Currently, we set rlim(RLIMIT_NOFILE) unlimited
and service_fd_rlim_cur to place service fds.
This leads to a signify problem: every task uses
the biggest possible files_struct in kernel, and
it consumes excess memory after restore
in comparation to dump. In some situations this
may end in restore fail as there is no enough
memory in memory cgroup of on node.

The patch fixes the problem by introducing
task-measured service_fd_base. It's calculated
in dependence of max used file fd and is placed
near the right border of kernel-allocated memory
hunk for task's fds (see alloc_fdtable() for
details). This reduces kernel-allocated files_struct
to 512 fds for the most process in standard linux
system (I've analysed the processes in my work system).

Also, since the "standard processes" will have the same
service_fd_base, clone_service_fd() won't have to
actualy dup() their service fds for them like we
have at the moment. This is the one of reasons why
we still keep service fds as a range of fds,
and do not try to use unused holes in task fds.
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>

v2: Add a handle for very big fd numbers near service_fd_rlim_cur.
v3: Fix excess accounting for nr equal to pow 2 minus 1.
Signed-off-by: Andrei Vagin <avagin@virtuozzo.com>