userns: Don't allow CLONE_NEWUSER | CLONE_FS

commit e66eded8 upstream.

Don't allowing sharing the root directory with processes in a
different user namespace.  There doesn't seem to be any point, and to
allow it would require the overhead of putting a user namespace
reference in fs_struct (for permission checks) and incrementing that
reference count on practically every call to fork.

So just perform the inexpensive test of forbidding sharing fs_struct
acrosss processes in different user namespaces.  We already disallow
other forms of threading when unsharing a user namespace so this
should be no real burden in practice.

This updates setns, clone, and unshare to disallow multiple user
namespaces sharing an fs_struct.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

kernel/fork.c

@@ -1141,6 +1141,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
 		return ERR_PTR(-EINVAL);
 
+	if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS))
+		return ERR_PTR(-EINVAL);
+
 	/*
 	 * Thread groups must share signals as well, and detached threads
 	 * can only be started up within the thread group.
@@ -1801,7 +1804,7 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 	 * If unsharing a user namespace must also unshare the thread.
 	 */
 	if (unshare_flags & CLONE_NEWUSER)
-		unshare_flags |= CLONE_THREAD;
+		unshare_flags |= CLONE_THREAD | CLONE_FS;
 	/*
 	 * If unsharing a pid namespace must also unshare the thread.
 	 */

kernel/user_namespace.c

@@ -21,6 +21,7 @@
 #include <linux/uaccess.h>
 #include <linux/ctype.h>
 #include <linux/projid.h>
+#include <linux/fs_struct.h>
 
 static struct kmem_cache *user_ns_cachep __read_mostly;
 
@@ -803,6 +804,9 @@ static int userns_install(struct nsproxy *nsproxy, void *ns)
 	if (atomic_read(&current->mm->mm_users) > 1)
 		return -EINVAL;
 
+	if (current->fs->users != 1)
+		return -EINVAL;
+
 	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
 		return -EPERM;