3 files changed, 117 insertions, 1 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index a50a6debe5fc..32b2d8bdc9f5 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -40,6 +40,7 @@ obj-$(CONFIG_CGROUPS) += cgroup.o
 obj-$(CONFIG_CGROUP_DEBUG) += cgroup_debug.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
 obj-$(CONFIG_CGROUP_CPUACCT) += cpu_acct.o
+obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o
 obj-$(CONFIG_IKCONFIG) += configs.o
 obj-$(CONFIG_STOP_MACHINE) += stop_machine.o
 obj-$(CONFIG_AUDIT) += audit.o auditfilter.o
diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c
new file mode 100644
index 000000000000..aead4d69f62b
--- /dev/null
+++ b/kernel/ns_cgroup.c
@@ -0,0 +1,100 @@
+/*
+ * ns_cgroup.c - namespace cgroup subsystem
+ *
+ * Copyright 2006, 2007 IBM Corp
+ */
+
+#include <linux/module.h>
+#include <linux/cgroup.h>
+#include <linux/fs.h>
+
+struct ns_cgroup {
+	struct cgroup_subsys_state css;
+	spinlock_t lock;
+};
+
+struct cgroup_subsys ns_subsys;
+
+static inline struct ns_cgroup *cgroup_to_ns(
+		struct cgroup *cgroup)
+{
+	return container_of(cgroup_subsys_state(cgroup, ns_subsys_id),
+			    struct ns_cgroup, css);
+}
+
+int ns_cgroup_clone(struct task_struct *task)
+{
+	return cgroup_clone(task, &ns_subsys);
+}
+
+/*
+ * Rules:
+ *   1. you can only enter a cgroup which is a child of your current
+ *     cgroup
+ *   2. you can only place another process into a cgroup if
+ *     a. you have CAP_SYS_ADMIN
+ *     b. your cgroup is an ancestor of task's destination cgroup
+ *       (hence either you are in the same cgroup as task, or in an
+ *        ancestor cgroup thereof)
+ */
+static int ns_can_attach(struct cgroup_subsys *ss,
+		struct cgroup *new_cgroup, struct task_struct *task)
+{
+	struct cgroup *orig;
+
+	if (current != task) {
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		if (!cgroup_is_descendant(new_cgroup))
+			return -EPERM;
+	}
+
+	if (atomic_read(&new_cgroup->count) != 0)
+		return -EPERM;
+
+	orig = task_cgroup(task, ns_subsys_id);
+	if (orig && orig != new_cgroup->parent)
+		return -EPERM;
+
+	return 0;
+}
+
+/*
+ * Rules: you can only create a cgroup if
+ *     1. you are capable(CAP_SYS_ADMIN)
+ *     2. the target cgroup is a descendant of your own cgroup
+ */
+static struct cgroup_subsys_state *ns_create(struct cgroup_subsys *ss,
+						struct cgroup *cgroup)
+{
+	struct ns_cgroup *ns_cgroup;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+	if (!cgroup_is_descendant(cgroup))
+		return ERR_PTR(-EPERM);
+
+	ns_cgroup = kzalloc(sizeof(*ns_cgroup), GFP_KERNEL);
+	if (!ns_cgroup)
+		return ERR_PTR(-ENOMEM);
+	spin_lock_init(&ns_cgroup->lock);
+	return &ns_cgroup->css;
+}
+
+static void ns_destroy(struct cgroup_subsys *ss,
+			struct cgroup *cgroup)
+{
+	struct ns_cgroup *ns_cgroup;
+
+	ns_cgroup = cgroup_to_ns(cgroup);
+	kfree(ns_cgroup);
+}
+
+struct cgroup_subsys ns_subsys = {
+	.name = "ns",
+	.can_attach = ns_can_attach,
+	.create = ns_create,
+	.destroy  = ns_destroy,
+	.subsys_id = ns_subsys_id,
+};
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 049e7c0ac566..ac99837e7a04 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -156,7 +156,14 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 		goto out;
 	}
 
+	err = ns_cgroup_clone(tsk);
+	if (err) {
+		put_nsproxy(new_ns);
+		goto out;
+	}
+
 	tsk->nsproxy = new_ns;
+
 out:
 	put_nsproxy(old_ns);
 	return err;
@@ -196,8 +203,16 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags,
 
 	*new_nsp = create_new_namespaces(unshare_flags, current,
 				new_fs ? new_fs : current->fs);
-	if (IS_ERR(*new_nsp))
+	if (IS_ERR(*new_nsp)) {
 		err = PTR_ERR(*new_nsp);
+		goto out;
+	}
+
+	err = ns_cgroup_clone(current);
+	if (err)
+		put_nsproxy(*new_nsp);
+
+out:
 	return err;
 }