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>

1 files changed, 100 insertions, 0 deletions

diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c
new file mode 100644
index 0000000..aead4d6
--- /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,
+};