gcc miscompiles csum_tcpudp_magic() on ARMv5

[linux@arm.linux.org.uk (Russell King - ARM Linux)]

On Thu, Dec 12, 2013 at 06:11:08PM +0100, Willy Tarreau wrote:
> Another thing that can be done to improve the folding of the 16-bit
> checksum is to swap the values to be added, sum them and only keep
> the high half integer which already contains the carry. At least on
> x86 I save some cycles doing this :
> 
>               31:24  23:16  15:8  7:0
>      sum32 =    D      C      B    A
> 
>      To fold this into 16-bit at a time, I just do this :
> 
>                    31:24     23:16          15:8  7:0
>      sum32           D         C              B    A
>   +  sum32swapped    B         A              D    C
>   =                 A+B  C+A+carry(B+D/C+A)  B+D  C+A
> 
> so just take the upper result and you get the final 16-bit word at
> once.
> 
> In C it does :
> 
>        fold16 = (((sum32 >> 16) | (sum32 << 16)) + sum32) >> 16
> 
> When the CPU has a rotate instruction, it's fast :-)

Indeed - and if your CPU can do the rotate and add at the same time,
it's just a singe instruction, and it ends up looking remarkably
similar to this:

static inline __sum16 csum_fold(__wsum sum)
{
        __asm__(
        "add    %0, %1, %1, ror #16     @ csum_fold"
        : "=r" (sum)
        : "r" (sum)
        : "cc");
        return (__force __sum16)(~(__force u32)sum >> 16);
}