OC底层探索(十一)dyld流程

引入

• 在ViewController中添加Load方法，输出打印。

#import "ViewController.h"

@interface ViewController ()

@end

@implementation ViewController

+ (void)load{
    NSLog(@"%s",__func__);
}

- (void)viewDidLoad {
    [super viewDidLoad];
    // Do any additional setup after loading the view.
}


@end

• 在main.m文件中添加一个C++函数

#import <UIKit/UIKit.h>
#import "AppDelegate.h"



// 内存 main() dyld image init 注册回调通知 - dyld_start  -> dyld::main()  -> main()
// rax
int main(int argc, char * argv[]) {
    NSString * appDelegateClassName;
    
    NSLog(@"1223333");
    
    @autoreleasepool {
        // Setup code that might create autoreleased objects goes here.
        appDelegateClassName = NSStringFromClass([AppDelegate class]);
    }
    return UIApplicationMain(argc, argv, nil, appDelegateClassName);
}


// load -> Cxx -> main
__attribute__((constructor)) void kcFunc(){
    printf("来了 : %s \n",__func__);
}

• 运行程序，查看打印结果
  
• 先执行load，然后在执行C++函数，最后执行main函数。

编译过程

• 源文件：载入.h、.m、.cpp等文件
• 预编译：替换宏，删除注释，展开头文件，产生.i文件
• 编译：将.i文件转换为汇编语言，产生.s文件
• 汇编：将汇编文件转换为机器码文件，产生.o文件
• 链接：对.o文件中引用其他库的地方进行引用，生成最后的可执行文件

动态链接 – dyld加载流程分析

dyld的概念

dyld（the dynamic link editor）是苹果的动态链接器，是苹果操作系统一个重要组成部分，在系统内核做好程序准备工作之后，交由dyld负责连接，加载程序。

dyld加载过程

app启动的起始点

• 在一开始load函数处打一个断点
  

• 在控制台输入bt就可以发现一开始的堆栈是 _dyld_start
  

• 或者查看左侧堆栈信息,也会发现是_dyld_start
  

【app启动起点】：通过程序运行发现，是从dyld中的_dyld_start开始的，所以需要去OpenSource下载一份dyld的源码来进行分析。

dyld 源码分析

• 在源码中全局搜索_dyld_start，发现源码是由汇编编写完成的，源码中可以看到一条bl命令，根据注释可以知道是跳转到dyldbootstrap::start()函数。
  

• dyldbootstrap::start是C++语法，dyldbootstrap是命名空间。我们全局搜索dyldbootstrap，并找到start方法
  
  其中start方法中做了三件事：
  a. dyld重定位
  b. 栈溢出保护
  c. 进入dyld::main函数

• control + command点击进入main函数， dyld::_main()是整个App启动的关键函数，此函数里面做了很多事情。

_main(const macho_header* mainExecutableMH, uintptr_t mainExecutableSlide, 
		int argc, const char* argv[], const char* envp[], const char* apple[], 
		uintptr_t* startGlue)
{
	if (dyld3::kdebug_trace_dyld_enabled(DBG_DYLD_TIMING_LAUNCH_EXECUTABLE)) {
		launchTraceID = dyld3::kdebug_trace_dyld_duration_start(DBG_DYLD_TIMING_LAUNCH_EXECUTABLE, (uint64_t)mainExecutableMH, 0, 0);
	}

	//Check and see if there are any kernel flags
	dyld3::BootArgs::setFlags(hexToUInt64(_simple_getenv(apple, "dyld_flags"), nullptr));

    // Grab the cdHash of the main executable from the environment
	// 第一步，设置运行环境
	uint8_t mainExecutableCDHashBuffer[20];
	const uint8_t* mainExecutableCDHash = nullptr;
	if ( hexToBytes(_simple_getenv(apple, "executable_cdhash"), 40, mainExecutableCDHashBuffer) )
		// 获取主程序的hash
		mainExecutableCDHash = mainExecutableCDHashBuffer;

#if !TARGET_OS_SIMULATOR
	// Trace dyld's load
	notifyKernelAboutImage((macho_header*)&__dso_handle, _simple_getenv(apple, "dyld_file"));
	// Trace the main executable's load
	notifyKernelAboutImage(mainExecutableMH, _simple_getenv(apple, "executable_file"));
#endif

	uintptr_t result = 0;
	// 获取主程序的macho_header结构
	sMainExecutableMachHeader = mainExecutableMH;
	// 获取主程序的slide值
	sMainExecutableSlide = mainExecutableSlide;


	// Set the platform ID in the all image infos so debuggers can tell the process type
	// FIXME: This can all be removed once we make the kernel handle it in rdar://43369446
	if (gProcessInfo->version >= 16) {
		__block bool platformFound = false;
		((dyld3::MachOFile*)mainExecutableMH)->forEachSupportedPlatform(^(dyld3::Platform platform, uint32_t minOS, uint32_t sdk) {
			if (platformFound) {
				halt("MH_EXECUTE binaries may only specify one platform");
			}
			gProcessInfo->platform = (uint32_t)platform;
			platformFound = true;
		});
		if (gProcessInfo->platform == (uint32_t)dyld3::Platform::unknown) {
			// There were no platforms found in the binary. This may occur on macOS for alternate toolchains and old binaries.
			// It should never occur on any of our embedded platforms.
#if __MAC_OS_X_VERSION_MIN_REQUIRED
			gProcessInfo->platform = (uint32_t)dyld3::Platform::macOS;
#else
			halt("MH_EXECUTE binaries must specify a minimum supported OS version");
#endif
		}
	}

#if __MAC_OS_X_VERSION_MIN_REQUIRED
	// Check to see if we need to override the platform
	const char* forcedPlatform = _simple_getenv(envp, "DYLD_FORCE_PLATFORM");
	if (forcedPlatform) {
		if (strncmp(forcedPlatform, "6", 1) != 0) {
			halt("DYLD_FORCE_PLATFORM is only supported for platform 6");
		}
		const dyld3::MachOFile* mf = (dyld3::MachOFile*)sMainExecutableMachHeader;
		if (mf->allowsAlternatePlatform()) {
			gProcessInfo->platform = PLATFORM_IOSMAC;
		}
	}

	// if this is host dyld, check to see if iOS simulator is being run
	const char* rootPath = _simple_getenv(envp, "DYLD_ROOT_PATH");
	if ( (rootPath != NULL) ) {
		// look to see if simulator has its own dyld
		char simDyldPath[PATH_MAX]; 
		strlcpy(simDyldPath, rootPath, PATH_MAX);
		strlcat(simDyldPath, "/usr/lib/dyld_sim", PATH_MAX);
		int fd = my_open(simDyldPath, O_RDONLY, 0);
		if ( fd != -1 ) {
			const char* errMessage = useSimulatorDyld(fd, mainExecutableMH, simDyldPath, argc, argv, envp, apple, startGlue, &result);
			if ( errMessage != NULL )
				halt(errMessage);
			return result;
		}
	}
	else {
		((dyld3::MachOFile*)mainExecutableMH)->forEachSupportedPlatform(^(dyld3::Platform platform, uint32_t minOS, uint32_t sdk) {
			if ( dyld3::MachOFile::isSimulatorPlatform(platform) )
				halt("attempt to run simulator program outside simulator (DYLD_ROOT_PATH not set)");
		});
	}
#endif

	CRSetCrashLogMessage("dyld: launch started");
	// 设置上下文信息
	setContext(mainExecutableMH, argc, argv, envp, apple);

	// Pickup the pointer to the exec path.
	// 获取主程序路径
	sExecPath = _simple_getenv(apple, "executable_path");

	// <rdar://problem/13868260> Remove interim apple[0] transition code from dyld
	if (!sExecPath) sExecPath = apple[0];

#if __IPHONE_OS_VERSION_MIN_REQUIRED && !TARGET_OS_SIMULATOR
	// <rdar://54095622> kernel is not passing a real path for main executable
	if ( strncmp(sExecPath, "/var/containers/Bundle/Application/", 35) == 0 ) {
		if ( char* newPath = (char*)malloc(strlen(sExecPath)+10) ) {
			strcpy(newPath, "/private");
			strcat(newPath, sExecPath);
			sExecPath = newPath;
		}
	}
#endif

	if ( sExecPath[0] != '/' ) {
		// have relative path, use cwd to make absolute
		char cwdbuff[MAXPATHLEN];
	    if ( getcwd(cwdbuff, MAXPATHLEN) != NULL ) {
			// maybe use static buffer to avoid calling malloc so early...
			char* s = new char[strlen(cwdbuff) + strlen(sExecPath) + 2];
			strcpy(s, cwdbuff);
			strcat(s, "/");
			strcat(s, sExecPath);
			sExecPath = s;
		}
	}

	// Remember short name of process for later logging
	 // 获取进程名称
	sExecShortName = ::strrchr(sExecPath, '/');
	if ( sExecShortName != NULL )
		++sExecShortName;
	else
		sExecShortName = sExecPath;

	// 配置进程受限模式
    configureProcessRestrictions(mainExecutableMH, envp);

	// Check if we should force dyld3.  Note we have to do this outside of the regular env parsing due to AMFI
	if ( dyld3::internalInstall() ) {
		if (const char* useClosures = _simple_getenv(envp, "DYLD_USE_CLOSURES")) {
			if ( strcmp(useClosures, "0") == 0 ) {
				sClosureMode = ClosureMode::Off;
			} else if ( strcmp(useClosures, "1") == 0 ) {
#if __MAC_OS_X_VERSION_MIN_REQUIRED

#if __i386__
				// don't support dyld3 for 32-bit macOS
#else
				// Also don't support dyld3 for iOSMac right now
				if ( gProcessInfo->platform != PLATFORM_IOSMAC ) {
					sClosureMode = ClosureMode::On;
				}
#endif // __i386__

#else
				sClosureMode = ClosureMode::On;
#endif // __MAC_OS_X_VERSION_MIN_REQUIRED
			} else {
				dyld::warn("unknown option to DYLD_USE_CLOSURES.  Valid options are: 0 and 1\n");
			}

		}
	}

#if __MAC_OS_X_VERSION_MIN_REQUIRED
    if ( !gLinkContext.allowEnvVarsPrint && !gLinkContext.allowEnvVarsPath && !gLinkContext.allowEnvVarsSharedCache ) {
		
		pruneEnvironmentVariables(envp, &apple);
		// set again because envp and apple may have changed or moved
		setContext(mainExecutableMH, argc, argv, envp, apple);
	}
	else
#endif
	{
		// 检测环境变量
		checkEnvironmentVariables(envp);
		defaultUninitializedFallbackPaths(envp);
	}
#if __MAC_OS_X_VERSION_MIN_REQUIRED
	if ( gProcessInfo->platform == PLATFORM_IOSMAC ) {
		gLinkContext.rootPaths = parseColonList("/System/iOSSupport", NULL);
		gLinkContext.iOSonMac = true;
		if ( sEnv.DYLD_FALLBACK_LIBRARY_PATH == sLibraryFallbackPaths )
			sEnv.DYLD_FALLBACK_LIBRARY_PATH = sRestrictedLibraryFallbackPaths;
		if ( sEnv.DYLD_FALLBACK_FRAMEWORK_PATH == sFrameworkFallbackPaths )
			sEnv.DYLD_FALLBACK_FRAMEWORK_PATH = sRestrictedFrameworkFallbackPaths;
	}
	else if ( ((dyld3::MachOFile*)mainExecutableMH)->supportsPlatform(dyld3::Platform::driverKit) ) {
		gLinkContext.driverKit = true;
		gLinkContext.sharedRegionMode = ImageLoader::kDontUseSharedRegion;
	}
#endif
	if ( sEnv.DYLD_PRINT_OPTS )
		printOptions(argv);
	if ( sEnv.DYLD_PRINT_ENV ) 
		printEnvironmentVariables(envp);

	// Parse this envirionment variable outside of the regular logic as we want to accept
	// this on binaries without an entitelment
#if !TARGET_OS_SIMULATOR
	if ( _simple_getenv(envp, "DYLD_JUST_BUILD_CLOSURE") != nullptr ) {
#if TARGET_OS_IPHONE
		const char* tempDir = getTempDir(envp);
		if ( (tempDir != nullptr) && (geteuid() != 0) ) {
			// Use realpath to prevent something like TMPRIR=/tmp/../usr/bin
			char realPath[PATH_MAX];
			if ( realpath(tempDir, realPath) != NULL )
				tempDir = realPath;
			if (strncmp(tempDir, "/private/var/mobile/Containers/", strlen("/private/var/mobile/Containers/")) == 0) {
				sJustBuildClosure = true;
			}
		}
#endif
		// If we didn't like the format of TMPDIR, just exit.  We don't want to launch the app as that would bring up the UI
		if (!sJustBuildClosure) {
			_exit(EXIT_SUCCESS);
		}
	}
#endif

	if ( sJustBuildClosure )
		sClosureMode = ClosureMode::On;
	// 获取当前程序架构
	getHostInfo(mainExecutableMH, mainExecutableSlide);
	 //-------------第一步结束-------------
	

	// load shared cache
	// 第二步，加载共享缓存
	   // 检查共享缓存是否开启，iOS必须开启
	checkSharedRegionDisable((dyld3::MachOLoaded*)mainExecutableMH, mainExecutableSlide);
	if ( gLinkContext.sharedRegionMode != ImageLoader::kDontUseSharedRegion ) {
#if TARGET_OS_SIMULATOR
		if ( sSharedCacheOverrideDir)
			mapSharedCache();
#else
		mapSharedCache();
#endif
	}

	// If we haven't got a closure mode yet, then check the environment and cache type
	if ( sClosureMode == ClosureMode::Unset ) {
		// First test to see if we forced in dyld2 via a kernel boot-arg
		if ( dyld3::BootArgs::forceDyld2() ) {
			sClosureMode = ClosureMode::Off;
		} else if ( inDenyList(sExecPath) ) {
			sClosureMode = ClosureMode::Off;
		} else if ( sEnv.hasOverride ) {
			sClosureMode = ClosureMode::Off;
		} else if ( dyld3::BootArgs::forceDyld3() ) {
			sClosureMode = ClosureMode::On;
		} else {
			sClosureMode = getPlatformDefaultClosureMode();
		}
	}

#if !TARGET_OS_SIMULATOR
	if ( sClosureMode == ClosureMode::Off ) {
		if ( gLinkContext.verboseWarnings )
			dyld::log("dyld: not using closure because of DYLD_USE_CLOSURES or -force_dyld2=1 override\n");
	} else {
		const dyld3::closure::LaunchClosure* mainClosure = nullptr;
		dyld3::closure::LoadedFileInfo mainFileInfo;
		mainFileInfo.fileContent = mainExecutableMH;
		mainFileInfo.path = sExecPath;
		// FIXME: If we are saving this closure, this slice offset/length is probably wrong in the case of FAT files.
		mainFileInfo.sliceOffset = 0;
		mainFileInfo.sliceLen = -1;
		struct stat mainExeStatBuf;
		if ( ::stat(sExecPath, &mainExeStatBuf) == 0 ) {
			mainFileInfo.inode = mainExeStatBuf.st_ino;
			mainFileInfo.mtime = mainExeStatBuf.st_mtime;
		}
		// check for closure in cache first
		if ( sSharedCacheLoadInfo.loadAddress != nullptr ) {
			mainClosure = sSharedCacheLoadInfo.loadAddress->findClosure(sExecPath);
			if ( gLinkContext.verboseWarnings && (mainClosure != nullptr) )
				dyld::log("dyld: found closure %p (size=%lu) in dyld shared cache\n", mainClosure, mainClosure->size());
		}

		// We only want to try build a closure at runtime if its an iOS third party binary, or a macOS binary from the shared cache
		bool allowClosureRebuilds = false;
		if ( sClosureMode == ClosureMode::On ) {
			allowClosureRebuilds = true;
		} else if ( (sClosureMode == ClosureMode::PreBuiltOnly) && (mainClosure != nullptr) ) {
			allowClosureRebuilds = true;
		}

		if ( (mainClosure != nullptr) && !closureValid(mainClosure, mainFileInfo, mainExecutableCDHash, true, envp) )
			mainClosure = nullptr;

		// If we didn't find a valid cache closure then try build a new one
		if ( (mainClosure == nullptr) && allowClosureRebuilds ) {
			// if forcing closures, and no closure in cache, or it is invalid, check for cached closure
			if ( !sForceInvalidSharedCacheClosureFormat )
				mainClosure = findCachedLaunchClosure(mainExecutableCDHash, mainFileInfo, envp);
			if ( mainClosure == nullptr ) {
				// if  no cached closure found, build new one
				mainClosure = buildLaunchClosure(mainExecutableCDHash, mainFileInfo, envp);
			}
		}

		// exit dyld after closure is built, without running program
		if ( sJustBuildClosure )
			_exit(EXIT_SUCCESS);

		// try using launch closure
		if ( mainClosure != nullptr ) {
			CRSetCrashLogMessage("dyld3: launch started");
			bool launched = launchWithClosure(mainClosure, sSharedCacheLoadInfo.loadAddress, (dyld3::MachOLoaded*)mainExecutableMH,
											  mainExecutableSlide, argc, argv, envp, apple, &result, startGlue);
			if ( !launched && allowClosureRebuilds ) {
				// closure is out of date, build new one
				mainClosure = buildLaunchClosure(mainExecutableCDHash, mainFileInfo, envp);
				if ( mainClosure != nullptr ) {
					launched = launchWithClosure(mainClosure, sSharedCacheLoadInfo.loadAddress, (dyld3::MachOLoaded*)mainExecutableMH,
												 mainExecutableSlide, argc, argv, envp, apple, &result, startGlue);
				}
			}
			if ( launched ) {
				gLinkContext.startedInitializingMainExecutable = true;
#if __has_feature(ptrauth_calls)
				// start() calls the result pointer as a function pointer so we need to sign it.
				result = (uintptr_t)__builtin_ptrauth_sign_unauthenticated((void*)result, 0, 0);
#endif
				if (sSkipMain)
					result = (uintptr_t)&fake_main;
				return result;
			}
			else {
				if ( gLinkContext.verboseWarnings ) {
					dyld::log("dyld: unable to use closure %p\n", mainClosure);
				}
			}
		}
	}
#endif // TARGET_OS_SIMULATOR
	// could not use closure info, launch old way



	// install gdb notifier
	stateToHandlers(dyld_image_state_dependents_mapped, sBatchHandlers)->push_back(notifyGDB);
	stateToHandlers(dyld_image_state_mapped, sSingleHandlers)->push_back(updateAllImages);
	// make initial allocations large enough that it is unlikely to need to be re-alloced
	sImageRoots.reserve(16);
	sAddImageCallbacks.reserve(4);
	sRemoveImageCallbacks.reserve(4);
	sAddLoadImageCallbacks.reserve(4);
	sImageFilesNeedingTermination.reserve(16);
	sImageFilesNeedingDOFUnregistration.reserve(8);

#if !TARGET_OS_SIMULATOR
#ifdef WAIT_FOR_SYSTEM_ORDER_HANDSHAKE
	// <rdar://problem/6849505> Add gating mechanism to dyld support system order file generation process
	WAIT_FOR_SYSTEM_ORDER_HANDSHAKE(dyld::gProcessInfo->systemOrderFlag);
#endif
#endif


	try {
		// add dyld itself to UUID list
		addDyldImageToUUIDList();

#if SUPPORT_ACCELERATE_TABLES
#if __arm64e__
		// Disable accelerator tables when we have threaded rebase/bind, which is arm64e executables only for now.
		if (sMainExecutableMachHeader->cpusubtype == CPU_SUBTYPE_ARM64E)
			sDisableAcceleratorTables = true;
#endif
		bool mainExcutableAlreadyRebased = false;
		if ( (sSharedCacheLoadInfo.loadAddress != nullptr) && !dylibsCanOverrideCache() && !sDisableAcceleratorTables && (sSharedCacheLoadInfo.loadAddress->header.accelerateInfoAddr != 0) ) {
			struct stat statBuf;
			if ( ::stat(IPHONE_DYLD_SHARED_CACHE_DIR "no-dyld2-accelerator-tables", &statBuf) != 0 )
				sAllCacheImagesProxy = ImageLoaderMegaDylib::makeImageLoaderMegaDylib(&sSharedCacheLoadInfo.loadAddress->header, sSharedCacheLoadInfo.slide, mainExecutableMH, gLinkContext);
		}

reloadAllImages:
#endif


	#if __MAC_OS_X_VERSION_MIN_REQUIRED
		gLinkContext.strictMachORequired = false;
        // <rdar://problem/22805519> be less strict about old macOS mach-o binaries
        ((dyld3::MachOFile*)mainExecutableMH)->forEachSupportedPlatform(^(dyld3::Platform platform, uint32_t minOS, uint32_t sdk) {
            if ( (platform == dyld3::Platform::macOS) && (sdk >= DYLD_PACKED_VERSION(10,15,0)) ) {
            	gLinkContext.strictMachORequired = true;
			}
        });
	    if ( gLinkContext.iOSonMac )
		    gLinkContext.strictMachORequired = true;
	#else
		// simulators, iOS, tvOS, watchOS, are always strict
		gLinkContext.strictMachORequired = true;
	#endif


		CRSetCrashLogMessage(sLoadingCrashMessage);
		// instantiate ImageLoader for main executable
		// 第三步 实例化主程序
		sMainExecutable = instantiateFromLoadedImage(mainExecutableMH, mainExecutableSlide, sExecPath);
		gLinkContext.mainExecutable = sMainExecutable;
		gLinkContext.mainExecutableCodeSigned = hasCodeSignatureLoadCommand(mainExecutableMH);

#if TARGET_OS_SIMULATOR
		// check main executable is not too new for this OS
		{
			if ( ! isSimulatorBinary((uint8_t*)mainExecutableMH, sExecPath) ) {
				throwf("program was built for a platform that is not supported by this runtime");
			}
			uint32_t mainMinOS = sMainExecutable->minOSVersion();

			// dyld is always built for the current OS, so we can get the current OS version
			// from the load command in dyld itself.
			uint32_t dyldMinOS = ImageLoaderMachO::minOSVersion((const mach_header*)&__dso_handle);
			if ( mainMinOS > dyldMinOS ) {
	#if TARGET_OS_WATCH
				throwf("app was built for watchOS %d.%d which is newer than this simulator %d.%d",
						mainMinOS >> 16, ((mainMinOS >> 8) & 0xFF),
						dyldMinOS >> 16, ((dyldMinOS >> 8) & 0xFF));
	#elif TARGET_OS_TV
				throwf("app was built for tvOS %d.%d which is newer than this simulator %d.%d",
						mainMinOS >> 16, ((mainMinOS >> 8) & 0xFF),
						dyldMinOS >> 16, ((dyldMinOS >> 8) & 0xFF));
	#else
				throwf("app was built for iOS %d.%d which is newer than this simulator %d.%d",
						mainMinOS >> 16, ((mainMinOS >> 8) & 0xFF),
						dyldMinOS >> 16, ((dyldMinOS >> 8) & 0xFF));
	#endif
			}
		}
#endif


	#if SUPPORT_ACCELERATE_TABLES
		sAllImages.reserve((sAllCacheImagesProxy != NULL) ? 16 : INITIAL_IMAGE_COUNT);
	#else
		sAllImages.reserve(INITIAL_IMAGE_COUNT);
	#endif

		// Now that shared cache is loaded, setup an versioned dylib overrides
	#if SUPPORT_VERSIONED_PATHS
		checkVersionedPaths();
	#endif


		// dyld_all_image_infos image list does not contain dyld
		// add it as dyldPath field in dyld_all_image_infos
		// for simulator, dyld_sim is in image list, need host dyld added
#if TARGET_OS_SIMULATOR
		// get path of host dyld from table of syscall vectors in host dyld
		void* addressInDyld = gSyscallHelpers;
#else
		// get path of dyld itself
		void*  addressInDyld = (void*)&__dso_handle;
#endif
		char dyldPathBuffer[MAXPATHLEN+1];
		int len = proc_regionfilename(getpid(), (uint64_t)(long)addressInDyld, dyldPathBuffer, MAXPATHLEN);
		if ( len > 0 ) {
			dyldPathBuffer[len] = '\0'; // proc_regionfilename() does not zero terminate returned string
			if ( strcmp(dyldPathBuffer, gProcessInfo->dyldPath) != 0 )
				gProcessInfo->dyldPath = strdup(dyldPathBuffer);
		}

		// load any inserted libraries
		 // 第四步 加载插入的动态库
		if	( sEnv.DYLD_INSERT_LIBRARIES != NULL ) {
			for (const char* const* lib = sEnv.DYLD_INSERT_LIBRARIES; *lib != NULL; ++lib) 
				loadInsertedDylib(*lib);
		}
		// record count of inserted libraries so that a flat search will look at 
		// inserted libraries, then main, then others.
		// 记录插入的动态库数量
		sInsertedDylibCount = sAllImages.size()-1;

		// link main executable
		// 第五步 链接主程序
		gLinkContext.linkingMainExecutable = true;
#if SUPPORT_ACCELERATE_TABLES
		if ( mainExcutableAlreadyRebased ) {
			// previous link() on main executable has already adjusted its internal pointers for ASLR
			// work around that by rebasing by inverse amount
			sMainExecutable->rebase(gLinkContext, -mainExecutableSlide);
		}
#endif
		link(sMainExecutable, sEnv.DYLD_BIND_AT_LAUNCH, true, ImageLoader::RPathChain(NULL, NULL), -1);
		sMainExecutable->setNeverUnloadRecursive();
		if ( sMainExecutable->forceFlat() ) {
			gLinkContext.bindFlat = true;
			gLinkContext.prebindUsage = ImageLoader::kUseNoPrebinding;
		}

		// link any inserted libraries
		// do this after linking main executable so that any dylibs pulled in by inserted 
		// dylibs (e.g. libSystem) will not be in front of dylibs the program uses
		// 第六步 链接插入的动态库
		if ( sInsertedDylibCount > 0 ) {
			for(unsigned int i=0; i < sInsertedDylibCount; ++i) {
				ImageLoader* image = sAllImages[i+1];
				link(image, sEnv.DYLD_BIND_AT_LAUNCH, true, ImageLoader::RPathChain(NULL, NULL), -1);
				image->setNeverUnloadRecursive();
			}
			if ( gLinkContext.allowInterposing ) {
				// only INSERTED libraries can interpose
				// register interposing info after all inserted libraries are bound so chaining works
				for(unsigned int i=0; i < sInsertedDylibCount; ++i) {
					ImageLoader* image = sAllImages[i+1];
					image->registerInterposing(gLinkContext);
				}
			}
		}

		if ( gLinkContext.allowInterposing ) {
			// <rdar://problem/19315404> dyld should support interposition even without DYLD_INSERT_LIBRARIES
			 // 第七步 执行弱符号绑定
			for (long i=sInsertedDylibCount+1; i < sAllImages.size(); ++i) {
				ImageLoader* image = sAllImages[i];
				if ( image->inSharedCache() )
					continue;
				image->registerInterposing(gLinkContext);
			}
		}
	#if SUPPORT_ACCELERATE_TABLES
		if ( (sAllCacheImagesProxy != NULL) && ImageLoader::haveInterposingTuples() ) {
			// Accelerator tables cannot be used with implicit interposing, so relaunch with accelerator tables disabled
			ImageLoader::clearInterposingTuples();
			// unmap all loaded dylibs (but not main executable)
			for (long i=1; i < sAllImages.size(); ++i) {
				ImageLoader* image = sAllImages[i];
				if ( image == sMainExecutable )
					continue;
				if ( image == sAllCacheImagesProxy )
					continue;
				image->setCanUnload();
				ImageLoader::deleteImage(image);
			}
			// note: we don't need to worry about inserted images because if DYLD_INSERT_LIBRARIES was set we would not be using the accelerator table
			sAllImages.clear();
			sImageRoots.clear();
			sImageFilesNeedingTermination.clear();
			sImageFilesNeedingDOFUnregistration.clear();
			sAddImageCallbacks.clear();
			sRemoveImageCallbacks.clear();
			sAddLoadImageCallbacks.clear();
			sAddBulkLoadImageCallbacks.clear();
			sDisableAcceleratorTables = true;
			sAllCacheImagesProxy = NULL;
			sMappedRangesStart = NULL;
			mainExcutableAlreadyRebased = true;
			gLinkContext.linkingMainExecutable = false;
			resetAllImages();
			goto reloadAllImages;
		}
	#endif

		// apply interposing to initial set of images
		for(int i=0; i < sImageRoots.size(); ++i) {
			sImageRoots[i]->applyInterposing(gLinkContext);
		}
		ImageLoader::applyInterposingToDyldCache(gLinkContext);

		// Bind and notify for the main executable now that interposing has been registered
		uint64_t bindMainExecutableStartTime = mach_absolute_time();
		sMainExecutable->recursiveBindWithAccounting(gLinkContext, sEnv.DYLD_BIND_AT_LAUNCH, true);
		uint64_t bindMainExecutableEndTime = mach_absolute_time();
		ImageLoaderMachO::fgTotalBindTime += bindMainExecutableEndTime - bindMainExecutableStartTime;
		gLinkContext.notifyBatch(dyld_image_state_bound, false);

		// Bind and notify for the inserted images now interposing has been registered
		if ( sInsertedDylibCount > 0 ) {
			for(unsigned int i=0; i < sInsertedDylibCount; ++i) {
				ImageLoader* image = sAllImages[i+1];
				image->recursiveBind(gLinkContext, sEnv.DYLD_BIND_AT_LAUNCH, true);
			}
		}
		
		// <rdar://problem/12186933> do weak binding only after all inserted images linked
		sMainExecutable->weakBind(gLinkContext);
		gLinkContext.linkingMainExecutable = false;

		sMainExecutable->recursiveMakeDataReadOnly(gLinkContext);

		CRSetCrashLogMessage("dyld: launch, running initializers");
	#if SUPPORT_OLD_CRT_INITIALIZATION
		// Old way is to run initializers via a callback from crt1.o
		if ( ! gRunInitializersOldWay ) 
			initializeMainExecutable(); 
	#else
		// run all initializers
		// 第八步 执行初始化方法
		initializeMainExecutable(); 
	#endif

		// notify any montoring proccesses that this process is about to enter main()
		notifyMonitoringDyldMain();
		if (dyld3::kdebug_trace_dyld_enabled(DBG_DYLD_TIMING_LAUNCH_EXECUTABLE)) {
			dyld3::kdebug_trace_dyld_duration_end(launchTraceID, DBG_DYLD_TIMING_LAUNCH_EXECUTABLE, 0, 0, 2);
		}
		ARIADNEDBG_CODE(220, 1);

#if __MAC_OS_X_VERSION_MIN_REQUIRED
		if ( gLinkContext.driverKit ) {
			// 第九步 查找入口点并返回
			result = (uintptr_t)sEntryOveride;
			if ( result == 0 )
				halt("no entry point registered");
			*startGlue = (uintptr_t)gLibSystemHelpers->startGlueToCallExit;
		}
		else
#endif
		{
			// find entry point for main executable
			// 第九步 查找入口点并返回
			result = (uintptr_t)sMainExecutable->getEntryFromLC_MAIN();
			if ( result != 0 ) {
				// main executable uses LC_MAIN, we need to use helper in libdyld to call into main()
				if ( (gLibSystemHelpers != NULL) && (gLibSystemHelpers->version >= 9) )
					*startGlue = (uintptr_t)gLibSystemHelpers->startGlueToCallExit;
				else
					halt("libdyld.dylib support not present for LC_MAIN");
			}
			else {
				// main executable uses LC_UNIXTHREAD, dyld needs to let "start" in program set up for main()
				result = (uintptr_t)sMainExecutable->getEntryFromLC_UNIXTHREAD();
				*startGlue = 0;
			}
		}
#if __has_feature(ptrauth_calls)
		// start() calls the result pointer as a function pointer so we need to sign it.
		result = (uintptr_t)__builtin_ptrauth_sign_unauthenticated((void*)result, 0, 0);
#endif
	}
	catch(const char* message) {
		syncAllImages();
		halt(message);
	}
	catch(...) {
		dyld::log("dyld: launch failed\n");
	}

	CRSetCrashLogMessage("dyld2 mode");
#if !TARGET_OS_SIMULATOR
	if (sLogClosureFailure) {
		// We failed to launch in dyld3, but dyld2 can handle it. synthesize a crash report for analytics
		dyld3::syntheticBacktrace("Could not generate launchClosure, falling back to dyld2", true);
	}
#endif

	if (sSkipMain) {
		notifyMonitoringDyldMain();
		if (dyld3::kdebug_trace_dyld_enabled(DBG_DYLD_TIMING_LAUNCH_EXECUTABLE)) {
			dyld3::kdebug_trace_dyld_duration_end(launchTraceID, DBG_DYLD_TIMING_LAUNCH_EXECUTABLE, 0, 0, 2);
		}
		ARIADNEDBG_CODE(220, 1);
		result = (uintptr_t)&fake_main;
		*startGlue = (uintptr_t)gLibSystemHelpers->startGlueToCallExit;
	}
	
	return result;
}

在源码中可以发现： 整个加载过程可细分为九步：

• 第一步：设置运行环境。
• 第二步：加载共享缓存。
• 第三步：实例化主程序。
• 第四步：加载插入的动态库。
• 第五步：链接主程序。
• 第六步：链接插入的动态库。
• 第七步：执行弱符号绑定
• 第八步：执行初始化方法。
• 第九步：查找入口点并返回。

【第八步执行初始化方法】initializeMainExecutable();

• 进入initializeMainExecutable源码,主要是循环遍历，都会执行runInitializers方法

void initializeMainExecutable()
{
	// record that we've reached this step
	gLinkContext.startedInitializingMainExecutable = true;

	// run initialzers for any inserted dylibs  为所有插入的 dylibs 执行initialzers
	ImageLoader::InitializerTimingList initializerTimes[allImagesCount()];
	initializerTimes[0].count = 0;
	const size_t rootCount = sImageRoots.size();
	if ( rootCount > 1 ) {
		for(size_t i=1; i < rootCount; ++i) {
		//核心
			sImageRoots[i]->runInitializers(gLinkContext, initializerTimes[0]);
		}
	}
	
	// run initializers for main executable and everything it brings up  
	//运行主可执行文件及其弹出的所有文件的初始化项
	sMainExecutable->runInitializers(gLinkContext, initializerTimes[0]);
	
	// register cxa_atexit() handler to run static terminators in all loaded images when this process exits
	//注册cxa_atexit()处理程序，在进程退出时在所有加载的图像中运行静态终止符
	if ( gLibSystemHelpers != NULL ) 
		(*gLibSystemHelpers->cxa_atexit)(&runAllStaticTerminators, NULL, NULL);

	// dump info if requested
	if ( sEnv.DYLD_PRINT_STATISTICS )
		ImageLoader::printStatistics((unsigned int)allImagesCount(), initializerTimes[0]);
	if ( sEnv.DYLD_PRINT_STATISTICS_DETAILS )
		ImageLoaderMachO::printStatisticsDetails((unsigned int)allImagesCount(), initializerTimes[0]);
}

• 进入initializeMainExecutable源码，其核心代码是processInitializers函数的调用

void ImageLoader::runInitializers(const LinkContext& context, InitializerTimingList& timingInfo)
{
	uint64_t t1 = mach_absolute_time();
	mach_port_t thisThread = mach_thread_self();
	ImageLoader::UninitedUpwards up;
	up.count = 1;
	up.imagesAndPaths[0] = { this, this->getPath() };
	//核心
	processInitializers(context, thisThread, timingInfo, up);
	context.notifyBatch(dyld_image_state_initialized, false);
	mach_port_deallocate(mach_task_self(), thisThread);
	uint64_t t2 = mach_absolute_time();
	fgTotalInitTime += (t2 - t1);
}

• 进入processInitializers函数的源码实现，其中对镜像列表调用recursiveInitialization函数进行递归实例化

// To handle dangling dylibs which are upward linked but not downward, all upward linked dylibs
// have their initialization postponed until after the recursion through downward dylibs
// has completed.
//
void ImageLoader::processInitializers(const LinkContext& context, mach_port_t thisThread,
									 InitializerTimingList& timingInfo, ImageLoader::UninitedUpwards& images)
{
	uint32_t maxImageCount = context.imageCount()+2;
	ImageLoader::UninitedUpwards upsBuffer[maxImageCount];
	ImageLoader::UninitedUpwards& ups = upsBuffer[0];
	ups.count = 0;
	// Calling recursive init on all images in images list, building a new list of
	// uninitialized upward dependencies.
	//对图像列表中的所有图像调用递归init，构建一个新的列表
	for (uintptr_t i=0; i < images.count; ++i) {
	//核心
		images.imagesAndPaths[i].first->recursiveInitialization(context, thisThread, images.imagesAndPaths[i].second, timingInfo, ups);
	}
	// If any upward dependencies remain, init them.
	if ( ups.count > 0 )
		processInitializers(context, thisThread, timingInfo, ups);
}

• 全局搜索recursiveInitialization(cons函数,其源码实现如下

void ImageLoader::recursiveInitialization(const LinkContext& context, mach_port_t this_thread, const char* pathToInitialize,
										  InitializerTimingList& timingInfo, UninitedUpwards& uninitUps)
{
	recursive_lock lock_info(this_thread);
	recursiveSpinLock(lock_info);//递归加锁

	if ( fState < dyld_image_state_dependents_initialized-1 ) {
		uint8_t oldState = fState;
		// break cycles 结束递归
		fState = dyld_image_state_dependents_initialized-1;
		try {
			// initialize lower level libraries first
			for(unsigned int i=0; i < libraryCount(); ++i) {
				ImageLoader* dependentImage = libImage(i);
				if ( dependentImage != NULL ) {
					// don't try to initialize stuff "above" me yet
					if ( libIsUpward(i) ) {
						uninitUps.imagesAndPaths[uninitUps.count] = { dependentImage, libPath(i) };
						uninitUps.count++;
					}
					else if ( dependentImage->fDepth >= fDepth ) {
						dependentImage->recursiveInitialization(context, this_thread, libPath(i), timingInfo, uninitUps);
					}
                }
			}
			//*******核心********
			// record termination order
			if ( this->needsTermination() )
				context.terminationRecorder(this);

			// let objc know we are about to initialize this image
			//让objc知道我们要初始化这个镜像
			uint64_t t1 = mach_absolute_time();
			fState = dyld_image_state_dependents_initialized;
			oldState = fState;
			context.notifySingle(dyld_image_state_dependents_initialized, this, &timingInfo);
			
			// initialize this image
			//初始化 image
			bool hasInitializers = this->doInitialization(context);

			// let anyone know we finished initializing this image
			// 初始化完成
			fState = dyld_image_state_initialized;
			oldState = fState;
			context.notifySingle(dyld_image_state_initialized, this, NULL);
			//*******核心********
			if ( hasInitializers ) {
				uint64_t t2 = mach_absolute_time();
				timingInfo.addTime(this->getShortName(), t2-t1);
			}
		}
		catch (const char* msg) {
			// this image is not initialized
			fState = oldState;
			recursiveSpinUnLock();
			throw;
		}
	}
	
	recursiveSpinUnLock();
}

• 在这里，需要分成两部分探索，一部分是notifySingle函数，一部分是doInitialization函数，首先探索notifySingle函数

notifySingle函数

• 全局搜索notifySingle(函数,其重点是(*sNotifyObjCInit)(image->getRealPath(),
  image->machHeader());这句

static void notifySingle(dyld_image_states state, const ImageLoader* image, ImageLoader::InitializerTimingList* timingInfo)
{
	//dyld::log("notifySingle(state=%d, image=%s)\n", state, image->getPath());
	std::vector<dyld_image_state_change_handler>* handlers = stateToHandlers(state, sSingleHandlers);
	if ( handlers != NULL ) {
		dyld_image_info info;
		info.imageLoadAddress	= image->machHeader();
		info.imageFilePath		= image->getRealPath();
		info.imageFileModDate	= image->lastModified();
		for (std::vector<dyld_image_state_change_handler>::iterator it = handlers->begin(); it != handlers->end(); ++it) {
			const char* result = (*it)(state, 1, &info);
			if ( (result != NULL) && (state == dyld_image_state_mapped) ) {
				//fprintf(stderr, "  image rejected by handler=%p\n", *it);
				// make copy of thrown string so that later catch clauses can free it
				const char* str = strdup(result);
				throw str;
			}
		}
	}
	if ( state == dyld_image_state_mapped ) {
		// <rdar://problem/7008875> Save load addr + UUID for images from outside the shared cache
		if ( !image->inSharedCache() ) {
			dyld_uuid_info info;
			if ( image->getUUID(info.imageUUID) ) {
				info.imageLoadAddress = image->machHeader();
				addNonSharedCacheImageUUID(info);
			}
		}
	}
	if ( (state == dyld_image_state_dependents_initialized) && (sNotifyObjCInit != NULL) && image->notifyObjC() ) {
		uint64_t t0 = mach_absolute_time();
		dyld3::ScopedTimer timer(DBG_DYLD_TIMING_OBJC_INIT, (uint64_t)image->machHeader(), 0, 0);
		//********核心**********
		(*sNotifyObjCInit)(image->getRealPath(), image->machHeader());
		//********核心**********
		uint64_t t1 = mach_absolute_time();
		uint64_t t2 = mach_absolute_time();
		uint64_t timeInObjC = t1-t0;
		uint64_t emptyTime = (t2-t1)*100;
		if ( (timeInObjC > emptyTime) && (timingInfo != NULL) ) {
			timingInfo->addTime(image->getShortName(), timeInObjC);
		}
	}
    // mach message csdlc about dynamically unloaded images
	if ( image->addFuncNotified() && (state == dyld_image_state_terminated) ) {
		notifyKernel(*image, false);
		const struct mach_header* loadAddress[] = { image->machHeader() };
		const char* loadPath[] = { image->getPath() };
		notifyMonitoringDyld(true, 1, loadAddress, loadPath);
	}
}

• 全局搜索sNotifyObjCInit，发现没有找到实现，但是有赋值操作

void registerObjCNotifiers(_dyld_objc_notify_mapped mapped, _dyld_objc_notify_init init, _dyld_objc_notify_unmapped unmapped)
{
	// record functions to call
	sNotifyObjCMapped	= mapped;
	//*****赋值******
	sNotifyObjCInit		= init;
	sNotifyObjCUnmapped = unmapped;

	// call 'mapped' function with all images mapped so far
	try {
		notifyBatchPartial(dyld_image_state_bound, true, NULL, false, true);
	}
	catch (const char* msg) {
		// ignore request to abort during registration
	}

	// <rdar://problem/32209809> call 'init' function on all images already init'ed (below libSystem)
	for (std::vector<ImageLoader*>::iterator it=sAllImages.begin(); it != sAllImages.end(); it++) {
		ImageLoader* image = *it;
		if ( (image->getState() == dyld_image_state_initialized) && image->notifyObjC() ) {
			dyld3::ScopedTimer timer(DBG_DYLD_TIMING_OBJC_INIT, (uint64_t)image->machHeader(), 0, 0);
			(*sNotifyObjCInit)(image->getRealPath(), image->machHeader());
		}
	}
}

• 搜索registerObjCNotifiers在哪里调用了，发现在_dyld_objc_notify_register进行了调用

void _dyld_objc_notify_register(_dyld_objc_notify_mapped    mapped,
                                _dyld_objc_notify_init      init,
                                _dyld_objc_notify_unmapped  unmapped)
{
//******调用点*******
	dyld::registerObjCNotifiers(mapped, init, unmapped);
}

• 在dyld源码中搜索_dyld_objc_notify_register函数的调用点，你就会发现竟然没有。那怎么办呢？试一下libobjc中存不存在？在libobjc中搜索调用点，发现在_objc_init源码中调用了该方法，并传入了参数，所以sNotifyObjCInit的赋值的就是objc中的load_images，而load_images会调用所有的+load方法。所以综上所述，notifySingle是一个回调函数

void _objc_init(void)
{
    static bool initialized = false;
    if (initialized) return;
    initialized = true;
    
    // fixme defer initialization until an objc-using image is found?
    environ_init();
    tls_init();
    static_init();
    runtime_init();
    exception_init();
    cache_init();
    _imp_implementationWithBlock_init();
//*******调用点********
    _dyld_objc_notify_register(&map_images, load_images, unmap_image);

#if __OBJC2__
    didCallDyldNotifyRegister = true;
#endif
}

• 进入load_images函数，查看一下是否调用了所有的load函数。

void
load_images(const char *path __unused, const struct mach_header *mh)
{
    if (!didInitialAttachCategories && didCallDyldNotifyRegister) {
        didInitialAttachCategories = true;
        loadAllCategories();
    }

    // Return without taking locks if there are no +load methods here.
    if (!hasLoadMethods((const headerType *)mh)) return;

    recursive_mutex_locker_t lock(loadMethodLock);

    // Discover load methods
    {
        mutex_locker_t lock2(runtimeLock);
        prepare_load_methods((const headerType *)mh);
    }

    // Call +load methods (without runtimeLock - re-entrant)
    //*****调用load方法*****
    call_load_methods();
}

• 进入call_load_methods源码实现，可以发现其核心是通过do-while循环调用+load方法

void call_load_methods(void)
{
    static bool loading = NO;
    bool more_categories;

    loadMethodLock.assertLocked();

    // Re-entrant calls do nothing; the outermost call will finish the job.
    if (loading) return;
    loading = YES;

    void *pool = objc_autoreleasePoolPush();

    do {
        // 1. Repeatedly call class +loads until there aren't any more
        while (loadable_classes_used > 0) {
        //******循环调用load方法******
            call_class_loads();
        }

        // 2. Call category +loads ONCE
        more_categories = call_category_loads();

        // 3. Run more +loads if there are classes OR more untried categories
    } while (loadable_classes_used > 0  ||  more_categories);

    objc_autoreleasePoolPop(pool);

    loading = NO;
}

• 进入call_class_loads源码实现，了解到这里调用的load方法证实我们前文提及的类的load方法

static void call_class_loads(void)
{
    int i;
    
    // Detach current loadable list.
    struct loadable_class *classes = loadable_classes;
    int used = loadable_classes_used;
    loadable_classes = nil;
    loadable_classes_allocated = 0;
    loadable_classes_used = 0;
    
    // Call all +loads for the detached list.
    for (i = 0; i < used; i++) {
        Class cls = classes[i].cls;
        load_method_t load_method = (load_method_t)classes[i].method;
        if (!cls) continue; 

        if (PrintLoading) {
            _objc_inform("LOAD: +[%s load]\n", cls->nameForLogging());
        }
        //*****调用load******
        (*load_method)(cls, @selector(load));
    }
    
    // Destroy the detached list.
    if (classes) free(classes);
}

正好对应上堆栈中显示的堆栈信息：

总结：
load的源码链为：_dyld_start --> dyldbootstrap::start --> dyld::_main --> dyld::initializeMainExecutable --> ImageLoader::runInitializers --> ImageLoader::processInitializers --> ImageLoader::recursiveInitialization --> dyld::notifySingle(是一个回调处理) --> sNotifyObjCInit --> load_images(libobjc.A.dylib)

思考：_objc_init是什么时候调用的呢？

doInitialization函数

• 在recursiveInitialization递归函数的源码实现，发现我们忽略了一个函数doInitialization
  

• 进入doInitialization函数的源码实现,就会发现执行了两个函数doImageInit和doModInitFunctions函数

bool ImageLoaderMachO::doInitialization(const LinkContext& context)
{
	CRSetCrashLogMessage2(this->getPath());

	// mach-o has -init and static initializers
	doImageInit(context);
	doModInitFunctions(context);
	
	CRSetCrashLogMessage2(NULL);
	
	return (fHasDashInit || fHasInitializers);
}

• 进入doImageInit源码实现，其核心主要是for循环加载方法的调用，这里需要注意的一点是，libSystem的初始化必须先运行
  

• 进入doModInitFunctions源码实现，这个方法中加载了所有Cxx文件
  

• 但是走到这里，还是没有找到_objc_init的调用！！！不要慌我们加一个_objc_init符号断点，查看一下调用_objc_init前的堆栈信息。

• 在libsystem中查找libSystem_initializer，查看其中的实现
  

• 根据前面的堆栈信息，我们发现走的是libSystem_initializer中会调用libdispatch_init函数，而这个函数的源码是在libdispatch开源库中的，在libdispatch中搜索libdispatch_init
  

• 进入_os_object_init源码实现，其源码实现调用了_objc_init函数
  

• 结合上面的分析，从初始化_objc_init注册的_dyld_objc_notify_register的参数2，即load_images，到sNotifySingle --> sNotifyObjCInie=参数2 到sNotifyObjcInit()调用，形成了一个闭环

总结： _objc_init的源码链：_dyld_start --> dyldbootstrap::start --> dyld::_main --> dyld::initializeMainExecutable --> ImageLoader::runInitializers --> ImageLoader::processInitializers --> ImageLoader::recursiveInitialization --> doInitialization -->libSystem_initializer（libSystem.B.dylib） --> _os_object_init（libdispatch.dylib） --> _objc_init(libobjc.A.dylib)

综上所述：dyld加载流程图