iOS逆向--fishHook源码分析

2,136 阅读6分钟

上一篇文章,分析了fishHook的原理,这一篇我们对fishHook的源码进行分析一下。

结构体 rebinding

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!
};

fishHook使用的时候需要我们创建一个结构体数组rebinding,我们先看一下rebinding结构体的属性:

  • name:是C字符串,fishHook就是通过name去machO中去找到系统函数对应的符号
  • replacement:是一个指针,指向的是我们需要替换的新函数的函数地址
  • replaced:一个二级指针,因为程序在加载时候无法找到真正系统函数的函数地址,只有在链接完成后才能知道,而fishHook在Hook完成后需要一个指针去将真正的函数的函数地址保存起来,这个时候就需要我们自定义一个函数指针用来保存真正系统函数的函数地址,否则当hook完系统函数后,就无法调用真正的系统函数

int rebind_symbols(struct rebinding rebindings[], size_t rebindings_nel);

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;
}

我们发现首先会调动prepend_rebindings函数对传进来的参数rebindings通过链表的形式进行保存。

prepend_rebindings

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

static struct rebindings_entry *_rebindings_head;


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;
}

第一次调用的话,调_dyld_register_func_for_add_image注册监听方法.

不是第一次调用遍历已经加载的image,通过_rebind_symbols_for_image函数进行hook

_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);
}

调用的是rebind_symbols_for_image函数

rebind_symbols_for_image,真正的hook函数

//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) {
    
    /*dladdr() 可确定指定的address 是否位于构成进程的进址空间的其中一个加载模块(可执行库或共享库)内,如果某个地址位于在其上面映射加载模块的基址和为该加载模块映射的最高虚拟地址之间(包括两端),则认为该地址在加载模块的范围内。如果某个加载模块符合这个条件,则会搜索其动态符号表,以查找与指定的address 最接近的符号。最接近的符号是指其值等于,或最为接近但小于指定的address 的符号。
     */
    /*
     如果指定的address 不在其中一个加载模块的范围内,则返回0 ;且不修改Dl_info 结构的内容。否则,将返回一个非零值,同时设置Dl_info 结构的字段。
     如果在包含address 的加载模块内,找不到其值小于或等于address 的符号,则dli_sname 、dli_saddr 和dli_size字段将设置为0 ; dli_bind 字段设置为STB_LOCAL , dli_type 字段设置为STT_NOTYPE 。
     */
    //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;
//    printf("地址:%p\n",linkedit_base);
    //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);
        }
      }
    }
  }
}
  • 先通过dladdr来判断传进来的image是否在进程的内存空间内,如果不在则return
  • 定义好几个变量,通过遍历找到几个关键表的地址,并用变量保存起来
  • 找到程序链接时候的基准地址,然后加上表的偏移,然后再遍历segment,找到符号的懒加载和非懒加载表通过perform_rebinding_with_section函数进行符号重定向

perform_rebinding_with_section


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:;
  }
}
  • 通过传进来表的指针地址来变量session里面的每一个符号
  • 找到符号对应的是函数名的话,然后再变量传进来来的rebindings数组,如果匹配的上,则开始进行重定向
    • 先判断传进来的rebindings结构体的replaced不为空,且符号对应的函数地址和传进来的新函数地址不一致,这个时候用rebindings的replaced将符号对应的函数地址保存起来
    • 然后将传进来的rebindings的replacement替换掉符号本身对应的函数地址,至此:hook完成