#define _GNU_SOURCE 1
#include <unistd.h>
#include <sys/mman.h>
#include <sys/time.h>
#include <stdio.h>
#include <stdlib.h>
#include <numa.h>
#include <numaif.h>
#include <errno.h>
#include <sched.h>

#ifndef MPOL_MF_LAZY
#define MPOL_MF_LAZY (1<<3)
#endif

#define TOTALPAGES 262144

int nbpages, loop;
int pagesize;

int main(int argc, char **argv) {
  void *buffer;
  int i, err;
  unsigned long nodemask;
  int maxnode;
  struct timeval tv1, tv2;
  unsigned long us;
  cpu_set_t cset;

  /* put the thread on node 0 */
  CPU_ZERO(&cset);
  CPU_SET(0, &cset);
  err = sched_setaffinity(0, sizeof(cset), &cset);
  if (err < 0) {
    perror("sched_setaffinity");
    exit(-1);
  }

  pagesize = getpagesize();
  maxnode = numa_max_node();

  fprintf(stdout, "# Nb_pages\tCost(ns)\n");
  for(nbpages=2 ; nbpages<=TOTALPAGES ; nbpages*=2) {
    int loops = TOTALPAGES/nbpages;
    if (loops > 128) loops = 128;

    buffer = mmap(NULL, TOTALPAGES*pagesize, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);
    if (buffer == MAP_FAILED) {
      perror("mmap");
      exit(-1);
    }

    /* bind to node 1 and prefault */
    nodemask = 1<<1;
    err = mbind(buffer, TOTALPAGES*pagesize, MPOL_BIND, &nodemask, maxnode+2, MPOL_MF_MOVE);
    if (err < 0) {
      perror("mbind");
      exit(-1);
    }
    for(i=0 ; i<TOTALPAGES ; i++)
      *(int*)(buffer+i*pagesize) = 0;

    gettimeofday(&tv1, NULL);
 
    for(loop=0 ; loop<loops ; loop++) {
      /* mark subbuf as next-touch and touch it */
      void *subbuf = buffer + loop*nbpages*pagesize;
      err = mbind(subbuf, nbpages*pagesize, MPOL_PREFERRED, NULL, 0, MPOL_MF_MOVE|MPOL_MF_LAZY);
      if (err < 0) {
        perror("mbind");
	exit(-1);
      }
      for(i=0;i<nbpages;i++)
        *(int*)(subbuf + i*pagesize) = 42;
    }
    gettimeofday(&tv2, NULL);

    us = (tv2.tv_sec - tv1.tv_sec) * 1000000 + (tv2.tv_usec - tv1.tv_usec);
    fprintf(stdout, "%d\t%ld\n", nbpages, us * 1000/loops);
    fflush(stdout);

    munmap(buffer, TOTALPAGES*pagesize);
  }

  return 0;
}