FishHook 源码解读

结合官方的例子和MachOView对源码进行理解

static int (*orig_close)(int);
static int (*orig_open)(const char *, int, ...);

int my_close(int fd) {
    printf("Calling real close(%d)\n", fd);
    return orig_close(fd);
}

int my_open(const char *path, int oflag, ...) {
    va_list ap = {0};
    mode_t mode = 0;
    
    if ((oflag & O_CREAT) != 0) {
        // mode only applies to O_CREAT
        va_start(ap, oflag);
        mode = va_arg(ap, int);
        va_end(ap);
        printf("Calling real open('%s', %d, %d)\n", path, oflag, mode);
        return orig_open(path, oflag, mode);
    } else {
        printf("Calling real open('%s', %d)\n", path, oflag);
        return orig_open(path, oflag, mode);
    }
}
struct rebinding reb[2];
reb[0].name = "close";
reb[0].replacement = my_close;
reb[0].replaced = (void **)&orig_close;
        
reb[1].name = "open";
reb[1].replacement = my_open;
reb[1].replaced = (void **)&orig_open;
      
rebind_symbols(reb, 2);

官方的例子是对标准库中open和close中进行hook的,两个结构体,my_close和my_close分别是新写的两个函数。

进入rebind_symbols

int rebind_symbols(struct rebinding rebindings[], size_t rebindings_nel) {
  int retval = prepend_rebindings(&_rebindings_head, rebindings, rebindings_nel);
  if (retval < 0) {
    return retval;
  }
  // If this was the first call, register callback for image additions (which is also invoked for
  // existing images, otherwise, just run on existing images
  if (!_rebindings_head->next) {   
     _dyld_register_func_for_add_image(_rebind_symbols_for_image);
  } else {
    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;
}

再进入prepend_rebindings函数

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

就是fishhook会维护一个链表,所有新添加的hook函数会添加到链表头部,如果你hook了同一个函数多次,那么后添加的就会先执行到。

if (!_rebindings_head->next) {
      _dyld_register_func_for_add_image(_rebind_symbols_for_image);
  }

_dyld_register_func_for_add_image 注册回调,当访问动态链接库函数的时候,链接器会链接这个库,在链接库的时候,会触发回调函数,再回调函数中,会对需要hook的函数进行替换,具体看源码:

static void rebind_symbols_for_image(struct rebindings_entry *rebindings,
                                     const struct mach_header *header,
                                     intptr_t slide) {
  Dl_info info;
   
  if (dladdr(header, &info) == 0) {
    return;
  }

  segment_command_t *cur_seg_cmd;
  segment_command_t *linkedit_segment = NULL;
  struct symtab_command* symtab_cmd = NULL;
  struct dysymtab_command* dysymtab_cmd = NULL;

  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;
    }
  }

  if (!symtab_cmd || !dysymtab_cmd || !linkedit_segment ||
      !dysymtab_cmd->nindirectsyms) {
    return;
  }

  // Find base symbol/string table addresses
  uintptr_t linkedit_base = (uintptr_t)slide + linkedit_segment->vmaddr - linkedit_segment->fileoff;
  nlist_t *symtab = (nlist_t *)(linkedit_base + symtab_cmd->symoff);
  char *strtab = (char *)(linkedit_base + symtab_cmd->stroff);

  // Get indirect symbol table (array of uint32_t indices into symbol table)
  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) {
      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;
        if ((sect->flags & SECTION_TYPE) == S_LAZY_SYMBOL_POINTERS) {
          perform_rebinding_with_section(rebindings, sect, slide, symtab, strtab, indirect_symtab);
        }
        if ((sect->flags & SECTION_TYPE) == S_NON_LAZY_SYMBOL_POINTERS) {
          perform_rebinding_with_section(rebindings, sect, slide, symtab, strtab, indirect_symtab);
        }
      }
    }
  }
}

接下来会通过三部分对该代码进行分析:
1、dladdr(header, &info) == 0 会对头进行检测是否合法,这里的头mach-o文件的header部分,先来看下用MachOView查看的可执行文件:

Mach-O

分为三部分:
头部(header structure)
加载命令(load command)
段(segment)

这里的检测就是对header。

2、获取LC结构体的地址

  segment_command_t *cur_seg_cmd;
  segment_command_t *linkedit_segment = NULL;
  struct symtab_command* symtab_cmd = NULL;
  struct dysymtab_command* dysymtab_cmd = NULL;

  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;
    }
  }

这里通过for循环获取Load Commands中的
LC_SEGMENT_64(_LINKEDIT)
LC_SYMTAB
LC_DYSYMTAB
三个结构体在虚拟内存中的地址。

LC_SEGMENT_64(_LINKEDIT) 包含给动态链接器的原始数据的段,包括符号和字符串表,压缩动态链接信息,以及动态符号表等。
LC_SYMTAB 符号表。
LC_DYSYMTAB 表示动态符号表。
在xcode中进行断点调试和MachOView中的结果进行比较:
LC_SEGMENT_64(_LINKEDIT)地址:

linkedit_segment指针
LC_SEGMENT_64(_LINKEDIT)

LC_SYMTAB 符号表地址:

symtab_cmd
LC_SYMTAB

LC_DYSYMTAB 动态符号表地址:

dysymtab_cmd
LC_DYSYMTAB

3、得到延迟加载和非延迟加载的Section

uintptr_t linkedit_base = (uintptr_t)slide + linkedit_segment->vmaddr - linkedit_segment->fileoff;
  nlist_t *symtab = (nlist_t *)(linkedit_base + symtab_cmd->symoff);
  char *strtab = (char *)(linkedit_base + symtab_cmd->stroff);

  // Get indirect symbol table (array of uint32_t indices into symbol table)
  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) {
      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;
        if ((sect->flags & SECTION_TYPE) == S_LAZY_SYMBOL_POINTERS) {
          perform_rebinding_with_section(rebindings, sect, slide, symtab, strtab, indirect_symtab);
        }
        if ((sect->flags & SECTION_TYPE) == S_NON_LAZY_SYMBOL_POINTERS) {
          perform_rebinding_with_section(rebindings, sect, slide, symtab, strtab, indirect_symtab);
        }
      }
    }
  }

symtab 符号表地址,作用是为了寻找函数名称的字符
indirect_symtab 动态符号表地址,作用是为了寻找在函数在字符表中的地址。
strtab 字符标地址,也就是函数名城地址,作用在hook的时候会对字符进行比较。

通过for循环,可以拿到延迟加载和非延迟加载的Section,通过Section中的偏移量,可以找到在indirect_symtab中的地址。

非延迟加载的section
WeChat_1504596261.jpeg

得着Section后,调用perform_rebinding_with_section。
源码如下:

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) {
  uint32_t *indirect_symbol_indices = indirect_symtab + section->reserved1;
  void **indirect_symbol_bindings = (void **)((uintptr_t)slide + section->addr);
  for (uint i = 0; i < section->size / sizeof(void *); i++) {
    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;
    }
    uint32_t strtab_offset = symtab[symtab_index].n_un.n_strx;
    char *symbol_name = strtab + strtab_offset;
    if (strnlen(symbol_name, 2) < 2) {
      continue;
    }
    struct rebindings_entry *cur = rebindings;
    while (cur) {
      for (uint j = 0; j < cur->rebindings_nel; j++) {
        if (strcmp(&symbol_name[1], cur->rebindings[j].name) == 0) {
          if (cur->rebindings[j].replaced != NULL &&
              indirect_symbol_bindings[i] != cur->rebindings[j].replacement) {
            *(cur->rebindings[j].replaced) = indirect_symbol_bindings[i];
          }
          indirect_symbol_bindings[i] = cur->rebindings[j].replacement;
          goto symbol_loop;
        }
      }
      cur = cur->next;
    }
  symbol_loop:;
  }
}

uint32_t *indirect_symbol_indices = indirect_symtab + section->reserved1; 通过Section偏移量得到在动态符号表中的地址。

uint32_t symtab_index = indirect_symbol_indices[i]; 得到在符号表中的偏移量。

uint32_t strtab_offset = symtab[symtab_index].n_un.n_strx;得到函数符号在字符表中的偏移量,从而得到函数字符symbol_name,通过while循环和链表中的每个节点进行函数名称的比较。

while (cur) {
      for (uint j = 0; j < cur->rebindings_nel; j++) {
        if (strcmp(&symbol_name[1], cur->rebindings[j].name) == 0) {
          if (cur->rebindings[j].replaced != NULL &&
              indirect_symbol_bindings[i] != cur->rebindings[j].replacement) {
            *(cur->rebindings[j].replaced) = indirect_symbol_bindings[i];
          }
          indirect_symbol_bindings[i] = cur->rebindings[j].replacement;
          goto symbol_loop;
        }
      }
      cur = cur->next;
    }

如果相同的话,会在具体的函数地址indirect_symbol_bindings中进行替换。indirect_symbol_bindings[i] = cur->rebindings[j].replacement;

*(cur->rebindings[j].replaced) = indirect_symbol_bindings[i];将原来的函数保存。

到此,hook动作就完成了。

结论:
初始化时
myclose的函数地址:
Printing description of reb[0].replacement:
(void *) replacement = 0x00000001000019b0

myopen的函数地址:
Printing description of reb[1].replacement:
(void *) replacement = 0x00000001000019f0

当替换完成后查看虚拟内存地址:

已经hook完成

最后编辑于
©著作权归作者所有,转载或内容合作请联系作者
  • 序言:七十年代末,一起剥皮案震惊了整个滨河市,随后出现的几起案子,更是在滨河造成了极大的恐慌,老刑警刘岩,带你破解...
    沈念sama阅读 194,390评论 5 459
  • 序言:滨河连续发生了三起死亡事件,死亡现场离奇诡异,居然都是意外死亡,警方通过查阅死者的电脑和手机,发现死者居然都...
    沈念sama阅读 81,821评论 2 371
  • 文/潘晓璐 我一进店门,熙熙楼的掌柜王于贵愁眉苦脸地迎上来,“玉大人,你说我怎么就摊上这事。” “怎么了?”我有些...
    开封第一讲书人阅读 141,632评论 0 319
  • 文/不坏的土叔 我叫张陵,是天一观的道长。 经常有香客问我,道长,这世上最难降的妖魔是什么? 我笑而不...
    开封第一讲书人阅读 52,170评论 1 263
  • 正文 为了忘掉前任,我火速办了婚礼,结果婚礼上,老公的妹妹穿的比我还像新娘。我一直安慰自己,他们只是感情好,可当我...
    茶点故事阅读 61,033评论 4 355
  • 文/花漫 我一把揭开白布。 她就那样静静地躺着,像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上,一...
    开封第一讲书人阅读 46,098评论 1 272
  • 那天,我揣着相机与录音,去河边找鬼。 笑死,一个胖子当着我的面吹牛,可吹牛的内容都是我干的。 我是一名探鬼主播,决...
    沈念sama阅读 36,511评论 3 381
  • 文/苍兰香墨 我猛地睁开眼,长吁一口气:“原来是场噩梦啊……” “哼!你这毒妇竟也来了?” 一声冷哼从身侧响起,我...
    开封第一讲书人阅读 35,204评论 0 253
  • 序言:老挝万荣一对情侣失踪,失踪者是张志新(化名)和其女友刘颖,没想到半个月后,有当地人在树林里发现了一具尸体,经...
    沈念sama阅读 39,479评论 1 290
  • 正文 独居荒郊野岭守林人离奇死亡,尸身上长有42处带血的脓包…… 初始之章·张勋 以下内容为张勋视角 年9月15日...
    茶点故事阅读 34,572评论 2 309
  • 正文 我和宋清朗相恋三年,在试婚纱的时候发现自己被绿了。 大学时的朋友给我发了我未婚夫和他白月光在一起吃饭的照片。...
    茶点故事阅读 36,341评论 1 326
  • 序言:一个原本活蹦乱跳的男人离奇死亡,死状恐怖,灵堂内的尸体忽然破棺而出,到底是诈尸还是另有隐情,我是刑警宁泽,带...
    沈念sama阅读 32,213评论 3 312
  • 正文 年R本政府宣布,位于F岛的核电站,受9级特大地震影响,放射性物质发生泄漏。R本人自食恶果不足惜,却给世界环境...
    茶点故事阅读 37,576评论 3 298
  • 文/蒙蒙 一、第九天 我趴在偏房一处隐蔽的房顶上张望。 院中可真热闹,春花似锦、人声如沸。这庄子的主人今日做“春日...
    开封第一讲书人阅读 28,893评论 0 17
  • 文/苍兰香墨 我抬头看了看天上的太阳。三九已至,却和暖如春,着一层夹袄步出监牢的瞬间,已是汗流浃背。 一阵脚步声响...
    开封第一讲书人阅读 30,171评论 1 250
  • 我被黑心中介骗来泰国打工, 没想到刚下飞机就差点儿被人妖公主榨干…… 1. 我叫王不留,地道东北人。 一个月前我还...
    沈念sama阅读 41,486评论 2 341
  • 正文 我出身青楼,却偏偏与公主长得像,于是被迫代替她去往敌国和亲。 传闻我的和亲对象是个残疾皇子,可洞房花烛夜当晚...
    茶点故事阅读 40,676评论 2 335

推荐阅读更多精彩内容

  • 关键时刻,第一时间送达! 问题种类 时间复杂度 在集合里数据量小的情况下时间复杂度对于性能的影响看起来微乎其微。但...
    C9090阅读 863评论 0 1
  • 13. Hook原理介绍 13.1 Objective-C消息传递(Messaging) 对于C/C++这类静态语...
    Flonger阅读 1,392评论 0 3
  • 这是Mach-O系列的第三篇 阅读 FishHook源码之前,你可能需要对以下知识有个简单的了解 Mach-O文件...
    Joy___阅读 7,741评论 9 45
  • 一、温故而知新 1. 内存不够怎么办 内存简单分配策略的问题地址空间不隔离内存使用效率低程序运行的地址不确定 关于...
    SeanCST阅读 7,752评论 0 27
  • 萌芽 两年前,稀里糊涂决定要去新加坡留学。留学是件大事,按理说应该事无巨细将各种因素都考虑在内,而我当时的想法特简...
    我素我素阅读 237评论 0 0