楼  【原创】从源代码看.net下exe的加载过程
|
|
标 题: 【原创】从源代码看.net下exe的加载过程
作 者: tankaiha
时 间: 2006-09-11,18:24
链 接: http://bbs./showthread.php?threadid=31799
这里的源代码自然不是指.net Framework的源码，不过微软公开了一个代号为rotor的open source cli的源码，你可以把它看为轻量级的.net framework。最关键的是，它俩的运行机理大致相同。今天，我们就从rotor的源码中看看做为程序调试最基本的exe文件的动态加载。同样，先给出参考文献，免得有人说我抄袭。《inside the rotor cli》，另一本是《shared source cli》，只不过网上搞不到。当然，还要从MSDN的网站下载sscli2.0压缩包。
和win32下一样，系统会提供一个loader将exe读入，sscli中提供了另一个loader的例子：clix.exe。我们暂且把它看为系统默认的loader，来看源码（clix.cpp），注意红色的代码
代码:
DWORD Launch(WCHAR* pFileName, WCHAR* pCmdLine)
{
WCHAR exeFileName[MAX_PATH + 1];
DWORD dwAttrs;
DWORD dwError;
DWORD nExitCode;
...
//这里进行一系列文件的属性检查
...
if (dwError != ERROR_SUCCESS) {
// We can‘t find the file, or there‘s some other problem. Exit with an error.
fwprintf(stderr, L"%s: ", pFileName);
DisplayMessageFromSystem(dwError);
return 1; // error
}
nExitCode = _CorExeMain2(NULL, 0, pFileName, NULL, pCmdLine);
// _CorExeMain2 never returns with success
_ASSERTE(nExitCode != 0);
DisplayMessageFromSystem(::GetLastError());
return nExitCode;
}
这里我们看到了著名的CorExeMain，还记得用PE编辑文件打开.netPE文件，只引入了一个函数吗？mscoree.dll!_CorExeMain。奇怪，怎么不是_CorExeMain2呢？这只是rotor和商业版的framework的一点区别而已。你可以用IDApro逆一下mscoree.dll，就可以看到_CorExeMain()只不过是一个中转，代码如下
代码:
.text:79011B47 push offset a_corexemain ; "_CorExeMain"
.text:79011B4C push [ebp+hModule] ; hModule
.text:79011B4F call ds:__imp__GetProcAddress@8 ; GetProcAddress(x,x)
.text:79011B55 test eax, eax
.text:79011B57 jz loc_79019B46
.text:79011B5D call eax
进入后马上就调用了mscorwks.dll的_CorExeMain。而这个函数和rotor中刚才提到的_CorExeMain2提供的功能差不多，就开始exe载入的初始化了。这些都可以从反汇编代码与源代码比较看出来。继续回到sscli中，来看_CorExeMain2()的代码（ceemain.cpp）
代码:
__int32 STDMETHODCALLTYPE _CorExeMain2( // Executable exit code.
PBYTE pUnmappedPE, // -> memory mapped code
DWORD cUnmappedPE, // Size of memory mapped code
__in LPWSTR pImageNameIn, // -> Executable Name
__in LPWSTR pLoadersFileName, // -> Loaders Name
__in LPWSTR pCmdLine) // -> Command Line
{
// This entry point is used by clix
BOOL bRetVal = 0;
//BEGIN_ENTRYPOINT_VOIDRET;
// Before we initialize the EE, make sure we‘ve snooped for all EE-specific
// command line arguments that might guide our startup.
HRESULT result = CorCommandLine::SetArgvW(pCmdLine);
if (!CacheCommandLine(pCmdLine, CorCommandLine::GetArgvW(NULL))) {
LOG((LF_STARTUP, LL_INFO10, "Program exiting - CacheCommandLine failed\n"));
bRetVal = -1;
goto exit;
}
if (SUCCEEDED(result))
result = CoInitializeEE(COINITEE_DEFAULT | COINITEE_MAIN);
if (FAILED(result)) {
VMDumpCOMErrors(result);
SetLatchedExitCode (-1);
goto exit;
}
// This is here to get the ZAPMONITOR working correctly
INSTALL_UNWIND_AND_CONTINUE_HANDLER;
// Load the executable
bRetVal = ExecuteEXE(pImageNameIn);
...
...
大多数代码都可以略过，关键的就两个，一个是初始化ee（execute engine），初始化成功后就调用ExecuteEXE，参数是文件名。这里可以清楚地看到_CorExeMain()的传入参数是什么。ExecuteEXE()的代码不多，也是个跳板：
代码:
BOOL STDMETHODCALLTYPE ExecuteEXE(HMODULE hMod)
{
STATIC_CONTRACT_GC_TRIGGERS;
_ASSERTE(hMod);
if (!hMod)
return FALSE;
ETWTraceStartup::TraceEvent(ETW_TYPE_STARTUP_EXEC_EXE);
TIMELINE_START(STARTUP, ("ExecuteExe"));
EX_TRY_NOCATCH
{
// Executables are part of the system domain
SystemDomain::ExecuteMainMethod(hMod);
}
EX_END_NOCATCH;
ETWTraceStartup::TraceEvent(ETW_TYPE_STARTUP_EXEC_EXE+1);
TIMELINE_END(STARTUP, ("ExecuteExe"));
return TRUE;
}
同样，关键的代码只有一行，SystemDomain::ExecuteMainMethod(hMod)。其中，字面上看ExecuteMainMethod是将传入的文件作为了一个module，在.net中，如果要以包含关系算的话，assembly > module > class > method。也就是说每一个assembly可能包含多个module，且至少有一个module有且只有一个MainMethod，就是入口方法。
下面转到SystemDomain::ExecuteMainMethod()的代码中（assembly.cpp）
代码:
INT32 Assembly::ExecuteMainMethod(PTRARRAYREF *stringArgs)
{
CONTRACTL
{
INSTANCE_CHECK;
THROWS;
GC_TRIGGERS;
MODE_ANY;
ENTRY_POINT;
INJECT_FAULT(COMPlusThrowOM());
}
CONTRACTL_END;
HRESULT hr = S_OK;
INT32 iRetVal = 0;
BEGIN_ENTRYPOINT_THROWS;
Thread *pThread = GetThread();
MethodDesc *pMeth;
{
// This thread looks like it wandered in -- but actually we rely on it to keep the process alive.
pThread->SetBackground(FALSE);
GCX_COOP();
pMeth = GetEntryPoint();
if (pMeth) {
RunMainPre();
hr = ClassLoader::RunMain(pMeth, 1, &iRetVal, stringArgs);
}
}
//RunMainPost is supposed to be called on the main thread of an EXE,
//after that thread has finished doing useful work. It contains logic
//to decide when the process should get torn down. So, don‘t call it from
// AppDomain.ExecuteAssembly()
if (pMeth) {
if (stringArgs == NULL)
RunMainPost();
}
else {
StackSString displayName;
GetDisplayName(displayName);
COMPlusThrowHR(COR_E_MISSINGMETHOD, IDS_EE_FAILED_TO_FIND_MAIN, displayName);
}
if (FAILED(hr))
ThrowHR(hr);
END_ENTRYPOINT_THROWS;
return iRetVal;
}
关键的步骤还是两个，准备好线程环境，然后运行Main方法。下面来到clsload.cpp中看ClassLoader::RunMain，这也是这次我们的最后一站。
代码:
HRESULT ClassLoader::RunMain(MethodDesc *pFD ,
short numSkipArgs,
INT32 *piRetVal,
PTRARRAYREF *stringArgs /*=NULL*/)
{
STATIC_CONTRACT_THROWS;
_ASSERTE(piRetVal);
DWORD cCommandArgs = 0; // count of args on command line
DWORD arg = 0;
LPWSTR *wzArgs = NULL; // command line args
HRESULT hr = S_OK;
*piRetVal = -1;
// The exit code for the process is communicated in one of two ways. If the
// entrypoint returns an ‘int‘ we take that. Otherwise we take a latched
// process exit code. This can be modified by the app via setting
// Environment‘s ExitCode property.
if (stringArgs == NULL)
SetLatchedExitCode(0);
if (!pFD) {
_ASSERTE(!"Must have a function to call!");
return E_FAIL;
}
CorEntryPointType EntryType = EntryManagedMain;
ValidateMainMethod(pFD, &EntryType);
if ((EntryType == EntryManagedMain) &&
(stringArgs == NULL)) {
// If you look at the DIFF on this code then you will see a major change which is that we
// no longer accept all the different types of data arguments to main. We now only accept
// an array of strings.
wzArgs = CorCommandLine::GetArgvW(&cCommandArgs);
// In the WindowsCE case where the app has additional args the count will come back zero.
if (cCommandArgs > 0) {
if (!wzArgs)
return E_INVALIDARG;
}
}
ETWTraceStartup::TraceEvent(ETW_TYPE_STARTUP_MAIN);
TIMELINE_START(STARTUP, ("RunMain"));
EX_TRY_NOCATCH
{
MethodDescCallSite threadStart(pFD);
PTRARRAYREF StrArgArray = NULL;
GCPROTECT_BEGIN(StrArgArray);
// Build the parameter array and invoke the method.
if (EntryType == EntryManagedMain) {
if (stringArgs == NULL) {
// Allocate a COM Array object with enough slots for cCommandArgs - 1
StrArgArray = (PTRARRAYREF) AllocateObjectArray((cCommandArgs - numSkipArgs), g_pStringClass);
// Create Stringrefs for each of the args
for( arg = numSkipArgs; arg < cCommandArgs; arg++) {
STRINGREF sref = COMString::NewString(wzArgs[arg]);
StrArgArray->SetAt(arg-numSkipArgs, (OBJECTREF) sref);
}
}
else
StrArgArray = *stringArgs;
}
#ifdef STRESS_THREAD
OBJECTHANDLE argHandle = (StrArgArray != NULL) ? CreateGlobalStrongHandle (StrArgArray) : NULL;
Stress_Thread_Param Param = {pFD, argHandle, numSkipArgs, EntryType, 0};
Stress_Thread_Start (&Param);
#endif
ARG_SLOT stackVar = ObjToArgSlot(StrArgArray);
if (pFD->IsVoid())
{
// Set the return value to 0 instead of returning random junk
*piRetVal = 0;
threadStart.Call(&stackVar);
}
else
{
*piRetVal = (INT32)threadStart.Call_RetArgSlot(&stackVar);
if (stringArgs == NULL)
{
SetLatchedExitCode(*piRetVal);
}
}
GCPROTECT_END();
fflush(stdout);
fflush(stderr);
}
EX_END_NOCATCH
ETWTraceStartup::TraceEvent(ETW_TYPE_STARTUP_MAIN+1);
TIMELINE_END(STARTUP, ("RunMain"));
return hr;
}
这些代码主要是进行方法最终运行前的一些准备，然后运行。分两种，有返回值的和void()的。下面的运行情况就是深入到framework的核心中了，改天看了再写吧。代码中运用了许多COM下的定义，也可见.net和COM关系的密切。就像.net下的Debugger和Profiler甚至直接调用了COM接口来编译。只是我对COM了解不深，无法就此问题深入。
btw:在看雪发了几篇.net文章，主要是看雪类似的文章较少，研究的人也不多。要是有兴趣共同学习.net 的内核，欢迎和我交流。
由 tankaiha 于 2006-09-11 20:25 最后编辑
|
