cgroup.c

	/* leave @task alone if post_fork() hasn't linked it yet */
	if (list_empty(&task->cg_list))
		return;

	cset = task_css_set(task);
	if (!cset->mg_src_cgrp)
		return;

	mgctx->tset.nr_tasks++;

	list_move_tail(&task->cg_list, &cset->mg_tasks);
	if (list_empty(&cset->mg_node))
		list_add_tail(&cset->mg_node,
			      &mgctx->tset.src_csets);
	if (list_empty(&cset->mg_dst_cset->mg_node))
		list_add_tail(&cset->mg_dst_cset->mg_node,
			      &mgctx->tset.dst_csets);
}

/**
 * cgroup_taskset_first - reset taskset and return the first task
 * @tset: taskset of interest
 * @dst_cssp: output variable for the destination css
 *
 * @tset iteration is initialized and the first task is returned.
 */
struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
					 struct cgroup_subsys_state **dst_cssp)
{
	tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node);
	tset->cur_task = NULL;

	return cgroup_taskset_next(tset, dst_cssp);
}

/**
 * cgroup_taskset_next - iterate to the next task in taskset
 * @tset: taskset of interest
 * @dst_cssp: output variable for the destination css
 *
 * 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 cgroup_subsys_state **dst_cssp)
{
	struct css_set *cset = tset->cur_cset;
	struct task_struct *task = tset->cur_task;

	while (&cset->mg_node != tset->csets) {
		if (!task)
			task = list_first_entry(&cset->mg_tasks,
						struct task_struct, cg_list);
		else
			task = list_next_entry(task, cg_list);

		if (&task->cg_list != &cset->mg_tasks) {
			tset->cur_cset = cset;
			tset->cur_task = task;

			/*
			 * This function may be called both before and
			 * after cgroup_taskset_migrate().  The two cases
			 * can be distinguished by looking at whether @cset
			 * has its ->mg_dst_cset set.
			 */
			if (cset->mg_dst_cset)
				*dst_cssp = cset->mg_dst_cset->subsys[tset->ssid];
			else
				*dst_cssp = cset->subsys[tset->ssid];

			return task;
		}

		cset = list_next_entry(cset, mg_node);
		task = NULL;
	}

	return NULL;
}

/**
 * cgroup_taskset_migrate - migrate a taskset
 * @mgctx: migration context
 *
 * Migrate tasks in @mgctx as setup by migration preparation functions.
 * This function fails iff one of the ->can_attach callbacks fails and
 * guarantees that either all or none of the tasks in @mgctx are migrated.
 * @mgctx is consumed regardless of success.
 */
static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx)
{
	struct cgroup_taskset *tset = &mgctx->tset;
	struct cgroup_subsys *ss;
	struct task_struct *task, *tmp_task;
	struct css_set *cset, *tmp_cset;
	int ssid, failed_ssid, ret;

	/* check that we can legitimately attach to the cgroup */
	if (tset->nr_tasks) {
		do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
			if (ss->can_attach) {
				tset->ssid = ssid;
				ret = ss->can_attach(tset);
				if (ret) {
					failed_ssid = ssid;
					goto out_cancel_attach;
				}
			}
		} while_each_subsys_mask();
	}

	/*
	 * Now that we're guaranteed success, proceed to move all tasks to
	 * the new cgroup.  There are no failure cases after here, so this
	 * is the commit point.
	 */
	spin_lock_irq(&css_set_lock);
	list_for_each_entry(cset, &tset->src_csets, mg_node) {
		list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) {
			struct css_set *from_cset = task_css_set(task);
			struct css_set *to_cset = cset->mg_dst_cset;

			get_css_set(to_cset);
			to_cset->nr_tasks++;
			css_set_move_task(task, from_cset, to_cset, true);
			put_css_set_locked(from_cset);
			from_cset->nr_tasks--;
		}
	}
	spin_unlock_irq(&css_set_lock);

	/*
	 * Migration is committed, all target tasks are now on dst_csets.
	 * Nothing is sensitive to fork() after this point.  Notify
	 * controllers that migration is complete.
	 */
	tset->csets = &tset->dst_csets;

	if (tset->nr_tasks) {
		do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
			if (ss->attach) {
				tset->ssid = ssid;
				ss->attach(tset);
			}
		} while_each_subsys_mask();
	}

	ret = 0;
	goto out_release_tset;

out_cancel_attach:
	if (tset->nr_tasks) {
		do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
			if (ssid == failed_ssid)
				break;
			if (ss->cancel_attach) {
				tset->ssid = ssid;
				ss->cancel_attach(tset);
			}
		} while_each_subsys_mask();
	}
out_release_tset:
	spin_lock_irq(&css_set_lock);
	list_splice_init(&tset->dst_csets, &tset->src_csets);
	list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) {
		list_splice_tail_init(&cset->mg_tasks, &cset->tasks);
		list_del_init(&cset->mg_node);
	}
	spin_unlock_irq(&css_set_lock);
	return ret;
}

/**
 * cgroup_may_migrate_to - verify whether a cgroup can be migration destination
 * @dst_cgrp: destination cgroup to test
 *
 * On the default hierarchy, except for the root, subtree_control must be
 * zero for migration destination cgroups with tasks so that child cgroups
 * don't compete against tasks.
 */
bool cgroup_may_migrate_to(struct cgroup *dst_cgrp)
{
	return !cgroup_on_dfl(dst_cgrp) || !cgroup_parent(dst_cgrp) ||
		!dst_cgrp->subtree_control;
}

/**
 * cgroup_migrate_finish - cleanup after attach
 * @mgctx: migration context
 *
 * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst().  See
 * those functions for details.
 */
void cgroup_migrate_finish(struct cgroup_mgctx *mgctx)
{
	LIST_HEAD(preloaded);
	struct css_set *cset, *tmp_cset;

	lockdep_assert_held(&cgroup_mutex);

	spin_lock_irq(&css_set_lock);

	list_splice_tail_init(&mgctx->preloaded_src_csets, &preloaded);
	list_splice_tail_init(&mgctx->preloaded_dst_csets, &preloaded);

	list_for_each_entry_safe(cset, tmp_cset, &preloaded, mg_preload_node) {
		cset->mg_src_cgrp = NULL;
		cset->mg_dst_cgrp = NULL;
		cset->mg_dst_cset = NULL;
		list_del_init(&cset->mg_preload_node);
		put_css_set_locked(cset);
	}

	spin_unlock_irq(&css_set_lock);
}

/**
 * cgroup_migrate_add_src - add a migration source css_set
 * @src_cset: the source css_set to add
 * @dst_cgrp: the destination cgroup
 * @mgctx: migration context
 *
 * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp.  Pin
 * @src_cset and add it to @mgctx->src_csets, which should later be cleaned
 * up by cgroup_migrate_finish().
 *
 * This function may be called without holding cgroup_threadgroup_rwsem
 * even if the target is a process.  Threads may be created and destroyed
 * but as long as cgroup_mutex is not dropped, no new css_set can be put
 * into play and the preloaded css_sets are guaranteed to cover all
 * migrations.
 */
void cgroup_migrate_add_src(struct css_set *src_cset,
			    struct cgroup *dst_cgrp,
			    struct cgroup_mgctx *mgctx)
{
	struct cgroup *src_cgrp;

	lockdep_assert_held(&cgroup_mutex);
	lockdep_assert_held(&css_set_lock);

	/*
	 * If ->dead, @src_set is associated with one or more dead cgroups
	 * and doesn't contain any migratable tasks.  Ignore it early so
	 * that the rest of migration path doesn't get confused by it.
	 */
	if (src_cset->dead)
		return;

	src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);

	if (!list_empty(&src_cset->mg_preload_node))
		return;

	WARN_ON(src_cset->mg_src_cgrp);
	WARN_ON(src_cset->mg_dst_cgrp);
	WARN_ON(!list_empty(&src_cset->mg_tasks));
	WARN_ON(!list_empty(&src_cset->mg_node));

	src_cset->mg_src_cgrp = src_cgrp;
	src_cset->mg_dst_cgrp = dst_cgrp;
	get_css_set(src_cset);
	list_add_tail(&src_cset->mg_preload_node, &mgctx->preloaded_src_csets);
}

/**
 * cgroup_migrate_prepare_dst - prepare destination css_sets for migration
 * @mgctx: migration context
 *
 * Tasks are about to be moved and all the source css_sets have been
 * preloaded to @mgctx->preloaded_src_csets.  This function looks up and
 * pins all destination css_sets, links each to its source, and append them
 * to @mgctx->preloaded_dst_csets.
 *
 * This function must be called after cgroup_migrate_add_src() has been
 * called on each migration source css_set.  After migration is performed
 * using cgroup_migrate(), cgroup_migrate_finish() must be called on
 * @mgctx.
 */
int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
{
	struct css_set *src_cset, *tmp_cset;

	lockdep_assert_held(&cgroup_mutex);

	/* look up the dst cset for each src cset and link it to src */
	list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets,
				 mg_preload_node) {
		struct css_set *dst_cset;
		struct cgroup_subsys *ss;
		int ssid;

		dst_cset = find_css_set(src_cset, src_cset->mg_dst_cgrp);
		if (!dst_cset)
			goto err;

		WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset);

		/*
		 * If src cset equals dst, it's noop.  Drop the src.
		 * cgroup_migrate() will skip the cset too.  Note that we
		 * can't handle src == dst as some nodes are used by both.
		 */
		if (src_cset == dst_cset) {
			src_cset->mg_src_cgrp = NULL;
			src_cset->mg_dst_cgrp = NULL;
			list_del_init(&src_cset->mg_preload_node);
			put_css_set(src_cset);
			put_css_set(dst_cset);
			continue;
		}

		src_cset->mg_dst_cset = dst_cset;

		if (list_empty(&dst_cset->mg_preload_node))
			list_add_tail(&dst_cset->mg_preload_node,
				      &mgctx->preloaded_dst_csets);
		else
			put_css_set(dst_cset);

		for_each_subsys(ss, ssid)
			if (src_cset->subsys[ssid] != dst_cset->subsys[ssid])
				mgctx->ss_mask |= 1 << ssid;
	}

	return 0;
err:
	cgroup_migrate_finish(mgctx);
	return -ENOMEM;
}

/**
 * cgroup_migrate - migrate a process or task to a cgroup
 * @leader: the leader of the process or the task to migrate
 * @threadgroup: whether @leader points to the whole process or a single task
 * @mgctx: migration context
 *
 * Migrate a process or task denoted by @leader.  If migrating a process,
 * the caller must be holding cgroup_threadgroup_rwsem.  The caller is also
 * responsible for invoking cgroup_migrate_add_src() and
 * cgroup_migrate_prepare_dst() on the targets before invoking this
 * function and following up with cgroup_migrate_finish().
 *
 * As long as a controller's ->can_attach() doesn't fail, this function is
 * guaranteed to succeed.  This means that, excluding ->can_attach()
 * failure, when migrating multiple targets, the success or failure can be
 * decided for all targets by invoking group_migrate_prepare_dst() before
 * actually starting migrating.
 */
int cgroup_migrate(struct task_struct *leader, bool threadgroup,
		   struct cgroup_mgctx *mgctx)
{
	struct task_struct *task;

	/*
	 * 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.
	 */
	spin_lock_irq(&css_set_lock);
	rcu_read_lock();
	task = leader;
	do {
		cgroup_migrate_add_task(task, mgctx);
		if (!threadgroup)
			break;
	} while_each_thread(leader, task);
	rcu_read_unlock();
	spin_unlock_irq(&css_set_lock);

	return cgroup_migrate_execute(mgctx);
}

/**
 * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup
 * @dst_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 cgroup_threadgroup_rwsem.
 */
int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
		       bool threadgroup)
{
	DEFINE_CGROUP_MGCTX(mgctx);
	struct task_struct *task;
	int ret;

	if (!cgroup_may_migrate_to(dst_cgrp))
		return -EBUSY;

	/* look up all src csets */
	spin_lock_irq(&css_set_lock);
	rcu_read_lock();
	task = leader;
	do {
		cgroup_migrate_add_src(task_css_set(task), dst_cgrp, &mgctx);
		if (!threadgroup)
			break;
	} while_each_thread(leader, task);
	rcu_read_unlock();
	spin_unlock_irq(&css_set_lock);

	/* prepare dst csets and commit */
	ret = cgroup_migrate_prepare_dst(&mgctx);
	if (!ret)
		ret = cgroup_migrate(leader, threadgroup, &mgctx);

	cgroup_migrate_finish(&mgctx);

	if (!ret)
		trace_cgroup_attach_task(dst_cgrp, leader, threadgroup);

	return ret;
}

static int cgroup_procs_write_permission(struct task_struct *task,
					 struct cgroup *dst_cgrp,
					 struct kernfs_open_file *of)
{
	struct super_block *sb = of->file->f_path.dentry->d_sb;
	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
	struct cgroup *root_cgrp = ns->root_cset->dfl_cgrp;
	struct cgroup *src_cgrp, *com_cgrp;
	struct inode *inode;
	int ret;

	if (!cgroup_on_dfl(dst_cgrp)) {
		const struct cred *cred = current_cred();
		const struct cred *tcred = get_task_cred(task);

		/*
		 * even if we're attaching all tasks in the thread group,
		 * we only need to check permissions on one of them.
		 */
		if (uid_eq(cred->euid, GLOBAL_ROOT_UID) ||
		    uid_eq(cred->euid, tcred->uid) ||
		    uid_eq(cred->euid, tcred->suid))
			ret = 0;
		else
			ret = -EACCES;

		put_cred(tcred);
		return ret;
	}

	/* find the source cgroup */
	spin_lock_irq(&css_set_lock);
	src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
	spin_unlock_irq(&css_set_lock);

	/* and the common ancestor */
	com_cgrp = src_cgrp;
	while (!cgroup_is_descendant(dst_cgrp, com_cgrp))
		com_cgrp = cgroup_parent(com_cgrp);

	/* %current should be authorized to migrate to the common ancestor */
	inode = kernfs_get_inode(sb, com_cgrp->procs_file.kn);
	if (!inode)
		return -ENOMEM;

	ret = inode_permission(inode, MAY_WRITE);
	iput(inode);
	if (ret)
		return ret;

	/*
	 * If namespaces are delegation boundaries, %current must be able
	 * to see both source and destination cgroups from its namespace.
	 */
	if ((cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) &&
	    (!cgroup_is_descendant(src_cgrp, root_cgrp) ||
	     !cgroup_is_descendant(dst_cgrp, root_cgrp)))
		return -ENOENT;

	return 0;
}

/*
 * 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.
 */
ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
			     size_t nbytes, loff_t off, bool threadgroup)
{
	struct task_struct *tsk;
	struct cgroup_subsys *ss;
	struct cgroup *cgrp;
	pid_t pid;
	int ssid, ret;

	if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
		return -EINVAL;

	cgrp = cgroup_kn_lock_live(of->kn, false);
	if (!cgrp)
		return -ENODEV;

	percpu_down_write(&cgroup_threadgroup_rwsem);
	rcu_read_lock();
	if (pid) {
		tsk = find_task_by_vpid(pid);
		if (!tsk) {
			ret = -ESRCH;
			goto out_unlock_rcu;
		}
	} else {
		tsk = current;
	}

	if (threadgroup)
		tsk = tsk->group_leader;

	/*
	 * kthreads may acquire PF_NO_SETAFFINITY during initialization.
	 * If userland migrates such a kthread to a non-root cgroup, it can
	 * become trapped in a cpuset, or RT kthread may be born in a
	 * cgroup with no rt_runtime allocated.  Just say no.
	 */
	if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) {
		ret = -EINVAL;
		goto out_unlock_rcu;
	}

	get_task_struct(tsk);
	rcu_read_unlock();

	ret = cgroup_procs_write_permission(tsk, cgrp, of);
	if (!ret)
		ret = cgroup_attach_task(cgrp, tsk, threadgroup);

	put_task_struct(tsk);
	goto out_unlock_threadgroup;

out_unlock_rcu:
	rcu_read_unlock();
out_unlock_threadgroup:
	percpu_up_write(&cgroup_threadgroup_rwsem);
	for_each_subsys(ss, ssid)
		if (ss->post_attach)
			ss->post_attach();
	cgroup_kn_unlock(of->kn);
	return ret ?: nbytes;
}

ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes,
			   loff_t off)
{
	return __cgroup_procs_write(of, buf, nbytes, off, true);
}

static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask)
{
	struct cgroup_subsys *ss;
	bool printed = false;
	int ssid;

	do_each_subsys_mask(ss, ssid, ss_mask) {
		if (printed)
			seq_putc(seq, ' ');
		seq_printf(seq, "%s", ss->name);
		printed = true;
	} while_each_subsys_mask();
	if (printed)
		seq_putc(seq, '\n');
}

/* show controllers which are enabled from the parent */
static int cgroup_controllers_show(struct seq_file *seq, void *v)
{
	struct cgroup *cgrp = seq_css(seq)->cgroup;

	cgroup_print_ss_mask(seq, cgroup_control(cgrp));
	return 0;
}

/* show controllers which are enabled for a given cgroup's children */
static int cgroup_subtree_control_show(struct seq_file *seq, void *v)
{
	struct cgroup *cgrp = seq_css(seq)->cgroup;

	cgroup_print_ss_mask(seq, cgrp->subtree_control);
	return 0;
}

/**
 * cgroup_update_dfl_csses - update css assoc of a subtree in default hierarchy
 * @cgrp: root of the subtree to update csses for
 *
 * @cgrp's control masks have changed and its subtree's css associations
 * need to be updated accordingly.  This function looks up all css_sets
 * which are attached to the subtree, creates the matching updated css_sets
 * and migrates the tasks to the new ones.
 */
static int cgroup_update_dfl_csses(struct cgroup *cgrp)
{
	DEFINE_CGROUP_MGCTX(mgctx);
	struct cgroup_subsys_state *d_css;
	struct cgroup *dsct;
	struct css_set *src_cset;
	int ret;

	lockdep_assert_held(&cgroup_mutex);

	percpu_down_write(&cgroup_threadgroup_rwsem);

	/* look up all csses currently attached to @cgrp's subtree */
	spin_lock_irq(&css_set_lock);
	cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
		struct cgrp_cset_link *link;

		list_for_each_entry(link, &dsct->cset_links, cset_link)
			cgroup_migrate_add_src(link->cset, dsct, &mgctx);
	}
	spin_unlock_irq(&css_set_lock);

	/* NULL dst indicates self on default hierarchy */
	ret = cgroup_migrate_prepare_dst(&mgctx);
	if (ret)
		goto out_finish;

	spin_lock_irq(&css_set_lock);
	list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_preload_node) {
		struct task_struct *task, *ntask;

		/* all tasks in src_csets need to be migrated */
		list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list)
			cgroup_migrate_add_task(task, &mgctx);
	}
	spin_unlock_irq(&css_set_lock);

	ret = cgroup_migrate_execute(&mgctx);
out_finish:
	cgroup_migrate_finish(&mgctx);
	percpu_up_write(&cgroup_threadgroup_rwsem);
	return ret;
}

/**
 * cgroup_lock_and_drain_offline - lock cgroup_mutex and drain offlined csses
 * @cgrp: root of the target subtree
 *
 * Because css offlining is asynchronous, userland may try to re-enable a
 * controller while the previous css is still around.  This function grabs
 * cgroup_mutex and drains the previous css instances of @cgrp's subtree.
 */
void cgroup_lock_and_drain_offline(struct cgroup *cgrp)
	__acquires(&cgroup_mutex)
{
	struct cgroup *dsct;
	struct cgroup_subsys_state *d_css;
	struct cgroup_subsys *ss;
	int ssid;

restart:
	mutex_lock(&cgroup_mutex);

	cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) {
		for_each_subsys(ss, ssid) {
			struct cgroup_subsys_state *css = cgroup_css(dsct, ss);
			DEFINE_WAIT(wait);

			if (!css || !percpu_ref_is_dying(&css->refcnt))
				continue;

			cgroup_get_live(dsct);
			prepare_to_wait(&dsct->offline_waitq, &wait,
					TASK_UNINTERRUPTIBLE);

			mutex_unlock(&cgroup_mutex);
			schedule();
			finish_wait(&dsct->offline_waitq, &wait);

			cgroup_put(dsct);
			goto restart;
		}
	}
}

/**
 * cgroup_save_control - save control masks of a subtree
 * @cgrp: root of the target subtree
 *
 * Save ->subtree_control and ->subtree_ss_mask to the respective old_
 * prefixed fields for @cgrp's subtree including @cgrp itself.
 */
static void cgroup_save_control(struct cgroup *cgrp)
{
	struct cgroup *dsct;
	struct cgroup_subsys_state *d_css;

	cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
		dsct->old_subtree_control = dsct->subtree_control;
		dsct->old_subtree_ss_mask = dsct->subtree_ss_mask;
	}
}

/**
 * cgroup_propagate_control - refresh control masks of a subtree
 * @cgrp: root of the target subtree
 *
 * For @cgrp and its subtree, ensure ->subtree_ss_mask matches
 * ->subtree_control and propagate controller availability through the
 * subtree so that descendants don't have unavailable controllers enabled.
 */
static void cgroup_propagate_control(struct cgroup *cgrp)
{
	struct cgroup *dsct;
	struct cgroup_subsys_state *d_css;

	cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
		dsct->subtree_control &= cgroup_control(dsct);
		dsct->subtree_ss_mask =
			cgroup_calc_subtree_ss_mask(dsct->subtree_control,
						    cgroup_ss_mask(dsct));
	}
}

/**
 * cgroup_restore_control - restore control masks of a subtree
 * @cgrp: root of the target subtree
 *
 * Restore ->subtree_control and ->subtree_ss_mask from the respective old_
 * prefixed fields for @cgrp's subtree including @cgrp itself.
 */
static void cgroup_restore_control(struct cgroup *cgrp)
{
	struct cgroup *dsct;
	struct cgroup_subsys_state *d_css;

	cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) {
		dsct->subtree_control = dsct->old_subtree_control;
		dsct->subtree_ss_mask = dsct->old_subtree_ss_mask;
	}
}

static bool css_visible(struct cgroup_subsys_state *css)
{
	struct cgroup_subsys *ss = css->ss;
	struct cgroup *cgrp = css->cgroup;

	if (cgroup_control(cgrp) & (1 << ss->id))
		return true;
	if (!(cgroup_ss_mask(cgrp) & (1 << ss->id)))
		return false;
	return cgroup_on_dfl(cgrp) && ss->implicit_on_dfl;
}

/**
 * cgroup_apply_control_enable - enable or show csses according to control
 * @cgrp: root of the target subtree
 *
 * Walk @cgrp's subtree and create new csses or make the existing ones
 * visible.  A css is created invisible if it's being implicitly enabled
 * through dependency.  An invisible css is made visible when the userland
 * explicitly enables it.
 *
 * Returns 0 on success, -errno on failure.  On failure, csses which have
 * been processed already aren't cleaned up.  The caller is responsible for
 * cleaning up with cgroup_apply_control_disable().
 */
static int cgroup_apply_control_enable(struct cgroup *cgrp)
{
	struct cgroup *dsct;
	struct cgroup_subsys_state *d_css;
	struct cgroup_subsys *ss;
	int ssid, ret;

	cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
		for_each_subsys(ss, ssid) {
			struct cgroup_subsys_state *css = cgroup_css(dsct, ss);

			WARN_ON_ONCE(css && percpu_ref_is_dying(&css->refcnt));

			if (!(cgroup_ss_mask(dsct) & (1 << ss->id)))
				continue;

			if (!css) {
				css = css_create(dsct, ss);
				if (IS_ERR(css))
					return PTR_ERR(css);
			}

			if (css_visible(css)) {
				ret = css_populate_dir(css);
				if (ret)
					return ret;
			}
		}
	}

	return 0;
}

/**
 * cgroup_apply_control_disable - kill or hide csses according to control
 * @cgrp: root of the target subtree
 *
 * Walk @cgrp's subtree and kill and hide csses so that they match
 * cgroup_ss_mask() and cgroup_visible_mask().
 *
 * A css is hidden when the userland requests it to be disabled while other
 * subsystems are still depending on it.  The css must not actively control
 * resources and be in the vanilla state if it's made visible again later.
 * Controllers which may be depended upon should provide ->css_reset() for
 * this purpose.
 */
static void cgroup_apply_control_disable(struct cgroup *cgrp)
{
	struct cgroup *dsct;
	struct cgroup_subsys_state *d_css;
	struct cgroup_subsys *ss;
	int ssid;

	cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) {
		for_each_subsys(ss, ssid) {
			struct cgroup_subsys_state *css = cgroup_css(dsct, ss);

			WARN_ON_ONCE(css && percpu_ref_is_dying(&css->refcnt));

			if (!css)
				continue;

			if (css->parent &&
			    !(cgroup_ss_mask(dsct) & (1 << ss->id))) {
				kill_css(css);
			} else if (!css_visible(css)) {
				css_clear_dir(css);
				if (ss->css_reset)
					ss->css_reset(css);
			}
		}
	}
}

/**
 * cgroup_apply_control - apply control mask updates to the subtree
 * @cgrp: root of the target subtree
 *
 * subsystems can be enabled and disabled in a subtree using the following
 * steps.
 *
 * 1. Call cgroup_save_control() to stash the current state.
 * 2. Update ->subtree_control masks in the subtree as desired.
 * 3. Call cgroup_apply_control() to apply the changes.
 * 4. Optionally perform other related operations.
 * 5. Call cgroup_finalize_control() to finish up.
 *
 * This function implements step 3 and propagates the mask changes
 * throughout @cgrp's subtree, updates csses accordingly and perform
 * process migrations.
 */
static int cgroup_apply_control(struct cgroup *cgrp)
{
	int ret;

	cgroup_propagate_control(cgrp);

	ret = cgroup_apply_control_enable(cgrp);
	if (ret)
		return ret;

	/*
	 * At this point, cgroup_e_css() results reflect the new csses
	 * making the following cgroup_update_dfl_csses() properly update
	 * css associations of all tasks in the subtree.
	 */
	ret = cgroup_update_dfl_csses(cgrp);
	if (ret)
		return ret;

	return 0;
}

/**
 * cgroup_finalize_control - finalize control mask update
 * @cgrp: root of the target subtree
 * @ret: the result of the update
 *
 * Finalize control mask update.  See cgroup_apply_control() for more info.
 */
static void cgroup_finalize_control(struct cgroup *cgrp, int ret)
{
	if (ret) {
		cgroup_restore_control(cgrp);
		cgroup_propagate_control(cgrp);
	}

	cgroup_apply_control_disable(cgrp);
}

/* change the enabled child controllers for a cgroup in the default hierarchy */
static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
					    char *buf, size_t nbytes,
					    loff_t off)
{
	u16 enable = 0, disable = 0;
	struct cgroup *cgrp, *child;
	struct cgroup_subsys *ss;
	char *tok;
	int ssid, ret;

	/*
	 * Parse input - space separated list of subsystem names prefixed
	 * with either + or -.
	 */
	buf = strstrip(buf);
	while ((tok = strsep(&buf, " "))) {
		if (tok[0] == '\0')
			continue;
		do_each_subsys_mask(ss, ssid, ~cgrp_dfl_inhibit_ss_mask) {
			if (!cgroup_ssid_enabled(ssid) ||
			    strcmp(tok + 1, ss->name))
				continue;

			if (*tok == '+') {
				enable |= 1 << ssid;
				disable &= ~(1 << ssid);
			} else if (*tok == '-') {
				disable |= 1 << ssid;
				enable &= ~(1 << ssid);
			} else {
				return -EINVAL;
			}
			break;
		} while_each_subsys_mask();
		if (ssid == CGROUP_SUBSYS_COUNT)
			return -EINVAL;
	}

	cgrp = cgroup_kn_lock_live(of->kn, true);
	if (!cgrp)
		return -ENODEV;

	for_each_subsys(ss, ssid) {
		if (enable & (1 << ssid)) {
			if (cgrp->subtree_control & (1 << ssid)) {
				enable &= ~(1 << ssid);
				continue;
			}

			if (!(cgroup_control(cgrp) & (1 << ssid))) {
				ret = -ENOENT;
				goto out_unlock;
			}
		} else if (disable & (1 << ssid)) {
			if (!(cgrp->subtree_control & (1 << ssid))) {
				disable &= ~(1 << ssid);
				continue;
			}

			/* a child has it enabled? */
			cgroup_for_each_live_child(child, cgrp) {
				if (child->subtree_control & (1 << ssid)) {
					ret = -EBUSY;
					goto out_unlock;
				}
			}
		}
	}

	if (!enable && !disable) {
		ret = 0;
		goto out_unlock;
	}

	/*
	 * Except for the root, subtree_control must be zero for a cgroup
	 * with tasks so that child cgroups don't compete against tasks.
	 */
	if (enable && cgroup_parent(cgrp)) {
		struct cgrp_cset_link *link;

		/*
		 * Because namespaces pin csets too, @cgrp->cset_links
		 * might not be empty even when @cgrp is empty.  Walk and
		 * verify each cset.
		 */
		spin_lock_irq(&css_set_lock);

		ret = 0;
		list_for_each_entry(link, &cgrp->cset_links, cset_link) {
			if (css_set_populated(link->cset)) {
				ret = -EBUSY;
				break;
			}
		}

		spin_unlock_irq(&css_set_lock);

		if (ret)
			goto out_unlock;
	}

	/* save and update control masks and prepare csses */
	cgroup_save_control(cgrp);

	cgrp->subtree_control |= enable;