cgroup.c

	/*
	 * We're accessing css_set_count without locking css_set_lock here,
	 * but that's OK - it can only be increased by someone holding
	 * cgroup_lock, and that's us.  Later rebinding may disable
	 * controllers on the default hierarchy and thus create new csets,
	 * which can't be more than the existing ones.  Allocate 2x.
	 */
	ret = allocate_cgrp_cset_links(2 * css_set_count, &tmp_links);
	if (ret)
		goto cancel_ref;

	ret = cgroup_init_root_id(root);
	if (ret)
		goto cancel_ref;

	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 = css_populate_dir(&root_cgrp->self);
	if (ret)
		goto destroy_root;

	ret = rebind_subsystems(root, ss_mask);
	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 root cgroup in this hierarchy into all the css_set
	 * objects.
	 */
	spin_lock_irq(&css_set_lock);
	hash_for_each(css_set_table, i, cset, hlist) {
		link_css_set(&tmp_links, cset, root_cgrp);
		if (css_set_populated(cset))
			cgroup_update_populated(root_cgrp, true);
	}
	spin_unlock_irq(&css_set_lock);

	BUG_ON(!list_empty(&root_cgrp->self.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);
cancel_ref:
	percpu_ref_exit(&root_cgrp->self.refcnt);
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)
{
	bool is_v2 = fs_type == &cgroup2_fs_type;
	struct super_block *pinned_sb = NULL;
	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
	struct cgroup_subsys *ss;
	struct cgroup_root *root;
	struct cgroup_sb_opts opts;
	struct dentry *dentry;
	int ret;
	int i;
	bool new_sb;

	get_cgroup_ns(ns);

	/* Check if the caller has permission to mount. */
	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) {
		put_cgroup_ns(ns);
		return ERR_PTR(-EPERM);
	}

	/*
	 * 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();

	if (is_v2) {
		if (data) {
			pr_err("cgroup2: unknown option \"%s\"\n", (char *)data);
			put_cgroup_ns(ns);
			return ERR_PTR(-EINVAL);
		}
		cgrp_dfl_visible = true;
		root = &cgrp_dfl_root;
		cgroup_get(&root->cgrp);
		goto out_mount;
	}

	cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);

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

	/*
	 * Destruction of cgroup root is asynchronous, so subsystems may
	 * still be dying after the previous unmount.  Let's drain the
	 * dying subsystems.  We just need to ensure that the ones
	 * unmounted previously finish dying and don't care about new ones
	 * starting.  Testing ref liveliness is good enough.
	 */
	for_each_subsys(ss, i) {
		if (!(opts.subsys_mask & (1 << i)) ||
		    ss->root == &cgrp_dfl_root)
			continue;

		if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) {
			mutex_unlock(&cgroup_mutex);
			msleep(10);
			ret = restart_syscall();
			goto out_free;
		}
		cgroup_put(&ss->root->cgrp);
	}

	for_each_root(root) {
		bool name_match = false;

		if (root == &cgrp_dfl_root)
			continue;

		/*
		 * 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)
			pr_warn("new mount options do not match the existing superblock, will be ignored\n");

		/*
		 * We want to reuse @root whose lifetime is governed by its
		 * ->cgrp.  Let's check whether @root is alive and keep it
		 * that way.  As cgroup_kill_sb() can happen anytime, we
		 * want to block it by pinning the sb so that @root doesn't
		 * get killed before mount is complete.
		 *
		 * With the sb pinned, tryget_live can reliably indicate
		 * whether @root can be reused.  If it's being killed,
		 * drain it.  We can use wait_queue for the wait but this
		 * path is super cold.  Let's just sleep a bit and retry.
		 */
		pinned_sb = kernfs_pin_sb(root->kf_root, NULL);
		if (IS_ERR(pinned_sb) ||
		    !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
			mutex_unlock(&cgroup_mutex);
			if (!IS_ERR_OR_NULL(pinned_sb))
				deactivate_super(pinned_sb);
			msleep(10);
			ret = restart_syscall();
			goto out_free;
		}

		ret = 0;
		goto out_unlock;
	}

	/*
	 * No such thing, create a new one.  name= matching without subsys
	 * specification is allowed for already existing hierarchies but we
	 * can't create new one without subsys specification.
	 */
	if (!opts.subsys_mask && !opts.none) {
		ret = -EINVAL;
		goto out_unlock;
	}

	/* Hierarchies may only be created in the initial cgroup namespace. */
	if (ns != &init_cgroup_ns) {
		ret = -EPERM;
		goto out_unlock;
	}

	root = kzalloc(sizeof(*root), GFP_KERNEL);
	if (!root) {
		ret = -ENOMEM;
		goto out_unlock;
	}

	init_cgroup_root(root, &opts);

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

out_unlock:
	mutex_unlock(&cgroup_mutex);
out_free:
	kfree(opts.release_agent);
	kfree(opts.name);

	if (ret) {
		put_cgroup_ns(ns);
		return ERR_PTR(ret);
	}
out_mount:
	dentry = kernfs_mount(fs_type, flags, root->kf_root,
			      is_v2 ? CGROUP2_SUPER_MAGIC : CGROUP_SUPER_MAGIC,
			      &new_sb);

	/*
	 * In non-init cgroup namespace, instead of root cgroup's
	 * dentry, we return the dentry corresponding to the
	 * cgroupns->root_cgrp.
	 */
	if (!IS_ERR(dentry) && ns != &init_cgroup_ns) {
		struct dentry *nsdentry;
		struct cgroup *cgrp;

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

		cgrp = cset_cgroup_from_root(ns->root_cset, root);

		spin_unlock_irq(&css_set_lock);
		mutex_unlock(&cgroup_mutex);

		nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb);
		dput(dentry);
		dentry = nsdentry;
	}

	if (IS_ERR(dentry) || !new_sb)
		cgroup_put(&root->cgrp);

	/*
	 * If @pinned_sb, we're reusing an existing root and holding an
	 * extra ref on its sb.  Mount is complete.  Put the extra ref.
	 */
	if (pinned_sb) {
		WARN_ON(new_sb);
		deactivate_super(pinned_sb);
	}

	put_cgroup_ns(ns);
	return dentry;
}

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

	/*
	 * If @root doesn't have any mounts or children, start killing it.
	 * This prevents new mounts by disabling percpu_ref_tryget_live().
	 * cgroup_mount() may wait for @root's release.
	 *
	 * And don't kill the default root.
	 */
	if (!list_empty(&root->cgrp.self.children) ||
	    root == &cgrp_dfl_root)
		cgroup_put(&root->cgrp);
	else
		percpu_ref_kill(&root->cgrp.self.refcnt);

	kernfs_kill_sb(sb);
}

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

static struct file_system_type cgroup2_fs_type = {
	.name = "cgroup2",
	.mount = cgroup_mount,
	.kill_sb = cgroup_kill_sb,
	.fs_flags = FS_USERNS_MOUNT,
};

static int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen,
				 struct cgroup_namespace *ns)
{
	struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root);

	return kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen);
}

int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
		   struct cgroup_namespace *ns)
{
	int ret;

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

	ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns);

	spin_unlock_irq(&css_set_lock);
	mutex_unlock(&cgroup_mutex);

	return ret;
}
EXPORT_SYMBOL_GPL(cgroup_path_ns);

/**
 * 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().
 */
int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
{
	struct cgroup_root *root;
	struct cgroup *cgrp;
	int hierarchy_id = 1;
	int ret;

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

	root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id);

	if (root) {
		cgrp = task_cgroup_from_root(task, root);
		ret = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns);
	} else {
		/* if no hierarchy exists, everyone is in "/" */
		ret = strlcpy(buf, "/", buflen);
	}

	spin_unlock_irq(&css_set_lock);
	mutex_unlock(&cgroup_mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(task_cgroup_path);

/* used to track tasks and other necessary states during migration */
struct cgroup_taskset {
	/* the src and dst cset list running through cset->mg_node */
	struct list_head	src_csets;
	struct list_head	dst_csets;

	/* the subsys currently being processed */
	int			ssid;

	/*
	 * Fields for cgroup_taskset_*() iteration.
	 *
	 * Before migration is committed, the target migration tasks are on
	 * ->mg_tasks of the csets on ->src_csets.  After, on ->mg_tasks of
	 * the csets on ->dst_csets.  ->csets point to either ->src_csets
	 * or ->dst_csets depending on whether migration is committed.
	 *
	 * ->cur_csets and ->cur_task point to the current task position
	 * during iteration.
	 */
	struct list_head	*csets;
	struct css_set		*cur_cset;
	struct task_struct	*cur_task;
};

#define CGROUP_TASKSET_INIT(tset)	(struct cgroup_taskset){	\
	.src_csets		= LIST_HEAD_INIT(tset.src_csets),	\
	.dst_csets		= LIST_HEAD_INIT(tset.dst_csets),	\
	.csets			= &tset.src_csets,			\
}

/**
 * cgroup_taskset_add - try to add a migration target task to a taskset
 * @task: target task
 * @tset: target taskset
 *
 * Add @task, which is a migration target, to @tset.  This function becomes
 * noop if @task doesn't need to be migrated.  @task's css_set should have
 * been added as a migration source and @task->cg_list will be moved from
 * the css_set's tasks list to mg_tasks one.
 */
static void cgroup_taskset_add(struct task_struct *task,
			       struct cgroup_taskset *tset)
{
	struct css_set *cset;

	lockdep_assert_held(&css_set_lock);

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

	/* 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;

	list_move_tail(&task->cg_list, &cset->mg_tasks);
	if (list_empty(&cset->mg_node))
		list_add_tail(&cset->mg_node, &tset->src_csets);
	if (list_empty(&cset->mg_dst_cset->mg_node))
		list_move_tail(&cset->mg_dst_cset->mg_node,
			       &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
 * @tset: taget taskset
 * @root: cgroup root the migration is taking place on
 *
 * Migrate tasks in @tset 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 @tset are migrated.
 * @tset is consumed regardless of success.
 */
static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
				  struct cgroup_root *root)
{
	struct cgroup_subsys *ss;
	struct task_struct *task, *tmp_task;
	struct css_set *cset, *tmp_cset;
	int ssid, failed_ssid, ret;

	/* methods shouldn't be called if no task is actually migrating */
	if (list_empty(&tset->src_csets))
		return 0;

	/* check that we can legitimately attach to the cgroup */
	do_each_subsys_mask(ss, ssid, root->subsys_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);
			css_set_move_task(task, from_cset, to_cset, true);
			put_css_set_locked(from_cset);
		}
	}
	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;

	do_each_subsys_mask(ss, ssid, root->subsys_mask) {
		if (ss->attach) {
			tset->ssid = ssid;
			ss->attach(tset);
		}
	} while_each_subsys_mask();

	ret = 0;
	goto out_release_tset;

out_cancel_attach:
	do_each_subsys_mask(ss, ssid, root->subsys_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.
 */
static 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
 * @preloaded_csets: list of preloaded css_sets
 *
 * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst().  See
 * those functions for details.
 */
static void cgroup_migrate_finish(struct list_head *preloaded_csets)
{
	struct css_set *cset, *tmp_cset;

	lockdep_assert_held(&cgroup_mutex);

	spin_lock_irq(&css_set_lock);
	list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, 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
 * @preloaded_csets: list of preloaded css_sets
 *
 * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp.  Pin
 * @src_cset and add it to @preloaded_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.
 */
static void cgroup_migrate_add_src(struct css_set *src_cset,
				   struct cgroup *dst_cgrp,
				   struct list_head *preloaded_csets)
{
	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(&src_cset->mg_preload_node, preloaded_csets);
}

/**
 * cgroup_migrate_prepare_dst - prepare destination css_sets for migration
 * @preloaded_csets: list of preloaded source css_sets
 *
 * Tasks are about to be moved and all the source css_sets have been
 * preloaded to @preloaded_csets.  This function looks up and pins all
 * destination css_sets, links each to its source, and append them to
 * @preloaded_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
 * @preloaded_csets.
 */
static int cgroup_migrate_prepare_dst(struct list_head *preloaded_csets)
{
	LIST_HEAD(csets);
	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, preloaded_csets, mg_preload_node) {
		struct css_set *dst_cset;

		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(&dst_cset->mg_preload_node, &csets);
		else
			put_css_set(dst_cset);
	}

	list_splice_tail(&csets, preloaded_csets);
	return 0;
err:
	cgroup_migrate_finish(&csets);
	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
 * @root: cgroup root migration is taking place on
 *
 * 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.
 */
static int cgroup_migrate(struct task_struct *leader, bool threadgroup,
			  struct cgroup_root *root)
{
	struct cgroup_taskset tset = CGROUP_TASKSET_INIT(tset);
	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_taskset_add(task, &tset);
		if (!threadgroup)
			break;
	} while_each_thread(leader, task);
	rcu_read_unlock();
	spin_unlock_irq(&css_set_lock);

	return cgroup_taskset_migrate(&tset, root);
}

/**
 * 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.
 */
static int cgroup_attach_task(struct cgroup *dst_cgrp,
			      struct task_struct *leader, bool threadgroup)
{
	LIST_HEAD(preloaded_csets);
	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,
				       &preloaded_csets);
		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(&preloaded_csets);
	if (!ret)
		ret = cgroup_migrate(leader, threadgroup, dst_cgrp->root);

	cgroup_migrate_finish(&preloaded_csets);
	return ret;
}

static int cgroup_procs_write_permission(struct task_struct *task,
					 struct cgroup *dst_cgrp,
					 struct kernfs_open_file *of)
{
	const struct cred *cred = current_cred();
	const struct cred *tcred = get_task_cred(task);
	int ret = 0;

	/*
	 * 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 = -EACCES;

	if (!ret && cgroup_on_dfl(dst_cgrp)) {
		struct super_block *sb = of->file->f_path.dentry->d_sb;
		struct cgroup *cgrp;
		struct inode *inode;

		spin_lock_irq(&css_set_lock);
		cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
		spin_unlock_irq(&css_set_lock);

		while (!cgroup_is_descendant(dst_cgrp, cgrp))
			cgrp = cgroup_parent(cgrp);

		ret = -ENOMEM;
		inode = kernfs_get_inode(sb, cgrp->procs_file.kn);
		if (inode) {
			ret = inode_permission(inode, MAY_WRITE);
			iput(inode);
		}
	}

	put_cred(tcred);
	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.
 */
static 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;

	/*
	 * 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;
		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;
}

/**
 * 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 cgroup_root *root;
	int retval = 0;

	mutex_lock(&cgroup_mutex);
	percpu_down_write(&cgroup_threadgroup_rwsem);
	for_each_root(root) {
		struct cgroup *from_cgrp;

		if (root == &cgrp_dfl_root)
			continue;

		spin_lock_irq(&css_set_lock);
		from_cgrp = task_cgroup_from_root(from, root);
		spin_unlock_irq(&css_set_lock);

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

	return retval;
}
EXPORT_SYMBOL_GPL(cgroup_attach_task_all);

static ssize_t cgroup_tasks_write(struct kernfs_open_file *of,
				  char *buf, size_t nbytes, loff_t off)
{
	return __cgroup_procs_write(of, buf, nbytes, off, false);
}

static 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 ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,
					  char *buf, size_t nbytes, loff_t off)
{
	struct cgroup *cgrp;

	BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);

	cgrp = cgroup_kn_lock_live(of->kn, false);
	if (!cgrp)
		return -ENODEV;
	spin_lock(&release_agent_path_lock);
	strlcpy(cgrp->root->release_agent_path, strstrip(buf),
		sizeof(cgrp->root->release_agent_path));
	spin_unlock(&release_agent_path_lock);
	cgroup_kn_unlock(of->kn);
	return nbytes;
}