Re: [PATCH 4/8] i386: bitops: Kill volatile-casting of memory addresses

[Nick Piggin]

Linus Torvalds wrote:
> On Tue, 24 Jul 2007, Benjamin Herrenschmidt wrote:

> > Besides, as Nick pointed out, it prevents some valid optimizations.
>
>
> No it doesn't. Not the ones on the functions that just do an inline asm.
>
> The only valid optimization it might break is for "constant_test_bit()", 
> which isn't even using inline asm.

The constant case is probably most used (at least for page flags), and
is most important for me. constant_test_bit may not be using inline asm,
but the volatile pointer target means that it reloads the value and can't
do much optimisation over it.

BTW. once volatile goes away, i386 really should start using the C
versions of __set_bit and __clear_bit as well IMO. (at least for the
constant bitnr case), so gcc can potentially optimise better.

--
SUSE Labs, Novell Inc.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/