systematic panic on an SMP machine for 5.1-Release

[Kevin Oberman]

> From: Thierry Herbelot <thierry at herbelot.com>
> Date: Tue, 8 Jul 2003 21:47:23 +0200
> Sender: owner-freebsd-current at freebsd.org
> 
> PS : is this an indication of bug in the p-III or in the chipset ?
> (ISTR these options could be used to get around unnamed errata of
> the p-IV)

Terry has never been specific (due to non-disclosure), but adding
options DISABLE_PSE to the kernel of my P4 system results in a solid
crash when the apm driver probes. (This could be an apm(4) problem, as
well.)

I wish I knew just when this option might be needed as I run on a wide
variety of platforms including P2, K6-3, P3, and P4 with an Athlon
coming soon. I'd just as soon only use this option where it's really
required. I'm twice shy about it after adding it to the P4 and
watching it crash.
-- 
R. Kevin Oberman, Network Engineer
Energy Sciences Network (ESnet)
Ernest O. Lawrence Berkeley National Laboratory (Berkeley Lab)
E-mail: oberman at es.net			Phone: +1 510 486-8634