1. 程式人生 > >linker原始碼解析,脫殼點,在分析過程中產生的反除錯思路

linker原始碼解析,脫殼點,在分析過程中產生的反除錯思路

前言
linker是Android系統動態庫so的載入器和連結器,也是Android脫殼一重要脫殼點,這裡介紹一下此部分的Android原始碼,並介紹幾個脫殼點,及分析過程中產生的反除錯手段,學習Linker的載入和啟動原理,又需要介紹so的載入和啟動。
系統 :Android4.4-r1
linker原始碼的位置 : Android/bionic/linker

0x00 載入與啟動so

1、Java層中宣告載入某個so檔案以共享,則可在Java層宣告程式碼:

static{
    System.loadLibrary("libhello.so")
}

其對應的執行流程如下:
1、 定位到檔案Dalvik/vm/native/java_lang_Runtime.cpp
2、 呼叫Dalvik_java_lang_Runtime_nativeLoad -> Dalvik/vm/Native.cpp:dvmLoadNativeCode
具體程式碼如下,我略過一些錯誤判斷程式碼,這段程式碼以/* 說明 *

/的形式省略

bool dvmLoadNativeCode(const char* pathName, Object* classLoader,
        char** detail)
{
    SharedLib* pEntry;
    void* handle;
    bool verbose;

    /*********根據path查詢so檔案**********/
    pEntry = findSharedLibEntry(pathName);

    /*********載入指定so檔案,並延遲載入*******/
    handle = dlopen(pathName, RTLD_LAZY);
    dvmChangeStatus(self, oldStatus);

    /* create a new entry */
SharedLib* pNewEntry; /*.......*/ /* try to add it to the list */ /***當執行addShareLibEntry()方法的時候,如果還有執行緒B同時在載入該so,***/ /***並且B執行緒先執行到了這裡,那麼就說明該so的資訊已經新增過了,我們就不需要再執行新增pNewEntry的操作***/ SharedLib* pActualEntry = addSharedLibEntry(pNewEntry); if (pNewEntry != pActualEntry) { ALOGI("WOW: we lost a race to add a shared lib (%s CL=%p)"
, pathName, classLoader); freeSharedLibEntry(pNewEntry); return checkOnLoadResult(pActualEntry); } else { if (verbose) ALOGD("Added shared lib %s %p", pathName, classLoader); bool result = false; void* vonLoad; int version; /***定位JNI_OnLoad()方法***/ vonLoad = dlsym(handle, "JNI_OnLoad");// /***如果找不到則延遲載入,說明是用javah風格的程式碼**/ if (vonLoad == NULL) { ALOGD("No JNI_OnLoad found in %s %p, skipping init", pathName, classLoader); result = true; } else { /* * Call JNI_OnLoad. We have to override the current class * loader, which will always be "null" since the stuff at the * top of the stack is around Runtime.loadLibrary(). (See * the comments in the JNI FindClass function.) */ /***這裡省略了重寫相應類載入器的程式碼,如上面雞腸文所示功能,不重要**/ /***gDvm是一個全域性變數,功能後面再補***/ if (gDvm.verboseJni) { ALOGI("[Calling JNI_OnLoad for \"%s\"]", pathName); } /***執行JNI_OnLoad***/ version = (*func)(gDvmJni.jniVm, NULL); /***省略一大段程式碼。。。***/ dvmUnlockMutex(&pNewEntry->onLoadLock); return result; } }

從上面的程式碼我們可看出
1、Android系統載入so檔案時使用了dlopen函式;
2、定位JNI_OnLoad()方法,則dlsym(handle, “JNI_OnLoad”);
3、執行JNI_OnLoad()方法:(*func)(gDvmJni.jniVm, NULL)
我們查詢載入so檔案的函式dlopen在bionic/linker/dlfcn.c中,而此函式有主要呼叫了do_dlopen函式,這裡對dlopen函式不詳細贅述,主要解析一下do_dlopen函式,而此關鍵函式正是在Linker中。接下來詳細分析Linker原始碼。

0x01 Linker原始碼總覽

這裡寫圖片描述

0x02 do_dlopen

先貼上程式碼:

soinfo* si = find_library(name);//**完成so的載入到記憶體的工作
  if (si != NULL) {
    si->CallConstructors();//**完成so及本身的建構函式的呼叫。完成so檔案的載入
  }

嗯,註釋簡單明瞭,接下來解析find_library(name)與si->CallConstructors()。

0x03 續0 find_library

作用:完成so的載入到記憶體的工作,成為是否載入過該so的重要依據

static soinfo* find_library(const char* name) {//成為是否載入過該so的重要依據
  soinfo* si = find_library_internal(name);//尋找相應的so資訊
  if (si != NULL) {
    si->ref_count++;
  }
  return si;

嗯,還是很清晰,裡面的呼叫的方法先放下先,我們現分析如下方法。

0x04 si->CallConstructors()

完成so及本身的建構函式的呼叫。完成so檔案的載入

/***省略一大堆程式碼,下面是主要函式****/
 if (dynamic != NULL) {
    for (Elf32_Dyn* d = dynamic; d->d_tag != DT_NULL; ++d) {
      if (d->d_tag == DT_NEEDED) {//調動依賴庫的建構函式
        const char* library_name = strtab + d->d_un.d_val;
        TRACE("\"%s\": calling constructors in DT_NEEDED \"%s\"", name, library_name);
        find_loaded_library(library_name)->CallConstructors();
      }
       // DT_INIT should be called before DT_INIT_ARRAY if both are present.
  TRACE("\"%s\": calling constructors", name);
  CallFunction("DT_INIT", init_func);//呼叫自己的一系列建構函式後返回,這裡是so檔案加殼的脫殼點
  CallArray("DT_INIT_ARRAY", init_array, init_array_count, false);//dex檔案的脫殼點

這主要是完成so檔案的載入,然後遍歷所有動態節,再根據標籤d_tag ==DT_NEEDED呼叫依賴庫的建構函式,再呼叫自己的一系列建構函式,以及init_arry函式,其中後面兩個函式分別是so檔案和dex檔案的脫殼點,這樣就結束了so檔案的載入,但分析遠遠沒有結束,我們需要回過頭來解析find_library方法。

0x05 find_library 之find_library_internal()

操作:尋找相應的so資訊

static soinfo* find_library_internal(const char* name) {
  if (name == NULL) {
    return somain;
  }

  soinfo* si = find_loaded_library(name);
  if (si != NULL) {
    if (si->flags & FLAG_LINKED) {
      return si;
    }
    DL_ERR("OOPS: recursive link to \"%s\"", si->name);
    return NULL;
  }

  TRACE("[ '%s' has not been loaded yet.  Locating...]", name);
  si = load_library(name);//真正載入so檔案的函式
  if (si == NULL) {
    return NULL;
  }

  // At this point we know that whatever is loaded @ base is a valid ELF
  // shared library whose segments are properly mapped in.
  TRACE("[ init_library base=0x%08x sz=0x%08x name='%s' ]",
        si->base, si->size, si->name);

  if (!soinfo_link_image(si)) {//進行重定位
    munmap(reinterpret_cast<void*>(si->base), si->size);
    soinfo_free(si);
    return NULL;
  }

註釋很明白,整理一下基本流程:
1、find_loaded_library():尋找相應的so資訊
2、load_library():真正載入so檔案的函式
3、soinfo_link_image():處理動態節dynamic section,初始化動態節dynamic section的屬性

0x06 find_library_internal() 之 find_loaded_library()

//尋找相應的so資訊 
 static soinfo *find_loaded_library(const char *name)
{
    soinfo *si;
    const char *bname;

    // TODO: don't use basename only for determining libraries
    // http://code.google.com/p/android/issues/detail?id=6670

    bname = strrchr(name, '/');//查詢一個字元"/"在另一個字串name中末次出現的位置並返回這個位置的地址
    bname = bname ? bname + 1 : name;

    for (si = solist; si != NULL; si = si->next) {//判斷是否有載入這個so
        if (!strcmp(bname, si->name)) {
            return si;
        }
    }
    return NULL;
}

0x07 find_library_internal() 之load_library()

操作:真正載入so檔案的函式

static soinfo* load_library(const char* name) {
    // Open the file.
    int fd = open_library(name);
    if (fd == -1) {
        DL_ERR("library \"%s\" not found", name);
        return NULL;
    }

    // Read the ELF header and load the segments.
    ElfReader elf_reader(name, fd);
    if (!elf_reader.Load()) {//讀取elf的操作,原始碼中看出只讀取了Program 段
        return NULL;
    }
     const char* bname = strrchr(name, '/');
     //在so檔案載入完以後,接著就會呼叫soinfo_alloc函式為so分配soinfo
    soinfo* si = soinfo_alloc(bname ? bname + 1 : name);
    if (si == NULL) {
        return NULL;
    }//利用裝載結果初始化soinfo物件
    si->base = elf_reader.load_start();
    si->size = elf_reader.load_size();
    si->load_bias = elf_reader.load_bias();
    si->flags = 0;
    si->entry = 0;
    si->dynamic = NULL;
    si->phnum = elf_reader.phdr_count();
    si->phdr = elf_reader.loaded_phdr();
    return si;
}

這裡著重強調一下elf_reader.Load()方法:

bool ElfReader::Load() {
  return ReadElfHeader() &&
         VerifyElfHeader() &&
         ReadProgramHeader() &&
         ReserveAddressSpace() &&
         LoadSegments() &&
         FindPhdr();
}

可以看出讀取elf的操作,原始碼中看出只讀取了Program 段,這也是很多加固進行抹頭操作的原因:IDA只通過載入section Header段,來讀取so檔案,而實際上原始碼只讀取了Program段,如果只是將section Header段抹頭了,IDA便無法正常解析so檔案,而Android系統卻可以正常解析so檔案,這也是一種反除錯手段。
再後來就進行一系列對so檔案的初始化操作:

si->base = elf_reader.load_start();
    si->size = elf_reader.load_size();
    si->load_bias = elf_reader.load_bias();
    si->flags = 0;
    si->entry = 0;
    si->dynamic = NULL;
    si->phnum = elf_reader.phdr_count();
    si->phdr = elf_reader.loaded_phdr();
    return si;

其中si結構體如下(可略):

struct soinfo {
 public:
  char name[SOINFO_NAME_LEN];
  const Elf32_Phdr* phdr;
  size_t phnum;
  Elf32_Addr entry;
  Elf32_Addr base;
  unsigned size;

  uint32_t unused1;  // DO NOT USE, maintained for compatibility.

  Elf32_Dyn* dynamic;

  uint32_t unused2; // DO NOT USE, maintained for compatibility
  uint32_t unused3; // DO NOT USE, maintained for compatibility

  soinfo* next;
  unsigned flags;

  const char* strtab;
  Elf32_Sym* symtab;

  size_t nbucket;
  size_t nchain;
  unsigned* bucket;
  unsigned* chain;

  unsigned* plt_got;

  Elf32_Rel* plt_rel;
  size_t plt_rel_count;

  Elf32_Rel* rel;
  size_t rel_count;

  linker_function_t* preinit_array;
  size_t preinit_array_count;

  linker_function_t* init_array;
  size_t init_array_count;
  linker_function_t* fini_array;
  size_t fini_array_count;

  linker_function_t init_func;
  linker_function_t fini_func;

#if defined(ANDROID_ARM_LINKER)
  // ARM EABI section used for stack unwinding.
  unsigned* ARM_exidx;
  size_t ARM_exidx_count;
#elif defined(ANDROID_MIPS_LINKER)
  unsigned mips_symtabno;
  unsigned mips_local_gotno;
  unsigned mips_gotsym;
#endif

  size_t ref_count;
  link_map_t link_map;

  bool constructors_called;

  // When you read a virtual address from the ELF file, add this
  // value to get the corresponding address in the process' address space.
  Elf32_Addr load_bias;

  bool has_text_relocations;
  bool has_DT_SYMBOLIC;

  void CallConstructors();
  void CallDestructors();
  void CallPreInitConstructors();

 private:
  void CallArray(const char* array_name, linker_function_t* functions, size_t count, bool reverse);//dex檔案脫殼點
  void CallFunction(const char* function_name, linker_function_t function);//so檔案脫殼點
};

0x07 find_library_internal() 之soinfo_link_image(si)

這一部分參考了雪一夢師傅的分析,並作了一些補充:
http://blog.csdn.net/feibabeibei_beibei/article/details/53004525
在si = load_library(name)獲得了so檔案的info之後,就開始進行一系列操作:
1、定位動態節;
2、解析動態節;
3、載入動態節
4、重定位

1、定位動態節:

phdr_table_get_dynamic_section(const Elf32_Phdr* phdr_table,
                               int               phdr_count,
                               Elf32_Addr        load_bias,
                               Elf32_Dyn**       dynamic,
                               size_t*           dynamic_count,
                               Elf32_Word*       dynamic_flags)
{
    const Elf32_Phdr* phdr = phdr_table;
    const Elf32_Phdr* phdr_limit = phdr + phdr_count;

    for (phdr = phdr_table; phdr < phdr_limit; phdr++) {
        if (phdr->p_type != PT_DYNAMIC) {//遍歷phdr尋找DYNAMIC段,存放了字串,方法等偏移地址
            continue;
        }

        *dynamic = reinterpret_cast<Elf32_Dyn*>(load_bias + phdr->p_vaddr);
        if (dynamic_count) {
            *dynamic_count = (unsigned)(phdr->p_memsz / 8);
        }
        if (dynamic_flags) {
            *dynamic_flags = phdr->p_flags;
        }
        return;
    }
    *dynamic = NULL;
    if (dynamic_count) {
        *dynamic_count = 0;
    }
}

值得注意的是,這裡原始碼載入動態節的時候只加載了第一個動態節,後面的動態節都沒有載入,因此我們可以自己自定義多個programm段中的動態節區,然後在section header中也改變相應的資料,這樣IDA解析的資訊是有所偏差的,因為Android系統實際上只讀取了第一個動態節。
2、解析動態節。
解析程式碼如下:

for (Elf32_Dyn* d = si->dynamic; d->d_tag != DT_NULL; ++d) {
        DEBUG("d = %p, d[0](tag) = 0x%08x d[1](val) = 0x%08x", d, d->d_tag, d->d_un.d_val);
        switch(d->d_tag){/初始化動態節dynamic section的屬性
        case DT_HASH:
            si->nbucket = ((unsigned *) (base + d->d_un.d_ptr))[0];
            si->nchain = ((unsigned *) (base + d->d_un.d_ptr))[1];
            si->bucket = (unsigned *) (base + d->d_un.d_ptr + 8);
            si->chain = (unsigned *) (base + d->d_un.d_ptr + 8 + si->nbucket * 4);
            break;
        case DT_STRTAB:
            si->strtab = (const char *) (base + d->d_un.d_ptr);
            break;
        case DT_SYMTAB:
            si->symtab = (Elf32_Sym *) (base + d->d_un.d_ptr);
            break;
        case DT_PLTREL:
            if (d->d_un.d_val != DT_REL) {
                DL_ERR("unsupported DT_RELA in \"%s\"", si->name);
                return false;
            }
            break;
        case DT_JMPREL:
            si->plt_rel = (Elf32_Rel*) (base + d->d_un.d_ptr);
            break;
        case DT_PLTRELSZ:
            si->plt_rel_count = d->d_un.d_val / sizeof(Elf32_Rel);
            break;
        case DT_REL:
            si->rel = (Elf32_Rel*) (base + d->d_un.d_ptr);
            break;
        case DT_RELSZ:
            si->rel_count = d->d_un.d_val / sizeof(Elf32_Rel);
            break;
        case DT_PLTGOT:
            /* Save this in case we decide to do lazy binding. We don't yet. */
            si->plt_got = (unsigned *)(base + d->d_un.d_ptr);
            break;
        case DT_DEBUG:
            // Set the DT_DEBUG entry to the address of _r_debug for GDB
            // if the dynamic table is writable
            if ((dynamic_flags & PF_W) != 0) {
                d->d_un.d_val = (int) &_r_debug;
            }
            break;
         case DT_RELA:
            DL_ERR("unsupported DT_RELA in \"%s\"", si->name);
            return false;
        case DT_INIT:
            si->init_func = reinterpret_cast<linker_function_t>(base + d->d_un.d_ptr);
            DEBUG("%s constructors (DT_INIT) found at %p", si->name, si->init_func);
            break;
        case DT_FINI:
            si->fini_func = reinterpret_cast<linker_function_t>(base + d->d_un.d_ptr);
            DEBUG("%s destructors (DT_FINI) found at %p", si->name, si->fini_func);
            break;
        case DT_INIT_ARRAY:
            si->init_array = reinterpret_cast<linker_function_t*>(base + d->d_un.d_ptr);
            DEBUG("%s constructors (DT_INIT_ARRAY) found at %p", si->name, si->init_array);
            break;
        case DT_INIT_ARRAYSZ:
            si->init_array_count = ((unsigned)d->d_un.d_val) / sizeof(Elf32_Addr);
            break;
        case DT_FINI_ARRAY:
            si->fini_array = reinterpret_cast<linker_function_t*>(base + d->d_un.d_ptr);
            DEBUG("%s destructors (DT_FINI_ARRAY) found at %p", si->name, si->fini_array);
            break;
        case DT_FINI_ARRAYSZ:
            si->fini_array_count = ((unsigned)d->d_un.d_val) / sizeof(Elf32_Addr);
            break;
        case DT_PREINIT_ARRAY:
            si->preinit_array = reinterpret_cast<linker_function_t*>(base + d->d_un.d_ptr);
            DEBUG("%s constructors (DT_PREINIT_ARRAY) found at %p", si->name, si->preinit_array);
            break;
        case DT_PREINIT_ARRAYSZ:
            si->preinit_array_count = ((unsigned)d->d_un.d_val) / sizeof(Elf32_Addr);
            break;
        case DT_TEXTREL:
            si->has_text_relocations = true;
            break;
        case DT_SYMBOLIC:
            si->has_DT_SYMBOLIC = true;
            break;
        case DT_NEEDED:
            ++needed_count;
            break;
#if defined DT_FLAGS
        // TODO: why is DT_FLAGS not defined?
        case DT_FLAGS:
            if (d->d_un.d_val & DF_TEXTREL) {
                si->has_text_relocations = true;
            }
            if (d->d_un.d_val & DF_SYMBOLIC) {
                si->has_DT_SYMBOLIC = true;
            }
            break;
#endif
#if defined(ANDROID_MIPS_LINKER)
        case DT_STRSZ:
        case DT_SYMENT:
        case DT_RELENT:
             break;
        case DT_MIPS_RLD_MAP:
            // Set the DT_MIPS_RLD_MAP entry to the address of _r_debug for GDB.
            {
              r_debug** dp = (r_debug**) d->d_un.d_ptr;
              *dp = &_r_debug;
            }
            break;
        case DT_MIPS_RLD_VERSION:
        case DT_MIPS_FLAGS:
        case DT_MIPS_BASE_ADDRESS:
        case DT_MIPS_UNREFEXTNO:
            break;

        case DT_MIPS_SYMTABNO:
            si->mips_symtabno = d->d_un.d_val;
            break;

        case DT_MIPS_LOCAL_GOTNO:
            si->mips_local_gotno = d->d_un.d_val;
            break;

        case DT_MIPS_GOTSYM:
            si->mips_gotsym = d->d_un.d_val;
            break;

        default:
            DEBUG("Unused DT entry: type 0x%08x arg 0x%08x", d->d_tag, d->d_un.d_val);
            break;
#endif
        }
    }

3、載入依賴庫

 //********載入依賴庫 (NEEDED)       Shared library: [liblog.so]
    for (Elf32_Dyn* d = si->dynamic; d->d_tag != DT_NULL; ++d) {
        if (d->d_tag == DT_NEEDED) {
            const char* library_name = si->strtab + d->d_un.d_val;
            DEBUG("%s needs %s", si->name, library_name);
            soinfo* lsi = find_library(library_name);
            if (lsi == NULL) {
                strlcpy(tmp_err_buf, linker_get_error_buffer(), sizeof(tmp_err_buf));
                DL_ERR("could not load library \"%s\" needed by \"%s\"; caused by %s",
                       library_name, si->name, tmp_err_buf);
                return false;
            }
            *pneeded++ = lsi;
        }
    }

4、重定位操作

if (si->has_text_relocations) {//重定位操作
        /* Unprotect the segments, i.e. make them writable, to allow
         * text relocations to work properly. We will later call
         * phdr_table_protect_segments() after all of them are applied
         * and all constructors are run.
         */
        DL_WARN("%s has text relocations. This is wasting memory and is "
                "a security risk. Please fix.", si->name);
        if (phdr_table_unprotect_segments(si->phdr, si->phnum, si->load_bias) < 0) {
            DL_ERR("can't unprotect loadable segments for \"%s\": %s",
                   si->name, strerror(errno));
            return false;
        }
    }

    if (si->plt_rel != NULL) {//修改資料達到重定位的目的
        DEBUG("[ relocating %s plt ]", si->name );
        if (soinfo_relocate(si, si->plt_rel, si->plt_rel_count, needed)) {
            return false;//修改資料達到重定位的目的
        }
    }
    if (si->rel != NULL) {
        DEBUG("[ relocating %s ]", si->name );
        if (soinfo_relocate(si, si->rel, si->rel_count, needed)) {
            return false;
        }
    }

0xFF 收尾

1、dlopen執行完畢後
2、呼叫 vonLoad = dlsym(handle, “JNI_OnLoad”)定位JNI_Onload
3、再執行version = (*func)(gDvmJni.jniVm, NULL);執行JNI_Onload
期間可以有三個斷點:
.init->.init_array->JNI_Onload->java_com_XX.
反除錯思路:
1、section Header的抹頭操作
2、自定義多個動態節