Files
netbird/client/iface/configurer/kernel_unix.go
T
Zoltan Papp 01185ba353 [client] Configure the userspace device through its typed API (#7937)
* [client] Configure the userspace device through its typed API

The userspace configurer drove wireguard-go through UAPI text: every
write was rendered to the configuration protocol and parsed back, and
every read, including the per-second statistics poll, dumped the whole
device as text and parsed it again. With 10000 peers a statistics read
cost about 16 ms, and clearing one endpoint needed a peer remove and a
re-add because the protocol cannot clear an endpoint or drop a single
prefix in place. The allowed IP mirror in the configurer existed only
to feed those rewrites.

The wireguard-go fork now exposes a typed peer API, so the configurer
calls the device directly: ConfigurePeer for creates and updates,
single-prefix add and remove on the routing table, ClearEndpoint, and
accessors for statistics. The mirror, the UAPI rendering and the
parsers are gone from the userspace path; the UAPI socket for wg show
stays.

Clearing an endpoint keeps the peer object, its counters and its
allowed IPs, but resets the session and switches the keepalive off
until the next endpoint arrives. The watcher expects a fresh handshake
after an endpoint reset, and an endpoint-less peer with a keepalive
would retry handshakes it cannot send; this is what the remove and
re-add provided before. Handshake times now carry nanosecond precision
like the kernel path.

Measured with 10000 peers against the UAPI implementation: clearing an
endpoint drops from 713 ms to 3 ms for all peers, a statistics read
from 15 ms to 0.9 ms, a full dump from 18 ms to 4 ms, and single
allowed IP changes are 7 to 20 times faster.

* [client] Keep the allowed IP mirror kernel-only

The userspace configurer no longer uses the allowed IP mirror, so its
ensure method and the preshared key config helper had no caller left
on Windows and macOS, where the kernel configurer is not compiled, and
the unused linter failed there.

The mirror and its tests now carry the kernel build tag, the prefix
normalizers that both paths share move to common.go, and the preshared
key helper moves next to its only caller.

* [client] Trim historical references from configurer comments

* [client] Keep the endpoint zone in the userspace configurer

The UAPI path wrote the endpoint as text, so a link-local IPv6 endpoint
reached the device with its zone. The typed path built the address from
the IP bytes only and dropped the zone, leaving the device with an
unroutable fe80:: address. The activity recorder keeps the zone-less
address it always had.

* [client] Run the prefix conversion tests on every platform

prefixesToIPNets lives in the untagged common.go and the userspace stats
path uses it on every platform, but its tests stayed in the kernel-tagged
allowedips_test.go, so darwin and windows CI stopped running them. Move
them next to the normalizePrefix tests. The round-trip test stays tagged
because ipNetsToPrefixes is kernel-only.

* [client] Pin wireguard-go to the merged typed peer API

The typed peer configuration API landed on master as #23, so the
replace no longer needs to point at the PR branch commit.
2026-10-12 10:29:26 +02:00

384 lines
10 KiB
Go

//go:build (linux && !android) || freebsd
package configurer
import (
"fmt"
"net"
"net/netip"
"slices"
"time"
log "github.com/sirupsen/logrus"
"golang.zx2c4.com/wireguard/wgctrl"
"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
"github.com/netbirdio/netbird/monotime"
)
type KernelConfigurer struct {
deviceName string
statsCache *statsCache
allowedIPs *allowedIPStore
}
// NewKernelConfigurer creates a configurer with an empty allowed IP mirror
// and a statistics cache for the named kernel device.
func NewKernelConfigurer(deviceName string) *KernelConfigurer {
c := &KernelConfigurer{
deviceName: deviceName,
allowedIPs: newAllowedIPStore(),
}
c.statsCache = newStatsCache(statsCacheTTL, c.fetchStats)
return c
}
// ConfigureInterface sets the device key, port and firewall mark, replacing all peers.
// The allowed IP mirror is reset only after the device accepts the configuration.
func (c *KernelConfigurer) ConfigureInterface(privateKey string, port int) error {
log.Debugf("adding Wireguard private key")
key, err := wgtypes.ParseKey(privateKey)
if err != nil {
return err
}
fwmark := getFwmark()
config := wgtypes.Config{
PrivateKey: &key,
ReplacePeers: true,
FirewallMark: &fwmark,
ListenPort: &port,
}
err = c.configure(config)
if err != nil {
return fmt.Errorf(`received error "%w" while configuring interface %s with port %d`, err, c.deviceName, port)
}
c.allowedIPs.reset()
return nil
}
// SetPresharedKey sets the preshared key for a peer.
// If updateOnly is true, only updates the existing peer; if false, creates or updates.
func (c *KernelConfigurer) SetPresharedKey(peerKey string, psk wgtypes.Key, updateOnly bool) error {
parsedPeerKey, err := wgtypes.ParseKey(peerKey)
if err != nil {
return err
}
cfg := buildPresharedKeyConfig(parsedPeerKey, psk, updateOnly)
if err := c.configure(cfg); err != nil {
return err
}
// Without updateOnly this creates the peer when it is absent, so the store has to
// know about it even though no allowed IP was configured.
if !updateOnly {
c.allowedIPs.ensure(parsedPeerKey)
}
return nil
}
// UpdatePeer creates or updates a peer, merging allowed IPs with its existing set.
// Prefixes assigned to this peer are transferred from their previous owners.
func (c *KernelConfigurer) UpdatePeer(peerKey string, allowedIps []netip.Prefix, keepAlive time.Duration, endpoint *net.UDPAddr, preSharedKey *wgtypes.Key) error {
peerKeyParsed, err := wgtypes.ParseKey(peerKey)
if err != nil {
return err
}
peer := wgtypes.PeerConfig{
PublicKey: peerKeyParsed,
ReplaceAllowedIPs: false,
// don't replace allowed ips, wg will handle duplicated peer IP
AllowedIPs: prefixesToIPNets(allowedIps),
PersistentKeepaliveInterval: &keepAlive,
Endpoint: endpoint,
PresharedKey: preSharedKey,
}
config := wgtypes.Config{
Peers: []wgtypes.PeerConfig{peer},
}
err = c.configure(config)
if err != nil {
return fmt.Errorf(`received error "%w" while updating peer on interface %s with settings: allowed ips %s, endpoint %s`, err, c.deviceName, allowedIps, endpoint.String())
}
c.allowedIPs.add(peerKeyParsed, allowedIps)
return nil
}
// RemoveEndpointAddress clears the endpoint of a peer while keeping it configured.
// Neither the netlink API nor the userspace one can clear an endpoint in place, so the peer
// is removed and re-added with the allowed IPs it already had.
func (c *KernelConfigurer) RemoveEndpointAddress(peerKey string) error {
peerKeyParsed, err := wgtypes.ParseKey(peerKey)
if err != nil {
return err
}
allowedIPs, err := c.peerAllowedIPs(peerKeyParsed)
if err != nil {
return err
}
removePeerCfg := wgtypes.PeerConfig{
PublicKey: peerKeyParsed,
Remove: true,
}
if err := c.configure(wgtypes.Config{Peers: []wgtypes.PeerConfig{removePeerCfg}}); err != nil {
return fmt.Errorf("remove peer %s from interface %s: %w", peerKey, c.deviceName, err)
}
reAddPeerCfg := wgtypes.PeerConfig{
PublicKey: peerKeyParsed,
AllowedIPs: prefixesToIPNets(allowedIPs),
ReplaceAllowedIPs: true,
}
if err := c.configure(wgtypes.Config{Peers: []wgtypes.PeerConfig{reAddPeerCfg}}); err != nil {
c.allowedIPs.forget(peerKeyParsed)
return fmt.Errorf(
"re-add peer %s to interface %s with allowed IPs %v: %w",
peerKey, c.deviceName, allowedIPs, err,
)
}
return nil
}
// RemovePeer removes a peer and forgets its allowed IPs after a successful device write.
func (c *KernelConfigurer) RemovePeer(peerKey string) error {
peerKeyParsed, err := wgtypes.ParseKey(peerKey)
if err != nil {
return err
}
peer := wgtypes.PeerConfig{
PublicKey: peerKeyParsed,
Remove: true,
}
config := wgtypes.Config{
Peers: []wgtypes.PeerConfig{peer},
}
err = c.configure(config)
if err != nil {
return fmt.Errorf(`received error "%w" while removing peer %s from interface %s`, err, peerKey, c.deviceName)
}
c.allowedIPs.forget(peerKeyParsed)
return nil
}
// AddAllowedIP adds a prefix to an existing peer; an absent peer is a silent no-op.
func (c *KernelConfigurer) AddAllowedIP(peerKey string, allowedIP netip.Prefix) error {
peerKeyParsed, err := wgtypes.ParseKey(peerKey)
if err != nil {
return err
}
peer := wgtypes.PeerConfig{
PublicKey: peerKeyParsed,
UpdateOnly: true,
ReplaceAllowedIPs: false,
AllowedIPs: prefixesToIPNets([]netip.Prefix{allowedIP}),
}
config := wgtypes.Config{
Peers: []wgtypes.PeerConfig{peer},
}
err = c.configure(config)
if err != nil {
return fmt.Errorf(`received error "%w" while adding allowed Ip to peer on interface %s with settings: allowed ips %s`, err, c.deviceName, allowedIP)
}
c.allowedIPs.addExisting(peerKeyParsed, []netip.Prefix{allowedIP})
return nil
}
// RemoveAllowedIP removes a prefix while preserving the peer's other allowed IPs.
// A prefix not assigned to the peer is a no-op.
func (c *KernelConfigurer) RemoveAllowedIP(peerKey string, allowedIP netip.Prefix) error {
peerKeyParsed, err := wgtypes.ParseKey(peerKey)
if err != nil {
return fmt.Errorf("parse peer key: %w", err)
}
currentAllowedIPs, err := c.peerAllowedIPs(peerKeyParsed)
if err != nil {
return err
}
idx := slices.Index(currentAllowedIPs, normalizePrefix(allowedIP))
if idx < 0 {
return nil
}
newAllowedIPs := slices.Delete(currentAllowedIPs, idx, idx+1)
peer := wgtypes.PeerConfig{
PublicKey: peerKeyParsed,
UpdateOnly: true,
ReplaceAllowedIPs: true,
AllowedIPs: prefixesToIPNets(newAllowedIPs),
}
config := wgtypes.Config{
Peers: []wgtypes.PeerConfig{peer},
}
if err := c.configure(config); err != nil {
return fmt.Errorf("remove allowed IP %s on interface %s: %w", allowedIP, c.deviceName, err)
}
c.allowedIPs.set(peerKeyParsed, newAllowedIPs)
return nil
}
// peerAllowedIPs returns the allowed IPs configured for a peer, reading them from the device
// only for a peer the store has not seen. Dumping the device costs a netlink round trip
// proportional to the whole network map, and this runs on every relay and ICE transition.
func (c *KernelConfigurer) peerAllowedIPs(peerKey wgtypes.Key) ([]netip.Prefix, error) {
if prefixes, ok := c.allowedIPs.get(peerKey); ok {
return prefixes, nil
}
existingPeer, err := c.getPeer(c.deviceName, peerKey)
if err != nil {
return nil, fmt.Errorf("get peer: %w", err)
}
prefixes := ipNetsToPrefixes(existingPeer.AllowedIPs)
c.allowedIPs.set(peerKey, prefixes)
return prefixes, nil
}
// getPeer scans the device for one peer. wgtypes.Key is an array, so the comparison is a
// plain equality: Key.String would base64 encode into a fresh allocation for every peer.
func (c *KernelConfigurer) getPeer(ifaceName string, peerPubKey wgtypes.Key) (wgtypes.Peer, error) {
wg, err := wgctrl.New()
if err != nil {
return wgtypes.Peer{}, fmt.Errorf("wgctl: %w", err)
}
defer func() {
err = wg.Close()
if err != nil {
log.Errorf("Got error while closing wgctl: %v", err)
}
}()
wgDevice, err := wg.Device(ifaceName)
if err != nil {
return wgtypes.Peer{}, fmt.Errorf("get device %s: %w", ifaceName, err)
}
for _, peer := range wgDevice.Peers {
if peer.PublicKey == peerPubKey {
return peer, nil
}
}
return wgtypes.Peer{}, ErrPeerNotFound
}
func (c *KernelConfigurer) configure(config wgtypes.Config) error {
wg, err := wgctrl.New()
if err != nil {
return err
}
defer func() {
if err := wg.Close(); err != nil {
log.Errorf("Failed to close wgctrl client: %v", err)
}
}()
return wg.ConfigureDevice(c.deviceName, config)
}
func (c *KernelConfigurer) Close() {
}
func (c *KernelConfigurer) FullStats() (*Stats, error) {
wg, err := wgctrl.New()
if err != nil {
return nil, fmt.Errorf("wgctl: %w", err)
}
defer func() {
err = wg.Close()
if err != nil {
log.Errorf("Got error while closing wgctl: %v", err)
}
}()
wgDevice, err := wg.Device(c.deviceName)
if err != nil {
return nil, fmt.Errorf("get device %s: %w", c.deviceName, err)
}
fullStats := &Stats{
DeviceName: wgDevice.Name,
PublicKey: wgDevice.PublicKey.String(),
ListenPort: wgDevice.ListenPort,
FWMark: wgDevice.FirewallMark,
Peers: []Peer{},
}
for _, p := range wgDevice.Peers {
peer := Peer{
PublicKey: p.PublicKey.String(),
AllowedIPs: p.AllowedIPs,
TxBytes: p.TransmitBytes,
RxBytes: p.ReceiveBytes,
LastHandshake: p.LastHandshakeTime,
PresharedKey: [32]byte(p.PresharedKey),
}
if p.Endpoint != nil {
peer.Endpoint = *p.Endpoint
}
fullStats.Peers = append(fullStats.Peers, peer)
}
return fullStats, nil
}
func (c *KernelConfigurer) GetStats() (map[string]WGStats, error) {
return c.statsCache.get()
}
func (c *KernelConfigurer) LastActivities() map[string]monotime.Time {
return nil
}
func (c *KernelConfigurer) fetchStats() (map[string]WGStats, error) {
stats := make(map[string]WGStats)
wg, err := wgctrl.New()
if err != nil {
return nil, fmt.Errorf("wgctl: %w", err)
}
defer func() {
err = wg.Close()
if err != nil {
log.Errorf("Got error while closing wgctl: %v", err)
}
}()
wgDevice, err := wg.Device(c.deviceName)
if err != nil {
return nil, fmt.Errorf("get device %s: %w", c.deviceName, err)
}
for _, peer := range wgDevice.Peers {
stats[peer.PublicKey.String()] = WGStats{
LastHandshake: peer.LastHandshakeTime,
TxBytes: peer.TransmitBytes,
RxBytes: peer.ReceiveBytes,
}
}
return stats, nil
}
func buildPresharedKeyConfig(peerKey wgtypes.Key, psk wgtypes.Key, updateOnly bool) wgtypes.Config {
return wgtypes.Config{
Peers: []wgtypes.PeerConfig{{
PublicKey: peerKey,
PresharedKey: &psk,
UpdateOnly: updateOnly,
}},
}
}