Compare commits

..

2 Commits

Author SHA1 Message Date
mlsmaycon
b10e18fe42 [e2e] Close the two gaps the first spike run left on Vertex
The publisher listing answered only under v1beta1, and returned two
models — fewer than the catalog ships. That is what a publisher-global
list looks like rather than what a given project has enabled, and
per-project availability is most of why live discovery beats a static
catalogue. The project-scoped form was only tried under v1, which 404s
like every other v1 path here, so try it under the version that answers.

Also ask for all versions. A publisher model is addressed as
'<id>@<version>' on the rawPredict path while the plain listing reports
one versionId per model, so a model with several live versions would
have the rest silently hidden from a picker.

Report the version in the extracted id for the same reason: Vertex
splits the wire id across name and versionId, and a listing that showed
only the name would look usable without being so.
2026-08-19 06:43:27 +00:00
mlsmaycon
47cb96c010 [e2e] Spike the vendors' own model-discovery endpoints
Management could populate the provider-config model picker from live
vendor data instead of the hand-curated catalog, which today carries
comments tracking which models a vendor retired on which date and which
cannot know what a particular account may actually invoke.

Whether that is a small feature or a large one turns on one unknown:
ListInferenceProfiles is a control-plane operation on
bedrock.<region>.amazonaws.com, while a provider record's upstream must
be bedrock-runtime.<region> for InvokeModel. Nothing documents whether a
Bedrock API key authorises the control plane, and if it does not, live
discovery for Bedrock needs SigV4 signing in management.

Probe each vendor directly — no proxy, no tunnel, no containers — under
the credential an operator would actually supply, and print a verdict
table. Bedrock gets three probes so the control-plane answer is read
against the runtime host we already know 404s, rather than as a lone
data point; Vertex gets three because which path serves the publisher
listing is itself part of the question. Vertex reuses the same JWT mint
and cloud-platform scope llm_router uses in production, so a result here
transfers.

No status code is asserted: the status is the finding. A probe fails
only when its credential is present and the request could not be made at
all, which is a broken probe rather than an answer.

Add a test_pattern dispatch input so this can run on its own in about a
minute instead of behind the sixteen-minute container suite. It reaches
the shell through an env var, since a dispatch input interpolated into a
run script is a script-injection seam.
2026-08-19 06:31:30 +00:00
190 changed files with 1887 additions and 7616 deletions

View File

@@ -12,6 +12,13 @@ on:
AWS issues it. Leave empty for the Sonnet 4.6 default.
required: false
default: ""
test_pattern:
description: >-
Package pattern to run. Defaults to the whole suite; narrow it to one
package (e.g. ./e2e/providerdiscovery/...) when a run only needs that
package's answer and not the sixteen minutes the container suite costs.
required: false
default: "./e2e/..."
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
@@ -77,4 +84,8 @@ jobs:
GOOGLE_VERTEX_PROJECT: ${{ secrets.E2E_GOOGLE_VERTEX_PROJECT }}
GOOGLE_VERTEX_REGION: ${{ secrets.E2E_GOOGLE_VERTEX_REGION }}
GOOGLE_VERTEX_MODEL: ${{ secrets.E2E_GOOGLE_VERTEX_MODEL }}
run: go test -tags e2e -timeout 40m -v ./e2e/...
# Read through an env var rather than interpolated into the run
# script: a dispatch input reaching a shell command directly is a
# script-injection seam, however trusted the dispatcher.
TEST_PATTERN: ${{ inputs.test_pattern || './e2e/...' }}
run: go test -tags e2e -timeout 40m -v "$TEST_PATTERN"

View File

@@ -92,11 +92,6 @@ nfpms:
dst: /usr/share/applications/org.wails.netbird.desktop
- src: client/ui/build/appicon.png
dst: /usr/share/pixmaps/netbird.png
# Names the polkit action for the elevation prompt the app raises when an
# unprivileged user changes a privileged setting; without it the dialog
# shows a raw command line.
- src: client/ui/build/linux/polkit/io.netbird.settings.policy
dst: /usr/share/polkit-1/actions/io.netbird.settings.policy
dependencies:
- netbird (>= 0.75.0)
- libgtk-4-1 (>= 4.14)
@@ -121,11 +116,6 @@ nfpms:
dst: /usr/share/applications/org.wails.netbird.desktop
- src: client/ui/build/appicon.png
dst: /usr/share/pixmaps/netbird.png
# Names the polkit action for the elevation prompt the app raises when an
# unprivileged user changes a privileged setting; without it the dialog
# shows a raw command line.
- src: client/ui/build/linux/polkit/io.netbird.settings.policy
dst: /usr/share/polkit-1/actions/io.netbird.settings.policy
dependencies:
- netbird >= 0.75.0
- (gtk4 >= 4.14 or libgtk-4-1 >= 4.14)

View File

@@ -26,8 +26,6 @@ import (
"github.com/netbirdio/netbird/client/internal/routemanager"
"github.com/netbirdio/netbird/client/internal/stdnet"
"github.com/netbirdio/netbird/client/net"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/client/netsweep"
"github.com/netbirdio/netbird/client/system"
"github.com/netbirdio/netbird/formatter"
"github.com/netbirdio/netbird/route"
@@ -42,6 +40,11 @@ const (
AnonymizeLevelStrict = nbAnonymize.LevelStrictString
)
// ConnectionListener export internal Listener for mobile
type ConnectionListener interface {
peer.Listener
}
// TunAdapter export internal TunAdapter for mobile
type TunAdapter interface {
device.TunAdapter
@@ -82,13 +85,6 @@ type Client struct {
deviceName string
uiVersion string
networkChangeListener listener.NetworkChangeListener
// netState outlives engine restarts: it mirrors the OS connectivity, not
// the engine lifecycle. Run and RunWithoutLogin inject it into each new
// ConnectClient, which distributes it to every reconnection loop.
netState *netstate.State
// sweeper also outlives engine restarts; NotifyNetworkChange sweeps it.
sweeper *netsweep.Sweeper
stateMu sync.RWMutex
connectClient *internal.ConnectClient
@@ -152,7 +148,6 @@ func NewClient(androidSDKVersion int, deviceName string, uiVersion string, tunAd
execWorkaround(androidSDKVersion)
net.SetAndroidProtectSocketFn(tunAdapter.ProtectSocket)
system.SetIFaceDiscover(iFaceDiscover)
return &Client{
deviceName: deviceName,
uiVersion: uiVersion,
@@ -161,8 +156,6 @@ func NewClient(androidSDKVersion int, deviceName string, uiVersion string, tunAd
recorder: peer.NewRecorder(""),
ctxCancelLock: &sync.Mutex{},
networkChangeListener: networkChangeListener,
netState: netstate.New(),
sweeper: netsweep.New(),
}
}
@@ -203,8 +196,7 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
}
// todo do not throw error in case of cancelled context
ctx = internal.CtxInitState(ctx)
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
c.setState(cfg, cacheDir, cfgFile, connectClient)
// This path runs the interactive SSO flow, so reaching here means the peer
// is authenticated again — release the latch Status() reports from. Clear
@@ -245,8 +237,7 @@ func (c *Client) RunWithoutLogin(platformFiles PlatformFiles, dns *DNSList, dnsR
// todo do not throw error in case of cancelled context
ctx = internal.CtxInitState(ctx)
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
c.setState(cfg, cacheDir, cfgFile, connectClient)
return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
}
@@ -294,24 +285,6 @@ func (c *Client) GetTunSettings() (*TunSettings, error) {
}, nil
}
// SetNetworkAvailable feeds OS-reported network availability into the client.
// While unavailable, the internal reconnect loops suspend their attempts and
// the connection listener reports NoNetwork instead of Connecting; when
// availability returns, the loops resume immediately with a fresh backoff.
func (c *Client) SetNetworkAvailable(available bool) {
c.netState.Set(available)
c.recorder.SetNetworkAvailable(available)
}
// NotifyNetworkChange marks the management, signal and relay connections
// stale after the OS switched networks and schedules a sweep that cuts
// whatever has not redialed on the new network by then. The engine and the
// TUN device stay untouched.
func (c *Client) NotifyNetworkChange() {
c.sweeper.MarkNetworkChange()
log.Infof("network change: connections marked stale")
}
// DebugBundle generates a debug bundle, uploads it, and returns the upload key.
// It works both with and without a running engine. anonymizeLevel is "default"
// or "strict"; strict also anonymizes internal IP ranges, peer names, and
@@ -552,11 +525,7 @@ func (c *Client) OnUpdatedHostDNS(list *DNSList) error {
// SetConnectionListener set the network connection listener
func (c *Client) SetConnectionListener(listener ConnectionListener) {
if listener == nil {
c.recorder.RemoveConnectionListener()
return
}
c.recorder.SetConnectionListener(connectionListenerAdapter{listener})
c.recorder.SetConnectionListener(listener)
}
// RemoveConnectionListener remove connection listener

View File

@@ -1,41 +0,0 @@
//go:build android
package android
import (
"github.com/netbirdio/netbird/client/internal/peer"
)
// Client state values delivered via ConnectionListener.OnStateChanged,
// re-exported as basic constants so gomobile emits them into the generated
// Java bindings. They mirror peer.ClientState*: append-only, never reorder.
const (
ClientStateDisconnected = int(peer.ClientStateDisconnected)
ClientStateConnected = int(peer.ClientStateConnected)
ClientStateConnecting = int(peer.ClientStateConnecting)
ClientStateDisconnecting = int(peer.ClientStateDisconnecting)
ClientStateNoNetwork = int(peer.ClientStateNoNetwork)
)
// ConnectionListener export internal Listener for mobile. It mirrors
// peer.Listener with OnStateChanged taking a plain int (one of the
// ClientState* constants), because gomobile cannot bind named types.
type ConnectionListener interface {
OnStateChanged(state int)
OnConnected()
OnDisconnected()
OnConnecting()
OnDisconnecting()
OnAddressChanged(string, string)
OnPeersListChanged(int)
}
// connectionListenerAdapter adapts the gomobile-facing ConnectionListener to
// peer.Listener, converting the typed state to the int the binding carries.
type connectionListenerAdapter struct {
ConnectionListener
}
func (a connectionListenerAdapter) OnStateChanged(state peer.ClientState) {
a.ConnectionListener.OnStateChanged(int(state))
}

View File

@@ -45,8 +45,8 @@ func daemonServerOptions(network string) []grpc.ServerOption {
return nil
}
creds := ipcauth.NewTransportCredentials() //nolint:staticcheck
if creds == nil { //nolint:staticcheck // nil only on platforms without a peer-identity primitive
creds := ipcauth.NewTransportCredentials()
if creds == nil {
log.Warnf("daemon IPC has no peer-identity primitive on %s: privileged operations will be denied", runtime.GOOS)
return nil
}

View File

@@ -27,8 +27,8 @@ func listenOnAddress(addr string) (*socketListener, error) {
}
if network == "npipe" {
listener, path, err := listenNamedPipe(address) //nolint:staticcheck
if err != nil { //nolint:staticcheck // always errors on non-Windows builds
listener, path, err := listenNamedPipe(address)
if err != nil {
return nil, err
}
return &socketListener{Listener: listener, network: network, address: path}, nil

View File

@@ -6,7 +6,7 @@ import (
"testing"
"time"
"go.uber.org/mock/gomock"
"github.com/golang/mock/gomock"
"github.com/stretchr/testify/require"
"go.opentelemetry.io/otel"
"google.golang.org/grpc"

View File

@@ -6,7 +6,7 @@ import (
"testing"
"time"
"go.uber.org/mock/gomock"
"github.com/golang/mock/gomock"
"github.com/stretchr/testify/require"
"google.golang.org/grpc"

View File

@@ -5,7 +5,7 @@ import (
"net/netip"
"testing"
"go.uber.org/mock/gomock"
"github.com/golang/mock/gomock"
"github.com/google/gopacket"
"github.com/google/gopacket/layers"
"github.com/stretchr/testify/require"

View File

@@ -4,7 +4,7 @@ import (
"net/netip"
"testing"
"go.uber.org/mock/gomock"
"github.com/golang/mock/gomock"
"github.com/google/gopacket/layers"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"

View File

@@ -16,47 +16,28 @@ import (
"google.golang.org/grpc"
nbnet "github.com/netbirdio/netbird/client/net"
"github.com/netbirdio/netbird/client/netsweep"
)
func WithCustomDialer(_ bool, _ string) grpc.DialOption {
return grpc.WithContextDialer(dialContext)
}
// WithSweeper dials like WithCustomDialer but registers connections and
// dials with the sweeper. Append it after WithCustomDialer: gRPC applies
// dial options in order, so the later context dialer wins.
func WithSweeper(sweeper *netsweep.Sweeper) grpc.DialOption {
return grpc.WithContextDialer(func(ctx context.Context, addr string) (net.Conn, error) {
dial := sweeper.StartDial(ctx)
defer dial.Release()
if runtime.GOOS == "linux" {
currentUser, err := user.Current()
if err != nil {
return nil, status.Errorf(codes.FailedPrecondition, "failed to get current user: %v", err)
}
conn, err := dialContext(dial.Ctx(), addr)
if err != nil {
return nil, err
// the custom dialer requires root permissions which are not required for use cases run as non-root
if currentUser.Uid != "0" {
log.Debug("Not running as root, using standard dialer")
dialer := &net.Dialer{}
return dialer.DialContext(ctx, "tcp", addr)
}
}
return dial.WrapConn(conn)
conn, err := nbnet.NewDialer().DialContext(ctx, "tcp", addr)
if err != nil {
return nil, fmt.Errorf("nbnet.NewDialer().DialContext: %w", err)
}
return conn, nil
})
}
func dialContext(ctx context.Context, addr string) (net.Conn, error) {
if runtime.GOOS == "linux" {
currentUser, err := user.Current()
if err != nil {
return nil, status.Errorf(codes.FailedPrecondition, "failed to get current user: %v", err)
}
// the custom dialer requires root permissions which are not required for use cases run as non-root
if currentUser.Uid != "0" {
log.Debug("Not running as root, using standard dialer")
dialer := &net.Dialer{}
return dialer.DialContext(ctx, "tcp", addr)
}
}
conn, err := nbnet.NewDialer().DialContext(ctx, "tcp", addr)
if err != nil {
return nil, fmt.Errorf("nbnet.NewDialer().DialContext: %w", err)
}
return conn, nil
}

View File

@@ -3,7 +3,6 @@ package grpc
import (
"google.golang.org/grpc"
"github.com/netbirdio/netbird/client/netsweep"
"github.com/netbirdio/netbird/util/wsproxy/client"
)
@@ -12,8 +11,3 @@ import (
func WithCustomDialer(tlsEnabled bool, component string) grpc.DialOption {
return client.WithWebSocketDialer(tlsEnabled, component)
}
// WithSweeper is a no-op on WASM/JS: there is no network change signal.
func WithSweeper(_ *netsweep.Sweeper) grpc.DialOption {
return grpc.EmptyDialOption{}
}

View File

@@ -1,49 +0,0 @@
package grpc
import (
"context"
"errors"
"time"
"github.com/cenkalti/backoff/v4"
"github.com/netbirdio/netbird/client/netstate"
)
// Retry mirrors backoff.Retry, but the sleep between attempts also wakes on
// OS network availability transitions: an operation cut down by a network
// change retries the moment the network settles instead of sleeping through
// the recovery. A nil netState never fires, leaving plain backoff.Retry
// behavior.
func Retry(ctx context.Context, operation backoff.Operation, bo backoff.BackOff, netState *netstate.State) error {
bo.Reset()
for {
err := operation()
if err == nil {
return nil
}
var permanent *backoff.PermanentError
if errors.As(err, &permanent) {
return permanent.Err
}
next := bo.NextBackOff()
if next == backoff.Stop {
if cerr := ctx.Err(); cerr != nil {
return cerr
}
return err
}
timer := time.NewTimer(next)
select {
case <-timer.C:
case <-netState.Changed():
timer.Stop()
case <-ctx.Done():
timer.Stop()
return ctx.Err()
}
}
}

View File

@@ -1,91 +0,0 @@
package grpc
import (
"context"
"errors"
"testing"
"time"
"github.com/cenkalti/backoff/v4"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/client/netstate"
)
func TestRetryWakesOnNetworkChange(t *testing.T) {
ns := netstate.New()
attempts := 0
operation := func() error {
attempts++
if attempts == 1 {
return errors.New("cut by network change")
}
return nil
}
go func() {
time.Sleep(20 * time.Millisecond)
ns.Set(false)
}()
start := time.Now()
err := Retry(context.Background(), operation, backoff.NewConstantBackOff(time.Minute), ns)
require.NoError(t, err)
assert.Equal(t, 2, attempts, "network change must cause one immediate retry")
assert.Less(t, time.Since(start), time.Second, "the transition must cut the minute-long sleep short")
}
func TestRetryPermanentError(t *testing.T) {
sentinel := errors.New("permission denied")
operation := func() error {
return backoff.Permanent(sentinel)
}
err := Retry(context.Background(), operation, backoff.NewConstantBackOff(time.Millisecond), nil)
assert.ErrorIs(t, err, sentinel, "permanent errors must stop retries")
}
func TestRetryNilNetState(t *testing.T) {
attempts := 0
operation := func() error {
attempts++
if attempts < 3 {
return errors.New("transient")
}
return nil
}
err := Retry(context.Background(), operation, backoff.NewConstantBackOff(time.Millisecond), nil)
require.NoError(t, err)
assert.Equal(t, 3, attempts, "nil network state must preserve timed retries")
}
func TestRetryStops(t *testing.T) {
failure := errors.New("still failing")
operation := func() error {
return failure
}
err := Retry(context.Background(), operation, &backoff.StopBackOff{}, nil)
assert.ErrorIs(t, err, failure, "stop backoff must return the operation error")
}
func TestRetryCtxCancelDuringSleep(t *testing.T) {
ctx, cancel := context.WithCancel(context.Background())
operation := func() error {
return errors.New("failing")
}
go func() {
time.Sleep(20 * time.Millisecond)
cancel()
}()
start := time.Now()
err := Retry(ctx, operation, backoff.NewConstantBackOff(time.Minute), netstate.New())
assert.ErrorIs(t, err, context.Canceled, "context cancellation must stop the retry loop")
assert.Less(t, time.Since(start), time.Second, "context cancellation must interrupt backoff sleep")
}

View File

@@ -4,7 +4,7 @@ import (
"net"
"testing"
"go.uber.org/mock/gomock"
"github.com/golang/mock/gomock"
"github.com/google/gopacket"
"github.com/google/gopacket/layers"

View File

@@ -8,7 +8,7 @@ import (
"net/netip"
reflect "reflect"
gomock "go.uber.org/mock/gomock"
gomock "github.com/golang/mock/gomock"
)
// MockPacketFilter is a mock of PacketFilter interface.

View File

@@ -8,7 +8,7 @@ import (
os "os"
reflect "reflect"
gomock "go.uber.org/mock/gomock"
gomock "github.com/golang/mock/gomock"
tun "golang.zx2c4.com/wireguard/tun"
)

View File

@@ -53,15 +53,15 @@ func NewProxyBind(bind Bind, mtu uint16) *ProxyBind {
return p
}
// AddRelayedConn adds a new connection to the bind.
// AddTurnConn adds a new connection to the bind.
// endpoint is the NetBird address of the remote peer. The SetEndpoint return with the address what will be used in the
// WireGuard configuration.
//
// Parameters:
// - ctx: Context is used for proxyToLocal to avoid unnecessary error messages
// - nbAddr: The NetBird UDP address of the remote peer, it required to generate fake address
// - remoteConn: The established relayed connection to the remote peer
func (p *ProxyBind) AddRelayedConn(ctx context.Context, nbAddr *net.UDPAddr, remoteConn net.Conn) error {
// - remoteConn: The established TURN connection to the remote peer
func (p *ProxyBind) AddTurnConn(ctx context.Context, nbAddr *net.UDPAddr, remoteConn net.Conn) error {
fakeNetIP, err := fakeAddress(nbAddr)
if err != nil {
return err

View File

@@ -30,9 +30,9 @@ type WGEBPFProxy struct {
proxyPort int
mtu uint16
ebpfManager ebpfMgr.Manager
relayedConnStore map[uint16]net.Conn
relayedConnMutex sync.Mutex
ebpfManager ebpfMgr.Manager
turnConnStore map[uint16]net.Conn
turnConnMutex sync.Mutex
lastUsedPort uint16
rawConnIPv4 net.PacketConn
@@ -50,7 +50,7 @@ func NewWGEBPFProxy(wgPort int, mtu uint16) *WGEBPFProxy {
localWGListenPort: wgPort,
mtu: mtu,
ebpfManager: ebpf.GetEbpfManagerInstance(),
relayedConnStore: make(map[uint16]net.Conn),
turnConnStore: make(map[uint16]net.Conn),
}
return wgProxy
}
@@ -110,14 +110,14 @@ func (p *WGEBPFProxy) Listen() error {
return nil
}
// AddRelayedConn add new relayed connection for the proxy
func (p *WGEBPFProxy) AddRelayedConn(relayedConn net.Conn) (*net.UDPAddr, error) {
wgEndpointPort, err := p.storeRelayedConn(relayedConn)
// AddTurnConn add new turn connection for the proxy
func (p *WGEBPFProxy) AddTurnConn(turnConn net.Conn) (*net.UDPAddr, error) {
wgEndpointPort, err := p.storeTurnConn(turnConn)
if err != nil {
return nil, err
}
log.Infof("relayed conn added to wg proxy store: %s, endpoint port: :%d", relayedConn.RemoteAddr(), wgEndpointPort)
log.Infof("turn conn added to wg proxy store: %s, endpoint port: :%d", turnConn.RemoteAddr(), wgEndpointPort)
wgEndpoint := &net.UDPAddr{
IP: net.ParseIP(loopbackAddr),
@@ -186,48 +186,48 @@ func (p *WGEBPFProxy) readAndForwardPacket(buf []byte) error {
return fmt.Errorf("failed to read UDP packet from WG: %w", err)
}
p.relayedConnMutex.Lock()
conn, ok := p.relayedConnStore[uint16(addr.Port)]
p.relayedConnMutex.Unlock()
p.turnConnMutex.Lock()
conn, ok := p.turnConnStore[uint16(addr.Port)]
p.turnConnMutex.Unlock()
if !ok {
if p.ctx.Err() == nil {
log.Debugf("relayed conn not found by port because conn already has been closed: %d", addr.Port)
log.Debugf("turn conn not found by port because conn already has been closed: %d", addr.Port)
}
return nil
}
if _, err := conn.Write(buf[:n]); err != nil {
return fmt.Errorf("forward local WG packet (%d) to remote relayed conn: %w", addr.Port, err)
return fmt.Errorf("failed to forward local WG packet (%d) to remote turn conn: %w", addr.Port, err)
}
return nil
}
func (p *WGEBPFProxy) storeRelayedConn(relayedConn net.Conn) (uint16, error) {
p.relayedConnMutex.Lock()
defer p.relayedConnMutex.Unlock()
func (p *WGEBPFProxy) storeTurnConn(turnConn net.Conn) (uint16, error) {
p.turnConnMutex.Lock()
defer p.turnConnMutex.Unlock()
np, err := p.nextFreePort()
if err != nil {
return np, err
}
p.relayedConnStore[np] = relayedConn
p.turnConnStore[np] = turnConn
return np, nil
}
func (p *WGEBPFProxy) removeRelayedConn(relayedConnID uint16) {
p.relayedConnMutex.Lock()
defer p.relayedConnMutex.Unlock()
func (p *WGEBPFProxy) removeTurnConn(turnConnID uint16) {
p.turnConnMutex.Lock()
defer p.turnConnMutex.Unlock()
_, ok := p.relayedConnStore[relayedConnID]
_, ok := p.turnConnStore[turnConnID]
if ok {
log.Debugf("remove relayed conn from store by port: %d", relayedConnID)
log.Debugf("remove turn conn from store by port: %d", turnConnID)
}
delete(p.relayedConnStore, relayedConnID)
delete(p.turnConnStore, turnConnID)
}
func (p *WGEBPFProxy) nextFreePort() (uint16, error) {
if len(p.relayedConnStore) == 65535 {
return 0, fmt.Errorf("reached maximum relayed connection numbers")
if len(p.turnConnStore) == 65535 {
return 0, fmt.Errorf("reached maximum turn connection numbers")
}
generatePort:
if p.lastUsedPort == 65535 {
@@ -236,7 +236,7 @@ generatePort:
p.lastUsedPort++
}
if _, ok := p.relayedConnStore[p.lastUsedPort]; ok {
if _, ok := p.turnConnStore[p.lastUsedPort]; ok {
goto generatePort
}
return p.lastUsedPort, nil

View File

@@ -9,32 +9,32 @@ import (
func TestWGEBPFProxy_connStore(t *testing.T) {
wgProxy := NewWGEBPFProxy(1, 1280)
p, _ := wgProxy.storeRelayedConn(nil)
p, _ := wgProxy.storeTurnConn(nil)
if p != 1 {
t.Errorf("invalid initial port: %d", wgProxy.lastUsedPort)
}
numOfConns := 10
for i := 0; i < numOfConns; i++ {
p, _ = wgProxy.storeRelayedConn(nil)
p, _ = wgProxy.storeTurnConn(nil)
}
if p != uint16(numOfConns)+1 {
t.Errorf("invalid last used port: %d, expected: %d", p, numOfConns+1)
}
if len(wgProxy.relayedConnStore) != numOfConns+1 {
t.Errorf("invalid store size: %d, expected: %d", len(wgProxy.relayedConnStore), numOfConns+1)
if len(wgProxy.turnConnStore) != numOfConns+1 {
t.Errorf("invalid store size: %d, expected: %d", len(wgProxy.turnConnStore), numOfConns+1)
}
}
func TestWGEBPFProxy_portCalculation_overflow(t *testing.T) {
wgProxy := NewWGEBPFProxy(1, 1280)
_, _ = wgProxy.storeRelayedConn(nil)
_, _ = wgProxy.storeTurnConn(nil)
wgProxy.lastUsedPort = 65535
p, _ := wgProxy.storeRelayedConn(nil)
p, _ := wgProxy.storeTurnConn(nil)
if len(wgProxy.relayedConnStore) != 2 {
t.Errorf("invalid store size: %d, expected: %d", len(wgProxy.relayedConnStore), 2)
if len(wgProxy.turnConnStore) != 2 {
t.Errorf("invalid store size: %d, expected: %d", len(wgProxy.turnConnStore), 2)
}
if p != 2 {
@@ -46,11 +46,11 @@ func TestWGEBPFProxy_portCalculation_maxConn(t *testing.T) {
wgProxy := NewWGEBPFProxy(1, 1280)
for i := 0; i < 65535; i++ {
_, _ = wgProxy.storeRelayedConn(nil)
_, _ = wgProxy.storeTurnConn(nil)
}
_, err := wgProxy.storeRelayedConn(nil)
_, err := wgProxy.storeTurnConn(nil)
if err == nil {
t.Errorf("invalid relayed conn store calculation")
t.Errorf("invalid turn conn store calculation")
}
}

View File

@@ -121,10 +121,10 @@ func NewProxyWrapper(proxy *WGEBPFProxy) *ProxyWrapper {
}
}
func (p *ProxyWrapper) AddRelayedConn(ctx context.Context, _ *net.UDPAddr, remoteConn net.Conn) error {
addr, err := p.wgeBPFProxy.AddRelayedConn(remoteConn)
func (p *ProxyWrapper) AddTurnConn(ctx context.Context, _ *net.UDPAddr, remoteConn net.Conn) error {
addr, err := p.wgeBPFProxy.AddTurnConn(remoteConn)
if err != nil {
return fmt.Errorf("add relayed conn: %w", err)
return fmt.Errorf("add turn conn: %w", err)
}
headers, err := NewPacketHeaders(p.wgeBPFProxy.localWGListenPort, addr)
@@ -252,7 +252,7 @@ func (p *ProxyWrapper) CloseConn() error {
}
func (p *ProxyWrapper) proxyToLocal(ctx context.Context) {
defer p.wgeBPFProxy.removeRelayedConn(uint16(p.wgRelayedEndpointAddr.Port))
defer p.wgeBPFProxy.removeTurnConn(uint16(p.wgRelayedEndpointAddr.Port))
buf := make([]byte, p.wgeBPFProxy.mtu+bufsize.WGBufferOverhead)
for {
@@ -273,7 +273,7 @@ func (p *ProxyWrapper) proxyToLocal(ctx context.Context) {
if ctx.Err() != nil {
return
}
log.Errorf("failed to write out relayed pkg to local conn: %v", err)
log.Errorf("failed to write out turn pkg to local conn: %v", err)
}
}
}
@@ -286,7 +286,7 @@ func (p *ProxyWrapper) readFromRemote(ctx context.Context, buf []byte) (int, err
}
p.closeListener.Notify()
if !errors.Is(err, io.EOF) {
log.Errorf("failed to read from relayed conn (endpoint: :%d): %s", p.wgRelayedEndpointAddr.Port, err)
log.Errorf("failed to read from turn conn (endpoint: :%d): %s", p.wgRelayedEndpointAddr.Port, err)
}
return 0, err
}

View File

@@ -7,7 +7,7 @@ import (
// Proxy is a transfer layer between the relayed connection and the WireGuard
type Proxy interface {
AddRelayedConn(ctx context.Context, endpoint *net.UDPAddr, remoteConn net.Conn) error
AddTurnConn(ctx context.Context, endpoint *net.UDPAddr, remoteConn net.Conn) error
EndpointAddr() *net.UDPAddr // EndpointAddr returns the address of the WireGuard peer endpoint
Work() // Work start or resume the proxy
Pause() // Pause to forward the packages from remote connection to WireGuard. The opposite way still works.

View File

@@ -95,7 +95,7 @@ func TestProxyCloseByRemoteConn(t *testing.T) {
t.Run(tt.name, func(t *testing.T) {
addr, _ := net.ResolveUDPAddr("udp", "100.108.135.221:51892")
relayedConn := newMockConn()
err := tt.proxy.AddRelayedConn(ctx, addr, relayedConn)
err := tt.proxy.AddTurnConn(ctx, addr, relayedConn)
if err != nil {
t.Errorf("error: %v", err)
}
@@ -157,7 +157,7 @@ func redirectTraffic(t *testing.T, proxy Proxy, wgPort int, endPointAddr *net.UD
_ = relayedServer.Close()
}()
if err := proxy.AddRelayedConn(context.Background(), endPointAddr, relayedConn); err != nil {
if err := proxy.AddTurnConn(context.Background(), endPointAddr, relayedConn); err != nil {
t.Errorf("error: %v", err)
}
defer func() {

View File

@@ -119,9 +119,9 @@ func testRedirectAs(t *testing.T, proxy Proxy, wgPort int, nbAddr, p2pEndpoint *
}
defer relayConn.Close()
// Add relayed connection to proxy
if err := proxy.AddRelayedConn(ctx, nbAddr, relayConn); err != nil {
t.Fatalf("failed to add relayed connection: %v", err)
// Add TURN connection to proxy
if err := proxy.AddTurnConn(ctx, nbAddr, relayConn); err != nil {
t.Fatalf("failed to add TURN connection: %v", err)
}
defer func() {
if err := proxy.CloseConn(); err != nil {
@@ -304,8 +304,8 @@ func TestRedirectAs_Multiple_Switches(t *testing.T) {
Port: 38746,
}
if err := proxy.AddRelayedConn(ctx, nbAddr, relayConn); err != nil {
t.Fatalf("failed to add relayed connection: %v", err)
if err := proxy.AddTurnConn(ctx, nbAddr, relayConn); err != nil {
t.Fatalf("failed to add TURN connection: %v", err)
}
defer func() {
if err := proxy.CloseConn(); err != nil {

View File

@@ -51,12 +51,12 @@ func NewWGUDPProxy(wgPort int, mtu uint16) *WGUDPProxy {
return p
}
// AddRelayedConn dials the local WireGuard port and stores the relayed connection.
// AddTurnConn
// The provided Context must be non-nil. If the context expires before
// the connection is complete, an error is returned. Once successfully
// connected, any expiration of the context will not affect the
// connection.
func (p *WGUDPProxy) AddRelayedConn(ctx context.Context, _ *net.UDPAddr, remoteConn net.Conn) error {
func (p *WGUDPProxy) AddTurnConn(ctx context.Context, _ *net.UDPAddr, remoteConn net.Conn) error {
dialer := net.Dialer{}
localConn, err := dialer.DialContext(ctx, "udp", fmt.Sprintf(":%d", p.localWGListenPort))
if err != nil {

View File

@@ -116,11 +116,11 @@ func (d *DefaultManager) ApplyFiltering(networkMap *mgmProto.NetworkMap, dnsRout
// firewall state, so an identical hash means an identical resulting ruleset.
func (d *DefaultManager) firewallConfigHash(networkMap *mgmProto.NetworkMap, dnsRouteFeatureFlag bool) (uint64, error) {
return hashstructure.Hash(struct {
PeerRules []*mgmProto.FirewallRule
PeerRulesIsEmpty bool
RouteRules []*mgmProto.RouteFirewallRule
RouteRulesIsEmpty bool
DNSRouteFeatureFlag bool
PeerRules []*mgmProto.FirewallRule
PeerRulesIsEmpty bool
RouteRules []*mgmProto.RouteFirewallRule
RouteRulesIsEmpty bool
DNSRouteFeatureFlag bool
}{
PeerRules: networkMap.GetFirewallRules(),
PeerRulesIsEmpty: networkMap.GetFirewallRulesIsEmpty(),
@@ -144,13 +144,13 @@ func (d *DefaultManager) applyPeerACLs(networkMap *mgmProto.NetworkMap) {
log.Warn("this peer is connected to a NetBird Management service with an older version. Allowing all traffic from connected peers")
rules = append(rules,
&mgmProto.FirewallRule{
PeerIP: "0.0.0.0", //nolint:staticcheck
PeerIP: "0.0.0.0",
Direction: mgmProto.RuleDirection_IN,
Action: mgmProto.RuleAction_ACCEPT,
Protocol: mgmProto.RuleProtocol_ALL,
},
&mgmProto.FirewallRule{
PeerIP: "0.0.0.0", //nolint:staticcheck
PeerIP: "0.0.0.0",
Direction: mgmProto.RuleDirection_OUT,
Action: mgmProto.RuleAction_ACCEPT,
Protocol: mgmProto.RuleProtocol_ALL,
@@ -407,6 +407,7 @@ func (d *DefaultManager) getRuleGroupingSelector(rule *mgmProto.FirewallRule) st
return fmt.Sprintf("%v:%v:%v:%s:%v", strconv.Itoa(int(rule.Direction)), rule.Action, rule.Protocol, rule.Port, rule.PortInfo)
}
// extractRuleIP extracts the peer IP from a firewall rule.
// If sourcePrefixes is populated (new management), decode the first entry and use its address.
// Otherwise fall back to the deprecated PeerIP string field (old management).

View File

@@ -5,9 +5,9 @@ import (
"net/netip"
"testing"
"github.com/golang/mock/gomock"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"go.uber.org/mock/gomock"
"github.com/netbirdio/netbird/client/firewall"
"github.com/netbirdio/netbird/client/iface"
@@ -87,7 +87,7 @@ func TestDefaultManager(t *testing.T) {
networkMap.FirewallRules = append(
networkMap.FirewallRules,
&mgmProto.FirewallRule{
PeerIP: "10.93.0.3", //nolint:staticcheck
PeerIP: "10.93.0.3",
Direction: mgmProto.RuleDirection_IN,
Action: mgmProto.RuleAction_DROP,
Protocol: mgmProto.RuleProtocol_ICMP,
@@ -556,12 +556,12 @@ func TestApplyFilteringSkipsUnchangedConfig(t *testing.T) {
func buildNetworkMap(peerRules, routeRules int) *mgmProto.NetworkMap {
nm := &mgmProto.NetworkMap{
FirewallRulesIsEmpty: peerRules == 0,
FirewallRulesIsEmpty: peerRules == 0,
RoutesFirewallRulesIsEmpty: routeRules == 0,
}
for i := range peerRules {
nm.FirewallRules = append(nm.FirewallRules, &mgmProto.FirewallRule{
PeerIP: fmt.Sprintf("10.%d.%d.%d", i>>16&0xff, i>>8&0xff, i&0xff), //nolint:staticcheck
PeerIP: fmt.Sprintf("10.%d.%d.%d", i>>16&0xff, i>>8&0xff, i&0xff),
Direction: mgmProto.RuleDirection_IN,
Action: mgmProto.RuleAction_ACCEPT,
Protocol: mgmProto.RuleProtocol_TCP,

View File

@@ -7,7 +7,7 @@ package mocks
import (
reflect "reflect"
gomock "go.uber.org/mock/gomock"
gomock "github.com/golang/mock/gomock"
wgdevice "golang.zx2c4.com/wireguard/device"
"github.com/netbirdio/netbird/client/iface/device"

View File

@@ -38,8 +38,6 @@ import (
"github.com/netbirdio/netbird/client/internal/updater"
"github.com/netbirdio/netbird/client/internal/updater/installer"
nbnet "github.com/netbirdio/netbird/client/net"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/client/netsweep"
cProto "github.com/netbirdio/netbird/client/proto"
"github.com/netbirdio/netbird/client/ssh"
sshconfig "github.com/netbirdio/netbird/client/ssh/config"
@@ -72,42 +70,18 @@ type ConnectClient struct {
updateManager *updater.Manager
persistSyncResponse bool
// netState gates every reconnection loop on OS-reported network
// availability. Nil (the default) disables gating; mobile platforms
// inject it via WithNetworkState.
netState *netstate.State
// sweeper cuts the management, signal and relay connections on network
// change; nil disables it.
sweeper *netsweep.Sweeper
}
// ConnectClientOption configures optional ConnectClient behavior.
type ConnectClientOption func(*ConnectClient)
// WithNetworkState injects the OS network availability state that gates every
// reconnection loop; without it gating is disabled.
func WithNetworkState(netState *netstate.State) ConnectClientOption {
return func(c *ConnectClient) { c.netState = netState }
}
// WithSweeper injects the network change sweeper.
func WithSweeper(sweeper *netsweep.Sweeper) ConnectClientOption {
return func(c *ConnectClient) { c.sweeper = sweeper }
}
func NewConnectClient(
ctx context.Context,
config *profilemanager.Config,
statusRecorder *peer.Status,
opts ...ConnectClientOption,
) *ConnectClient {
// Derive the run context here so Stop owns the cancel that unblocks the run
// loop. runCancel is set once at construction, so Stop can call it without
// racing the run loop's startup. Callers therefore need not cancel before Stop.
runCtx, runCancel := context.WithCancel(ctx)
c := &ConnectClient{
return &ConnectClient{
ctx: runCtx,
runCancel: runCancel,
runExited: make(chan struct{}),
@@ -115,10 +89,6 @@ func NewConnectClient(
statusRecorder: statusRecorder,
engineMutex: sync.Mutex{},
}
for _, opt := range opts {
opt(c)
}
return c
}
func (c *ConnectClient) SetUpdateManager(um *updater.Manager) {
@@ -304,13 +274,6 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
return nil
}
// suspend connection attempts while the OS reports no usable network
if waited, err := c.netState.Wait(c.ctx); err != nil {
return nil
} else if waited {
backOff.Reset()
}
state.Set(StatusConnecting)
engineCtx, cancel := context.WithCancel(c.ctx)
@@ -322,8 +285,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
}()
log.Debugf("connecting to the Management service %s", c.config.ManagementURL.Host)
mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled,
mgm.WithNetworkState(c.netState), mgm.WithSweeper(c.sweeper))
mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled)
if err != nil {
// On daemon shutdown / Down() the parent context is cancelled
// and the dial fails with "context canceled". Wrapping that
@@ -398,7 +360,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
}()
// with the global Netbird config in hand connect (just a connection, no stream yet) Signal
signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey, c.netState, c.sweeper)
signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey)
if err != nil {
log.Error(err)
return wrapErr(err)
@@ -434,8 +396,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
engineConfig.StateDir = filepath.Dir(path)
}
relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU,
relayClient.WithNetworkState(c.netState), relayClient.WithSweeper(c.sweeper))
relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU)
c.statusRecorder.SetRelayMgr(relayManager)
if len(relayURLs) > 0 {
if token != nil {
@@ -463,7 +424,6 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
UpdateManager: c.updateManager,
ClientMetrics: c.clientMetrics,
MetricsCtx: c.ctx,
NetState: c.netState,
}, mobileDependency)
engine.SetSyncResponsePersistence(c.persistSyncResponse)
c.engine = engine
@@ -520,16 +480,6 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
// status stream stuck at Connecting.
err = backoff.Retry(operation, backoff.WithContext(backOff, c.ctx))
if err != nil {
// Once the client context is cancelled backoff.WithContext surfaces the
// bare context error, and any attempt torn down mid-flight reports the
// same. That cancellation is the caller asking us to stop (Stop, Down or
// an engine restart), so exit cleanly instead of handing back a failure
// the caller would have to distinguish from a real one.
if c.ctx.Err() != nil && errors.Is(err, context.Canceled) {
log.Info("exiting client retry loop, context cancelled")
return nil
}
log.Debugf("exiting client retry loop due to unrecoverable error: %s", err)
if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.PermissionDenied) {
state.Set(StatusNeedsLogin)
@@ -723,7 +673,7 @@ func selectMTU(localMTU uint16, peerMTU int32) uint16 {
}
// connectToSignal creates Signal Service client and established a connection
func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key, netState *netstate.State, sweeper *netsweep.Sweeper) (*signal.GrpcClient, error) {
func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key) (*signal.GrpcClient, error) {
var sigTLSEnabled bool
if wtConfig.Signal.Protocol == mgmProto.HostConfig_HTTPS {
sigTLSEnabled = true
@@ -731,8 +681,7 @@ func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourP
sigTLSEnabled = false
}
signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled,
signal.WithNetworkState(netState), signal.WithSweeper(sweeper))
signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled)
if err != nil {
log.Errorf("error while connecting to the Signal Exchange Service %s: %s", wtConfig.Signal.Uri, err)
return nil, gstatus.Errorf(codes.FailedPrecondition, "failed connecting to Signal Service : %s", err)

View File

@@ -1,17 +0,0 @@
package daemonaddr
import "strings"
// CarriesIdentity reports whether the control channel at addr conveys the
// connecting process's identity to the daemon. A Unix socket carries peer
// credentials and a named pipe carries the client's token. Nothing else does, TCP
// included, and there the daemon can authorize a privileged operation for nobody
// at all: see ResolveDaemonAddr, which says as much to anyone still reaching the
// Windows daemon on the address it served before it had a pipe.
//
// A client uses this to tell whether becoming privileged would get it anywhere.
// It answers from the scheme and nothing else, so an address it does not
// recognise counts as carrying no identity.
func CarriesIdentity(addr string) bool {
return strings.HasPrefix(addr, "unix://") || strings.HasPrefix(addr, pipeScheme)
}

View File

@@ -1,29 +0,0 @@
package daemonaddr
import (
"testing"
"github.com/stretchr/testify/assert"
)
func TestCarriesIdentity(t *testing.T) {
tests := []struct {
addr string
want bool
}{
{"unix:///var/run/netbird.sock", true},
{"unix:///var/run/netbird/default.sock", true},
{"npipe://netbird", true},
{`npipe://\\.\pipe\ProtectedPrefix\Administrators\netbird`, true},
{"tcp://127.0.0.1:41731", false},
{"tcp://localhost:41731", false},
{"", false},
{"/var/run/netbird.sock", false},
}
for _, tt := range tests {
t.Run(tt.addr, func(t *testing.T) {
assert.Equal(t, tt.want, CarriesIdentity(tt.addr), "address %q", tt.addr)
})
}
}

View File

@@ -459,7 +459,7 @@ func (r *registryConfigurator) flushDNSCache() {
ret, _, err := dnsFlushResolverCacheFn.Call()
if ret == 0 {
if !errors.Is(err, syscall.Errno(0)) {
if err != nil && !errors.Is(err, syscall.Errno(0)) {
log.Errorf("DnsFlushResolverCache failed: %v", err)
return
}
@@ -627,7 +627,7 @@ func refreshGroupPolicy() error {
)
if ret == 0 {
if !errors.Is(err, syscall.Errno(0)) {
if err != nil && !errors.Is(err, syscall.Errno(0)) {
return fmt.Errorf("RefreshPolicyEx failed: %w", err)
}
return fmt.Errorf("RefreshPolicyEx failed")

View File

@@ -4,7 +4,7 @@ import (
"net"
"testing"
"go.uber.org/mock/gomock"
"github.com/golang/mock/gomock"
"github.com/google/gopacket"
"github.com/google/gopacket/layers"
"github.com/miekg/dns"

View File

@@ -9,7 +9,7 @@ import (
"os"
"testing"
"go.uber.org/mock/gomock"
"github.com/golang/mock/gomock"
"github.com/miekg/dns"
"github.com/stretchr/testify/assert"
"golang.zx2c4.com/wireguard/wgctrl/wgtypes"

View File

@@ -101,7 +101,7 @@ func (m *Manager) Start(fwdEntries []*ForwarderEntry) error {
m.dnsForwarder = NewDNSForwarder(listenAddress, dnsTTL, m.firewall, m.statusRecorder, m.wgIface)
go func() {
if err := m.dnsForwarder.Listen(fwdEntries); err != nil { //nolint:staticcheck
if err := m.dnsForwarder.Listen(fwdEntries); err != nil {
// todo handle close error if it is exists
log.Errorf("failed to start DNS forwarder, err: %v", err)
}

View File

@@ -1,74 +0,0 @@
// Package elevate re-runs this very executable under the operating system's own
// privilege-elevation mechanism and waits for it to finish.
//
// It exists so that a change the daemon restricts to root/administrator can be
// authorized from the GUI, by the user, at the moment they ask for it: Windows
// shows the UAC consent dialog, macOS the system authentication dialog, and
// Linux/FreeBSD the session's polkit agent. The credentials, where any are
// asked for, are collected by the operating system and never pass through
// NetBird.
//
// What the elevated process then does is the caller's business: it is the same
// binary, in a one-shot mode, and it is authorized by the daemon exactly like
// any other privileged caller, from the identity the kernel reports on the
// control channel. Nothing here grants privilege, and the daemon gains no new
// way to be talked into something: elevation only changes who is calling it.
package elevate
import (
"context"
"errors"
log "github.com/sirupsen/logrus"
)
// AppliedMarker is what the elevated process prints on standard output once it has
// done what it was run for.
//
// macOS's AuthorizationExecuteWithPrivileges reports no exit status and does not
// say which process it started, so there this line is the only evidence that the
// change was applied. The other platforms have an exit code and ignore it.
const AppliedMarker = "netbird-elevated: applied"
var (
// ErrDeclined reports that the user dismissed the prompt or did not
// authenticate. Nothing happened and nothing is wrong: a caller undoes its
// optimistic update and stays quiet.
ErrDeclined = errors.New("authorization declined")
// ErrUnavailable reports that this host has no elevation mechanism we can
// drive: no polkit on a Unix desktop, or an executable we decline to run as
// root. A caller falls back to telling the user which command to run.
ErrUnavailable = errors.New("no privilege elevation mechanism available")
)
// Run runs this executable with args under the platform's elevation mechanism
// and waits for it to exit. A non-zero exit is returned as an error, so the
// caller can treat a completed Run as the operation having succeeded.
//
// The args are the caller's own command line, so they cross no privilege
// boundary: only a user who has just authenticated as an administrator can get
// them run at all.
func Run(ctx context.Context, args ...string) error {
self, err := trustedSelf()
if err != nil {
return err
}
return run(ctx, self, args)
}
// Available reports whether Run has a mechanism to use on this host, so a caller
// can offer the prompt only when there is one and otherwise fall back to
// guidance the user can act on. It answers from what is installed, not from what
// the user is allowed to do: an administrator's password may still be required
// and may still not be given, which is ErrDeclined from Run.
func Available() bool {
if _, err := trustedSelf(); err != nil {
// Worth a line: this is also what a build run from a group-writable
// directory hits, and there is nothing in the UI to say why the offer is
// missing.
log.Debugf("not offering privilege elevation: %v", err)
return false
}
return mechanismAvailable()
}

View File

@@ -1,18 +0,0 @@
package elevate
import "strings"
// noOutput stands in for a process that said nothing, so that a report of what it
// said still reads as a sentence.
const noOutput = "no output"
func firstLine(s string) string {
s = strings.TrimSpace(s)
if s == "" {
return noOutput
}
if i := strings.IndexByte(s, '\n'); i >= 0 {
return s[:i]
}
return s
}

View File

@@ -1,21 +0,0 @@
package elevate
import (
"testing"
"github.com/stretchr/testify/assert"
)
func TestFirstLine(t *testing.T) {
tests := []struct{ in, want string }{
{in: "", want: noOutput},
{in: " \n ", want: noOutput},
{in: "one line", want: "one line"},
{in: "first\nsecond", want: "first"},
{in: "\nsecond\n", want: "second"},
}
for _, tt := range tests {
assert.Equal(t, tt.want, firstLine(tt.in), "input %q", tt.in)
}
}

View File

@@ -1,359 +0,0 @@
package elevate
import (
"context"
"errors"
"fmt"
"os"
"runtime"
"strings"
"sync"
"syscall"
"unsafe"
"github.com/ebitengine/purego"
log "github.com/sirupsen/logrus"
)
// Authorization Services, reached through purego rather than cgo so the released
// binaries keep building with CGO_ENABLED=0.
//
// The prompt belongs to this process, which is what makes it carry the
// application's name and our own explanation. Going through osascript instead puts
// the very same trampoline behind a dialog attributed to osascript, and means
// handing a shell a command line to re-parse.
//
// # On AuthorizationExecuteWithPrivileges
//
// It is deprecated, and Apple's guidance (Quinn, "BSD Privilege Escalation on
// macOS", developer.apple.com/forums/thread/708765) is "while it still works, it's
// been deprecated for many years. Do not use it in a widely distributed product."
// It is used here anyway, knowingly, because the alternatives Apple offers are for
// *obtaining* ongoing privileges — an installer package, SMAppService, SMJobBless —
// and NetBird already has what they would install: a launchd daemon running as
// root. What is missing is only a way for an unprivileged client to ask it to act.
//
// The way to that without a deprecated call is to authorize the client instead of
// elevating one: the app takes the right with AuthorizationCreate, passes the
// AuthorizationExternalForm to the daemon, and the daemon checks it with
// AuthorizationCopyRights before acting — none of which is deprecated. It is the
// better design and it is where this should end up. It also means the daemon
// accepting an authorization over its control socket, which is a new way to be
// asked for privileged work and wants reviewing as such, so it is deliberately not
// bundled in with the rest of this.
//
// Until then, three things keep the deprecation from being a trap. Every symbol is
// resolved with an error rather than a panic, so a macOS that has dropped this
// function leaves the app offering the user a command instead of crashing on the
// way to a prompt. A failure to run the tool is reported as ErrUnavailable, so the
// fallback is the same one an agent-less Linux session gets. And the whole path
// runs under guard, which turns a panic out of the FFI layer into that same
// fallback.
//
// The trampoline passes on the environment it was given, so what it starts as root
// must be an executable this user's peers cannot influence: that is what
// trustedSelf refuses, and what signing the binary settles for the loader.
const (
securityFramework = "/System/Library/Frameworks/Security.framework/Security"
libSystem = "/usr/lib/libSystem.B.dylib"
// trampoline is what the framework hands the tool to. Present on every macOS,
// and worth confirming before offering a prompt rather than mid-prompt.
trampoline = "/usr/libexec/security_authtrampoline"
)
// rightExecute is the right an administrator holds, and what
// AuthorizationExecuteWithPrivileges requires of us.
const rightExecute = "system.privilege.admin"
// promptKey is kAuthorizationEnvironmentPrompt, which puts a sentence of ours above
// the system's in the dialog. It is about the change rather than the mechanism.
const (
promptKey = "prompt"
promptText = "NetBird needs to change a setting that grants SSH access to this computer."
)
// OSStatus values from SecBase.h that mean something to us; anything else is
// reported as it comes.
const (
errAuthorizationSuccess = 0
errAuthorizationDenied = -60005
errAuthorizationCanceled = -60006
errAuthorizationInteractionNotAllowed = -60007
errAuthorizationToolExecuteFailure = -60031
errAuthorizationToolEnvironmentError = -60032
)
// AuthorizationFlags from Authorization.h.
const (
flagDefaults = 0
flagInteractionAllowed = 1 << 0
flagExtendRights = 1 << 1
flagDestroyRights = 1 << 3
flagPreAuthorize = 1 << 4
)
// authorizationItem mirrors AuthorizationItem: a name, and a value the name gives
// meaning to. 32 bytes on both amd64 and arm64.
type authorizationItem struct {
name *byte
valueLength uintptr
value unsafe.Pointer
// flags is reserved by the API and always zero. Declared because the layout
// is the contract: without it the struct is 24 bytes where C reads 32.
flags uint32 //nolint:unused // part of the C layout
}
// authorizationItemSet mirrors AuthorizationItemSet, which serves as both an
// AuthorizationRights and an AuthorizationEnvironment.
type authorizationItemSet struct {
count uint32
items *authorizationItem
}
var (
authorizationCreate func(rights, environment *authorizationItemSet, flags uint32, authorization *uintptr) int32
authorizationExecuteWithPrivileges func(authorization uintptr, pathToTool string, options uint32, arguments *uintptr, communicationsPipe *uintptr) int32
authorizationFree func(authorization uintptr, flags uint32) int32
fileno func(stream uintptr) int32
fclose func(stream uintptr) int32
loadOnce sync.Once
loadErr error
)
// load resolves the functions once. A framework that cannot be opened, or a symbol
// that is no longer there, leaves the host without a mechanism rather than taking
// the process down with it: see the note on deprecation above.
func load() error {
loadOnce.Do(func() { loadErr = guard("loading Security.framework", resolve) })
return loadErr
}
// guard turns a panic out of the FFI layer into an error, so an API that has
// changed under us costs the user a prompt rather than the window they were
// clicking in. purego panics on a signature it cannot map, and this is the one
// place in the client that calls a deprecated system function.
//
// It catches Go panics, which is what purego raises. A fault inside the framework
// itself is not a panic and not recoverable; the layout the tests pin down is what
// stands between us and that.
func guard(what string, fn func() error) (err error) {
defer func() {
r := recover()
if r == nil {
return
}
log.Errorf("%s panicked: %v", what, r)
err = fmt.Errorf("%w: %s: %v", ErrUnavailable, what, r)
}()
return fn()
}
func resolve() error {
security, err := purego.Dlopen(securityFramework, purego.RTLD_LAZY|purego.RTLD_GLOBAL)
if err != nil {
return fmt.Errorf("open %s: %w", securityFramework, err)
}
system, err := purego.Dlopen(libSystem, purego.RTLD_LAZY|purego.RTLD_GLOBAL)
if err != nil {
return fmt.Errorf("open %s: %w", libSystem, err)
}
// purego.RegisterLibFunc panics on a symbol it cannot find, which is not how a
// deprecated function's disappearance should reach the user.
for _, fn := range []struct {
ptr any
handle uintptr
name string
}{
{&authorizationCreate, security, "AuthorizationCreate"},
{&authorizationExecuteWithPrivileges, security, "AuthorizationExecuteWithPrivileges"},
{&authorizationFree, security, "AuthorizationFree"},
{&fileno, system, "fileno"},
{&fclose, system, "fclose"},
} {
symbol, err := purego.Dlsym(fn.handle, fn.name)
if err != nil {
return fmt.Errorf("resolve %s: %w", fn.name, err)
}
if symbol == 0 {
return fmt.Errorf("resolve %s: not present on this system", fn.name)
}
purego.RegisterFunc(fn.ptr, symbol)
}
return nil
}
// run asks the system to run self as root: first for the right, which is what puts
// up the authentication dialog and collects the password or takes the Touch ID,
// then for the tool. The credentials go to the system's authorization trampoline
// and never to us.
//
// The context bounds only our own waiting; the dialog belongs to the system and
// closes when the user answers it.
func run(ctx context.Context, self string, args []string) error {
if err := load(); err != nil {
return fmt.Errorf("%w: %v", ErrUnavailable, err)
}
return guard("asking for privileges", func() error {
authorization, err := authorize()
if err != nil {
return err
}
defer authorizationFree(authorization, flagDestroyRights)
return execute(ctx, authorization, self, args)
})
}
func mechanismAvailable() bool {
if err := load(); err != nil {
return false
}
info, err := os.Stat(trampoline)
return err == nil && !info.IsDir()
}
// authorize obtains the right, prompting for it. A dismissed dialog comes back as
// errAuthorizationCanceled and a password given up on as errAuthorizationDenied;
// both are the user's answer rather than a failure.
func authorize() (uintptr, error) {
var pinner runtime.Pinner
defer pinner.Unpin()
rights := itemSet(&pinner, authorizationItem{name: cString(&pinner, rightExecute)})
environment := itemSet(&pinner, promptItem(&pinner))
var authorization uintptr
status := authorizationCreate(rights, environment,
flagDefaults|flagInteractionAllowed|flagPreAuthorize|flagExtendRights, &authorization)
switch status {
case errAuthorizationSuccess:
return authorization, nil
case errAuthorizationCanceled, errAuthorizationDenied:
return 0, ErrDeclined
case errAuthorizationInteractionNotAllowed:
// Nowhere to put a dialog, so there is nobody to ask: a launch daemon, or
// a session with no window server.
return 0, fmt.Errorf("%w: this session cannot show an authorization prompt", ErrUnavailable)
default:
return 0, fmt.Errorf("request %s: OSStatus %d", rightExecute, status)
}
}
// execute runs the tool with the right in hand and waits for it by reading the pipe
// it is given until the tool closes it.
//
// AuthorizationExecuteWithPrivileges reports no exit status and does not say what
// process it started, which is why the one-shot says so itself: what it prints is
// the only evidence that the change was applied.
func execute(ctx context.Context, authorization uintptr, self string, args []string) error {
var pinner runtime.Pinner
defer pinner.Unpin()
argv := make([]uintptr, 0, len(args)+1)
for _, arg := range args {
argv = append(argv, uintptr(unsafe.Pointer(cString(&pinner, arg))))
}
argv = append(argv, 0)
pinner.Pin(&argv[0])
var pipe uintptr
status := authorizationExecuteWithPrivileges(authorization, self, flagDefaults, &argv[0], &pipe)
switch status {
case errAuthorizationSuccess:
case errAuthorizationCanceled:
return ErrDeclined
case errAuthorizationToolExecuteFailure, errAuthorizationToolEnvironmentError:
// The right was granted and the tool still did not start. Nothing the user
// can do about it from here, so point them at the command instead.
return fmt.Errorf("%w: the system would not run %s elevated (OSStatus %d)", ErrUnavailable, self, status)
default:
return fmt.Errorf("run %s elevated: OSStatus %d", self, status)
}
out, err := readPipe(ctx, pipe)
if err != nil {
return err
}
return checkApplied(out)
}
// checkApplied reads the one-shot's report, which stands in for the exit status
// there is no way to ask for here. A run that said nothing did not apply the
// change, whatever else went on.
func checkApplied(out string) error {
if !strings.Contains(out, AppliedMarker) {
return fmt.Errorf("elevated netbird did not report the change as applied: %s", firstLine(out))
}
return nil
}
// readPipe drains the tool's output, which ends when the tool exits and is
// therefore also how we wait for it.
func readPipe(ctx context.Context, pipe uintptr) (string, error) {
if pipe == 0 {
return "", nil
}
defer fclose(pipe)
fd := int(fileno(pipe))
if fd < 0 {
return "", nil
}
var out strings.Builder
buf := make([]byte, 4096)
for {
if err := ctx.Err(); err != nil {
return out.String(), err
}
n, err := syscall.Read(fd, buf)
if n > 0 {
out.Write(buf[:n])
}
switch {
case errors.Is(err, syscall.EINTR):
// A signal landed mid-read, which says nothing about the tool.
continue
case err != nil:
log.Debugf("read the elevated process's output: %v", err)
return out.String(), nil
case n <= 0:
// End of file: the tool closed the pipe, which is how it exiting
// reaches us.
return out.String(), nil
}
}
}
// itemSet builds an AuthorizationItemSet over items, pinned for the call.
func itemSet(pinner *runtime.Pinner, items ...authorizationItem) *authorizationItemSet {
pinner.Pin(&items[0])
set := &authorizationItemSet{count: uint32(len(items)), items: &items[0]}
pinner.Pin(set)
return set
}
// promptItem is the environment entry carrying our sentence for the dialog.
func promptItem(pinner *runtime.Pinner) authorizationItem {
value := []byte(promptText)
pinner.Pin(&value[0])
return authorizationItem{
name: cString(pinner, promptKey),
valueLength: uintptr(len(value)),
value: unsafe.Pointer(&value[0]),
}
}
// cString returns a NUL-terminated copy of s, pinned so the C side may hold it for
// the duration of the call.
func cString(pinner *runtime.Pinner, s string) *byte {
b := append([]byte(s), 0)
pinner.Pin(&b[0])
return &b[0]
}

View File

@@ -1,111 +0,0 @@
package elevate
import (
"errors"
"runtime"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// The framework has to load and the symbols have to resolve, or nothing else here
// means anything.
func TestSecurityFrameworkLoads(t *testing.T) {
require.NoError(t, load(), "Security.framework must open")
for name, fn := range map[string]any{
"AuthorizationCreate": authorizationCreate,
"AuthorizationExecuteWithPrivileges": authorizationExecuteWithPrivileges,
"AuthorizationFree": authorizationFree,
"fileno": fileno,
"fclose": fclose,
} {
assert.NotNil(t, fn, "%s must resolve", name)
}
}
// A request with no interaction allowed exercises the whole call — the rights and
// environment structs, and the OSStatus that comes back — without a dialog anybody
// has to answer. What the system decides is its business; that it decides at all is
// what this asserts.
func TestAuthorizationCreateWithoutInteraction(t *testing.T) {
if err := load(); err != nil {
t.Skipf("Security.framework did not open: %v", err)
}
var pinner runtime.Pinner
defer pinner.Unpin()
rights := itemSet(&pinner, authorizationItem{name: cString(&pinner, rightExecute)})
environment := itemSet(&pinner, promptItem(&pinner))
require.EqualValues(t, 1, rights.count, "the rights struct layout must match the C one")
var authorization uintptr
status := authorizationCreate(rights, environment, flagDefaults|flagExtendRights, &authorization)
switch status {
case errAuthorizationSuccess:
// Credentials were already cached for this session.
authorizationFree(authorization, flagDestroyRights)
case errAuthorizationDenied, errAuthorizationInteractionNotAllowed:
// The expected answers when nobody may be asked.
default:
require.Failf(t, "unknown OSStatus", "AuthorizationCreate returned %d, want a status we recognise", status)
}
}
// Asking with a right nobody has must not be mistaken for a declined prompt: the
// caller would report nothing at all.
func TestAuthorizeUnknownRightIsNotDeclined(t *testing.T) {
if err := load(); err != nil {
t.Skipf("Security.framework did not open: %v", err)
}
var pinner runtime.Pinner
defer pinner.Unpin()
rights := itemSet(&pinner, authorizationItem{name: cString(&pinner, "io.netbird.right.that.does.not.exist")})
var authorization uintptr
status := authorizationCreate(rights, nil, flagDefaults|flagExtendRights, &authorization)
if status == errAuthorizationSuccess {
authorizationFree(authorization, flagDestroyRights)
}
assert.NotEqual(t, int32(errAuthorizationSuccess), status, "a right that does not exist must not be granted")
}
func TestMechanismAvailable(t *testing.T) {
assert.True(t, mechanismAvailable(), "the trampoline exists on every macOS")
}
// The one-shot's report is what stands in for an exit status here, so a run that
// says nothing must not read as success.
func TestCheckApplied(t *testing.T) {
require.NoError(t, checkApplied(AppliedMarker+"\n"), "the report the one-shot prints")
require.NoError(t, checkApplied("some warning\n"+AppliedMarker+"\n"), "the report after other output")
assert.Error(t, checkApplied(""), "a run that printed nothing did not apply the change")
assert.Error(t, checkApplied("dyld: library not loaded\n"), "output that is not the report")
}
// A panic out of the FFI layer has to reach the caller as "no mechanism", which is
// the outcome that offers the user the command instead of taking the window down.
func TestGuardTurnsAPanicIntoUnavailable(t *testing.T) {
err := guard("pretending to call something", func() error {
panic("purego: signature it cannot map")
})
require.ErrorIs(t, err, ErrUnavailable, "a panic must read as a missing mechanism")
assert.Contains(t, err.Error(), "pretending to call something", "what panicked")
}
// guard wraps every darwin path, so what a caller switches on has to survive it.
func TestGuardPassesErrorsThrough(t *testing.T) {
sentinel := errors.New("the call itself failed")
assert.ErrorIs(t, guard("calling", func() error { return sentinel }), sentinel,
"the error it was given")
assert.ErrorIs(t, guard("calling", func() error { return ErrDeclined }), ErrDeclined,
"a declined prompt stays declined")
assert.NoError(t, guard("calling", func() error { return nil }), "a call that worked")
}

View File

@@ -1,117 +0,0 @@
//go:build linux
package elevate
import (
"context"
"errors"
"fmt"
"io"
"os"
"os/exec"
"strings"
)
// pkexec exit codes that are about the authorization rather than about the program
// we asked it to run. The manual page reserves both.
const (
// exitDismissed is returned when the user dismissed the authentication
// dialog.
exitDismissed = 126
// exitNotAuthorized is returned when the authorization was not obtained. That
// covers the user saying no as well as pkexec having had nobody to ask: see
// noAgentMarkers.
exitNotAuthorized = 127
)
// exitNotAuthorized covers three different endings that only pkexec's own words
// tell apart, so they are matched here. Read with LC_ALL=C so the words are the
// ones written below.
//
// refusedMarker is a refusal: the user said no, gave up on the password, or holds
// an account that may not elevate at all.
const refusedMarker = "Not authorized"
// noAgentMarkers say pkexec had no way to ask: no agent registered for the
// session, and no controlling terminal for the textual agent it falls back to.
var noAgentMarkers = []string{"authentication agent", "controlling terminal"}
// run asks polkit to run self as root. pkexec hands the request to the session's
// polkit agent, which is what prompts and what collects any password; we see only
// its verdict.
//
// The environment is otherwise deliberately not passed through: pkexec clears it
// bar a small allowlist, and the one-shot needs nothing from it.
func run(ctx context.Context, self string, args []string) error {
pkexec, err := exec.LookPath("pkexec")
if err != nil {
return fmt.Errorf("%w: pkexec is not installed", ErrUnavailable)
}
cmd := exec.CommandContext(ctx, pkexec, append([]string{self}, args...)...)
// C locale so pkexec's own diagnostics are the ones noAgentMarkers knows.
cmd.Env = append(os.Environ(), "LC_ALL=C")
var stderr strings.Builder
cmd.Stderr = &stderr
// The one-shot reports itself on stdout for macOS's sake, where there is no
// exit status to read. Here there is one, so that line is noise.
cmd.Stdout = io.Discard
err = cmd.Run()
if err == nil {
return nil
}
var exitErr *exec.ExitError
if !errors.As(err, &exitErr) {
return fmt.Errorf("run pkexec: %w", err)
}
// Matched against everything pkexec said, reported as one line: a complaint
// that is not the first thing printed still has to be recognised, and reading
// it as a refusal would swallow it.
full := stderr.String()
out := firstLine(full)
switch exitErr.ExitCode() {
case exitDismissed:
return ErrDeclined
case exitNotAuthorized:
return notAuthorized(full, out)
default:
return fmt.Errorf("elevated netbird exited with %d: %s", exitErr.ExitCode(), out)
}
}
// notAuthorized sorts out the three endings pkexec reports as exitNotAuthorized.
//
// It also returns that code when the authorization succeeded and it then could
// not run the program, so a refusal has to be recognised rather than assumed:
// reading every one of these as "the user said no" would revert the control in
// silence on a host where elevation is broken.
func notAuthorized(full, out string) error {
switch {
case hasAny(full, noAgentMarkers):
return fmt.Errorf("%w: polkit had no way to ask: %s", ErrUnavailable, out)
case out == noOutput, strings.Contains(full, refusedMarker):
// The user said no, which needs no message; that an account barred from
// elevating altogether lands here too is why the reason is kept.
return fmt.Errorf("%w: %s", ErrDeclined, out)
default:
return fmt.Errorf("pkexec could not run elevated netbird: %s", out)
}
}
func hasAny(s string, markers []string) bool {
for _, marker := range markers {
if strings.Contains(s, marker) {
return true
}
}
return false
}
func mechanismAvailable() bool {
_, err := exec.LookPath("pkexec")
return err == nil
}

View File

@@ -1,110 +0,0 @@
//go:build linux
package elevate
import (
"context"
"fmt"
"os"
"path/filepath"
"strings"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// fakePkexec puts a pkexec on PATH that exits with the given code, so the
// mapping from polkit's exit codes onto our errors can be exercised without a
// polkit agent.
func fakePkexec(t *testing.T, exitCode int, stderr string) {
t.Helper()
dir := t.TempDir()
script := fmt.Sprintf("#!/bin/sh\necho %s >&2\nexit %d\n", shellQuote(stderr), exitCode)
require.NoError(t, os.WriteFile(filepath.Join(dir, "pkexec"), []byte(script), 0o700), "write the fake pkexec")
t.Setenv("PATH", dir)
}
func shellQuote(s string) string {
return "'" + strings.ReplaceAll(s, "'", `'\''`) + "'"
}
func TestRunMapsPkexecExitCodes(t *testing.T) {
tests := []struct {
name string
exitCode int
stderr string
wantErr error
}{
{name: "applied", exitCode: 0},
{
name: "dialog dismissed",
exitCode: exitDismissed,
stderr: "Error executing command as another user: Request dismissed",
wantErr: ErrDeclined,
},
{
// What a graphical agent reports for a cancelled prompt. Not a
// failure: the user was asked and answered.
name: "prompt cancelled",
exitCode: exitNotAuthorized,
stderr: "Error executing command as another user: Not authorized",
wantErr: ErrDeclined,
},
{
// The same status, but pkexec never got to ask anybody.
name: "no agent and no terminal to fall back on",
exitCode: exitNotAuthorized,
stderr: "Error creating textual authentication agent: Error opening current controlling terminal for the process (`/dev/tty'): No such device or address",
wantErr: ErrUnavailable,
},
{
// And the same status again once the authorization succeeded and
// pkexec could not run what it had been authorized to run. Reading
// that as a refusal would revert the control in silence on a host
// where elevation is broken.
name: "authorized but not runnable",
exitCode: exitNotAuthorized,
stderr: "Error executing command as another user: No such file or directory",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
fakePkexec(t, tt.exitCode, tt.stderr)
err := run(context.Background(), "/nonexistent/netbird-ui", []string{"--flag"})
switch {
case tt.wantErr != nil:
require.ErrorIs(t, err, tt.wantErr, "exit %d said %q", tt.exitCode, tt.stderr)
case tt.exitCode == 0:
require.NoError(t, err, "a pkexec that exited cleanly applied the change")
default:
require.Error(t, err, "exit %d said %q", tt.exitCode, tt.stderr)
assert.NotErrorIs(t, err, ErrDeclined, "not the user's answer")
assert.NotErrorIs(t, err, ErrUnavailable, "not a missing mechanism")
}
})
}
}
// An exit code that is not polkit's is the one-shot's own failure, and has to
// stay distinguishable from a declined prompt: the caller reports it.
func TestRunReportsOneShotFailure(t *testing.T) {
fakePkexec(t, 3, "the one-shot said no")
err := run(context.Background(), "/nonexistent/netbird-ui", nil)
require.Error(t, err, "a one-shot that failed is not a prompt that was answered")
assert.NotErrorIs(t, err, ErrDeclined, "not the user's answer")
assert.NotErrorIs(t, err, ErrUnavailable, "not a missing mechanism")
}
func TestRunWithoutPkexecIsUnavailable(t *testing.T) {
t.Setenv("PATH", t.TempDir())
err := run(context.Background(), "/nonexistent/netbird-ui", nil)
require.ErrorIs(t, err, ErrUnavailable, "no pkexec means no mechanism")
assert.False(t, mechanismAvailable(), "mechanismAvailable without pkexec on PATH")
}

View File

@@ -1,19 +0,0 @@
//go:build !windows && !darwin && !linux
package elevate
import "context"
// run reports that this platform has no elevation prompt to drive.
//
// The desktop app is the only caller and is not built for any of these: mobile
// and WASM have no local user to ask, and the FreeBSD client ships without a UI.
// pkexec would be the mechanism there, and run_unix.go is what to widen if that
// changes.
func run(context.Context, string, []string) error {
return ErrUnavailable
}
func mechanismAvailable() bool {
return false
}

View File

@@ -1,187 +0,0 @@
package elevate
import (
"context"
"errors"
"fmt"
"runtime"
"unsafe"
log "github.com/sirupsen/logrus"
"golang.org/x/sys/windows"
)
const (
// seeMaskNoCloseProcess keeps the started process's handle open in
// hProcess so we can wait for it.
seeMaskNoCloseProcess = 0x00000040
// seeMaskNoAsync makes ShellExecuteExW finish its work before returning,
// which it must when the calling thread does not pump messages.
seeMaskNoAsync = 0x00000100
// seeMaskFlagNoUI suppresses the shell's own error dialogs; the UAC consent
// dialog is not one of them and still appears.
seeMaskFlagNoUI = 0x00000400
// swHide: the one-shot has no window to show.
swHide = 0
)
// shellExecuteInfoW mirrors SHELLEXECUTEINFOW. The field order and Go's own
// padding match the C layout on both 386 and amd64.
type shellExecuteInfoW struct {
cbSize uint32
fMask uint32
hwnd windows.HWND
lpVerb *uint16
lpFile *uint16
lpParameters *uint16
lpDirectory *uint16
nShow int32
hInstApp windows.Handle
lpIDList uintptr
lpClass *uint16
hkeyClass windows.Handle
dwHotKey uint32
hIconOrMonitor windows.Handle
hProcess windows.Handle
}
var (
shell32 = windows.NewLazySystemDLL("shell32.dll")
procShellExecuteEx = shell32.NewProc("ShellExecuteExW")
)
// run starts self elevated with the "runas" verb, which is what raises the UAC
// consent dialog, and waits for it to finish. Windows decides whether consent is
// enough or an administrator's credentials are needed, and collects them itself.
func run(ctx context.Context, self string, args []string) error {
verb, err := windows.UTF16PtrFromString("runas")
if err != nil {
return fmt.Errorf("encode verb: %w", err)
}
file, err := windows.UTF16PtrFromString(self)
if err != nil {
return fmt.Errorf("encode %s: %w", self, err)
}
params, err := windows.UTF16PtrFromString(windows.ComposeCommandLine(args))
if err != nil {
return fmt.Errorf("encode arguments: %w", err)
}
info := shellExecuteInfoW{
fMask: seeMaskNoCloseProcess | seeMaskNoAsync | seeMaskFlagNoUI,
hwnd: ownerWindow(),
lpVerb: verb,
lpFile: file,
lpParameters: params,
nShow: swHide,
}
info.cbSize = uint32(unsafe.Sizeof(info))
process, err := shellExecute(&info)
if err != nil {
return err
}
defer func() {
if err := windows.CloseHandle(process); err != nil {
log.Debugf("close elevated process handle: %v", err)
}
}()
return waitForProcess(ctx, process)
}
// shellExecute performs the call itself. ShellExecuteExW wants COM initialised on
// the calling thread, so the goroutine is pinned to one for the duration and COM
// is set up on it; an "already initialised, different mode" answer is fine,
// because then somebody else has done it for us.
func shellExecute(info *shellExecuteInfoW) (windows.Handle, error) {
runtime.LockOSThread()
defer runtime.UnlockOSThread()
switch err := windows.CoInitializeEx(0, windows.COINIT_APARTMENTTHREADED); {
case err == nil, isHResult(err, windows.S_FALSE):
// Ours, or already initialised in the same mode: either way this call
// counts and has to be balanced.
defer windows.CoUninitialize()
case isHResult(err, windows.RPC_E_CHANGED_MODE):
// The thread is already in the other apartment model. ShellExecuteExW
// works there too, and there is nothing of ours to balance.
default:
return 0, fmt.Errorf("initialise COM: %w", err)
}
ret, _, lastErr := procShellExecuteEx.Call(uintptr(unsafe.Pointer(info)))
if ret != 0 {
return info.hProcess, nil
}
if errors.Is(lastErr, windows.ERROR_CANCELLED) {
return 0, ErrDeclined
}
return 0, fmt.Errorf("run elevated: %w", lastErr)
}
// ownerWindow returns this process's foreground window, and 0 when the window in
// front belongs to somebody else or cannot be attributed. ShellExecuteExW takes it
// as the parent for the UI it raises, which is what keeps the consent dialog in
// front of the window the user was just clicking in instead of behind it. It is
// also what a remote-desktop session needs to place the dialog at all when the
// secure desktop is switched off.
func ownerWindow() windows.HWND {
hwnd := windows.GetForegroundWindow()
if hwnd == 0 {
return 0
}
var pid uint32
if _, err := windows.GetWindowThreadProcessId(hwnd, &pid); err != nil {
log.Debugf("cannot attribute the foreground window, raising the prompt without an owner: %v", err)
return 0
}
if pid != windows.GetCurrentProcessId() {
return 0
}
return hwnd
}
// isHResult reports whether err carries the given HRESULT. CoInitializeEx
// returns its HRESULT as an Errno, so the comparison is on the raw value.
func isHResult(err error, hresult windows.Handle) bool {
var errno windows.Errno
return errors.As(err, &errno) && uintptr(errno) == uintptr(hresult)
}
func waitForProcess(ctx context.Context, process windows.Handle) error {
// The wait is interruptible so a cancelled context stops us waiting on a
// consent dialog nobody is going to answer. The elevated process is not
// ours to kill, and it either applies the change or does not.
for {
event, err := windows.WaitForSingleObject(process, 250)
if err != nil {
return fmt.Errorf("wait for the elevated process: %w", err)
}
if event == uint32(windows.WAIT_OBJECT_0) {
break
}
if err := ctx.Err(); err != nil {
return err
}
}
var code uint32
if err := windows.GetExitCodeProcess(process, &code); err != nil {
return fmt.Errorf("read the elevated process's exit code: %w", err)
}
if code != 0 {
return fmt.Errorf("elevated netbird exited with %d", code)
}
return nil
}
// mechanismAvailable is true on Windows: UAC prompts for consent when the user
// is an administrator and for an administrator's credentials when they are not,
// so there is always something to ask.
func mechanismAvailable() bool {
return true
}

View File

@@ -1,40 +0,0 @@
package elevate
import (
"fmt"
"os"
"path/filepath"
)
// trustedSelf returns the path of this executable, provided it is one we are
// willing to have run as root.
//
// The check is what keeps elevation from becoming a way to launder someone
// else's code into a root process: the user consents to NetBird being elevated,
// having been shown NetBird's name, so what runs must be the file NetBird was
// installed as and not something a third party could have swapped for it. An
// executable only its owner can write is that; anything wider is refused, and
// the caller falls back to showing the command instead.
//
// The owner writing to their own executable is not part of that threat: code
// running as the user can already prompt them for anything, and could just as
// well ask them to run the command by hand. What matters is that no *other*
// unprivileged account can reach it.
func trustedSelf() (string, error) {
exe, err := os.Executable()
if err != nil {
return "", fmt.Errorf("locate this executable: %w", err)
}
// Resolve symlinks so the checks below apply to the file that would actually
// be executed, not to a link somebody else may control.
resolved, err := filepath.EvalSymlinks(exe)
if err != nil {
return "", fmt.Errorf("resolve %s: %w", exe, err)
}
if err := checkOnlyOwnerWritable(resolved); err != nil {
return "", fmt.Errorf("%w: %s cannot be trusted to run as root: %w", ErrUnavailable, resolved, err)
}
return resolved, nil
}

View File

@@ -1,10 +0,0 @@
package elevate
// adminWriteGIDs are the groups whose write access to an executable does not
// widen who could authorize elevating it.
//
// macOS installs applications as root:admin, mode 0775, /Applications included,
// so requiring owner-only write would reject every normal install. Group admin
// (gid 80) is exactly the set of accounts that can answer the authentication
// dialog, so its write access grants nothing the prompt would not.
var adminWriteGIDs = []uint32{0, 80}

View File

@@ -1,9 +0,0 @@
//go:build !windows && !darwin
package elevate
// adminWriteGIDs are the groups whose write access to an executable does not
// widen who could authorize elevating it. Only root's own group qualifies here:
// a distribution installs into root-owned directories, and there is no
// system-wide administrators group that both writes them and answers polkit.
var adminWriteGIDs = []uint32{0}

View File

@@ -1,119 +0,0 @@
//go:build !windows
package elevate
import (
"errors"
"fmt"
"os"
"path/filepath"
"slices"
"strconv"
"syscall"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/internal/getent"
)
// checkOnlyOwnerWritable reports an error unless path, and every directory leading
// to it, is owned by either root or this user and writable by nobody who could not
// already act as its owner. A writable directory is as good as a writable file,
// since anything in it can be replaced, so the whole chain is checked.
func checkOnlyOwnerWritable(path string) error {
self := uint32(os.Getuid())
for dir := path; ; dir = filepath.Dir(dir) {
info, err := os.Lstat(dir)
if err != nil {
return fmt.Errorf("stat %s: %w", dir, err)
}
stat, ok := info.Sys().(*syscall.Stat_t)
if !ok {
return errors.New("file ownership is unavailable on this platform")
}
if stat.Uid != 0 && stat.Uid != self {
return fmt.Errorf("%s is owned by uid %d, neither root nor this user", dir, stat.Uid)
}
if err := checkWriteBits(dir, info, stat.Uid, stat.Gid); err != nil {
return err
}
if parent := filepath.Dir(dir); parent == dir {
return nil
}
}
}
func checkWriteBits(path string, info os.FileInfo, uid, gid uint32) error {
// On a directory the sticky bit stands in for the write bits: whoever may
// write there still cannot replace an entry they do not own, which is the
// only thing that would matter to us. /tmp is the usual example.
sticky := info.IsDir() && info.Mode()&os.ModeSticky != 0
return writeBitsAllow(path, info.Mode().Perm(), sticky, groupWriteAllowed(uid, gid))
}
// writeBitsAllow decides on the permission bits alone, given whether the group's
// write access has been vouched for.
func writeBitsAllow(path string, perm os.FileMode, sticky, groupAllowed bool) error {
if sticky {
return nil
}
if perm&0o020 != 0 && !groupAllowed {
return fmt.Errorf("%s is writable by a group with members other than its owner (%v)", path, perm)
}
if perm&0o002 != 0 {
return fmt.Errorf("%s is world-writable (%v)", path, perm)
}
return nil
}
// groupWriteAllowed reports whether a group's write access to a file owned by uid
// puts it in reach of anyone who could not already act as that owner.
//
// Two ways it does not. A group in adminWriteGIDs holds the accounts that can
// answer the elevation prompt anyway. And a user private group is how Debian,
// Ubuntu and Fedora ship: their umask of 002 makes a home directory and
// everything built in it group-writable, so refusing that would refuse every
// build not installed from a package.
func groupWriteAllowed(uid, gid uint32) bool {
if slices.Contains(adminWriteGIDs, gid) {
return true
}
group, err := getent.LookupGroupID(strconv.FormatUint(uint64(gid), 10))
if err != nil {
log.Debugf("cannot look up group %d, treating it as shared: %v", gid, err)
return false
}
owner, err := getent.LookupUserID(strconv.FormatUint(uint64(uid), 10))
if err != nil {
log.Debugf("cannot look up uid %d, treating its group as shared: %v", uid, err)
return false
}
if group.Name != owner.Username {
return false
}
return !groupHasOtherMembers(group.Name, owner.Username)
}
// groupHasOtherMembers reports whether the group lists a member besides owner.
//
// Sharing the owner's name is what a user private group is recognised by, and it
// says nothing about who is in it: a group that has since gained a member is
// still named that way, and that member can write whatever the group can. So the
// membership is read rather than assumed. A group whose members cannot be
// listed, because no source on this host describes it, is treated as shared:
// the name alone cannot vouch for who writes through it.
func groupHasOtherMembers(name, owner string) bool {
members, err := getent.GroupMembers(name)
if err != nil {
log.Debugf("cannot list the members of group %q, treating it as shared: %v", name, err)
return true
}
return slices.ContainsFunc(members, func(member string) bool { return member != owner })
}

View File

@@ -1,148 +0,0 @@
//go:build !windows
package elevate
import (
"os"
"os/user"
"path/filepath"
"strconv"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// ownerOnlyDir is t.TempDir() with the write bits tightened. testing creates its
// numbered directory with 0777 minus the umask, so under the common 002 umask it
// is group-writable and would fail the check under test on its own.
func ownerOnlyDir(t *testing.T) string {
t.Helper()
dir := t.TempDir()
require.NoError(t, os.Chmod(dir, 0o755), "tighten the temporary directory")
return dir
}
// writeExecutable creates a plain executable file, the shape trustedSelf checks.
func writeExecutable(t *testing.T, dir string) string {
t.Helper()
path := filepath.Join(dir, "netbird-ui")
require.NoError(t, os.WriteFile(path, []byte("#!/bin/sh\n"), 0o755), "write the executable")
require.NoError(t, os.Chmod(path, 0o755), "set the executable's mode")
return path
}
func TestCheckOnlyOwnerWritableAcceptsOwnerOnly(t *testing.T) {
err := checkOnlyOwnerWritable(writeExecutable(t, ownerOnlyDir(t)))
assert.NoError(t, err, "an owner-only writable executable is trustworthy")
}
func TestCheckOnlyOwnerWritableRejectsWorldWritableFile(t *testing.T) {
path := writeExecutable(t, ownerOnlyDir(t))
require.NoError(t, os.Chmod(path, 0o777), "make the executable world-writable")
assert.Error(t, checkOnlyOwnerWritable(path), "a world-writable executable must be refused")
}
// The permission policy on its own, without a filesystem to arrange: whether the
// group has been vouched for is the only thing that makes group write acceptable.
func TestWriteBitsAllow(t *testing.T) {
tests := []struct {
name string
perm os.FileMode
sticky bool
groupAllowed bool
wantErr bool
}{
{name: "owner only", perm: 0o755},
{name: "group write in a private group", perm: 0o775, groupAllowed: true},
{name: "group write in a shared group", perm: 0o775, wantErr: true},
{name: "world write", perm: 0o777, groupAllowed: true, wantErr: true},
{name: "world write on a sticky directory", perm: 0o777, sticky: true},
{name: "group write on a sticky directory", perm: 0o775, sticky: true},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
err := writeBitsAllow("/path", tt.perm, tt.sticky, tt.groupAllowed)
if tt.wantErr {
assert.Error(t, err, "perm %v, sticky %v, group allowed %v", tt.perm, tt.sticky, tt.groupAllowed)
return
}
assert.NoError(t, err, "perm %v, sticky %v, group allowed %v", tt.perm, tt.sticky, tt.groupAllowed)
})
}
}
// A build under a home directory on a distribution with a 002 umask, which is what
// a locally built or tarball-installed binary looks like. Its group has no members
// but its owner, so it is as good as owner-only.
//
// Whether this host is such a distribution is read from the environment rather than
// from groupWriteAllowed: asking the function under test whether to run would let
// it skip its own coverage away if it regressed to refusing everything.
func TestCheckOnlyOwnerWritableAcceptsOwnPrivateGroup(t *testing.T) {
requirePrivatePrimaryGroup(t)
dir := ownerOnlyDir(t)
path := writeExecutable(t, dir)
require.NoError(t, os.Chmod(dir, 0o775), "make the directory group-writable")
require.NoError(t, os.Chmod(path, 0o775), "make the executable group-writable")
err := checkOnlyOwnerWritable(path)
assert.NoError(t, err, "group write in the owner's own private group reaches nobody else")
}
// A group whose membership no source can answer for is treated as shared: the
// private-group allowance must not stand on a name nobody can vouch for. The
// membership listing itself lives in the getent package and is tested there.
func TestGroupHasOtherMembersRejectsAnUnknownGroup(t *testing.T) {
assert.True(t, groupHasOtherMembers("nonexistent_group_xyzzy_12345", "vma"),
"a group no source describes")
}
// A writable directory is as good as a writable file: whoever can write the
// directory can put a different binary at the same path.
func TestCheckOnlyOwnerWritableRejectsWritableDirectory(t *testing.T) {
dir := filepath.Join(ownerOnlyDir(t), "bin")
require.NoError(t, os.Mkdir(dir, 0o755), "create the directory")
path := writeExecutable(t, dir)
require.NoError(t, os.Chmod(dir, 0o777), "make the directory world-writable")
assert.Error(t, checkOnlyOwnerWritable(path), "an executable in a world-writable directory must be refused")
}
// A sticky world-writable directory is exempt: the sticky bit is what stops one
// user replacing another's entries. /tmp is why this matters.
func TestCheckOnlyOwnerWritableAcceptsStickyDirectory(t *testing.T) {
dir := filepath.Join(ownerOnlyDir(t), "sticky")
require.NoError(t, os.Mkdir(dir, 0o755), "create the directory")
path := writeExecutable(t, dir)
require.NoError(t, os.Chmod(dir, 0o777|os.ModeSticky), "make the directory sticky and world-writable")
err := checkOnlyOwnerWritable(path)
assert.NoError(t, err, "the sticky bit stops another user replacing the executable")
}
func TestCheckOnlyOwnerWritableRejectsMissingFile(t *testing.T) {
err := checkOnlyOwnerWritable(filepath.Join(ownerOnlyDir(t), "absent"))
assert.Error(t, err, "an executable that is not there must be refused")
}
// requirePrivatePrimaryGroup skips unless this user's primary group is their own,
// which is what the user-private-group allowance is about.
func requirePrivatePrimaryGroup(t *testing.T) {
t.Helper()
self, err := user.Current()
require.NoError(t, err, "look up the test user")
group, err := user.LookupGroupId(strconv.Itoa(os.Getgid()))
require.NoError(t, err, "look up the test user's primary group")
if group.Name != self.Username {
t.Skipf("the test user's primary group is %q, not their own, so there is nothing to assert here", group.Name)
}
if groupHasOtherMembers(group.Name, self.Username) {
t.Skipf("group %q has other members, so it is not a private group", group.Name)
}
}

View File

@@ -1,215 +0,0 @@
package elevate
import (
"errors"
"fmt"
"path/filepath"
"slices"
"unsafe"
"golang.org/x/sys/windows"
)
const (
// fileDeleteChild is FILE_DELETE_CHILD, which x/sys does not define: the
// right to delete an entry of a directory without holding DELETE on it.
fileDeleteChild = 0x00000040
// accessAllowedCallbackACEType is an allow ACE with a condition appended to
// the ACCESS_ALLOWED_ACE layout, so its trustee is still at SidStart.
accessAllowedCallbackACEType = 0x9
// The allow ACE types that carry object GUIDs ahead of the trustee, so the
// SID is not at SidStart. They occur on directory-service objects rather
// than files, and are refused rather than skipped: see aceTrustee.
accessAllowedObjectACEType = 0x5
accessAllowedCallbackObjectACEType = 0xB
)
// fileWriteAccess are the rights that let a trustee rewrite or replace a file,
// or take it over and then do so.
const fileWriteAccess = windows.FILE_WRITE_DATA | windows.FILE_APPEND_DATA |
windows.DELETE | windows.WRITE_DAC | windows.WRITE_OWNER |
windows.GENERIC_WRITE | windows.GENERIC_ALL
// dirWriteAccess are the rights over a directory that let a trustee replace an
// entry somebody else owns. Creating a new entry is not one of them, which is
// what the Unix sticky bit says in one bit: the root of every volume grants
// BUILTIN\Users the right to add directories under it, and that reaches nothing
// already there.
const dirWriteAccess = fileDeleteChild | windows.DELETE |
windows.WRITE_DAC | windows.WRITE_OWNER | windows.GENERIC_ALL
// trustedInstallerSID owns much of what Windows itself installs. x/sys has no
// well-known constant for it.
const trustedInstallerSID = "S-1-5-80-956008885-3418522649-1831038044-1853292631-2271478464"
// checkOnlyOwnerWritable reports an error unless path, and every directory
// leading to it, is owned by an account that can elevate (or by this user) and
// grants write access to nobody else. A writable directory is as good as a
// writable file, since an entry in it can be replaced, so the whole chain is
// checked.
func checkOnlyOwnerWritable(path string) error {
owners, err := trustedOwners()
if err != nil {
return err
}
writers, err := trustedWriters(owners)
if err != nil {
return err
}
writeAccess := windows.ACCESS_MASK(fileWriteAccess)
for target := path; ; target = filepath.Dir(target) {
if err := checkSecurity(target, writeAccess, owners, writers); err != nil {
return err
}
if parent := filepath.Dir(target); parent == target {
return nil
}
writeAccess = dirWriteAccess
}
}
// trustedOwners are the accounts we accept as the owner of the executable and of
// the directories above it: the ones that can already answer the UAC prompt,
// plus this user, whose own executable is theirs to write. Code running as the
// user could prompt them for anything anyway; what matters is that no *other*
// unprivileged account can reach it.
func trustedOwners() ([]*windows.SID, error) {
self, err := currentUserSID()
if err != nil {
return nil, err
}
owners := []*windows.SID{self}
for _, wellKnown := range []windows.WELL_KNOWN_SID_TYPE{
windows.WinLocalSystemSid,
windows.WinBuiltinAdministratorsSid,
} {
sid, err := windows.CreateWellKnownSid(wellKnown)
if err != nil {
return nil, fmt.Errorf("build well-known SID %d: %w", wellKnown, err)
}
owners = append(owners, sid)
}
installer, err := windows.StringToSid(trustedInstallerSID)
if err != nil {
return nil, fmt.Errorf("parse TrustedInstaller SID: %w", err)
}
return append(owners, installer), nil
}
// trustedWriters are the trustees whose write access does not widen who could
// decide what runs behind the prompt. The owners, and CREATOR OWNER, which
// resolves to the object's owner and is therefore already vetted.
func trustedWriters(owners []*windows.SID) ([]*windows.SID, error) {
creatorOwner, err := windows.CreateWellKnownSid(windows.WinCreatorOwnerSid)
if err != nil {
return nil, fmt.Errorf("build the CREATOR OWNER SID: %w", err)
}
return append(slices.Clone(owners), creatorOwner), nil
}
func checkSecurity(path string, writeAccess windows.ACCESS_MASK, owners, writers []*windows.SID) error {
sd, err := windows.GetNamedSecurityInfo(path, windows.SE_FILE_OBJECT,
windows.OWNER_SECURITY_INFORMATION|windows.DACL_SECURITY_INFORMATION)
if err != nil {
return fmt.Errorf("read security descriptor of %s: %w", path, err)
}
owner, _, err := sd.Owner()
if err != nil {
return fmt.Errorf("read owner of %s: %w", path, err)
}
if !containsSID(owners, owner) {
return fmt.Errorf("%s is owned by %s, which is neither this user nor an account that can elevate", path, owner)
}
dacl, _, err := sd.DACL()
if err != nil {
return fmt.Errorf("read DACL of %s: %w", path, err)
}
// A NULL DACL grants everyone everything; only an absent security
// descriptor would have got us here without one, and neither is trustworthy.
if dacl == nil {
return fmt.Errorf("%s has no DACL, so it grants write access to everyone", path)
}
return checkDACL(path, dacl, writeAccess, writers)
}
// checkDACL refuses an ACL that grants write access to a trustee outside
// writers.
//
// An allowlist, because the trustees that must not have it cannot be listed: an
// ACE naming an ordinary user account hands that account the same power as one
// naming Everyone, and only the accounts that may hold it are knowable.
func checkDACL(path string, dacl *windows.ACL, writeAccess windows.ACCESS_MASK, writers []*windows.SID) error {
for i := uint32(0); i < uint32(dacl.AceCount); i++ {
var ace *windows.ACCESS_ALLOWED_ACE
if err := windows.GetAce(dacl, i, &ace); err != nil {
return fmt.Errorf("read ACE %d of %s: %w", i, path, err)
}
// An inherit-only ACE says what children of this object get, not what
// this object grants.
if ace.Header.AceFlags&windows.INHERIT_ONLY_ACE != 0 {
continue
}
if ace.Mask&writeAccess == 0 {
continue
}
// Only an allow ACE grants anything; a deny ACE narrows what one gave.
if !isAllowACE(ace.Header.AceType) {
continue
}
trustee, err := aceTrustee(ace)
if err != nil {
return fmt.Errorf("read the trustee of ACE %d of %s: %w", i, path, err)
}
if !containsSID(writers, trustee) {
return fmt.Errorf("%s grants write access to %s", path, trustee)
}
}
return nil
}
// isAllowACE reports whether an ACE type grants rights, rather than denying,
// auditing or labelling them.
func isAllowACE(aceType uint8) bool {
switch aceType {
case windows.ACCESS_ALLOWED_ACE_TYPE, accessAllowedCallbackACEType,
accessAllowedObjectACEType, accessAllowedCallbackObjectACEType:
return true
default:
return false
}
}
// aceTrustee returns who an allow ACE grants its rights to. An ACE whose trustee
// cannot be located is an error rather than something to skip past: being unable
// to read who is being given write access is a refusal.
func aceTrustee(ace *windows.ACCESS_ALLOWED_ACE) (*windows.SID, error) {
switch ace.Header.AceType {
case windows.ACCESS_ALLOWED_ACE_TYPE, accessAllowedCallbackACEType:
//nolint:gosec // SidStart is the first uint32 of the variable-length SID that follows the ACE header.
return (*windows.SID)(unsafe.Pointer(&ace.SidStart)), nil
default:
return nil, errors.New("an object-type allow ACE does not carry its trustee where we can read it")
}
}
func containsSID(sids []*windows.SID, sid *windows.SID) bool {
return slices.ContainsFunc(sids, sid.Equals)
}
func currentUserSID() (*windows.SID, error) {
token := windows.GetCurrentProcessToken()
user, err := token.GetTokenUser()
if err != nil {
return nil, fmt.Errorf("read this process's user: %w", err)
}
return user.User.Sid, nil
}

View File

@@ -1,126 +0,0 @@
package elevate
import (
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"golang.org/x/sys/windows"
)
// A file the test user created under their own profile, which is what a per-user
// install looks like. The whole chain up to the volume root is walked, so this is
// also what says the walk does not refuse an ordinary Windows installation: the
// root of every volume grants BUILTIN\Users rights that are not ours to worry
// about.
func TestCheckOnlyOwnerWritableAcceptsOwnFile(t *testing.T) {
err := checkOnlyOwnerWritable(writeExecutable(t))
assert.NoError(t, err, "a file the test user owns, under directories only administrators can write")
}
// Write access held by an account that cannot answer the UAC prompt means that
// account decides what runs behind it, whoever the ACE names. The trustees that
// must not have it cannot be listed, so the check names the ones that may.
func TestCheckOnlyOwnerWritableRejectsUntrustedWriters(t *testing.T) {
tests := []struct {
name string
wellKnown windows.WELL_KNOWN_SID_TYPE
}{
{name: "everyone", wellKnown: windows.WinWorldSid},
{name: "authenticated users", wellKnown: windows.WinAuthenticatedUserSid},
{name: "builtin users", wellKnown: windows.WinBuiltinUsersSid},
// A service account, which no denylist of the obvious groups would name
// and which cannot elevate any more than Everyone can.
{name: "local service", wellKnown: windows.WinLocalServiceSid},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
path := writeExecutable(t)
grantWrite(t, path, tt.wellKnown)
assert.Error(t, checkOnlyOwnerWritable(path),
"write access for %s must be refused", tt.name)
})
}
}
// The masks are the policy: on a file any write reaches its contents, while on a
// directory only deleting or taking over an entry reaches something already
// there. Adding an entry does not, which is why the walk survives a volume root.
func TestWriteAccessMasks(t *testing.T) {
assert.NotZero(t, fileWriteAccess&windows.FILE_WRITE_DATA, "writing a file's data reaches its contents")
assert.NotZero(t, fileWriteAccess&windows.FILE_APPEND_DATA, "appending to a file reaches its contents")
assert.Zero(t, dirWriteAccess&windows.FILE_WRITE_DATA, "adding a file to a directory replaces nothing")
assert.Zero(t, dirWriteAccess&windows.FILE_APPEND_DATA, "adding a subdirectory replaces nothing")
assert.NotZero(t, dirWriteAccess&fileDeleteChild, "deleting an entry replaces it")
assert.NotZero(t, dirWriteAccess&windows.DELETE, "deleting the directory takes its entries with it")
}
func TestIsAllowACE(t *testing.T) {
tests := []struct {
name string
aceType uint8
want bool
}{
{name: "allowed", aceType: windows.ACCESS_ALLOWED_ACE_TYPE, want: true},
{name: "allowed callback", aceType: accessAllowedCallbackACEType, want: true},
{name: "allowed object", aceType: accessAllowedObjectACEType, want: true},
{name: "allowed callback object", aceType: accessAllowedCallbackObjectACEType, want: true},
{name: "denied", aceType: windows.ACCESS_DENIED_ACE_TYPE},
// SYSTEM_AUDIT_ACE_TYPE, which x/sys does not define: an ACE that records
// access rather than granting it.
{name: "audit", aceType: 0x2},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
assert.Equal(t, tt.want, isAllowACE(tt.aceType), "ACE type %#x", tt.aceType)
})
}
}
// writeExecutable creates a plain file under the test's own directory, the shape
// trustedSelf checks.
func writeExecutable(t *testing.T) string {
t.Helper()
path := filepath.Join(t.TempDir(), "netbird-ui.exe")
require.NoError(t, os.WriteFile(path, []byte("MZ"), 0o755), "write the executable")
return path
}
// grantWrite replaces the file's DACL with one that grants a well-known trustee
// everything, keeping the test user's own access so the file stays deletable.
func grantWrite(t *testing.T, path string, wellKnown windows.WELL_KNOWN_SID_TYPE) {
t.Helper()
trustee, err := windows.CreateWellKnownSid(wellKnown)
require.NoError(t, err, "build the trustee SID")
self, err := currentUserSID()
require.NoError(t, err, "read the test user's SID")
acl, err := windows.ACLFromEntries([]windows.EXPLICIT_ACCESS{
fullControl(self, windows.TRUSTEE_IS_USER),
fullControl(trustee, windows.TRUSTEE_IS_WELL_KNOWN_GROUP),
}, nil)
require.NoError(t, err, "build the ACL")
require.NoError(t, windows.SetNamedSecurityInfo(path, windows.SE_FILE_OBJECT,
windows.DACL_SECURITY_INFORMATION|windows.PROTECTED_DACL_SECURITY_INFORMATION,
nil, nil, acl, nil), "set the DACL")
}
func fullControl(sid *windows.SID, trusteeType uint32) windows.EXPLICIT_ACCESS {
return windows.EXPLICIT_ACCESS{
AccessPermissions: windows.GENERIC_ALL,
AccessMode: windows.GRANT_ACCESS,
Trustee: windows.TRUSTEE{
TrusteeForm: windows.TRUSTEE_IS_SID,
TrusteeType: windows.TRUSTEE_TYPE(trusteeType),
TrusteeValue: windows.TrusteeValueFromSID(sid),
},
}
}

View File

@@ -59,7 +59,6 @@ import (
"github.com/netbirdio/netbird/client/internal/syncstore"
"github.com/netbirdio/netbird/client/internal/updater"
"github.com/netbirdio/netbird/client/jobexec"
"github.com/netbirdio/netbird/client/netstate"
cProto "github.com/netbirdio/netbird/client/proto"
"github.com/netbirdio/netbird/client/system"
nbdns "github.com/netbirdio/netbird/dns"
@@ -182,9 +181,6 @@ type EngineServices struct {
UpdateManager *updater.Manager
ClientMetrics *metrics.ClientMetrics
MetricsCtx context.Context
// NetState gates the reconnection loops on OS-reported network
// availability; nil disables gating.
NetState *netstate.State
}
// Engine is a mechanism responsible for reacting on Signal and Management stream events and managing connections to the remote peers.
@@ -208,10 +204,6 @@ type Engine struct {
config *EngineConfig
mobileDep MobileDependency
// netState gates the peer reconnection guards on OS-reported network
// availability; nil disables gating.
netState *netstate.State
// STUNs is a list of STUN servers used by ICE
STUNs []*stun.URI
// TURNs is a list of STUN servers used by ICE
@@ -345,7 +337,6 @@ func NewEngine(
syncMsgMux: &sync.Mutex{},
config: config,
mobileDep: mobileDep,
netState: services.NetState,
STUNs: []*stun.URI{},
TURNs: []*stun.URI{},
networkSerial: 0,
@@ -1902,8 +1893,7 @@ func (e *Engine) createPeerConn(pubKey string, allowedIPs []netip.Prefix, agentV
Addr: e.getRosenpassAddr(),
PermissiveMode: e.config.RosenpassPermissive,
},
ICEConfig: e.createICEConfig(),
NetworkState: e.netState,
ICEConfig: e.createICEConfig(),
}
serviceDependencies := peer.ServiceDependencies{
@@ -2572,7 +2562,7 @@ func (e *Engine) SetCapture(pc device.PacketCapture) error {
}
afc := capture.NewAFPacketCapture(intf.Name(), sess)
if err := afc.Start(); err != nil { //nolint:staticcheck // always errors on non-Linux builds
if err := afc.Start(); err != nil {
return fmt.Errorf("start AF_PACKET capture on %s: %w", intf.Name(), err)
}
e.afpacketCapture = afc

View File

@@ -12,7 +12,7 @@ import (
"testing"
"time"
"go.uber.org/mock/gomock"
"github.com/golang/mock/gomock"
"github.com/google/uuid"
log "github.com/sirupsen/logrus"
"github.com/stretchr/testify/assert"

View File

@@ -1,36 +0,0 @@
//go:build cgo && !osusergo && !windows
package getent
import "os/user"
// Built with cgo, os/user resolves through libc (getpwnam_r and friends),
// which goes through the host's NSS stack natively. Whatever it fails to
// find, the getent command would not find either, so there is nothing to
// fall back to.
// LookupUser looks up a user by name.
func LookupUser(username string) (*user.User, error) {
return user.Lookup(username)
}
// LookupUserID looks up a user by UID.
func LookupUserID(uid string) (*user.User, error) {
return user.LookupId(uid)
}
// CurrentUser returns the user this process runs as.
func CurrentUser() (*user.User, error) {
return user.Current()
}
// LookupGroupID looks up a group by GID.
func LookupGroupID(gid string) (*user.Group, error) {
return user.LookupGroupId(gid)
}
// GroupIDs returns the IDs of the groups the user is a member of; libc's
// getgrouplist handles NSS groups natively.
func GroupIDs(u *user.User) ([]string, error) {
return u.GroupIds()
}

View File

@@ -1,6 +0,0 @@
// Package getent resolves users and groups through the host's NSS stack.
// Built without cgo, os/user reads /etc/passwd and /etc/group alone and misses
// anything LDAP, SSSD or winbind provide; the getent and id commands resolve
// through NSS whatever the build. The lookups here try the standard library
// first, which needs no subprocess, and fall back to those commands.
package getent

View File

@@ -1,110 +0,0 @@
//go:build (!cgo || osusergo) && !windows
package getent
import (
"os"
"os/user"
"strconv"
log "github.com/sirupsen/logrus"
)
// Without cgo, os/user only reads /etc/passwd and /etc/group and misses
// NSS-provided users and groups; the getent and id commands go through the
// host's NSS stack.
// LookupUser looks up a user by name, falling back to getent if os/user fails.
func LookupUser(username string) (*user.User, error) {
u, err := user.Lookup(username)
if err == nil {
return u, nil
}
stdErr := err
log.Debugf("os/user.Lookup(%q) failed, trying getent: %v", username, err)
u, _, getentErr := passwdLookup(username)
if getentErr != nil {
log.Debugf("getent fallback for %q also failed: %v", username, getentErr)
return nil, stdErr
}
return u, nil
}
// LookupUserID looks up a user by UID, falling back to getent if os/user fails.
func LookupUserID(uid string) (*user.User, error) {
u, err := user.LookupId(uid)
if err == nil {
return u, nil
}
stdErr := err
log.Debugf("os/user.LookupId(%q) failed, trying getent: %v", uid, err)
u, _, getentErr := passwdLookup(uid)
if getentErr != nil {
log.Debugf("getent fallback for uid %s also failed: %v", uid, getentErr)
return nil, stdErr
}
return u, nil
}
// CurrentUser returns the user this process runs as, falling back to getent
// if os/user fails.
func CurrentUser() (*user.User, error) {
u, err := user.Current()
if err == nil {
return u, nil
}
stdErr := err
uid := strconv.Itoa(os.Getuid())
log.Debugf("os/user.Current() failed, trying getent with UID %s: %v", uid, err)
u, _, getentErr := passwdLookup(uid)
if getentErr != nil {
return nil, stdErr
}
return u, nil
}
// LookupGroupID looks up a group by GID, falling back to getent if os/user
// fails.
func LookupGroupID(gid string) (*user.Group, error) {
g, err := user.LookupGroupId(gid)
if err == nil {
return g, nil
}
stdErr := err
log.Debugf("os/user.LookupGroupId(%q) failed, trying getent: %v", gid, err)
g, _, getentErr := groupLookup(gid)
if getentErr != nil {
log.Debugf("getent fallback for gid %s also failed: %v", gid, getentErr)
return nil, stdErr
}
return g, nil
}
// GroupIDs returns the IDs of the groups the user is a member of.
// NOTE: unlike the lookups above, which try the standard library first, this
// intentionally tries `id -G` first because without cgo, user.GroupIds only
// reads /etc/group and silently returns incomplete results for NSS users
// (no error, just missing groups). The id command goes through NSS and
// returns the full set.
func GroupIDs(u *user.User) ([]string, error) {
ids, err := idGroups(u.Username)
if err == nil {
return ids, nil
}
log.Debugf("id -G %q failed, falling back to user.GroupIds(): %v", u.Username, err)
ids, stdErr := u.GroupIds()
if stdErr != nil {
return nil, stdErr
}
return ids, nil
}

View File

@@ -1,224 +0,0 @@
//go:build !windows
package getent
import (
"bufio"
"context"
"fmt"
"os"
"os/exec"
"os/user"
"runtime"
"strings"
"time"
log "github.com/sirupsen/logrus"
)
const commandTimeout = 5 * time.Second
// groupFile lists which accounts are in which group, for hosts where the
// getent command is not available (macOS ships without it).
const groupFile = "/etc/group"
// UserShell returns the login shell getent reports for the user with this UID.
// It reaches shells that /etc/passwd does not list, because getent resolves
// through the host's NSS stack.
func UserShell(uid string) (string, error) {
_, shell, err := passwdLookup(uid)
if err != nil {
return "", err
}
return shell, nil
}
// GroupMembers returns the names of the group's members: from getent, which
// resolves through NSS, or from /etc/group where getent is not available. A
// group neither source describes is an error; an empty member list is not,
// since accounts with the group as their primary one are not listed in it.
func GroupMembers(name string) ([]string, error) {
_, members, err := groupLookup(name)
if err == nil {
return members, nil
}
log.Debugf("getent cannot list group %q, reading %s: %v", name, groupFile, err)
return groupMembersFromFile(groupFile, name)
}
// passwdLookup executes `getent passwd <query>`, where query is a username or
// UID, and returns the user and login shell.
func passwdLookup(query string) (*user.User, string, error) {
out, err := run("passwd", query)
if err != nil {
return nil, "", err
}
return parsePasswd(string(out))
}
// groupLookup executes `getent group <query>`, where query is a group name or
// GID, and returns the group and its member names.
func groupLookup(query string) (*user.Group, []string, error) {
out, err := run("group", query)
if err != nil {
return nil, nil, err
}
return parseGroup(string(out))
}
// run executes `getent <database> <key>` with a timeout.
func run(database, key string) ([]byte, error) {
if !validateInput(key) {
return nil, fmt.Errorf("invalid getent input: %q", key)
}
ctx, cancel := context.WithTimeout(context.Background(), commandTimeout)
defer cancel()
out, err := exec.CommandContext(ctx, "getent", database, key).Output()
if err != nil {
return nil, fmt.Errorf("getent %s %s: %w", database, key, err)
}
return out, nil
}
// parsePasswd parses getent passwd output: "name:x:uid:gid:gecos:home:shell"
func parsePasswd(output string) (*user.User, string, error) {
fields := strings.SplitN(strings.TrimSpace(output), ":", 8)
if len(fields) < 6 {
return nil, "", fmt.Errorf("unexpected getent output (need 6+ fields): %q", output)
}
if fields[0] == "" || fields[2] == "" || fields[3] == "" {
return nil, "", fmt.Errorf("missing required fields in getent output: %q", output)
}
var shell string
if len(fields) >= 7 {
shell = fields[6]
}
return &user.User{
Username: fields[0],
Uid: fields[2],
Gid: fields[3],
Name: fields[4],
HomeDir: fields[5],
}, shell, nil
}
// parseGroup parses getent group output: "name:x:gid:member,member"
func parseGroup(output string) (*user.Group, []string, error) {
fields := strings.SplitN(strings.TrimSpace(output), ":", 4)
if len(fields) < 3 {
return nil, nil, fmt.Errorf("unexpected getent output (need 3+ fields): %q", output)
}
if fields[0] == "" || fields[2] == "" {
return nil, nil, fmt.Errorf("missing required fields in getent output: %q", output)
}
var members []string
if len(fields) >= 4 {
members = splitMembers(fields[3])
}
return &user.Group{Name: fields[0], Gid: fields[2]}, members, nil
}
func splitMembers(list string) []string {
var members []string
for member := range strings.SplitSeq(list, ",") {
if member != "" {
members = append(members, member)
}
}
return members
}
// groupMembersFromFile finds the group's member list in a file of /etc/group's
// format. A group the file does not describe, because it comes from LDAP or
// another NSS source, is an error rather than an empty list.
func groupMembersFromFile(path, name string) ([]string, error) {
file, err := os.Open(path)
if err != nil {
return nil, fmt.Errorf("open %s: %w", path, err)
}
defer func() {
if err := file.Close(); err != nil {
log.Debugf("close %s: %v", path, err)
}
}()
scanner := bufio.NewScanner(file)
for scanner.Scan() {
// name:password:gid:member,member
fields := strings.Split(scanner.Text(), ":")
if len(fields) < 4 || fields[0] != name {
continue
}
return splitMembers(fields[3]), nil
}
if err := scanner.Err(); err != nil {
return nil, fmt.Errorf("read %s: %w", path, err)
}
return nil, fmt.Errorf("%s does not describe group %q", path, name)
}
// validateInput checks that the input is safe to pass to getent or id.
// Allows POSIX usernames, numeric IDs, and common NSS extensions
// (@ for Kerberos, $ for Samba, + for NIS compat). A leading hyphen is
// rejected so the input can never be parsed as a command-line flag.
func validateInput(input string) bool {
maxLen := 32
if runtime.GOOS == "linux" {
maxLen = 256
}
if len(input) == 0 || len(input) > maxLen {
return false
}
if input[0] == '-' {
return false
}
for _, r := range input {
if isAllowedChar(r) {
continue
}
return false
}
return true
}
func isAllowedChar(r rune) bool {
if r >= 'a' && r <= 'z' || r >= 'A' && r <= 'Z' || r >= '0' && r <= '9' {
return true
}
switch r {
case '.', '_', '-', '@', '+', '$':
return true
}
return false
}
// idGroups runs `id -G <username>` and returns the space-separated group IDs.
func idGroups(username string) ([]string, error) {
if !validateInput(username) {
return nil, fmt.Errorf("invalid username for id command: %q", username)
}
ctx, cancel := context.WithTimeout(context.Background(), commandTimeout)
defer cancel()
out, err := exec.CommandContext(ctx, "id", "-G", username).Output()
if err != nil {
return nil, fmt.Errorf("id -G %s: %w", username, err)
}
trimmed := strings.TrimSpace(string(out))
if trimmed == "" {
return nil, fmt.Errorf("id -G %s: empty output", username)
}
return strings.Fields(trimmed), nil
}

View File

@@ -1,36 +0,0 @@
//go:build windows
package getent
import (
"errors"
"os/user"
)
// Windows does not use NSS or getent; os/user resolves accounts there
// without cgo, so everything delegates to it.
// LookupUser looks up a user by name.
func LookupUser(username string) (*user.User, error) {
return user.Lookup(username)
}
// LookupUserID looks up a user by UID.
func LookupUserID(uid string) (*user.User, error) {
return user.LookupId(uid)
}
// CurrentUser returns the user this process runs as.
func CurrentUser() (*user.User, error) {
return user.Current()
}
// GroupIDs returns the IDs of the groups the user is a member of.
func GroupIDs(u *user.User) ([]string, error) {
return u.GroupIds()
}
// UserShell is unanswerable on Windows, which has no login-shell database.
func UserShell(string) (string, error) {
return "", errors.ErrUnsupported
}

View File

@@ -91,12 +91,6 @@ func SelfDelegatesTo() (Identity, bool) {
return selfIdentity, true
}
// The values PrivilegedActorKey returns.
const (
ActorKeyAdministrator = "administrator"
ActorKeyRoot = "root"
)
// PrivilegedActor names the principal a privileged operation requires, for use
// in messages shown to the user.
func PrivilegedActor() string {
@@ -106,16 +100,6 @@ func PrivilegedActor() string {
return "root"
}
// PrivilegedActorKey identifies that principal without wording it, for a client
// that writes its own message in the user's language. The words PrivilegedActor
// returns are English, and a translated sentence cannot borrow them.
func PrivilegedActorKey() string {
if runtime.GOOS == "windows" {
return ActorKeyAdministrator
}
return ActorKeyRoot
}
// ElevatedCommand renders a command so that running it grants the privileges the
// operation needs. Windows has no in-line equivalent of sudo, so the command is
// returned unchanged and the user is expected to run it from an elevated

View File

@@ -26,7 +26,6 @@ import (
"github.com/netbirdio/netbird/client/internal/portforward"
"github.com/netbirdio/netbird/client/internal/rosenpass"
"github.com/netbirdio/netbird/client/internal/stdnet"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/route"
relayClient "github.com/netbirdio/netbird/shared/relay/client"
)
@@ -94,10 +93,6 @@ type ConnConfig struct {
// ICEConfig ICE protocol configuration
ICEConfig icemaker.Config
// NetworkState gates the reconnection guard on OS-reported network
// availability; nil disables gating.
NetworkState *netstate.State
}
type Conn struct {
@@ -259,7 +254,7 @@ func (conn *Conn) open(engineCtx context.Context, firstPacket []byte) error {
conn.handshaker.AddICEListener(conn.workerICE.OnNewOffer)
}
conn.guard = guard.NewGuard(conn.Log, conn.isConnectedOnAllWay, conn.config.Timeout, conn.srWatcher, conn.config.NetworkState)
conn.guard = guard.NewGuard(conn.Log, conn.isConnectedOnAllWay, conn.config.Timeout, conn.srWatcher)
conn.wg.Add(1)
go func() {
@@ -445,7 +440,7 @@ func (conn *Conn) onICEConnectionIsReady(priority conntype.ConnPriority, iceConn
conn.dumpState.NewLocalProxy()
wgProxy, err = conn.newProxy(iceConnInfo.RemoteConn)
if err != nil {
conn.Log.Errorf("failed to add relayed net.Conn to local proxy: %v", err)
conn.Log.Errorf("failed to add turn net.Conn to local proxy: %v", err)
return
}
ep = wgProxy.EndpointAddr()
@@ -883,8 +878,9 @@ func (conn *Conn) newProxy(remoteConn net.Conn) (wgproxy.Proxy, error) {
}
wgProxy := conn.config.WgConfig.WgInterface.GetProxy()
if err := wgProxy.AddRelayedConn(conn.ctx, udpAddr, remoteConn); err != nil {
return nil, fmt.Errorf("add relayed conn to proxy: %w", err)
if err := wgProxy.AddTurnConn(conn.ctx, udpAddr, remoteConn); err != nil {
conn.Log.Errorf("failed to add turn net.Conn to local proxy: %v", err)
return nil, err
}
return wgProxy, nil
}

View File

@@ -6,8 +6,6 @@ import (
"github.com/cenkalti/backoff/v4"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/netstate"
)
// ConnStatus represents the connection state as seen by the guard.
@@ -33,26 +31,20 @@ type connStatusFunc func() ConnStatus
// - Relayed connection disconnected
// - ICE candidate changes
type Guard struct {
log *log.Entry
isConnectedOnAllWay connStatusFunc
timeout time.Duration
srWatcher *SRWatcher
// netState gates reconnect attempts on OS-reported network availability;
// nil disables gating.
netState *netstate.State
log *log.Entry
isConnectedOnAllWay connStatusFunc
timeout time.Duration
srWatcher *SRWatcher
relayedConnDisconnected chan struct{}
iCEConnDisconnected chan struct{}
}
// NewGuard creates a reconnection guard for a peer connection. A nil netState
// disables network availability gating.
func NewGuard(log *log.Entry, isConnectedFn connStatusFunc, timeout time.Duration, srWatcher *SRWatcher, netState *netstate.State) *Guard {
func NewGuard(log *log.Entry, isConnectedFn connStatusFunc, timeout time.Duration, srWatcher *SRWatcher) *Guard {
return &Guard{
log: log,
isConnectedOnAllWay: isConnectedFn,
timeout: timeout,
srWatcher: srWatcher,
netState: netState,
relayedConnDisconnected: make(chan struct{}, 1),
iCEConnDisconnected: make(chan struct{}, 1),
}
@@ -104,16 +96,9 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) {
iceState := &iceRetryState{log: g.log}
defer iceState.reset()
netChanged := g.netState.Changed()
for {
select {
case <-tickerChannel:
// skip attempts while the OS reports no usable network; the
// netChanged case below resumes the loop once it returns
if !g.netState.IsOnline() {
continue
}
switch g.isConnectedOnAllWay() {
case ConnStatusConnected:
// all good, nothing to do
@@ -150,23 +135,6 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) {
tickerChannel = ticker.C
iceState.reset()
case <-netChanged:
// Re-arm for the next transition before acting on this one.
netChanged = g.netState.Changed()
if !g.netState.IsOnline() {
continue
}
// Ticks skipped while offline drove the backoff towards its
// maximum without ever attempting, and left the ICE budget
// frozen — possibly in hourly mode. Recover on our own so the
// peer does not depend on a signal or relay event that never
// comes when both stayed up across the outage.
g.log.Debugf("network is back, reset reconnection ticker")
ticker.Stop()
ticker = g.newReconnectTicker(ctx)
tickerChannel = ticker.C
iceState.reset()
case <-ctx.Done():
g.log.Debugf("context is done, stop reconnect loop")
return

View File

@@ -15,7 +15,7 @@ import (
func newTestGuard(status connStatusFunc) *Guard {
srw := NewSRWatcher(nil, nil, nil, ice.Config{})
return NewGuard(log.WithField("test", "guard"), status, 50*time.Millisecond, srw, nil)
return NewGuard(log.WithField("test", "guard"), status, 50*time.Millisecond, srw)
}
// countBackoffTickerGoroutines returns how many goroutines are currently sitting

View File

@@ -1,107 +0,0 @@
package guard
import (
"context"
"sync/atomic"
"testing"
"time"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/internal/peer/ice"
"github.com/netbirdio/netbird/client/netstate"
)
// newTestGuardWithNetState builds a guard with a realistic MaxInterval: the
// backoff must be able to grow well past the outage, as it does in production
// where the timeout is seconds to minutes.
func newTestGuardWithNetState(status connStatusFunc, netState *netstate.State) *Guard {
srw := NewSRWatcher(nil, nil, nil, ice.Config{})
return NewGuard(log.WithField("test", "guard"), status, 30*time.Second, srw, netState)
}
// TestGuard_RecoversAfterOfflineToOnline covers a peer that stays disconnected
// across a network outage while neither signal nor relay reports an event —
// both stayed up, as on a short airplane mode toggle over Wi-Fi.
//
// Every tick taken while offline is skipped, but it still advances the
// exponential backoff, so by the time the network returns the next tick can be
// tens of seconds away. Without an explicit reaction to the transition the
// peer waits out that interval for a recovery that could start immediately.
func TestGuard_RecoversAfterOfflineToOnline(t *testing.T) {
netState := netstate.New()
var attempts atomic.Int32
g := newTestGuardWithNetState(func() ConnStatus { return ConnStatusDisconnected }, netState)
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
// Start from the reconnect ticker (800ms initial interval), the state a
// peer is in after it loses its connection.
go g.Start(ctx, func() { attempts.Add(1) })
g.SetRelayedConnDisconnected()
// Let the backoff climb: 0.8s, 1.6s, 3.2s, 6.4s ... every tick is skipped
// while offline, but each one doubles the wait for the next.
netState.Set(false)
time.Sleep(8 * time.Second)
offlineAttempts := attempts.Load()
if offlineAttempts != 0 {
t.Fatalf("callback ran %d times while offline, want 0", offlineAttempts)
}
netState.Set(true)
// The next organic tick is now several seconds out, so anything within
// this window can only come from reacting to the transition itself.
pollCtx, stopPolling := context.WithTimeout(ctx, 2*time.Second)
defer stopPolling()
select {
case <-pollCtx.Done():
t.Fatal("peer was not retried within 2s of the network coming back, " +
"with neither a signal nor a relay event to fall back on")
case <-pollUntil(pollCtx, func() bool { return attempts.Load() > 0 }):
}
}
// TestGuard_OfflineTransitionDoesNotRetry checks the other direction: going
// offline must not itself trigger an attempt.
func TestGuard_OfflineTransitionDoesNotRetry(t *testing.T) {
netState := netstate.New()
var attempts atomic.Int32
g := newTestGuardWithNetState(func() ConnStatus { return ConnStatusDisconnected }, netState)
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go g.Start(ctx, func() { attempts.Add(1) })
netState.Set(false)
time.Sleep(5 * time.Second)
if got := attempts.Load(); got != 0 {
t.Fatalf("callback ran %d times after going offline, want 0", got)
}
}
// pollUntil closes the returned channel once cond holds. It gives up when ctx
// is done, so the polling goroutine never outlives the test that started it.
func pollUntil(ctx context.Context, cond func() bool) <-chan struct{} {
done := make(chan struct{})
go func() {
for {
if cond() {
close(done)
return
}
select {
case <-ctx.Done():
return
case <-time.After(10 * time.Millisecond):
}
}
}()
return done
}

View File

@@ -1,40 +1,11 @@
package peer
// ClientState identifies the client connection state delivered via
// Listener.OnStateChanged.
type ClientState int
// Client states. The numeric values cross the gomobile boundary (the mobile
// bindings re-export them as integer constants), so they are a wire format:
// append new states at the end, never reorder or insert.
const (
ClientStateDisconnected ClientState = iota
ClientStateConnected
ClientStateConnecting
ClientStateDisconnecting
// ClientStateNoNetwork is an overlay state: it is never stored as the
// last notification, only derived from ClientStateConnecting while the
// OS reports no usable network (see notifier.effectiveState).
ClientStateNoNetwork
)
// Listener is a callback type about the NetBird network connection state
type Listener interface {
// OnStateChanged reports every client state transition. New states are
// delivered only through this callback; the per-state callbacks below
// are kept for compatibility and will be removed once all consumers
// have migrated.
OnStateChanged(state ClientState)
// Deprecated: consume OnStateChanged instead.
OnConnected()
// Deprecated: consume OnStateChanged instead.
OnDisconnected()
// Deprecated: consume OnStateChanged instead.
OnConnecting()
// Deprecated: consume OnStateChanged instead.
OnDisconnecting()
OnAddressChanged(string, string)
OnPeersListChanged(int)
}

View File

@@ -4,64 +4,31 @@ import (
"sync"
)
const (
stateDisconnected = iota
stateConnected
stateConnecting
stateDisconnecting
)
type notifier struct {
// publishLock orders state publication: it is held across computing the
// effective state and handing it to the listener, so a transition cannot
// overtake a newer one and leave the listener on a stale state.
publishLock sync.Mutex
serverStateLock sync.Mutex
listenersLock sync.Mutex
listener Listener
currentClientState bool
lastNotification ClientState
lastNotification int
lastNumberOfPeers int
lastFqdnAddress string
lastIPAddress string
networkAvailable bool
}
func newNotifier() *notifier {
return &notifier{
networkAvailable: true,
}
}
// effectiveState maps the computed state to what listeners should see:
// while the OS reports no usable network, "Connecting" would be a lie —
// connection attempts are suspended — so it is reported as NoNetwork.
// Caller must hold serverStateLock.
func (n *notifier) effectiveState(state ClientState) ClientState {
if !n.networkAvailable && state == ClientStateConnecting {
return ClientStateNoNetwork
}
return state
}
// setNetworkAvailable records the OS network availability and re-notifies
// the listener when the flag flips the effective state (Connecting <->
// NoNetwork).
func (n *notifier) setNetworkAvailable(available bool) {
n.publishLock.Lock()
defer n.publishLock.Unlock()
n.serverStateLock.Lock()
if n.networkAvailable == available {
n.serverStateLock.Unlock()
return
}
previous := n.effectiveState(n.lastNotification)
n.networkAvailable = available
current := n.effectiveState(n.lastNotification)
n.serverStateLock.Unlock()
if previous != current {
n.notify(current)
}
return &notifier{}
}
func (n *notifier) setListener(listener Listener) {
n.serverStateLock.Lock()
lastNotification := n.effectiveState(n.lastNotification)
lastNotification := n.lastNotification
numOfPeers := n.lastNumberOfPeers
fqdnAddress := n.lastFqdnAddress
address := n.lastIPAddress
@@ -85,9 +52,6 @@ func (n *notifier) removeListener() {
}
func (n *notifier) updateServerStates(mgmState bool, signalState bool) {
n.publishLock.Lock()
defer n.publishLock.Unlock()
n.serverStateLock.Lock()
calculatedState := n.calculateState(mgmState, signalState)
@@ -97,54 +61,43 @@ func (n *notifier) updateServerStates(mgmState bool, signalState bool) {
}
n.lastNotification = calculatedState
effective := n.effectiveState(calculatedState)
n.serverStateLock.Unlock()
n.notify(effective)
n.notify(calculatedState)
}
func (n *notifier) clientStart() {
n.publishLock.Lock()
defer n.publishLock.Unlock()
n.serverStateLock.Lock()
n.currentClientState = true
n.lastNotification = ClientStateConnecting
effective := n.effectiveState(ClientStateConnecting)
n.lastNotification = stateConnecting
n.serverStateLock.Unlock()
n.notify(effective)
n.notify(stateConnecting)
}
func (n *notifier) clientStop() {
n.publishLock.Lock()
defer n.publishLock.Unlock()
n.serverStateLock.Lock()
n.currentClientState = false
n.lastNotification = ClientStateDisconnected
n.lastNotification = stateDisconnected
n.serverStateLock.Unlock()
n.notify(ClientStateDisconnected)
n.notify(stateDisconnected)
}
func (n *notifier) clientTearDown() {
n.publishLock.Lock()
defer n.publishLock.Unlock()
n.serverStateLock.Lock()
n.currentClientState = false
n.lastNotification = ClientStateDisconnecting
n.lastNotification = stateDisconnecting
n.serverStateLock.Unlock()
n.notify(ClientStateDisconnecting)
n.notify(stateDisconnecting)
}
func (n *notifier) isServerStateChanged(newState ClientState) bool {
func (n *notifier) isServerStateChanged(newState int) bool {
return n.lastNotification != newState
}
func (n *notifier) notify(state ClientState) {
func (n *notifier) notify(state int) {
n.listenersLock.Lock()
listener := n.listener
n.listenersLock.Unlock()
@@ -156,20 +109,20 @@ func (n *notifier) notify(state ClientState) {
notifyListener(listener, state)
}
func (n *notifier) calculateState(managementConn, signalConn bool) ClientState {
func (n *notifier) calculateState(managementConn, signalConn bool) int {
if managementConn && signalConn {
return ClientStateConnected
return stateConnected
}
if !managementConn && !signalConn && !n.currentClientState {
return ClientStateDisconnected
return stateDisconnected
}
if n.lastNotification == ClientStateDisconnecting {
return ClientStateDisconnecting
if n.lastNotification == stateDisconnecting {
return stateDisconnecting
}
return ClientStateConnecting
return stateConnecting
}
func (n *notifier) peerListChanged(numOfPeers int) {
@@ -206,19 +159,15 @@ func (n *notifier) localAddressChanged(fqdn, address string) {
listener.OnAddressChanged(fqdn, address)
}
func notifyListener(l Listener, state ClientState) {
// legacy per-state callbacks; NoNetwork is delivered only via
// OnStateChanged below
func notifyListener(l Listener, state int) {
switch state {
case ClientStateDisconnected:
case stateDisconnected:
l.OnDisconnected()
case ClientStateConnected:
case stateConnected:
l.OnConnected()
case ClientStateConnecting:
case stateConnecting:
l.OnConnecting()
case ClientStateDisconnecting:
case stateDisconnecting:
l.OnDisconnecting()
}
l.OnStateChanged(state)
}

View File

@@ -1,108 +0,0 @@
package peer
import (
"sync"
"testing"
"time"
)
type recordingListener struct {
mu sync.Mutex
states []ClientState
onState func(ClientState)
}
func (l *recordingListener) OnStateChanged(state ClientState) {
l.mu.Lock()
l.states = append(l.states, state)
hook := l.onState
l.mu.Unlock()
if hook != nil {
hook(state)
}
}
func (l *recordingListener) last() (ClientState, bool) {
l.mu.Lock()
defer l.mu.Unlock()
if len(l.states) == 0 {
return 0, false
}
return l.states[len(l.states)-1], true
}
func (l *recordingListener) snapshot() []ClientState {
l.mu.Lock()
defer l.mu.Unlock()
return append([]ClientState(nil), l.states...)
}
func (l *recordingListener) OnConnected() {}
func (l *recordingListener) OnDisconnected() {}
func (l *recordingListener) OnConnecting() {}
func (l *recordingListener) OnDisconnecting() {}
func (l *recordingListener) OnAddressChanged(string, string) {}
func (l *recordingListener) OnPeersListChanged(int) {}
// TestNotifier_ConcurrentAvailabilityFlipOrdersPublication holds the first
// transition inside the listener callback and flips availability again from
// another goroutine while it is parked. The second flip must not publish
// ahead of the one in flight, otherwise the listener ends up on a state the
// notifier already superseded.
func TestNotifier_ConcurrentAvailabilityFlipOrdersPublication(t *testing.T) {
n := newNotifier()
n.currentClientState = true
n.lastNotification = ClientStateConnecting
entered := make(chan struct{})
release := make(chan struct{})
l := &recordingListener{}
l.onState = func(state ClientState) {
if state != ClientStateNoNetwork {
return
}
l.mu.Lock()
l.onState = nil
l.mu.Unlock()
close(entered)
<-release
}
n.listener = l
var wg sync.WaitGroup
wg.Add(1)
go func() {
defer wg.Done()
n.setNetworkAvailable(false)
}()
<-entered
flipped := make(chan struct{})
go func() {
defer close(flipped)
n.setNetworkAvailable(true)
}()
select {
case <-flipped:
t.Fatal("the online transition published while the offline one was " +
"still in flight; publication is not serialized")
case <-time.After(200 * time.Millisecond):
}
close(release)
<-flipped
wg.Wait()
got, ok := l.last()
if !ok {
t.Fatal("listener never observed a state")
}
if got != ClientStateConnecting {
t.Fatalf("listener holds %v after the network came back, want Connecting; sequence: %v",
got, l.snapshot())
}
}

View File

@@ -6,32 +6,29 @@ import (
)
type mocListener struct {
lastState ClientState
lastState int
wg sync.WaitGroup
peersWg sync.WaitGroup
peers int
}
func (l *mocListener) OnConnected() {
l.lastState = ClientStateConnected
l.lastState = stateConnected
l.wg.Done()
}
func (l *mocListener) OnDisconnected() {
l.lastState = ClientStateDisconnected
l.lastState = stateDisconnected
l.wg.Done()
}
func (l *mocListener) OnConnecting() {
l.lastState = ClientStateConnecting
l.lastState = stateConnecting
l.wg.Done()
}
func (l *mocListener) OnDisconnecting() {
l.lastState = ClientStateDisconnecting
l.lastState = stateDisconnecting
l.wg.Done()
}
func (l *mocListener) OnStateChanged(state ClientState) {
}
func (l *mocListener) OnAddressChanged(host, addr string) {
}
@@ -60,15 +57,15 @@ func Test_notifier_serverState(t *testing.T) {
type scenario struct {
name string
expected ClientState
expected int
mgmState bool
signalState bool
}
scenarios := []scenario{
{"connected", ClientStateConnected, true, true},
{"mgm down", ClientStateConnecting, false, true},
{"signal down", ClientStateConnecting, true, false},
{"disconnected", ClientStateDisconnected, false, false},
{"connected", stateConnected, true, true},
{"mgm down", stateConnecting, false, true},
{"signal down", stateConnecting, true, false},
{"disconnected", stateDisconnected, false, false},
}
for _, tt := range scenarios {
@@ -88,7 +85,7 @@ func Test_notifier_SetListener(t *testing.T) {
listener.setPeersWaiter()
n := newNotifier()
n.lastNotification = ClientStateConnecting
n.lastNotification = stateConnecting
n.setListener(listener)
listener.wait()
listener.waitPeers()
@@ -102,7 +99,7 @@ func Test_notifier_RemoveListener(t *testing.T) {
listener.setWaiter()
listener.setPeersWaiter()
n := newNotifier()
n.lastNotification = ClientStateConnecting
n.lastNotification = stateConnecting
n.setListener(listener)
// setListener replays cached state on a goroutine; wait for both the state
// and peers callbacks to finish so we don't race on listener.peers.

View File

@@ -1211,12 +1211,6 @@ func (d *Status) ClientTeardown() {
d.notifyStateChange()
}
// SetNetworkAvailable records the OS-reported network availability; while
// unavailable, listeners see NoNetwork instead of Connecting.
func (d *Status) SetNetworkAvailable(available bool) {
d.notifier.setNetworkAvailable(available)
}
// SetConnectionListener set a listener to the notifier
func (d *Status) SetConnectionListener(listener Listener) {
d.notifier.setListener(listener)

View File

@@ -255,8 +255,8 @@ func (w *WorkerICE) connect(ctx context.Context, agent *icemaker.ThreadSafeAgent
return
}
w.log.Debugf("agent dial")
remoteConn, err := w.agentDial(ctx, agent, remoteOfferAnswer)
w.log.Debugf("turn agent dial")
remoteConn, err := w.turnAgentDial(ctx, agent, remoteOfferAnswer)
if err != nil {
w.log.Debugf("failed to dial the remote peer: %s", err)
w.closeAgent(agent, w.agentDialerCancel)
@@ -517,8 +517,8 @@ func (w *WorkerICE) onConnectionStateChange(agent *icemaker.ThreadSafeAgent, dia
w.logSuccessfulPaths(agent)
return
case ice.ConnectionStateFailed, ice.ConnectionStateDisconnected, ice.ConnectionStateClosed:
// ice.ConnectionStateClosed happens when we recreate the agent. The P2P to relay switch requires
// notifying conn.onICEStateDisconnected so it can update the currently used priority.
// ice.ConnectionStateClosed happens when we recreate the agent. For the P2P to TURN switch important to
// notify the conn.onICEStateDisconnected changes to update the current used priority
sessionChanged := w.closeAgent(agent, dialerCancel)
@@ -532,7 +532,7 @@ func (w *WorkerICE) onConnectionStateChange(agent *icemaker.ThreadSafeAgent, dia
}
}
func (w *WorkerICE) agentDial(ctx context.Context, agent *icemaker.ThreadSafeAgent, remoteOfferAnswer *OfferAnswer) (*ice.Conn, error) {
func (w *WorkerICE) turnAgentDial(ctx context.Context, agent *icemaker.ThreadSafeAgent, remoteOfferAnswer *OfferAnswer) (*ice.Conn, error) {
if isController(w.config) {
return agent.Dial(ctx, remoteOfferAnswer.IceCredentials.UFrag, remoteOfferAnswer.IceCredentials.Pwd)
} else {

View File

@@ -18,8 +18,8 @@ type Service struct {
}
func New() (*Service, error) {
d, err := NewDetector() //nolint:staticcheck
if err != nil { //nolint:staticcheck // always errors on platforms without a sleep detector
d, err := NewDetector()
if err != nil {
return nil, err
}

View File

@@ -37,32 +37,23 @@
// Updater Process (Setup):
//
// 1. Receives parameters from service via command-line arguments
// 2. Terminates the UI so the installer does not have to replace a locked image
// file, which would otherwise leave the install needing a reboot
// 3. Runs installer with appropriate silent/quiet flags:
// 2. Runs installer with appropriate silent/quiet flags:
// - Windows EXE: installer.exe /S
// - Windows MSI: msiexec.exe /i installer.msi /qn /norestart REBOOT=ReallySuppress /l*v msi.log
// - Windows MSI: msiexec.exe /i installer.msi /quiet /qn /l*v msi.log
// - macOS PKG: installer -pkg installer.pkg -target /
// - macOS Homebrew: brew upgrade netbirdio/tap/netbird
// 4. Installer terminates the daemon
// 5. Installer replaces binaries with new version
// 6. Updater waits for installer to complete. On Windows, MSI exit codes 3010
// (ERROR_SUCCESS_REBOOT_REQUIRED) and 1641 (ERROR_SUCCESS_REBOOT_INITIATED)
// are a pending-reboot outcome, not a failure: the install succeeded, but
// some files are only replaced on the next restart (the reboot itself is
// suppressed via /norestart and REBOOT=ReallySuppress), and the flow
// continues as on success
// 7. Updater restarts daemon:
// 3. Installer terminates daemon and UI processes
// 4. Installer replaces binaries with new version
// 5. Updater waits for installer to complete
// 6. Updater restarts daemon:
// - Windows: netbird.exe service start
// - macOS/Linux: netbird service start
// 8. Updater restarts UI:
// - Windows: Launches netbird-ui.exe using CreateProcessAsUser in every
// session it was terminated in, falling back to the active console session
// 7. Updater restarts UI:
// - Windows: Launches netbird-ui.exe as active console user using CreateProcessAsUser
// - macOS: Uses launchctl asuser to launch NetBird.app for console user
// - Linux: Not implemented (UI typically auto-starts)
// 9. Updater writes result.json with success/error status (a pending reboot is
// recorded as success)
// 10. Updater process exits
// 8. Updater writes result.json with success/error status
// 9. Updater process exits
//
// # Result Communication
//

View File

@@ -42,9 +42,6 @@ func NewWithDir(tempDir string) *Installer {
// This will run by the original service process
func (u *Installer) RunInstallation(ctx context.Context, targetVersion string) (err error) {
resultHandler := NewResultHandler(u.tempDir)
if err := resultHandler.ClearStaleResult(); err != nil {
log.Warnf("clear stale installer result: %v", err)
}
defer func() {
if err != nil {

View File

@@ -2,7 +2,6 @@ package installer
import (
"context"
"errors"
"fmt"
"os"
"os/exec"
@@ -23,12 +22,6 @@ const (
msiLogFile = "msi.log"
// ERROR_SUCCESS_REBOOT_REQUIRED and ERROR_SUCCESS_REBOOT_INITIATED
msiRebootRequired = 3010
msiRebootInitiated = 1641
processExitWait = 10 * time.Second
msiDownloadURL = "https://github.com/netbirdio/netbird/releases/download/v%version/netbird_installer_%version_windows_%arch.msi"
exeDownloadURL = "https://github.com/netbirdio/netbird/releases/download/v%version/netbird_installer_%version_windows_%arch.exe"
)
@@ -45,8 +38,6 @@ var (
func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string, daemonFolder string) (resultErr error) {
resultHandler := NewResultHandler(u.tempDir)
var uiSessions []uint32
// Always ensure daemon and UI are restarted after setup
defer func() {
log.Infof("starting daemon back")
@@ -55,7 +46,7 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string
}
log.Infof("starting UI back")
if err := u.startUI(daemonFolder, uiSessions); err != nil {
if err := u.startUIAsUser(daemonFolder); err != nil {
log.Errorf("failed to start UI: %v", err)
}
@@ -84,14 +75,6 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string
return
}
// The UI holds an open handle on its own image. Left running, Restart Manager
// cannot shut it down (msiexec runs as LocalSystem here, the UI as the
// interactive user), so the MSI falls back to replacing the file on reboot and
// marks the install as restart-required. The deferred close-application action
// in the package runs too late to prevent that, it happens after
// InstallValidate has already registered the file as in use.
uiSessions = killUI()
var cmd *exec.Cmd
switch installerType {
case TypeExe:
@@ -101,9 +84,7 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string
installerDir := filepath.Dir(installerFile)
logPath := filepath.Join(installerDir, msiLogFile)
log.Infof("run msi installer: %s", installerFile)
// REBOOT=ReallySuppress: a silent install has no way to ask, so without it
// msiexec reboots the machine on its own if it decides one is needed.
cmd = exec.CommandContext(ctx, "msiexec.exe", "/i", filepath.Base(installerFile), "/qn", "/norestart", "REBOOT=ReallySuppress", "/l*v", logPath)
cmd = exec.CommandContext(ctx, "msiexec.exe", "/i", filepath.Base(installerFile), "/quiet", "/qn", "/l*v", logPath)
}
cmd.Dir = filepath.Dir(installerFile)
@@ -114,13 +95,9 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string
}
log.Infof("installer started with PID %d", cmd.Process.Pid)
if err := cmd.Wait(); err != nil {
if !isRebootPending(err) {
resultErr = err
log.Errorf("installer process finished with error: %v", err)
return
}
log.Warnf("installer completed but reported a pending reboot, some files will be replaced on the next restart")
if resultErr = cmd.Wait(); resultErr != nil {
log.Errorf("installer process finished with error: %v", resultErr)
return
}
return nil
@@ -140,142 +117,16 @@ func (u *Installer) startDaemon(daemonFolder string) error {
return nil
}
func (u *Installer) startUI(daemonFolder string, sessionIDs []uint32) error {
func (u *Installer) startUIAsUser(daemonFolder string) error {
uiPath := filepath.Join(daemonFolder, uiName)
log.Infof("starting netbird-ui: %s", uiPath)
if len(sessionIDs) == 0 {
sessionID := windows.WTSGetActiveConsoleSessionId()
if sessionID == 0xFFFFFFFF {
return fmt.Errorf("no active user session found")
}
sessionIDs = []uint32{sessionID}
// Get the active console session ID
sessionID := windows.WTSGetActiveConsoleSessionId()
if sessionID == 0xFFFFFFFF {
return fmt.Errorf("no active user session found")
}
var errs []error
for _, sessionID := range sessionIDs {
if err := startUIInSession(uiPath, sessionID); err != nil {
errs = append(errs, fmt.Errorf("session %d: %w", sessionID, err))
continue
}
log.Infof("netbird-ui started successfully in session %d", sessionID)
}
return errors.Join(errs...)
}
// isRebootPending reports whether the installer exit code means it succeeded but
// left work for the next restart. The reboot itself is suppressed, so this is not
// a failure.
func isRebootPending(err error) bool {
var exitErr *exec.ExitError
if !errors.As(err, &exitErr) {
return false
}
switch exitErr.ExitCode() {
case msiRebootRequired, msiRebootInitiated:
return true
default:
return false
}
}
// killUI terminates any running netbird-ui process and returns the IDs of the
// interactive sessions the terminated processes belonged to. Setup starts the
// UI again in those sessions once the installer is done.
func killUI() []uint32 {
pids, err := processIDsByName(uiName)
if err != nil {
log.Warnf("failed to look up %s processes: %v", uiName, err)
return nil
}
sessions := make(map[uint32]struct{})
for _, pid := range pids {
var sessionID uint32
if err := windows.ProcessIdToSessionId(pid, &sessionID); err != nil {
log.Warnf("failed to look up session of %s (PID %d): %v", uiName, pid, err)
}
if err := terminateProcess(pid); err != nil {
log.Warnf("failed to terminate %s (PID %d): %v", uiName, pid, err)
continue
}
log.Infof("terminated %s (PID %d) in session %d", uiName, pid, sessionID)
if sessionID != 0 {
sessions[sessionID] = struct{}{}
}
}
sessionIDs := make([]uint32, 0, len(sessions))
for sessionID := range sessions {
sessionIDs = append(sessionIDs, sessionID)
}
return sessionIDs
}
func processIDsByName(name string) ([]uint32, error) {
snapshot, err := windows.CreateToolhelp32Snapshot(windows.TH32CS_SNAPPROCESS, 0)
if err != nil {
return nil, fmt.Errorf("create process snapshot: %w", err)
}
defer func() {
if err := windows.CloseHandle(snapshot); err != nil {
log.Warnf("failed to close process snapshot: %v", err)
}
}()
var entry windows.ProcessEntry32
entry.Size = uint32(unsafe.Sizeof(entry))
var pids []uint32
for err = windows.Process32First(snapshot, &entry); err == nil; err = windows.Process32Next(snapshot, &entry) {
if strings.EqualFold(windows.UTF16ToString(entry.ExeFile[:]), name) {
pids = append(pids, entry.ProcessID)
}
}
if !errors.Is(err, windows.ERROR_NO_MORE_FILES) {
return nil, fmt.Errorf("enumerate processes: %w", err)
}
return pids, nil
}
func terminateProcess(pid uint32) error {
handle, err := windows.OpenProcess(windows.PROCESS_TERMINATE|windows.SYNCHRONIZE, false, pid)
if err != nil {
// The process may have exited between enumeration and now.
if errors.Is(err, windows.ERROR_INVALID_PARAMETER) {
return nil
}
return fmt.Errorf("open process: %w", err)
}
defer func() {
if err := windows.CloseHandle(handle); err != nil {
log.Warnf("failed to close process handle: %v", err)
}
}()
if err := windows.TerminateProcess(handle, 0); err != nil {
return fmt.Errorf("terminate process: %w", err)
}
// Wait for the handle to signal so the image file is released before the
// installer tries to overwrite it. A timeout is reported through the returned
// event, not through err, which stays nil unless the wait itself failed.
event, err := windows.WaitForSingleObject(handle, uint32(processExitWait.Milliseconds()))
if err != nil {
return fmt.Errorf("wait for process exit: %w", err)
}
if event != windows.WAIT_OBJECT_0 {
return fmt.Errorf("wait for process exit: unexpected wait result %#x", event)
}
return nil
}
func startUIInSession(uiPath string, sessionID uint32) error {
// Get the user token for that session
var userToken windows.Token
err := windows.WTSQueryUserToken(sessionID, &userToken)
@@ -307,16 +158,6 @@ func startUIInSession(uiPath string, sessionID uint32) error {
}
}()
var env *uint16
if err := windows.CreateEnvironmentBlock(&env, primaryToken, false); err != nil {
return fmt.Errorf("create environment block: %w", err)
}
defer func() {
if err := windows.DestroyEnvironmentBlock(env); err != nil {
log.Warnf("failed to destroy environment block: %v", err)
}
}()
// Prepare startup info
var si windows.StartupInfo
si.Cb = uint32(unsafe.Sizeof(si))
@@ -339,7 +180,7 @@ func startUIInSession(uiPath string, sessionID uint32) error {
nil,
false,
creationFlags,
env,
nil,
nil,
&si,
&pi,
@@ -356,6 +197,7 @@ func startUIInSession(uiPath string, sessionID uint32) error {
log.Warnf("failed to close thread handle: %v", err)
}
log.Infof("netbird-ui started successfully in session %d", sessionID)
return nil
}

View File

@@ -1,108 +0,0 @@
package installer
import (
"errors"
"os/exec"
"slices"
"strconv"
"testing"
)
// exitErrorWithCode returns a real *exec.ExitError carrying the given exit code.
func exitErrorWithCode(t *testing.T, code int) error {
t.Helper()
err := exec.Command("cmd.exe", "/c", "exit "+strconv.Itoa(code)).Run()
if err == nil {
t.Fatalf("expected a non-zero exit for code %d", code)
}
return err
}
func TestIsRebootPending(t *testing.T) {
tests := []struct {
name string
code int
want bool
}{
{name: "reboot required", code: msiRebootRequired, want: true},
{name: "reboot initiated", code: msiRebootInitiated, want: true},
{name: "generic failure", code: 1603, want: false},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
if got := isRebootPending(exitErrorWithCode(t, tt.code)); got != tt.want {
t.Errorf("isRebootPending(exit %d) = %v, want %v", tt.code, got, tt.want)
}
})
}
}
// TestProcessIDsByNameAndTerminate spawns a long-running system process, finds it
// by name and terminates it, covering the path the updater uses to release the UI
// image file before the installer replaces it.
func TestProcessIDsByNameAndTerminate(t *testing.T) {
cmd := exec.Command("ping.exe", "-n", "60", "127.0.0.1")
if err := cmd.Start(); err != nil {
t.Fatalf("start ping: %v", err)
}
pid := uint32(cmd.Process.Pid)
killed := false
t.Cleanup(func() {
if !killed {
_ = cmd.Process.Kill()
}
_ = cmd.Wait()
})
// Name matching must be case-insensitive: the snapshot reports PING.EXE.
pids, err := processIDsByName("ping.exe")
if err != nil {
t.Fatalf("processIDsByName: %v", err)
}
if !slices.Contains(pids, pid) {
t.Fatalf("PID %d not among the ping.exe processes found: %v", pid, pids)
}
if err := terminateProcess(pid); err != nil {
t.Fatalf("terminateProcess: %v", err)
}
killed = true
// terminateProcess only returns once the handle has signalled, so the process
// is already gone and Wait must not block. It exits with the code passed to
// TerminateProcess, which is 0, so Wait reports no error.
if err := cmd.Wait(); err != nil {
t.Fatalf("wait for terminated ping: %v", err)
}
if !cmd.ProcessState.Exited() {
t.Error("process did not exit after terminateProcess")
}
remaining, err := processIDsByName("ping.exe")
if err != nil {
t.Fatalf("processIDsByName after terminate: %v", err)
}
if slices.Contains(remaining, pid) {
t.Errorf("PID %d still listed after terminateProcess", pid)
}
}
func TestProcessIDsByNameNoMatch(t *testing.T) {
pids, err := processIDsByName("netbird-nonexistent-process.exe")
if err != nil {
t.Fatalf("processIDsByName: %v", err)
}
if len(pids) != 0 {
t.Errorf("expected no matches, got %v", pids)
}
}
func TestIsRebootPendingNonExitError(t *testing.T) {
if isRebootPending(errors.New("start installer: file not found")) {
t.Error("a non-exit error must not be treated as a pending reboot")
}
}

View File

@@ -54,12 +54,6 @@ func (rh *ResultHandler) GetErrorResultReason() string {
return ""
}
// ClearStaleResult removes a result file left over from a previous installation
// attempt so result watchers cannot read an outdated outcome for the current attempt.
func (rh *ResultHandler) ClearStaleResult() error {
return rh.cleanup()
}
func (rh *ResultHandler) WriteSuccess() error {
result := Result{
Success: true,

View File

@@ -435,7 +435,7 @@ func (m *Manager) install(ctx context.Context, pendingVersion *v.Version) error
}
inst := installer.New()
if err := inst.RunInstallation(ctx, pendingVersion.String()); err != nil { //nolint:staticcheck // always errors on platforms without an installer
if err := inst.RunInstallation(ctx, pendingVersion.String()); err != nil {
log.Errorf("error triggering update: %v", err)
m.statusRecorder.PublishEvent(
cProto.SystemEvent_ERROR,

View File

@@ -22,8 +22,6 @@ import (
"github.com/netbirdio/netbird/client/internal/listener"
"github.com/netbirdio/netbird/client/internal/peer"
"github.com/netbirdio/netbird/client/internal/profilemanager"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/client/netsweep"
"github.com/netbirdio/netbird/client/system"
"github.com/netbirdio/netbird/formatter"
"github.com/netbirdio/netbird/route"
@@ -38,6 +36,11 @@ const (
AnonymizeLevelStrict = nbAnonymize.LevelStrictString
)
// ConnectionListener export internal Listener for mobile
type ConnectionListener interface {
peer.Listener
}
// RouteListener export internal RouteListener for mobile
type NetworkChangeListener interface {
listener.NetworkChangeListener
@@ -84,12 +87,6 @@ type Client struct {
onHostDnsFn func([]string)
dnsManager dns.IosDnsManager
loginComplete bool
// netState outlives engine restarts: it mirrors the OS connectivity, not
// the engine lifecycle. Run injects it into each new ConnectClient, which
// distributes it to every reconnection loop.
netState *netstate.State
// sweeper also outlives engine restarts; NotifyNetworkChange sweeps it.
sweeper *netsweep.Sweeper
// preloadedConfig holds config loaded from JSON (used on tvOS where file writes are blocked)
preloadedConfig *profilemanager.Config
@@ -112,8 +109,6 @@ func NewClient(cfgFile, stateFile, cacheDir, logFilePath, deviceName string, osV
ctxCancelLock: &sync.Mutex{},
networkChangeListener: networkChangeListener,
dnsManager: dnsManager,
netState: netstate.New(),
sweeper: netsweep.New(),
}
}
@@ -189,8 +184,7 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
c.onHostDnsFn = func([]string) {}
cfg.WgIface = interfaceName
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
c.setState(cfg, connectClient)
// Persist the latest sync response so DebugBundle can include the network
// map. On iOS this is backed by disk to keep it out of the constrained
@@ -199,25 +193,6 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
return connectClient.RunOniOS(fd, c.networkChangeListener, c.dnsManager, c.stateFile, c.cacheDir, c.logFilePath)
}
// SetNetworkAvailable feeds OS-reported network availability into the client
// (e.g. from NWPathMonitor). While unavailable, the internal reconnect loops
// suspend their attempts and the connection listener reports NoNetwork
// instead of Connecting; when availability returns, the loops resume
// immediately with a fresh backoff.
func (c *Client) SetNetworkAvailable(available bool) {
c.netState.Set(available)
c.recorder.SetNetworkAvailable(available)
}
// NotifyNetworkChange marks the management, signal and relay connections
// stale after the OS switched networks and schedules a sweep that cuts
// whatever has not redialed on the new network by then. The engine and the
// TUN device stay untouched.
func (c *Client) NotifyNetworkChange() {
c.sweeper.MarkNetworkChange()
log.Infof("network change: connections marked stale")
}
// Stop the internal client and free the resources
func (c *Client) Stop() {
c.ctxCancelLock.Lock()
@@ -356,11 +331,7 @@ func (c *Client) GetStatusDetails() *StatusDetails {
// SetConnectionListener set the network connection listener
func (c *Client) SetConnectionListener(listener ConnectionListener) {
if listener == nil {
c.recorder.RemoveConnectionListener()
return
}
c.recorder.SetConnectionListener(connectionListenerAdapter{listener})
c.recorder.SetConnectionListener(listener)
}
// RemoveConnectionListener remove connection listener

View File

@@ -1,43 +0,0 @@
//go:build ios
package NetBirdSDK
import (
"github.com/netbirdio/netbird/client/internal/peer"
)
// Client state values, re-exported as basic constants so gomobile emits them
// into the generated bindings. They mirror peer.ClientState*: append-only,
// never reorder.
const (
ClientStateDisconnected = int(peer.ClientStateDisconnected)
ClientStateConnected = int(peer.ClientStateConnected)
ClientStateConnecting = int(peer.ClientStateConnecting)
ClientStateDisconnecting = int(peer.ClientStateDisconnecting)
ClientStateNoNetwork = int(peer.ClientStateNoNetwork)
)
// ConnectionListener export internal Listener for mobile.
//
// It intentionally lacks OnStateChanged for now: adding a method to a gomobile
// interface breaks every Swift implementation, so the iOS app keeps building
// against the legacy per-state callbacks. A follow-up will extend it together
// with the app.
type ConnectionListener interface {
OnConnected()
OnDisconnected()
OnConnecting()
OnDisconnecting()
OnAddressChanged(string, string)
OnPeersListChanged(int)
}
// connectionListenerAdapter adapts the gomobile-facing ConnectionListener to
// peer.Listener.
type connectionListenerAdapter struct {
ConnectionListener
}
// OnStateChanged is dropped on iOS until the app adopts the state callback;
// the legacy per-state callbacks continue to fire.
func (a connectionListenerAdapter) OnStateChanged(peer.ClientState) {}

View File

@@ -1,110 +0,0 @@
// Package netstate tracks OS-reported network availability for the client.
//
// A State instance is owned by the platform integration (e.g. the Android or
// iOS bindings, fed from ConnectivityManager callbacks or NWPathMonitor) and
// is injected into the connection retry loops (management, signal, relay,
// peer guards and the top-level connect loop), which consult it to avoid
// burning CPU and battery on reconnect attempts while the device has no
// network at all (e.g. airplane mode), and to reset their backoff as soon as
// the network returns.
//
// Consumers hold a *State that may be nil — every non-mobile platform leaves
// it unset. The read methods are safe on a nil receiver: they report online
// and never block, so consumers behave as if this package did not exist.
package netstate
import (
"context"
"sync"
log "github.com/sirupsen/logrus"
)
// State holds the OS-reported network availability. The zero value is not
// usable; create instances with New.
type State struct {
mu sync.Mutex
online bool
changed chan struct{}
}
// New creates a State that starts online. Platforms without network tracking
// pass a nil *State instead: the read methods treat nil as always online and
// never block, so consumers need no nil guards.
func New() *State {
return &State{
online: true,
changed: make(chan struct{}),
}
}
// Set records whether the OS reports any usable network. Transitions wake up
// all Wait callers immediately. Unlike the read methods, Set is not nil-safe:
// it is only for the platform owner that created the State with New.
func (s *State) Set(online bool) {
s.mu.Lock()
defer s.mu.Unlock()
if s.online == online {
return
}
s.online = online
close(s.changed)
s.changed = make(chan struct{})
log.Infof("OS network availability changed: online=%t", online)
}
// IsOnline reports whether the OS reports at least one usable network. On a
// nil receiver — no State injected — it reports online.
func (s *State) IsOnline() bool {
if s == nil {
return true
}
s.mu.Lock()
defer s.mu.Unlock()
return s.online
}
// Changed returns a channel closed on the next availability transition, for
// callers that already own a select loop and cannot block in Wait. Re-read it
// after every fire: each transition installs a fresh channel. On a nil
// receiver — no State injected — it returns nil, which blocks forever in a
// select, so the caller simply never observes a transition.
func (s *State) Changed() <-chan struct{} {
if s == nil {
return nil
}
s.mu.Lock()
defer s.mu.Unlock()
return s.changed
}
// Wait blocks while the network is offline. It reports whether it had to
// wait, so callers can reset their backoff after an outage. It returns early
// with the context error when ctx is done. On a nil receiver — no State
// injected — it returns immediately.
func (s *State) Wait(ctx context.Context) (bool, error) {
if s == nil {
return false, nil
}
waited := false
for {
s.mu.Lock()
if s.online {
s.mu.Unlock()
return waited, nil
}
ch := s.changed
s.mu.Unlock()
if !waited {
waited = true
log.Debugf("network is offline, pausing connection attempts")
}
select {
case <-ctx.Done():
return waited, ctx.Err()
case <-ch:
}
}
}

View File

@@ -1,170 +0,0 @@
package netstate
import (
"context"
"sync"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestNewStateIsOnline(t *testing.T) {
assert.True(t, New().IsOnline(), "a fresh State should start online")
}
func TestSetTogglesOnlineState(t *testing.T) {
s := New()
s.Set(false)
assert.False(t, s.IsOnline(), "state should be offline after Set(false)")
s.Set(true)
assert.True(t, s.IsOnline(), "state should be online after Set(true)")
}
func TestWaitReturnsImmediatelyWhenOnline(t *testing.T) {
s := New()
ctx, cancel := context.WithTimeout(context.Background(), time.Second)
defer cancel()
waited, err := s.Wait(ctx)
require.NoError(t, err)
assert.False(t, waited, "Wait should not block when the network is online")
}
func TestWaitBlocksUntilOnline(t *testing.T) {
s := New()
s.Set(false)
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
result := make(chan bool, 1)
go func() {
waited, err := s.Wait(ctx)
if err != nil {
result <- false
return
}
result <- waited
}()
// Verify Wait is actually blocking while offline
select {
case <-result:
t.Fatal("Wait should block while the network is offline")
case <-time.After(100 * time.Millisecond):
}
s.Set(true)
select {
case waited := <-result:
assert.True(t, waited, "Wait should report that it had to wait for the network")
case <-time.After(2 * time.Second):
t.Fatal("Wait should return promptly after the network becomes available")
}
}
func TestWaitReturnsOnContextCancel(t *testing.T) {
s := New()
s.Set(false)
ctx, cancel := context.WithCancel(context.Background())
result := make(chan error, 1)
go func() {
_, err := s.Wait(ctx)
result <- err
}()
cancel()
select {
case err := <-result:
assert.ErrorIs(t, err, context.Canceled)
case <-time.After(2 * time.Second):
t.Fatal("Wait should return promptly after context cancellation")
}
}
func TestWaitWakesAllWaiters(t *testing.T) {
s := New()
s.Set(false)
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
const waiters = 10
var wg sync.WaitGroup
results := make(chan bool, waiters)
for i := 0; i < waiters; i++ {
wg.Add(1)
go func() {
defer wg.Done()
waited, err := s.Wait(ctx)
if err != nil {
results <- false
return
}
results <- waited
}()
}
time.Sleep(100 * time.Millisecond)
s.Set(true)
wg.Wait()
close(results)
count := 0
for waited := range results {
assert.True(t, waited, "every waiter should report that it waited")
count++
}
assert.Equal(t, waiters, count, "all waiters should have returned")
}
func TestNilStateReadsAreNoops(t *testing.T) {
var s *State
assert.True(t, s.IsOnline(), "nil State should report online")
waited, err := s.Wait(context.Background())
require.NoError(t, err)
assert.False(t, waited, "nil State's Wait should not block")
}
func TestConcurrentSetAndWait(t *testing.T) {
s := New()
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
var wg sync.WaitGroup
for i := 0; i < 4; i++ {
wg.Add(1)
go func() {
defer wg.Done()
for j := 0; j < 100; j++ {
s.Set(j%2 == 0)
s.IsOnline()
}
}()
}
for i := 0; i < 4; i++ {
wg.Add(1)
go func() {
defer wg.Done()
for j := 0; j < 100; j++ {
if _, err := s.Wait(ctx); err != nil {
return
}
}
}()
}
wg.Wait()
}

View File

@@ -1,267 +0,0 @@
// Package netsweep cuts network-bound activity when the OS switches networks:
// a sweep closes the registered connections and aborts the in-flight dials, so
// their owners redial immediately instead of waiting for the old sockets to
// time out.
//
// A nil *Sweeper disables everything: all methods are nil-safe no-ops.
package netsweep
import (
"context"
"errors"
"net"
"sync"
"time"
"github.com/cenkalti/backoff/v4"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/netstate"
)
// DefaultSweepDelay absorbs network flapping while the OS settles on a
// default network before the stale registrations are cut.
const DefaultSweepDelay = 500 * time.Millisecond
const recentMarkWindow = 3 * time.Second
// Config customizes a Sweeper. The zero value applies the defaults.
type Config struct {
// SweepDelay overrides DefaultSweepDelay when positive.
SweepDelay time.Duration
}
// ErrSwept reports that a dial finished after a network change swept its
// registration. The connection is already closed; the caller must treat it
// as a failed dial and redial on the new network.
var ErrSwept = errors.New("netsweep: connection swept by network change")
// sweepID identifies one registration in a sweeper. Connections and dials
// draw from the same counter, so an id is unique across both registries.
type sweepID uint64
type connEntry struct {
conn net.Conn
gen uint64
}
// Dial tracks one dial from start to connection registration. It hands the
// dialed connection to the sweeper atomically, so a sweep can never fall
// between the dial finishing and the connection being registered.
type Dial struct {
sweeper *Sweeper
ctx context.Context
cancel context.CancelFunc
id sweepID
done bool // set by a sweep, WrapConn or Release; guarded by sweeper.mu
gen uint64
}
// Ctx returns the dial's context. A sweep cancels it, so a dial started on the
// old network aborts instead of waiting out its handshake timeout.
func (d *Dial) Ctx() context.Context {
return d.ctx
}
// Release ends the dial's registration and cancels its context. It is
// idempotent and safe after WrapConn, so callers can defer it.
func (d *Dial) Release() {
s := d.sweeper
if s == nil {
return
}
s.mu.Lock()
d.done = true
delete(s.dials, d.id)
s.mu.Unlock()
d.cancel()
}
// sweptConn deregisters itself from the sweeper when closed.
type sweptConn struct {
net.Conn
sweeper *Sweeper
id sweepID
}
func (c *sweptConn) Close() error {
c.sweeper.deregister(c.id)
return c.Conn.Close()
}
// Sweeper registers live connections and in-flight dials so the
// network-change sweep can cut everything registered before the change.
type Sweeper struct {
mu sync.Mutex
conns map[sweepID]connEntry
dials map[sweepID]*Dial
nextID sweepID
gen uint64
timer *time.Timer
sweepDelay time.Duration
lastMark time.Time
}
// New creates an empty sweeper with the default configuration.
func New() *Sweeper {
return NewWithConfig(Config{})
}
// NewWithConfig creates an empty sweeper customized by cfg.
func NewWithConfig(cfg Config) *Sweeper {
delay := cfg.SweepDelay
if delay <= 0 {
delay = DefaultSweepDelay
}
return &Sweeper{
conns: make(map[sweepID]connEntry),
dials: make(map[sweepID]*Dial),
sweepDelay: delay,
}
}
// StartDial registers an in-flight dial. Dial with Ctx, hand the result to
// WrapConn, and Release the dial when the attempt is over, typically deferred.
func (s *Sweeper) StartDial(ctx context.Context) *Dial {
if s == nil {
return &Dial{ctx: ctx}
}
ctx, cancel := context.WithCancel(ctx)
d := &Dial{sweeper: s, ctx: ctx, cancel: cancel}
s.mu.Lock()
d.id = s.nextID
s.nextID++
d.gen = s.gen
s.dials[d.id] = d
s.mu.Unlock()
return d
}
// WrapConn hands conn over to the sweeper. If a sweep ran since StartDial,
// the connection belongs to the old network: it is closed and ErrSwept is
// returned. Otherwise conn is registered against the next sweep and returned
// wrapped, deregistering itself on Close. Call it once, before Release.
func (d *Dial) WrapConn(conn net.Conn) (net.Conn, error) {
s := d.sweeper
if s == nil {
return conn, nil
}
s.mu.Lock()
if d.done {
s.mu.Unlock()
if err := conn.Close(); err != nil {
log.Debugf("swept dial close error: %v", err)
}
return nil, ErrSwept
}
d.done = true
delete(s.dials, d.id)
id := s.nextID
s.nextID++
// The conn inherits the dial's generation: the socket was bound to the
// network that was default when the dial started, not when it finished.
s.conns[id] = connEntry{conn: conn, gen: d.gen}
s.mu.Unlock()
return &sweptConn{Conn: conn, sweeper: s, id: id}, nil
}
// MarkNetworkChange records that the OS switched networks: everything
// registered so far becomes stale, and a sweep is (re)scheduled after the
// configured delay to cut whatever is still stale by then. Owners that
// redialed in the meantime hold fresh-generation registrations and survive,
// so no cancellation is needed around the sweep.
func (s *Sweeper) MarkNetworkChange() {
if s == nil {
return
}
s.mu.Lock()
s.gen++
cutoff := s.gen
s.lastMark = time.Now()
if s.timer != nil {
s.timer.Stop()
}
s.timer = time.AfterFunc(s.sweepDelay, func() {
n := s.sweep(cutoff)
log.Infof("network change sweep: closed %d stale connections", n)
})
s.mu.Unlock()
}
// QuickRetryBackoff wraps bo so that after each Reset the first retry comes
// quickly when the disconnect followed a recent network change and the
// network is online. Any other failure keeps bo's spread, so the clients of
// a restarted server still scatter their reconnects. A nil sweeper returns
// bo unchanged.
func (s *Sweeper) QuickRetryBackoff(ctx context.Context, bo backoff.BackOff, netState *netstate.State) backoff.BackOff {
if s == nil {
return bo
}
return backoff.WithContext(newQuickRetryBackoff(bo, s, netState), ctx)
}
func (s *Sweeper) markedRecently() bool {
if s == nil {
return false
}
s.mu.Lock()
defer s.mu.Unlock()
return !s.lastMark.IsZero() && time.Since(s.lastMark) < recentMarkWindow
}
// sweep closes the registered connections and aborts the in-flight dials
// older than cutoff, and returns how many connections it closed. A dial
// whose connection was not yet handed to WrapConn is marked, so the late
// WrapConn closes it instead of registering it.
func (s *Sweeper) sweep(cutoff uint64) int {
if s == nil {
return 0
}
s.mu.Lock()
var conns []net.Conn
for id, e := range s.conns {
if e.gen < cutoff {
delete(s.conns, id)
conns = append(conns, e.conn)
}
}
var dials []*Dial
for id, d := range s.dials {
if d.gen < cutoff {
d.done = true
delete(s.dials, id)
dials = append(dials, d)
}
}
s.mu.Unlock()
if len(dials) > 0 {
log.Debugf("aborting %d in-flight dials", len(dials))
for _, d := range dials {
d.cancel()
}
}
for _, conn := range conns {
log.Debugf("sweeping connection %s -> %s", conn.LocalAddr(), conn.RemoteAddr())
if err := conn.Close(); err != nil {
log.Debugf("swept connection close error: %v", err)
}
}
return len(conns)
}
func (s *Sweeper) deregister(id sweepID) {
s.mu.Lock()
delete(s.conns, id)
s.mu.Unlock()
}

View File

@@ -1,241 +0,0 @@
package netsweep
import (
"context"
"math"
"net"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestSweepClosesRegisteredConns(t *testing.T) {
sweeper := New()
c1 := wrap(t, sweeper, connPair(t))
c2 := wrap(t, sweeper, connPair(t))
assert.Equal(t, 2, sweeper.sweepAll(), "both live connections should be closed")
// The wrappers must report closed now.
buf := make([]byte, 1)
_, err := c1.Read(buf)
assert.Error(t, err, "first connection should be unusable after the sweep")
_, err = c2.Read(buf)
assert.Error(t, err, "second connection should be unusable after the sweep")
assert.Equal(t, 0, sweeper.sweepAll(), "second sweep should find nothing")
}
func TestCloseDeregisters(t *testing.T) {
sweeper := New()
conn := wrap(t, sweeper, connPair(t))
require.NoError(t, conn.Close())
assert.Equal(t, 0, sweeper.sweepAll(), "closed connection must leave the registry")
}
func TestCloseIsIdempotent(t *testing.T) {
sweeper := New()
conn := wrap(t, sweeper, connPair(t))
require.NoError(t, conn.Close())
assert.Error(t, conn.Close(), "double close surfaces the underlying error but must not panic")
}
func TestSweepOnlyAffectsOlderConns(t *testing.T) {
sweeper := New()
_ = wrap(t, sweeper, connPair(t))
assert.Equal(t, 1, sweeper.sweepAll())
// A connection dialed after the sweep must survive until the next one.
_ = wrap(t, sweeper, connPair(t))
assert.Equal(t, 1, sweeper.sweepAll(), "post-sweep connection belongs to the next sweep")
}
func TestSweepAbortsInFlightDials(t *testing.T) {
sweeper := New()
dial := sweeper.StartDial(context.Background())
defer dial.Release()
sweeper.sweepAll()
assert.ErrorIs(t, dial.Ctx().Err(), context.Canceled, "sweep must cancel the in-flight dial context")
}
func TestReleasedDialIsNotAborted(t *testing.T) {
sweeper := New()
// Simulate a dial that finished before the sweep.
released := sweeper.StartDial(context.Background())
released.Release()
// A dial still in flight during the sweep.
pending := sweeper.StartDial(context.Background())
defer pending.Release()
sweeper.sweepAll()
assert.ErrorIs(t, pending.Ctx().Err(), context.Canceled, "pending dial must be aborted")
}
func TestSweepBetweenDialAndHandoffClosesConn(t *testing.T) {
sweeper := New()
dial := sweeper.StartDial(context.Background())
defer dial.Release()
// The dial succeeds on the old network, then the sweep lands before the
// connection is handed over.
conn := connPair(t)
assert.Equal(t, 0, sweeper.sweepAll(), "the connection is not registered yet")
wrapped, err := dial.WrapConn(conn)
require.ErrorIs(t, err, ErrSwept)
require.Nil(t, wrapped)
buf := make([]byte, 1)
_, err = conn.Read(buf)
assert.Error(t, err, "the old-network connection must be closed, not leaked")
assert.Equal(t, 0, sweeper.sweepAll(), "nothing may leak into the next sweep")
}
func TestMarkNetworkChangeSparesFreshConns(t *testing.T) {
sweeper := NewWithConfig(Config{SweepDelay: 10 * time.Millisecond})
stale := wrap(t, sweeper, connPair(t))
sweeper.MarkNetworkChange()
_ = wrap(t, sweeper, connPair(t))
_ = stale.SetReadDeadline(time.Now().Add(time.Second))
buf := make([]byte, 1)
_, err := stale.Read(buf)
require.ErrorIs(t, err, net.ErrClosed, "stale connection must be closed by the delayed sweep")
assert.Equal(t, 1, sweeper.sweepAll(), "the fresh connection must survive the stale sweep")
}
func TestMarkNetworkChangeAbortsStaleDials(t *testing.T) {
sweeper := NewWithConfig(Config{SweepDelay: 10 * time.Millisecond})
stale := sweeper.StartDial(context.Background())
defer stale.Release()
sweeper.MarkNetworkChange()
fresh := sweeper.StartDial(context.Background())
defer fresh.Release()
assert.Eventually(t, func() bool {
return stale.Ctx().Err() != nil
}, time.Second, 5*time.Millisecond, "stale dial must be aborted by the delayed sweep")
assert.NoError(t, fresh.Ctx().Err(), "post-mark dial must not be aborted")
}
func TestConnInheritsDialGeneration(t *testing.T) {
sweeper := NewWithConfig(Config{SweepDelay: 20 * time.Millisecond})
// The dial starts before the network change but completes after it: the
// socket is bound to the old network, so the sweep must still cut it.
dial := sweeper.StartDial(context.Background())
defer dial.Release()
sweeper.MarkNetworkChange()
wrapped, err := dial.WrapConn(connPair(t))
require.NoError(t, err)
_ = wrapped.SetReadDeadline(time.Now().Add(time.Second))
buf := make([]byte, 1)
_, err = wrapped.Read(buf)
require.ErrorIs(t, err, net.ErrClosed, "old-generation connection must be swept")
}
func TestRepeatedMarksCoalesce(t *testing.T) {
sweeper := NewWithConfig(Config{SweepDelay: 20 * time.Millisecond})
first := wrap(t, sweeper, connPair(t))
sweeper.MarkNetworkChange()
second := wrap(t, sweeper, connPair(t))
sweeper.MarkNetworkChange()
_ = wrap(t, sweeper, connPair(t))
buf := make([]byte, 1)
for _, conn := range []net.Conn{first, second} {
_ = conn.SetReadDeadline(time.Now().Add(time.Second))
_, err := conn.Read(buf)
require.ErrorIs(t, err, net.ErrClosed, "every pre-mark connection must be swept by the rescheduled sweep")
}
assert.Equal(t, 1, sweeper.sweepAll(), "only the newest-generation connection may remain")
}
func TestNilSweeperIsNoop(t *testing.T) {
var sweeper *Sweeper
conn := connPair(t)
dial := sweeper.StartDial(context.Background())
defer dial.Release()
wrapped, err := dial.WrapConn(conn)
require.NoError(t, err)
assert.Equal(t, conn, wrapped, "nil sweeper must return the conn unchanged")
assert.NoError(t, dial.Ctx().Err(), "nil sweeper must not cancel the dial context")
assert.Equal(t, 0, sweeper.sweepAll(), "nil sweeper closes nothing")
}
// wrap registers conn with the sweeper through a completed dial.
func wrap(t *testing.T, sweeper *Sweeper, conn net.Conn) net.Conn {
t.Helper()
dial := sweeper.StartDial(context.Background())
defer dial.Release()
wrapped, err := dial.WrapConn(conn)
require.NoError(t, err)
return wrapped
}
// connPair dials a loopback TCP connection and keeps the accepted peer open
// until the test ends: a peer that closed early would make the connection
// unreadable on its own, so a read error after the sweep would prove nothing.
func connPair(t *testing.T) net.Conn {
t.Helper()
l, err := net.Listen("tcp", "127.0.0.1:0")
require.NoError(t, err)
t.Cleanup(func() {
if err := l.Close(); err != nil {
t.Logf("listener close error: %v", err)
}
})
accepted := make(chan net.Conn, 1)
go func() {
conn, err := l.Accept()
if err != nil {
close(accepted)
return
}
accepted <- conn
}()
conn, err := net.Dial("tcp", l.Addr().String())
require.NoError(t, err)
peer, ok := <-accepted
require.True(t, ok, "listener must accept the dialed connection")
t.Cleanup(func() {
if err := peer.Close(); err != nil {
t.Logf("peer close error: %v", err)
}
})
return conn
}
// sweepAll cuts every registration regardless of generation.
func (s *Sweeper) sweepAll() int {
return s.sweep(math.MaxUint64)
}

View File

@@ -1,39 +0,0 @@
package netsweep
import (
"time"
"github.com/cenkalti/backoff/v4"
"github.com/netbirdio/netbird/client/netstate"
)
const quickRetryDelay = 200 * time.Millisecond
type quickRetryBackoff struct {
backoff.BackOff
sweeper *Sweeper
netState *netstate.State
used bool
}
func newQuickRetryBackoff(bo backoff.BackOff, sweeper *Sweeper, netState *netstate.State) *quickRetryBackoff {
return &quickRetryBackoff{
BackOff: bo,
sweeper: sweeper,
netState: netState,
}
}
func (b *quickRetryBackoff) NextBackOff() time.Duration {
if !b.used && b.sweeper.markedRecently() && b.netState.IsOnline() {
b.used = true
return quickRetryDelay
}
return b.BackOff.NextBackOff()
}
func (b *quickRetryBackoff) Reset() {
b.used = false
b.BackOff.Reset()
}

View File

@@ -1,58 +0,0 @@
package netsweep
import (
"context"
"testing"
"time"
"github.com/cenkalti/backoff/v4"
"github.com/stretchr/testify/assert"
)
func TestQuickRetryAfterRecentMark(t *testing.T) {
sweeper := New()
sweeper.MarkNetworkChange()
slow := backoff.NewConstantBackOff(5 * time.Second)
bo := sweeper.QuickRetryBackoff(context.Background(), slow, nil)
assert.Equal(t, quickRetryDelay, bo.NextBackOff(), "first retry after a mark must be quick")
assert.Equal(t, 5*time.Second, bo.NextBackOff(), "second retry must fall back to the wrapped backoff")
bo.Reset()
assert.Equal(t, quickRetryDelay, bo.NextBackOff(), "reset must re-arm the quick retry")
}
func TestQuickRetryWithoutMarkKeepsSpread(t *testing.T) {
sweeper := New()
slow := backoff.NewConstantBackOff(5 * time.Second)
bo := sweeper.QuickRetryBackoff(context.Background(), slow, nil)
assert.Equal(t, 5*time.Second, bo.NextBackOff(), "without a mark the wrapped backoff decides")
sweeper.mu.Lock()
sweeper.lastMark = time.Now().Add(-recentMarkWindow)
sweeper.mu.Unlock()
assert.Equal(t, 5*time.Second, bo.NextBackOff(), "a stale mark must not trigger the quick retry")
}
func TestQuickRetryNilSweeperPassthrough(t *testing.T) {
var sweeper *Sweeper
slow := backoff.NewConstantBackOff(5 * time.Second)
bo := sweeper.QuickRetryBackoff(context.Background(), slow, nil)
assert.Equal(t, backoff.BackOff(slow), bo, "nil sweeper must return the backoff unchanged")
}
func TestQuickRetryHonorsContext(t *testing.T) {
sweeper := New()
sweeper.MarkNetworkChange()
ctx, cancel := context.WithCancel(context.Background())
cancel()
bo := sweeper.QuickRetryBackoff(ctx, backoff.NewConstantBackOff(time.Millisecond), nil)
assert.Equal(t, backoff.Stop, bo.NextBackOff(), "cancelled context must stop the retry loop")
}

View File

@@ -3,7 +3,6 @@
package server
import (
"errors"
"fmt"
"os"
"path"
@@ -70,7 +69,7 @@ func setStdHandle(f *os.File) error {
handle := f.Fd()
r0, _, e1 := setStdHandleFn.Call(stdErrorHandle, handle)
if r0 == 0 {
if !errors.Is(e1, syscall.Errno(0)) {
if e1 != nil {
return e1
}
return syscall.EINVAL

View File

@@ -10,7 +10,7 @@ import (
"testing"
"time"
"go.uber.org/mock/gomock"
"github.com/golang/mock/gomock"
"github.com/stretchr/testify/require"
"go.opentelemetry.io/otel"

View File

@@ -75,8 +75,8 @@ func (s *Server) createCommand(logger *log.Entry, privilegeResult PrivilegeCheck
}
// Try su first for system integration (PAM/audit) when privileged
cmd, err := s.createSuCommand(logger, session, localUser, hasPty) //nolint:staticcheck
if err != nil || privilegeResult.UsedFallback { //nolint:staticcheck // always errors on platforms without su
cmd, err := s.createSuCommand(logger, session, localUser, hasPty)
if err != nil || privilegeResult.UsedFallback {
logger.Debugf("su command failed, falling back to executor: %v", err)
cmd, cleanup, err := s.createExecutorCommand(logger, session, localUser, hasPty)
if err != nil {

View File

@@ -0,0 +1,24 @@
//go:build cgo && !osusergo && !windows
package server
import "os/user"
// lookupWithGetent with CGO delegates directly to os/user.Lookup.
// When CGO is enabled, os/user uses libc (getpwnam_r) which goes through
// the NSS stack natively. If it fails, the user truly doesn't exist and
// getent would also fail.
func lookupWithGetent(username string) (*user.User, error) {
return user.Lookup(username)
}
// currentUserWithGetent with CGO delegates directly to os/user.Current.
func currentUserWithGetent() (*user.User, error) {
return user.Current()
}
// groupIdsWithFallback with CGO delegates directly to user.GroupIds.
// libc's getgrouplist handles NSS groups natively.
func groupIdsWithFallback(u *user.User) ([]string, error) {
return u.GroupIds()
}

View File

@@ -0,0 +1,74 @@
//go:build (!cgo || osusergo) && !windows
package server
import (
"os"
"os/user"
"strconv"
log "github.com/sirupsen/logrus"
)
// lookupWithGetent looks up a user by name, falling back to getent if os/user fails.
// Without CGO, os/user only reads /etc/passwd and misses NSS-provided users.
// getent goes through the host's NSS stack.
func lookupWithGetent(username string) (*user.User, error) {
u, err := user.Lookup(username)
if err == nil {
return u, nil
}
stdErr := err
log.Debugf("os/user.Lookup(%q) failed, trying getent: %v", username, err)
u, _, getentErr := runGetent(username)
if getentErr != nil {
log.Debugf("getent fallback for %q also failed: %v", username, getentErr)
return nil, stdErr
}
return u, nil
}
// currentUserWithGetent gets the current user, falling back to getent if os/user fails.
func currentUserWithGetent() (*user.User, error) {
u, err := user.Current()
if err == nil {
return u, nil
}
stdErr := err
uid := strconv.Itoa(os.Getuid())
log.Debugf("os/user.Current() failed, trying getent with UID %s: %v", uid, err)
u, _, getentErr := runGetent(uid)
if getentErr != nil {
return nil, stdErr
}
return u, nil
}
// groupIdsWithFallback gets group IDs for a user via the id command first,
// falling back to user.GroupIds().
// NOTE: unlike lookupWithGetent/currentUserWithGetent which try stdlib first,
// this intentionally tries `id -G` first because without CGO, user.GroupIds()
// only reads /etc/group and silently returns incomplete results for NSS users
// (no error, just missing groups). The id command goes through NSS and returns
// the full set.
func groupIdsWithFallback(u *user.User) ([]string, error) {
ids, err := runIdGroups(u.Username)
if err == nil {
return ids, nil
}
log.Debugf("id -G %q failed, falling back to user.GroupIds(): %v", u.Username, err)
ids, stdErr := u.GroupIds()
if stdErr != nil {
return nil, stdErr
}
return ids, nil
}

View File

@@ -1,4 +1,4 @@
package getent
package server
import (
"os/user"
@@ -10,48 +10,38 @@ import (
"github.com/stretchr/testify/require"
)
func TestLookupUser_CurrentUser(t *testing.T) {
func TestLookupWithGetent_CurrentUser(t *testing.T) {
// The current user should always be resolvable on any platform
current, err := user.Current()
require.NoError(t, err)
u, err := LookupUser(current.Username)
u, err := lookupWithGetent(current.Username)
require.NoError(t, err)
assert.Equal(t, current.Username, u.Username)
assert.Equal(t, current.Uid, u.Uid)
assert.Equal(t, current.Gid, u.Gid)
}
func TestLookupUser_NonexistentUser(t *testing.T) {
_, err := LookupUser("nonexistent_user_xyzzy_12345")
func TestLookupWithGetent_NonexistentUser(t *testing.T) {
_, err := lookupWithGetent("nonexistent_user_xyzzy_12345")
require.Error(t, err, "should fail for nonexistent user")
}
func TestLookupUserID_CurrentUser(t *testing.T) {
current, err := user.Current()
require.NoError(t, err)
u, err := LookupUserID(current.Uid)
require.NoError(t, err)
assert.Equal(t, current.Username, u.Username)
assert.Equal(t, current.Uid, u.Uid)
}
func TestCurrentUser(t *testing.T) {
func TestCurrentUserWithGetent(t *testing.T) {
stdUser, err := user.Current()
require.NoError(t, err)
u, err := CurrentUser()
u, err := currentUserWithGetent()
require.NoError(t, err)
assert.Equal(t, stdUser.Uid, u.Uid)
assert.Equal(t, stdUser.Username, u.Username)
}
func TestGroupIDs_CurrentUser(t *testing.T) {
func TestGroupIdsWithFallback_CurrentUser(t *testing.T) {
current, err := user.Current()
require.NoError(t, err)
groups, err := GroupIDs(current)
groups, err := groupIdsWithFallback(current)
require.NoError(t, err)
require.NotEmpty(t, groups, "current user should have at least one group")
@@ -63,30 +53,32 @@ func TestGroupIDs_CurrentUser(t *testing.T) {
}
}
func TestUserShell_CurrentUser(t *testing.T) {
func TestGetShellFromGetent_CurrentUser(t *testing.T) {
if runtime.GOOS == "windows" {
// Windows stub always returns empty, which is correct
shell := getShellFromGetent("1000")
assert.Empty(t, shell, "Windows stub should return empty")
return
}
current, err := user.Current()
require.NoError(t, err)
// getent may not be available on all systems (e.g., macOS without
// Homebrew getent), and Windows has no login shells at all.
shell, err := UserShell(current.Uid)
if err != nil {
t.Logf("UserShell failed, getent may not be available: %v", err)
return
}
// getent may not be available on all systems (e.g., macOS without Homebrew getent)
shell := getShellFromGetent(current.Uid)
if shell == "" {
t.Log("UserShell returned empty, the user has no shell set")
t.Log("getShellFromGetent returned empty, getent may not be available")
return
}
assert.True(t, shell[0] == '/', "shell should be an absolute path, got %q", shell)
}
func TestLookupUser_RootUser(t *testing.T) {
func TestLookupWithGetent_RootUser(t *testing.T) {
if runtime.GOOS == "windows" {
t.Skip("no root user on Windows")
}
u, err := LookupUser("root")
u, err := lookupWithGetent("root")
if err != nil {
t.Skip("root user not available on this system")
}
@@ -94,25 +86,25 @@ func TestLookupUser_RootUser(t *testing.T) {
}
// TestIntegration_FullLookupChain exercises the complete user lookup chain
// against the real system, testing that all wrappers (LookupUser,
// CurrentUser, GroupIDs, UserShell) produce consistent and correct results
// when composed together.
// against the real system, testing that all wrappers (lookupWithGetent,
// currentUserWithGetent, groupIdsWithFallback, getShellFromGetent) produce
// consistent and correct results when composed together.
func TestIntegration_FullLookupChain(t *testing.T) {
// Step 1: CurrentUser must resolve the running user.
current, err := CurrentUser()
require.NoError(t, err, "CurrentUser must resolve the running user")
// Step 1: currentUserWithGetent must resolve the running user.
current, err := currentUserWithGetent()
require.NoError(t, err, "currentUserWithGetent must resolve the running user")
require.NotEmpty(t, current.Uid)
require.NotEmpty(t, current.Username)
// Step 2: LookupUser by the same username must return matching identity.
byName, err := LookupUser(current.Username)
// Step 2: lookupWithGetent by the same username must return matching identity.
byName, err := lookupWithGetent(current.Username)
require.NoError(t, err)
assert.Equal(t, current.Uid, byName.Uid, "lookup by name should return same UID")
assert.Equal(t, current.Gid, byName.Gid, "lookup by name should return same GID")
assert.Equal(t, current.HomeDir, byName.HomeDir, "lookup by name should return same home")
// Step 3: GroupIDs must return at least the primary GID.
groups, err := GroupIDs(current)
// Step 3: groupIdsWithFallback must return at least the primary GID.
groups, err := groupIdsWithFallback(current)
require.NoError(t, err)
require.NotEmpty(t, groups, "user must have at least one group")
@@ -127,20 +119,29 @@ func TestIntegration_FullLookupChain(t *testing.T) {
}
}
assert.True(t, foundPrimary, "primary GID %s should appear in supplementary groups", current.Gid)
// Step 4: getShellFromGetent should either return a valid shell path or empty
// (empty is OK when getent is not available, e.g. macOS without Homebrew getent).
if runtime.GOOS != "windows" {
shell := getShellFromGetent(current.Uid)
if shell != "" {
assert.True(t, shell[0] == '/', "shell should be an absolute path, got %q", shell)
}
}
}
// TestIntegration_LookupAndGroupsConsistency verifies that a user resolved via
// LookupUser can have their groups resolved via GroupIDs, testing the handoff
// between the two functions as used by the SSH server.
// lookupWithGetent can have their groups resolved via groupIdsWithFallback,
// testing the handoff between the two functions as used by the SSH server.
func TestIntegration_LookupAndGroupsConsistency(t *testing.T) {
current, err := user.Current()
require.NoError(t, err)
// Simulate the SSH server flow: lookup user, then get their groups.
resolved, err := LookupUser(current.Username)
resolved, err := lookupWithGetent(current.Username)
require.NoError(t, err)
groups, err := GroupIDs(resolved)
groups, err := groupIdsWithFallback(resolved)
require.NoError(t, err)
require.NotEmpty(t, groups, "resolved user must have groups")
@@ -153,3 +154,19 @@ func TestIntegration_LookupAndGroupsConsistency(t *testing.T) {
}
}
}
// TestIntegration_ShellLookupChain tests the full shell resolution chain
// (getShellFromPasswd -> getShellFromGetent -> $SHELL -> default) on Unix.
func TestIntegration_ShellLookupChain(t *testing.T) {
if runtime.GOOS == "windows" {
t.Skip("Unix shell lookup not applicable on Windows")
}
current, err := user.Current()
require.NoError(t, err)
// getUserShell is the top-level function used by the SSH server.
shell := getUserShell(current.Uid)
require.NotEmpty(t, shell, "getUserShell must always return a shell")
assert.True(t, shell[0] == '/', "shell should be an absolute path, got %q", shell)
}

View File

@@ -0,0 +1,127 @@
//go:build !windows
package server
import (
"context"
"fmt"
"os/exec"
"os/user"
"runtime"
"strings"
"time"
)
const getentTimeout = 5 * time.Second
// getShellFromGetent gets a user's login shell via getent by UID.
// This is needed even with CGO because getShellFromPasswd reads /etc/passwd
// directly and won't find NSS-provided users there.
func getShellFromGetent(userID string) string {
_, shell, err := runGetent(userID)
if err != nil {
return ""
}
return shell
}
// runGetent executes `getent passwd <query>` and returns the user and login shell.
func runGetent(query string) (*user.User, string, error) {
if !validateGetentInput(query) {
return nil, "", fmt.Errorf("invalid getent input: %q", query)
}
ctx, cancel := context.WithTimeout(context.Background(), getentTimeout)
defer cancel()
out, err := exec.CommandContext(ctx, "getent", "passwd", query).Output()
if err != nil {
return nil, "", fmt.Errorf("getent passwd %s: %w", query, err)
}
return parseGetentPasswd(string(out))
}
// parseGetentPasswd parses getent passwd output: "name:x:uid:gid:gecos:home:shell"
func parseGetentPasswd(output string) (*user.User, string, error) {
fields := strings.SplitN(strings.TrimSpace(output), ":", 8)
if len(fields) < 6 {
return nil, "", fmt.Errorf("unexpected getent output (need 6+ fields): %q", output)
}
if fields[0] == "" || fields[2] == "" || fields[3] == "" {
return nil, "", fmt.Errorf("missing required fields in getent output: %q", output)
}
var shell string
if len(fields) >= 7 {
shell = fields[6]
}
return &user.User{
Username: fields[0],
Uid: fields[2],
Gid: fields[3],
Name: fields[4],
HomeDir: fields[5],
}, shell, nil
}
// validateGetentInput checks that the input is safe to pass to getent or id.
// Allows POSIX usernames, numeric UIDs, and common NSS extensions
// (@ for Kerberos, $ for Samba, + for NIS compat). A leading hyphen is
// rejected so the input can never be parsed as a command-line flag.
func validateGetentInput(input string) bool {
maxLen := 32
if runtime.GOOS == "linux" {
maxLen = 256
}
if len(input) == 0 || len(input) > maxLen {
return false
}
if input[0] == '-' {
return false
}
for _, r := range input {
if isAllowedGetentChar(r) {
continue
}
return false
}
return true
}
func isAllowedGetentChar(r rune) bool {
if r >= 'a' && r <= 'z' || r >= 'A' && r <= 'Z' || r >= '0' && r <= '9' {
return true
}
switch r {
case '.', '_', '-', '@', '+', '$':
return true
}
return false
}
// runIdGroups runs `id -G <username>` and returns the space-separated group IDs.
func runIdGroups(username string) ([]string, error) {
if !validateGetentInput(username) {
return nil, fmt.Errorf("invalid username for id command: %q", username)
}
ctx, cancel := context.WithTimeout(context.Background(), getentTimeout)
defer cancel()
out, err := exec.CommandContext(ctx, "id", "-G", username).Output()
if err != nil {
return nil, fmt.Errorf("id -G %s: %w", username, err)
}
trimmed := strings.TrimSpace(string(out))
if trimmed == "" {
return nil, fmt.Errorf("id -G %s: empty output", username)
}
return strings.Fields(trimmed), nil
}

View File

@@ -1,12 +1,10 @@
//go:build !windows
package getent
package server
import (
"os"
"os/exec"
"os/user"
"path/filepath"
"runtime"
"strconv"
"testing"
@@ -15,7 +13,7 @@ import (
"github.com/stretchr/testify/require"
)
func TestParsePasswd(t *testing.T) {
func TestParseGetentPasswd(t *testing.T) {
tests := []struct {
name string
input string
@@ -130,7 +128,7 @@ func TestParsePasswd(t *testing.T) {
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
u, shell, err := parsePasswd(tt.input)
u, shell, err := parseGetentPasswd(tt.input)
if tt.wantErr {
require.Error(t, err)
if tt.errContains != "" {
@@ -149,120 +147,7 @@ func TestParsePasswd(t *testing.T) {
}
}
func TestParseGroup(t *testing.T) {
tests := []struct {
name string
input string
wantGroup *user.Group
wantMembers []string
wantErr bool
}{
{
name: "no members",
input: "vma:x:1000:\n",
wantGroup: &user.Group{Name: "vma", Gid: "1000"},
},
{
name: "one member",
input: "sudo:x:27:alice",
wantGroup: &user.Group{Name: "sudo", Gid: "27"},
wantMembers: []string{"alice"},
},
{
name: "several members",
input: "docker:x:998:alice,bob\n",
wantGroup: &user.Group{Name: "docker", Gid: "998"},
wantMembers: []string{"alice", "bob"},
},
{
name: "too few fields",
input: "bad:x",
wantErr: true,
},
{
name: "empty group name",
input: ":x:1000:alice",
wantErr: true,
},
{
name: "empty GID",
input: "vma:x::alice",
wantErr: true,
},
{
name: "empty input",
input: "",
wantErr: true,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
g, members, err := parseGroup(tt.input)
if tt.wantErr {
require.Error(t, err)
return
}
require.NoError(t, err)
assert.Equal(t, tt.wantGroup.Name, g.Name, "group name")
assert.Equal(t, tt.wantGroup.Gid, g.Gid, "GID")
assert.Equal(t, tt.wantMembers, members, "members")
})
}
}
func TestGroupMembersFromFile(t *testing.T) {
tests := []struct {
name string
entry string
want []string
}{
{name: "no members", entry: "vma:x:1000:"},
{name: "only the owner", entry: "vma:x:1000:vma", want: []string{"vma"}},
{name: "two members", entry: "vma:x:1000:vma,bob", want: []string{"vma", "bob"}},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
path := filepath.Join(t.TempDir(), "group")
body := "root:x:0:\n" + tt.entry + "\nsudo:x:27:vma\n"
require.NoError(t, os.WriteFile(path, []byte(body), 0o644), "write the group file")
members, err := groupMembersFromFile(path, "vma")
require.NoError(t, err, "entry %q", tt.entry)
assert.Equal(t, tt.want, members, "entry %q", tt.entry)
})
}
}
// A group the file does not describe, because it comes from LDAP or another
// NSS source, is an error rather than an empty member list: the caller must
// be able to tell "no members" from "no answer".
func TestGroupMembersFromFileUnknownGroup(t *testing.T) {
path := filepath.Join(t.TempDir(), "group")
require.NoError(t, os.WriteFile(path, []byte("root:x:0:\n"), 0o644), "write the group file")
_, err := groupMembersFromFile(path, "vma")
assert.Error(t, err, "a group the file does not describe")
_, err = groupMembersFromFile(filepath.Join(t.TempDir(), "absent"), "vma")
assert.Error(t, err, "no group file at all")
}
// GroupMembers on the root group, which every Unix has, whichever source
// answers for it.
func TestGroupMembers_RootGroup(t *testing.T) {
rootGroup := "root"
switch runtime.GOOS {
case "darwin", "dragonfly", "freebsd", "netbsd", "openbsd":
rootGroup = "wheel"
}
_, err := GroupMembers(rootGroup)
assert.NoError(t, err, "the %s group must be describable", rootGroup)
}
func TestValidateInput(t *testing.T) {
func TestValidateGetentInput(t *testing.T) {
tests := []struct {
name string
input string
@@ -295,7 +180,7 @@ func TestValidateInput(t *testing.T) {
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
assert.Equal(t, tt.want, validateInput(tt.input))
assert.Equal(t, tt.want, validateGetentInput(tt.input))
})
}
}
@@ -308,12 +193,12 @@ func makeLongString(n int) string {
return string(b)
}
func TestPasswdLookup_RootUser(t *testing.T) {
func TestRunGetent_RootUser(t *testing.T) {
if _, err := exec.LookPath("getent"); err != nil {
t.Skip("getent not available on this system")
}
u, shell, err := passwdLookup("root")
u, shell, err := runGetent("root")
require.NoError(t, err)
assert.Equal(t, "root", u.Username)
assert.Equal(t, "0", u.Uid)
@@ -321,55 +206,44 @@ func TestPasswdLookup_RootUser(t *testing.T) {
assert.NotEmpty(t, shell, "root should have a shell")
}
func TestPasswdLookup_ByUID(t *testing.T) {
func TestRunGetent_ByUID(t *testing.T) {
if _, err := exec.LookPath("getent"); err != nil {
t.Skip("getent not available on this system")
}
u, _, err := passwdLookup("0")
u, _, err := runGetent("0")
require.NoError(t, err)
assert.Equal(t, "root", u.Username)
assert.Equal(t, "0", u.Uid)
}
func TestPasswdLookup_NonexistentUser(t *testing.T) {
func TestRunGetent_NonexistentUser(t *testing.T) {
if _, err := exec.LookPath("getent"); err != nil {
t.Skip("getent not available on this system")
}
_, _, err := passwdLookup("nonexistent_user_xyzzy_12345")
_, _, err := runGetent("nonexistent_user_xyzzy_12345")
assert.Error(t, err)
}
func TestPasswdLookup_InvalidInput(t *testing.T) {
_, _, err := passwdLookup("")
func TestRunGetent_InvalidInput(t *testing.T) {
_, _, err := runGetent("")
assert.Error(t, err)
_, _, err = passwdLookup("user\x00name")
_, _, err = runGetent("user\x00name")
assert.Error(t, err)
}
func TestPasswdLookup_NotAvailable(t *testing.T) {
func TestRunGetent_NotAvailable(t *testing.T) {
if _, err := exec.LookPath("getent"); err == nil {
t.Skip("getent is available, can't test missing case")
}
_, _, err := passwdLookup("root")
_, _, err := runGetent("root")
assert.Error(t, err, "should fail when getent is not installed")
}
func TestGroupLookup_RootGroup(t *testing.T) {
if _, err := exec.LookPath("getent"); err != nil {
t.Skip("getent not available on this system")
}
g, _, err := groupLookup("0")
require.NoError(t, err)
assert.Equal(t, "0", g.Gid, "GID 0 resolves to the root group")
assert.NotEmpty(t, g.Name, "the root group has a name")
}
func TestIdGroups_CurrentUser(t *testing.T) {
func TestRunIdGroups_CurrentUser(t *testing.T) {
if _, err := exec.LookPath("id"); err != nil {
t.Skip("id not available on this system")
}
@@ -377,7 +251,7 @@ func TestIdGroups_CurrentUser(t *testing.T) {
current, err := user.Current()
require.NoError(t, err)
groups, err := idGroups(current.Username)
groups, err := runIdGroups(current.Username)
require.NoError(t, err)
require.NotEmpty(t, groups, "current user should have at least one group")
@@ -387,20 +261,20 @@ func TestIdGroups_CurrentUser(t *testing.T) {
}
}
func TestIdGroups_NonexistentUser(t *testing.T) {
func TestRunIdGroups_NonexistentUser(t *testing.T) {
if _, err := exec.LookPath("id"); err != nil {
t.Skip("id not available on this system")
}
_, err := idGroups("nonexistent_user_xyzzy_12345")
_, err := runIdGroups("nonexistent_user_xyzzy_12345")
assert.Error(t, err)
}
func TestIdGroups_InvalidInput(t *testing.T) {
_, err := idGroups("")
func TestRunIdGroups_InvalidInput(t *testing.T) {
_, err := runIdGroups("")
assert.Error(t, err)
_, err = idGroups("user\x00name")
_, err = runIdGroups("user\x00name")
assert.Error(t, err)
}
@@ -412,7 +286,7 @@ func TestGetentResultsMatchStdlib(t *testing.T) {
current, err := user.Current()
require.NoError(t, err)
getentUser, _, err := passwdLookup(current.Username)
getentUser, _, err := runGetent(current.Username)
require.NoError(t, err)
assert.Equal(t, current.Username, getentUser.Username, "username should match")
@@ -429,7 +303,7 @@ func TestGetentResultsMatchStdlib_ByUID(t *testing.T) {
current, err := user.Current()
require.NoError(t, err)
getentUser, _, err := passwdLookup(current.Uid)
getentUser, _, err := runGetent(current.Uid)
require.NoError(t, err)
assert.Equal(t, current.Username, getentUser.Username, "username should match when looked up by UID")
@@ -449,12 +323,12 @@ func TestIdGroupsMatchStdlib(t *testing.T) {
t.Skip("os/user.GroupIds() not working, likely CGO_ENABLED=0")
}
idGroupIDs, err := idGroups(current.Username)
idGroups, err := runIdGroups(current.Username)
require.NoError(t, err)
// Deduplicate both lists: id -G can return duplicates (e.g., root in Docker)
// and ElementsMatch treats duplicates as distinct.
assert.ElementsMatch(t, uniqueStrings(stdGroups), uniqueStrings(idGroupIDs), "id -G should return same groups as os/user")
assert.ElementsMatch(t, uniqueStrings(stdGroups), uniqueStrings(idGroups), "id -G should return same groups as os/user")
}
func uniqueStrings(ss []string) []string {
@@ -469,3 +343,71 @@ func uniqueStrings(ss []string) []string {
}
return out
}
// TestGetShellFromPasswd_CurrentUser verifies that getShellFromPasswd correctly
// reads the current user's shell from /etc/passwd by comparing it against what
// getent reports (which goes through NSS).
func TestGetShellFromPasswd_CurrentUser(t *testing.T) {
current, err := user.Current()
require.NoError(t, err)
shell := getShellFromPasswd(current.Uid)
if shell == "" {
t.Skip("current user not found in /etc/passwd (may be an NSS-only user)")
}
assert.True(t, shell[0] == '/', "shell should be an absolute path, got %q", shell)
if _, err := exec.LookPath("getent"); err == nil {
_, getentShell, getentErr := runGetent(current.Uid)
if getentErr == nil && getentShell != "" {
assert.Equal(t, getentShell, shell, "shell from /etc/passwd should match getent")
}
}
}
// TestGetShellFromPasswd_RootUser verifies that getShellFromPasswd can read
// root's shell from /etc/passwd. Root is guaranteed to be in /etc/passwd on
// any standard Unix system.
func TestGetShellFromPasswd_RootUser(t *testing.T) {
shell := getShellFromPasswd("0")
require.NotEmpty(t, shell, "root (UID 0) must be in /etc/passwd")
assert.True(t, shell[0] == '/', "root shell should be an absolute path, got %q", shell)
}
// TestGetShellFromPasswd_NonexistentUID verifies that getShellFromPasswd
// returns empty for a UID that doesn't exist in /etc/passwd.
func TestGetShellFromPasswd_NonexistentUID(t *testing.T) {
shell := getShellFromPasswd("4294967294")
assert.Empty(t, shell, "nonexistent UID should return empty shell")
}
// TestGetShellFromPasswd_MatchesGetentForKnownUsers reads /etc/passwd directly
// and cross-validates every entry against getent to ensure parseGetentPasswd
// and getShellFromPasswd agree on shell values.
func TestGetShellFromPasswd_MatchesGetentForKnownUsers(t *testing.T) {
if _, err := exec.LookPath("getent"); err != nil {
t.Skip("getent not available")
}
// Pick a few well-known system UIDs that are virtually always in /etc/passwd.
uids := []string{"0"} // root
current, err := user.Current()
require.NoError(t, err)
uids = append(uids, current.Uid)
for _, uid := range uids {
passwdShell := getShellFromPasswd(uid)
if passwdShell == "" {
continue
}
_, getentShell, err := runGetent(uid)
if err != nil {
continue
}
assert.Equal(t, getentShell, passwdShell, "shell mismatch for UID %s", uid)
}
}

View File

@@ -0,0 +1,26 @@
//go:build windows
package server
import "os/user"
// lookupWithGetent on Windows just delegates to os/user.Lookup.
// Windows does not use NSS/getent; its user lookup works without CGO.
func lookupWithGetent(username string) (*user.User, error) {
return user.Lookup(username)
}
// currentUserWithGetent on Windows just delegates to os/user.Current.
func currentUserWithGetent() (*user.User, error) {
return user.Current()
}
// getShellFromGetent is a no-op on Windows; shell resolution uses PowerShell detection.
func getShellFromGetent(_ string) string {
return ""
}
// groupIdsWithFallback on Windows just delegates to u.GroupIds().
func groupIdsWithFallback(u *user.User) ([]string, error) {
return u.GroupIds()
}

View File

@@ -13,8 +13,6 @@ import (
"github.com/gliderlabs/ssh"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/internal/getent"
)
const (
@@ -58,11 +56,7 @@ func getUnixUserShell(userID string) string {
return shell
}
shell, err := getent.UserShell(userID)
if err != nil {
log.Debugf("look up the shell for uid %s through getent: %v", userID, err)
}
if shell != "" {
if shell := getShellFromGetent(userID); shell != "" {
return shell
}

View File

@@ -1,94 +0,0 @@
//go:build !windows
package server
import (
"os/exec"
"os/user"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/client/internal/getent"
)
// TestGetShellFromPasswd_CurrentUser verifies that getShellFromPasswd correctly
// reads the current user's shell from /etc/passwd by comparing it against what
// getent reports (which goes through NSS).
func TestGetShellFromPasswd_CurrentUser(t *testing.T) {
current, err := user.Current()
require.NoError(t, err)
shell := getShellFromPasswd(current.Uid)
if shell == "" {
t.Skip("current user not found in /etc/passwd (may be an NSS-only user)")
}
assert.True(t, shell[0] == '/', "shell should be an absolute path, got %q", shell)
if _, err := exec.LookPath("getent"); err == nil {
getentShell, getentErr := getent.UserShell(current.Uid)
if getentErr == nil && getentShell != "" {
assert.Equal(t, getentShell, shell, "shell from /etc/passwd should match getent")
}
}
}
// TestGetShellFromPasswd_RootUser verifies that getShellFromPasswd can read
// root's shell from /etc/passwd. Root is guaranteed to be in /etc/passwd on
// any standard Unix system.
func TestGetShellFromPasswd_RootUser(t *testing.T) {
shell := getShellFromPasswd("0")
require.NotEmpty(t, shell, "root (UID 0) must be in /etc/passwd")
assert.True(t, shell[0] == '/', "root shell should be an absolute path, got %q", shell)
}
// TestGetShellFromPasswd_NonexistentUID verifies that getShellFromPasswd
// returns empty for a UID that doesn't exist in /etc/passwd.
func TestGetShellFromPasswd_NonexistentUID(t *testing.T) {
shell := getShellFromPasswd("4294967294")
assert.Empty(t, shell, "nonexistent UID should return empty shell")
}
// TestGetShellFromPasswd_MatchesGetentForKnownUsers reads /etc/passwd directly
// and cross-validates every entry against getent to ensure the two shell
// sources agree.
func TestGetShellFromPasswd_MatchesGetentForKnownUsers(t *testing.T) {
if _, err := exec.LookPath("getent"); err != nil {
t.Skip("getent not available")
}
// Pick a few well-known system UIDs that are virtually always in /etc/passwd.
uids := []string{"0"} // root
current, err := user.Current()
require.NoError(t, err)
uids = append(uids, current.Uid)
for _, uid := range uids {
passwdShell := getShellFromPasswd(uid)
if passwdShell == "" {
continue
}
getentShell, err := getent.UserShell(uid)
if err != nil {
continue
}
assert.Equal(t, getentShell, passwdShell, "shell mismatch for UID %s", uid)
}
}
// TestIntegration_ShellLookupChain tests the full shell resolution chain
// (getShellFromPasswd -> getent -> $SHELL -> default).
func TestIntegration_ShellLookupChain(t *testing.T) {
current, err := user.Current()
require.NoError(t, err)
// getUserShell is the top-level function used by the SSH server.
shell := getUserShell(current.Uid)
require.NotEmpty(t, shell, "getUserShell must always return a shell")
assert.True(t, shell[0] == '/', "shell should be an absolute path, got %q", shell)
}

View File

@@ -9,8 +9,6 @@ import (
"strings"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/internal/getent"
)
var (
@@ -20,8 +18,8 @@ var (
// Dependency injection variables for testing - allows mocking dynamic runtime checks
var (
getCurrentUser = getent.CurrentUser
lookupUser = getent.LookupUser
getCurrentUser = currentUserWithGetent
lookupUser = lookupWithGetent
getCurrentOS = func() string { return runtime.GOOS }
getIsProcessPrivileged = isCurrentProcessPrivileged

View File

@@ -16,8 +16,6 @@ import (
"github.com/gliderlabs/ssh"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/internal/getent"
)
// POSIX portable filename character set regex: [a-zA-Z0-9._-]
@@ -162,7 +160,7 @@ func (s *Server) parseUserCredentials(localUser *user.User) (uint32, uint32, []u
// getSupplementaryGroups retrieves supplementary group IDs for a user.
// Uses id/getent fallback for NSS users in CGO_ENABLED=0 builds.
func (s *Server) getSupplementaryGroups(u *user.User) ([]uint32, error) {
groupIDStrings, err := getent.GroupIDs(u)
groupIDStrings, err := groupIdsWithFallback(u)
if err != nil {
return nil, fmt.Errorf("get group IDs for user %s: %w", u.Username, err)
}

View File

@@ -30,11 +30,6 @@ func GetInfo(ctx context.Context) *Info {
kernelVersion = osInfo[2]
}
addrs, err := networkAddresses()
if err != nil {
log.Warnf("discover network addresses: %s", err)
}
gio := &Info{
GoOS: runtime.GOOS,
Kernel: kernel,
@@ -46,7 +41,6 @@ func GetInfo(ctx context.Context) *Info {
NetbirdVersion: version.NetbirdVersion(),
UIVersion: extractUIVersion(ctx),
KernelVersion: kernelVersion,
NetworkAddresses: addrs,
SystemSerialNumber: serial(),
SystemProductName: productModel(),
SystemManufacturer: productManufacturer(),

View File

@@ -1,4 +1,4 @@
//go:build !ios && !android
//go:build !ios
package system

View File

@@ -1,89 +0,0 @@
package system
import (
"net/netip"
"strings"
)
var iFaceDiscover IFaceDiscover
type IFaceDiscover interface {
IFaces() (string, error)
}
// SetIFaceDiscover configures the Android interface discovery provider.
func SetIFaceDiscover(discover IFaceDiscover) {
iFaceDiscover = discover
}
func networkAddresses() ([]NetworkAddress, error) {
if iFaceDiscover == nil {
return nil, nil
}
ifaces, err := iFaceDiscover.IFaces()
if err != nil {
return nil, err
}
var netAddresses []NetworkAddress
for _, line := range strings.Split(ifaces, "\n") {
addresses, ok := interfaceAddresses(line)
if !ok {
continue
}
for _, address := range addresses {
netAddr, ok := toNetworkAddress(address)
if !ok {
continue
}
if isDuplicated(netAddresses, netAddr) {
continue
}
netAddresses = append(netAddresses, netAddr)
}
}
return netAddresses, nil
}
func interfaceAddresses(line string) ([]string, bool) {
parts := strings.Split(line, "|")
if len(parts) != 2 {
return nil, false
}
flags := strings.Fields(parts[0])
if len(flags) != 8 {
return nil, false
}
up, loopback := flags[3], flags[5]
if up != "true" || loopback == "true" {
return nil, false
}
return strings.Fields(parts[1]), true
}
func toNetworkAddress(address string) (NetworkAddress, bool) {
prefix, err := netip.ParsePrefix(address)
if err != nil {
return NetworkAddress{}, false
}
if prefix.Addr().Is4In6() {
if prefix.Bits() < 96 {
return NetworkAddress{}, false
}
prefix = netip.PrefixFrom(prefix.Addr().Unmap(), prefix.Bits()-96)
}
ip := prefix.Addr()
if ip.IsLoopback() || ip.IsLinkLocalUnicast() || ip.IsMulticast() {
return NetworkAddress{}, false
}
return NetworkAddress{NetIP: prefix}, true
}
func isDuplicated(addresses []NetworkAddress, addr NetworkAddress) bool {
for _, duplicated := range addresses {
if duplicated.NetIP == addr.NetIP {
return true
}
}
return false
}

Some files were not shown because too many files have changed in this diff Show More