On Fri, Oct 27, 2023 at 03:43:51PM -0700, Charlie Jenkins wrote: > /* > * computes the checksum of a memory block at buff, length len, > * and adds in "sum" (32-bit) > @@ -31,9 +33,7 @@ extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl); > static inline __sum16 csum_fold(__wsum csum) > { > u32 sum = (__force u32)csum; > - sum = (sum & 0xffff) + (sum >> 16); > - sum = (sum & 0xffff) + (sum >> 16); > - return (__force __sum16)~sum; > + return (__force __sum16)((~sum - ror32(sum, 16)) >> 16); > } Will (~(sum + ror32(sum, 16))>>16 produce worse code than that? Because at least with recent gcc this will generate the exact thing you get from arm inline asm...