derp: add new health update and server restarting frame types

Updates #2756
Updates #2746

Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>

derp/derp.go

@@ -101,6 +101,20 @@
 
 	framePing = frameType(0x12) // 8 byte ping payload, to be echoed back in framePong
 	framePong = frameType(0x13) // 8 byte payload, the contents of the ping being replied to
+
+	// frameHealth is sent from server to client to tell the client
+	// if their connection is unhealthy somehow. Currently the only unhealthy state
+	// is whether the connection is detected as a duplicate.
+	// The entire frame body is the text of the error message. An empty message
+	// clears the error state.
+	frameHealth = frameType(0x14)
+
+	// frameRestarting is sent from server to client for the
+	// server to declare that it's restarting. Payload is two big
+	// endian uint32 durations in milliseconds: when to reconnect,
+	// and how long to try total. See ServerRestartingMessage docs for
+	// more details on how the client should interpret them.
+	frameRestarting = frameType(0x15)
 )
 
 var bin = binary.BigEndian

derp/derp_client.go

@@ -7,6 +7,7 @@
 import (
 	"bufio"
 	crand "crypto/rand"
+	"encoding/binary"
 	"encoding/json"
 	"errors"
 	"fmt"
@@ -369,6 +370,40 @@ type KeepAliveMessage struct{
 
 func (KeepAliveMessage) msg() {}
 
+// HealthMessage is a one-way message from server to client, declaring the
+// connection health state.
+type HealthMessage struct {
+	// Problem, if non-empty, is a description of why the connection
+	// is unhealthy.
+	//
+	// The empty string means the connection is healthy again.
+	//
+	// The default condition is healthy, so the server doesn't
+	// broadcast a HealthMessage until a problem exists.
+	Problem string
+}
+
+func (HealthMessage) msg() {}
+
+// ServerRestartingMessage is a one-way message from server to client,
+// advertising that the server is restarting.
+type ServerRestartingMessage struct {
+	// ReconnectIn is an advisory duration that the client should wait
+	// before attempting to reconnect. It might be zero.
+	// It exists for the server to smear out the reconnects.
+	ReconnectIn time.Duration
+
+	// TryFor is an advisory duration for how long the client
+	// should attempt to reconnect before giving up and proceeding
+	// with its normal connection failure logic. The interval
+	// between retries is undefined for now.
+	// A server should not send a TryFor duration more than a few
+	// seconds.
+	TryFor time.Duration
+}
+
+func (ServerRestartingMessage) msg() {}
+
 // Recv reads a message from the DERP server.
 //
 // The returned message may alias memory owned by the Client; it
@@ -486,6 +521,19 @@ func (c *Client) recvTimeout(timeout time.Duration) (m ReceivedMessage, err erro
 			}
 			copy(pm[:], b[:])
 			return pm, nil
+
+		case frameHealth:
+			return HealthMessage{Problem: string(b[:])}, nil
+
+		case frameRestarting:
+			var m ServerRestartingMessage
+			if n < 8 {
+				c.logf("[unexpected] dropping short server restarting frame")
+				continue
+			}
+			m.ReconnectIn = time.Duration(binary.BigEndian.Uint32(b[0:4])) * time.Millisecond
+			m.TryFor = time.Duration(binary.BigEndian.Uint32(b[4:8])) * time.Millisecond
+			return m, nil
 		}
 	}
 }

derp/derp_test.go

@@ -814,6 +814,33 @@ func TestClientRecv(t *testing.T) {
 			},
 			want: PingMessage{1, 2, 3, 4, 5, 6, 7, 8},
 		},
+		{
+			name: "health_bad",
+			input: []byte{
+				byte(frameHealth), 0, 0, 0, 3,
+				byte('B'), byte('A'), byte('D'),
+			},
+			want: HealthMessage{Problem: "BAD"},
+		},
+		{
+			name: "health_ok",
+			input: []byte{
+				byte(frameHealth), 0, 0, 0, 0,
+			},
+			want: HealthMessage{},
+		},
+		{
+			name: "server_restarting",
+			input: []byte{
+				byte(frameRestarting), 0, 0, 0, 8,
+				0, 0, 0, 1,
+				0, 0, 0, 2,
+			},
+			want: ServerRestartingMessage{
+				ReconnectIn: 1 * time.Millisecond,
+				TryFor:      2 * time.Millisecond,
+			},
+		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {