Date: Thu, 23 Apr 1998 10:38:37 -0500 From: Jonathan Lemon <jlemon@americantv.com> To: "David E. Cross" <dec@phoenix.its.rpi.edu> Cc: Alfred Perlstein <perlsta@fang.cs.sunyit.edu>, freebsd-hackers@FreeBSD.ORG Subject: Re: Protected mode instructions which reduce to noop. Message-ID: <19980423103837.32719@right.PCS> In-Reply-To: <Pine.BSF.3.96.980423112432.9592C-100000@phoenix.its.rpi.edu>; from David E. Cross on Apr 04, 1998 at 11:25:05AM -0400 References: <Pine.BSF.3.95.980423101923.15642A-100000@fang.cs.sunyit.edu> <Pine.BSF.3.96.980423112432.9592C-100000@phoenix.its.rpi.edu>
next in thread | previous in thread | raw e-mail | index | archive | help
On Apr 04, 1998 at 11:25:05AM -0400, David E. Cross wrote: > On Thu, 23 Apr 1998, Alfred Perlstein wrote: > > > i'm seriously doubtful of this. i think intels throw instr fault > > exceptions when stuff like that is executed. > > > > -Alfred > > > > On Thu, 23 Apr 1998, David E. Cross wrote: > > > > > Awhile ago it was discussed about implimenting a VM type architecture on > > > intel, and it was agreed that this would be very difficult because intel > > > had decided that instead of throwing an illegal instruction exception for > > > protected mode instructions that were not run as supervisor, it would > > > simply reduce the instriction to NOOP. What are these instructions. > > > > > Heh, I just read my own post... it was not *all* protected mode > instructions, but *some* of them. AFAIK, all privileged instructions, when executed in a non-supervisor context, generate an exception of some sort. This applies to the sti, cli, popfl, I/O family of instructions, as well as those insns which diddle with the control registers. What VM type architecture were you referring to? -- Jonathan To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19980423103837.32719>