iOS类的加载原理（上）
2021-07-14 本文已影响0人
似水流年_9ebe
前言
iOS-dyld加载分析一文中我们介绍了dyld加载分析，那么我们的类是如何被加载进来的，它的原理又是什么呢？我们带着这些疑问开始我们的探索之旅。
_objc_init分析
为什么从_objc_init分析iOS-dyld加载分析一文中有介绍，这里不做解释了，我们先贴下这个函数的代码，如下图：
1
environ_init();就是环境变量的初始化，方便我们调试程序。
2
这些相关变量我们可以在xcode中的Arguments中的Environment Variables中配置，这里不再进行一一展开说明。
tls_init(); 关于线程key的绑定 - ⽐如每线程数据的析构函数。
static_init();运⾏C ++静态构造函数。在dyld调⽤我们的静态构造函数之前，
libobjc 会调⽤ _objc_init（），因此我们必须⾃⼰做如下图：
3
runtime_init(); 如图
4
运行时环境初如化，里面主要是unAttachedCategories，allocatedClasses 后面会分析。
exception_init();初始化libobjc的异常处理系统。
catche_init()缓存条件初始化。
_dyld_objc_notify_register(&map_images, load_images, unmap_image);是重点分析对象，这里会调用map_images,那么map_imges到底做了什么？我们将进行着重分析。
map_images分析
** _dyld_objc_notify_register这个函数的调用，会先进入 map_images， load_images这两个函数中， map_images是引用类型，也就是指针传递， map_images会跟着内部的变化而变化(不断的循环和递归)，而load_images（主要就是调用load方法）是指针拷贝。
我们看下 map_images**函数的代码，如图：
4
我们再看下map_images_nolock函数的代码，如下：
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;
// Perform first-time initialization if necessary.
// This function is called before ordinary library initializers.
// fixme defer initialization until an objc-using image is found?
if (firstTime) {
preopt_init();
}
if (PrintImages) {
_objc_inform("IMAGES: processing %u newly-mapped images...\n", mhCount);
}
// Find all images with Objective-C metadata.
hCount = 0;
// Count classes. Size various table based on the total.
int totalClasses = 0;
int unoptimizedTotalClasses = 0;
{
uint32_t i = mhCount;
while (i--) {
const headerType *mhdr = (const headerType *)mhdrs[I];
auto hi = addHeader(mhdr, mhPaths[i], totalClasses, unoptimizedTotalClasses);
if (!hi) {
// no objc data in this entry
continue;
}
if (mhdr->filetype == MH_EXECUTE) {
// Size some data structures based on main executable's size
#if __OBJC2__
// If dyld3 optimized the main executable, then there shouldn't
// be any selrefs needed in the dynamic map so we can just init
// to a 0 sized map
if ( !hi->hasPreoptimizedSelectors() ) {
size_t count;
_getObjc2SelectorRefs(hi, &count);
selrefCount += count;
_getObjc2MessageRefs(hi, &count);
selrefCount += count;
}
#else
_getObjcSelectorRefs(hi, &selrefCount);
#endif
#if SUPPORT_GC_COMPAT
// Halt if this is a GC app.
if (shouldRejectGCApp(hi)) {
_objc_fatal_with_reason
(OBJC_EXIT_REASON_GC_NOT_SUPPORTED,
OS_REASON_FLAG_CONSISTENT_FAILURE,
"Objective-C garbage collection "
"is no longer supported.");
}
#endif
}
hList[hCount++] = hi;
if (PrintImages) {
_objc_inform("IMAGES: loading image for %s%s%s%s%s\n",
hi->fname(),
mhdr->filetype == MH_BUNDLE ? " (bundle)" : "",
hi->info()->isReplacement() ? " (replacement)" : "",
hi->info()->hasCategoryClassProperties() ? " (has class properties)" : "",
hi->info()->optimizedByDyld()?" (preoptimized)":"");
}
}
}
// Perform one-time runtime initialization that must be deferred until
// the executable itself is found. This needs to be done before
// further initialization.
// (The executable may not be present in this infoList if the
// executable does not contain Objective-C code but Objective-C
// is dynamically loaded later.
if (firstTime) {
sel_init(selrefCount);
arr_init();
#if SUPPORT_GC_COMPAT
// Reject any GC images linked to the main executable.
// We already rejected the app itself above.
// Images loaded after launch will be rejected by dyld.
for (uint32_t i = 0; i < hCount; i++) {
auto hi = hList[I];
auto mh = hi->mhdr();
if (mh->filetype != MH_EXECUTE && shouldRejectGCImage(mh)) {
_objc_fatal_with_reason
(OBJC_EXIT_REASON_GC_NOT_SUPPORTED,
OS_REASON_FLAG_CONSISTENT_FAILURE,
"%s requires Objective-C garbage collection "
"which is no longer supported.", hi->fname());
}
}
#endif
#if TARGET_OS_OSX
// Disable +initialize fork safety if the app is too old (< 10.13).
// Disable +initialize fork safety if the app has a
// __DATA,__objc_fork_ok section.
// if (!dyld_program_sdk_at_least(dyld_platform_version_macOS_10_13)) {
// DisableInitializeForkSafety = true;
// if (PrintInitializing) {
// _objc_inform("INITIALIZE: disabling +initialize fork "
// "safety enforcement because the app is "
// "too old.)");
// }
// }
for (uint32_t i = 0; i < hCount; i++) {
auto hi = hList[I];
auto mh = hi->mhdr();
if (mh->filetype != MH_EXECUTE) continue;
unsigned long size;
if (getsectiondata(hi->mhdr(), "__DATA", "__objc_fork_ok", &size)) {
DisableInitializeForkSafety = true;
if (PrintInitializing) {
_objc_inform("INITIALIZE: disabling +initialize fork "
"safety enforcement because the app has "
"a __DATA,__objc_fork_ok section");
}
}
break; // assume only one MH_EXECUTE image
}
#endif
}
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]);
}
}
}
** _read_images(hList, hCount, totalClasses, unoptimizedTotalClasses);**就是读取我们的镜像文件。
我们再看下它的代码：
/***********************************************************************
* _read_images
* Perform initial processing of the headers in the linked
* list beginning with headerList.
*
* Called by: map_images_nolock
*
* Locking: runtimeLock acquired by map_images
**********************************************************************/
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;
#if SUPPORT_NONPOINTER_ISA
// Disable non-pointer isa under some conditions.
# if SUPPORT_INDEXED_ISA
// Disable nonpointer isa if any image contains old Swift code
for (EACH_HEADER) {
if (hi->info()->containsSwift() &&
hi->info()->swiftUnstableVersion() < objc_image_info::SwiftVersion3)
{
DisableNonpointerIsa = true;
if (PrintRawIsa) {
_objc_inform("RAW ISA: disabling non-pointer isa because "
"the app or a framework contains Swift code "
"older than Swift 3.0");
}
break;
}
}
# endif
# if TARGET_OS_OSX
// Disable non-pointer isa if the app is too old
// (linked before OS X 10.11)
// if (!dyld_program_sdk_at_least(dyld_platform_version_macOS_10_11)) {
// DisableNonpointerIsa = true;
// if (PrintRawIsa) {
// _objc_inform("RAW ISA: disabling non-pointer isa because "
// "the app is too old.");
// }
// }
// Disable non-pointer isa if the app has a __DATA,__objc_rawisa section
// New apps that load old extensions may need this.
for (EACH_HEADER) {
if (hi->mhdr()->filetype != MH_EXECUTE) continue;
unsigned long size;
if (getsectiondata(hi->mhdr(), "__DATA", "__objc_rawisa", &size)) {
DisableNonpointerIsa = true;
if (PrintRawIsa) {
_objc_inform("RAW ISA: disabling non-pointer isa because "
"the app has a __DATA,__objc_rawisa section");
}
}
break; // assume only one MH_EXECUTE image
}
# endif
#endif
if (DisableTaggedPointers) {
disableTaggedPointers();
}
initializeTaggedPointerObfuscator();
if (PrintConnecting) {
_objc_inform("CLASS: found %d classes during launch", totalClasses);
}
// namedClasses
// Preoptimized classes don't go in this table.
// 4/3 is NXMapTable's load factor
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) {
if (! mustReadClasses(hi, hasDyldRoots)) {
// Image is sufficiently optimized that we need not call readClass()
continue;
}
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");
// Fix up remapped classes
// Class list and nonlazy class list remain unremapped.
// Class refs and super refs are remapped for message dispatching.
if (!noClassesRemapped()) {
for (EACH_HEADER) {
Class *classrefs = _getObjc2ClassRefs(hi, &count);
for (i = 0; i < count; i++) {
remapClassRef(&classrefs[I]);
}
// fixme why doesn't test future1 catch the absence of this?
classrefs = _getObjc2SuperRefs(hi, &count);
for (i = 0; i < count; i++) {
remapClassRef(&classrefs[I]);
}
}
}
ts.log("IMAGE TIMES: remap classes");
#if SUPPORT_FIXUP
// Fix up old objc_msgSend_fixup call sites
for (EACH_HEADER) {
message_ref_t *refs = _getObjc2MessageRefs(hi, &count);
if (count == 0) continue;
if (PrintVtables) {
_objc_inform("VTABLES: repairing %zu unsupported vtable dispatch "
"call sites in %s", count, hi->fname());
}
for (i = 0; i < count; i++) {
fixupMessageRef(refs+i);
}
}
ts.log("IMAGE TIMES: fix up objc_msgSend_fixup");
#endif
// Discover protocols. Fix up protocol refs.
for (EACH_HEADER) {
extern objc_class OBJC_CLASS_$_Protocol;
Class cls = (Class)&OBJC_CLASS_$_Protocol;
ASSERT(cls);
NXMapTable *protocol_map = protocols();
bool isPreoptimized = hi->hasPreoptimizedProtocols();
// Skip reading protocols if this is an image from the shared cache
// and we support roots
// Note, after launch we do need to walk the protocol as the protocol
// in the shared cache is marked with isCanonical() and that may not
// be true if some non-shared cache binary was chosen as the canonical
// definition
if (launchTime && isPreoptimized) {
if (PrintProtocols) {
_objc_inform("PROTOCOLS: Skipping reading protocols in image: %s",
hi->fname());
}
continue;
}
bool isBundle = hi->isBundle();
protocol_t * const *protolist = _getObjc2ProtocolList(hi, &count);
for (i = 0; i < count; i++) {
readProtocol(protolist[i], cls, protocol_map,
isPreoptimized, isBundle);
}
}
ts.log("IMAGE TIMES: discover protocols");
// Fix up @protocol references
// Preoptimized images may have the right
// answer already but we don't know for sure.
for (EACH_HEADER) {
// At launch time, we know preoptimized image refs are pointing at the
// shared cache definition of a protocol. We can skip the check on
// launch, but have to visit @protocol refs for shared cache images
// loaded later.
if (launchTime && hi->isPreoptimized())
continue;
protocol_t **protolist = _getObjc2ProtocolRefs(hi, &count);
for (i = 0; i < count; i++) {
remapProtocolRef(&protolist[I]);
}
}
ts.log("IMAGE TIMES: fix up @protocol references");
// Discover categories. Only do this after the initial category
// attachment has been done. For categories present at startup,
// discovery is deferred until the first load_images call after
// the call to _dyld_objc_notify_register completes. rdar://problem/53119145
if (didInitialAttachCategories) {
for (EACH_HEADER) {
load_categories_nolock(hi);
}
}
ts.log("IMAGE TIMES: discover categories");
// Category discovery MUST BE Late to avoid potential races
// when other threads call the new category code before
// this thread finishes its fixups.
// +load handled by prepare_load_methods()
// 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);
}
}
ts.log("IMAGE TIMES: realize non-lazy classes");
// Realize newly-resolved future classes, in case CF manipulates them
if (resolvedFutureClasses) {
for (i = 0; i < resolvedFutureClassCount; i++) {
Class cls = resolvedFutureClasses[I];
if (cls->isSwiftStable()) {
_objc_fatal("Swift class is not allowed to be future");
}
realizeClassWithoutSwift(cls, nil);
cls->setInstancesRequireRawIsaRecursively(false/*inherited*/);
}
free(resolvedFutureClasses);
}
ts.log("IMAGE TIMES: realize future classes");
if (DebugNonFragileIvars) {
realizeAllClasses();
}
// Print preoptimization statistics
if (PrintPreopt) {
static unsigned int PreoptTotalMethodLists;
static unsigned int PreoptOptimizedMethodLists;
static unsigned int PreoptTotalClasses;
static unsigned int PreoptOptimizedClasses;
for (EACH_HEADER) {
if (hi->hasPreoptimizedSelectors()) {
_objc_inform("PREOPTIMIZATION: honoring preoptimized selectors "
"in %s", hi->fname());
}
else if (hi->info()->optimizedByDyld()) {
_objc_inform("PREOPTIMIZATION: IGNORING preoptimized selectors "
"in %s", hi->fname());
}
classref_t const *classlist = _getObjc2ClassList(hi, &count);
for (i = 0; i < count; i++) {
Class cls = remapClass(classlist[i]);
if (!cls) continue;
PreoptTotalClasses++;
if (hi->hasPreoptimizedClasses()) {
PreoptOptimizedClasses++;
}
const method_list_t *mlist;
if ((mlist = cls->bits.safe_ro()->baseMethods())) {
PreoptTotalMethodLists++;
if (mlist->isFixedUp()) {
PreoptOptimizedMethodLists++;
}
}
if ((mlist = cls->ISA()->bits.safe_ro()->baseMethods())) {
PreoptTotalMethodLists++;
if (mlist->isFixedUp()) {
PreoptOptimizedMethodLists++;
}
}
}
}
_objc_inform("PREOPTIMIZATION: %zu selector references not "
"pre-optimized", UnfixedSelectors);
_objc_inform("PREOPTIMIZATION: %u/%u (%.3g%%) method lists pre-sorted",
PreoptOptimizedMethodLists, PreoptTotalMethodLists,
PreoptTotalMethodLists
? 100.0*PreoptOptimizedMethodLists/PreoptTotalMethodLists
: 0.0);
_objc_inform("PREOPTIMIZATION: %u/%u (%.3g%%) classes pre-registered",
PreoptOptimizedClasses, PreoptTotalClasses,
PreoptTotalClasses
? 100.0*PreoptOptimizedClasses/PreoptTotalClasses
: 0.0);
_objc_inform("PREOPTIMIZATION: %zu protocol references not "
"pre-optimized", UnfixedProtocolReferences);
}
#undef EACH_HEADER
}
这里的代码过长，我们只分析比较主要的，其它的大家可以自行阅读。
我们先介绍下read_images大体的流程：
1.条件控制进⾏⼀次的加载。
2.修复预编译阶段的@selector的混乱问题。
3.错误混乱的类处理。
4.修复重映射一些滑被镜像文件加载进来的类。
5.修复一些消息！
6.当我们的类里面有协议的时候：readProtocol。
8.分类处理。
9.类的加载处理。
10.没有被处理的类，优化那些被侵犯的类。
这里第8，9，10三个是我们要进行着重分析的，因为这些都是有关类的加载。
initializeTaggedPointerObfuscator();这行代码是对小对象的一些混淆，代码如图：
4
objc_debug_taggedpointer_obfuscator &= ~(_OBJC_TAG_EXT_MASK | _OBJC_TAG_NO_OBFUSCATION_MASK);就是编码取值。
int namedClassesSize =
(isPreoptimized() ? unoptimizedTotalClasses : totalClasses) * 4 / 3;
gdb_objc_realized_classes =
NXCreateMapTable(NXStrValueMapPrototype, namedClassesSize);
这里是创建表，** namedClassesSize是创建表的大小，这个大小为什么是乘4除3？我们接着分析。
乘4除3是负载因子，namedClassesSize是要开启的总容积，假如我们总共要开辟的大小是8， 那么也就是84/3，当我们往里面添加的时候，什么时候扩容呢，也就是x3/4 = 8*4/3，所以x不能超过8。
上文中我们有介绍过runtime_init()这个里面也在创建表，代码如下：
objc::unattachedCategories.init(32);
objc::allocatedClasses.init();
objc::allocatedClasses.init();这个表与** gdb_objc_realized_classes这个表有什么区别呢，我们接着分析，
** gdb_objc_realized_classes这个表是NXMapTable类型，这个是不管是否实现与否的总表。
objc::allocatedClasses.init();这个表是已经开辟过的表。
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;
}
}
}
}
这段代码是修复selector的引用。
下面我们来分析这段代码：
for (EACH_HEADER) {
if (! mustReadClasses(hi, hasDyldRoots)) {
// Image is sufficiently optimized that we need not call readClass()
continue;
}
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;
}
}
}
这段代码在执行过程中没有进入resolvedFutureClasses这个方法的调用，这是为什么呢，我们继续往往下分析。
resolvedFutureClasses这个方法的意思是未来要处理的类，处理没有删除干净的类（会引起混乱）。
我们重新运行，断点这行代码** Class newCls = readClass(cls, headerIsBundle, headerIsPreoptimized);，如图所示：
5
这里做了类的处理，那么它就是我们要研究的重点，下面我们将对readClass**这个函数进行分析。
我们先贴下这个函数的代码，然后分析：
/***********************************************************************
* readClass
* Read a class and metaclass as written by a compiler.
* Returns the new class pointer. This could be:
* - cls
* - nil (cls has a missing weak-linked superclass)
* - something else (space for this class was reserved by a future class)
*
* Note that all work performed by this function is preflighted by
* mustReadClasses(). Do not change this function without updating that one.
*
* Locking: runtimeLock acquired by map_images or objc_readClassPair
**********************************************************************/
Class readClass(Class cls, bool headerIsBundle, bool headerIsPreoptimized)
{
const char *mangledName = cls->nonlazyMangledName();
if (missingWeakSuperclass(cls)) {
// No superclass (probably weak-linked).
// Disavow any knowledge of this subclass.
if (PrintConnecting) {
_objc_inform("CLASS: IGNORING class '%s' with "
"missing weak-linked superclass",
cls->nameForLogging());
}
addRemappedClass(cls, nil);
cls->setSuperclass(nil);
return nil;
}
cls->fixupBackwardDeployingStableSwift();
Class replacing = nil;
if (mangledName != nullptr) {
if (Class newCls = popFutureNamedClass(mangledName)) {
// This name was previously allocated as a future class.
// Copy objc_class to future class's struct.
// Preserve future's rw data block.
if (newCls->isAnySwift()) {
_objc_fatal("Can't complete future class request for '%s' "
"because the real class is too big.",
cls->nameForLogging());
}
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) {
// class list built in shared cache
// fixme strict assert doesn't work because of duplicates
// ASSERT(cls == getClass(name));
ASSERT(mangledName == nullptr || getClassExceptSomeSwift(mangledName));
} 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;
}
这段代码是这个函数的核心：
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);
我们在终端po mangledName是一个"NSStackBlock"字符串，o为了方便，我们先加入：
printf("%s- RO---%s",__func__, mangledName);
然后重新运行，可以看到有RoPerson的打印。
我们再加一些判断代码，来判断我们自己的类是怎么加载的，如下：
const char *RoPersonName = "RoPerson";
if (strcmp(mangledName, RoPersonName)==0) {
printf("%s---RO-----%s\n",__func__, mangledName);
}
然后再重新运行，断点，如图所示：
5
发现**if (Class newCls = popFutureNamedClass(mangledName)) **这里根本没进来。
接着会调这段代码：
if (mangledName) { //some Swift generic classes can lazily generate their names
addNamedClass(cls, mangledName, replacing);
}
加入到哈希map中去。
addClassTableEntry(cls);这个函数的代码如下：
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();
ASSERT(set.find(cls) == set.end());
if (!isKnownClass(cls))
set.insert(cls);
if (addMeta)
addClassTableEntry(cls->ISA(), false);
}
if (!isKnownClass(cls))
set.insert(cls); 如果当前类不存在（未知的）会插入到被当前被加载类中去，同时会判断是否要把元类插入进来。
realizeClass的分析
我们为了方便调试，可以在类相关的地方加入以下代码方便我们调试
const char *mangledName = cls->nonlazyMangledName();
const char *RoPersonName = "RoPerson";
if (strcmp(mangledName, RoPersonName) == 0) {
printf("%s -RO: 要研究的: - %s\n",__func__,mangledName);
}
然后我们在类相关的地方打个断点调试，如图所示代码：
6
从上图可以看出mangledName就是RoPerson，断点继续执行，发现走到了** realizeClassWithoutSwift(cls, nil);**这行代码，这行代码就是类的实现，也就是核心重点。
我们先把这段代码贴出来，如下：
/***********************************************************************
* realizeClassWithoutSwift
* Performs first-time initialization on class cls,
* including allocating its read-write data.
* Does not perform any Swift-side initialization.
* Returns the real class structure for the class.
* Locking: runtimeLock must be write-locked by the caller
*****************************核心重点*****************************************/
static Class realizeClassWithoutSwift(Class cls, Class previously)
{
runtimeLock.assertLocked();
class_rw_t *rw;
Class supercls;
Class metacls;
if (!cls) return nil;
if (cls->isRealized()) {
validateAlreadyRealizedClass(cls);
return cls;
}
ASSERT(cls == remapClass(cls));
// fixme verify class is not in an un-dlopened part of the shared cache?
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. ro -> rw
rw = objc::zalloc<class_rw_t>();
rw->set_ro(ro);
rw->flags = RW_REALIZED|RW_REALIZING|isMeta;
cls->setData(rw);
}
cls->cache.initializeToEmptyOrPreoptimizedInDisguise();
#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();
if (PrintConnecting) {
_objc_inform("CLASS: realizing class '%s'%s %p %p #%u %s%s",
cls->nameForLogging(), isMeta ? " (meta)" : "",
(void*)cls, ro, cls->classArrayIndex(),
cls->isSwiftStable() ? "(swift)" : "",
cls->isSwiftLegacy() ? "(pre-stable swift)" : "");
}
// Realize superclass and metaclass, if they aren't already.
// This needs to be done after RW_REALIZED is set above, for root classes.
// This needs to be done after class index is chosen, for root metaclasses.
// This assumes that none of those classes have Swift contents,
// or that Swift's initializers have already been called.
// fixme that assumption will be wrong if we add support
// for ObjC subclasses of Swift classes.
supercls = realizeClassWithoutSwift(remapClass(cls->getSuperclass()), nil);
metacls = realizeClassWithoutSwift(remapClass(cls->ISA()), nil);
#if SUPPORT_NONPOINTER_ISA
if (isMeta) {
// Metaclasses do not need any features from non pointer ISA
// This allows for a faspath for classes in objc_retain/objc_release.
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);
cls->initClassIsa(metacls);
// 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;
}
下面我们就断点调试这个函数，如图所示：
7
这里的cls就是RoPerson。
我们再看下ro这个变量，如图：
8
说明ro已经有了数据。
我们再查看baseMethodList如图所示：
9
这里发现baseMethodList没有方法列表，而RoPerson明明是有方法的，这又是为什么呢？
这是因为这里只是一个基本数据结构，还没有加载进来，我们接着往下分析。
// Normal class. Allocate writeable class data. ro -> rw
rw = objc::zalloc<class_rw_t>();
rw->set_ro(ro);
rw->flags = RW_REALIZED|RW_REALIZING|isMeta;
cls->setData(rw);
这段代码的操作是把ro（就是上面data中的数据）复制到rw中去。
cls->setInstancesRequireRawIsa();这行代码说明了元类的isa地址与类的名字是一样的。
supercls = realizeClassWithoutSwift(remapClass(cls->getSuperclass()), nil);
metacls = realizeClassWithoutSwift(remapClass(cls->ISA()), nil);
cls->setSuperclass(supercls);
cls->initClassIsa(metacls);
这说明了之前介绍的isa的指向和继承链的关系。
我们在这个函数再加一些判断代码，再重新断点调试，如图：
截屏2021-07-17 上午9.51.38.png
接着我们在methodizeClass这个函数也加入测试代码，如图：
10
在这里我们在查看下baseMethodList，如图：
11
还是没有方法，这又是为什么呢，方法列表为什么没有，我们接着分析methodizeClass
methodizeClass分析
我们在methodizeClass这个函数继续执行，如图所示：
12
在这里发现list是有值的，但是打印不出来的。
我们看下** prepareMethodLists**这个函数的代码，如下：
static void
prepareMethodLists(Class cls, method_list_t **addedLists, int addedCount,
bool baseMethods, bool methodsFromBundle, const char *why)
{
runtimeLock.assertLocked();
if (addedCount == 0) return;
// There exist RR/AWZ/Core special cases for some class's base methods.
// But this code should never need to scan base methods for RR/AWZ/Core:
// default RR/AWZ/Core cannot be set before setInitialized().
// Therefore we need not handle any special cases here.
if (baseMethods) {
ASSERT(cls->hasCustomAWZ() && cls->hasCustomRR() && cls->hasCustomCore());
} else if (cls->cache.isConstantOptimizedCache()) {
cls->setDisallowPreoptCachesRecursively(why);
} else if (cls->allowsPreoptInlinedSels()) {
#if CONFIG_USE_PREOPT_CACHES
SEL *sels = (SEL *)objc_opt_offsets[OBJC_OPT_INLINED_METHODS_START];
SEL *sels_end = (SEL *)objc_opt_offsets[OBJC_OPT_INLINED_METHODS_END];
if (method_lists_contains_any(addedLists, addedLists + addedCount, sels, sels_end - sels)) {
cls->setDisallowPreoptInlinedSelsRecursively(why);
}
#endif
}
// Add method lists to array.
// Reallocate un-fixed method lists.
// The new methods are PREPENDED to the method list array.
for (int i = 0; i < addedCount; i++) {
method_list_t *mlist = addedLists[I];
ASSERT(mlist);
// Fixup selectors if necessary
if (!mlist->isFixedUp()) {
fixupMethodList(mlist, methodsFromBundle, true/*sort*/);
}
}
// If the class is initialized, then scan for method implementations
// tracked by the class's flags. If it's not initialized yet,
// then objc_class::setInitialized() will take care of it.
if (cls->isInitialized()) {
objc::AWZScanner::scanAddedMethodLists(cls, addedLists, addedCount);
objc::RRScanner::scanAddedMethodLists(cls, addedLists, addedCount);
objc::CoreScanner::scanAddedMethodLists(cls, addedLists, addedCount);
}
}
** fixupMethodList**再看下这个函数的代码：
static void
fixupMethodList(method_list_t *mlist, bool bundleCopy, bool sort)
{
runtimeLock.assertLocked();
ASSERT(!mlist->isFixedUp());
// fixme lock less in attachMethodLists ?
// dyld3 may have already uniqued, but not sorted, the list
if (!mlist->isUniqued()) {
mutex_locker_t lock(selLock);
// Unique selectors in list.
for (auto& meth : *mlist) {
const char *name = sel_cname(meth.name());
// printf("上面 : %s - %p\n",name,meth.name());
meth.setName(sel_registerNameNoLock(name, bundleCopy));
}
}
// Sort by selector address.
// Don't try to sort small lists, as they're immutable.
// Don't try to sort big lists of nonstandard size, as stable_sort
// won't copy the entries properly.
if (sort && !mlist->isSmallList() && mlist->entsize() == method_t::bigSize) {
method_t::SortBySELAddress sorter;
std::stable_sort(&mlist->begin()->big(), &mlist->end()->big(), sorter);
}
// Mark method list as uniqued and sorted.
// Can't mark small lists, since they're immutable.
if (!mlist->isSmallList()) {
mlist->setFixedUp();
}
}
const char *name = sel_cname(meth.name());
meth.setName(sel_registerNameNoLock(name, bundleCopy));
这两行代码拿到sel，再把sel和地址放到meth中去，然后根据地址排序。
这个时候我们走完这个函数，然后再打印一下ro,如图：
12
发现baseMethodList依然没有数据，我们明明把它加进来了，这是为什么？我们接着分析。
懒加载类与非懒加载类
在这个函数methodizeClass的prepareMethodLists执行完后，直接跳过了if (rwe) rwe->methods.attachLists(&list, 1);这行代码，那么rwe是什么时候赋值的， 我们后面再分析。
我们回过头看下_read_images这个函数的这几行代码，如下：
// 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;
const char *mangledName = cls->nonlazyMangledName();
// 测试
const char *RoPersonName = "RoPerson";
if (strcmp(mangledName, RoPersonName) == 0) {
printf("%s Realize non-lazy classes-RO: 要研究的: - %s\n",__func__,mangledName);
}
// 测试
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);
}
}
Realize non-lazy classes (for +load methods and static instances)这行注释说明只要非懒加载的类实现Load方法就可以断点进入上面的代码。
为了节约内存，提高速度通过懒加载类实现。
如果没有实现load方法的是在哪加载的呢，我们往下分析。
我们在realizeClassWithoutSwift这个函数的开头部分加入以下代码，如下：
auto ro = (const class_ro_t *)cls->data();
auto isMeta = ro->flags & RO_META;
// 测试
const char *mangledName = cls->nonlazyMangledName();
const char *RoPersonName = "RoPerson";
if (strcmp(mangledName, RoPersonName) == 0) {
printf("%s realizeClassWithoutSwift: 要研究的: - %s\n",__func__,mangledName);
}
// 测试
（一定要把RoPerson中的load方法关掉）我们运行，断点，并bt打印堆栈，如图：
13
realizeClassWithoutSwift是由realizeClassMaybeSwiftMaybeRelock调起的，而它又是lookUpImpOrForward调起的。
这也说明了只要在类发送消息的时候，类会进行加载。
14
分类的本质探索
realizeClassWithoutSwift这个函数有以下一行代码，如下所示：
// Attach categories
methodizeClass(cls, previously);
这行代码对我们的方法，协议有什么影响，我们往下分析。
我们在main函数加RoPerson的分类，如下：
@interface RoPerson (RO) <NSObject>
@property (nonatomic, copy) NSString *cate_name;
@property (nonatomic, assign) int cate_age;
- (void)cate_instanceMethod1;
- (void)cate_instanceMethod2;
+ (void)cate_classMethod3;
@end
@implementation RoPerson (RO)
- (void)cate_instanceMethod1{
NSLog(@"%s",__func__);
}
- (void)cate_instanceMethod2{
NSLog(@"%s",__func__);
}
+ (void)cate_classMethod3{
NSLog(@"%s",__func__);
}
@end
我们用clang命令把它翻译成C++代码。
在最后面我们发现以下代码：
static struct _category_t *L_OBJC_LABEL_CATEGORY_$ [1] __attribute__((used, section ("__DATA, __objc_catlist,regular,no_dead_strip")))= {
&_OBJC_$_CATEGORY_RoPerson_$_RO,
};
这行也就是RoPerson的分类，我们看下_category_t是什么类型，搜索后，如下：
15
那么分类也是一个结构体，里面有
name分类的名字
const struct _method_list_t *instance_methods;
const struct _method_list_t *class_methods;
为什么对象方法和类方法都在里面呢？
因为分类没有元类的缘故。
我们在搜索下** _category_t**关键字，发现以下代码：
static struct _category_t _OBJC_$_CATEGORY_RoPerson_$_RO __attribute__ ((used, section ("__DATA,__objc_const"))) =
{
"RoPerson",
0, // &OBJC_CLASS_$_RoPerson,
(const struct _method_list_t *)&_OBJC_$_CATEGORY_INSTANCE_METHODS_RoPerson_$_RO,
(const struct _method_list_t *)&_OBJC_$_CATEGORY_CLASS_METHODS_RoPerson_$_RO,
(const struct _protocol_list_t *)&_OBJC_CATEGORY_PROTOCOLS_$_RoPerson_$_RO,
(const struct _prop_list_t *)&_OBJC_$_PROP_LIST_RoPerson_$_RO,
};
为什么这里的name是** RoPerson而不是Ro呢，因为这里只是编译，还没有进入运行时，只是随机赋了个值。
那么这些分析跟我们的源码是否一致，我们在源码中搜索 _category_t**找到以下代码：
struct category_t {
const char *name;
classref_t cls;
WrappedPtr<method_list_t, PtrauthStrip> instanceMethods;
WrappedPtr<method_list_t, PtrauthStrip> classMethods;
struct protocol_list_t *protocols;
struct property_list_t *instanceProperties;
// Fields below this point are not always present on disk.
struct property_list_t *_classProperties;
method_list_t *methodsForMeta(bool isMeta) {
if (isMeta) return classMethods;
else return instanceMethods;
}
property_list_t *propertiesForMeta(bool isMeta, struct header_info *hi);
protocol_list_t *protocolsForMeta(bool isMeta) {
if (isMeta) return nullptr;
else return protocols;
}
};
发现有些不一样，比如对象方法和类方法。
那么分类是怎么加载的呢，由于篇幅太长，我们这里先引入一下。
分类加载的引入
我们看下methodizeClass这个函数中的objc::unattachedCategories.attachToClass(cls, previously,
ATTACH_METACLASS);这行代码，
我们看下attachToClass这个函数，代码如下：
void attachToClass(Class cls, Class previously, int flags)
{
runtimeLock.assertLocked();
ASSERT((flags & ATTACH_CLASS) ||
(flags & ATTACH_METACLASS) ||
(flags & ATTACH_CLASS_AND_METACLASS));
auto &map = get();
auto it = map.find(previously);
if (it != map.end()) {
category_list &list = it->second;
if (flags & ATTACH_CLASS_AND_METACLASS) {
int otherFlags = flags & ~ATTACH_CLASS_AND_METACLASS;
attachCategories(cls, list.array(), list.count(), otherFlags | ATTACH_CLASS);
attachCategories(cls->ISA(), list.array(), list.count(), otherFlags | ATTACH_METACLASS);
} else {
attachCategories(cls, list.array(), list.count(), flags);
}
map.erase(it);
}
}
做了一些方法的处理，那么它又是怎么控制的呢，我们继分析，
我们先看下rwe,auto methodizeClass这个函数由这行代码rwe = rw->ext();为rwe控制，我们看下：
15
从上图可以看出extAllocIfNeeded可以条件判断，我们搜下** extAllocIfNeeded，得到如下：
attachCategories在这个函数中找到了调用，在添加分类的时候rwe就是能够赋上值的。
addMethods_finish添加方法的时候也会赋值。
class_addProtocol添加协议的时候也会赋值。
_class_addProperty添加属性的时候也会赋值。
objc_duplicateClass重命名的时候也会赋值。
也就是说动态处理时候才会对rwe的处理。
我们重点关注attachCategories分类的加载。
我们搜索attachCategories**
attachToClass有调用。
load_categories_nolock有调用。
后面会详细介绍。
结语
这篇文章介绍了类的加载大致流程，_objc_init分析，map_images分析，realizeClass的分析，methodizeClass分析，懒加载类与非懒加载类，分类的本质探索，类的加载原理还未介绍完，我们将在类的加载原理（下）再次介绍。
