whither patch that fixed K6 32M bug on 2.1.56?

Hi. I just bought a computer (cheap!) that appears to have a K6 processor with the bug this website is dedicated to:

http://membres.lycos.fr/poulot/k6bug.html

The problem appears to be a hardware glitch in the K6 where it gets overly paranoid about self-modifying code. There is a patch at the above website that changes the 2.1.56 kernel thusly:

Description : If page A is a code page, and A+32MB is a data page, then the bug can occur. If the memory allocation is modified to prevent these collisions, the failure rate should decrease dramatically.

Has anyone done anything with this patch since 2.1.56? I see some stuff in 2.4.20 that appears to test for the bug and print a warning that the system may be unstable on detection.

--Ed L Cashin     PGP public key: http://noserose.net/e/pgp/