Improve __csum_partial by interleaving loads and adds.

On a 8xx, it brings neither improvement nor degradation.
On a 83xx, it brings a 25% improvement.
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: NSegher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>