Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull userns fixes from Eric W Biederman:
 "The bulk of the changes are fixing the worst consequences of the user
  namespace design oversight in not considering what happens when one
  namespace starts off as a clone of another namespace, as happens with
  the mount namespace.

  The rest of the changes are just plain bug fixes.

  Many thanks to Andy Lutomirski for pointing out many of these issues."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  userns: Restrict when proc and sysfs can be mounted
  ipc: Restrict mounting the mqueue filesystem
  vfs: Carefully propogate mounts across user namespaces
  vfs: Add a mount flag to lock read only bind mounts
  userns:  Don't allow creation if the user is chrooted
  yama:  Better permission check for ptraceme
  pid: Handle the exit of a multi-threaded init.
  scm: Require CAP_SYS_ADMIN over the current pidns to spoof pids.

3 files changed, 15 insertions, 1 deletions

diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index c1c3dc1c6023..bea15bdf82b0 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -181,6 +181,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
         int nr;
         int rc;
         struct task_struct *task, *me = current;
+        int init_pids = thread_group_leader(me) ? 1 : 2;
 
         /* Don't allow any more processes into the pid namespace */
         disable_pid_allocation(pid_ns);
@@ -230,7 +231,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
          */
         for (;;) {
                 set_current_state(TASK_UNINTERRUPTIBLE);
-                if (pid_ns->nr_hashed == 1)
+                if (pid_ns->nr_hashed == init_pids)
                         break;
                 schedule();
         }
diff --git a/kernel/user.c b/kernel/user.c
index e81978e8c03b..8e635a18ab52 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,6 +51,8 @@ struct user_namespace init_user_ns = {
         .owner = GLOBAL_ROOT_UID,
         .group = GLOBAL_ROOT_GID,
         .proc_inum = PROC_USER_INIT_INO,
+        .may_mount_sysfs = true,
+        .may_mount_proc = true,
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index b14f4d342043..a54f26f82eb2 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -61,6 +61,15 @@ int create_user_ns(struct cred *new)
         kgid_t group = new->egid;
         int ret;
 
+        /*
+         * Verify that we can not violate the policy of which files
+         * may be accessed that is specified by the root directory,
+         * by verifing that the root directory is at the root of the
+         * mount namespace which allows all files to be accessed.
+         */
+        if (current_chrooted())
+                return -EPERM;
+
         /* The creator needs a mapping in the parent user namespace
          * or else we won't be able to reasonably tell userspace who
          * created a user_namespace.
@@ -87,6 +96,8 @@ int create_user_ns(struct cred *new)
 
         set_cred_user_ns(new, ns);
 
+        update_mnt_policy(ns);
+
         return 0;
 }