cgroup: move cgroup v1 specific code to kernel/cgroup/cgroup-v1.c

cgroup.c is getting too unwieldy.  Let's move out cgroup v1 specific
code along with the debug controller into kernel/cgroup/cgroup-v1.c.

v2: cgroup_mutex and css_set_lock made available in cgroup-internal.h
    regardless of CONFIG_PROVE_RCU.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Acked-by: Zefan Li <lizefan@huawei.com>

1 files changed, 1027 insertions, 0 deletions

diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
new file mode 100644
index 000000000000..7af745a46f91
--- /dev/null
+++ b/kernel/cgroup/cgroup-v1.c
@@ -0,0 +1,1027 @@
+#include "cgroup-internal.h"
+
+#include <linux/kmod.h>
+#include <linux/sort.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/delayacct.h>
+#include <linux/pid_namespace.h>
+#include <linux/cgroupstats.h>
+
+#include <trace/events/cgroup.h>
+
+/*
+ * pidlists linger the following amount before being destroyed.  The goal
+ * is avoiding frequent destruction in the middle of consecutive read calls
+ * Expiring in the middle is a performance problem not a correctness one.
+ * 1 sec should be enough.
+ */
+#define CGROUP_PIDLIST_DESTROY_DELAY	HZ
+
+/* Controllers blocked by the commandline in v1 */
+static u16 cgroup_no_v1_mask;
+
+/*
+ * pidlist destructions need to be flushed on cgroup destruction.  Use a
+ * separate workqueue as flush domain.
+ */
+static struct workqueue_struct *cgroup_pidlist_destroy_wq;
+
+/*
+ * Protects cgroup_subsys->release_agent_path.  Modifying it also requires
+ * cgroup_mutex.  Reading requires either cgroup_mutex or this spinlock.
+ */
+DEFINE_SPINLOCK(release_agent_path_lock);
+
+bool cgroup_ssid_no_v1(int ssid)
+{
+	return cgroup_no_v1_mask & (1 << ssid);
+}
+
+/**
+ * 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);
+
+/**
+ * cgroup_trasnsfer_tasks - move tasks from one cgroup to another
+ * @to: cgroup to which the tasks will be moved
+ * @from: cgroup in which the tasks currently reside
+ *
+ * Locking rules between cgroup_post_fork() and the migration path
+ * guarantee that, if a task is forking while being migrated, the new child
+ * is guaranteed to be either visible in the source cgroup after the
+ * parent's migration is complete or put into the target cgroup.  No task
+ * can slip out of migration through forking.
+ */
+int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
+{
+	LIST_HEAD(preloaded_csets);
+	struct cgrp_cset_link *link;
+	struct css_task_iter it;
+	struct task_struct *task;
+	int ret;
+
+	if (cgroup_on_dfl(to))
+		return -EINVAL;
+
+	if (!cgroup_may_migrate_to(to))
+		return -EBUSY;
+
+	mutex_lock(&cgroup_mutex);
+
+	percpu_down_write(&cgroup_threadgroup_rwsem);
+
+	/* all tasks in @from are being moved, all csets are source */
+	spin_lock_irq(&css_set_lock);
+	list_for_each_entry(link, &from->cset_links, cset_link)
+		cgroup_migrate_add_src(link->cset, to, &preloaded_csets);
+	spin_unlock_irq(&css_set_lock);
+
+	ret = cgroup_migrate_prepare_dst(&preloaded_csets);
+	if (ret)
+		goto out_err;
+
+	/*
+	 * Migrate tasks one-by-one until @from is empty.  This fails iff
+	 * ->can_attach() fails.
+	 */
+	do {
+		css_task_iter_start(&from->self, &it);
+		task = css_task_iter_next(&it);
+		if (task)
+			get_task_struct(task);
+		css_task_iter_end(&it);
+
+		if (task) {
+			ret = cgroup_migrate(task, false, to->root);
+			if (!ret)
+				trace_cgroup_transfer_tasks(to, task, false);
+			put_task_struct(task);
+		}
+	} while (task && !ret);
+out_err:
+	cgroup_migrate_finish(&preloaded_csets);
+	percpu_up_write(&cgroup_threadgroup_rwsem);
+	mutex_unlock(&cgroup_mutex);
+	return ret;
+}
+
+/*
+ * Stuff for reading the 'tasks'/'procs' files.
+ *
+ * Reading this file can return large amounts of data if a cgroup has
+ * *lots* of attached tasks. So it may need several calls to read(),
+ * but we cannot guarantee that the information we produce is correct
+ * unless we produce it entirely atomically.
+ *
+ */
+
+/* which pidlist file are we talking about? */
+enum cgroup_filetype {
+	CGROUP_FILE_PROCS,
+	CGROUP_FILE_TASKS,
+};
+
+/*
+ * A pidlist is a list of pids that virtually represents the contents of one
+ * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists,
+ * a pair (one each for procs, tasks) for each pid namespace that's relevant
+ * to the cgroup.
+ */
+struct cgroup_pidlist {
+	/*
+	 * used to find which pidlist is wanted. doesn't change as long as
+	 * this particular list stays in the list.
+	*/
+	struct { enum cgroup_filetype type; struct pid_namespace *ns; } key;
+	/* array of xids */
+	pid_t *list;
+	/* how many elements the above list has */
+	int length;
+	/* each of these stored in a list by its cgroup */
+	struct list_head links;
+	/* pointer to the cgroup we belong to, for list removal purposes */
+	struct cgroup *owner;
+	/* for delayed destruction */
+	struct delayed_work destroy_dwork;
+};
+
+/*
+ * The following two functions "fix" the issue where there are more pids
+ * than kmalloc will give memory for; in such cases, we use vmalloc/vfree.
+ * TODO: replace with a kernel-wide solution to this problem
+ */
+#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2))
+static void *pidlist_allocate(int count)
+{
+	if (PIDLIST_TOO_LARGE(count))
+		return vmalloc(count * sizeof(pid_t));
+	else
+		return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
+}
+
+static void pidlist_free(void *p)
+{
+	kvfree(p);
+}
+
+/*
+ * Used to destroy all pidlists lingering waiting for destroy timer.  None
+ * should be left afterwards.
+ */
+void cgroup_pidlist_destroy_all(struct cgroup *cgrp)
+{
+	struct cgroup_pidlist *l, *tmp_l;
+
+	mutex_lock(&cgrp->pidlist_mutex);
+	list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links)
+		mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0);
+	mutex_unlock(&cgrp->pidlist_mutex);
+
+	flush_workqueue(cgroup_pidlist_destroy_wq);
+	BUG_ON(!list_empty(&cgrp->pidlists));
+}
+
+static void cgroup_pidlist_destroy_work_fn(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist,
+						destroy_dwork);
+	struct cgroup_pidlist *tofree = NULL;
+
+	mutex_lock(&l->owner->pidlist_mutex);
+
+	/*
+	 * Destroy iff we didn't get queued again.  The state won't change
+	 * as destroy_dwork can only be queued while locked.
+	 */
+	if (!delayed_work_pending(dwork)) {
+		list_del(&l->links);
+		pidlist_free(l->list);
+		put_pid_ns(l->key.ns);
+		tofree = l;
+	}
+
+	mutex_unlock(&l->owner->pidlist_mutex);
+	kfree(tofree);
+}
+
+/*
+ * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
+ * Returns the number of unique elements.
+ */
+static int pidlist_uniq(pid_t *list, int length)
+{
+	int src, dest = 1;
+
+	/*
+	 * we presume the 0th element is unique, so i starts at 1. trivial
+	 * edge cases first; no work needs to be done for either
+	 */
+	if (length == 0 || length == 1)
+		return length;
+	/* src and dest walk down the list; dest counts unique elements */
+	for (src = 1; src < length; src++) {
+		/* find next unique element */
+		while (list[src] == list[src-1]) {
+			src++;
+			if (src == length)
+				goto after;
+		}
+		/* dest always points to where the next unique element goes */
+		list[dest] = list[src];
+		dest++;
+	}
+after:
+	return dest;
+}
+
+/*
+ * The two pid files - task and cgroup.procs - guaranteed that the result
+ * is sorted, which forced this whole pidlist fiasco.  As pid order is
+ * different per namespace, each namespace needs differently sorted list,
+ * making it impossible to use, for example, single rbtree of member tasks
+ * sorted by task pointer.  As pidlists can be fairly large, allocating one
+ * per open file is dangerous, so cgroup had to implement shared pool of
+ * pidlists keyed by cgroup and namespace.
+ */
+static int cmppid(const void *a, const void *b)
+{
+	return *(pid_t *)a - *(pid_t *)b;
+}
+
+static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
+						  enum cgroup_filetype type)
+{
+	struct cgroup_pidlist *l;
+	/* don't need task_nsproxy() if we're looking at ourself */
+	struct pid_namespace *ns = task_active_pid_ns(current);
+
+	lockdep_assert_held(&cgrp->pidlist_mutex);
+
+	list_for_each_entry(l, &cgrp->pidlists, links)
+		if (l->key.type == type && l->key.ns == ns)
+			return l;
+	return NULL;
+}
+
+/*
+ * find the appropriate pidlist for our purpose (given procs vs tasks)
+ * returns with the lock on that pidlist already held, and takes care
+ * of the use count, or returns NULL with no locks held if we're out of
+ * memory.
+ */
+static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp,
+						enum cgroup_filetype type)
+{
+	struct cgroup_pidlist *l;
+
+	lockdep_assert_held(&cgrp->pidlist_mutex);
+
+	l = cgroup_pidlist_find(cgrp, type);
+	if (l)
+		return l;
+
+	/* entry not found; create a new one */
+	l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
+	if (!l)
+		return l;
+
+	INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn);
+	l->key.type = type;
+	/* don't need task_nsproxy() if we're looking at ourself */
+	l->key.ns = get_pid_ns(task_active_pid_ns(current));
+	l->owner = cgrp;
+	list_add(&l->links, &cgrp->pidlists);
+	return l;
+}
+
+/**
+ * cgroup_task_count - count the number of tasks in a cgroup.
+ * @cgrp: the cgroup in question
+ *
+ * Return the number of tasks in the cgroup.  The returned number can be
+ * higher than the actual number of tasks due to css_set references from
+ * namespace roots and temporary usages.
+ */
+static int cgroup_task_count(const struct cgroup *cgrp)
+{
+	int count = 0;
+	struct cgrp_cset_link *link;
+
+	spin_lock_irq(&css_set_lock);
+	list_for_each_entry(link, &cgrp->cset_links, cset_link)
+		count += atomic_read(&link->cset->refcount);
+	spin_unlock_irq(&css_set_lock);
+	return count;
+}
+
+/*
+ * Load a cgroup's pidarray with either procs' tgids or tasks' pids
+ */
+static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
+			      struct cgroup_pidlist **lp)
+{
+	pid_t *array;
+	int length;
+	int pid, n = 0; /* used for populating the array */
+	struct css_task_iter it;
+	struct task_struct *tsk;
+	struct cgroup_pidlist *l;
+
+	lockdep_assert_held(&cgrp->pidlist_mutex);
+
+	/*
+	 * If cgroup gets more users after we read count, we won't have
+	 * enough space - tough.  This race is indistinguishable to the
+	 * caller from the case that the additional cgroup users didn't
+	 * show up until sometime later on.
+	 */
+	length = cgroup_task_count(cgrp);
+	array = pidlist_allocate(length);
+	if (!array)
+		return -ENOMEM;
+	/* now, populate the array */
+	css_task_iter_start(&cgrp->self, &it);
+	while ((tsk = css_task_iter_next(&it))) {
+		if (unlikely(n == length))
+			break;
+		/* get tgid or pid for procs or tasks file respectively */
+		if (type == CGROUP_FILE_PROCS)
+			pid = task_tgid_vnr(tsk);
+		else
+			pid = task_pid_vnr(tsk);
+		if (pid > 0) /* make sure to only use valid results */
+			array[n++] = pid;
+	}
+	css_task_iter_end(&it);
+	length = n;
+	/* now sort & (if procs) strip out duplicates */
+	sort(array, length, sizeof(pid_t), cmppid, NULL);
+	if (type == CGROUP_FILE_PROCS)
+		length = pidlist_uniq(array, length);
+
+	l = cgroup_pidlist_find_create(cgrp, type);
+	if (!l) {
+		pidlist_free(array);
+		return -ENOMEM;
+	}
+
+	/* store array, freeing old if necessary */
+	pidlist_free(l->list);
+	l->list = array;
+	l->length = length;
+	*lp = l;
+	return 0;
+}
+
+/*
+ * seq_file methods for the tasks/procs files. The seq_file position is the
+ * next pid to display; the seq_file iterator is a pointer to the pid
+ * in the cgroup->l->list array.
+ */
+
+static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
+{
+	/*
+	 * Initially we receive a position value that corresponds to
+	 * one more than the last pid shown (or 0 on the first call or
+	 * after a seek to the start). Use a binary-search to find the
+	 * next pid to display, if any
+	 */
+	struct kernfs_open_file *of = s->private;
+	struct cgroup *cgrp = seq_css(s)->cgroup;
+	struct cgroup_pidlist *l;
+	enum cgroup_filetype type = seq_cft(s)->private;
+	int index = 0, pid = *pos;
+	int *iter, ret;
+
+	mutex_lock(&cgrp->pidlist_mutex);
+
+	/*
+	 * !NULL @of->priv indicates that this isn't the first start()
+	 * after open.  If the matching pidlist is around, we can use that.
+	 * Look for it.  Note that @of->priv can't be used directly.  It
+	 * could already have been destroyed.
+	 */
+	if (of->priv)
+		of->priv = cgroup_pidlist_find(cgrp, type);
+
+	/*
+	 * Either this is the first start() after open or the matching
+	 * pidlist has been destroyed inbetween.  Create a new one.
+	 */
+	if (!of->priv) {
+		ret = pidlist_array_load(cgrp, type,
+					 (struct cgroup_pidlist **)&of->priv);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+	l = of->priv;
+
+	if (pid) {
+		int end = l->length;
+
+		while (index < end) {
+			int mid = (index + end) / 2;
+			if (l->list[mid] == pid) {
+				index = mid;
+				break;
+			} else if (l->list[mid] <= pid)
+				index = mid + 1;
+			else
+				end = mid;
+		}
+	}
+	/* If we're off the end of the array, we're done */
+	if (index >= l->length)
+		return NULL;
+	/* Update the abstract position to be the actual pid that we found */
+	iter = l->list + index;
+	*pos = *iter;
+	return iter;
+}
+
+static void cgroup_pidlist_stop(struct seq_file *s, void *v)
+{
+	struct kernfs_open_file *of = s->private;
+	struct cgroup_pidlist *l = of->priv;
+
+	if (l)
+		mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork,
+				 CGROUP_PIDLIST_DESTROY_DELAY);
+	mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex);
+}
+
+static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	struct kernfs_open_file *of = s->private;
+	struct cgroup_pidlist *l = of->priv;
+	pid_t *p = v;
+	pid_t *end = l->list + l->length;
+	/*
+	 * Advance to the next pid in the array. If this goes off the
+	 * end, we're done
+	 */
+	p++;
+	if (p >= end) {
+		return NULL;
+	} else {
+		*pos = *p;
+		return p;
+	}
+}
+
+static int cgroup_pidlist_show(struct seq_file *s, void *v)
+{
+	seq_printf(s, "%d\n", *(int *)v);
+
+	return 0;
+}
+
+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_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;
+}
+
+static int cgroup_release_agent_show(struct seq_file *seq, void *v)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+
+	spin_lock(&release_agent_path_lock);
+	seq_puts(seq, cgrp->root->release_agent_path);
+	spin_unlock(&release_agent_path_lock);
+	seq_putc(seq, '\n');
+	return 0;
+}
+
+static int cgroup_sane_behavior_show(struct seq_file *seq, void *v)
+{
+	seq_puts(seq, "0\n");
+	return 0;
+}
+
+static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css,
+					 struct cftype *cft)
+{
+	return notify_on_release(css->cgroup);
+}
+
+static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css,
+					  struct cftype *cft, u64 val)
+{
+	if (val)
+		set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags);
+	else
+		clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags);
+	return 0;
+}
+
+static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css,
+				      struct cftype *cft)
+{
+	return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags);
+}
+
+static int cgroup_clone_children_write(struct cgroup_subsys_state *css,
+				       struct cftype *cft, u64 val)
+{
+	if (val)
+		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags);
+	else
+		clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags);
+	return 0;
+}
+
+/* cgroup core interface files for the legacy hierarchies */
+struct cftype cgroup_legacy_base_files[] = {
+	{
+		.name = "cgroup.procs",
+		.seq_start = cgroup_pidlist_start,
+		.seq_next = cgroup_pidlist_next,
+		.seq_stop = cgroup_pidlist_stop,
+		.seq_show = cgroup_pidlist_show,
+		.private = CGROUP_FILE_PROCS,
+		.write = cgroup_procs_write,
+	},
+	{
+		.name = "cgroup.clone_children",
+		.read_u64 = cgroup_clone_children_read,
+		.write_u64 = cgroup_clone_children_write,
+	},
+	{
+		.name = "cgroup.sane_behavior",
+		.flags = CFTYPE_ONLY_ON_ROOT,
+		.seq_show = cgroup_sane_behavior_show,
+	},
+	{
+		.name = "tasks",
+		.seq_start = cgroup_pidlist_start,
+		.seq_next = cgroup_pidlist_next,
+		.seq_stop = cgroup_pidlist_stop,
+		.seq_show = cgroup_pidlist_show,
+		.private = CGROUP_FILE_TASKS,
+		.write = cgroup_tasks_write,
+	},
+	{
+		.name = "notify_on_release",
+		.read_u64 = cgroup_read_notify_on_release,
+		.write_u64 = cgroup_write_notify_on_release,
+	},
+	{
+		.name = "release_agent",
+		.flags = CFTYPE_ONLY_ON_ROOT,
+		.seq_show = cgroup_release_agent_show,
+		.write = cgroup_release_agent_write,
+		.max_write_len = PATH_MAX - 1,
+	},
+	{ }	/* terminate */
+};
+
+/* Display information about each subsystem and each hierarchy */
+static int proc_cgroupstats_show(struct seq_file *m, void *v)
+{
+	struct cgroup_subsys *ss;
+	int i;
+
+	seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n");
+	/*
+	 * ideally we don't want subsystems moving around while we do this.
+	 * cgroup_mutex is also necessary to guarantee an atomic snapshot of
+	 * subsys/hierarchy state.
+	 */
+	mutex_lock(&cgroup_mutex);
+
+	for_each_subsys(ss, i)
+		seq_printf(m, "%s\t%d\t%d\t%d\n",
+			   ss->legacy_name, ss->root->hierarchy_id,
+			   atomic_read(&ss->root->nr_cgrps),
+			   cgroup_ssid_enabled(i));
+
+	mutex_unlock(&cgroup_mutex);
+	return 0;
+}
+
+static int cgroupstats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, proc_cgroupstats_show, NULL);
+}
+
+const struct file_operations proc_cgroupstats_operations = {
+	.open = cgroupstats_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+/**
+ * cgroupstats_build - build and fill cgroupstats
+ * @stats: cgroupstats to fill information into
+ * @dentry: A dentry entry belonging to the cgroup for which stats have
+ * been requested.
+ *
+ * Build and fill cgroupstats so that taskstats can export it to user
+ * space.
+ */
+int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
+{
+	struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
+	struct cgroup *cgrp;
+	struct css_task_iter it;
+	struct task_struct *tsk;
+
+	/* it should be kernfs_node belonging to cgroupfs and is a directory */
+	if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
+	    kernfs_type(kn) != KERNFS_DIR)
+		return -EINVAL;
+
+	mutex_lock(&cgroup_mutex);
+
+	/*
+	 * We aren't being called from kernfs and there's no guarantee on
+	 * @kn->priv's validity.  For this and css_tryget_online_from_dir(),
+	 * @kn->priv is RCU safe.  Let's do the RCU dancing.
+	 */
+	rcu_read_lock();
+	cgrp = rcu_dereference(kn->priv);
+	if (!cgrp || cgroup_is_dead(cgrp)) {
+		rcu_read_unlock();
+		mutex_unlock(&cgroup_mutex);
+		return -ENOENT;
+	}
+	rcu_read_unlock();
+
+	css_task_iter_start(&cgrp->self, &it);
+	while ((tsk = css_task_iter_next(&it))) {
+		switch (tsk->state) {
+		case TASK_RUNNING:
+			stats->nr_running++;
+			break;
+		case TASK_INTERRUPTIBLE:
+			stats->nr_sleeping++;
+			break;
+		case TASK_UNINTERRUPTIBLE:
+			stats->nr_uninterruptible++;
+			break;
+		case TASK_STOPPED:
+			stats->nr_stopped++;
+			break;
+		default:
+			if (delayacct_is_task_waiting_on_io(tsk))
+				stats->nr_io_wait++;
+			break;
+		}
+	}
+	css_task_iter_end(&it);
+
+	mutex_unlock(&cgroup_mutex);
+	return 0;
+}
+
+void check_for_release(struct cgroup *cgrp)
+{
+	if (notify_on_release(cgrp) && !cgroup_is_populated(cgrp) &&
+	    !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp))
+		schedule_work(&cgrp->release_agent_work);
+}
+
+/*
+ * Notify userspace when a cgroup is released, by running the
+ * configured release agent with the name of the cgroup (path
+ * relative to the root of cgroup file system) as the argument.
+ *
+ * Most likely, this user command will try to rmdir this cgroup.
+ *
+ * This races with the possibility that some other task will be
+ * attached to this cgroup before it is removed, or that some other
+ * user task will 'mkdir' a child cgroup of this cgroup.  That's ok.
+ * The presumed 'rmdir' will fail quietly if this cgroup is no longer
+ * unused, and this cgroup will be reprieved from its death sentence,
+ * to continue to serve a useful existence.  Next time it's released,
+ * we will get notified again, if it still has 'notify_on_release' set.
+ *
+ * The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which
+ * means only wait until the task is successfully execve()'d.  The
+ * separate release agent task is forked by call_usermodehelper(),
+ * then control in this thread returns here, without waiting for the
+ * release agent task.  We don't bother to wait because the caller of
+ * this routine has no use for the exit status of the release agent
+ * task, so no sense holding our caller up for that.
+ */
+void cgroup_release_agent(struct work_struct *work)
+{
+	struct cgroup *cgrp =
+		container_of(work, struct cgroup, release_agent_work);
+	char *pathbuf = NULL, *agentbuf = NULL;
+	char *argv[3], *envp[3];
+	int ret;
+
+	mutex_lock(&cgroup_mutex);
+
+	pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
+	agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
+	if (!pathbuf || !agentbuf)
+		goto out;
+
+	spin_lock_irq(&css_set_lock);
+	ret = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns);
+	spin_unlock_irq(&css_set_lock);
+	if (ret < 0 || ret >= PATH_MAX)
+		goto out;
+
+	argv[0] = agentbuf;
+	argv[1] = pathbuf;
+	argv[2] = NULL;
+
+	/* minimal command environment */
+	envp[0] = "HOME=/";
+	envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
+	envp[2] = NULL;
+
+	mutex_unlock(&cgroup_mutex);
+	call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
+	goto out_free;
+out:
+	mutex_unlock(&cgroup_mutex);
+out_free:
+	kfree(agentbuf);
+	kfree(pathbuf);
+}
+
+/*
+ * cgroup_rename - Only allow simple rename of directories in place.
+ */
+int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
+		  const char *new_name_str)
+{
+	struct cgroup *cgrp = kn->priv;
+	int ret;
+
+	if (kernfs_type(kn) != KERNFS_DIR)
+		return -ENOTDIR;
+	if (kn->parent != new_parent)
+		return -EIO;
+
+	/*
+	 * This isn't a proper migration and its usefulness is very
+	 * limited.  Disallow on the default hierarchy.
+	 */
+	if (cgroup_on_dfl(cgrp))
+		return -EPERM;
+
+	/*
+	 * We're gonna grab cgroup_mutex which nests outside kernfs
+	 * active_ref.  kernfs_rename() doesn't require active_ref
+	 * protection.  Break them before grabbing cgroup_mutex.
+	 */
+	kernfs_break_active_protection(new_parent);
+	kernfs_break_active_protection(kn);
+
+	mutex_lock(&cgroup_mutex);
+
+	ret = kernfs_rename(kn, new_parent, new_name_str);
+	if (!ret)
+		trace_cgroup_rename(cgrp);
+
+	mutex_unlock(&cgroup_mutex);
+
+	kernfs_unbreak_active_protection(kn);
+	kernfs_unbreak_active_protection(new_parent);
+	return ret;
+}
+
+static int __init cgroup1_wq_init(void)
+{
+	/*
+	 * Used to destroy pidlists and separate to serve as flush domain.
+	 * Cap @max_active to 1 too.
+	 */
+	cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy",
+						    0, 1);
+	BUG_ON(!cgroup_pidlist_destroy_wq);
+	return 0;
+}
+core_initcall(cgroup1_wq_init);
+
+static int __init cgroup_no_v1(char *str)
+{
+	struct cgroup_subsys *ss;
+	char *token;
+	int i;
+
+	while ((token = strsep(&str, ",")) != NULL) {
+		if (!*token)
+			continue;
+
+		if (!strcmp(token, "all")) {
+			cgroup_no_v1_mask = U16_MAX;
+			break;
+		}
+
+		for_each_subsys(ss, i) {
+			if (strcmp(token, ss->name) &&
+			    strcmp(token, ss->legacy_name))
+				continue;
+
+			cgroup_no_v1_mask |= 1 << i;
+		}
+	}
+	return 1;
+}
+__setup("cgroup_no_v1=", cgroup_no_v1);
+
+
+#ifdef CONFIG_CGROUP_DEBUG
+static struct cgroup_subsys_state *
+debug_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+	struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
+
+	if (!css)
+		return ERR_PTR(-ENOMEM);
+
+	return css;
+}
+
+static void debug_css_free(struct cgroup_subsys_state *css)
+{
+	kfree(css);
+}
+
+static u64 debug_taskcount_read(struct cgroup_subsys_state *css,
+				struct cftype *cft)
+{
+	return cgroup_task_count(css->cgroup);
+}
+
+static u64 current_css_set_read(struct cgroup_subsys_state *css,
+				struct cftype *cft)
+{
+	return (u64)(unsigned long)current->cgroups;
+}
+
+static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css,
+					 struct cftype *cft)
+{
+	u64 count;
+
+	rcu_read_lock();
+	count = atomic_read(&task_css_set(current)->refcount);
+	rcu_read_unlock();
+	return count;
+}
+
+static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
+{
+	struct cgrp_cset_link *link;
+	struct css_set *cset;
+	char *name_buf;
+
+	name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL);
+	if (!name_buf)
+		return -ENOMEM;
+
+	spin_lock_irq(&css_set_lock);
+	rcu_read_lock();
+	cset = rcu_dereference(current->cgroups);
+	list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
+		struct cgroup *c = link->cgrp;
+
+		cgroup_name(c, name_buf, NAME_MAX + 1);
+		seq_printf(seq, "Root %d group %s\n",
+			   c->root->hierarchy_id, name_buf);
+	}
+	rcu_read_unlock();
+	spin_unlock_irq(&css_set_lock);
+	kfree(name_buf);
+	return 0;
+}
+
+#define MAX_TASKS_SHOWN_PER_CSS 25
+static int cgroup_css_links_read(struct seq_file *seq, void *v)
+{
+	struct cgroup_subsys_state *css = seq_css(seq);
+	struct cgrp_cset_link *link;
+
+	spin_lock_irq(&css_set_lock);
+	list_for_each_entry(link, &css->cgroup->cset_links, cset_link) {
+		struct css_set *cset = link->cset;
+		struct task_struct *task;
+		int count = 0;
+
+		seq_printf(seq, "css_set %p\n", cset);
+
+		list_for_each_entry(task, &cset->tasks, cg_list) {
+			if (count++ > MAX_TASKS_SHOWN_PER_CSS)
+				goto overflow;
+			seq_printf(seq, "  task %d\n", task_pid_vnr(task));
+		}
+
+		list_for_each_entry(task, &cset->mg_tasks, cg_list) {
+			if (count++ > MAX_TASKS_SHOWN_PER_CSS)
+				goto overflow;
+			seq_printf(seq, "  task %d\n", task_pid_vnr(task));
+		}
+		continue;
+	overflow:
+		seq_puts(seq, "  ...\n");
+	}
+	spin_unlock_irq(&css_set_lock);
+	return 0;
+}
+
+static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	return (!cgroup_is_populated(css->cgroup) &&
+		!css_has_online_children(&css->cgroup->self));
+}
+
+static struct cftype debug_files[] =  {
+	{
+		.name = "taskcount",
+		.read_u64 = debug_taskcount_read,
+	},
+
+	{
+		.name = "current_css_set",
+		.read_u64 = current_css_set_read,
+	},
+
+	{
+		.name = "current_css_set_refcount",
+		.read_u64 = current_css_set_refcount_read,
+	},
+
+	{
+		.name = "current_css_set_cg_links",
+		.seq_show = current_css_set_cg_links_read,
+	},
+
+	{
+		.name = "cgroup_css_links",
+		.seq_show = cgroup_css_links_read,
+	},
+
+	{
+		.name = "releasable",
+		.read_u64 = releasable_read,
+	},
+
+	{ }	/* terminate */
+};
+
+struct cgroup_subsys debug_cgrp_subsys = {
+	.css_alloc = debug_css_alloc,
+	.css_free = debug_css_free,
+	.legacy_cftypes = debug_files,
+};
+#endif /* CONFIG_CGROUP_DEBUG */