Andrew Kieschnick wrote:
> On Mon, 10 Nov 1997, Alan Cox wrote:
>
> > > The pentium bug is caused by the chip executing an invalid opcode - its
> > > really a very different bug from the cyrix bug.... I doubt
> > > enabling/disabling anything is going to help with the pentium bug.
> >
> > They are very similar it appears. One is "lock cmpxchg8" which causes a double
> > lock cycle on the bus (I believe its to the bus), the other is a dual issue
> > of an implicitly locked operation (again dual lock).
>
> Hmm. Indeed, thats pretty similar... hadn't thought about that.
>
> I still say that they're also significantly different in that the pentium
> is executing what should be an invalid instruction, and the cyrix is
> executing valid instructions stupidly.
>
That's completely besides the point.
The point is that we have user space valid code that will send both
processors to limbo. That makes both processors bad choices for
multiuser OS's like Linux. At least for the Cyrix 6x86, I seem to have
found a simple workaround.
There are some differences: the Pentium stops dead (the processor is
stopped, as indicated by its low temperature), the 6x86 will loop
infinitely.
In both cases there may be an incorrect handling of locked bus cycles by
the instruction decoding logic.
Regards,
========================================================
Andrew D. Balsa
Home Page: http://www.tux.org/~balsa
andrewbalsa@usa.net
========================================================