Android Linker详解

static soinfo* load_library(const char* name) {    //...    ElfReader elf_reader(name, fd);    if (!elf_reader.Load()) {        return NULL;    }     const char* bname = strrchr(name, '/');    soinfo* si = soinfo_alloc(bname ? bname + 1 : name);    if (si == NULL) {        return NULL;    }    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;}

static soinfo* find_library_internal(const char* name) {  //...  si = load_library(name);  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)) {    munmap(reinterpret_cast<void*>(si->base), si->size);    soinfo_free(si);    return NULL;  }   return si;}

static bool soinfo_link_image(soinfo* si) {    //拿到地址、段表指针、段表数    Elf32_Addr base = si->load_bias;    const Elf32_Phdr *phdr = si->phdr;    int phnum = si->phnum;     //...     size_t dynamic_count;    Elf32_Word dynamic_flags;    //这个函数很简单，就是遍历段表，找到类型为PT_DYNAMIC的段    phdr_table_get_dynamic_section(phdr, phnum, base, &si->dynamic,                                   &dynamic_count, &dynamic_flags);    if (si->dynamic == NULL) {        if (!relocating_linker) {            DL_ERR("missing PT_DYNAMIC in "%s"", si->name);        }        return false;    } #ifdef ANDROID_ARM_LINKER    //异常相关，有兴趣的同学可以看看    (void) phdr_table_get_arm_exidx(phdr, phnum, base,                                    &si->ARM_exidx, &si->ARM_exidx_count);#endif    //上面我们解析到了Dynamic段的地址跟数量，下面就开始遍历Dynamic信息    uint32_t needed_count = 0;    //DT_NULL表示结束    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){        case DT_HASH:            //哈希表            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:            //字符串表            si->strtab = (const char *) (base + d->d_un.d_ptr);            break;        case DT_SYMTAB:            //符号表            si->symtab = (Elf32_Sym *) (base + d->d_un.d_ptr);            break;        case DT_PLTREL:            //未处理            if (d->d_un.d_val != DT_REL) {                DL_ERR("unsupported DT_RELA in "%s"", si->name);                return false;            }            break;        case DT_JMPREL:            //PLT重定位表            si->plt_rel = (Elf32_Rel*) (base + d->d_un.d_ptr);            break;        case DT_PLTRELSZ:            //PLT重定位表大小            si->plt_rel_count = d->d_un.d_val / sizeof(Elf32_Rel);            break;        case DT_REL:            //重定位表            si->rel = (Elf32_Rel*) (base + d->d_un.d_ptr);            break;        case DT_RELSZ:            //重定位表大小            si->rel_count = d->d_un.d_val / sizeof(Elf32_Rel);            break;        case DT_PLTGOT:            //GOT全局偏移表，跟PLT延时绑定相关，此处未处理，在Unidbg中也没有处理此项            si->plt_got = (unsigned *)(base + d->d_un.d_ptr);            break;        case DT_DEBUG:            //调试相关, Unidbg未处理，不必理会            if ((dynamic_flags & PF_W) != 0) {                d->d_un.d_val = (int) &_r_debug;            }            break;         case DT_RELA:            //RELA表跟REL表在Unidbg中的处理方案是相同的，这两个值有哪个就用哪个，RELA只是比REL表多了一个adden常量            DL_ERR("unsupported DT_RELA in "%s"", si->name);            return false;        case DT_INIT:            //初始化函数            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:            //析构函数            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:            //init.array 初始化函数列表，后面我们会看到这些初始化函数的调用顺序            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:            //init.array 大小            si->init_array_count = ((unsigned)d->d_un.d_val) / sizeof(Elf32_Addr);            break;        case DT_FINI_ARRAY:            //析构函数列表            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:            //fini.array 大小            si->fini_array_count = ((unsigned)d->d_un.d_val) / sizeof(Elf32_Addr);            break;        case DT_PREINIT_ARRAY:            //也是初始化函数，但是跟init.array不同，这个段大多只出现在可执行文件中，在So中我选择了忽略            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:            //preinit 列表大小            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:            //当前So的依赖            ++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        }    }     //... Sanity checks.     //至此，Dynamic段的信息就解析完毕了，其中想表达的信息也被处理后放到了soinfo中，后面直接就可以拿来用了    // 开辟依赖库的soinfo空间，准备处理依赖    soinfo** needed = (soinfo**) alloca((1 + needed_count) * sizeof(soinfo*));    soinfo** pneeded = needed;    //再次遍历Dynamic段    for (Elf32_Dyn* d = si->dynamic; d->d_tag != DT_NULL; ++d) {        if (d->d_tag == DT_NEEDED) {            //查找DT_NEEDED项            const char* library_name = si->strtab + d->d_un.d_val;            DEBUG("%s needs %s", si->name, library_name);            //进行依赖处理，跟加载so一样的路线，还是已加载直接返回，未加载进行查找加载            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;        }    }    *pneeded = NULL;    //至此依赖库也已经加载完毕     //处理重定位    if (si->plt_rel != NULL) {        DEBUG("[ relocating %s plt ]", si->name );        if (soinfo_relocate(si, si->plt_rel, si->plt_rel_count, needed)) {            return false;        }    }    if (si->rel != NULL) {        DEBUG("[ relocating %s ]", si->name );        if (soinfo_relocate(si, si->rel, si->rel_count, needed)) {            return false;        }    }    //设置soinfo的LINKED标志，表示已进行链接    si->flags |= FLAG_LINKED;    DEBUG("[ finished linking %s ]", si->name);     //...    return true;}

static int soinfo_relocate(soinfo* si, Elf32_Rel* rel, unsigned count,                           soinfo* needed[]){    //拿到符号表和字符串表，定义一些变量    Elf32_Sym* symtab = si->symtab;    const char* strtab = si->strtab;    Elf32_Sym* s;    Elf32_Rel* start = rel;    soinfo* lsi;     //遍历重定位表    for (size_t idx = 0; idx < count; ++idx, ++rel) {        //拿到重定位类型        unsigned type = ELF32_R_TYPE(rel->r_info);        //拿到重定位符号        unsigned sym = ELF32_R_SYM(rel->r_info);        //计算需要重定位的地址        Elf32_Addr reloc = static_cast<Elf32_Addr>(rel->r_offset + si->load_bias);        Elf32_Addr sym_addr = 0;        char* sym_name = NULL;         DEBUG("Processing '%s' relocation at index %d", si->name, idx);        if (type == 0) { // R_*_NONE            continue;        }        if (sym != 0) {            //如果sym不为0，说明重定位需要用到符号，先来找符号，拿到符号名            sym_name = (char *)(strtab + symtab[sym].st_name);            //下面这个函数大家有兴趣的可以看一下，就是根据符号名来从依赖so中查找所需要的符号            s = soinfo_do_lookup(si, sym_name, &lsi, needed);            if (s == NULL) {                //如果没找到，就用本身So的符号                s = &symtab[sym];                if (ELF32_ST_BIND(s->st_info) != STB_WEAK) {                    DL_ERR("cannot locate symbol "%s" referenced by "%s"...", sym_name, si->name);                    return -1;                }                switch (type) {                    //下面是如果符号不为外部符号，就只能为以下几种类型#if defined(ANDROID_ARM_LINKER)                case R_ARM_JUMP_SLOT:                case R_ARM_GLOB_DAT:                case R_ARM_ABS32:                case R_ARM_RELATIVE:    /* Don't care. */#endif /* ANDROID_*_LINKER */                    /* sym_addr was initialized to be zero above or relocation                       code below does not care about value of sym_addr.                       No need to do anything.  */                    break; #if defined(ANDROID_ARM_LINKER)                case R_ARM_COPY:                    /* Fall through.  Can't really copy if weak symbol is                       not found in run-time.  */#endif /* ANDROID_ARM_LINKER */                default:                    DL_ERR("unknown weak reloc type %d @ %p (%d)",                                 type, rel, (int) (rel - start));                    return -1;                }            } else {                //如果我们找到了外部符号，取到外部符号的地址                sym_addr = static_cast<Elf32_Addr>(s->st_value + lsi->load_bias);            }            count_relocation(kRelocSymbol);        } else {            //如果sym为0，就说明当前重定位用不到符号            s = NULL;        }         //下面根据重定位类型来处理重定位        switch(type){#if defined(ANDROID_ARM_LINKER)        case R_ARM_JUMP_SLOT:            count_relocation(kRelocAbsolute);            MARK(rel->r_offset);            TRACE_TYPE(RELO, "RELO JMP_SLOT %08x <- %08x %s", reloc, sym_addr, sym_name);            //直接将需要重定位的地方，写入获取到的符号地址            *reinterpret_cast<Elf32_Addr*>(reloc) = sym_addr;            break;        case R_ARM_GLOB_DAT:            count_relocation(kRelocAbsolute);            MARK(rel->r_offset);            TRACE_TYPE(RELO, "RELO GLOB_DAT %08x <- %08x %s", reloc, sym_addr, sym_name);            //直接将需要重定位的地方，写入获取到的符号地址，与R_ARM_JUMP_SLOT相同            *reinterpret_cast<Elf32_Addr*>(reloc) = sym_addr;            break;        case R_ARM_ABS32:            count_relocation(kRelocAbsolute);            MARK(rel->r_offset);            TRACE_TYPE(RELO, "RELO ABS %08x <- %08x %s", reloc, sym_addr, sym_name);            //先读出需要重定位地方的数据，将其和符号地址相加，写入需要重定位的地方            *reinterpret_cast<Elf32_Addr*>(reloc) += sym_addr;            break;        case R_ARM_REL32:            count_relocation(kRelocRelative);            MARK(rel->r_offset);            TRACE_TYPE(RELO, "RELO REL32 %08x <- %08x - %08x %s",                       reloc, sym_addr, rel->r_offset, sym_name);            //先读出需要重定位地方的数据，将其和符号地址相加，再与重定位的地址相减，重定位的写入需要重定位的地方。此处Unidbg并未处理，也可忽略，应该是用不到的            *reinterpret_cast<Elf32_Addr*>(reloc) += sym_addr - rel->r_offset;            break;#endif /* ANDROID_*_LINKER */ #if defined(ANDROID_ARM_LINKER)        case R_ARM_RELATIVE:#endif /* ANDROID_*_LINKER */            count_relocation(kRelocRelative);            MARK(rel->r_offset);            if (sym) {                DL_ERR("odd RELATIVE form...");                return -1;            }            TRACE_TYPE(RELO, "RELO RELATIVE %08x <- +%08x", reloc, si->base);            //先读出需要重定位地方的数据，将其和So的基址相加，写入需要重定位的地方            *reinterpret_cast<Elf32_Addr*>(reloc) += si->base;            break; #ifdef ANDROID_ARM_LINKER        case R_ARM_COPY:            //.. 进行了一些错误处理            break;#endif /* ANDROID_ARM_LINKER */         default:            DL_ERR("unknown reloc type %d @ %p (%d)",                   type, rel, (int) (rel - start));            return -1;        }    }    return 0;}

soinfo* do_dlopen(const char* name, int flags) {  if ((flags & ~(RTLD_NOW|RTLD_LAZY|RTLD_LOCAL|RTLD_GLOBAL)) != 0) {    DL_ERR("invalid flags to dlopen: %x", flags);    return NULL;  }  set_soinfo_pool_protection(PROT_READ | PROT_WRITE);  soinfo* si = find_library(name);  if (si != NULL) {    si->CallConstructors();  }  set_soinfo_pool_protection(PROT_READ);  return si;}

void soinfo::CallConstructors() {  if (constructors_called) {    return;  }  constructors_called = true;   if ((flags & FLAG_EXE) == 0 && preinit_array != NULL) {    // The GNU dynamic linker silently ignores these, but we warn the developer.    PRINT(""%s": ignoring %d-entry DT_PREINIT_ARRAY in shared library!",          name, preinit_array_count);  }   //如果Dynamic段不为空，先处理依赖库的初始化  if (dynamic != NULL) {    for (Elf32_Dyn* d = dynamic; d->d_tag != DT_NULL; ++d) {      if (d->d_tag == DT_NEEDED) {        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();      }    }  }  TRACE(""%s": calling constructors", name);  //我们来看下面一句英文注释，非常重要。他说如果DT_INIT和DT_INIT_ARRAY都存在，DT_INIT应该在DT_INIT_ARRAY之前被调用  // DT_INIT should be called before DT_INIT_ARRAY if both are present.  //下面就是在调用两者，CallArray只是在循环调用CallFunction，我们看一下CallFunction  CallFunction("DT_INIT", init_func);  CallArray("DT_INIT_ARRAY", init_array, init_array_count, false);}

void soinfo::CallFunction(const char* function_name UNUSED, linker_function_t function) {  if (function == NULL || reinterpret_cast<uintptr_t>(function) == static_cast<uintptr_t>(-1)) {    return;  }   TRACE("[ Calling %s @ %p for '%s' ]", function_name, function, name);  //在这里被调用了，其他没啥好说的  function();  TRACE("[ Done calling %s @ %p for '%s' ]", function_name, function, name);   // The function may have called dlopen(3) or dlclose(3), so we need to ensure our data structures  // are still writable. This happens with our debug malloc (see http://b/7941716).  set_soinfo_pool_protection(PROT_READ | PROT_WRITE);}

if (elfFile.file_type == ElfFile.FT_DYN) { // not executable    int init = dynamicStructure.getInit();    if (init != 0) {        initFunctionList.add(new LinuxInitFunction(load_base, soName, init));        //new LinuxInitFunction(load_base, soName, init).call(emulator);    }     int initArraySize = dynamicStructure.getInitArraySize();    int count = initArraySize / emulator.getPointerSize();    if (count > 0) {        Pointer pointer = UnidbgPointer.pointer(emulator, load_base + dynamicStructure.getInitArrayOffset());        if (pointer == null) {            throw new IllegalStateException("DT_INIT_ARRAY is null");        }        for (int i = 0; i < count; i++) {            Pointer func = pointer.getPointer((long) i * emulator.getPointerSize());            if (func != null) {                initFunctionList.add(new AbsoluteInitFunction(load_base, soName, ((UnidbgPointer) func).peer));            }        }    }}