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()
  ...

2 files changed, 159 insertions, 65 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index f8a030ced0c..7d73905dcba 100644
--- a/include/linux/cgroup.h
+++ b/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
 
@@ -422,23 +416,6 @@ int cgroup_task_count(const struct cgroup *cgrp);
 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;
@@ -489,17 +467,6 @@ 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
 	 * cgroup cover those of its children.  If %true, hierarchy support
@@ -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;
diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index b90091af579..e4238ceaa4d 100644
--- a/include/linux/freezer.h
+++ b/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. */