iOS进阶之底层原理-锁、synchronized

锁主要分为两种，自旋锁和互斥锁。

自旋锁

线程反复检查锁变量是否可用，处于忙等状态。一旦获取了自旋锁，线程会一直保持该锁，直至释放，会阻塞线程，但是避免了线程上下文的调度开销，适合短时间的场合。

互斥锁

是⼀种⽤于多线程编程中，防⽌两条线程同时对同⼀公共资源（⽐如全局变量）进⾏读写的机制。该⽬的通过将代码切⽚成⼀个⼀个的临界区⽽达成。

递归锁

同一个线程可以加锁N次而不会引发死锁 。NSRecursiveLock ；pthread_mutex(recursive)

读写锁

读写锁实际是⼀种特殊的⾃旋锁，它把对共享资源的访问者划分成读者和写者，读者只对共享资源进⾏读访问，写者则需要对共享资源进⾏写操作。

synchronized

想要看源码，却不知道在哪里，根据经验就进入汇编调试了。发现了objc_sync_enter入口和objc_sync_exit出口，这是在objc源码中。

objc_sync_enter，如果没有objc的话，就什么也不操作；有objc生成对应的SyncData，内部封装了互斥锁mutex，这是一个链表的数据结构，会进行tls线程操作。ACQUIRE状态会对对象进行锁的计数加一。

int objc_sync_enter(id obj)
{
    int result = OBJC_SYNC_SUCCESS;

    if (obj) {
        SyncData* data = id2data(obj, ACQUIRE);
        ASSERT(data);
        data->mutex.lock();
    } else {
        // @synchronized(nil) does nothing
        if (DebugNilSync) {
            _objc_inform("NIL SYNC DEBUG: @synchronized(nil); set a breakpoint on objc_sync_nil to debug");
        }
        objc_sync_nil();
    }

    return result;
}
typedef struct alignas(CacheLineSize) SyncData {
    struct SyncData* nextData;
    DisguisedPtr<objc_object> object;
    int32_t threadCount;  // number of THREADS using this block
    recursive_mutex_t mutex;
} SyncData;

objc_sync_exit，出口会调用id2data，状态传RELEASE，会对内部封装的lockCount减去，最后为0的时候，从表中移除

int objc_sync_exit(id obj)
{
    int result = OBJC_SYNC_SUCCESS;
    if (obj) {
        SyncData* data = id2data(obj, RELEASE); 
        if (!data) {
            result = OBJC_SYNC_NOT_OWNING_THREAD_ERROR;
        } else {
            bool okay = data->mutex.tryUnlock();
            if (!okay) {
                result = OBJC_SYNC_NOT_OWNING_THREAD_ERROR;
            }
        }
    } else {
        // @synchronized(nil) does nothing
    }
    return result;
}

id2data这里是核心

• 刚加锁时，外面传入状态为ACQUIRE，会从StripedMap表中判断是否有根据这个对象生成的SyncData，有的话，lockCount加1，然后线程操作，没有的话，根据对象创建SyncData
• 退出时也一样会调用id2data只是状态为RELEASE，同样会从StripedMap表中根据obj获取到SyncData，再相应的lockCount减1，最后如果变为0的话，移除StripedMap表中的SyncData

static SyncData* id2data(id object, enum usage why)
{
    spinlock_t *lockp = &LOCK_FOR_OBJ(object);
    SyncData **listp = &LIST_FOR_OBJ(object);
    SyncData* result = NULL;

#if SUPPORT_DIRECT_THREAD_KEYS
    // Check per-thread single-entry fast cache for matching object
    bool fastCacheOccupied = NO;
    SyncData *data = (SyncData *)tls_get_direct(SYNC_DATA_DIRECT_KEY);
    if (data) {
        fastCacheOccupied = YES;

        if (data->object == object) {
            // Found a match in fast cache.
            uintptr_t lockCount;

            result = data;
            lockCount = (uintptr_t)tls_get_direct(SYNC_COUNT_DIRECT_KEY);
            if (result->threadCount <= 0  ||  lockCount <= 0) {
                _objc_fatal("id2data fastcache is buggy");
            }

            switch(why) {
            case ACQUIRE: {
                lockCount++;
                tls_set_direct(SYNC_COUNT_DIRECT_KEY, (void*)lockCount);
                break;
            }
            case RELEASE:
                lockCount--;
                tls_set_direct(SYNC_COUNT_DIRECT_KEY, (void*)lockCount);
                if (lockCount == 0) {
                    // remove from fast cache
                    tls_set_direct(SYNC_DATA_DIRECT_KEY, NULL);
                    // atomic because may collide with concurrent ACQUIRE
                    OSAtomicDecrement32Barrier(&result->threadCount);
                }
                break;
            case CHECK:
                // do nothing
                break;
            }

            return result;
        }
    }
#endif

    // Check per-thread cache of already-owned locks for matching object
    SyncCache *cache = fetch_cache(NO);
    if (cache) {
        unsigned int i;
        for (i = 0; i < cache->used; i++) {
            SyncCacheItem *item = &cache->list[i];
            if (item->data->object != object) continue;

            // Found a match.
            result = item->data;
            if (result->threadCount <= 0  ||  item->lockCount <= 0) {
                _objc_fatal("id2data cache is buggy");
            }
                
            switch(why) {
            case ACQUIRE:
                item->lockCount++;
                break;
            case RELEASE:
                item->lockCount--;
                if (item->lockCount == 0) {
                    // remove from per-thread cache
                    cache->list[i] = cache->list[--cache->used];
                    // atomic because may collide with concurrent ACQUIRE
                    OSAtomicDecrement32Barrier(&result->threadCount);
                }
                break;
            case CHECK:
                // do nothing
                break;
            }

            return result;
        }
    }

    // Thread cache didn't find anything.
    // Walk in-use list looking for matching object
    // Spinlock prevents multiple threads from creating multiple 
    // locks for the same new object.
    // We could keep the nodes in some hash table if we find that there are
    // more than 20 or so distinct locks active, but we don't do that now.
    
    lockp->lock();

    {
        SyncData* p;
        SyncData* firstUnused = NULL;
        for (p = *listp; p != NULL; p = p->nextData) {
            if ( p->object == object ) {
                result = p;
                // atomic because may collide with concurrent RELEASE
                OSAtomicIncrement32Barrier(&result->threadCount);
                goto done;
            }
            if ( (firstUnused == NULL) && (p->threadCount == 0) )
                firstUnused = p;
        }
    
        // no SyncData currently associated with object
        if ( (why == RELEASE) || (why == CHECK) )
            goto done;
    
        // an unused one was found, use it
        if ( firstUnused != NULL ) {
            result = firstUnused;
            result->object = (objc_object *)object;
            result->threadCount = 1;
            goto done;
        }
    }

    // Allocate a new SyncData and add to list.
    // XXX allocating memory with a global lock held is bad practice,
    // might be worth releasing the lock, allocating, and searching again.
    // But since we never free these guys we won't be stuck in allocation very often.
    posix_memalign((void **)&result, alignof(SyncData), sizeof(SyncData));
    result->object = (objc_object *)object;
    result->threadCount = 1;
    new (&result->mutex) recursive_mutex_t(fork_unsafe_lock);
    result->nextData = *listp;
    *listp = result;
    
 done:
    lockp->unlock();
    if (result) {
        // Only new ACQUIRE should get here.
        // All RELEASE and CHECK and recursive ACQUIRE are 
        // handled by the per-thread caches above.
        if (why == RELEASE) {
            // Probably some thread is incorrectly exiting 
            // while the object is held by another thread.
            return nil;
        }
        if (why != ACQUIRE) _objc_fatal("id2data is buggy");
        if (result->object != object) _objc_fatal("id2data is buggy");

#if SUPPORT_DIRECT_THREAD_KEYS
        if (!fastCacheOccupied) {
            // Save in fast thread cache
            tls_set_direct(SYNC_DATA_DIRECT_KEY, result);
            tls_set_direct(SYNC_COUNT_DIRECT_KEY, (void*)1);
        } else 
#endif
        {
            // Save in thread cache
            if (!cache) cache = fetch_cache(YES);
            cache->list[cache->used].data = result;
            cache->list[cache->used].lockCount = 1;
            cache->used++;
        }
    }

    return result;
}

锁的性能

这里有张从其他地方获来的截图，可以详细的介绍了各种锁的性能。synchronized性能显示最差是因为内部不断的增删改查，但是可以避免死锁，所以使用频繁。