Re: [PATCH] NMI trap revised (was Re: NMI errors in 2.0.30??)

Matthias Urlichs (
19 May 1997 01:48:17 +0200 writes:
> > After studying lots of specs and testing it on several motherboards, it
> > seems that those bits are implemented almost everywhere and hard-wired to zeroes
> > on the remaining MB's. We probably should honor them and report the reason
> > to the user if we find any.
> So if at boot we check writablity of bit 2 and 3 we can know if this
> mechanism is implemented or not ?
It seems that if you write a 1 into the partiy-enable bit and you don't
have parity, you get an instant NMI, which you can't handle because your
NMI handler is in RAM => instant death.

Whether the memory has parity or not needs to be tested from BIOS EPROM.

Food that tastes the best has the highest number of calories.
                                        -- Rozanne Weissman
Matthias Urlichs         \  noris network GmbH  /  Xlink-POP Nürnberg 
Schleiermacherstraße 12   \   Linux+Internet   /   EMail:
90491 Nürnberg (Germany)   \    Consulting+Programming+Networking+etc'ing
   PGP: 1024/4F578875   1B 89 E2 1C 43 EA 80 44  15 D2 29 CF C6 C7 E0 DE
       Click <A HREF="">here</A>.    42