From: Paul Menage <menage@google.com>

Add the following files to the cgroup filesystem:

notify_on_release - configures/reports whether the cgroup subsystem should
attempt to run a release script when this cgroup becomes unused

release_agent - configures/reports the release agent to be used for this
hierarchy (top level in each hierarchy only)

releasable - reports whether this cgroup would have been auto-released if
notify_on_release was true and a release agent was configured (mainly useful
for debugging)

To avoid locking issues, invoking the userspace release agent is done via a
workqueue task; cgroups that need to have their release agents invoked by
the workqueue task are linked on to a list.

Signed-off-by: Paul Menage <menage@google.com>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Paul Jackson <pj@sgi.com>
Cc: Kirill Korotaev <dev@openvz.org>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/cgroup.h |   11 
 kernel/cgroup.c        |  425 ++++++++++++++++++++++++++++++++----
 2 files changed, 393 insertions(+), 43 deletions(-)

diff -puN include/linux/cgroup.h~task-cgroupsv11-automatic-userspace-notification-of-idle-cgroups include/linux/cgroup.h
--- a/include/linux/cgroup.h~task-cgroupsv11-automatic-userspace-notification-of-idle-cgroups
+++ a/include/linux/cgroup.h
@@ -77,10 +77,11 @@ static inline void css_get(struct contai
  * css_get()
  */
 
+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))
-		atomic_dec(&css->refcnt);
+		__css_put(css);
 }
 
 struct cgroup {
@@ -112,6 +113,13 @@ struct cgroup {
 	 * tasks in this cgroup. Protected by css_set_lock
 	 */
 	struct list_head css_sets;
+
+	/*
+	 * Linked list running through all cgroups that can
+	 * potentially be reaped by the release agent. Protected by
+	 * release_list_lock
+	 */
+	struct list_head release_list;
 };
 
 /* A css_set is a structure holding pointers to a set of
@@ -285,7 +293,6 @@ struct task_struct *cgroup_iter_next(
 					struct cgroup_iter *it);
 void cgroup_iter_end(struct cgroup *cont, struct cgroup_iter *it);
 
-
 #else /* !CONFIG_CGROUPS */
 
 static inline int cgroup_init_early(void) { return 0; }
diff -puN kernel/cgroup.c~task-cgroupsv11-automatic-userspace-notification-of-idle-cgroups kernel/cgroup.c
--- a/kernel/cgroup.c~task-cgroupsv11-automatic-userspace-notification-of-idle-cgroups
+++ a/kernel/cgroup.c
@@ -44,6 +44,8 @@
 #include <linux/sort.h>
 #include <asm/atomic.h>
 
+static DEFINE_MUTEX(cgroup_mutex);
+
 /* Generate an array of cgroup subsystem pointers */
 #define SUBSYS(_x) &_x ## _subsys,
 
@@ -82,6 +84,13 @@ struct cgroupfs_root {
 
 	/* Hierarchy-specific flags */
 	unsigned long flags;
+
+	/* The path to use for release notifications. No locking
+	 * between setting and use - so if userspace updates this
+	 * while child cgroups exist, you could miss a
+	 * notification. We ensure that it's always a valid
+	 * NUL-terminated string */
+	char release_agent_path[PATH_MAX];
 };
 
 
@@ -109,7 +118,13 @@ static int need_forkexit_callback;
 
 /* bits in struct cgroup flags field */
 enum {
+	/* Control Group is dead */
 	CONT_REMOVED,
+	/* Control Group has previously had a child cgroup or a task,
+	 * but no longer (only if CONT_NOTIFY_ON_RELEASE is set) */
+	CONT_RELEASABLE,
+	/* Control Group requires release notifications to userspace */
+	CONT_NOTIFY_ON_RELEASE,
 };
 
 /* convenient tests for these bits */
@@ -123,6 +138,19 @@ enum {
 	ROOT_NOPREFIX, /* mounted subsystems have no named prefix */
 };
 
+inline int cgroup_is_releasable(const struct cgroup *cont)
+{
+	const int bits =
+		(1 << CONT_RELEASABLE) |
+		(1 << CONT_NOTIFY_ON_RELEASE);
+	return (cont->flags & bits) == bits;
+}
+
+inline int notify_on_release(const struct cgroup *cont)
+{
+	return test_bit(CONT_NOTIFY_ON_RELEASE, &cont->flags);
+}
+
 /*
  * for_each_subsys() allows you to iterate on each subsystem attached to
  * an active hierarchy
@@ -134,6 +162,14 @@ list_for_each_entry(_ss, &_root->subsys_
 #define for_each_root(_root) \
 list_for_each_entry(_root, &roots, root_list)
 
+/* the list of cgroups eligible for automatic release. Protected by
+ * release_list_lock */
+static LIST_HEAD(release_list);
+static DEFINE_SPINLOCK(release_list_lock);
+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 *cont);
+
 /* Link structure for associating css_set objects with cgroups */
 struct cg_cgroup_link {
 	/*
@@ -188,11 +224,8 @@ static int use_task_css_set_links;
 /*
  * unlink a css_set from the list and free it
  */
-static void release_css_set(struct kref *k)
+static void unlink_css_set(struct css_set *cg)
 {
-	struct css_set *cg = container_of(k, struct css_set, ref);
-	int i;
-
 	write_lock(&css_set_lock);
 	list_del(&cg->list);
 	css_set_count--;
@@ -205,11 +238,39 @@ static void release_css_set(struct kre
 		kfree(link);
 	}
 	write_unlock(&css_set_lock);
-	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++)
-		atomic_dec(&cg->subsys[i]->cgroup->count);
+}
+
+static void __release_css_set(struct kref *k, int taskexit)
+{
+	int i;
+	struct css_set *cg = container_of(k, struct css_set, ref);
+
+	unlink_css_set(cg);
+
+	rcu_read_lock();
+	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+		struct cgroup *cont = cg->subsys[i]->cgroup;
+		if (atomic_dec_and_test(&cont->count) &&
+		    notify_on_release(cont)) {
+			if (taskexit)
+				set_bit(CONT_RELEASABLE, &cont->flags);
+			check_for_release(cont);
+		}
+	}
+	rcu_read_unlock();
 	kfree(cg);
 }
 
+static void release_css_set(struct kref *k)
+{
+	__release_css_set(k, 0);
+}
+
+static void release_css_set_taskexit(struct kref *k)
+{
+	__release_css_set(k, 1);
+}
+
 /*
  * refcounted get/put for css_set objects
  */
@@ -223,6 +284,11 @@ static inline void put_css_set(struct 
 	kref_put(&cg->ref, release_css_set);
 }
 
+static inline void put_css_set_taskexit(struct css_set *cg)
+{
+	kref_put(&cg->ref, release_css_set_taskexit);
+}
+
 /*
  * find_existing_css_set() is a helper for
  * find_css_set(), and checks to see whether an existing
@@ -464,8 +530,6 @@ static struct css_set *find_css_set(
  * update of a tasks cgroup pointer by attach_task()
  */
 
-static DEFINE_MUTEX(cgroup_mutex);
-
 /**
  * cgroup_lock - lock out any changes to cgroup structures
  *
@@ -524,6 +588,13 @@ static void cgroup_diput(struct dentr
 	if (S_ISDIR(inode->i_mode)) {
 		struct cgroup *cont = dentry->d_fsdata;
 		BUG_ON(!(cgroup_is_removed(cont)));
+		/* It's possible for external users to be holding css
+		 * reference counts on a cgroup; css_put() needs to
+		 * be able to access the cgroup after decrementing
+		 * the reference count in order to know if it needs to
+		 * queue the cgroup to be handled by the release
+		 * agent */
+		synchronize_rcu();
 		kfree(cont);
 	}
 	iput(inode);
@@ -668,6 +739,8 @@ static int cgroup_show_options(struct
 		seq_printf(seq, ",%s", ss->name);
 	if (test_bit(ROOT_NOPREFIX, &root->flags))
 		seq_puts(seq, ",noprefix");
+	if (strlen(root->release_agent_path))
+		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
 	mutex_unlock(&cgroup_mutex);
 	return 0;
 }
@@ -675,6 +748,7 @@ static int cgroup_show_options(struct
 struct cgroup_sb_opts {
 	unsigned long subsys_bits;
 	unsigned long flags;
+	char *release_agent;
 };
 
 /* Convert a hierarchy specifier into a bitmask of subsystems and
@@ -686,6 +760,7 @@ static int parse_cgroupfs_options(cha
 
 	opts->subsys_bits = 0;
 	opts->flags = 0;
+	opts->release_agent = NULL;
 
 	while ((token = strsep(&o, ",")) != NULL) {
 		if (!*token)
@@ -694,6 +769,15 @@ static int parse_cgroupfs_options(cha
 			opts->subsys_bits = (1 << CGROUP_SUBSYS_COUNT) - 1;
 		} else if (!strcmp(token, "noprefix")) {
 			set_bit(ROOT_NOPREFIX, &opts->flags);
+		} else if (!strncmp(token, "release_agent=", 14)) {
+			/* Specifying two release agents is forbidden */
+			if (opts->release_agent)
+				return -EINVAL;
+			opts->release_agent = kzalloc(PATH_MAX, GFP_KERNEL);
+			if (!opts->release_agent)
+				return -ENOMEM;
+			strncpy(opts->release_agent, token + 14, PATH_MAX - 1);
+			opts->release_agent[PATH_MAX - 1] = 0;
 		} else {
 			struct cgroup_subsys *ss;
 			int i;
@@ -743,7 +827,11 @@ static int cgroup_remount(struct supe
 	if (!ret)
 		cgroup_populate_dir(cont);
 
+	if (opts.release_agent)
+		strcpy(root->release_agent_path, opts.release_agent);
  out_unlock:
+	if (opts.release_agent)
+		kfree(opts.release_agent);
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cont->dentry->d_inode->i_mutex);
 	return ret;
@@ -767,6 +855,7 @@ static void init_cgroup_root(struct c
 	INIT_LIST_HEAD(&cont->sibling);
 	INIT_LIST_HEAD(&cont->children);
 	INIT_LIST_HEAD(&cont->css_sets);
+	INIT_LIST_HEAD(&cont->release_list);
 }
 
 static int cgroup_test_super(struct super_block *sb, void *data)
@@ -841,8 +930,11 @@ static int cgroup_get_sb(struct file_
 
 	/* First find the desired set of subsystems */
 	ret = parse_cgroupfs_options(data, &opts);
-	if (ret)
+	if (ret) {
+		if (opts.release_agent)
+			kfree(opts.release_agent);
 		return ret;
+	}
 
 	root = kzalloc(sizeof(*root), GFP_KERNEL);
 	if (!root)
@@ -851,6 +943,10 @@ static int cgroup_get_sb(struct file_
 	init_cgroup_root(roo