Merge branch 'for-4.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - threadgroup_lock got reorganized so that its users can pick the
   actual locking mechanism to use.  Its only user - cgroups - is
   updated to use a percpu_rwsem instead of per-process rwsem.

   This makes things a bit lighter on hot paths and allows cgroups to
   perform and fail multi-task (a process) migrations atomically.
   Multi-task migrations are used in several places including the
   unified hierarchy.

 - Delegation rule and documentation added to unified hierarchy.  This
   will likely be the last interface update from the cgroup core side
   for unified hierarchy before lifting the devel mask.

 - Some groundwork for the pids controller which is scheduled to be
   merged in the coming devel cycle.

* 'for-4.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: add delegation section to unified hierarchy documentation
  cgroup: require write perm on common ancestor when moving processes on the default hierarchy
  cgroup: separate out cgroup_procs_write_permission() from __cgroup_procs_write()
  kernfs: make kernfs_get_inode() public
  MAINTAINERS: add a cgroup core co-maintainer
  cgroup: fix uninitialised iterator in for_each_subsys_which
  cgroup: replace explicit ss_mask checking with for_each_subsys_which
  cgroup: use bitmask to filter for_each_subsys
  cgroup: add seq_file forward declaration for struct cftype
  cgroup: simplify threadgroup locking
  sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem
  sched, cgroup: reorganize threadgroup locking
  cgroup: switch to unsigned long for bitmasks
  cgroup: reorganize include/linux/cgroup.h
  cgroup: separate out include/linux/cgroup-defs.h
  cgroup: fix some comment typos
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index e7da0aa..a593e29 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -11,94 +11,200 @@
 #include <linux/sched.h>
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
-#include <linux/rcupdate.h>
 #include <linux/rculist.h>
 #include <linux/cgroupstats.h>
 #include <linux/rwsem.h>
-#include <linux/idr.h>
-#include <linux/workqueue.h>
 #include <linux/fs.h>
-#include <linux/percpu-refcount.h>
 #include <linux/seq_file.h>
 #include <linux/kernfs.h>
-#include <linux/wait.h>
+
+#include <linux/cgroup-defs.h>
 
 #ifdef CONFIG_CGROUPS
 
-struct cgroup_root;
-struct cgroup_subsys;
-struct cgroup;
+/* a css_task_iter should be treated as an opaque object */
+struct css_task_iter {
+	struct cgroup_subsys		*ss;
 
-extern int cgroup_init_early(void);
-extern int cgroup_init(void);
-extern void cgroup_fork(struct task_struct *p);
-extern void cgroup_post_fork(struct task_struct *p);
-extern void cgroup_exit(struct task_struct *p);
-extern int cgroupstats_build(struct cgroupstats *stats,
-				struct dentry *dentry);
+	struct list_head		*cset_pos;
+	struct list_head		*cset_head;
 
-extern int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
-			    struct pid *pid, struct task_struct *tsk);
-
-/* define the enumeration of all cgroup subsystems */
-#define SUBSYS(_x) _x ## _cgrp_id,
-enum cgroup_subsys_id {
-#include <linux/cgroup_subsys.h>
-	CGROUP_SUBSYS_COUNT,
+	struct list_head		*task_pos;
+	struct list_head		*tasks_head;
+	struct list_head		*mg_tasks_head;
 };
+
+extern struct cgroup_root cgrp_dfl_root;
+extern struct css_set init_css_set;
+
+#define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys;
+#include <linux/cgroup_subsys.h>
 #undef SUBSYS
 
+bool css_has_online_children(struct cgroup_subsys_state *css);
+struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss);
+struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup,
+					     struct cgroup_subsys *ss);
+struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
+						       struct cgroup_subsys *ss);
+
+bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor);
+int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
+int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
+
+int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
+int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
+int cgroup_rm_cftypes(struct cftype *cfts);
+
+char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
+int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry);
+int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
+		     struct pid *pid, struct task_struct *tsk);
+
+void cgroup_fork(struct task_struct *p);
+void cgroup_post_fork(struct task_struct *p);
+void cgroup_exit(struct task_struct *p);
+
+int cgroup_init_early(void);
+int cgroup_init(void);
+
 /*
- * Per-subsystem/per-cgroup state maintained by the system.  This is the
- * fundamental structural building block that controllers deal with.
- *
- * Fields marked with "PI:" are public and immutable and may be accessed
- * directly without synchronization.
+ * Iteration helpers and macros.
  */
-struct cgroup_subsys_state {
-	/* PI: the cgroup that this css is attached to */
-	struct cgroup *cgroup;
 
-	/* PI: the cgroup subsystem that this css is attached to */
-	struct cgroup_subsys *ss;
+struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos,
+					   struct cgroup_subsys_state *parent);
+struct cgroup_subsys_state *css_next_descendant_pre(struct cgroup_subsys_state *pos,
+						    struct cgroup_subsys_state *css);
+struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state *pos);
+struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos,
+						     struct cgroup_subsys_state *css);
 
-	/* reference count - access via css_[try]get() and css_put() */
-	struct percpu_ref refcnt;
+struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset);
+struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset);
 
-	/* PI: the parent css */
-	struct cgroup_subsys_state *parent;
+void css_task_iter_start(struct cgroup_subsys_state *css,
+			 struct css_task_iter *it);
+struct task_struct *css_task_iter_next(struct css_task_iter *it);
+void css_task_iter_end(struct css_task_iter *it);
 
-	/* siblings list anchored at the parent's ->children */
-	struct list_head sibling;
-	struct list_head children;
+/**
+ * css_for_each_child - iterate through children of a css
+ * @pos: the css * to use as the loop cursor
+ * @parent: css whose children to walk
+ *
+ * Walk @parent's children.  Must be called under rcu_read_lock().
+ *
+ * If a subsystem synchronizes ->css_online() and the start of iteration, a
+ * css which finished ->css_online() is guaranteed to be visible in the
+ * future iterations and will stay visible until the last reference is put.
+ * A css which hasn't finished ->css_online() or already finished
+ * ->css_offline() may show up during traversal.  It's each subsystem's
+ * responsibility to synchronize against on/offlining.
+ *
+ * It is allowed to temporarily drop RCU read lock during iteration.  The
+ * caller is responsible for ensuring that @pos remains accessible until
+ * the start of the next iteration by, for example, bumping the css refcnt.
+ */
+#define css_for_each_child(pos, parent)					\
+	for ((pos) = css_next_child(NULL, (parent)); (pos);		\
+	     (pos) = css_next_child((pos), (parent)))
 
-	/*
-	 * PI: Subsys-unique ID.  0 is unused and root is always 1.  The
-	 * matching css can be looked up using css_from_id().
-	 */
-	int id;
+/**
+ * css_for_each_descendant_pre - pre-order walk of a css's descendants
+ * @pos: the css * to use as the loop cursor
+ * @root: css whose descendants to walk
+ *
+ * Walk @root's descendants.  @root is included in the iteration and the
+ * first node to be visited.  Must be called under rcu_read_lock().
+ *
+ * If a subsystem synchronizes ->css_online() and the start of iteration, a
+ * css which finished ->css_online() is guaranteed to be visible in the
+ * future iterations and will stay visible until the last reference is put.
+ * A css which hasn't finished ->css_online() or already finished
+ * ->css_offline() may show up during traversal.  It's each subsystem's
+ * responsibility to synchronize against on/offlining.
+ *
+ * For example, the following guarantees that a descendant can't escape
+ * state updates of its ancestors.
+ *
+ * my_online(@css)
+ * {
+ *	Lock @css's parent and @css;
+ *	Inherit state from the parent;
+ *	Unlock both.
+ * }
+ *
+ * my_update_state(@css)
+ * {
+ *	css_for_each_descendant_pre(@pos, @css) {
+ *		Lock @pos;
+ *		if (@pos == @css)
+ *			Update @css's state;
+ *		else
+ *			Verify @pos is alive and inherit state from its parent;
+ *		Unlock @pos;
+ *	}
+ * }
+ *
+ * As long as the inheriting step, including checking the parent state, is
+ * enclosed inside @pos locking, double-locking the parent isn't necessary
+ * while inheriting.  The state update to the parent is guaranteed to be
+ * visible by walking order and, as long as inheriting operations to the
+ * same @pos are atomic to each other, multiple updates racing each other
+ * still result in the correct state.  It's guaranateed that at least one
+ * inheritance happens for any css after the latest update to its parent.
+ *
+ * If checking parent's state requires locking the parent, each inheriting
+ * iteration should lock and unlock both @pos->parent and @pos.
+ *
+ * Alternatively, a subsystem may choose to use a single global lock to
+ * synchronize ->css_online() and ->css_offline() against tree-walking
+ * operations.
+ *
+ * It is allowed to temporarily drop RCU read lock during iteration.  The
+ * caller is responsible for ensuring that @pos remains accessible until
+ * the start of the next iteration by, for example, bumping the css refcnt.
+ */
+#define css_for_each_descendant_pre(pos, css)				\
+	for ((pos) = css_next_descendant_pre(NULL, (css)); (pos);	\
+	     (pos) = css_next_descendant_pre((pos), (css)))
 
-	unsigned int flags;
+/**
+ * css_for_each_descendant_post - post-order walk of a css's descendants
+ * @pos: the css * to use as the loop cursor
+ * @css: css whose descendants to walk
+ *
+ * Similar to css_for_each_descendant_pre() but performs post-order
+ * traversal instead.  @root is included in the iteration and the last
+ * node to be visited.
+ *
+ * If a subsystem synchronizes ->css_online() and the start of iteration, a
+ * css which finished ->css_online() is guaranteed to be visible in the
+ * future iterations and will stay visible until the last reference is put.
+ * A css which hasn't finished ->css_online() or already finished
+ * ->css_offline() may show up during traversal.  It's each subsystem's
+ * responsibility to synchronize against on/offlining.
+ *
+ * Note that the walk visibility guarantee example described in pre-order
+ * walk doesn't apply the same to post-order walks.
+ */
+#define css_for_each_descendant_post(pos, css)				\
+	for ((pos) = css_next_descendant_post(NULL, (css)); (pos);	\
+	     (pos) = css_next_descendant_post((pos), (css)))
 
-	/*
-	 * Monotonically increasing unique serial number which defines a
-	 * uniform order among all csses.  It's guaranteed that all
-	 * ->children lists are in the ascending order of ->serial_nr and
-	 * used to allow interrupting and resuming iterations.
-	 */
-	u64 serial_nr;
+/**
+ * cgroup_taskset_for_each - iterate cgroup_taskset
+ * @task: the loop cursor
+ * @tset: taskset to iterate
+ */
+#define cgroup_taskset_for_each(task, tset)				\
+	for ((task) = cgroup_taskset_first((tset)); (task);		\
+	     (task) = cgroup_taskset_next((tset)))
 
-	/* percpu_ref killing and RCU release */
-	struct rcu_head rcu_head;
-	struct work_struct destroy_work;
-};
-
-/* bits in struct cgroup_subsys_state flags field */
-enum {
-	CSS_NO_REF	= (1 << 0), /* no reference counting for this css */
-	CSS_ONLINE	= (1 << 1), /* between ->css_online() and ->css_offline() */
-	CSS_RELEASED	= (1 << 2), /* refcnt reached zero, released */
-};
+/*
+ * Inline functions.
+ */
 
 /**
  * css_get - obtain a reference on the specified css
@@ -185,309 +291,112 @@
 		percpu_ref_put_many(&css->refcnt, n);
 }
 
-/* bits in struct cgroup flags field */
-enum {
-	/* Control Group requires release notifications to userspace */
-	CGRP_NOTIFY_ON_RELEASE,
-	/*
-	 * Clone the parent's configuration when creating a new child
-	 * cpuset cgroup.  For historical reasons, this option can be
-	 * specified at mount time and thus is implemented here.
-	 */
-	CGRP_CPUSET_CLONE_CHILDREN,
-};
-
-struct cgroup {
-	/* self css with NULL ->ss, points back to this cgroup */
-	struct cgroup_subsys_state self;
-
-	unsigned long flags;		/* "unsigned long" so bitops work */
-
-	/*
-	 * idr allocated in-hierarchy ID.
-	 *
-	 * ID 0 is not used, the ID of the root cgroup is always 1, and a
-	 * new cgroup will be assigned with a smallest available ID.
-	 *
-	 * Allocating/Removing ID must be protected by cgroup_mutex.
-	 */
-	int id;
-
-	/*
-	 * If this cgroup contains any tasks, it contributes one to
-	 * populated_cnt.  All children with non-zero popuplated_cnt of
-	 * their own contribute one.  The count is zero iff there's no task
-	 * in this cgroup or its subtree.
-	 */
-	int populated_cnt;
-
-	struct kernfs_node *kn;		/* cgroup kernfs entry */
-	struct kernfs_node *populated_kn; /* kn for "cgroup.subtree_populated" */
-
-	/*
-	 * The bitmask of subsystems enabled on the child cgroups.
-	 * ->subtree_control is the one configured through
-	 * "cgroup.subtree_control" while ->child_subsys_mask is the
-	 * effective one which may have more subsystems enabled.
-	 * Controller knobs are made available iff it's enabled in
-	 * ->subtree_control.
-	 */
-	unsigned int subtree_control;
-	unsigned int child_subsys_mask;
-
-	/* Private pointers for each registered subsystem */
-	struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT];
-
-	struct cgroup_root *root;
-
-	/*
-	 * List of cgrp_cset_links pointing at css_sets with tasks in this
-	 * cgroup.  Protected by css_set_lock.
-	 */
-	struct list_head cset_links;
-
-	/*
-	 * On the default hierarchy, a css_set for a cgroup with some
-	 * susbsys disabled will point to css's which are associated with
-	 * the closest ancestor which has the subsys enabled.  The
-	 * following lists all css_sets which point to this cgroup's css
-	 * for the given subsystem.
-	 */
-	struct list_head e_csets[CGROUP_SUBSYS_COUNT];
-
-	/*
-	 * list of pidlists, up to two for each namespace (one for procs, one
-	 * for tasks); created on demand.
-	 */
-	struct list_head pidlists;
-	struct mutex pidlist_mutex;
-
-	/* used to wait for offlining of csses */
-	wait_queue_head_t offline_waitq;
-
-	/* used to schedule release agent */
-	struct work_struct release_agent_work;
-};
-
-#define MAX_CGROUP_ROOT_NAMELEN 64
-
-/* cgroup_root->flags */
-enum {
-	CGRP_ROOT_SANE_BEHAVIOR	= (1 << 0), /* __DEVEL__sane_behavior specified */
-	CGRP_ROOT_NOPREFIX	= (1 << 1), /* mounted subsystems have no named prefix */
-	CGRP_ROOT_XATTR		= (1 << 2), /* supports extended attributes */
-};
-
-/*
- * A cgroup_root represents the root of a cgroup hierarchy, and may be
- * associated with a kernfs_root to form an active hierarchy.  This is
- * internal to cgroup core.  Don't access directly from controllers.
- */
-struct cgroup_root {
-	struct kernfs_root *kf_root;
-
-	/* The bitmask of subsystems attached to this hierarchy */
-	unsigned int subsys_mask;
-
-	/* Unique id for this hierarchy. */
-	int hierarchy_id;
-
-	/* The root cgroup.  Root is destroyed on its release. */
-	struct cgroup cgrp;
-
-	/* Number of cgroups in the hierarchy, used only for /proc/cgroups */
-	atomic_t nr_cgrps;
-
-	/* A list running through the active hierarchies */
-	struct list_head root_list;
-
-	/* Hierarchy-specific flags */
-	unsigned int flags;
-
-	/* IDs for cgroups in this hierarchy */
-	struct idr cgroup_idr;
-
-	/* The path to use for release notifications. */
-	char release_agent_path[PATH_MAX];
-
-	/* The name for this hierarchy - may be empty */
-	char name[MAX_CGROUP_ROOT_NAMELEN];
-};
-
-/*
- * A css_set is a structure holding pointers to a set of
- * cgroup_subsys_state objects. This saves space in the task struct
- * object and speeds up fork()/exit(), since a single inc/dec and a
- * list_add()/del() can bump the reference count on the entire cgroup
- * set for a task.
- */
-
-struct css_set {
-
-	/* Reference count */
-	atomic_t refcount;
-
-	/*
-	 * List running through all cgroup groups in the same hash
-	 * slot. Protected by css_set_lock
-	 */
-	struct hlist_node hlist;
-
-	/*
-	 * Lists running through all tasks using this cgroup group.
-	 * mg_tasks lists tasks which belong to this cset but are in the
-	 * process of being migrated out or in.  Protected by
-	 * css_set_rwsem, but, during migration, once tasks are moved to
-	 * mg_tasks, it can be read safely while holding cgroup_mutex.
-	 */
-	struct list_head tasks;
-	struct list_head mg_tasks;
-
-	/*
-	 * List of cgrp_cset_links pointing at cgroups referenced from this
-	 * css_set.  Protected by css_set_lock.
-	 */
-	struct list_head cgrp_links;
-
-	/* the default cgroup associated with this css_set */
-	struct cgroup *dfl_cgrp;
-
-	/*
-	 * Set of subsystem states, one for each subsystem. This array is
-	 * immutable after creation apart from the init_css_set during
-	 * subsystem registration (at boot time).
-	 */
-	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
-
-	/*
-	 * List of csets participating in the on-going migration either as
-	 * source or destination.  Protected by cgroup_mutex.
-	 */
-	struct list_head mg_preload_node;
-	struct list_head mg_node;
-
-	/*
-	 * If this cset is acting as the source of migration the following
-	 * two fields are set.  mg_src_cgrp is the source cgroup of the
-	 * on-going migration and mg_dst_cset is the destination cset the
-	 * target tasks on this cset should be migrated to.  Protected by
-	 * cgroup_mutex.
-	 */
-	struct cgroup *mg_src_cgrp;
-	struct css_set *mg_dst_cset;
-
-	/*
-	 * On the default hierarhcy, ->subsys[ssid] may point to a css
-	 * attached to an ancestor instead of the cgroup this css_set is
-	 * associated with.  The following node is anchored at
-	 * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to
-	 * iterate through all css's attached to a given cgroup.
-	 */
-	struct list_head e_cset_node[CGROUP_SUBSYS_COUNT];
-
-	/* For RCU-protected deletion */
-	struct rcu_head rcu_head;
-};
-
-/*
- * struct cftype: handler definitions for cgroup control files
+/**
+ * task_css_set_check - obtain a task's css_set with extra access conditions
+ * @task: the task to obtain css_set for
+ * @__c: extra condition expression to be passed to rcu_dereference_check()
  *
- * When reading/writing to a file:
- *	- the cgroup to use is file->f_path.dentry->d_parent->d_fsdata
- *	- the 'cftype' of the file is file->f_path.dentry->d_fsdata
+ * A task's css_set is RCU protected, initialized and exited while holding
+ * task_lock(), and can only be modified while holding both cgroup_mutex
+ * and task_lock() while the task is alive.  This macro verifies that the
+ * caller is inside proper critical section and returns @task's css_set.
+ *
+ * The caller can also specify additional allowed conditions via @__c, such
+ * as locks used during the cgroup_subsys::attach() methods.
  */
-
-/* cftype->flags */
-enum {
-	CFTYPE_ONLY_ON_ROOT	= (1 << 0),	/* only create on root cgrp */
-	CFTYPE_NOT_ON_ROOT	= (1 << 1),	/* don't create on root cgrp */
-	CFTYPE_NO_PREFIX	= (1 << 3),	/* (DON'T USE FOR NEW FILES) no subsys prefix */
-
-	/* internal flags, do not use outside cgroup core proper */
-	__CFTYPE_ONLY_ON_DFL	= (1 << 16),	/* only on default hierarchy */
-	__CFTYPE_NOT_ON_DFL	= (1 << 17),	/* not on default hierarchy */
-};
-
-#define MAX_CFTYPE_NAME		64
-
-struct cftype {
-	/*
-	 * By convention, the name should begin with the name of the
-	 * subsystem, followed by a period.  Zero length string indicates
-	 * end of cftype array.
-	 */
-	char name[MAX_CFTYPE_NAME];
-	int private;
-	/*
-	 * If not 0, file mode is set to this value, otherwise it will
-	 * be figured out automatically
-	 */
-	umode_t mode;
-
-	/*
-	 * The maximum length of string, excluding trailing nul, that can
-	 * be passed to write.  If < PAGE_SIZE-1, PAGE_SIZE-1 is assumed.
-	 */
-	size_t max_write_len;
-
-	/* CFTYPE_* flags */
-	unsigned int flags;
-
-	/*
-	 * Fields used for internal bookkeeping.  Initialized automatically
-	 * during registration.
-	 */
-	struct cgroup_subsys *ss;	/* NULL for cgroup core files */
-	struct list_head node;		/* anchored at ss->cfts */
-	struct kernfs_ops *kf_ops;
-
-	/*
-	 * read_u64() is a shortcut for the common case of returning a
-	 * single integer. Use it in place of read()
-	 */
-	u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft);
-	/*
-	 * read_s64() is a signed version of read_u64()
-	 */
-	s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft);
-
-	/* generic seq_file read interface */
-	int (*seq_show)(struct seq_file *sf, void *v);
-
-	/* optional ops, implement all or none */
-	void *(*seq_start)(struct seq_file *sf, loff_t *ppos);
-	void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos);
-	void (*seq_stop)(struct seq_file *sf, void *v);
-
-	/*
-	 * write_u64() is a shortcut for the common case of accepting
-	 * a single integer (as parsed by simple_strtoull) from
-	 * userspace. Use in place of write(); return 0 or error.
-	 */
-	int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft,
-			 u64 val);
-	/*
-	 * write_s64() is a signed version of write_u64()
-	 */
-	int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft,
-			 s64 val);
-
-	/*
-	 * write() is the generic write callback which maps directly to
-	 * kernfs write operation and overrides all other operations.
-	 * Maximum write size is determined by ->max_write_len.  Use
-	 * of_css/cft() to access the associated css and cft.
-	 */
-	ssize_t (*write)(struct kernfs_open_file *of,
-			 char *buf, size_t nbytes, loff_t off);
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lock_class_key	lockdep_key;
+#ifdef CONFIG_PROVE_RCU
+extern struct mutex cgroup_mutex;
+extern struct rw_semaphore css_set_rwsem;
+#define task_css_set_check(task, __c)					\
+	rcu_dereference_check((task)->cgroups,				\
+		lockdep_is_held(&cgroup_mutex) ||			\
+		lockdep_is_held(&css_set_rwsem) ||			\
+		((task)->flags & PF_EXITING) || (__c))
+#else
+#define task_css_set_check(task, __c)					\
+	rcu_dereference((task)->cgroups)
 #endif
-};
 
-extern struct cgroup_root cgrp_dfl_root;
-extern struct css_set init_css_set;
+/**
+ * task_css_check - obtain css for (task, subsys) w/ extra access conds
+ * @task: the target task
+ * @subsys_id: the target subsystem ID
+ * @__c: extra condition expression to be passed to rcu_dereference_check()
+ *
+ * Return the cgroup_subsys_state for the (@task, @subsys_id) pair.  The
+ * synchronization rules are the same as task_css_set_check().
+ */
+#define task_css_check(task, subsys_id, __c)				\
+	task_css_set_check((task), (__c))->subsys[(subsys_id)]
+
+/**
+ * task_css_set - obtain a task's css_set
+ * @task: the task to obtain css_set for
+ *
+ * See task_css_set_check().
+ */
+static inline struct css_set *task_css_set(struct task_struct *task)
+{
+	return task_css_set_check(task, false);
+}
+
+/**
+ * task_css - obtain css for (task, subsys)
+ * @task: the target task
+ * @subsys_id: the target subsystem ID
+ *
+ * See task_css_check().
+ */
+static inline struct cgroup_subsys_state *task_css(struct task_struct *task,
+						   int subsys_id)
+{
+	return task_css_check(task, subsys_id, false);
+}
+
+/**
+ * task_get_css - find and get the css for (task, subsys)
+ * @task: the target task
+ * @subsys_id: the target subsystem ID
+ *
+ * Find the css for the (@task, @subsys_id) combination, increment a
+ * reference on and return it.  This function is guaranteed to return a
+ * valid css.
+ */
+static inline struct cgroup_subsys_state *
+task_get_css(struct task_struct *task, int subsys_id)
+{
+	struct cgroup_subsys_state *css;
+
+	rcu_read_lock();
+	while (true) {
+		css = task_css(task, subsys_id);
+		if (likely(css_tryget_online(css)))
+			break;
+		cpu_relax();
+	}
+	rcu_read_unlock();
+	return css;
+}
+
+/**
+ * task_css_is_root - test whether a task belongs to the root css
+ * @task: the target task
+ * @subsys_id: the target subsystem ID
+ *
+ * Test whether @task belongs to the root css on the specified subsystem.
+ * May be invoked in any context.
+ */
+static inline bool task_css_is_root(struct task_struct *task, int subsys_id)
+{
+	return task_css_check(task, subsys_id, true) ==
+		init_css_set.subsys[subsys_id];
+}
+
+static inline struct cgroup *task_cgroup(struct task_struct *task,
+					 int subsys_id)
+{
+	return task_css(task, subsys_id)->cgroup;
+}
 
 /**
  * cgroup_on_dfl - test whether a cgroup is on the default hierarchy
@@ -604,392 +513,22 @@
 	pr_cont_kernfs_path(cgrp->kn);
 }
 
-char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
-
-int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
-int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
-int cgroup_rm_cftypes(struct cftype *cfts);
-
-bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor);
-
-/*
- * Control Group taskset, used to pass around set of tasks to cgroup_subsys
- * methods.
- */
-struct cgroup_taskset;
-struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset);
-struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset);
-
-/**
- * cgroup_taskset_for_each - iterate cgroup_taskset
- * @task: the loop cursor
- * @tset: taskset to iterate
- */
-#define cgroup_taskset_for_each(task, tset)				\
-	for ((task) = cgroup_taskset_first((tset)); (task);		\
-	     (task) = cgroup_taskset_next((tset)))
-
-/*
- * Control Group subsystem type.
- * See Documentation/cgroups/cgroups.txt for details
- */
-
-struct cgroup_subsys {
-	struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css);
-	int (*css_online)(struct cgroup_subsys_state *css);
-	void (*css_offline)(struct cgroup_subsys_state *css);
-	void (*css_released)(struct cgroup_subsys_state *css);
-	void (*css_free)(struct cgroup_subsys_state *css);
-	void (*css_reset)(struct cgroup_subsys_state *css);
-	void (*css_e_css_changed)(struct cgroup_subsys_state *css);
-
-	int (*can_attach)(struct cgroup_subsys_state *css,
-			  struct cgroup_taskset *tset);
-	void (*cancel_attach)(struct cgroup_subsys_state *css,
-			      struct cgroup_taskset *tset);
-	void (*attach)(struct cgroup_subsys_state *css,
-		       struct cgroup_taskset *tset);
-	void (*fork)(struct task_struct *task);
-	void (*exit)(struct cgroup_subsys_state *css,
-		     struct cgroup_subsys_state *old_css,
-		     struct task_struct *task);
-	void (*bind)(struct cgroup_subsys_state *root_css);
-
-	int disabled;
-	int early_init;
-
-	/*
-	 * If %false, this subsystem is properly hierarchical -
-	 * configuration, resource accounting and restriction on a parent
-	 * cgroup cover those of its children.  If %true, hierarchy support
-	 * is broken in some ways - some subsystems ignore hierarchy
-	 * completely while others are only implemented half-way.
-	 *
-	 * It's now disallowed to create nested cgroups if the subsystem is
-	 * broken and cgroup core will emit a warning message on such
-	 * cases.  Eventually, all subsystems will be made properly
-	 * hierarchical and this will go away.
-	 */
-	bool broken_hierarchy;
-	bool warned_broken_hierarchy;
-
-	/* the following two fields are initialized automtically during boot */
-	int id;
-#define MAX_CGROUP_TYPE_NAMELEN 32
-	const char *name;
-
-	/* link to parent, protected by cgroup_lock() */
-	struct cgroup_root *root;
-
-	/* idr for css->id */
-	struct idr css_idr;
-
-	/*
-	 * List of cftypes.  Each entry is the first entry of an array
-	 * terminated by zero length name.
-	 */
-	struct list_head cfts;
-
-	/*
-	 * Base cftypes which are automatically registered.  The two can
-	 * point to the same array.
-	 */
-	struct cftype *dfl_cftypes;	/* for the default hierarchy */
-	struct cftype *legacy_cftypes;	/* for the legacy hierarchies */
-
-	/*
-	 * A subsystem may depend on other subsystems.  When such subsystem
-	 * is enabled on a cgroup, the depended-upon subsystems are enabled
-	 * together if available.  Subsystems enabled due to dependency are
-	 * not visible to userland until explicitly enabled.  The following
-	 * specifies the mask of subsystems that this one depends on.
-	 */
-	unsigned int depends_on;
-};
-
-#define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys;
-#include <linux/cgroup_subsys.h>
-#undef SUBSYS
-
-/**
- * task_css_set_check - obtain a task's css_set with extra access conditions
- * @task: the task to obtain css_set for
- * @__c: extra condition expression to be passed to rcu_dereference_check()
- *
- * A task's css_set is RCU protected, initialized and exited while holding
- * task_lock(), and can only be modified while holding both cgroup_mutex
- * and task_lock() while the task is alive.  This macro verifies that the
- * caller is inside proper critical section and returns @task's css_set.
- *
- * The caller can also specify additional allowed conditions via @__c, such
- * as locks used during the cgroup_subsys::attach() methods.
- */
-#ifdef CONFIG_PROVE_RCU
-extern struct mutex cgroup_mutex;
-extern struct rw_semaphore css_set_rwsem;
-#define task_css_set_check(task, __c)					\
-	rcu_dereference_check((task)->cgroups,				\
-		lockdep_is_held(&cgroup_mutex) ||			\
-		lockdep_is_held(&css_set_rwsem) ||			\
-		((task)->flags & PF_EXITING) || (__c))
-#else
-#define task_css_set_check(task, __c)					\
-	rcu_dereference((task)->cgroups)
-#endif
-
-/**
- * task_css_check - obtain css for (task, subsys) w/ extra access conds
- * @task: the target task
- * @subsys_id: the target subsystem ID
- * @__c: extra condition expression to be passed to rcu_dereference_check()
- *
- * Return the cgroup_subsys_state for the (@task, @subsys_id) pair.  The
- * synchronization rules are the same as task_css_set_check().
- */
-#define task_css_check(task, subsys_id, __c)				\
-	task_css_set_check((task), (__c))->subsys[(subsys_id)]
-
-/**
- * task_css_set - obtain a task's css_set
- * @task: the task to obtain css_set for
- *
- * See task_css_set_check().
- */
-static inline struct css_set *task_css_set(struct task_struct *task)
-{
-	return task_css_set_check(task, false);
-}
-
-/**
- * task_css - obtain css for (task, subsys)
- * @task: the target task
- * @subsys_id: the target subsystem ID
- *
- * See task_css_check().
- */
-static inline struct cgroup_subsys_state *task_css(struct task_struct *task,
-						   int subsys_id)
-{
-	return task_css_check(task, subsys_id, false);
-}
-
-/**
- * task_get_css - find and get the css for (task, subsys)
- * @task: the target task
- * @subsys_id: the target subsystem ID
- *
- * Find the css for the (@task, @subsys_id) combination, increment a
- * reference on and return it.  This function is guaranteed to return a
- * valid css.
- */
-static inline struct cgroup_subsys_state *
-task_get_css(struct task_struct *task, int subsys_id)
-{
-	struct cgroup_subsys_state *css;
-
-	rcu_read_lock();
-	while (true) {
-		css = task_css(task, subsys_id);
-		if (likely(css_tryget_online(css)))
-			break;
-		cpu_relax();
-	}
-	rcu_read_unlock();
-	return css;
-}
-
-/**
- * task_css_is_root - test whether a task belongs to the root css
- * @task: the target task
- * @subsys_id: the target subsystem ID
- *
- * Test whether @task belongs to the root css on the specified subsystem.
- * May be invoked in any context.
- */
-static inline bool task_css_is_root(struct task_struct *task, int subsys_id)
-{
-	return task_css_check(task, subsys_id, true) ==
-		init_css_set.subsys[subsys_id];
-}
-
-static inline struct cgroup *task_cgroup(struct task_struct *task,
-					 int subsys_id)
-{
-	return task_css(task, subsys_id)->cgroup;
-}
-
-struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos,
-					   struct cgroup_subsys_state *parent);
-
-struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss);
-
-/**
- * css_for_each_child - iterate through children of a css
- * @pos: the css * to use as the loop cursor
- * @parent: css whose children to walk
- *
- * Walk @parent's children.  Must be called under rcu_read_lock().
- *
- * If a subsystem synchronizes ->css_online() and the start of iteration, a
- * css which finished ->css_online() is guaranteed to be visible in the
- * future iterations and will stay visible until the last reference is put.
- * A css which hasn't finished ->css_online() or already finished
- * ->css_offline() may show up during traversal.  It's each subsystem's
- * responsibility to synchronize against on/offlining.
- *
- * It is allowed to temporarily drop RCU read lock during iteration.  The
- * caller is responsible for ensuring that @pos remains accessible until
- * the start of the next iteration by, for example, bumping the css refcnt.
- */
-#define css_for_each_child(pos, parent)					\
-	for ((pos) = css_next_child(NULL, (parent)); (pos);		\
-	     (pos) = css_next_child((pos), (parent)))
-
-struct cgroup_subsys_state *
-css_next_descendant_pre(struct cgroup_subsys_state *pos,
-			struct cgroup_subsys_state *css);
-
-struct cgroup_subsys_state *
-css_rightmost_descendant(struct cgroup_subsys_state *pos);
-
-/**
- * css_for_each_descendant_pre - pre-order walk of a css's descendants
- * @pos: the css * to use as the loop cursor
- * @root: css whose descendants to walk
- *
- * Walk @root's descendants.  @root is included in the iteration and the
- * first node to be visited.  Must be called under rcu_read_lock().
- *
- * If a subsystem synchronizes ->css_online() and the start of iteration, a
- * css which finished ->css_online() is guaranteed to be visible in the
- * future iterations and will stay visible until the last reference is put.
- * A css which hasn't finished ->css_online() or already finished
- * ->css_offline() may show up during traversal.  It's each subsystem's
- * responsibility to synchronize against on/offlining.
- *
- * For example, the following guarantees that a descendant can't escape
- * state updates of its ancestors.
- *
- * my_online(@css)
- * {
- *	Lock @css's parent and @css;
- *	Inherit state from the parent;
- *	Unlock both.
- * }
- *
- * my_update_state(@css)
- * {
- *	css_for_each_descendant_pre(@pos, @css) {
- *		Lock @pos;
- *		if (@pos == @css)
- *			Update @css's state;
- *		else
- *			Verify @pos is alive and inherit state from its parent;
- *		Unlock @pos;
- *	}
- * }
- *
- * As long as the inheriting step, including checking the parent state, is
- * enclosed inside @pos locking, double-locking the parent isn't necessary
- * while inheriting.  The state update to the parent is guaranteed to be
- * visible by walking order and, as long as inheriting operations to the
- * same @pos are atomic to each other, multiple updates racing each other
- * still result in the correct state.  It's guaranateed that at least one
- * inheritance happens for any css after the latest update to its parent.
- *
- * If checking parent's state requires locking the parent, each inheriting
- * iteration should lock and unlock both @pos->parent and @pos.
- *
- * Alternatively, a subsystem may choose to use a single global lock to
- * synchronize ->css_online() and ->css_offline() against tree-walking
- * operations.
- *
- * It is allowed to temporarily drop RCU read lock during iteration.  The
- * caller is responsible for ensuring that @pos remains accessible until
- * the start of the next iteration by, for example, bumping the css refcnt.
- */
-#define css_for_each_descendant_pre(pos, css)				\
-	for ((pos) = css_next_descendant_pre(NULL, (css)); (pos);	\
-	     (pos) = css_next_descendant_pre((pos), (css)))
-
-struct cgroup_subsys_state *
-css_next_descendant_post(struct cgroup_subsys_state *pos,
-			 struct cgroup_subsys_state *css);
-
-/**
- * css_for_each_descendant_post - post-order walk of a css's descendants
- * @pos: the css * to use as the loop cursor
- * @css: css whose descendants to walk
- *
- * Similar to css_for_each_descendant_pre() but performs post-order
- * traversal instead.  @root is included in the iteration and the last
- * node to be visited.
- *
- * If a subsystem synchronizes ->css_online() and the start of iteration, a
- * css which finished ->css_online() is guaranteed to be visible in the
- * future iterations and will stay visible until the last reference is put.
- * A css which hasn't finished ->css_online() or already finished
- * ->css_offline() may show up during traversal.  It's each subsystem's
- * responsibility to synchronize against on/offlining.
- *
- * Note that the walk visibility guarantee example described in pre-order
- * walk doesn't apply the same to post-order walks.
- */
-#define css_for_each_descendant_post(pos, css)				\
-	for ((pos) = css_next_descendant_post(NULL, (css)); (pos);	\
-	     (pos) = css_next_descendant_post((pos), (css)))
-
-bool css_has_online_children(struct cgroup_subsys_state *css);
-
-/* A css_task_iter should be treated as an opaque object */
-struct css_task_iter {
-	struct cgroup_subsys		*ss;
-
-	struct list_head		*cset_pos;
-	struct list_head		*cset_head;
-
-	struct list_head		*task_pos;
-	struct list_head		*tasks_head;
-	struct list_head		*mg_tasks_head;
-};
-
-void css_task_iter_start(struct cgroup_subsys_state *css,
-			 struct css_task_iter *it);
-struct task_struct *css_task_iter_next(struct css_task_iter *it);
-void css_task_iter_end(struct css_task_iter *it);
-
-int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
-int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
-
-struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup,
-					     struct cgroup_subsys *ss);
-struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
-						       struct cgroup_subsys *ss);
-
 #else /* !CONFIG_CGROUPS */
 
 struct cgroup_subsys_state;
 
-static inline int cgroup_init_early(void) { return 0; }
-static inline int cgroup_init(void) { return 0; }
+static inline void css_put(struct cgroup_subsys_state *css) {}
+static inline int cgroup_attach_task_all(struct task_struct *from,
+					 struct task_struct *t) { return 0; }
+static inline int cgroupstats_build(struct cgroupstats *stats,
+				    struct dentry *dentry) { return -EINVAL; }
+
 static inline void cgroup_fork(struct task_struct *p) {}
 static inline void cgroup_post_fork(struct task_struct *p) {}
 static inline void cgroup_exit(struct task_struct *p) {}
 
-static inline int cgroupstats_build(struct cgroupstats *stats,
-					struct dentry *dentry)
-{
-	return -EINVAL;
-}
-
-static inline void css_put(struct cgroup_subsys_state *css) {}
-
-/* No cgroups - nothing to do */
-static inline int cgroup_attach_task_all(struct task_struct *from,
-					 struct task_struct *t)
-{
-	return 0;
-}
+static inline int cgroup_init_early(void) { return 0; }
+static inline int cgroup_init(void) { return 0; }
 
 #endif /* !CONFIG_CGROUPS */