Re: [net-next PATCH] csum: Update csum_block_add to use rotate instead of byteswap

[Joe Perches <joe@perches.com>]

On Tue, 2016-03-08 at 14:42 -0800, Alexander Duyck wrote:
> The code for csum_block_add was doing a funky byteswap to swap the even and
> odd bytes of the checksum if the offset was odd.  Instead of doing this we
> can save ourselves some trouble and just shift by 8 as this should have the
> same effect in terms of the final checksum value and only requires one
> instruction.

3 instructions?

> In addition we can update csum_block_sub to just use csum_block_add with a
> inverse value for csum2.  This way we follow the same code path as
> csum_block_add without having to duplicate it.
> 
> Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
> ---
>  include/net/checksum.h |   11 +++++------
>  1 file changed, 5 insertions(+), 6 deletions(-)
> 
> diff --git a/include/net/checksum.h b/include/net/checksum.h
> index 10a16b5bd1c7..f9fac66c0e66 100644
> --- a/include/net/checksum.h
> +++ b/include/net/checksum.h
> @@ -88,8 +88,10 @@ static inline __wsum
>  csum_block_add(__wsum csum, __wsum csum2, int offset)
>  {
>  	u32 sum = (__force u32)csum2;
> -	if (offset&1)
> -		sum = ((sum&0xFF00FF)<<8)+((sum>>8)&0xFF00FF);
> +
> +	if (offset & 1)
> +		sum = (sum << 24) + (sum >> 8);

Maybe use ror32(sum, 8);

or maybe something like:

{
	u32 sum;

	/* rotated csum2 of odd offset will be the right checksum */
	if (offset & 1)
		sum = ror32((__force u32)csum2, 8);
	else
		sum = (__force u32)csum2;