From: Hans-Bernhard Broeker <broeker AT physik DOT rwth-aachen DOT de>
Newsgroups: comp.os.msdos.djgpp
Subject: Re: CWSDPMR0: system crash on INVD
Date: 29 Mar 2001 12:31:41 GMT
Organization: Aachen University of Technology (RWTH)
Lines: 22
Message-ID: <99v9vd$nfu$1@nets3.rz.RWTH-Aachen.DE>
References: <99t5g6$m5r$1 AT murdoch DOT acc DOT Virginia DOT EDU> <99t7j4$7ce$1 AT node17 DOT cwnet DOT frontiernet DOT net> <99t91t$rgg$1 AT murdoch DOT acc DOT Virginia DOT EDU> <99ta4e$r99$1 AT nets3 DOT rz DOT RWTH-Aachen DOT DE> <99to44$jj9$1 AT murdoch DOT acc DOT Virginia DOT EDU>
NNTP-Posting-Host: acp3bf.physik.rwth-aachen.de
X-Trace: nets3.rz.RWTH-Aachen.DE 985869101 24062 137.226.32.75 (29 Mar 2001 12:31:41 GMT)
X-Complaints-To: abuse AT rwth-aachen DOT de
NNTP-Posting-Date: 29 Mar 2001 12:31:41 GMT
Originator: broeker@
To: djgpp AT delorie DOT com
DJ-Gateway: from newsgroup comp.os.msdos.djgpp
Reply-To: djgpp AT delorie DOT com

Clark L. Coleman <clc5q AT cobra DOT cs DOT virginia DOT edu> wrote:
[...]
> If that were the case, and I were running in Ring 3, then how would I
> be successfully executing every other Ring 0 instruction that I have
> tried besides INVD ? 

Well, you didn't really clearly state that the other instructuion you
mentioned, WBINVD, is also a Ring 0 instruction, and I know neither of
them offhand.

This still leaves one possibility: incorrect assembly of this
instruction, either because you mis-guessed the AT&T mnemonic for it,
or because gas miscompiled it --- for a supposedly rarely used
instruction like this, that's always a possibility.

So: could you see what happens if you insert this instruction by hex
code, rather than by mnemonic? And/or verify the objdump of the
relevant function against an Intel Opcode manual?

-- 
Hans-Bernhard Broeker (broeker AT physik DOT rwth-aachen DOT de)
Even if all the snow were burnt, ashes would remain.