Re: partially working SMP again

[Martin Husemann <martin%duskware.de@localhost>]

On Fri, May 29, 2009 at 10:08:15PM +0100, David Laight wrote:
> Isn't that backwards?
> I thought cache conguency was a problem when the same physical
> memory was mapped to different virtual addresses.

We are doing both: CPUINFO_VA is a fixed VA where we map a different
physical page per cpu. Each of these has another (global) VA, so that
we can touch it from other CPUs, i.e. every cpu can iterate over all the
cpu_infos.

Martin