iOS objc_class之cache_t结构&流程解析

静态源码分析

---

objc_class 概况

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
 // ... 此处省略函数代码
}

• 从源码得知objc_class继承objc_object,其中有一个isa 联合体结构 8字节
• superclass 是一个Class是一个指向objc_class的指针类型,8字节
  结论1: 根据结构体内存排布得知，cache的首地址在objec_object首地址偏移16字节的位置

cache_t 源码

struct cache_t {
#if CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_OUTLINED
    explicit_atomic _buckets;
    explicit_atomic _mask;
#elif CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_HIGH_16
    explicit_atomic _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 _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();

#if __LP64__
    bool getBit(uint16_t flags) const {
        return _flags & flags;
    }
    void setBit(uint16_t set) {
        __c11_atomic_fetch_or((_Atomic(uint16_t) *)&_flags, set, __ATOMIC_RELAXED);
    }
    void clearBit(uint16_t clear) {
        __c11_atomic_fetch_and((_Atomic(uint16_t) *)&_flags, ~clear, __ATOMIC_RELAXED);
    }
#endif

#if FAST_CACHE_ALLOC_MASK
    bool hasFastInstanceSize(size_t extra) const
    {
        if (__builtin_constant_p(extra) && extra == 0) {
            return _flags & FAST_CACHE_ALLOC_MASK16;
        }
        return _flags & FAST_CACHE_ALLOC_MASK;
    }

    size_t fastInstanceSize(size_t extra) const
    {
        ASSERT(hasFastInstanceSize(extra));

        if (__builtin_constant_p(extra) && extra == 0) {
            return _flags & FAST_CACHE_ALLOC_MASK16;
        } else {
            size_t size = _flags & FAST_CACHE_ALLOC_MASK;
            // remove the FAST_CACHE_ALLOC_DELTA16 that was added
            // by setFastInstanceSize
            return align16(size + extra - FAST_CACHE_ALLOC_DELTA16);
        }
    }

    void setFastInstanceSize(size_t newSize)
    {
        // Set during realization or construction only. No locking needed.
        uint16_t newBits = _flags & ~FAST_CACHE_ALLOC_MASK;
        uint16_t sizeBits;

        // Adding FAST_CACHE_ALLOC_DELTA16 allows for FAST_CACHE_ALLOC_MASK16
        // to yield the proper 16byte aligned allocation size with a single mask
        sizeBits = word_align(newSize) + FAST_CACHE_ALLOC_DELTA16;
        sizeBits &= FAST_CACHE_ALLOC_MASK;
        if (newSize <= sizeBits) {
            newBits |= sizeBits;
        }
        _flags = newBits;
    }
#else
    bool hasFastInstanceSize(size_t extra) const {
        return false;
    }
    size_t fastInstanceSize(size_t extra) const {
        abort();
    }
    void setFastInstanceSize(size_t extra) {
        // nothing
    }
#endif

    static size_t bytesForCapacity(uint32_t cap);
    static struct bucket_t * endMarker(struct bucket_t *b, uint32_t cap);

    void reallocate(mask_t oldCapacity, mask_t newCapacity, bool freeOld);
    void insert(Class cls, SEL sel, IMP imp, id receiver);

    static void bad_cache(id receiver, SEL sel, Class isa) __attribute__((noreturn, cold));
};

我们先把属性拎出来分别是

• _buckets: 一个指向结构体bucket_t的指针
• _mask:掩码，值为容量（capacity）-1，因为capacity为2^n，所以掩码的规律是高位为0低位为1的组合(00000111, 00001111, 00011111)，可以用取&运算来做hash算法。
• _flags:一些cache_t的标志写入其中,目前先不做考虑
• _occupied:大小为已存入的方法数量。

bucket_t 结构

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 _imp;
    explicit_atomic _sel;
#else
    explicit_atomic _sel;
    explicit_atomic _imp;
#endif

    // Compute the ptrauth signing modifier from &_imp, newSel, and cls.
    uintptr_t modifierForSEL(SEL newSel, Class cls) const {
        return (uintptr_t)&_imp ^ (uintptr_t)newSel ^ (uintptr_t)cls;
    }

    // Sign newImp, with &_imp, newSel, and cls as modifiers.
    uintptr_t encodeImp(IMP newImp, SEL newSel, Class cls) const {
        if (!newImp) return 0;
#if CACHE_IMP_ENCODING == CACHE_IMP_ENCODING_PTRAUTH
        return (uintptr_t)
            ptrauth_auth_and_resign(newImp,
                                    ptrauth_key_function_pointer, 0,
                                    ptrauth_key_process_dependent_code,
                                    modifierForSEL(newSel, cls));
#elif CACHE_IMP_ENCODING == CACHE_IMP_ENCODING_ISA_XOR
        return (uintptr_t)newImp ^ (uintptr_t)cls;
#elif CACHE_IMP_ENCODING == CACHE_IMP_ENCODING_NONE
        return (uintptr_t)newImp;
#else
#error Unknown method cache IMP encoding.
#endif
    }

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 
    void set(SEL newSel, IMP newImp, Class cls);
};

把重要的东西拎出来:

• 两个属性: _imp和_sel;
• 两个方法: sel()和imp();

执行代码辅助分析

---

准备如下代码

@interface LGPerson : NSObject
@property (nonatomic, copy) NSString *lgName;
@property (nonatomic, strong) NSString *nickName;
- (void)sayHello;
- (void)sayCode;
- (void)sayMaster;
- (void)sayNB;
+ (void)sayHappy;
@end

@implementation LGPerson
- (void)sayHello{
    NSLog(@"LGPerson say : %s",__func__);
}

- (void)sayCode{
    NSLog(@"LGPerson say : %s",__func__);
}

- (void)sayMaster{
    NSLog(@"LGPerson say : %s",__func__);
}

- (void)sayNB{
    NSLog(@"LGPerson say : %s",__func__);
}

+ (void)sayHappy{
    NSLog(@"LGPerson say : %s",__func__);
}
@end

int main(int argc, const char * argv[]) {
    @autoreleasepool {
        // insert code here...
        LGPerson *p  = [LGPerson alloc];
        Class pClass = [LGPerson class];

        [p sayHello];
        [p sayCode];
        [p sayMaster];
        [p sayNB];
        NSLog(@"%@",pClass);
    }
    return 0;
}

我们在[p sayHello];加入断点运行,分析如下图

image.png

但我们运行到[p sayCode];打印时

image.png

我们不妨通过cache_t 里面的方法buckets (),以及进行下列分析

image.png

为什么我们不直接拿cache_t里面的_bucket来操作呢，因为这个指针类型其实被explicit_atomic修饰了，无法直接打印。接下来的调用sel()方法亦是如此.

结论2:我们在cache内的bucket找到了我们的调用方法

深入分析cache_t缓存流程

cache_t方法实现的文件中找到

image.png

具体流程为:
1、 计算当前缓存占用的数量
mask_t newOccupied = occupied() + 1;
2、执行条件：

• 如果当前未空缓存，也就是第一次进来: 申请开辟内存 容量为4

ALWAYS_INLINE
void cache_t::reallocate(mask_t oldCapacity, mask_t newCapacity, bool freeOld)
{
   bucket_t *oldBuckets = buckets();
   bucket_t *newBuckets = allocateBuckets(newCapacity);

   // Cache's old contents are not propagated. 
   // This is thought to save cache memory at the cost of extra cache fills.
   // fixme re-measure this

   ASSERT(newCapacity > 0);
   ASSERT((uintptr_t)(mask_t)(newCapacity-1) == newCapacity-1);

   setBucketsAndMask(newBuckets, newCapacity - 1);
   
   if (freeOld) {
       cache_collect_free(oldBuckets, oldCapacity);
   }
}

• 如果存入缓存后小于等于3/4，不做处理
• 如果前两个条件都不满足，则开始扩容;扩容规则为:放弃就缓存，新缓存大小为原来的2倍,并且重新梳理缓存

3、针对这一次的方法进行bucket内部存储