// Example zero-copy network transmission with vmsplice
// From http://codemonkeytips.blogspot.com/2011/07/zero-copy-network-transmission-with.html

#define _GNU_SOURCE

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <unistd.h>

#include <errno.h>
#include <fcntl.h>
#include <netinet/if_ether.h>
#include <netinet/in.h>
#include <sys/socket.h>
#include <sys/types.h>
#include <sys/uio.h>

/// source IP address in host byte order
#define CONF_TXHOST_HBO ((127 << 24)) + 1

static int tx_splicefd[2], tx_nullfd, tx_rawsockfd;

/// open a RAW or UDP socket for retransmission
//  @return 0 on success, -1 on failure
static int
do_init(void)
{
  struct sockaddr_in saddr;

  // open tx socket
  tx_rawsockfd = socket(PF_INET, SOCK_RAW, IPPROTO_RAW);
  if (tx_rawsockfd < 0) {
    perror("socket() tx");
    return -1;
  }

  // configure raw socket
  memset(&saddr, 0, sizeof(saddr));
  saddr.sin_family      = AF_INET;
  saddr.sin_port        = htons(ETH_P_IP);
  saddr.sin_addr.s_addr = htonl(CONF_TXHOST_HBO);

  if (connect(tx_rawsockfd, &saddr, sizeof(saddr))) {
    perror("connect() tx");
    return -1;
  }

  // when splicing, have to first send to kernel pipe, then to tx socket.
  // also, unwanted data must be flushed to /dev/null
  // create pipe to splice to kernel
  if (pipe(tx_splicefd)) {
    perror("pipe() tx");
    return -1;
  }

  // open /dev/null for splicing trash
  tx_nullfd = open("/dev/null", O_WRONLY);
  if (tx_nullfd < 0) {
    perror("open() /dev/null");
    return -1;
  }

  return 0;
}

static int
do_exit(void)
{
  int ret = 0;

  if (close(tx_nullfd)) {
    perror("close /dev/null");
    ret = 1;
  }
  if (close(tx_rawsockfd)) {
    perror("close tx");
    ret = 1;
  }
  if (close(tx_splicefd[1])) {
    perror("close pipe[1]");
    ret = 1;
  }
  if (close(tx_splicefd[0])) {
    perror("close pipe[0]");
    ret = 1;
  }

  return 0;
}

/// transmit a packet using splice
static int
do_transmit(void *page, int pkt_offset, int pktlen)
{
  struct iovec iov[1];
  int ret, len_tail;

  // send page to kernel pipe
  iov[0].iov_base = page;
  iov[0].iov_len = getpagesize();

  ret = vmsplice(tx_splicefd[1], iov, 1, SPLICE_F_GIFT);
  if (ret != getpagesize()) {
    fprintf(stderr, "vmsplice()\n");
    return 1;
  }

  // splice unused headspace to /dev/null (because our packet is not aligned)
  ret = splice(tx_splicefd[0], NULL, tx_nullfd, NULL, pkt_offset, SPLICE_F_MOVE);
  if (ret != pkt_offset
) {
    fprintf(stderr, "splice() header\n");
    return 1;
  }

  // splice or sendfile packet to tx socket
  ret = splice(tx_splicefd[0], NULL, tx_rawsockfd, NULL, pktlen, SPLICE_F_MOVE);
  if (ret != pktlen) {
    fprintf(stderr, "splice() main\n");
    return 1;
  }

  // splice unused tailspace to /dev/null
  len_tail = getpagesize() - pktlen - pkt_offset;
  ret = splice(tx_splicefd[0], NULL, tx_nullfd, NULL, len_tail, SPLICE_F_MOVE);
  if (ret != len_tail) {
    fprintf(stderr, "splice() footer\n");
    return 1;
  }
  return 0;
}

int
main(int argc, char **argv)
{
  char *page;

  if (posix_memalign((void **) &page, getpagesize(), getpagesize())) {
    fprintf(stderr, "posix_memalign");
    return 1;
  }
 
  if (do_init())
    return 1;

  // TODO: create packet(s) in this page
  //do_transmit(page, 0, 100);

  if (do_exit())
    return 1;

  return 0;
}