Re: Pentium DEATH and Cyrix COMA in user-mode

Andre Derrick Balsa (andrewbalsa@usa.net)
Tue, 11 Nov 1997 05:57:01 +0100


Hi,

Jason Burrell wrote:
...
> I did that last night when a friend using BSD couldn't get Alan's code to
> compile. This following code just loops indefinately on my P133 with a
> stepping of 12 regardless of what user executes it.

WRONG!!! The code below is the example *I* posted to the linux-kernel
list to test the Cyrix bug. In case you wondered, the four hex codes in
array c are the letters "Cyri".
>
> I haven't tried the "full fledged" code with the STI in it, but I'm
> guessing that doesn't make a difference considering what was posted to
> BUGTRAQ.

It would make no difference, since the code below will never lock a
Pentium.

>
> static unsigned char c[4] = {0x36, 0x78, 0x38, 0x36};
>
> main()
> {
> asm ("movl $c, %ebx\n\t"
> "again: xchgl (%ebx), %eax\n\t"
> "movl %eax, %edx\n\t"
> "jmp again\n\t");
> }
>
At least it was copied correctly... Next time please name the source.

> processor : 0
> cpu : 586
> model : Pentium 75+
> vendor_id : GenuineIntel
> stepping : 12
...
That's a genuine Intel Pentium with the genuine F0 bug. Try again with
the code posted by Richard B. Johnson.

========================================================
Andrew D. Balsa
Home Page: http://www.tux.org/~balsa
andrewbalsa@usa.net
========================================================