Merge branch 'for-3.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:
 "cgroup file type addition / removal is updated so that file types are
  added and removed instead of individual files so that dynamic file
  type addition / removal can be implemented by cgroup and used by
  controllers.  blkio controller changes which will come through block
  tree are dependent on this.  Other changes include res_counter cleanup
  and disallowing kthread / PF_THREAD_BOUND threads to be attached to
  non-root cgroups.

  There's a reported bug with the file type addition / removal handling
  which can lead to oops on cgroup umount.  The issue is being looked
  into.  It shouldn't cause problems for most setups and isn't a
  security concern."

Fix up trivial conflict in Documentation/feature-removal-schedule.txt

* 'for-3.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (21 commits)
  res_counter: Account max_usage when calling res_counter_charge_nofail()
  res_counter: Merge res_counter_charge and res_counter_charge_nofail
  cgroups: disallow attaching kthreadd or PF_THREAD_BOUND threads
  cgroup: remove cgroup_subsys->populate()
  cgroup: get rid of populate for memcg
  cgroup: pass struct mem_cgroup instead of struct cgroup to socket memcg
  cgroup: make css->refcnt clearing on cgroup removal optional
  cgroup: use negative bias on css->refcnt to block css_tryget()
  cgroup: implement cgroup_rm_cftypes()
  cgroup: introduce struct cfent
  cgroup: relocate __d_cgrp() and __d_cft()
  cgroup: remove cgroup_add_file[s]()
  cgroup: convert memcg controller to the new cftype interface
  memcg: always create memsw files if CONFIG_CGROUP_MEM_RES_CTLR_SWAP
  cgroup: convert all non-memcg controllers to the new cftype interface
  cgroup: relocate cftype and cgroup_subsys definitions in controllers
  cgroup: merge cft_release_agent cftype array into the base files array
  cgroup: implement cgroup_add_cftypes() and friends
  cgroup: build list of all cgroups under a given cgroupfs_root
  cgroup: move cgroup_clear_directory() call out of cgroup_populate_dir()
  ...

18 files changed, 687 insertions, 438 deletions

diff --git a/Documentation/cgroups/resource_counter.txt b/Documentation/cgroups/resource_counter.txt
index 95b24d766eab..f3c4ec3626a2 100644
--- a/Documentation/cgroups/resource_counter.txt
+++ b/Documentation/cgroups/resource_counter.txt
@@ -77,11 +77,11 @@ to work with it.
 	where the charging failed.
 
  d. int res_counter_charge_locked
-			(struct res_counter *rc, unsigned long val)
+			(struct res_counter *rc, unsigned long val, bool force)
 
 	The same as res_counter_charge(), but it must not acquire/release the
 	res_counter->lock internally (it must be called with res_counter->lock
-	held).
+	held). The force parameter indicates whether we can bypass the limit.
 
  e. void res_counter_uncharge[_locked]
 			(struct res_counter *rc, unsigned long val)
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index e9abede594e1..1e69a81e99d4 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -556,3 +556,14 @@ Why:	The V4L2_CID_VCENTER, V4L2_CID_HCENTER controls have been deprecated
 	There are newer controls (V4L2_CID_PAN*, V4L2_CID_TILT*) that provide
 	similar	functionality.
 Who:	Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
+
+----------------------------
+
+What:	cgroup option updates via remount
+When:	March 2013
+Why:	Remount currently allows changing bound subsystems and
+	release_agent.  Rebinding is hardly useful as it only works
+	when the hierarchy is empty and release_agent itself should be
+	replaced with conventional fsnotify.
+
+----------------------------
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index ea84a23d5e68..126c341955de 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -28,34 +28,12 @@ static LIST_HEAD(blkio_list);
 struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };
 EXPORT_SYMBOL_GPL(blkio_root_cgroup);
 
-static struct cgroup_subsys_state *blkiocg_create(struct cgroup *);
-static int blkiocg_can_attach(struct cgroup *, struct cgroup_taskset *);
-static void blkiocg_attach(struct cgroup *, struct cgroup_taskset *);
-static void blkiocg_destroy(struct cgroup *);
-static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *);
-
 /* for encoding cft->private value on file */
 #define BLKIOFILE_PRIVATE(x, val)	(((x) << 16) | (val))
 /* What policy owns the file, proportional or throttle */
 #define BLKIOFILE_POLICY(val)		(((val) >> 16) & 0xffff)
 #define BLKIOFILE_ATTR(val)		((val) & 0xffff)
 
-struct cgroup_subsys blkio_subsys = {
-	.name = "blkio",
-	.create = blkiocg_create,
-	.can_attach = blkiocg_can_attach,
-	.attach = blkiocg_attach,
-	.destroy = blkiocg_destroy,
-	.populate = blkiocg_populate,
-#ifdef CONFIG_BLK_CGROUP
-	/* note: blkio_subsys_id is otherwise defined in blk-cgroup.h */
-	.subsys_id = blkio_subsys_id,
-#endif
-	.use_id = 1,
-	.module = THIS_MODULE,
-};
-EXPORT_SYMBOL_GPL(blkio_subsys);
-
 static inline void blkio_policy_insert_node(struct blkio_cgroup *blkcg,
 					    struct blkio_policy_node *pn)
 {
@@ -1537,14 +1515,9 @@ struct cftype blkio_files[] = {
 		.read_map = blkiocg_file_read_map,
 	},
 #endif
+	{ }	/* terminate */
 };
 
-static int blkiocg_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup)
-{
-	return cgroup_add_files(cgroup, subsys, blkio_files,
-				ARRAY_SIZE(blkio_files));
-}
-
 static void blkiocg_destroy(struct cgroup *cgroup)
 {
 	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
@@ -1658,6 +1631,22 @@ static void blkiocg_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 	}
 }
 
+struct cgroup_subsys blkio_subsys = {
+	.name = "blkio",
+	.create = blkiocg_create,
+	.can_attach = blkiocg_can_attach,
+	.attach = blkiocg_attach,
+	.destroy = blkiocg_destroy,
+#ifdef CONFIG_BLK_CGROUP
+	/* note: blkio_subsys_id is otherwise defined in blk-cgroup.h */
+	.subsys_id = blkio_subsys_id,
+#endif
+	.base_cftypes = blkio_files,
+	.use_id = 1,
+	.module = THIS_MODULE,
+};
+EXPORT_SYMBOL_GPL(blkio_subsys);
+
 void blkio_policy_register(struct blkio_policy_type *blkiop)
 {
 	spin_lock(&blkio_list_lock);
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 5a85b3415c1b..d3f5fba2c159 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -16,6 +16,7 @@
 #include <linux/prio_heap.h>
 #include <linux/rwsem.h>
 #include <linux/idr.h>
+#include <linux/workqueue.h>
 
 #ifdef CONFIG_CGROUPS
 
@@ -76,12 +77,16 @@ struct cgroup_subsys_state {
 	unsigned long flags;
 	/* ID for this css, if possible */
 	struct css_id __rcu *id;
+
+	/* Used to put @cgroup->dentry on the last css_put() */
+	struct work_struct dput_work;
 };
 
 /* bits in struct cgroup_subsys_state flags field */
 enum {
 	CSS_ROOT, /* This CSS is the root of the subsystem */
 	CSS_REMOVED, /* This CSS is dead */
+	CSS_CLEAR_CSS_REFS,		/* @ss->__DEPRECATED_clear_css_refs */
 };
 
 /* Caller must verify that the css is not for root cgroup */
@@ -115,16 +120,12 @@ static inline bool css_is_removed(struct cgroup_subsys_state *css)
  * the css has been destroyed.
  */
 
+extern bool __css_tryget(struct cgroup_subsys_state *css);
 static inline bool css_tryget(struct cgroup_subsys_state *css)
 {
 	if (test_bit(CSS_ROOT, &css->flags))
 		return true;
-	while (!atomic_inc_not_zero(&css->refcnt)) {
-		if (test_bit(CSS_REMOVED, &css->flags))
-			return false;
-		cpu_relax();
-	}
-	return true;
+	return __css_tryget(css);
 }
 
 /*
@@ -132,11 +133,11 @@ static inline bool css_tryget(struct cgroup_subsys_state *css)
  * css_get() or css_tryget()
  */
 
-extern void __css_put(struct cgroup_subsys_state *css, int count);
+extern void __css_put(struct cgroup_subsys_state *css);
 static inline void css_put(struct cgroup_subsys_state *css)
 {
 	if (!test_bit(CSS_ROOT, &css->flags))
-		__css_put(css, 1);
+		__css_put(css);
 }
 
 /* bits in struct cgroup flags field */
@@ -175,6 +176,7 @@ struct cgroup {
 	 */
 	struct list_head sibling;	/* my parent's children */
 	struct list_head children;	/* my children */
+	struct list_head files;		/* my files */
 
 	struct cgroup *parent;		/* my parent */
 	struct dentry __rcu *dentry;	/* cgroup fs entry, RCU protected */
@@ -191,6 +193,9 @@ struct cgroup {
 	 */
 	struct list_head css_sets;
 
+	struct list_head allcg_node;	/* cgroupfs_root->allcg_list */
+	struct list_head cft_q_node;	/* used during cftype add/rm */
+
 	/*
 	 * Linked list running through all cgroups that can
 	 * potentially be reaped by the release agent. Protected by
@@ -275,11 +280,17 @@ struct cgroup_map_cb {
  *	- the 'cftype' of the file is file->f_dentry->d_fsdata
  */
 
-#define MAX_CFTYPE_NAME 64
+/* cftype->flags */
+#define CFTYPE_ONLY_ON_ROOT	(1U << 0)	/* only create on root cg */
+#define CFTYPE_NOT_ON_ROOT	(1U << 1)	/* don't create onp root cg */
+
+#define MAX_CFTYPE_NAME		64
+
 struct cftype {
 	/*
 	 * By convention, the name should begin with the name of the
-	 * subsystem, followed by a period
+	 * subsystem, followed by a period.  Zero length string indicates
+	 * end of cftype array.
 	 */
 	char name[MAX_CFTYPE_NAME];
 	int private;
@@ -295,6 +306,9 @@ struct cftype {
 	 */
 	size_t max_write_len;
 
+	/* CFTYPE_* flags */
+	unsigned int flags;
+
 	int (*open)(struct inode *inode, struct file *file);
 	ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft,
 			struct file *file,
@@ -373,6 +387,16 @@ struct cftype {
 			struct eventfd_ctx *eventfd);
 };
 
+/*
+ * cftype_sets describe cftypes belonging to a subsystem and are chained at
+ * cgroup_subsys->cftsets.  Each cftset points to an array of cftypes
+ * terminated by zero length name.
+ */
+struct cftype_set {
+	struct list_head		node;	/* chained at subsys->cftsets */
+	const struct cftype		*cfts;
+};
+
 struct cgroup_scanner {
 	struct cgroup *cg;
 	int (*test_task)(struct task_struct *p, struct cgroup_scanner *scan);
@@ -382,21 +406,8 @@ struct cgroup_scanner {
 	void *data;
 };
 
-/*
- * Add a new file to the given cgroup directory. Should only be
- * called by subsystems from within a populate() method
- */
-int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
-		       const struct cftype *cft);
-
-/*
- * Add a set of new files to the given cgroup directory. Should
- * only be called by subsystems from within a populate() method
- */
-int cgroup_add_files(struct cgroup *cgrp,
-			struct cgroup_subsys *subsys,
-			const struct cftype cft[],
-			int count);
+int cgroup_add_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts);
+int cgroup_rm_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts);
 
 int cgroup_is_removed(const struct cgroup *cgrp);
 
@@ -461,7 +472,6 @@ struct cgroup_subsys {
 	void (*fork)(struct task_struct *task);
 	void (*exit)(struct cgroup *cgrp, struct cgroup *old_cgrp,
 		     struct task_struct *task);
-	int (*populate)(struct cgroup_subsys *ss, struct cgroup *cgrp);
 	void (*post_clone)(struct cgroup *cgrp);
 	void (*bind)(struct cgroup *root);
 
@@ -474,6 +484,18 @@ struct cgroup_subsys {
 	 * (not available in early_init time.)
 	 */
 	bool use_id;
+
+	/*
+	 * If %true, cgroup removal will try to clear css refs by retrying
+	 * ss->pre_destroy() until there's no css ref left.  This behavior
+	 * is strictly for backward compatibility and will be removed as
+	 * soon as the current user (memcg) is updated.
+	 *
+	 * If %false, ss->pre_destroy() can't fail and cgroup removal won't
+	 * wait for css refs to drop to zero before proceeding.
+	 */
+	bool __DEPRECATED_clear_css_refs;
+
 #define MAX_CGROUP_TYPE_NAMELEN 32
 	const char *name;
 
@@ -500,6 +522,13 @@ struct cgroup_subsys {
 	struct idr idr;
 	spinlock_t id_lock;
 
+	/* list of cftype_sets */
+	struct list_head cftsets;
+
+	/* base cftypes, automatically [de]registered with subsys itself */
+	struct cftype *base_cftypes;
+	struct cftype_set base_cftset;
+
 	/* should be defined only by modular subsystems */
 	struct module *module;
 };
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index da81af086eaf..fb201896a8b0 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -116,7 +116,7 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent);
  */
 
 int __must_check res_counter_charge_locked(struct res_counter *counter,
-		unsigned long val);
+					   unsigned long val, bool force);
 int __must_check res_counter_charge(struct res_counter *counter,
 		unsigned long val, struct res_counter **limit_fail_at);
 int __must_check res_counter_charge_nofail(struct res_counter *counter,
diff --git a/include/net/sock.h b/include/net/sock.h
index da931555e000..d89f0582b6b6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -70,16 +70,16 @@
 struct cgroup;
 struct cgroup_subsys;
 #ifdef CONFIG_NET
-int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss);
-void mem_cgroup_sockets_destroy(struct cgroup *cgrp);
+int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss);
+void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg);
 #else
 static inline
-int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss)
+int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
 	return 0;
 }
 static inline
-void mem_cgroup_sockets_destroy(struct cgroup *cgrp)
+void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg)
 {
 }
 #endif
@@ -914,9 +914,9 @@ struct proto {
 	 * This function has to setup any files the protocol want to
 	 * appear in the kmem cgroup filesystem.
 	 */
-	int			(*init_cgroup)(struct cgroup *cgrp,
+	int			(*init_cgroup)(struct mem_cgroup *memcg,
 					       struct cgroup_subsys *ss);
-	void			(*destroy_cgroup)(struct cgroup *cgrp);
+	void			(*destroy_cgroup)(struct mem_cgroup *memcg);
 	struct cg_proto		*(*proto_cgroup)(struct mem_cgroup *memcg);
 #endif
 };
diff --git a/include/net/tcp_memcontrol.h b/include/net/tcp_memcontrol.h
index 48410ff25c9e..7df18bc43a97 100644
--- a/include/net/tcp_memcontrol.h
+++ b/include/net/tcp_memcontrol.h
@@ -12,8 +12,8 @@ struct tcp_memcontrol {
 };
 
 struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg);
-int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss);
-void tcp_destroy_cgroup(struct cgroup *cgrp);
+int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss);
+void tcp_destroy_cgroup(struct mem_cgroup *memcg);
 unsigned long long tcp_max_memory(const struct mem_cgroup *memcg);
 void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx);
 #endif /* _TCP_MEMCG_H */
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index ed64ccac67c9..ad8eae5bb801 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -60,9 +60,13 @@
 #include <linux/eventfd.h>
 #include <linux/poll.h>
 #include <linux/flex_array.h> /* used in cgroup_attach_proc */
+#include <linux/kthread.h>
 
 #include <linux/atomic.h>
 
+/* css deactivation bias, makes css->refcnt negative to deny new trygets */
+#define CSS_DEACT_BIAS		INT_MIN
+
 /*
  * cgroup_mutex is the master lock.  Any modification to cgroup or its
  * hierarchy must be performed while holding it.
@@ -127,6 +131,9 @@ struct cgroupfs_root {
 	/* A list running through the active hierarchies */
 	struct list_head root_list;
 
+	/* All cgroups on this root, cgroup_mutex protected */
+	struct list_head allcg_list;
+
 	/* Hierarchy-specific flags */
 	unsigned long flags;
 
@@ -145,6 +152,15 @@ struct cgroupfs_root {
 static struct cgroupfs_root rootnode;
 
 /*
+ * cgroupfs file entry, pointed to from leaf dentry->d_fsdata.
+ */
+struct cfent {
+	struct list_head		node;
+	struct dentry			*dentry;
+	struct cftype			*type;
+};
+
+/*
  * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when
  * cgroup_subsys->use_id != 0.
  */
@@ -239,6 +255,14 @@ int cgroup_lock_is_held(void)
 
 EXPORT_SYMBOL_GPL(cgroup_lock_is_held);
 
+/* the current nr of refs, always >= 0 whether @css is deactivated or not */
+static int css_refcnt(struct cgroup_subsys_state *css)
+{
+	int v = atomic_read(&css->refcnt);
+
+	return v >= 0 ? v : v - CSS_DEACT_BIAS;
+}
+
 /* convenient tests for these bits */
 inline int cgroup_is_removed(const struct cgroup *cgrp)
 {
@@ -279,6 +303,21 @@ list_for_each_entry(_ss, &_root->subsys_list, sibling)
 #define for_each_active_root(_root) \
 list_for_each_entry(_root, &roots, root_list)
 
+static inline struct cgroup *__d_cgrp(struct dentry *dentry)
+{
+	return dentry->d_fsdata;
+}
+
+static inline struct cfent *__d_cfe(struct dentry *dentry)
+{
+	return dentry->d_fsdata;
+}
+
+static inline struct cftype *__d_cft(struct dentry *dentry)
+{
+	return __d_cfe(dentry)->type;
+}
+
 /* the list of cgroups eligible for automatic release. Protected by
  * release_list_lock */
 static LIST_HEAD(release_list);
@@ -816,12 +855,17 @@ 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) {
-			ret = ss->pre_destroy(cgrp);
-			if (ret)
-				break;
+	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;
 }
@@ -864,6 +908,14 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		BUG_ON(!list_empty(&cgrp->pidlists));
 
 		kfree_rcu(cgrp, rcu_head);
+	} else {
+		struct cfent *cfe = __d_cfe(dentry);
+		struct cgroup *cgrp = dentry->d_parent->d_fsdata;
+
+		WARN_ONCE(!list_empty(&cfe->node) &&
+			  cgrp != &cgrp->root->top_cgroup,
+			  "cfe still linked for %s\n", cfe->type->name);
+		kfree(cfe);
 	}
 	iput(inode);
 }
@@ -882,34 +934,36 @@ static void remove_dir(struct dentry *d)
 	dput(parent);
 }
 
-static void cgroup_clear_directory(struct dentry *dentry)
-{
-	struct list_head *node;
-
-	BUG_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
-	spin_lock(&dentry->d_lock);
-	node = dentry->d_subdirs.next;
-	while (node != &dentry->d_subdirs) {
-		struct dentry *d = list_entry(node, struct dentry, d_u.d_child);
-
-		spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
-		list_del_init(node);
-		if (d->d_inode) {
-			/* This should never be called on a cgroup
-			 * directory with child cgroups */
-			BUG_ON(d->d_inode->i_mode & S_IFDIR);
-			dget_dlock(d);
-			spin_unlock(&d->d_lock);
-			spin_unlock(&dentry->d_lock);
-			d_delete(d);
-			simple_unlink(dentry->d_inode, d);
-			dput(d);
-			spin_lock(&dentry->d_lock);
-		} else
-			spin_unlock(&d->d_lock);
-		node = dentry->d_subdirs.next;
+static int cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
+{
+	struct cfent *cfe;
+
+	lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
+	lockdep_assert_held(&cgroup_mutex);
+
+	list_for_each_entry(cfe, &cgrp->files, node) {
+		struct dentry *d = cfe->dentry;
+
+		if (cft && cfe->type != cft)
+			continue;
+
+		dget(d);
+		d_delete(d);
+		simple_unlink(d->d_inode, d);
+		list_del_init(&cfe->node);
+		dput(d);
+
+		return 0;
 	}
-	spin_unlock(&dentry->d_lock);
+	return -ENOENT;
+}
+
+static void cgroup_clear_directory(struct dentry *dir)
+{
+	struct cgroup *cgrp = __d_cgrp(dir);
+
+	while (!list_empty(&cgrp->files))
+		cgroup_rm_file(cgrp, NULL);
 }
 
 /*
@@ -1294,6 +1348,11 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 	if (ret)
 		goto out_unlock;
 
+	/* See feature-removal-schedule.txt */
+	if (opts.subsys_bits != root->actual_subsys_bits || opts.release_agent)
+		pr_warning("cgroup: option changes via remount are deprecated (pid=%d comm=%s)\n",
+			   task_tgid_nr(current), current->comm);
+
 	/* Don't allow flags or name to change at remount */
 	if (opts.flags != root->flags ||
 	    (opts.name && strcmp(opts.name, root->name))) {
@@ -1308,7 +1367,8 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 		goto out_unlock;
 	}
 
-	/* (re)populate subsystem files */
+	/* clear out any existing files and repopulate subsystem files */
+	cgroup_clear_directory(cgrp->dentry);
 	cgroup_populate_dir(cgrp);
 
 	if (opts.release_agent)
@@ -1333,6 +1393,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 {
 	INIT_LIST_HEAD(&cgrp->sibling);
 	INIT_LIST_HEAD(&cgrp->children);
+	INIT_LIST_HEAD(&cgrp->files);
 	INIT_LIST_HEAD(&cgrp->css_sets);
 	INIT_LIST_HEAD(&cgrp->release_list);
 	INIT_LIST_HEAD(&cgrp->pidlists);
@@ -1344,11 +1405,14 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 static void init_cgroup_root(struct cgroupfs_root *root)
 {
 	struct cgroup *cgrp = &root->top_cgroup;
+
 	INIT_LIST_HEAD(&root->subsys_list);
 	INIT_LIST_HEAD(&root->root_list);
+	INIT_LIST_HEAD(&root->allcg_list);
 	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);
 }
 
@@ -1692,16 +1756,6 @@ static struct file_system_type cgroup_fs_type = {
 
 static struct kobject *cgroup_kobj;
 
-static inline struct cgroup *__d_cgrp(struct dentry *dentry)
-{
-	return dentry->d_fsdata;
-}
-
-static inline struct cftype *__d_cft(struct dentry *dentry)
-{
-	return dentry->d_fsdata;
-}
-
 /**
  * cgroup_path - generate the path of a cgroup
  * @cgrp: the cgroup in question
@@ -2172,6 +2226,18 @@ retry_find_task:
 
 	if (threadgroup)
 		tsk = tsk->group_leader;
+
+	/*
+	 * Workqueue threads may acquire PF_THREAD_BOUND and become
+	 * trapped in a cpuset, or RT worker may be born in a cgroup
+	 * with no rt_runtime allocated.  Just say no.
+	 */
+	if (tsk == kthreadd_task || (tsk->flags & PF_THREAD_BOUND)) {
+		ret = -EINVAL;
+		rcu_read_unlock();
+		goto out_unlock_cgroup;
+	}
+
 	get_task_struct(tsk);
 	rcu_read_unlock();
 
@@ -2603,50 +2669,191 @@ static umode_t cgroup_file_mode(const struct cftype *cft)
 	return mode;
 }
 
-int cgroup_add_file(struct cgroup *cgrp,
-		       struct cgroup_subsys *subsys,
-		       const struct cftype *cft)
+static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
+			   const struct cftype *cft)
 {
 	struct dentry *dir = cgrp->dentry;
+	struct cgroup *parent = __d_cgrp(dir);
 	struct dentry *dentry;
+	struct cfent *cfe;
 	int error;
 	umode_t mode;
-
 	char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };
+
+	/* 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, ".");
 	}
 	strcat(name, cft->name);
+
 	BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex));
+
+	cfe = kzalloc(sizeof(*cfe), GFP_KERNEL);
+	if (!cfe)
+		return -ENOMEM;
+
 	dentry = lookup_one_len(name, dir, strlen(name));
-	if (!IS_ERR(dentry)) {
-		mode = cgroup_file_mode(cft);
-		error = cgroup_create_file(dentry, mode | S_IFREG,
-						cgrp->root->sb);
-		if (!error)
-			dentry->d_fsdata = (void *)cft;
-		dput(dentry);
-	} else
+	if (IS_ERR(dentry)) {
 		error = PTR_ERR(dentry);
+		goto out;
+	}
+
+	mode = cgroup_file_mode(cft);
+	error = cgroup_create_file(dentry, mode | S_IFREG, cgrp->root->sb);
+	if (!error) {
+		cfe->type = (void *)cft;
+		cfe->dentry = dentry;
+		dentry->d_fsdata = cfe;
+		list_add_tail(&cfe->node, &parent->files);
+		cfe = NULL;
+	}
+	dput(dentry);
+out:
+	kfree(cfe);
 	return error;
 }
-EXPORT_SYMBOL_GPL(cgroup_add_file);
 
-int cgroup_add_files(struct cgroup *cgrp,
-			struct cgroup_subsys *subsys,
-			const struct cftype cft[],
-			int count)
+static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys,
+			      const struct cftype cfts[], bool is_add)
 {
-	int i, err;
-	for (i = 0; i < count; i++) {
-		err = cgroup_add_file(cgrp, subsys, &cft[i]);
-		if (err)
-			return err;
+	const struct cftype *cft;
+	int err, ret = 0;
+
+	for (cft = cfts; cft->name[0] != '\0'; cft++) {
+		if (is_add)
+			err = cgroup_add_file(cgrp, subsys, cft);
+		else
+			err = cgroup_rm_file(cgrp, cft);
+		if (err) {
+			pr_warning("cgroup_addrm_files: failed to %s %s, err=%d\n",
+				   is_add ? "add" : "remove", cft->name, err);
+			ret = err;
+		}
+	}
+	return ret;
+}
+
+static DEFINE_MUTEX(cgroup_cft_mutex);
+
+static void cgroup_cfts_prepare(void)
+	__acquires(&cgroup_cft_mutex) __acquires(&cgroup_mutex)
+{
+	/*
+	 * Thanks to the entanglement with vfs inode locking, we can't walk
+	 * the existing cgroups under cgroup_mutex and create files.
+	 * Instead, we increment reference on all cgroups and build list of
+	 * them using @cgrp->cft_q_node.  Grab cgroup_cft_mutex to ensure
+	 * exclusive access to the field.
+	 */
+	mutex_lock(&cgroup_cft_mutex);
+	mutex_lock(&cgroup_mutex);
+}
+
+static void cgroup_cfts_commit(struct cgroup_subsys *ss,
+			       const struct cftype *cfts, bool is_add)
+	__releases(&cgroup_mutex) __releases(&cgroup_cft_mutex)
+{
+	LIST_HEAD(pending);
+	struct cgroup *cgrp, *n;
+
+	/* %NULL @cfts indicates abort and don't bother if @ss isn't attached */
+	if (cfts && ss->root != &rootnode) {
+		list_for_each_entry(cgrp, &ss->root->allcg_list, allcg_node) {
+			dget(cgrp->dentry);
+			list_add_tail(&cgrp->cft_q_node, &pending);
+		}
+	}
+
+	mutex_unlock(&cgroup_mutex);
+
+	/*
+	 * All new cgroups will see @cfts update on @ss->cftsets.  Add/rm
+	 * files for all cgroups which were created before.
+	 */
+	list_for_each_entry_safe(cgrp, n, &pending, cft_q_node) {
+		struct inode *inode = cgrp->dentry->d_inode;
+
+		mutex_lock(&inode->i_mutex);
+		mutex_lock(&cgroup_mutex);
+		if (!cgroup_is_removed(cgrp))
+			cgroup_addrm_files(cgrp, ss, cfts, is_add);
+		mutex_unlock(&cgroup_mutex);
+		mutex_unlock(&inode->i_mutex);
+
+		list_del_init(&cgrp->cft_q_node);
+		dput(cgrp->dentry);
 	}
+
+	mutex_unlock(&cgroup_cft_mutex);
+}
+
+/**
+ * cgroup_add_cftypes - add an array of cftypes to a subsystem
+ * @ss: target cgroup subsystem
+ * @cfts: zero-length name terminated array of cftypes
+ *
+ * Register @cfts to @ss.  Files described by @cfts are created for all
+ * existing cgroups to which @ss is attached and all future cgroups will
+ * have them too.  This function can be called anytime whether @ss is
+ * attached or not.
+ *
+ * Returns 0 on successful registration, -errno on failure.  Note that this
+ * function currently returns 0 as long as @cfts registration is successful
+ * even if some file creation attempts on existing cgroups fail.
+ */
+int cgroup_add_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts)
+{
+	struct cftype_set *set;
+
+	set = kzalloc(sizeof(*set), GFP_KERNEL);
+	if (!set)
+		return -ENOMEM;
+
+	cgroup_cfts_prepare();
+	set->cfts = cfts;
+	list_add_tail(&set->node, &ss->cftsets);
+	cgroup_cfts_commit(ss, cfts, true);
+
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cgroup_add_files);
+EXPORT_SYMBOL_GPL(cgroup_add_cftypes);
+
+/**
+ * cgroup_rm_cftypes - remove an array of cftypes from a subsystem
+ * @ss: target cgroup subsystem
+ * @cfts: zero-length name terminated array of cftypes
+ *
+ * Unregister @cfts from @ss.  Files described by @cfts are removed from
+ * all existing cgroups to which @ss is attached and all future cgroups
+ * won't have them either.  This function can be called anytime whether @ss
+ * is attached or not.
+ *
+ * Returns 0 on successful unregistration, -ENOENT if @cfts is not
+ * registered with @ss.
+ */
+int cgroup_rm_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts)
+{
+	struct cftype_set *set;
+
+	cgroup_cfts_prepare();
+
+	list_for_each_entry(set, &ss->cftsets, node) {
+		if (set->cfts == cfts) {
+			list_del_init(&set->node);
+			cgroup_cfts_commit(ss, cfts, false);
+			return 0;
+		}
+	}
+
+	cgroup_cfts_commit(ss, NULL, false);
+	return -ENOENT;
+}
 
 /**
  * cgroup_task_count - count the number of tasks in a cgroup.
@@ -3625,13 +3832,14 @@ static struct cftype files[] = {
 		.read_u64 = cgroup_clone_children_read,
 		.write_u64 = cgroup_clone_children_write,
 	},
-};
-
-static struct cftype cft_release_agent = {
-	.name = "release_agent",
-	.read_seq_string = cgroup_release_agent_show,
-	.write_string = cgroup_release_agent_write,
-	.max_write_len = PATH_MAX,
+	{
+		.name = "release_agent",
+		.flags = CFTYPE_ONLY_ON_ROOT,
+		.read_seq_string = cgroup_release_agent_show,
+		.write_string = cgroup_release_agent_write,
+		.max_write_len = PATH_MAX,
+	},
+	{ }	/* terminate */
 };
 
 static int cgroup_populate_dir(struct cgroup *cgrp)
@@ -3639,22 +3847,18 @@ static int cgroup_populate_dir(struct cgroup *cgrp)
 	int err;
 	struct cgroup_subsys *ss;
 
-	/* First clear out any existing files */
-	cgroup_clear_directory(cgrp->dentry);
-
-	err = cgroup_add_files(cgrp, NULL, files, ARRAY_SIZE(files));
+	err = cgroup_addrm_files(cgrp, NULL, files, true);
 	if (err < 0)
 		return err;
 
-	if (cgrp == cgrp->top_cgroup) {
-		if ((err = cgroup_add_file(cgrp, NULL, &cft_release_agent)) < 0)
-			return err;
-	}
-
+	/* process cftsets of each subsystem */
 	for_each_subsys(cgrp->root, ss) {
-		if (ss->populate && (err = ss->populate(ss, cgrp)) < 0)
-			return err;
+		struct cftype_set *set;
+
+		list_for_each_entry(set, &ss->cftsets, node)
+			cgroup_addrm_files(cgrp, ss, set->cfts, true);
 	}
+
 	/* This cgroup is ready now */
 	for_each_subsys(cgrp->root, ss) {
 		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
@@ -3670,6 +3874,14 @@ static int cgroup_populate_dir(struct cgroup *cgrp)
 	return 0;
 }
 
+static void css_dput_fn(struct work_struct *work)
+{
+	struct cgroup_subsys_state *css =
+		container_of(work, struct cgroup_subsys_state, dput_work);
+
+	dput(css->cgroup->dentry);
+}
+
 static void init_cgroup_css(struct cgroup_subsys_state *css,
 			       struct cgroup_subsys *ss,
 			       struct cgroup *cgrp)
@@ -3682,6 +3894,16 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 		set_bit(CSS_ROOT, &css->flags);
 	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
+