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

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

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

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

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

   - netcls_cgroup and netprio_cgroup updated to handle hierarchy
     properly.

   - Various fixes and cleanups.

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

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

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

Documentation/cgroups/00-INDEX

@@ -1,7 +1,11 @@
 00-INDEX
 	- this file
+blkio-controller.txt
+	- Description for Block IO Controller, implementation and usage details.
 cgroups.txt
 	- Control Groups definition, implementation details, examples and API.
+cgroup_event_listener.c
+	- A user program for cgroup listener.
 cpuacct.txt
 	- CPU Accounting Controller; account CPU usage for groups of tasks.
 cpusets.txt
@@ -10,9 +14,13 @@ devices.txt
 	- Device Whitelist Controller; description, interface and security.
 freezer-subsystem.txt
 	- checkpointing; rationale to not use signals, interface.
+hugetlb.txt
+	- HugeTLB Controller implementation and usage details.
 memcg_test.txt
 	- Memory Resource Controller; implementation details.
 memory.txt
 	- Memory Resource Controller; design, accounting, interface, testing.
+net_prio.txt
+	- Network priority cgroups details and usages.
 resource_counter.txt
 	- Resource Counter API.

Documentation/cgroups/cgroups.txt

@@ -299,11 +299,9 @@ a cgroup hierarchy's release_agent path is empty.
 1.5 What does clone_children do ?
 ---------------------------------
 
-If the clone_children flag is enabled (1) in a cgroup, then all
-cgroups created beneath will call the post_clone callbacks for each
-subsystem of the newly created cgroup. Usually when this callback is
-implemented for a subsystem, it copies the values of the parent
-subsystem, this is the case for the cpuset.
+This flag only affects the cpuset controller. If the clone_children
+flag is enabled (1) in a cgroup, a new cpuset cgroup will copy its
+configuration from the parent during initialization.
 
 1.6 How do I use cgroups ?
 --------------------------
@@ -553,16 +551,16 @@ call to cgroup_unload_subsys(). It should also set its_subsys.module =
 THIS_MODULE in its .c file.
 
 Each subsystem may export the following methods. The only mandatory
-methods are create/destroy. Any others that are null are presumed to
+methods are css_alloc/free. Any others that are null are presumed to
 be successful no-ops.
 
-struct cgroup_subsys_state *create(struct cgroup *cgrp)
+struct cgroup_subsys_state *css_alloc(struct cgroup *cgrp)
 (cgroup_mutex held by caller)
 
-Called to create a subsystem state object for a cgroup. The
+Called to allocate a subsystem state object for a cgroup. The
 subsystem should allocate its subsystem state object for the passed
 cgroup, returning a pointer to the new object on success or a
-negative error code. On success, the subsystem pointer should point to
+ERR_PTR() value. On success, the subsystem pointer should point to
 a structure of type cgroup_subsys_state (typically embedded in a
 larger subsystem-specific object), which will be initialized by the
 cgroup system. Note that this will be called at initialization to
@@ -571,24 +569,33 @@ identified by the passed cgroup object having a NULL parent (since
 it's the root of the hierarchy) and may be an appropriate place for
 initialization code.
 
-void destroy(struct cgroup *cgrp)
+int css_online(struct cgroup *cgrp)
 (cgroup_mutex held by caller)
 
-The cgroup system is about to destroy the passed cgroup; the subsystem
-should do any necessary cleanup and free its subsystem state
-object. By the time this method is called, the cgroup has already been
-unlinked from the file system and from the child list of its parent;
-cgroup->parent is still valid. (Note - can also be called for a
-newly-created cgroup if an error occurs after this subsystem's
-create() method has been called for the new cgroup).
+Called after @cgrp successfully completed all allocations and made
+visible to cgroup_for_each_child/descendant_*() iterators. The
+subsystem may choose to fail creation by returning -errno. This
+callback can be used to implement reliable state sharing and
+propagation along the hierarchy. See the comment on
+cgroup_for_each_descendant_pre() for details.
 
-int pre_destroy(struct cgroup *cgrp);
+void css_offline(struct cgroup *cgrp);
 
-Called before checking the reference count on each subsystem. This may
-be useful for subsystems which have some extra references even if
-there are not tasks in the cgroup. If pre_destroy() returns error code,
-rmdir() will fail with it. From this behavior, pre_destroy() can be
-called multiple times against a cgroup.
+This is the counterpart of css_online() and called iff css_online()
+has succeeded on @cgrp. This signifies the beginning of the end of
+@cgrp. @cgrp is being removed and the subsystem should start dropping
+all references it's holding on @cgrp. When all references are dropped,
+cgroup removal will proceed to the next step - css_free(). After this
+callback, @cgrp should be considered dead to the subsystem.
+
+void css_free(struct cgroup *cgrp)
+(cgroup_mutex held by caller)
+
+The cgroup system is about to free @cgrp; the subsystem should free
+its subsystem state object. By the time this method is called, @cgrp
+is completely unused; @cgrp->parent is still valid. (Note - can also
+be called for a newly-created cgroup if an error occurs after this
+subsystem's create() method has been called for the new cgroup).
 
 int can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 (cgroup_mutex held by caller)
@@ -635,14 +642,6 @@ void exit(struct task_struct *task)
 
 Called during task exit.
 
-void post_clone(struct cgroup *cgrp)
-(cgroup_mutex held by caller)
-
-Called during cgroup_create() to do any parameter
-initialization which might be required before a task could attach.  For
-example, in cpusets, no task may attach before 'cpus' and 'mems' are set
-up.
-
 void bind(struct cgroup *root)
 (cgroup_mutex held by caller)
 

Documentation/cgroups/freezer-subsystem.txt

@@ -49,13 +49,49 @@ prevent the freeze/unfreeze cycle from becoming visible to the tasks
 being frozen. This allows the bash example above and gdb to run as
 expected.
 
-The freezer subsystem in the container filesystem defines a file named
-freezer.state. Writing "FROZEN" to the state file will freeze all tasks in the
-cgroup. Subsequently writing "THAWED" will unfreeze the tasks in the cgroup.
-Reading will return the current state.
+The cgroup freezer is hierarchical. Freezing a cgroup freezes all
+tasks beloning to the cgroup and all its descendant cgroups. Each
+cgroup has its own state (self-state) and the state inherited from the
+parent (parent-state). Iff both states are THAWED, the cgroup is
+THAWED.
 
-Note freezer.state doesn't exist in root cgroup, which means root cgroup
-is non-freezable.
+The following cgroupfs files are created by cgroup freezer.
+
+* freezer.state: Read-write.
+
+  When read, returns the effective state of the cgroup - "THAWED",
+  "FREEZING" or "FROZEN". This is the combined self and parent-states.
+  If any is freezing, the cgroup is freezing (FREEZING or FROZEN).
+
+  FREEZING cgroup transitions into FROZEN state when all tasks
+  belonging to the cgroup and its descendants become frozen. Note that
+  a cgroup reverts to FREEZING from FROZEN after a new task is added
+  to the cgroup or one of its descendant cgroups until the new task is
+  frozen.
+
+  When written, sets the self-state of the cgroup. Two values are
+  allowed - "FROZEN" and "THAWED". If FROZEN is written, the cgroup,
+  if not already freezing, enters FREEZING state along with all its
+  descendant cgroups.
+
+  If THAWED is written, the self-state of the cgroup is changed to
+  THAWED.  Note that the effective state may not change to THAWED if
+  the parent-state is still freezing. If a cgroup's effective state
+  becomes THAWED, all its descendants which are freezing because of
+  the cgroup also leave the freezing state.
+
+* freezer.self_freezing: Read only.
+
+  Shows the self-state. 0 if the self-state is THAWED; otherwise, 1.
+  This value is 1 iff the last write to freezer.state was "FROZEN".
+
+* freezer.parent_freezing: Read only.
+
+  Shows the parent-state.  0 if none of the cgroup's ancestors is
+  frozen; otherwise, 1.
+
+The root cgroup is non-freezable and the above interface files don't
+exist.
 
 * Examples of usage :
 
@@ -85,18 +121,3 @@ to unfreeze all tasks in the container :
 
 This is the basic mechanism which should do the right thing for user space task
 in a simple scenario.
-
-It's important to note that freezing can be incomplete. In that case we return
-EBUSY. This means that some tasks in the cgroup are busy doing something that
-prevents us from completely freezing the cgroup at this time. After EBUSY,
-the cgroup will remain partially frozen -- reflected by freezer.state reporting
-"FREEZING" when read. The state will remain "FREEZING" until one of these
-things happens:
-
-	1) Userspace cancels the freezing operation by writing "THAWED" to
-		the freezer.state file
-	2) Userspace retries the freezing operation by writing "FROZEN" to
-		the freezer.state file (writing "FREEZING" is not legal
-		and returns EINVAL)
-	3) The tasks that blocked the cgroup from entering the "FROZEN"
-		state disappear from the cgroup's set of tasks.

Documentation/cgroups/net_prio.txt

@@ -51,3 +51,5 @@ One usage for the net_prio cgroup is with mqprio qdisc allowing application
 traffic to be steered to hardware/driver based traffic classes. These mappings
 can then be managed by administrators or other networking protocols such as
 DCBX.
+
+A new net_prio cgroup inherits the parent's configuration.

block/blk-cgroup.c

@@ -600,7 +600,7 @@ struct cftype blkcg_files[] = {
 };
 
 /**
- * blkcg_pre_destroy - cgroup pre_destroy callback
+ * blkcg_css_offline - cgroup css_offline callback
  * @cgroup: cgroup of interest
  *
  * This function is called when @cgroup is about to go away and responsible
@@ -610,7 +610,7 @@ struct cftype blkcg_files[] = {
  *
  * This is the blkcg counterpart of ioc_release_fn().
  */
-static int blkcg_pre_destroy(struct cgroup *cgroup)
+static void blkcg_css_offline(struct cgroup *cgroup)
 {
 	struct blkcg *blkcg = cgroup_to_blkcg(cgroup);
 
@@ -632,10 +632,9 @@ static int blkcg_pre_destroy(struct cgroup *cgroup)
 	}
 
 	spin_unlock_irq(&blkcg->lock);
-	return 0;
 }
 
-static void blkcg_destroy(struct cgroup *cgroup)
+static void blkcg_css_free(struct cgroup *cgroup)
 {
 	struct blkcg *blkcg = cgroup_to_blkcg(cgroup);
 
@@ -643,7 +642,7 @@ static void blkcg_destroy(struct cgroup *cgroup)
 		kfree(blkcg);
 }
 
-static struct cgroup_subsys_state *blkcg_create(struct cgroup *cgroup)
+static struct cgroup_subsys_state *blkcg_css_alloc(struct cgroup *cgroup)
 {
 	static atomic64_t id_seq = ATOMIC64_INIT(0);
 	struct blkcg *blkcg;
@@ -740,10 +739,10 @@ static int blkcg_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 
 struct cgroup_subsys blkio_subsys = {
 	.name = "blkio",
-	.create = blkcg_create,
+	.css_alloc = blkcg_css_alloc,
+	.css_offline = blkcg_css_offline,
+	.css_free = blkcg_css_free,
 	.can_attach = blkcg_can_attach,
-	.pre_destroy = blkcg_pre_destroy,
-	.destroy = blkcg_destroy,
 	.subsys_id = blkio_subsys_id,
 	.base_cftypes = blkcg_files,
 	.module = THIS_MODULE,

include/linux/cgroup.h

@@ -12,6 +12,7 @@
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
 #include <linux/rcupdate.h>
+#include <linux/rculist.h>
 #include <linux/cgroupstats.h>
 #include <linux/prio_heap.h>
 #include <linux/rwsem.h>
@@ -34,7 +35,6 @@ extern int cgroup_lock_is_held(void);
 extern bool cgroup_lock_live_group(struct cgroup *cgrp);
 extern void cgroup_unlock(void);
 extern void cgroup_fork(struct task_struct *p);
-extern void cgroup_fork_callbacks(struct task_struct *p);
 extern void cgroup_post_fork(struct task_struct *p);
 extern void cgroup_exit(struct task_struct *p, int run_callbacks);
 extern int cgroupstats_build(struct cgroupstats *stats,
@@ -66,7 +66,7 @@ struct cgroup_subsys_state {
 	/*
 	 * State maintained by the cgroup system to allow subsystems
 	 * to be "busy". Should be accessed via css_get(),
-	 * css_tryget() and and css_put().
+	 * css_tryget() and css_put().
 	 */
 
 	atomic_t refcnt;
@@ -81,9 +81,8 @@ struct cgroup_subsys_state {
 
 /* bits in struct cgroup_subsys_state flags field */
 enum {
-	CSS_ROOT, /* This CSS is the root of the subsystem */
-	CSS_REMOVED, /* This CSS is dead */
-	CSS_CLEAR_CSS_REFS,		/* @ss->__DEPRECATED_clear_css_refs */
+	CSS_ROOT	= (1 << 0), /* this CSS is the root of the subsystem */
+	CSS_ONLINE	= (1 << 1), /* between ->css_online() and ->css_offline() */
 };
 
 /* Caller must verify that the css is not for root cgroup */
@@ -102,15 +101,10 @@ static inline void __css_get(struct cgroup_subsys_state *css, int count)
 static inline void css_get(struct cgroup_subsys_state *css)
 {
 	/* We don't need to reference count the root state */
-	if (!test_bit(CSS_ROOT, &css->flags))
+	if (!(css->flags & CSS_ROOT))
 		__css_get(css, 1);
 }
 
-static inline bool css_is_removed(struct cgroup_subsys_state *css)
-{
-	return test_bit(CSS_REMOVED, &css->flags);
-}
-
 /*
  * Call css_tryget() to take a reference on a css if your existing
  * (known-valid) reference isn't already ref-counted. Returns false if
@@ -120,7 +114,7 @@ static inline bool css_is_removed(struct cgroup_subsys_state *css)
 extern bool __css_tryget(struct cgroup_subsys_state *css);
 static inline bool css_tryget(struct cgroup_subsys_state *css)
 {
-	if (test_bit(CSS_ROOT, &css->flags))
+	if (css->flags & CSS_ROOT)
 		return true;
 	return __css_tryget(css);
 }
@@ -133,7 +127,7 @@ static inline bool css_tryget(struct cgroup_subsys_state *css)
 extern void __css_put(struct cgroup_subsys_state *css);
 static inline void css_put(struct cgroup_subsys_state *css)
 {
-	if (!test_bit(CSS_ROOT, &css->flags))
+	if (!(css->flags & CSS_ROOT))
 		__css_put(css);
 }
 
@@ -149,13 +143,11 @@ enum {
 	/* Control Group requires release notifications to userspace */
 	CGRP_NOTIFY_ON_RELEASE,
 	/*
-	 * A thread in rmdir() is wating for this cgroup.
-	 */
-	CGRP_WAIT_ON_RMDIR,
-	/*
-	 * Clone cgroup values when creating a new child cgroup
+	 * 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_CLONE_CHILDREN,
+	CGRP_CPUSET_CLONE_CHILDREN,
 };
 
 struct cgroup {
@@ -167,6 +159,8 @@ struct cgroup {
 	 */
 	atomic_t count;
 
+	int id;				/* ida allocated in-hierarchy ID */
+
 	/*
 	 * We link our 'sibling' struct into our parent's 'children'.
 	 * Our children link their 'sibling' into our 'children'.
@@ -176,7 +170,7 @@ struct cgroup {
 	struct list_head files;		/* my files */
 
 	struct cgroup *parent;		/* my parent */
-	struct dentry __rcu *dentry;	/* cgroup fs entry, RCU protected */
+	struct dentry *dentry;		/* cgroup fs entry, RCU protected */
 
 	/* Private pointers for each registered subsystem */
 	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
@@ -282,7 +276,7 @@ struct cgroup_map_cb {
 
 /* cftype->flags */
 #define CFTYPE_ONLY_ON_ROOT	(1U << 0)	/* only create on root cg */
-#define CFTYPE_NOT_ON_ROOT	(1U << 1)	/* don't create onp root cg */
+#define CFTYPE_NOT_ON_ROOT	(1U << 1)	/* don't create on root cg */
 
 #define MAX_CFTYPE_NAME		64
 
@@ -421,23 +415,6 @@ int cgroup_task_count(const struct cgroup *cgrp);
 /* Return true if cgrp is a descendant of the task's cgroup */
 int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task);
 
-/*
- * When the subsys has to access css and may add permanent refcnt to css,
- * it should take care of racy conditions with rmdir(). Following set of
- * functions, is for stop/restart rmdir if necessary.
- * Because these will call css_get/put, "css" should be alive css.
- *
- *  cgroup_exclude_rmdir();
- *  ...do some jobs which may access arbitrary empty cgroup
- *  cgroup_release_and_wakeup_rmdir();
- *
- *  When someone removes a cgroup while cgroup_exclude_rmdir() holds it,
- *  it sleeps and cgroup_release_and_wakeup_rmdir() will wake him up.
- */
-
-void cgroup_exclude_rmdir(struct cgroup_subsys_state *css);
-void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css);
-
 /*
  * Control Group taskset, used to pass around set of tasks to cgroup_subsys
  * methods.
@@ -466,16 +443,17 @@ int cgroup_taskset_size(struct cgroup_taskset *tset);
  */
 
 struct cgroup_subsys {
-	struct cgroup_subsys_state *(*create)(struct cgroup *cgrp);
-	int (*pre_destroy)(struct cgroup *cgrp);
-	void (*destroy)(struct cgroup *cgrp);
+	struct cgroup_subsys_state *(*css_alloc)(struct cgroup *cgrp);
+	int (*css_online)(struct cgroup *cgrp);
+	void (*css_offline)(struct cgroup *cgrp);
+	void (*css_free)(struct cgroup *cgrp);
+
 	int (*can_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
 	void (*cancel_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
 	void (*attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
 	void (*fork)(struct task_struct *task);
 	void (*exit)(struct cgroup *cgrp, struct cgroup *old_cgrp,
 		     struct task_struct *task);
-	void (*post_clone)(struct cgroup *cgrp);
 	void (*bind)(struct cgroup *root);
 
 	int subsys_id;
@@ -488,17 +466,6 @@ struct cgroup_subsys {
 	 */
 	bool use_id;
 
-	/*
-	 * If %true, cgroup removal will try to clear css refs by retrying
-	 * ss->pre_destroy() until there's no css ref left.  This behavior
-	 * is strictly for backward compatibility and will be removed as
-	 * soon as the current user (memcg) is updated.
-	 *
-	 * If %false, ss->pre_destroy() can't fail and cgroup removal won't
-	 * wait for css refs to drop to zero before proceeding.
-	 */
-	bool __DEPRECATED_clear_css_refs;
-
 	/*
 	 * If %false, this subsystem is properly hierarchical -
 	 * configuration, resource accounting and restriction on a parent
@@ -572,6 +539,100 @@ static inline struct cgroup* task_cgroup(struct task_struct *task,
 	return task_subsys_state(task, subsys_id)->cgroup;
 }
 
+/**
+ * cgroup_for_each_child - iterate through children of a cgroup
+ * @pos: the cgroup * to use as the loop cursor
+ * @cgroup: cgroup whose children to walk
+ *
+ * Walk @cgroup's children.  Must be called under rcu_read_lock().  A child
+ * cgroup which hasn't finished ->css_online() or already has finished
+ * ->css_offline() may show up during traversal and it's each subsystem's
+ * responsibility to verify that each @pos is alive.
+ *
+ * If a subsystem synchronizes against the parent in its ->css_online() and
+ * before starting iterating, a cgroup which finished ->css_online() is
+ * guaranteed to be visible in the future iterations.
+ */
+#define cgroup_for_each_child(pos, cgroup)				\
+	list_for_each_entry_rcu(pos, &(cgroup)->children, sibling)
+
+struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos,
+					  struct cgroup *cgroup);
+
+/**
+ * cgroup_for_each_descendant_pre - pre-order walk of a cgroup's descendants
+ * @pos: the cgroup * to use as the loop cursor
+ * @cgroup: cgroup whose descendants to walk
+ *
+ * Walk @cgroup's descendants.  Must be called under rcu_read_lock().  A
+ * descendant cgroup which hasn't finished ->css_online() or already has
+ * finished ->css_offline() may show up during traversal and it's each
+ * subsystem's responsibility to verify that each @pos is alive.
+ *
+ * If a subsystem synchronizes against the parent in its ->css_online() and
+ * before starting iterating, and synchronizes against @pos on each
+ * iteration, any descendant cgroup which finished ->css_offline() is
+ * guaranteed to be visible in the future iterations.
+ *
+ * In other words, the following guarantees that a descendant can't escape
+ * state updates of its ancestors.
+ *
+ * my_online(@cgrp)
+ * {
+ *	Lock @cgrp->parent and @cgrp;
+ *	Inherit state from @cgrp->parent;
+ *	Unlock both.
+ * }
+ *
+ * my_update_state(@cgrp)
+ * {
+ *	Lock @cgrp;
+ *	Update @cgrp's state;
+ *	Unlock @cgrp;
+ *
+ *	cgroup_for_each_descendant_pre(@pos, @cgrp) {
+ *		Lock @pos;
+ *		Verify @pos is alive and inherit state from @pos->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 cgroup 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.
+ */
+#define cgroup_for_each_descendant_pre(pos, cgroup)			\
+	for (pos = cgroup_next_descendant_pre(NULL, (cgroup)); (pos);	\
+	     pos = cgroup_next_descendant_pre((pos), (cgroup)))
+
+struct cgroup *cgroup_next_descendant_post(struct cgroup *pos,
+					   struct cgroup *cgroup);
+
+/**
+ * cgroup_for_each_descendant_post - post-order walk of a cgroup's descendants
+ * @pos: the cgroup * to use as the loop cursor
+ * @cgroup: cgroup whose descendants to walk
+ *
+ * Similar to cgroup_for_each_descendant_pre() but performs post-order
+ * traversal instead.  Note that the walk visibility guarantee described in
+ * pre-order walk doesn't apply the same to post-order walks.
+ */
+#define cgroup_for_each_descendant_post(pos, cgroup)			\
+	for (pos = cgroup_next_descendant_post(NULL, (cgroup)); (pos);	\
+	     pos = cgroup_next_descendant_post((pos), (cgroup)))
+
 /* A cgroup_iter should be treated as an opaque object */
 struct cgroup_iter {
 	struct list_head *cg_link;

include/linux/freezer.h

@@ -75,35 +75,68 @@ static inline bool cgroup_freezing(struct task_struct *task)
  */
 
 
-/* Tell the freezer not to count the current task as freezable. */
+/**
+ * freezer_do_not_count - tell freezer to ignore %current
+ *
+ * Tell freezers to ignore the current task when determining whether the
+ * target frozen state is reached.  IOW, the current task will be
+ * considered frozen enough by freezers.
+ *
+ * The caller shouldn't do anything which isn't allowed for a frozen task
+ * until freezer_cont() is called.  Usually, freezer[_do_not]_count() pair
+ * wrap a scheduling operation and nothing much else.
+ */
 static inline void freezer_do_not_count(void)
 {
 	current->flags |= PF_FREEZER_SKIP;
 }
 
-/*
- * Tell the freezer to count the current task as freezable again and try to
- * freeze it.
+/**
+ * freezer_count - tell freezer to stop ignoring %current
+ *
+ * Undo freezer_do_not_count().  It tells freezers that %current should be
+ * considered again and tries to freeze if freezing condition is already in
+ * effect.
  */
 static inline void freezer_count(void)
 {
 	current->flags &= ~PF_FREEZER_SKIP;
+	/*
+	 * If freezing is in progress, the following paired with smp_mb()
+	 * in freezer_should_skip() ensures that either we see %true
+	 * freezing() or freezer_should_skip() sees !PF_FREEZER_SKIP.
+	 */
+	smp_mb();
 	try_to_freeze();
 }
 
-/*
- * Check if the task should be counted as freezable by the freezer
+/**
+ * freezer_should_skip - whether to skip a task when determining frozen
+ *			 state is reached
+ * @p: task in quesion
+ *
+ * This function is used by freezers after establishing %true freezing() to
+ * test whether a task should be skipped when determining the target frozen
+ * state is reached.  IOW, if this function returns %true, @p is considered
+ * frozen enough.
  */
-static inline int freezer_should_skip(struct task_struct *p)
+static inline bool freezer_should_skip(struct task_struct *p)
 {
-	return !!(p->flags & PF_FREEZER_SKIP);
+	/*
+	 * The following smp_mb() paired with the one in freezer_count()
+	 * ensures that either freezer_count() sees %true freezing() or we
+	 * see cleared %PF_FREEZER_SKIP and return %false.  This makes it
+	 * impossible for a task to slip frozen state testing after
+	 * clearing %PF_FREEZER_SKIP.
+	 */
+	smp_mb();
+	return p->flags & PF_FREEZER_SKIP;
 }
 
 /*
- * These macros are intended to be used whenever you want allow a task that's
- * sleeping in TASK_UNINTERRUPTIBLE or TASK_KILLABLE state to be frozen. Note
- * that neither return any clear indication of whether a freeze event happened
- * while in this function.
+ * These macros are intended to be used whenever you want allow a sleeping
+ * task to be frozen. Note that neither return any clear indication of
+ * whether a freeze event happened while in this function.
  */
 
 /* Like schedule(), but should not block the freezer. */

include/net/netprio_cgroup.h

@@ -27,7 +27,6 @@ struct netprio_map {
 
 struct cgroup_netprio_state {
 	struct cgroup_subsys_state css;
-	u32 prioidx;
 };
 
 extern void sock_update_netprioidx(struct sock *sk, struct task_struct *task);
@@ -36,13 +35,12 @@ extern void sock_update_netprioidx(struct sock *sk, struct task_struct *task);
 
 static inline u32 task_netprioidx(struct task_struct *p)
 {
-	struct cgroup_netprio_state *state;
+	struct cgroup_subsys_state *css;
 	u32 idx;
 
 	rcu_read_lock();
-	state = container_of(task_subsys_state(p, net_prio_subsys_id),
-			     struct cgroup_netprio_state, css);
-	idx = state->prioidx;
+	css = task_subsys_state(p, net_prio_subsys_id);
+	idx = css->cgroup->id;
 	rcu_read_unlock();
 	return idx;
 }
@@ -57,8 +55,7 @@ static inline u32 task_netprioidx(struct task_struct *p)
 	rcu_read_lock();
 	css = task_subsys_state(p, net_prio_subsys_id);
 	if (css)
-		idx = container_of(css,
-				   struct cgroup_netprio_state, css)->prioidx;
+		idx = css->cgroup->id;
 	rcu_read_unlock();
 	return idx;
 }

kernel/cgroup.c

@@ -138,6 +138,9 @@ struct cgroupfs_root {
 	/* Hierarchy-specific flags */
 	unsigned long flags;
 
+	/* IDs for cgroups in this hierarchy */
+	struct ida cgroup_ida;
+
 	/* The path to use for release notifications. */
 	char release_agent_path[PATH_MAX];
 
@@ -171,8 +174,8 @@ struct css_id {
 	 * The css to which this ID points. This pointer is set to valid value
 	 * after cgroup is populated. If cgroup is removed, this will be NULL.
 	 * This pointer is expected to be RCU-safe because destroy()
-	 * is called after synchronize_rcu(). But for safe use, css_is_removed()
-	 * css_tryget() should be used for avoiding race.
+	 * is called after synchronize_rcu(). But for safe use, css_tryget()
+	 * should be used for avoiding race.
 	 */
 	struct cgroup_subsys_state __rcu *css;
 	/*
@@ -242,6 +245,10 @@ static DEFINE_SPINLOCK(hierarchy_id_lock);
  */
 static int need_forkexit_callback __read_mostly;
 
+static int cgroup_destroy_locked(struct cgroup *cgrp);
+static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys,
+			      struct cftype cfts[], bool is_add);
+
 #ifdef CONFIG_PROVE_LOCKING
 int cgroup_lock_is_held(void)
 {
@@ -294,11 +301,6 @@ static int notify_on_release(const struct cgroup *cgrp)
 	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 }
 
-static int clone_children(const struct cgroup *cgrp)
-{
-	return test_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
-}
-
 /*
  * for_each_subsys() allows you to iterate on each subsystem attached to
  * an active hierarchy
@@ -782,12 +784,12 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
  *	The task_lock() exception
  *
  * The need for this exception arises from the action of
- * cgroup_attach_task(), which overwrites one tasks cgroup pointer with
+ * cgroup_attach_task(), which overwrites one task's cgroup pointer with
  * another.  It does so using cgroup_mutex, however there are
  * several performance critical places that need to reference
  * task->cgroup without the expense of grabbing a system global
  * mutex.  Therefore except as noted below, when dereferencing or, as
- * in cgroup_attach_task(), modifying a task'ss cgroup pointer we use
+ * in cgroup_attach_task(), modifying a task's cgroup pointer we use
  * task_lock(), which acts on a spinlock (task->alloc_lock) already in
  * the task_struct routinely used for such matters.
  *
@@ -854,30 +856,6 @@ static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
 	return inode;
 }
 
-/*
- * Call subsys's pre_destroy handler.
- * This is called before css refcnt check.
- */
-static int cgroup_call_pre_destroy(struct cgroup *cgrp)
-{
-	struct cgroup_subsys *ss;
-	int ret = 0;
-
-	for_each_subsys(cgrp->root, ss) {
-		if (!ss->pre_destroy)
-			continue;
-
-		ret = ss->pre_destroy(cgrp);
-		if (ret) {
-			/* ->pre_destroy() failure is being deprecated */
-			WARN_ON_ONCE(!ss->__DEPRECATED_clear_css_refs);
-			break;
-		}
-	}
-
-	return ret;
-}
-
 static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 {
 	/* is dentry a directory ? if so, kfree() associated cgroup */
@@ -898,7 +876,7 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		 * Release the subsystem state objects.
 		 */
 		for_each_subsys(cgrp->root, ss)
-			ss->destroy(cgrp);
+			ss->css_free(cgrp);
 
 		cgrp->root->number_of_cgroups--;
 		mutex_unlock(&cgroup_mutex);
@@ -917,6 +895,7 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 
 		simple_xattrs_free(&cgrp->xattrs);
 
+		ida_simple_remove(&cgrp->root->cgroup_ida, cgrp->id);
 		kfree_rcu(cgrp, rcu_head);
 	} else {
 		struct cfent *cfe = __d_cfe(dentry);
@@ -987,7 +966,7 @@ static void cgroup_clear_directory(struct dentry *dir, bool base_files,
 		if (!test_bit(ss->subsys_id, &subsys_mask))
 			continue;
 		list_for_each_entry(set, &ss->cftsets, node)
-			cgroup_rm_file(cgrp, set->cfts);
+			cgroup_addrm_files(cgrp, NULL, set->cfts, false);
 	}
 	if (base_files) {
 		while (!list_empty(&cgrp->files))
@@ -1014,33 +993,6 @@ static void cgroup_d_remove_dir(struct dentry *dentry)
 	remove_dir(dentry);
 }
 
-/*
- * A queue for waiters to do rmdir() cgroup. A tasks will sleep when
- * cgroup->count == 0 && list_empty(&cgroup->children) && subsys has some
- * reference to css->refcnt. In general, this refcnt is expected to goes down
- * to zero, soon.
- *
- * CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex;
- */
-static DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
-
-static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp)
-{
-	if (unlikely(test_and_clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
-		wake_up_all(&cgroup_rmdir_waitq);
-}
-
-void cgroup_exclude_rmdir(struct cgroup_subsys_state *css)
-{
-	css_get(css);
-}
-
-void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css)
-{
-	cgroup_wakeup_rmdir_waiter(css->cgroup);
-	css_put(css);
-}
-
 /*
  * Call with cgroup_mutex held. Drops reference counts on modules, including
  * any duplicate ones that parse_cgroupfs_options took. If this function
@@ -1150,7 +1102,7 @@ static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",xattr");
 	if (strlen(root->release_agent_path))
 		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
-	if (clone_children(&root->top_cgroup))
+	if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags))
 		seq_puts(seq, ",clone_children");
 	if (strlen(root->name))
 		seq_printf(seq, ",name=%s", root->name);
@@ -1162,7 +1114,7 @@ struct cgroup_sb_opts {
 	unsigned long subsys_mask;
 	unsigned long flags;
 	char *release_agent;
-	bool clone_children;
+	bool cpuset_clone_children;
 	char *name;
 	/* User explicitly requested empty subsystem */
 	bool none;
@@ -1213,7 +1165,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 			continue;
 		}
 		if (!strcmp(token, "clone_children")) {
-			opts->clone_children = true;
+			opts->cpuset_clone_children = true;
 			continue;
 		}
 		if (!strcmp(token, "xattr")) {
@@ -1397,14 +1349,21 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 		goto out_unlock;
 	}
 
+	/*
+	 * Clear out the files of subsystems that should be removed, do
+	 * this before rebind_subsystems, since rebind_subsystems may
+	 * change this hierarchy's subsys_list.
+	 */
+	cgroup_clear_directory(cgrp->dentry, false, removed_mask);
+
 	ret = rebind_subsystems(root, opts.subsys_mask);
 	if (ret) {
+		/* rebind_subsystems failed, re-populate the removed files */
+		cgroup_populate_dir(cgrp, false, removed_mask);
 		drop_parsed_module_refcounts(opts.subsys_mask);
 		goto out_unlock;
 	}
 
-	/* clear out any existing files and repopulate subsystem files */
-	cgroup_clear_directory(cgrp->dentry, false, removed_mask);
 	/* re-populate subsystem files */
 	cgroup_populate_dir(cgrp, false, added_mask);
 
@@ -1432,6 +1391,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	INIT_LIST_HEAD(&cgrp->children);
 	INIT_LIST_HEAD(&cgrp->files);
 	INIT_LIST_HEAD(&cgrp->css_sets);
+	INIT_LIST_HEAD(&cgrp->allcg_node);
 	INIT_LIST_HEAD(&cgrp->release_list);
 	INIT_LIST_HEAD(&cgrp->pidlists);
 	mutex_init(&cgrp->pidlist_mutex);
@@ -1450,8 +1410,8 @@ static void init_cgroup_root(struct cgroupfs_root *root)
 	root->number_of_cgroups = 1;
 	cgrp->root = root;
 	cgrp->top_cgroup = cgrp;
-	list_add_tail(&cgrp->allcg_node, &root->allcg_list);
 	init_cgroup_housekeeping(cgrp);
+	list_add_tail(&cgrp->allcg_node, &root->allcg_list);
 }
 
 static bool init_root_id(struct cgroupfs_root *root)
@@ -1518,12 +1478,13 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
 
 	root->subsys_mask = opts->subsys_mask;
 	root->flags = opts->flags;
+	ida_init(&root->cgroup_ida);
 	if (opts->release_agent)
 		strcpy(root->release_agent_path, opts->release_agent);
 	if (opts->name)
 		strcpy(root->name, opts->name);
-	if (opts->clone_children)
-		set_bit(CGRP_CLONE_CHILDREN, &root->top_cgroup.flags);
+	if (opts->cpuset_clone_children)
+		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags);
 	return root;
 }
 
@@ -1536,6 +1497,7 @@ static void cgroup_drop_root(struct cgroupfs_root *root)
 	spin_lock(&hierarchy_id_lock);
 	ida_remove(&hierarchy_ida, root->hierarchy_id);
 	spin_unlock(&hierarchy_id_lock);
+	ida_destroy(&root->cgroup_ida);
 	kfree(root);
 }
 
@@ -1701,7 +1663,6 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 
 		free_cg_links(&tmp_cg_links);
 
-		BUG_ON(!list_empty(&root_cgrp->sibling));
 		BUG_ON(!list_empty(&root_cgrp->children));
 		BUG_ON(root->number_of_cgroups != 1);
 
@@ -1750,7 +1711,6 @@ static void cgroup_kill_sb(struct super_block *sb) {
 
 	BUG_ON(root->number_of_cgroups != 1);
 	BUG_ON(!list_empty(&cgrp->children));
-	BUG_ON(!list_empty(&cgrp->sibling));
 
 	mutex_lock(&cgroup_mutex);
 	mutex_lock(&cgroup_root_mutex);
@@ -1808,9 +1768,11 @@ static struct kobject *cgroup_kobj;
  */
 int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 {
+	struct dentry *dentry = cgrp->dentry;
 	char *start;
-	struct dentry *dentry = rcu_dereference_check(cgrp->dentry,
-						      cgroup_lock_is_held());
+
+	rcu_lockdep_assert(rcu_read_lock_held() || cgroup_lock_is_held(),
+			   "cgroup_path() called without proper locking");
 
 	if (!dentry || cgrp == dummytop) {
 		/*
@@ -1821,9 +1783,9 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 		return 0;
 	}
 
-	start = buf + buflen;
+	start = buf + buflen - 1;
 
-	*--start = '\0';
+	*start = '\0';
 	for (;;) {
 		int len = dentry->d_name.len;
 
@@ -1834,8 +1796,7 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 		if (!cgrp)
 			break;
 
-		dentry = rcu_dereference_check(cgrp->dentry,
-					       cgroup_lock_is_held());
+		dentry = cgrp->dentry;
 		if (!cgrp->parent)
 			continue;
 		if (--start < buf)
@@ -1930,9 +1891,7 @@ EXPORT_SYMBOL_GPL(cgroup_taskset_size);
 /*
  * cgroup_task_migrate - move a task from one cgroup to another.
  *
- * 'guarantee' is set if the caller promises that a new css_set for the task
- * will already exist. If not set, this function might sleep, and can fail with
- * -ENOMEM. Must be called with cgroup_mutex and threadgroup locked.
+ * Must be called with cgroup_mutex and threadgroup locked.
  */
 static void cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
 				struct task_struct *tsk, struct css_set *newcg)
@@ -2025,12 +1984,6 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	}
 
 	synchronize_rcu();
-
-	/*
-	 * wake up rmdir() waiter. the rmdir should fail since the cgroup
-	 * is no longer empty.
-	 */
-	cgroup_wakeup_rmdir_waiter(cgrp);
 out:
 	if (retval) {
 		for_each_subsys(root, ss) {
@@ -2200,7 +2153,6 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 	 * step 5: success! and cleanup
 	 */
 	synchronize_rcu();
-	cgroup_wakeup_rmdir_waiter(cgrp);
 	retval = 0;
 out_put_css_set_refs:
 	if (retval) {
@@ -2711,10 +2663,17 @@ static int cgroup_create_file(struct dentry *dentry, umode_t mode,
 
 		/* start off with i_nlink == 2 (for "." entry) */
 		inc_nlink(inode);
+		inc_nlink(dentry->d_parent->d_inode);
 
-		/* start with the directory inode held, so that we can
-		 * populate it without racing with another mkdir */
-		mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
+		/*
+		 * Control reaches here with cgroup_mutex held.
+		 * @inode->i_mutex should nest outside cgroup_mutex but we
+		 * want to populate it immediately without releasing
+		 * cgroup_mutex.  As @inode isn't visible to anyone else
+		 * yet, trylock will always succeed without affecting
+		 * lockdep checks.
+		 */
+		WARN_ON_ONCE(!mutex_trylock(&inode->i_mutex));
 	} else if (S_ISREG(mode)) {
 		inode->i_size = 0;
 		inode->i_fop = &cgroup_file_operations;
@@ -2725,32 +2684,6 @@ static int cgroup_create_file(struct dentry *dentry, umode_t mode,
 	return 0;
 }
 
-/*
- * cgroup_create_dir - create a directory for an object.
- * @cgrp: the cgroup we create the directory for. It must have a valid
- *        ->parent field. And we are going to fill its ->dentry field.
- * @dentry: dentry of the new cgroup
- * @mode: mode to set on new directory.
- */
-static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry,
-				umode_t mode)
-{
-	struct dentry *parent;
-	int error = 0;
-
-	parent = cgrp->parent->dentry;
-	error = cgroup_create_file(dentry, S_IFDIR | mode, cgrp->root->sb);
-	if (!error) {
-		dentry->d_fsdata = cgrp;
-		inc_nlink(parent->d_inode);
-		rcu_assign_pointer(cgrp->dentry, dentry);
-		dget(dentry);
-	}
-	dput(dentry);
-
-	return error;
-}
-
 /**
  * cgroup_file_mode - deduce file mode of a control file
  * @cft: the control file in question
@@ -2791,12 +2724,6 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
 
 	simple_xattrs_init(&cft->xattrs);
 
-	/* does @cft->flags tell us to skip creation on @cgrp? */
-	if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent)
-		return 0;
-	if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgrp->parent)
-		return 0;
-
 	if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) {
 		strcpy(name, subsys->name);
 		strcat(name, ".");
@@ -2837,6 +2764,12 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys,
 	int err, ret = 0;
 
 	for (cft = cfts; cft->name[0] != '\0'; cft++) {
+		/* does cft->flags tell us to skip this file on @cgrp? */
+		if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent)
+			continue;
+		if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgrp->parent)
+			continue;
+
 		if (is_add)
 			err = cgroup_add_file(cgrp, subsys, cft);
 		else
@@ -3044,6 +2977,92 @@ static void cgroup_enable_task_cg_lists(void)
 	write_unlock(&css_set_lock);
 }
 
+/**
+ * cgroup_next_descendant_pre - find the next descendant for pre-order walk
+ * @pos: the current position (%NULL to initiate traversal)
+ * @cgroup: cgroup whose descendants to walk
+ *
+ * To be used by cgroup_for_each_descendant_pre().  Find the next
+ * descendant to visit for pre-order traversal of @cgroup's descendants.
+ */
+struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos,
+					  struct cgroup *cgroup)
+{
+	struct cgroup *next;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	/* if first iteration, pretend we just visited @cgroup */
+	if (!pos) {
+		if (list_empty(&cgroup->children))
+			return NULL;
+		pos = cgroup;
+	}
+
+	/* visit the first child if exists */
+	next = list_first_or_null_rcu(&pos->children, struct cgroup, sibling);
+	if (next)
+		return next;
+
+	/* no child, visit my or the closest ancestor's next sibling */
+	do {
+		next = list_entry_rcu(pos->sibling.next, struct cgroup,
+				      sibling);
+		if (&next->sibling != &pos->parent->children)
+			return next;
+
+		pos = pos->parent;
+	} while (pos != cgroup);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(cgroup_next_descendant_pre);
+
+static struct cgroup *cgroup_leftmost_descendant(struct cgroup *pos)
+{
+	struct cgroup *last;
+
+	do {
+		last = pos;
+		pos = list_first_or_null_rcu(&pos->children, struct cgroup,
+					     sibling);
+	} while (pos);
+
+	return last;
+}
+
+/**
+ * cgroup_next_descendant_post - find the next descendant for post-order walk
+ * @pos: the current position (%NULL to initiate traversal)
+ * @cgroup: cgroup whose descendants to walk
+ *
+ * To be used by cgroup_for_each_descendant_post().  Find the next
+ * descendant to visit for post-order traversal of @cgroup's descendants.
+ */
+struct cgroup *cgroup_next_descendant_post(struct cgroup *pos,
+					   struct cgroup *cgroup)
+{
+	struct cgroup *next;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	/* if first iteration, visit the leftmost descendant */
+	if (!pos) {
+		next = cgroup_leftmost_descendant(cgroup);
+		return next != cgroup ? next : NULL;
+	}
+
+	/* if there's an unvisited sibling, visit its leftmost descendant */
+	next = list_entry_rcu(pos->sibling.next, struct cgroup, sibling);
+	if (&next->sibling != &pos->parent->children)
+		return cgroup_leftmost_descendant(next);
+
+	/* no sibling left, visit parent */
+	next = pos->parent;
+	return next != cgroup ? next : NULL;
+}
+EXPORT_SYMBOL_GPL(cgroup_next_descendant_post);
+
 void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it)
 	__acquires(css_set_lock)
 {
@@ -3757,7 +3776,7 @@ static int cgroup_event_wake(wait_queue_t *wait, unsigned mode,
 	if (flags & POLLHUP) {
 		__remove_wait_queue(event->wqh, &event->wait);
 		spin_lock(&cgrp->event_list_lock);
-		list_del(&event->list);
+		list_del_init(&event->list);
 		spin_unlock(&cgrp->event_list_lock);
 		/*
 		 * We are in atomic context, but cgroup_event_remove() may
@@ -3894,7 +3913,7 @@ fail:
 static u64 cgroup_clone_children_read(struct cgroup *cgrp,
 				    struct cftype *cft)
 {
-	return clone_children(cgrp);
+	return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 }
 
 static int cgroup_clone_children_write(struct cgroup *cgrp,
@@ -3902,9 +3921,9 @@ static int cgroup_clone_children_write(struct cgroup *cgrp,
 				     u64 val)
 {
 	if (val)
-		set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 	else
-		clear_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+		clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 	return 0;
 }
 
@@ -4017,19 +4036,57 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 	css->flags = 0;
 	css->id = NULL;
 	if (cgrp == dummytop)
-		set_bit(CSS_ROOT, &css->flags);
+		css->flags |= CSS_ROOT;
 	BUG_ON(cgrp->subsys[ss->subsys_id]);
 	cgrp->subsys[ss->subsys_id] = css;
 
 	/*
-	 * If !clear_css_refs, css holds an extra ref to @cgrp->dentry
-	 * which is put on the last css_put().  dput() requires process
-	 * context, which css_put() may be called without.  @css->dput_work
-	 * will be used to invoke dput() asynchronously from css_put().
+	 * css holds an extra ref to @cgrp->dentry which is put on the last
+	 * css_put().  dput() requires process context, which css_put() may
+	 * be called without.  @css->dput_work will be used to invoke
+	 * dput() asynchronously from css_put().
 	 */
 	INIT_WORK(&css->dput_work, css_dput_fn);
-	if (ss->__DEPRECATED_clear_css_refs)
-		set_bit(CSS_CLEAR_CSS_REFS, &css->flags);
+}
+
+/* invoke ->post_create() on a new CSS and mark it online if successful */
+static int online_css(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+	int ret = 0;
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	if (ss->css_online)
+		ret = ss->css_online(cgrp);
+	if (!ret)
+		cgrp->subsys[ss->subsys_id]->flags |= CSS_ONLINE;
+	return ret;
+}
+
+/* if the CSS is online, invoke ->pre_destory() on it and mark it offline */
+static void offline_css(struct cgroup_subsys *ss, struct cgroup *cgrp)
+	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
+{
+	struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	if (!(css->flags & CSS_ONLINE))
+		return;
+
+	/*
+	 * css_offline() should be called with cgroup_mutex unlocked.  See
+	 * 3fa59dfbc3 ("cgroup: fix potential deadlock in pre_destroy") for
+	 * details.  This temporary unlocking should go away once
+	 * cgroup_mutex is unexported from controllers.
+	 */
+	if (ss->css_offline) {
+		mutex_unlock(&cgroup_mutex);
+		ss->css_offline(cgrp);
+		mutex_lock(&cgroup_mutex);
+	}
+
+	cgrp->subsys[ss->subsys_id]->flags &= ~CSS_ONLINE;
 }
 
 /*
@@ -4049,10 +4106,27 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	struct cgroup_subsys *ss;
 	struct super_block *sb = root->sb;
 
+	/* allocate the cgroup and its ID, 0 is reserved for the root */
 	cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
 	if (!cgrp)
 		return -ENOMEM;
 
+	cgrp->id = ida_simple_get(&root->cgroup_ida, 1, 0, GFP_KERNEL);
+	if (cgrp->id < 0)
+		goto err_free_cgrp;
+
+	/*
+	 * Only live parents can have children.  Note that the liveliness
+	 * check isn't strictly necessary because cgroup_mkdir() and
+	 * cgroup_rmdir() are fully synchronized by i_mutex; however, do it
+	 * anyway so that locking is contained inside cgroup proper and we
+	 * don't get nasty surprises if we ever grow another caller.
+	 */
+	if (!cgroup_lock_live_group(parent)) {
+		err = -ENODEV;
+		goto err_free_id;
+	}
+
 	/* Grab a reference on the superblock so the hierarchy doesn't
 	 * get deleted on unmount if there are child cgroups.  This
 	 * can be done outside cgroup_mutex, since the sb can't
@@ -4060,8 +4134,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	 * fs */
 	atomic_inc(&sb->s_active);
 
-	mutex_lock(&cgroup_mutex);
-
 	init_cgroup_housekeeping(cgrp);
 
 	cgrp->parent = parent;
@@ -4071,26 +4143,51 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	if (notify_on_release(parent))
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 
-	if (clone_children(parent))
-		set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+	if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags))
+		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 
 	for_each_subsys(root, ss) {
 		struct cgroup_subsys_state *css;
 
-		css = ss->create(cgrp);
+		css = ss->css_alloc(cgrp);
 		if (IS_ERR(css)) {
 			err = PTR_ERR(css);
-			goto err_destroy;
+			goto err_free_all;
 		}
 		init_cgroup_css(css, ss, cgrp);
 		if (ss->use_id) {
 			err = alloc_css_id(ss, parent, cgrp);
 			if (err)
-				goto err_destroy;
+				goto err_free_all;
 		}
-		/* At error, ->destroy() callback has to free assigned ID. */
-		if (clone_children(parent) && ss->post_clone)
-			ss->post_clone(cgrp);
+	}
+
+	/*
+	 * Create directory.  cgroup_create_file() returns with the new
+	 * directory locked on success so that it can be populated without
+	 * dropping cgroup_mutex.
+	 */
+	err = cgroup_create_file(dentry, S_IFDIR | mode, sb);
+	if (err < 0)
+		goto err_free_all;
+	lockdep_assert_held(&dentry->d_inode->i_mutex);
+
+	/* allocation complete, commit to creation */
+	dentry->d_fsdata = cgrp;
+	cgrp->dentry = dentry;
+	list_add_tail(&cgrp->allcg_node, &root->allcg_list);
+	list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
+	root->number_of_cgroups++;
+
+	/* each css holds a ref to the cgroup's dentry */
+	for_each_subsys(root, ss)
+		dget(dentry);
+
+	/* creation succeeded, notify subsystems */
+	for_each_subsys(root, ss) {
+		err = online_css(ss, cgrp);
+		if (err)
+			goto err_destroy;
 
 		if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
 		    parent->parent) {
@@ -4102,50 +4199,34 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 		}
 	}
 
-	list_add(&cgrp->sibling, &cgrp->parent->children);
-	root->number_of_cgroups++;
-
-	err = cgroup_create_dir(cgrp, dentry, mode);
-	if (err < 0)
-		goto err_remove;
-
-	/* If !clear_css_refs, each css holds a ref to the cgroup's dentry */
-	for_each_subsys(root, ss)
-		if (!ss->__DEPRECATED_clear_css_refs)
-			dget(dentry);
-
-	/* The cgroup directory was pre-locked for us */
-	BUG_ON(!mutex_is_locked(&cgrp->dentry->d_inode->i_mutex));
-
-	list_add_tail(&cgrp->allcg_node, &root->allcg_list);
-
 	err = cgroup_populate_dir(cgrp, true, root->subsys_mask);
-	/* If err < 0, we have a half-filled directory - oh well ;) */
+	if (err)
+		goto err_destroy;
 
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
 
 	return 0;
 
- err_remove:
-
-	list_del(&cgrp->sibling);
-	root->number_of_cgroups--;
-
- err_destroy:
-
+err_free_all:
 	for_each_subsys(root, ss) {
 		if (cgrp->subsys[ss->subsys_id])
-			ss->destroy(cgrp);
+			ss->css_free(cgrp);
 	}
-
 	mutex_unlock(&cgroup_mutex);
-
 	/* Release the reference count that we took on the superblock */
 	deactivate_super(sb);
-
+err_free_id:
+	ida_simple_remove(&root->cgroup_ida, cgrp->id);
+err_free_cgrp:
 	kfree(cgrp);
 	return err;
+
+err_destroy:
+	cgroup_destroy_locked(cgrp);
+	mutex_unlock(&cgroup_mutex);
+	mutex_unlock(&dentry->d_inode->i_mutex);
+	return err;
 }
 
 static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
@@ -4197,153 +4278,60 @@ static int cgroup_has_css_refs(struct cgroup *cgrp)
 	return 0;
 }
 
-/*
- * Atomically mark all (or else none) of the cgroup's CSS objects as
- * CSS_REMOVED. Return true on success, or false if the cgroup has
- * busy subsystems. Call with cgroup_mutex held
- *
- * Depending on whether a subsys has __DEPRECATED_clear_css_refs set or
- * not, cgroup removal behaves differently.
- *
- * If clear is set, css refcnt for the subsystem should be zero before
- * cgroup removal can be committed.  This is implemented by
- * CGRP_WAIT_ON_RMDIR and retry logic around ->pre_destroy(), which may be
- * called multiple times until all css refcnts reach zero and is allowed to
- * veto removal on any invocation.  This behavior is deprecated and will be
- * removed as soon as the existing user (memcg) is updated.
- *
- * If clear is not set, each css holds an extra reference to the cgroup's
- * dentry and cgroup removal proceeds regardless of css refs.
- * ->pre_destroy() will be called at least once and is not allowed to fail.
- * On the last put of each css, whenever that may be, the extra dentry ref
- * is put so that dentry destruction happens only after all css's are
- * released.
- */
-static int cgroup_clear_css_refs(struct cgroup *cgrp)
+static int cgroup_destroy_locked(struct cgroup *cgrp)
+	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
 {
+	struct dentry *d = cgrp->dentry;
+	struct cgroup *parent = cgrp->parent;
+	DEFINE_WAIT(wait);
+	struct cgroup_event *event, *tmp;
 	struct cgroup_subsys *ss;
-	unsigned long flags;
-	bool failed = false;
+	LIST_HEAD(tmp_list);
+
+	lockdep_assert_held(&d->d_inode->i_mutex);
+	lockdep_assert_held(&cgroup_mutex);
 
-	local_irq_save(flags);
+	if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children))
+		return -EBUSY;
 
 	/*
-	 * Block new css_tryget() by deactivating refcnt.  If all refcnts
-	 * for subsystems w/ clear_css_refs set were 1 at the moment of
-	 * deactivation, we succeeded.
+	 * Block new css_tryget() by deactivating refcnt and mark @cgrp
+	 * removed.  This makes future css_tryget() and child creation
+	 * attempts fail thus maintaining the removal conditions verified
+	 * above.
 	 */
 	for_each_subsys(cgrp->root, ss) {
 		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
 
 		WARN_ON(atomic_read(&css->refcnt) < 0);
 		atomic_add(CSS_DEACT_BIAS, &css->refcnt);
-
-		if (ss->__DEPRECATED_clear_css_refs)
-			failed |= css_refcnt(css) != 1;
-	}
-
-	/*
-	 * If succeeded, set REMOVED and put all the base refs; otherwise,
-	 * restore refcnts to positive values.  Either way, all in-progress
-	 * css_tryget() will be released.
-	 */
-	for_each_subsys(cgrp->root, ss) {
-		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
-
-		if (!failed) {
-			set_bit(CSS_REMOVED, &css->flags);
-			css_put(css);
-		} else {
-			atomic_sub(CSS_DEACT_BIAS, &css->refcnt);
-		}
 	}
+	set_bit(CGRP_REMOVED, &cgrp->flags);
 
-	local_irq_restore(flags);
-	return !failed;
-}
-
-static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
-{
-	struct cgroup *cgrp = dentry->d_fsdata;
-	struct dentry *d;
-	struct cgroup *parent;
-	DEFINE_WAIT(wait);
-	struct cgroup_event *event, *tmp;
-	int ret;
-
-	/* the vfs holds both inode->i_mutex already */
-again:
-	mutex_lock(&cgroup_mutex);
-	if (atomic_read(&cgrp->count) != 0) {
-		mutex_unlock(&cgroup_mutex);
-		return -EBUSY;
-	}
-	if (!list_empty(&cgrp->children)) {
-		mutex_unlock(&cgroup_mutex);
-		return -EBUSY;
-	}
-	mutex_unlock(&cgroup_mutex);
-
-	/*
-	 * In general, subsystem has no css->refcnt after pre_destroy(). But
-	 * in racy cases, subsystem may have to get css->refcnt after
-	 * pre_destroy() and it makes rmdir return with -EBUSY. This sometimes
-	 * make rmdir return -EBUSY too often. To avoid that, we use waitqueue
-	 * for cgroup's rmdir. CGRP_WAIT_ON_RMDIR is for synchronizing rmdir
-	 * and subsystem's reference count handling. Please see css_get/put
-	 * and css_tryget() and cgroup_wakeup_rmdir_waiter() implementation.
-	 */
-	set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
+	/* tell subsystems to initate destruction */
+	for_each_subsys(cgrp->root, ss)
+		offline_css(ss, cgrp);
 
 	/*
-	 * Call pre_destroy handlers of subsys. Notify subsystems
-	 * that rmdir() request comes.
+	 * Put all the base refs.  Each css holds an extra reference to the
+	 * cgroup's dentry and cgroup removal proceeds regardless of css
+	 * refs.  On the last put of each css, whenever that may be, the
+	 * extra dentry ref is put so that dentry destruction happens only
+	 * after all css's are released.
 	 */
-	ret = cgroup_call_pre_destroy(cgrp);
-	if (ret) {
-		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
-		return ret;
-	}
-
-	mutex_lock(&cgroup_mutex);
-	parent = cgrp->parent;
-	if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
-		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
-		mutex_unlock(&cgroup_mutex);
-		return -EBUSY;
-	}
-	prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE);
-	if (!cgroup_clear_css_refs(cgrp)) {
-		mutex_unlock(&cgroup_mutex);
-		/*
-		 * Because someone may call cgroup_wakeup_rmdir_waiter() before
-		 * prepare_to_wait(), we need to check this flag.
-		 */
-		if (test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags))
-			schedule();
-		finish_wait(&cgroup_rmdir_waitq, &wait);
-		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
-		if (signal_pending(current))
-			return -EINTR;
-		goto again;
-	}
-	/* NO css_tryget() can success after here. */
-	finish_wait(&cgroup_rmdir_waitq, &wait);
-	clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
+	for_each_subsys(cgrp->root, ss)
+		css_put(cgrp->subsys[ss->subsys_id]);
 
 	raw_spin_lock(&release_list_lock);
-	set_bit(CGRP_REMOVED, &cgrp->flags);
 	if (!list_empty(&cgrp->release_list))
 		list_del_init(&cgrp->release_list);
 	raw_spin_unlock(&release_list_lock);
 
 	/* delete this cgroup from parent->children */
-	list_del_init(&cgrp->sibling);
-
+	list_del_rcu(&cgrp->sibling);
 	list_del_init(&cgrp->allcg_node);
 
-	d = dget(cgrp->dentry);
-
+	dget(d);
 	cgroup_d_remove_dir(d);
 	dput(d);
 
@@ -4353,21 +4341,35 @@ again:
 	/*
 	 * Unregister events and notify userspace.
 	 * Notify userspace about cgroup removing only after rmdir of cgroup
-	 * directory to avoid race between userspace and kernelspace
+	 * directory to avoid race between userspace and kernelspace. Use
+	 * a temporary list to avoid a deadlock with cgroup_event_wake(). Since
+	 * cgroup_event_wake() is called with the wait queue head locked,
+	 * remove_wait_queue() cannot be called while holding event_list_lock.
 	 */
 	spin_lock(&cgrp->event_list_lock);
-	list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
-		list_del(&event->list);
+	list_splice_init(&cgrp->event_list, &tmp_list);
+	spin_unlock(&cgrp->event_list_lock);
+	list_for_each_entry_safe(event, tmp, &tmp_list, list) {
+		list_del_init(&event->list);
 		remove_wait_queue(event->wqh, &event->wait);
 		eventfd_signal(event->eventfd, 1);
 		schedule_work(&event->remove);
 	}
-	spin_unlock(&cgrp->event_list_lock);
 
-	mutex_unlock(&cgroup_mutex);
 	return 0;
 }
 
+static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
+{
+	int ret;
+
+	mutex_lock(&cgroup_mutex);
+	ret = cgroup_destroy_locked(dentry->d_fsdata);
+	mutex_unlock(&cgroup_mutex);
+
+	return ret;
+}
+
 static void __init_or_module cgroup_init_cftsets(struct cgroup_subsys *ss)
 {
 	INIT_LIST_HEAD(&ss->cftsets);
@@ -4388,13 +4390,15 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 
 	printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name);
 
+	mutex_lock(&cgroup_mutex);
+
 	/* init base cftset */
 	cgroup_init_cftsets(ss);
 
 	/* Create the top cgroup state for this subsystem */
 	list_add(&ss->sibling, &rootnode.subsys_list);
 	ss->root = &rootnode;
-	css = ss->create(dummytop);
+	css = ss->css_alloc(dummytop);
 	/* We don't handle early failures gracefully */
 	BUG_ON(IS_ERR(css));
 	init_cgroup_css(css, ss, dummytop);
@@ -4403,7 +4407,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	 * pointer to this state - since the subsystem is
 	 * newly registered, all tasks and hence the
 	 * init_css_set is in the subsystem's top cgroup. */
-	init_css_set.subsys[ss->subsys_id] = dummytop->subsys[ss->subsys_id];
+	init_css_set.subsys[ss->subsys_id] = css;
 
 	need_forkexit_callback |= ss->fork || ss->exit;
 
@@ -4413,6 +4417,9 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	BUG_ON(!list_empty(&init_task.tasks));
 
 	ss->active = 1;
+	BUG_ON(online_css(ss, dummytop));
+
+	mutex_unlock(&cgroup_mutex);
 
 	/* this function shouldn't be used with modular subsystems, since they
 	 * need to register a subsys_id, among other things */
@@ -4430,12 +4437,12 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
  */
 int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 {
-	int i;
 	struct cgroup_subsys_state *css;
+	int i, ret;
 
 	/* check name and function validity */
 	if (ss->name == NULL || strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN ||
-	    ss->create == NULL || ss->destroy == NULL)
+	    ss->css_alloc == NULL || ss->css_free == NULL)
 		return -EINVAL;
 
 	/*
@@ -4464,10 +4471,11 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	subsys[ss->subsys_id] = ss;
 
 	/*
-	 * no ss->create seems to need anything important in the ss struct, so
-	 * this can happen first (i.e. before the rootnode attachment).
+	 * no ss->css_alloc seems to need anything important in the ss
+	 * struct, so this can happen first (i.e. before the rootnode
+	 * attachment).
 	 */
-	css = ss->create(dummytop);
+	css = ss->css_alloc(dummytop);
 	if (IS_ERR(css)) {
 		/* failure case - need to deassign the subsys[] slot. */
 		subsys[ss->subsys_id] = NULL;
@@ -4482,14 +4490,9 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	init_cgroup_css(css, ss, dummytop);
 	/* init_idr must be after init_cgroup_css because it sets css->id. */
 	if (ss->use_id) {
-		int ret = cgroup_init_idr(ss, css);
-		if (ret) {
-			dummytop->subsys[ss->subsys_id] = NULL;
-			ss->destroy(dummytop);
-			subsys[ss->subsys_id] = NULL;
-			mutex_unlock(&cgroup_mutex);
-			return ret;
-		}
+		ret = cgroup_init_idr(ss, css);
+		if (ret)
+			goto err_unload;
 	}
 
 	/*
@@ -4522,10 +4525,19 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	write_unlock(&css_set_lock);
 
 	ss->active = 1;
+	ret = online_css(ss, dummytop);
+	if (ret)
+		goto err_unload;
 
 	/* success! */
 	mutex_unlock(&cgroup_mutex);
 	return 0;
+
+err_unload:
+	mutex_unlock(&cgroup_mutex);
+	/* @ss can't be mounted here as try_module_get() would fail */
+	cgroup_unload_subsys(ss);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(cgroup_load_subsys);
 
@@ -4552,6 +4564,15 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 	BUG_ON(ss->root != &rootnode);
 
 	mutex_lock(&cgroup_mutex);
+
+	offline_css(ss, dummytop);
+	ss->active = 0;
+
+	if (ss->use_id) {
+		idr_remove_all(&ss->idr);
+		idr_destroy(&ss->idr);
+	}
+
 	/* deassign the subsys_id */
 	subsys[ss->subsys_id] = NULL;
 
@@ -4567,7 +4588,6 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 		struct css_set *cg = link->cg;
 
 		hlist_del(&cg->hlist);
-		BUG_ON(!cg->subsys[ss->subsys_id]);
 		cg->subsys[ss->subsys_id] = NULL;
 		hhead = css_set_hash(cg->subsys);
 		hlist_add_head(&cg->hlist, hhead);
@@ -4575,12 +4595,12 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 	write_unlock(&css_set_lock);
 
 	/*
-	 * remove subsystem's css from the dummytop and free it - need to free
-	 * before marking as null because ss->destroy needs the cgrp->subsys
-	 * pointer to find their state. note that this also takes care of
-	 * freeing the css_id.
+	 * remove subsystem's css from the dummytop and free it - need to
+	 * free before marking as null because ss->css_free needs the
+	 * cgrp->subsys pointer to find their state. note that this also
+	 * takes care of freeing the css_id.
 	 */
-	ss->destroy(dummytop);
+	ss->css_free(dummytop);
 	dummytop->subsys[ss->subsys_id] = NULL;
 
 	mutex_unlock(&cgroup_mutex);
@@ -4624,8 +4644,8 @@ int __init cgroup_init_early(void)
 
 		BUG_ON(!ss->name);
 		BUG_ON(strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN);
-		BUG_ON(!ss->create);
-		BUG_ON(!ss->destroy);
+		BUG_ON(!ss->css_alloc);
+		BUG_ON(!ss->css_free);
 		if (ss->subsys_id != i) {
 			printk(KERN_ERR "cgroup: Subsys %s id == %d\n",
 			       ss->name, ss->subsys_id);
@@ -4831,45 +4851,20 @@ void cgroup_fork(struct task_struct *child)
 	INIT_LIST_HEAD(&child->cg_list);
 }
 
-/**
- * cgroup_fork_callbacks - run fork callbacks
- * @child: the new task
- *
- * Called on a new task very soon before adding it to the
- * tasklist. No need to take any locks since no-one can
- * be operating on this task.
- */
-void cgroup_fork_callbacks(struct task_struct *child)
-{
-	if (need_forkexit_callback) {
-		int i;
-		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-			struct cgroup_subsys *ss = subsys[i];
-
-			/*
-			 * forkexit callbacks are only supported for
-			 * builtin subsystems.
-			 */
-			if (!ss || ss->module)
-				continue;
-
-			if (ss->fork)
-				ss->fork(child);
-		}
-	}
-}
-
 /**
  * cgroup_post_fork - called on a new task after adding it to the task list
  * @child: the task in question
  *
- * Adds the task to the list running through its css_set if necessary.
- * Has to be after the task is visible on the task list in case we race
- * with the first call to cgroup_iter_start() - to guarantee that the
- * new task ends up on its list.
+ * Adds the task to the list running through its css_set if necessary and
+ * call the subsystem fork() callbacks.  Has to be after the task is
+ * visible on the task list in case we race with the first call to
+ * cgroup_iter_start() - to guarantee that the new task ends up on its
+ * list.
  */
 void cgroup_post_fork(struct task_struct *child)
 {
+	int i;
+
 	/*
 	 * use_task_css_set_links is set to 1 before we walk the tasklist
 	 * under the tasklist_lock and we read it here after we added the child
@@ -4889,7 +4884,30 @@ void cgroup_post_fork(struct task_struct *child)
 		task_unlock(child);
 		write_unlock(&css_set_lock);
 	}
+
+	/*
+	 * Call ss->fork().  This must happen after @child is linked on
+	 * css_set; otherwise, @child might change state between ->fork()
+	 * and addition to css_set.
+	 */
+	if (need_forkexit_callback) {
+		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+			struct cgroup_subsys *ss = subsys[i];
+
+			/*
+			 * fork/exit callbacks are supported only for
+			 * builtin subsystems and we don't need further
+			 * synchronization as they never go away.
+			 */
+			if (!ss || ss->module)
+				continue;
+
+			if (ss->fork)
+				ss->fork(child);
+		}
+	}
 }
+
 /**
  * cgroup_exit - detach cgroup from exiting task
  * @tsk: pointer to task_struct of exiting process
@@ -5022,15 +5040,17 @@ static void check_for_release(struct cgroup *cgrp)
 /* Caller must verify that the css is not for root cgroup */
 bool __css_tryget(struct cgroup_subsys_state *css)
 {
-	do {
-		int v = css_refcnt(css);
+	while (true) {
+		int t, v;
 
-		if (atomic_cmpxchg(&css->refcnt, v, v + 1) == v)
+		v = css_refcnt(css);
+		t = atomic_cmpxchg(&css->refcnt, v, v + 1);
+		if (likely(t == v))
 			return true;
+		else if (t < 0)
+			return false;
 		cpu_relax();
-	} while (!test_bit(CSS_REMOVED, &css->flags));
-
-	return false;
+	}
 }
 EXPORT_SYMBOL_GPL(__css_tryget);
 
@@ -5049,11 +5069,9 @@ void __css_put(struct cgroup_subsys_state *css)
 			set_bit(CGRP_RELEASABLE, &cgrp->flags);
 			check_for_release(cgrp);
 		}
-		cgroup_wakeup_rmdir_waiter(cgrp);
 		break;
 	case 0:
-		if (!test_bit(CSS_CLEAR_CSS_REFS, &css->flags))
-			schedule_work(&css->dput_work);
+		schedule_work(&css->dput_work);
 		break;
 	}
 	rcu_read_unlock();
@@ -5439,7 +5457,7 @@ struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id)
 }
 
 #ifdef CONFIG_CGROUP_DEBUG
-static struct cgroup_subsys_state *debug_create(struct cgroup *cont)
+static struct cgroup_subsys_state *debug_css_alloc(struct cgroup *cont)
 {
 	struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
 
@@ -5449,7 +5467,7 @@ static struct cgroup_subsys_state *debug_create(struct cgroup *cont)
 	return css;
 }
 
-static void debug_destroy(struct cgroup *cont)
+static void debug_css_free(struct cgroup *cont)
 {
 	kfree(cont->subsys[debug_subsys_id]);
 }
@@ -5578,8 +5596,8 @@ static struct cftype debug_files[] =  {
 
 struct cgroup_subsys debug_subsys = {
 	.name = "debug",
-	.create = debug_create,
-	.destroy = debug_destroy,
+	.css_alloc = debug_css_alloc,
+	.css_free = debug_css_free,
 	.subsys_id = debug_subsys_id,
 	.base_cftypes = debug_files,
 };

kernel/cgroup_freezer.c

@@ -22,24 +22,33 @@
 #include <linux/freezer.h>
 #include <linux/seq_file.h>
 
-enum freezer_state {
-	CGROUP_THAWED = 0,
-	CGROUP_FREEZING,
-	CGROUP_FROZEN,
+/*
+ * A cgroup is freezing if any FREEZING flags are set.  FREEZING_SELF is
+ * set if "FROZEN" is written to freezer.state cgroupfs file, and cleared
+ * for "THAWED".  FREEZING_PARENT is set if the parent freezer is FREEZING
+ * for whatever reason.  IOW, a cgroup has FREEZING_PARENT set if one of
+ * its ancestors has FREEZING_SELF set.
+ */
+enum freezer_state_flags {
+	CGROUP_FREEZER_ONLINE	= (1 << 0), /* freezer is fully online */
+	CGROUP_FREEZING_SELF	= (1 << 1), /* this freezer is freezing */
+	CGROUP_FREEZING_PARENT	= (1 << 2), /* the parent freezer is freezing */
+	CGROUP_FROZEN		= (1 << 3), /* this and its descendants frozen */
+
+	/* mask for all FREEZING flags */
+	CGROUP_FREEZING		= CGROUP_FREEZING_SELF | CGROUP_FREEZING_PARENT,
 };
 
 struct freezer {
-	struct cgroup_subsys_state css;
-	enum freezer_state state;
-	spinlock_t lock; /* protects _writes_ to state */
+	struct cgroup_subsys_state	css;
+	unsigned int			state;
+	spinlock_t			lock;
 };
 
-static inline struct freezer *cgroup_freezer(
-		struct cgroup *cgroup)
+static inline struct freezer *cgroup_freezer(struct cgroup *cgroup)
 {
-	return container_of(
-		cgroup_subsys_state(cgroup, freezer_subsys_id),
-		struct freezer, css);
+	return container_of(cgroup_subsys_state(cgroup, freezer_subsys_id),
+			    struct freezer, css);
 }
 
 static inline struct freezer *task_freezer(struct task_struct *task)
@@ -48,14 +57,21 @@ static inline struct freezer *task_freezer(struct task_struct *task)
 			    struct freezer, css);
 }
 
+static struct freezer *parent_freezer(struct freezer *freezer)
+{
+	struct cgroup *pcg = freezer->css.cgroup->parent;
+
+	if (pcg)
+		return cgroup_freezer(pcg);
+	return NULL;
+}
+
 bool cgroup_freezing(struct task_struct *task)
 {
-	enum freezer_state state;
 	bool ret;
 
 	rcu_read_lock();
-	state = task_freezer(task)->state;
-	ret = state == CGROUP_FREEZING || state == CGROUP_FROZEN;
+	ret = task_freezer(task)->state & CGROUP_FREEZING;
 	rcu_read_unlock();
 
 	return ret;
@@ -65,70 +81,18 @@ bool cgroup_freezing(struct task_struct *task)
  * cgroups_write_string() limits the size of freezer state strings to
  * CGROUP_LOCAL_BUFFER_SIZE
  */
-static const char *freezer_state_strs[] = {
-	"THAWED",
-	"FREEZING",
-	"FROZEN",
+static const char *freezer_state_strs(unsigned int state)
+{
+	if (state & CGROUP_FROZEN)
+		return "FROZEN";
+	if (state & CGROUP_FREEZING)
+		return "FREEZING";
+	return "THAWED";
 };
 
-/*
- * State diagram
- * Transitions are caused by userspace writes to the freezer.state file.
- * The values in parenthesis are state labels. The rest are edge labels.
- *
- * (THAWED) --FROZEN--> (FREEZING) --FROZEN--> (FROZEN)
- *    ^ ^                    |                     |
- *    | \_______THAWED_______/                     |
- *    \__________________________THAWED____________/
- */
-
 struct cgroup_subsys freezer_subsys;
 
-/* Locks taken and their ordering
- * ------------------------------
- * cgroup_mutex (AKA cgroup_lock)
- * freezer->lock
- * css_set_lock
- * task->alloc_lock (AKA task_lock)
- * task->sighand->siglock
- *
- * cgroup code forces css_set_lock to be taken before task->alloc_lock
- *
- * freezer_create(), freezer_destroy():
- * cgroup_mutex [ by cgroup core ]
- *
- * freezer_can_attach():
- * cgroup_mutex (held by caller of can_attach)
- *
- * freezer_fork() (preserving fork() performance means can't take cgroup_mutex):
- * freezer->lock
- *  sighand->siglock (if the cgroup is freezing)
- *
- * freezer_read():
- * cgroup_mutex
- *  freezer->lock
- *   write_lock css_set_lock (cgroup iterator start)
- *    task->alloc_lock
- *   read_lock css_set_lock (cgroup iterator start)
- *
- * freezer_write() (freeze):
- * cgroup_mutex
- *  freezer->lock
- *   write_lock css_set_lock (cgroup iterator start)
- *    task->alloc_lock
- *   read_lock css_set_lock (cgroup iterator start)
- *    sighand->siglock (fake signal delivery inside freeze_task())
- *
- * freezer_write() (unfreeze):
- * cgroup_mutex
- *  freezer->lock
- *   write_lock css_set_lock (cgroup iterator start)
- *    task->alloc_lock
- *   read_lock css_set_lock (cgroup iterator start)
- *    task->alloc_lock (inside __thaw_task(), prevents race with refrigerator())
- *     sighand->siglock
- */
-static struct cgroup_subsys_state *freezer_create(struct cgroup *cgroup)
+static struct cgroup_subsys_state *freezer_css_alloc(struct cgroup *cgroup)
 {
 	struct freezer *freezer;
 
@@ -137,160 +101,244 @@ static struct cgroup_subsys_state *freezer_create(struct cgroup *cgroup)
 		return ERR_PTR(-ENOMEM);
 
 	spin_lock_init(&freezer->lock);
-	freezer->state = CGROUP_THAWED;
 	return &freezer->css;
 }
 
-static void freezer_destroy(struct cgroup *cgroup)
+/**
+ * freezer_css_online - commit creation of a freezer cgroup
+ * @cgroup: cgroup being created
+ *
+ * We're committing to creation of @cgroup.  Mark it online and inherit
+ * parent's freezing state while holding both parent's and our
+ * freezer->lock.
+ */
+static int freezer_css_online(struct cgroup *cgroup)
+{
+	struct freezer *freezer = cgroup_freezer(cgroup);
+	struct freezer *parent = parent_freezer(freezer);
+
+	/*
+	 * The following double locking and freezing state inheritance
+	 * guarantee that @cgroup can never escape ancestors' freezing
+	 * states.  See cgroup_for_each_descendant_pre() for details.
+	 */
+	if (parent)
+		spin_lock_irq(&parent->lock);
+	spin_lock_nested(&freezer->lock, SINGLE_DEPTH_NESTING);
+
+	freezer->state |= CGROUP_FREEZER_ONLINE;
+
+	if (parent && (parent->state & CGROUP_FREEZING)) {
+		freezer->state |= CGROUP_FREEZING_PARENT | CGROUP_FROZEN;
+		atomic_inc(&system_freezing_cnt);
+	}
+
+	spin_unlock(&freezer->lock);
+	if (parent)
+		spin_unlock_irq(&parent->lock);
+
+	return 0;
+}
+
+/**
+ * freezer_css_offline - initiate destruction of @cgroup
+ * @cgroup: cgroup being destroyed
+ *
+ * @cgroup is going away.  Mark it dead and decrement system_freezing_count
+ * if it was holding one.
+ */
+static void freezer_css_offline(struct cgroup *cgroup)
 {
 	struct freezer *freezer = cgroup_freezer(cgroup);
 
-	if (freezer->state != CGROUP_THAWED)
+	spin_lock_irq(&freezer->lock);
+
+	if (freezer->state & CGROUP_FREEZING)
 		atomic_dec(&system_freezing_cnt);
-	kfree(freezer);
+
+	freezer->state = 0;
+
+	spin_unlock_irq(&freezer->lock);
 }
 
-/* task is frozen or will freeze immediately when next it gets woken */
-static bool is_task_frozen_enough(struct task_struct *task)
+static void freezer_css_free(struct cgroup *cgroup)
 {
-	return frozen(task) ||
-		(task_is_stopped_or_traced(task) && freezing(task));
+	kfree(cgroup_freezer(cgroup));
 }
 
 /*
- * The call to cgroup_lock() in the freezer.state write method prevents
- * a write to that file racing against an attach, and hence the
- * can_attach() result will remain valid until the attach completes.
+ * Tasks can be migrated into a different freezer anytime regardless of its
+ * current state.  freezer_attach() is responsible for making new tasks
+ * conform to the current state.
+ *
+ * Freezer state changes and task migration are synchronized via
+ * @freezer->lock.  freezer_attach() makes the new tasks conform to the
+ * current state and all following state changes can see the new tasks.
  */
-static int freezer_can_attach(struct cgroup *new_cgroup,
-			      struct cgroup_taskset *tset)
+static void freezer_attach(struct cgroup *new_cgrp, struct cgroup_taskset *tset)
 {
-	struct freezer *freezer;
+	struct freezer *freezer = cgroup_freezer(new_cgrp);
 	struct task_struct *task;
+	bool clear_frozen = false;
+
+	spin_lock_irq(&freezer->lock);
 
 	/*
-	 * Anything frozen can't move or be moved to/from.
+	 * Make the new tasks conform to the current state of @new_cgrp.
+	 * For simplicity, when migrating any task to a FROZEN cgroup, we
+	 * revert it to FREEZING and let update_if_frozen() determine the
+	 * correct state later.
+	 *
+	 * Tasks in @tset are on @new_cgrp but may not conform to its
+	 * current state before executing the following - !frozen tasks may
+	 * be visible in a FROZEN cgroup and frozen tasks in a THAWED one.
 	 */
-	cgroup_taskset_for_each(task, new_cgroup, tset)
-		if (cgroup_freezing(task))
-			return -EBUSY;
+	cgroup_taskset_for_each(task, new_cgrp, tset) {
+		if (!(freezer->state & CGROUP_FREEZING)) {
+			__thaw_task(task);
+		} else {
+			freeze_task(task);
+			freezer->state &= ~CGROUP_FROZEN;
+			clear_frozen = true;
+		}
+	}
 
-	freezer = cgroup_freezer(new_cgroup);
-	if (freezer->state != CGROUP_THAWED)
-		return -EBUSY;
+	spin_unlock_irq(&freezer->lock);
 
-	return 0;
+	/*
+	 * Propagate FROZEN clearing upwards.  We may race with
+	 * update_if_frozen(), but as long as both work bottom-up, either
+	 * update_if_frozen() sees child's FROZEN cleared or we clear the
+	 * parent's FROZEN later.  No parent w/ !FROZEN children can be
+	 * left FROZEN.
+	 */
+	while (clear_frozen && (freezer = parent_freezer(freezer))) {
+		spin_lock_irq(&freezer->lock);
+		freezer->state &= ~CGROUP_FROZEN;
+		clear_frozen = freezer->state & CGROUP_FREEZING;
+		spin_unlock_irq(&freezer->lock);
+	}
 }
 
 static void freezer_fork(struct task_struct *task)
 {
 	struct freezer *freezer;
 
-	/*
-	 * No lock is needed, since the task isn't on tasklist yet,
-	 * so it can't be moved to another cgroup, which means the
-	 * freezer won't be removed and will be valid during this
-	 * function call.  Nevertheless, apply RCU read-side critical
-	 * section to suppress RCU lockdep false positives.
-	 */
 	rcu_read_lock();
 	freezer = task_freezer(task);
-	rcu_read_unlock();
 
 	/*
 	 * The root cgroup is non-freezable, so we can skip the
 	 * following check.
 	 */
 	if (!freezer->css.cgroup->parent)
-		return;
+		goto out;
 
 	spin_lock_irq(&freezer->lock);
-	BUG_ON(freezer->state == CGROUP_FROZEN);
-
-	/* Locking avoids race with FREEZING -> THAWED transitions. */
-	if (freezer->state == CGROUP_FREEZING)
+	if (freezer->state & CGROUP_FREEZING)
 		freeze_task(task);
 	spin_unlock_irq(&freezer->lock);
+out:
+	rcu_read_unlock();
 }
 
-/*
- * caller must hold freezer->lock
+/**
+ * update_if_frozen - update whether a cgroup finished freezing
+ * @cgroup: cgroup of interest
+ *
+ * Once FREEZING is initiated, transition to FROZEN is lazily updated by
+ * calling this function.  If the current state is FREEZING but not FROZEN,
+ * this function checks whether all tasks of this cgroup and the descendant
+ * cgroups finished freezing and, if so, sets FROZEN.
+ *
+ * The caller is responsible for grabbing RCU read lock and calling
+ * update_if_frozen() on all descendants prior to invoking this function.
+ *
+ * Task states and freezer state might disagree while tasks are being
+ * migrated into or out of @cgroup, so we can't verify task states against
+ * @freezer state here.  See freezer_attach() for details.
  */
-static void update_if_frozen(struct cgroup *cgroup,
-				 struct freezer *freezer)
+static void update_if_frozen(struct cgroup *cgroup)
 {
+	struct freezer *freezer = cgroup_freezer(cgroup);
+	struct cgroup *pos;
 	struct cgroup_iter it;
 	struct task_struct *task;
-	unsigned int nfrozen = 0, ntotal = 0;
-	enum freezer_state old_state = freezer->state;
 
-	cgroup_iter_start(cgroup, &it);
-	while ((task = cgroup_iter_next(cgroup, &it))) {
-		ntotal++;
-		if (freezing(task) && is_task_frozen_enough(task))
-			nfrozen++;
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	spin_lock_irq(&freezer->lock);
+
+	if (!(freezer->state & CGROUP_FREEZING) ||
+	    (freezer->state & CGROUP_FROZEN))
+		goto out_unlock;
+
+	/* are all (live) children frozen? */
+	cgroup_for_each_child(pos, cgroup) {
+		struct freezer *child = cgroup_freezer(pos);
+
+		if ((child->state & CGROUP_FREEZER_ONLINE) &&
+		    !(child->state & CGROUP_FROZEN))
+			goto out_unlock;
 	}
 
-	if (old_state == CGROUP_THAWED) {
-		BUG_ON(nfrozen > 0);
-	} else if (old_state == CGROUP_FREEZING) {
-		if (nfrozen == ntotal)
-			freezer->state = CGROUP_FROZEN;
-	} else { /* old_state == CGROUP_FROZEN */
-		BUG_ON(nfrozen != ntotal);
+	/* are all tasks frozen? */
+	cgroup_iter_start(cgroup, &it);
+
+	while ((task = cgroup_iter_next(cgroup, &it))) {
+		if (freezing(task)) {
+			/*
+			 * freezer_should_skip() indicates that the task
+			 * should be skipped when determining freezing
+			 * completion.  Consider it frozen in addition to
+			 * the usual frozen condition.
+			 */
+			if (!frozen(task) && !freezer_should_skip(task))
+				goto out_iter_end;
+		}
 	}
 
+	freezer->state |= CGROUP_FROZEN;
+out_iter_end:
 	cgroup_iter_end(cgroup, &it);
+out_unlock:
+	spin_unlock_irq(&freezer->lock);
 }
 
 static int freezer_read(struct cgroup *cgroup, struct cftype *cft,
 			struct seq_file *m)
 {
-	struct freezer *freezer;
-	enum freezer_state state;
+	struct cgroup *pos;
 
-	if (!cgroup_lock_live_group(cgroup))
-		return -ENODEV;
+	rcu_read_lock();
 
-	freezer = cgroup_freezer(cgroup);
-	spin_lock_irq(&freezer->lock);
-	state = freezer->state;
-	if (state == CGROUP_FREEZING) {
-		/* We change from FREEZING to FROZEN lazily if the cgroup was
-		 * only partially frozen when we exitted write. */
-		update_if_frozen(cgroup, freezer);
-		state = freezer->state;
-	}
-	spin_unlock_irq(&freezer->lock);
-	cgroup_unlock();
+	/* update states bottom-up */
+	cgroup_for_each_descendant_post(pos, cgroup)
+		update_if_frozen(pos);
+	update_if_frozen(cgroup);
+
+	rcu_read_unlock();
 
-	seq_puts(m, freezer_state_strs[state]);
+	seq_puts(m, freezer_state_strs(cgroup_freezer(cgroup)->state));
 	seq_putc(m, '\n');
 	return 0;
 }
 
-static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
+static void freeze_cgroup(struct freezer *freezer)
 {
+	struct cgroup *cgroup = freezer->css.cgroup;
 	struct cgroup_iter it;
 	struct task_struct *task;
-	unsigned int num_cant_freeze_now = 0;
 
 	cgroup_iter_start(cgroup, &it);
-	while ((task = cgroup_iter_next(cgroup, &it))) {
-		if (!freeze_task(task))
-			continue;
-		if (is_task_frozen_enough(task))
-			continue;
-		if (!freezing(task) && !freezer_should_skip(task))
-			num_cant_freeze_now++;
-	}
+	while ((task = cgroup_iter_next(cgroup, &it)))
+		freeze_task(task);
 	cgroup_iter_end(cgroup, &it);
-
-	return num_cant_freeze_now ? -EBUSY : 0;
 }
 
-static void unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
+static void unfreeze_cgroup(struct freezer *freezer)
 {
+	struct cgroup *cgroup = freezer->css.cgroup;
 	struct cgroup_iter it;
 	struct task_struct *task;
 
@@ -300,59 +348,111 @@ static void unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
 	cgroup_iter_end(cgroup, &it);
 }
 
-static int freezer_change_state(struct cgroup *cgroup,
-				enum freezer_state goal_state)
+/**
+ * freezer_apply_state - apply state change to a single cgroup_freezer
+ * @freezer: freezer to apply state change to
+ * @freeze: whether to freeze or unfreeze
+ * @state: CGROUP_FREEZING_* flag to set or clear
+ *
+ * Set or clear @state on @cgroup according to @freeze, and perform
+ * freezing or thawing as necessary.
+ */
+static void freezer_apply_state(struct freezer *freezer, bool freeze,
+				unsigned int state)
 {
-	struct freezer *freezer;
-	int retval = 0;
-
-	freezer = cgroup_freezer(cgroup);
+	/* also synchronizes against task migration, see freezer_attach() */
+	lockdep_assert_held(&freezer->lock);
 
-	spin_lock_irq(&freezer->lock);
+	if (!(freezer->state & CGROUP_FREEZER_ONLINE))
+		return;
 
-	update_if_frozen(cgroup, freezer);
-
-	switch (goal_state) {
-	case CGROUP_THAWED:
-		if (freezer->state != CGROUP_THAWED)
-			atomic_dec(&system_freezing_cnt);
-		freezer->state = CGROUP_THAWED;
-		unfreeze_cgroup(cgroup, freezer);
-		break;
-	case CGROUP_FROZEN:
-		if (freezer->state == CGROUP_THAWED)
+	if (freeze) {
+		if (!(freezer->state & CGROUP_FREEZING))
 			atomic_inc(&system_freezing_cnt);
-		freezer->state = CGROUP_FREEZING;
-		retval = try_to_freeze_cgroup(cgroup, freezer);
-		break;
-	default:
-		BUG();
+		freezer->state |= state;
+		freeze_cgroup(freezer);
+	} else {
+		bool was_freezing = freezer->state & CGROUP_FREEZING;
+
+		freezer->state &= ~state;
+
+		if (!(freezer->state & CGROUP_FREEZING)) {
+			if (was_freezing)
+				atomic_dec(&system_freezing_cnt);
+			freezer->state &= ~CGROUP_FROZEN;
+			unfreeze_cgroup(freezer);
+		}
 	}
+}
 
+/**
+ * freezer_change_state - change the freezing state of a cgroup_freezer
+ * @freezer: freezer of interest
+ * @freeze: whether to freeze or thaw
+ *
+ * Freeze or thaw @freezer according to @freeze.  The operations are
+ * recursive - all descendants of @freezer will be affected.
+ */
+static void freezer_change_state(struct freezer *freezer, bool freeze)
+{
+	struct cgroup *pos;
+
+	/* update @freezer */
+	spin_lock_irq(&freezer->lock);
+	freezer_apply_state(freezer, freeze, CGROUP_FREEZING_SELF);
 	spin_unlock_irq(&freezer->lock);
 
-	return retval;
+	/*
+	 * Update all its descendants in pre-order traversal.  Each
+	 * descendant will try to inherit its parent's FREEZING state as
+	 * CGROUP_FREEZING_PARENT.
+	 */
+	rcu_read_lock();
+	cgroup_for_each_descendant_pre(pos, freezer->css.cgroup) {
+		struct freezer *pos_f = cgroup_freezer(pos);
+		struct freezer *parent = parent_freezer(pos_f);
+
+		/*
+		 * Our update to @parent->state is already visible which is
+		 * all we need.  No need to lock @parent.  For more info on
+		 * synchronization, see freezer_post_create().
+		 */
+		spin_lock_irq(&pos_f->lock);
+		freezer_apply_state(pos_f, parent->state & CGROUP_FREEZING,
+				    CGROUP_FREEZING_PARENT);
+		spin_unlock_irq(&pos_f->lock);
+	}
+	rcu_read_unlock();
 }
 
-static int freezer_write(struct cgroup *cgroup,
-			 struct cftype *cft,
+static int freezer_write(struct cgroup *cgroup, struct cftype *cft,
 			 const char *buffer)
 {
-	int retval;
-	enum freezer_state goal_state;
+	bool freeze;
 
-	if (strcmp(buffer, freezer_state_strs[CGROUP_THAWED]) == 0)
-		goal_state = CGROUP_THAWED;
-	else if (strcmp(buffer, freezer_state_strs[CGROUP_FROZEN]) == 0)
-		goal_state = CGROUP_FROZEN;
+	if (strcmp(buffer, freezer_state_strs(0)) == 0)
+		freeze = false;
+	else if (strcmp(buffer, freezer_state_strs(CGROUP_FROZEN)) == 0)
+		freeze = true;
 	else
 		return -EINVAL;
 
-	if (!cgroup_lock_live_group(cgroup))
-		return -ENODEV;
-	retval = freezer_change_state(cgroup, goal_state);
-	cgroup_unlock();
-	return retval;
+	freezer_change_state(cgroup_freezer(cgroup), freeze);
+	return 0;
+}
+
+static u64 freezer_self_freezing_read(struct cgroup *cgroup, struct cftype *cft)
+{
+	struct freezer *freezer = cgroup_freezer(cgroup);
+
+	return (bool)(freezer->state & CGROUP_FREEZING_SELF);
+}
+
+static u64 freezer_parent_freezing_read(struct cgroup *cgroup, struct cftype *cft)
+{
+	struct freezer *freezer = cgroup_freezer(cgroup);
+
+	return (bool)(freezer->state & CGROUP_FREEZING_PARENT);
 }
 
 static struct cftype files[] = {
@@ -362,23 +462,27 @@ static struct cftype files[] = {
 		.read_seq_string = freezer_read,
 		.write_string = freezer_write,
 	},
+	{
+		.name = "self_freezing",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = freezer_self_freezing_read,
+	},
+	{
+		.name = "parent_freezing",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = freezer_parent_freezing_read,
+	},
 	{ }	/* terminate */
 };
 
 struct cgroup_subsys freezer_subsys = {
 	.name		= "freezer",
-	.create		= freezer_create,
-	.destroy	= freezer_destroy,
+	.css_alloc	= freezer_css_alloc,
+	.css_online	= freezer_css_online,
+	.css_offline	= freezer_css_offline,
+	.css_free	= freezer_css_free,
 	.subsys_id	= freezer_subsys_id,
-	.can_attach	= freezer_can_attach,
+	.attach		= freezer_attach,
 	.fork		= freezer_fork,
 	.base_cftypes	= files,
-
-	/*
-	 * freezer subsys doesn't handle hierarchy at all.  Frozen state
-	 * should be inherited through the hierarchy - if a parent is
-	 * frozen, all its children should be frozen.  Fix it and remove
-	 * the following.
-	 */
-	.broken_hierarchy = true,
 };

kernel/cpuset.c

@@ -1784,56 +1784,20 @@ static struct cftype files[] = {
 };
 
 /*
- * post_clone() is called during cgroup_create() when the
- * clone_children mount argument was specified.  The cgroup
- * can not yet have any tasks.
- *
- * Currently we refuse to set up the cgroup - thereby
- * refusing the task to be entered, and as a result refusing
- * the sys_unshare() or clone() which initiated it - if any
- * sibling cpusets have exclusive cpus or mem.
- *
- * If this becomes a problem for some users who wish to
- * allow that scenario, then cpuset_post_clone() could be
- * changed to grant parent->cpus_allowed-sibling_cpus_exclusive
- * (and likewise for mems) to the new cgroup. Called with cgroup_mutex
- * held.
- */
-static void cpuset_post_clone(struct cgroup *cgroup)
-{
-	struct cgroup *parent, *child;
-	struct cpuset *cs, *parent_cs;
-
-	parent = cgroup->parent;
-	list_for_each_entry(child, &parent->children, sibling) {
-		cs = cgroup_cs(child);
-		if (is_mem_exclusive(cs) || is_cpu_exclusive(cs))
-			return;
-	}
-	cs = cgroup_cs(cgroup);
-	parent_cs = cgroup_cs(parent);
-
-	mutex_lock(&callback_mutex);
-	cs->mems_allowed = parent_cs->mems_allowed;
-	cpumask_copy(cs->cpus_allowed, parent_cs->cpus_allowed);
-	mutex_unlock(&callback_mutex);
-	return;
-}
-
-/*
- *	cpuset_create - create a cpuset
+ *	cpuset_css_alloc - allocate a cpuset css
  *	cont:	control group that the new cpuset will be part of
  */
 
-static struct cgroup_subsys_state *cpuset_create(struct cgroup *cont)
+static struct cgroup_subsys_state *cpuset_css_alloc(struct cgroup *cont)
 {
-	struct cpuset *cs;
-	struct cpuset *parent;
+	struct cgroup *parent_cg = cont->parent;
+	struct cgroup *tmp_cg;
+	struct cpuset *parent, *cs;
 
-	if (!cont->parent) {
+	if (!parent_cg)
 		return &top_cpuset.css;
-	}
-	parent = cgroup_cs(cont->parent);
+	parent = cgroup_cs(parent_cg);
+
 	cs = kmalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
@@ -1855,7 +1819,36 @@ static struct cgroup_subsys_state *cpuset_create(struct cgroup *cont)
 
 	cs->parent = parent;
 	number_of_cpusets++;
-	return &cs->css ;
+
+	if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &cont->flags))
+		goto skip_clone;
+
+	/*
+	 * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is
+	 * set.  This flag handling is implemented in cgroup core for
+	 * histrical reasons - the flag may be specified during mount.
+	 *
+	 * Currently, if any sibling cpusets have exclusive cpus or mem, we
+	 * refuse to clone the configuration - thereby refusing the task to
+	 * be entered, and as a result refusing the sys_unshare() or
+	 * clone() which initiated it.  If this becomes a problem for some
+	 * users who wish to allow that scenario, then this could be
+	 * changed to grant parent->cpus_allowed-sibling_cpus_exclusive
+	 * (and likewise for mems) to the new cgroup.
+	 */
+	list_for_each_entry(tmp_cg, &parent_cg->children, sibling) {
+		struct cpuset *tmp_cs = cgroup_cs(tmp_cg);
+
+		if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs))
+			goto skip_clone;
+	}
+
+	mutex_lock(&callback_mutex);
+	cs->mems_allowed = parent->mems_allowed;
+	cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
+	mutex_unlock(&callback_mutex);
+skip_clone:
+	return &cs->css;
 }
 
 /*
@@ -1864,7 +1857,7 @@ static struct cgroup_subsys_state *cpuset_create(struct cgroup *cont)
  * will call async_rebuild_sched_domains().
  */
 
-static void cpuset_destroy(struct cgroup *cont)
+static void cpuset_css_free(struct cgroup *cont)
 {
 	struct cpuset *cs = cgroup_cs(cont);
 
@@ -1878,11 +1871,10 @@ static void cpuset_destroy(struct cgroup *cont)
 
 struct cgroup_subsys cpuset_subsys = {
 	.name = "cpuset",
-	.create = cpuset_create,
-	.destroy = cpuset_destroy,
+	.css_alloc = cpuset_css_alloc,
+	.css_free = cpuset_css_free,
 	.can_attach = cpuset_can_attach,
 	.attach = cpuset_attach,
-	.post_clone = cpuset_post_clone,
 	.subsys_id = cpuset_subsys_id,
 	.base_cftypes = files,
 	.early_init = 1,

kernel/events/core.c

@@ -7434,7 +7434,7 @@ unlock:
 device_initcall(perf_event_sysfs_init);
 
 #ifdef CONFIG_CGROUP_PERF
-static struct cgroup_subsys_state *perf_cgroup_create(struct cgroup *cont)
+static struct cgroup_subsys_state *perf_cgroup_css_alloc(struct cgroup *cont)
 {
 	struct perf_cgroup *jc;
 
@@ -7451,7 +7451,7 @@ static struct cgroup_subsys_state *perf_cgroup_create(struct cgroup *cont)
 	return &jc->css;
 }
 
-static void perf_cgroup_destroy(struct cgroup *cont)
+static void perf_cgroup_css_free(struct cgroup *cont)
 {
 	struct perf_cgroup *jc;
 	jc = container_of(cgroup_subsys_state(cont, perf_subsys_id),
@@ -7492,8 +7492,8 @@ static void perf_cgroup_exit(struct cgroup *cgrp, struct cgroup *old_cgrp,
 struct cgroup_subsys perf_subsys = {
 	.name		= "perf_event",
 	.subsys_id	= perf_subsys_id,
-	.create		= perf_cgroup_create,
-	.destroy	= perf_cgroup_destroy,
+	.css_alloc	= perf_cgroup_css_alloc,
+	.css_free	= perf_cgroup_css_free,
 	.exit		= perf_cgroup_exit,
 	.attach		= perf_cgroup_attach,
 

kernel/fork.c

@@ -1137,7 +1137,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 {
 	int retval;
 	struct task_struct *p;
-	int cgroup_callbacks_done = 0;
 
 	if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
 		return ERR_PTR(-EINVAL);
@@ -1395,12 +1394,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
-	/* Now that the task is set up, run cgroup callbacks if
-	 * necessary. We need to run them before the task is visible
-	 * on the tasklist. */
-	cgroup_fork_callbacks(p);
-	cgroup_callbacks_done = 1;
-
 	/* Need tasklist lock for parent etc handling! */
 	write_lock_irq(&tasklist_lock);
 
@@ -1505,7 +1498,7 @@ bad_fork_cleanup_cgroup:
 #endif
 	if (clone_flags & CLONE_THREAD)
 		threadgroup_change_end(current);
-	cgroup_exit(p, cgroup_callbacks_done);
+	cgroup_exit(p, 0);
 	delayacct_tsk_free(p);
 	module_put(task_thread_info(p)->exec_domain->module);
 bad_fork_cleanup_count:

kernel/freezer.c

@@ -116,17 +116,10 @@ bool freeze_task(struct task_struct *p)
 		return false;
 	}
 
-	if (!(p->flags & PF_KTHREAD)) {
+	if (!(p->flags & PF_KTHREAD))
 		fake_signal_wake_up(p);
-		/*
-		 * fake_signal_wake_up() goes through p's scheduler
-		 * lock and guarantees that TASK_STOPPED/TRACED ->
-		 * TASK_RUNNING transition can't race with task state
-		 * testing in try_to_freeze_tasks().
-		 */
-	} else {
+	else
 		wake_up_state(p, TASK_INTERRUPTIBLE);
-	}
 
 	spin_unlock_irqrestore(&freezer_lock, flags);
 	return true;

kernel/power/process.c

@@ -48,18 +48,7 @@ static int try_to_freeze_tasks(bool user_only)
 			if (p == current || !freeze_task(p))
 				continue;
 
-			/*
-			 * Now that we've done set_freeze_flag, don't
-			 * perturb a task in TASK_STOPPED or TASK_TRACED.
-			 * It is "frozen enough".  If the task does wake
-			 * up, it will immediately call try_to_freeze.
-			 *
-			 * Because freeze_task() goes through p's scheduler lock, it's
-			 * guaranteed that TASK_STOPPED/TRACED -> TASK_RUNNING
-			 * transition can't race with task state testing here.
-			 */
-			if (!task_is_stopped_or_traced(p) &&
-			    !freezer_should_skip(p))
+			if (!freezer_should_skip(p))
 				todo++;
 		} while_each_thread(g, p);
 		read_unlock(&tasklist_lock);

kernel/sched/core.c

@@ -7484,7 +7484,7 @@ static inline struct task_group *cgroup_tg(struct cgroup *cgrp)
 			    struct task_group, css);
 }
 
-static struct cgroup_subsys_state *cpu_cgroup_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cpu_cgroup_css_alloc(struct cgroup *cgrp)
 {
 	struct task_group *tg, *parent;
 
@@ -7501,7 +7501,7 @@ static struct cgroup_subsys_state *cpu_cgroup_create(struct cgroup *cgrp)
 	return &tg->css;
 }
 
-static void cpu_cgroup_destroy(struct cgroup *cgrp)
+static void cpu_cgroup_css_free(struct cgroup *cgrp)
 {
 	struct task_group *tg = cgroup_tg(cgrp);
 
@@ -7861,8 +7861,8 @@ static struct cftype cpu_files[] = {
 
 struct cgroup_subsys cpu_cgroup_subsys = {
 	.name		= "cpu",
-	.create		= cpu_cgroup_create,
-	.destroy	= cpu_cgroup_destroy,
+	.css_alloc	= cpu_cgroup_css_alloc,
+	.css_free	= cpu_cgroup_css_free,
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
 	.exit		= cpu_cgroup_exit,
@@ -7885,7 +7885,7 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 struct cpuacct root_cpuacct;
 
 /* create a new cpu accounting group */
-static struct cgroup_subsys_state *cpuacct_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp)
 {
 	struct cpuacct *ca;
 
@@ -7915,7 +7915,7 @@ out:
 }
 
 /* destroy an existing cpu accounting group */
-static void cpuacct_destroy(struct cgroup *cgrp)
+static void cpuacct_css_free(struct cgroup *cgrp)
 {
 	struct cpuacct *ca = cgroup_ca(cgrp);
 
@@ -8086,8 +8086,8 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 
 struct cgroup_subsys cpuacct_subsys = {
 	.name = "cpuacct",
-	.create = cpuacct_create,
-	.destroy = cpuacct_destroy,
+	.css_alloc = cpuacct_css_alloc,
+	.css_free = cpuacct_css_free,
 	.subsys_id = cpuacct_subsys_id,
 	.base_cftypes = files,
 };

kernel/signal.c

@@ -1908,7 +1908,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 		preempt_disable();
 		read_unlock(&tasklist_lock);
 		preempt_enable_no_resched();
-		schedule();
+		freezable_schedule();
 	} else {
 		/*
 		 * By the time we got the lock, our tracer went away.
@@ -1929,13 +1929,6 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 		read_unlock(&tasklist_lock);
 	}
 
-	/*
-	 * While in TASK_TRACED, we were considered "frozen enough".
-	 * Now that we woke up, it's crucial if we're supposed to be
-	 * frozen that we freeze now before running anything substantial.
-	 */
-	try_to_freeze();
-
 	/*
 	 * We are back.  Now reacquire the siglock before touching
 	 * last_siginfo, so that we are sure to have synchronized with
@@ -2092,7 +2085,7 @@ static bool do_signal_stop(int signr)
 		}
 
 		/* Now we don't run again until woken by SIGCONT or SIGKILL */
-		schedule();
+		freezable_schedule();
 		return true;
 	} else {
 		/*
@@ -2200,15 +2193,14 @@ int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka,
 	if (unlikely(uprobe_deny_signal()))
 		return 0;
 
-relock:
 	/*
-	 * We'll jump back here after any time we were stopped in TASK_STOPPED.
-	 * While in TASK_STOPPED, we were considered "frozen enough".
-	 * Now that we woke up, it's crucial if we're supposed to be
-	 * frozen that we freeze now before running anything substantial.
+	 * Do this once, we can't return to user-mode if freezing() == T.
+	 * do_signal_stop() and ptrace_stop() do freezable_schedule() and
+	 * thus do not need another check after return.
 	 */
 	try_to_freeze();
 
+relock:
 	spin_lock_irq(&sighand->siglock);
 	/*
 	 * Every stopped thread goes here after wakeup. Check to see if

mm/hugetlb_cgroup.c

@@ -77,7 +77,7 @@ static inline bool hugetlb_cgroup_have_usage(struct cgroup *cg)
 	return false;
 }
 
-static struct cgroup_subsys_state *hugetlb_cgroup_create(struct cgroup *cgroup)
+static struct cgroup_subsys_state *hugetlb_cgroup_css_alloc(struct cgroup *cgroup)
 {
 	int idx;
 	struct cgroup *parent_cgroup;
@@ -101,7 +101,7 @@ static struct cgroup_subsys_state *hugetlb_cgroup_create(struct cgroup *cgroup)
 	return &h_cgroup->css;
 }
 
-static void hugetlb_cgroup_destroy(struct cgroup *cgroup)
+static void hugetlb_cgroup_css_free(struct cgroup *cgroup)
 {
 	struct hugetlb_cgroup *h_cgroup;
 
@@ -155,18 +155,13 @@ out:
  * Force the hugetlb cgroup to empty the hugetlb resources by moving them to
  * the parent cgroup.
  */
-static int hugetlb_cgroup_pre_destroy(struct cgroup *cgroup)
+static void hugetlb_cgroup_css_offline(struct cgroup *cgroup)
 {
 	struct hstate *h;
 	struct page *page;
-	int ret = 0, idx = 0;
+	int idx = 0;
 
 	do {
-		if (cgroup_task_count(cgroup) ||
-		    !list_empty(&cgroup->children)) {
-			ret = -EBUSY;
-			goto out;
-		}
 		for_each_hstate(h) {
 			spin_lock(&hugetlb_lock);
 			list_for_each_entry(page, &h->hugepage_activelist, lru)
@@ -177,8 +172,6 @@ static int hugetlb_cgroup_pre_destroy(struct cgroup *cgroup)
 		}
 		cond_resched();
 	} while (hugetlb_cgroup_have_usage(cgroup));
-out:
-	return ret;
 }
 
 int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
@@ -411,8 +404,8 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage)
 
 struct cgroup_subsys hugetlb_subsys = {
 	.name = "hugetlb",
-	.create     = hugetlb_cgroup_create,
-	.pre_destroy = hugetlb_cgroup_pre_destroy,
-	.destroy    = hugetlb_cgroup_destroy,
-	.subsys_id  = hugetlb_subsys_id,
+	.css_alloc	= hugetlb_cgroup_css_alloc,
+	.css_offline	= hugetlb_cgroup_css_offline,
+	.css_free	= hugetlb_cgroup_css_free,
+	.subsys_id	= hugetlb_subsys_id,
 };

mm/memcontrol.c

@@ -2370,7 +2370,6 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 again:
 	if (*ptr) { /* css should be a valid one */
 		memcg = *ptr;
-		VM_BUG_ON(css_is_removed(&memcg->css));
 		if (mem_cgroup_is_root(memcg))
 			goto done;
 		if (nr_pages == 1 && consume_stock(memcg))
@@ -2510,9 +2509,9 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg,
 
 /*
  * A helper function to get mem_cgroup from ID. must be called under
- * rcu_read_lock(). The caller must check css_is_removed() or some if
- * it's concern. (dropping refcnt from swap can be called against removed
- * memcg.)
+ * rcu_read_lock().  The caller is responsible for calling css_tryget if
+ * the mem_cgroup is used for charging. (dropping refcnt from swap can be
+ * called against removed memcg.)
  */
 static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
 {
@@ -2709,13 +2708,6 @@ static int mem_cgroup_move_account(struct page *page,
 	/* caller should have done css_get */
 	pc->mem_cgroup = to;
 	mem_cgroup_charge_statistics(to, anon, nr_pages);
-	/*
-	 * We charges against "to" which may not have any tasks. Then, "to"
-	 * can be under rmdir(). But in current implementation, caller of
-	 * this function is just force_empty() and move charge, so it's
-	 * guaranteed that "to" is never removed. So, we don't check rmdir
-	 * status here.
-	 */
 	move_unlock_mem_cgroup(from, &flags);
 	ret = 0;
 unlock:
@@ -2729,10 +2721,27 @@ out:
 	return ret;
 }
 
-/*
- * move charges to its parent.
+/**
+ * mem_cgroup_move_parent - moves page to the parent group
+ * @page: the page to move
+ * @pc: page_cgroup of the page
+ * @child: page's cgroup
+ *
+ * move charges to its parent or the root cgroup if the group has no
+ * parent (aka use_hierarchy==0).
+ * Although this might fail (get_page_unless_zero, isolate_lru_page or
+ * mem_cgroup_move_account fails) the failure is always temporary and
+ * it signals a race with a page removal/uncharge or migration. In the
+ * first case the page is on the way out and it will vanish from the LRU
+ * on the next attempt and the call should be retried later.
+ * Isolation from the LRU fails only if page has been isolated from
+ * the LRU since we looked at it and that usually means either global
+ * reclaim or migration going on. The page will either get back to the
+ * LRU or vanish.
+ * Finaly mem_cgroup_move_account fails only if the page got uncharged
+ * (!PageCgroupUsed) or moved to a different group. The page will
+ * disappear in the next attempt.
  */
-
 static int mem_cgroup_move_parent(struct page *page,
 				  struct page_cgroup *pc,
 				  struct mem_cgroup *child)
@@ -2742,9 +2751,7 @@ static int mem_cgroup_move_parent(struct page *page,
 	unsigned long uninitialized_var(flags);
 	int ret;
 
-	/* Is ROOT ? */
-	if (mem_cgroup_is_root(child))
-		return -EINVAL;
+	VM_BUG_ON(mem_cgroup_is_root(child));
 
 	ret = -EBUSY;
 	if (!get_page_unless_zero(page))
@@ -2761,8 +2768,10 @@ static int mem_cgroup_move_parent(struct page *page,
 	if (!parent)
 		parent = root_mem_cgroup;
 
-	if (nr_pages > 1)
+	if (nr_pages > 1) {
+		VM_BUG_ON(!PageTransHuge(page));
 		flags = compound_lock_irqsave(page);
+	}
 
 	ret = mem_cgroup_move_account(page, nr_pages,
 				pc, child, parent);
@@ -2904,7 +2913,6 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
 		return;
 	if (!memcg)
 		return;
-	cgroup_exclude_rmdir(&memcg->css);
 
 	__mem_cgroup_commit_charge(memcg, page, 1, ctype, true);
 	/*
@@ -2918,12 +2926,6 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
 		swp_entry_t ent = {.val = page_private(page)};
 		mem_cgroup_uncharge_swap(ent);
 	}
-	/*
-	 * At swapin, we may charge account against cgroup which has no tasks.
-	 * So, rmdir()->pre_destroy() can be called while we do this charge.
-	 * In that case, we need to call pre_destroy() again. check it here.
-	 */
-	cgroup_release_and_wakeup_rmdir(&memcg->css);
 }
 
 void mem_cgroup_commit_charge_swapin(struct page *page,
@@ -3371,8 +3373,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 
 	if (!memcg)
 		return;
-	/* blocks rmdir() */
-	cgroup_exclude_rmdir(&memcg->css);
+
 	if (!migration_ok) {
 		used = oldpage;
 		unused = newpage;
@@ -3406,13 +3407,6 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	 */
 	if (anon)
 		mem_cgroup_uncharge_page(used);
-	/*
-	 * At migration, we may charge account against cgroup which has no
-	 * tasks.
-	 * So, rmdir()->pre_destroy() can be called while we do this charge.
-	 * In that case, we need to call pre_destroy() again. check it here.
-	 */
-	cgroup_release_and_wakeup_rmdir(&memcg->css);
 }
 
 /*
@@ -3712,17 +3706,22 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 	return nr_reclaimed;
 }
 
-/*
+/**
+ * mem_cgroup_force_empty_list - clears LRU of a group
+ * @memcg: group to clear
+ * @node: NUMA node
+ * @zid: zone id
+ * @lru: lru to to clear
+ *
  * Traverse a specified page_cgroup list and try to drop them all.  This doesn't
- * reclaim the pages page themselves - it just removes the page_cgroups.
- * Returns true if some page_cgroups were not freed, indicating that the caller
- * must retry this operation.
+ * reclaim the pages page themselves - pages are moved to the parent (or root)
+ * group.
  */
-static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
+static void mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 				int node, int zid, enum lru_list lru)
 {
 	struct lruvec *lruvec;
-	unsigned long flags, loop;
+	unsigned long flags;
 	struct list_head *list;
 	struct page *busy;
 	struct zone *zone;
@@ -3731,11 +3730,8 @@ static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 	lruvec = mem_cgroup_zone_lruvec(zone, memcg);
 	list = &lruvec->lists[lru];
 
-	loop = mem_cgroup_get_lru_size(lruvec, lru);
-	/* give some margin against EBUSY etc...*/
-	loop += 256;
 	busy = NULL;
-	while (loop--) {
+	do {
 		struct page_cgroup *pc;
 		struct page *page;
 
@@ -3761,76 +3757,72 @@ static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 			cond_resched();
 		} else
 			busy = NULL;
-	}
-	return !list_empty(list);
+	} while (!list_empty(list));
 }
 
 /*
- * make mem_cgroup's charge to be 0 if there is no task.
+ * make mem_cgroup's charge to be 0 if there is no task by moving
+ * all the charges and pages to the parent.
  * This enables deleting this mem_cgroup.
+ *
+ * Caller is responsible for holding css reference on the memcg.
  */
-static int mem_cgroup_force_empty(struct mem_cgroup *memcg, bool free_all)
+static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
 {
-	int ret;
-	int node, zid, shrink;
-	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
-	struct cgroup *cgrp = memcg->css.cgroup;
-
-	css_get(&memcg->css);
+	int node, zid;
 
-	shrink = 0;
-	/* should free all ? */
-	if (free_all)
-		goto try_to_free;
-move_account:
 	do {
-		ret = -EBUSY;
-		if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
-			goto out;
 		/* This is for making all *used* pages to be on LRU. */
 		lru_add_drain_all();
 		drain_all_stock_sync(memcg);
-		ret = 0;
 		mem_cgroup_start_move(memcg);
 		for_each_node_state(node, N_HIGH_MEMORY) {
-			for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
+			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
 				enum lru_list lru;
 				for_each_lru(lru) {
-					ret = mem_cgroup_force_empty_list(memcg,
+					mem_cgroup_force_empty_list(memcg,
 							node, zid, lru);
-					if (ret)
-						break;
 				}
 			}
-			if (ret)
-				break;
 		}
 		mem_cgroup_end_move(memcg);
 		memcg_oom_recover(memcg);
 		cond_resched();
-	/* "ret" should also be checked to ensure all lists are empty. */
-	} while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0 || ret);
-out:
-	css_put(&memcg->css);
-	return ret;
 
-try_to_free:
+		/*
+		 * This is a safety check because mem_cgroup_force_empty_list
+		 * could have raced with mem_cgroup_replace_page_cache callers
+		 * so the lru seemed empty but the page could have been added
+		 * right after the check. RES_USAGE should be safe as we always
+		 * charge before adding to the LRU.
+		 */
+	} while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0);
+}
+
+/*
+ * Reclaims as many pages from the given memcg as possible and moves
+ * the rest to the parent.
+ *
+ * Caller is responsible for holding css reference for memcg.
+ */
+static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
+{
+	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+	struct cgroup *cgrp = memcg->css.cgroup;
+
 	/* returns EBUSY if there is a task or if we come here twice. */
-	if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children) || shrink) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
+		return -EBUSY;
+
 	/* we call try-to-free pages for make this cgroup empty */
 	lru_add_drain_all();
 	/* try to free all pages in this cgroup */
-	shrink = 1;
 	while (nr_retries && res_counter_read_u64(&memcg->res, RES_USAGE) > 0) {
 		int progress;
 
-		if (signal_pending(current)) {
-			ret = -EINTR;
-			goto out;
-		}
+		if (signal_pending(current))
+			return -EINTR;
+
 		progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL,
 						false);
 		if (!progress) {
@@ -3841,13 +3833,23 @@ try_to_free:
 
 	}
 	lru_add_drain();
-	/* try move_account...there may be some *locked* pages. */
-	goto move_account;
+	mem_cgroup_reparent_charges(memcg);
+
+	return 0;
 }
 
 static int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event)
 {
-	return mem_cgroup_force_empty(mem_cgroup_from_cont(cont), true);
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	int ret;
+
+	if (mem_cgroup_is_root(memcg))
+		return -EINVAL;
+	css_get(&memcg->css);
+	ret = mem_cgroup_force_empty(memcg);
+	css_put(&memcg->css);
+
+	return ret;
 }
 
 
@@ -4953,7 +4955,7 @@ err_cleanup:
 }
 
 static struct cgroup_subsys_state * __ref
-mem_cgroup_create(struct cgroup *cont)
+mem_cgroup_css_alloc(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg, *parent;
 	long error = -ENOMEM;
@@ -5034,14 +5036,14 @@ free_out:
 	return ERR_PTR(error);
 }
 
-static int mem_cgroup_pre_destroy(struct cgroup *cont)
+static void mem_cgroup_css_offline(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
-	return mem_cgroup_force_empty(memcg, false);
+	mem_cgroup_reparent_charges(memcg);
 }
 
-static void mem_cgroup_destroy(struct cgroup *cont)
+static void mem_cgroup_css_free(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
@@ -5631,16 +5633,15 @@ static void mem_cgroup_move_task(struct cgroup *cont,
 struct cgroup_subsys mem_cgroup_subsys = {
 	.name = "memory",
 	.subsys_id = mem_cgroup_subsys_id,
-	.create = mem_cgroup_create,
-	.pre_destroy = mem_cgroup_pre_destroy,
-	.destroy = mem_cgroup_destroy,
+	.css_alloc = mem_cgroup_css_alloc,
+	.css_offline = mem_cgroup_css_offline,
+	.css_free = mem_cgroup_css_free,
 	.can_attach = mem_cgroup_can_attach,
 	.cancel_attach = mem_cgroup_cancel_attach,
 	.attach = mem_cgroup_move_task,
 	.base_cftypes = mem_cgroup_files,
 	.early_init = 0,
 	.use_id = 1,
-	.__DEPRECATED_clear_css_refs = true,
 };
 
 #ifdef CONFIG_MEMCG_SWAP

net/core/netprio_cgroup.c

@@ -27,11 +27,7 @@
 
 #include <linux/fdtable.h>
 
-#define PRIOIDX_SZ 128
-
-static unsigned long prioidx_map[PRIOIDX_SZ];
-static DEFINE_SPINLOCK(prioidx_map_lock);
-static atomic_t max_prioidx = ATOMIC_INIT(0);
+#define PRIOMAP_MIN_SZ		128
 
 static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgrp)
 {
@@ -39,136 +35,157 @@ static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgr
 			    struct cgroup_netprio_state, css);
 }
 
-static int get_prioidx(u32 *prio)
-{
-	unsigned long flags;
-	u32 prioidx;
-
-	spin_lock_irqsave(&prioidx_map_lock, flags);
-	prioidx = find_first_zero_bit(prioidx_map, sizeof(unsigned long) * PRIOIDX_SZ);
-	if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) {
-		spin_unlock_irqrestore(&prioidx_map_lock, flags);
-		return -ENOSPC;
-	}
-	set_bit(prioidx, prioidx_map);
-	if (atomic_read(&max_prioidx) < prioidx)
-		atomic_set(&max_prioidx, prioidx);
-	spin_unlock_irqrestore(&prioidx_map_lock, flags);
-	*prio = prioidx;
-	return 0;
-}
-
-static void put_prioidx(u32 idx)
+/*
+ * Extend @dev->priomap so that it's large enough to accomodate
+ * @target_idx.  @dev->priomap.priomap_len > @target_idx after successful
+ * return.  Must be called under rtnl lock.
+ */
+static int extend_netdev_table(struct net_device *dev, u32 target_idx)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&prioidx_map_lock, flags);
-	clear_bit(idx, prioidx_map);
-	spin_unlock_irqrestore(&prioidx_map_lock, flags);
-}
+	struct netprio_map *old, *new;
+	size_t new_sz, new_len;
 
-static int extend_netdev_table(struct net_device *dev, u32 new_len)
-{
-	size_t new_size = sizeof(struct netprio_map) +
-			   ((sizeof(u32) * new_len));
-	struct netprio_map *new_priomap = kzalloc(new_size, GFP_KERNEL);
-	struct netprio_map *old_priomap;
+	/* is the existing priomap large enough? */
+	old = rtnl_dereference(dev->priomap);
+	if (old && old->priomap_len > target_idx)
+		return 0;
 
-	old_priomap  = rtnl_dereference(dev->priomap);
+	/*
+	 * Determine the new size.  Let's keep it power-of-two.  We start
+	 * from PRIOMAP_MIN_SZ and double it until it's large enough to
+	 * accommodate @target_idx.
+	 */
+	new_sz = PRIOMAP_MIN_SZ;
+	while (true) {
+		new_len = (new_sz - offsetof(struct netprio_map, priomap)) /
+			sizeof(new->priomap[0]);
+		if (new_len > target_idx)
+			break;
+		new_sz *= 2;
+		/* overflowed? */
+		if (WARN_ON(new_sz < PRIOMAP_MIN_SZ))
+			return -ENOSPC;
+	}
 
-	if (!new_priomap) {
+	/* allocate & copy */
+	new = kzalloc(new_sz, GFP_KERNEL);
+	if (!new) {
 		pr_warn("Unable to alloc new priomap!\n");
 		return -ENOMEM;
 	}
 
-	if (old_priomap)
-		memcpy(new_priomap->priomap, old_priomap->priomap,
-		       old_priomap->priomap_len *
-		       sizeof(old_priomap->priomap[0]));
+	if (old)
+		memcpy(new->priomap, old->priomap,
+		       old->priomap_len * sizeof(old->priomap[0]));
 
-	new_priomap->priomap_len = new_len;
+	new->priomap_len = new_len;
 
-	rcu_assign_pointer(dev->priomap, new_priomap);
-	if (old_priomap)
-		kfree_rcu(old_priomap, rcu);
+	/* install the new priomap */
+	rcu_assign_pointer(dev->priomap, new);
+	if (old)
+		kfree_rcu(old, rcu);
 	return 0;
 }
 
-static int write_update_netdev_table(struct net_device *dev)
+/**
+ * netprio_prio - return the effective netprio of a cgroup-net_device pair
+ * @cgrp: cgroup part of the target pair
+ * @dev: net_device part of the target pair
+ *
+ * Should be called under RCU read or rtnl lock.
+ */
+static u32 netprio_prio(struct cgroup *cgrp, struct net_device *dev)
+{
+	struct netprio_map *map = rcu_dereference_rtnl(dev->priomap);
+
+	if (map && cgrp->id < map->priomap_len)
+		return map->priomap[cgrp->id];
+	return 0;
+}
+
+/**
+ * netprio_set_prio - set netprio on a cgroup-net_device pair
+ * @cgrp: cgroup part of the target pair
+ * @dev: net_device part of the target pair
+ * @prio: prio to set
+ *
+ * Set netprio to @prio on @cgrp-@dev pair.  Should be called under rtnl
+ * lock and may fail under memory pressure for non-zero @prio.
+ */
+static int netprio_set_prio(struct cgroup *cgrp, struct net_device *dev,
+			    u32 prio)
 {
-	int ret = 0;
-	u32 max_len;
 	struct netprio_map *map;
+	int ret;
 
-	max_len = atomic_read(&max_prioidx) + 1;
+	/* avoid extending priomap for zero writes */
 	map = rtnl_dereference(dev->priomap);
-	if (!map || map->priomap_len < max_len)
-		ret = extend_netdev_table(dev, max_len);
+	if (!prio && (!map || map->priomap_len <= cgrp->id))
+		return 0;
 
-	return ret;
+	ret = extend_netdev_table(dev, cgrp->id);
+	if (ret)
+		return ret;
+
+	map = rtnl_dereference(dev->priomap);
+	map->priomap[cgrp->id] = prio;
+	return 0;
 }
 
-static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp)
 {
 	struct cgroup_netprio_state *cs;
-	int ret = -EINVAL;
 
 	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
 
-	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx)
-		goto out;
-
-	ret = get_prioidx(&cs->prioidx);
-	if (ret < 0) {
-		pr_warn("No space in priority index array\n");
-		goto out;
-	}
-
 	return &cs->css;
-out:
-	kfree(cs);
-	return ERR_PTR(ret);
 }
 
-static void cgrp_destroy(struct cgroup *cgrp)
+static int cgrp_css_online(struct cgroup *cgrp)
 {
-	struct cgroup_netprio_state *cs;
+	struct cgroup *parent = cgrp->parent;
 	struct net_device *dev;
-	struct netprio_map *map;
+	int ret = 0;
+
+	if (!parent)
+		return 0;
 
-	cs = cgrp_netprio_state(cgrp);
 	rtnl_lock();
+	/*
+	 * Inherit prios from the parent.  As all prios are set during
+	 * onlining, there is no need to clear them on offline.
+	 */
 	for_each_netdev(&init_net, dev) {
-		map = rtnl_dereference(dev->priomap);
-		if (map && cs->prioidx < map->priomap_len)
-			map->priomap[cs->prioidx] = 0;
+		u32 prio = netprio_prio(parent, dev);
+
+		ret = netprio_set_prio(cgrp, dev, prio);
+		if (ret)
+			break;
 	}
 	rtnl_unlock();
-	put_prioidx(cs->prioidx);
-	kfree(cs);
+	return ret;
+}
+
+static void cgrp_css_free(struct cgroup *cgrp)
+{
+	kfree(cgrp_netprio_state(cgrp));
 }
 
 static u64 read_prioidx(struct cgroup *cgrp, struct cftype *cft)
 {
-	return (u64)cgrp_netprio_state(cgrp)->prioidx;
+	return cgrp->id;
 }
 
 static int read_priomap(struct cgroup *cont, struct cftype *cft,
 			struct cgroup_map_cb *cb)
 {
 	struct net_device *dev;
-	u32 prioidx = cgrp_netprio_state(cont)->prioidx;
-	u32 priority;
-	struct netprio_map *map;
 
 	rcu_read_lock();
-	for_each_netdev_rcu(&init_net, dev) {
-		map = rcu_dereference(dev->priomap);
-		priority = (map && prioidx < map->priomap_len) ? map->priomap[prioidx] : 0;
-		cb->fill(cb, dev->name, priority);
-	}
+	for_each_netdev_rcu(&init_net, dev)
+		cb->fill(cb, dev->name, netprio_prio(cont, dev));
 	rcu_read_unlock();
 	return 0;
 }
@@ -176,66 +193,24 @@ static int read_priomap(struct cgroup *cont, struct cftype *cft,
 static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
 			 const char *buffer)
 {
-	char *devname = kstrdup(buffer, GFP_KERNEL);
-	int ret = -EINVAL;
-	u32 prioidx = cgrp_netprio_state(cgrp)->prioidx;
-	unsigned long priority;
-	char *priostr;
+	char devname[IFNAMSIZ + 1];
 	struct net_device *dev;
-	struct netprio_map *map;
-
-	if (!devname)
-		return -ENOMEM;
-
-	/*
-	 * Minimally sized valid priomap string
-	 */
-	if (strlen(devname) < 3)
-		goto out_free_devname;
-
-	priostr = strstr(devname, " ");
-	if (!priostr)
-		goto out_free_devname;
-
-	/*
-	 *Separate the devname from the associated priority
-	 *and advance the priostr pointer to the priority value
-	 */
-	*priostr = '\0';
-	priostr++;
-
-	/*
-	 * If the priostr points to NULL, we're at the end of the passed
-	 * in string, and its not a valid write
-	 */
-	if (*priostr == '\0')
-		goto out_free_devname;
-
-	ret = kstrtoul(priostr, 10, &priority);
-	if (ret < 0)
-		goto out_free_devname;
+	u32 prio;
+	int ret;
 
-	ret = -ENODEV;
+	if (sscanf(buffer, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2)
+		return -EINVAL;
 
 	dev = dev_get_by_name(&init_net, devname);
 	if (!dev)
-		goto out_free_devname;
+		return -ENODEV;
 
 	rtnl_lock();
-	ret = write_update_netdev_table(dev);
-	if (ret < 0)
-		goto out_put_dev;
 
-	map = rtnl_dereference(dev->priomap);
-	if (map)
-		map->priomap[prioidx] = priority;
+	ret = netprio_set_prio(cgrp, dev, prio);
 
-out_put_dev:
 	rtnl_unlock();
 	dev_put(dev);
-
-out_free_devname:
-	kfree(devname);
 	return ret;
 }
 
@@ -276,22 +251,13 @@ static struct cftype ss_files[] = {
 
 struct cgroup_subsys net_prio_subsys = {
 	.name		= "net_prio",
-	.create		= cgrp_create,
-	.destroy	= cgrp_destroy,
+	.css_alloc	= cgrp_css_alloc,
+	.css_online	= cgrp_css_online,
+	.css_free	= cgrp_css_free,
 	.attach		= net_prio_attach,
 	.subsys_id	= net_prio_subsys_id,
 	.base_cftypes	= ss_files,
 	.module		= THIS_MODULE,
-
-	/*
-	 * net_prio has artificial limit on the number of cgroups and
-	 * disallows nesting making it impossible to co-mount it with other
-	 * hierarchical subsystems.  Remove the artificially low PRIOIDX_SZ
-	 * limit and properly nest configuration such that children follow
-	 * their parents' configurations by default and are allowed to
-	 * override and remove the following.
-	 */
-	.broken_hierarchy = true,
 };
 
 static int netprio_device_event(struct notifier_block *unused,

net/sched/cls_cgroup.c

@@ -34,21 +34,25 @@ static inline struct cgroup_cls_state *task_cls_state(struct task_struct *p)
 			    struct cgroup_cls_state, css);
 }
 
-static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp)
 {
 	struct cgroup_cls_state *cs;
 
 	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
+	return &cs->css;
+}
 
+static int cgrp_css_online(struct cgroup *cgrp)
+{
 	if (cgrp->parent)
-		cs->classid = cgrp_cls_state(cgrp->parent)->classid;
-
-	return &cs->css;
+		cgrp_cls_state(cgrp)->classid =
+			cgrp_cls_state(cgrp->parent)->classid;
+	return 0;
 }
 
-static void cgrp_destroy(struct cgroup *cgrp)
+static void cgrp_css_free(struct cgroup *cgrp)
 {
 	kfree(cgrp_cls_state(cgrp));
 }
@@ -75,20 +79,12 @@ static struct cftype ss_files[] = {
 
 struct cgroup_subsys net_cls_subsys = {
 	.name		= "net_cls",
-	.create		= cgrp_create,
-	.destroy	= cgrp_destroy,
+	.css_alloc	= cgrp_css_alloc,
+	.css_online	= cgrp_css_online,
+	.css_free	= cgrp_css_free,
 	.subsys_id	= net_cls_subsys_id,
 	.base_cftypes	= ss_files,
 	.module		= THIS_MODULE,
-
-	/*
-	 * While net_cls cgroup has the rudimentary hierarchy support of
-	 * inheriting the parent's classid on cgroup creation, it doesn't
-	 * properly propagates config changes in ancestors to their
-	 * descendents.  A child should follow the parent's configuration
-	 * but be allowed to override it.  Fix it and remove the following.
-	 */
-	.broken_hierarchy = true,
 };
 
 struct cls_cgroup_head {

security/device_cgroup.c

@@ -82,6 +82,8 @@ static int dev_exceptions_copy(struct list_head *dest, struct list_head *orig)
 {
 	struct dev_exception_item *ex, *tmp, *new;
 
+	lockdep_assert_held(&devcgroup_mutex);
+
 	list_for_each_entry(ex, orig, list) {
 		new = kmemdup(ex, sizeof(*ex), GFP_KERNEL);
 		if (!new)
@@ -107,6 +109,8 @@ static int dev_exception_add(struct dev_cgroup *dev_cgroup,
 {
 	struct dev_exception_item *excopy, *walk;
 
+	lockdep_assert_held(&devcgroup_mutex);
+
 	excopy = kmemdup(ex, sizeof(*ex), GFP_KERNEL);
 	if (!excopy)
 		return -ENOMEM;
@@ -137,6 +141,8 @@ static void dev_exception_rm(struct dev_cgroup *dev_cgroup,
 {
 	struct dev_exception_item *walk, *tmp;
 
+	lockdep_assert_held(&devcgroup_mutex);
+
 	list_for_each_entry_safe(walk, tmp, &dev_cgroup->exceptions, list) {
 		if (walk->type != ex->type)
 			continue;
@@ -163,6 +169,8 @@ static void dev_exception_clean(struct dev_cgroup *dev_cgroup)
 {
 	struct dev_exception_item *ex, *tmp;
 
+	lockdep_assert_held(&devcgroup_mutex);
+
 	list_for_each_entry_safe(ex, tmp, &dev_cgroup->exceptions, list) {
 		list_del_rcu(&ex->list);
 		kfree_rcu(ex, rcu);
@@ -172,7 +180,7 @@ static void dev_exception_clean(struct dev_cgroup *dev_cgroup)
 /*
  * called from kernel/cgroup.c with cgroup_lock() held.
  */
-static struct cgroup_subsys_state *devcgroup_create(struct cgroup *cgroup)
+static struct cgroup_subsys_state *devcgroup_css_alloc(struct cgroup *cgroup)
 {
 	struct dev_cgroup *dev_cgroup, *parent_dev_cgroup;
 	struct cgroup *parent_cgroup;
@@ -202,7 +210,7 @@ static struct cgroup_subsys_state *devcgroup_create(struct cgroup *cgroup)
 	return &dev_cgroup->css;
 }
 
-static void devcgroup_destroy(struct cgroup *cgroup)
+static void devcgroup_css_free(struct cgroup *cgroup)
 {
 	struct dev_cgroup *dev_cgroup;
 
@@ -298,6 +306,10 @@ static int may_access(struct dev_cgroup *dev_cgroup,
 	struct dev_exception_item *ex;
 	bool match = false;
 
+	rcu_lockdep_assert(rcu_read_lock_held() ||
+			   lockdep_is_held(&devcgroup_mutex),
+			   "device_cgroup::may_access() called without proper synchronization");
+
 	list_for_each_entry_rcu(ex, &dev_cgroup->exceptions, list) {
 		if ((refex->type & DEV_BLOCK) && !(ex->type & DEV_BLOCK))
 			continue;
@@ -552,8 +564,8 @@ static struct cftype dev_cgroup_files[] = {
 struct cgroup_subsys devices_subsys = {
 	.name = "devices",
 	.can_attach = devcgroup_can_attach,
-	.create = devcgroup_create,
-	.destroy = devcgroup_destroy,
+	.css_alloc = devcgroup_css_alloc,
+	.css_free = devcgroup_css_free,
 	.subsys_id = devices_subsys_id,
 	.base_cftypes = dev_cgroup_files,