Oh, ye Gods. I didn't think the asm patch would _really_ make any
difference, but I was obviusly wrong. That's good news to some degree,
because it does mean that we may have a handle on the problem, and that my
basic suspicion for why it happened was on the right track.
However, the asm patch was only meant to be an aid in figuring out whether
this was really the basic problem: I can't use it in any real kernel if
for no other reason that it obviously works only on x86. I'll have to come
up with something better that is portable.
Anyway, thanks for the feedback, and it is interesting that this actually
does make a difference. I think I have an idea on how to possibly fix
this,
Linus
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu