Merge branch 'for-3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - Fixes and a lot of cleanups.  Locking cleanup is finally complete.
   cgroup_mutex is no longer exposed to individual controlelrs which
   used to cause nasty deadlock issues.  Li fixed and cleaned up quite a
   bit including long standing ones like racy cgroup_path().

 - device cgroup now supports proper hierarchy thanks to Aristeu.

 - perf_event cgroup now supports proper hierarchy.

 - A new mount option "__DEVEL__sane_behavior" is added.  As indicated
   by the name, this option is to be used for development only at this
   point and generates a warning message when used.  Unfortunately,
   cgroup interface currently has too many brekages and inconsistencies
   to implement a consistent and unified hierarchy on top.  The new flag
   is used to collect the behavior changes which are necessary to
   implement consistent unified hierarchy.  It's likely that this flag
   won't be used verbatim when it becomes ready but will be enabled
   implicitly along with unified hierarchy.

   The option currently disables some of broken behaviors in cgroup core
   and also .use_hierarchy switch in memcg (will be routed through -mm),
   which can be used to make very unusual hierarchy where nesting is
   partially honored.  It will also be used to implement hierarchy
   support for blk-throttle which would be impossible otherwise without
   introducing a full separate set of control knobs.

   This is essentially versioning of interface which isn't very nice but
   at this point I can't see any other options which would allow keeping
   the interface the same while moving towards hierarchy behavior which
   is at least somewhat sane.  The planned unified hierarchy is likely
   to require some level of adaptation from userland anyway, so I think
   it'd be best to take the chance and update the interface such that
   it's supportable in the long term.

   Maintaining the existing interface does complicate cgroup core but
   shouldn't put too much strain on individual controllers and I think
   it'd be manageable for the foreseeable future.  Maybe we'll be able
   to drop it in a decade.

Fix up conflicts (including a semantic one adding a new #include to ppc
that was uncovered by header the file changes) as per Tejun.

* 'for-3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (45 commits)
  cpuset: fix compile warning when CONFIG_SMP=n
  cpuset: fix cpu hotplug vs rebuild_sched_domains() race
  cpuset: use rebuild_sched_domains() in cpuset_hotplug_workfn()
  cgroup: restore the call to eventfd->poll()
  cgroup: fix use-after-free when umounting cgroupfs
  cgroup: fix broken file xattrs
  devcg: remove parent_cgroup.
  memcg: force use_hierarchy if sane_behavior
  cgroup: remove cgrp->top_cgroup
  cgroup: introduce sane_behavior mount option
  move cgroupfs_root to include/linux/cgroup.h
  cgroup: convert cgroupfs_root flag bits to masks and add CGRP_ prefix
  cgroup: make cgroup_path() not print double slashes
  Revert "cgroup: remove bind() method from cgroup_subsys."
  perf: make perf_event cgroup hierarchical
  cgroup: implement cgroup_is_descendant()
  cgroup: make sure parent won't be destroyed before its children
  cgroup: remove bind() method from cgroup_subsys.
  devcg: remove broken_hierarchy tag
  cgroup: remove cgroup_lock_is_held()
  ...

1 files changed, 299 insertions, 425 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 1f628bc039f4..eeb7e49946b2 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -30,7 +30,6 @@
 #include <linux/cred.h>
 #include <linux/ctype.h>
 #include <linux/errno.h>
-#include <linux/fs.h>
 #include <linux/init_task.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
@@ -59,7 +58,7 @@
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
 #include <linux/eventfd.h>
 #include <linux/poll.h>
-#include <linux/flex_array.h> /* used in cgroup_attach_proc */
+#include <linux/flex_array.h> /* used in cgroup_attach_task */
 #include <linux/kthread.h>
 
 #include <linux/atomic.h>
@@ -83,7 +82,13 @@
  * B happens only through cgroup_show_options() and using cgroup_root_mutex
  * breaks it.
  */
+#ifdef CONFIG_PROVE_RCU
+DEFINE_MUTEX(cgroup_mutex);
+EXPORT_SYMBOL_GPL(cgroup_mutex);	/* only for task_subsys_state_check() */
+#else
 static DEFINE_MUTEX(cgroup_mutex);
+#endif
+
 static DEFINE_MUTEX(cgroup_root_mutex);
 
 /*
@@ -98,56 +103,6 @@ static struct cgroup_subsys *subsys[CGROUP_SUBSYS_COUNT] = {
 #include <linux/cgroup_subsys.h>
 };
 
-#define MAX_CGROUP_ROOT_NAMELEN 64
-
-/*
- * A cgroupfs_root represents the root of a cgroup hierarchy,
- * and may be associated with a superblock to form an active
- * hierarchy
- */
-struct cgroupfs_root {
-	struct super_block *sb;
-
-	/*
-	 * The bitmask of subsystems intended to be attached to this
-	 * hierarchy
-	 */
-	unsigned long subsys_mask;
-
-	/* Unique id for this hierarchy. */
-	int hierarchy_id;
-
-	/* The bitmask of subsystems currently attached to this hierarchy */
-	unsigned long actual_subsys_mask;
-
-	/* A list running through the attached subsystems */
-	struct list_head subsys_list;
-
-	/* The root cgroup for this hierarchy */
-	struct cgroup top_cgroup;
-
-	/* Tracks how many cgroups are currently defined in hierarchy.*/
-	int number_of_cgroups;
-
-	/* A list running through the active hierarchies */
-	struct list_head root_list;
-
-	/* All cgroups on this root, cgroup_mutex protected */
-	struct list_head allcg_list;
-
-	/* Hierarchy-specific flags */
-	unsigned long flags;
-
-	/* IDs for cgroups in this hierarchy */
-	struct ida cgroup_ida;
-
-	/* The path to use for release notifications. */
-	char release_agent_path[PATH_MAX];
-
-	/* The name for this hierarchy - may be empty */
-	char name[MAX_CGROUP_ROOT_NAMELEN];
-};
-
 /*
  * The "rootnode" hierarchy is the "dummy hierarchy", reserved for the
  * subsystems that are otherwise unattached - it never has more than a
@@ -162,6 +117,9 @@ struct cfent {
 	struct list_head		node;
 	struct dentry			*dentry;
 	struct cftype			*type;
+
+	/* file xattrs */
+	struct simple_xattrs		xattrs;
 };
 
 /*
@@ -238,6 +196,8 @@ static DEFINE_SPINLOCK(hierarchy_id_lock);
 /* dummytop is a shorthand for the dummy hierarchy's top cgroup */
 #define dummytop (&rootnode.top_cgroup)
 
+static struct cgroup_name root_cgroup_name = { .name = "/" };
+
 /* This flag indicates whether tasks in the fork and exit paths should
  * check for fork/exit handlers to call. This avoids us having to do
  * extra work in the fork/exit path if none of the subsystems need to
@@ -249,20 +209,6 @@ 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)
-{
-	return lockdep_is_held(&cgroup_mutex);
-}
-#else /* #ifdef CONFIG_PROVE_LOCKING */
-int cgroup_lock_is_held(void)
-{
-	return mutex_is_locked(&cgroup_mutex);
-}
-#endif /* #else #ifdef CONFIG_PROVE_LOCKING */
-
-EXPORT_SYMBOL_GPL(cgroup_lock_is_held);
-
 static int css_unbias_refcnt(int refcnt)
 {
 	return refcnt >= 0 ? refcnt : refcnt - CSS_DEACT_BIAS;
@@ -282,11 +228,25 @@ inline int cgroup_is_removed(const struct cgroup *cgrp)
 	return test_bit(CGRP_REMOVED, &cgrp->flags);
 }
 
-/* bits in struct cgroupfs_root flags field */
-enum {
-	ROOT_NOPREFIX,	/* mounted subsystems have no named prefix */
-	ROOT_XATTR,	/* supports extended attributes */
-};
+/**
+ * cgroup_is_descendant - test ancestry
+ * @cgrp: the cgroup to be tested
+ * @ancestor: possible ancestor of @cgrp
+ *
+ * Test whether @cgrp is a descendant of @ancestor.  It also returns %true
+ * if @cgrp == @ancestor.  This function is safe to call as long as @cgrp
+ * and @ancestor are accessible.
+ */
+bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor)
+{
+	while (cgrp) {
+		if (cgrp == ancestor)
+			return true;
+		cgrp = cgrp->parent;
+	}
+	return false;
+}
+EXPORT_SYMBOL_GPL(cgroup_is_descendant);
 
 static int cgroup_is_releasable(const struct cgroup *cgrp)
 {
@@ -327,6 +287,23 @@ static inline struct cftype *__d_cft(struct dentry *dentry)
 	return __d_cfe(dentry)->type;
 }
 
+/**
+ * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
+ * @cgrp: the cgroup to be checked for liveness
+ *
+ * On success, returns true; the mutex should be later unlocked.  On
+ * failure returns false with no lock held.
+ */
+static bool cgroup_lock_live_group(struct cgroup *cgrp)
+{
+	mutex_lock(&cgroup_mutex);
+	if (cgroup_is_removed(cgrp)) {
+		mutex_unlock(&cgroup_mutex);
+		return false;
+	}
+	return true;
+}
+
 /* the list of cgroups eligible for automatic release. Protected by
  * release_list_lock */
 static LIST_HEAD(release_list);
@@ -800,27 +777,6 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
  * update of a tasks cgroup pointer by cgroup_attach_task()
  */
 
-/**
- * cgroup_lock - lock out any changes to cgroup structures
- *
- */
-void cgroup_lock(void)
-{
-	mutex_lock(&cgroup_mutex);
-}
-EXPORT_SYMBOL_GPL(cgroup_lock);
-
-/**
- * cgroup_unlock - release lock on cgroup changes
- *
- * Undo the lock taken in a previous cgroup_lock() call.
- */
-void cgroup_unlock(void)
-{
-	mutex_unlock(&cgroup_mutex);
-}
-EXPORT_SYMBOL_GPL(cgroup_unlock);
-
 /*
  * A couple of forward declarations required, due to cyclic reference loop:
  * cgroup_mkdir -> cgroup_create -> cgroup_populate_dir ->
@@ -859,6 +815,17 @@ static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
 	return inode;
 }
 
+static struct cgroup_name *cgroup_alloc_name(struct dentry *dentry)
+{
+	struct cgroup_name *name;
+
+	name = kmalloc(sizeof(*name) + dentry->d_name.len + 1, GFP_KERNEL);
+	if (!name)
+		return NULL;
+	strcpy(name->name, dentry->d_name.name);
+	return name;
+}
+
 static void cgroup_free_fn(struct work_struct *work)
 {
 	struct cgroup *cgrp = container_of(work, struct cgroup, free_work);
@@ -875,8 +842,18 @@ static void cgroup_free_fn(struct work_struct *work)
 	mutex_unlock(&cgroup_mutex);
 
 	/*
+	 * We get a ref to the parent's dentry, and put the ref when
+	 * this cgroup is being freed, so it's guaranteed that the
+	 * parent won't be destroyed before its children.
+	 */
+	dput(cgrp->parent->dentry);
+
+	ida_simple_remove(&cgrp->root->cgroup_ida, cgrp->id);
+
+	/*
 	 * Drop the active superblock reference that we took when we
-	 * created the cgroup
+	 * created the cgroup. This will free cgrp->root, if we are
+	 * holding the last reference to @sb.
 	 */
 	deactivate_super(cgrp->root->sb);
 
@@ -888,7 +865,7 @@ static void cgroup_free_fn(struct work_struct *work)
 
 	simple_xattrs_free(&cgrp->xattrs);
 
-	ida_simple_remove(&cgrp->root->cgroup_ida, cgrp->id);
+	kfree(rcu_dereference_raw(cgrp->name));
 	kfree(cgrp);
 }
 
@@ -910,13 +887,12 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 	} else {
 		struct cfent *cfe = __d_cfe(dentry);
 		struct cgroup *cgrp = dentry->d_parent->d_fsdata;
-		struct cftype *cft = cfe->type;
 
 		WARN_ONCE(!list_empty(&cfe->node) &&
 			  cgrp != &cgrp->root->top_cgroup,
 			  "cfe still linked for %s\n", cfe->type->name);
+		simple_xattrs_free(&cfe->xattrs);
 		kfree(cfe);
-		simple_xattrs_free(&cft->xattrs);
 	}
 	iput(inode);
 }
@@ -1108,9 +1084,11 @@ static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
 	mutex_lock(&cgroup_root_mutex);
 	for_each_subsys(root, ss)
 		seq_printf(seq, ",%s", ss->name);
-	if (test_bit(ROOT_NOPREFIX, &root->flags))
+	if (root->flags & CGRP_ROOT_SANE_BEHAVIOR)
+		seq_puts(seq, ",sane_behavior");
+	if (root->flags & CGRP_ROOT_NOPREFIX)
 		seq_puts(seq, ",noprefix");
-	if (test_bit(ROOT_XATTR, &root->flags))
+	if (root->flags & CGRP_ROOT_XATTR)
 		seq_puts(seq, ",xattr");
 	if (strlen(root->release_agent_path))
 		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
@@ -1172,8 +1150,12 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 			all_ss = true;
 			continue;
 		}
+		if (!strcmp(token, "__DEVEL__sane_behavior")) {
+			opts->flags |= CGRP_ROOT_SANE_BEHAVIOR;
+			continue;
+		}
 		if (!strcmp(token, "noprefix")) {
-			set_bit(ROOT_NOPREFIX, &opts->flags);
+			opts->flags |= CGRP_ROOT_NOPREFIX;
 			continue;
 		}
 		if (!strcmp(token, "clone_children")) {
@@ -1181,7 +1163,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 			continue;
 		}
 		if (!strcmp(token, "xattr")) {
-			set_bit(ROOT_XATTR, &opts->flags);
+			opts->flags |= CGRP_ROOT_XATTR;
 			continue;
 		}
 		if (!strncmp(token, "release_agent=", 14)) {
@@ -1259,13 +1241,26 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 
 	/* Consistency checks */
 
+	if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
+		pr_warning("cgroup: sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");
+
+		if (opts->flags & CGRP_ROOT_NOPREFIX) {
+			pr_err("cgroup: sane_behavior: noprefix is not allowed\n");
+			return -EINVAL;
+		}
+
+		if (opts->cpuset_clone_children) {
+			pr_err("cgroup: sane_behavior: clone_children is not allowed\n");
+			return -EINVAL;
+		}
+	}
+
 	/*
 	 * Option noprefix was introduced just for backward compatibility
 	 * with the old cpuset, so we allow noprefix only if mounting just
 	 * the cpuset subsystem.
 	 */
-	if (test_bit(ROOT_NOPREFIX, &opts->flags) &&
-	    (opts->subsys_mask & mask))
+	if ((opts->flags & CGRP_ROOT_NOPREFIX) && (opts->subsys_mask & mask))
 		return -EINVAL;
 
 
@@ -1336,6 +1331,11 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 	struct cgroup_sb_opts opts;
 	unsigned long added_mask, removed_mask;
 
+	if (root->flags & CGRP_ROOT_SANE_BEHAVIOR) {
+		pr_err("cgroup: sane_behavior: remount is not allowed\n");
+		return -EINVAL;
+	}
+
 	mutex_lock(&cgrp->dentry->d_inode->i_mutex);
 	mutex_lock(&cgroup_mutex);
 	mutex_lock(&cgroup_root_mutex);
@@ -1421,7 +1421,7 @@ static void init_cgroup_root(struct cgroupfs_root *root)
 	INIT_LIST_HEAD(&root->allcg_list);
 	root->number_of_cgroups = 1;
 	cgrp->root = root;
-	cgrp->top_cgroup = cgrp;
+	cgrp->name = &root_cgroup_name;
 	init_cgroup_housekeeping(cgrp);
 	list_add_tail(&cgrp->allcg_node, &root->allcg_list);
 }
@@ -1685,6 +1685,14 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 		 * any) is not needed
 		 */
 		cgroup_drop_root(opts.new_root);
+
+		if (((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) &&
+		    root->flags != opts.flags) {
+			pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n");
+			ret = -EINVAL;
+			goto drop_new_super;
+		}
+
 		/* no subsys rebinding, so refcounts don't change */
 		drop_parsed_module_refcounts(opts.subsys_mask);
 	}
@@ -1769,49 +1777,48 @@ static struct kobject *cgroup_kobj;
  * @buf: the buffer to write the path into
  * @buflen: the length of the buffer
  *
- * Called with cgroup_mutex held or else with an RCU-protected cgroup
- * reference.  Writes path of cgroup into buf.  Returns 0 on success,
- * -errno on error.
+ * Writes path of cgroup into buf.  Returns 0 on success, -errno on error.
+ *
+ * We can't generate cgroup path using dentry->d_name, as accessing
+ * dentry->name must be protected by irq-unsafe dentry->d_lock or parent
+ * inode's i_mutex, while on the other hand cgroup_path() can be called
+ * with some irq-safe spinlocks held.
  */
 int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 {
-	struct dentry *dentry = cgrp->dentry;
+	int ret = -ENAMETOOLONG;
 	char *start;
 
-	rcu_lockdep_assert(rcu_read_lock_held() || cgroup_lock_is_held(),
-			   "cgroup_path() called without proper locking");
-
-	if (cgrp == dummytop) {
-		/*
-		 * Inactive subsystems have no dentry for their root
-		 * cgroup
-		 */
-		strcpy(buf, "/");
+	if (!cgrp->parent) {
+		if (strlcpy(buf, "/", buflen) >= buflen)
+			return -ENAMETOOLONG;
 		return 0;
 	}
 
 	start = buf + buflen - 1;
-
 	*start = '\0';
-	for (;;) {
-		int len = dentry->d_name.len;
 
+	rcu_read_lock();
+	do {
+		const char *name = cgroup_name(cgrp);
+		int len;
+
+		len = strlen(name);
 		if ((start -= len) < buf)
-			return -ENAMETOOLONG;
-		memcpy(start, dentry->d_name.name, len);
-		cgrp = cgrp->parent;
-		if (!cgrp)
-			break;
+			goto out;
+		memcpy(start, name, len);
 
-		dentry = cgrp->dentry;
-		if (!cgrp->parent)
-			continue;
 		if (--start < buf)
-			return -ENAMETOOLONG;
+			goto out;
 		*start = '/';
-	}
+
+		cgrp = cgrp->parent;
+	} while (cgrp->parent);
+	ret = 0;
 	memmove(buf, start, buf + buflen - start);
-	return 0;
+out:
+	rcu_read_unlock();
+	return ret;
 }
 EXPORT_SYMBOL_GPL(cgroup_path);
 
@@ -1900,7 +1907,7 @@ EXPORT_SYMBOL_GPL(cgroup_taskset_size);
  *
  * Must be called with cgroup_mutex and threadgroup locked.
  */
-static void cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
+static void cgroup_task_migrate(struct cgroup *oldcgrp,
 				struct task_struct *tsk, struct css_set *newcg)
 {
 	struct css_set *oldcg;
@@ -1933,121 +1940,22 @@ static void cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
 }
 
 /**
- * cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
- * @cgrp: the cgroup the task is attaching to
- * @tsk: the task to be attached
- *
- * Call with cgroup_mutex and threadgroup locked. May take task_lock of
- * @tsk during call.
- */
-int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
-{
-	int retval = 0;
-	struct cgroup_subsys *ss, *failed_ss = NULL;
-	struct cgroup *oldcgrp;
-	struct cgroupfs_root *root = cgrp->root;
-	struct cgroup_taskset tset = { };
-	struct css_set *newcg;
-
-	/* @tsk either already exited or can't exit until the end */
-	if (tsk->flags & PF_EXITING)
-		return -ESRCH;
-
-	/* Nothing to do if the task is already in that cgroup */
-	oldcgrp = task_cgroup_from_root(tsk, root);
-	if (cgrp == oldcgrp)
-		return 0;
-
-	tset.single.task = tsk;
-	tset.single.cgrp = oldcgrp;
-
-	for_each_subsys(root, ss) {
-		if (ss->can_attach) {
-			retval = ss->can_attach(cgrp, &tset);
-			if (retval) {
-				/*
-				 * Remember on which subsystem the can_attach()
-				 * failed, so that we only call cancel_attach()
-				 * against the subsystems whose can_attach()
-				 * succeeded. (See below)
-				 */
-				failed_ss = ss;
-				goto out;
-			}
-		}
-	}
-
-	newcg = find_css_set(tsk->cgroups, cgrp);
-	if (!newcg) {
-		retval = -ENOMEM;
-		goto out;
-	}
-
-	cgroup_task_migrate(cgrp, oldcgrp, tsk, newcg);
-
-	for_each_subsys(root, ss) {
-		if (ss->attach)
-			ss->attach(cgrp, &tset);
-	}
-
-out:
-	if (retval) {
-		for_each_subsys(root, ss) {
-			if (ss == failed_ss)
-				/*
-				 * This subsystem was the one that failed the
-				 * can_attach() check earlier, so we don't need
-				 * to call cancel_attach() against it or any
-				 * remaining subsystems.
-				 */
-				break;
-			if (ss->cancel_attach)
-				ss->cancel_attach(cgrp, &tset);
-		}
-	}
-	return retval;
-}
-
-/**
- * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from'
- * @from: attach to all cgroups of a given task
- * @tsk: the task to be attached
- */
-int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
-{
-	struct cgroupfs_root *root;
-	int retval = 0;
-
-	cgroup_lock();
-	for_each_active_root(root) {
-		struct cgroup *from_cg = task_cgroup_from_root(from, root);
-
-		retval = cgroup_attach_task(from_cg, tsk);
-		if (retval)
-			break;
-	}
-	cgroup_unlock();
-
-	return retval;
-}
-EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
-
-/**
- * cgroup_attach_proc - attach all threads in a threadgroup to a cgroup
+ * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup
  * @cgrp: the cgroup to attach to
- * @leader: the threadgroup leader task_struct of the group to be attached
+ * @tsk: the task or the leader of the threadgroup to be attached
+ * @threadgroup: attach the whole threadgroup?
  *
  * Call holding cgroup_mutex and the group_rwsem of the leader. Will take
- * task_lock of each thread in leader's threadgroup individually in turn.
+ * task_lock of @tsk or each thread in the threadgroup individually in turn.
  */
-static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
+static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
+			      bool threadgroup)
 {
 	int retval, i, group_size;
 	struct cgroup_subsys *ss, *failed_ss = NULL;
-	/* guaranteed to be initialized later, but the compiler needs this */
 	struct cgroupfs_root *root = cgrp->root;
 	/* threadgroup list cursor and array */
-	struct task_struct *tsk;
+	struct task_struct *leader = tsk;
 	struct task_and_cgroup *tc;
 	struct flex_array *group;
 	struct cgroup_taskset tset = { };
@@ -2059,17 +1967,19 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 	 * group - group_rwsem prevents new threads from appearing, and if
 	 * threads exit, this will just be an over-estimate.
 	 */
-	group_size = get_nr_threads(leader);
+	if (threadgroup)
+		group_size = get_nr_threads(tsk);
+	else
+		group_size = 1;
 	/* flex_array supports very large thread-groups better than kmalloc. */
 	group = flex_array_alloc(sizeof(*tc), group_size, GFP_KERNEL);
 	if (!group)
 		return -ENOMEM;
 	/* pre-allocate to guarantee space while iterating in rcu read-side. */
-	retval = flex_array_prealloc(group, 0, group_size - 1, GFP_KERNEL);
+	retval = flex_array_prealloc(group, 0, group_size, GFP_KERNEL);
 	if (retval)
 		goto out_free_group_list;
 
-	tsk = leader;
 	i = 0;
 	/*
 	 * Prevent freeing of tasks while we take a snapshot. Tasks that are
@@ -2098,6 +2008,9 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 		retval = flex_array_put(group, i, &ent, GFP_ATOMIC);
 		BUG_ON(retval != 0);
 		i++;
+
+		if (!threadgroup)
+			break;
 	} while_each_thread(leader, tsk);
 	rcu_read_unlock();
 	/* remember the number of threads in the array for later. */
@@ -2143,7 +2056,7 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 	 */
 	for (i = 0; i < group_size; i++) {
 		tc = flex_array_get(group, i);
-		cgroup_task_migrate(cgrp, tc->cgrp, tc->task, tc->cg);
+		cgroup_task_migrate(tc->cgrp, tc->task, tc->cg);
 	}
 	/* nothing is sensitive to fork() after this point. */
 
@@ -2251,17 +2164,42 @@ retry_find_task:
 			put_task_struct(tsk);
 			goto retry_find_task;
 		}
-		ret = cgroup_attach_proc(cgrp, tsk);
-	} else
-		ret = cgroup_attach_task(cgrp, tsk);
+	}
+
+	ret = cgroup_attach_task(cgrp, tsk, threadgroup);
+
 	threadgroup_unlock(tsk);
 
 	put_task_struct(tsk);
 out_unlock_cgroup:
-	cgroup_unlock();
+	mutex_unlock(&cgroup_mutex);
 	return ret;
 }
 
+/**
+ * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from'
+ * @from: attach to all cgroups of a given task
+ * @tsk: the task to be attached
+ */
+int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
+{
+	struct cgroupfs_root *root;
+	int retval = 0;
+
+	mutex_lock(&cgroup_mutex);
+	for_each_active_root(root) {
+		struct cgroup *from_cg = task_cgroup_from_root(from, root);
+
+		retval = cgroup_attach_task(from_cg, tsk, false);
+		if (retval)
+			break;
+	}
+	mutex_unlock(&cgroup_mutex);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
+
 static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
 {
 	return attach_task_by_pid(cgrp, pid, false);
@@ -2272,24 +2210,6 @@ static int cgroup_procs_write(struct cgroup *cgrp, struct cftype *cft, u64 tgid)
 	return attach_task_by_pid(cgrp, tgid, true);
 }
 
-/**
- * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
- * @cgrp: the cgroup to be checked for liveness
- *
- * On success, returns true; the lock should be later released with
- * cgroup_unlock(). On failure returns false with no lock held.
- */
-bool cgroup_lock_live_group(struct cgroup *cgrp)
-{
-	mutex_lock(&cgroup_mutex);
-	if (cgroup_is_removed(cgrp)) {
-		mutex_unlock(&cgroup_mutex);
-		return false;
-	}
-	return true;
-}
-EXPORT_SYMBOL_GPL(cgroup_lock_live_group);
-
 static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
 				      const char *buffer)
 {
@@ -2301,7 +2221,7 @@ static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
 	mutex_lock(&cgroup_root_mutex);
 	strcpy(cgrp->root->release_agent_path, buffer);
 	mutex_unlock(&cgroup_root_mutex);
-	cgroup_unlock();
+	mutex_unlock(&cgroup_mutex);
 	return 0;
 }
 
@@ -2312,7 +2232,14 @@ static int cgroup_release_agent_show(struct cgroup *cgrp, struct cftype *cft,
 		return -ENODEV;
 	seq_puts(seq, cgrp->root->release_agent_path);
 	seq_putc(seq, '\n');
-	cgroup_unlock();
+	mutex_unlock(&cgroup_mutex);
+	return 0;
+}
+
+static int cgroup_sane_behavior_show(struct cgroup *cgrp, struct cftype *cft,
+				     struct seq_file *seq)
+{
+	seq_printf(seq, "%d\n", cgroup_sane_behavior(cgrp));
 	return 0;
 }
 
@@ -2537,13 +2464,40 @@ static int cgroup_file_release(struct inode *inode, struct file *file)
 static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
 			    struct inode *new_dir, struct dentry *new_dentry)
 {
+	int ret;
+	struct cgroup_name *name, *old_name;
+	struct cgroup *cgrp;
+
+	/*
+	 * It's convinient to use parent dir's i_mutex to protected
+	 * cgrp->name.
+	 */
+	lockdep_assert_held(&old_dir->i_mutex);
+
 	if (!S_ISDIR(old_dentry->d_inode->i_mode))
 		return -ENOTDIR;
 	if (new_dentry->d_inode)
 		return -EEXIST;
 	if (old_dir != new_dir)
 		return -EIO;
-	return simple_rename(old_dir, old_dentry, new_dir, new_dentry);
+
+	cgrp = __d_cgrp(old_dentry);
+
+	name = cgroup_alloc_name(new_dentry);
+	if (!name)
+		return -ENOMEM;
+
+	ret = simple_rename(old_dir, old_dentry, new_dir, new_dentry);
+	if (ret) {
+		kfree(name);
+		return ret;
+	}
+
+	old_name = cgrp->name;
+	rcu_assign_pointer(cgrp->name, name);
+
+	kfree_rcu(old_name, rcu_head);
+	return 0;
 }
 
 static struct simple_xattrs *__d_xattrs(struct dentry *dentry)
@@ -2551,13 +2505,13 @@ static struct simple_xattrs *__d_xattrs(struct dentry *dentry)
 	if (S_ISDIR(dentry->d_inode->i_mode))
 		return &__d_cgrp(dentry)->xattrs;
 	else
-		return &__d_cft(dentry)->xattrs;
+		return &__d_cfe(dentry)->xattrs;
 }
 
 static inline int xattr_enabled(struct dentry *dentry)
 {
 	struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
-	return test_bit(ROOT_XATTR, &root->flags);
+	return root->flags & CGRP_ROOT_XATTR;
 }
 
 static bool is_valid_xattr(const char *name)
@@ -2727,9 +2681,7 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
 	umode_t mode;
 	char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };
 
-	simple_xattrs_init(&cft->xattrs);
-
-	if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) {
+	if (subsys && !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) {
 		strcpy(name, subsys->name);
 		strcat(name, ".");
 	}
@@ -2753,6 +2705,7 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
 		cfe->type = (void *)cft;
 		cfe->dentry = dentry;
 		dentry->d_fsdata = cfe;
+		simple_xattrs_init(&cfe->xattrs);
 		list_add_tail(&cfe->node, &parent->files);
 		cfe = NULL;
 	}
@@ -2770,6 +2723,8 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys,
 
 	for (cft = cfts; cft->name[0] != '\0'; cft++) {
 		/* does cft->flags tell us to skip this file on @cgrp? */
+		if ((cft->flags & CFTYPE_INSANE) && cgroup_sane_behavior(cgrp))
+			continue;
 		if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent)
 			continue;
 		if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgrp->parent)
@@ -3300,6 +3255,34 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
 	return 0;
 }
 
+static void cgroup_transfer_one_task(struct task_struct *task,
+				     struct cgroup_scanner *scan)
+{
+	struct cgroup *new_cgroup = scan->data;
+
+	mutex_lock(&cgroup_mutex);
+	cgroup_attach_task(new_cgroup, task, false);
+	mutex_unlock(&cgroup_mutex);
+}
+
+/**
+ * cgroup_trasnsfer_tasks - move tasks from one cgroup to another
+ * @to: cgroup to which the tasks will be moved
+ * @from: cgroup in which the tasks currently reside
+ */
+int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
+{
+	struct cgroup_scanner scan;
+
+	scan.cg = from;
+	scan.test_task = NULL; /* select all tasks in cgroup */
+	scan.process_task = cgroup_transfer_one_task;
+	scan.heap = NULL;
+	scan.data = to;
+
+	return cgroup_scan_tasks(&scan);
+}
+
 /*
  * Stuff for reading the 'tasks'/'procs' files.
  *
@@ -3362,35 +3345,14 @@ static void pidlist_free(void *p)
 	else
 		kfree(p);
 }
-static void *pidlist_resize(void *p, int newcount)
-{
-	void *newlist;
-	/* note: if new alloc fails, old p will still be valid either way */
-	if (is_vmalloc_addr(p)) {
-		newlist = vmalloc(newcount * sizeof(pid_t));
-		if (!newlist)
-			return NULL;
-		memcpy(newlist, p, newcount * sizeof(pid_t));
-		vfree(p);
-	} else {
-		newlist = krealloc(p, newcount * sizeof(pid_t), GFP_KERNEL);
-	}
-	return newlist;
-}
 
 /*
  * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
- * If the new stripped list is sufficiently smaller and there's enough memory
- * to allocate a new buffer, will let go of the unneeded memory. Returns the
- * number of unique elements.
+ * Returns the number of unique elements.
  */
-/* is the size difference enough that we should re-allocate the array? */
-#define PIDLIST_REALLOC_DIFFERENCE(old, new) ((old) - PAGE_SIZE >= (new))
-static int pidlist_uniq(pid_t **p, int length)
+static int pidlist_uniq(pid_t *list, int length)
 {
 	int src, dest = 1;
-	pid_t *list = *p;
-	pid_t *newlist;
 
 	/*
 	 * we presume the 0th element is unique, so i starts at 1. trivial
@@ -3411,16 +3373,6 @@ static int pidlist_uniq(pid_t **p, int length)
 		dest++;
 	}
 after:
-	/*
-	 * if the length difference is large enough, we want to allocate a
-	 * smaller buffer to save memory. if this fails due to out of memory,
-	 * we'll just stay with what we've got.
-	 */
-	if (PIDLIST_REALLOC_DIFFERENCE(length, dest)) {
-		newlist = pidlist_resize(list, dest);
-		if (newlist)
-			*p = newlist;
-	}
 	return dest;
 }
 
@@ -3516,7 +3468,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 	/* now sort & (if procs) strip out duplicates */
 	sort(array, length, sizeof(pid_t), cmppid, NULL);
 	if (type == CGROUP_FILE_PROCS)
-		length = pidlist_uniq(&array, length);
+		length = pidlist_uniq(array, length);
 	l = cgroup_pidlist_find(cgrp, type);
 	if (!l) {
 		pidlist_free(array);
@@ -3930,11 +3882,7 @@ static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft,
 	if (ret)
 		goto fail;
 
-	if (efile->f_op->poll(efile, &event->pt) & POLLHUP) {
-		event->cft->unregister_event(cgrp, event->cft, event->eventfd);
-		ret = 0;
-		goto fail;
-	}
+	efile->f_op->poll(efile, &event->pt);
 
 	/*
 	 * Events should be removed after rmdir of cgroup directory, but before
@@ -4016,10 +3964,16 @@ static struct cftype files[] = {
 	},
 	{
 		.name = "cgroup.clone_children",
+		.flags = CFTYPE_INSANE,
 		.read_u64 = cgroup_clone_children_read,
 		.write_u64 = cgroup_clone_children_write,
 	},
 	{
+		.name = "cgroup.sane_behavior",
+		.flags = CFTYPE_ONLY_ON_ROOT,
+		.read_seq_string = cgroup_sane_behavior_show,
+	},
+	{
 		.name = "release_agent",
 		.flags = CFTYPE_ONLY_ON_ROOT,
 		.read_seq_string = cgroup_release_agent_show,
@@ -4131,17 +4085,8 @@ static void offline_css(struct cgroup_subsys *ss, struct cgroup *cgrp)
 	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);
+	if (ss->css_offline)
 		ss->css_offline(cgrp);
-		mutex_lock(&cgroup_mutex);
-	}
 
 	cgrp->subsys[ss->subsys_id]->flags &= ~CSS_ONLINE;
 }
@@ -4158,6 +4103,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 			     umode_t mode)
 {
 	struct cgroup *cgrp;
+	struct cgroup_name *name;
 	struct cgroupfs_root *root = parent->root;
 	int err = 0;
 	struct cgroup_subsys *ss;
@@ -4168,9 +4114,14 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	if (!cgrp)
 		return -ENOMEM;
 
+	name = cgroup_alloc_name(dentry);
+	if (!name)
+		goto err_free_cgrp;
+	rcu_assign_pointer(cgrp->name, name);
+
 	cgrp->id = ida_simple_get(&root->cgroup_ida, 1, 0, GFP_KERNEL);
 	if (cgrp->id < 0)
-		goto err_free_cgrp;
+		goto err_free_name;
 
 	/*
 	 * Only live parents can have children.  Note that the liveliness
@@ -4198,7 +4149,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
 	cgrp->parent = parent;
 	cgrp->root = parent->root;
-	cgrp->top_cgroup = parent->top_cgroup;
 
 	if (notify_on_release(parent))
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
@@ -4241,6 +4191,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	for_each_subsys(root, ss)
 		dget(dentry);
 
+	/* hold a ref to the parent's dentry */
+	dget(parent->dentry);
+
 	/* creation succeeded, notify subsystems */
 	for_each_subsys(root, ss) {
 		err = online_css(ss, cgrp);
@@ -4276,6 +4229,8 @@ err_free_all:
 	deactivate_super(sb);
 err_free_id:
 	ida_simple_remove(&root->cgroup_ida, cgrp->id);
+err_free_name:
+	kfree(rcu_dereference_raw(cgrp->name));
 err_free_cgrp:
 	kfree(cgrp);
 	return err;
@@ -4295,56 +4250,13 @@ static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	return cgroup_create(c_parent, dentry, mode | S_IFDIR);
 }
 
-/*
- * Check the reference count on each subsystem. Since we already
- * established that there are no tasks in the cgroup, if the css refcount
- * is also 1, then there should be no outstanding references, so the
- * subsystem is safe to destroy. We scan across all subsystems rather than
- * using the per-hierarchy linked list of mounted subsystems since we can
- * be called via check_for_release() with no synchronization other than
- * RCU, and the subsystem linked list isn't RCU-safe.
- */
-static int cgroup_has_css_refs(struct cgroup *cgrp)
-{
-	int i;
-
-	/*
-	 * We won't need to lock the subsys array, because the subsystems
-	 * we're concerned about aren't going anywhere since our cgroup root
-	 * has a reference on them.
-	 */
-	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-		struct cgroup_subsys *ss = subsys[i];
-		struct cgroup_subsys_state *css;
-
-		/* Skip subsystems not present or not in this hierarchy */
-		if (ss == NULL || ss->root != cgrp->root)
-			continue;
-
-		css = cgrp->subsys[ss->subsys_id];
-		/*
-		 * When called from check_for_release() it's possible
-		 * that by this point the cgroup has been removed
-		 * and the css deleted. But a false-positive doesn't
-		 * matter, since it can only happen if the cgroup
-		 * has been deleted and hence no longer needs the
-		 * release agent to be called anyway.
-		 */
-		if (css && css_refcnt(css) > 1)
-			return 1;
-	}
-	return 0;
-}
-
 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;
-	LIST_HEAD(tmp_list);
 
 	lockdep_assert_held(&d->d_inode->i_mutex);
 	lockdep_assert_held(&cgroup_mutex);
@@ -4935,17 +4847,17 @@ void cgroup_post_fork(struct task_struct *child)
 	 * and addition to css_set.
 	 */
 	if (need_forkexit_callback) {
-		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+		/*
+		 * fork/exit callbacks are supported only for builtin
+		 * subsystems, and the builtin section of the subsys
+		 * array is immutable, so we don't need to lock the
+		 * subsys array here. On the other hand, modular section
+		 * of the array can be freed at module unload, so we
+		 * can't touch that.
+		 */
+		for (i = 0; i < CGROUP_BUILTIN_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);
 		}
@@ -5010,13 +4922,13 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 	tsk->cgroups = &init_css_set;
 
 	if (run_callbacks && need_forkexit_callback) {
-		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+		/*
+		 * fork/exit callbacks are supported only for builtin
+		 * subsystems, see cgroup_post_fork() for details.
+		 */
+		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
 			struct cgroup_subsys *ss = subsys[i];
 
-			/* modular subsystems can't use callbacks */
-			if (!ss || ss->module)
-				continue;
-
 			if (ss->exit) {
 				struct cgroup *old_cgrp =
 					rcu_dereference_raw(cg->subsys[i])->cgroup;
@@ -5030,44 +4942,19 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 	put_css_set_taskexit(cg);
 }
 
-/**
- * cgroup_is_descendant - see if @cgrp is a descendant of @task's cgrp
- * @cgrp: the cgroup in question
- * @task: the task in question
- *
- * See if @cgrp is a descendant of @task's cgroup in the appropriate
- * hierarchy.
- *
- * If we are sending in dummytop, then presumably we are creating
- * the top cgroup in the subsystem.
- *
- * Called only by the ns (nsproxy) cgroup.
- */
-int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task)
-{
-	int ret;
-	struct cgroup *target;
-
-	if (cgrp == dummytop)
-		return 1;
-
-	target = task_cgroup_from_root(task, cgrp->root);
-	while (cgrp != target && cgrp!= cgrp->top_cgroup)
-		cgrp = cgrp->parent;
-	ret = (cgrp == target);
-	return ret;
-}
-
 static void check_for_release(struct cgroup *cgrp)
 {
 	/* All of these checks rely on RCU to keep the cgroup
 	 * structure alive */
-	if (cgroup_is_releasable(cgrp) && !atomic_read(&cgrp->count)
-	    && list_empty(&cgrp->children) && !cgroup_has_css_refs(cgrp)) {
-		/* Control Group is currently removeable. If it's not
+	if (cgroup_is_releasable(cgrp) &&
+	    !atomic_read(&cgrp->count) && list_empty(&cgrp->children)) {
+		/*
+		 * Control Group is currently removeable. If it's not
 		 * already queued for a userspace notification, queue
-		 * it now */
+		 * it now
+		 */
 		int need_schedule_work = 0;
+
 		raw_spin_lock(&release_list_lock);
 		if (!cgroup_is_removed(cgrp) &&
 		    list_empty(&cgrp->release_list)) {
@@ -5100,24 +4987,11 @@ EXPORT_SYMBOL_GPL(__css_tryget);
 /* Caller must verify that the css is not for root cgroup */
 void __css_put(struct cgroup_subsys_state *css)
 {
-	struct cgroup *cgrp = css->cgroup;
 	int v;
 
-	rcu_read_lock();
 	v = css_unbias_refcnt(atomic_dec_return(&css->refcnt));
-
-	switch (v) {
-	case 1:
-		if (notify_on_release(cgrp)) {
-			set_bit(CGRP_RELEASABLE, &cgrp->flags);
-			check_for_release(cgrp);
-		}
-		break;
-	case 0:
+	if (v == 0)
 		schedule_work(&css->dput_work);
-		break;
-	}
-	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(__css_put);