diff --git a/src/sync/once.go b/src/sync/once.go
index d8ef952ea54..84761970dd8 100644
--- a/src/sync/once.go
+++ b/src/sync/once.go
@@ -10,8 +10,13 @@ import (
 
 // Once is an object that will perform exactly one action.
 type Once struct {
-	m    Mutex
+	// done indicates whether the action has been performed.
+	// It is first in the struct because it is used in the hot path.
+	// The hot path is inlined at every call site.
+	// Placing done first allows more compact instructions on some architectures (amd64/x86),
+	// and fewer instructions (to calculate offset) on other architectures.
 	done uint32
+	m    Mutex
 }
 
 // Do calls the function f if and only if Do is being called for the
@@ -33,10 +38,13 @@ type Once struct {
 // without calling f.
 //
 func (o *Once) Do(f func()) {
-	if atomic.LoadUint32(&o.done) == 1 {
-		return
+	if atomic.LoadUint32(&o.done) == 0 {
+		// Outlined slow-path to allow inlining of the fast-path.
+		o.doSlow(f)
 	}
-	// Slow-path.
+}
+
+func (o *Once) doSlow(f func()) {
 	o.m.Lock()
 	defer o.m.Unlock()
 	if o.done == 0 {
diff --git a/test/inline_sync.go b/test/inline_sync.go
index a14f58c4320..3473b92b4ac 100644
--- a/test/inline_sync.go
+++ b/test/inline_sync.go
@@ -31,3 +31,10 @@ func small6() { // ERROR "can inline small6"
 	// the Lock fast path should be inlined
 	mutex.Lock() // ERROR "inlining call to sync\.\(\*Mutex\)\.Lock" "&sync\.m\.state escapes to heap"
 }
+
+var once *sync.Once
+
+func small7() { // ERROR "can inline small7"
+        // the Do fast path should be inlined
+        once.Do(small5) // ERROR "inlining call to sync\.\(\*Once\)\.Do" "&sync\.o\.done escapes to heap"
+}