Android函數抽取殼的實現
0x0 前言
函數抽取殼這個詞不知道從哪起源的,但我理解的函數抽取殼是那種將dex文件中的函數代碼給nop,然後在運行時再把位元組碼給填回dex的這麼一種殼。
函數抽取前:
函數抽取後:
很早之前就想寫這類的殼,最近終於把它做出來了,取名為dpt。現在將代碼分享出來,歡迎把玩。項目地址://github.com/luoyesiqiu/dpt-shell
0x1 項目的結構
dpt代碼分為兩個部分,一個是proccessor,另一個是shell。
proccessor是可以將普通apk處理成加殼apk的模塊。它的主要功能有:
-
解壓apk
-
提取apk中的dex的codeitem保存起來
-
修改Androidmanifest.xml中的Application類名
-
生成新的apk
流程如下:
shell模塊最終生成的dex文件和so文件將被集成到需要加殼的apk中。它的要功能有:
-
處理App的啟動
-
替換dexElements
-
hook相關函數
-
調用目標Application
-
codeitem文件讀取
-
codeitem填回
流程如下:
0x2 proccessor
proccessor比較重要的邏輯兩點,AndroidManiest.xml的處理和Codeitem的提取
(1)處理Androidmanifest.xml
我們處理AndroidManifest.xml的操作主要是備份原Application的類名和寫入殼的代理Application的類名。備份原Application類名目的是在殼的流程執行完成後,調用我們原APK的Application。寫入殼的代理Application類名的目的是在app啟動時儘早的啟動我們的代理Application,這樣我們就可以做一些準備工作,比如自定義加載dex,Hook一些函數等。我們知道,AndroidManifest.xml在生成apk後它不是以普通xml文件的格式來存放的,而是以axml格式來存放的。不過幸運的是,已經有許多大佬寫了對axml解析和編輯的庫,我們直接拿來用就行。這裡用到的axml處理的庫是ManifestEditor。
提取原Androidmanifest.xml Application完整類名代碼如下,直接調用getApplicationName函數即可
public static String getValue(String file,String tag,String ns,String attrName){
byte[] axmlData = IoUtils.readFile(file);
AxmlParser axmlParser = new AxmlParser(axmlData);
try {
while (axmlParser.next() != AxmlParser.END_FILE) {
if (axmlParser.getAttrCount() != 0 && !axmlParser.getName().equals(tag)) {
continue;
}
for (int i = 0; i < axmlParser.getAttrCount(); i++) {
if (axmlParser.getNamespacePrefix().equals(ns) && axmlParser.getAttrName(i).equals(attrName)) {
return (String) axmlParser.getAttrValue(i);
}
}
}
} catch (Exception e) {
e.printStackTrace();
}
return null;
}
public static String getApplicationName(String file) {
return getValue(file,"application","android","name");
}
寫入Application類名的代碼如下:
public static void writeApplicationName(String inManifestFile, String outManifestFile, String newApplicationName){
ModificationProperty property = new ModificationProperty();
property.addApplicationAttribute(new AttributeItem(NodeValue.Application.NAME,newApplicationName));
FileProcesser.processManifestFile(inManifestFile, outManifestFile, property);
}
(2) 提取CodeItem
CodeItem是dex文件中存放函數位元組碼相關數據的結構。下圖顯示的就是CodeItem大概的樣子。
說是提取CodeItem,其實我們提取的是CodeItem中的insns,它裏面存放的是函數真正的位元組碼。提取insns,我們使用的是Android源碼中的dx工具,使用dx工具可以很方便的讀取dex文件的各個部分。
下面的代碼遍歷所有ClassDef,並遍歷其中的所有函數,再調用extractMethod對單個函數進行處理。
public static List<Instruction> extractAllMethods(File dexFile, File outDexFile) {
List<Instruction> instructionList = new ArrayList<>();
Dex dex = null;
RandomAccessFile randomAccessFile = null;
byte[] dexData = IoUtils.readFile(dexFile.getAbsolutePath());
IoUtils.writeFile(outDexFile.getAbsolutePath(),dexData);
try {
dex = new Dex(dexFile);
randomAccessFile = new RandomAccessFile(outDexFile, "rw");
Iterable<ClassDef> classDefs = dex.classDefs();
for (ClassDef classDef : classDefs) {
......
if(classDef.getClassDataOffset() == 0){
String log = String.format("class '%s' data offset is zero",classDef.toString());
logger.warn(log);
continue;
}
ClassData classData = dex.readClassData(classDef);
ClassData.Method[] directMethods = classData.getDirectMethods();
ClassData.Method[] virtualMethods = classData.getVirtualMethods();
for (ClassData.Method method : directMethods) {
Instruction instruction = extractMethod(dex,randomAccessFile,classDef,method);
if(instruction != null) {
instructionList.add(instruction);
}
}
for (ClassData.Method method : virtualMethods) {
Instruction instruction = extractMethod(dex, randomAccessFile,classDef, method);
if(instruction != null) {
instructionList.add(instruction);
}
}
}
}
catch (Exception e){
e.printStackTrace();
}
finally {
IoUtils.close(randomAccessFile);
}
return instructionList;
}
處理函數的過程中發現沒有代碼(通常為native函數)或者insns的容量不足以填充return語句則跳過處理。這裡就是對應函數抽取殼的抽取操作
private static Instruction extractMethod(Dex dex ,RandomAccessFile outRandomAccessFile,ClassDef classDef,ClassData.Method method)
throws Exception{
String returnTypeName = dex.typeNames().get(dex.protoIds().get(dex.methodIds().get(method.getMethodIndex()).getProtoIndex()).getReturnTypeIndex());
String methodName = dex.strings().get(dex.methodIds().get(method.getMethodIndex()).getNameIndex());
String className = dex.typeNames().get(classDef.getTypeIndex());
//native函數
if(method.getCodeOffset() == 0){
String log = String.format("method code offset is zero,name = %s.%s , returnType = %s",
TypeUtils.getHumanizeTypeName(className),
methodName,
TypeUtils.getHumanizeTypeName(returnTypeName));
logger.warn(log);
return null;
}
Instruction instruction = new Instruction();
//16 = registers_size + ins_size + outs_size + tries_size + debug_info_off + insns_size
int insnsOffset = method.getCodeOffset() + 16;
Code code = dex.readCode(method);
//容錯處理
if(code.getInstructions().length == 0){
String log = String.format("method has no code,name = %s.%s , returnType = %s",
TypeUtils.getHumanizeTypeName(className),
methodName,
TypeUtils.getHumanizeTypeName(returnTypeName));
logger.warn(log);
return null;
}
int insnsCapacity = code.getInstructions().length;
//insns容量不足以存放return語句,跳過
byte[] returnByteCodes = getReturnByteCodes(returnTypeName);
if(insnsCapacity * 2 < returnByteCodes.length){
logger.warn("The capacity of insns is not enough to store the return statement. {}.{}() -> {} insnsCapacity = {}byte(s),returnByteCodes = {}byte(s)",
TypeUtils.getHumanizeTypeName(className),
methodName,
TypeUtils.getHumanizeTypeName(returnTypeName),
insnsCapacity * 2,
returnByteCodes.length);
return null;
}
instruction.setOffsetOfDex(insnsOffset);
//這裡的MethodIndex對應method_ids區的索引
instruction.setMethodIndex(method.getMethodIndex());
//注意:這裡是數組的大小
instruction.setInstructionDataSize(insnsCapacity * 2);
byte[] byteCode = new byte[insnsCapacity * 2];
//寫入nop指令
for (int i = 0; i < insnsCapacity; i++) {
outRandomAccessFile.seek(insnsOffset + (i * 2));
byteCode[i * 2] = outRandomAccessFile.readByte();
byteCode[i * 2 + 1] = outRandomAccessFile.readByte();
outRandomAccessFile.seek(insnsOffset + (i * 2));
outRandomAccessFile.writeShort(0);
}
instruction.setInstructionsData(byteCode);
outRandomAccessFile.seek(insnsOffset);
//寫出return語句
outRandomAccessFile.write(returnByteCodes);
return instruction;
}
0x3 shell模塊
shell模塊是函數抽取殼的主要邏輯,它的功能我們上面已經講過。
(1) Hook函數
Hook函數時機最好要早點,dpt在_init
函數中開始進行一系列HOOK
extern "C" void _init(void) {
dpt_hook();
}
Hook框架使用的Dobby,主要Hook兩個函數:MapFileAtAddress和LoadMethod。
Hook MapFileAtAddress函數的目的是在我們加載dex能夠修改dex的屬性,讓加載的dex可寫,這樣我們才能把位元組碼填回dex,有大佬詳細的分析過,具體參考這篇文章。
void* MapFileAtAddressAddr = DobbySymbolResolver(GetArtLibPath(),MapFileAtAddress_Sym());
DobbyHook(MapFileAtAddressAddr, (void *) MapFileAtAddress28,(void **) &g_originMapFileAtAddress28);
Hook到了之後,給prot參數追加PROT_WRITE屬性
void* MapFileAtAddress28(uint8_t* expected_ptr,
size_t byte_count,
int prot,
int flags,
int fd,
off_t start,
bool low_4gb,
bool reuse,
const char* filename,
std::string* error_msg){
int new_prot = (prot | PROT_WRITE);
if(nullptr != g_originMapFileAtAddress28) {
return g_originMapFileAtAddress28(expected_ptr,byte_count,new_prot,flags,fd,start,low_4gb,reuse,filename,error_msg);
}
}
在Hook LoadMethod函數之前,我們需要了解LoadMethod函數流程。為什麼是這個LoadMethod函數,其他函數是否可行?
當一個類被加載的時候,它的調用鏈是這樣的(部分流程已省略):
ClassLoader.java::loadClass -> DexPathList.java::findClass -> DexFile.java::defineClass -> class_linker.cc::LoadClass -> class_linker.cc::LoadClassMembers -> class_linker.cc::LoadMethod
也就是說,當一個類被加載,它是會去調用LoadMethod函數的,我們看一下它的函數原型:
void ClassLinker::LoadMethod(const DexFile& dex_file,
const ClassDataItemIterator& it,
Handle<mirror::Class> klass,
ArtMethod* dst);
這個函數太爆炸了,它有兩個爆炸性的參數,DexFile和ClassDataItemIterator,我們可以從這個函數得到當前加載函數所在的DexFile結構和當前函數的一些信息,可以看一下ClassDataItemIterator結構:
class ClassDataItemIterator{
......
// A decoded version of the method of a class_data_item
struct ClassDataMethod {
uint32_t method_idx_delta_; // delta of index into the method_ids array for MethodId
uint32_t access_flags_;
uint32_t code_off_;
ClassDataMethod() : method_idx_delta_(0), access_flags_(0), code_off_(0) {}
private:
DISALLOW_COPY_AND_ASSIGN(ClassDataMethod);
};
ClassDataMethod method_;
// Read and decode a method from a class_data_item stream into method
void ReadClassDataMethod();
const DexFile& dex_file_;
size_t pos_; // integral number of items passed
const uint8_t* ptr_pos_; // pointer into stream of class_data_item
uint32_t last_idx_; // last read field or method index to apply delta to
DISALLOW_IMPLICIT_CONSTRUCTORS(ClassDataItemIterator);
};
其中最重要的字段就是code_off_
它的值是當前加載的函數的CodeItem相對於DexFile的偏移,當相應的函數被加載,我們就可以直接訪問到它的CodeItem。其他函數是否也可以?在上面的流程中沒有比LoadMethod更適合我們Hook的函數,所以它是最佳的Hook點。
Hook LoadMethod稍微複雜一些,倒不是Hook代碼複雜,而是Hook觸發後處理的代碼比較複雜,我們要適配多個Android版本,每個版本LoadMethod函數的參數都可能有改變,幸運的是,LoadMethod改動也不是很大。那麼,我們如何讀取ClassDataItemIterator類中的code_off_
呢?比較直接的做法是計算偏移,然後在代碼中維護一份偏移。不過這樣的做法不易閱讀很容易出錯。dpt的做法是把ClassDataItemIterator類拷過來,然後將ClassDataItemIterator引用直接轉換為我們自定義的ClassDataItemIterator引用,這樣就可以方便的讀取字段的值。
下面是LoadMethod被調用後做的操作,邏輯是讀取存在map中的insns,然後將它們填回指定位置。
void LoadMethod(void *thiz, void *self, const void *dex_file, const void *it, const void *method,
void *klass, void *dst) {
if (g_originLoadMethod25 != nullptr
|| g_originLoadMethod28 != nullptr
|| g_originLoadMethod29 != nullptr) {
uint32_t location_offset = getDexFileLocationOffset();
uint32_t begin_offset = getDataItemCodeItemOffset();
callOriginLoadMethod(thiz, self, dex_file, it, method, klass, dst);
ClassDataItemReader *classDataItemReader = getClassDataItemReader(it,method);
uint8_t **begin_ptr = (uint8_t **) ((uint8_t *) dex_file + begin_offset);
uint8_t *begin = *begin_ptr;
// vtable(4|8) + prev_fields_size
std::string *location = (reinterpret_cast<std::string *>((uint8_t *) dex_file +
location_offset));
if (location->find("base.apk") != std::string::npos) {
//code_item_offset == 0說明是native方法或者沒有代碼
if (classDataItemReader->GetMethodCodeItemOffset() == 0) {
DLOGW("native method? = %s code_item_offset = 0x%x",
classDataItemReader->MemberIsNative() ? "true" : "false",
classDataItemReader->GetMethodCodeItemOffset());
return;
}
uint16_t firstDvmCode = *((uint16_t*)(begin + classDataItemReader->GetMethodCodeItemOffset() + 16));
if(firstDvmCode != 0x0012 && firstDvmCode != 0x0016 && firstDvmCode != 0x000e){
NLOG("this method has code no need to patch");
return;
}
uint32_t dexSize = *((uint32_t*)(begin + 0x20));
int dexIndex = dexNumber(location);
auto dexIt = dexMap.find(dexIndex - 1);
if (dexIt != dexMap.end()) {
auto dexMemIt = dexMemMap.find(dexIndex);
if(dexMemIt == dexMemMap.end()){
changeDexProtect(begin,location->c_str(),dexSize,dexIndex);
}
auto codeItemMap = dexIt->second;
int methodIdx = classDataItemReader->GetMemberIndex();
auto codeItemIt = codeItemMap->find(methodIdx);
if (codeItemIt != codeItemMap->end()) {
CodeItem* codeItem = codeItemIt->second;
uint8_t *realCodeItemPtr = (uint8_t*)(begin +
classDataItemReader->GetMethodCodeItemOffset() +
16);
memcpy(realCodeItemPtr,codeItem->getInsns(),codeItem->getInsnsSize());
}
}
}
}
}
(2) 加載dex
其實dex在App啟動的時候已經被加載過一次了,但是,我們為什麼還要再加載一次?因為系統加載的dex是以只讀方式加載的,我們沒辦法去修改那一部分的內存。而且App的dex加載早於我們Application的啟動,這樣,我們在代碼根本沒法感知到,所以我們要重新加載dex。
private ClassLoader loadDex(Context context){
String sourcePath = context.getApplicationInfo().sourceDir;
String nativePath = context.getApplicationInfo().nativeLibraryDir;
ShellClassLoader shellClassLoader = new ShellClassLoader(sourcePath,nativePath,ClassLoader.getSystemClassLoader());
return shellClassLoader;
}
自定義的ClassLoader
public class ShellClassLoader extends PathClassLoader {
private final String TAG = ShellClassLoader.class.getSimpleName();
public ShellClassLoader(String dexPath,ClassLoader classLoader) {
super(dexPath,classLoader);
}
public ShellClassLoader(String dexPath, String librarySearchPath,ClassLoader classLoader) {
super(dexPath, librarySearchPath, classLoader);
}
}
(3) 替換dexElements
這一步也非常重要,這一步的目的是使ClassLoader從我們新加載的dex文件中加載類。代碼如下:
void mergeDexElements(JNIEnv* env,jclass klass,jobject oldClassLoader,jobject newClassLoader){
jclass BaseDexClassLoaderClass = env->FindClass("dalvik/system/BaseDexClassLoader");
jfieldID pathList = env->GetFieldID(BaseDexClassLoaderClass,"pathList","Ldalvik/system/DexPathList;");
jobject oldDexPathListObj = env->GetObjectField(oldClassLoader,pathList);
if(env->ExceptionCheck() || nullptr == oldDexPathListObj ){
env->ExceptionClear();
DLOGW("mergeDexElements oldDexPathListObj get fail");
return;
}
jobject newDexPathListObj = env->GetObjectField(newClassLoader,pathList);
if(env->ExceptionCheck() || nullptr == newDexPathListObj){
env->ExceptionClear();
DLOGW("mergeDexElements newDexPathListObj get fail");
return;
}
jclass DexPathListClass = env->FindClass("dalvik/system/DexPathList");
jfieldID dexElementField = env->GetFieldID(DexPathListClass,"dexElements","[Ldalvik/system/DexPathList$Element;");
jobjectArray newClassLoaderDexElements = static_cast<jobjectArray>(env->GetObjectField(
newDexPathListObj, dexElementField));
if(env->ExceptionCheck() || nullptr == newClassLoaderDexElements){
env->ExceptionClear();
DLOGW("mergeDexElements new dexElements get fail");
return;
}
jobjectArray oldClassLoaderDexElements = static_cast<jobjectArray>(env->GetObjectField(
oldDexPathListObj, dexElementField));
if(env->ExceptionCheck() || nullptr == oldClassLoaderDexElements){
env->ExceptionClear();
DLOGW("mergeDexElements old dexElements get fail");
return;
}
jint oldLen = env->GetArrayLength(oldClassLoaderDexElements);
jint newLen = env->GetArrayLength(newClassLoaderDexElements);
DLOGD("mergeDexElements oldlen = %d , newlen = %d",oldLen,newLen);
jclass ElementClass = env->FindClass("dalvik/system/DexPathList$Element");
jobjectArray newElementArray = env->NewObjectArray(oldLen + newLen,ElementClass, nullptr);
for(int i = 0;i < newLen;i++) {
jobject elementObj = env->GetObjectArrayElement(newClassLoaderDexElements, i);
env->SetObjectArrayElement(newElementArray,i,elementObj);
}
for(int i = newLen;i < oldLen + newLen;i++) {
jobject elementObj = env->GetObjectArrayElement(oldClassLoaderDexElements, i - newLen);
env->SetObjectArrayElement(newElementArray,i,elementObj);
}
env->SetObjectField(oldDexPathListObj, dexElementField,newElementArray);
DLOGD("mergeDexElements success");
}
0x4 總結
做這個殼確實花了不少的時間,其中走過的彎路只有自己知道,不過還好做出來了。dpt未經過大量測試,後續發現問題再慢慢解決。