cmd/compile,runtime: allocate defer records on the stack

When a defer is executed at most once in a function body,
we can allocate the defer record for it on the stack instead
of on the heap.

This should make defers like this (which are very common) faster.

This optimization applies to 363 out of the 370 static defer sites
in the cmd/go binary.

name     old time/op  new time/op  delta
Defer-4  52.2ns ± 5%  36.2ns ± 3%  -30.70%  (p=0.000 n=10+10)

Fixes #6980
Update #14939

Change-Id: I697109dd7aeef9e97a9eeba2ef65ff53d3ee1004
Reviewed-on: https://go-review.googlesource.com/c/go/+/171758
Run-TryBot: Keith Randall <khr@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Austin Clements <austin@google.com>

1 files changed, 55 insertions, 0 deletions

diff --git a/src/runtime/stack_test.go b/src/runtime/stack_test.go
index df73b3a1d5..143d3a99a0 100644
--- a/src/runtime/stack_test.go
+++ b/src/runtime/stack_test.go
@@ -799,3 +799,58 @@ func TestDeferLiveness(t *testing.T) {
 		t.Errorf("output:\n%s\n\nwant no output", output)
 	}
 }
+
+func TestDeferHeapAndStack(t *testing.T) {
+	P := 4     // processors
+	N := 10000 //iterations
+	D := 200   // stack depth
+
+	if testing.Short() {
+		P /= 2
+		N /= 10
+		D /= 10
+	}
+	c := make(chan bool)
+	for p := 0; p < P; p++ {
+		go func() {
+			for i := 0; i < N; i++ {
+				if deferHeapAndStack(D) != 2*D {
+					panic("bad result")
+				}
+			}
+			c <- true
+		}()
+	}
+	for p := 0; p < P; p++ {
+		<-c
+	}
+}
+
+// deferHeapAndStack(n) computes 2*n
+func deferHeapAndStack(n int) (r int) {
+	if n == 0 {
+		return 0
+	}
+	if n%2 == 0 {
+		// heap-allocated defers
+		for i := 0; i < 2; i++ {
+			defer func() {
+				r++
+			}()
+		}
+	} else {
+		// stack-allocated defers
+		defer func() {
+			r++
+		}()
+		defer func() {
+			r++
+		}()
+	}
+	r = deferHeapAndStack(n - 1)
+	escapeMe(new([1024]byte)) // force some GCs
+	return
+}
+
+// Pass a value to escapeMe to force it to escape.
+var escapeMe = func(x interface{}) {}