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

Pull user namespace updates from Eric Biederman:
 "This finishes up the changes to ensure proc and sysfs do not start
  implementing executable files, as the there are application today that
  are only secure because such files do not exist.

  It akso fixes a long standing misfeature of /proc/<pid>/mountinfo that
  did not show the proper source for files bind mounted from
  /proc/<pid>/ns/*.

  It also straightens out the handling of clone flags related to user
  namespaces, fixing an unnecessary failure of unshare(CLONE_NEWUSER)
  when files such as /proc/<pid>/environ are read while <pid> is calling
  unshare.  This winds up fixing a minor bug in unshare flag handling
  that dates back to the first version of unshare in the kernel.

  Finally, this fixes a minor regression caused by the introduction of
  sysfs_create_mount_point, which broke someone's in house application,
  by restoring the size of /sys/fs/cgroup to 0 bytes.  Apparently that
  application uses the directory size to determine if a tmpfs is mounted
  on /sys/fs/cgroup.

  The bind mount escape fixes are present in Al Viros for-next branch.
  and I expect them to come from there.  The bind mount escape is the
  last of the user namespace related security bugs that I am aware of"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  fs: Set the size of empty dirs to 0.
  userns,pidns: Force thread group sharing, not signal handler sharing.
  unshare: Unsharing a thread does not require unsharing a vm
  nsfs: Add a show_path method to fix mountinfo
  mnt: fs_fully_visible enforce noexec and nosuid  if !SB_I_NOEXEC
  vfs: Commit to never having exectuables on proc and sysfs.

3 files changed, 25 insertions, 18 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 0d93b4d..2b1a61c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1280,10 +1280,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	/*
 	 * If the new process will be in a different pid or user namespace
-	 * do not allow it to share a thread group or signal handlers or
-	 * parent with the forking task.
+	 * do not allow it to share a thread group with the forking task.
 	 */
-	if (clone_flags & CLONE_SIGHAND) {
+	if (clone_flags & CLONE_THREAD) {
 		if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
 		    (task_active_pid_ns(current) !=
 				current->nsproxy->pid_ns_for_children))
@@ -1872,13 +1871,21 @@ static int check_unshare_flags(unsigned long unshare_flags)
 				CLONE_NEWUSER|CLONE_NEWPID))
 		return -EINVAL;
 	/*
-	 * Not implemented, but pretend it works if there is nothing to
-	 * unshare. Note that unsharing CLONE_THREAD or CLONE_SIGHAND
-	 * needs to unshare vm.
+	 * Not implemented, but pretend it works if there is nothing
+	 * to unshare.  Note that unsharing the address space or the
+	 * signal handlers also need to unshare the signal queues (aka
+	 * CLONE_THREAD).
 	 */
 	if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) {
-		/* FIXME: get_task_mm() increments ->mm_users */
-		if (atomic_read(&current->mm->mm_users) > 1)
+		if (!thread_group_empty(current))
+			return -EINVAL;
+	}
+	if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) {
+		if (atomic_read(&current->sighand->count) > 1)
+			return -EINVAL;
+	}
+	if (unshare_flags & CLONE_VM) {
+		if (!current_is_single_threaded())
 			return -EINVAL;
 	}
 
@@ -1942,21 +1949,22 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 	int err;
 
 	/*
-	 * If unsharing a user namespace must also unshare the thread.
+	 * If unsharing a user namespace must also unshare the thread group
+	 * and unshare the filesystem root and working directories.
 	 */
 	if (unshare_flags & CLONE_NEWUSER)
 		unshare_flags |= CLONE_THREAD | CLONE_FS;
 	/*
-	 * If unsharing a thread from a thread group, must also unshare vm.
-	 */
-	if (unshare_flags & CLONE_THREAD)
-		unshare_flags |= CLONE_VM;
-	/*
 	 * If unsharing vm, must also unshare signal handlers.
 	 */
 	if (unshare_flags & CLONE_VM)
 		unshare_flags |= CLONE_SIGHAND;
 	/*
+	 * If unsharing a signal handlers, must also unshare the signal queues.
+	 */
+	if (unshare_flags & CLONE_SIGHAND)
+		unshare_flags |= CLONE_THREAD;
+	/*
 	 * If unsharing namespace, must also unshare filesystem information.
 	 */
 	if (unshare_flags & CLONE_NEWNS)
diff --git a/kernel/sys.c b/kernel/sys.c
index 259fda2..fa2f2f6 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1668,8 +1668,7 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 	 * overall picture.
 	 */
 	err = -EACCES;
-	if (!S_ISREG(inode->i_mode)	||
-	    exe.file->f_path.mnt->mnt_flags & MNT_NOEXEC)
+	if (!S_ISREG(inode->i_mode) || path_noexec(&exe.file->f_path))
 		goto exit;
 
 	err = inode_permission(inode, MAY_EXEC);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 4109f83..f65a0a0 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -976,8 +976,8 @@ static int userns_install(struct nsproxy *nsproxy, struct ns_common *ns)
 	if (user_ns == current_user_ns())
 		return -EINVAL;
 
-	/* Threaded processes may not enter a different user namespace */
-	if (atomic_read(&current->mm->mm_users) > 1)
+	/* Tasks that share a thread group must share a user namespace */
+	if (!thread_group_empty(current))
 		return -EINVAL;
 
 	if (current->fs->users != 1)