mesh-controller/internal/inventory/tunnel.go

package inventory

import (
	"context"
	"encoding/json"
	"errors"
	"fmt"
	"net/netip"
	"strings"
	"time"

	"github.com/jackc/pgx/v5"
)

// The tunnel a node found on its machine, and the peers it carried (novox/hq ADR 0105).
//
// On an adopted node that is the hub, the private network takes over the tunnel it finds: its
// private key, its port, its address and range, and every peer the found interface had. The node
// presents what it found when it enrols, in the same breath as its keys — the found tunnel's key is
// its key on the private network from then on — and the mesh composes every address from it: the
// hub's is the tunnel's, the range is the tunnel's, and a peer that enrols keeps the address the
// tunnel already had for its key.

// Tunnel is what a node found on its machine, as it presented it. No private key: the node keeps
// it as its own overlay key, sealed like any own secret, and the mesh records only the public half
// — which is then the node's overlay key too.
type Tunnel struct {
	// Interface, Unit and Config are what the host takes over: the found interface, the unit
	// that raised it, and its configuration file, which is kept like any held file.
	Interface string `json:"interface"`
	Unit      string `json:"unit"`
	Config    string `json:"config"`
	// Port is the port the found interface listened on — one the hosting provider already lets
	// through, which is why it is worth taking.
	Port int `json:"port"`
	// Address is the interface's own address with its prefix length, 192.0.2.1/24; Range is the
	// network that prefix names, 192.0.2.0/24.
	Address string `json:"address"`
	Range   string `json:"range"`
	// PublicKey is the found interface's, which every peer knows the tunnel by.
	PublicKey string `json:"public_key"`
	// Peers are the found interface's peers: each a public key and the address the tunnel routed
	// to it.
	Peers []TunnelPeer `json:"peers,omitempty"`
	// At is when the node presented it; zero on a tunnel not yet recorded.
	At time.Time `json:"at,omitempty"`
}

// TunnelPeer is one peer of a found tunnel.
type TunnelPeer struct {
	PublicKey string `json:"public_key"`
	// Address is the one host address the tunnel routed to the peer, without a prefix.
	Address string `json:"address"`
}

// Carried is what a node last said about carrying the tunnel it found: the found interface down
// and disabled, the mesh's up in its place with the found key.
type Carried struct {
	Interface string `json:"interface"`
	Port      int    `json:"port"`
	Range     string `json:"range"`
	Peers     int    `json:"peers"`
	// State is one of the CarriedStates: the found interface is still up and the mesh's is not
	// (not taken), the found one is down and the mesh's up with its key (taken), or the found one
	// is down and the mesh's is not up — the one state where the peers reach nothing. Note is
	// what the host did about it, when it did something. Kept is where the found configuration's
	// original was kept.
	State string    `json:"state"`
	Note  string    `json:"note,omitempty"`
	Kept  string    `json:"kept,omitempty"`
	At    time.Time `json:"at"`
}

// The states a carried tunnel's account can be in, as the host says them.
const (
	CarriedNotTaken = "not-taken"
	CarriedTaken    = "taken"
	CarriedDown     = "down"
)

// CarriedPeer is one peer of the adopted tunnel as the mesh holds it: a peer of the tunnel, and
// — once a node enrols with that key — a node of the mesh as well.
type CarriedPeer struct {
	PublicKey string
	Address   string
	// EnrolledAs names the node that enrolled with this key, or is empty while none has.
	EnrolledAs string
	// Named is what the operator said this peer is, before it enrolled (novox/hq issue 112) —
	// a statement the mesh records and cannot verify, which is why enrolment checks it.
	Named string
}

// ErrNoTunnel is asking about a tunnel on a node that presented none.
var ErrNoTunnel = errors.New("that node presented no tunnel")

// RecordTunnel keeps what a node presented, replacing what was there: the question is the tunnel
// as the node found it now. The peers are replaced whole for the same reason.
func (i *Inventory) RecordTunnel(ctx context.Context, nodeID string, t Tunnel) error {
	if strings.TrimSpace(t.Interface) == "" || strings.TrimSpace(t.PublicKey) == "" {
		return errors.New("a found tunnel names its interface and its public key, and this names neither")
	}
	if _, err := netip.ParsePrefix(t.Range); err != nil {
		return fmt.Errorf("the found tunnel's range %q is not a range: %w", t.Range, err)
	}
	address, err := netip.ParsePrefix(t.Address)
	if err != nil {
		return fmt.Errorf("the found tunnel's address %q is not an address with a prefix: %w", t.Address, err)
	}
	peers := make([]TunnelPeer, 0, len(t.Peers))
	for _, p := range t.Peers {
		host, single := peerHost(p.Address)
		if !single {
			// A peer routed a range rather than one address is a spoke's view of its hub — the
			// predecessor gives a spoke the whole subnet through the hub — and a hub is not a peer
			// the mesh carries. Skipped, not refused: a spoke enrols with what it found, and only
			// the hub's peers are ever carried (novox/hq ADR 0105).
			continue
		}
		if !address.Masked().Contains(host) {
			return fmt.Errorf("the found tunnel's peer %s is routed at %s, outside the tunnel's %s",
				shortKey(p.PublicKey), host, t.Range)
		}
		peers = append(peers, TunnelPeer{PublicKey: p.PublicKey, Address: host.String()})
	}
	t.Peers = nil
	t.At = time.Now().UTC()
	raw, err := json.Marshal(t)
	if err != nil {
		return err
	}
	tx, err := i.store.Pool().Begin(ctx)
	if err != nil {
		return err
	}
	defer func() { _ = tx.Rollback(context.WithoutCancel(ctx)) }()
	if _, err := tx.Exec(ctx, `update node set tunnel = $2 where id = $1`, nodeID, raw); err != nil {
		return err
	}
	if _, err := tx.Exec(ctx, `delete from tunnel_peer where node = $1`, nodeID); err != nil {
		return err
	}
	for _, p := range peers {
		if _, err := tx.Exec(ctx,
			`insert into tunnel_peer (node, public_key, address) values ($1, $2, $3::inet)`,
			nodeID, p.PublicKey, p.Address); err != nil {
			return fmt.Errorf("recording the found tunnel's peer %s: %w", shortKey(p.PublicKey), err)
		}
	}
	return tx.Commit(ctx)
}

// peerHost is the one host address a peer's allowed address names — a bare address, or a /32
// (or /128) — and false for anything wider or unreadable: a peer routed a whole range is not a
// machine with an address the mesh could give a node.
func peerHost(allowed string) (netip.Addr, bool) {
	allowed = strings.TrimSpace(allowed)
	if a, err := netip.ParseAddr(allowed); err == nil {
		return a, true
	}
	p, err := netip.ParsePrefix(allowed)
	if err != nil || !p.IsSingleIP() {
		return netip.Addr{}, false
	}
	return p.Addr(), true
}

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

// TunnelOf is the tunnel a node presented, with its peers, or ErrNoTunnel.
func (i *Inventory) TunnelOf(ctx context.Context, name string) (Tunnel, error) {
	var raw []byte
	var id string
	err := i.store.Pool().QueryRow(ctx,
		`select id, tunnel from node where name = $1`, name).Scan(&id, &raw)
	if errors.Is(err, pgx.ErrNoRows) {
		return Tunnel{}, fmt.Errorf("%w: %s", ErrNoSuchNode, name)
	}
	if err != nil {
		return Tunnel{}, err
	}
	if len(raw) == 0 {
		return Tunnel{}, fmt.Errorf("%w: %s", ErrNoTunnel, name)
	}
	var t Tunnel
	if err := json.Unmarshal(raw, &t); err != nil {
		return Tunnel{}, err
	}
	t.Peers, err = i.tunnelPeers(ctx, id)
	return t, err
}

func (i *Inventory) tunnelPeers(ctx context.Context, nodeID string) ([]TunnelPeer, error) {
	rows, err := i.store.Pool().Query(ctx,
		`select public_key, host(address) from tunnel_peer where node = $1 order by address`, nodeID)
	if err != nil {
		return nil, err
	}
	defer rows.Close()
	var out []TunnelPeer
	for rows.Next() {
		var p TunnelPeer
		if err := rows.Scan(&p.PublicKey, &p.Address); err != nil {
			return nil, err
		}
		out = append(out, p)
	}
	return out, rows.Err()
}

// AdoptedTunnel is the tunnel the mesh's private network runs over, if the hub adopted one: the
// hub's found tunnel, when the hub's overlay key is the tunnel's. Absent, the mesh runs on its own
// range — and a hub that found a tunnel but holds another key did not adopt it, which `overlay
// show` says.
//
// The condition on the key is the condition of the whole record: a hub raised with a key of its
// own would drop every peer's packets on the found port (novox/hq ADR 0105, option 2), so the
// tunnel is adopted only when the hub answers to the key its peers know. **Not a condition on the
// node's mode**: the range and the carried peers are facts of the mesh once the tunnel is taken,
// and converging the hub — which flips its mode — must not renumber the mesh or drop the peers
// still reaching it.
func (i *Inventory) AdoptedTunnel(ctx context.Context) (Tunnel, string, bool, error) {
	var name string
	var key *string
	err := i.store.Pool().QueryRow(ctx,
		`select name, overlay_key from node where is_hub and tunnel is not null`).
		Scan(&name, &key)
	if errors.Is(err, pgx.ErrNoRows) {
		return Tunnel{}, "", false, nil
	}
	if err != nil {
		return Tunnel{}, "", false, err
	}
	t, err := i.TunnelOf(ctx, name)
	if err != nil {
		return Tunnel{}, "", false, err
	}
	if key == nil || *key != t.PublicKey {
		return t, name, false, nil
	}
	return t, name, true, nil
}

// CarriedPeers is every peer of the adopted tunnel, with the node that enrolled under its key
// where one has: peers of the tunnel, and nodes of the mesh once they enrol. Empty when the hub
// adopted no tunnel.
func (i *Inventory) CarriedPeers(ctx context.Context) ([]CarriedPeer, error) {
	rows, err := i.store.Pool().Query(ctx,
		`select p.public_key, host(p.address), coalesce(n.name, ''), coalesce(p.named, '')
		   from tunnel_peer p
		   join node hub on hub.id = p.node and hub.is_hub
		        and hub.tunnel is not null and hub.overlay_key = hub.tunnel->>'public_key'
		   left join node n on n.overlay_key = p.public_key
		  order by p.address`)
	if err != nil {
		return nil, err
	}
	defer rows.Close()
	var out []CarriedPeer
	for rows.Next() {
		var p CarriedPeer
		if err := rows.Scan(&p.PublicKey, &p.Address, &p.EnrolledAs, &p.Named); err != nil {
			return nil, err
		}
		out = append(out, p)
	}
	return out, rows.Err()
}

// NamePeer records the operator's statement that a carried address is a particular machine
// (novox/hq issue 112). Refused when nothing carried has that address, when a node of the mesh
// already has the name — the statement would collide with something verified — and when another
// peer was already named it. Naming an enrolled peer is refused too: its name is the node's now.
func (i *Inventory) NamePeer(ctx context.Context, address, name string) error {
	peers, err := i.CarriedPeers(ctx)
	if err != nil {
		return err
	}
	var at *CarriedPeer
	for idx := range peers {
		if peers[idx].Address == address {
			at = &peers[idx]
			continue
		}
		if peers[idx].Named == name {
			return fmt.Errorf("the carried peer at %s is already named %q — one machine per name",
				peers[idx].Address, name)
		}
	}
	if at == nil {
		return fmt.Errorf("no carried peer has the address %s — `overlay show` lists them", address)
	}
	if at.EnrolledAs != "" {
		return fmt.Errorf("the peer at %s enrolled as %q — its name is the node's now", address, at.EnrolledAs)
	}
	if _, err := i.NodeByName(ctx, name); err == nil {
		return fmt.Errorf("%q is a node of this mesh — a carried peer cannot be named after one", name)
	}
	tag, err := i.store.Pool().Exec(ctx,
		`update tunnel_peer set named = $2 where host(address) = $1`, address, name)
	if err != nil {
		return err
	}
	if tag.RowsAffected() == 0 {
		return fmt.Errorf("no carried peer has the address %s", address)
	}
	return nil
}

// FoundTunnel is a node's found tunnel with the node's mode, for composing: the takeover is
// declared to an adopted node only, since only there is a found unit kept to be stopped.
type FoundTunnel struct {
	Tunnel
	NodeAdopted bool
}

// Tunnels is every node's found tunnel by node name, for the ones whose overlay key is the
// tunnel's — the ones whose private network takes it over. A found tunnel under another key is
// left running beside the mesh's, and ADR 0100's rule that the ranges differ applies to it.
func (i *Inventory) Tunnels(ctx context.Context) (map[string]FoundTunnel, error) {
	rows, err := i.store.Pool().Query(ctx,
		`select name, tunnel, adopted from node
		  where tunnel is not null and overlay_key = tunnel->>'public_key'`)
	if err != nil {
		return nil, err
	}
	defer rows.Close()
	out := map[string]FoundTunnel{}
	for rows.Next() {
		var name string
		var raw []byte
		var adopted bool
		if err := rows.Scan(&name, &raw, &adopted); err != nil {
			return nil, err
		}
		var t Tunnel
		if err := json.Unmarshal(raw, &t); err != nil {
			return nil, err
		}
		out[name] = FoundTunnel{Tunnel: t, NodeAdopted: adopted}
	}
	return out, rows.Err()
}

// ErrStaleRekey is a rekey that names a previous overlay key other than the one recorded: a
// replay of a rekey already done, or one made against a record that has since moved on.
var ErrStaleRekey = errors.New("the rekey names a previous overlay key that is not the node's current one")

// Rekey records that a node took a found tunnel's key as its overlay key after enrolling (novox/hq
// ADR 0105): the key and the tunnel are recorded as enrolment would have, and a hub is moved to the
// tunnel's address so nothing derived from it is stale. The caller has verified the node signed
// for this; what is checked here is that it follows the record — `previous` is the overlay key the
// node holds now — so the same message cannot be applied twice.
func (i *Inventory) Rekey(ctx context.Context, nodeID, previous, key string, t Tunnel) error {
	if key != t.PublicKey {
		return errors.New("a rekey takes a tunnel over with the tunnel's own key, and this names another")
	}
	var current *string
	var hub bool
	if err := i.store.Pool().QueryRow(ctx,
		`select overlay_key, is_hub from node where id = $1`, nodeID).Scan(&current, &hub); err != nil {
		return err
	}
	if (current == nil && previous != "") || (current != nil && *current != previous) {
		return ErrStaleRekey
	}
	if err := i.RecordOverlayKey(ctx, nodeID, key); err != nil {
		return err
	}
	if err := i.RecordTunnel(ctx, nodeID, t); err != nil {
		return err
	}
	if hub {
		address, err := netip.ParsePrefix(t.Address)
		if err != nil {
			return err
		}
		if _, err := i.place(ctx, nodeID, address.Addr().String()); err != nil {
			return err
		}
	}
	return nil
}

// RecordCarriedTunnel keeps what a node last said about carrying its found tunnel.
func (i *Inventory) RecordCarriedTunnel(ctx context.Context, nodeID string, c Carried) error {
	c.At = time.Now().UTC()
	raw, err := json.Marshal(c)
	if err != nil {
		return err
	}
	_, err = i.store.Pool().Exec(ctx, `update node set tunnel_carried = $2 where id = $1`, nodeID, raw)
	return err
}

// CarriedTunnelOf is a node's last account of carrying its found tunnel, and whether it ever gave one.
func (i *Inventory) CarriedTunnelOf(ctx context.Context, name string) (Carried, bool, error) {
	var raw []byte
	err := i.store.Pool().QueryRow(ctx, `select tunnel_carried from node where name = $1`, name).Scan(&raw)
	if errors.Is(err, pgx.ErrNoRows) {
		return Carried{}, false, fmt.Errorf("%w: %s", ErrNoSuchNode, name)
	}
	if err != nil {
		return Carried{}, false, err
	}
	if len(raw) == 0 {
		return Carried{}, false, nil
	}
	var c Carried
	if err := json.Unmarshal(raw, &c); err != nil {
		return Carried{}, false, err
	}
	return c, true, nil
}