OC对象之旅 weak弱引用实现分析

Runtime学习 -- weak应用源码学习

  Runtime源码分析，带你了解OC实现过程。其中参考了大量的大神的代码以及文献，里面也有个人的见解，欢迎拍砖，欢迎交流。

两种常见使用场景

/// weak属性
@interface XX : XX
@property(nonatomic,weak) Type* weakPtr;
@end

/// 代码块中使用
{
    /// 使用__weak
    __weak Type* weakPtr = [[SomeObject alloc] init];
}

根据调试信息，发现两者的区别是：

• 第一种进入到 id objc_storeWeak(id *location, id newObj)方法

/**
 * This function stores a new value into a __weak variable. It would
 * be used anywhere a __weak variable is the target of an assignment.
 *
 * @param location The address of the weak pointer itself
 * @param newObj The new object this weak ptr should now point to
 *
 * @return \e newObj
 */
id
objc_storeWeak(id *location, id newObj)
{
    return storeWeak<DoHaveOld, DoHaveNew, DoCrashIfDeallocating>
        (location, (objc_object *)newObj);
}

• 第二种绕一个远路，先初始化 id objc_initWeak(id *location, id newObj)

/**
 * Initialize a fresh weak pointer to some object location.
 * It would be used for code like:
 *
 * (The nil case)
 * __weak id weakPtr;
 * (The non-nil case)
 * NSObject *o = ...;
 * __weak id weakPtr = o;
 *
 * This function IS NOT thread-safe with respect to concurrent
 * modifications to the weak variable. (Concurrent weak clear is safe.)
 *
 * @param location Address of __weak ptr.
 * @param newObj Object ptr.
 */
id objc_initWeak(id *location, id newObj)
{
    if (!newObj) {
        *location = nil;
        return nil;
    }

    return storeWeak<DontHaveOld, DoHaveNew, DoCrashIfDeallocating>
        (location, (objc_object*)newObj);
}

• 两者最终进入到如下方法

template <HaveOld haveOld, HaveNew haveNew,
          CrashIfDeallocating crashIfDeallocating>
static id
storeWeak(id *location, objc_object *newObj)
{
    ///略去，下面会进行分析
    ...
    return (id)newObj;
}

所以重点就在 storeWeak这个方法中，let's do it

分析源码

storeWeak源码的如下：

template <HaveOld haveOld, HaveNew haveNew,
          CrashIfDeallocating crashIfDeallocating>
static id storeWeak(id *location, objc_object *newObj)
{
    assert(haveOld  ||  haveNew);
    if (!haveNew) assert(newObj == nil);

    Class previouslyInitializedClass = nil;
    id oldObj;
    SideTable *oldTable;
    SideTable *newTable;

    // Acquire locks for old and new values.
    // Order by lock address to prevent lock ordering problems.
    // Retry if the old value changes underneath us.
 retry:
    if (haveOld) {
        oldObj = *location;
        oldTable = &SideTables()[oldObj];
    } else {
        oldTable = nil;
    }
    if (haveNew) {
        newTable = &SideTables()[newObj];
    } else {
        newTable = nil;
    }

    SideTable::lockTwo<haveOld, haveNew>(oldTable, newTable);

    if (haveOld  &&  *location != oldObj) {
        SideTable::unlockTwo<haveOld, haveNew>(oldTable, newTable);
        goto retry;
    }
    // Prevent a deadlock between the weak reference machinery
    // and the +initialize machinery by ensuring that no
    // weakly-referenced object has an un-+initialized isa.
    /// 注释大意是通过下面操作，保证所有的弱引用对象的isa都被初始化，这样可以防止死锁，PS,这里我不是太明白，求指教
    if (haveNew  &&  newObj) {
        /// 下面的操作是初始化isa
        Class cls = newObj->getIsa();
        if (cls != previouslyInitializedClass  &&
            !((objc_class *)cls)->isInitialized())
        {
            SideTable::unlockTwo<haveOld, haveNew>(oldTable, newTable);
            _class_initialize(_class_getNonMetaClass(cls, (id)newObj));

            // If this class is finished with +initialize then we're good.
            // If this class is still running +initialize on this thread
            // (i.e. +initialize called storeWeak on an instance of itself)
            // then we may proceed but it will appear initializing and
            // not yet initialized to the check above.
            // Instead set previouslyInitializedClass to recognize it on retry.
            previouslyInitializedClass = cls;

            goto retry;
        }
    }

    // Clean up old value, if any.
    if (haveOld) {
        weak_unregister_no_lock(&oldTable->weak_table, oldObj, location);
    }

    // Assign new value, if any.
    if (haveNew) {
        newObj = (objc_object *)
            weak_register_no_lock(&newTable->weak_table, (id)newObj, location,
                                  crashIfDeallocating);
        // weak_register_no_lock returns nil if weak store should be rejected

        // Set is-weakly-referenced bit in refcount table.
        if (newObj  &&  !newObj->isTaggedPointer()) {
            newObj->setWeaklyReferenced_nolock();
        }

        // Do not set *location anywhere else. That would introduce a race.
        *location = (id)newObj;
    }
    else {
        // No new value. The storage is not changed.
    }

    SideTable::unlockTwo<haveOld, haveNew>(oldTable, newTable);

    return (id)newObj;
}

• template <HaveOld haveOld, HaveNew haveNew,CrashIfDeallocating crashIfDeallocating>是C++的一种泛型实现，相当于这里申明了变量或者类型，可以在代码块中使用，用于处理不同的未知类型&枚举。
• haveOld 弱引用是否已经有所指向
• haveNew 是否有新的指向
• CrashIfDeallocating 执行方法时发生Deallocate是否Crash

PS:初始化ISA那部分为何能阻止死锁，我没有看懂

该函数流程如下：

重点来了：

/// SideTables
oldTable = &SideTables()[oldObj];
newTable = &SideTables()[newObj];
/// taggedPointer是什么鬼
isTaggedPointer
/// 注册弱引用
weak_register_no_lock(&newTable->weak_table, (id)newObj, location,crashIfDeallocating);
/// 消除弱引用
weak_unregister_no_lock(&oldTable->weak_table, oldObj, location);

SideTable

SideTable是一个结构体，定义如下

struct SideTable {
    spinlock_t slock;
    RefcountMap refcnts;
    weak_table_t weak_table;

    SideTable() {
        memset(&weak_table, 0, sizeof(weak_table));
    }

    ~SideTable() {
        _objc_fatal("Do not delete SideTable.");
    }

    ///锁
    ....
};

• spinlock_t solck 锁
• RefcountMap refcnts 强引用使用，略过
• weak_table_t weak_table 弱引用表
  
  SideTable是存放引用关系的，对象通过Hash值操作，在SideTableBuf 中寻找与之对应的SideTable，SideTableBuf初始化过程如下：

alignas(StripedMap<SideTable>) static uint8_t
    SideTableBuf[sizeof(StripedMap<SideTable>)];
    /// 会在Objc_init中调用该方法
static void SideTableInit() {
    /// 这句话貌似没什么卵用，求指教
    new (SideTableBuf) StripedMap<SideTable>();
}
/// 寻找SideTable
static StripedMap<SideTable>& SideTables() {
    return *reinterpret_cast<StripedMap<SideTable>*>(SideTableBuf);
}

StripedMap是一个泛型类，并重写了[]运算符，通过对象的地址，运算出Hash值，通过该hash值找到对象的SideTable

template<typename T>
class StripedMap {
    enum { CacheLineSize = 64 };
#if TARGET_OS_EMBEDDED
    enum { StripeCount = 8 };
#else
    enum { StripeCount = 64 };
#endif
    struct PaddedT {
        T value alignas(CacheLineSize);
    };
    PaddedT array[StripeCount];
    /// 运算
    static unsigned int indexForPointer(const void *p) {
        uintptr_t addr = reinterpret_cast<uintptr_t>(p);
        /// 位运算可以控制返回值在0-63之间
        return ((addr >> 4) ^ (addr >> 9)) % StripeCount;
    }

 public:
    T& operator[] (const void *p) {
        return array[indexForPointer(p)].value;
    }
    /// 下面略去
    ...
}

taggedPointer

简单的说，这是一种优化手段，即将对象的值，存入对象的地址中，这些工程师简直丧心病狂，就为了省一点内存嘛！

进入正题，看看怎么实现弱引用的

先看看注册的过程吧

/**
 * Registers a new (object, weak pointer) pair. Creates a new weak
 * object entry if it does not exist.
 *
 * @param weak_table The global weak table.
 * @param referent The object pointed to by the weak reference.
 * @param referrer The weak pointer address.
 */
id weak_register_no_lock(weak_table_t *weak_table, id referent_id,
                      id *referrer_id, bool crashIfDeallocating)
{
    /// 转化为object
    objc_object *referent = (objc_object *)referent_id;
    objc_object **referrer = (objc_object **)referrer_id;
    /// 如果是taggedPointer,就没有引用的过程了
    if (!referent  ||  referent->isTaggedPointer()) return referent_id;

    // ensure that the referenced object is viable
    bool deallocating;
    if (!referent->ISA()->hasCustomRR()) {
        deallocating = referent->rootIsDeallocating();
    }
    else {
        BOOL (*allowsWeakReference)(objc_object *, SEL) =
            (BOOL(*)(objc_object *, SEL))
            object_getMethodImplementation((id)referent,
                                           SEL_allowsWeakReference);
        if ((IMP)allowsWeakReference == _objc_msgForward) {
            return nil;
        }
        deallocating =
            ! (*allowsWeakReference)(referent, SEL_allowsWeakReference);
    }
    /// 如果正在被销毁
    if (deallocating) {
        if (crashIfDeallocating) {
            _objc_fatal("Cannot form weak reference to instance (%p) of "
                        "class %s. It is possible that this object was "
                        "over-released, or is in the process of deallocation.",
                        (void*)referent, object_getClassName((id)referent));
        } else {
            return nil;
        }
    }

    // now remember it and where it is being stored
    weak_entry_t *entry;
    if ((entry = weak_entry_for_referent(weak_table, referent))) {
        append_referrer(entry, referrer);
    }
    else {
        weak_entry_t new_entry(referent, referrer);
        weak_grow_maybe(weak_table);
        weak_entry_insert(weak_table, &new_entry);
    }

    // Do not set *referrer. objc_storeWeak() requires that the
    // value not change.

    return referent_id;
}

先从这行数的参数说起，参数有4个

• weak_table_t *weak_table hash表
• id referent_id, 弱引用对象
• id *referrer_id, 弱引用指针
• bool crashIfDeallocating 如果正在Deallocate是否crash

后三个参数不用解释，主要解释第一个参数，weak_table_t,定义如下

/**
 * The global weak references table. Stores object ids as keys,
 * and weak_entry_t structs as their values.
 */
struct weak_table_t {
    weak_entry_t *weak_entries; ///数组，用于存储引用对象集合
    size_t    num_entries;  /// 存储数目
    uintptr_t mask; /// 当前分配容量
    uintptr_t max_hash_displacement; /// 已使用容量
};

没错，weak_table_t就是寄存在SideTable中

• weak_entry_t *weak_entries; ///数组，用于存储引用对象集合
• size_t num_entries; /// 存储数目
• uintptr_t mask; /// 当前分配容量
• uintptr_t max_hash_displacement; /// 已使用容量

定义中我们重点关注weak_entry_t

struct weak_entry_t {
    DisguisedPtr<objc_object> referent;
    union {
        struct {
            weak_referrer_t *referrers;
            uintptr_t        out_of_line_ness : 2;
            uintptr_t        num_refs : PTR_MINUS_2;
            uintptr_t        mask;
            uintptr_t        max_hash_displacement;
        };
        struct {
            // out_of_line_ness field is low bits of inline_referrers[1]
            weak_referrer_t  inline_referrers[WEAK_INLINE_COUNT];
        };
    };

    bool out_of_line() {
        return (out_of_line_ness == REFERRERS_OUT_OF_LINE);
    }

    weak_entry_t& operator=(const weak_entry_t& other) {
        memcpy(this, &other, sizeof(other));
        return *this;
    }

    weak_entry_t(objc_object *newReferent, objc_object **newReferrer)
        : referent(newReferent)
    {
        inline_referrers[0] = newReferrer;
        for (int i = 1; i < WEAK_INLINE_COUNT; i++) {
            inline_referrers[i] = nil;
        }
    }
};

weak_entry_t是最终存放对象和引用指针的地方，referent是被引用的对象，联合体union释义如下

• weak_referrer_t *referrers; 存放引用指针
• uintptr_t out_of_line_ness : 2 标识当前存储是否在初始WEAK_INLINE_COUNT个数之内
• uintptr_t num_refs : PTR_MINUS_2 引用的个数
• uintptr_t mask; 实际分配容量
• uintptr_t max_hash_displacement; 实际使用容量，包括已经被释放的，每次调整容量时会更新重置
• weak_referrer_t inline_referrers[WEAK_INLINE_COUNT]; 当引用个数小于WEAK_INLINE_COUNT时，使用该数组存放。

注册引用过程中，重点关注下面代码：

{
weak_entry_t *entry;
    /// 查找是否已经注册过了
    if ((entry = weak_entry_for_referent(weak_table, referent))) {
        /// 加上去就可以了
        append_referrer(entry, referrer);
    }
    else {
        /// 新建一个
        weak_entry_t new_entry(referent, referrer);
        /// 调整weak_table_t 的容量大小
        weak_grow_maybe(weak_table);
        /// 插入一个
        weak_entry_insert(weak_table, &new_entry);
    }
}

新建

通过weak_entry_t的源码，可以看到新建一个weak_entry_t的过程是

• 将被引用对象赋予referent
• 将引用指针放入到inline_referrers，因为此时数目还很少

调整weak_table_t的容量大小

static void weak_resize(weak_table_t *weak_table, size_t new_size)
{
    size_t old_size = TABLE_SIZE(weak_table);

    weak_entry_t *old_entries = weak_table->weak_entries;
    weak_entry_t *new_entries = (weak_entry_t *)
        calloc(new_size, sizeof(weak_entry_t));

    weak_table->mask = new_size - 1;
    weak_table->weak_entries = new_entries;
    /// 重置
    weak_table->max_hash_displacement = 0;
    weak_table->num_entries = 0;  // restored by weak_entry_insert below

    if (old_entries) {
        weak_entry_t *entry;
        weak_entry_t *end = old_entries + old_size;
        for (entry = old_entries; entry < end; entry++) {
            if (entry->referent) {
                weak_entry_insert(weak_table, entry);
            }
        }
        free(old_entries);
    }
}

// Grow the given zone's table of weak references if it is full.
static void weak_grow_maybe(weak_table_t *weak_table)
{
    size_t old_size = TABLE_SIZE(weak_table);

    // Grow if at least 3/4 full.
    if (weak_table->num_entries >= old_size * 3 / 4) {
        weak_resize(weak_table, old_size ? old_size*2 : 64);
    }
}

当实际的数目大于old_size（old_size就是mask的大小+1)，就去调整大小，同时重置max_hash_displacement为0，通过calloc函数，动态分配mask个的内存，然后通过循环，将原有的weak_entry_t插入到新的容器中，在插入的过程中，更新max_hash_displacement.

在weak_table_t插入weak_entry_t

static void weak_entry_insert(weak_table_t *weak_table, weak_entry_t *new_entry)
{
    weak_entry_t *weak_entries = weak_table->weak_entries;
    assert(weak_entries != nil);

    size_t begin = hash_pointer(new_entry->referent) & (weak_table->mask);
    size_t index = begin;
    size_t hash_displacement = 0;
    while (weak_entries[index].referent != nil) {
        index = (index+1) & weak_table->mask;
        if (index == begin) bad_weak_table(weak_entries);
        hash_displacement++;
    }
    /// 把新的加进去
    weak_entries[index] = *new_entry;
    /// 引用计数+1
    weak_table->num_entries++;
    /// 扩容前最大占位
    if (hash_displacement > weak_table->max_hash_displacement) {
        weak_table->max_hash_displacement = hash_displacement;
    }
}

过程比较简单，也是利用hash处理，方便后面查找。

在weak_table_t查找对象是通过循环遍历的方式，过程如下

static weak_entry_t *
weak_entry_for_referent(weak_table_t *weak_table, objc_object *referent)
{
    assert(referent);

    weak_entry_t *weak_entries = weak_table->weak_entries;

    if (!weak_entries) return nil;

    size_t begin = hash_pointer(referent) & weak_table->mask; /// 获取hash值
    size_t index = begin;
    size_t hash_displacement = 0;
    /// 循环遍历，查找
    while (weak_table->weak_entries[index].referent != referent) {
        index = (index+1) & weak_table->mask;
        if (index == begin) bad_weak_table(weak_table->weak_entries);
        // 查找到最大的时候，结束
        hash_displacement++;
        if (hash_displacement > weak_table->max_hash_displacement) {
            return nil;
        }
    }

    return &weak_table->weak_entries[index];
}

在已有的weak_entry_t中加入引用

static void append_referrer(weak_entry_t *entry, objc_object **new_referrer)
{
    /// 如果是数组,即个数比较少
    if (! entry->out_of_line()) {
        // Try to insert inline.
        for (size_t i = 0; i < WEAK_INLINE_COUNT; i++) {
            if (entry->inline_referrers[i] == nil) {
                entry->inline_referrers[i] = new_referrer;
                return;
            }
        }

        // Couldn't insert inline. Allocate out of line.
        weak_referrer_t *new_referrers = (weak_referrer_t *)
            calloc(WEAK_INLINE_COUNT, sizeof(weak_referrer_t));
        // This constructed table is invalid, but grow_refs_and_insert
        // will fix it and rehash it.
        for (size_t i = 0; i < WEAK_INLINE_COUNT; i++) {
            new_referrers[i] = entry->inline_referrers[i];
        }
        entry->referrers = new_referrers;
        entry->num_refs = WEAK_INLINE_COUNT;
        entry->out_of_line_ness = REFERRERS_OUT_OF_LINE;
        entry->mask = WEAK_INLINE_COUNT-1;
        entry->max_hash_displacement = 0;
    }

    assert(entry->out_of_line());

    if (entry->num_refs >= TABLE_SIZE(entry) * 3/4) {
        return grow_refs_and_insert(entry, new_referrer);
    }
    size_t begin = w_hash_pointer(new_referrer) & (entry->mask);
    size_t index = begin;
    size_t hash_displacement = 0;
    while (entry->referrers[index] != nil) {
        hash_displacement++;
        index = (index+1) & entry->mask;
        if (index == begin) bad_weak_table(entry);
    }
    if (hash_displacement > entry->max_hash_displacement) {
        entry->max_hash_displacement = hash_displacement;
    }
    weak_referrer_t &ref = entry->referrers[index];
    ref = new_referrer;
    entry->num_refs++;
}

该过程同在weak_table_t中插入weak_entry_t如出一辙，要注意的是需要判断引用的个数，当引用个数大于WEAK_INLINE_COUNT时，需要将原有的引用指针也移到referrers中，同时更新相关计数器。

上面过程的流程如下：

消除弱引用

消除弱引用过程同注册大致相同，只是部分地方是相反操作，不做赘述了