type WaitGroup struct {
   noCopy noCopy
   // 64-bit value: high 32 bits are counter, low 32 bits are waiter count.
   // 64-bit atomic operations require 64-bit alignment, but 32-bit
   // compilers only guarantee that 64-bit fields are 32-bit aligned.
   // For this reason on 32 bit architectures we need to check in state()
   // if state1 is aligned or not, and dynamically "swap" the field order if
   // needed.
   state1 uint64
   state2 uint32
}

func (wg *WaitGroup) state() (statep *uint64, semap *uint32) {
	if unsafe.Alignof(wg.state1) == 8 || uintptr(unsafe.Pointer(&wg.state1))%8 == 0 {
		// state1 is 64-bit aligned: nothing to do.
		return &wg.state1, &wg.state2
	} else {
		// state1 is 32-bit aligned but not 64-bit aligned: this means that
		// (&state1)+4 is 64-bit aligned.
		state := (*[3]uint32)(unsafe.Pointer(&wg.state1))
		return (*uint64)(unsafe.Pointer(&state[1])), &state[0]
	}
}

func (wg *WaitGroup) Add(delta int) {
    // wg.state()返回的是地址
	statep, semap := wg.state()
    // 原子操作，修改statep高32位的值，即counter的值
	state := atomic.AddUint64(statep, uint64(delta)<<32)
    // 右移32位，使高32位變成了低32，得到counter的值
	v := int32(state >> 32)
    // 直接取低32位，得到waiter的值
	w := uint32(state)
	// 不規范的操作
	if v < 0 {
		panic("sync: negative WaitGroup counter")
	}
    // 不規范的操作
	if w != 0 && delta > 0 && v == int32(delta) {
		panic("sync: WaitGroup misuse: Add called concurrently with Wait")
	}
    // 這是正常的情況
	if v > 0 || w == 0 {
		return
	}
    // 剩下的就是 counter == 0 且 waiter != 0 的情況
    // 在這個情況下，*statep 的值就是 waiter 的值，否則就有問題
    // 在這個情況下，所有的任務都已經完成，可以將 *statep 整個置0
    // 同時向所有的Waiter釋放信號量
	// This goroutine has set counter to 0 when waiters > 0.
	// Now there can't be concurrent mutations of state:
	// - Adds must not happen concurrently with Wait,
	// - Wait does not increment waiters if it sees counter == 0.
	// Still do a cheap sanity check to detect WaitGroup misuse.
	if *statep != state {
		panic("sync: WaitGroup misuse: Add called concurrently with Wait")
	}
	// Reset waiters count to 0.
	*statep = 0
	for ; w != 0; w-- {
		runtime_Semrelease(semap, false, 0)
	}
}

func (wg *WaitGroup) Done() {
	wg.Add(-1)
}

func (wg *WaitGroup) Wait() {
    // wg.state()返回的是地址
	statep, semap := wg.state()
    // for循環是配合CAS操作
	for {
		state := atomic.LoadUint64(statep)
		v := int32(state >> 32) // counter
		w := uint32(state) // waiter
        // 如果counter為0，說明所有的任務在調用Wait的時候就已經完成了，直接退出
        // 這就要求，必須在同步的情況下調用Add()，否則Wait可能先退出了
		if v == 0 {
			return
		}
		// waiter++，原子操作
		if atomic.CompareAndSwapUint64(statep, state, state+1) {
            // 如果自增成功，則獲取信號量，此處信號量起到了同步的作用
			runtime_Semacquire(semap)
			return
		}
	}
}