类（三）-- cache_t分析

类（一）-- 底层探索
类（二）-- method归属
类（三）-- cache_t分析

cache_t作用

用来缓存通过对象调用过的方法。当再次调用的时候，能够快速的通过sel找到方法imp

cache_t结构

相关源码如下：

#if defined(__arm64__) && __LP64__
#define CACHE_MASK_STORAGE CACHE_MASK_STORAGE_HIGH_16
#elif defined(__arm64__) && !__LP64__
#define CACHE_MASK_STORAGE CACHE_MASK_STORAGE_LOW_4
#else
#define CACHE_MASK_STORAGE CACHE_MASK_STORAGE_OUTLINED
#endif

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;
    
    //省略后面代码
    ......
}

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
    //省略后面代码
    ......
}

• 结构体cache_t中进行了编译条件判断：

  • CACHE_MASK_STORAGE_OUTLINED：其它情况（本文主要研究方向，另外两种同理，但是稍微复杂）
  • CACHE_MASK_STORAGE_HIGH_16：代表arm64平台并且是64位设备
  • CACHE_MASK_STORAGE_LOW_4：代表arm64平台、非64位设备

• _buckets：struct bucket_t类型，数组形式存储sel和imp。（注意，不同平台下，sel和imp顺序不一样。原因注释中有解释，就是一种针对不同平台的优化。）

• _mask：mask_t类型。也是针对不同平台的定义的别名，源码如下：

  #if __LP64__
  typedef uint32_t mask_t;  // x86_64 & arm64 asm are less efficient with 16-bits
  #else
  typedef uint16_t mask_t;
  

  作用是记录当前已开辟的内存空间可用的最大值。

• _flags：uint16_t类型，内部使用的标志位。

• _occupied：uint16_t类型，表示缓存中已经占用数。如果缓存了一个方法，_occupied就设置为1。两个方法，则为2。

lldb调试

Person *p  = [Person alloc];
Class pClass = [Person class];
[p sayHello];
[p sayCode];
NSLog(@"%@",pClass);

• 打印类的内存地址
• cache_t cache在结构体中第三个位置，前两个是指针类型，分别是isa和superclass，所以内存便宜是16字节，转换16进制是10。因此在原地址上进行+10操作。
• 得到cache_t *类型的$1，调用buckets()函数得到bucket_t *类型的$2
• 调用sel()和imp(pClass)函数，可以打印出缓存的方法的sel和imp
• 通过指针偏移打印后面的缓存方法信息。
• 通过打印$1中的值，能够看到目前_occupied的值是2，说明目前的缓存空间占用了2个位置，就是示例中调用过的两个方法被缓存了。

方法缓存的插入逻辑

对象调用方法会间接调用源码中的下面函数

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)) { // 4  3 + 1 bucket cache_t
        // Cache is less than 3/4 full. Use it as-is.
    }
    else {
        capacity = capacity ? capacity * 2 : INIT_CACHE_SIZE;  // 扩容两倍 4
        if (capacity > MAX_CACHE_SIZE) {
            capacity = MAX_CACHE_SIZE;
        }
        reallocate(oldCapacity, capacity, true);  // 内存 库容完毕
    }

    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);
}

源码的逻辑：

• 首先进行cache是否为空的状态if (slowpath(isConstantEmptyCache()))，然后对容器大小进行初始值赋值capacity = INIT_CACHE_SIZE，并且调用reallocate函数进行内存空间开辟
• 然后进行容器大小的3/4判断，如果超过3/4，进行二倍扩容，调用reallocate函数开辟内存空间
• 保证空间够用后，最后进行保存被调用方法的sel和imp：
  • 此处对sel进行哈希计算（哈希函数：sel转换成无符号的长整形 & 当前的可用空间大小mask），求出位置
  • 进行do-while循环，看看这个位置有没有值：
    • 没有值就插入
    • 有值进行sel比较，相等就直接返回，说明此方法已经缓存过；
    • 如果位置上有值，并且sel不相等，就对位置+1后 & 总空间大小mask，进行再次哈希（哈希冲突的开放地址法）。）。