rootfs: switch ms_private remount of oldroot to ms_slave

Using MS_PRIVATE meant that there was a race between the mount(2) and
the umount2(2) calls where runc inadvertently has a live reference to a
mountpoint that existed on the host (which the host cannot kill
implicitly through an unmount and peer sharing).

In particular, this means that if we have a devicemapper mountpoint and
the host is trying to delete the underlying device, the delete will fail
because it is "in use" during the race. While the race is _very_ small
(and libdm actually retries to avoid these sorts of cases) this appears
to manifest in various cases.

Signed-off-by: Aleksa Sarai <asarai@suse.de>

libcontainer/rootfs_linux.go

@@ -668,9 +668,12 @@ func pivotRoot(rootfs string) error {
 		return err
 	}
 
-	// Make oldroot rprivate to make sure our unmounts don't propagate to the
-	// host (and thus bork the machine).
-	if err := unix.Mount("", ".", "", unix.MS_PRIVATE|unix.MS_REC, ""); err != nil {
+	// Make oldroot rslave to make sure our unmounts don't propagate to the
+	// host (and thus bork the machine). We don't use rprivate because this is
+	// known to cause issues due to races where we still have a reference to a
+	// mount while a process in the host namespace are trying to operate on
+	// something they think has no mounts (devicemapper in particular).
+	if err := unix.Mount("", ".", "", unix.MS_SLAVE|unix.MS_REC, ""); err != nil {
 		return err
 	}
 	// Preform the unmount. MNT_DETACH allows us to unmount /proc/self/cwd.