Messages in this thread |  | | Date | Tue, 10 Sep 1996 21:43:56 +0100 (BST) | From | Bryn Paul Arnold Jones <> | Subject | Re: [off-topic] Fully virtualisable CPUs |
| |
On Sun, 8 Sep 1996, Graham Mitchell wrote:
> On 7 Sep 96 at 12:26, Craig Milo Rogers wrote: > > > Hmmm... if AMD or Cyrix were to offer this as an architectural > > extension, I bet they'd sell a *lot* of chips to Linux users. Maybe > > it could be done in a way that doesn't require much kernel support > > beyond what's already in place for DOSEMU, too. > > The problem is, that this would probably break Win3, Win95, WinNT, > SCO and about every other program that relies on the virtualisation > happening in the current manner.I wouldn't hold my breath waiting for > them to do this. >
No, I don't think it would, as I see it, what we have now is that various things create exceptions, which we can trap (wether we have to trap everything, or if we can just trap some things I don't know, I don't have to).
The only problem is that fact we can't trap things that show the actual cpu status. We can then return a bogus result, like you can on other archiectures, in order to hide the fact that whatever isn't actually the only thing running, and that it's really just being helped along by something else that is in total control (or not ;).
It would make running any of WinNT, Win95, (Win3.xx), Linux, SCO, (DOS) under any other trival (well _under_ not those in ()'s), with a little work to support it (in the OS/microkernel/schedular/... running the show).
> Graham Bryn -- PGP key pass phrase forgotten, \ Overload -- core meltdown sequence again :( and I don't care ;) | initiated. / This space is intentionally left | blank, apart from this text ;-) \____________________________________
|  |