&css->online_cnt);
		if (css->parent)
			atomic_inc(&css->parent->online_cnt);
	}
	return ret;
}

/* if the CSS is online, invoke ->css_offline() on it and mark it offline */
static void offline_css(struct cgroup_subsys_state *css)
{
	struct cgroup_subsys *ss = css->ss;

	lockdep_assert_held(&cgroup_mutex);

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

	if (ss->css_reset)
		ss->css_reset(css);

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

	css->flags &= ~CSS_ONLINE;
	RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL);

	wake_up_all(&css->cgroup->offline_waitq);
}

/**
 * css_create - create a cgroup_subsys_state
 * @cgrp: the cgroup new css will be associated with
 * @ss: the subsys of new css
 *
 * Create a new css associated with @cgrp - @ss pair.  On success, the new
 * css is online and installed in @cgrp.  This function doesn't create the
 * interface files.  Returns 0 on success, -errno on failure.
 */
static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
					      struct cgroup_subsys *ss)
{
	struct cgroup *parent = cgroup_parent(cgrp);
	struct cgroup_subsys_state *parent_css = cgroup_css(parent, ss);
	struct cgroup_subsys_state *css;
	int err;

	lockdep_assert_held(&cgroup_mutex);

	css = ss->css_alloc(parent_css);
	if (!css)
		css = ERR_PTR(-ENOMEM);
	if (IS_ERR(css))
		return css;

	init_and_link_css(css, ss, cgrp);

	err = percpu_ref_init(&css->refcnt, css_release, 0, GFP_KERNEL);
	if (err)
		goto err_free_css;

	err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL);
	if (err < 0)
		goto err_free_css;
	css->id = err;

	/* @css is ready to be brought online now, make it visible */
	list_add_tail_rcu(&css->sibling, &parent_css->children);
	cgroup_idr_replace(&ss->css_idr, css, css->id);

	err = online_css(css);
	if (err)
		goto err_list_del;

	if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
	    cgroup_parent(parent)) {
		pr_warn("%s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
			current->comm, current->pid, ss->name);
		if (!strcmp(ss->name, "memory"))
			pr_warn("\"memory\" requires setting use_hierarchy to 1 on the root\n");
		ss->warned_broken_hierarchy = true;
	}

	return css;

err_list_del:
	list_del_rcu(&css->sibling);
err_free_css:
	call_rcu(&css->rcu_head, css_free_rcu_fn);
	return ERR_PTR(err);
}

/*
 * The returned cgroup is fully initialized including its control mask, but
 * it isn't associated with its kernfs_node and doesn't have the control
 * mask applied.
 */
static struct cgroup *cgroup_create(struct cgroup *parent)
{
	struct cgroup_root *root = parent->root;
	struct cgroup *cgrp, *tcgrp;
	int level = parent->level + 1;
	int ret;

	/* allocate the cgroup and its ID, 0 is reserved for the root */
	cgrp = kzalloc(sizeof(*cgrp) +
		       sizeof(cgrp->ancestor_ids[0]) * (level + 1), GFP_KERNEL);
	if (!cgrp)
		return ERR_PTR(-ENOMEM);

	ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL);
	if (ret)
		goto out_free_cgrp;

	/*
	 * Temporarily set the pointer to NULL, so idr_find() won't return
	 * a half-baked cgroup.
	 */
	cgrp->id = cgroup_idr_alloc(&root->cgroup_idr, NULL, 2, 0, GFP_KERNEL);
	if (cgrp->id < 0) {
		ret = -ENOMEM;
		goto out_cancel_ref;
	}

	init_cgroup_housekeeping(cgrp);

	cgrp->self.parent = &parent->self;
	cgrp->root = root;
	cgrp->level = level;

	for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp))
		cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;

	if (notify_on_release(parent))
		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);

	if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags))
		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);

	cgrp->self.serial_nr = css_serial_nr_next++;

	/* allocation complete, commit to creation */
	list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children);
	atomic_inc(&root->nr_cgrps);
	cgroup_get_live(parent);

	/*
	 * @cgrp is now fully operational.  If something fails after this
	 * point, it'll be released via the normal destruction path.
	 */
	cgroup_idr_replace(&root->cgroup_idr, cgrp, cgrp->id);

	/*
	 * On the default hierarchy, a child doesn't automatically inherit
	 * subtree_control from the parent.  Each is configured manually.
	 */
	if (!cgroup_on_dfl(cgrp))
		cgrp->subtree_control = cgroup_control(cgrp);

	if (parent)
		cgroup_bpf_inherit(cgrp, parent);

	cgroup_propagate_control(cgrp);

	return cgrp;

out_cancel_ref:
	percpu_ref_exit(&cgrp->self.refcnt);
out_free_cgrp:
	kfree(cgrp);
	return ERR_PTR(ret);
}

int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode)
{
	struct cgroup *parent, *cgrp;
	struct kernfs_node *kn;
	int ret;

	/* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */
	if (strchr(name, '\n'))
		return -EINVAL;

	parent = cgroup_kn_lock_live(parent_kn, false);
	if (!parent)
		return -ENODEV;

	cgrp = cgroup_create(parent);
	if (IS_ERR(cgrp)) {
		ret = PTR_ERR(cgrp);
		goto out_unlock;
	}

	/* create the directory */
	kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
	if (IS_ERR(kn)) {
		ret = PTR_ERR(kn);
		goto out_destroy;
	}
	cgrp->kn = kn;

	/*
	 * This extra ref will be put in cgroup_free_fn() and guarantees
	 * that @cgrp->kn is always accessible.
	 */
	kernfs_get(kn);

	ret = cgroup_kn_set_ugid(kn);
	if (ret)
		goto out_destroy;

	ret = css_populate_dir(&cgrp->self);
	if (ret)
		goto out_destroy;

	ret = cgroup_apply_control_enable(cgrp);
	if (ret)
		goto out_destroy;

	trace_cgroup_mkdir(cgrp);

	/* let's create and online css's */
	kernfs_activate(kn);

	ret = 0;
	goto out_unlock;

out_destroy:
	cgroup_destroy_locked(cgrp);
out_unlock:
	cgroup_kn_unlock(parent_kn);
	return ret;
}

/*
 * This is called when the refcnt of a css is confirmed to be killed.
 * css_tryget_online() is now guaranteed to fail.  Tell the subsystem to
 * initate destruction and put the css ref from kill_css().
 */
static void css_killed_work_fn(struct work_struct *work)
{
	struct cgroup_subsys_state *css =
		container_of(work, struct cgroup_subsys_state, destroy_work);

	mutex_lock(&cgroup_mutex);

	do {
		offline_css(css);
		css_put(css);
		/* @css can't go away while we're holding cgroup_mutex */
		css = css->parent;
	} while (css && atomic_dec_and_test(&css->online_cnt));

	mutex_unlock(&cgroup_mutex);
}

/* css kill confirmation processing requires process context, bounce */
static void css_killed_ref_fn(struct percpu_ref *ref)
{
	struct cgroup_subsys_state *css =
		container_of(ref, struct cgroup_subsys_state, refcnt);

	if (atomic_dec_and_test(&css->online_cnt)) {
		INIT_WORK(&css->destroy_work, css_killed_work_fn);
		queue_work(cgroup_destroy_wq, &css->destroy_work);
	}
}

/**
 * kill_css - destroy a css
 * @css: css to destroy
 *
 * This function initiates destruction of @css by removing cgroup interface
 * files and putting its base reference.  ->css_offline() will be invoked
 * asynchronously once css_tryget_online() is guaranteed to fail and when
 * the reference count reaches zero, @css will be released.
 */
static void kill_css(struct cgroup_subsys_state *css)
{
	lockdep_assert_held(&cgroup_mutex);

	if (css->flags & CSS_DYING)
		return;

	css->flags |= CSS_DYING;

	/*
	 * This must happen before css is disassociated with its cgroup.
	 * See seq_css() for details.
	 */
	css_clear_dir(css);

	/*
	 * Killing would put the base ref, but we need to keep it alive
	 * until after ->css_offline().
	 */
	css_get(css);

	/*
	 * cgroup core guarantees that, by the time ->css_offline() is
	 * invoked, no new css reference will be given out via
	 * css_tryget_online().  We can't simply call percpu_ref_kill() and
	 * proceed to offlining css's because percpu_ref_kill() doesn't
	 * guarantee that the ref is seen as killed on all CPUs on return.
	 *
	 * Use percpu_ref_kill_and_confirm() to get notifications as each
	 * css is confirmed to be seen as killed on all CPUs.
	 */
	percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn);
}

/**
 * cgroup_destroy_locked - the first stage of cgroup destruction
 * @cgrp: cgroup to be destroyed
 *
 * css's make use of percpu refcnts whose killing latency shouldn't be
 * exposed to userland and are RCU protected.  Also, cgroup core needs to
 * guarantee that css_tryget_online() won't succeed by the time
 * ->css_offline() is invoked.  To satisfy all the requirements,
 * destruction is implemented in the following two steps.
 *
 * s1. Verify @cgrp can be destroyed and mark it dying.  Remove all
 *     userland visible parts and start killing the percpu refcnts of
 *     css's.  Set up so that the next stage will be kicked off once all
 *     the percpu refcnts are confirmed to be killed.
 *
 * s2. Invoke ->css_offline(), mark the cgroup dead and proceed with the
 *     rest of destruction.  Once all cgroup references are gone, the
 *     cgroup is RCU-freed.
 *
 * This function implements s1.  After this step, @cgrp is gone as far as
 * the userland is concerned and a new cgroup with the same name may be
 * created.  As cgroup doesn't care about the names internally, this
 * doesn't cause any problem.
 */
static int cgroup_destroy_locked(struct cgroup *cgrp)
	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
{
	struct cgroup_subsys_state *css;
	struct cgrp_cset_link *link;
	int ssid;

	lockdep_assert_held(&cgroup_mutex);

	/*
	 * Only migration can raise populated from zero and we're already
	 * holding cgroup_mutex.
	 */
	if (cgroup_is_populated(cgrp))
		return -EBUSY;

	/*
	 * Make sure there's no live children.  We can't test emptiness of
	 * ->self.children as dead children linger on it while being
	 * drained; otherwise, "rmdir parent/child parent" may fail.
	 */
	if (css_has_online_children(&cgrp->self))
		return -EBUSY;

	/*
	 * Mark @cgrp and the associated csets dead.  The former prevents
	 * further task migration and child creation by disabling
	 * cgroup_lock_live_group().  The latter makes the csets ignored by
	 * the migration path.
	 */
	cgrp->self.flags &= ~CSS_ONLINE;

	spin_lock_irq(&css_set_lock);
	list_for_each_entry(link, &cgrp->cset_links, cset_link)
		link->cset->dead = true;
	spin_unlock_irq(&css_set_lock);

	/* initiate massacre of all css's */
	for_each_css(css, ssid, cgrp)
		kill_css(css);

	/*
	 * Remove @cgrp directory along with the base files.  @cgrp has an
	 * extra ref on its kn.
	 */
	kernfs_remove(cgrp->kn);

	cgroup1_check_for_release(cgroup_parent(cgrp));

	/* put the base reference */
	percpu_ref_kill(&cgrp->self.refcnt);

	return 0;
};

int cgroup_rmdir(struct kernfs_node *kn)
{
	struct cgroup *cgrp;
	int ret = 0;

	cgrp = cgroup_kn_lock_live(kn, false);
	if (!cgrp)
		return 0;

	ret = cgroup_destroy_locked(cgrp);

	if (!ret)
		trace_cgroup_rmdir(cgrp);

	cgroup_kn_unlock(kn);
	return ret;
}

static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
	.show_options		= cgroup_show_options,
	.remount_fs		= cgroup_remount,
	.mkdir			= cgroup_mkdir,
	.rmdir			= cgroup_rmdir,
	.show_path		= cgroup_show_path,
};

static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
{
	struct cgroup_subsys_state *css;

	pr_debug("Initializing cgroup subsys %s\n", ss->name);

	mutex_lock(&cgroup_mutex);

	idr_init(&ss->css_idr);
	INIT_LIST_HEAD(&ss->cfts);

	/* Create the root cgroup state for this subsystem */
	ss->root = &cgrp_dfl_root;
	css = ss->css_alloc(cgroup_css(&cgrp_dfl_root.cgrp, ss));
	/* We don't handle early failures gracefully */
	BUG_ON(IS_ERR(css));
	init_and_link_css(css, ss, &cgrp_dfl_root.cgrp);

	/*
	 * Root csses are never destroyed and we can't initialize
	 * percpu_ref during early init.  Disable refcnting.
	 */
	css->flags |= CSS_NO_REF;

	if (early) {
		/* allocation can't be done safely during early init */
		css->id = 1;
	} else {
		css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL);
		BUG_ON(css->id < 0);
	}

	/* Update the init_css_set to contain a subsys
	 * pointer to this state - since the subsystem is
	 * newly registered, all tasks and hence the
	 * init_css_set is in the subsystem's root cgroup. */
	init_css_set.subsys[ss->id] = css;

	have_fork_callback |= (bool)ss->fork << ss->id;
	have_exit_callback |= (bool)ss->exit << ss->id;
	have_free_callback |= (bool)ss->free << ss->id;
	have_canfork_callback |= (bool)ss->can_fork << ss->id;

	/* At system boot, before all subsystems have been
	 * registered, no tasks have been forked, so we don't
	 * need to invoke fork callbacks here. */
	BUG_ON(!list_empty(&init_task.tasks));

	BUG_ON(online_css(css));

	mutex_unlock(&cgroup_mutex);
}

/**
 * cgroup_init_early - cgroup initialization at system boot
 *
 * Initialize cgroups at system boot, and initialize any
 * subsystems that request early init.
 */
int __init cgroup_init_early(void)
{
	static struct cgroup_sb_opts __initdata opts;
	struct cgroup_subsys *ss;
	int i;

	init_cgroup_root(&cgrp_dfl_root, &opts);
	cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF;

	RCU_INIT_POINTER(init_task.cgroups, &init_css_set);

	for_each_subsys(ss, i) {
		WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id,
		     "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p id:name=%d:%s\n",
		     i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free,
		     ss->id, ss->name);
		WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN,
		     "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]);

		ss->id = i;
		ss->name = cgroup_subsys_name[i];
		if (!ss->legacy_name)
			ss->legacy_name = cgroup_subsys_name[i];

		if (ss->early_init)
			cgroup_init_subsys(ss, true);
	}
	return 0;
}

static u16 cgroup_disable_mask __initdata;

/**
 * cgroup_init - cgroup initialization
 *
 * Register cgroup filesystem and /proc file, and initialize
 * any subsystems that didn't request early init.
 */
int __init cgroup_init(void)
{
	struct cgroup_subsys *ss;
	int ssid;

	BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16);
	BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem));
	BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files));
	BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files));

	/*
	 * The latency of the synchronize_sched() is too high for cgroups,
	 * avoid it at the cost of forcing all readers into the slow path.
	 */
	rcu_sync_enter_start(&cgroup_threadgroup_rwsem.rss);

	get_user_ns(init_cgroup_ns.user_ns);

	mutex_lock(&cgroup_mutex);

	/*
	 * Add init_css_set to the hash table so that dfl_root can link to
	 * it during init.
	 */
	hash_add(css_set_table, &init_css_set.hlist,
		 css_set_hash(init_css_set.subsys));

	BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0, 0));

	mutex_unlock(&cgroup_mutex);

	for_each_subsys(ss, ssid) {
		if (ss->early_init) {
			struct cgroup_subsys_state *css =
				init_css_set.subsys[ss->id];

			css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2,
						   GFP_KERNEL);
			BUG_ON(css->id < 0);
		} else {
			cgroup_init_subsys(ss, false);
		}

		list_add_tail(&init_css_set.e_cset_node[ssid],
			      &cgrp_dfl_root.cgrp.e_csets[ssid]);

		/*
		 * Setting dfl_root subsys_mask needs to consider the
		 * disabled flag and cftype registration needs kmalloc,
		 * both of which aren't available during early_init.
		 */
		if (cgroup_disable_mask & (1 << ssid)) {
			static_branch_disable(cgroup_subsys_enabled_key[ssid]);
			printk(KERN_INFO "Disabling %s control group subsystem\n",
			       ss->name);
			continue;
		}

		if (cgroup1_ssid_disabled(ssid))
			printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n",
			       ss->name);

		cgrp_dfl_root.subsys_mask |= 1 << ss->id;

		if (ss->implicit_on_dfl)
			cgrp_dfl_implicit_ss_mask |= 1 << ss->id;
		else if (!ss->dfl_cftypes)
			cgrp_dfl_inhibit_ss_mask |= 1 << ss->id;

		if (ss->dfl_cftypes == ss->legacy_cftypes) {
			WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes));
		} else {
			WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes));
			WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes));
		}

		if (ss->bind)
			ss->bind(init_css_set.subsys[ssid]);

		mutex_lock(&cgroup_mutex);
		css_populate_dir(init_css_set.subsys[ssid]);
		mutex_unlock(&cgroup_mutex);
	}

	/* init_css_set.subsys[] has been updated, re-hash */
	hash_del(&init_css_set.hlist);
	hash_add(css_set_table, &init_css_set.hlist,
		 css_set_hash(init_css_set.subsys));

	WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup"));
	WARN_ON(register_filesystem(&cgroup_fs_type));
	WARN_ON(register_filesystem(&cgroup2_fs_type));
	WARN_ON(!proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations));

	return 0;
}

static int __init cgroup_wq_init(void)
{
	/*
	 * There isn't much point in executing destruction path in
	 * parallel.  Good chunk is serialized with cgroup_mutex anyway.
	 * Use 1 for @max_active.
	 *
	 * We would prefer to do this in cgroup_init() above, but that
	 * is called before init_workqueues(): so leave this until after.
	 */
	cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
	BUG_ON(!cgroup_destroy_wq);
	return 0;
}
core_initcall(cgroup_wq_init);

/*
 * proc_cgroup_show()
 *  - Print task's cgroup paths into seq_file, one line for each hierarchy
 *  - Used for /proc/<pid>/cgroup.
 */
int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
		     struct pid *pid, struct task_struct *tsk)
{
	char *buf;
	int retval;
	struct cgroup_root *root;

	retval = -ENOMEM;
	buf = kmalloc(PATH_MAX, GFP_KERNEL);
	if (!buf)
		goto out;

	mutex_lock(&cgroup_mutex);
	spin_lock_irq(&css_set_lock);

	for_each_root(root) {
		struct cgroup_subsys *ss;
		struct cgroup *cgrp;
		int ssid, count = 0;

		if (root == &cgrp_dfl_root && !cgrp_dfl_visible)
			continue;

		seq_printf(m, "%d:", root->hierarchy_id);
		if (root != &cgrp_dfl_root)
			for_each_subsys(ss, ssid)
				if (root->subsys_mask & (1 << ssid))
					seq_printf(m, "%s%s", count++ ? "," : "",
						   ss->legacy_name);
		if (strlen(root->name))
			seq_printf(m, "%sname=%s", count ? "," : "",
				   root->name);
		seq_putc(m, ':');

		cgrp = task_cgroup_from_root(tsk, root);

		/*
		 * On traditional hierarchies, all zombie tasks show up as
		 * belonging to the root cgroup.  On the default hierarchy,
		 * while a zombie doesn't show up in "cgroup.procs" and
		 * thus can't be migrated, its /proc/PID/cgroup keeps
		 * reporting the cgroup it belonged to before exiting.  If
		 * the cgroup is removed before the zombie is reaped,
		 * " (deleted)" is appended to the cgroup path.
		 */
		if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) {
			retval = cgroup_path_ns_locked(cgrp, buf, PATH_MAX,
						current->nsproxy->cgroup_ns);
			if (retval >= PATH_MAX)
				retval = -ENAMETOOLONG;
			if (retval < 0)
				goto out_unlock;

			seq_puts(m, buf);
		} else {
			seq_puts(m, "/");
		}

		if (cgroup_on_dfl(cgrp) && cgroup_is_dead(cgrp))
			seq_puts(m, " (deleted)\n");
		else
			seq_putc(m, '\n');
	}

	retval = 0;
out_unlock:
	spin_unlock_irq(&css_set_lock);
	mutex_unlock(&cgroup_mutex);
	kfree(buf);
out:
	return retval;
}

/**
 * cgroup_fork - initialize cgroup related fields during copy_process()
 * @child: pointer to task_struct of forking parent process.
 *
 * A task is associated with the init_css_set until cgroup_post_fork()
 * attaches it to the parent's css_set.  Empty cg_list indicates that
 * @child isn't holding reference to its css_set.
 */
void cgroup_fork(struct task_struct *child)
{
	RCU_INIT_POINTER(child->cgroups, &init_css_set);
	INIT_LIST_HEAD(&child->cg_list);
}

/**
 * cgroup_can_fork - called on a new task before the process is exposed
 * @child: the task in question.
 *
 * This calls the subsystem can_fork() callbacks. If the can_fork() callback
 * returns an error, the fork aborts with that error code. This allows for
 * a cgroup subsystem to conditionally allow or deny new forks.
 */
int cgroup_can_fork(struct task_struct *child)
{
	struct cgroup_subsys *ss;
	int i, j, ret;

	do_each_subsys_mask(ss, i, have_canfork_callback) {
		ret = ss->can_fork(child);
		if (ret)
			goto out_revert;
	} while_each_subsys_mask();

	return 0;

out_revert:
	for_each_subsys(ss, j) {
		if (j >= i)
			break;
		if (ss->cancel_fork)
			ss->cancel_fork(child);
	}

	return ret;
}

/**
 * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork()
 * @child: the task in question
 *
 * This calls the cancel_fork() callbacks if a fork failed *after*
 * cgroup_can_fork() succeded.
 */
void cgroup_cancel_fork(struct task_struct *child)
{
	struct cgroup_subsys *ss;
	int i;

	for_each_subsys(ss, i)
		if (ss->cancel_fork)
			ss->cancel_fork(child);
}

/**
 * cgroup_post_fork - called on a new task after adding it to the task list
 * @child: the task in question
 *
 * Adds the task to the list running through its css_set if necessary and
 * call the subsystem fork() callbacks.  Has to be after the task is
 * visible on the task list in case we race with the first call to
 * cgroup_task_iter_start() - to guarantee that the new task ends up on its
 * list.
 */
void cgroup_post_fork(struct task_struct *child)
{
	struct cgroup_subsys *ss;
	int i;

	/*
	 * This may race against cgroup_enable_task_cg_lists().  As that
	 * function sets use_task_css_set_links before grabbing
	 * tasklist_lock and we just went through tasklist_lock to add
	 * @child, it's guaranteed that either we see the set
	 * use_task_css_set_links or cgroup_enable_task_cg_lists() sees
	 * @child during its iteration.
	 *
	 * If we won the race, @child is associated with %current's
	 * css_set.  Grabbing css_set_lock guarantees both that the
	 * association is stable, and, on completion of the parent's
	 * migration, @child is visible in the source of migration or
	 * already in the destination cgroup.  This guarantee is necessary
	 * when implementing operations which need to migrate all tasks of
	 * a cgroup to another.
	 *
	 * Note that if we lose to cgroup_enable_task_cg_lists(), @child
	 * will remain in init_css_set.  This is safe because all tasks are
	 * in the init_css_set before cg_links is enabled and there's no
	 * operation which transfers all tasks out of init_css_set.
	 */
	if (use_task_css_set_links) {
		struct css_set *cset;

		spin_lock_irq(&css_set_lock);
		cset = task_css_set(current);
		if (list_empty(&child->cg_list)) {
			get_css_set(cset);
			cset->nr_tasks++;
			css_set_move_task(child, NULL, cset, false);
		}
		spin_unlock_irq(&css_set_lock);
	}

	/*
	 * Call ss->fork().  This must happen after @child is linked on
	 * css_set; otherwise, @child might change state between ->fork()
	 * and addition to css_set.
	 */
	do_each_subsys_mask(ss, i, have_fork_callback) {
		ss->fork(child);
	} while_each_subsys_mask();
}

/**
 * cgroup_exit - detach cgroup from exiting task
 * @tsk: pointer to task_struct of exiting process
 *
 * Description: Detach cgroup from @tsk and release it.
 *
 * Note that cgroups marked notify_on_release force every task in
 * them to take the global cgroup_mutex mutex when exiting.
 * This could impact scaling on very large systems.  Be reluctant to
 * use notify_on_release cgroups where very high task exit scaling
 * is required on large systems.
 *
 * We set the exiting tasks cgroup to the root cgroup (top_cgroup).  We
 * call cgroup_exit() while the task is still competent to handle
 * notify_on_release(), then leave the task attached to the root cgroup in
 * each hierarchy for the remainder of its exit.  No need to bother with
 * init_css_set refcnting.  init_css_set never goes away and we can't race
 * with migration path - PF_EXITING is visible to migration path.
 */
void cgroup_exit(struct task_struct *tsk)
{
	struct cgroup_subsys *ss;
	struct css_set *cset;
	int i;

	/*
	 * Unlink from @tsk from its css_set.  As migration path can't race
	 * with us, we can check css_set and cg_list without synchronization.
	 */
	cset = task_css_set(tsk);

	if (!list_empty(&tsk->cg_list)) {
		spin_lock_irq(&css_set_lock);
		css_set_move_task(tsk, cset, NULL, false);
		cset->nr_tasks--;
		spin_unlock_irq(&css_set_lock);
	} else {
		get_css_set(cset);
	}

	/* see cgroup_post_fork() for details */
	do_each_subsys_mask(ss, i, have_exit_callback) {
		ss->exit(tsk);
	} while_each_subsys_mask();
}

void cgroup_free(struct task_struct *task)
{
	struct css_set *cset = task_css_set(task);
	struct cgroup_subsys *ss;
	int ssid;

	do_each_subsys_mask(ss, ssid, have_free_callback) {
		ss->free(task);
	} while_each_subsys_mask();

	put_css_set(cset);
}

static int __init cgroup_disable(char *str)
{
	struct cgroup_subsys *ss;
	char *token;
	int i;

	while ((token = strsep(&str, ",")) != NULL) {
		if (!*token)
			continue;

		for_each_subsys(ss, i) {
			if (strcmp(token, ss->name) &&
			    strcmp(token, ss->legacy_name))
				continue;
			cgroup_disable_mask |= 1 << i;
		}
	}
	return 1;
}
__setup("cgroup_disable=", cgroup_disable);

/**
 * css_tryget_online_from_dir - get corresponding css from a cgroup dentry
 * @dentry: directory dentry of interest
 * @ss: subsystem of interest
 *
 * If @dentry is a directory for a cgroup which has @ss enabled on it, try
 * to get the corresponding css and return it.  If such css doesn't exist
 * or can't be pinned, an ERR_PTR value is returned.
 */
struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,