Re: Cyrix 6x86MX and Centaur C6 CPUs in 2.1.102

Linus Torvalds (
Tue, 19 May 1998 09:18:04 -0700 (PDT)

On Tue, 19 May 1998, David Woodhouse wrote:
> > then that part I have no argument with. HOWEVER, if so, you'd better
> > make it a new capability or something, because I don't want to have
> > "real" kernel code having to care.
> How about an extra bug field in the struct cpuinfo_x86?
> If the TSC instructions are present, fill in the relevant bit in the
> capability field, but if it's one of the broken chips, we set the bug flag too.

Yes. This sounds like a buug idea. Right now we have the (euphemism alert)
"bad capability" scattered around in multiple places, it certainly makes
sense to me to make it the same kind of bitmap as the "good capabilities".

Another thing that would be good would be to have some names for the
capabilities we currently use: using "x & 16" and just magically knowing
that "16" is the bit value for X86_CAP_TSC is kind of obscure.

Anybody want to do something like this?


To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to