其他分享
首页 > 其他分享> > iOS-底层原理 17：类的加载（上）

iOS-底层原理 17：类的加载（上）

作者：互联网

在上一篇iOS-底层原理 16：dyld与objc的关联文章中，我们理解了dyld与objc是如何关联的，本文的主要目的是理解类的相关信息是如何加载到内存的，其中重点关注map_images和load_images

其中代码通过编译，读取到Mach-O可执行文件中，再从Mach-O中读取到内存，如下图所示

watermark,size_16,text_QDUxQ1RP5Y2a5a6i,color_FFFFFF,t_100,g_se,x_10,y_10,shadow_90,type_ZmFuZ3poZW5naGVpdGk=

dyld与objc的关联 以及数据加载流程

 

map_images：加载镜像文件到内存

在查看源码之前，首先需要说明为什么map_images有&，而load_images没有

map_images源码流程

map_images方法的主要作用是将Mach-O中的类信息加载到内存

 

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[])
{
//...省略

// Find all images with Objective-C metadata.查找所有带有Objective-C元数据的映像
    hCount = 0;

// Count classes. Size various table based on the total.计算类的个数
int totalClasses = 0;
int unoptimizedTotalClasses = 0;
//代码块：作用域，进行局部处理，即局部处理一些事件
{
//...省略
}

//...省略

if (hCount > 0) {
//加载镜像文件
_read_images(hList, hCount, totalClasses, unoptimizedTotalClasses);
}

    firstTime = NO;

// Call image load funcs after everything is set up.一切设置完成后，调用镜像加载功能。
for (auto func : loadImageFuncs) {
for (uint32_t i = 0; i < mhCount; i++) {
func(mhdrs[i]);
}
}
}

_read_images 源码实现

_read_images主要是主要是加载类信息，即类、分类、协议等，进入_read_images源码实现，主要分为以下几部分：

1、条件控制进行的一次加载

在doneOnce流程中通过NXCreateMapTable 创建表，存放类信息，即创建一张类的哈希表``gdb_objc_realized_classes，其目的是为了类查找方便、快捷

 

if (!doneOnce) {

//...省略

// namedClasses
// Preoptimized classes don't go in this table.
// 4/3 is NXMapTable's load factor
int namedClassesSize = 
(isPreoptimized() ? unoptimizedTotalClasses : totalClasses) * 4 / 3;
//创建表（哈希表key-value），目的是查找快
    gdb_objc_realized_classes =
NXCreateMapTable(NXStrValueMapPrototype, namedClassesSize);

    ts.log("IMAGE TIMES: first time tasks");
}

查看gdb_objc_realized_classes的注释说明，这个哈希表用于存储不在共享缓存且已命名类，无论类是否实现，其容量是类数量的4/3

 

// This is a misnomer: gdb_objc_realized_classes is actually a list of 
// named classes not in the dyld shared cache, whether realized or not.
//gdb_objc_realized_classes实际上是不在dyld共享缓存中的已命名类的列表，无论是否实现
NXMapTable *gdb_objc_realized_classes;  // exported for debuggers in objc-gdb.h

2、修复预编译阶段的@selector的混乱问题

主要是通过通过_getObjc2SelectorRefs拿到Mach_O中的静态段__objc_selrefs，遍历列表调用sel_registerNameNoLock将SEL添加到namedSelectors哈希表中

 

// Fix up @selector references 修复@selector引用
//sel 不是简单的字符串，而是带地址的字符串
static size_t UnfixedSelectors;
{
    mutex_locker_t lock(selLock);
for (EACH_HEADER) {
if (hi->hasPreoptimizedSelectors()) continue;

bool isBundle = hi->isBundle();
//通过_getObjc2SelectorRefs拿到Mach-O中的静态段__objc_selrefs
        SEL *sels = _getObjc2SelectorRefs(hi, &count);
        UnfixedSelectors += count;
for (i = 0; i < count; i++) { //列表遍历
const char *name = sel_cname(sels[i]);
//注册sel操作，即将sel添加到
            SEL sel = sel_registerNameNoLock(name, isBundle);
if (sels[i] != sel) {//当sel与sels[i]地址不一致时，需要调整为一致的
                sels[i] = sel;
}
}
}
}

 

//      function name                 content type     section name
GETSECT(_getObjc2SelectorRefs,        SEL,             "__objc_selrefs"); 
GETSECT(_getObjc2MessageRefs,         message_ref_t,   "__objc_msgrefs"); 
GETSECT(_getObjc2Cla***efs,           Class,           "__objc_cla***efs");
GETSECT(_getObjc2SuperRefs,           Class,           "__objc_superrefs");
GETSECT(_getObjc2ClassList,           cla***ef_t const,      "__objc_classlist");
GETSECT(_getObjc2NonlazyClassList,    cla***ef_t const,      "__objc_nlclslist");
GETSECT(_getObjc2CategoryList,        category_t * const,    "__objc_catlist");
GETSECT(_getObjc2CategoryList2,       category_t * const,    "__objc_catlist2");
GETSECT(_getObjc2NonlazyCategoryList, category_t * const,    "__objc_nlcatlist");
GETSECT(_getObjc2ProtocolList,        protocol_t * const,    "__objc_protolist");
GETSECT(_getObjc2ProtocolRefs,        protocol_t *,    "__objc_protorefs");
GETSECT(getLibobjcInitializers,       UnsignedInitializer, "__objc_init_func");

 

SEL sel_registerNameNoLock(const char *name, bool copy) {
return __sel_registerName(name, 0, copy);  // NO lock, maybe copy
}

????
static SEL __sel_registerName(const char *name, bool shouldLock, bool copy) 
{
    SEL result = 0;

if (shouldLock) selLock.assertUnlocked();
else selLock.assertLocked();

if (!name) return (SEL)0;

    result = search_builtins(name);
if (result) return result;

    conditional_mutex_locker_t lock(selLock, shouldLock);
auto it = namedSelectors.get().insert(name);//sel插入表
if (it.second) {
// No match. Insert.
*it.first = (const char *)sel_alloc(name, copy);
}
return (SEL)*it.first;
}

3、错误混乱的类处理

主要是从Mach-O中取出所有类，在遍历进行处理

 

//3、错误混乱的类处理
// Discover classes. Fix up unresolved future classes. Mark bundle classes.
bool hasDyldRoots = dyld_shared_cache_some_image_overridden();
//读取类：readClass
for (EACH_HEADER) {
if (! mustReadClasses(hi, hasDyldRoots)) {
// Image is sufficiently optimized that we need not call readClass()
continue;
}
//从编译后的类列表中取出所有类，即从Mach-O中获取静态段__objc_classlist，是一个cla***ef_t类型的指针
    cla***ef_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];//此时获取的cls只是一个地址
        Class newCls = readClass(cls, headerIsBundle, headerIsPreoptimized); //读取类，经过这步后，cls获取的值才是一个名字
//经过调试，并未执行if里面的流程
//初始化所有懒加载的类需要的内存空间，但是懒加载类的数据现在是没有加载到的，连类都没有初始化
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.
//将懒加载的类添加到数组中
            resolvedFutureClasses = (Class *)
realloc(resolvedFutureClasses, 
(resolvedFutureClassCount+1) * sizeof(Class));
            resolvedFutureClasses[resolvedFutureClassCount++] = newCls;
}
}
}
ts.log("IMAGE TIMES: discover classes");

所以到这步为止，类的信息目前仅存储了地址+名称

4、修复重映射一些没有被镜像文件加载进来的类

主要是将未映射的Class 和Super Class进行重映射，其中

 

//4、修复重映射一些没有被镜像文件加载进来的类
// Fix up remapped classes 修正重新映射的类
// Class list and nonlazy class list remain unremapped.类列表和非惰性类列表保持未映射
// Class refs and super refs are remapped for message dispatching.类引用和超级引用将重新映射以进行消息分发
//经过调试，并未执行if里面的流程
//将未映射的Class 和 Super Class重映射，被remap的类都是懒加载的类
if (!noClassesRemapped()) {
for (EACH_HEADER) {
Class *cla***efs = _getObjc2Cla***efs(hi, &count);//Mach-O的静态段 __objc_cla***efs
for (i = 0; i < count; i++) {
remapCla***ef(&cla***efs[i]);
}
// fixme why doesn't test future1 catch the absence of this?
        cla***efs = _getObjc2SuperRefs(hi, &count);//Mach_O中的静态段 __objc_superrefs
for (i = 0; i < count; i++) {
remapCla***ef(&cla***efs[i]);
}
}
}

ts.log("IMAGE TIMES: remap classes");

5、修复一些消息

主要是通过_getObjc2MessageRefs 获取Mach-O的静态段 __objc_msgrefs，并遍历通过fixupMessageRef将函数指针进行注册，并fix为新的函数指针

 

#if SUPPORT_FIXUP
//5、修复一些消息
// Fix up old objc_msgSend_fixup call sites
for (EACH_HEADER) {
// _getObjc2MessageRefs 获取Mach-O的静态段 __objc_msgrefs
        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());
}
//经过调试，并未执行for里面的流程
//遍历将函数指针进行注册，并fix为新的函数指针
for (i = 0; i < count; i++) {
fixupMessageRef(refs+i);
}
}

    ts.log("IMAGE TIMES: fix up objc_msgSend_fixup");
#endif

6、当类里面有协议时：readProtocol 读取协议

 

//6、当类里面有协议时：readProtocol 读取协议
// Discover protocols. Fix up protocol refs. 发现协议。修正协议参考
//遍历所有协议列表，并且将协议列表加载到Protocol的哈希表中
for (EACH_HEADER) {
extern objc_class OBJC_CLASS_$_Protocol;
//cls = Protocol类，所有协议和对象的结构体都类似，isa都对应Protocol类
    Class cls = (Class)&OBJC_CLASS_$_Protocol;
ASSERT(cls);
//获取protocol哈希表 -- protocol_map
    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 && cacheSupportsProtocolRoots) {
if (PrintProtocols) {
_objc_inform("PROTOCOLS: Skipping reading protocols in image: %s",
                         hi->fname());
}
continue;
}

    bool isBundle = hi->isBundle();
//通过_getObjc2ProtocolList 获取到Mach-O中的静态段__objc_protolist协议列表，
//即从编译器中读取并初始化protocol
    protocol_t * const *protolist = _getObjc2ProtocolList(hi, &count);
for (i = 0; i < count; i++) {
//通过添加protocol到protocol_map哈希表中
readProtocol(protolist[i], cls, protocol_map, 
                     isPreoptimized, isBundle);
}
}

ts.log("IMAGE TIMES: discover protocols");

 

/***********************************************************************
* protocols
* Returns the protocol name => protocol map for protocols.
* Locking: runtimeLock must read- or write-locked by the caller
**********************************************************************/
static NXMapTable *protocols(void)
{
static NXMapTable *protocol_map = nil;

    runtimeLock.assertLocked();

INIT_ONCE_PTR(protocol_map, 
NXCreateMapTable(NXStrValueMapPrototype, 16), 
NXFreeMapTable(v) );

return protocol_map;
}

 

protocol_t * const *protolist = _getObjc2ProtocolList(hi, &count);

 

readProtocol(protolist[i], cls, protocol_map, 
                         isPreoptimized, isBundle);

7、修复没有被加载的协议

主要是通过 _getObjc2ProtocolRefs 获取到Mach-O的静态段 __objc_protorefs（与6中的__objc_protolist并不是同一个东西），然后遍历需要修复的协议，通过remapProtocolRef比较当前协议和协议列表中的同一个内存地址的协议是否相同，如果不同则替换

 

//7、修复没有被加载的协议
// 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 && cacheSupportsProtocolRoots && hi->isPreoptimized())
continue;
//_getObjc2ProtocolRefs 获取到Mach-O的静态段 __objc_protorefs
    protocol_t **protolist = _getObjc2ProtocolRefs(hi, &count);
for (i = 0; i < count; i++) {//遍历
//比较当前协议和协议列表中的同一个内存地址的协议是否相同，如果不同则替换
remapProtocolRef(&protolist[i]);//经过代码调试，并未执行
}
}

ts.log("IMAGE TIMES: fix up @protocol references");

其中remapProtocolRef的源码实现如下

 

/***********************************************************************
* remapProtocolRef
* Fix up a protocol ref, in case the protocol referenced has been reallocated.
* Locking: runtimeLock must be read- or write-locked by the caller
**********************************************************************/
static size_t UnfixedProtocolReferences;
static void remapProtocolRef(protocol_t **protoref)
{
    runtimeLock.assertLocked();
//获取协议列表中统一内存地址的协议
    protocol_t *newproto = remapProtocol((protocol_ref_t)*protoref);
if (*protoref != newproto) {//如果当前协议 与 同一内存地址协议不同，则替换
*protoref = newproto;
        UnfixedProtocolReferences++;
}
}

8、分类处理

主要是处理分类，需要在分类初始化并将数据加载到类后才执行，对于运行时出现的分类，将分类的发现推迟推迟到对_dyld_objc_notify_register的调用完成后的第一个load_images调用为止

 

//8、分类处理
// Discover categories. Only do this after the initial category 发现分类
// 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");

9、类的加载处理

主要是实现类的加载处理，实现非懒加载类

 

// Realize non-lazy classes (for +load methods and static instances) 初始化非懒加载类，进行rw、ro等操作：realizeClassWithoutSwift
//懒加载类 -- 别人不动我，我就不动
//实现非懒加载的类，对于load方法和静态实例变量
for (EACH_HEADER) {
//通过_getObjc2NonlazyClassList获取Mach-O的静态段__objc_nlclslist非懒加载类表
        cla***ef_t const *classlist = 
_getObjc2NonlazyClassList(hi, &count);
for (i = 0; i < count; i++) {
            Class cls = remapClass(classlist[i]);

const char *mangledName  = cls->mangledName();
const char *LGPersonName = "LGPerson";

if (strcmp(mangledName, LGPersonName) == 0) {
auto kc_ro = (const class_ro_t *)cls->data();
printf("_getObjc2NonlazyClassList: 这个是我要研究的 %s \n",LGPersonName);
}

if (!cls) continue;

addClassTableEntry(cls);//插入表，但是前面已经插入过了，所以不会重新插入

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
}
//实现当前的类，因为前面readClass读取到内存的仅仅只有地址+名称，类的data数据并没有加载出来
//实现所有非懒加载的类(实例化类对象的一些信息，例如rw)
realizeClassWithoutSwift(cls, nil);
}
}

    ts.log("IMAGE TIMES: realize non-lazy classes");

10、没有被处理的类，优化那些被侵犯的类

主要是实现没有被处理的类，优化被侵犯的类

 

// 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");
}
//实现类
realizeClassWithoutSwift(cls, nil);
            cls->setInstancesRequireRawIsaRecursively(false/*inherited*/);
}
free(resolvedFutureClasses);
}

    ts.log("IMAGE TIMES: realize future classes");

if (DebugNonFragileIvars) {
//实现所有类
realizeAllClasses();
}

我们需要重点关注的是3中的readClass以及9中realizeClassWithoutSwift两个方法

readClass：读取类

readClass主要是读取类，在未调用该方法前，cls只是一个地址，执行该方法后，cls是类的名称，其源码实现如下，关键代码是addNamedClass和addClassTableEntry，源码实现如下

 

/***********************************************************************
* readClass
* Read a class and metaclass as written by a compiler. 读取编译器编写的类和元类
* Returns the new class pointer. This could be:  返回新的类指针，可能是：
* - 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->mangledName();//名字

// **CJL写的** ----如果想进入自定义，自己加一个判断
const char *LGPersonName = "LGPerson";
if (strcmp(mangledName, LGPersonName) == 0) {
        auto kc_ro = (const class_ro_t *)cls->data();
printf("%s -- 研究重点--%s\n", __func__,mangledName);
}
//当前类的父类中若有丢失的weak-linked类，则返回nil
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->superclass = nil;
return nil;
}

    cls->fixupBackwardDeployingStableSwift();
//判断是不是后期要处理的类
//正常情况下，不会走到popFutureNamedClass，因为这是专门针对未来待处理的类的操作
//通过断点调试，不会走到if流程里面，因此也不会对ro、rw进行操作
    Class replacing = nil;
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());
}
//读取class的data，设置ro、rw
//经过调试，并不会走到这里
        class_rw_t *rw = newCls->data();
const class_ro_t *old_ro = rw->ro();
memcpy(newCls, cls, sizeof(objc_class));
        rw->set_ro((class_ro_t *)newCls->data());
        newCls->setData(rw);
freeIfMutable((char *)old_ro->name);
free((void *)old_ro);

addRemappedClass(cls, newCls);

        replacing = cls;
        cls = newCls;
}
//判断是否类是否已经加载到内存
if (headerIsPreoptimized  &&  !replacing) {
// class list built in shared cache
// fixme strict assert doesn't work because of duplicates
// ASSERT(cls == getClass(name));
ASSERT(getClassExceptSomeSwift(mangledName));
} else {
addNamedClass(cls, mangledName, replacing);//加载共享缓存中的类
addClassTableEntry(cls);//插入表，即相当于从mach-O文件 读取到 内存 中
}

// 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;
}

通过源码实现，主要分为以下几步：

 

const char *mangledName() { 
// fixme can't assert locks here
ASSERT(this);

if (isRealized()  ||  isFuture()) { //这个初始化判断在lookupImp也有类似的
return data()->ro()->name;//如果已经实例化，则从ro中获取name
} else {
return ((const class_ro_t *)data())->name;//反之，从mach-O的数据data中获取name
}
}

 

/***********************************************************************
* addNamedClass 加载共享缓存中的类 插入表
* Adds name => cls to the named non-meta class map. 将name=> cls添加到命名的非元类映射
* Warns about duplicate class names and keeps the old mapping.
* Locking: runtimeLock must be held by the caller
**********************************************************************/
static void addNamedClass(Class cls, const char *name, Class replacing = nil)
{
    runtimeLock.assertLocked();
    Class old;
if ((old = getClassExceptSomeSwift(name))  &&  old != replacing) {
inform_duplicate(name, old, cls);

// getMaybeUnrealizedNonMetaClass uses name lookups.
// Classes not found by name lookup must be in the
// secondary meta->nonmeta table.
addNonMetaClass(cls);
} else {
//添加到gdb_objc_realized_classes哈希表
NXMapInsert(gdb_objc_realized_classes, name, cls);
}
ASSERT(!(cls->data()->flags & RO_META));

// wrong: constructed classes are already realized when they get here
// ASSERT(!cls->isRealized());
}

 

/***********************************************************************
* addClassTableEntry 将一个类添加到所有类的表中
* Add a class to the table of all classes. If addMeta is true,
* automatically adds the metaclass of the class as well.
* Locking: runtimeLock must be held by the caller.
**********************************************************************/
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();//开辟的类的表，在objc_init中的runtime_init就创建了表

ASSERT(set.find(cls) == set.end());

if (!isKnownClass(cls))
set.insert(cls);
if (addMeta)
//添加到allocatedClasses哈希表
addClassTableEntry(cls->ISA(), false);
}

如果我们想在readClass源码中想定位到自定义的类，可以自定义加if判断

watermark,size_16,text_QDUxQ1RP5Y2a5a6i,color_FFFFFF,t_100,g_se,x_10,y_10,shadow_90,type_ZmFuZ3poZW5naGVpdGk=

readClass中增加自定义判断

 

总结

所以综上所述，readClass的主要作用就是将Mach-O中的类读取到内存，即插入表中，但是目前的类仅有两个信息：地址以及名称，而mach-O的其中的data数据还未读取出来

realizeClassWithoutSwift：实现类

realizeClassWithoutSwift方法中有ro、rw的相关操作，这个方法在消息流程的慢速查找中有所提及,方法路径为：慢速查找(lookUpImpOrForward) -- realizeClassMaybeSwiftAndLeaveLocked -- realizeClassMaybeSwiftMaybeRelock -- realizeClassWithoutSwift（实现类）

realizeClassWithoutSwift方法主要作用是实现类，将类的data数据加载到内存中，主要有以下几部分操作：

第一步：读取data数据

读取class的data数据，并将其强转为ro，以及rw初始化和ro拷贝一份到rw中的ro

 

// fixme verify class is not in an un-dlopened part of the shared cache?
//读取class的data()，以及ro/rw创建
auto ro = (const class_ro_t *)cls->data(); //读取类结构的bits属性、//ro -- clean memory，在编译时就已经确定了内存
auto isMeta = ro->flags & RO_META; //判断元类
if (ro->flags & RO_FUTURE) {
// This was a future class. rw data is already allocated.
    rw = cls->data(); //dirty memory 进行赋值
    ro = cls->data()->ro();
ASSERT(!isMeta);
    cls->changeInfo(RW_REALIZED|RW_REALIZING, RW_FUTURE);
} else { //此时将数据读取进来了，也赋值完毕了
// Normal class. Allocate writeable class data.
    rw = objc::zalloc<class_rw_t>(); //申请开辟zalloc -- rw
    rw->set_ro(ro);//rw中的ro设置为临时变量ro
    rw->flags = RW_REALIZED|RW_REALIZING|isMeta;
    cls->setData(rw);//将cls的data赋值为rw形式
}

【第二步】递归调用 realizeClassWithoutSwift 完善 继承链

递归调用realizeClassWithoutSwift完善继承链,并设置当前类、父类、元类的rw

 

 // 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. --
//递归调用realizeClassWithoutSwift完善继承链,并处理当前类的父类、元类
//递归实现 设置当前类、父类、元类的 rw，主要目的是确定继承链 （类继承链、元类继承链）
//实现元类、父类
//当isa找到根元类之后，根元类的isa是指向自己的，不会返回nil从而导致死循环——remapClass中对类在表中进行查找的操作，如果表中已有该类，则返回一个空值；如果没有则返回当前类，这样保证了类只加载一次并结束递归
    supercls = realizeClassWithoutSwift(remapClass(cls->superclass), nil);
    metacls = realizeClassWithoutSwift(remapClass(cls->ISA()), nil);

...

// Update superclass and metaclass in case of remapping -- class 是 双向链表结构 即父子关系都确认了
// 将父类和元类给我们的类 分别是isa和父类的对应值
cls->superclass = supercls;
cls->initClassIsa(metacls);

...

// Connect this class to its superclass's subclass lists
//双向链表指向关系 父类中可以找到子类 子类中也可以找到父类
//通过addSubclass把当前类放到父类的子类列表中去
if (supercls) {
addSubclass(supercls, cls);
} else {
addRootClass(cls);
}

这里有一个问题，realizeClassWithoutSwift递归调用时，isa找到根元类之后，根元类的isa是指向自己，并不会返回nil，所以有以下递归终止条件，其目的是保证类只加载一次

 

static Class realizeClassWithoutSwift(Class cls, Class previously)
{
    runtimeLock.assertLocked();

//如果类不存在，则返回nil
if (!cls) return nil;
    如果类已经实现，则直接返回cls
if (cls->isRealized()) return cls;
ASSERT(cls == remapClass(cls));

...
}

 

/***********************************************************************
* remapClass
* Returns the live class pointer for cls, which may be pointing to 
* a class struct that has been reallocated.
* Returns nil if cls is ignored because of weak linking.
* Locking: runtimeLock must be read- or write-locked by the caller
**********************************************************************/
static Class remapClass(Class cls)
{
    runtimeLock.assertLocked();

if (!cls) return nil;//如果cls不存在，则返回nil

    auto *map = remappedClasses(NO);
if (!map)
return cls;

    auto iterator = map->find(cls);
if (iterator == map->end())
return cls;
return std::get<1>(*iterator);
}

【第三步】通过 methodizeClass 方法化类

通过methodizeClass方法，从ro中读取方法列表（包括分类中的方法）、属性列表、协议列表赋值给rw，并返回cls

 

// Attach categories 附加类别 -- 疑问：ro中也有方法列表 rw中也有方法列表，下面这个方法可以说明
//将ro数据写入到rw
methodizeClass(cls, previously);

return cls;

断点调试 realizeClassWithoutSwift

如果我们需要跟踪自定义类，同样需要_read_images方法中的第九步的realizeClassWithoutSwift调用前，以及realizeClassWithoutSwift方法中增加自定义逻辑，主要是为了方便调试自定义类

下面，开启我们的断点调试

methodizeClass：方法化类

其中methodizeClass的源码实现如下，主要分为几部分：

 

static void methodizeClass(Class cls, Class previously)
{
    runtimeLock.assertLocked();

    bool isMeta = cls->isMetaClass();
    auto rw = cls->data(); // 初始化一个rw
    auto ro = rw->ro();
    auto rwe = rw->ext();

...

// Install methods and properties that the class implements itself.
//将属性列表、方法列表、协议列表等贴到rw中
// 将ro中的方法列表加入到rw中
    method_list_t *list = ro->baseMethods();//获取ro的baseMethods
if (list) {
prepareMethodLists(cls, &list, 1, YES, isBundleClass(cls));//methods进行排序
if (rwe) rwe->methods.attachLists(&list, 1);//对rwe进行处理
}
// 加入属性
    property_list_t *proplist = ro->baseProperties;
if (rwe && proplist) {
        rwe->properties.attachLists(&proplist, 1);
}
// 加入协议
    protocol_list_t *protolist = ro->baseProtocols;
if (rwe && protolist) {
        rwe->protocols.attachLists(&protolist, 1);
}

// Root classes get bonus method implementations if they don't have 
// them already. These apply before category replacements.
if (cls->isRootMetaclass()) {
// root metaclass
addMethod(cls, @selector(initialize), (IMP)&objc_noop_imp, "", NO);
}

// Attach categories.
// 加入分类中的方法
if (previously) {
if (isMeta) {
            objc::unattachedCategories.attachToClass(cls, previously,
ATTACH_METACLASS);
} else {
// When a class relocates, categories with class methods
// may be registered on the class itself rather than on
// the metaclass. Tell attachToClass to look for those.
            objc::unattachedCategories.attachToClass(cls, previously,
ATTACH_CLASS_AND_METACLASS);
}
}
    objc::unattachedCategories.attachToClass(cls, cls,
                                             isMeta ? ATTACH_METACLASS : ATTACH_CLASS);

....
}

rwe的逻辑

方法列表加入rwe的逻辑如下：

方法如何排序

在消息流程的慢速查找流程iOS-底层原理 13：消息流程分析之慢速查找文章中，方法的查找算法是通过二分查找算法，说明sel-imp是有排序的，那么是如何排序的呢？

 

static void 
prepareMethodLists(Class cls, method_list_t **addedLists, int addedCount,
bool baseMethods, bool methodsFromBundle)
{
...

// 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*/);//排序
}
}

...
}

 

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);
            meth.name = sel_registerNameNoLock(name, bundleCopy);
}
}

// Sort by selector address.根据sel地址排序
if (sort) {
        method_t::SortBySELAddress sorter;
        std::stable_sort(mlist->begin(), mlist->end(), sorter);
}

// Mark method list as uniqued and sorted
    mlist->setFixedUp();
}

验证方法排序

下面我们可以通过调试来验证方法的排序

所以 排序前后的methodlist对比如下，所以总结如下：methodizeClass方法中实现类中方法（协议等）的序列化

watermark,size_16,text_QDUxQ1RP5Y2a5a6i,color_FFFFFF,t_100,g_se,x_10,y_10,shadow_90,type_ZmFuZ3poZW5naGVpdGk=

排序前后对比

 

attachToClass方法

在methodlist方法主要是将分类添加到主类中，其源码实现如下

 

void attachToClass(Class cls, Class previously, int flags)
{
    runtimeLock.assertLocked();
ASSERT((flags & ATTACH_CLASS) ||
(flags & ATTACH_METACLASS) ||
(flags & ATTACH_CLASS_AND_METACLASS));


const char *mangledName  = cls->mangledName();
const char *LGPersonName = "LGPerson";

if (strcmp(mangledName, LGPersonName) == 0) {
bool kc_isMeta = cls->isMetaClass();
auto kc_rw = cls->data();
auto kc_ro = kc_rw->ro();
if (!kc_isMeta) {
printf("%s: 这个是我要研究的 %s \n",__func__,LGPersonName);
}
}


auto &map = get();
auto it = map.find(previously);//找到一个分类进来一次，即一个个加载分类，不要混乱

if (it != map.end()) {//这里会走进来：当主类没有实现load，分类开始加载，迫使主类加载，会走到if流程里面
        category_list &list = it->second;
if (flags & ATTACH_CLASS_AND_METACLASS) {//判断是否是元类
int otherFlags = flags & ~ATTACH_CLASS_AND_METACLASS;
attachCategories(cls, list.array(), list.count(), otherFlags | ATTACH_CLASS);//实例方法
attachCategories(cls->ISA(), list.array(), list.count(), otherFlags | ATTACH_METACLASS);//类方法
} else {
//如果不是元类，则只走一次 attachCategories
attachCategories(cls, list.array(), list.count(), flags);
}
        map.erase(it);
}
}

因为attachToClass中的外部循环是找到一个分类就会进到attachCategories一次，即找一个就循环一次

attachCategories方法

在attachCategories 方法中准备分类的数据，其源码实现如下

 

static void
attachCategories(Class cls, const locstamped_category_t *cats_list, uint32_t cats_count,
int flags)
{
if (slowpath(PrintReplacedMethods)) {
printReplacements(cls, cats_list, cats_count);
}
if (slowpath(PrintConnecting)) {
_objc_inform("CLASS: attaching %d categories to%s class '%s'%s",
                     cats_count, (flags & ATTACH_EXISTING) ? " existing" : "",
                     cls->nameForLogging(), (flags & ATTACH_METACLASS) ? " (meta)" : "");
}

/*
     * Only a few classes have more than 64 categories during launch.
     * This uses a little stack, and avoids malloc.
     *
     * Categories must be added in the proper order, which is back
     * to front. To do that with the chunking, we iterate cats_list
     * from front to back, build up the local buffers backwards,
     * and call attachLists on the chunks. attachLists prepends the
     * lists, so the final result is in the expected order.
     */
constexpr uint32_t ATTACH_BUFSIZ = 64;
    method_list_t   *mlists[ATTACH_BUFSIZ];
    property_list_t *proplists[ATTACH_BUFSIZ];
    protocol_list_t *protolists[ATTACH_BUFSIZ];

uint32_t mcount = 0;
uint32_t propcount = 0;
uint32_t protocount = 0;
bool fromBundle = NO;
bool isMeta = (flags & ATTACH_METACLASS);
/*
     rwe的创建，
     那么为什么要在这里进行`rwe的初始化`？因为我们现在要做一件事：往`本类`中`添加属性、方法、协议`等
     */
auto rwe = cls->data()->extAllocIfNeeded();

//mlists 是一个二维数组
for (uint32_t i = 0; i < cats_count; i++) {
auto& entry = cats_list[i];

        method_list_t *mlist = entry.cat->methodsForMeta(isMeta);
if (mlist) {
if (mcount == ATTACH_BUFSIZ) {//mcount = 0，ATTACH_BUFSIZ= 64，不会走到if里面的流程
prepareMethodLists(cls, mlists, mcount, NO, fromBundle);//准备排序
                rwe->methods.attachLists(mlists, mcount);
                mcount = 0;
}
            mlists[ATTACH_BUFSIZ - ++mcount] = mlist;
            fromBundle |= entry.hi->isBundle();
}

        property_list_t *proplist =
            entry.cat->propertiesForMeta(isMeta, entry.hi);
if (proplist) {
if (propcount == ATTACH_BUFSIZ) {
                rwe->properties.attachLists(proplists, propcount);
                propcount = 0;
}
            proplists[ATTACH_BUFSIZ - ++propcount] = proplist;
}

        protocol_list_t *protolist = entry.cat->protocolsForMeta(isMeta);
if (protolist) {
if (protocount == ATTACH_BUFSIZ) {
                rwe->protocols.attachLists(protolists, protocount);
                protocount = 0;
}
            protolists[ATTACH_BUFSIZ - ++protocount] = protolist;
}
}

if (mcount > 0) {
prepareMethodLists(cls, mlists + ATTACH_BUFSIZ - mcount, mcount, NO, fromBundle);//排序
        rwe->methods.attachLists(mlists + ATTACH_BUFSIZ - mcount, mcount);//mlists + ATTACH_BUFSIZ - mcount 为内存平移
if (flags & ATTACH_EXISTING) flushCaches(cls);
}

    rwe->properties.attachLists(proplists + ATTACH_BUFSIZ - propcount, propcount);

    rwe->protocols.attachLists(protolists + ATTACH_BUFSIZ - protocount, protocount);
}

 

class_rw_ext_t *extAllocIfNeeded() {
auto v = get_ro_or_rwe();
if (fastpath(v.is<class_rw_ext_t *>())) { //判断rwe是否存在
return v.get<class_rw_ext_t *>();//如果存在，则直接获取
} else {
return extAlloc(v.get<const class_ro_t *>());//如果不存在则进行开辟
}
}

????//extAlloc源码实现
class_rw_ext_t *
class_rw_t::extAlloc(const class_ro_t *ro, bool deepCopy)
{
    runtimeLock.assertLocked();
//此时只有rw，需要对rwe进行数据添加，即0-1的过程
auto rwe = objc::zalloc<class_rw_ext_t>();//创建

    rwe->version = (ro->flags & RO_META) ? 7 : 0;

    method_list_t *list = ro->baseMethods();
if (list) {
if (deepCopy) list = list->duplicate();
        rwe->methods.attachLists(&list, 1);
}

// See comments in objc_duplicateClass
// property lists and protocol lists historically
// have not been deep-copied
//
// This is probably wrong and ought to be fixed some day
    property_list_t *proplist = ro->baseProperties;
if (proplist) {
        rwe->properties.attachLists(&proplist, 1);
}

    protocol_list_t *protolist = ro->baseProtocols;
if (protolist) {
        rwe->protocols.attachLists(&protolist, 1);
}

set_ro_or_rwe(rwe, ro);
return rwe;
}

总结:本类 中 需要添加属性、方法等，所以需要初始化rwe,rwe的初始化主要涉及：分类、addMethod、addProperty、addprotocol ， 即对原始类进行修改或者处理时，才会进行rwe的初始化

attachLists方法：插入

 

struct method_list_t : entsize_list_tt<method_t, method_list_t, 0x3> 

struct property_list_t : entsize_list_tt<property_t, property_list_t, 0> 

struct protocol_list_t {
// count is pointer-sized by accident.
    uintptr_t count;
    protocol_ref_t list[0]; // variable-size

    size_t byteSize() const {
return sizeof(*this) + count*sizeof(list[0]);
}

    protocol_list_t *duplicate() const {
return (protocol_list_t *)memdup(this, this->byteSize());
}
...
}

 

void attachLists(List* const * addedLists, uint32_t addedCount) {
if (addedCount == 0) return;

if (hasArray()) {
// many lists -> many lists
//计算数组中旧lists的大小
uint32_t oldCount = array()->count;
//计算新的容量大小 = 旧数据大小+新数据大小
uint32_t newCount = oldCount + addedCount;
//根据新的容量大小，开辟一个数组，类型是 array_t，通过array()获取
setArray((array_t *)realloc(array(), array_t::byteSize(newCount)));
//设置数组大小
array()->count = newCount;
//旧的数据从 addedCount 数组下标开始 存放旧的lists，大小为 旧数据大小 * 单个旧list大小
memmove(array()->lists + addedCount, array()->lists, 
                oldCount * sizeof(array()->lists[0]));
//新数据从数组 首位置开始存储，存放新的lists，大小为 新数据大小 * 单个list大小
memcpy(
array()->lists, addedLists, 
               addedCount * sizeof(array()->lists[0]));
}
else if (!list  &&  addedCount == 1) {
// 0 lists -> 1 list
        list = addedLists[0];//将list加入mlists的第一个元素，此时的list是一个一维数组
} 
else {
// 1 list -> many lists 有了一个list，有往里加很多list
//新的list就是分类，来自LRU的算法思维，即最近最少使用
//获取旧的list
        List* oldList = list;
uint32_t oldCount = oldList ? 1 : 0;
//计算容量和 = 旧list个数+新lists的个数
uint32_t newCount = oldCount + addedCount;
//开辟一个容量和大小的集合，类型是 array_t，即创建一个数组，放到array中，通过array()获取
setArray((array_t *)malloc(array_t::byteSize(newCount)));
//设置数组的大小
array()->count = newCount;
//判断old是否存在，old肯定是存在的，将旧的list放入到数组的末尾
if (oldList) array()->lists[addedCount] = oldList;
// memcpy（开始位置，放什么，放多大） 是内存平移，从数组起始位置存入新的list
//其中array()->lists 表示首位元素位置
memcpy(array()->lists, addedLists, 
               addedCount * sizeof(array()->lists[0]));
}
}

从源码可以得知，插入表主要分为三种情况：

针对情况3，这里的lists是指分类

memmove和memcpy的区别

rwe 数据加载

rwe -- 本类的数据加载【重点！！！】

下面通过调试来验证rwe数据0-1的过程，即添加类的方法列表

总结 ：所以 0对1是一种一维赋值，函数路径为：map_images -> _read_images -> readClass -> realizeClassWithoutSwift -> methodizeClass -> prepareMethodLists -> fixupMethodList -> attachToClass -> load_categories_nolock -> attachCategories -> extAllocIfNeeded -> extAlloc -> attachLists

rwe -- LGA分类数据加载【重点！！！】

总结:如果本类只有一个分类，则会走到情况3，即1对多的情况

rwe -- LGB分类数据加载【重点！！！】

如果再加一个分类LGB，走到第三种情况，即多对多

其输出的顺序是

总结

综上所述，attachLists方法主要是将类 和 分类 的数据加载到rwe中

如下图所示

 

watermark,size_16,text_QDUxQ1RP5Y2a5a6i,color_FFFFFF,t_100,g_se,x_10,y_10,shadow_90,type_ZmFuZ3poZW5naGVpdGk=

attachLists的三种流程

懒加载类 和 非懒加载类

在这里，尽管方法处理完毕，但是并没有从rw中存储到rwe中，那么问题来了，到目前为止，从data -> ro -> rw -> 看到了rwe,即realizeClassWithoutSwift（ro、rw操作）-> methodizeClass，但是并没有走if里面的流程，为什么？

究其根本原因是_read_images方法中的第九步 实现非懒加载类，那么我们是如何将 懒加载类 变成 非懒加载类的呢?

主要是在运行objc源码前，我们在LGPerson中实现了一个+load方法，反之，如果去掉+load方法，是懒加载类，不会走到第九步的for循环中

所以，综上所述，懒加载类和 非懒加载类的区别 就是 是否实现了+load方法

为什么实现load方法就会变成非懒加载类？

懒加载类在什么时候加载？

调试验证 懒加载类加载的时机

下面通过代码调试来验证

堆栈信息验证

也可以通过bt 堆栈信息查看，方法为什么能来？其本质是因为 走到realizeClassWithoutSwift，其本质是调用alloc，即消息的发送

watermark,size_16,text_QDUxQ1RP5Y2a5a6i,color_FFFFFF,t_100,g_se,x_10,y_10,shadow_90,type_ZmFuZ3poZW5naGVpdGk=

bt验证懒加载类数据加载时机

 

所以懒加载类和非懒加载类的数据加载时机如下图所示

watermark,size_16,text_QDUxQ1RP5Y2a5a6i,color_FFFFFF,t_100,g_se,x_10,y_10,shadow_90,type_ZmFuZ3poZW5naGVpdGk=

懒加载类和非懒加载类

 

总结

综上所述，类从Mach-O加载到内存的流程图如下所示

watermark,size_16,text_QDUxQ1RP5Y2a5a6i,color_FFFFFF,t_100,g_se,x_10,y_10,shadow_90,type_ZmFuZ3poZW5naGVpdGk=

类加载流程

 

标签：rwe,17,iOS,list,加载,objc,ro,cls
来源： https://blog.51cto.com/u_12801393/2955021