On Wed, 18 Apr 2001, Chris Gilbert wrote:

> Note this is mailer code, so may or may not actually work.  Note that you do
> need to have a direct virtual to physical mapping for the code that enables
> the mmu, otherwise the mmu comes on and the PC is pointing at nothing, and
> would probably abort in some way.

Umm... shouldn't do. You have from the time you enable the MMU to the time
that the pipeline empties to branch to the new address of the code.

Worked for me when I wrote a bootloader and the beginnings of a kernel on
the StrongARM, anyway.

-- 
Gillette - the best a man can forget