Date: Tue, 20 May 1997 15:49:43 -0600 (MDT) From: sclawson@bottles.cs.utah.edu (steve clawson) To: thorpej@nas.nasa.gov Cc: dg@root.com, yokota@zodiac.mech.utsunomiya-u.ac.jp, freebsd-hackers@FreeBSD.ORG, freebsd-bugs@FreeBSD.ORG Subject: Re: trap type 29 on P6 Message-ID: <199705202149.PAA02983@bottles.cs.utah.edu> In-Reply-To: <199705200311.UAA19076@lestat.nas.nasa.gov> from "Jason Thorpe" at May 19, 97 08:11:37 pm
next in thread | previous in thread | raw e-mail | index | archive | help
Jason Thorpe uttered:
> There's not much you can do about it, really... you can't really
> stop the condition from occurring, short of publicly flogging
> purveyors of broken hardware (and it's not clear that'll help
> anyhow). It was fixed in NetBSD-current some time ago by catching
> and ignoring this particular reserved trap vector.
In this case it's both because of a broken motherboard and a
broken chip. =) Intel finally put it's errata list on the net
(ftp://download.intel.com/design/{pentium,pro}/update/) and this
particular problem shows up as errata 5AP: Virtual Wire Mode Through
Local APIC May Cause Int 15. This is supposedly fixed in the very
latest stepping of the Pro.
Intel's workaround is to have to BIOS disable the local APIC in
uniprocessor machines and in MP's that don't use an I/O APIC.
Probably easier to just ignore the trap though. =)
steve
--
// stephen clawson sclawson@cs.utah.edu
// university of utah
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199705202149.PAA02983>