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

5 files changed, 796 insertions, 790 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
new file mode 100644
index 0000000..93755a6
--- /dev/null
+++ b/include/linux/cgroup-defs.h
@@ -0,0 +1,501 @@
+/*
+ * linux/cgroup-defs.h - basic definitions for cgroup
+ *
+ * This file provides basic type and interface.  Include this file directly
+ * only if necessary to avoid cyclic dependencies.
+ */
+#ifndef _LINUX_CGROUP_DEFS_H
+#define _LINUX_CGROUP_DEFS_H
+
+#include <linux/limits.h>
+#include <linux/list.h>
+#include <linux/idr.h>
+#include <linux/wait.h>
+#include <linux/mutex.h>
+#include <linux/rcupdate.h>
+#include <linux/percpu-refcount.h>
+#include <linux/percpu-rwsem.h>
+#include <linux/workqueue.h>
+
+#ifdef CONFIG_CGROUPS
+
+struct cgroup;
+struct cgroup_root;
+struct cgroup_subsys;
+struct cgroup_taskset;
+struct kernfs_node;
+struct kernfs_ops;
+struct kernfs_open_file;
+struct seq_file;
+
+#define MAX_CGROUP_TYPE_NAMELEN 32
+#define MAX_CGROUP_ROOT_NAMELEN 64
+#define MAX_CFTYPE_NAME		64
+
+/* 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,
+};
+#undef SUBSYS
+
+/* 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 */
+};
+
+/* 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,
+};
+
+/* 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 */
+};
+
+/* 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 */
+};
+
+/*
+ * 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.
+ */
+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;
+
+	/* reference count - access via css_[try]get() and css_put() */
+	struct percpu_ref refcnt;
+
+	/* PI: the parent css */
+	struct cgroup_subsys_state *parent;
+
+	/* siblings list anchored at the parent's ->children */
+	struct list_head sibling;
+	struct list_head children;
+
+	/*
+	 * 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;
+
+	unsigned int flags;
+
+	/*
+	 * 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;
+
+	/* percpu_ref killing and RCU release */
+	struct rcu_head rcu_head;
+	struct work_struct destroy_work;
+};
+
+/*
+ * 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 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 *procs_kn;	/* kn for "cgroup.procs" */
+	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;
+};
+
+/*
+ * 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];
+};
+
+/*
+ * struct cftype: handler definitions for cgroup control files
+ *
+ * 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
+ */
+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;
+#endif
+};
+
+/*
+ * 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;
+	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;
+};
+
+extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
+
+/**
+ * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups
+ * @tsk: target task
+ *
+ * Called from threadgroup_change_begin() and allows cgroup operations to
+ * synchronize against threadgroup changes using a percpu_rw_semaphore.
+ */
+static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk)
+{
+	percpu_down_read(&cgroup_threadgroup_rwsem);
+}
+
+/**
+ * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups
+ * @tsk: target task
+ *
+ * Called from threadgroup_change_end().  Counterpart of
+ * cgroup_threadcgroup_change_begin().
+ */
+static inline void cgroup_threadgroup_change_end(struct task_struct *tsk)
+{
+	percpu_up_read(&cgroup_threadgroup_rwsem);
+}
+
+#else	/* CONFIG_CGROUPS */
+
+#define CGROUP_SUBSYS_COUNT 0
+
+static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) {}
+static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {}
+
+#endif	/* CONFIG_CGROUPS */
+
+#endif	/* _LINUX_CGROUP_DEFS_H */
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;
+
+	struct list_head		*task_pos;
+	struct list_head		*tasks_head;
+	struct list_head		*mg_tasks_head;
+};
 
-extern int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
-			    struct pid *pid, struct task_struct *tsk);
+extern struct cgroup_root cgrp_dfl_root;
+extern struct css_set init_css_set;
 
-/* define the enumeration of all cgroup subsystems */
-#define SUBSYS(_x) _x ## _cgrp_id,
-enum cgroup_subsys_id {
+#define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys;
 #include <linux/cgroup_subsys.h>
-	CGROUP_SUBSYS_COUNT,
-};
 #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.
+ * Iteration helpers and macros.
+ */
+
+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);
+
+struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset);
+struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset);
+
+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);
+
+/**
+ * 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
  *
- * Fields marked with "PI:" are public and immutable and may be accessed
- * directly without synchronization.
+ * 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.
  */
-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;
-
-	/* reference count - access via css_[try]get() and css_put() */
-	struct percpu_ref refcnt;
-
-	/* PI: the parent css */
-	struct cgroup_subsys_state *parent;
-
-	/* siblings list anchored at the parent's ->children */
-	struct list_head sibling;
-	struct list_head children;
-
-	/*
-	 * 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;
-
-	unsigned int flags;
-
-	/*
-	 * 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;
-
-	/* percpu_ref killing and RCU release */
-	struct rcu_head rcu_head;
-	struct work_struct destroy_work;
-};
+#define css_for_each_child(pos, parent)					\
+	for ((pos) = css_next_child(NULL, (parent)); (pos);		\
+	     (pos) = css_next_child((pos), (parent)))
 
-/* 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 */
-};
+/**
+ * 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)))
+
+/**
+ * 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)))
+
+/**
+ * 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)))
+
+/*
+ * Inline functions.
+ */
 
 /**
  * css_get - obtain a reference on the specified css
@@ -185,532 +291,6 @@ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n)
 		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
- *
- * 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
- */
-
-/* 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;
-#endif
-};
-
-extern struct cgroup_root cgrp_dfl_root;
-extern struct css_set init_css_set;
-
-/**
- * cgroup_on_dfl - test whether a cgroup is on the default hierarchy
- * @cgrp: the cgroup of interest
- *
- * The default hierarchy is the v2 interface of cgroup and this function
- * can be used to test whether a cgroup is on the default hierarchy for
- * cases where a subsystem should behave differnetly depending on the
- * interface version.
- *
- * The set of behaviors which change on the default hierarchy are still
- * being determined and the mount option is prefixed with __DEVEL__.
- *
- * List of changed behaviors:
- *
- * - Mount options "noprefix", "xattr", "clone_children", "release_agent"
- *   and "name" are disallowed.
- *
- * - When mounting an existing superblock, mount options should match.
- *
- * - Remount is disallowed.
- *
- * - rename(2) is disallowed.
- *
- * - "tasks" is removed.  Everything should be at process granularity.  Use
- *   "cgroup.procs" instead.
- *
- * - "cgroup.procs" is not sorted.  pids will be unique unless they got
- *   recycled inbetween reads.
- *
- * - "release_agent" and "notify_on_release" are removed.  Replacement
- *   notification mechanism will be implemented.
- *
- * - "cgroup.clone_children" is removed.
- *
- * - "cgroup.subtree_populated" is available.  Its value is 0 if the cgroup
- *   and its descendants contain no task; otherwise, 1.  The file also
- *   generates kernfs notification which can be monitored through poll and
- *   [di]notify when the value of the file changes.
- *
- * - cpuset: tasks will be kept in empty cpusets when hotplug happens and
- *   take masks of ancestors with non-empty cpus/mems, instead of being
- *   moved to an ancestor.
- *
- * - cpuset: a task can be moved into an empty cpuset, and again it takes
- *   masks of ancestors.
- *
- * - memcg: use_hierarchy is on by default and the cgroup file for the flag
- *   is not created.
- *
- * - blkcg: blk-throttle becomes properly hierarchical.
- *
- * - debug: disallowed on the default hierarchy.
- */
-static inline bool cgroup_on_dfl(const struct cgroup *cgrp)
-{
-	return cgrp->root == &cgrp_dfl_root;
-}
-
-/* no synchronization, the result can only be used as a hint */
-static inline bool cgroup_has_tasks(struct cgroup *cgrp)
-{
-	return !list_empty(&cgrp->cset_links);
-}
-
-/* returns ino associated with a cgroup */
-static inline ino_t cgroup_ino(struct cgroup *cgrp)
-{
-	return cgrp->kn->ino;
-}
-
-/* cft/css accessors for cftype->write() operation */
-static inline struct cftype *of_cft(struct kernfs_open_file *of)
-{
-	return of->kn->priv;
-}
-
-struct cgroup_subsys_state *of_css(struct kernfs_open_file *of);
-
-/* cft/css accessors for cftype->seq_*() operations */
-static inline struct cftype *seq_cft(struct seq_file *seq)
-{
-	return of_cft(seq->private);
-}
-
-static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq)
-{
-	return of_css(seq->private);
-}
-
-/*
- * Name / path handling functions.  All are thin wrappers around the kernfs
- * counterparts and can be called under any context.
- */
-
-static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen)
-{
-	return kernfs_name(cgrp->kn, buf, buflen);
-}
-
-static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf,
-					      size_t buflen)
-{
-	return kernfs_path(cgrp->kn, buf, buflen);
-}
-
-static inline void pr_cont_cgroup_name(struct cgroup *cgrp)
-{
-	pr_cont_kernfs_name(cgrp->kn);
-}
-
-static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
-{
-	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
@@ -818,178 +398,137 @@ static inline struct cgroup *task_cgroup(struct task_struct *task,
 	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
+ * cgroup_on_dfl - test whether a cgroup is on the default hierarchy
+ * @cgrp: the cgroup of interest
  *
- * Walk @parent's children.  Must be called under rcu_read_lock().
+ * The default hierarchy is the v2 interface of cgroup and this function
+ * can be used to test whether a cgroup is on the default hierarchy for
+ * cases where a subsystem should behave differnetly depending on the
+ * interface version.
  *
- * 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.
+ * The set of behaviors which change on the default hierarchy are still
+ * being determined and the mount option is prefixed with __DEVEL__.
  *
- * 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
+ * List of changed behaviors:
  *
- * Walk @root's descendants.  @root is included in the iteration and the
- * first node to be visited.  Must be called under rcu_read_lock().
+ * - Mount options "noprefix", "xattr", "clone_children", "release_agent"
+ *   and "name" are disallowed.
  *
- * 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.
+ * - When mounting an existing superblock, mount options should match.
  *
- * For example, the following guarantees that a descendant can't escape
- * state updates of its ancestors.
+ * - Remount is disallowed.
  *
- * my_online(@css)
- * {
- *	Lock @css's parent and @css;
- *	Inherit state from the parent;
- *	Unlock both.
- * }
+ * - rename(2) is disallowed.
  *
- * 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;
- *	}
- * }
+ * - "tasks" is removed.  Everything should be at process granularity.  Use
+ *   "cgroup.procs" instead.
  *
- * 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.
+ * - "cgroup.procs" is not sorted.  pids will be unique unless they got
+ *   recycled inbetween reads.
  *
- * If checking parent's state requires locking the parent, each inheriting
- * iteration should lock and unlock both @pos->parent and @pos.
+ * - "release_agent" and "notify_on_release" are removed.  Replacement
+ *   notification mechanism will be implemented.
  *
- * Alternatively, a subsystem may choose to use a single global lock to
- * synchronize ->css_online() and ->css_offline() against tree-walking
- * operations.
+ * - "cgroup.clone_children" is removed.
  *
- * 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
+ * - "cgroup.subtree_populated" is available.  Its value is 0 if the cgroup
+ *   and its descendants contain no task; otherwise, 1.  The file also
+ *   generates kernfs notification which can be monitored through poll and
+ *   [di]notify when the value of the file changes.
  *
- * 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.
+ * - cpuset: tasks will be kept in empty cpusets when hotplug happens and
+ *   take masks of ancestors with non-empty cpus/mems, instead of being
+ *   moved to an ancestor.
  *
- * 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.
+ * - cpuset: a task can be moved into an empty cpuset, and again it takes
+ *   masks of ancestors.
  *
- * Note that the walk visibility guarantee example described in pre-order
- * walk doesn't apply the same to post-order walks.
+ * - memcg: use_hierarchy is on by default and the cgroup file for the flag
+ *   is not created.
+ *
+ * - blkcg: blk-throttle becomes properly hierarchical.
+ *
+ * - debug: disallowed on the default hierarchy.
  */
-#define css_for_each_descendant_post(pos, css)				\
-	for ((pos) = css_next_descendant_post(NULL, (css)); (pos);	\
-	     (pos) = css_next_descendant_post((pos), (css)))
+static inline bool cgroup_on_dfl(const struct cgroup *cgrp)
+{
+	return cgrp->root == &cgrp_dfl_root;
+}
 
-bool css_has_online_children(struct cgroup_subsys_state *css);
+/* no synchronization, the result can only be used as a hint */
+static inline bool cgroup_has_tasks(struct cgroup *cgrp)
+{
+	return !list_empty(&cgrp->cset_links);
+}
 
-/* A css_task_iter should be treated as an opaque object */
-struct css_task_iter {
-	struct cgroup_subsys		*ss;
+/* returns ino associated with a cgroup */
+static inline ino_t cgroup_ino(struct cgroup *cgrp)
+{
+	return cgrp->kn->ino;
+}
 
-	struct list_head		*cset_pos;
-	struct list_head		*cset_head;
+/* cft/css accessors for cftype->write() operation */
+static inline struct cftype *of_cft(struct kernfs_open_file *of)
+{
+	return of->kn->priv;
+}
 
-	struct list_head		*task_pos;
-	struct list_head		*tasks_head;
-	struct list_head		*mg_tasks_head;
-};
+struct cgroup_subsys_state *of_css(struct kernfs_open_file *of);
 
-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);
+/* cft/css accessors for cftype->seq_*() operations */
+static inline struct cftype *seq_cft(struct seq_file *seq)
+{
+	return of_cft(seq->private);
+}
 
-int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
-int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
+static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq)
+{
+	return of_css(seq->private);
+}
 
-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);
+/*
+ * Name / path handling functions.  All are thin wrappers around the kernfs
+ * counterparts and can be called under any context.
+ */
 
-#else /* !CONFIG_CGROUPS */
+static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen)
+{
+	return kernfs_name(cgrp->kn, buf, buflen);
+}
 
-struct cgroup_subsys_state;
+static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf,
+					      size_t buflen)
+{
+	return kernfs_path(cgrp->kn, buf, buflen);
+}
 
-static inline int cgroup_init_early(void) { return 0; }
-static inline int cgroup_init(void) { return 0; }
-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 void pr_cont_cgroup_name(struct cgroup *cgrp)
+{
+	pr_cont_kernfs_name(cgrp->kn);
+}
 
-static inline int cgroupstats_build(struct cgroupstats *stats,
-					struct dentry *dentry)
+static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
 {
-	return -EINVAL;
+	pr_cont_kernfs_path(cgrp->kn);
 }
 
-static inline void css_put(struct cgroup_subsys_state *css) {}
+#else /* !CONFIG_CGROUPS */
 
-/* No cgroups - nothing to do */
+struct cgroup_subsys_state;
+
+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;
-}
+					 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 cgroup_init_early(void) { return 0; }
+static inline int cgroup_init(void) { return 0; }
 
 #endif /* !CONFIG_CGROUPS */
 
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index bb9b075..e8493fe 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -25,13 +25,6 @@
 extern struct files_struct init_files;
 extern struct fs_struct init_fs;
 
-#ifdef CONFIG_CGROUPS
-#define INIT_GROUP_RWSEM(sig)						\
-	.group_rwsem = __RWSEM_INITIALIZER(sig.group_rwsem),
-#else
-#define INIT_GROUP_RWSEM(sig)
-#endif
-
 #ifdef CONFIG_CPUSETS
 #define INIT_CPUSET_SEQ(tsk)							\
 	.mems_allowed_seq = SEQCNT_ZERO(tsk.mems_allowed_seq),
@@ -55,7 +48,6 @@ extern struct fs_struct init_fs;
 	},								\
 	.cred_guard_mutex =						\
 		 __MUTEX_INITIALIZER(sig.cred_guard_mutex),		\
-	INIT_GROUP_RWSEM(sig)						\
 }
 
 extern struct nsproxy init_nsproxy;
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 71ecdab..e6b2f7d 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -277,6 +277,7 @@ void kernfs_put(struct kernfs_node *kn);
 
 struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry);
 struct kernfs_root *kernfs_root_from_sb(struct super_block *sb);
+struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn);
 
 struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
 				       unsigned int flags, void *priv);
@@ -352,6 +353,10 @@ static inline struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry)
 static inline struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
 { return NULL; }
 
+static inline struct inode *
+kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn)
+{ return NULL; }
+
 static inline struct kernfs_root *
 kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags,
 		   void *priv)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 93ed0b6..a09ece3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -58,6 +58,7 @@ struct sched_param {
 #include <linux/uidgid.h>
 #include <linux/gfp.h>
 #include <linux/magic.h>
+#include <linux/cgroup-defs.h>
 
 #include <asm/processor.h>
 
@@ -755,18 +756,6 @@ struct signal_struct {
 	unsigned audit_tty_log_passwd;
 	struct tty_audit_buf *tty_audit_buf;
 #endif
-#ifdef CONFIG_CGROUPS
-	/*
-	 * group_rwsem prevents new tasks from entering the threadgroup and
-	 * member tasks from exiting,a more specifically, setting of
-	 * PF_EXITING.  fork and exit paths are protected with this rwsem
-	 * using threadgroup_change_begin/end().  Users which require
-	 * threadgroup to remain stable should use threadgroup_[un]lock()
-	 * which also takes care of exec path.  Currently, cgroup is the
-	 * only user.
-	 */
-	struct rw_semaphore group_rwsem;
-#endif
 
 	oom_flags_t oom_flags;
 	short oom_score_adj;		/* OOM kill score adjustment */
@@ -2725,53 +2714,33 @@ static inline void unlock_task_sighand(struct task_struct *tsk,
 	spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
 }
 
-#ifdef CONFIG_CGROUPS
-static inline void threadgroup_change_begin(struct task_struct *tsk)
-{
-	down_read(&tsk->signal->group_rwsem);
-}
-static inline void threadgroup_change_end(struct task_struct *tsk)
-{
-	up_read(&tsk->signal->group_rwsem);
-}
-
 /**
- * threadgroup_lock - lock threadgroup
- * @tsk: member task of the threadgroup to lock
- *
- * Lock the threadgroup @tsk belongs to.  No new task is allowed to enter
- * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or
- * change ->group_leader/pid.  This is useful for cases where the threadgroup
- * needs to stay stable across blockable operations.
- *
- * fork and exit paths explicitly call threadgroup_change_{begin|end}() for
- * synchronization.  While held, no new task will be added to threadgroup
- * and no existing live task will have its PF_EXITING set.
+ * threadgroup_change_begin - mark the beginning of changes to a threadgroup
+ * @tsk: task causing the changes
  *
- * de_thread() does threadgroup_change_{begin|end}() when a non-leader
- * sub-thread becomes a new leader.
+ * All operations which modify a threadgroup - a new thread joining the
+ * group, death of a member thread (the assertion of PF_EXITING) and
+ * exec(2) dethreading the process and replacing the leader - are wrapped
+ * by threadgroup_change_{begin|end}().  This is to provide a place which
+ * subsystems needing threadgroup stability can hook into for
+ * synchronization.
  */
-static inline void threadgroup_lock(struct task_struct *tsk)
+static inline void threadgroup_change_begin(struct task_struct *tsk)
 {
-	down_write(&tsk->signal->group_rwsem);
+	might_sleep();
+	cgroup_threadgroup_change_begin(tsk);
 }
 
 /**
- * threadgroup_unlock - unlock threadgroup
- * @tsk: member task of the threadgroup to unlock
+ * threadgroup_change_end - mark the end of changes to a threadgroup
+ * @tsk: task causing the changes
  *
- * Reverse threadgroup_lock().
+ * See threadgroup_change_begin().
  */
-static inline void threadgroup_unlock(struct task_struct *tsk)
+static inline void threadgroup_change_end(struct task_struct *tsk)
 {
-	up_write(&tsk->signal->group_rwsem);
+	cgroup_threadgroup_change_end(tsk);
 }
-#else
-static inline void threadgroup_change_begin(struct task_struct *tsk) {}
-static inline void threadgroup_change_end(struct task_struct *tsk) {}
-static inline void threadgroup_lock(struct task_struct *tsk) {}
-static inline void threadgroup_unlock(struct task_struct *tsk) {}
-#endif
 
 #ifndef __HAVE_THREAD_FUNCTIONS