Subject: Re: Considering port to new processor
To: None <firstname.lastname@example.org, email@example.com>
From: Thor Lancelot Simon <firstname.lastname@example.org>
Date: 03/30/2001 19:08:39
On Fri, Mar 30, 2001 at 03:34:17PM -0800, Erik E. Fair wrote:
> There was a time when UNIX did not page - it swapped. Processes were
> either all the way in RAM, or not there at all - no "pages" at all.
> On that sort of system, there is no need to support restartable
> instructions for page faults.
Let me try this again: if you're building an absolute-bare-minimum
MMU, I contend that you need a way to cause a trap or fault on access
to an arbitrary location -- whether the result of that trap or fault
is going to be to page or swap, I care not -- and a way to restart
what you were doing at the same instruction after you service the
trap or fault.
You don't necessarily need page protections. You *do* need the ability
to protect some region of memory specified *somehow* in order to switch
contexts and to prevent processes from scribbling on each others' "private"
view of the system memory.