Merge branch 'for-3.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup changes from Tejun Heo:
 "A lot of activities on cgroup side.  The big changes are focused on
  making cgroup hierarchy handling saner.

   - cgroup_rmdir() had peculiar semantics - it allowed cgroup
     destruction to be vetoed by individual controllers and tried to
     drain refcnt synchronously.  The vetoing never worked properly and
     caused good deal of contortions in cgroup.  memcg was the last
     reamining user.  Michal Hocko removed the usage and cgroup_rmdir()
     path has been simplified significantly.  This was done in a
     separate branch so that the memcg people can base further memcg
     changes on top.

   - The above allowed cleaning up cgroup lifecycle management and
     implementation of generic cgroup iterators which are used to
     improve hierarchy support.

   - cgroup_freezer updated to allow migration in and out of a frozen
     cgroup and handle hierarchy.  If a cgroup is frozen, all descendant
     cgroups are frozen.

   - netcls_cgroup and netprio_cgroup updated to handle hierarchy
     properly.

   - Various fixes and cleanups.

   - Two merge commits.  One to pull in memcg and rmdir cleanups (needed
     to build iterators).  The other pulled in cgroup/for-3.7-fixes for
     device_cgroup fixes so that further device_cgroup patches can be
     stacked on top."

Fixed up a trivial conflict in mm/memcontrol.c as per Tejun (due to
commit bea8c150a7 ("memcg: fix hotplugged memory zone oops") in master
touching code close to commit 2ef37d3fe4 ("memcg: Simplify
mem_cgroup_force_empty_list error handling") in for-3.8)

* 'for-3.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (65 commits)
  cgroup: update Documentation/cgroups/00-INDEX
  cgroup_rm_file: don't delete the uncreated files
  cgroup: remove subsystem files when remounting cgroup
  cgroup: use cgroup_addrm_files() in cgroup_clear_directory()
  cgroup: warn about broken hierarchies only after css_online
  cgroup: list_del_init() on removed events
  cgroup: fix lockdep warning for event_control
  cgroup: move list add after list head initilization
  netprio_cgroup: allow nesting and inherit config on cgroup creation
  netprio_cgroup: implement netprio[_set]_prio() helpers
  netprio_cgroup: use cgroup->id instead of cgroup_netprio_state->prioidx
  netprio_cgroup: reimplement priomap expansion
  netprio_cgroup: shorten variable names in extend_netdev_table()
  netprio_cgroup: simplify write_priomap()
  netcls_cgroup: move config inheritance to ->css_online() and remove .broken_hierarchy marking
  cgroup: remove obsolete guarantee from cgroup_task_migrate.
  cgroup: add cgroup->id
  cgroup, cpuset: remove cgroup_subsys->post_clone()
  cgroup: s/CGRP_CLONE_CHILDREN/CGRP_CPUSET_CLONE_CHILDREN/
  cgroup: rename ->create/post_create/pre_destroy/destroy() to ->css_alloc/online/offline/free()
  ...

9 files changed, 758 insertions, 677 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index f24f724620d..f34c41bfaa3 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -138,6 +138,9 @@ struct cgroupfs_root {
 	/* Hierarchy-specific flags */
 	unsigned long flags;
 
+	/* IDs for cgroups in this hierarchy */
+	struct ida cgroup_ida;
+
 	/* The path to use for release notifications. */
 	char release_agent_path[PATH_MAX];
 
@@ -171,8 +174,8 @@ struct css_id {
 	 * The css to which this ID points. This pointer is set to valid value
 	 * after cgroup is populated. If cgroup is removed, this will be NULL.
 	 * This pointer is expected to be RCU-safe because destroy()
-	 * is called after synchronize_rcu(). But for safe use, css_is_removed()
-	 * css_tryget() should be used for avoiding race.
+	 * is called after synchronize_rcu(). But for safe use, css_tryget()
+	 * should be used for avoiding race.
 	 */
 	struct cgroup_subsys_state __rcu *css;
 	/*
@@ -242,6 +245,10 @@ static DEFINE_SPINLOCK(hierarchy_id_lock);
  */
 static int need_forkexit_callback __read_mostly;
 
+static int cgroup_destroy_locked(struct cgroup *cgrp);
+static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys,
+			      struct cftype cfts[], bool is_add);
+
 #ifdef CONFIG_PROVE_LOCKING
 int cgroup_lock_is_held(void)
 {
@@ -294,11 +301,6 @@ static int notify_on_release(const struct cgroup *cgrp)
 	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 }
 
-static int clone_children(const struct cgroup *cgrp)
-{
-	return test_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
-}
-
 /*
  * for_each_subsys() allows you to iterate on each subsystem attached to
  * an active hierarchy
@@ -782,12 +784,12 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
  *	The task_lock() exception
  *
  * The need for this exception arises from the action of
- * cgroup_attach_task(), which overwrites one tasks cgroup pointer with
+ * cgroup_attach_task(), which overwrites one task's cgroup pointer with
  * another.  It does so using cgroup_mutex, however there are
  * several performance critical places that need to reference
  * task->cgroup without the expense of grabbing a system global
  * mutex.  Therefore except as noted below, when dereferencing or, as
- * in cgroup_attach_task(), modifying a task'ss cgroup pointer we use
+ * in cgroup_attach_task(), modifying a task's cgroup pointer we use
  * task_lock(), which acts on a spinlock (task->alloc_lock) already in
  * the task_struct routinely used for such matters.
  *
@@ -854,30 +856,6 @@ static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
 	return inode;
 }
 
-/*
- * Call subsys's pre_destroy handler.
- * This is called before css refcnt check.
- */
-static int cgroup_call_pre_destroy(struct cgroup *cgrp)
-{
-	struct cgroup_subsys *ss;
-	int ret = 0;
-
-	for_each_subsys(cgrp->root, ss) {
-		if (!ss->pre_destroy)
-			continue;
-
-		ret = ss->pre_destroy(cgrp);
-		if (ret) {
-			/* ->pre_destroy() failure is being deprecated */
-			WARN_ON_ONCE(!ss->__DEPRECATED_clear_css_refs);
-			break;
-		}
-	}
-
-	return ret;
-}
-
 static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 {
 	/* is dentry a directory ? if so, kfree() associated cgroup */
@@ -898,7 +876,7 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		 * Release the subsystem state objects.
 		 */
 		for_each_subsys(cgrp->root, ss)
-			ss->destroy(cgrp);
+			ss->css_free(cgrp);
 
 		cgrp->root->number_of_cgroups--;
 		mutex_unlock(&cgroup_mutex);
@@ -917,6 +895,7 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 
 		simple_xattrs_free(&cgrp->xattrs);
 
+		ida_simple_remove(&cgrp->root->cgroup_ida, cgrp->id);
 		kfree_rcu(cgrp, rcu_head);
 	} else {
 		struct cfent *cfe = __d_cfe(dentry);
@@ -987,7 +966,7 @@ static void cgroup_clear_directory(struct dentry *dir, bool base_files,
 		if (!test_bit(ss->subsys_id, &subsys_mask))
 			continue;
 		list_for_each_entry(set, &ss->cftsets, node)
-			cgroup_rm_file(cgrp, set->cfts);
+			cgroup_addrm_files(cgrp, NULL, set->cfts, false);
 	}
 	if (base_files) {
 		while (!list_empty(&cgrp->files))
@@ -1015,33 +994,6 @@ static void cgroup_d_remove_dir(struct dentry *dentry)
 }
 
 /*
- * A queue for waiters to do rmdir() cgroup. A tasks will sleep when
- * cgroup->count == 0 && list_empty(&cgroup->children) && subsys has some
- * reference to css->refcnt. In general, this refcnt is expected to goes down
- * to zero, soon.
- *
- * CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex;
- */
-static DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
-
-static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp)
-{
-	if (unlikely(test_and_clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
-		wake_up_all(&cgroup_rmdir_waitq);
-}
-
-void cgroup_exclude_rmdir(struct cgroup_subsys_state *css)
-{
-	css_get(css);
-}
-
-void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css)
-{
-	cgroup_wakeup_rmdir_waiter(css->cgroup);
-	css_put(css);
-}
-
-/*
  * Call with cgroup_mutex held. Drops reference counts on modules, including
  * any duplicate ones that parse_cgroupfs_options took. If this function
  * returns an error, no reference counts are touched.
@@ -1150,7 +1102,7 @@ static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",xattr");
 	if (strlen(root->release_agent_path))
 		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
-	if (clone_children(&root->top_cgroup))
+	if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags))
 		seq_puts(seq, ",clone_children");
 	if (strlen(root->name))
 		seq_printf(seq, ",name=%s", root->name);
@@ -1162,7 +1114,7 @@ struct cgroup_sb_opts {
 	unsigned long subsys_mask;
 	unsigned long flags;
 	char *release_agent;
-	bool clone_children;
+	bool cpuset_clone_children;
 	char *name;
 	/* User explicitly requested empty subsystem */
 	bool none;
@@ -1213,7 +1165,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 			continue;
 		}
 		if (!strcmp(token, "clone_children")) {
-			opts->clone_children = true;
+			opts->cpuset_clone_children = true;
 			continue;
 		}
 		if (!strcmp(token, "xattr")) {
@@ -1397,14 +1349,21 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 		goto out_unlock;
 	}
 
+	/*
+	 * Clear out the files of subsystems that should be removed, do
+	 * this before rebind_subsystems, since rebind_subsystems may
+	 * change this hierarchy's subsys_list.
+	 */
+	cgroup_clear_directory(cgrp->dentry, false, removed_mask);
+
 	ret = rebind_subsystems(root, opts.subsys_mask);
 	if (ret) {
+		/* rebind_subsystems failed, re-populate the removed files */
+		cgroup_populate_dir(cgrp, false, removed_mask);
 		drop_parsed_module_refcounts(opts.subsys_mask);
 		goto out_unlock;
 	}
 
-	/* clear out any existing files and repopulate subsystem files */
-	cgroup_clear_directory(cgrp->dentry, false, removed_mask);
 	/* re-populate subsystem files */
 	cgroup_populate_dir(cgrp, false, added_mask);
 
@@ -1432,6 +1391,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	INIT_LIST_HEAD(&cgrp->children);
 	INIT_LIST_HEAD(&cgrp->files);
 	INIT_LIST_HEAD(&cgrp->css_sets);
+	INIT_LIST_HEAD(&cgrp->allcg_node);
 	INIT_LIST_HEAD(&cgrp->release_list);
 	INIT_LIST_HEAD(&cgrp->pidlists);
 	mutex_init(&cgrp->pidlist_mutex);
@@ -1450,8 +1410,8 @@ static void init_cgroup_root(struct cgroupfs_root *root)
 	root->number_of_cgroups = 1;
 	cgrp->root = root;
 	cgrp->top_cgroup = cgrp;
-	list_add_tail(&cgrp->allcg_node, &root->allcg_list);
 	init_cgroup_housekeeping(cgrp);
+	list_add_tail(&cgrp->allcg_node, &root->allcg_list);
 }
 
 static bool init_root_id(struct cgroupfs_root *root)
@@ -1518,12 +1478,13 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
 
 	root->subsys_mask = opts->subsys_mask;
 	root->flags = opts->flags;
+	ida_init(&root->cgroup_ida);
 	if (opts->release_agent)
 		strcpy(root->release_agent_path, opts->release_agent);
 	if (opts->name)
 		strcpy(root->name, opts->name);
-	if (opts->clone_children)
-		set_bit(CGRP_CLONE_CHILDREN, &root->top_cgroup.flags);
+	if (opts->cpuset_clone_children)
+		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags);
 	return root;
 }
 
@@ -1536,6 +1497,7 @@ static void cgroup_drop_root(struct cgroupfs_root *root)
 	spin_lock(&hierarchy_id_lock);
 	ida_remove(&hierarchy_ida, root->hierarchy_id);
 	spin_unlock(&hierarchy_id_lock);
+	ida_destroy(&root->cgroup_ida);
 	kfree(root);
 }
 
@@ -1701,7 +1663,6 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 
 		free_cg_links(&tmp_cg_links);
 
-		BUG_ON(!list_empty(&root_cgrp->sibling));
 		BUG_ON(!list_empty(&root_cgrp->children));
 		BUG_ON(root->number_of_cgroups != 1);
 
@@ -1750,7 +1711,6 @@ static void cgroup_kill_sb(struct super_block *sb) {
 
 	BUG_ON(root->number_of_cgroups != 1);
 	BUG_ON(!list_empty(&cgrp->children));
-	BUG_ON(!list_empty(&cgrp->sibling));
 
 	mutex_lock(&cgroup_mutex);
 	mutex_lock(&cgroup_root_mutex);
@@ -1808,9 +1768,11 @@ static struct kobject *cgroup_kobj;
  */
 int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 {
+	struct dentry *dentry = cgrp->dentry;
 	char *start;
-	struct dentry *dentry = rcu_dereference_check(cgrp->dentry,
-						      cgroup_lock_is_held());
+
+	rcu_lockdep_assert(rcu_read_lock_held() || cgroup_lock_is_held(),
+			   "cgroup_path() called without proper locking");
 
 	if (!dentry || cgrp == dummytop) {
 		/*
@@ -1821,9 +1783,9 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 		return 0;
 	}
 
-	start = buf + buflen;
+	start = buf + buflen - 1;
 
-	*--start = '\0';
+	*start = '\0';
 	for (;;) {
 		int len = dentry->d_name.len;
 
@@ -1834,8 +1796,7 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 		if (!cgrp)
 			break;
 
-		dentry = rcu_dereference_check(cgrp->dentry,
-					       cgroup_lock_is_held());
+		dentry = cgrp->dentry;
 		if (!cgrp->parent)
 			continue;
 		if (--start < buf)
@@ -1930,9 +1891,7 @@ EXPORT_SYMBOL_GPL(cgroup_taskset_size);
 /*
  * cgroup_task_migrate - move a task from one cgroup to another.
  *
- * 'guarantee' is set if the caller promises that a new css_set for the task
- * will already exist. If not set, this function might sleep, and can fail with
- * -ENOMEM. Must be called with cgroup_mutex and threadgroup locked.
+ * Must be called with cgroup_mutex and threadgroup locked.
  */
 static void cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
 				struct task_struct *tsk, struct css_set *newcg)
@@ -2025,12 +1984,6 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	}
 
 	synchronize_rcu();
-
-	/*
-	 * wake up rmdir() waiter. the rmdir should fail since the cgroup
-	 * is no longer empty.
-	 */
-	cgroup_wakeup_rmdir_waiter(cgrp);
 out:
 	if (retval) {
 		for_each_subsys(root, ss) {
@@ -2200,7 +2153,6 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 	 * step 5: success! and cleanup
 	 */
 	synchronize_rcu();
-	cgroup_wakeup_rmdir_waiter(cgrp);
 	retval = 0;
 out_put_css_set_refs:
 	if (retval) {
@@ -2711,10 +2663,17 @@ static int cgroup_create_file(struct dentry *dentry, umode_t mode,
 
 		/* start off with i_nlink == 2 (for "." entry) */
 		inc_nlink(inode);
+		inc_nlink(dentry->d_parent->d_inode);
 
-		/* start with the directory inode held, so that we can
-		 * populate it without racing with another mkdir */
-		mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
+		/*
+		 * Control reaches here with cgroup_mutex held.
+		 * @inode->i_mutex should nest outside cgroup_mutex but we
+		 * want to populate it immediately without releasing
+		 * cgroup_mutex.  As @inode isn't visible to anyone else
+		 * yet, trylock will always succeed without affecting
+		 * lockdep checks.
+		 */
+		WARN_ON_ONCE(!mutex_trylock(&inode->i_mutex));
 	} else if (S_ISREG(mode)) {
 		inode->i_size = 0;
 		inode->i_fop = &cgroup_file_operations;
@@ -2725,32 +2684,6 @@ static int cgroup_create_file(struct dentry *dentry, umode_t mode,
 	return 0;
 }
 
-/*
- * cgroup_create_dir - create a directory for an object.
- * @cgrp: the cgroup we create the directory for. It must have a valid
- *        ->parent field. And we are going to fill its ->dentry field.
- * @dentry: dentry of the new cgroup
- * @mode: mode to set on new directory.
- */
-static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry,
-				umode_t mode)
-{
-	struct dentry *parent;
-	int error = 0;
-
-	parent = cgrp->parent->dentry;
-	error = cgroup_create_file(dentry, S_IFDIR | mode, cgrp->root->sb);
-	if (!error) {
-		dentry->d_fsdata = cgrp;
-		inc_nlink(parent->d_inode);
-		rcu_assign_pointer(cgrp->dentry, dentry);
-		dget(dentry);
-	}
-	dput(dentry);
-
-	return error;
-}
-
 /**
  * cgroup_file_mode - deduce file mode of a control file
  * @cft: the control file in question
@@ -2791,12 +2724,6 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
 
 	simple_xattrs_init(&cft->xattrs);
 
-	/* does @cft->flags tell us to skip creation on @cgrp? */
-	if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent)
-		return 0;
-	if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgrp->parent)
-		return 0;
-
 	if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) {
 		strcpy(name, subsys->name);
 		strcat(name, ".");
@@ -2837,6 +2764,12 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys,
 	int err, ret = 0;
 
 	for (cft = cfts; cft->name[0] != '\0'; cft++) {
+		/* does cft->flags tell us to skip this file on @cgrp? */
+		if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent)
+			continue;
+		if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgrp->parent)
+			continue;
+
 		if (is_add)
 			err = cgroup_add_file(cgrp, subsys, cft);
 		else
@@ -3044,6 +2977,92 @@ static void cgroup_enable_task_cg_lists(void)
 	write_unlock(&css_set_lock);
 }
 
+/**
+ * cgroup_next_descendant_pre - find the next descendant for pre-order walk
+ * @pos: the current position (%NULL to initiate traversal)
+ * @cgroup: cgroup whose descendants to walk
+ *
+ * To be used by cgroup_for_each_descendant_pre().  Find the next
+ * descendant to visit for pre-order traversal of @cgroup's descendants.
+ */
+struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos,
+					  struct cgroup *cgroup)
+{
+	struct cgroup *next;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	/* if first iteration, pretend we just visited @cgroup */
+	if (!pos) {
+		if (list_empty(&cgroup->children))
+			return NULL;
+		pos = cgroup;
+	}
+
+	/* visit the first child if exists */
+	next = list_first_or_null_rcu(&pos->children, struct cgroup, sibling);
+	if (next)
+		return next;
+
+	/* no child, visit my or the closest ancestor's next sibling */
+	do {
+		next = list_entry_rcu(pos->sibling.next, struct cgroup,
+				      sibling);
+		if (&next->sibling != &pos->parent->children)
+			return next;
+
+		pos = pos->parent;
+	} while (pos != cgroup);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(cgroup_next_descendant_pre);
+
+static struct cgroup *cgroup_leftmost_descendant(struct cgroup *pos)
+{
+	struct cgroup *last;
+
+	do {
+		last = pos;
+		pos = list_first_or_null_rcu(&pos->children, struct cgroup,
+					     sibling);
+	} while (pos);
+
+	return last;
+}
+
+/**
+ * cgroup_next_descendant_post - find the next descendant for post-order walk
+ * @pos: the current position (%NULL to initiate traversal)
+ * @cgroup: cgroup whose descendants to walk
+ *
+ * To be used by cgroup_for_each_descendant_post().  Find the next
+ * descendant to visit for post-order traversal of @cgroup's descendants.
+ */
+struct cgroup *cgroup_next_descendant_post(struct cgroup *pos,
+					   struct cgroup *cgroup)
+{
+	struct cgroup *next;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	/* if first iteration, visit the leftmost descendant */
+	if (!pos) {
+		next = cgroup_leftmost_descendant(cgroup);
+		return next != cgroup ? next : NULL;
+	}
+
+	/* if there's an unvisited sibling, visit its leftmost descendant */
+	next = list_entry_rcu(pos->sibling.next, struct cgroup, sibling);
+	if (&next->sibling != &pos->parent->children)
+		return cgroup_leftmost_descendant(next);
+
+	/* no sibling left, visit parent */
+	next = pos->parent;
+	return next != cgroup ? next : NULL;
+}
+EXPORT_SYMBOL_GPL(cgroup_next_descendant_post);
+
 void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it)
 	__acquires(css_set_lock)
 {
@@ -3757,7 +3776,7 @@ static int cgroup_event_wake(wait_queue_t *wait, unsigned mode,
 	if (flags & POLLHUP) {
 		__remove_wait_queue(event->wqh, &event->wait);
 		spin_lock(&cgrp->event_list_lock);
-		list_del(&event->list);
+		list_del_init(&event->list);
 		spin_unlock(&cgrp->event_list_lock);
 		/*
 		 * We are in atomic context, but cgroup_event_remove() may
@@ -3894,7 +3913,7 @@ fail:
 static u64 cgroup_clone_children_read(struct cgroup *cgrp,
 				    struct cftype *cft)
 {
-	return clone_children(cgrp);
+	return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 }
 
 static int cgroup_clone_children_write(struct cgroup *cgrp,
@@ -3902,9 +3921,9 @@ static int cgroup_clone_children_write(struct cgroup *cgrp,
 				     u64 val)
 {
 	if (val)
-		set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 	else
-		clear_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+		clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 	return 0;
 }
 
@@ -4017,19 +4036,57 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 	css->flags = 0;
 	css->id = NULL;
 	if (cgrp == dummytop)
-		set_bit(CSS_ROOT, &css->flags);
+		css->flags |= CSS_ROOT;
 	BUG_ON(cgrp->subsys[ss->subsys_id]);
 	cgrp->subsys[ss->subsys_id] = css;
 
 	/*
-	 * If !clear_css_refs, css holds an extra ref to @cgrp->dentry
-	 * which is put on the last css_put().  dput() requires process
-	 * context, which css_put() may be called without.  @css->dput_work
-	 * will be used to invoke dput() asynchronously from css_put().
+	 * css holds an extra ref to @cgrp->dentry which is put on the last
+	 * css_put().  dput() requires process context, which css_put() may
+	 * be called without.  @css->dput_work will be used to invoke
+	 * dput() asynchronously from css_put().
 	 */
 	INIT_WORK(&css->dput_work, css_dput_fn);
-	if (ss->__DEPRECATED_clear_css_refs)
-		set_bit(CSS_CLEAR_CSS_REFS, &css->flags);
+}
+
+/* invoke ->post_create() on a new CSS and mark it online if successful */
+static int online_css(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+	int ret = 0;
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	if (ss->css_online)
+		ret = ss->css_online(cgrp);
+	if (!ret)
+		cgrp->subsys[ss->subsys_id]->flags |= CSS_ONLINE;
+	return ret;
+}
+
+/* if the CSS is online, invoke ->pre_destory() on it and mark it offline */
+static void offline_css(struct cgroup_subsys *ss, struct cgroup *cgrp)
+	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
+{
+	struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	if (!(css->flags & CSS_ONLINE))
+		return;
+
+	/*
+	 * css_offline() should be called with cgroup_mutex unlocked.  See
+	 * 3fa59dfbc3 ("cgroup: fix potential deadlock in pre_destroy") for
+	 * details.  This temporary unlocking should go away once
+	 * cgroup_mutex is unexported from controllers.
+	 */
+	if (ss->css_offline) {
+		mutex_unlock(&cgroup_mutex);
+		ss->css_offline(cgrp);
+		mutex_lock(&cgroup_mutex);
+	}
+
+	cgrp->subsys[ss->subsys_id]->flags &= ~CSS_ONLINE;
 }
 
 /*
@@ -4049,10 +4106,27 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	struct cgroup_subsys *ss;
 	struct super_block *sb = root->sb;
 
+	/* allocate the cgroup and its ID, 0 is reserved for the root */
 	cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
 	if (!cgrp)
 		return -ENOMEM;
 
+	cgrp->id = ida_simple_get(&root->cgroup_ida, 1, 0, GFP_KERNEL);
+	if (cgrp->id < 0)
+		goto err_free_cgrp;
+
+	/*
+	 * Only live parents can have children.  Note that the liveliness
+	 * check isn't strictly necessary because cgroup_mkdir() and
+	 * cgroup_rmdir() are fully synchronized by i_mutex; however, do it
+	 * anyway so that locking is contained inside cgroup proper and we
+	 * don't get nasty surprises if we ever grow another caller.
+	 */
+	if (!cgroup_lock_live_group(parent)) {
+		err = -ENODEV;
+		goto err_free_id;
+	}
+
 	/* Grab a reference on the superblock so the hierarchy doesn't
 	 * get deleted on unmount if there are child cgroups.  This
 	 * can be done outside cgroup_mutex, since the sb can't
@@ -4060,8 +4134,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	 * fs */
 	atomic_inc(&sb->s_active);
 
-	mutex_lock(&cgroup_mutex);
-
 	init_cgroup_housekeeping(cgrp);
 
 	cgrp->parent = parent;
@@ -4071,26 +4143,51 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	if (notify_on_release(parent))
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 
-	if (clone_children(parent))
-		set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+	if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags))
+		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 
 	for_each_subsys(root, ss) {
 		struct cgroup_subsys_state *css;
 
-		css = ss->create(cgrp);
+		css = ss->css_alloc(cgrp);
 		if (IS_ERR(css)) {
 			err = PTR_ERR(css);
-			goto err_destroy;
+			goto err_free_all;
 		}
 		init_cgroup_css(css, ss, cgrp);
 		if (ss->use_id) {
 			err = alloc_css_id(ss, parent, cgrp);
 			if (err)
-				goto err_destroy;
+				goto err_free_all;
 		}
-		/* At error, ->destroy() callback has to free assigned ID. */
-		if (clone_children(parent) && ss->post_clone)
-			ss->post_clone(cgrp);
+	}
+
+	/*
+	 * Create directory.  cgroup_create_file() returns with the new
+	 * directory locked on success so that it can be populated without
+	 * dropping cgroup_mutex.
+	 */
+	err = cgroup_create_file(dentry, S_IFDIR | mode, sb);
+	if (err < 0)
+		goto err_free_all;
+	lockdep_assert_held(&dentry->d_inode->i_mutex);
+
+	/* allocation complete, commit to creation */
+	dentry->d_fsdata = cgrp;
+	cgrp->dentry = dentry;
+	list_add_tail(&cgrp->allcg_node, &root->allcg_list);
+	list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
+	root->number_of_cgroups++;
+
+	/* each css holds a ref to the cgroup's dentry */
+	for_each_subsys(root, ss)
+		dget(dentry);
+
+	/* creation succeeded, notify subsystems */
+	for_each_subsys(root, ss) {
+		err = online_css(ss, cgrp);
+		if (err)
+			goto err_destroy;
 
 		if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
 		    parent->parent) {
@@ -4102,50 +4199,34 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 		}
 	}
 
-	list_add(&cgrp->sibling, &cgrp->parent->children);
-	root->number_of_cgroups++;
-
-	err = cgroup_create_dir(cgrp, dentry, mode);
-	if (err < 0)
-		goto err_remove;
-
-	/* If !clear_css_refs, each css holds a ref to the cgroup's dentry */
-	for_each_subsys(root, ss)
-		if (!ss->__DEPRECATED_clear_css_refs)
-			dget(dentry);
-
-	/* The cgroup directory was pre-locked for us */
-	BUG_ON(!mutex_is_locked(&cgrp->dentry->d_inode->i_mutex));
-
-	list_add_tail(&cgrp->allcg_node, &root->allcg_list);
-
 	err = cgroup_populate_dir(cgrp, true, root->subsys_mask);
-	/* If err < 0, we have a half-filled directory - oh well ;) */
+	if (err)
+		goto err_destroy;
 
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
 
 	return 0;
 
- err_remove:
-
-	list_del(&cgrp->sibling);
-	root->number_of_cgroups--;
-
- err_destroy:
-
+err_free_all:
 	for_each_subsys(root, ss) {
 		if (cgrp->subsys[ss->subsys_id])
-			ss->destroy(cgrp);
+			ss->css_free(cgrp);
 	}
-
 	mutex_unlock(&cgroup_mutex);
-
 	/* Release the reference count that we took on the superblock */
 	deactivate_super(sb);
-
+err_free_id:
+	ida_simple_remove(&root->cgroup_ida, cgrp->id);
+err_free_cgrp:
 	kfree(cgrp);
 	return err;
+
+err_destroy:
+	cgroup_destroy_locked(cgrp);
+	mutex_unlock(&cgroup_mutex);
+	mutex_unlock(&dentry->d_inode->i_mutex);
+	return err;
 }
 
 static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
@@ -4197,153 +4278,60 @@ static int cgroup_has_css_refs(struct cgroup *cgrp)
 	return 0;
 }
 
-/*
- * Atomically mark all (or else none) of the cgroup's CSS objects as
- * CSS_REMOVED. Return true on success, or false if the cgroup has
- * busy subsystems. Call with cgroup_mutex held
- *
- * Depending on whether a subsys has __DEPRECATED_clear_css_refs set or
- * not, cgroup removal behaves differently.
- *
- * If clear is set, css refcnt for the subsystem should be zero before
- * cgroup removal can be committed.  This is implemented by
- * CGRP_WAIT_ON_RMDIR and retry logic around ->pre_destroy(), which may be
- * called multiple times until all css refcnts reach zero and is allowed to
- * veto removal on any invocation.  This behavior is deprecated and will be
- * removed as soon as the existing user (memcg) is updated.
- *
- * If clear is not set, each css holds an extra reference to the cgroup's
- * dentry and cgroup removal proceeds regardless of css refs.
- * ->pre_destroy() will be called at least once and is not allowed to fail.
- * On the last put of each css, whenever that may be, the extra dentry ref
- * is put so that dentry destruction happens only after all css's are
- * released.
- */
-static int cgroup_clear_css_refs(struct cgroup *cgrp)
+static int cgroup_destroy_locked(struct cgroup *cgrp)
+	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
 {
+	struct dentry *d = cgrp->dentry;
+	struct cgroup *parent = cgrp->parent;
+	DEFINE_WAIT(wait);
+	struct cgroup_event *event, *tmp;
 	struct cgroup_subsys *ss;
-	unsigned long flags;
-	bool failed = false;
+	LIST_HEAD(tmp_list);
+
+	lockdep_assert_held(&d->d_inode->i_mutex);
+	lockdep_assert_held(&cgroup_mutex);
 
-	local_irq_save(flags);
+	if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children))
+		return -EBUSY;
 
 	/*
-	 * Block new css_tryget() by deactivating refcnt.  If all refcnts
-	 * for subsystems w/ clear_css_refs set were 1 at the moment of
-	 * deactivation, we succeeded.
+	 * Block new css_tryget() by deactivating refcnt and mark @cgrp
+	 * removed.  This makes future css_tryget() and child creation
+	 * attempts fail thus maintaining the removal conditions verified
+	 * above.
 	 */
 	for_each_subsys(cgrp->root, ss) {
 		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
 
 		WARN_ON(atomic_read(&css->refcnt) < 0);
 		atomic_add(CSS_DEACT_BIAS, &css->refcnt);
-
-		if (ss->__DEPRECATED_clear_css_refs)
-			failed |= css_refcnt(css) != 1;
-	}
-
-	/*
-	 * If succeeded, set REMOVED and put all the base refs; otherwise,
-	 * restore refcnts to positive values.  Either way, all in-progress
-	 * css_tryget() will be released.
-	 */
-	for_each_subsys(cgrp->root, ss) {
-		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
-
-		if (!failed) {
-			set_bit(CSS_REMOVED, &css->flags);
-			css_put(css);
-		} else {
-			atomic_sub(CSS_DEACT_BIAS, &css->refcnt);
-		}
 	}
+	set_bit(CGRP_REMOVED, &cgrp->flags);
 
-	local_irq_restore(flags);
-	return !failed;
-}
-
-static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
-{
-	struct cgroup *cgrp = dentry->d_fsdata;
-	struct dentry *d;
-	struct cgroup *parent;
-	DEFINE_WAIT(wait);
-	struct cgroup_event *event, *tmp;
-	int ret;
-
-	/* the vfs holds both inode->i_mutex already */
-again:
-	mutex_lock(&cgroup_mutex);
-	if (atomic_read(&cgrp->count) != 0) {
-		mutex_unlock(&cgroup_mutex);
-		return -EBUSY;
-	}
-	if (!list_empty(&cgrp->children)) {
-		mutex_unlock(&cgroup_mutex);
-		return -EBUSY;
-	}
-	mutex_unlock(&cgroup_mutex);
-
-	/*
-	 * In general, subsystem has no css->refcnt after pre_destroy(). But
-	 * in racy cases, subsystem may have to get css->refcnt after
-	 * pre_destroy() and it makes rmdir return with -EBUSY. This sometimes
-	 * make rmdir return -EBUSY too often. To avoid that, we use waitqueue
-	 * for cgroup's rmdir. CGRP_WAIT_ON_RMDIR is for synchronizing rmdir
-	 * and subsystem's reference count handling. Please see css_get/put
-	 * and css_tryget() and cgroup_wakeup_rmdir_waiter() implementation.
-	 */
-	set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
+	/* tell subsystems to initate destruction */
+	for_each_subsys(cgrp->root, ss)
+		offline_css(ss, cgrp);
 
 	/*
-	 * Call pre_destroy handlers of subsys. Notify subsystems
-	 * that rmdir() request comes.
+	 * Put all the base refs.  Each css holds an extra reference to the
+	 * cgroup's dentry and cgroup removal proceeds regardless of css
+	 * refs.  On the last put of each css, whenever that may be, the
+	 * extra dentry ref is put so that dentry destruction happens only
+	 * after all css's are released.
 	 */
-	ret = cgroup_call_pre_destroy(cgrp);
-	if (ret) {
-		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
-		return ret;
-	}
-
-	mutex_lock(&cgroup_mutex);
-	parent = cgrp->parent;
-	if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
-		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
-		mutex_unlock(&cgroup_mutex);
-		return -EBUSY;
-	}
-	prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE);
-	if (!cgroup_clear_css_refs(cgrp)) {
-		mutex_unlock(&cgroup_mutex);
-		/*
-		 * Because someone may call cgroup_wakeup_rmdir_waiter() before
-		 * prepare_to_wait(), we need to check this flag.
-		 */
-		if (test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags))
-			schedule();
-		finish_wait(&cgroup_rmdir_waitq, &wait);
-		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
-		if (signal_pending(current))
-			return -EINTR;
-		goto again;
-	}
-	/* NO css_tryget() can success after here. */
-	finish_wait(&cgroup_rmdir_waitq, &wait);
-	clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
+	for_each_subsys(cgrp->root, ss)
+		css_put(cgrp->subsys[ss->subsys_id]);
 
 	raw_spin_lock(&release_list_lock);
-	set_bit(CGRP_REMOVED, &cgrp->flags);
 	if (!list_empty(&cgrp->release_list))
 		list_del_init(&cgrp->release_list);
 	raw_spin_unlock(&release_list_lock);
 
 	/* delete this cgroup from parent->children */
-	list_del_init(&cgrp->sibling);
-
+	list_del_rcu(&cgrp->sibling);
 	list_del_init(&cgrp->allcg_node);
 
-	d = dget(cgrp->dentry);
-
+	dget(d);
 	cgroup_d_remove_dir(d);
 	dput(d);
 
@@ -4353,21 +4341,35 @@ again:
 	/*
 	 * Unregister events and notify userspace.
 	 * Notify userspace about cgroup removing only after rmdir of cgroup
-	 * directory to avoid race between userspace and kernelspace
+	 * directory to avoid race between userspace and kernelspace. Use
+	 * a temporary list to avoid a deadlock with cgroup_event_wake(). Since
+	 * cgroup_event_wake() is called with the wait queue head locked,
+	 * remove_wait_queue() cannot be called while holding event_list_lock.
 	 */
 	spin_lock(&cgrp->event_list_lock);
-	list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
-		list_del(&event->list);
+	list_splice_init(&cgrp->event_list, &tmp_list);
+	spin_unlock(&cgrp->event_list_lock);
+	list_for_each_entry_safe(event, tmp, &tmp_list, list) {
+		list_del_init(&event->list);
 		remove_wait_queue(event->wqh, &event->wait);
 		eventfd_signal(event->eventfd, 1);
 		schedule_work(&event->remove);
 	}
-	spin_unlock(&cgrp->event_list_lock);
 
-	mutex_unlock(&cgroup_mutex);
 	return 0;
 }
 
+static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
+{
+	int ret;
+
+	mutex_lock(&cgroup_mutex);
+	ret = cgroup_destroy_locked(dentry->d_fsdata);
+	mutex_unlock(&cgroup_mutex);
+
+	return ret;
+}
+
 static void __init_or_module cgroup_init_cftsets(struct cgroup_subsys *ss)
 {
 	INIT_LIST_HEAD(&ss->cftsets);
@@ -4388,13 +4390,15 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 
 	printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name);
 
+	mutex_lock(&cgroup_mutex);
+
 	/* init base cftset */
 	cgroup_init_cftsets(ss);
 
 	/* Create the top cgroup state for this subsystem */
 	list_add(&ss->sibling, &rootnode.subsys_list);
 	ss->root = &rootnode;
-	css = ss->create(dummytop);
+	css = ss->css_alloc(dummytop);
 	/* We don't handle early failures gracefully */
 	BUG_ON(IS_ERR(css));
 	init_cgroup_css(css, ss, dummytop);
@@ -4403,7 +4407,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	 * pointer to this state - since the subsystem is
 	 * newly registered, all tasks and hence the
 	 * init_css_set is in the subsystem's top cgroup. */
-	init_css_set.subsys[ss->subsys_id] = dummytop->subsys[ss->subsys_id];
+	init_css_set.subsys[ss->subsys_id] = css;
 
 	need_forkexit_callback |= ss->fork || ss->exit;
 
@@ -4413,6 +4417,9 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	BUG_ON(!list_empty(&init_task.tasks));
 
 	ss->active = 1;
+	BUG_ON(online_css(ss, dummytop));
+
+	mutex_unlock(&cgroup_mutex);
 
 	/* this function shouldn't be used with modular subsystems, since they
 	 * need to register a subsys_id, among other things */
@@ -4430,12 +4437,12 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
  */
 int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 {
-	int i;
 	struct cgroup_subsys_state *css;
+	int i, ret;
 
 	/* check name and function validity */
 	if (ss->name == NULL || strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN ||
-	    ss->create == NULL || ss->destroy == NULL)
+	    ss->css_alloc == NULL || ss->css_free == NULL)
 		return -EINVAL;
 
 	/*
@@ -4464,10 +4471,11 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	subsys[ss->subsys_id] = ss;
 
 	/*
-	 * no ss->create seems to need anything important in the ss struct, so
-	 * this can happen first (i.e. before the rootnode attachment).
+	 * no ss->css_alloc seems to need anything important in the ss
+	 * struct, so this can happen first (i.e. before the rootnode
+	 * attachment).
 	 */
-	css = ss->create(dummytop);
+	css = ss->css_alloc(dummytop);
 	if (IS_ERR(css)) {
 		/* failure case - need to deassign the subsys[] slot. */
 		subsys[ss->subsys_id] = NULL;
@@ -4482,14 +4490,9 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	init_cgroup_css(css, ss, dummytop);
 	/* init_idr must be after init_cgroup_css because it sets css->id. */
 	if (ss->use_id) {
-		int ret = cgroup_init_idr(ss, css);
-		if (ret) {
-			dummytop->subsys[ss->subsys_id] = NULL;
-			ss->destroy(dummytop);
-			subsys[ss->subsys_id] = NULL;
-			mutex_unlock(&cgroup_mutex);
-			return ret;
-		}
+		ret = cgroup_init_idr(ss, css);
+		if (ret)
+			goto err_unload;
 	}
 
 	/*
@@ -4522,10 +4525,19 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	write_unlock(&css_set_lock);
 
 	ss->active = 1;
+	ret = online_css(ss, dummytop);
+	if (ret)
+		goto err_unload;
 
 	/* success! */
 	mutex_unlock(&cgroup_mutex);
 	return 0;
+
+err_unload:
+	mutex_unlock(&cgroup_mutex);
+	/* @ss can't be mounted here as try_module_get() would fail */
+	cgroup_unload_subsys(ss);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(cgroup_load_subsys);
 
@@ -4552,6 +4564,15 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 	BUG_ON(ss->root != &rootnode);
 
 	mutex_lock(&cgroup_mutex);
+
+	offline_css(ss, dummytop);
+	ss->active = 0;
+
+	if (ss->use_id) {
+		idr_remove_all(&ss->idr);
+		idr_destroy(&ss->idr);
+	}
+
 	/* deassign the subsys_id */
 	subsys[ss->subsys_id] = NULL;
 
@@ -4567,7 +4588,6 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 		struct css_set *cg = link->cg;
 
 		hlist_del(&cg->hlist);
-		BUG_ON(!cg->subsys[ss->subsys_id]);
 		cg->subsys[ss->subsys_id] = NULL;
 		hhead = css_set_hash(cg->subsys);
 		hlist_add_head(&cg->hlist, hhead);
@@ -4575,12 +4595,12 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 	write_unlock(&css_set_lock);
 
 	/*
-	 * remove subsystem's css from the dummytop and free it - need to free
-	 * before marking as null because ss->destroy needs the cgrp->subsys
-	 * pointer to find their state. note that this also takes care of
-	 * freeing the css_id.
+	 * remove subsystem's css from the dummytop and free it - need to
+	 * free before marking as null because ss->css_free needs the
+	 * cgrp->subsys pointer to find their state. note that this also
+	 * takes care of freeing the css_id.
 	 */
-	ss->destroy(dummytop);
+	ss->css_free(dummytop);
 	dummytop->subsys[ss->subsys_id] = NULL;
 
 	mutex_unlock(&cgroup_mutex);
@@ -4624,8 +4644,8 @@ int __init cgroup_init_early(void)
 
 		BUG_ON(!ss->name);
 		BUG_ON(strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN);
-		BUG_ON(!ss->create);
-		BUG_ON(!ss->destroy);
+		BUG_ON(!ss->css_alloc);
+		BUG_ON(!ss->css_free);
 		if (ss->subsys_id != i) {
 			printk(KERN_ERR "cgroup: Subsys %s id == %d\n",
 			       ss->name, ss->subsys_id);
@@ -4832,44 +4852,19 @@ void cgroup_fork(struct task_struct *child)
 }
 
 /**
- * cgroup_fork_callbacks - run fork callbacks
- * @child: the new task
- *
- * Called on a new task very soon before adding it to the
- * tasklist. No need to take any locks since no-one can
- * be operating on this task.
- */
-void cgroup_fork_callbacks(struct task_struct *child)
-{
-	if (need_forkexit_callback) {
-		int i;
-		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-			struct cgroup_subsys *ss = subsys[i];
-
-			/*
-			 * forkexit callbacks are only supported for
-			 * builtin subsystems.
-			 */
-			if (!ss || ss->module)
-				continue;
-
-			if (ss->fork)
-				ss->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.
- * Has to be after the task is visible on the task list in case we race
- * with the first call to cgroup_iter_start() - to guarantee that the
- * new task ends up on its list.
+ * 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_iter_start() - to guarantee that the new task ends up on its
+ * list.
  */
 void cgroup_post_fork(struct task_struct *child)
 {
+	int i;
+
 	/*
 	 * use_task_css_set_links is set to 1 before we walk the tasklist
 	 * under the tasklist_lock and we read it here after we added the child
@@ -4889,7 +4884,30 @@ void cgroup_post_fork(struct task_struct *child)
 		task_unlock(child);
 		write_unlock(&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.
+	 */
+	if (need_forkexit_callback) {
+		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+			struct cgroup_subsys *ss = subsys[i];
+
+			/*
+			 * fork/exit callbacks are supported only for
+			 * builtin subsystems and we don't need further
+			 * synchronization as they never go away.
+			 */
+			if (!ss || ss->module)
+				continue;
+
+			if (ss->fork)
+				ss->fork(child);
+		}
+	}
 }
+
 /**
  * cgroup_exit - detach cgroup from exiting task
  * @tsk: pointer to task_struct of exiting process
@@ -5022,15 +5040,17 @@ static void check_for_release(struct cgroup *cgrp)
 /* Caller must verify that the css is not for root cgroup */
 bool __css_tryget(struct cgroup_subsys_state *css)
 {
-	do {
-		int v = css_refcnt(css);
+	while (true) {
+		int t, v;
 
-		if (atomic_cmpxchg(&css->refcnt, v, v + 1) == v)
+		v = css_refcnt(css);
+		t = atomic_cmpxchg(&css->refcnt, v, v + 1);
+		if (likely(t == v))
 			return true;
+		else if (t < 0)
+			return false;
 		cpu_relax();
-	} while (!test_bit(CSS_REMOVED, &css->flags));
-
-	return false;
+	}
 }
 EXPORT_SYMBOL_GPL(__css_tryget);
 
@@ -5049,11 +5069,9 @@ void __css_put(struct cgroup_subsys_state *css)
 			set_bit(CGRP_RELEASABLE, &cgrp->flags);
 			check_for_release(cgrp);
 		}
-		cgroup_wakeup_rmdir_waiter(cgrp);
 		break;
 	case 0:
-		if (!test_bit(CSS_CLEAR_CSS_REFS, &css->flags))
-			schedule_work(&css->dput_work);
+		schedule_work(&css->dput_work);
 		break;
 	}
 	rcu_read_unlock();
@@ -5439,7 +5457,7 @@ struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id)
 }
 
 #ifdef CONFIG_CGROUP_DEBUG
-static struct cgroup_subsys_state *debug_create(struct cgroup *cont)
+static struct cgroup_subsys_state *debug_css_alloc(struct cgroup *cont)
 {
 	struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
 
@@ -5449,7 +5467,7 @@ static struct cgroup_subsys_state *debug_create(struct cgroup *cont)
 	return css;
 }
 
-static void debug_destroy(struct cgroup *cont)
+static void debug_css_free(struct cgroup *cont)
 {
 	kfree(cont->subsys[debug_subsys_id]);
 }
@@ -5578,8 +5596,8 @@ static struct cftype debug_files[] =  {
 
 struct cgroup_subsys debug_subsys = {
 	.name = "debug",
-	.create = debug_create,
-	.destroy = debug_destroy,
+	.css_alloc = debug_css_alloc,
+	.css_free = debug_css_free,
 	.subsys_id = debug_subsys_id,
 	.base_cftypes = debug_files,
 };
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index b1724ce9898..75dda1ea502 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -22,24 +22,33 @@
 #include <linux/freezer.h>
 #include <linux/seq_file.h>
 
-enum freezer_state {
-	CGROUP_THAWED = 0,
-	CGROUP_FREEZING,
-	CGROUP_FROZEN,
+/*
+ * A cgroup is freezing if any FREEZING flags are set.  FREEZING_SELF is
+ * set if "FROZEN" is written to freezer.state cgroupfs file, and cleared
+ * for "THAWED".  FREEZING_PARENT is set if the parent freezer is FREEZING
+ * for whatever reason.  IOW, a cgroup has FREEZING_PARENT set if one of
+ * its ancestors has FREEZING_SELF set.
+ */
+enum freezer_state_flags {
+	CGROUP_FREEZER_ONLINE	= (1 << 0), /* freezer is fully online */
+	CGROUP_FREEZING_SELF	= (1 << 1), /* this freezer is freezing */
+	CGROUP_FREEZING_PARENT	= (1 << 2), /* the parent freezer is freezing */
+	CGROUP_FROZEN		= (1 << 3), /* this and its descendants frozen */
+
+	/* mask for all FREEZING flags */
+	CGROUP_FREEZING		= CGROUP_FREEZING_SELF | CGROUP_FREEZING_PARENT,
 };
 
 struct freezer {
-	struct cgroup_subsys_state css;
-	enum freezer_state state;
-	spinlock_t lock; /* protects _writes_ to state */
+	struct cgroup_subsys_state	css;
+	unsigned int			state;
+	spinlock_t			lock;
 };
 
-static inline struct freezer *cgroup_freezer(
-		struct cgroup *cgroup)
+static inline struct freezer *cgroup_freezer(struct cgroup *cgroup)
 {
-	return container_of(
-		cgroup_subsys_state(cgroup, freezer_subsys_id),
-		struct freezer, css);
+	return container_of(cgroup_subsys_state(cgroup, freezer_subsys_id),
+			    struct freezer, css);
 }
 
 static inline struct freezer *task_freezer(struct task_struct *task)
@@ -48,14 +57,21 @@ static inline struct freezer *task_freezer(struct task_struct *task)
 			    struct freezer, css);
 }
 
+static struct freezer *parent_freezer(struct freezer *freezer)
+{
+	struct cgroup *pcg = freezer->css.cgroup->parent;
+
+	if (pcg)
+		return cgroup_freezer(pcg);
+	return NULL;
+}
+
 bool cgroup_freezing(struct task_struct *task)
 {
-	enum freezer_state state;
 	bool ret;
 
 	rcu_read_lock();
-	state = task_freezer(task)->state;
-	ret = state == CGROUP_FREEZING || state == CGROUP_FROZEN;
+	ret = task_freezer(task)->state & CGROUP_FREEZING;
 	rcu_read_unlock();
 
 	return ret;
@@ -65,70 +81,18 @@ bool cgroup_freezing(struct task_struct *task)
  * cgroups_write_string() limits the size of freezer state strings to
  * CGROUP_LOCAL_BUFFER_SIZE
  */
-static const char *freezer_state_strs[] = {
-	"THAWED",
-	"FREEZING",
-	"FROZEN",
+static const char *freezer_state_strs(unsigned int state)
+{
+	if (state & CGROUP_FROZEN)
+		return "FROZEN";
+	if (state & CGROUP_FREEZING)
+		return "FREEZING";
+	return "THAWED";
 };
 
-/*
- * State diagram
- * Transitions are caused by userspace writes to the freezer.state file.
- * The values in parenthesis are state labels. The rest are edge labels.
- *
- * (THAWED) --FROZEN--> (FREEZING) --FROZEN--> (FROZEN)
- *    ^ ^                    |                     |
- *    | \_______THAWED_______/                     |
- *    \__________________________THAWED____________/
- */
-
 struct cgroup_subsys freezer_subsys;
 
-/* Locks taken and their ordering
- * ------------------------------
- * cgroup_mutex (AKA cgroup_lock)
- * freezer->lock
- * css_set_lock
- * task->alloc_lock (AKA task_lock)
- * task->sighand->siglock
- *
- * cgroup code forces css_set_lock to be taken before task->alloc_lock
- *
- * freezer_create(), freezer_destroy():
- * cgroup_mutex [ by cgroup core ]
- *
- * freezer_can_attach():
- * cgroup_mutex (held by caller of can_attach)
- *
- * freezer_fork() (preserving fork() performance means can't take cgroup_mutex):
- * freezer->lock
- *  sighand->siglock (if the cgroup is freezing)
- *
- * freezer_read():
- * cgroup_mutex
- *  freezer->lock
- *   write_lock css_set_lock (cgroup iterator start)
- *    task->alloc_lock
- *   read_lock css_set_lock (cgroup iterator start)
- *
- * freezer_write() (freeze):
- * cgroup_mutex
- *  freezer->lock
- *   write_lock css_set_lock (cgroup iterator start)
- *    task->alloc_lock
- *   read_lock css_set_lock (cgroup iterator start)
- *    sighand->siglock (fake signal delivery inside freeze_task())
- *
- * freezer_write() (unfreeze):
- * cgroup_mutex
- *  freezer->lock
- *   write_lock css_set_lock (cgroup iterator start)
- *    task->alloc_lock
- *   read_lock css_set_lock (cgroup iterator start)
- *    task->alloc_lock (inside __thaw_task(), prevents race with refrigerator())
- *     sighand->siglock
- */
-static struct cgroup_subsys_state *freezer_create(struct cgroup *cgroup)
+static struct cgroup_subsys_state *freezer_css_alloc(struct cgroup *cgroup)
 {
 	struct freezer *freezer;
 
@@ -137,160 +101,244 @@ static struct cgroup_subsys_state *freezer_create(struct cgroup *cgroup)
 		return ERR_PTR(-ENOMEM);
 
 	spin_lock_init(&freezer->lock);
-	freezer->state = CGROUP_THAWED;
 	return &freezer->css;
 }
 
-static void freezer_destroy(struct cgroup *cgroup)
+/**
+ * freezer_css_online - commit creation of a freezer cgroup
+ * @cgroup: cgroup being created
+ *
+ * We're committing to creation of @cgroup.  Mark it online and inherit
+ * parent's freezing state while holding both parent's and our
+ * freezer->lock.
+ */
+static int freezer_css_online(struct cgroup *cgroup)
+{
+	struct freezer *freezer = cgroup_freezer(cgroup);
+	struct freezer *parent = parent_freezer(freezer);
+
+	/*
+	 * The following double locking and freezing state inheritance
+	 * guarantee that @cgroup can never escape ancestors' freezing
+	 * states.  See cgroup_for_each_descendant_pre() for details.
+	 */
+	if (parent)
+		spin_lock_irq(&parent->lock);
+	spin_lock_nested(&freezer->lock, SINGLE_DEPTH_NESTING);
+
+	freezer->state |= CGROUP_FREEZER_ONLINE;
+
+	if (parent && (parent->state & CGROUP_FREEZING)) {
+		freezer->state |= CGROUP_FREEZING_PARENT | CGROUP_FROZEN;
+		atomic_inc(&system_freezing_cnt);
+	}
+
+	spin_unlock(&freezer->lock);
+	if (parent)
+		spin_unlock_irq(&parent->lock);
+
+	return 0;
+}
+
+/**
+ * freezer_css_offline - initiate destruction of @cgroup
+ * @cgroup: cgroup being destroyed
+ *
+ * @cgroup is going away.  Mark it dead and decrement system_freezing_count
+ * if it was holding one.
+ */
+static void freezer_css_offline(struct cgroup *cgroup)
 {
 	struct freezer *freezer = cgroup_freezer(cgroup);
 
-	if (freezer->state != CGROUP_THAWED)
+	spin_lock_irq(&freezer->lock);
+
+	if (freezer->state & CGROUP_FREEZING)
 		atomic_dec(&system_freezing_cnt);
-	kfree(freezer);
+
+	freezer->state = 0;
+
+	spin_unlock_irq(&freezer->lock);
 }
 
-/* task is frozen or will freeze immediately when next it gets woken */
-static bool is_task_frozen_enough(struct task_struct *task)
+static void freezer_css_free(struct cgroup *cgroup)
 {
-	return frozen(task) ||
-		(task_is_stopped_or_traced(task) && freezing(task));
+	kfree(cgroup_freezer(cgroup));
 }
 
 /*
- * The call to cgroup_lock() in the freezer.state write method prevents
- * a write to that file racing against an attach, and hence the
- * can_attach() result will remain valid until the attach completes.
+ * Tasks can be migrated into a different freezer anytime regardless of its
+ * current state.  freezer_attach() is responsible for making new tasks
+ * conform to the current state.
+ *
+ * Freezer state changes and task migration are synchronized via
+ * @freezer->lock.  freezer_attach() makes the new tasks conform to the
+ * current state and all following state changes can see the new tasks.
  */
-static int freezer_can_attach(struct cgroup *new_cgroup,
-			      struct cgroup_taskset *tset)
+static void freezer_attach(struct cgroup *new_cgrp, struct cgroup_taskset *tset)
 {
-	struct freezer *freezer;
+	struct freezer *freezer = cgroup_freezer(new_cgrp);
 	struct task_struct *task;
+	bool clear_frozen = false;
+
+	spin_lock_irq(&freezer->lock);
 
 	/*
-	 * Anything frozen can't move or be moved to/from.
+	 * Make the new tasks conform to the current state of @new_cgrp.
+	 * For simplicity, when migrating any task to a FROZEN cgroup, we
+	 * revert it to FREEZING and let update_if_frozen() determine the
+	 * correct state later.
+	 *
+	 * Tasks in @tset are on @new_cgrp but may not conform to its
+	 * current state before executing the following - !frozen tasks may
+	 * be visible in a FROZEN cgroup and frozen tasks in a THAWED one.
 	 */
-	cgroup_taskset_for_each(task, new_cgroup, tset)
-		if (cgroup_freezing(task))
-			return -EBUSY;
+	cgroup_taskset_for_each(task, new_cgrp, tset) {
+		if (!(freezer->state & CGROUP_FREEZING)) {
+			__thaw_task(task);
+		} else {
+			freeze_task(task);
+			freezer->state &= ~CGROUP_FROZEN;
+			clear_frozen = true;
+		}
+	}
 
-	freezer = cgroup_freezer(new_cgroup);
-	if (freezer->state != CGROUP_THAWED)
-		return -EBUSY;
+	spin_unlock_irq(&freezer->lock);
 
-	return 0;
+	/*
+	 * Propagate FROZEN clearing upwards.  We may race with
+	 * update_if_frozen(), but as long as both work bottom-up, either
+	 * update_if_frozen() sees child's FROZEN cleared or we clear the
+	 * parent's FROZEN later.  No parent w/ !FROZEN children can be
+	 * left FROZEN.
+	 */
+	while (clear_frozen && (freezer = parent_freezer(freezer))) {
+		spin_lock_irq(&freezer->lock);
+		freezer->state &= ~CGROUP_FROZEN;
+		clear_frozen = freezer->state & CGROUP_FREEZING;
+		spin_unlock_irq(&freezer->lock);
+	}
 }
 
 static void freezer_fork(struct task_struct *task)
 {
 	struct freezer *freezer;
 
-	/*
-	 * No lock is needed, since the task isn't on tasklist yet,
-	 * so it can't be moved to another cgroup, which means the
-	 * freezer won't be removed and will be valid during this
-	 * function call.  Nevertheless, apply RCU read-side critical
-	 * section to suppress RCU lockdep false positives.
-	 */
 	rcu_read_lock();
 	freezer = task_freezer(task);
-	rcu_read_unlock();
 
 	/*
 	 * The root cgroup is non-freezable, so we can skip the
 	 * following check.
 	 */
 	if (!freezer->css.cgroup->parent)
-		return;
+		goto out;
 
 	spin_lock_irq(&freezer->lock);
-	BUG_ON(freezer->state == CGROUP_FROZEN);
-
-	/* Locking avoids race with FREEZING -> THAWED transitions. */
-	if (freezer->state == CGROUP_FREEZING)
+	if (freezer->state & CGROUP_FREEZING)
 		freeze_task(task);
 	spin_unlock_irq(&freezer->lock);
+out:
+	rcu_read_unlock();
 }
 
-/*
- * caller must hold freezer->lock
+/**
+ * update_if_frozen - update whether a cgroup finished freezing
+ * @cgroup: cgroup of interest
+ *
+ * Once FREEZING is initiated, transition to FROZEN is lazily updated by
+ * calling this function.  If the current state is FREEZING but not FROZEN,
+ * this function checks whether all tasks of this cgroup and the descendant
+ * cgroups finished freezing and, if so, sets FROZEN.
+ *
+ * The caller is responsible for grabbing RCU read lock and calling
+ * update_if_frozen() on all descendants prior to invoking this function.
+ *
+ * Task states and freezer state might disagree while tasks are being
+ * migrated into or out of @cgroup, so we can't verify task states against
+ * @freezer state here.  See freezer_attach() for details.
  */
-static void update_if_frozen(struct cgroup *cgroup,
-				 struct freezer *freezer)
+static void update_if_frozen(struct cgroup *cgroup)
 {
+	struct freezer *freezer = cgroup_freezer(cgroup);
+	struct cgroup *pos;
 	struct cgroup_iter it;
 	struct task_struct *task;
-	unsigned int nfrozen = 0, ntotal = 0;
-	enum freezer_state old_state = freezer->state;
 
-	cgroup_iter_start(cgroup, &it);
-	while ((task = cgroup_iter_next(cgroup, &it))) {
-		ntotal++;
-		if (freezing(task) && is_task_frozen_enough(task))
-			nfrozen++;
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	spin_lock_irq(&freezer->lock);
+
+	if (!(freezer->state & CGROUP_FREEZING) ||
+	    (freezer->state & CGROUP_FROZEN))
+		goto out_unlock;
+
+	/* are all (live) children frozen? */
+	cgroup_for_each_child(pos, cgroup) {
+		struct freezer *child = cgroup_freezer(pos);
+
+		if ((child->state & CGROUP_FREEZER_ONLINE) &&
+		    !(child->state & CGROUP_FROZEN))
+			goto out_unlock;
 	}
 
-	if (old_state == CGROUP_THAWED) {
-		BUG_ON(nfrozen > 0);
-	} else if (old_state == CGROUP_FREEZING) {
-		if (nfrozen == ntotal)
-			freezer->state = CGROUP_FROZEN;
-	} else { /* old_state == CGROUP_FROZEN */
-		BUG_ON(nfrozen != ntotal);
+	/* are all tasks frozen? */
+	cgroup_iter_start(cgroup, &it);
+
+	while ((task = cgroup_iter_next(cgroup, &it))) {
+		if (freezing(task)) {
+			/*
+			 * freezer_should_skip() indicates that the task
+			 * should be skipped when determining freezing
+			 * completion.  Consider it frozen in addition to
+			 * the usual frozen condition.
+			 */
+			if (!frozen(task) && !freezer_should_skip(task))
+				goto out_iter_end;
+		}
 	}
 
+	freezer->state |= CGROUP_FROZEN;
+out_iter_end:
 	cgroup_iter_end(cgroup, &it);
+out_unlock:
+	spin_unlock_irq(&freezer->lock);
 }
 
 static int freezer_read(struct cgroup *cgroup, struct cftype *cft,
 			struct seq_file *m)
 {
-	struct freezer *freezer;
-	enum freezer_state state;
+	struct cgroup *pos;
 
-	if (!cgroup_lock_live_group(cgroup))
-		return -ENODEV;
+	rcu_read_lock();
 
-	freezer = cgroup_freezer(cgroup);
-	spin_lock_irq(&freezer->lock);
-	state = freezer->state;
-	if (state == CGROUP_FREEZING) {
-		/* We change from FREEZING to FROZEN lazily if the cgroup was
-		 * only partially frozen when we exitted write. */
-		update_if_frozen(cgroup, freezer);
-		state = freezer->state;
-	}
-	spin_unlock_irq(&freezer->lock);
-	cgroup_unlock();
+	/* update states bottom-up */
+	cgroup_for_each_descendant_post(pos, cgroup)
+		update_if_frozen(pos);
+	update_if_frozen(cgroup);
+
+	rcu_read_unlock();
 
-	seq_puts(m, freezer_state_strs[state]);
+	seq_puts(m, freezer_state_strs(cgroup_freezer(cgroup)->state));
 	seq_putc(m, '\n');
 	return 0;
 }
 
-static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
+static void freeze_cgroup(struct freezer *freezer)
 {
+	struct cgroup *cgroup = freezer->css.cgroup;
 	struct cgroup_iter it;
 	struct task_struct *task;
-	unsigned int num_cant_freeze_now = 0;
 
 	cgroup_iter_start(cgroup, &it);
-	while ((task = cgroup_iter_next(cgroup, &it))) {
-		if (!freeze_task(task))
-			continue;
-		if (is_task_frozen_enough(task))
-			continue;
-		if (!freezing(task) && !freezer_should_skip(task))
-			num_cant_freeze_now++;
-	}
+	while ((task = cgroup_iter_next(cgroup, &it)))
+		freeze_task(task);
 	cgroup_iter_end(cgroup, &it);
-
-	return num_cant_freeze_now ? -EBUSY : 0;
 }
 
-static void unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
+static void unfreeze_cgroup(struct freezer *freezer)
 {
+	struct cgroup *cgroup = freezer->css.cgroup;
 	struct cgroup_iter it;
 	struct task_struct *task;
 
@@ -300,59 +348,111 @@ static void unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
 	cgroup_iter_end(cgroup, &it);
 }
 
-static int freezer_change_state(struct cgroup *cgroup,
-				enum freezer_state goal_state)
+/**
+ * freezer_apply_state - apply state change to a single cgroup_freezer
+ * @freezer: freezer to apply state change to
+ * @freeze: whether to freeze or unfreeze
+ * @state: CGROUP_FREEZING_* flag to set or clear
+ *
+ * Set or clear @state on @cgroup according to @freeze, and perform
+ * freezing or thawing as necessary.
+ */
+static void freezer_apply_state(struct freezer *freezer, bool freeze,
+				unsigned int state)
 {
-	struct freezer *freezer;
-	int retval = 0;
-
-	freezer = cgroup_freezer(cgroup);
+	/* also synchronizes against task migration, see freezer_attach() */
+	lockdep_assert_held(&freezer->lock);
 
-	spin_lock_irq(&freezer->lock);
+	if (!(freezer->state & CGROUP_FREEZER_ONLINE))
+		return;
 
-	update_if_frozen(cgroup, freezer);
-
-	switch (goal_state) {
-	case CGROUP_THAWED:
-		if (freezer->state != CGROUP_THAWED)
-			atomic_dec(&system_freezing_cnt);
-		freezer->state = CGROUP_THAWED;
-		unfreeze_cgroup(cgroup, freezer);
-		break;
-	case CGROUP_FROZEN:
-		if (freezer->state == CGROUP_THAWED)
+	if (freeze) {
+		if (!(freezer->state & CGROUP_FREEZING))
 			atomic_inc(&system_freezing_cnt);
-		freezer->state = CGROUP_FREEZING;
-		retval = try_to_freeze_cgroup(cgroup, freezer);
-		break;
-	default:
-		BUG();
+		freezer->state |= state;
+		freeze_cgroup(freezer);
+	} else {
+		bool was_freezing = freezer->state & CGROUP_FREEZING;
+
+		freezer->state &= ~state;
+
+		if (!(freezer->state & CGROUP_FREEZING)) {
+			if (was_freezing)
+				atomic_dec(&system_freezing_cnt);
+			freezer->state &= ~CGROUP_FROZEN;
+			unfreeze_cgroup(freezer);
+		}
 	}
+}
 
+/**
+ * freezer_change_state - change the freezing state of a cgroup_freezer
+ * @freezer: freezer of interest
+ * @freeze: whether to freeze or thaw
+ *
+ * Freeze or thaw @freezer according to @freeze.  The operations are
+ * recursive - all descendants of @freezer will be affected.
+ */
+static void freezer_change_state(struct freezer *freezer, bool freeze)
+{
+	struct cgroup *pos;
+
+	/* update @freezer */
+	spin_lock_irq(&freezer->lock);
+	freezer_apply_state(freezer, freeze, CGROUP_FREEZING_SELF);
 	spin_unlock_irq(&freezer->lock);
 
-	return retval;
+	/*
+	 * Update all its descendants in pre-order traversal.  Each
+	 * descendant will try to inherit its parent's FREEZING state as
+	 * CGROUP_FREEZING_PARENT.
+	 */
+	rcu_read_lock();
+	cgroup_for_each_descendant_pre(pos, freezer->css.cgroup) {
+		struct freezer *pos_f = cgroup_freezer(pos);
+		struct freezer *parent = parent_freezer(pos_f);
+
+		/*
+		 * Our update to @parent->state is already visible which is
+		 * all we need.  No need to lock @parent.  For more info on
+		 * synchronization, see freezer_post_create().
+		 */
+		spin_lock_irq(&pos_f->lock);
+		freezer_apply_state(pos_f, parent->state & CGROUP_FREEZING,
+				    CGROUP_FREEZING_PARENT);
+		spin_unlock_irq(&pos_f->lock);
+	}
+	rcu_read_unlock();
 }
 
-static int freezer_write(struct cgroup *cgroup,
-			 struct cftype *cft,
+static int freezer_write(struct cgroup *cgroup, struct cftype *cft,
 			 const char *buffer)
 {
-	int retval;
-	enum freezer_state goal_state;
+	bool freeze;
 
-	if (strcmp(buffer, freezer_state_strs[CGROUP_THAWED]) == 0)
-		goal_state = CGROUP_THAWED;
-	else if (strcmp(buffer, freezer_state_strs[CGROUP_FROZEN]) == 0)
-		goal_state = CGROUP_FROZEN;
+	if (strcmp(buffer, freezer_state_strs(0)) == 0)
+		freeze = false;
+	else if (strcmp(buffer, freezer_state_strs(CGROUP_FROZEN)) == 0)
+		freeze = true;
 	else
 		return -EINVAL;
 
-	if (!cgroup_lock_live_group(cgroup))
-		return -ENODEV;
-	retval = freezer_change_state(cgroup, goal_state);
-	cgroup_unlock();
-	return retval;
+	freezer_change_state(cgroup_freezer(cgroup), freeze);
+	return 0;
+}
+
+static u64 freezer_self_freezing_read(struct cgroup *cgroup, struct cftype *cft)
+{
+	struct freezer *freezer = cgroup_freezer(cgroup);
+
+	return (bool)(freezer->state & CGROUP_FREEZING_SELF);
+}
+
+static u64 freezer_parent_freezing_read(struct cgroup *cgroup, struct cftype *cft)
+{
+	struct freezer *freezer = cgroup_freezer(cgroup);
+
+	return (bool)(freezer->state & CGROUP_FREEZING_PARENT);
 }
 
 static struct cftype files[] = {
@@ -362,23 +462,27 @@ static struct cftype files[] = {
 		.read_seq_string = freezer_read,
 		.write_string = freezer_write,
 	},
+	{
+		.name = "self_freezing",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = freezer_self_freezing_read,
+	},
+	{
+		.name = "parent_freezing",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = freezer_parent_freezing_read,
+	},
 	{ }	/* terminate */
 };
 
 struct cgroup_subsys freezer_subsys = {
 	.name		= "freezer",
-	.create		= freezer_create,
-	.destroy	= freezer_destroy,
+	.css_alloc	= freezer_css_alloc,
+	.css_online	= freezer_css_online,
+	.css_offline	= freezer_css_offline,
+	.css_free	= freezer_css_free,
 	.subsys_id	= freezer_subsys_id,
-	.can_attach	= freezer_can_attach,
+	.attach		= freezer_attach,
 	.fork		= freezer_fork,
 	.base_cftypes	= files,
-
-	/*
-	 * freezer subsys doesn't handle hierarchy at all.  Frozen state
-	 * should be inherited through the hierarchy - if a parent is
-	 * frozen, all its children should be frozen.  Fix it and remove
-	 * the following.
-	 */
-	.broken_hierarchy = true,
 };
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index f33c7153b6d..b017887d632 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1784,56 +1784,20 @@ static struct cftype files[] = {
 };
 
 /*
- * post_clone() is called during cgroup_create() when the
- * clone_children mount argument was specified.  The cgroup
- * can not yet have any tasks.
- *
- * Currently we refuse to set up the cgroup - thereby
- * refusing the task to be entered, and as a result refusing
- * the sys_unshare() or clone() which initiated it - if any
- * sibling cpusets have exclusive cpus or mem.
- *
- * If this becomes a problem for some users who wish to
- * allow that scenario, then cpuset_post_clone() could be
- * changed to grant parent->cpus_allowed-sibling_cpus_exclusive
- * (and likewise for mems) to the new cgroup. Called with cgroup_mutex
- * held.
- */
-static void cpuset_post_clone(struct cgroup *cgroup)
-{
-	struct cgroup *parent, *child;
-	struct cpuset *cs, *parent_cs;
-
-	parent = cgroup->parent;
-	list_for_each_entry(child, &parent->children, sibling) {
-		cs = cgroup_cs(child);
-		if (is_mem_exclusive(cs) || is_cpu_exclusive(cs))
-			return;
-	}
-	cs = cgroup_cs(cgroup);
-	parent_cs = cgroup_cs(parent);
-
-	mutex_lock(&callback_mutex);
-	cs->mems_allowed = parent_cs->mems_allowed;
-	cpumask_copy(cs->cpus_allowed, parent_cs->cpus_allowed);
-	mutex_unlock(&callback_mutex);
-	return;
-}
-
-/*
- *	cpuset_create - create a cpuset
+ *	cpuset_css_alloc - allocate a cpuset css
  *	cont:	control group that the new cpuset will be part of
  */
 
-static struct cgroup_subsys_state *cpuset_create(struct cgroup *cont)
+static struct cgroup_subsys_state *cpuset_css_alloc(struct cgroup *cont)
 {
-	struct cpuset *cs;
-	struct cpuset *parent;
+	struct cgroup *parent_cg = cont->parent;
+	struct cgroup *tmp_cg;
+	struct cpuset *parent, *cs;
 
-	if (!cont->parent) {
+	if (!parent_cg)
 		return &top_cpuset.css;
-	}
-	parent = cgroup_cs(cont->parent);
+	parent = cgroup_cs(parent_cg);
+
 	cs = kmalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
@@ -1855,7 +1819,36 @@ static struct cgroup_subsys_state *cpuset_create(struct cgroup *cont)
 
 	cs->parent = parent;
 	number_of_cpusets++;
-	return &cs->css ;
+
+	if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &cont->flags))
+		goto skip_clone;
+
+	/*
+	 * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is
+	 * set.  This flag handling is implemented in cgroup core for
+	 * histrical reasons - the flag may be specified during mount.
+	 *
+	 * Currently, if any sibling cpusets have exclusive cpus or mem, we
+	 * refuse to clone the configuration - thereby refusing the task to
+	 * be entered, and as a result refusing the sys_unshare() or
+	 * clone() which initiated it.  If this becomes a problem for some
+	 * users who wish to allow that scenario, then this could be
+	 * changed to grant parent->cpus_allowed-sibling_cpus_exclusive
+	 * (and likewise for mems) to the new cgroup.
+	 */
+	list_for_each_entry(tmp_cg, &parent_cg->children, sibling) {
+		struct cpuset *tmp_cs = cgroup_cs(tmp_cg);
+
+		if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs))
+			goto skip_clone;
+	}
+
+	mutex_lock(&callback_mutex);
+	cs->mems_allowed = parent->mems_allowed;
+	cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
+	mutex_unlock(&callback_mutex);
+skip_clone:
+	return &cs->css;
 }
 
 /*
@@ -1864,7 +1857,7 @@ static struct cgroup_subsys_state *cpuset_create(struct cgroup *cont)
  * will call async_rebuild_sched_domains().
  */
 
-static void cpuset_destroy(struct cgroup *cont)
+static void cpuset_css_free(struct cgroup *cont)
 {
 	struct cpuset *cs = cgroup_cs(cont);
 
@@ -1878,11 +1871,10 @@ static void cpuset_destroy(struct cgroup *cont)
 
 struct cgroup_subsys cpuset_subsys = {
 	.name = "cpuset",
-	.create = cpuset_create,
-	.destroy = cpuset_destroy,
+	.css_alloc = cpuset_css_alloc,
+	.css_free = cpuset_css_free,
 	.can_attach = cpuset_can_attach,
 	.attach = cpuset_attach,
-	.post_clone = cpuset_post_clone,
 	.subsys_id = cpuset_subsys_id,
 	.base_cftypes = files,
 	.early_init = 1,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dbccf83c134..f9ff5493171 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7434,7 +7434,7 @@ unlock:
 device_initcall(perf_event_sysfs_init);
 
 #ifdef CONFIG_CGROUP_PERF
-static struct cgroup_subsys_state *perf_cgroup_create(struct cgroup *cont)
+static struct cgroup_subsys_state *perf_cgroup_css_alloc(struct cgroup *cont)
 {
 	struct perf_cgroup *jc;
 
@@ -7451,7 +7451,7 @@ static struct cgroup_subsys_state *perf_cgroup_create(struct cgroup *cont)
 	return &jc->css;
 }
 
-static void perf_cgroup_destroy(struct cgroup *cont)
+static void perf_cgroup_css_free(struct cgroup *cont)
 {
 	struct perf_cgroup *jc;
 	jc = container_of(cgroup_subsys_state(cont, perf_subsys_id),
@@ -7492,8 +7492,8 @@ static void perf_cgroup_exit(struct cgroup *cgrp, struct cgroup *old_cgrp,
 struct cgroup_subsys perf_subsys = {
 	.name		= "perf_event",
 	.subsys_id	= perf_subsys_id,
-	.create		= perf_cgroup_create,
-	.destroy	= perf_cgroup_destroy,
+	.css_alloc	= perf_cgroup_css_alloc,
+	.css_free	= perf_cgroup_css_free,
 	.exit		= perf_cgroup_exit,
 	.attach		= perf_cgroup_attach,
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 850dde1e0c8..79de9f99a48 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1137,7 +1137,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 {
 	int retval;
 	struct task_struct *p;
-	int cgroup_callbacks_done = 0;
 
 	if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
 		return ERR_PTR(-EINVAL);
@@ -1395,12 +1394,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
-	/* Now that the task is set up, run cgroup callbacks if
-	 * necessary. We need to run them before the task is visible
-	 * on the tasklist. */
-	cgroup_fork_callbacks(p);
-	cgroup_callbacks_done = 1;
-
 	/* Need tasklist lock for parent etc handling! */
 	write_lock_irq(&tasklist_lock);
 
@@ -1505,7 +1498,7 @@ bad_fork_cleanup_cgroup:
 #endif
 	if (clone_flags & CLONE_THREAD)
 		threadgroup_change_end(current);
-	cgroup_exit(p, cgroup_callbacks_done);
+	cgroup_exit(p, 0);
 	delayacct_tsk_free(p);
 	module_put(task_thread_info(p)->exec_domain->module);
 bad_fork_cleanup_count:
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 11f82a4d4ea..c38893b0efb 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -116,17 +116,10 @@ bool freeze_task(struct task_struct *p)
 		return false;
 	}
 
-	if (!(p->flags & PF_KTHREAD)) {
+	if (!(p->flags & PF_KTHREAD))
 		fake_signal_wake_up(p);
-		/*
-		 * fake_signal_wake_up() goes through p's scheduler
-		 * lock and guarantees that TASK_STOPPED/TRACED ->
-		 * TASK_RUNNING transition can't race with task state
-		 * testing in try_to_freeze_tasks().
-		 */
-	} else {
+	else
 		wake_up_state(p, TASK_INTERRUPTIBLE);
-	}
 
 	spin_unlock_irqrestore(&freezer_lock, flags);
 	return true;
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 87da817f9e1..d5a258b60c6 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -48,18 +48,7 @@ static int try_to_freeze_tasks(bool user_only)
 			if (p == current || !freeze_task(p))
 				continue;
 
-			/*
-			 * Now that we've done set_freeze_flag, don't
-			 * perturb a task in TASK_STOPPED or TASK_TRACED.
-			 * It is "frozen enough".  If the task does wake
-			 * up, it will immediately call try_to_freeze.
-			 *
-			 * Because freeze_task() goes through p's scheduler lock, it's
-			 * guaranteed that TASK_STOPPED/TRACED -> TASK_RUNNING
-			 * transition can't race with task state testing here.
-			 */
-			if (!task_is_stopped_or_traced(p) &&
-			    !freezer_should_skip(p))
+			if (!freezer_should_skip(p))
 				todo++;
 		} while_each_thread(g, p);
 		read_unlock(&tasklist_lock);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f5066a61f97..6271b89f87a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7484,7 +7484,7 @@ static inline struct task_group *cgroup_tg(struct cgroup *cgrp)
 			    struct task_group, css);
 }
 
-static struct cgroup_subsys_state *cpu_cgroup_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cpu_cgroup_css_alloc(struct cgroup *cgrp)
 {
 	struct task_group *tg, *parent;
 
@@ -7501,7 +7501,7 @@ static struct cgroup_subsys_state *cpu_cgroup_create(struct cgroup *cgrp)
 	return &tg->css;
 }
 
-static void cpu_cgroup_destroy(struct cgroup *cgrp)
+static void cpu_cgroup_css_free(struct cgroup *cgrp)
 {
 	struct task_group *tg = cgroup_tg(cgrp);
 
@@ -7861,8 +7861,8 @@ static struct cftype cpu_files[] = {
 
 struct cgroup_subsys cpu_cgroup_subsys = {
 	.name		= "cpu",
-	.create		= cpu_cgroup_create,
-	.destroy	= cpu_cgroup_destroy,
+	.css_alloc	= cpu_cgroup_css_alloc,
+	.css_free	= cpu_cgroup_css_free,
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
 	.exit		= cpu_cgroup_exit,
@@ -7885,7 +7885,7 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 struct cpuacct root_cpuacct;
 
 /* create a new cpu accounting group */
-static struct cgroup_subsys_state *cpuacct_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp)
 {
 	struct cpuacct *ca;
 
@@ -7915,7 +7915,7 @@ out:
 }
 
 /* destroy an existing cpu accounting group */
-static void cpuacct_destroy(struct cgroup *cgrp)
+static void cpuacct_css_free(struct cgroup *cgrp)
 {
 	struct cpuacct *ca = cgroup_ca(cgrp);
 
@@ -8086,8 +8086,8 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 
 struct cgroup_subsys cpuacct_subsys = {
 	.name = "cpuacct",
-	.create = cpuacct_create,
-	.destroy = cpuacct_destroy,
+	.css_alloc = cpuacct_css_alloc,
+	.css_free = cpuacct_css_free,
 	.subsys_id = cpuacct_subsys_id,
 	.base_cftypes = files,
 };
diff --git a/kernel/signal.c b/kernel/signal.c
index 0af8868525d..5ffb5626e07 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1908,7 +1908,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 		preempt_disable();
 		read_unlock(&tasklist_lock);
 		preempt_enable_no_resched();
-		schedule();
+		freezable_schedule();
 	} else {
 		/*
 		 * By the time we got the lock, our tracer went away.
@@ -1930,13 +1930,6 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 	}
 
 	/*
-	 * While in TASK_TRACED, we were considered "frozen enough".
-	 * Now that we woke up, it's crucial if we're supposed to be
-	 * frozen that we freeze now before running anything substantial.
-	 */
-	try_to_freeze();
-
-	/*
 	 * We are back.  Now reacquire the siglock before touching
 	 * last_siginfo, so that we are sure to have synchronized with
 	 * any signal-sending on another CPU that wants to examine it.
@@ -2092,7 +2085,7 @@ static bool do_signal_stop(int signr)
 		}
 
 		/* Now we don't run again until woken by SIGCONT or SIGKILL */
-		schedule();
+		freezable_schedule();
 		return true;
 	} else {
 		/*
@@ -2200,15 +2193,14 @@ int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka,
 	if (unlikely(uprobe_deny_signal()))
 		return 0;
 
-relock:
 	/*
-	 * We'll jump back here after any time we were stopped in TASK_STOPPED.
-	 * While in TASK_STOPPED, we were considered "frozen enough".
-	 * Now that we woke up, it's crucial if we're supposed to be
-	 * frozen that we freeze now before running anything substantial.
+	 * Do this once, we can't return to user-mode if freezing() == T.
+	 * do_signal_stop() and ptrace_stop() do freezable_schedule() and
+	 * thus do not need another check after return.
 	 */
 	try_to_freeze();
 
+relock:
 	spin_lock_irq(&sighand->siglock);
 	/*
 	 * Every stopped thread goes here after wakeup. Check to see if