memcpy

Are you tired of hacking?, take some rest here.
Just help me out with my small experiment regarding memcpy performance.
after that, flag is yours.

http://pwnable.kr/bin/memcpy.c

ssh memcpy@pwnable.kr -p2222 (pw:guest)

 

源代码如下：

// compiled with : gcc -o memcpy memcpy.c -m32 -lm
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <signal.h>
#include <unistd.h>
#include <sys/mman.h>
#include <math.h>

unsigned long long rdtsc(){
        asm("rdtsc");
}

char* slow_memcpy(char* dest, const char* src, size_t len){
    int i;
    for (i=0; i<len; i++) {
        dest[i] = src[i];
    }
    return dest;
}

char* fast_memcpy(char* dest, const char* src, size_t len){
    size_t i;
    // 64-byte block fast copy
    if(len >= 64){
        i = len / 64;
        len &= (64-1);
        while(i-- > 0){
            __asm__ __volatile__ (
            "movdqa (%0), %%xmm0\n"
            "movdqa 16(%0), %%xmm1\n"
            "movdqa 32(%0), %%xmm2\n"
            "movdqa 48(%0), %%xmm3\n"
            "movntps %%xmm0, (%1)\n"
            "movntps %%xmm1, 16(%1)\n"
            "movntps %%xmm2, 32(%1)\n"
            "movntps %%xmm3, 48(%1)\n"
            ::"r"(src),"r"(dest):"memory");
            dest += 64;
            src += 64;
        }
    }

    // byte-to-byte slow copy
    if(len) slow_memcpy(dest, src, len);
    return dest;
}

int main(void){

    setvbuf(stdout, 0, _IONBF, 0);
    setvbuf(stdin, 0, _IOLBF, 0);

    printf("Hey, I have a boring assignment for CS class.. :(\n");
    printf("The assignment is simple.\n");

    printf("-----------------------------------------------------\n");
    printf("- What is the best implementation of memcpy?        -\n");
    printf("- 1. implement your own slow/fast version of memcpy -\n");
    printf("- 2. compare them with various size of data         -\n");
    printf("- 3. conclude your experiment and submit report     -\n");
    printf("-----------------------------------------------------\n");

    printf("This time, just help me out with my experiment and get flag\n");
    printf("No fancy hacking, I promise :D\n");

    unsigned long long t1, t2;
    int e;
    char* src;
    char* dest;
    unsigned int low, high;
    unsigned int size;
    // allocate memory
    char* cache1 = mmap(0, 0x4000, 7, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);
    char* cache2 = mmap(0, 0x4000, 7, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);
    src = mmap(0, 0x2000, 7, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);

    size_t sizes[10];
    int i=0;

    // setup experiment parameters
    for(e=4; e<14; e++){    // 2^13 = 8K
        low = pow(2,e-1);
        high = pow(2,e);
        printf("specify the memcpy amount between %d ~ %d : ", low, high);
        scanf("%d", &size);
        if( size < low || size > high ){
            printf("don't mess with the experiment.\n");
            exit(0);
        }
        sizes[i++] = size;
    }

    sleep(1);
    printf("ok, lets run the experiment with your configuration\n");
    sleep(1);

    // run experiment
    for(i=0; i<10; i++){
        size = sizes[i];
        printf("experiment %d : memcpy with buffer size %d\n", i+1, size);
        dest = malloc( size );

        memcpy(cache1, cache2, 0x4000);        // to eliminate cache effect
        t1 = rdtsc();
        slow_memcpy(dest, src, size);        // byte-to-byte memcpy
        t2 = rdtsc();
        printf("ellapsed CPU cycles for slow_memcpy : %llu\n", t2-t1);

        memcpy(cache1, cache2, 0x4000);        // to eliminate cache effect
        t1 = rdtsc();
        fast_memcpy(dest, src, size);        // block-to-block memcpy
        t2 = rdtsc();
        printf("ellapsed CPU cycles for fast_memcpy : %llu\n", t2-t1);
        printf("\n");
    }

    printf("thanks for helping my experiment!\n");
    printf("flag : ----- erased in this source code -----\n");
    return 0;
}

发现他的写法里用了movdqa和movntps，其中后者是要求内存16对齐的，因此每次选择的size要保持申请的堆块内存对齐即可