There is a small race between exitings tasks and cgroup freezer:
it can report a pid of exiting process which we will consider
as a zombie and refuse to checkpoint. Lets do a trick instead:
if we meets such task just wait a bit and repeate a freezing.

v3: Use EAGAIN instead of EPERM since EPERM collide
    with general -1 error code.

travis-ci: success for freeze -- Wait for exiting tasks to complete (rev3)
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>