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 f24f724620dd..f34c41bfaa37 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 kern