Merge branch 'android-2.6.36' into android-tegra-2.6.36

2 files changed, 98 insertions, 87 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 0c991023ee47..ae9613be93fd 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -84,12 +84,6 @@ enum {
 	CSS_REMOVED, /* This CSS is dead */
 };
 
-/* Caller must verify that the css is not for root cgroup */
-static inline void __css_get(struct cgroup_subsys_state *css, int count)
-{
-	atomic_add(count, &css->refcnt);
-}
-
 /*
  * Call css_get() to hold a reference on the css; it can be used
  * for a reference obtained via:
@@ -97,6 +91,7 @@ static inline void __css_get(struct cgroup_subsys_state *css, int count)
  * - task->cgroups for a locked task
  */
 
+extern 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 */
@@ -143,10 +138,7 @@ static inline void css_put(struct cgroup_subsys_state *css)
 enum {
 	/* Control Group is dead */
 	CGRP_REMOVED,
-	/*
-	 * Control Group has previously had a child cgroup or a task,
-	 * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set)
-	 */
+	/* Control Group has ever had a child cgroup or a task */
 	CGRP_RELEASABLE,
 	/* Control Group requires release notifications to userspace */
 	CGRP_NOTIFY_ON_RELEASE,
@@ -283,6 +275,7 @@ struct css_set {
 
 	/* For RCU-protected deletion */
 	struct rcu_head rcu_head;
+	struct work_struct work;
 };
 
 /*
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b90316504417..3f1552c7ee11 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -264,6 +264,33 @@ static void cgroup_release_agent(struct work_struct *work);
 static DECLARE_WORK(release_agent_work, cgroup_release_agent);
 static void check_for_release(struct cgroup *cgrp);
 
+/*
+ * 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;
+ */
+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);
+}
+
 /* Link structure for associating css_set objects with cgroups */
 struct cg_cgroup_link {
 	/*
@@ -323,10 +350,35 @@ static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[])
 	return &css_set_table[index];
 }
 
+static void free_css_set_work(struct work_struct *work)
+{
+	struct css_set *cg = container_of(work, struct css_set, work);
+	struct cg_cgroup_link *link;
+	struct cg_cgroup_link *saved_link;
+
+	write_lock(&css_set_lock);
+	list_for_each_entry_safe(link, saved_link, &cg->cg_links,
+				 cg_link_list) {
+		struct cgroup *cgrp = link->cgrp;
+		list_del(&link->cg_link_list);
+		list_del(&link->cgrp_link_list);
+		if (atomic_dec_and_test(&cgrp->count)) {
+			check_for_release(cgrp);
+			cgroup_wakeup_rmdir_waiter(cgrp);
+		}
+		kfree(link);
+	}
+	write_unlock(&css_set_lock);
+
+	kfree(cg);
+}
+
 static void free_css_set_rcu(struct rcu_head *obj)
 {
 	struct css_set *cg = container_of(obj, struct css_set, rcu_head);
-	kfree(cg);
+
+	INIT_WORK(&cg->work, free_css_set_work);
+	schedule_work(&cg->work);
 }
 
 /* We don't maintain the lists running through each css_set to its
@@ -335,10 +387,16 @@ static void free_css_set_rcu(struct rcu_head *obj)
  * compiled into their kernel but not actually in use */
 static int use_task_css_set_links __read_mostly;
 
-static void __put_css_set(struct css_set *cg, int taskexit)
+/*
+ * refcounted get/put for css_set objects
+ */
+static inline void get_css_set(struct css_set *cg)
+{
+	atomic_inc(&cg->refcount);
+}
+
+static void put_css_set(struct css_set *cg)
 {
-	struct cg_cgroup_link *link;
-	struct cg_cgroup_link *saved_link;
 	/*
 	 * Ensure that the refcount doesn't hit zero while any readers
 	 * can see it. Similar to atomic_dec_and_lock(), but for an
@@ -352,48 +410,14 @@ static void __put_css_set(struct css_set *cg, int taskexit)
 		return;
 	}
 
-	/* This css_set is dead. unlink it and release cgroup refcounts */
 	hlist_del(&cg->hlist);
 	css_set_count--;
 
-	list_for_each_entry_safe(link, saved_link, &cg->cg_links,
-				 cg_link_list) {
-		struct cgroup *cgrp = link->cgrp;
-		list_del(&link->cg_link_list);
-		list_del(&link->cgrp_link_list);
-		if (atomic_dec_and_test(&cgrp->count) &&
-		    notify_on_release(cgrp)) {
-			if (taskexit)
-				set_bit(CGRP_RELEASABLE, &cgrp->flags);
-			check_for_release(cgrp);
-		}
-
-		kfree(link);
-	}
-
 	write_unlock(&css_set_lock);
 	call_rcu(&cg->rcu_head, free_css_set_rcu);
 }
 
 /*
- * refcounted get/put for css_set objects
- */
-static inline void get_css_set(struct css_set *cg)
-{
-	atomic_inc(&cg->refcount);
-}
-
-static inline void put_css_set(struct css_set *cg)
-{
-	__put_css_set(cg, 0);
-}
-
-static inline void put_css_set_taskexit(struct css_set *cg)
-{
-	__put_css_set(cg, 1);
-}
-
-/*
  * compare_css_sets - helper function for find_existing_css_set().
  * @cg: candidate css_set being tested
  * @old_cg: existing css_set for a task
@@ -722,9 +746,9 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
  * cgroup_attach_task(), which overwrites one tasks 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
+ * task->cgroups 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 cgroups pointer we use
  * task_lock(), which acts on a spinlock (task->alloc_lock) already in
  * the task_struct routinely used for such matters.
  *
@@ -905,33 +929,6 @@ static void cgroup_d_remove_dir(struct dentry *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;
- */
-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
  * returns an error, no reference counts are touched.
@@ -1773,8 +1770,8 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 		if (ss->attach)
 			ss->attach(ss, cgrp, oldcgrp, tsk, false);
 	}
-	set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
-	synchronize_rcu();
+	set_bit(CGRP_RELEASABLE, &cgrp->flags);
+	/* put_css_set will not destroy cg until after an RCU grace period */
 	put_css_set(cg);
 
 	/*
@@ -3361,6 +3358,8 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	if (err < 0)
 		goto err_remove;
 
+	set_bit(CGRP_RELEASABLE, &parent->flags);
+
 	/* The cgroup directory was pre-locked for us */
 	BUG_ON(!mutex_is_locked(&cgrp->dentry->d_inode->i_mutex));
 
@@ -3492,6 +3491,21 @@ static int cgroup_clear_css_refs(struct cgroup *cgrp)
 	return !failed;
 }
 
+/* checks if all of the css_sets attached to a cgroup have a refcount of 0.
+ * Must be called with css_set_lock held */
+static int cgroup_css_sets_empty(struct cgroup *cgrp)
+{
+	struct cg_cgroup_link *link;
+
+	list_for_each_entry(link, &cgrp->css_sets, cgrp_link_list) {
+		struct css_set *cg = link->cg;
+		if (atomic_read(&cg->refcount) > 0)
+			return 0;
+	}
+
+	return 1;
+}
+
 static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 {
 	struct cgroup *cgrp = dentry->d_fsdata;
@@ -3504,7 +3518,7 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	/* the vfs holds both inode->i_mutex already */
 again:
 	mutex_lock(&cgroup_mutex);
-	if (atomic_read(&cgrp->count) != 0) {
+	if (!cgroup_css_sets_empty(cgrp)) {
 		mutex_unlock(&cgroup_mutex);
 		return -EBUSY;
 	}
@@ -3537,7 +3551,7 @@ again:
 
 	mutex_lock(&cgroup_mutex);
 	parent = cgrp->parent;
-	if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
+	if (!cgroup_css_sets_empty(cgrp) || !list_empty(&cgrp->children)) {
 		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
 		mutex_unlock(&cgroup_mutex);
 		return -EBUSY;
@@ -3579,7 +3593,6 @@ again:
 	cgroup_d_remove_dir(d);
 	dput(d);
 
-	set_bit(CGRP_RELEASABLE, &parent->flags);
 	check_for_release(parent);
 
 	/*
@@ -4174,7 +4187,7 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 	tsk->cgroups = &init_css_set;
 	task_unlock(tsk);
 	if (cg)
-		put_css_set_taskexit(cg);
+		put_css_set(cg);
 }
 
 /**
@@ -4344,6 +4357,14 @@ static void check_for_release(struct cgroup *cgrp)
 }
 
 /* Caller must verify that the css is not for root cgroup */
+void __css_get(struct cgroup_subsys_state *css, int count)
+{
+	atomic_add(count, &css->refcnt);
+	set_bit(CGRP_RELEASABLE, &css->cgroup->flags);
+}
+EXPORT_SYMBOL_GPL(__css_get);
+
+/* Caller must verify that the css is not for root cgroup */
 void __css_put(struct cgroup_subsys_state *css, int count)
 {
 	struct cgroup *cgrp = css->cgroup;
@@ -4351,10 +4372,7 @@ void __css_put(struct cgroup_subsys_state *css, int count)
 	rcu_read_lock();
 	val = atomic_sub_return(count, &css->refcnt);
 	if (val == 1) {
-		if (notify_on_release(cgrp)) {
-			set_bit(CGRP_RELEASABLE, &cgrp->flags);
-			check_for_release(cgrp);
-		}
+		check_for_release(cgrp);
 		cgroup_wakeup_rmdir_waiter(cgrp);
 	}
 	rcu_read_unlock();