Csum

#include <stdio.h>
#include <stdint.h>

static inline unsigned short csum_fold(unsigned int sum)
{
    asm("  addl %1,%0\n"
        "  adcl $0xffff,%0"
        : "=r" (sum)
        : "r" ((unsigned int)sum << 16),
          "0" ((unsigned int)sum & 0xffff0000));
    return (unsigned short)(~(unsigned int)sum >> 16);
}

static inline unsigned add32_with_carry(unsigned a, unsigned b)
{
    asm("addl %2,%0\n\t"
        "adcl $0,%0"
        : "=r" (a)
        : "0" (a), "rm" (b));
    return a;
}

static inline unsigned short from32to16(unsigned a)
{
    unsigned short b = a >> 16;
    asm("addw %w2,%w0\n\t"
        "adcw $0,%w0\n"
        : "=r" (b)
        : "0" (b), "r" (a));
    return b;
}

/*
 * Do a 64-bit checksum on an arbitrary memory area.
 * Returns a 32bit checksum.
 *
 * This isn't as time critical as it used to be because many NICs
 * do hardware checksumming these days.
 *
 * Things tried and found to not make it faster:
 * Manual Prefetching
 * Unrolling to an 128 bytes inner loop.
 * Using interleaving with more registers to break the carry chains.
 */
static unsigned do_csum(const unsigned char *buff, unsigned len)
{
    unsigned odd, count;
    unsigned long result = 0;

    if ((len == 0))
        return result;
    odd = 1 & (unsigned long) buff;
    if ((odd)) {
        result = *buff << 8;
        len--;
        buff++;
    }
    count = len >> 1;       /* nr of 16-bit words.. */
    if (count) {
        if (2 & (unsigned long) buff) {
            result += *(unsigned short *)buff;
            count--;
            len -= 2;
            buff += 2;
        }
        count >>= 1;        /* nr of 32-bit words.. */
        if (count) {
            unsigned long zero;
            unsigned count64;
            if (4 & (unsigned long) buff) {
                result += *(unsigned int *) buff;
                count--;
                len -= 4;
                buff += 4;
            }
            count >>= 1;    /* nr of 64-bit words.. */

            /* main loop using 64byte blocks */
            zero = 0;
            count64 = count >> 3;
            while (count64) {
                asm("addq 0*8(%[src]),%[res]\n\t"
                    "adcq 1*8(%[src]),%[res]\n\t"
                    "adcq 2*8(%[src]),%[res]\n\t"
                    "adcq 3*8(%[src]),%[res]\n\t"
                    "adcq 4*8(%[src]),%[res]\n\t"
                    "adcq 5*8(%[src]),%[res]\n\t"
                    "adcq 6*8(%[src]),%[res]\n\t"
                    "adcq 7*8(%[src]),%[res]\n\t"
                    "adcq %[zero],%[res]"
                    : [res] "=r" (result)
                    : [src] "r" (buff), [zero] "r" (zero),
                    "[res]" (result));
                buff += 64;
                count64--;
            }

            /* last up to 7 8byte blocks */
            count %= 8;
            while (count) {
                asm("addq %1,%0\n\t"
                    "adcq %2,%0\n"
                        : "=r" (result)
                    : "m" (*(unsigned long *)buff),
                    "r" (zero),  "0" (result));
                --count;
                    buff += 8;
            }
            result = add32_with_carry(result>>32,
                          result&0xffffffff);

            if (len & 4) {
                result += *(unsigned int *) buff;
                buff += 4;
            }
        }
        if (len & 2) {
            result += *(unsigned short *) buff;
            buff += 2;
        }
    }
    if (len & 1)
        result += *buff;
    result = add32_with_carry(result>>32, result & 0xffffffff);
    if ((odd)) {
        result = from32to16(result);
        result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
    }
    return result;
}

/*
 * computes the checksum of a memory block at buff, length len,
 * and adds in "sum" (32-bit)
 *
 * returns a 32-bit number suitable for feeding into itself
 * or csum_tcpudp_magic
 *
 * this function must be called with even lengths, except
 * for the last fragment, which may be odd
 *
 * it's best to have buff aligned on a 64-bit boundary
 */
unsigned int csum_partial(const void *buff, int len, unsigned int sum)
{
    return (unsigned int)add32_with_carry(do_csum(buff, len), sum);
}

uint16_t
hev_checksum_compute (uint16_t *data, size_t size)
{
    register uint32_t sum = 0;
    unsigned short oddbyte;

    while (1 < size) {
        sum += *data++;
        size -= 2;
    }
    if(1 == size) {
        oddbyte = 0;
        *((uint8_t *) &oddbyte) = *(uint8_t *) data;
        sum += oddbyte;
    }

    sum = (sum >> 16) + (sum & 0xffff);
    sum += (sum >> 16);

    return (uint16_t) ~sum;
}

int
main (int argc, char *argv[])
{
    unsigned char buff[1400];

    unsigned int sum = 0;

    printf ("%x\n", hev_checksum_compute ((uint16_t *) buff, 1400));

    sum = csum_partial (buff, 4, sum);
    sum = csum_partial (buff + 4 , 1400 - 4, sum);
    printf ("%x\n", csum_fold (sum));

    sum = csum_partial (buff, 3, sum);
    sum = csum_partial (buff + 3 , 1400 - 3, sum);
    printf ("%x\n", csum_fold (sum));

    return 0;
}