cache_t的底层分析

380 阅读3分钟

cache_t顾名思义,其作用就是缓存一些数据。在Class的底层结构中,存在着cache_t类型的cache, 它的主要作用是调用方法的缓存。方便下次调用是直接从缓存中获取IMP地址,加快执行效率。

分析cache_t的底层结构

struct cache_t {
private:
    explicit_atomic<uintptr_t> _bucketsAndMaybeMask;
    union {
        struct {
            explicit_atomic<mask_t>    _maybeMask;
#if __LP64__
            uint16_t                   _flags;
#endif
            uint16_t                   _occupied;
        };
        explicit_atomic<preopt_cache_t *> _originalPreoptCache;
    };
}

cache_t底层是一个结构体,包含着一个uintptr_t的_bucketsAndMaybeMask,然后就是一个共用体, 共用体中有一个结构体和一个preopt_cache_t的指针。简单了解了cache_t的底层结构之后, 接着去看看还有些什么。

#if CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_OUTLINED
    // _bucketsAndMaybeMask is a buckets_t pointer
    // _maybeMask is the buckets mask

    static constexpr uintptr_t bucketsMask = ~0ul;
    static_assert(!CONFIG_USE_PREOPT_CACHES, "preoptimized caches not supported");
#elif CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_HIGH_16_BIG_ADDRS
    static constexpr uintptr_t maskShift = 48;
    static constexpr uintptr_t maxMask = ((uintptr_t)1 << (64 - maskShift)) - 1;
    static constexpr uintptr_t bucketsMask = ((uintptr_t)1 << maskShift) - 1;
    
    static_assert(bucketsMask >= MACH_VM_MAX_ADDRESS, "Bucket field doesn't have enough bits for arbitrary pointers.");
#if CONFIG_USE_PREOPT_CACHES
    static constexpr uintptr_t preoptBucketsMarker = 1ul;
    static constexpr uintptr_t preoptBucketsMask = bucketsMask & ~preoptBucketsMarker;
#endif
#elif CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_HIGH_16
    // _bucketsAndMaybeMask is a buckets_t pointer in the low 48 bits
    // _maybeMask is unused, the mask is stored in the top 16 bits.

    // 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.");

#if CONFIG_USE_PREOPT_CACHES
    static constexpr uintptr_t preoptBucketsMarker = 1ul;
#if __has_feature(ptrauth_calls)
    // 63..60: hash_mask_shift
    // 59..55: hash_shift
    // 54.. 1: buckets ptr + auth
    //      0: always 1
    static constexpr uintptr_t preoptBucketsMask = 0x007ffffffffffffe;
    static inline uintptr_t preoptBucketsHashParams(const preopt_cache_t *cache) {
        uintptr_t value = (uintptr_t)cache->shift << 55;
        // masks have 11 bits but can be 0, so we compute
        // the right shift for 0x7fff rather than 0xffff
        return value | ((objc::mask16ShiftBits(cache->mask) - 1) << 60);
    }
#else
    // 63..53: hash_mask
    // 52..48: hash_shift
    // 47.. 1: buckets ptr
    //      0: always 1
    static constexpr uintptr_t preoptBucketsMask = 0x0000fffffffffffe;
    static inline uintptr_t preoptBucketsHashParams(const preopt_cache_t *cache) {
        return (uintptr_t)cache->hash_params << 48;
    }
#endif
#endif // CONFIG_USE_PREOPT_CACHES
#elif CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_LOW_4
    // _bucketsAndMaybeMask is a buckets_t pointer in the top 28 bits
    // _maybeMask is unused, the mask length is stored in the low 4 bits

    static constexpr uintptr_t maskBits = 4;
    static constexpr uintptr_t maskMask = (1 << maskBits) - 1;
    static constexpr uintptr_t bucketsMask = ~maskMask;
    static_assert(!CONFIG_USE_PREOPT_CACHES, "preoptimized caches not supported");
#else
#error Unknown cache mask storage type.
#endif

这里都是一些静态变量,其中看到有很多左移操作,并且注释中最后也解释那些位代表啥,与isa类似。接着就是一些成员函数(缓存操作,就像数据库一下,CURD,所以挑重点的说)。

void insert(SEL sel, IMP imp, id receiver); insert明显就是插入,将对应的sel,imp 插入缓存。

void cache_t::insert(SEL sel, IMP imp, id receiver)
{
    runtimeLock.assertLocked();

    // Never cache before +initialize is done
    if (slowpath(!cls()->isInitialized())) {
        return;
    }

    if (isConstantOptimizedCache()) {
        _objc_fatal("cache_t::insert() called with a preoptimized cache for %s",
                    cls()->nameForLogging());
    }

#if DEBUG_TASK_THREADS
    return _collecting_in_critical();
#else
#if CONFIG_USE_CACHE_LOCK
    mutex_locker_t lock(cacheUpdateLock);
#endif

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

    // Use the cache as-is if until we exceed our expected fill ratio.
    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 <= cache_fill_ratio(capacity))) {
        // Cache is less than 3/4 or 7/8 full. Use it as-is.
    }
#if CACHE_ALLOW_FULL_UTILIZATION
    else if (capacity <= FULL_UTILIZATION_CACHE_SIZE && newOccupied + CACHE_END_MARKER <= capacity) {
        // Allow 100% cache utilization for small buckets. Use it as-is.
    }
#endif
    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.
    do {
        if (fastpath(b[i].sel() == 0)) {
            incrementOccupied();
            b[i].set<Atomic, Encoded>(b, 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));

    bad_cache(receiver, (SEL)sel);
#endif // !DEBUG_TASK_THREADS
}

insert具体逻辑:

newOccupied先将当前的occupied()+1,occupied(英文的意思:占位,使用中),联想到缓存,那大概就跟存储容量相关。判断当前cache是否为空,如果为空就创建缓存。如果当前缓存不为空,并且大于3/4容量就重新2倍扩容。 然后将sel与capacity进行hash,得到一个索引,并将对应的sel,imp,和class存入缓存。如果当前已经存在,就不做任何操作。

具体函数分析

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) {
        collect_free(oldBuckets, oldCapacity);
    }
}

获取旧的oldBuckets,创建一个newCapacity大小的newBuckets, 然后setBucketsAndMask(newBuckets, newCapacity - 1);,并释放旧的oldBuckets

其中bucket的结构也是一个结构体,里面缓存着selimp

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
void cache_t::setBucketsAndMask(struct bucket_t *newBuckets, mask_t newMask)
{
    // objc_msgSend uses mask and buckets with no locks.
    // It is safe for objc_msgSend to see new buckets but old mask.
    // (It will get a cache miss but not overrun the buckets' bounds).
    // It is unsafe for objc_msgSend to see old buckets and new mask.
    // Therefore we write new buckets, wait a lot, then write new mask.
    // objc_msgSend reads mask first, then buckets.

#ifdef __arm__
    // ensure other threads see buckets contents before buckets pointer
    mega_barrier();

    _bucketsAndMaybeMask.store((uintptr_t)newBuckets, memory_order_relaxed);

    // ensure other threads see new buckets before new mask
    mega_barrier();

    _maybeMask.store(newMask, memory_order_relaxed);
    _occupied = 0;
#elif __x86_64__ || i386
    // ensure other threads see buckets contents before buckets pointer
    _bucketsAndMaybeMask.store((uintptr_t)newBuckets, memory_order_release);

    // ensure other threads see new buckets before new mask
    _maybeMask.store(newMask, memory_order_release);
    _occupied = 0;
#else
#error Don't know how to do setBucketsAndMask on this architecture.
#endif
}

setBucketsAndMask(newBuckets, newCapacity - 1); 中主要就是对创建的buckets和**newMask(就是newCapacity-1)**存储,然后将_occupied赋值为0,表示当前cache中一个内容都没有,从中知道 cache_t 结构中的第一个成员变量 _bucketsAndMaybeMask,以及 _occupied 的含义。

hash函数

static inline mask_t cache_hash(SEL sel, mask_t mask) 
{
    uintptr_t value = (uintptr_t)sel;
#if CONFIG_USE_PREOPT_CACHES
    value ^= value >> 7;
#endif
    return (mask_t)(value & mask);
}

selsel右移7位的值并异或,然后在于mask进行与操作。

总结:

cache_t.png