userns: Implement unshare of the user namespace

- Add CLONE_THREAD to the unshare flags if CLONE_NEWUSER is selected
  As changing user namespaces is only valid if all there is only
  a single thread.
- Restore the code to add CLONE_VM if CLONE_THREAD is selected and
  the code to addCLONE_SIGHAND if CLONE_VM is selected.
  Making the constraints in the code clear.

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

3 files changed, 41 insertions, 7 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 8c29abb19014..38e53b87402c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1687,7 +1687,7 @@ static int check_unshare_flags(unsigned long unshare_flags)
         if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
                                 CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
                                 CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET|
-                                CLONE_NEWPID))
+                                CLONE_NEWUSER|CLONE_NEWPID))
                 return -EINVAL;
         /*
          * Not implemented, but pretend it works if there is nothing to
@@ -1754,11 +1754,17 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 {
         struct fs_struct *fs, *new_fs = NULL;
         struct files_struct *fd, *new_fd = NULL;
+        struct cred *new_cred = NULL;
         struct nsproxy *new_nsproxy = NULL;
         int do_sysvsem = 0;
         int err;
 
         /*
+         * If unsharing a user namespace must also unshare the thread.
+         */
+        if (unshare_flags & CLONE_NEWUSER)
+                unshare_flags |= CLONE_THREAD;
+        /*
          * If unsharing a pid namespace must also unshare the thread.
          */
         if (unshare_flags & CLONE_NEWPID)
@@ -1795,11 +1801,15 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
         err = unshare_fd(unshare_flags, &new_fd);
         if (err)
                 goto bad_unshare_cleanup_fs;
-        err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_fs);
+        err = unshare_userns(unshare_flags, &new_cred);
         if (err)
                 goto bad_unshare_cleanup_fd;
+        err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy,
+                                         new_cred, new_fs);
+        if (err)
+                goto bad_unshare_cleanup_cred;
 
-        if (new_fs || new_fd || do_sysvsem || new_nsproxy) {
+        if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) {
                 if (do_sysvsem) {
                         /*
                          * CLONE_SYSVSEM is equivalent to sys_exit().
@@ -1832,11 +1842,20 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
                 }
 
                 task_unlock(current);
+
+                if (new_cred) {
+                        /* Install the new user namespace */
+                        commit_creds(new_cred);
+                        new_cred = NULL;
+                }
         }
 
         if (new_nsproxy)
                 put_nsproxy(new_nsproxy);
 
+bad_unshare_cleanup_cred:
+        if (new_cred)
+                put_cred(new_cred);
 bad_unshare_cleanup_fd:
         if (new_fd)
                 put_files_struct(new_fd);
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 2ddd81657a2a..78e2ecb20165 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -186,7 +186,7 @@ void free_nsproxy(struct nsproxy *ns)
  * On success, returns the new nsproxy.
  */
 int unshare_nsproxy_namespaces(unsigned long unshare_flags,
-                struct nsproxy **new_nsp, struct fs_struct *new_fs)
+        struct nsproxy **new_nsp, struct cred *new_cred, struct fs_struct *new_fs)
 {
         struct user_namespace *user_ns;
         int err = 0;
@@ -195,12 +195,12 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags,
                                CLONE_NEWNET | CLONE_NEWPID)))
                 return 0;
 
-        if (!nsown_capable(CAP_SYS_ADMIN))
+        user_ns = new_cred ? new_cred->user_ns : current_user_ns();
+        if (!ns_capable(user_ns, CAP_SYS_ADMIN))
                 return -EPERM;
 
-        user_ns = current_user_ns();
         *new_nsp = create_new_namespaces(unshare_flags, current, user_ns,
-                                new_fs ? new_fs : current->fs);
+                                         new_fs ? new_fs : current->fs);
         if (IS_ERR(*new_nsp)) {
                 err = PTR_ERR(*new_nsp);
                 goto out;
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index a9460774e77d..ce92f7e6290a 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -82,6 +82,21 @@ int create_user_ns(struct cred *new)
         return 0;
 }
 
+int unshare_userns(unsigned long unshare_flags, struct cred **new_cred)
+{
+        struct cred *cred;
+
+        if (!(unshare_flags & CLONE_NEWUSER))
+                return 0;
+
+        cred = prepare_creds();
+        if (!cred)
+                return -ENOMEM;
+
+        *new_cred = cred;
+        return create_user_ns(cred);
+}
+
 void free_user_ns(struct kref *kref)
 {
         struct user_namespace *parent, *ns =