main

首先从 main 来看：

/* Main entry point */

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

  if (isatty(2) && !getenv("AFL_QUIET")) {

    SAYF(cCYA "afl-cc " cBRI VERSION cRST " by <lcamtuf@google.com>\n");

  } else be_quiet = 1;

  if (argc < 2) {

    SAYF("\n"
         "This is a helper application for afl-fuzz. It serves as a drop-in replacement\n"
         "for gcc or clang, letting you recompile third-party code with the required\n"
         "runtime instrumentation. A common use pattern would be one of the following:\n\n"

         "  CC=%s/afl-gcc ./configure\n"
         "  CXX=%s/afl-g++ ./configure\n\n"

         "You can specify custom next-stage toolchain via AFL_CC, AFL_CXX, and AFL_AS.\n"
         "Setting AFL_HARDEN enables hardening optimizations in the compiled code.\n\n",
         BIN_PATH, BIN_PATH);

    exit(1);

  }

  find_as(argv[0]);

  edit_params(argc, argv);

  execvp(cc_params[0], (char**)cc_params);

  FATAL("Oops, failed to execute '%s' - check your PATH", cc_params[0]);

  return 0;

}

会首先检查

isatty(2) 是否为 1 // stdout
设置了 AFL_QUIET 环境变量

如果有一个不满足则切换为 quiet 模式

接下来主要流程分配三个阶段：

find_as
edit_params
execvp

find_as

该函数会去寻找所使用的汇编器，传入的 argv0 就是 afl-gcc s：

/* Try to find our "fake" GNU assembler in AFL_PATH or at the location derived
   from argv[0]. If that fails, abort. */

static void find_as(u8* argv0) {

  u8 *afl_path = getenv("AFL_PATH");
  u8 *slash, *tmp;

  if (afl_path) {

    tmp = alloc_printf("%s/as", afl_path);

    if (!access(tmp, X_OK)) {
      as_path = afl_path;
      ck_free(tmp);
      return;
    }

    ck_free(tmp);

  }

  slash = strrchr(argv0, '/');

  if (slash) {

    u8 *dir;

    *slash = 0;
    dir = ck_strdup(argv0);
    *slash = '/';

    tmp = alloc_printf("%s/afl-as", dir);

    if (!access(tmp, X_OK)) {
      as_path = dir;
      ck_free(tmp);
      return;
    }

    ck_free(tmp);
    ck_free(dir);

  }

  if (!access(AFL_PATH "/as", X_OK)) {
    as_path = AFL_PATH;
    return;
  }

  FATAL("Unable to find AFL wrapper binary for 'as'. Please set AFL_PATH");
 
}

其步骤如下：

获得环境变量 AFL_PATH 并赋值给 afl_path
- 如果 afl_path 存在，则将 afl_path 拼接上 “/as” 作为 as 的路径，检查其是否可访问，可访问则返回
从 argv0 中寻找是否有 “/” 字符
- 如果有则将 “/” 字符之前的内容拆分，并拼接上 “/afl-as” 作为 as 的路径，检查其是否可访问，可访问则返回
如果都不行则最后抛出异常

edit_params

edit_params 函数主要用于更改一些参数：

/* Copy argv to cc_params, making the necessary edits. */

static void edit_params(u32 argc, char** argv) {

  u8 fortify_set = 0, asan_set = 0;
  u8 *name;

#if defined(__FreeBSD__) && defined(__x86_64__)
  u8 m32_set = 0;
#endif

  cc_params = ck_alloc((argc + 128) * sizeof(u8*));

  name = strrchr(argv[0], '/');
  if (!name) name = argv[0]; else name++;

  if (!strncmp(name, "afl-clang", 9)) {

    clang_mode = 1;

    setenv(CLANG_ENV_VAR, "1", 1);

    if (!strcmp(name, "afl-clang++")) {
      u8* alt_cxx = getenv("AFL_CXX");
      cc_params[0] = alt_cxx ? alt_cxx : (u8*)"clang++";
    } else {
      u8* alt_cc = getenv("AFL_CC");
      cc_params[0] = alt_cc ? alt_cc : (u8*)"clang";
    }

  } else {

    /* With GCJ and Eclipse installed, you can actually compile Java! The
       instrumentation will work (amazingly). Alas, unhandled exceptions do
       not call abort(), so afl-fuzz would need to be modified to equate
       non-zero exit codes with crash conditions when working with Java
       binaries. Meh. */

#ifdef __APPLE__

    if (!strcmp(name, "afl-g++")) cc_params[0] = getenv("AFL_CXX");
    else if (!strcmp(name, "afl-gcj")) cc_params[0] = getenv("AFL_GCJ");
    else cc_params[0] = getenv("AFL_CC");

    if (!cc_params[0]) {

      SAYF("\n" cLRD "[-] " cRST
           "On Apple systems, 'gcc' is usually just a wrapper for clang. Please use the\n"
           "    'afl-clang' utility instead of 'afl-gcc'. If you really have GCC installed,\n"
           "    set AFL_CC or AFL_CXX to specify the correct path to that compiler.\n");

      FATAL("AFL_CC or AFL_CXX required on MacOS X");

    }

#else

    if (!strcmp(name, "afl-g++")) {
      u8* alt_cxx = getenv("AFL_CXX");
      cc_params[0] = alt_cxx ? alt_cxx : (u8*)"g++";
    } else if (!strcmp(name, "afl-gcj")) {
      u8* alt_cc = getenv("AFL_GCJ");
      cc_params[0] = alt_cc ? alt_cc : (u8*)"gcj";
    } else {
      u8* alt_cc = getenv("AFL_CC");
      cc_params[0] = alt_cc ? alt_cc : (u8*)"gcc";
    }

#endif /* __APPLE__ */

  }

  while (--argc) {
    u8* cur = *(++argv);

    if (!strncmp(cur, "-B", 2)) {

      if (!be_quiet) WARNF("-B is already set, overriding");

      if (!cur[2] && argc > 1) { argc--; argv++; }
      continue;

    }

    if (!strcmp(cur, "-integrated-as")) continue;

    if (!strcmp(cur, "-pipe")) continue;

#if defined(__FreeBSD__) && defined(__x86_64__)
    if (!strcmp(cur, "-m32")) m32_set = 1;
#endif

    if (!strcmp(cur, "-fsanitize=address") ||
        !strcmp(cur, "-fsanitize=memory")) asan_set = 1;

    if (strstr(cur, "FORTIFY_SOURCE")) fortify_set = 1;

    cc_params[cc_par_cnt++] = cur;

  }

  cc_params[cc_par_cnt++] = "-B";
  cc_params[cc_par_cnt++] = as_path;

  if (clang_mode)
    cc_params[cc_par_cnt++] = "-no-integrated-as";

  if (getenv("AFL_HARDEN")) {

    cc_params[cc_par_cnt++] = "-fstack-protector-all";

    if (!fortify_set)
      cc_params[cc_par_cnt++] = "-D_FORTIFY_SOURCE=2";

  }

  if (asan_set) {

    /* Pass this on to afl-as to adjust map density. */

    setenv("AFL_USE_ASAN", "1", 1);

  } else if (getenv("AFL_USE_ASAN")) {

    if (getenv("AFL_USE_MSAN"))
      FATAL("ASAN and MSAN are mutually exclusive");

    if (getenv("AFL_HARDEN"))
      FATAL("ASAN and AFL_HARDEN are mutually exclusive");

    cc_params[cc_par_cnt++] = "-U_FORTIFY_SOURCE";
    cc_params[cc_par_cnt++] = "-fsanitize=address";

  } else if (getenv("AFL_USE_MSAN")) {

    if (getenv("AFL_USE_ASAN"))
      FATAL("ASAN and MSAN are mutually exclusive");

    if (getenv("AFL_HARDEN"))
      FATAL("MSAN and AFL_HARDEN are mutually exclusive");

    cc_params[cc_par_cnt++] = "-U_FORTIFY_SOURCE";
    cc_params[cc_par_cnt++] = "-fsanitize=memory";

  }

  if (!getenv("AFL_DONT_OPTIMIZE")) {

#if defined(__FreeBSD__) && defined(__x86_64__)

    /* On 64-bit FreeBSD systems, clang -g -m32 is broken, but -m32 itself
       works OK. This has nothing to do with us, but let's avoid triggering
       that bug. */

    if (!clang_mode || !m32_set)
      cc_params[cc_par_cnt++] = "-g";

#else

      cc_params[cc_par_cnt++] = "-g";

#endif

    cc_params[cc_par_cnt++] = "-O3";
    cc_params[cc_par_cnt++] = "-funroll-loops";

    /* Two indicators that you're building for fuzzing; one of them is
       AFL-specific, the other is shared with libfuzzer. */

    cc_params[cc_par_cnt++] = "-D__AFL_COMPILER=1";
    cc_params[cc_par_cnt++] = "-DFUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION=1";

  }

  if (getenv("AFL_NO_BUILTIN")) {

    cc_params[cc_par_cnt++] = "-fno-builtin-strcmp";
    cc_params[cc_par_cnt++] = "-fno-builtin-strncmp";
    cc_params[cc_par_cnt++] = "-fno-builtin-strcasecmp";
    cc_params[cc_par_cnt++] = "-fno-builtin-strncasecmp";
    cc_params[cc_par_cnt++] = "-fno-builtin-memcmp";
    cc_params[cc_par_cnt++] = "-fno-builtin-strstr";
    cc_params[cc_par_cnt++] = "-fno-builtin-strcasestr";

  }

  cc_params[cc_par_cnt] = NULL;

}

首先为 cc_params 分配空间，大小为 (argc + 128) * sizeof(u8*)
随后判断 argv[0] 是否包含 afl-clang，如果包含
- 设置 CLANG_ENV_VAR 为 1
- 判断 argv[0] 包含的是 afl-clang 还是 afl-clang++
  - 如果是 afl-clang ，则获取环境变量 AFL_CC
    - 没有环境变量，将 cc_params[0] 设为 clang
    - 否则设置为 AFL_CC
  - 如果是 afl-clang++ ，则获取环境变量 AFL_CXX
    - 没有环境变量，将 cc_params[0] 设为 clang++
    - 否则设置为 AFL_CXX
如果不包含
- 如果是 apple 平台，分别判断
  - 为 afl-g++ ，设置 cc_params[0] 为环境变量中的 AFL_CXX
  - 为 afl-gcj ，设置 cc_params[0] 为环境变量中的 AFL_GCJ
  - 设置 cc_params[0] 为环境变量中的 AFL_CC
  - 如果都不行，抛出错误
- 否则
  - 为 afl-g++ ，设置 cc_params[0] 为环境变量中的 AFL_CXX 或 g++
  - 为 afl-gcj ，设置 cc_params[0] 为环境变量中的 AFL_GCJ 或 gcj
  - 设置 cc_params[0] 为环境变量中的 AFL_CC 或 gcc
随后根据 argc 进行 argv 的遍历
- 默认设置 -B ，且跟着的参数为 as 的路径
- 忽略 -integrated-as 和 -pipe
- 如果是 clang 模式，则设置 -no-integrated-as
- 如果有环境变量 AFL_HARDEN ，则设置 -fstack-protector-all
  - 如果遍历的时候有 FORTIFY_SOURCE ，则变为 -D_FORTIFY_SOURCE=2
- 如果遍历的时候有 -fsanitize=address 或 -fsanitize=memory
  - 设置环境变量 AFL_USE_ASAN 为 1
- 否则，如果有设置环境变量 AFL_USE_ASAN
  - 判断是否有环境变量 AFL_USE_MSAN 和 FL_HARDEN ，有的话则抛出错误
  - 设置 -U_FORTIFY_SOURCE 和 -fsanitize=address
- 否则，如果有设置环境变量 AFL_USE_MSAN
  - 判断是否有环境变量 AFL_USE_ASAN 和 FL_HARDEN ，有的话则抛出错误
  - 设置 -U_FORTIFY_SOURCE 和 -fsanitize=memory
接下来判断是否有环境变量 AFL_DONT_OPTIMIZE ，如果没有的话
- 判断是否为 64-bit FreeBSD 平台，如果是的话则 clang -g -m32 会导致错误，但是 -m32 却可以，为了修复该 bug 直接加 -g 即可
- 之后分别添加以下参数
  - -O3
  - -funroll-loops
  - -D__AFL_COMPILER=1
  - -DFUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION=1
最后判断是否有环境变量 AFL_NO_BUILTIN ，如果有的话添加以下参数
- -fno-builtin-strcmp
- -fno-builtin-strncmp
- -fno-builtin-strcasecmp
- -fno-builtin-strncasecmp
- -fno-builtin-memcmp
- -fno-builtin-strstr
- -fno-builtin-strcasestr

execvp

最后的 execvp 则是将替换过后的执行运行，我们可以使用以下代码打印出来进行对比：

for(int i = 0; i < argc; i++){
  printf("\t[*] argv[%d] : %s\n",i,argv[i]);
}

printf("\n");

for(int i = 0; i < sizeof(cc_params); i++){
  printf("\t[*] cc_params[%d] : %s\n",i,cc_params[i]);
}

结果：

afl-cc 2.57b by <lcamtuf@google.com>
	[*] argv[0] : afl-gcc
	[*] argv[1] : test.c
	[*] argv[2] : -o
	[*] argv[3] : test
	[*] cc_params[0] : gcc
	[*] cc_params[1] : test.c
	[*] cc_params[2] : -o
	[*] cc_params[3] : test
	[*] cc_params[4] : -B
	[*] cc_params[5] : /usr/local/lib/afl
	[*] cc_params[6] : -g
	[*] cc_params[7] : -O3

可以看得出来 afl-gcc 的本质就是一层 wrapper