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

#define CACHE_SIZE (64*64*8)
unsigned char *cache_L1;
unsigned long *T = NULL;

void measures(){

    asm volatile(
        "mov $1000000,%%r11\n\t"// number of loop iteration
        "mov %%rax,%%r12\n\t"
        "mov %%rbx,%%r10\n\t"

        "loop:\n\t"

            // Serialize before beginning
            "xor %%rax,%%rax\n\tcpuid\n\t"

            // Make sure that [r12+4096] is not is cache
            "mov %%r12,%%rax\n\t"
            "add $4096, %%rax\n\t" // For experiment 1, this line is changed to 'add $0,%%rax'
            "clflush (%%rax)\n\t"

            // Make sure that [r12 + 32768] is not in cache
            "mov %%r12,%%rax\n\t"
            "add $32768, %%rax\n\t"
            "clflush (%%rax)\n\t"


            // Serialize to make sure that all previous operation are finished before continuing.
            "xor %%rax,%%rax\n\tcpuid\n\t"  // 1 load

            // Put [r12 + 4096] in cache
            "mov %%r12,%%rax\n\t"
            "add $4096,%%rax\n\t" // For experiment 1, this line is changed to 'add $0,%%rax'
                        "mov (%%rax),%%r8\n\t"

            // Serialize to make sure that all previous operation are finished before continuing.
            "xor %%rax,%%rax\n\tcpuid\n\t"

            // ------ Now I will try to access [r12 + 32768]. Since it was fflushed, I expect it is not in cache and I expect to measure a cache miss when reading [r12 + 32768].


            // Read PMC configured with MEM_LOAD_UOPS_RETIRED.L1_MISS
            "xor %%rcx,%%rcx\n\trdpmc\n\tshl $32,%%rdx\n\tor %%rdx,%%rax\n\tmov %%rax,%%r9\n\t"

            // Serialize to make sure that all previous operation are finished before continuing.
            "xor %%rax,%%rax\n\tcpuid\n\t"  // 1 load


            // Access [r12 + 32768 ]
            "mov  %%r12, %%rax\n\t"
            "add $32768,%%rax\n\t"
            "mov (%%rax),%%r8\n\t"

            // Serialize to make sure that all previous operation are finished before continuing.
            "xor %%rax,%%rax\n\tcpuid\n\t" // 1 load

            // Read PMC configured with MEM_LOAD_UOPS_RETIRED.L1_MISS. Substract with the first read. Store the result in r15
                        "xor %%rcx,%%rcx\n\trdpmc\n\tshl $32,%%rdx\n\tor %%rdx,%%rax\n\tmov %%rax,%%r15\n\t"

            // Serialize to make sure that all previous operation are finished before continuing.
            "xor %%rax,%%rax\n\tcpuid\n\t" // 1 load

            // STORE
            "mov %%r10,%%rbx\n\t"
            "sub %%r9,%%r15\n\t"
            "movq %%r15, (%%rbx)\n\t"
            "clflush (%%r10)\n\t"
            "add $8,%%r10\n\t"

            // Serialize to make sure that all previous operation are finished before continuing.
            "xor %%rax,%%rax\n\tcpuid\n\t" // 1 load


        "dec %%r11\n\t"
        "jnz loop\n\t"
        "endloop:"

            :
            :"a"(cache_L1),"b"(T)
            :"rcx","rdx","r8","r9","r10","r11","r15");



}


int main()
{
    // Configure PMC by writting in /dev/CONFIG_MODULE0 (This file is created by a kernel module I made)
    int pmcfd;
    char *pmcname;
    pmcname = "MEM_LOAD_UOPS_RETIRED.L1_MISS";
    pmcfd = open("/dev/CONFIG_MODULE0", O_RDWR);
    assert(pmcfd != -1);
    write(pmcfd, "CHANGEPMC=0",strlen("CHANGEPMC=0"));
    write(pmcfd, pmcname,strlen(pmcname));
    close(pmcfd);

    // Allocate a memory buffer and align it to L1 set 0
    cache_L1 = calloc(6*CACHE_SIZE,1);
    unsigned long currentSet = ((unsigned long)cache_L1 >> 6) & 63;
    while(currentSet != 0){
        cache_L1 += 64; // cache line size to jump to the next set
        currentSet = ((long)cache_L1 >> 6) & 63;
    }

    // Allocate an array to store results
    T = calloc(1000000,sizeof(unsigned long));


    // Perform the measures
    measures();

    // Print the measures
    for(int nbrmes=0;nbrmes<1000000;++nbrmes)
        printf("%ld\n",T[nbrmes]);

}