fishhook源码拷贝

Posted 2021-05-19 雨筱逸悠

#ifndef fishhook_h
#define fishhook_h

#include <stddef.h>
#include <stdint.h>

#if !defined(FISHHOOK_EXPORT)
#define FISHHOOK_VISIBILITY __attribute__((visibility("hidden")))
#else
#define FISHHOOK_VISIBILITY __attribute__((visibility("default")))
#endif

#ifdef __cplusplus
extern "C" {
#endif //__cplusplus

/*
 * A structure representing a particular intended rebinding from a symbol
 * name to its replacement
 */
struct rebinding {
  const char *name;
  void *replacement;
  void **replaced;
};

/*
 * For each rebinding in rebindings, rebinds references to external, indirect
 * symbols with the specified name to instead point at replacement for each
 * image in the calling process as well as for all future images that are loaded
 * by the process. If rebind_functions is called more than once, the symbols to
 * rebind are added to the existing list of rebindings, and if a given symbol
 * is rebound more than once, the later rebinding will take precedence.
 */
FISHHOOK_VISIBILITY
int rebind_symbols(struct rebinding rebindings[], size_t rebindings_nel);

/*
 * Rebinds as above, but only in the specified image. The header should point
 * to the mach-o header, the slide should be the slide offset. Others as above.
 */
FISHHOOK_VISIBILITY
int rebind_symbols_image(void *header,
                         intptr_t slide,
                         struct rebinding rebindings[],
                         size_t rebindings_nel);

#ifdef __cplusplus
}
#endif //__cplusplus

#endif //fishhook_h

#include "fishhook.h"

#include <dlfcn.h>
#include <stdbool.h>
#include <stdlib.h>
#include <string.h>
#include <sys/mman.h>
#include <sys/types.h>
#include <mach/mach.h>
#include <mach/vm_map.h>
#include <mach/vm_region.h>
#include <mach-o/dyld.h>
#include <mach-o/loader.h>
#include <mach-o/nlist.h>

#ifdef __LP64__
typedef struct mach_header_64 mach_header_t;
typedef struct segment_command_64 segment_command_t;
typedef struct section_64 section_t;
typedef struct nlist_64 nlist_t;
#define LC_SEGMENT_ARCH_DEPENDENT LC_SEGMENT_64
#else
typedef struct mach_header mach_header_t;
typedef struct segment_command segment_command_t;
typedef struct section section_t;
typedef struct nlist nlist_t;
#define LC_SEGMENT_ARCH_DEPENDENT LC_SEGMENT
#endif

#ifndef SEG_DATA_CONST
#define SEG_DATA_CONST  "__DATA_CONST"
#endif

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

static struct rebindings_entry *_rebindings_head;

// 拷贝记录 rebingdings 设置，保存 _rebindings_head 这个链表中，FILO 更新 链表的 HEAD 指针
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;
}

static vm_prot_t get_protection(void *sectionStart) {
  mach_port_t task = mach_task_self();
  vm_size_t size = 0;
  vm_address_t address = (vm_address_t)sectionStart;
  memory_object_name_t object;
#if __LP64__
  mach_msg_type_number_t count = VM_REGION_BASIC_INFO_COUNT_64;
  vm_region_basic_info_data_64_t info;
  kern_return_t info_ret = vm_region_64(
      task, &address, &size, VM_REGION_BASIC_INFO_64, (vm_region_info_64_t)&info, &count, &object);
#else
  mach_msg_type_number_t count = VM_REGION_BASIC_INFO_COUNT;
  vm_region_basic_info_data_t info;
  kern_return_t info_ret = vm_region(task, &address, &size, VM_REGION_BASIC_INFO, (vm_region_info_t)&info, &count, &object);
#endif
  if (info_ret == KERN_SUCCESS) {
    return info.protection;
  } else {
    return VM_PROT_READ;
  }
}

// 进行绑定操作
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) {
  const bool isDataConst = strcmp(section->segname, SEG_DATA_CONST) == 0;
  uint32_t *indirect_symbol_indices = indirect_symtab + section->reserved1;
  void **indirect_symbol_bindings = (void **)((uintptr_t)slide + section->addr);
  vm_prot_t oldProtection = VM_PROT_READ;
  if (isDataConst) {
    oldProtection = get_protection(rebindings);
    mprotect(indirect_symbol_bindings, section->size, PROT_READ | PROT_WRITE);
  }
  // 遍历所有的函数段找到匹配的函数，替换函数指针
  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;
    bool symbol_name_longer_than_1 = symbol_name[0] && symbol_name[1];
    struct rebindings_entry *cur = rebindings;
    while (cur) {
      for (uint j = 0; j < cur->rebindings_nel; j++) {
        if (symbol_name_longer_than_1 &&
            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:;
  }
  if (isDataConst) {
    int protection = 0;
    if (oldProtection & VM_PROT_READ) {
      protection |= PROT_READ;
    }
    if (oldProtection & VM_PROT_WRITE) {
      protection |= PROT_WRITE;
    }
    if (oldProtection & VM_PROT_EXECUTE) {
      protection |= PROT_EXEC;
    }
    mprotect(indirect_symbol_bindings, section->size, protection);
  }
}

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;

  // 下面方法为找出上面这四个需要使用到的关键值
  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;
        // 找到相关的代码 存放的 段
        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);
        }
      }
    }
  }
}

static void _rebind_symbols_for_image(const struct mach_header *header,
                                      intptr_t slide) {
    rebind_symbols_for_image(_rebindings_head, header, slide);
}

int rebind_symbols_image(void *header,
                         intptr_t slide,
                         struct rebinding rebindings[],
                         size_t rebindings_nel) {
    struct rebindings_entry *rebindings_head = NULL;
    int retval = prepend_rebindings(&rebindings_head, rebindings, rebindings_nel);
    rebind_symbols_for_image(rebindings_head, (const struct mach_header *) header, slide);
    if (rebindings_head) {
      free(rebindings_head->rebindings);
    }
    free(rebindings_head);
    return retval;
}

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) {
    // 这个方法会多次调用并且携带入参和下面的方法结果一致（测试时发现直接只使用下面这个代码也是OK的）
    _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;
}