11、HOOK原理（上）--- fishHook

2021-05-11  本文已影响0人  Jax_YD

HOOK

建议大家先对MachO有一定的了解，因为下面的内容会涉及到MachO里面的内容3、iOS强化 --- Mach-O 文件
HOOK，中文译为“挂钩”或“钩子”。在iOS逆向中时指改变程序运行流程的一种技术。通过HOOK可以让别人的程序执行自己所写的代码。在逆向中经常使用这种技术。
下面我们来简单看一下HOOK的工作流程是怎样的。

HOOK示意图

iOS中HOOK的几种方式

fishHook

这里我们简单的使用一下fishHook。fishHook地址
fishHook只给我们提供了两个函数和一个结构体

FISHHOOK_VISIBILITY
int rebind_symbols(struct rebinding rebindings[], size_t rebindings_nel);
// 参数一 ： 存放rebinding结构体的数组（可以同时交换多个函数）
// 参数二 ： rebinding数组长度

// 跟上面的函数比起来，这个函数可以指定image(镜像文件)
FISHHOOK_VISIBILITY
int rebind_symbols_image(void *header,
                         intptr_t slide,
                         struct rebinding rebindings[],
                         size_t rebindings_nel);

struct rebinding {
  const char *name;//需要HOOK的函数名称，C字符串
  void *replacement;//新函数的地址
  void **replaced;//原始函数地址的指针！
};

下面我们就来使用一下fishHook。

int rebind_symbols(struct rebinding rebindings[], size_t rebindings_nel) {
    //prepend_rebindings的函数会将整个 rebindings 数组添加到 _rebindings_head 这个链表的头部
    //Fishhook采用链表的方式来存储每一次调用rebind_symbols传入的参数，每次调用，就会在链表的头部插入一个节点，链表的头部是：_rebindings_head
    int retval = prepend_rebindings(&_rebindings_head, rebindings, rebindings_nel);
    //根据上面的prepend_rebinding来做判断，如果小于0的话，直接返回一个错误码回去
    if (retval < 0) {
    return retval;
  }
    //根据_rebindings_head->next是否为空判断是不是第一次调用。
  if (!_rebindings_head->next) {
      //第一次调用的话，调用_dyld_register_func_for_add_image注册监听方法.
      //已经被dyld加载的image会立刻进入回调。
      //之后的image会在dyld装载的时候触发回调。
    _dyld_register_func_for_add_image(_rebind_symbols_for_image);
  } else {
      //遍历已经加载的image，进行的hook
    uint32_t c = _dyld_image_count();
    for (uint32_t i = 0; i < c; i++) {
      _rebind_symbols_for_image(_dyld_get_image_header(i), _dyld_get_image_vmaddr_slide(i));
    }
  }
  return retval;
}

根据代码，我们可以看到，首先会有一个retval的判断，那么我们来看看prepend_rebindings这个方法

static int prepend_rebindings(struct rebindings_entry **rebindings_head,
                              struct rebinding rebindings[],
                              size_t nel) {
  struct rebindings_entry *new_entry = (struct rebindings_entry *) malloc(sizeof(struct rebindings_entry));
  if (!new_entry) {
    return -1;
  }
  new_entry->rebindings = (struct rebinding *) malloc(sizeof(struct rebinding) * nel);
  if (!new_entry->rebindings) {
    free(new_entry);
    return -1;
  }
  memcpy(new_entry->rebindings, rebindings, sizeof(struct rebinding) * nel);
  new_entry->rebindings_nel = nel;
  new_entry->next = *rebindings_head;
  *rebindings_head = new_entry;
  return 0;
}

可以看到*rebindings_head = new_entry;，也就是我们之前传入的&_rebindings_head。我们再来看一下_rebindings_head是什么：

struct rebindings_entry {
  struct rebinding *rebindings;
  size_t rebindings_nel;
  struct rebindings_entry *next;
};

static struct rebindings_entry *_rebindings_head;

到这里不难看出_rebindings_head其实就是一个链表的表头。
下面我们继续在rebind_symbols方法里面往下走，这里跟大家说一下，我们在动态调试的时候，无论是第一次调用还是第N次调用，都会进入_rebind_symbols_for_image，这里大家只要打断点调试一下就可以看到。那么我们直接去_rebind_symbols_for_image方法。

/*****************************************/
// _rebind_symbols_for_image
/*****************************************/
static void _rebind_symbols_for_image(const struct mach_header *header,
                                      intptr_t slide) {
    rebind_symbols_for_image(_rebindings_head, header, slide);
}
👇
/*****************************************/
// rebind_symbols_for_image
/*****************************************/
//回调的最终就是这个函数！ 三个参数：要交换的数组  、 image的头 、 ASLR的偏移
static void rebind_symbols_for_image(struct rebindings_entry *rebindings,
                                     const struct mach_header *header,
                                     intptr_t slide){}

rebind_symbols_for_image方法中有一个函数，要先跟大家讲清楚，那就是dladdr()。

//回调的最终就是这个函数！ 三个参数：要交换的数组  、 image的头 、 ASLR的偏移
static void rebind_symbols_for_image(struct rebindings_entry *rebindings,
                                     const struct mach_header *header,
                                     intptr_t slide) {
  //这个dladdr函数就是在程序里面找header
  Dl_info info;
  if (dladdr(header, &info) == 0) {
    return;
  }
  //下面就是定义好几个变量，准备从MachO里面去找！
  segment_command_t *cur_seg_cmd;
  segment_command_t *linkedit_segment = NULL;
  struct symtab_command* symtab_cmd = NULL;
  struct dysymtab_command* dysymtab_cmd = NULL;
  //跳过header的大小，找loadCommand
  uintptr_t cur = (uintptr_t)header + sizeof(mach_header_t);
  for (uint i = 0; i < header->ncmds; i++, cur += cur_seg_cmd->cmdsize) {
    cur_seg_cmd = (segment_command_t *)cur;
    if (cur_seg_cmd->cmd == LC_SEGMENT_ARCH_DEPENDENT) {
      if (strcmp(cur_seg_cmd->segname, SEG_LINKEDIT) == 0) {
        linkedit_segment = cur_seg_cmd;
      }
    } else if (cur_seg_cmd->cmd == LC_SYMTAB) {
      symtab_cmd = (struct symtab_command*)cur_seg_cmd;
    } else if (cur_seg_cmd->cmd == LC_DYSYMTAB) {
      dysymtab_cmd = (struct dysymtab_command*)cur_seg_cmd;
    }
  }
   //如果刚才获取的，有一项为空就直接返回
  if (!symtab_cmd || !dysymtab_cmd || !linkedit_segment ||
      !dysymtab_cmd->nindirectsyms) {
    return;
  }

  // Find base symbol/string table addresses
  //链接时程序的基址 = __LINKEDIT.VM_Address -__LINKEDIT.File_Offset + silde的改变值
  uintptr_t linkedit_base = (uintptr_t)slide + linkedit_segment->vmaddr - linkedit_segment->fileoff;
  //符号表的地址 = 基址 + 符号表偏移量
  nlist_t *symtab = (nlist_t *)(linkedit_base + symtab_cmd->symoff);
  //字符串表的地址 = 基址 + 字符串表偏移量
  char *strtab = (char *)(linkedit_base + symtab_cmd->stroff);

  // Get indirect symbol table (array of uint32_t indices into symbol table)
  //动态符号表地址 = 基址 + 动态符号表偏移量
  uint32_t *indirect_symtab = (uint32_t *)(linkedit_base + dysymtab_cmd->indirectsymoff);

  cur = (uintptr_t)header + sizeof(mach_header_t);
  for (uint i = 0; i < header->ncmds; i++, cur += cur_seg_cmd->cmdsize) {
    cur_seg_cmd = (segment_command_t *)cur;
    if (cur_seg_cmd->cmd == LC_SEGMENT_ARCH_DEPENDENT) {
        //寻找到data段
      if (strcmp(cur_seg_cmd->segname, SEG_DATA) != 0 &&
          strcmp(cur_seg_cmd->segname, SEG_DATA_CONST) != 0) {
        continue;
      }
        
      for (uint j = 0; j < cur_seg_cmd->nsects; j++) {
        section_t *sect =
          (section_t *)(cur + sizeof(segment_command_t)) + j;
          //找懒加载表
        if ((sect->flags & SECTION_TYPE) == S_LAZY_SYMBOL_POINTERS) {
          perform_rebinding_with_section(rebindings, sect, slide, symtab, strtab, indirect_symtab);
        }
          //非懒加载表
        if ((sect->flags & SECTION_TYPE) == S_NON_LAZY_SYMBOL_POINTERS) {
          perform_rebinding_with_section(rebindings, sect, slide, symtab, strtab, indirect_symtab);
        }
      }
    }
  }
}

最后我们看到，无论是懒加载符号表还是非懒加载符号表，都回去调用perform_rebinding_with_section。那我们就继续跟进perform_rebinding_with_section，这里面就有意思了，有我们想要的HOOK；我们上面提到的函数指针的替换，就在这里面：

static void perform_rebinding_with_section(struct rebindings_entry *rebindings,
                                           section_t *section,
                                           intptr_t slide,
                                           nlist_t *symtab,
                                           char *strtab,
                                           uint32_t *indirect_symtab) {
    //nl_symbol_ptr和la_symbol_ptrsection中的reserved1字段指明对应的indirect symbol table起始的index
  uint32_t *indirect_symbol_indices = indirect_symtab + section->reserved1;
    //slide+section->addr 就是符号对应的存放函数实现的数组也就是我相应的__nl_symbol_ptr和__la_symbol_ptr相应的函数指针都在这里面了，所以可以去寻找到函数的地址
  void **indirect_symbol_bindings = (void **)((uintptr_t)slide + section->addr);
    //遍历section里面的每一个符号
  for (uint i = 0; i < section->size / sizeof(void *); i++) {
      //找到符号在Indrect Symbol Table表中的值
      //读取indirect table中的数据
    uint32_t symtab_index = indirect_symbol_indices[i];
    if (symtab_index == INDIRECT_SYMBOL_ABS || symtab_index == INDIRECT_SYMBOL_LOCAL ||
        symtab_index == (INDIRECT_SYMBOL_LOCAL   | INDIRECT_SYMBOL_ABS)) {
      continue;
    }
      //以symtab_index作为下标，访问symbol table
      uint32_t strtab_offset = symtab[symtab_index].n_un.n_strx;
      //获取到symbol_name
      char *symbol_name = strtab + strtab_offset;
      //判断是否函数的名称是否有两个字符，为啥是两个，因为函数前面有个_，所以方法的名称最少要1个
      bool symbol_name_longer_than_1 = symbol_name[0] && symbol_name[1];
      //遍历最初的链表，来进行hook
      struct rebindings_entry *cur = rebindings;
      while (cur) {
          for (uint j = 0; j < cur->rebindings_nel; j++) {
              //这里if的条件就是判断从symbol_name[1]两个函数的名字是否都是一致的，以及判断两个
              if (symbol_name_longer_than_1 &&
                  strcmp(&symbol_name[1], cur->rebindings[j].name) == 0) {
                  //判断replaced的地址不为NULL以及我方法的实现和rebindings[j].replacement的方法不一致
                  if (cur->rebindings[j].replaced != NULL &&
                      indirect_symbol_bindings[i] != cur->rebindings[j].replacement) {
                      //让rebindings[j].replaced保存indirect_symbol_bindings[i]的函数地址
                      *(cur->rebindings[j].replaced) = indirect_symbol_bindings[i];
                  }
                  //将替换后的方法给原先的方法，也就是替换内容为自定义函数地址
                  indirect_symbol_bindings[i] = cur->rebindings[j].replacement;
                  goto symbol_loop;
        }
      }
      cur = cur->next;
    }
  symbol_loop:;
  }
}

最关键的两句代码：

//让rebindings[j].replaced保存indirect_symbol_bindings[i]的函数地址
*(cur->rebindings[j].replaced) = indirect_symbol_bindings[i];

//将替换后的方法给原先的方法，也就是替换内容为自定义函数地址
indirect_symbol_bindings[i] = cur->rebindings[j].replacement;

这就与我们之前分析的fishHook的HOOK过程对应起来了。

总结：

上一篇下一篇

猜你喜欢

热点阅读