From owner-freebsd-hackers  Fri Nov  7 13:04:02 1997
Return-Path: <owner-freebsd-hackers>
Received: (from root@localhost)
          by hub.freebsd.org (8.8.7/8.8.7) id NAA23412
          for hackers-outgoing; Fri, 7 Nov 1997 13:04:02 -0800 (PST)
          (envelope-from owner-freebsd-hackers)
Received: from lucifer.guardian.no (gate.guardian.no [195.1.254.2])
          by hub.freebsd.org (8.8.7/8.8.7) with SMTP id NAA23373
          for <hackers@FreeBSD.ORG>; Fri, 7 Nov 1997 13:03:56 -0800 (PST)
          (envelope-from finnag@guardian.no)
Received: (qmail 24162 invoked by uid 21574); 7 Nov 1997 21:03:48 -0000
Date: Fri, 7 Nov 1997 22:03:48 +0100 (MET)
From: Finn Arne Gangstad <finnag@guardian.no>
To: hackers@FreeBSD.ORG
Subject: Re: Newest Pentium bug (fatal)
In-Reply-To: <3463605C.41C67EA6@whistle.com>
Message-ID: <Pine.LNX.3.95.971107214918.23770A-100000@lucifer.guardian.no>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: owner-freebsd-hackers@FreeBSD.ORG
X-Loop: FreeBSD.org
Precedence: bulk



On Fri, 7 Nov 1997, Julian Elischer wrote:

> On a "genuine Intel" pentium (not pentium pro)
> execution of the following sequence, 0xf0 0x0f 0xc7 0xc8
> 
> will stop the processor. This is doable from user mode and in 
> 16bitmode, or in fact any mode.
> 
> try the following c program.
> 
> unsigned char x[] = { 0xfo, 0x0f, 0xc7, 0xc8 };
> main ()
> {
>   void (*f)(void) = x;
>   f();
> }

EEk - don't try this on a compaq armada 1510 - no hard reset button (that
i can find) and power button is also soft power - so now I have to wait
for the battery to go empty on me..

objdump --disassemble-all --show-raw-insn  pentiumcrash.o
Disassembly of section .data:
00000000 <x> f0 0f c7 c8  lock cmpxchg8b %eax

Bleh - illegal address mode but why oh why does it have to hang :(

- Finn Arne