On Tue, May 22, 2018 at 08:57:01AM +0200, Christophe Leroy wrote:
> The generic csum_ipv6_magic() generates a pretty bad result

<snip>

Please try with a more recent compiler, what you used is pretty ancient.
It's not like recent compilers do great on this either, but it's not
*that* bad anymore ;-)

> --- a/arch/powerpc/lib/checksum_32.S
> +++ b/arch/powerpc/lib/checksum_32.S
> @@ -293,3 +293,36 @@ dst_error:
>       EX_TABLE(51b, dst_error);
>  
>  EXPORT_SYMBOL(csum_partial_copy_generic)
> +
> +/*
> + * static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
> + *                                 const struct in6_addr *daddr,
> + *                                 __u32 len, __u8 proto, __wsum sum)
> + */
> +
> +_GLOBAL(csum_ipv6_magic)
> +     lwz     r8, 0(r3)
> +     lwz     r9, 4(r3)
> +     lwz     r10, 8(r3)
> +     lwz     r11, 12(r3)
> +     addc    r0, r5, r6
> +     adde    r0, r0, r7
> +     adde    r0, r0, r8
> +     adde    r0, r0, r9
> +     adde    r0, r0, r10
> +     adde    r0, r0, r11
> +     lwz     r8, 0(r4)
> +     lwz     r9, 4(r4)
> +     lwz     r10, 8(r4)
> +     lwz     r11, 12(r4)
> +     adde    r0, r0, r8
> +     adde    r0, r0, r9
> +     adde    r0, r0, r10
> +     adde    r0, r0, r11
> +     addze   r0, r0
> +     rotlwi  r3, r0, 16
> +     add     r3, r0, r3
> +     not     r3, r3
> +     rlwinm  r3, r3, 16, 16, 31
> +     blr
> +EXPORT_SYMBOL(csum_ipv6_magic)

Clustering the loads and carry insns together is pretty much the worst you
can do on most 32-bit CPUs.


Segher

Reply via email to