iOS-底层（8）：类结构之cache_t结构分析

今天我们来研究一下cache_t是什么

前文书我们说过，在类的结构体中有个cache_t，我们来看看在类中的位置

struct objc_class : objc_object {
    // Class ISA;
    Class superclass;
    cache_t cache;             // formerly cache pointer and vtable
    class_data_bits_t bits;    // class_rw_t * plus custom rr/alloc flags

    class_rw_t *data() const {
        return bits.data();
    }
  //...此处省略很多坨代码
}

cache_t的结构

struct cache_t {
#if CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_OUTLINED
    explicit_atomic<struct bucket_t *> _buckets;
    explicit_atomic<mask_t> _mask;
#elif CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_HIGH_16
    explicit_atomic<uintptr_t> _maskAndBuckets;
    mask_t _mask_unused;
    
    // How much the mask is shifted by.
    static constexpr uintptr_t maskShift = 48;
    
    // Additional bits after the mask which must be zero. msgSend
    // takes advantage of these additional bits to construct the value
    // `mask << 4` from `_maskAndBuckets` in a single instruction.
    static constexpr uintptr_t maskZeroBits = 4;
    
    // The largest mask value we can store.
    static constexpr uintptr_t maxMask = ((uintptr_t)1 << (64 - maskShift)) - 1;
    
    // The mask applied to `_maskAndBuckets` to retrieve the buckets pointer.
    static constexpr uintptr_t bucketsMask = ((uintptr_t)1 << (maskShift - maskZeroBits)) - 1;
    
    // Ensure we have enough bits for the buckets pointer.
    static_assert(bucketsMask >= MACH_VM_MAX_ADDRESS, "Bucket field doesn't have enough bits for arbitrary pointers.");
#elif CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_LOW_4
    // _maskAndBuckets stores the mask shift in the low 4 bits, and
    // the buckets pointer in the remainder of the value. The mask
    // shift is the value where (0xffff >> shift) produces the correct
    // mask. This is equal to 16 - log2(cache_size).
    explicit_atomic<uintptr_t> _maskAndBuckets;
    mask_t _mask_unused;

    static constexpr uintptr_t maskBits = 4;
    static constexpr uintptr_t maskMask = (1 << maskBits) - 1;
    static constexpr uintptr_t bucketsMask = ~maskMask;
#else
#error Unknown cache mask storage type.
#endif
    
#if __LP64__
    uint16_t _flags;
#endif
    uint16_t _occupied;

public:
    static bucket_t *emptyBuckets();
    
    struct bucket_t *buckets();
    mask_t mask();
    mask_t occupied();
    void incrementOccupied();
    void setBucketsAndMask(struct bucket_t *newBuckets, mask_t newMask);
    void initializeToEmpty();

    unsigned capacity();
    bool isConstantEmptyCache();
    bool canBeFreed();

    //此处省略

cache_t 的结构分三个架构来处理，macOS i386，模拟器x86，真机arm64
下面的三个宏定义：

• #define CACHE_MASK_STORAGE_OUTLINED 1 运行环境为macOS 或 模拟器
• #define CACHE_MASK_STORAGE_HIGH_16 2 运行环境为64位真机
• #define CACHE_MASK_STORAGE_LOW_4 3 运行环境为非64位真机等

在真机环境下，由于为了进一步优化内存，将bucket和mask写到了一起，使用_maskAndBuckets，通过掩码来获取相应数据

bucket_t源码

struct bucket_t {
private:
    // IMP-first is better for arm64e ptrauth and no worse for arm64.
    // SEL-first is better for armv7* and i386 and x86_64.
#if __arm64__
    explicit_atomic<uintptr_t> _imp;
    explicit_atomic<SEL> _sel;
#else
    explicit_atomic<SEL> _sel;
    explicit_atomic<uintptr_t> _imp;
#endif

 //....省
public:
    inline SEL sel() const { return _sel.load(memory_order::memory_order_relaxed); }

    inline IMP imp(Class cls) const {
        uintptr_t imp = _imp.load(memory_order::memory_order_relaxed);
        if (!imp) return nil;
#if CACHE_IMP_ENCODING == CACHE_IMP_ENCODING_PTRAUTH
        SEL sel = _sel.load(memory_order::memory_order_relaxed);
        return (IMP)
            ptrauth_auth_and_resign((const void *)imp,
                                    ptrauth_key_process_dependent_code,
                                    modifierForSEL(sel, cls),
                                    ptrauth_key_function_pointer, 0);
#elif CACHE_IMP_ENCODING == CACHE_IMP_ENCODING_ISA_XOR
        return (IMP)(imp ^ (uintptr_t)cls);
#elif CACHE_IMP_ENCODING == CACHE_IMP_ENCODING_NONE
        return (IMP)imp;
#else
#error Unknown method cache IMP encoding.
#endif
    }

    template <Atomicity, IMPEncoding>
    void set(SEL newSel, IMP newImp, Class cls);
};

上面的源码我们可以得出：IMP和SEL就存在bucket_t中。

一 通过源码查找 sel和imp

下一个断点

image.png image.png

根据，地址偏移，指针 和类中提供的方法等一系列操作，查看打印结果，当前断点前调用了两个方法，_occupied = 2，说明方法调用一次，就会缓存一次。

二 脱离源码通过项目查找

在工程中我们定义与cache_t结构类似的类，然后进行强转。

#import "LGPerson.h"
#import <objc/runtime.h>

typedef uint32_t mask_t;  // x86_64 & arm64 asm are less efficient with 16-bits

struct lg_bucket_t {
    SEL _sel;
    IMP _imp;
};

struct lg_cache_t {
    struct lg_bucket_t * _buckets;
    mask_t _mask;
    uint16_t _flags;
    uint16_t _occupied;
};

struct lg_class_data_bits_t {
    uintptr_t bits;
};

struct lg_objc_class {
    Class ISA;
    Class superclass;
    struct lg_cache_t cache;             // formerly cache pointer and vtable
    struct lg_class_data_bits_t bits;    // class_rw_t * plus custom rr/alloc flags
};


int main(int argc, const char * argv[]) {
    @autoreleasepool {
        LGPerson *p  = [LGPerson alloc];
        Class pClass = [LGPerson class];  // objc_clas
        [p say1];
        [p say2];
        [p say3];
        [p say4];
         
        // _occupied  _mask 是什么  cup - 1
        // 会变化 2-3 -> 2-7
        // bucket 会有丢失  重新申请
        // 顺序有点问题  哈希
  
        // 线索 :
        
        struct lg_objc_class *lg_pClass = (__bridge struct lg_objc_class *)(pClass);
        NSLog(@"%hu - %u",lg_pClass->cache._occupied,lg_pClass->cache._mask);
        for (mask_t i = 0; i<lg_pClass->cache._mask; i++) {
            // 打印获取的 bucket
            struct lg_bucket_t bucket = lg_pClass->cache._buckets[i];
            NSLog(@"%@ - %p",NSStringFromSelector(bucket._sel),bucket._imp);
        }

        
        NSLog(@"Hello, World!");
    }
    return 0;
}

• 我们先只调用两个方法 [p say1] 和[p say2] 我们看打印结果

image.png

• 打开say3和say4方法，再次运行看打印

image.png

看到上面的打印，我们不禁有些疑问

• 1、_mask是什么？
• 2、_occupied 是什么？
• 3、为什么随着方法调用的增多，其打印的occupied 和 mask会变化？
• 4、bucket数据为什么会有丢失的情况？，例如2-7中，只有say3、say4方法有函数指针
• 5、2-7中say3、say4的打印顺序为什么是say4先打印，say3后打印，且还是挨着的，即顺序有问题？
• 6、打印的cache_t中的_ocupied为什么是从2开始？

乱序存储，我们一帮会想到哈希，那么是否和哈希有关，我们继续探索

cache_t底层原理分析

image.png

实现：

void cache_t::incrementOccupied() 
{
    _occupied++;
}

我们看到cache_t中有一个incrementOccupied方法：增加Occupied
全局搜索一下哪里调用了

image.png

在cache_t的插入方法里

image.png

void cache_t::insert(Class cls, SEL sel, IMP imp, id receiver)
{
#if CONFIG_USE_CACHE_LOCK
    cacheUpdateLock.assertLocked();
#else
    runtimeLock.assertLocked();
#endif

    ASSERT(sel != 0 && cls->isInitialized());

    // Use the cache as-is if it is less than 3/4 full
    mask_t newOccupied = occupied() + 1;
    unsigned oldCapacity = capacity(), capacity = oldCapacity;
    if (slowpath(isConstantEmptyCache())) {
        // Cache is read-only. Replace it.
        if (!capacity) capacity = INIT_CACHE_SIZE;
        reallocate(oldCapacity, capacity, /* freeOld */false);
    }
    else if (fastpath(newOccupied + CACHE_END_MARKER <= capacity / 4 * 3)) {
        // Cache is less than 3/4 full. Use it as-is.
    }
    else {
        capacity = capacity ? capacity * 2 : INIT_CACHE_SIZE;
        if (capacity > MAX_CACHE_SIZE) {
            capacity = MAX_CACHE_SIZE;
        }
        reallocate(oldCapacity, capacity, true);
    }

    bucket_t *b = buckets();
    mask_t m = capacity - 1;
    mask_t begin = cache_hash(sel, m);
    mask_t i = begin;

    // Scan for the first unused slot and insert there.
    // There is guaranteed to be an empty slot because the
    // minimum size is 4 and we resized at 3/4 full.
    do {
        if (fastpath(b[i].sel() == 0)) {
            incrementOccupied();
            b[i].set<Atomic, Encoded>(sel, imp, cls);
            return;
        }
        if (b[i].sel() == sel) {
            // The entry was added to the cache by some other thread
            // before we grabbed the cacheUpdateLock.
            return;
        }
    } while (fastpath((i = cache_next(i, m)) != begin));

    cache_t::bad_cache(receiver, (SEL)sel, cls);
}

首先开辟