I think the next step should be to map in one page of kernel code in a
user-readable location, and just do it there.
It's not just 386 vs later due to cmpxchg. It's also the simple issue of
UP vs SMP - a UP system still wants to do locking, but it doesn't need the
lock prefix. And that lock prefix makes a _huge_ difference
performance-wise.
So my suggestion is: ignore i386 for now (no _relevant_ SMP boxes exist
anyway), and plan on solving the problem with a separate library page
before 2.6.x gets released.
Linus
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/