From owner-freebsd-hackers Fri Nov 1 13:52:20 1996 Return-Path: owner-hackers Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA27018 for hackers-outgoing; Fri, 1 Nov 1996 13:52:20 -0800 (PST) Received: from irz301.inf.tu-dresden.de (irz301.inf.tu-dresden.de [141.76.1.11]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id NAA26965 for ; Fri, 1 Nov 1996 13:52:08 -0800 (PST) Received: from sax.sax.de (sax.sax.de [193.175.26.33]) by irz301.inf.tu-dresden.de (8.6.12/8.6.12-s1) with ESMTP id WAA23474 for ; Fri, 1 Nov 1996 22:51:58 +0100 Received: (from uucp@localhost) by sax.sax.de (8.6.12/8.6.12-s1) with UUCP id WAA03019 for freebsd-hackers@freebsd.org; Fri, 1 Nov 1996 22:51:58 +0100 Received: (from j@localhost) by uriah.heep.sax.de (8.8.2/8.6.9) id WAA23428 for freebsd-hackers@freebsd.org; Fri, 1 Nov 1996 22:37:39 +0100 (MET) From: J Wunsch Message-Id: <199611012137.WAA23428@uriah.heep.sax.de> Subject: Re: VM answer requested To: freebsd-hackers@freebsd.org (FreeBSD hackers) Date: Fri, 1 Nov 1996 22:37:39 +0100 (MET) Reply-To: joerg_wunsch@uriah.heep.sax.de (Joerg Wunsch) In-Reply-To: <199611011842.LAA28151@phaeton.artisoft.com> from Terry Lambert at "Nov 1, 96 11:42:21 am" X-Phone: +49-351-2012 669 X-PGP-Fingerprint: DC 47 E6 E4 FF A6 E9 8F 93 21 E0 7D F9 12 D6 4E X-Mailer: ELM [version 2.4ME+ PL17 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hackers@freebsd.org X-Loop: FreeBSD.org Precedence: bulk As Terry Lambert wrote: > What about the aligned access bit in recent Intel processors? > > I'd like to be able to turn on the bit so that I get a fault (and it > kills the offending process) when an unaligned access occurs. Adding support for this should be fairly simple. I wonder why you didn't simply implement it yourself and faced us with a comparision of the results. :-) If i got it right, it requires a little magic inside machdep.c (depending on the detected CPU type), and another case label in trap.c. However, i don't think you can _force_ the AC flag, even not for a user program. Modifying the flag is IMHO not a privileged instruction, hence any user program can revert it. > I'd also like to get kernel faults if this happens in the kernel According to my 486 docs, this is impossible. The AC flag is only honored in `ring 3' mode. -- cheers, J"org joerg_wunsch@uriah.heep.sax.de -- http://www.sax.de/~joerg/ -- NIC: JW11-RIPE Never trust an operating system you don't have sources for. ;-)