RFC: Simplfying hyperthreading distinctions

[Slawa Olhovchenkov]

On Sun, Mar 22, 2015 at 10:44:51AM -0700, Adrian Chadd wrote:

> ... or maybe the scheduler shouldn't be the primary source of the CPU
> topology information, but instead should be a consumer. :)

And may be good think unified API (userland also) for get full
topology (with PCIe, USB bus, USB HUB and other devices and IRQ
handlers).

Currently for detect IRQ handlers of NIC I am need to parse
hw.intrnames with hacks for maping 't5nex0:0.1' to cxl0 and
'ix1:que 2' to ix1.