cgroups: implement namespace tracking subsystem

When a task enters a new namespace via a clone() or unshare(), a new cgroup
is created and the task moves into it.

This version names cgroups which are automatically created using
cgroup_clone() as "node_<pid>" where pid is the pid of the unsharing or
cloned process.  (Thanks Pavel for the idea) This is safe because if the
process unshares again, it will create

	/cgroups/(...)/node_<pid>/node_<pid>

The only possibilities (AFAICT) for a -EEXIST on unshare are

	1. pid wraparound
	2. a process fails an unshare, then tries again.

Case 1 is unlikely enough that I ignore it (at least for now).  In case 2, the
node_<pid> will be empty and can be rmdir'ed to make the subsequent unshare()
succeed.

Changelog:
	Name cloned cgroups as "node_<pid>".

[clg@fr.ibm.com: fix order of cgroup subsystems in init/Kconfig]
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Paul Menage <menage@google.com>
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 146 insertions, 8 deletions

diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index cbadc3b5dbc0..651ff0869b2d 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -24,3 +24,9 @@ SUBSYS(debug)
 #endif
 
 /* */
+
+#ifdef CONFIG_CGROUP_NS
+SUBSYS(ns)
+#endif
+
+/* */
diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index 033a648709b6..f1eca68751a9 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -55,4 +55,11 @@ static inline void exit_task_namespaces(struct task_struct *p)
 		put_nsproxy(ns);
 	}
 }
+
+#ifdef CONFIG_CGROUP_NS
+int ns_cgroup_clone(struct task_struct *tsk);
+#else
+static inline int ns_cgroup_clone(struct task_struct *tsk) { return 0; }
+#endif
+
 #endif
diff --git a/init/Kconfig b/init/Kconfig
index 6687f805b38d..0007d1b5e867 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -288,6 +288,22 @@ config CGROUP_DEBUG
 
 	  Say N if unsure
 
+config CGROUP_NS
+        bool "Namespace cgroup subsystem"
+        depends on CGROUPS
+        help
+          Provides a simple namespace cgroup subsystem to
+          provide hierarchical naming of sets of namespaces,
+          for instance virtual servers and checkpoint/restart
+          jobs.
+
+config CGROUP_CPUACCT
+	bool "Simple CPU accounting cgroup subsystem"
+	depends on CGROUPS
+	help
+	  Provides a simple Resource Controller for monitoring the
+	  total CPU consumed by the tasks in a cgroup
+
 config CPUSETS
 	bool "Cpuset support"
 	depends on SMP && CGROUPS
@@ -345,13 +361,6 @@ config PROC_PID_CPUSET
 	depends on CPUSETS
 	default y
 
-config CGROUP_CPUACCT
-	bool "Simple CPU accounting cgroup subsystem"
-	depends on CGROUPS
-	help
-	  Provides a simple Resource Controller for monitoring the
-	  total CPU consumed by the tasks in a cgroup
-
 config RELAY
 	bool "Kernel->user space relay support (formerly relayfs)"
 	help
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;
 }