bytes: minor optimization to lastIndexFunc

Before and after:
BenchmarkTrimSpace  20000000   81.3 ns/op
BenchmarkTrimSpace  50000000   58.0 ns/op

(most whitespace trimming is ASCII whitespace)

Same optimization appeared a handful of other places
in this file, but not here.

R=golang-dev, dave
CC=golang-dev
https://golang.org/cl/7305063

src/pkg/bytes/bytes.go

@@ -571,7 +571,10 @@ func indexFunc(s []byte, f func(r rune) bool, truth bool) int {
 // inverted.
 func lastIndexFunc(s []byte, f func(r rune) bool, truth bool) int {
 	for i := len(s); i > 0; {
-		r, size := utf8.DecodeLastRune(s[0:i])
+		r, size := rune(s[i-1]), 1
+		if r >= utf8.RuneSelf {
+			r, size = utf8.DecodeLastRune(s[0:i])
+		}
 		i -= size
 		if f(r) == truth {
 			return i

src/pkg/bytes/bytes_test.go

@@ -1073,3 +1073,10 @@ func BenchmarkFieldsFunc(b *testing.B) {
 		FieldsFunc(fieldsInput, unicode.IsSpace)
 	}
 }
+
+func BenchmarkTrimSpace(b *testing.B) {
+	s := []byte("  Some text.  \n")
+	for i := 0; i < b.N; i++ {
+		TrimSpace(s)
+	}
+}