iOS-类的加载(上)

前言

在之前的文章dyld与objc的关联分析,我们分析了_objc_init方法中的各个初始化方法及
_dyld_objc_notify_register方法与dyld链接之间的关系,那么接下来我们就探究一下的相关信息是如何加载到内存的以及懒加载类非懒加载类

map_images分析

在上文的最后,我们分析到了map_images方法,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);
}

map_images_nolock

void
map_images_nolock(unsigned mhCount, const char * const mhPaths[],
                  const struct mach_header * const mhdrs[])
{
    //.....省略部分代码

    // 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
    {
        //.....省略部分代码
    }
    
    //.....省略部分代码

    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分析

_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:

/***********************************************************************
* _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) {...}
    // Fix up @selector references
    static size_t UnfixedSelectors;
    {...}

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

#if SUPPORT_FIXUP
    // Fix up old objc_msgSend_fixup call sites
    for (EACH_HEADER) {...}
    ts.log("IMAGE TIMES: fix up objc_msgSend_fixup");
#endif

    bool cacheSupportsProtocolRoots = sharedCacheSupportsProtocolRoots();

    // Discover protocols. Fix up protocol refs.
    for (EACH_HEADER) {...}
    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) {...}
    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) {...}
    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) {...}
    ts.log("IMAGE TIMES: realize non-lazy classes");

    // Realize newly-resolved future classes, in case CF manipulates them
    if (resolvedFutureClasses) {...}
    ts.log("IMAGE TIMES: realize future classes");

    if (DebugNonFragileIvars) {...}
    // Print preoptimization statistics
    if (PrintPreopt) {...}

#undef EACH_HEADER
}


代码非常长,400多行,这里我们把不是重点的代码折叠起来。注释有Fix up字段的先不看,已ts.log()方法为界一块一块的分析观察,发现一共做了下面几件事

1、条件控制进行的一次加载
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、修复重映射一些没有被镜像文件加载进来的类
5、修复一些消息
6、当类里面有协议时:readProtocol读取协议
7、修复没有被加载的协议
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

接下来挨个分析:

1、条件控制进行的一次加载

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
   //这个表中不包含预先优化的类。
   // 4/3是NXMapTable的装载因子
    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_registerNameNoLockSEL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;
            }
        }
    }
}

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classref_t类型的指针
    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];//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");

这里有一个值得注意的地方,我们通过LLDB调试,发现了在未执行readClass方法前,cls是一个地址,而执行过readClass方法后,cls变成了类的名称,所以readClass方法肯定做了些特殊的事情,这个我们稍后分析!

cls前后对比

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

_getObjc2ClassRefs是获取Mach-O中的静态段__objc_classrefs即类的引用
_getObjc2SuperRefs是获取Mach-O中的静态段__objc_superrefs即父类的引用

通过注释可以得知,被remapClassRef的类都是懒加载的类,所以最初经过调试时,这部分代码是没有执行的

//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 *classrefs = _getObjc2ClassRefs(hi, &count);//Mach-O的静态段 __objc_classrefs
        for (i = 0; i < count; i++) {
            remapClassRef(&classrefs[I]);
        }
        // fixme why doesn't test future1 catch the absence of this?
        classrefs = _getObjc2SuperRefs(hi, &count);//Mach_O中的静态段 __objc_superrefs
        for (i = 0; i < count; i++) {
            remapClassRef(&classrefs[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");

通过NXMapTable *protocol_map = protocols();创建protocol哈希表

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");

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

主要是实现的加载处理,实现非懒加载类

  • 通过_getObjc2NonlazyClassList获取Mach-O的静态段__objc_nlclslist非懒加载类表
  • 通过addClassTableEntry将非懒加载类插入类表,存储到内存,如果已经添加就不会载添加,需要确保整个结构都被添加
  • 通过realizeClassWithoutSwift实现当前的类,因为前面3中的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
// 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
        classref_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
    
    // **自己加的** ----判断自己的类
    const char *ZGPersonName = "ZGPerson";
    if (strcmp(mangledName, ZGPersonName) == 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;
}

主要分为以下几步:

    1. 通过mangledName获取类的名字,源码如下
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
        }
    }
    1. 当前类的父类中若有丢失的weak-linked类,则返回nil
    1. 判断是不是后期需要处理的类,在正常情况下,不会走到popFutureNamedClass,这是专门针对未来待处理的类的操作,也可以通过断点调试,可知不会走到if流程里面,因此也不会对ro、rw进行操作
    1. 通过addNamedClass将当前类添加到已经创建好的gdb_objc_realized_classes哈希表,该表用于存放所有类

addNamedClass源码

/***********************************************************************
* 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());
}
    1. 通过addClassTableEntry,将初始化的类添加到allocatedClasses表,_objc_init中的runtime_init就创建了allocatedClasses

addClassTableEntry源码

/***********************************************************************
* 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);
}

可以看出readClass方法的主要作用就是将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

realizeClassWithoutSwift方法中有ro、rw的相关操作,这个方法在之前的文章objc_msgSend 流程之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:

    1. 读取data数据,并设置ro、rw
    1. 递归调用realizeClassWithoutSwift完善继承链
    1. 通过methodizeClass方法化类
// 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.
        rw = objc::zalloc();
        rw->set_ro(ro);
        rw->flags = RW_REALIZED|RW_REALIZING|isMeta;
        cls->setData(rw);
    }

1. 读取data数据

读取classdata数据,并将其强转为ro,以及rw初始化ro拷贝一份到rw中的ro

这里对一些名词作出解释:

  • ro ro 表示 readOnly,即只读,其在编译时就已经确定了内存,包含类名称、方法、协议和实例变量的信息,由于是只读的,所以属于Clean Memory,而Clean Memory是指加载后不会发生更改的内存

  • rwrw 表示 readWrite,即可读可写,由于其动态性,可能会往类中添加属性、方法、添加协议,在最新的2020的WWDC的对内存优化的说明Advancements in the Objective-C runtime - WWDC 2020 - Videos - Apple Developer中,提到rw,其实在rw中只有10%的类真正的更改了它们的方法,所以有了rwe,即类的额外信息。对于那些确实需要额外信息的类,可以分配rwe扩展记录中的一个,并将其滑入类中供其使用。其中rw就属于dirty memory,而 dirty memory是指在进程运行时会发生更改的内存类结构一经使用就会变成 ditry memory,因为运行时会向它写入新数据.

  • rw可以理解为 rw的内存大小 = ro内存 + rwe额外内存信息

2. 递归调用realizeClassWithoutSwift完善继承链

 // 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);
    
.....省略一些代码

// 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);

.....省略一些代码

// 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);
}

这里通过递归调用realizeClassWithoutSwift设置父类、元类,并设置父类和元类的isa指向,最后通过addSubclassaddRootClass设置父子的双向链表指向关系,即父类中可以找到子类,子类中可以找到父类。

这里递归结束的条件值得注意一下:

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));    
   ...
}

isa找到根元类之后,根元类的isa是指向根类,根类的isa指向nil,所以有上面的递归终止条件,其目的是保证类只加载一次

3. 通过 methodizeClass 方法化类

其中methodizeClass的源码实现如下

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);

    ....
}

这里将属性列表、方法列表、协议列表等通过attachLists方法加入到rwe中,其中Attach categories.为附加分类中的方法,我们下回分解。

prepareMethodLists方法排序

在消息流程的objc_msgSend 流程之慢速查找文章中,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?

  • 进入prepareMethodLists的源码实现,其内部是通过fixupMethodList方法排序
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
        }
    }

    ...
}

  • 进入fixupMethodList源码实现,是根据selector address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();
}

懒加载类 和 非懒加载类

  • 懒加载:推迟到第一次消息发送的时候才加载
  • 非懒加载:当map_images的时候,加载所有类数据的时候就加载
    其中懒加载和非懒加载的区别标志:当前类是否实现load方法

_read_images方法中的第九步的realizeClassWithoutSwift调用前增加自定义逻辑

// 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) 是否有load方法
for (EACH_HEADER) {
        classref_t const *classlist = 
            _getObjc2NonlazyClassList(hi, &count);
        for (i = 0; i < count; i++) {
            Class cls = remapClass(classlist[i]);
            if (!cls) continue;

            addClassTableEntry(cls);
            //自己增加的代码
            const char *mangledName  = cls->mangledName();
            const char *ZGPersonName = "ZGPerson";
            
            if (strcmp(mangledName, ZGPersonName) == 0) {
                
                auto kc_rw = cls->data();
                
                printf("%s: 这个是我要研究的 %s \n",__func__,ZGPersonName);
            }

            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);
        }
    }

同时在ZGPerson中增加load方法

@implementation ZGPerson
+ (void)load{

}
@end

发现如果增加load方法会加入我们的判断,如果没有load方法则不会进入判断

增加判断

你可能感兴趣的:(iOS-类的加载(上))