On Sat, Jul 01, 2000 at 09:55:03AM +0200, Poul-Henning Kamp wrote:
> In message <[EMAIL PROTECTED]>, Mike Smith writes:
> >> In message <[EMAIL PROTECTED]>, KATO Takenori writ
> >> es:
> >> >The invlpg instruction causes strange signal 11 problem on some
> >> >PentiumPro box. This problem seems to hapen when (1) mother board is
> >> >very old and (2) BIOS update is not available and (3) cpuid < 0x619.
> >> >
> >> >Following patch automatically disables invlpg when PentiumPro with
> >> >cpuid < 0x619 is found.
> >> >
> >> >Please comment to this patch.
> >>
> >> I'm against this patch. This is so specific and marginal to a
> >> out-of-spec hardware configuration, that it should not be put in
> >> the FreeBSD tree.
> >
> >I'd disagree with that. This is just the same as the 0xf00f workaround,
> >saving only in degree. If it's something that can be done as eg. a KLD
> >we might want to do that instead, or through some other mechanism for
> >handling these sort of CPU quirks.
>
> Please Mike, just because you see my name you shouldn't take a contrary
> positition until you have actually looked into matters.
>
> Look at the first paragraph: This is for Pentium Pro cpus running
> in motherboards where the BIOS does not contain the needed microcode
> updates.
>
> The patch disables invlpg on all cpuid's < 0x619, despite the fact
> that they work just fine if your motherboards BIOS have the right
> microcode update for your cpu stepping.
>
> This hack should be maintained by the person who need it, it should
> not be lobotomizing FreeBSD in general.
Maybe make it conditional via an option in the kernel config file?
Off by default of course. Looking at LINT/NOTES I see very obscure things
for Cyrix and Bluelightning CPUs already.
--
Wilko Bulte http://www.freebsd.org "Do, or do not. There is no try"
[EMAIL PROTECTED] http://www.nlfug.nl Yoda - The Empire Strikes Back
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message