userns: add a user_namespace as creator/owner of uts_namespace

The expected course of development for user namespaces targeted
capabilities is laid out at https://wiki.ubuntu.com/UserNamespace.

Goals:

- Make it safe for an unprivileged user to unshare namespaces.  They
  will be privileged with respect to the new namespace, but this should
  only include resources which the unprivileged user already owns.

- Provide separate limits and accounting for userids in different
  namespaces.

Status:

  Currently (as of 2.6.38) you can clone with the CLONE_NEWUSER flag to
  get a new user namespace if you have the CAP_SYS_ADMIN, CAP_SETUID, and
  CAP_SETGID capabilities.  What this gets you is a whole new set of
  userids, meaning that user 500 will have a different 'struct user' in
  your namespace than in other namespaces.  So any accounting information
  stored in struct user will be unique to your namespace.

  However, throughout the kernel there are checks which

  - simply check for a capability.  Since root in a child namespace
    has all capabilities, this means that a child namespace is not
    constrained.

  - simply compare uid1 == uid2.  Since these are the integer uids,
    uid 500 in namespace 1 will be said to be equal to uid 500 in
    namespace 2.

  As a result, the lxc implementation at lxc.sf.net does not use user
  namespaces.  This is actually helpful because it leaves us free to
  develop user namespaces in such a way that, for some time, user
  namespaces may be unuseful.

Bugs aside, this patchset is supposed to not at all affect systems which
are not actively using user namespaces, and only restrict what tasks in
child user namespace can do.  They begin to limit privilege to a user
namespace, so that root in a container cannot kill or ptrace tasks in the
parent user namespace, and can only get world access rights to files.
Since all files currently belong to the initila user namespace, that means
that child user namespaces can only get world access rights to *all*
files.  While this temporarily makes user namespaces bad for system
containers, it starts to get useful for some sandboxing.

I've run the 'runltplite.sh' with and without this patchset and found no
difference.

This patch:

copy_process() handles CLONE_NEWUSER before the rest of the namespaces.
So in the case of clone(CLONE_NEWUSER|CLONE_NEWUTS) the new uts namespace
will have the new user namespace as its owner.  That is what we want,
since we want root in that new userns to be able to have privilege over
it.

Changelog:
	Feb 15: don't set uts_ns->user_ns if we didn't create
		a new uts_ns.
	Feb 23: Move extern init_user_ns declaration from
		init/version.c to utsname.h.

Signed-off-by: Serge E. Hallyn <serge.hallyn@canonical.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Daniel Lezcano <daniel.lezcano@free.fr>
Acked-by: David Howells <dhowells@redhat.com>
Cc: James Morris <jmorris@namei.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 20 insertions, 2 deletions

diff --git a/include/linux/utsname.h b/include/linux/utsname.h
index 69f3997..2c3c0f5 100644
--- a/include/linux/utsname.h
+++ b/include/linux/utsname.h
@@ -37,9 +37,13 @@ struct new_utsname {
 #include <linux/nsproxy.h>
 #include <linux/err.h>
 
+struct user_namespace;
+extern struct user_namespace init_user_ns;
+
 struct uts_namespace {
 	struct kref kref;
 	struct new_utsname name;
+	struct user_namespace *user_ns;
 };
 extern struct uts_namespace init_uts_ns;
 
diff --git a/init/version.c b/init/version.c
index adff586..86fe0cc 100644
--- a/init/version.c
+++ b/init/version.c
@@ -33,6 +33,7 @@ struct uts_namespace init_uts_ns = {
 		.machine	= UTS_MACHINE,
 		.domainname	= UTS_DOMAINNAME,
 	},
+	.user_ns = &init_user_ns,
 };
 EXPORT_SYMBOL_GPL(init_uts_ns);
 
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index f74e6c0..034dc2e 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -74,6 +74,11 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 		err = PTR_ERR(new_nsp->uts_ns);
 		goto out_uts;
 	}
+	if (new_nsp->uts_ns != tsk->nsproxy->uts_ns) {
+		put_user_ns(new_nsp->uts_ns->user_ns);
+		new_nsp->uts_ns->user_ns = task_cred_xxx(tsk, user)->user_ns;
+		get_user_ns(new_nsp->uts_ns->user_ns);
+	}
 
 	new_nsp->ipc_ns = copy_ipcs(flags, tsk->nsproxy->ipc_ns);
 	if (IS_ERR(new_nsp->ipc_ns)) {
diff --git a/kernel/user.c b/kernel/user.c
index 5c598ca..9e03e9c 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -17,9 +17,13 @@
 #include <linux/module.h>
 #include <linux/user_namespace.h>
 
+/*
+ * userns count is 1 for root user, 1 for init_uts_ns,
+ * and 1 for... ?
+ */
 struct user_namespace init_user_ns = {
 	.kref = {
-		.refcount	= ATOMIC_INIT(2),
+		.refcount	= ATOMIC_INIT(3),
 	},
 	.creator = &root_user,
 };
@@ -47,7 +51,7 @@ static struct kmem_cache *uid_cachep;
  */
 static DEFINE_SPINLOCK(uidhash_lock);
 
-/* root_user.__count is 2, 1 for init task cred, 1 for init_user_ns->creator */
+/* root_user.__count is 2, 1 for init task cred, 1 for init_user_ns->user_ns */
 struct user_struct root_user = {
 	.__count	= ATOMIC_INIT(2),
 	.processes	= ATOMIC_INIT(1),
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 8a82b4b..a7b3a8d 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -14,6 +14,7 @@
 #include <linux/utsname.h>
 #include <linux/err.h>
 #include <linux/slab.h>
+#include <linux/user_namespace.h>
 
 static struct uts_namespace *create_uts_ns(void)
 {
@@ -40,6 +41,8 @@ static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns)
 
 	down_read(&uts_sem);
 	memcpy(&ns->name, &old_ns->name, sizeof(ns->name));
+	ns->user_ns = old_ns->user_ns;
+	get_user_ns(ns->user_ns);
 	up_read(&uts_sem);
 	return ns;
 }
@@ -71,5 +74,6 @@ void free_uts_ns(struct kref *kref)
 	struct uts_namespace *ns;
 
 	ns = container_of(kref, struct uts_namespace, kref);
+	put_user_ns(ns->user_ns);
 	kfree(ns);
 }