`map_images`和`load_images`（上）
在上一篇文章中，我们探索了dyld的加载流程，dyld在初始化动态库的时候程序在_objc_init中通过_dyld_objc_notify_register()调用map_images和load_images这两个函数。接下来我们就来研究一下map_images和load_images这两个函数都做了什么操作。
上一篇文章中我们也知道_objc_init初始化的时候，还进行了很多的init操作。
```js
void _objc_init(void) {
// fixme defer initialization until an objc-using image is found?
environ_init(); // 环境变量的初始化
tls_init(); // 为每一条线程创建析构函数 tls：线程的局部存储
static_init(); // 运行c++的静态构造函数
runtime_init(); // 初始化分类和类表
exception_init(); // 初始化异常处理系统 Called by map_images()
if OBJC2
cache_t::init(); // 初始化缓存
endif
_imp_implementationWithBlock_init(); // mac os 处理 _dyld_objc_notify_register(&map_images, load_images, unmap_image); } ``` 我们先来看一下这些初始化操作都做了什么
environ_init
```js void environ_init(void) { bool PrintHelp = false; bool PrintOptions = false; bool maybeMallocDebugging = false;
for (char p = _NSGetEnviron(); p != nil; p++) {
......
if (0 == strncmp(p, "OBJC_HELP=", 10)) {
PrintHelp = true;
continue;
}
if (0 == strncmp(p, "OBJC_PRINT_OPTIONS=", 19)) {
PrintOptions = true;
continue;
}
......
}
......
// Print OBJC_HELP and OBJC_PRINT_OPTIONS output.
if (PrintHelp || PrintOptions) {
if (PrintHelp) {
_objc_inform("Objective-C runtime debugging. Set variable=YES to enable.");
_objc_inform("OBJC_HELP: describe available environment variables");
if (PrintOptions) {
_objc_inform("OBJC_HELP is set");
}
_objc_inform("OBJC_PRINT_OPTIONS: list which options are set");
}
if (PrintOptions) {
_objc_inform("OBJC_PRINT_OPTIONS is set");
}
for (size_t i = 0; i < sizeof(Settings)/sizeof(Settings[0]); i++) {
const option_t opt = &Settings[i];
if (PrintHelp) _objc_inform("%s: %s", opt->env, opt->help);
if (PrintOptions && opt->var) _objc_inform("%s is set", opt->env);
}
}
}
``
我们可以看到这里处理的是我们配置的一些环境变量，我们可以在工程的Scheme的Arguments`中加入变量看一下控制台的打印日志
我们看到这里打印的是我们环境变量的配置信息，我们可以在这里获取想要改变的环境变量，然后在
Scheme进行修改，如想要关闭指针优化就在Scheme中配置OBJC_DISABLE_NONPOINTER_ISA:YES即可，还有打印所有实现+load方法的类或分类的配置OBJC_PRINT_LOAD_METHODS，打印dyld加载的所有imageOBJC_PRINT_IMAGES等等，
runtime_init
js
void runtime_init(void) {
objc::unattachedCategories.init(32); // 初始化分类表
objc::allocatedClasses.init(); // 初始化类表
}
初始化分类及类的表，对于分类及类的加载就会在这两张表中进行插入数据。
load_images
先来看一下其内部源码 ```js 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(); } ``` 很简单，加载所有分类，查找load方法，执行所有load方法，我们先看一下怎么查找load方法的
js
void prepare_load_methods(const headerType *mhdr) {
size_t count, i;
runtimeLock.assertLocked();
// 获取所有的非懒加载类
classref_t const *classlist = _getObjc2NonlazyClassList(mhdr, &count);
for (i = 0; i < count; i++) {
schedule_class_load(remapClass(classlist[i]));
}
// 获取所有的非懒加载分类
category_t * const *categorylist = _getObjc2NonlazyCategoryList(mhdr, &count);
for (i = 0; i < count; i++) {
category_t *cat = categorylist[i];
Class cls = remapClass(cat->cls);
if (!cls) continue; // category for ignored weak-linked class
if (cls->isSwiftStable()) {
_objc_fatal("Swift class extensions and categories on Swift "
"classes are not allowed to have +load methods");
}
realizeClassWithoutSwift(cls, nil);
ASSERT(cls->ISA()->isRealized());
add_category_to_loadable_list(cat);
}
}
先获取所有的非懒加载类，类分为懒加载类与非懒加载类，只要重写load方法都是非懒加载类或非懒加载分类，类通过schedule_class_load递归调用其父类的schedule_class_load，然后使用add_class_to_loadable_list将类添加到loadable_classes中，每个元素是一个名为loadable_class结构体，其中包含了类和其load方法IMP。
js
void add_class_to_loadable_list(Class cls) {
IMP method;
loadMethodLock.assertLocked();
method = cls->getLoadMethod(); // 获取load方法实现
if (!method) return; // Don't bother if cls has no +load method
if (PrintLoading) {
_objc_inform("LOAD: class '%s' scheduled for +load", cls->nameForLogging());
}
// 扩容
if (loadable_classes_used == loadable_classes_allocated) {
loadable_classes_allocated = loadable_classes_allocated*2 + 16;
loadable_classes = (struct loadable_class *) realloc(loadable_classes, loadable_classes_allocated * sizeof(struct loadable_class));
}
// 保存类及load方法
loadable_classes[loadable_classes_used].cls = cls;
loadable_classes[loadable_classes_used].method = method;
loadable_classes_used++; //指针指向下一地址
}
类的load方法找完后，再找分懒加载分类的load方法，add_category_to_loadable_list将分类添加到loadable_categories中，每个元素是一个名为loadable_categories结构体，其中包含了分类和其load方法IMP，和类的区别就是，类会递归调用父类，分类只会调用本类。下面我们来看一下call_load_methods()是如果执行load方法的
```js 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; }
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()); } (*load_method)(cls, @selector(load)); } // Destroy the detached list. if (classes) free(classes); }
static bool call_category_loads(void){ int i, shift; bool new_categories_added = NO; // Detach current loadable list. struct loadable_category *cats = loadable_categories; int used = loadable_categories_used; int allocated = loadable_categories_allocated; loadable_categories = nil; loadable_categories_allocated = 0; loadable_categories_used = 0;
// Call all +loads for the detached list. for (i = 0; i < used; i++) { Category cat = cats[i].cat; load_method_t load_method = (load_method_t)cats[i].method; Class cls; if (!cat) continue; cls = _category_getClass(cat); if (cls && cls->isLoadable()) { if (PrintLoading) { _objc_inform("LOAD: +[%s(%s) load]\n", cls->nameForLogging(), _category_getName(cat)); } (*load_method)(cls, @selector(load)); cats[i].cat = nil; } } ...... return new_categories_added;
}
``
在这个方法中，对获取到的类和分类两个list进行遍历，由于我们在存储的时候已经存储了IMP，所以可以直接使用IMP进行调用load方法。在类的列表中，由于结构体的一个元素就是class，另一个就是load的IMP，所以使用(*load_method)(cls, @selector(load))就是直接调用类的load`的方法。而在分类中，就是通过分类拿到类，然后再进行调用。
map_images
同样源码先行
```js void map_images(unsigned count, const char * const paths[], const struct mach_header * const mhdrs[]) { mutex_locker_t lock(runtimeLock); return map_images_nolock(count, paths, mhdrs); }
void map_images_nolock(unsigned mhCount, const char * const mhPaths[], const struct mach_header * const mhdrs[]) { static bool firstTime = YES; header_info *hList[mhCount]; uint32_t hCount; size_t selrefCount = 0; // 共享缓存的优化处理 if (firstTime) { preopt_init(); } ......
// Find all images with Objective-C metadata.
hCount = 0; // 统计所以的类 int totalClasses = 0; int unoptimizedTotalClasses = 0; { uint32_t i = mhCount; while (i--) { ...... } }
if (firstTime) {
sel_init(selrefCount); // 初始化c++的构造和析构函数 arr_init(); //初始化自动释放池、散列表、关联对象 }
if (hCount > 0) {
_read_images(hList, hCount, totalClasses, unoptimizedTotalClasses);
}
firstTime = NO;
// Call image load funcs after everything is set up.
for (auto func : loadImageFuncs) {
for (uint32_t i = 0; i < mhCount; i++) {
func(mhdrs[i]);
}
}
内部其实是调用`map_images_nolock`，第一次进入会先去执行`preopt_init`，其内部就是优化共享缓存的处理js
void preopt_init(void){
......
const uintptr_t start = (uintptr_t)_dyld_get_shared_cache_range(&length);
if (start) {
objc::dataSegmentsRanges.setSharedCacheRange(start, start + length);
}
// opt not set at compile time in order to detect too-early usage
const char failure = nil;
opt = &_objc_opt_data; //共享缓存的处理
if (DisablePreopt) { // 环境变量，关闭dyld共享缓存优化
// OBJC_DISABLE_PREOPTIMIZATION is set
// If opt->version != VERSION then you continue at your own risk.
failure = "(by OBJC_DISABLE_PREOPTIMIZATION)";
}
......
if (failure) {
// All preoptimized selector references are invalid.
preoptimized = NO;
opt = nil;
disableSharedCacheOptimizations();
} else {
// Valid optimization data written by dyld shared cache
preoptimized = YES;
}
}
接下来`map_images_nolock`使用循环统计所有的类，再次初始化c++的构造和析构函数，初始化自动释放池、散列表、关联对象，然后调用`_read_images`js
void _read_images(header_info hList, uint32_t hCount, int totalClasses, int unoptimizedTotalClasses) {
header_info hi;
uint32_t hIndex;
size_t count;
size_t i;
Class *resolvedFutureClasses = nil;
size_t resolvedFutureClassCount = 0;
static bool doneOnce;
bool launchTime = NO;
TimeLogger ts(PrintImageTimes);
runtimeLock.assertLocked();
#define EACH_HEADER \
hIndex = 0; \
hIndex < hCount && (hi = hList[hIndex]); \
hIndex++
if (!doneOnce) {
doneOnce = YES;
launchTime = YES;
...开启指针优化...
if (DisableTaggedPointers) { // 关闭NSNumber、NSString等小对象 的Tagged Pointer优化
disableTaggedPointers();
}
initializeTaggedPointerObfuscator(); // Tagged Pointer 处理
// 创建 gdb_objc_realized_classes 表，存放dyld share cache的数据
int namedClassesSize = (isPreoptimized() ? unoptimizedTotalClasses : totalClasses) * 4 / 3;
gdb_objc_realized_classes = NXCreateMapTable(NXStrValueMapPrototype, namedClassesSize);
ts.log("IMAGE TIMES: first time tasks");
}
// Fix up @selector references
static size_t UnfixedSelectors;
{
mutex_locker_t lock(selLock);
for (EACH_HEADER) {
if (hi->hasPreoptimizedSelectors()) continue;
bool isBundle = hi->isBundle();
SEL sels = _getObjc2SelectorRefs(hi, &count);
UnfixedSelectors += count;
for (i = 0; i < count; i++) {
const char name = sel_cname(sels[i]);
SEL sel = sel_registerNameNoLock(name, isBundle);
if (sels[i] != sel) {
sels[i] = sel;
}
}
}
}
ts.log("IMAGE TIMES: fix up selector references");
// Discover classes. Fix up unresolved future classes. Mark bundle classes.
bool hasDyldRoots = dyld_shared_cache_some_image_overridden();
for (EACH_HEADER) {
……
classref_t const classlist = _getObjc2ClassList(hi, &count);
bool headerIsBundle = hi->isBundle();
bool headerIsPreoptimized = hi->hasPreoptimizedClasses();
for (i = 0; i < count; i++) {
Class cls = (Class)classlist[i];
Class newCls = readClass(cls, headerIsBundle, headerIsPreoptimized);
if (newCls != cls && newCls) {
// Class was moved but not deleted. Currently this occurs
// only when the new class resolved a future class.
// Non-lazily realize the class below.
resolvedFutureClasses = (Class )
realloc(resolvedFutureClasses,
(resolvedFutureClassCount+1) * sizeof(Class));
resolvedFutureClasses[resolvedFutureClassCount++] = newCls;
}
}
}
ts.log("IMAGE TIMES: discover classes");
......
ts.log("IMAGE TIMES: discover categories");
ts.log("IMAGE TIMES: realize non-lazy classes");
ts.log("IMAGE TIMES: realize future classes");
if (DebugNonFragileIvars) {
realizeAllClasses();
}
我们现在使用的是虚拟内存(ASLR)，需要dyld进行rebase和binding操作来修复我们镜像的资源指针，指向正确的内存地址，`_read_images`首先`doneOnce`只调用一次，内部开启指针优化和`Tagged Pointer`处理，并创建一张存放dyld共享缓存数据的表`gdb_objc_realized_classes`；接下来会去修复`selector`，将指向错误的内存地址的sel修复成正确的sel内存地址，这个过程就是rebase的过程，将虚拟内存地址换成真实内存地址，下面继续修复`protocol`、`objc_msgSend_fixup`等；然后初始化所有非懒加载类，进行rw、ro等操作；遍历已标记的懒加载类，并作初始化操作；处理所以分类，包括类和元类；初始化所有未初始化的类。
这其中有个很重要的过程，`Discover classes`，发现所有的类，其内部使用`readClass`进行类的获取js
Class readClass(Class cls, bool headerIsBundle, bool headerIsPreoptimized) {
const char mangledName = cls->nonlazyMangledName();
if (missingWeakSuperclass(cls)) {
……
}
cls->fixupBackwardDeployingStableSwift();
Class replacing = nil;
if (mangledName != nullptr) {
if (Class newCls = popFutureNamedClass(mangledName)) {
if (newCls->isAnySwift()) {
……
}
class_rw_t rw = newCls->data();
const class_ro_t old_ro = rw->ro();
memcpy(newCls, cls, sizeof(objc_class));
// Manually set address-discriminated ptrauthed fields
// so that newCls gets the correct signatures.
newCls->setSuperclass(cls->getSuperclass());
newCls->initIsa(cls->getIsa());
rw->set_ro((class_ro_t )newCls->data());
newCls->setData(rw);
freeIfMutable((char )old_ro->getName());
free((void )old_ro);
addRemappedClass(cls, newCls);
replacing = cls;
cls = newCls;
}
}
if (headerIsPreoptimized && !replacing) { ...... } else { if (mangledName) { //some Swift generic classes can lazily generate their names addNamedClass(cls, mangledName, replacing); } else { Class meta = cls->ISA(); const class_ro_t *metaRO = meta->bits.safe_ro(); ASSERT(metaRO->getNonMetaclass() && "Metaclass with lazy name must have a pointer to the corresponding nonmetaclass."); ASSERT(metaRO->getNonMetaclass() == cls && "Metaclass nonmetaclass pointer must equal the original class."); } addClassTableEntry(cls); } // for future reference: shared cache never contains MH_BUNDLEs if (headerIsBundle) { cls->data()->flags |= RO_FROM_BUNDLE; cls->ISA()->data()->flags |= RO_FROM_BUNDLE; } return cls; }
static void addClassTableEntry(Class cls, bool addMeta = true) {
runtimeLock.assertLocked();
// This class is allowed to be a known class via the shared cache or via
// data segments, but it is not allowed to be in the dynamic table already.
auto &set = objc::allocatedClasses.get(); // runtime init 时初始化的表
ASSERT(set.find(cls) == set.end());
if (!isKnownClass(cls))
set.insert(cls);
if (addMeta)
addClassTableEntry(cls->ISA(), false);
}
``
可是当我们在rw、ro处进行断点，发现其并没有进入执行，所以rw、ro并不是这里初始化的，不过其内部调用addClassTableEntry初始化类，然后再次调用addClassTableEntry第二个参数为false初始化元类，并将类和元类都加入到runtime init初始化的allocatedClasses表中。readClass的作用是把已经分配过内存空间的类和元类添加到allocatedClasses`表中。
我们将初始化非懒加载类代码单独拿出来
js
// Realize non-lazy classes (for +load methods and static instances)
for (EACH_HEADER) {
classref_t const *classlist = hi->nlclslist(&count);
for (i = 0; i < count; i++) {
Class cls = remapClass(classlist[i]);
if (!cls) continue;
addClassTableEntry(cls);
if (cls->isSwiftStable()) {
if (cls->swiftMetadataInitializer()) {
_objc_fatal("Swift class %s with a metadata initializer "
"is not allowed to be non-lazy",
cls->nameForLogging());
}
// fixme also disallow relocatable classes
// We can't disallow all Swift classes because of
// classes like Swift.__EmptyArrayStorage
}
realizeClassWithoutSwift(cls, nil);
}
}
其内部同样调用了addClassTableEntry初始化类，同时还调用了realizeClassWithoutSwift，我们查看其源代码发现，realizeClassWithoutSwift才是真正的初始化本身、父类及元类，并进行rw、ro等操作。
```js
static Class realizeClassWithoutSwift(Class cls, Class previously) {
runtimeLock.assertLocked();
class_rw_t rw;
Class supercls;
Class metacls;
……
auto ro = (const class_ro_t )cls->data();
auto isMeta = ro->flags & RO_META;
if (ro->flags & RO_FUTURE) {
// This was a future class. rw data is already allocated.
rw = cls->data();
ro = cls->data()->ro();
ASSERT(!isMeta);
cls->changeInfo(RW_REALIZED|RW_REALIZING, RW_FUTURE);
} else {
// Normal class. Allocate writeable class data.
rw = objc::zalloc
if FAST_CACHE_META
if (isMeta) cls->cache.setBit(FAST_CACHE_META);
endif
// Choose an index for this class. // Sets cls->instancesRequireRawIsa if indexes no more indexes are available cls->chooseClassArrayIndex(); ……
// 递归调用 初始化 supercls 和 metacls
supercls = realizeClassWithoutSwift(remapClass(cls->getSuperclass()), nil); metacls = realizeClassWithoutSwift(remapClass(cls->ISA()), nil);
if SUPPORT_NONPOINTER_ISA
if (isMeta) { cls->setInstancesRequireRawIsa(); } else { // Disable non-pointer isa for some classes and/or platforms. // Set instancesRequireRawIsa. bool instancesRequireRawIsa = cls->instancesRequireRawIsa(); bool rawIsaIsInherited = false; static bool hackedDispatch = false; if (DisableNonpointerIsa) { // Non-pointer isa disabled by environment or app SDK version instancesRequireRawIsa = true; } else if (!hackedDispatch && 0 == strcmp(ro->getName(), "OS_object")) { // hack for libdispatch et al - isa also acts as vtable pointer hackedDispatch = true; instancesRequireRawIsa = true; } else if (supercls && supercls->getSuperclass() && supercls->instancesRequireRawIsa()) { // This is also propagated by addSubclass() // but nonpointer isa setup needs it earlier. // Special case: instancesRequireRawIsa does not propagate // from root class to root metaclass instancesRequireRawIsa = true; rawIsaIsInherited = true; }
if (instancesRequireRawIsa) { cls->setInstancesRequireRawIsaRecursively(rawIsaIsInherited); } } // SUPPORT_NONPOINTER_ISA
endif
// Update superclass and metaclass in case of remapping cls->setSuperclass(supercls); // 设置父类 cls->initClassIsa(metacls); // 设置元类
// Reconcile instance variable offsets / layout. // This may reallocate class_ro_t, updating our ro variable. if (supercls && !isMeta) reconcileInstanceVariables(cls, supercls, ro); // Set fastInstanceSize if it wasn't set already. cls->setInstanceSize(ro->instanceSize); // Copy some flags from ro to rw if (ro->flags & RO_HAS_CXX_STRUCTORS) { cls->setHasCxxDtor(); if (! (ro->flags & RO_HAS_CXX_DTOR_ONLY)) { cls->setHasCxxCtor(); } }
// Propagate the associated objects forbidden flag from ro or from // the superclass. if ((ro->flags & RO_FORBIDS_ASSOCIATED_OBJECTS) || (supercls && supercls->forbidsAssociatedObjects())) { rw->flags |= RW_FORBIDS_ASSOCIATED_OBJECTS; }
// Connect this class to its superclass's subclass lists if (supercls) { addSubclass(supercls, cls); } else { addRootClass(cls); }
// Attach categories methodizeClass(cls, previously);
return cls;
}
``
里面我们也清晰的看到了rw是在该函数中进行的alloc，而ro已经在编译的时候存在了，在这里只是赋值给rw`。
总结
load_images就是调用load方法，所以load方法先于main函数。其流程是会把所有非懒加载类的load方法放到loadable_classes中，把分类的load方法loadable_categories中，然后对其进行遍历，找到相关的类和方法直接使用存储的load method调用。
- load的查找流程是父类->子类->分类
- 因为子类中会递归查找父类的load方法，所以我们重写load时是不需要使用[super load]的
- 两个分类都重写了load，则看编译器顺序，哪个后编译，哪个先执行
- 获取和调用load方法时都进行了加锁操作，所以load方法是线程安全的
非懒加载类的真正初始化是由realizeClassWithoutSwift进行的，其内部开辟rw的内存空间，将ro放入rw中。
rebase：将指向错误的内存地址指针修复成指向正确的内存地址，将虚拟内存地址换成真实内存地址