mesh-host/internal/tunnel/tunnel.go

// Package tunnel reads the tunnel a predecessor left on a machine, so the mesh's private network
// can take it over in place (novox/hq ADR 0105).
//
// On an adopted node that is the hub, the mesh's interface is raised with the found interface's
// private key, on its port, with its address and range, and every peer it had. The found interface
// is stopped, never flushed; its configuration stays on disk until the take is proven — a peer
// has handshaken with the mesh's interface — and is then retired (novox/hq ADR 0119). What this
// package does is the
// reading: which interface is there, what its file says, and what of that travels to the mesh —
// everything but the private key, which becomes the node's own overlay key and is stored the way
// that key is stored.
package tunnel

import (
	"context"
	"crypto/ecdh"
	"encoding/base64"
	"encoding/json"
	"errors"
	"fmt"
	"net"
	"os"
	"sort"
	"strconv"
	"strings"
)

// Runner executes a command. The same shape as everywhere else in this host.
type Runner func(ctx context.Context, name string, args ...string) (string, error)

// MeshInterface is the private network's own interface, which is never the found one.
const MeshInterface = "mesh0"

// ConfigDir is where wg-quick keeps an interface's configuration.
const ConfigDir = "/etc/wireguard"

// Found is a tunnel as found on the machine: everything the mesh is told about it, and the
// private key, which it is not.
type Found struct {
	// Interface, Unit and Config are what the mesh's interface takes over.
	Interface string `json:"interface"`
	Unit      string `json:"unit"`
	Config    string `json:"config"`
	// Port is the port the interface listens on; Address its own address with prefix length;
	// Range the network that prefix names.
	Port    int    `json:"port"`
	Address string `json:"address"`
	Range   string `json:"range"`
	// MTU is the interface's, when the found config set one. Kept because a tuned tunnel (a path
	// that needs 1380, say) breaks silently if the mesh's interface comes up at the 1420 default:
	// no ping fails, but TLS handshakes stall and transfers hang (novox/hq: a taken tunnel carries
	// its MTU). Zero when the config named none, and the mesh sets no MTU line then.
	MTU int `json:"mtu,omitempty"`
	// PublicKey is what every peer knows this tunnel by — derived here from the private key, so
	// it is the key the file actually holds and not a comment beside it.
	PublicKey string `json:"public_key"`
	Peers     []Peer `json:"peers,omitempty"`

	// privateKey never travels and never prints: not in JSON, not in %v. It is read once, to
	// become the node's overlay key, and the file it came from is kept as found.
	privateKey string
}

// Peer is one peer of the found tunnel.
type Peer struct {
	PublicKey string `json:"public_key"`
	// Address is the one address the tunnel routes to the peer, as the file's AllowedIPs said it
	// (with or without a /32).
	Address string `json:"address"`
	// Endpoint is where the found tunnel dialled the peer, if it did. Not carried to the mesh —
	// a carried peer dials in, as it always did — but kept so a person reading the report sees
	// what the file said.
	Endpoint string `json:"endpoint,omitempty"`
}

// PrivateKey is the found interface's private key, base64 as WireGuard writes it. The one
// accessor; a caller that has it is taking it as the node's key.
func (f Found) PrivateKey() string { return f.privateKey }

// String is what a found tunnel prints as: never the key.
func (f Found) String() string {
	return fmt.Sprintf("%s on port %d, %s in %s, %d peer(s)", f.Interface, f.Port, f.Address,
		f.Range, len(f.Peers))
}

// MarshalJSON writes everything but the private key, whatever a caller passes to an encoder.
func (f Found) MarshalJSON() ([]byte, error) {
	type wire Found
	return json.Marshal(wire(f))
}

// ErrNone is a machine with no tunnel to take over.
var ErrNone = errors.New("no tunnel is up on this machine besides the mesh's own")

// ErrSeveral is a machine with more than one, when nobody said which.
var ErrSeveral = errors.New("more than one tunnel is up on this machine")

// ReadFile is how a configuration is read; a variable so a test can hand in a file.
var ReadFile = os.ReadFile

// Find reads the tunnel to take over: the one named, or the one interface up besides the mesh's
// own. Nothing up is ErrNone — an ordinary answer, the machine has no tunnel to adopt — and two
// or more with none named is ErrSeveral, naming them, because choosing would be deciding.
//
// Read from the interface's configuration file rather than from the running interface: the file
// is what wg-quick raised and what carries the address, which the kernel does not report per
// interface the way the key and peers are. The running interface is consulted only to know the
// tunnel is up — a file for an interface nothing runs is not a tunnel the peers are reaching.
func Find(ctx context.Context, run Runner, named string) (Found, error) {
	out, err := run(ctx, "wg", "show", "interfaces")
	if err != nil {
		return Found{}, fmt.Errorf("cannot ask which tunnels are up on this machine: %w", err)
	}
	var up []string
	for _, iface := range strings.Fields(out) {
		if iface != MeshInterface {
			up = append(up, iface)
		}
	}
	sort.Strings(up)
	iface := named
	switch {
	case named != "":
		found := false
		for _, u := range up {
			if u == named {
				found = true
			}
		}
		if !found {
			return Found{}, fmt.Errorf("%s was named as the tunnel to take over and is not up; up: %s",
				named, orNone(up))
		}
	case len(up) == 0:
		return Found{}, ErrNone
	case len(up) > 1:
		return Found{}, fmt.Errorf("%w: %s. Name the one the predecessor's machines reach with --tunnel",
			ErrSeveral, strings.Join(up, ", "))
	default:
		iface = up[0]
	}

	path := ConfigDir + "/" + iface + ".conf"
	raw, err := ReadFile(path)
	if err != nil {
		return Found{}, fmt.Errorf("%s is up and its configuration cannot be read: %w", iface, err)
	}
	found, err := Parse(raw)
	if err != nil {
		return Found{}, fmt.Errorf("%s: %w", path, err)
	}
	found.Interface, found.Unit, found.Config = iface, "wg-quick@"+iface, path
	return found, nil
}

// Handshaken is how many peers of an interface have completed a handshake with it: the proof that
// the interface carries the tunnel, rather than merely being up (novox/hq ADR 0119).
//
// Asked of the running interface, since a handshake is a fact about the kernel's tunnel that no
// file records. A question that cannot be asked — no `wg` on the machine, no such interface, a
// permission refused — is an error and never a zero: "no peer has handshaken" retires nothing
// either, but it is a different thing to tell a person.
func Handshaken(ctx context.Context, run Runner, iface string) (int, error) {
	out, err := run(ctx, "wg", "show", iface, "latest-handshakes")
	if err != nil {
		return 0, fmt.Errorf("cannot ask %s which peers have handshaken: %w", iface, err)
	}
	return ParseHandshakes(out)
}

// ParseHandshakes reads `wg show <interface> latest-handshakes`: one line per peer, its public key
// and the Unix time of its latest handshake, tab-separated — zero for a peer that never has. What
// is counted is the peers with a time. A line that is not a key and a time is refused rather than
// skipped: output this does not understand is not evidence of anything.
func ParseHandshakes(out string) (int, error) {
	n := 0
	for i, line := range strings.Split(out, "\n") {
		line = strings.TrimSpace(line)
		if line == "" {
			continue
		}
		fields := strings.Fields(line)
		if len(fields) != 2 {
			return 0, fmt.Errorf("line %d of the handshakes is not a peer and a time: %q", i+1, line)
		}
		at, err := strconv.ParseInt(fields[1], 10, 64)
		if err != nil || at < 0 {
			return 0, fmt.Errorf("line %d of the handshakes does not end in a time: %q", i+1, line)
		}
		if at > 0 {
			n++
		}
	}
	return n, nil
}

func orNone(names []string) string {
	if len(names) == 0 {
		return "none"
	}
	return strings.Join(names, ", ")
}

// Parse reads a wg-quick configuration: the interface's key, port and address, and each peer's
// key and allowed address. Refused when it lacks what the mesh needs — a key, an address with a
// prefix — because a tunnel taken over without them is one the peers cannot reach.
func Parse(raw []byte) (Found, error) {
	var f Found
	section := ""
	var peer *Peer
	closePeer := func() error {
		if peer == nil {
			return nil
		}
		if peer.PublicKey == "" {
			return errors.New("a [Peer] section has no PublicKey")
		}
		if peer.Address == "" {
			return fmt.Errorf("the peer %s has no AllowedIPs, so the tunnel routes nothing to it",
				short(peer.PublicKey))
		}
		f.Peers = append(f.Peers, *peer)
		peer = nil
		return nil
	}
	for n, line := range strings.Split(string(raw), "\n") {
		line = strings.TrimSpace(line)
		if i := strings.IndexAny(line, "#;"); i >= 0 {
			line = strings.TrimSpace(line[:i])
		}
		if line == "" {
			continue
		}
		if strings.HasPrefix(line, "[") {
			if err := closePeer(); err != nil {
				return Found{}, err
			}
			section = strings.ToLower(strings.Trim(line, "[]"))
			if section == "peer" {
				peer = &Peer{}
			}
			continue
		}
		key, value, ok := strings.Cut(line, "=")
		if !ok {
			return Found{}, fmt.Errorf("line %d is not `key = value`", n+1)
		}
		key, value = strings.ToLower(strings.TrimSpace(key)), strings.TrimSpace(value)
		switch section {
		case "interface":
			switch key {
			case "privatekey":
				f.privateKey = value
			case "listenport":
				port, err := strconv.Atoi(value)
				if err != nil || port < 1 || port > 65535 {
					return Found{}, fmt.Errorf("ListenPort %q is not a port", value)
				}
				f.Port = port
			case "mtu":
				mtu, err := strconv.Atoi(value)
				if err != nil || mtu < 576 || mtu > 65535 {
					return Found{}, fmt.Errorf("MTU %q is not a plausible MTU", value)
				}
				f.MTU = mtu
			case "address":
				// The first address is the interface's; a second family would be a second
				// tunnel's worth of addressing, which this does not carry.
				first := strings.TrimSpace(strings.Split(value, ",")[0])
				ip, network, err := net.ParseCIDR(first)
				if err != nil {
					return Found{}, fmt.Errorf("Address %q is not an address with a prefix length, "+
						"and the range the mesh takes over is read from the prefix", first)
				}
				f.Address = first
				f.Range = network.String()
				_ = ip
			}
		case "peer":
			switch key {
			case "publickey":
				peer.PublicKey = value
			case "allowedips":
				peer.Address = strings.TrimSpace(strings.Split(value, ",")[0])
			case "endpoint":
				peer.Endpoint = value
			}
		}
	}
	if err := closePeer(); err != nil {
		return Found{}, err
	}
	if f.privateKey == "" {
		return Found{}, errors.New("no PrivateKey in [Interface]; the mesh takes a tunnel over with its key or not at all")
	}
	if f.Address == "" {
		return Found{}, errors.New("no Address in [Interface], so neither the hub's address nor the range can be read")
	}
	if f.Port == 0 {
		return Found{}, errors.New("no ListenPort in [Interface]: a tunnel with no port is one nothing dials, so there is nothing to take over")
	}
	public, err := PublicKeyOf(f.privateKey)
	if err != nil {
		return Found{}, err
	}
	f.PublicKey = public
	return f, nil
}

// PublicKeyOf derives the public half of a WireGuard private key, both base64.
func PublicKeyOf(privateBase64 string) (string, error) {
	raw, err := base64.StdEncoding.DecodeString(privateBase64)
	if err != nil {
		return "", fmt.Errorf("the private key is not base64: %w", err)
	}
	private, err := ecdh.X25519().NewPrivateKey(raw)
	if err != nil {
		return "", fmt.Errorf("the private key is not a Curve25519 key: %w", err)
	}
	return base64.StdEncoding.EncodeToString(private.PublicKey().Bytes()), nil
}

func short(key string) string {
	if len(key) > 8 {
		return key[:8] + "…"
	}
	return key
}