device: reduce RoutineHandshake allocations

Reduce allocations by eliminating byte reader, hand-rolled decoding and
reusing message structs.

Synthetic benchmark:

    var msgSink MessageInitiation
    func BenchmarkMessageInitiationUnmarshal(b *testing.B) {
        packet := make([]byte, MessageInitiationSize)
        reader := bytes.NewReader(packet)
        err := binary.Read(reader, binary.LittleEndian, &msgSink)
        if err != nil {
            b.Fatal(err)
        }
        b.Run("binary.Read", func(b *testing.B) {
            b.ReportAllocs()
            for range b.N {
                reader := bytes.NewReader(packet)
                _ = binary.Read(reader, binary.LittleEndian, &msgSink)
            }
        })
        b.Run("unmarshal", func(b *testing.B) {
            b.ReportAllocs()
            for range b.N {
                _ = msgSink.unmarshal(packet)
            }
        })
    }

Results:
                                         │      -      │
                                         │   sec/op    │
MessageInitiationUnmarshal/binary.Read-8   1.508µ ± 2%
MessageInitiationUnmarshal/unmarshal-8     12.66n ± 2%

                                         │      -       │
                                         │     B/op     │
MessageInitiationUnmarshal/binary.Read-8   208.0 ± 0%
MessageInitiationUnmarshal/unmarshal-8     0.000 ± 0%

                                         │      -       │
                                         │  allocs/op   │
MessageInitiationUnmarshal/binary.Read-8   2.000 ± 0%
MessageInitiationUnmarshal/unmarshal-8     0.000 ± 0%

Signed-off-by: Alexander Yastrebov <yastrebov.alex@gmail.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

device/noise-protocol.go

@@ -6,6 +6,7 @@
 package device
 
 import (
+	"encoding/binary"
 	"errors"
 	"fmt"
 	"sync"
@@ -115,6 +116,53 @@ type MessageCookieReply struct {
 	Cookie   [blake2s.Size128 + poly1305.TagSize]byte
 }
 
+var errMessageTooShort = errors.New("message too short")
+
+func (msg *MessageInitiation) unmarshal(b []byte) error {
+	if len(b) < MessageInitiationSize {
+		return errMessageTooShort
+	}
+
+	msg.Type = binary.LittleEndian.Uint32(b)
+	msg.Sender = binary.LittleEndian.Uint32(b[4:])
+	copy(msg.Ephemeral[:], b[8:])
+	copy(msg.Static[:], b[8+len(msg.Ephemeral):])
+	copy(msg.Timestamp[:], b[8+len(msg.Ephemeral)+len(msg.Static):])
+	copy(msg.MAC1[:], b[8+len(msg.Ephemeral)+len(msg.Static)+len(msg.Timestamp):])
+	copy(msg.MAC2[:], b[8+len(msg.Ephemeral)+len(msg.Static)+len(msg.Timestamp)+len(msg.MAC1):])
+
+	return nil
+}
+
+func (msg *MessageResponse) unmarshal(b []byte) error {
+	if len(b) < MessageResponseSize {
+		return errMessageTooShort
+	}
+
+	msg.Type = binary.LittleEndian.Uint32(b)
+	msg.Sender = binary.LittleEndian.Uint32(b[4:])
+	msg.Receiver = binary.LittleEndian.Uint32(b[8:])
+	copy(msg.Ephemeral[:], b[12:])
+	copy(msg.Empty[:], b[12+len(msg.Ephemeral):])
+	copy(msg.MAC1[:], b[12+len(msg.Ephemeral)+len(msg.Empty):])
+	copy(msg.MAC2[:], b[12+len(msg.Ephemeral)+len(msg.Empty)+len(msg.MAC1):])
+
+	return nil
+}
+
+func (msg *MessageCookieReply) unmarshal(b []byte) error {
+	if len(b) < MessageCookieReplySize {
+		return errMessageTooShort
+	}
+
+	msg.Type = binary.LittleEndian.Uint32(b)
+	msg.Receiver = binary.LittleEndian.Uint32(b[4:])
+	copy(msg.Nonce[:], b[8:])
+	copy(msg.Cookie[:], b[8+len(msg.Nonce):])
+
+	return nil
+}
+
 type Handshake struct {
 	state                     handshakeState
 	mutex                     sync.RWMutex