本篇文章主要是探索程序启动流程。

load方法断点

首先我们来个简单程序

static __attribute__((constructor)) void hfmain()
{
    NSLog(@"hello HF");
}

int main(int argc, char * argv[]) {
    NSString * appDelegateClassName;
    @autoreleasepool {
        // Setup code that might create autoreleased objects goes here.
        appDelegateClassName = NSStringFromClass([AppDelegate class]);
    }
    return UIApplicationMain(argc, argv, nil, appDelegateClassName);
}

在viewcontroller.m 里添加load方法
@interface ViewController ()

@end

@implementation ViewController

+ (void)load {
    NSLog(@"[%s]", __FUNCTION__);
}

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

@end
2021-07-13 16:34:47.731823+0800 Dyld启动流程[19287:6264922][+[ViewController load]]
2021-07-13 16:34:54.092403+0800 Dyld启动流程[19287:6264922] hello HF

通过打印我们知道+load > c++构造函数 > main
接下来我们看看+load方法的函数调用堆栈

image.png

_dyld_start->dyldbootstrap::start->dyld::_main->dyld dyld::initializeMainExecutable->ImageLoader::runInitializers->dyld ImageLoader::processInitializers->ImageLoader::recursiveInitialization->dyld::notifySingle->load_images
可以看到+load方法的调用函数堆栈，接下来我们就可以顺着这条主线去dyld源码里面看是否是这样的一个流程，dyld-852目前最新的源码，很可惜并不能调试，所以我们只能去看代码，顺着断点里的主线一步步研究

load流程分析

1 _dyld_start

_dyld_start调用了dyldbootstrap::start

image.png

2 dyldbootstrap::start

image.png

3 _main

_main函数有点大，截图不过来，有兴趣的可以去下载源码看，这边就附上_main函数的流程

image.png

紧接着我们顺着主线来到initializeMainExecutable

4 initializeMainExecutable

image.png

5 runInitializers

image.png

[图片上传中...(image.png-642a8d-1626161970567-0)]

6 processInitializers

image.png

7 recursiveInitialization

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);

    if ( fState < dyld_image_state_dependents_initialized-1 ) {
        uint8_t oldState = fState;
        // break cycles
        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);
                    }
                }
            }
            
            // record termination order
            if ( this->needsTermination() )
                context.terminationRecorder(this);

            // let objc know we are about to initialize this image
            uint64_t t1 = mach_absolute_time();
            fState = dyld_image_state_dependents_initialized;
            oldState = fState;
            context.notifySingle(dyld_image_state_dependents_initialized, this, &timingInfo); // dyld_image_state_dependents_initialized
            
            // initialize this image
            bool hasInitializers = this->doInitialization(context);  // 加载系统库，系统库初始化注册类和所有load方法

            // let anyone know we finished initializing this image
            fState = dyld_image_state_initialized;
            oldState = fState;
            context.notifySingle(dyld_image_state_initialized, this, NULL); // 调用了所有类的load方法
            
            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();
}

看到这里面有调用到notifySingle

8 notifySingle

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
        // <rdar://problem/50432671> Include UUIDs for shared cache dylibs in all image info when using private mapped shared caches
        if (!image->inSharedCache()
            || (gLinkContext.sharedRegionMode == ImageLoader::kUsePrivateSharedRegion)) {
            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);
        (*sNotifyObjCInit)(image->getRealPath(), image->machHeader());
        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);
    }
}

其实在源码中有两个notifySingle函数，但是我们通过真机里面断点，查看汇编代码来确定该函数。

9 _dyld_objc_notify_register的引出

(*sNotifyObjCInit)(image->getRealPath(), image->machHeader()); 这边正是调用load_Images函数从而调用我们的+load方法。但是这边sNotifyObjCInit是个函数指针，所以一定有地方进行赋值操作

image.png

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

最后面找到了这里，而_dyld_objc_notify_register在objc_init方法中有看到调用

image.png

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)
    call_load_methods();
}

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) {
            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;
}

上面就是调用的类的+load方法
虽然我们通过+load断点一步步跟踪大概知道了流程，但是这个load_images方法是什么时候注册的我们并不知道.接下来我们通过断点_objc_init来看看什么时候调用

_objc_init 调用流程

image.png

从函数堆栈中我们可以看到也是从dyld_start开始，只是后面的流程略有不同，那我们就来看看流程走向
dyld ImageLoaderMachO::doInitialization->dyld ImageLoaderMachO::doModInitFunctions->libSystem.B.dylib libSystem_initializer->libdispatch.dylib libdispatch_init->libdispatch.dylib _os_object_init

doInitialization

看源码recursiveInitialization确实调用了doInitialization

image.png

doModInitFunctions

image.png

libSystem

接下来我们来看看libSystem的库源码
__attribute__((constructor)) static void libSystem_initializer(int argc, const char* argv[], const char* envp[], const char* apple[], const struct ProgramVars* vars)这边是构造函数，也就是默认会调用的函数，而在函数里面会调用到libdispatch_init()刚好串起来。

c++构造方法流程分析

image.png

为什么load方法在c++构造方法之前？

image.png

源码地址

https://opensource.apple.com/tarballs/libdispatch/
https://opensource.apple.com/tarballs/Libsystem/
https://opensource.apple.com/tarballs/objc4/
https://opensource.apple.com/tarballs/dyld/