runtime/chan.go: improve closed channel receive performance

Use this benchmark ut:

```go
func BenchmarkReceiveDataFromClosedChan(b *testing.B) {
	count := b.N
	ch := make(chan struct{}, count)
	for i := 0; i < count; i++ {
		ch <- struct{}{}
	}

	b.ResetTimer()
	for range ch {
	}
}
```

Benchmark 10 times(`go test -bench=.`), and then use `benchstat` got the result:

```shell
name                         old time/op  new time/op  delta
ReceiveDataFromClosedChan-5  12.0ns ± 1%  11.4ns ± 0%  -5.54%  (p=0.000 n=10+8)
```

Fixes:  #52067

Change-Id: I8db398cc8c04a46cb66ffb6768ab72a87903812f
GitHub-Last-Rev: 1e0142416f
GitHub-Pull-Request: golang/go#52068
Reviewed-on: https://go-review.googlesource.com/c/go/+/396884
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
Reviewed-by: Keith Randall <khr@google.com>
Run-TryBot: Keith Randall <khr@google.com>
Auto-Submit: Keith Randall <khr@google.com>

src/runtime/chan.go

@@ -510,24 +510,28 @@ func chanrecv(c *hchan, ep unsafe.Pointer, block bool) (selected, received bool)
 
 	lock(&c.lock)
 
-	if c.closed != 0 && c.qcount == 0 {
-		if raceenabled {
-			raceacquire(c.raceaddr())
+	if c.closed != 0 {
+		if c.qcount == 0 {
+			if raceenabled {
+				raceacquire(c.raceaddr())
+			}
+			unlock(&c.lock)
+			if ep != nil {
+				typedmemclr(c.elemtype, ep)
+			}
+			return true, false
 		}
-		unlock(&c.lock)
-		if ep != nil {
-			typedmemclr(c.elemtype, ep)
+		// The channel has been closed, but the channel's buffer have data.
+	} else {
+		// Just found waiting sender with not closed.
+		if sg := c.sendq.dequeue(); sg != nil {
+			// Found a waiting sender. If buffer is size 0, receive value
+			// directly from sender. Otherwise, receive from head of queue
+			// and add sender's value to the tail of the queue (both map to
+			// the same buffer slot because the queue is full).
+			recv(c, sg, ep, func() { unlock(&c.lock) }, 3)
+			return true, true
 		}
-		return true, false
-	}
-
-	if sg := c.sendq.dequeue(); sg != nil {
-		// Found a waiting sender. If buffer is size 0, receive value
-		// directly from sender. Otherwise, receive from head of queue
-		// and add sender's value to the tail of the queue (both map to
-		// the same buffer slot because the queue is full).
-		recv(c, sg, ep, func() { unlock(&c.lock) }, 3)
-		return true, true
 	}
 
 	if c.qcount > 0 {

src/runtime/chan_test.go

@@ -1127,6 +1127,19 @@ func BenchmarkSelectProdCons(b *testing.B) {
 	}
 }
 
+func BenchmarkReceiveDataFromClosedChan(b *testing.B) {
+	count := b.N
+	ch := make(chan struct{}, count)
+	for i := 0; i < count; i++ {
+		ch <- struct{}{}
+	}
+	close(ch)
+
+	b.ResetTimer()
+	for range ch {
+	}
+}
+
 func BenchmarkChanCreation(b *testing.B) {
 	b.RunParallel(func(pb *testing.PB) {
 		for pb.Next() {