userns: Require CAP_SYS_ADMIN for most uses of setns.

Andy Lutomirski <luto@amacapital.net> found a nasty little bug in
the permissions of setns.  With unprivileged user namespaces it
became possible to create new namespaces without privilege.

However the setns calls were relaxed to only require CAP_SYS_ADMIN in
the user nameapce of the targed namespace.

Which made the following nasty sequence possible.

pid = clone(CLONE_NEWUSER | CLONE_NEWNS);
if (pid == 0) { /* child */
	system("mount --bind /home/me/passwd /etc/passwd");
}
else if (pid != 0) { /* parent */
	char path[PATH_MAX];
	snprintf(path, sizeof(path), "/proc/%u/ns/mnt");
	fd = open(path, O_RDONLY);
	setns(fd, 0);
	system("su -");
}

Prevent this possibility by requiring CAP_SYS_ADMIN
in the current user namespace when joing all but the user namespace.

Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

5 files changed, 10 insertions, 5 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index c1bbe86f4920..398a50ff2438 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2781,7 +2781,8 @@ static int mntns_install(struct nsproxy *nsproxy, void *ns)
         struct path root;
 
         if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) ||
-            !nsown_capable(CAP_SYS_CHROOT))
+            !nsown_capable(CAP_SYS_CHROOT) ||
+            !nsown_capable(CAP_SYS_ADMIN))
                 return -EPERM;
 
         if (fs->users != 1)
diff --git a/ipc/namespace.c b/ipc/namespace.c
index cf3386a51de2..7c1fa451b0b0 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -170,7 +170,8 @@ static void ipcns_put(void *ns)
 static int ipcns_install(struct nsproxy *nsproxy, void *new)
 {
         struct ipc_namespace *ns = new;
-        if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
+        if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
+            !nsown_capable(CAP_SYS_ADMIN))
                 return -EPERM;
 
         /* Ditch state from the old ipc namespace */
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 560da0dab230..fdbd0cdf271a 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -325,7 +325,8 @@ static int pidns_install(struct nsproxy *nsproxy, void *ns)
         struct pid_namespace *active = task_active_pid_ns(current);
         struct pid_namespace *ancestor, *new = ns;
 
-        if (!ns_capable(new->user_ns, CAP_SYS_ADMIN))
+        if (!ns_capable(new->user_ns, CAP_SYS_ADMIN) ||
+            !nsown_capable(CAP_SYS_ADMIN))
                 return -EPERM;
 
         /*
diff --git a/kernel/utsname.c b/kernel/utsname.c
index f6336d51d64c..08b197e8c485 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -113,7 +113,8 @@ static int utsns_install(struct nsproxy *nsproxy, void *new)
 {
         struct uts_namespace *ns = new;
 
-        if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
+        if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
+            !nsown_capable(CAP_SYS_ADMIN))
                 return -EPERM;
 
         get_uts_ns(ns);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 2e9a3132b8dd..8acce01b6dab 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -649,7 +649,8 @@ static int netns_install(struct nsproxy *nsproxy, void *ns)
 {
         struct net *net = ns;
 
-        if (!ns_capable(net->user_ns, CAP_SYS_ADMIN))
+        if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) ||
+            !nsown_capable(CAP_SYS_ADMIN))
                 return -EPERM;
 
         put_net(nsproxy->net_ns);