Compare commits

..

1 Commits

Author SHA1 Message Date
Viktor Liu
c007f3650f Fix TestResetAggregationWindow flakiness on coarse clocks 2026-07-09 06:16:07 +02:00
179 changed files with 1517 additions and 6783 deletions

View File

@@ -86,7 +86,7 @@ jobs:
${{ runner.os }}-pnpm-
- name: Install dependencies
run: pnpm install --frozen-lockfile --ignore-scripts
run: pnpm install --frozen-lockfile
- name: Generate Wails bindings
run: pnpm run bindings

View File

@@ -1,47 +1,16 @@
# NetBird Agent Network
Agent Network is NetBird's access control layer for AI agents and the people who run them.
It gives every agent a real identity, tied to an identity provider (IdP), and governs what it can reach: LLM APIs and
AI gateways it can call, and the internal resources it can access. Traffic flows only over the encrypted NetBird tunnel,
scoped by policy, with no API keys or other credentials to leak. It also gives you control over cost and token usage.
Agent Network is NetBird's access control layer for AI agents and the people who run
them. It gives every agent a real identity, tied to your identity provider (IdP), and
governs what it can reach — the LLM APIs and AI gateways it can call, and the internal
resources it can access. Traffic flows only over the encrypted NetBird tunnel, scoped by
policy, with no API keys to leak.
Because every LLM request passes through an
identity-aware proxy, you can:
- **Set spending and rate limits** per agent, per user, or per team — with hard caps
that stop requests once a budget is reached.
- **Restrict models and providers** so agents can only call approved (and cost-appropriate)
endpoints, keeping expensive models off-limits unless explicitly allowed.
- **Attribute usage** by tracking token consumption and cost per identity, group, or cost center so every
request is tied back to the agent and person responsible.
- **Reuse your existing AI gateway** — point the proxy at a gateway you already run,
keeping its routing and config in place while it adds identity on top, so you skip
API key distribution.
https://github.com/user-attachments/assets/44d18286-d8ab-49f8-a457-98ccd66f3268
> **Beta.** Agent Network is in beta, but it's stable and already running in
> production environments. It's fully open source and can be self-hosted on your own
> infrastructure, with no vendor lock-in and no data leaving your environment.
> **Beta.** Agent Network is open source and can be self-hosted on your own
> infrastructure.
## How it works
Say you have a simple use case: your Engineering or IT team needs access to Claude Code or Codex, and you want visibility into usage plus the ability to enforce budgets.
How can you do that without creating a dedicated API key for every team?
With Agent Network you get a private endpoint inside your network, for example: https://mirror.netbird.ai
Teams configure their agents to point to that endpoint instead of using individual API keys directly.
This endpoint is only reachable when users are connected to your NetBird network and authenticated through your IdP. Otherwise, it is not accessible from the public internet.
You can then use this private endpoint to configure your AI agents, whether that is Claude Code, Codex, or another tool.
## Quickstart
Full step-by-step setup:
**https://docs.netbird.io/agent-network/quickstart**
## Architecture
Agent Network is built on two existing NetBird capabilities:
- **Overlay network** — the encrypted WireGuard mesh between peers.
@@ -53,9 +22,6 @@ LLM traffic is routed through the proxy's identity-aware pipeline, while interna
resources (databases, internal APIs, self-hosted models) are reached directly over
peer-to-peer WireGuard tunnels, governed by the same identities and access policies.
<img width="4720" height="2218" alt="image" src="https://github.com/user-attachments/assets/1afa5da1-4b82-4f8a-a7a8-f417efadf1eb" />
## Where the code lives
There is no separate "agent-network" service — it reuses the reverse-proxy and management

View File

@@ -247,9 +247,6 @@ func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool) (strin
deps.SyncResponse = resp
if e := cc.Engine(); e != nil {
deps.RefreshStatus = func() {
e.RunHealthProbes(context.Background(), true)
}
if cm := e.GetClientMetrics(); cm != nil {
deps.ClientMetrics = cm
}

View File

@@ -17,9 +17,7 @@ import (
"github.com/netbirdio/netbird/client/internal"
"github.com/netbirdio/netbird/client/internal/auth"
"github.com/netbirdio/netbird/client/internal/profilemanager"
nbnet "github.com/netbirdio/netbird/client/net"
"github.com/netbirdio/netbird/client/proto"
"github.com/netbirdio/netbird/client/server"
"github.com/netbirdio/netbird/client/system"
"github.com/netbirdio/netbird/util"
)
@@ -333,14 +331,6 @@ func doForegroundLogin(ctx context.Context, cmd *cobra.Command, setupKey string,
return fmt.Errorf("read config file %s: %v", configFilePath, err)
}
// Mirror runInForegroundMode: recover residual state (DNS, firewall,
// ssh config, legacy routing) from a previous unclean shutdown and
// enable advanced routing before dialing management.
if err := server.RestoreResidualState(ctx, profilemanager.NewServiceManager(configFilePath).GetStatePath()); err != nil {
log.Warnf("failed to restore residual state: %v", err)
}
nbnet.Init()
err = foregroundLogin(ctx, cmd, config, setupKey, activeProf.ID)
if err != nil {
return fmt.Errorf("foreground login failed: %v", err)

View File

@@ -22,8 +22,6 @@ import (
"github.com/netbirdio/netbird/client/internal/peer"
"github.com/netbirdio/netbird/client/internal/profilemanager"
"github.com/netbirdio/netbird/client/proto"
nbnet "github.com/netbirdio/netbird/client/net"
"github.com/netbirdio/netbird/client/server"
"github.com/netbirdio/netbird/client/system"
"github.com/netbirdio/netbird/shared/management/domain"
"github.com/netbirdio/netbird/util"
@@ -231,24 +229,6 @@ func runInForegroundMode(ctx context.Context, cmd *cobra.Command, activeProf *pr
_, _ = profilemanager.UpdateOldManagementURL(ctx, config, configFilePath)
// Restore residual state left by a previous run that did not shut down
// cleanly, mirroring what the daemon does before connecting: it recovers
// DNS config (a stale resolv.conf takeover can make the management
// hostname unresolvable), firewall rules, ssh config and legacy routing.
// Route cleanup itself happens at engine start; nbnet.Init() below lets
// the management dial bypass a leftover fwmark rule until then.
// Foreground mode is particularly exposed in containers: a crashed
// container restarts inside the same (pod) network namespace, so stale
// state survives while the process does not.
if err := server.RestoreResidualState(ctx, profilemanager.NewServiceManager(configPath).GetStatePath()); err != nil {
log.Warnf("failed to restore residual state: %v", err)
}
// Enable advanced routing (as the daemon does on startup) so the
// management dial bypasses a leftover fwmark rule instead of being
// shunted into a stale routing table.
nbnet.Init()
err = foregroundLogin(ctx, cmd, config, providedSetupKey, activeProf.ID)
if err != nil {
return fmt.Errorf("foreground login failed: %v", err)

View File

@@ -121,7 +121,6 @@ type Manager struct {
udpTracker *conntrack.UDPTracker
icmpTracker *conntrack.ICMPTracker
tcpTracker *conntrack.TCPTracker
fragments *fragmentTracker
forwarder atomic.Pointer[forwarder.Forwarder]
pendingCapture atomic.Pointer[forwarder.PacketCapture]
logger *nblog.Logger
@@ -184,41 +183,6 @@ func (d *decoder) decodePacket(data []byte) error {
}
}
// decodeTransport decodes the transport header of a first fragment (which
// gopacket leaves undecoded) into the decoder and appends its layer type to
// decoded, so the ACL pipeline can evaluate it like a normal packet. It returns
// false if the protocol is unsupported or the header is truncated.
func (d *decoder) decodeTransport(proto layers.IPProtocol, payload []byte) bool {
var l4 gopacket.DecodingLayer
var layerType gopacket.LayerType
var minLen int
switch proto {
case layers.IPProtocolTCP:
l4, layerType, minLen = &d.tcp, layers.LayerTypeTCP, 20
case layers.IPProtocolUDP:
l4, layerType, minLen = &d.udp, layers.LayerTypeUDP, 8
case layers.IPProtocolICMPv4:
l4, layerType, minLen = &d.icmp4, layers.LayerTypeICMPv4, 8
case layers.IPProtocolICMPv6:
l4, layerType, minLen = &d.icmp6, layers.LayerTypeICMPv6, 8
default:
return false
}
// Reject a fragment too small to hold the full transport header before
// decoding: it can't be ACL-evaluated (tiny-fragment attack), and skipping
// the decode avoids gopacket allocating an error on the drop path.
if len(payload) < minLen {
return false
}
if err := l4.DecodeFromBytes(payload, gopacket.NilDecodeFeedback); err != nil {
return false
}
d.decoded = append(d.decoded, layerType)
return true
}
// Create userspace firewall manager constructor
func Create(iface common.IFaceMapper, disableServerRoutes bool, flowLogger nftypes.FlowLogger, mtu uint16) (*Manager, error) {
return create(iface, nil, disableServerRoutes, flowLogger, mtu)
@@ -322,8 +286,6 @@ func create(iface common.IFaceMapper, nativeFirewall firewall.Manager, disableSe
if err := m.localipmanager.UpdateLocalIPs(iface); err != nil {
return nil, fmt.Errorf("update local IPs: %w", err)
}
m.fragments = newFragmentTracker(m.logger)
if disableConntrack {
log.Info("conntrack is disabled")
} else {
@@ -337,7 +299,6 @@ func create(iface common.IFaceMapper, nativeFirewall firewall.Manager, disableSe
}
}
if err := iface.SetFilter(m); err != nil {
m.fragments.Close()
return nil, fmt.Errorf("set filter: %w", err)
}
return m, nil
@@ -733,10 +694,6 @@ func (m *Manager) resetState() {
m.tcpTracker.Close()
}
if m.fragments != nil {
m.fragments.Close()
}
if fwder := m.forwarder.Load(); fwder != nil {
fwder.SetCapture(nil)
fwder.Stop()
@@ -1089,20 +1046,19 @@ func (m *Manager) filterInbound(packetData []byte, size int) bool {
return true
}
// gopacket does not decode the transport header of any IP fragment, so
// fragments take a dedicated path: the first fragment's header is decoded
// and ACL-evaluated here, and the remaining fragments inherit its verdict.
// TODO: pass fragments of routed packets to forwarder
if fragment {
return m.filterInboundFragment(d, srcIP, dstIP, size)
if m.logger.Enabled(nblog.LevelTrace) {
if d.decoded[0] == layers.LayerTypeIPv4 {
m.logger.Trace4("packet is a fragment: src=%v dst=%v id=%v flags=%v",
srcIP, dstIP, d.ip4.Id, d.ip4.Flags)
} else {
m.logger.Trace2("packet is an IPv6 fragment: src=%v dst=%v", srcIP, dstIP)
}
}
return false
}
return m.filterInboundDecoded(d, srcIP, dstIP, packetData, size)
}
// filterInboundDecoded runs the ACL, DNAT and conntrack pipeline on a fully
// decoded (non-fragment) inbound packet. It returns true if the packet should
// be dropped.
func (m *Manager) filterInboundDecoded(d *decoder, srcIP, dstIP netip.Addr, packetData []byte, size int) bool {
// TODO: optimize port DNAT by caching matched rules in conntrack
if translated := m.translateInboundPortDNAT(packetData, d, srcIP, dstIP); translated {
// Re-decode after port DNAT translation to update port information
@@ -1133,226 +1089,33 @@ func (m *Manager) filterInboundDecoded(d *decoder, srcIP, dstIP netip.Addr, pack
return m.handleRoutedTraffic(d, srcIP, dstIP, packetData, size)
}
// fragmentMeta holds the reassembly identity and layout of an IP fragment,
// extracted uniformly for IPv4 and IPv6.
type fragmentMeta struct {
key fragmentKey
// offset is the fragment offset in 8-byte units (zero for the first
// fragment).
offset uint16
// moreFragments is the More Fragments bit. A first fragment with it unset is
// an IPv6 atomic fragment (a complete datagram, RFC 6946): it has no trailing
// fragments to inherit a verdict, so it must not be recorded.
moreFragments bool
proto layers.IPProtocol
// l4payload is the fragmentable payload of this fragment. For the first
// fragment it starts with the transport header.
l4payload []byte
// headerEndOctets is the first fragment's payload length in 8-byte units:
// the smallest offset a trailing fragment may start at without overlapping
// the inspected transport header.
headerEndOctets uint16
}
// fragmentMetadata extracts the fragment identity and layout from a decoded IP
// fragment. It returns false for fragments it can't interpret (e.g. an IPv6
// fragment header shorter than 8 bytes), which are then dropped.
func fragmentMetadata(d *decoder, srcIP, dstIP netip.Addr) (fragmentMeta, bool) {
switch d.decoded[0] {
case layers.LayerTypeIPv4:
payload := d.ip4.Payload
return fragmentMeta{
key: fragmentKey{srcIP: srcIP, dstIP: dstIP, id: uint32(d.ip4.Id), proto: uint8(d.ip4.Protocol)},
offset: d.ip4.FragOffset,
moreFragments: d.ip4.Flags&layers.IPv4MoreFragments != 0,
proto: d.ip4.Protocol,
l4payload: payload,
headerEndOctets: octets(len(payload)),
}, true
case layers.LayerTypeIPv6:
// IPv6 fragment extension header: 8 bytes, followed by the fragmentable
// payload. Layout: next header (1), reserved (1), offset+flags (2), id (4).
payload := d.ip6.Payload
if len(payload) < 8 {
return fragmentMeta{}, false
}
nextHeader := layers.IPProtocol(payload[0])
offsetFlags := binary.BigEndian.Uint16(payload[2:4])
id := binary.BigEndian.Uint32(payload[4:8])
l4 := payload[8:]
return fragmentMeta{
key: fragmentKey{srcIP: srcIP, dstIP: dstIP, id: id, proto: uint8(nextHeader)},
offset: offsetFlags >> 3,
moreFragments: offsetFlags&1 != 0,
proto: nextHeader,
l4payload: l4,
headerEndOctets: octets(len(l4)),
}, true
default:
return fragmentMeta{}, false
}
}
// octets rounds a byte length up to whole 8-byte units, the granularity of the
// IP fragment offset field.
func octets(nbytes int) uint16 {
return uint16((nbytes + 7) / 8)
}
// filterInboundFragment decides the fate of an IP fragment. gopacket stops
// decoding at the network layer for every fragment, so the first fragment's
// transport header is decoded and ACL-evaluated here and its verdict recorded;
// the remaining (headerless) fragments inherit that verdict. Anything that
// cannot be tied to an allowed, non-overlapping first fragment is dropped.
func (m *Manager) filterInboundFragment(d *decoder, srcIP, dstIP netip.Addr, size int) bool {
meta, ok := fragmentMetadata(d, srcIP, dstIP)
if !ok {
if m.logger.Enabled(nblog.LevelTrace) {
m.logger.Trace2("dropping unsupported fragment: src=%v dst=%v", srcIP, dstIP)
}
return true
}
if meta.offset != 0 {
return m.filterTrailingFragment(meta, srcIP, dstIP)
}
// A new first fragment supersedes any recorded verdict for this datagram, so
// a re-sent or overlapping offset-zero fragment can't inherit the old one.
m.fragments.poison(meta.key)
// First fragment: decode its transport header so the ACL can evaluate it. A
// decode failure means the fragment is too small to hold the full transport
// header (RFC 1858 §3 tiny-fragment attack); it can't be evaluated, so drop it.
if !d.decodeTransport(meta.proto, meta.l4payload) {
if m.logger.Enabled(nblog.LevelTrace) {
m.logger.Trace3("dropping first fragment without full L4 header: src=%v dst=%v id=%v",
srcIP, dstIP, meta.key.id)
}
return true
}
return m.filterFirstFragment(d, meta, srcIP, dstIP, size)
}
// filterTrailingFragment applies a recorded first-fragment verdict to a
// non-first fragment.
func (m *Manager) filterTrailingFragment(meta fragmentMeta, srcIP, dstIP netip.Addr) bool {
switch m.fragments.verdict(meta.key, meta.offset) {
case fragmentAllow:
return false
case fragmentOverlap:
if m.logger.Enabled(nblog.LevelTrace) {
m.logger.Trace3("dropping overlapping fragment rewriting inspected header: src=%v dst=%v id=%v",
srcIP, dstIP, meta.key.id)
}
return true
default:
if m.logger.Enabled(nblog.LevelTrace) {
m.logger.Trace3("dropping fragment with no allowed first fragment: src=%v dst=%v id=%v",
srcIP, dstIP, meta.key.id)
}
return true
}
}
// filterFirstFragment runs the verdict part of the inbound pipeline on a first
// fragment with its transport header decoded. It mirrors filterInboundDecoded
// but skips DNAT (port rewriting on fragments is unsupported) and forwarder
// injection (fragments are left to the stack to reassemble, not forwarded).
// Allowed fragments have their verdict recorded so the datagram's trailing
// fragments inherit it.
func (m *Manager) filterFirstFragment(d *decoder, meta fragmentMeta, srcIP, dstIP netip.Addr, size int) bool {
if m.stateful && m.isValidTrackedConnection(d, srcIP, dstIP, size) {
m.recordFirstFragment(meta)
return false
}
if m.localipmanager.IsLocalIP(dstIP) {
ruleID, blocked := m.peerACLsBlock(srcIP, d, nil)
if blocked {
m.storeDropFlow("Dropping local first fragment (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
d, srcIP, dstIP, ruleID, size)
return true
}
m.trackInbound(d, srcIP, dstIP, ruleID, size)
m.recordFirstFragment(meta)
return false
}
if !m.routingEnabled.Load() {
if m.logger.Enabled(nblog.LevelTrace) {
m.logger.Trace2("Dropping routed fragment (routing disabled): src=%s dst=%s", srcIP, dstIP)
}
return true
}
if m.nativeRouter.Load() {
m.trackInbound(d, srcIP, dstIP, nil, size)
m.recordFirstFragment(meta)
return false
}
// TODO: pass fragments of routed packets to the forwarder; until then
// allowed routed fragments go to the native stack.
srcPort, dstPort := getPortsFromPacket(d)
ruleID, pass := m.routeACLsPass(srcIP, dstIP, d.decoded[1], srcPort, dstPort)
if !pass {
m.storeDropFlow("Dropping routed first fragment (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
d, srcIP, dstIP, ruleID, size)
return true
}
m.recordFirstFragment(meta)
return false
}
// recordFirstFragment caches an allowed first fragment's verdict for its
// trailing fragments to inherit. Atomic fragments (no More Fragments bit) are
// complete datagrams with no trailing fragments, so they are not cached and
// cannot exhaust the verdict table.
func (m *Manager) recordFirstFragment(meta fragmentMeta) {
if !meta.moreFragments {
return
}
m.fragments.recordAllowed(meta.key, meta.headerEndOctets)
}
// storeDropFlow logs and records a netflow drop event for an inbound packet
// denied by the ACLs. msg is the trace format taking rule id, protocol, source
// and destination.
func (m *Manager) storeDropFlow(msg string, d *decoder, srcIP, dstIP netip.Addr, ruleID []byte, size int) {
pnum := getProtocolFromPacket(d)
srcPort, dstPort := getPortsFromPacket(d)
if m.logger.Enabled(nblog.LevelTrace) {
m.logger.Trace6(msg, ruleID, pnum, srcIP, srcPort, dstIP, dstPort)
}
m.flowLogger.StoreEvent(nftypes.EventFields{
FlowID: uuid.New(),
Type: nftypes.TypeDrop,
RuleID: ruleID,
Direction: nftypes.Ingress,
Protocol: pnum,
SourceIP: srcIP,
DestIP: dstIP,
SourcePort: srcPort,
DestPort: dstPort,
// TODO: icmp type/code
RxPackets: 1,
RxBytes: uint64(size),
})
}
// handleLocalTraffic handles local traffic.
// If it returns true, the packet should be dropped.
func (m *Manager) handleLocalTraffic(d *decoder, srcIP, dstIP netip.Addr, packetData []byte, size int) bool {
ruleID, blocked := m.peerACLsBlock(srcIP, d, packetData)
if blocked {
m.storeDropFlow("Dropping local packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
d, srcIP, dstIP, ruleID, size)
pnum := getProtocolFromPacket(d)
srcPort, dstPort := getPortsFromPacket(d)
if m.logger.Enabled(nblog.LevelTrace) {
m.logger.Trace6("Dropping local packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
ruleID, pnum, srcIP, srcPort, dstIP, dstPort)
}
m.flowLogger.StoreEvent(nftypes.EventFields{
FlowID: uuid.New(),
Type: nftypes.TypeDrop,
RuleID: ruleID,
Direction: nftypes.Ingress,
Protocol: pnum,
SourceIP: srcIP,
DestIP: dstIP,
SourcePort: srcPort,
DestPort: dstPort,
// TODO: icmp type/code
RxPackets: 1,
RxBytes: uint64(size),
})
return true
}
@@ -1405,8 +1168,27 @@ func (m *Manager) handleRoutedTraffic(d *decoder, srcIP, dstIP netip.Addr, packe
ruleID, pass := m.routeACLsPass(srcIP, dstIP, protoLayer, srcPort, dstPort)
if !pass {
m.storeDropFlow("Dropping routed packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
d, srcIP, dstIP, ruleID, size)
proto := getProtocolFromPacket(d)
if m.logger.Enabled(nblog.LevelTrace) {
m.logger.Trace6("Dropping routed packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
ruleID, proto, srcIP, srcPort, dstIP, dstPort)
}
m.flowLogger.StoreEvent(nftypes.EventFields{
FlowID: uuid.New(),
Type: nftypes.TypeDrop,
RuleID: ruleID,
Direction: nftypes.Ingress,
Protocol: proto,
SourceIP: srcIP,
DestIP: dstIP,
SourcePort: srcPort,
DestPort: dstPort,
// TODO: icmp type/code
RxPackets: 1,
RxBytes: uint64(size),
})
return true
}

View File

@@ -5,9 +5,7 @@ import (
"fmt"
"net"
"net/netip"
"os"
"runtime"
"strconv"
"sync"
"time"
@@ -33,11 +31,6 @@ const (
defaultMaxInFlight = 1024
iosReceiveWindow = 16384
iosMaxInFlight = 256
// envForceTCPRACK overrides the platform default for gVisor's RACK loss
// detection. Set to a truthy value to force RACK on, or a falsy value to
// force it off, on any platform.
envForceTCPRACK = "NB_FORCE_TCP_RACK"
)
type Forwarder struct {
@@ -159,8 +152,6 @@ func New(iface common.IFaceMapper, logger *nblog.Logger, flowLogger nftypes.Flow
maxInFlight = iosMaxInFlight
}
configureTCPRecovery(s)
tcpForwarder := tcp.NewForwarder(s, receiveWindow, maxInFlight, f.handleTCP)
s.SetTransportProtocolHandler(tcp.ProtocolNumber, tcpForwarder.HandlePacket)
@@ -475,31 +466,3 @@ func probeRawICMP(network, addr string, logger *nblog.Logger) bool {
logger.Debug1("forwarder: raw %s socket access available", network)
return true
}
// configureTCPRecovery disables gVisor's RACK loss detection on Windows, where
// it interacts poorly with the host and collapses throughput on routed TCP
// connections (gVisor issue #9778). Other platforms keep the default. The
// EnvForceTCPRACK environment variable overrides the platform default.
func configureTCPRecovery(s *stack.Stack) {
disableRACK := runtime.GOOS == "windows"
if val := os.Getenv(envForceTCPRACK); val != "" {
force, err := strconv.ParseBool(val)
if err != nil {
log.Warnf("parse %s: %v", envForceTCPRACK, err)
} else {
disableRACK = !force
}
}
if !disableRACK {
return
}
opt := tcpip.TCPRecovery(0)
if err := s.SetTransportProtocolOption(tcp.ProtocolNumber, &opt); err != nil {
log.Warnf("disable TCP RACK loss detection: %v", err)
return
}
log.Info("forwarder: TCP RACK loss detection disabled")
}

View File

@@ -1,204 +0,0 @@
package uspfilter
import (
"context"
"net/netip"
"os"
"strconv"
"sync"
"time"
nblog "github.com/netbirdio/netbird/client/firewall/uspfilter/log"
)
const (
// defaultFragmentTimeout bounds how long a first-fragment verdict is kept
// while the remaining fragments arrive. It mirrors the Linux IP reassembly
// timeout (net.ipv4.ipfrag_time).
defaultFragmentTimeout = 30 * time.Second
// fragmentCleanupInterval is how often expired verdicts are purged.
fragmentCleanupInterval = 10 * time.Second
// defaultMaxFragmentEntries caps the number of concurrently tracked
// fragmented datagrams. The table stays bounded because each datagram is a
// single small entry regardless of how many fragments it is split into, and
// the 13-bit IPv4 fragment-offset field limits any datagram to 64 KiB.
defaultMaxFragmentEntries = 16384
// EnvFragmentMaxEntries overrides defaultMaxFragmentEntries.
EnvFragmentMaxEntries = "NB_FRAGMENT_MAX_ENTRIES"
)
// fragmentVerdict is the decision for a trailing (headerless) fragment.
type fragmentVerdict int
const (
// fragmentDeny drops the fragment: no allowed first fragment is on record.
fragmentDeny fragmentVerdict = iota
// fragmentAllow passes the fragment: it belongs to an allowed datagram and
// does not overlap the already-inspected transport header.
fragmentAllow
// fragmentOverlap drops the fragment and poisons its datagram: it overlaps
// the transport header the ACL inspected (RFC 1858 §4, RFC 3128; RFC 5722
// requires discarding the whole datagram on overlap for IPv6).
fragmentOverlap
)
// fragmentKey identifies a fragmented datagram. It matches the RFC 791 / RFC
// 8200 reassembly key: source, destination, protocol and identification. The id
// is 32-bit to hold both the IPv4 (16-bit) and IPv6 (32-bit) identification.
type fragmentKey struct {
srcIP netip.Addr
dstIP netip.Addr
id uint32
proto uint8
}
// fragmentEntry records the verdict of an allowed first fragment.
type fragmentEntry struct {
// headerEndOctets is the offset, in 8-byte units, at which the first
// fragment's payload ended. A trailing fragment starting before this
// overlaps bytes the ACL already inspected and is rejected.
headerEndOctets uint16
// recordedAt is when the first fragment was accepted. The verdict expires a
// fixed timeout later and is not refreshed, mirroring the kernel reassembly
// timer so a trailing-fragment flood can't keep a datagram alive.
recordedAt time.Time
}
// fragmentTracker records the ACL verdict of a datagram's first fragment so the
// remaining fragments, which carry no L4 header, can inherit the decision
// without reassembling the datagram. Only allowed first fragments are stored;
// anything that cannot be tied to an allowed, non-overlapping first fragment is
// dropped (fail closed).
type fragmentTracker struct {
logger *nblog.Logger
mutex sync.Mutex
entries map[fragmentKey]fragmentEntry
timeout time.Duration
// maxEntries caps the table; atCapacity dedups the capacity warning until
// the table drains below the cap again.
maxEntries int
atCapacity bool
cleanupTicker *time.Ticker
cancel context.CancelFunc
}
func newFragmentTracker(logger *nblog.Logger) *fragmentTracker {
ctx, cancel := context.WithCancel(context.Background())
t := &fragmentTracker{
logger: logger,
entries: make(map[fragmentKey]fragmentEntry),
timeout: defaultFragmentTimeout,
maxEntries: fragmentMaxEntries(logger),
cleanupTicker: time.NewTicker(fragmentCleanupInterval),
cancel: cancel,
}
go t.cleanupRoutine(ctx)
return t
}
func fragmentMaxEntries(logger *nblog.Logger) int {
v := os.Getenv(EnvFragmentMaxEntries)
if v == "" {
return defaultMaxFragmentEntries
}
n, err := strconv.Atoi(v)
if err != nil || n <= 0 {
logger.Warn2("invalid %s=%q, using default", EnvFragmentMaxEntries, v)
return defaultMaxFragmentEntries
}
return n
}
// recordAllowed stores the verdict of an allowed first fragment. headerEndOctets
// is the first fragment's payload length in 8-byte units. When the table is full
// the record is dropped, which fails closed: the datagram's trailing fragments
// will be denied.
func (t *fragmentTracker) recordAllowed(key fragmentKey, headerEndOctets uint16) {
t.mutex.Lock()
defer t.mutex.Unlock()
if t.entries == nil {
return
}
if _, ok := t.entries[key]; !ok && len(t.entries) >= t.maxEntries {
if !t.atCapacity {
t.atCapacity = true
t.logger.Warn2("fragment verdict table at capacity (%d/%d): trailing fragments of new datagrams will be dropped",
len(t.entries), t.maxEntries)
}
return
}
t.entries[key] = fragmentEntry{
headerEndOctets: headerEndOctets,
recordedAt: time.Now(),
}
}
// poison drops any recorded verdict for a datagram, so its later fragments are
// denied until a new allowed first fragment is recorded. Called on every
// offset-zero fragment to defeat offset-zero overlap rewrites (RFC 3128).
func (t *fragmentTracker) poison(key fragmentKey) {
t.mutex.Lock()
defer t.mutex.Unlock()
delete(t.entries, key)
}
// verdict decides the fate of a trailing fragment at fragOffsetOctets (the IPv4
// fragment offset, in 8-byte units). A fragment overlapping the inspected
// header poisons the datagram: the entry is removed so all further fragments of
// that datagram are denied too.
func (t *fragmentTracker) verdict(key fragmentKey, fragOffsetOctets uint16) fragmentVerdict {
t.mutex.Lock()
defer t.mutex.Unlock()
entry, ok := t.entries[key]
if !ok {
return fragmentDeny
}
if time.Since(entry.recordedAt) > t.timeout {
delete(t.entries, key)
return fragmentDeny
}
if fragOffsetOctets < entry.headerEndOctets {
delete(t.entries, key)
return fragmentOverlap
}
return fragmentAllow
}
func (t *fragmentTracker) cleanupRoutine(ctx context.Context) {
defer t.cleanupTicker.Stop()
for {
select {
case <-t.cleanupTicker.C:
t.cleanup()
case <-ctx.Done():
return
}
}
}
func (t *fragmentTracker) cleanup() {
t.mutex.Lock()
defer t.mutex.Unlock()
for key, entry := range t.entries {
if time.Since(entry.recordedAt) > t.timeout {
delete(t.entries, key)
}
}
if len(t.entries) < t.maxEntries {
t.atCapacity = false
}
}
// Close stops the cleanup routine and releases resources.
func (t *fragmentTracker) Close() {
t.cancel()
t.mutex.Lock()
t.entries = nil
t.mutex.Unlock()
}

View File

@@ -1,115 +0,0 @@
package uspfilter
import (
"encoding/binary"
"testing"
)
// benchFilterInbound drives filterInbound over a fixed packet in a tight loop.
// Packets are built once, outside the timed region, so the benchmark measures
// only pipeline cost, which is what an attacker can amplify.
func benchFilterInbound(b *testing.B, pkt []byte) {
b.Helper()
b.ReportAllocs()
b.SetBytes(int64(len(pkt)))
b.ResetTimer()
for i := 0; i < b.N; i++ {
m := benchManager
m.filterInbound(pkt, len(pkt))
}
}
// benchManager is a package-level manager reused across fragment benchmarks so
// setup cost stays out of the timed region.
var benchManager *Manager
func setupBenchManager(b *testing.B) *Manager {
b.Helper()
m := newFragmentTestManager(b)
allowUDP(b, m, 8080)
// Disable conntrack so the allowed-first-fragment path measures transport
// decode + ACL every iteration instead of matching the connection tracked
// on the first iteration.
m.stateful = false
benchManager = m
return m
}
// BenchmarkInbound_NormalPacket is the baseline: a full, non-fragmented UDP
// packet that passes the ACL. Fragment paths should stay comparable to this.
func BenchmarkInbound_NormalPacket(b *testing.B) {
setupBenchManager(b)
pkt := normalUDPPacket(b, 8080, 32)
benchFilterInbound(b, pkt)
}
// BenchmarkInbound_FirstFragmentAllowed measures the first-fragment path:
// transport decode + ACL evaluation + verdict record.
func BenchmarkInbound_FirstFragmentAllowed(b *testing.B) {
setupBenchManager(b)
pkt := firstFragmentUDP(b, 0x2000, 8080, 32)
benchFilterInbound(b, pkt)
}
// BenchmarkInbound_TrailingFragmentAllowed measures the common trailing-fragment
// path: a single map lookup after the first fragment is on record.
func BenchmarkInbound_TrailingFragmentAllowed(b *testing.B) {
m := setupBenchManager(b)
first := firstFragmentUDP(b, 0x3000, 8080, 32)
m.filterInbound(first, len(first))
pkt := trailingFragment(b, 0x3000, 5, false, 24)
benchFilterInbound(b, pkt)
}
// BenchmarkInbound_TrailingFragmentNoFirst is the primary DoS vector: an
// attacker floods trailing fragments with no first fragment on record. Each is
// a map miss and must be cheap.
func BenchmarkInbound_TrailingFragmentNoFirst(b *testing.B) {
setupBenchManager(b)
pkt := trailingFragment(b, 0x4000, 185, false, 40)
benchFilterInbound(b, pkt)
}
// BenchmarkInbound_TinyFirstFragment measures the tiny-fragment drop path: a
// first fragment too small to decode a transport header.
func BenchmarkInbound_TinyFirstFragment(b *testing.B) {
setupBenchManager(b)
pkt := trailingFragment(b, 0x5000, 0, true, 4)
benchFilterInbound(b, pkt)
}
// BenchmarkInbound_TrailingFragmentDistinctIDs is the worst case for the
// verdict table: an attacker varies the datagram id on every packet so no first
// fragment ever matches. Verdict lookups always miss and nothing is recorded,
// so the table cannot grow. Each iteration rewrites the id field in place.
func BenchmarkInbound_TrailingFragmentDistinctIDs(b *testing.B) {
setupBenchManager(b)
pkt := trailingFragment(b, 0x6000, 185, false, 40)
m := benchManager
b.ReportAllocs()
b.SetBytes(int64(len(pkt)))
b.ResetTimer()
for i := 0; i < b.N; i++ {
// IPv4 identification field is at bytes 4:6.
binary.BigEndian.PutUint16(pkt[4:6], uint16(i))
m.filterInbound(pkt, len(pkt))
}
}
// BenchmarkInbound_FirstFragmentDistinctIDs measures sustained first-fragment
// pressure with distinct ids: transport decode + ACL + verdict insert until the
// table caps, exercising the map growth and capacity guard.
func BenchmarkInbound_FirstFragmentDistinctIDs(b *testing.B) {
setupBenchManager(b)
pkt := firstFragmentUDP(b, 0x7000, 8080, 32)
m := benchManager
b.ReportAllocs()
b.SetBytes(int64(len(pkt)))
b.ResetTimer()
for i := 0; i < b.N; i++ {
binary.BigEndian.PutUint16(pkt[4:6], uint16(i))
m.filterInbound(pkt, len(pkt))
}
}

View File

@@ -1,554 +0,0 @@
package uspfilter
import (
"encoding/binary"
"net"
"net/netip"
"testing"
"time"
"github.com/google/gopacket"
"github.com/google/gopacket/layers"
"github.com/stretchr/testify/require"
fw "github.com/netbirdio/netbird/client/firewall/manager"
nbiface "github.com/netbirdio/netbird/client/iface"
"github.com/netbirdio/netbird/client/iface/device"
"github.com/netbirdio/netbird/client/iface/wgaddr"
)
const (
fragTestSrc = "100.10.0.1"
fragTestDst = "100.10.0.100"
fragTestSrcV6 = "fd00::1"
fragTestDstV6 = "fd00::100"
)
func newFragmentTestManager(tb testing.TB) *Manager {
tb.Helper()
ifaceMock := &IFaceMock{
SetFilterFunc: func(device.PacketFilter) error { return nil },
AddressFunc: func() wgaddr.Address {
return wgaddr.Address{
IP: netip.MustParseAddr(fragTestDst),
Network: netip.MustParsePrefix("100.10.0.0/16"),
IPv6: netip.MustParseAddr(fragTestDstV6),
IPv6Net: netip.MustParsePrefix("fd00::/64"),
}
},
}
m, err := Create(ifaceMock, false, flowLogger, nbiface.DefaultMTU)
require.NoError(tb, err)
require.NoError(tb, m.UpdateLocalIPs())
tb.Cleanup(func() { require.NoError(tb, m.Close(nil)) })
return m
}
// firstFragmentUDPTo builds the first fragment of a fragmented UDP datagram to
// the given destination: it carries the full UDP header plus payloadLen bytes
// of data, with the More Fragments flag set and offset zero.
func firstFragmentUDPTo(tb testing.TB, dst string, id uint16, dstPort uint16, payloadLen int) []byte {
tb.Helper()
ip := &layers.IPv4{
Version: 4,
TTL: 64,
Id: id,
Protocol: layers.IPProtocolUDP,
SrcIP: net.ParseIP(fragTestSrc),
DstIP: net.ParseIP(dst),
Flags: layers.IPv4MoreFragments,
}
udp := &layers.UDP{SrcPort: 40000, DstPort: layers.UDPPort(dstPort)}
require.NoError(tb, udp.SetNetworkLayerForChecksum(ip))
buf := gopacket.NewSerializeBuffer()
opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, udp, gopacket.Payload(make([]byte, payloadLen))))
return buf.Bytes()
}
func firstFragmentUDP(tb testing.TB, id uint16, dstPort uint16, payloadLen int) []byte {
tb.Helper()
return firstFragmentUDPTo(tb, fragTestDst, id, dstPort, payloadLen)
}
// firstFragmentTCP builds the first fragment of a fragmented TCP datagram: the
// full 20-byte TCP header plus 12 bytes of data, with the More Fragments flag
// set and offset zero.
func firstFragmentTCP(tb testing.TB, id uint16, dstPort uint16) []byte {
tb.Helper()
ip := &layers.IPv4{
Version: 4,
TTL: 64,
Id: id,
Protocol: layers.IPProtocolTCP,
SrcIP: net.ParseIP(fragTestSrc),
DstIP: net.ParseIP(fragTestDst),
Flags: layers.IPv4MoreFragments,
}
tcp := &layers.TCP{SrcPort: 40000, DstPort: layers.TCPPort(dstPort), SYN: true, Window: 64240}
require.NoError(tb, tcp.SetNetworkLayerForChecksum(ip))
buf := gopacket.NewSerializeBuffer()
opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, tcp, gopacket.Payload(make([]byte, 12))))
return buf.Bytes()
}
// trailingFragmentTo builds a non-first fragment to the given destination: an
// IPv4 header at the given fragment offset (in 8-byte units) carrying raw
// payload and no L4 header.
func trailingFragmentTo(tb testing.TB, dst string, proto layers.IPProtocol, id uint16, fragOffsetOctets uint16, moreFragments bool, payloadLen int) []byte {
tb.Helper()
ip := &layers.IPv4{
Version: 4,
TTL: 64,
Id: id,
Protocol: proto,
SrcIP: net.ParseIP(fragTestSrc),
DstIP: net.ParseIP(dst),
FragOffset: fragOffsetOctets,
}
if moreFragments {
ip.Flags = layers.IPv4MoreFragments
}
buf := gopacket.NewSerializeBuffer()
opts := gopacket.SerializeOptions{FixLengths: true}
require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, gopacket.Payload(make([]byte, payloadLen))))
return buf.Bytes()
}
func trailingFragment(tb testing.TB, id uint16, fragOffsetOctets uint16, moreFragments bool, payloadLen int) []byte {
tb.Helper()
return trailingFragmentTo(tb, fragTestDst, layers.IPProtocolUDP, id, fragOffsetOctets, moreFragments, payloadLen)
}
// outboundUDPPacket builds a complete outbound UDP packet from the local
// address, used to establish conntrack state for reply-direction tests.
func outboundUDPPacket(tb testing.TB, srcPort, dstPort uint16) []byte {
tb.Helper()
ip := &layers.IPv4{
Version: 4,
TTL: 64,
Id: 1,
Protocol: layers.IPProtocolUDP,
SrcIP: net.ParseIP(fragTestDst),
DstIP: net.ParseIP(fragTestSrc),
}
udp := &layers.UDP{SrcPort: layers.UDPPort(srcPort), DstPort: layers.UDPPort(dstPort)}
require.NoError(tb, udp.SetNetworkLayerForChecksum(ip))
buf := gopacket.NewSerializeBuffer()
opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, udp, gopacket.Payload(make([]byte, 16))))
return buf.Bytes()
}
// normalUDPPacket builds a complete, non-fragmented UDP packet for baseline
// comparisons against the fragment paths.
func normalUDPPacket(tb testing.TB, dstPort uint16, payloadLen int) []byte {
tb.Helper()
ip := &layers.IPv4{
Version: 4,
TTL: 64,
Id: 1,
Protocol: layers.IPProtocolUDP,
SrcIP: net.ParseIP(fragTestSrc),
DstIP: net.ParseIP(fragTestDst),
}
udp := &layers.UDP{SrcPort: 40000, DstPort: layers.UDPPort(dstPort)}
require.NoError(tb, udp.SetNetworkLayerForChecksum(ip))
buf := gopacket.NewSerializeBuffer()
opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, udp, gopacket.Payload(make([]byte, payloadLen))))
return buf.Bytes()
}
func allowUDP(tb testing.TB, m *Manager, dstPort uint16) {
tb.Helper()
_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolUDP, nil,
&fw.Port{Values: []uint16{dstPort}}, fw.ActionAccept, "")
require.NoError(tb, err)
}
// TestFragment_TrailingWithoutFirstDropped is the core bypass repro: a trailing
// fragment with no allowed first fragment on record must be dropped. Before the
// fix, filterInbound returned false (allow) for any fragment.
func TestFragment_TrailingWithoutFirstDropped(t *testing.T) {
m := newFragmentTestManager(t)
frag := trailingFragment(t, 0x1234, 185, false, 40)
require.True(t, m.filterInbound(frag, len(frag)),
"trailing fragment without an allowed first fragment must be dropped")
}
// TestFragment_AllowedFirstPassesTrailing verifies that once a first fragment
// passes the ACL, its trailing fragments inherit the allow verdict.
func TestFragment_AllowedFirstPassesTrailing(t *testing.T) {
m := newFragmentTestManager(t)
allowUDP(t, m, 8080)
// First fragment: UDP header (8) + 32 payload = 40 octets -> headerEnd = 5.
first := firstFragmentUDP(t, 0x2222, 8080, 32)
require.False(t, m.filterInbound(first, len(first)),
"allowed first fragment should pass and be recorded")
trailing := trailingFragment(t, 0x2222, 5, false, 24)
require.False(t, m.filterInbound(trailing, len(trailing)),
"trailing fragment of an allowed datagram should pass")
}
// TestFragment_DeniedFirstDropsTrailing verifies that a first fragment blocked
// by the ACL leaves no verdict, so its trailing fragments are dropped.
func TestFragment_DeniedFirstDropsTrailing(t *testing.T) {
m := newFragmentTestManager(t)
// No accept rule: local traffic defaults to deny.
first := firstFragmentUDP(t, 0x3333, 9999, 32)
require.True(t, m.filterInbound(first, len(first)),
"first fragment to a blocked port should be dropped by the ACL")
trailing := trailingFragment(t, 0x3333, 5, false, 24)
require.True(t, m.filterInbound(trailing, len(trailing)),
"trailing fragment of a denied datagram must be dropped")
}
// TestFragment_OverlappingHeaderDropped covers the RFC 1858 §4 / RFC 3128
// overlapping-fragment rewrite: a trailing fragment starting inside the range
// the ACL already inspected is dropped and poisons the datagram. TCP is used so
// the overlap lands on real header bytes (the flags at byte 13).
func TestFragment_OverlappingHeaderDropped(t *testing.T) {
m := newFragmentTestManager(t)
_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolTCP, nil,
&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
require.NoError(t, err)
// First fragment: TCP header (20) + 12 data = 32 bytes -> headerEnd = 4 octets.
first := firstFragmentTCP(t, 0x4444, 8080)
require.False(t, m.filterInbound(first, len(first)))
// Overlapping fragment at offset 1 (byte 8) falls inside the inspected TCP
// header, so it could rewrite the flags or port on reassembly.
overlap := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x4444, 1, true, 32)
require.True(t, m.filterInbound(overlap, len(overlap)),
"fragment overlapping the inspected header must be dropped")
// The datagram is now poisoned: a later, non-overlapping fragment is also
// dropped because the verdict was removed.
later := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x4444, 4, false, 24)
require.True(t, m.filterInbound(later, len(later)),
"fragments after an overlap must be dropped (datagram poisoned)")
}
// TestFragment_OffsetZeroOverlapPoisons covers the RFC 3128 offset-zero rewrite:
// an allowed first fragment followed by a denied offset-zero fragment for the
// same datagram must not leave the earlier allow verdict in place.
func TestFragment_OffsetZeroOverlapPoisons(t *testing.T) {
m := newFragmentTestManager(t)
allowUDP(t, m, 8080)
allowed := firstFragmentUDP(t, 0x5A5A, 8080, 32)
require.False(t, m.filterInbound(allowed, len(allowed)),
"allowed first fragment should pass and be recorded")
// A second offset-zero fragment to a denied port supersedes the datagram's
// verdict; it is dropped and must not leave the allow in place.
denied := firstFragmentUDP(t, 0x5A5A, 9999, 32)
require.True(t, m.filterInbound(denied, len(denied)),
"denied offset-zero fragment must be dropped")
trailing := trailingFragment(t, 0x5A5A, 5, false, 24)
require.True(t, m.filterInbound(trailing, len(trailing)),
"trailing fragment must be denied after the datagram was poisoned")
}
// TestFragment_TinyFirstDropped covers the tiny-fragment attack: a first
// fragment too small to contain the full transport header can't be
// ACL-evaluated and must be dropped.
func TestFragment_TinyFirstDropped(t *testing.T) {
m := newFragmentTestManager(t)
allowUDP(t, m, 8080)
// IPv4 header + 4 raw bytes, MF set, offset 0: too small for the 8-byte UDP
// header, so it decodes to L3 only.
tiny := trailingFragment(t, 0x5555, 0, true, 4)
require.True(t, m.filterInbound(tiny, len(tiny)),
"tiny first fragment without a full L4 header must be dropped")
}
// TestFragment_TCPFirstFragment verifies the TCP arm of the transport decode: a
// first fragment carrying the full 20-byte TCP header is ACL-evaluated and its
// trailing fragments inherit the verdict.
func TestFragment_TCPFirstFragment(t *testing.T) {
m := newFragmentTestManager(t)
_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolTCP, nil,
&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
require.NoError(t, err)
// TCP header (20) + 12 data = 32 bytes -> headerEnd = 4 octets.
first := firstFragmentTCP(t, 0x6666, 8080)
require.False(t, m.filterInbound(first, len(first)),
"allowed TCP first fragment should pass and be recorded")
trailing := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x6666, 4, false, 24)
require.False(t, m.filterInbound(trailing, len(trailing)),
"trailing fragment of an allowed TCP datagram should pass")
}
// TestFragment_TCPTinyFirstDropped verifies the TCP minimum header length: 12
// bytes would satisfy a UDP header but falls short of the 20-byte TCP header.
func TestFragment_TCPTinyFirstDropped(t *testing.T) {
m := newFragmentTestManager(t)
_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolTCP, nil,
&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
require.NoError(t, err)
tiny := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x7777, 0, true, 12)
require.True(t, m.filterInbound(tiny, len(tiny)),
"first fragment shorter than the TCP header must be dropped")
}
// TestFragment_ConntrackAllowsFirstFragment verifies the conntrack branch: reply
// fragments of an outbound-established UDP flow pass without any inbound rule.
func TestFragment_ConntrackAllowsFirstFragment(t *testing.T) {
m := newFragmentTestManager(t)
out := outboundUDPPacket(t, 12345, 40000)
require.False(t, m.filterOutbound(out, len(out)))
first := firstFragmentUDP(t, 0x8888, 12345, 32)
require.False(t, m.filterInbound(first, len(first)),
"reply first fragment should pass via conntrack")
trailing := trailingFragment(t, 0x8888, 5, false, 24)
require.False(t, m.filterInbound(trailing, len(trailing)),
"trailing fragment of a tracked flow should pass")
}
// TestFragment_RoutingDisabledDropsFragment verifies routed first fragments are
// dropped when routing is disabled.
func TestFragment_RoutingDisabledDropsFragment(t *testing.T) {
m := newFragmentTestManager(t)
m.routingEnabled.Store(false)
first := firstFragmentUDPTo(t, "198.51.100.10", 0x9999, 8080, 32)
require.True(t, m.filterInbound(first, len(first)),
"routed first fragment must be dropped when routing is disabled")
}
// TestFragment_RouteACL verifies the route-ACL branch: fragments to a non-local
// destination follow the route rules, allowed datagrams pass their trailing
// fragments and denied ones don't.
func TestFragment_RouteACL(t *testing.T) {
m := newFragmentTestManager(t)
m.routingEnabled.Store(true)
m.nativeRouter.Store(false)
_, err := m.AddRouteFiltering(
[]byte("rt-1"),
[]netip.Prefix{netip.MustParsePrefix("100.10.0.0/16")},
fw.Network{Prefix: netip.MustParsePrefix("198.51.100.0/24")},
fw.ProtocolUDP,
nil,
&fw.Port{Values: []uint16{8080}},
fw.ActionAccept,
)
require.NoError(t, err)
first := firstFragmentUDPTo(t, "198.51.100.10", 0xAAAA, 8080, 32)
require.False(t, m.filterInbound(first, len(first)),
"route-ACL-allowed first fragment should pass")
trailing := trailingFragmentTo(t, "198.51.100.10", layers.IPProtocolUDP, 0xAAAA, 5, false, 24)
require.False(t, m.filterInbound(trailing, len(trailing)),
"trailing fragment of an allowed routed datagram should pass")
denied := firstFragmentUDPTo(t, "198.51.100.10", 0xBBBB, 9999, 32)
require.True(t, m.filterInbound(denied, len(denied)),
"route-ACL-denied first fragment must be dropped")
deniedTrailing := trailingFragmentTo(t, "198.51.100.10", layers.IPProtocolUDP, 0xBBBB, 5, false, 24)
require.True(t, m.filterInbound(deniedTrailing, len(deniedTrailing)),
"trailing fragment of a denied routed datagram must be dropped")
}
// TestFragment_ExpiredVerdictDropsTrailing verifies a verdict older than the
// tracker timeout no longer admits trailing fragments.
func TestFragment_ExpiredVerdictDropsTrailing(t *testing.T) {
m := newFragmentTestManager(t)
allowUDP(t, m, 8080)
first := firstFragmentUDP(t, 0xCCCC, 8080, 32)
require.False(t, m.filterInbound(first, len(first)))
m.fragments.mutex.Lock()
for key, entry := range m.fragments.entries {
entry.recordedAt = time.Now().Add(-defaultFragmentTimeout - time.Second)
m.fragments.entries[key] = entry
}
m.fragments.mutex.Unlock()
trailing := trailingFragment(t, 0xCCCC, 5, false, 24)
require.True(t, m.filterInbound(trailing, len(trailing)),
"trailing fragment after verdict expiry must be dropped")
}
// TestFragment_CapacityFailsClosed verifies the table cap: at capacity, new
// datagram verdicts are not recorded (their trailing fragments are dropped)
// while already-recorded datagrams keep working.
func TestFragment_CapacityFailsClosed(t *testing.T) {
m := newFragmentTestManager(t)
allowUDP(t, m, 8080)
m.fragments.mutex.Lock()
m.fragments.maxEntries = 1
m.fragments.mutex.Unlock()
first1 := firstFragmentUDP(t, 0x0101, 8080, 32)
require.False(t, m.filterInbound(first1, len(first1)))
first2 := firstFragmentUDP(t, 0x0202, 8080, 32)
require.False(t, m.filterInbound(first2, len(first2)),
"first fragment itself still passes at capacity")
trailing2 := trailingFragment(t, 0x0202, 5, false, 24)
require.True(t, m.filterInbound(trailing2, len(trailing2)),
"trailing fragment of an unrecorded datagram must be dropped at capacity")
trailing1 := trailingFragment(t, 0x0101, 5, false, 24)
require.False(t, m.filterInbound(trailing1, len(trailing1)),
"already-recorded datagram should keep passing at capacity")
}
// v6FragmentHeader builds the 8-byte IPv6 fragment extension header for the
// given inner protocol, offset (8-byte units), More Fragments bit and id.
func v6FragmentHeader(proto layers.IPProtocol, offsetOctets uint16, moreFragments bool, id uint32) []byte {
offsetFlags := offsetOctets << 3
if moreFragments {
offsetFlags |= 1
}
hdr := make([]byte, 8)
hdr[0] = uint8(proto)
binary.BigEndian.PutUint16(hdr[2:4], offsetFlags)
binary.BigEndian.PutUint32(hdr[4:8], id)
return hdr
}
func v6UDPHeader(dstPort uint16, dataLen int) []byte {
hdr := make([]byte, 8)
binary.BigEndian.PutUint16(hdr[0:2], 40000)
binary.BigEndian.PutUint16(hdr[2:4], dstPort)
binary.BigEndian.PutUint16(hdr[4:6], uint16(8+dataLen))
return hdr
}
// firstFragmentUDPv6 builds the first fragment of a fragmented IPv6 UDP
// datagram: fragment header (offset 0, More Fragments set) + full UDP header +
// data.
func firstFragmentUDPv6(tb testing.TB, id uint32, dstPort uint16, dataLen int) []byte {
tb.Helper()
return fragmentUDPv6(tb, id, dstPort, dataLen, true)
}
// fragmentUDPv6 builds an offset-zero IPv6 UDP fragment. With moreFragments
// false it is an atomic fragment (a complete datagram, RFC 6946).
func fragmentUDPv6(tb testing.TB, id uint32, dstPort uint16, dataLen int, moreFragments bool) []byte {
tb.Helper()
ip := &layers.IPv6{
Version: 6,
NextHeader: layers.IPProtocolIPv6Fragment,
HopLimit: 64,
SrcIP: net.ParseIP(fragTestSrcV6),
DstIP: net.ParseIP(fragTestDstV6),
}
payload := append(v6FragmentHeader(layers.IPProtocolUDP, 0, moreFragments, id), v6UDPHeader(dstPort, dataLen)...)
payload = append(payload, make([]byte, dataLen)...)
buf := gopacket.NewSerializeBuffer()
require.NoError(tb, gopacket.SerializeLayers(buf, gopacket.SerializeOptions{FixLengths: true}, ip, gopacket.Payload(payload)))
return buf.Bytes()
}
// trailingFragmentV6 builds a non-first IPv6 fragment: fragment header at the
// given offset carrying raw data and no transport header.
func trailingFragmentV6(tb testing.TB, id uint32, offsetOctets uint16, moreFragments bool, dataLen int) []byte {
tb.Helper()
ip := &layers.IPv6{
Version: 6,
NextHeader: layers.IPProtocolIPv6Fragment,
HopLimit: 64,
SrcIP: net.ParseIP(fragTestSrcV6),
DstIP: net.ParseIP(fragTestDstV6),
}
payload := append(v6FragmentHeader(layers.IPProtocolUDP, offsetOctets, moreFragments, id), make([]byte, dataLen)...)
buf := gopacket.NewSerializeBuffer()
require.NoError(tb, gopacket.SerializeLayers(buf, gopacket.SerializeOptions{FixLengths: true}, ip, gopacket.Payload(payload)))
return buf.Bytes()
}
// TestFragmentV6_TrailingWithoutFirstDropped verifies the IPv6 bypass is closed:
// a trailing fragment with no allowed first fragment is dropped.
func TestFragmentV6_TrailingWithoutFirstDropped(t *testing.T) {
m := newFragmentTestManager(t)
frag := trailingFragmentV6(t, 0xAABBCCDD, 100, false, 40)
require.True(t, m.filterInbound(frag, len(frag)),
"IPv6 trailing fragment without an allowed first fragment must be dropped")
}
// TestFragmentV6_AllowedFirstPassesTrailing verifies IPv6 fragments are
// evaluated like IPv4: an allowed first fragment lets its trailing fragments
// through.
func TestFragmentV6_AllowedFirstPassesTrailing(t *testing.T) {
m := newFragmentTestManager(t)
_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrcV6), fw.ProtocolUDP, nil,
&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
require.NoError(t, err)
// First fragment: UDP header (8) + 32 data = 40 octets -> headerEnd = 5.
first := firstFragmentUDPv6(t, 0xAABBCCDD, 8080, 32)
require.False(t, m.filterInbound(first, len(first)),
"allowed IPv6 first fragment should pass and be recorded")
trailing := trailingFragmentV6(t, 0xAABBCCDD, 5, false, 24)
require.False(t, m.filterInbound(trailing, len(trailing)),
"trailing fragment of an allowed IPv6 datagram should pass")
}
// TestFragmentV6_AtomicNotCached verifies an IPv6 atomic fragment (fragment
// header with offset 0 and no More Fragments, a complete datagram per RFC 6946)
// is evaluated but not recorded, so a flood of allowed atomic fragments can't
// exhaust the verdict table.
func TestFragmentV6_AtomicNotCached(t *testing.T) {
m := newFragmentTestManager(t)
_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrcV6), fw.ProtocolUDP, nil,
&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
require.NoError(t, err)
atomic := fragmentUDPv6(t, 0xA70301C, 8080, 16, false)
require.False(t, m.filterInbound(atomic, len(atomic)),
"allowed IPv6 atomic fragment should pass")
m.fragments.mutex.Lock()
n := len(m.fragments.entries)
m.fragments.mutex.Unlock()
require.Zero(t, n, "atomic fragment must not create a verdict entry")
// A genuine fragmented datagram (More Fragments set) is still recorded.
first := fragmentUDPv6(t, 0xBEEF, 8080, 32, true)
require.False(t, m.filterInbound(first, len(first)))
m.fragments.mutex.Lock()
n = len(m.fragments.entries)
m.fragments.mutex.Unlock()
require.Equal(t, 1, n, "genuine first fragment must record a verdict")
}

View File

@@ -3,31 +3,14 @@
package netstack
import (
"net"
"fmt"
"os"
"strconv"
log "github.com/sirupsen/logrus"
)
const (
EnvUseNetstackMode = "NB_USE_NETSTACK_MODE"
// EnvSocks5ListenerPort overrides the port the SOCKS5 proxy listens on.
EnvSocks5ListenerPort = "NB_SOCKS5_LISTENER_PORT"
// EnvSocks5ListenerAddress overrides the host/IP the SOCKS5 proxy binds to.
// The proxy is a bridge for local host applications into the userspace
// WireGuard netstack, so it binds to loopback by default. Override this only
// when the proxy must be reachable from other hosts (e.g. a container
// gateway); doing so exposes an unauthenticated SOCKS5 proxy on that
// address.
EnvSocks5ListenerAddress = "NB_SOCKS5_LISTENER_ADDRESS"
// defaultSocks5Host is the loopback address the SOCKS5 proxy binds to unless
// overridden via EnvSocks5ListenerAddress.
defaultSocks5Host = "127.0.0.1"
)
const EnvUseNetstackMode = "NB_USE_NETSTACK_MODE"
// IsEnabled todo: move these function to cmd layer
func IsEnabled() bool {
@@ -35,40 +18,24 @@ func IsEnabled() bool {
}
func ListenAddr() string {
return net.JoinHostPort(listenHost(), strconv.Itoa(listenPort()))
}
// listenHost returns the host/IP the SOCKS5 proxy binds to. It defaults to
// loopback and only honors EnvSocks5ListenerAddress when it holds a valid IP.
func listenHost() string {
addr := os.Getenv(EnvSocks5ListenerAddress)
if addr == "" {
return defaultSocks5Host
}
if net.ParseIP(addr) == nil {
log.Warnf("invalid socks5 listener address %q, falling back to default: %s", addr, defaultSocks5Host)
return defaultSocks5Host
}
return addr
}
// listenPort returns the port the SOCKS5 proxy binds to, defaulting to
// DefaultSocks5Port when EnvSocks5ListenerPort is unset or invalid.
func listenPort() int {
sPort := os.Getenv(EnvSocks5ListenerPort)
sPort := os.Getenv("NB_SOCKS5_LISTENER_PORT")
if sPort == "" {
return DefaultSocks5Port
return listenAddr(DefaultSocks5Port)
}
port, err := strconv.Atoi(sPort)
if err != nil {
log.Warnf("invalid socks5 listener port, unable to convert it to int, falling back to default: %d", DefaultSocks5Port)
return DefaultSocks5Port
return listenAddr(DefaultSocks5Port)
}
if port < 1 || port > 65535 {
log.Warnf("invalid socks5 listener port, it should be in the range 1-65535, falling back to default: %d", DefaultSocks5Port)
return DefaultSocks5Port
return listenAddr(DefaultSocks5Port)
}
return port
return listenAddr(port)
}
func listenAddr(port int) string {
return fmt.Sprintf("0.0.0.0:%d", port)
}

View File

@@ -1,63 +0,0 @@
//go:build !js
package netstack
import (
"net"
"strconv"
"testing"
)
func TestListenAddr_DefaultsToLoopback(t *testing.T) {
// No env overrides: must bind loopback, never all interfaces.
got := ListenAddr()
want := net.JoinHostPort("127.0.0.1", strconv.Itoa(DefaultSocks5Port))
if got != want {
t.Fatalf("ListenAddr() = %q, want %q", got, want)
}
}
func TestListenAddr_AddressOverride(t *testing.T) {
tests := []struct {
name string
env string
want string
}{
{name: "valid override honored", env: "0.0.0.0", want: "0.0.0.0"},
{name: "valid specific ip honored", env: "10.0.0.5", want: "10.0.0.5"},
{name: "ipv6 loopback bracketed", env: "::1", want: "::1"},
{name: "invalid falls back to loopback", env: "not-an-ip", want: "127.0.0.1"},
{name: "empty falls back to loopback", env: "", want: "127.0.0.1"},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
t.Setenv(EnvSocks5ListenerAddress, tc.env)
want := net.JoinHostPort(tc.want, strconv.Itoa(DefaultSocks5Port))
if got := ListenAddr(); got != want {
t.Fatalf("ListenAddr() = %q, want %q", got, want)
}
})
}
}
func TestListenAddr_PortOverride(t *testing.T) {
tests := []struct {
name string
env string
want int
}{
{name: "valid port honored", env: "1081", want: 1081},
{name: "non-numeric falls back", env: "abc", want: DefaultSocks5Port},
{name: "out of range falls back", env: "70000", want: DefaultSocks5Port},
{name: "zero falls back", env: "0", want: DefaultSocks5Port},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
t.Setenv(EnvSocks5ListenerPort, tc.env)
want := net.JoinHostPort("127.0.0.1", strconv.Itoa(tc.want))
if got := ListenAddr(); got != want {
t.Fatalf("ListenAddr() = %q, want %q", got, want)
}
})
}
}

View File

@@ -259,18 +259,12 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn
ticker := time.NewTicker(interval)
defer ticker.Stop()
log.Infof("device flow: waiting for user authorization, polling token endpoint every %s, code expires in %s", interval, timeout)
start := time.Now()
polls := 0
for {
select {
case <-waitCtx.Done():
return TokenInfo{}, waitCtx.Err()
case <-ticker.C:
polls++
tokenResponse, err := d.requestToken(info)
if err != nil {
return TokenInfo{}, fmt.Errorf("parsing token response failed with error: %v", err)
@@ -278,12 +272,10 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn
if tokenResponse.Error != "" {
if tokenResponse.Error == "authorization_pending" {
log.Tracef("device flow: authorization still pending after poll %d", polls)
continue
} else if tokenResponse.Error == "slow_down" {
interval += (3 * time.Second)
ticker.Reset(interval)
log.Infof("device flow: IdP requested slow_down, polling interval increased to %s", interval)
continue
}
@@ -299,12 +291,11 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn
UseIDToken: d.providerConfig.UseIDToken,
}
err = validateTokenAudience(tokenInfo.GetTokenToUse(), d.providerConfig.Audience)
err = isValidAccessToken(tokenInfo.GetTokenToUse(), d.providerConfig.Audience)
if err != nil {
return TokenInfo{}, fmt.Errorf("validate access token failed with error: %v", err)
}
log.Infof("device flow: user authorization confirmed after %d polls in %s", polls, time.Since(start).Round(time.Second))
return tokenInfo, err
}
}

View File

@@ -188,8 +188,6 @@ func (p *PKCEAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowInfo
waitCtx, cancel := context.WithTimeout(ctx, timeout)
defer cancel()
log.Infof("pkce flow: waiting for authorization callback on %s, timeout %s", p.oAuthConfig.RedirectURL, timeout)
tokenChan := make(chan *oauth2.Token, 1)
errChan := make(chan error, 1)
@@ -223,7 +221,6 @@ func (p *PKCEAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowInfo
func (p *PKCEAuthorizationFlow) startServer(server *http.Server, tokenChan chan<- *oauth2.Token, errChan chan<- error) {
mux := http.NewServeMux()
mux.HandleFunc("/", func(w http.ResponseWriter, req *http.Request) {
log.Infof("pkce flow: received authorization callback from IdP")
cert := p.providerConfig.ClientCertPair
if cert != nil {
tr := &http.Transport{
@@ -274,18 +271,11 @@ func (p *PKCEAuthorizationFlow) handleRequest(req *http.Request) (*oauth2.Token,
return nil, fmt.Errorf("authentication failed: missing code")
}
exchangeStart := time.Now()
token, err := p.oAuthConfig.Exchange(
return p.oAuthConfig.Exchange(
req.Context(),
code,
oauth2.SetAuthURLParam("code_verifier", p.codeVerifier),
)
if err != nil {
return nil, err
}
log.Infof("pkce flow: authorization code exchanged for token in %s", time.Since(exchangeStart).Round(time.Millisecond))
return token, nil
}
func (p *PKCEAuthorizationFlow) parseOAuthToken(token *oauth2.Token) (TokenInfo, error) {
@@ -306,7 +296,7 @@ func (p *PKCEAuthorizationFlow) parseOAuthToken(token *oauth2.Token) (TokenInfo,
audience = p.providerConfig.ClientID
}
if err := validateTokenAudience(tokenInfo.GetTokenToUse(), audience); err != nil {
if err := isValidAccessToken(tokenInfo.GetTokenToUse(), audience); err != nil {
return TokenInfo{}, fmt.Errorf("authentication failed: invalid access token - %w", err)
}
@@ -320,11 +310,6 @@ func (p *PKCEAuthorizationFlow) parseOAuthToken(token *oauth2.Token) (TokenInfo,
return tokenInfo, nil
}
// parseEmailFromIDToken extracts the email (or name) claim from an ID token
// without verifying its signature. The value is best-effort and used only as a
// UX convenience (login hint prefill and display); it never drives an
// authorization decision. The authoritative identity is established server-side
// from the signature-verified token.
func parseEmailFromIDToken(token string) (string, error) {
parts := strings.Split(token, ".")
if len(parts) < 2 {

View File

@@ -24,7 +24,11 @@ import (
)
const (
maxPastHorizon = 30 * 24 * time.Hour
// Skew tolerates a small clock difference between the management
// server and this peer before treating a deadline as "in the past".
// Slightly above typical NTP drift; tight enough that the UI doesn't
// paint a stale expiry as if it were valid.
Skew = 30 * time.Second
// maxDeadlineHorizon caps how far in the future an accepted deadline
// can sit. A timestamp beyond this is almost certainly a protocol
@@ -53,7 +57,7 @@ var (
ErrDeadlineTooFarFuture = errors.New("session deadline too far in the future")
// ErrDeadlineInPast is returned by Update when the supplied deadline
// is more than maxPastHorizon in the past.
// is more than Skew in the past.
ErrDeadlineInPast = errors.New("session deadline in the past")
)
@@ -62,14 +66,15 @@ var (
// for deadline change/clear, PublishEvent for the two warnings); tests pass
// a fake recorder so the same surface is observable without an engine.
//
// While the watcher runs, it owns the deadline propagated to the recorder:
// every set, clear and sanity-check rejection routes the value through
// SetSessionExpiresAt, so the SubscribeStatus snapshot the UI reads can
// never drift from the watcher's timer state. (SetSessionExpiresAt fans
// out its own state-change notification, so no separate notify is needed.)
// The recorder is server-scoped and outlives this engine-scoped watcher;
// Close deliberately leaves the recorder value in place so transient engine
// restarts don't blank it — the client run loop clears it on real teardown.
// The watcher is the single owner of the deadline propagated to the
// recorder: every set, clear, sanity-check rejection and Close routes the
// value through SetSessionExpiresAt, so the SubscribeStatus snapshot the UI
// reads can never drift from the watcher's timer state. (SetSessionExpiresAt
// fans out its own state-change notification, so no separate notify is
// needed.) The recorder is server-scoped and outlives this engine-scoped
// watcher — without the Close-time clear a teardown (Down, or the Down+Up of
// a profile switch) would leave the next session showing the previous one's
// stale "expires in" value.
//
// PublishEvent's signature mirrors peer.Status.PublishEvent: the watcher
// composes the metadata internally so the wire format (MetaSession*) is
@@ -130,13 +135,10 @@ func NewWithLeads(lead, final time.Duration, recorder StatusRecorder) *Watcher {
// was disabled).
//
// Same-value updates are no-ops. A different non-zero value cancels any
// pending timer, resets the "already fired" guards, and — when the
// deadline lies in the future — arms fresh warning timers. A deadline
// already in the past (within maxPastHorizon) is recorded as-is with no
// timers: the session has expired and consumers render it that way.
// pending timer, resets the "already fired" guard, and arms a new one.
//
// Returns one of the sentinel Err* values when the deadline fails the
// sanity checks (pre-epoch, far future, or past beyond maxPastHorizon).
// sanity checks (pre-epoch, far future, or in the past beyond Skew).
// In every error case the watcher first clears its state so it stays
// consistent with what the caller will push into its other sinks (e.g.
// applySessionDeadline forces a zero deadline into the status recorder
@@ -161,7 +163,7 @@ func (w *Watcher) Update(deadline time.Time) error {
case deadline.After(now.Add(maxDeadlineHorizon)):
w.clearLocked()
return fmt.Errorf("%w: %v", ErrDeadlineTooFarFuture, deadline)
case deadline.Before(now.Add(-maxPastHorizon)):
case deadline.Before(now.Add(-Skew)):
w.clearLocked()
return fmt.Errorf("%w: %v (now=%v)", ErrDeadlineInPast, deadline, now)
}
@@ -181,9 +183,7 @@ func (w *Watcher) Update(deadline time.Time) error {
w.finalFiredAt = time.Time{}
w.dismissedAt = time.Time{}
if deadline.After(now) {
w.armTimerLocked(deadline)
}
w.armTimerLocked(deadline)
recorder := w.recorder
w.mu.Unlock()
if recorder != nil {
@@ -227,25 +227,30 @@ func (w *Watcher) Dismiss() {
log.Infof("auth session final-warning dismissed for deadline %s", w.current.Format(time.RFC3339))
}
// Close stops any pending timer. Update calls after Close are ignored.
// The recorder keeps its deadline: the watcher is engine-scoped and closes
// on every engine restart (network change, sleep/wake, stream errors)
// while the SSO deadline stays valid across those, so clearing here would
// blank the UI's "expires in" row on every transient reconnect. The
// client run loop clears the server-scoped recorder when it exits for
// real (Down, profile switch, permanent login failure).
// Close stops any pending timer and drops the deadline on the status
// recorder. Update calls after Close are ignored. Clearing the recorder
// here is what keeps a teardown (Down, or the Down+Up of a profile switch)
// from leaving the next session showing this one's stale "expires in"
// value — the recorder is server-scoped and outlives this engine-scoped
// watcher, so nothing else drops the anchor on teardown.
func (w *Watcher) Close() {
w.mu.Lock()
defer w.mu.Unlock()
if w.closed {
w.mu.Unlock()
return
}
w.closed = true
w.stopTimerLocked()
hadDeadline := !w.current.IsZero()
w.current = time.Time{}
w.firedAt = time.Time{}
w.finalFiredAt = time.Time{}
w.dismissedAt = time.Time{}
recorder := w.recorder
w.mu.Unlock()
if recorder != nil && hadDeadline {
recorder.SetSessionExpiresAt(time.Time{})
}
}
// clearLocked drops the tracked deadline and notifies the recorder so

View File

@@ -224,13 +224,11 @@ func TestNewDeadlineCancelsPriorTimer(t *testing.T) {
func TestRefreshAfterFireArmsNewWarning(t *testing.T) {
r := &fakeRecorder{}
lead := 150 * time.Millisecond
lead := 30 * time.Millisecond
w := newWatcher(lead, r)
defer w.Close()
// Warning fires ~20ms in; the deadline itself stays 150ms away so the
// replacement below lands well before it.
first := time.Now().Add(170 * time.Millisecond)
first := time.Now().Add(50 * time.Millisecond)
_ = w.Update(first)
// Wait for stateChange + warning of the first cycle.
@@ -308,29 +306,7 @@ func TestUpdateRejectsTooFarFuture(t *testing.T) {
}
}
func TestUpdateRecentPastRecordedAsExpired(t *testing.T) {
r := &fakeRecorder{}
w := newWatcher(50*time.Millisecond, r)
defer w.Close()
d := time.Now().Add(-1 * time.Hour)
if err := w.Update(d); err != nil {
t.Fatalf("recent-past Update should succeed, got %v", err)
}
if !w.Deadline().Equal(d) {
t.Fatalf("expected deadline to be recorded, got %v want %v", w.Deadline(), d)
}
if got := r.deadline(); !got.Equal(d) {
t.Fatalf("recorder deadline = %v, want %v", got, d)
}
time.Sleep(80 * time.Millisecond)
if n := countWhere(r.snapshot(), func(e event) bool { return e.kind == publish }); n != 0 {
t.Fatalf("no warning events may fire for an already-past deadline, got %+v", r.snapshot())
}
}
func TestUpdateAncientPastRejected(t *testing.T) {
func TestUpdateInPastClearsDeadline(t *testing.T) {
r := &fakeRecorder{}
w := newWatcher(50*time.Millisecond, r)
defer w.Close()
@@ -342,12 +318,12 @@ func TestUpdateAncientPastRejected(t *testing.T) {
// Drain the stateChange from the seed.
waitForEvents(t, r, 1)
err := w.Update(time.Now().Add(-31 * 24 * time.Hour))
err := w.Update(time.Now().Add(-1 * time.Hour))
if !errors.Is(err, ErrDeadlineInPast) {
t.Fatalf("want ErrDeadlineInPast, got %v", err)
}
if !w.Deadline().IsZero() {
t.Fatalf("rejected ancient-past update must clear the deadline, got %v", w.Deadline())
t.Fatalf("in-past update must clear the deadline, got %v", w.Deadline())
}
events := waitForEvents(t, r, 2)
if events[1].kind != stateChange {
@@ -355,25 +331,39 @@ func TestUpdateAncientPastRejected(t *testing.T) {
}
}
func TestUpdateWithinSkewAccepted(t *testing.T) {
r := &fakeRecorder{}
w := newWatcher(50*time.Millisecond, r)
defer w.Close()
// 5 seconds in the past is within the 30s Skew tolerance — accept it.
d := time.Now().Add(-5 * time.Second)
if err := w.Update(d); err != nil {
t.Fatalf("within-skew Update should succeed, got %v", err)
}
if !w.Deadline().Equal(d) {
t.Fatalf("expected deadline to be applied, got %v want %v", w.Deadline(), d)
}
}
func TestCloseSilencesUpdates(t *testing.T) {
r := &fakeRecorder{}
w := newWatcher(50*time.Millisecond, r)
w.Close()
if err := w.Update(time.Now().Add(time.Hour)); err != nil {
t.Fatalf("Update after Close: want nil, got %v", err)
}
_ = w.Update(time.Now().Add(time.Hour))
time.Sleep(20 * time.Millisecond)
if got := r.snapshot(); len(got) != 0 {
t.Fatalf("expected no events after Close, got %+v", got)
}
}
// TestCloseKeepsRecorderDeadline pins the reconnect-flap fix: the watcher
// closes on every engine restart (network change, sleep/wake) while the
// SSO deadline stays valid across those, so Close must leave the
// server-scoped recorder's value in place. The client run loop clears the
// recorder when it exits for real.
func TestCloseKeepsRecorderDeadline(t *testing.T) {
// TestCloseClearsRecorderDeadline pins the profile-switch fix: a watcher
// holding a live deadline must zero the recorder on Close so the next
// engine's watcher (and the UI reading the shared server-scoped recorder)
// doesn't start out showing the previous session's stale "expires in".
func TestCloseClearsRecorderDeadline(t *testing.T) {
r := &fakeRecorder{}
w := newWatcher(time.Hour, r)
@@ -387,8 +377,8 @@ func TestCloseKeepsRecorderDeadline(t *testing.T) {
w.Close()
if got := r.deadline(); !got.Equal(d) {
t.Fatalf("recorder deadline after Close = %v, want %v", got, d)
if got := r.deadline(); !got.IsZero() {
t.Fatalf("recorder deadline after Close = %v, want zero", got)
}
}

View File

@@ -20,26 +20,14 @@ func randomBytesInHex(count int) (string, error) {
return hex.EncodeToString(buf), nil
}
// validateTokenAudience checks that the token is a well-formed JWT whose
// audience claim matches the expected audience.
//
// It does NOT verify the token's cryptographic signature and therefore must not
// be treated as an authenticity check. The token is obtained by the client
// directly from the IdP token endpoint over TLS, and its signature is verified
// server-side by the management server against the IdP's JWKS
// (see shared/auth/jwt/validator.go). This function is only a client-side
// sanity check that the returned token targets the expected audience.
func validateTokenAudience(token string, audience string) error {
// isValidAccessToken is a simple validation of the access token
func isValidAccessToken(token string, audience string) error {
if token == "" {
return fmt.Errorf("token received is empty")
}
parts := strings.Split(token, ".")
if len(parts) != 3 {
return fmt.Errorf("token is not a well-formed JWT")
}
claimsString, err := base64.RawURLEncoding.DecodeString(parts[1])
encodedClaims := strings.Split(token, ".")[1]
claimsString, err := base64.RawURLEncoding.DecodeString(encodedClaims)
if err != nil {
return err
}

View File

@@ -1,108 +0,0 @@
package auth
import (
"encoding/base64"
"encoding/json"
"testing"
)
// makeJWT builds an unsigned JWT-shaped string (header.payload.signature) with
// the given claims payload. The signature part is arbitrary because
// validateTokenAudience intentionally does not verify it.
func makeJWT(t *testing.T, claims map[string]interface{}) string {
t.Helper()
header := base64.RawURLEncoding.EncodeToString([]byte(`{"alg":"RS256","typ":"JWT"}`))
payloadBytes, err := json.Marshal(claims)
if err != nil {
t.Fatalf("marshal claims: %v", err)
}
payload := base64.RawURLEncoding.EncodeToString(payloadBytes)
return header + "." + payload + ".unverified-signature"
}
func TestValidateTokenAudience(t *testing.T) {
tests := []struct {
name string
token string
audience string
wantErr bool
}{
{
name: "empty token",
token: "",
audience: "netbird",
wantErr: true,
},
{
name: "not a JWT - no dots",
token: "notajwt",
audience: "netbird",
wantErr: true,
},
{
name: "not a JWT - two parts only",
token: "header.payload",
audience: "netbird",
wantErr: true,
},
{
name: "matching string audience",
token: makeJWT(t, map[string]interface{}{"aud": "netbird"}),
audience: "netbird",
wantErr: false,
},
{
name: "mismatching string audience",
token: makeJWT(t, map[string]interface{}{"aud": "other"}),
audience: "netbird",
wantErr: true,
},
{
name: "matching audience in array",
token: makeJWT(t, map[string]interface{}{"aud": []interface{}{"other", "netbird"}}),
audience: "netbird",
wantErr: false,
},
{
name: "mismatching audience array",
token: makeJWT(t, map[string]interface{}{"aud": []interface{}{"a", "b"}}),
audience: "netbird",
wantErr: true,
},
{
name: "missing audience claim",
token: makeJWT(t, map[string]interface{}{"sub": "user"}),
audience: "netbird",
wantErr: true,
},
{
name: "invalid base64 payload",
token: "header.!!!not-base64!!!.sig",
audience: "netbird",
wantErr: true,
},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
err := validateTokenAudience(tc.token, tc.audience)
if tc.wantErr && err == nil {
t.Fatalf("expected error, got nil")
}
if !tc.wantErr && err != nil {
t.Fatalf("expected no error, got %v", err)
}
})
}
}
// TestValidateTokenAudienceNoPanic guards the regression where a non-empty
// token without the JWT dot structure caused an index-out-of-range panic.
func TestValidateTokenAudienceNoPanic(t *testing.T) {
inputs := []string{"a", ".", "a.", "aaaa", "no-dots-here"}
for _, in := range inputs {
if err := validateTokenAudience(in, "netbird"); err == nil {
t.Fatalf("expected error for malformed token %q, got nil", in)
}
}
}

View File

@@ -109,7 +109,7 @@ func (e *ConnMgr) UpdatedRemoteFeatureFlag(ctx context.Context, enabled bool) er
return nil
}
log.Infof("lazy connection manager is enabled by the management feature flag")
log.Warnf("lazy connection manager is enabled by management feature flag")
e.initLazyManager(ctx)
e.statusRecorder.UpdateLazyConnection(true)
return e.addPeersToLazyConnManager()

View File

@@ -257,10 +257,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
log.Errorf("failed to clean up temporary installer file: %v", err)
}
defer func() {
c.statusRecorder.SetSessionExpiresAt(time.Time{})
c.statusRecorder.ClientStop()
}()
defer c.statusRecorder.ClientStop()
operation := func() error {
// if context cancelled we not start new backoff cycle
if c.ctx.Err() != nil {

View File

@@ -480,6 +480,7 @@ func (g *BundleGenerator) addStatus() error {
fullStatus := g.statusRecorder.GetFullStatus()
protoFullStatus := nbstatus.ToProtoFullStatus(fullStatus)
protoFullStatus.Events = g.statusRecorder.GetEventHistory()
overview := nbstatus.ConvertToStatusOutputOverview(protoFullStatus, nbstatus.ConvertOptions{
Anonymize: g.anonymize,
ProfileName: profName,

View File

@@ -292,16 +292,18 @@ func (s *serviceViaListener) generateFreePort() (uint16, error) {
return customPort, nil
}
probeListener, err := net.ListenUDP("udp4", &net.UDPAddr{})
udpAddr := net.UDPAddrFromAddrPort(netip.MustParseAddrPort("0.0.0.0:0"))
probeListener, err := net.ListenUDP("udp", udpAddr)
if err != nil {
log.Debugf("failed to bind random port for DNS: %s", err)
return 0, err
}
port := uint16(probeListener.LocalAddr().(*net.UDPAddr).Port)
if err = probeListener.Close(); err != nil {
addrPort := netip.MustParseAddrPort(probeListener.LocalAddr().String()) // might panic if address is incorrect
err = probeListener.Close()
if err != nil {
log.Debugf("failed to free up DNS port: %s", err)
return 0, err
}
return port, nil
return addrPort.Port(), nil
}

View File

@@ -52,14 +52,11 @@ int xdp_dns_fwd(struct iphdr *ip, struct udphdr *udp) {
if (udp->dest == GENERAL_DNS_PORT && ip->daddr == dns_ip) {
udp->dest = dns_port;
// Clear the now-stale checksum; zero means "not computed" for IPv4.
udp->check = 0;
return XDP_PASS;
}
if (udp->source == dns_port && ip->saddr == dns_ip) {
udp->source = GENERAL_DNS_PORT;
udp->check = 0;
return XDP_PASS;
}

View File

@@ -50,11 +50,5 @@ int xdp_wg_proxy(struct iphdr *ip, struct udphdr *udp) {
__be16 new_dst_port = htons(proxy_port);
udp->dest = new_dst_port;
udp->source = new_src_port;
// The ports are covered by the UDP checksum. This is an IPv4 loopback hop
// and the payload is already integrity-protected, so clear the checksum (a
// zero UDP checksum means "not computed" for IPv4) rather than leave a
// stale value the kernel would drop as UDP_CSUM.
udp->check = 0;
return XDP_PASS;
}

View File

@@ -551,7 +551,7 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
} else {
log.Infof("running rosenpass in strict mode")
}
e.rpManager, err = rosenpass.NewManager(e.config.PreSharedKey, e.config.WgIfaceName, publicKey)
e.rpManager, err = rosenpass.NewManager(e.config.PreSharedKey, e.config.WgIfaceName)
if err != nil {
return fmt.Errorf("create rosenpass manager: %w", err)
}
@@ -2605,14 +2605,13 @@ func (e *Engine) updateForwardRules(rules []*mgmProto.ForwardingRule) ([]firewal
func (e *Engine) toExcludedLazyPeers(rules []firewallManager.ForwardRule, peers []*mgmProto.RemotePeerConfig) map[string]bool {
excludedPeers := make(map[string]bool)
// Ingress forward targets: inbound forwarded traffic is initiated remotely and
// cannot wake a lazy connection, so the peer routing the target must stay
// permanently connected. AllowedIPs are already parsed on the peer conn, so
// reuse those typed prefixes instead of re-parsing the network map strings.
for _, r := range rules {
ip := r.TranslatedAddress
for _, p := range peers {
if e.peerRoutesAddr(p, r.TranslatedAddress) {
for _, allowedIP := range p.GetAllowedIps() {
if allowedIP != ip.String() {
continue
}
log.Infof("exclude forwarder peer from lazy connection: %s", p.GetWgPubKey())
excludedPeers[p.GetWgPubKey()] = true
}
@@ -2622,27 +2621,6 @@ func (e *Engine) toExcludedLazyPeers(rules []firewallManager.ForwardRule, peers
return excludedPeers
}
// peerRoutesAddr reports whether the peer is a router for addr, matched against
// the peer's already-parsed AllowedIPs from the store (the same typed value the
// lazy manager consumes) rather than re-parsing the network map strings.
func (e *Engine) peerRoutesAddr(p *mgmProto.RemotePeerConfig, addr netip.Addr) bool {
prefixes, ok := e.peerStore.AllowedIPs(p.GetWgPubKey())
if !ok {
return false
}
return prefixesContain(prefixes, addr)
}
// prefixesContain reports whether addr falls within any of the prefixes.
func prefixesContain(prefixes []netip.Prefix, addr netip.Addr) bool {
for _, prefix := range prefixes {
if prefix.Contains(addr) {
return true
}
}
return false
}
// isChecksEqual checks if two slices of checks are equal.
func isChecksEqual(checks1, checks2 []*mgmProto.Checks) bool {
normalize := func(checks []*mgmProto.Checks) []string {

View File

@@ -1,87 +0,0 @@
package internal
import (
"net/netip"
"testing"
"github.com/stretchr/testify/require"
firewallManager "github.com/netbirdio/netbird/client/firewall/manager"
"github.com/netbirdio/netbird/client/internal/peer"
"github.com/netbirdio/netbird/client/internal/peerstore"
mgmProto "github.com/netbirdio/netbird/shared/management/proto"
)
func TestPrefixesContain(t *testing.T) {
tests := []struct {
name string
prefixes []string
addr string
want bool
}{
{name: "own overlay /32 matches", prefixes: []string{"100.110.8.145/32"}, addr: "100.110.8.145", want: true},
{name: "addr inside routed subnet", prefixes: []string{"10.121.0.0/16"}, addr: "10.121.208.4", want: true},
{name: "addr outside subnet", prefixes: []string{"10.121.0.0/16"}, addr: "10.122.0.1", want: false},
{name: "different /32", prefixes: []string{"100.110.8.145/32"}, addr: "100.110.8.146", want: false},
{name: "ipv6 /128 matches", prefixes: []string{"fd00::1/128"}, addr: "fd00::1", want: true},
{name: "no prefixes", prefixes: nil, addr: "10.121.208.4", want: false},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
prefixes := make([]netip.Prefix, 0, len(tt.prefixes))
for _, p := range tt.prefixes {
prefixes = append(prefixes, netip.MustParsePrefix(p))
}
require.Equal(t, tt.want, prefixesContain(prefixes, netip.MustParseAddr(tt.addr)))
})
}
}
// TestToExcludedLazyPeers_ForwardTarget guards a regression: the forward-target
// peer (the peer routing a ForwardRule.TranslatedAddress) must be excluded from
// lazy connections, matched via the peer's already-parsed AllowedIPs.
func TestToExcludedLazyPeers_ForwardTarget(t *testing.T) {
const targetPeerKey = "cccccccccccccccccccccccccccccccccccccccccc0="
const otherPeerKey = "dddddddddddddddddddddddddddddddddddddddddd0="
store := peerstore.NewConnStore()
store.AddPeerConn(targetPeerKey, newTestConn(t, targetPeerKey, "100.110.8.145/32"))
store.AddPeerConn(otherPeerKey, newTestConn(t, otherPeerKey, "100.110.9.10/32"))
e := &Engine{peerStore: store}
peers := []*mgmProto.RemotePeerConfig{
{WgPubKey: targetPeerKey, AllowedIps: []string{"100.110.8.145/32"}},
{WgPubKey: otherPeerKey, AllowedIps: []string{"100.110.9.10/32"}},
}
rules := []firewallManager.ForwardRule{
{TranslatedAddress: netip.MustParseAddr("100.110.8.145")},
}
excluded := e.toExcludedLazyPeers(rules, peers)
require.True(t, excluded[targetPeerKey], "forward-target peer must be excluded from lazy connections")
require.False(t, excluded[otherPeerKey], "non-target peer must not be excluded")
require.Len(t, excluded, 1)
}
func TestToExcludedLazyPeers_NoRules(t *testing.T) {
e := &Engine{peerStore: peerstore.NewConnStore()}
peers := []*mgmProto.RemotePeerConfig{
{WgPubKey: "peer-a", AllowedIps: []string{"100.110.8.145/32"}},
}
require.Empty(t, e.toExcludedLazyPeers(nil, peers))
}
func newTestConn(t *testing.T, key, allowedIP string) *peer.Conn {
t.Helper()
conn, err := peer.NewConn(peer.ConnConfig{
Key: key,
WgConfig: peer.WgConfig{AllowedIps: []netip.Prefix{netip.MustParsePrefix(allowedIP)}},
}, peer.ServiceDependencies{})
require.NoError(t, err)
return conn
}

View File

@@ -75,14 +75,4 @@ func TestApplySessionDeadline_ThreeState(t *testing.T) {
require.True(t, e.statusRecorder.GetSessionExpiresAt().IsZero(),
"invalid timestamp must clear the deadline")
})
t.Run("recently expired timestamp stays visible as expired", func(t *testing.T) {
e := newEngine()
expired := time.Now().Add(-5 * time.Minute).UTC().Truncate(time.Second)
e.ApplySessionDeadline(timestamppb.New(expired))
require.True(t, e.statusRecorder.GetSessionExpiresAt().Equal(expired),
"recently-expired deadline must stay on the recorder so consumers render it as expired")
})
}

View File

@@ -175,9 +175,10 @@ func TestFlowAggregationOfUnknownProtocols(t *testing.T) {
}
func TestResetAggregationWindow(t *testing.T) {
now := time.Now()
nowFunc := func() time.Time { return now }
store := NewAggregatingMemoryStoreWithTimeFunc(nowFunc)
store := NewAggregatingMemoryStore()
// Backdate the window start so the reset produces a different timestamp
// even on platforms with coarse clock granularity.
store.WindowStart = store.WindowStart.Add(-time.Second)
store.StoreEvent(&types.Event{
ID: uuid.New(),
Timestamp: time.Now(),
@@ -200,7 +201,6 @@ func TestResetAggregationWindow(t *testing.T) {
},
})
now = now.Add(1 * time.Second)
reset := store.ResetAggregationWindow()
previousEvents, ok := reset.(*AggregatingMemory)
assert.True(t, ok)

View File

@@ -29,7 +29,6 @@ type AggregatingMemory struct {
WindowStart time.Time
WindowEnd time.Time
rnd *v2.PCG
nowFunc func() time.Time
}
func (m *Memory) StoreEvent(event *types.Event) {
@@ -63,19 +62,14 @@ func (m *Memory) DeleteEvents(ids []uuid.UUID) {
}
func NewAggregatingMemoryStore() *AggregatingMemory {
return NewAggregatingMemoryStoreWithTimeFunc(defaultNowFunc)
}
// used in tests when deterministic (less random) time intervals are required
func NewAggregatingMemoryStoreWithTimeFunc(nowFunc func() time.Time) *AggregatingMemory {
return &AggregatingMemory{WindowStart: nowFunc(), Memory: Memory{events: make(map[uuid.UUID]*types.Event)}, nowFunc: nowFunc, rnd: v2.NewPCG(rand.Uint64(), rand.Uint64())}
return &AggregatingMemory{WindowStart: time.Now(), Memory: Memory{events: make(map[uuid.UUID]*types.Event)}, rnd: v2.NewPCG(rand.Uint64(), rand.Uint64())}
}
func (am *AggregatingMemory) ResetAggregationWindow() types.FlowEventAggregator {
am.mux.Lock()
defer am.mux.Unlock()
now := am.nowFunc()
now := time.Now()
toret := AggregatingMemory{WindowStart: am.WindowStart, WindowEnd: now, Memory: Memory{events: am.events}, rnd: v2.NewPCG(rand.Uint64(), rand.Uint64())}
am.events = make(map[uuid.UUID]*types.Event)
@@ -158,7 +152,3 @@ func (am *AggregatingMemory) GetAggregatedEvents() []*types.Event {
return slices.Collect(maps.Values(aggregated)) // could return an iterator instead here
}
func defaultNowFunc() time.Time {
return time.Now()
}

View File

@@ -30,11 +30,6 @@ import (
relayClient "github.com/netbirdio/netbird/shared/relay/client"
)
// wgTimeoutEscalationThreshold is the number of consecutive WireGuard
// handshake timeouts after which the rosenpass state for the peer is
// considered desynced and gets reset.
const wgTimeoutEscalationThreshold = 3
// MetricsRecorder is an interface for recording peer connection metrics
type MetricsRecorder interface {
RecordConnectionStages(
@@ -123,9 +118,6 @@ type Conn struct {
wgWatcher *WGWatcher
wgWatcherWg sync.WaitGroup
wgWatcherCancel context.CancelFunc
// wgTimeouts counts consecutive WireGuard handshake timeouts without a
// successful handshake in between. Guarded by mu.
wgTimeouts int
// used to store the remote Rosenpass key for Relayed connection in case of connection update from ice
rosenpassRemoteKey []byte
@@ -203,6 +195,7 @@ func NewConn(config ConnConfig, services ServiceDependencies) (*Conn, error) {
statusICE: worker.NewAtomicStatus(),
dumpState: dumpState,
endpointUpdater: NewEndpointUpdater(connLog, config.WgConfig, isController(config)),
wgWatcher: NewWGWatcher(connLog, config.WgConfig.WgInterface, config.Key, dumpState),
metricsRecorder: services.MetricsRecorder,
}
@@ -670,12 +663,11 @@ func (conn *Conn) onGuardEvent() {
}
}
func (conn *Conn) onWGDisconnected(watcherCtx context.Context) {
func (conn *Conn) onWGDisconnected() {
conn.mu.Lock()
defer conn.mu.Unlock()
// watcherCtx guards against a stale watcher tearing down a connection that already superseded it.
if conn.ctx.Err() != nil || watcherCtx.Err() != nil {
if conn.ctx.Err() != nil {
return
}
@@ -691,29 +683,6 @@ func (conn *Conn) onWGDisconnected(watcherCtx context.Context) {
default:
conn.Log.Debugf("No active connection to close on WG timeout")
}
conn.escalateWGTimeoutLocked()
}
// escalateWGTimeoutLocked resets the peer's rosenpass state after repeated
// handshake timeouts. With rosenpass enabled, persistent timeouts mean the
// preshared keys have desynced; the renewal exchange runs over the dead
// tunnel and cannot resync them. Reporting the peer disconnected drops its
// rosenpass state, so the next connection configuration programs the
// rendezvous key and the tunnel can bootstrap again. Callers must hold mu.
func (conn *Conn) escalateWGTimeoutLocked() {
if conn.config.RosenpassConfig.PubKey == nil {
return
}
conn.wgTimeouts++
if conn.wgTimeouts < wgTimeoutEscalationThreshold || conn.onDisconnected == nil {
return
}
conn.wgTimeouts = 0
conn.Log.Warnf("%d consecutive WireGuard handshake timeouts, resetting rosenpass state for peer", wgTimeoutEscalationThreshold)
conn.onDisconnected(conn.config.WgConfig.RemoteKey)
}
func (conn *Conn) updateRelayStatus(relayServerAddr string, rosenpassPubKey []byte, updateTime time.Time) {
@@ -833,39 +802,25 @@ func (conn *Conn) isConnectedOnAllWay() (status guard.ConnStatus) {
})
}
// enableWgWatcherIfNeeded starts a fresh watcher instance per connection attempt, so its
// lifecycle stays bound to conn.mu and enable/disable can't race an old goroutine's shutdown.
// Caller must hold conn.mu.
func (conn *Conn) enableWgWatcherIfNeeded(enabledTime time.Time) {
if conn.wgWatcher != nil {
if !conn.wgWatcher.PrepareInitialHandshake() {
return
}
watcher := NewWGWatcher(conn.Log, conn.config.WgConfig.WgInterface, conn.config.Key, conn.dumpState)
watcher.PrepareInitialHandshake()
wgWatcherCtx, wgWatcherCancel := context.WithCancel(conn.ctx)
conn.wgWatcher = watcher
conn.wgWatcherCancel = wgWatcherCancel
conn.wgWatcherWg.Add(1)
go func() {
defer conn.wgWatcherWg.Done()
onDisconnected := func() { conn.onWGDisconnected(wgWatcherCtx) }
watcher.EnableWgWatcher(wgWatcherCtx, enabledTime, onDisconnected, conn.onWGHandshakeSuccess, conn.onWGCheckSuccess)
conn.wgWatcher.EnableWgWatcher(wgWatcherCtx, enabledTime, conn.onWGDisconnected, conn.onWGHandshakeSuccess)
}()
}
// disableWgWatcherIfNeeded cancels and drops the watcher once no transport is active. It never
// waits for the goroutine: the timeout path reentrantly calls back here under conn.mu, so
// blocking would deadlock. Caller must hold conn.mu.
func (conn *Conn) disableWgWatcherIfNeeded() {
if conn.currentConnPriority != conntype.None || conn.wgWatcher == nil {
return
if conn.currentConnPriority == conntype.None && conn.wgWatcherCancel != nil {
conn.wgWatcherCancel()
conn.wgWatcherCancel = nil
}
conn.wgWatcherCancel()
conn.wgWatcher = nil
conn.wgWatcherCancel = nil
}
func (conn *Conn) newProxy(remoteConn net.Conn) (wgproxy.Proxy, error) {
@@ -888,9 +843,7 @@ func (conn *Conn) resetEndpoint() {
return
}
conn.Log.Infof("reset wg endpoint")
if conn.wgWatcher != nil {
conn.wgWatcher.Reset()
}
conn.wgWatcher.Reset()
if err := conn.endpointUpdater.RemoveEndpointAddress(); err != nil {
conn.Log.Warnf("failed to remove endpoint address before update: %v", err)
}
@@ -939,15 +892,6 @@ func (conn *Conn) onWGHandshakeSuccess(when time.Time) {
conn.recordConnectionMetrics()
}
// onWGCheckSuccess is called for every watcher check that observed a fresh
// handshake, including handshakes of connections that were already up when
// the watcher started.
func (conn *Conn) onWGCheckSuccess() {
conn.mu.Lock()
conn.wgTimeouts = 0
conn.mu.Unlock()
}
// recordConnectionMetrics records connection stage timestamps as metrics
func (conn *Conn) recordConnectionMetrics() {
if conn.metricsRecorder == nil {

View File

@@ -7,7 +7,6 @@ import (
"testing"
"time"
log "github.com/sirupsen/logrus"
"github.com/stretchr/testify/assert"
"github.com/netbirdio/netbird/client/iface"
@@ -305,84 +304,3 @@ func TestConn_presharedKey_RosenpassManaged(t *testing.T) {
t.Fatalf("expected non-nil presharedKey before Rosenpass manages PSK")
}
}
func newWGTimeoutTestConn(rosenpassEnabled bool, disconnected *[]string) *Conn {
cfg := ConnConfig{
Key: "LLHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
LocalKey: "RRHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
WgConfig: WgConfig{RemoteKey: "LLHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU="},
}
if rosenpassEnabled {
cfg.RosenpassConfig = RosenpassConfig{PubKey: []byte("dummykey")}
}
conn := &Conn{
ctx: context.Background(),
config: cfg,
Log: log.WithField("peer", cfg.Key),
metricsStages: &MetricsStages{},
}
conn.SetOnDisconnected(func(remotePeer string) {
*disconnected = append(*disconnected, remotePeer)
})
return conn
}
// TestConn_onWGDisconnected_EscalatesToRosenpassReset: repeated handshake
// timeouts with rosenpass enabled mean the preshared keys have desynced. The
// renewal exchange runs over the dead tunnel and cannot resync them, so after
// wgTimeoutEscalationThreshold consecutive timeouts the conn must report the
// peer disconnected, dropping its rosenpass state so the next configuration
// programs the rendezvous key.
func TestConn_onWGDisconnected_EscalatesToRosenpassReset(t *testing.T) {
var disconnected []string
conn := newWGTimeoutTestConn(true, &disconnected)
for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
conn.onWGDisconnected(conn.ctx)
}
assert.Empty(t, disconnected, "escalation must not fire below the threshold")
conn.onWGDisconnected(conn.ctx)
assert.Equal(t, []string{conn.config.WgConfig.RemoteKey}, disconnected,
"reaching the threshold must report the peer disconnected once")
for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
conn.onWGDisconnected(conn.ctx)
}
assert.Len(t, disconnected, 1, "escalation must restart counting after firing")
conn.onWGDisconnected(conn.ctx)
assert.Len(t, disconnected, 2, "continued timeouts must escalate again")
}
// TestConn_onWGDisconnected_CheckSuccessResetsEscalation: a successful
// handshake between timeouts means the tunnel recovered; the counter must
// start over.
func TestConn_onWGDisconnected_CheckSuccessResetsEscalation(t *testing.T) {
var disconnected []string
conn := newWGTimeoutTestConn(true, &disconnected)
for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
conn.onWGDisconnected(conn.ctx)
}
conn.onWGCheckSuccess()
for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
conn.onWGDisconnected(conn.ctx)
}
assert.Empty(t, disconnected, "handshake success must reset the timeout count")
}
// TestConn_onWGDisconnected_NoEscalationWithoutRosenpass: without rosenpass
// there is no per-peer key state to reset; repeated timeouts must not report
// disconnects.
func TestConn_onWGDisconnected_NoEscalationWithoutRosenpass(t *testing.T) {
var disconnected []string
conn := newWGTimeoutTestConn(false, &disconnected)
for i := 0; i < wgTimeoutEscalationThreshold*3; i++ {
conn.onWGDisconnected(conn.ctx)
}
assert.Empty(t, disconnected, "escalation must be limited to rosenpass connections")
}

View File

@@ -813,14 +813,19 @@ func (d *Status) SetSessionExpiresAt(deadline time.Time) {
}
// GetSessionExpiresAt returns the most recently recorded SSO session deadline,
// or the zero value when no deadline is tracked. A deadline in the past is
// returned as-is: it means the session has expired, and consumers (tray row,
// CLI status) render it as "expired" rather than hiding it — masking it as
// "none" would blank the UI at the exact moment it should say the session
// ended.
// or the zero value when no deadline is tracked. A deadline that has already
// slipped into the past reports as "none": once the session has expired it is
// no longer a meaningful countdown, and the sessionwatch.Watcher does not
// arm a timer at the deadline itself to clear it (only the two pre-expiry
// warnings). Without this guard the UI would keep painting a stale
// "expires in …" against a moment that has passed until the next login,
// extend, or teardown rewrote the value.
func (d *Status) GetSessionExpiresAt() time.Time {
d.mux.Lock()
defer d.mux.Unlock()
if !d.sessionExpiresAt.IsZero() && d.sessionExpiresAt.Before(time.Now()) {
return time.Time{}
}
return d.sessionExpiresAt
}

View File

@@ -3,6 +3,7 @@ package peer
import (
"context"
"fmt"
"sync"
"time"
log "github.com/sirupsen/logrus"
@@ -23,14 +24,14 @@ type WGInterfaceStater interface {
GetStats() (map[string]configurer.WGStats, error)
}
// WGWatcher is single-shot: one instance per connection attempt, run once, then discarded.
// Lifecycle is owned by Conn under conn.mu, so it keeps no "enabled" state to go stale.
type WGWatcher struct {
log *log.Entry
wgIfaceStater WGInterfaceStater
peerKey string
stateDump *stateDump
enabled bool
muEnabled sync.Mutex
// initialHandshake is not thread-safe; never call PrepareInitialHandshake and EnableWgWatcher concurrently.
initialHandshake time.Time
@@ -47,23 +48,36 @@ func NewWGWatcher(log *log.Entry, wgIfaceStater WGInterfaceStater, peerKey strin
}
}
// PrepareInitialHandshake reads the peer's current WireGuard handshake time. It must be
// called before the peer is (re)configured on the WireGuard interface, so the captured
// baseline reflects the state prior to this connection attempt instead of racing with
// that configuration.
func (w *WGWatcher) PrepareInitialHandshake() {
// PrepareInitialHandshake reserves the watcher and reads the peer's current WireGuard
// handshake time. It must be called before the peer is (re)configured on the WireGuard
// interface, so the captured baseline reflects the state prior to this connection attempt
// instead of racing with that configuration. Returns ok=false if the watcher is already
// running, in which case EnableWgWatcher must not be called.
func (w *WGWatcher) PrepareInitialHandshake() (ok bool) {
w.muEnabled.Lock()
if w.enabled {
w.muEnabled.Unlock()
return false
}
w.log.Debugf("enable WireGuard watcher")
w.enabled = true
w.muEnabled.Unlock()
handshake, _ := w.wgState()
w.initialHandshake = handshake
return true
}
// EnableWgWatcher runs the WireGuard watcher loop using the handshake baseline captured by
// PrepareInitialHandshake. The watcher runs until ctx is cancelled. Caller is responsible
// for context lifecycle management. onHandshakeSuccessFn is called only for the first
// handshake observed by this run, onCheckSuccessFn for every check that observed a fresh
// handshake, including the first.
func (w *WGWatcher) EnableWgWatcher(ctx context.Context, enabledTime time.Time, onDisconnectedFn func(), onHandshakeSuccessFn func(when time.Time), onCheckSuccessFn func()) {
w.periodicHandshakeCheck(ctx, onDisconnectedFn, onHandshakeSuccessFn, onCheckSuccessFn, enabledTime, w.initialHandshake)
// for context lifecycle management.
func (w *WGWatcher) EnableWgWatcher(ctx context.Context, enabledTime time.Time, onDisconnectedFn func(), onHandshakeSuccessFn func(when time.Time)) {
w.periodicHandshakeCheck(ctx, onDisconnectedFn, onHandshakeSuccessFn, enabledTime, w.initialHandshake)
w.muEnabled.Lock()
w.enabled = false
w.muEnabled.Unlock()
}
// Reset signals the watcher that the WireGuard peer has been reset and a new
@@ -76,7 +90,7 @@ func (w *WGWatcher) Reset() {
}
// wgStateCheck help to check the state of the WireGuard handshake and relay connection
func (w *WGWatcher) periodicHandshakeCheck(ctx context.Context, onDisconnectedFn func(), onHandshakeSuccessFn func(when time.Time), onCheckSuccessFn func(), enabledTime time.Time, initialHandshake time.Time) {
func (w *WGWatcher) periodicHandshakeCheck(ctx context.Context, onDisconnectedFn func(), onHandshakeSuccessFn func(when time.Time), enabledTime time.Time, initialHandshake time.Time) {
w.log.Infof("WireGuard watcher started")
timer := time.NewTimer(wgHandshakeOvertime)
@@ -89,7 +103,6 @@ func (w *WGWatcher) periodicHandshakeCheck(ctx context.Context, onDisconnectedFn
case <-timer.C:
handshake, ok := w.handshakeCheck(lastHandshake)
if !ok {
// early ctx cancel check return
if ctx.Err() != nil {
return
}
@@ -104,10 +117,6 @@ func (w *WGWatcher) periodicHandshakeCheck(ctx context.Context, onDisconnectedFn
}
}
if onCheckSuccessFn != nil && ctx.Err() == nil {
onCheckSuccessFn()
}
lastHandshake = *handshake
resetTime := time.Until(handshake.Add(checkPeriod))
@@ -138,9 +147,9 @@ func (w *WGWatcher) handshakeCheck(lastHandshake time.Time) (*time.Time, bool) {
w.log.Tracef("previous handshake, handshake: %v, %v", lastHandshake, handshake)
// the current known handshake did not change
// the current know handshake did not change
if handshake.Equal(lastHandshake) {
w.log.Warnf("WireGuard handshake not updated: %v", handshake)
w.log.Warnf("WireGuard handshake timed out: %v", handshake)
return nil, false
}

View File

@@ -7,6 +7,7 @@ import (
"time"
log "github.com/sirupsen/logrus"
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/client/iface/configurer"
)
@@ -23,72 +24,6 @@ func (m *MocWgIface) disconnect() {
m.stop = true
}
type mockHandshakeStats struct {
mu sync.Mutex
handshake time.Time
}
func (m *mockHandshakeStats) GetStats() (map[string]configurer.WGStats, error) {
m.mu.Lock()
defer m.mu.Unlock()
return map[string]configurer.WGStats{"": {LastHandshake: m.handshake}}, nil
}
func (m *mockHandshakeStats) advance() {
m.mu.Lock()
defer m.mu.Unlock()
m.handshake = time.Now()
}
// TestWGWatcher_CheckSuccessCallback: onCheckSuccessFn must fire for a fresh
// handshake even when the watcher started with an existing handshake baseline,
// the case where onHandshakeSuccessFn stays silent.
func TestWGWatcher_CheckSuccessCallback(t *testing.T) {
// checkPeriod bounds how stale a handshake may be before the watcher treats it
// as a suspended-machine timeout. The first check fires after wgHandshakeOvertime,
// so keep checkPeriod well above any scheduling jitter to avoid a false timeout
// converting the expected success into a disconnect on a loaded runner.
checkPeriod = 1 * time.Minute
wgHandshakeOvertime = 1 * time.Second
mlog := log.WithField("peer", "tet")
// Use an old baseline so advance() yields a strictly newer handshake even on
// platforms with coarse clock resolution (Windows), where two time.Now() calls
// microseconds apart can return the same instant and read as a timed-out handshake.
stats := &mockHandshakeStats{handshake: time.Now().Add(-time.Hour)}
watcher := NewWGWatcher(mlog, stats, "", newStateDump("peer", mlog, &Status{}))
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
watcher.PrepareInitialHandshake()
firstHandshake := make(chan struct{}, 1)
checkSuccess := make(chan struct{}, 1)
go watcher.EnableWgWatcher(ctx, time.Now(), func() {}, func(when time.Time) {
firstHandshake <- struct{}{}
}, func() {
select {
case checkSuccess <- struct{}{}:
default:
}
})
stats.advance()
select {
case <-checkSuccess:
case <-time.After(10 * time.Second):
t.Errorf("timeout waiting for check success callback")
}
select {
case <-firstHandshake:
t.Errorf("first-handshake callback must not fire for a non-zero baseline")
default:
}
}
func TestWGWatcher_EnableWgWatcher(t *testing.T) {
checkPeriod = 5 * time.Second
wgHandshakeOvertime = 1 * time.Second
@@ -100,7 +35,8 @@ func TestWGWatcher_EnableWgWatcher(t *testing.T) {
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
watcher.PrepareInitialHandshake()
ok := watcher.PrepareInitialHandshake()
require.True(t, ok, "watcher should not be enabled yet")
onDisconnected := make(chan struct{}, 1)
go watcher.EnableWgWatcher(ctx, time.Now(), func() {
@@ -108,7 +44,7 @@ func TestWGWatcher_EnableWgWatcher(t *testing.T) {
onDisconnected <- struct{}{}
}, func(when time.Time) {
mlog.Infof("onHandshakeSuccess: %v", when)
}, nil)
})
// wait for initial reading
time.Sleep(2 * time.Second)
@@ -130,13 +66,14 @@ func TestWGWatcher_ReEnable(t *testing.T) {
watcher := NewWGWatcher(mlog, mocWgIface, "", newStateDump("peer", mlog, &Status{}))
ctx, cancel := context.WithCancel(context.Background())
watcher.PrepareInitialHandshake()
ok := watcher.PrepareInitialHandshake()
require.True(t, ok, "watcher should not be enabled yet")
wg := &sync.WaitGroup{}
wg.Add(1)
go func() {
defer wg.Done()
watcher.EnableWgWatcher(ctx, time.Now(), func() {}, func(when time.Time) {}, nil)
watcher.EnableWgWatcher(ctx, time.Now(), func() {}, func(when time.Time) {})
}()
cancel()
@@ -146,12 +83,13 @@ func TestWGWatcher_ReEnable(t *testing.T) {
ctx, cancel = context.WithCancel(context.Background())
defer cancel()
watcher.PrepareInitialHandshake()
ok = watcher.PrepareInitialHandshake()
require.True(t, ok, "watcher should be re-enabled after the previous run stopped")
onDisconnected := make(chan struct{}, 1)
go watcher.EnableWgWatcher(ctx, time.Now(), func() {
onDisconnected <- struct{}{}
}, func(when time.Time) {}, nil)
}, func(when time.Time) {})
time.Sleep(2 * time.Second)
mocWgIface.disconnect()

View File

@@ -11,7 +11,6 @@ import (
"runtime"
"sort"
"strings"
"syscall"
log "github.com/sirupsen/logrus"
@@ -440,11 +439,7 @@ func (s *ServiceManager) GetStatePath() string {
activeProf, err := s.GetActiveProfileState()
if err != nil {
if errors.Is(err, syscall.ENOSYS) {
log.Debugf("active profile state unavailable on this platform: %v", err)
} else {
log.Warnf("failed to get active profile state: %v", err)
}
log.Warnf("failed to get active profile state: %v", err)
return defaultStatePath
}

View File

@@ -39,7 +39,6 @@ type rpServer interface {
type Manager struct {
ifaceName string
localWgKey wgtypes.Key
spk []byte
ssk []byte
rpKeyHash string
@@ -52,9 +51,8 @@ type Manager struct {
wgIface PresharedKeySetter
}
// NewManager creates a new Rosenpass manager. localWgKey is the local
// WireGuard public key, used to derive the per-peer rendezvous key.
func NewManager(preSharedKey *wgtypes.Key, wgIfaceName string, localWgKey wgtypes.Key) (*Manager, error) {
// NewManager creates a new Rosenpass manager
func NewManager(preSharedKey *wgtypes.Key, wgIfaceName string) (*Manager, error) {
public, secret, err := rp.GenerateKeyPair()
if err != nil {
return nil, err
@@ -64,7 +62,6 @@ func NewManager(preSharedKey *wgtypes.Key, wgIfaceName string, localWgKey wgtype
log.Tracef("generated new rosenpass key pair with public key %s", rpKeyHash)
return &Manager{
ifaceName: wgIfaceName,
localWgKey: localWgKey,
rpKeyHash: rpKeyHash,
spk: public,
ssk: secret,
@@ -76,7 +73,7 @@ func NewManager(preSharedKey *wgtypes.Key, wgIfaceName string, localWgKey wgtype
// nil receiver in addPeer -> m.rpWgHandler.AddPeer. generateConfig will
// replace it with a fresh handler on each Run() to clear stale peer
// state from previous engine sessions.
rpWgHandler: NewNetbirdHandler((*[32]byte)(preSharedKey), localWgKey),
rpWgHandler: NewNetbirdHandler(),
lock: sync.Mutex{},
}, nil
}
@@ -164,7 +161,7 @@ func (m *Manager) generateConfig() (rp.Config, error) {
cfg.Peers = []rp.PeerConfig{}
m.lock.Lock()
m.rpWgHandler = NewNetbirdHandler(m.preSharedKey, m.localWgKey)
m.rpWgHandler = NewNetbirdHandler()
if m.wgIface != nil {
m.rpWgHandler.SetInterface(m.wgIface)
}

View File

@@ -85,7 +85,7 @@ func newTestManager(spkFirstByte byte, mock *mockServer) *Manager {
ssk: make([]byte, 32),
rpKeyHash: "test-hash",
rpPeerIDs: make(map[string]*rp.PeerID),
rpWgHandler: NewNetbirdHandler(nil, wgtypes.Key{0x01}),
rpWgHandler: NewNetbirdHandler(),
server: mock,
}
}
@@ -255,7 +255,7 @@ func TestAddPeer_NilServer_ReturnsErrorNoCrash(t *testing.T) {
// issue #4341 cannot occur in the window between NewManager and Run().
func TestNewManager_PreInitializesHandler(t *testing.T) {
psk := wgtypes.Key{}
m, err := NewManager(&psk, "wt0", wgtypes.Key{0x01})
m, err := NewManager(&psk, "wt0")
require.NoError(t, err)
require.NotNil(t, m.rpWgHandler, "rpWgHandler must be initialized in NewManager")
}
@@ -329,10 +329,10 @@ func TestIsPresharedKeyInitialized_AddedButNotHandshaken_ReturnsFalse(t *testing
require.False(t, m.IsPresharedKeyInitialized(wgKey))
}
// --- NetbirdHandler.applyKey ----------------------------------------------
// --- NetbirdHandler.outputKey ----------------------------------------------
func TestHandler_ApplyKey_FirstCallUsesUpdateOnlyFalse(t *testing.T) {
h := NewNetbirdHandler(nil, wgtypes.Key{0x01})
func TestHandler_OutputKey_FirstCallUsesUpdateOnlyFalse(t *testing.T) {
h := NewNetbirdHandler()
iface := &mockIface{}
h.SetInterface(iface)
@@ -348,8 +348,8 @@ func TestHandler_ApplyKey_FirstCallUsesUpdateOnlyFalse(t *testing.T) {
require.Equal(t, wgKey.String(), iface.calls[0].peerKey)
}
func TestHandler_ApplyKey_SubsequentCallsUseUpdateOnlyTrue(t *testing.T) {
h := NewNetbirdHandler(nil, wgtypes.Key{0x01})
func TestHandler_OutputKey_SubsequentCallsUseUpdateOnlyTrue(t *testing.T) {
h := NewNetbirdHandler()
iface := &mockIface{}
h.SetInterface(iface)
@@ -364,8 +364,8 @@ func TestHandler_ApplyKey_SubsequentCallsUseUpdateOnlyTrue(t *testing.T) {
require.True(t, iface.calls[1].updateOnly, "subsequent rotations must use updateOnly=true")
}
func TestHandler_ApplyKey_NilInterface_NoCrashNoCall(t *testing.T) {
h := NewNetbirdHandler(nil, wgtypes.Key{0x01})
func TestHandler_OutputKey_NilInterface_NoCrashNoCall(t *testing.T) {
h := NewNetbirdHandler()
// no SetInterface — iface remains nil
pid := rp.PeerID{0x03}
h.AddPeer(pid, "wt0", rp.Key(wgtypes.Key{}))
@@ -374,8 +374,8 @@ func TestHandler_ApplyKey_NilInterface_NoCrashNoCall(t *testing.T) {
h.HandshakeCompleted(pid, rp.Key{})
}
func TestHandler_ApplyKey_UnknownPeer_NoCall(t *testing.T) {
h := NewNetbirdHandler(nil, wgtypes.Key{0x01})
func TestHandler_OutputKey_UnknownPeer_NoCall(t *testing.T) {
h := NewNetbirdHandler()
iface := &mockIface{}
h.SetInterface(iface)
@@ -384,7 +384,7 @@ func TestHandler_ApplyKey_UnknownPeer_NoCall(t *testing.T) {
}
func TestHandler_RemovePeer_ClearsInitializedState(t *testing.T) {
h := NewNetbirdHandler(nil, wgtypes.Key{0x01})
h := NewNetbirdHandler()
iface := &mockIface{}
h.SetInterface(iface)
@@ -398,7 +398,7 @@ func TestHandler_RemovePeer_ClearsInitializedState(t *testing.T) {
}
func TestHandler_SetInterfaceAfterAddPeer_StillReceivesKey(t *testing.T) {
h := NewNetbirdHandler(nil, wgtypes.Key{0x01})
h := NewNetbirdHandler()
pid := rp.PeerID{0x05}
wgKey := wgtypes.Key{0xEE}
h.AddPeer(pid, "wt0", rp.Key(wgKey))

View File

@@ -18,34 +18,19 @@ type PresharedKeySetter interface {
type wireGuardPeer struct {
Interface string
PublicKey rp.Key
// initialized is true once a completed exchange has set a
// Rosenpass-managed PSK for this peer.
initialized bool
// chainKey is the key output by the last completed exchange, advanced by
// one ratchet step on expiry. Nil until the first exchange completes and
// after the peer has fallen back to the rendezvous key.
chainKey *wgtypes.Key
// expiries counts failed renewals since the last completed exchange.
expiries int
}
type NetbirdHandler struct {
mu sync.Mutex
iface PresharedKeySetter
// preSharedKey is the account-level preshared key, used as the rendezvous
// key when set. Nil means the deterministic seed key is used instead.
preSharedKey *[32]byte
// localWgKey is the local WireGuard public key, one of the two inputs to
// the deterministic seed key.
localWgKey wgtypes.Key
peers map[rp.PeerID]*wireGuardPeer
mu sync.Mutex
iface PresharedKeySetter
peers map[rp.PeerID]wireGuardPeer
initializedPeers map[rp.PeerID]bool
}
func NewNetbirdHandler(preSharedKey *[32]byte, localWgKey wgtypes.Key) *NetbirdHandler {
func NewNetbirdHandler() *NetbirdHandler {
return &NetbirdHandler{
preSharedKey: preSharedKey,
localWgKey: localWgKey,
peers: map[rp.PeerID]*wireGuardPeer{},
peers: map[rp.PeerID]wireGuardPeer{},
initializedPeers: map[rp.PeerID]bool{},
}
}
@@ -57,16 +42,10 @@ func (h *NetbirdHandler) SetInterface(iface PresharedKeySetter) {
h.iface = iface
}
// AddPeer registers a peer with the handler. Re-adding a known peer (every
// reconnection does) keeps its key recovery state.
func (h *NetbirdHandler) AddPeer(pid rp.PeerID, intf string, pk rp.Key) {
h.mu.Lock()
defer h.mu.Unlock()
if existing, ok := h.peers[pid]; ok && existing.PublicKey == pk {
existing.Interface = intf
return
}
h.peers[pid] = &wireGuardPeer{
h.peers[pid] = wireGuardPeer{
Interface: intf,
PublicKey: pk,
}
@@ -76,6 +55,7 @@ func (h *NetbirdHandler) RemovePeer(pid rp.PeerID) {
h.mu.Lock()
defer h.mu.Unlock()
delete(h.peers, pid)
delete(h.initializedPeers, pid)
}
// IsPeerInitialized returns true if Rosenpass has completed a handshake
@@ -83,120 +63,50 @@ func (h *NetbirdHandler) RemovePeer(pid rp.PeerID) {
func (h *NetbirdHandler) IsPeerInitialized(pid rp.PeerID) bool {
h.mu.Lock()
defer h.mu.Unlock()
peer, ok := h.peers[pid]
return ok && peer.initialized
return h.initializedPeers[pid]
}
// HandshakeCompleted programs the freshly exchanged output key and resets the
// peer's key recovery state.
func (h *NetbirdHandler) HandshakeCompleted(pid rp.PeerID, key rp.Key) {
psk := wgtypes.Key(key)
h.mu.Lock()
defer h.mu.Unlock()
peer, ok := h.peers[pid]
if !ok {
return
}
if peer.expiries > 0 {
log.Infof("rosenpass exchange completed for peer %s after %d expired renewals", wgtypes.Key(peer.PublicKey), peer.expiries)
}
// chainKey tracks the shared exchange output regardless of the local write
// outcome, so both ends still converge on the next expiry.
peer.chainKey = &psk
peer.expiries = 0
if !h.applyKeyLocked(pid, psk, peer.initialized) {
return
}
peer.initialized = true
h.outputKey(rp.KeyOutputReasonStale, pid, key)
}
// HandshakeExpired replaces the expired key. The renewal exchange runs over
// the tunnel keyed by the PSK itself, so the replacement must be derivable on
// both ends without communication: the first expiry ratchets the last shared
// key forward, repeated expiries (and expiries without a completed exchange)
// fall back to the rendezvous key and drop the peer out of the initialized
// state so connection reconfigurations reprogram the rendezvous key as well.
func (h *NetbirdHandler) HandshakeExpired(pid rp.PeerID) {
key, _ := rp.GeneratePresharedKey()
h.outputKey(rp.KeyOutputReasonStale, pid, key)
}
func (h *NetbirdHandler) outputKey(_ rp.KeyOutputReason, pid rp.PeerID, psk rp.Key) {
h.mu.Lock()
defer h.mu.Unlock()
iface := h.iface
wg, ok := h.peers[pid]
isInitialized := h.initializedPeers[pid]
h.mu.Unlock()
peer, ok := h.peers[pid]
if !ok {
return
}
peer.expiries++
var psk wgtypes.Key
if peer.chainKey != nil && peer.expiries == 1 {
log.Infof("rosenpass key for peer %s expired without renewal, advancing to ratcheted key", wgtypes.Key(peer.PublicKey))
psk = RatchetKey(*peer.chainKey)
peer.chainKey = &psk
} else {
rendezvous, err := h.rendezvousKey(peer)
if err != nil {
// Fail closed: without a rendezvous key the expired key must
// still be rotated out, even if the replacement is unusable.
log.Errorf("failed to derive rendezvous key, replacing expired key with a random one: %v", err)
h.applyRandomKeyLocked(pid)
return
}
log.Warnf("rosenpass key for peer %s expired %d times without renewal, falling back to the rendezvous key", wgtypes.Key(peer.PublicKey), peer.expiries)
psk = rendezvous
peer.chainKey = nil
peer.initialized = false
}
h.applyKeyLocked(pid, psk, true)
}
// rendezvousKey returns the key both ends converge on without communication:
// the account-level preshared key when configured, the deterministic seed key
// otherwise. It mirrors the key that peer connections program when Rosenpass
// does not manage the peer yet.
func (h *NetbirdHandler) rendezvousKey(peer *wireGuardPeer) (wgtypes.Key, error) {
if h.preSharedKey != nil {
return *h.preSharedKey, nil
}
seed, err := DeterministicSeedKey(h.localWgKey.String(), wgtypes.Key(peer.PublicKey).String())
if err != nil {
return wgtypes.Key{}, err
}
return *seed, nil
}
// applyKeyLocked writes the preshared key for the peer to the WireGuard
// interface and reports whether the write succeeded. Callers must hold h.mu
// for the whole state-mutation-plus-write so that a concurrent completion and
// expiry cannot reorder their writes relative to the in-memory chain key.
func (h *NetbirdHandler) applyKeyLocked(pid rp.PeerID, psk wgtypes.Key, updateOnly bool) bool {
peer, ok := h.peers[pid]
if !ok {
return false
}
if h.iface == nil {
if iface == nil {
log.Warn("rosenpass: interface not set, cannot update preshared key")
return false
}
peerKey := wgtypes.Key(peer.PublicKey).String()
if err := h.iface.SetPresharedKey(peerKey, psk, updateOnly); err != nil {
log.Errorf("Failed to apply rosenpass key: %v", err)
return false
}
return true
}
func (h *NetbirdHandler) applyRandomKeyLocked(pid rp.PeerID) {
key, err := rp.GeneratePresharedKey()
if err != nil {
log.Errorf("failed to generate random preshared key: %v", err)
return
}
h.applyKeyLocked(pid, wgtypes.Key(key), true)
if !ok {
return
}
peerKey := wgtypes.Key(wg.PublicKey).String()
pskKey := wgtypes.Key(psk)
// Use updateOnly=true for later rotations (peer already has Rosenpass PSK)
// Use updateOnly=false for first rotation (peer has original/empty PSK)
if err := iface.SetPresharedKey(peerKey, pskKey, isInitialized); err != nil {
log.Errorf("Failed to apply rosenpass key: %v", err)
return
}
// Mark peer as isInitialized after the successful first rotation
if !isInitialized {
h.mu.Lock()
if _, exists := h.peers[pid]; exists {
h.initializedPeers[pid] = true
}
h.mu.Unlock()
}
}

View File

@@ -1,250 +0,0 @@
package rosenpass
import (
"testing"
rp "cunicu.li/go-rosenpass"
"github.com/stretchr/testify/require"
"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
)
// handlerTestLink wires two NetbirdHandlers as the two ends of a single
// tunnel: handler A manages the rosenpass peer B and vice versa, the way two
// NetBird clients see each other.
type handlerTestLink struct {
handlerA, handlerB *NetbirdHandler
ifaceA, ifaceB *mockIface
pidA, pidB rp.PeerID
wgKeyA, wgKeyB wgtypes.Key
}
func newHandlerTestLink(t *testing.T, preSharedKey *[32]byte) *handlerTestLink {
t.Helper()
link := &handlerTestLink{
ifaceA: &mockIface{},
ifaceB: &mockIface{},
}
link.pidA[0] = 0xaa
link.pidB[0] = 0xbb
link.wgKeyA[31] = 1
link.wgKeyB[31] = 2
link.handlerA = NewNetbirdHandler(preSharedKey, link.wgKeyA)
link.handlerB = NewNetbirdHandler(preSharedKey, link.wgKeyB)
link.handlerA.SetInterface(link.ifaceA)
link.handlerB.SetInterface(link.ifaceB)
link.handlerA.AddPeer(link.pidB, "wt0", rp.Key(link.wgKeyB))
link.handlerB.AddPeer(link.pidA, "wt0", rp.Key(link.wgKeyA))
return link
}
// complete simulates a completed rosenpass exchange: both ends derive the
// same output key.
func (l *handlerTestLink) complete(osk rp.Key) {
l.handlerA.HandshakeCompleted(l.pidB, osk)
l.handlerB.HandshakeCompleted(l.pidA, osk)
}
// expire simulates a failed key renewal on both ends.
func (l *handlerTestLink) expire() {
l.handlerA.HandshakeExpired(l.pidB)
l.handlerB.HandshakeExpired(l.pidA)
}
func lastPSK(t *testing.T, m *mockIface) wgtypes.Key {
t.Helper()
m.mu.Lock()
defer m.mu.Unlock()
require.NotEmpty(t, m.calls, "expected at least one SetPresharedKey call")
return m.calls[len(m.calls)-1].psk
}
func TestHandshakeCompleted_SetsKeyAndInitializes(t *testing.T) {
link := newHandlerTestLink(t, nil)
var osk rp.Key
osk[0] = 0x42
link.complete(osk)
require.Equal(t, wgtypes.Key(osk), lastPSK(t, link.ifaceA), "completed exchange must program the osk")
require.False(t, link.ifaceA.calls[0].updateOnly, "first rotation must not be update-only")
require.True(t, link.handlerA.IsPeerInitialized(link.pidB), "peer must be initialized after first completed exchange")
link.complete(osk)
require.True(t, link.ifaceA.calls[1].updateOnly, "later rotations must be update-only")
}
// TestHandshakeExpired_BothSidesConverge encodes the core recovery invariant:
// rosenpass renewals run over the tunnel that the PSK itself keys, so when a
// renewal fails on both ends, both ends must fall back to the same key or the
// tunnel can never handshake again.
func TestHandshakeExpired_BothSidesConverge(t *testing.T) {
link := newHandlerTestLink(t, nil)
var osk rp.Key
osk[0] = 0x42
link.complete(osk)
link.expire()
keyA := lastPSK(t, link.ifaceA)
keyB := lastPSK(t, link.ifaceB)
require.NotEqual(t, wgtypes.Key(osk), keyA, "expired key must be rotated out")
require.Equal(t, keyA, keyB, "both ends must converge on the same key after expiry")
link.expire()
require.Equal(t, lastPSK(t, link.ifaceA), lastPSK(t, link.ifaceB),
"both ends must still converge after repeated expiries")
}
// TestHandshakeExpired_ExpiryWithoutCompletionConverges covers the bootstrap
// case: the initial exchange never completed (the tunnel ran on the rendezvous
// key), so an expiry must not replace the working key with an unrecoverable
// one on either end.
func TestHandshakeExpired_ExpiryWithoutCompletionConverges(t *testing.T) {
link := newHandlerTestLink(t, nil)
link.expire()
require.Equal(t, lastPSK(t, link.ifaceA), lastPSK(t, link.ifaceB),
"both ends must converge when the exchange never completed")
}
// TestHandshakeExpired_RepeatedExpiryClearsInitialized: once renewals keep
// failing, the peer must drop out of the initialized state so the next
// connection reconfiguration reprograms the rendezvous key instead of
// preserving a poisoned rosenpass-managed key.
func TestHandshakeExpired_RepeatedExpiryClearsInitialized(t *testing.T) {
link := newHandlerTestLink(t, nil)
var osk rp.Key
osk[0] = 0x42
link.complete(osk)
link.expire()
link.expire()
require.False(t, link.handlerA.IsPeerInitialized(link.pidB),
"repeated expiries must clear the initialized state")
require.False(t, link.handlerB.IsPeerInitialized(link.pidA),
"repeated expiries must clear the initialized state")
}
// TestHandshakeCompleted_AfterExpiryRecovers: a completed exchange after a
// desync must fully reset the recovery state.
func TestHandshakeCompleted_AfterExpiryRecovers(t *testing.T) {
link := newHandlerTestLink(t, nil)
var osk1, osk2 rp.Key
osk1[0] = 1
osk2[0] = 2
link.complete(osk1)
link.expire()
link.expire()
link.complete(osk2)
require.Equal(t, wgtypes.Key(osk2), lastPSK(t, link.ifaceA), "new exchange must program the fresh osk")
require.True(t, link.handlerA.IsPeerInitialized(link.pidB), "peer must be initialized again after recovery")
link.expire()
require.Equal(t, lastPSK(t, link.ifaceA), lastPSK(t, link.ifaceB),
"recovered link must converge again on the next expiry")
require.NotEqual(t, wgtypes.Key(osk2), lastPSK(t, link.ifaceA), "expired key must be rotated out")
}
// TestHandshakeExpired_FirstExpiryRatchetsLastKey: the first expiry must
// derive the replacement from the last shared key, so an attacker who only
// blocks the renewal exchange gains nothing over the previous key.
func TestHandshakeExpired_FirstExpiryRatchetsLastKey(t *testing.T) {
link := newHandlerTestLink(t, nil)
var osk rp.Key
osk[0] = 0x42
link.complete(osk)
link.expire()
require.Equal(t, RatchetKey(wgtypes.Key(osk)), lastPSK(t, link.ifaceA),
"first expiry must program the ratcheted key")
require.True(t, link.handlerA.IsPeerInitialized(link.pidB),
"ratchet step must keep the peer initialized so reconfigurations preserve the key")
}
// TestHandshakeExpired_RepeatedExpiryFallsBackToSeed: once the ratchet key
// also fails, both ends must land on the same key that peer connections
// program for uninitialized peers, so a reconnect completes the recovery.
func TestHandshakeExpired_RepeatedExpiryFallsBackToSeed(t *testing.T) {
link := newHandlerTestLink(t, nil)
var osk rp.Key
osk[0] = 0x42
link.complete(osk)
link.expire()
link.expire()
seed, err := DeterministicSeedKey(link.wgKeyA.String(), link.wgKeyB.String())
require.NoError(t, err)
require.Equal(t, *seed, lastPSK(t, link.ifaceA), "repeated expiry must fall back to the seed key")
require.Equal(t, *seed, lastPSK(t, link.ifaceB), "repeated expiry must fall back to the seed key")
}
// TestHandshakeExpired_ConfiguredPSKUsedAsRendezvous: with an account-level
// preshared key configured, the fallback must be that key, matching what peer
// connections program for uninitialized peers.
func TestHandshakeExpired_ConfiguredPSKUsedAsRendezvous(t *testing.T) {
psk := &[32]byte{0x77}
link := newHandlerTestLink(t, psk)
var osk rp.Key
osk[0] = 0x42
link.complete(osk)
link.expire()
link.expire()
require.Equal(t, wgtypes.Key(*psk), lastPSK(t, link.ifaceA),
"fallback must be the configured preshared key")
require.Equal(t, wgtypes.Key(*psk), lastPSK(t, link.ifaceB),
"fallback must be the configured preshared key on both ends")
}
// TestHandshakeExpired_ExpiryWritesAreUpdateOnly: expiry replacements must
// never create a WireGuard peer that connection management has removed.
func TestHandshakeExpired_ExpiryWritesAreUpdateOnly(t *testing.T) {
link := newHandlerTestLink(t, nil)
var osk rp.Key
osk[0] = 0x42
link.complete(osk)
link.expire()
link.expire()
for _, call := range link.ifaceA.calls[1:] {
require.True(t, call.updateOnly, "expiry writes must be update-only")
}
}
// TestAddPeer_ReAddKeepsRecoveryState: reconnections re-add the peer on every
// OnConnected; that must not reset the expiry chain state.
func TestAddPeer_ReAddKeepsRecoveryState(t *testing.T) {
link := newHandlerTestLink(t, nil)
var osk rp.Key
osk[0] = 0x42
link.complete(osk)
link.expire()
link.handlerA.AddPeer(link.pidB, "wt0", rp.Key(link.wgKeyB))
require.True(t, link.handlerA.IsPeerInitialized(link.pidB),
"re-adding a known peer must keep its state")
link.expire()
seed, err := DeterministicSeedKey(link.wgKeyA.String(), link.wgKeyB.String())
require.NoError(t, err)
require.Equal(t, *seed, lastPSK(t, link.ifaceA),
"second expiry after re-add must continue to the seed fallback")
}

View File

@@ -1,28 +1,11 @@
package rosenpass
import (
"crypto/sha256"
"fmt"
"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
)
// ratchetLabel domain-separates the expiry ratchet from other uses of the
// rosenpass output key.
const ratchetLabel = "netbird-rosenpass-expiry-ratchet"
// RatchetKey derives the successor preshared key from the previous Rosenpass
// output key. When a key expires without a completed renewal, both peers
// advance their last shared key by one ratchet step: the expired key is
// rotated out while both ends still converge on an identical, non-public
// replacement without communicating.
func RatchetKey(prev wgtypes.Key) wgtypes.Key {
input := make([]byte, 0, len(ratchetLabel)+len(prev))
input = append(input, ratchetLabel...)
input = append(input, prev[:]...)
return sha256.Sum256(input)
}
// DeterministicSeedKey derives a 32-byte WireGuard preshared key from a pair
// of peer public keys. Both peers, given the same key pair, produce the same
// output regardless of which side runs the function: the inputs are ordered

View File

@@ -185,7 +185,7 @@ func (r *Route) startResolver(ctx context.Context) {
}
func (r *Route) update(ctx context.Context) error {
resolved, err := r.resolveDomains(ctx)
resolved, err := r.resolveDomains()
if err != nil {
if len(resolved) == 0 {
return fmt.Errorf("resolve domains: %w", err)
@@ -199,9 +199,9 @@ func (r *Route) update(ctx context.Context) error {
return nil
}
func (r *Route) resolveDomains(ctx context.Context) (domainMap, error) {
func (r *Route) resolveDomains() (domainMap, error) {
results := make(chan resolveResult)
go r.resolve(ctx, results)
go r.resolve(results)
resolved := domainMap{}
var merr *multierror.Error
@@ -217,7 +217,7 @@ func (r *Route) resolveDomains(ctx context.Context) (domainMap, error) {
return resolved, nberrors.FormatErrorOrNil(merr)
}
func (r *Route) resolve(ctx context.Context, results chan resolveResult) {
func (r *Route) resolve(results chan resolveResult) {
var wg sync.WaitGroup
for _, d := range r.route.Domains {
@@ -225,10 +225,10 @@ func (r *Route) resolve(ctx context.Context, results chan resolveResult) {
go func(domain domain.Domain) {
defer wg.Done()
ips, err := r.getIPsFromResolver(ctx, domain)
ips, err := r.getIPsFromResolver(domain)
if err != nil {
log.Tracef("Failed to resolve domain %s with private resolver: %v", domain.SafeString(), err)
ips, err = lookupHostIPs(ctx, domain)
ips, err = net.LookupIP(domain.PunycodeString())
if err != nil {
results <- resolveResult{domain: domain, err: fmt.Errorf("resolve d %s: %w", domain.SafeString(), err)}
return
@@ -364,20 +364,6 @@ func determinePrefixChanges(oldPrefixes, newPrefixes []netip.Prefix) (toAdd, toR
return
}
// lookupHostIPs resolves d via the system resolver, honoring ctx cancellation.
func lookupHostIPs(ctx context.Context, d domain.Domain) ([]net.IP, error) {
addrs, err := net.DefaultResolver.LookupIPAddr(ctx, d.PunycodeString())
if err != nil {
return nil, err
}
ips := make([]net.IP, 0, len(addrs))
for _, addr := range addrs {
ips = append(ips, addr.IP)
}
return ips, nil
}
func combinePrefixes(oldPrefixes, removedPrefixes, addedPrefixes []netip.Prefix) []netip.Prefix {
prefixSet := make(map[netip.Prefix]struct{})
for _, prefix := range oldPrefixes {

View File

@@ -3,12 +3,11 @@
package dynamic
import (
"context"
"net"
"github.com/netbirdio/netbird/shared/management/domain"
)
func (r *Route) getIPsFromResolver(ctx context.Context, domain domain.Domain) ([]net.IP, error) {
return lookupHostIPs(ctx, domain)
func (r *Route) getIPsFromResolver(domain domain.Domain) ([]net.IP, error) {
return net.LookupIP(domain.PunycodeString())
}

View File

@@ -3,7 +3,6 @@
package dynamic
import (
"context"
"fmt"
"net"
"time"
@@ -17,7 +16,7 @@ import (
const dialTimeout = 10 * time.Second
func (r *Route) getIPsFromResolver(ctx context.Context, domain domain.Domain) ([]net.IP, error) {
func (r *Route) getIPsFromResolver(domain domain.Domain) ([]net.IP, error) {
privateClient, err := nbdns.GetClientPrivate(r.wgInterface, r.resolverAddr.Addr(), dialTimeout)
if err != nil {
return nil, fmt.Errorf("error while creating private client: %s", err)
@@ -33,7 +32,7 @@ func (r *Route) getIPsFromResolver(ctx context.Context, domain domain.Domain) ([
msg := new(dns.Msg)
msg.SetQuestion(fqdn, qtype)
response, _, err := nbdns.ExchangeWithFallback(ctx, privateClient, msg, r.resolverAddr.String())
response, _, err := nbdns.ExchangeWithFallback(nil, privateClient, msg, r.resolverAddr.String())
if err != nil {
if queryErr == nil {
queryErr = fmt.Errorf("DNS query for %s (type %d) after %s: %w", domain.SafeString(), qtype, time.Since(startTime), err)

View File

@@ -12,7 +12,6 @@ import (
"strings"
"sync"
"sync/atomic"
"syscall"
"time"
"github.com/google/uuid"
@@ -265,11 +264,7 @@ func (m *DefaultManager) initSelector() *routeselector.RouteSelector {
// restore selector state if it exists
if err := m.stateManager.LoadState(state); err != nil {
if errors.Is(err, syscall.ENOSYS) {
log.Debugf("route selector state unavailable on this platform: %v", err)
} else {
log.Warnf("failed to load state: %v", err)
}
log.Warnf("failed to load state: %v", err)
return routeselector.NewRouteSelector()
}

View File

@@ -1,7 +1,6 @@
package statemanager
import (
"bytes"
"context"
"encoding/json"
"errors"
@@ -306,11 +305,6 @@ func (m *Manager) loadStateFile(deleteCorrupt bool) (map[string]json.RawMessage,
var rawStates map[string]json.RawMessage
if err := json.Unmarshal(data, &rawStates); err != nil {
if len(bytes.TrimSpace(data)) == 0 {
log.Warnf("state file %s is empty (%d bytes)", m.filePath, len(data))
} else {
log.Warnf("state file %s has malformed content (%d bytes)", m.filePath, len(data))
}
m.handleCorruptedState(deleteCorrupt)
return nil, fmt.Errorf("unmarshal states: %w", err)
}

View File

@@ -233,9 +233,6 @@ func (c *Client) DebugBundle(anonymize bool) (string, error) {
deps.SyncResponse = resp
if e := cc.Engine(); e != nil {
deps.RefreshStatus = func() {
e.RunHealthProbes(context.Background(), true)
}
if cm := e.GetClientMetrics(); cm != nil {
deps.ClientMetrics = cm
}

View File

@@ -44,25 +44,10 @@ type Auth struct {
// NewAuth instantiate Auth struct and validate the management URL
func NewAuth(cfgPath string, mgmURL string) (*Auth, error) {
inputCfg := profilemanager.ConfigInput{
ConfigPath: cfgPath,
ManagementURL: mgmURL,
}
// Load the existing config when a config file is already present so an
// interactive re-login reuses the peer's persisted WireGuard private key
// (and thus its identity) instead of generating a fresh one. Generating a
// new key registers a brand-new peer on the management server on every
// re-auth (named after the fallback hostname). Only fall back to a fresh
// in-memory config for the first-time login when no config file exists yet.
// DirectUpdateOrCreateConfig uses non-atomic writes so it also works inside
// the tvOS App Group sandbox where atomic temp-file+rename is blocked.
var cfg *profilemanager.Config
var err error
if cfgPath != "" {
cfg, err = profilemanager.DirectUpdateOrCreateConfig(inputCfg)
} else {
cfg, err = profilemanager.CreateInMemoryConfig(inputCfg)
}
cfg, err := profilemanager.CreateInMemoryConfig(inputCfg)
if err != nil {
return nil, err
}

View File

@@ -22,7 +22,6 @@ var allKeys = []string{
KeyDisableMetricsCollection,
KeyAllowServerSSH,
KeyDisableAutoConnect,
KeyDisableAutostart,
KeyPreSharedKey,
KeyRosenpassEnabled,
KeyRosenpassPermissive,

View File

@@ -20,10 +20,10 @@ import (
// names (lowerCamelCase) so the daemon can map a Policy key directly to a
// configuration field.
const (
KeyManagementURL = "managementURL"
KeyDisableUpdateSettings = "disableUpdateSettings"
KeyDisableProfiles = "disableProfiles"
KeyDisableNetworks = "disableNetworks"
KeyManagementURL = "managementURL"
KeyDisableUpdateSettings = "disableUpdateSettings"
KeyDisableProfiles = "disableProfiles"
KeyDisableNetworks = "disableNetworks"
// KeyDisableAdvancedView gates the advanced-view section in the
// upcoming UI revision. UI-only: NOT stored on Config, not
// applied by applyMDMPolicy, not rejectable via SetConfig. The
@@ -37,16 +37,10 @@ const (
KeyDisableMetricsCollection = "disableMetricsCollection"
KeyAllowServerSSH = "allowServerSSH"
KeyDisableAutoConnect = "disableAutoConnect"
// KeyDisableAutostart suppresses the GUI's fresh-install
// launch-on-login default and marks the Settings toggle as
// MDM-managed. UI-only: NOT stored on Config and not applied by
// applyMDMPolicy; the GUI reads it directly and it appears in
// GetConfigResponse.mDMManagedFields when set.
KeyDisableAutostart = "disableAutostart"
KeyPreSharedKey = "preSharedKey"
KeyRosenpassEnabled = "rosenpassEnabled"
KeyRosenpassPermissive = "rosenpassPermissive"
KeyWireguardPort = "wireguardPort"
KeyPreSharedKey = "preSharedKey"
KeyRosenpassEnabled = "rosenpassEnabled"
KeyRosenpassPermissive = "rosenpassPermissive"
KeyWireguardPort = "wireguardPort"
// Split tunnel is modeled as a single conceptual policy with two
// registry/plist values. KeySplitTunnelMode is the discriminator

View File

@@ -181,7 +181,7 @@ func (s *Server) Start() error {
log.Warnf("failed to redirect stderr: %v", err)
}
if err := RestoreResidualState(s.rootCtx, s.profileManager.GetStatePath()); err != nil {
if err := restoreResidualState(s.rootCtx, s.profileManager.GetStatePath()); err != nil {
log.Warnf(errRestoreResidualState, err)
}
@@ -551,7 +551,7 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro
s.actCancel = cancel
s.mutex.Unlock()
if err := RestoreResidualState(s.rootCtx, s.profileManager.GetStatePath()); err != nil {
if err := restoreResidualState(s.rootCtx, s.profileManager.GetStatePath()); err != nil {
log.Warnf(errRestoreResidualState, err)
}
@@ -828,7 +828,6 @@ func (s *Server) WaitSSOLogin(callerCtx context.Context, msg *proto.WaitSSOLogin
return nil, err
}
log.Infof("SSO login flow finished, returning success to caller")
return &proto.WaitSSOLoginResponse{
Email: tokenInfo.Email,
}, nil
@@ -836,7 +835,6 @@ func (s *Server) WaitSSOLogin(callerCtx context.Context, msg *proto.WaitSSOLogin
// Up starts engine work in the daemon.
func (s *Server) Up(callerCtx context.Context, msg *proto.UpRequest) (*proto.UpResponse, error) {
log.Infof("up request received")
s.mutex.Lock()
// clientRunning is the daemon-intent flag (set by previous Up/Start, cleared
// by Down). connectionGoroutineRunning() reports whether the previous retry-loop
@@ -858,7 +856,7 @@ func (s *Server) Up(callerCtx context.Context, msg *proto.UpRequest) (*proto.UpR
return s.waitForUp(callerCtx)
}
if err := RestoreResidualState(callerCtx, s.profileManager.GetStatePath()); err != nil {
if err := restoreResidualState(callerCtx, s.profileManager.GetStatePath()); err != nil {
log.Warnf(errRestoreResidualState, err)
}
@@ -1081,10 +1079,7 @@ func (s *Server) Down(ctx context.Context, _ *proto.DownRequest) (*proto.DownRes
if err := s.cleanupConnection(); err != nil {
s.mutex.Unlock()
if errors.Is(err, ErrServiceNotUp) {
log.Debugf("Down called while service not up: %v", err)
return nil, err
}
// todo review to update the status in case any type of error
log.Errorf("failed to shut down properly: %v", err)
return nil, err
}
@@ -1157,7 +1152,7 @@ func (s *Server) cleanupConnection() error {
// making the run loop the sole owner of engine shutdown.
if engine != nil {
if err := engine.Stop(); err != nil {
log.Errorf("failed to stop engine during cleanup: %v", err)
return err
}
}

View File

@@ -46,7 +46,7 @@ func (s *Server) CleanState(ctx context.Context, req *proto.CleanStateRequest) (
if req.All {
// Reuse existing cleanup logic for all states
if err := RestoreResidualState(ctx, statePath); err != nil {
if err := restoreResidualState(ctx, statePath); err != nil {
return nil, status.Errorf(codes.Internal, "failed to clean all states: %v", err)
}
@@ -113,9 +113,9 @@ func (s *Server) DeleteState(ctx context.Context, req *proto.DeleteStateRequest)
}, nil
}
// RestoreResidualState checks if the client was not shut down in a clean way and restores residual if required.
// restoreResidualState checks if the client was not shut down in a clean way and restores residual if required.
// Otherwise, we might not be able to connect to the management server to retrieve new config.
func RestoreResidualState(ctx context.Context, statePath string) error {
func restoreResidualState(ctx context.Context, statePath string) error {
if statePath == "" {
return nil
}

View File

@@ -14,7 +14,6 @@ import (
log "github.com/sirupsen/logrus"
nbssh "github.com/netbirdio/netbird/client/ssh"
"github.com/netbirdio/netbird/shared/management/domain"
)
const (
@@ -219,20 +218,11 @@ func (m *Manager) buildHostPatterns(peer PeerSSHInfo) []string {
if peer.IPv6.IsValid() {
hostPatterns = append(hostPatterns, peer.IPv6.String())
}
// Peer FQDNs and hostnames originate from remote peers, so they must be
// validated as plain DNS names before being embedded in the ssh_config
// "Match host" pattern list. This prevents injection of arbitrary
// ssh_config directives via embedded quotes, whitespace, newlines, the
// comma pattern separator, or the "*"/"?" pattern metacharacters.
if domain.IsValidDomainNoWildcard(peer.FQDN) {
if peer.FQDN != "" {
hostPatterns = append(hostPatterns, peer.FQDN)
} else if peer.FQDN != "" {
log.Warnf("skipping peer FQDN with invalid characters in SSH config: %q", peer.FQDN)
}
if peer.Hostname != peer.FQDN && domain.IsValidDomainNoWildcard(peer.Hostname) {
if peer.Hostname != "" && peer.Hostname != peer.FQDN {
hostPatterns = append(hostPatterns, peer.Hostname)
} else if peer.Hostname != "" && peer.Hostname != peer.FQDN {
log.Warnf("skipping peer hostname with invalid characters in SSH config: %q", peer.Hostname)
}
return hostPatterns
}

View File

@@ -148,45 +148,6 @@ func TestManager_MatchHostFormat(t *testing.T) {
"should use Match host with comma-separated patterns")
}
func TestManager_HostPatternInjection(t *testing.T) {
tempDir, err := os.MkdirTemp("", "netbird-ssh-config-test")
require.NoError(t, err)
defer func() { assert.NoError(t, os.RemoveAll(tempDir)) }()
manager := &Manager{
sshConfigDir: filepath.Join(tempDir, "ssh_config.d"),
sshConfigFile: "99-netbird.conf",
}
// A malicious peer FQDN/hostname attempts to break out of the Match host
// directive and inject arbitrary ssh_config (a ProxyCommand executing a
// command). It must be rejected, not written to the config.
peers := []PeerSSHInfo{
{
Hostname: "evil\"\n ProxyCommand touch /tmp/pwned\nHost x",
IP: netip.MustParseAddr("100.125.1.1"),
FQDN: "evil\"\n ProxyCommand touch /tmp/pwned\nHost x.nb.internal",
},
{Hostname: "peer2", IP: netip.MustParseAddr("100.125.1.2"), FQDN: "peer2.nb.internal"},
}
err = manager.SetupSSHClientConfig(peers)
require.NoError(t, err)
configPath := filepath.Join(manager.sshConfigDir, manager.sshConfigFile)
content, err := os.ReadFile(configPath)
require.NoError(t, err)
configStr := string(content)
assert.NotContains(t, configStr, "ProxyCommand touch /tmp/pwned",
"injected directive must not appear in generated config")
assert.NotContains(t, configStr, "evil",
"malicious pattern must be dropped entirely")
// The valid peer must still be present, on a single Match host line.
assert.Contains(t, configStr, "Match host \"100.125.1.1,100.125.1.2,peer2.nb.internal,peer2\"",
"valid peers must survive, injected patterns dropped")
}
func TestManager_ForcedSSHConfig(t *testing.T) {
// Set force environment variable
t.Setenv(EnvForceSSHConfig, "true")

View File

@@ -69,8 +69,7 @@ func parseGetentPasswd(output string) (*user.User, string, error) {
// 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.
// (@ for Kerberos, $ for Samba, + for NIS compat).
func validateGetentInput(input string) bool {
maxLen := 32
if runtime.GOOS == "linux" {
@@ -81,10 +80,6 @@ func validateGetentInput(input string) bool {
return false
}
if input[0] == '-' {
return false
}
for _, r := range input {
if isAllowedGetentChar(r) {
continue

View File

@@ -157,9 +157,6 @@ func TestValidateGetentInput(t *testing.T) {
{"numeric UID", "1001", true},
{"dots and underscores", "alice.bob_test", true},
{"hyphen", "alice-bob", true},
{"leading hyphen rejected", "-i", false},
{"leading double hyphen rejected", "--no-idn", false},
{"lone hyphen rejected", "-", false},
{"kerberos principal", "user@REALM", true},
{"samba machine account", "MACHINE$", true},
{"NIS compat", "+user", true},

View File

@@ -746,8 +746,6 @@ func ToProtoFullStatus(fullStatus peer.FullStatus) *proto.FullStatus {
pbFullStatus.DnsServers = append(pbFullStatus.DnsServers, pbDnsState)
}
pbFullStatus.Events = fullStatus.Events
return &pbFullStatus
}

View File

@@ -7,7 +7,7 @@ import (
"os"
"slices"
"github.com/shirou/gopsutil/v4/process"
"github.com/shirou/gopsutil/v3/process"
)
// getRunningProcesses returns a list of running process paths. The context bounds the work:

View File

@@ -4,7 +4,7 @@ import (
"context"
"testing"
"github.com/shirou/gopsutil/v4/process"
"github.com/shirou/gopsutil/v3/process"
)
func Benchmark_getRunningProcesses(b *testing.B) {

View File

@@ -1,121 +0,0 @@
//go:build !android && !ios && !freebsd && !js
package main
import (
"context"
"os"
"path/filepath"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/internal/profilemanager"
"github.com/netbirdio/netbird/client/mdm"
"github.com/netbirdio/netbird/client/ui/preferences"
"github.com/netbirdio/netbird/client/ui/services"
)
// autostartDefaultState carries the guard inputs of the one-time autostart
// default decision so the decision itself stays a pure, testable function.
type autostartDefaultState struct {
supported bool
mdmDisabled bool
priorInstall bool
}
// shouldEnableAutostartDefault applies the first-run guards in order and
// returns whether autostart may be enabled, plus the reason when it may not.
func shouldEnableAutostartDefault(s autostartDefaultState) (bool, string) {
switch {
case !s.supported:
return false, "autostart not supported on this platform"
case s.mdmDisabled:
return false, "autostart disabled by MDM policy"
case s.priorInstall:
return false, "existing NetBird installation"
}
return true, ""
}
// autostartDisabledByMDM reports whether the MDM policy manages the
// disableAutostart key in a way that must suppress the default. An
// unparseable managed value is treated as disabled to stay on the safe side.
func autostartDisabledByMDM(policy *mdm.Policy) bool {
if !policy.HasKey(mdm.KeyDisableAutostart) {
return false
}
disabled, ok := policy.GetBool(mdm.KeyDisableAutostart)
return !ok || disabled
}
// netbirdFootprintExists reports whether the machine already carries NetBird
// daemon config or state, meaning this is not a genuinely fresh install. It is
// the update-safety gate for the autostart default: upgrading users always
// have a footprint, so an update can never trigger a autostart entry write.
func netbirdFootprintExists() bool {
candidates := []string{
profilemanager.DefaultConfigPath,
filepath.Join(profilemanager.DefaultConfigPathDir, "config.json"),
filepath.Join(profilemanager.DefaultConfigPathDir, "state.json"),
}
for _, path := range candidates {
if path != "" && fileExists(path) {
return true
}
}
return false
}
// applyAutostartDefault runs the one-time launch-on-login default for genuinely
// fresh installs. The autostartInitialized marker is persisted before any
// enable attempt so a crash mid-flow degrades to "never enabled" instead of
// retrying autostart entry writes on every launch. A user's later disable in
// Settings is never overridden: the marker guarantees at-most-once, ever.
func applyAutostartDefault(ctx context.Context, autostart *services.Autostart, prefs *preferences.Store, prefsFileExisted bool) {
mdmDisabled := autostartDisabledByMDM(mdm.LoadPolicy())
if mdmDisabled {
if enabled, err := autostart.IsEnabled(ctx); err != nil {
log.Warnf("MDM disableAutostart: read autostart state: %v", err)
} else if enabled {
if err := autostart.SetEnabled(ctx, false); err != nil {
log.Warnf("MDM disableAutostart: force off failed: %v", err)
} else {
log.Info("MDM disableAutostart enforced: autostart turned off")
}
}
}
priorFootprint := netbirdFootprintExists() || prefsFileExisted
if prefs.Get().AutostartInitialized {
return
}
if err := prefs.SetAutostartInitialized(true); err != nil {
log.Warnf("persist autostart marker, skipping autostart default: %v", err)
return
}
state := autostartDefaultState{
supported: autostart.Supported(ctx),
mdmDisabled: mdmDisabled,
priorInstall: priorFootprint,
}
enable, reason := shouldEnableAutostartDefault(state)
if !enable {
log.Debugf("skipping autostart default: %s", reason)
return
}
if err := autostart.SetEnabled(ctx, true); err != nil {
log.Warnf("enable autostart on fresh install: %v", err)
return
}
log.Info("autostart enabled by default on fresh install")
}
// fileExists reports whether path exists.
func fileExists(path string) bool {
_, err := os.Stat(path)
return err == nil
}

View File

@@ -1,125 +0,0 @@
//go:build !android && !ios && !freebsd && !js
package main
import (
"testing"
"github.com/stretchr/testify/assert"
"github.com/netbirdio/netbird/client/mdm"
)
func TestShouldEnableAutostartDefault(t *testing.T) {
allPass := autostartDefaultState{
supported: true,
mdmDisabled: false,
priorInstall: false,
}
tests := []struct {
name string
mutate func(*autostartDefaultState)
wantEnable bool
wantReason string
}{
{
name: "fresh install with all guards passing enables",
mutate: func(*autostartDefaultState) {},
wantEnable: true,
},
{
name: "unsupported platform skips",
mutate: func(s *autostartDefaultState) { s.supported = false },
wantReason: "autostart not supported on this platform",
},
{
name: "MDM disable skips",
mutate: func(s *autostartDefaultState) { s.mdmDisabled = true },
wantReason: "autostart disabled by MDM policy",
},
{
name: "existing installation (upgrade) skips",
mutate: func(s *autostartDefaultState) { s.priorInstall = true },
wantReason: "existing NetBird installation",
},
{
name: "unsupported wins over every other guard",
mutate: func(s *autostartDefaultState) {
s.supported = false
s.mdmDisabled = true
s.priorInstall = true
},
wantReason: "autostart not supported on this platform",
},
{
name: "MDM disable wins over prior install",
mutate: func(s *autostartDefaultState) {
s.mdmDisabled = true
s.priorInstall = true
},
wantReason: "autostart disabled by MDM policy",
},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
state := allPass
tc.mutate(&state)
enable, reason := shouldEnableAutostartDefault(state)
assert.Equal(t, tc.wantEnable, enable, "enable decision should match for state %+v", state)
assert.Equal(t, tc.wantReason, reason, "skip reason should identify the failing guard")
})
}
}
func TestAutostartDisabledByMDM(t *testing.T) {
tests := []struct {
name string
values map[string]any
want bool
}{
{
name: "empty policy does not disable",
values: nil,
want: false,
},
{
name: "unrelated managed keys do not disable",
values: map[string]any{mdm.KeyDisableAutoConnect: true},
want: false,
},
{
name: "disableAutostart true disables",
values: map[string]any{mdm.KeyDisableAutostart: true},
want: true,
},
{
name: "disableAutostart registry DWORD 1 disables",
values: map[string]any{mdm.KeyDisableAutostart: int64(1)},
want: true,
},
{
name: "disableAutostart string true disables",
values: map[string]any{mdm.KeyDisableAutostart: "true"},
want: true,
},
{
name: "disableAutostart explicit false allows",
values: map[string]any{mdm.KeyDisableAutostart: false},
want: false,
},
{
name: "unparseable managed value is treated as disabled",
values: map[string]any{mdm.KeyDisableAutostart: "not-a-bool"},
want: true,
},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
got := autostartDisabledByMDM(mdm.NewPolicy(tc.values))
assert.Equal(t, tc.want, got, "MDM disable decision should match for values %v", tc.values)
})
}
}

View File

@@ -16,13 +16,10 @@ import LoginWaitingForBrowserDialog from "@/modules/login/LoginWaitingForBrowser
import { initI18n } from "@/lib/i18n";
import { initPlatform } from "@/lib/platform";
import { initLogForwarding } from "@/lib/logs";
import { initStallWatch } from "@/lib/stallwatch";
// Must run first so even init-time logs reach the Go log pipeline.
initLogForwarding();
initStallWatch();
welcome();
Promise.all([

View File

@@ -1,13 +1,10 @@
import { useEffect, useState } from "react";
import { useTranslation } from "react-i18next";
import { AlertTriangleIcon, DownloadIcon } from "lucide-react";
import { Browser } from "@wailsio/runtime";
import { Version } from "@bindings/services";
import { Button } from "@/components/buttons/Button";
import { useStatus } from "@/contexts/StatusContext.tsx";
const RELEASES_URL = "https://github.com/netbirdio/netbird/releases/latest";
const RC_RELEASES_URL = "https://pkgs.netbird.io/releases/rc";
function openUrl(url: string) {
Browser.OpenURL(url).catch(() => globalThis.open(url, "_blank"));
@@ -15,26 +12,7 @@ function openUrl(url: string) {
export const DaemonOutdatedOverlay = () => {
const { t } = useTranslation();
const { status, isDaemonOutdated } = useStatus();
const [guiVersion, setGuiVersion] = useState<string>("-");
const clientVersion = status?.daemonVersion ?? "—";
const isRc = /-rc/i.test(guiVersion) || /-rc/i.test(clientVersion);
const downloadUrl = isRc ? RC_RELEASES_URL : RELEASES_URL;
useEffect(() => {
if (!isDaemonOutdated) return;
let cancelled = false;
Version.GUI()
.then((v) => {
if (!cancelled) setGuiVersion(v);
})
.catch((err) => console.error("[DaemonOutdatedOverlay] GUI version error", err));
return () => {
cancelled = true;
};
}, [isDaemonOutdated]);
const { isDaemonOutdated } = useStatus();
if (!isDaemonOutdated) return null;
@@ -60,37 +38,10 @@ export const DaemonOutdatedOverlay = () => {
<p className={"text-sm text-nb-gray-300"}>{t("daemon.outdated.description")}</p>
</div>
<div className={"flex flex-col items-center gap-0.5 text-center"}>
<p className={"text-sm font-semibold text-nb-gray-100"}>
{clientVersion === "development" ? (
<span>
{t("settings.about.clientName")}{" "}
<span className={"font-mono text-yellow-400"}>
{t("settings.about.development")}
</span>
</span>
) : (
t("settings.about.client", { version: clientVersion })
)}
</p>
<p className={"text-sm font-medium text-nb-gray-250"}>
{guiVersion === "development" ? (
<span>
{t("settings.about.guiName")}{" "}
<span className={"font-mono text-yellow-400"}>
{t("settings.about.development")}
</span>
</span>
) : (
t("settings.about.gui", { version: guiVersion })
)}
</p>
</div>
<div className={"wails-no-draggable"}>
<Button variant={"primary"} size={"xs"} onClick={() => openUrl(downloadUrl)}>
<Button variant={"primary"} size={"xs"} onClick={() => openUrl(RELEASES_URL)}>
<DownloadIcon size={14} />
{t("daemon.outdated.download")}
{t("update.card.getInstaller")}
</Button>
</div>
</div>

View File

@@ -28,7 +28,6 @@ type ProfileContextValue = {
loaded: boolean;
refresh: () => Promise<void>;
switchProfile: (id: string) => Promise<void>;
switchProfileNoConnect: (id: string) => Promise<void>;
addProfile: (name: string) => Promise<string>;
removeProfile: (id: string) => Promise<void>;
renameProfile: (id: string, newName: string) => Promise<void>;
@@ -113,16 +112,6 @@ export const ProfileProvider = ({ children }: { children: ReactNode }) => {
[username, refresh],
);
// Manage-profiles variant: switches without connecting, so the user can
// still adjust the management URL before bringing the connection up.
const switchProfileNoConnect = useCallback(
async (id: string) => {
await ProfileSwitcher.SwitchActiveNoConnect({ profileName: id, username });
await refresh();
},
[username, refresh],
);
// addProfile creates a profile by display name and returns the
// daemon-generated ID, so the caller can immediately address it by ID.
const addProfile = useCallback(
@@ -169,7 +158,6 @@ export const ProfileProvider = ({ children }: { children: ReactNode }) => {
loaded,
refresh,
switchProfile,
switchProfileNoConnect,
addProfile,
removeProfile,
renameProfile,
@@ -183,7 +171,6 @@ export const ProfileProvider = ({ children }: { children: ReactNode }) => {
loaded,
refresh,
switchProfile,
switchProfileNoConnect,
addProfile,
removeProfile,
renameProfile,

View File

@@ -51,14 +51,7 @@ async function runSsoLogin(
if (uri) await openBrowserLoginUri(uri);
const cancelPromise = buildSsoCancelPromise(state, signal);
// Combine wait + up in Go so the connection comes up the moment SSO
// completes. During SSO the tray window is hidden and the webview is
// suspended, so a frontend-driven Up (a promise continuation) would not
// fire until the user woke the window (e.g. hovering the tray icon).
const waitPromise = Connection.WaitSSOLoginAndUp(
{ userCode: result.userCode, hostname: "" },
{ profileName: "", username: "" },
);
const waitPromise = Connection.WaitSSOLogin({ userCode: result.userCode, hostname: "" });
try {
await Promise.race([waitPromise, cancelPromise]);
@@ -96,13 +89,13 @@ export async function startConnection(onSettled?: () => void, signal?: AbortSign
if (signal?.aborted) state.cancelled = true;
if (!state.cancelled && result.needsSsoLogin) {
// runSsoLogin brings the connection up in Go once SSO completes.
await runSsoLogin(result, state, signal);
} else {
if (!state.cancelled && signal?.aborted) state.cancelled = true;
if (!state.cancelled) {
await Connection.Up({ profileName: "", username: "" });
}
}
if (!state.cancelled && signal?.aborted) state.cancelled = true;
if (!state.cancelled) {
await Connection.Up({ profileName: "", username: "" });
}
} catch (e) {
WindowManager.CloseBrowserLogin().catch(console.error);

View File

@@ -1,31 +0,0 @@
// Detects webview suspension (macOS App Nap / hidden-window timer throttling).
// While the webview is suspended no JS runs at all, so detection happens on
// resume: a 1s interval measures wall-clock drift and reports how long timers
// were frozen. Silent unless a stall actually occurred; a stalled webview is
// what delays promise continuations such as the WaitSSOLogin → Up handoff.
const INTERVAL_MS = 1000;
const STALL_THRESHOLD_MS = 5000;
const REPORT_COOLDOWN_MS = 60_000;
let started = false;
export function initStallWatch() {
if (started) return;
started = true;
let last = Date.now();
let lastReport = 0;
setInterval(() => {
const now = Date.now();
const stall = now - last - INTERVAL_MS;
last = now;
if (stall < STALL_THRESHOLD_MS) return;
if (now - lastReport < REPORT_COOLDOWN_MS) return;
lastReport = now;
console.warn(
`webview timers were suspended for ${(stall / 1000).toFixed(1)}s ` +
`(App Nap / hidden-window throttling); pending UI work ran late`,
);
}, INTERVAL_MS);
}

View File

@@ -45,7 +45,7 @@ export function ProfilesTab() {
activeProfileId,
loaded,
username,
switchProfileNoConnect,
switchProfile,
addProfile,
removeProfile,
renameProfile,
@@ -100,7 +100,7 @@ export function ProfilesTab() {
confirmLabel: t("profile.switch.confirm"),
});
if (!ok) return;
await guarded(i18next.t("profile.error.switchTitle"), () => switchProfileNoConnect(id));
await guarded(i18next.t("profile.error.switchTitle"), () => switchProfile(id));
};
const handleDeregister = async (id: string, name: string) => {
@@ -129,13 +129,14 @@ export function ProfilesTab() {
await guarded(i18next.t("profile.error.createTitle"), async () => {
const id = await addProfile(name);
// SetConfig is keyed by the new profile's ID, so it writes the
// not-yet-active profile before the switch makes it current.
// not-yet-active profile. Write before switching so any reconnect
// targets the right deployment.
if (!isNetbirdCloud(managementUrl)) {
await SettingsSvc.SetConfig(
new SetConfigParams({ profileName: id, username, managementUrl }),
);
}
await switchProfileNoConnect(id);
await switchProfile(id);
});
};

View File

@@ -73,13 +73,6 @@ export default function SessionExpirationDialog() {
let offCancel: (() => void) | undefined;
// Return the dialog to its interactive state and dismiss the browser popup
const resetDialog = () => {
offCancel?.();
WindowManager.CloseBrowserLogin().catch(console.error);
setBusy(false);
};
try {
const start = await Session.RequestExtend({ hint: "" });
const uri = start.verificationUriComplete || start.verificationUri;
@@ -112,22 +105,25 @@ export default function SessionExpirationDialog() {
if (outcome.kind === "cancel") {
waitPromise.cancel?.();
waitPromise.catch(() => {});
resetDialog();
return;
}
// Another surface owns this flow; keep the dialog open to retry.
if (outcome.result.preempted) {
resetDialog();
return;
}
WindowManager.CloseRenewFlow().catch(console.error);
// Close before the popup so the restore can't flash this window back.
WindowManager.CloseSessionExpiration().catch(console.error);
} catch (e) {
resetDialog();
await errorDialog({
Title: t("sessionExpiration.extendFailedTitle"),
Message: formatErrorMessage(e),
});
} finally {
offCancel?.();
WindowManager.CloseBrowserLogin().catch(console.error);
setBusy(false);
}
}, [busy, t]);
@@ -143,11 +139,12 @@ export default function SessionExpirationDialog() {
});
WindowManager.CloseSessionExpiration().catch(console.error);
} catch (e) {
setBusy(false);
await errorDialog({
Title: t("sessionExpiration.logoutFailedTitle"),
Message: formatErrorMessage(e),
});
} finally {
setBusy(false);
}
}, [busy, t]);

View File

@@ -22,9 +22,6 @@ type WelcomeStepTrayProps = {
export function WelcomeStepTray({ onContinue }: Readonly<WelcomeStepTrayProps>) {
const { t } = useTranslation();
const trayScreenshot = trayScreenshotForOS();
// macOS has no tray — the icon sits in the menu bar, so the copy says so.
const titleKey = isMacOS() ? "welcome.titleMac" : "welcome.title";
const descriptionKey = isMacOS() ? "welcome.descriptionMac" : "welcome.description";
return (
<>
@@ -39,9 +36,9 @@ export function WelcomeStepTray({ onContinue }: Readonly<WelcomeStepTrayProps>)
<div className={"flex w-full flex-col gap-1"}>
<DialogHeading id={"nb-welcome-title"} align={"left"}>
{t(titleKey)}
{t("welcome.title")}
</DialogHeading>
<DialogDescription align={"left"}>{t(descriptionKey)}</DialogDescription>
<DialogDescription align={"left"}>{t("welcome.description")}</DialogDescription>
</div>
<DialogActions>

View File

@@ -8,7 +8,6 @@
{"code": "fr", "displayName": "Français", "englishName": "French"},
{"code": "it", "displayName": "Italiano", "englishName": "Italian"},
{"code": "pt", "displayName": "Português", "englishName": "Portuguese"},
{"code": "zh-CN", "displayName": "简体中文", "englishName": "Simplified Chinese"},
{"code": "ja", "displayName": "日本語", "englishName": "Japanese"}
{"code": "zh-CN", "displayName": "简体中文", "englishName": "Simplified Chinese"}
]
}

View File

@@ -1034,15 +1034,9 @@
"welcome.title": {
"message": "Suchen Sie NetBird in der Taskleiste"
},
"welcome.titleMac": {
"message": "Suchen Sie NetBird in der Menüleiste"
},
"welcome.description": {
"message": "NetBird läuft in Ihrer Taskleiste. Klicken Sie auf das Symbol, um sich zu verbinden, Profile zu wechseln oder die Einstellungen zu öffnen."
},
"welcome.descriptionMac": {
"message": "NetBird läuft in Ihrer Menüleiste. Klicken Sie auf das Symbol, um sich zu verbinden, Profile zu wechseln oder die Einstellungen zu öffnen."
},
"welcome.continue": {
"message": "Weiter"
},
@@ -1299,13 +1293,10 @@
"message": "Dokumentation"
},
"daemon.outdated.title": {
"message": "NetBird Client ist veraltet"
"message": "NetBird-Dienst ist veraltet"
},
"daemon.outdated.description": {
"message": "Die neue GUI ist nicht mit Ihrem älteren Client kompatibel. Aktualisieren Sie Ihren Client, um die neue Anwendung zu verwenden."
},
"daemon.outdated.download": {
"message": "Neueste Version herunterladen"
"message": "Aktualisieren Sie den NetBird-Dienst, um diese App zu verwenden."
},
"error.jwt_clock_skew": {
"message": "Anmeldung fehlgeschlagen: Die Uhr dieses Geräts ist nicht mit dem Server synchron. Bitte synchronisieren Sie die Systemuhr und versuchen Sie es erneut."

View File

@@ -1377,19 +1377,11 @@
},
"welcome.title": {
"message": "Look for NetBird in your tray",
"description": "Heading on the first onboarding step, pointing the user to the tray icon. Shown on Windows and Linux; macOS uses welcome.titleMac."
},
"welcome.titleMac": {
"message": "Look for NetBird in your menu bar",
"description": "Heading on the first onboarding step on macOS, pointing the user to the menu bar icon. Use your language's Apple term for the macOS menu bar."
"description": "Heading on the first onboarding step, pointing the user to the tray icon. 'tray' = system tray / menu bar."
},
"welcome.description": {
"message": "NetBird lives in your tray. Click the icon to connect, switch profiles, or open settings.",
"description": "Body of the first onboarding step explaining the tray icon. Shown on Windows and Linux; macOS uses welcome.descriptionMac."
},
"welcome.descriptionMac": {
"message": "NetBird lives in your menu bar. Click the icon to connect, switch profiles, or open settings.",
"description": "Body of the first onboarding step on macOS explaining the menu bar icon. Use your language's Apple term for the macOS menu bar."
"description": "Body of the first onboarding step explaining the tray icon."
},
"welcome.continue": {
"message": "Continue",
@@ -1732,16 +1724,12 @@
"description": "Documentation link on the daemon-unavailable overlay."
},
"daemon.outdated.title": {
"message": "NetBird Client Is Outdated",
"description": "Title of the overlay shown when the NetBird client (daemon) is too old to drive this UI."
"message": "NetBird Service Is Outdated",
"description": "Title of the overlay shown when the NetBird background service is too old to drive this UI."
},
"daemon.outdated.description": {
"message": "The new GUI isn't compatible with the older NetBird client. Update your client to use the new application.",
"description": "Body of the daemon-outdated overlay explaining that the GUI is newer than the client and the client must be updated."
},
"daemon.outdated.download": {
"message": "Download Latest",
"description": "Button on the daemon-outdated overlay that opens the download page for the latest release."
"message": "Update the NetBird service to use this app.",
"description": "Body of the daemon-outdated overlay telling the user to upgrade the service."
},
"error.jwt_clock_skew": {
"message": "Sign-in failed: this device's clock is out of sync with the server. Please sync your system clock and try again.",

View File

@@ -1034,15 +1034,9 @@
"welcome.title": {
"message": "Busque NetBird en su bandeja del sistema"
},
"welcome.titleMac": {
"message": "Busque NetBird en su barra de menús"
},
"welcome.description": {
"message": "NetBird reside en su bandeja del sistema. Haga clic en el icono para conectarse, cambiar de perfil o abrir la configuración."
},
"welcome.descriptionMac": {
"message": "NetBird reside en su barra de menús. Haga clic en el icono para conectarse, cambiar de perfil o abrir la configuración."
},
"welcome.continue": {
"message": "Continuar"
},
@@ -1299,13 +1293,10 @@
"message": "Documentación"
},
"daemon.outdated.title": {
"message": "NetBird Client está desactualizado"
"message": "El servicio de NetBird está desactualizado"
},
"daemon.outdated.description": {
"message": "La nueva GUI no es compatible con su cliente anterior. Actualice su cliente para usar la nueva aplicación."
},
"daemon.outdated.download": {
"message": "Descargar la última versión"
"message": "Actualice el servicio de NetBird para usar esta aplicación."
},
"error.jwt_clock_skew": {
"message": "Error al iniciar sesión: el reloj de este dispositivo no está sincronizado con el servidor. Sincronice el reloj del sistema e inténtelo de nuevo."

View File

@@ -1034,15 +1034,9 @@
"welcome.title": {
"message": "Cherchez NetBird dans votre barre détat système"
},
"welcome.titleMac": {
"message": "Cherchez NetBird dans votre barre des menus"
},
"welcome.description": {
"message": "NetBird se trouve dans votre barre détat système. Cliquez sur licône pour vous connecter, changer de profil ou ouvrir les paramètres."
},
"welcome.descriptionMac": {
"message": "NetBird se trouve dans votre barre des menus. Cliquez sur licône pour vous connecter, changer de profil ou ouvrir les paramètres."
},
"welcome.continue": {
"message": "Continuer"
},
@@ -1299,13 +1293,10 @@
"message": "Documentation"
},
"daemon.outdated.title": {
"message": "Le Client NetBird est obsolète"
"message": "Le service NetBird est obsolète"
},
"daemon.outdated.description": {
"message": "La nouvelle GUI n'est pas compatible avec votre ancien client. Mettez à jour votre client pour utiliser la nouvelle application."
},
"daemon.outdated.download": {
"message": "Télécharger la dernière version"
"message": "Mettez à jour le service NetBird pour utiliser cette application."
},
"error.jwt_clock_skew": {
"message": "Échec de la connexion : lhorloge de cet appareil nest pas synchronisée avec le serveur. Veuillez synchroniser lhorloge de votre système et réessayer."

View File

@@ -1034,15 +1034,9 @@
"welcome.title": {
"message": "Keresse a NetBirdöt a tálcán"
},
"welcome.titleMac": {
"message": "Keresse a NetBirdöt a menüsorban"
},
"welcome.description": {
"message": "A NetBird a tálcán fut. Kattintson az ikonra a csatlakozáshoz, profilváltáshoz vagy a beállítások megnyitásához."
},
"welcome.descriptionMac": {
"message": "A NetBird a menüsorban fut. Kattintson az ikonra a csatlakozáshoz, profilváltáshoz vagy a beállítások megnyitásához."
},
"welcome.continue": {
"message": "Folytatás"
},
@@ -1299,13 +1293,10 @@
"message": "Dokumentáció"
},
"daemon.outdated.title": {
"message": "A NetBird Kliens elavult"
"message": "A NetBird szolgáltatás elavult"
},
"daemon.outdated.description": {
"message": "Az új GUI nem kompatibilis a régebbi klienseddel. Frissítsd a klienst az új alkalmazás használatához."
},
"daemon.outdated.download": {
"message": "Legújabb letöltése"
"message": "Frissítsd a NetBird szolgáltatást az alkalmazás használatához."
},
"error.jwt_clock_skew": {
"message": "A bejelentkezés sikertelen: az eszköz órája eltér a szerverétől. Kérjük, szinkronizálja a rendszer óráját, majd próbálja újra."

View File

@@ -1034,15 +1034,9 @@
"welcome.title": {
"message": "Cerchi NetBird nella tray"
},
"welcome.titleMac": {
"message": "Cerchi NetBird nella barra dei menu"
},
"welcome.description": {
"message": "NetBird risiede nella tray. Clicchi sull'icona per connettersi, cambiare profilo o aprire le impostazioni."
},
"welcome.descriptionMac": {
"message": "NetBird risiede nella barra dei menu. Clicchi sull'icona per connettersi, cambiare profilo o aprire le impostazioni."
},
"welcome.continue": {
"message": "Continua"
},
@@ -1299,13 +1293,10 @@
"message": "Documentazione"
},
"daemon.outdated.title": {
"message": "NetBird Client è obsoleto"
"message": "Il servizio NetBird è obsoleto"
},
"daemon.outdated.description": {
"message": "La nuova GUI non è compatibile con il tuo client precedente. Aggiorna il client per usare la nuova applicazione."
},
"daemon.outdated.download": {
"message": "Scarica l'ultima versione"
"message": "Aggiorna il servizio NetBird per usare questa app."
},
"error.jwt_clock_skew": {
"message": "Accesso non riuscito: l'orologio di questo dispositivo non è sincronizzato con il server. Sincronizzi l'orologio di sistema e riprovi."

File diff suppressed because it is too large Load Diff

View File

@@ -1034,15 +1034,9 @@
"welcome.title": {
"message": "Procure o NetBird na sua bandeja"
},
"welcome.titleMac": {
"message": "Procure o NetBird na sua barra de menus"
},
"welcome.description": {
"message": "O NetBird fica na sua bandeja. Clique no ícone para conectar, alternar perfis ou abrir as configurações."
},
"welcome.descriptionMac": {
"message": "O NetBird fica na sua barra de menus. Clique no ícone para conectar, alternar perfis ou abrir as configurações."
},
"welcome.continue": {
"message": "Continuar"
},
@@ -1299,13 +1293,10 @@
"message": "Documentação"
},
"daemon.outdated.title": {
"message": "O NetBird Client está desatualizado"
"message": "O serviço NetBird está desatualizado"
},
"daemon.outdated.description": {
"message": "A nova GUI não é compatível com o seu cliente mais antigo. Atualize o seu cliente para usar o novo aplicativo."
},
"daemon.outdated.download": {
"message": "Baixar a versão mais recente"
"message": "Atualize o serviço NetBird para usar este aplicativo."
},
"error.jwt_clock_skew": {
"message": "Falha no login: o relógio deste dispositivo está fora de sincronia com o servidor. Sincronize o relógio do sistema e tente novamente."

View File

@@ -1034,15 +1034,9 @@
"welcome.title": {
"message": "Найдите NetBird в системном трее"
},
"welcome.titleMac": {
"message": "Найдите NetBird в строке меню"
},
"welcome.description": {
"message": "NetBird находится в системном трее. Нажмите на значок, чтобы подключиться, переключить профиль или открыть настройки."
},
"welcome.descriptionMac": {
"message": "NetBird находится в строке меню. Нажмите на значок, чтобы подключиться, переключить профиль или открыть настройки."
},
"welcome.continue": {
"message": "Продолжить"
},
@@ -1299,13 +1293,10 @@
"message": "Документация"
},
"daemon.outdated.title": {
"message": "Клиент NetBird устарел"
"message": "Служба NetBird устарела"
},
"daemon.outdated.description": {
"message": "Новый GUI несовместим с вашим более старым клиентом. Обновите клиент, чтобы использовать новое приложение."
},
"daemon.outdated.download": {
"message": "Скачать последнюю версию"
"message": "Обновите службу NetBird, чтобы использовать это приложение."
},
"error.jwt_clock_skew": {
"message": "Не удалось войти: часы этого устройства рассинхронизированы с сервером. Синхронизируйте системные часы и повторите попытку."

View File

@@ -1034,15 +1034,9 @@
"welcome.title": {
"message": "在托盘中查找 NetBird"
},
"welcome.titleMac": {
"message": "在菜单栏中查找 NetBird"
},
"welcome.description": {
"message": "NetBird 驻留在您的托盘中。点击图标即可连接、切换配置文件或打开设置。"
},
"welcome.descriptionMac": {
"message": "NetBird 驻留在您的菜单栏中。点击图标即可连接、切换配置文件或打开设置。"
},
"welcome.continue": {
"message": "继续"
},
@@ -1299,13 +1293,10 @@
"message": "文档"
},
"daemon.outdated.title": {
"message": "NetBird 客户端版本过旧"
"message": "NetBird 服务版本过旧"
},
"daemon.outdated.description": {
"message": "新版 GUI 与您较旧的客户端不兼容。请更新客户端以使用应用。"
},
"daemon.outdated.download": {
"message": "下载最新版本"
"message": "请更新 NetBird 服务以使用应用。"
},
"error.jwt_clock_skew": {
"message": "登录失败:此设备的时钟与服务器不同步。请同步您的系统时钟后重试。"

View File

@@ -197,9 +197,6 @@ func main() {
// daemon may keep the main window from showing, so the OS toast is the
// only reliable signal the user gets.
go notifyIfDaemonOutdated(compat, notifier, localizer)
// One-time launch-on-login default for fresh installs; gated by the
// NetBird footprint check, MDM policy, and the persisted marker.
go applyAutostartDefault(context.Background(), services.NewAutostart(app.Autostart), prefStore, prefStore.ExistedAtLoad())
})
if err := app.Run(); err != nil {

View File

@@ -54,10 +54,6 @@ type UIPreferences struct {
Language i18n.LanguageCode `json:"language"`
ViewMode ViewMode `json:"viewMode"`
OnboardingCompleted bool `json:"onboardingCompleted"`
// AutostartInitialized records that the one-time autostart default
// decision has run for this OS user. It only ever transitions to true
// and is never reset, so the default-on flow runs at most once, ever.
AutostartInitialized bool `json:"autostartInitialized"`
}
// LanguageValidator rejects SetLanguage inputs with no shipped bundle.
@@ -76,9 +72,8 @@ type Emitter interface {
type Store struct {
path string
mu sync.RWMutex
current UIPreferences
existedAtLoad bool
mu sync.RWMutex
current UIPreferences
subsMu sync.Mutex
subs []chan UIPreferences
@@ -162,27 +157,6 @@ func (s *Store) SetOnboardingCompleted(done bool) error {
return nil
}
// SetAutostartInitialized persists the one-time autostart decision marker.
// No-op if unchanged.
func (s *Store) SetAutostartInitialized(done bool) error {
s.mu.Lock()
if s.current.AutostartInitialized == done {
s.mu.Unlock()
return nil
}
next := s.current
next.AutostartInitialized = done
if err := s.persistLocked(next); err != nil {
s.mu.Unlock()
return fmt.Errorf("persist preferences: %w", err)
}
s.current = next
s.mu.Unlock()
s.broadcast(next)
return nil
}
// SetLanguage validates, persists, and broadcasts. No-op if unchanged.
func (s *Store) SetLanguage(lang i18n.LanguageCode) error {
if lang == "" {
@@ -232,29 +206,13 @@ func (s *Store) Subscribe() (<-chan UIPreferences, func()) {
return ch, unsubscribe
}
// ExistedAtLoad reports whether the backing preferences file was present on
// disk when the store loaded. It distinguishes a user who ran a prior GUI
// version from a brand-new OS user with no preferences yet.
func (s *Store) ExistedAtLoad() bool {
s.mu.RLock()
defer s.mu.RUnlock()
return s.existedAtLoad
}
// load reads the file into current. A missing file is not an error (the
// in-memory default stands); malformed contents return an error.
func (s *Store) load() error {
if _, err := os.Stat(s.path); err != nil {
if errors.Is(err, os.ErrNotExist) {
return nil
}
return fmt.Errorf("stat preferences: %w", err)
if _, err := os.Stat(s.path); errors.Is(err, os.ErrNotExist) {
return nil
}
s.mu.Lock()
s.existedAtLoad = true
s.mu.Unlock()
var loaded UIPreferences
if _, err := util.ReadJson(s.path, &loaded); err != nil {
return err

View File

@@ -215,46 +215,6 @@ func TestStore_FileShapeIsJSON(t *testing.T) {
assert.Equal(t, i18n.LanguageCode("hu"), parsed.Language)
}
func TestStore_SetAutostartInitializedPersistsAcrossReload(t *testing.T) {
withTempConfigDir(t)
emitter := &recordingEmitter{}
s, err := NewStore(nil, emitter)
require.NoError(t, err)
assert.False(t, s.Get().AutostartInitialized, "marker must default to false when no file is on disk")
require.NoError(t, s.SetAutostartInitialized(true))
assert.True(t, s.Get().AutostartInitialized, "Get should reflect the persisted marker")
require.Len(t, emitter.calledWith(EventPreferencesChanged), 1, "first marker write should broadcast")
// Re-setting the same value must be a no-op: no disk write, no broadcast.
require.NoError(t, s.SetAutostartInitialized(true))
assert.Len(t, emitter.calledWith(EventPreferencesChanged), 1, "idempotent marker write should not broadcast again")
// A fresh Store (new GUI launch) must see the marker so the autostart
// default decision never runs twice.
reloaded, err := NewStore(nil, nil)
require.NoError(t, err)
assert.True(t, reloaded.Get().AutostartInitialized, "marker must survive a reload from disk")
}
func TestStore_ExistedAtLoad(t *testing.T) {
withTempConfigDir(t)
// Brand-new OS user: no preferences file on disk yet.
fresh, err := NewStore(nil, nil)
require.NoError(t, err)
assert.False(t, fresh.ExistedAtLoad(), "ExistedAtLoad must be false when no file is on disk")
// Persisting a value writes the file to disk.
require.NoError(t, fresh.SetLanguage("en"))
// A subsequent GUI launch reopens the now-present file.
reopened, err := NewStore(nil, nil)
require.NoError(t, err)
assert.True(t, reopened.ExistedAtLoad(), "ExistedAtLoad must be true after the store has persisted and is reopened")
}
func TestStore_ErrUnsupportedSentinel(t *testing.T) {
// Verifies callers can match on the sentinel error rather than parsing
// strings — protects against accidental %v -> %w changes that would

View File

@@ -10,7 +10,7 @@ import (
"github.com/wailsapp/wails/v3/pkg/application"
)
// Autostart facade over Wails' AutostartManager. The OS autostart entry registration
// Autostart facade over Wails' AutostartManager. The OS login-item registration
// is the single source of truth; nothing is mirrored to preferences.
type Autostart struct {
mgr *application.AutostartManager

View File

@@ -35,7 +35,7 @@ type LoginResult struct {
VerificationURIComplete string `json:"verificationUriComplete"`
}
// WaitSSOParams are the inputs to waitSSOLogin.
// WaitSSOParams are the inputs to WaitSSOLogin.
type WaitSSOParams struct {
UserCode string `json:"userCode"`
Hostname string `json:"hostname"`
@@ -116,7 +116,6 @@ func (s *Connection) Login(ctx context.Context, p LoginParams) (LoginResult, err
if err != nil {
return LoginResult{}, s.classifyDaemonError(err)
}
log.Infof("daemon login response received, needs SSO login: %v", resp.GetNeedsSSOLogin())
return LoginResult{
NeedsSSOLogin: resp.GetNeedsSSOLogin(),
UserCode: resp.GetUserCode(),
@@ -125,12 +124,26 @@ func (s *Connection) Login(ctx context.Context, p LoginParams) (LoginResult, err
}, nil
}
func (s *Connection) WaitSSOLogin(ctx context.Context, p WaitSSOParams) (string, error) {
cli, err := s.conn.Client()
if err != nil {
return "", err
}
resp, err := cli.WaitSSOLogin(ctx, &proto.WaitSSOLoginRequest{
UserCode: p.UserCode,
Hostname: p.Hostname,
})
if err != nil {
return "", s.classifyDaemonError(err)
}
return resp.GetEmail(), nil
}
func (s *Connection) Up(ctx context.Context, p UpParams) error {
cli, err := s.conn.Client()
if err != nil {
return err
}
log.Infof("sending up request to daemon")
// Always async: status updates flow via SubscribeStatus.
req := &proto.UpRequest{Async: true}
if p.ProfileName != "" {
@@ -145,27 +158,6 @@ func (s *Connection) Up(ctx context.Context, p UpParams) error {
return nil
}
// WaitSSOLoginAndUp blocks until the SSO login completes and then brings the
// connection up, both from the Go side. Keeping the post-login Up here rather
// than as a frontend continuation is deliberate: during SSO the tray window is
// hidden and the webview is suspended (macOS App Nap / hidden-window timer
// throttling), so a frontend-driven Up would not run until the user woke the
// window (e.g. by hovering the tray icon). Doing it in Go connects the moment
// the daemon reports SSO success. Returns the authenticated user's email.
func (s *Connection) WaitSSOLoginAndUp(ctx context.Context, wait WaitSSOParams, up UpParams) (string, error) {
email, err := s.waitSSOLogin(ctx, wait)
if err != nil {
return "", err
}
if err := ctx.Err(); err != nil {
return "", err
}
if err := s.Up(ctx, up); err != nil {
return "", err
}
return email, nil
}
func (s *Connection) Down(ctx context.Context) error {
cli, err := s.conn.Client()
if err != nil {
@@ -225,26 +217,6 @@ func (s *Connection) Logout(ctx context.Context, p LogoutParams) error {
return nil
}
// waitSSOLogin blocks until the daemon reports the SSO login result and returns
// the authenticated user's email. It is unexported because the frontend drives
// SSO through the exported WaitSSOLoginAndUp.
func (s *Connection) waitSSOLogin(ctx context.Context, p WaitSSOParams) (string, error) {
cli, err := s.conn.Client()
if err != nil {
return "", err
}
log.Infof("waiting for SSO login to complete")
resp, err := cli.WaitSSOLogin(ctx, &proto.WaitSSOLoginRequest{
UserCode: p.UserCode,
Hostname: p.Hostname,
})
if err != nil {
return "", s.classifyDaemonError(err)
}
log.Infof("SSO login completed, daemon reported success")
return resp.GetEmail(), nil
}
// classifyDaemonError maps a gRPC error to a localised ClientError.
func (s *Connection) classifyDaemonError(err error) *ClientError {
return s.classifier.classify(err)

View File

@@ -12,15 +12,13 @@ import (
"github.com/netbirdio/netbird/client/internal/profilemanager"
)
// ProfileSwitcher holds the switch policy shared by the tray and React
// frontend so both flip profiles identically. SwitchActive (plain selection:
// header dropdown, tray submenu) always connects after the switch;
// SwitchActiveNoConnect (manage-profiles screen) never does, so the user can
// still adjust the management URL before connecting. prevStatus from
// DaemonFeed.Get at entry only decides the teardown:
// ProfileSwitcher holds the reconnect policy shared by the tray and React
// frontend so both flip profiles identically. The policy keys off prevStatus
// from DaemonFeed.Get at SwitchActive entry:
//
// Connected/Connecting/NeedsLogin/LoginFailed/SessionExpired → Down first.
// Idle → no Down.
// Connected/Connecting → Switch + Down + Up; optimistic Connecting paint.
// NeedsLogin/LoginFailed/SessionExpired → Switch + Down; clear stale error for re-login.
// Idle → Switch only.
type ProfileSwitcher struct {
profiles *Profiles
connection *Connection
@@ -31,40 +29,29 @@ func NewProfileSwitcher(profiles *Profiles, connection *Connection, feed *Daemon
return &ProfileSwitcher{profiles: profiles, connection: connection, feed: feed}
}
// SwitchActive switches to the named profile and always connects afterwards.
// SwitchActive switches to the named profile applying the reconnect policy.
func (s *ProfileSwitcher) SwitchActive(ctx context.Context, p ProfileRef) error {
return s.switchActive(ctx, p, true)
}
// SwitchActiveNoConnect switches to the named profile without connecting,
// tearing down any existing connection first.
func (s *ProfileSwitcher) SwitchActiveNoConnect(ctx context.Context, p ProfileRef) error {
return s.switchActive(ctx, p, false)
}
func (s *ProfileSwitcher) switchActive(ctx context.Context, p ProfileRef, connect bool) error {
prevStatus := ""
if s.feed != nil {
if st, err := s.feed.Get(ctx); err == nil {
prevStatus = st.Status
} else {
log.Warnf("profileswitcher: get status: %v", err)
}
if st, err := s.feed.Get(ctx); err == nil {
prevStatus = st.Status
} else {
log.Warnf("profileswitcher: get status: %v", err)
}
needsDown := strings.EqualFold(prevStatus, StatusConnected) ||
strings.EqualFold(prevStatus, StatusConnecting) ||
wasActive := strings.EqualFold(prevStatus, StatusConnected) ||
strings.EqualFold(prevStatus, StatusConnecting)
needsDown := wasActive ||
strings.EqualFold(prevStatus, StatusNeedsLogin) ||
strings.EqualFold(prevStatus, StatusLoginFailed) ||
strings.EqualFold(prevStatus, StatusSessionExpired)
log.Infof("profileswitcher: switch profile=%q prevStatus=%q connect=%v needsDown=%v",
p.ProfileName, prevStatus, connect, needsDown)
log.Infof("profileswitcher: switch profile=%q prevStatus=%q wasActive=%v needsDown=%v",
p.ProfileName, prevStatus, wasActive, needsDown)
// Optimistic Connecting paint plus stale-push suppression during Down (see
// DaemonFeed suppression table); also arms the login-watch that pops
// browser-login when the new profile turns out to need SSO.
if connect && s.feed != nil {
// Optimistic Connecting paint only when wasActive: those prevStatuses emit
// stale Connected + transient Idle pushes during Down that must be
// suppressed until Up resumes the stream (see DaemonFeed suppression table).
if wasActive {
s.feed.BeginProfileSwitch()
}
@@ -89,9 +76,9 @@ func (s *ProfileSwitcher) switchActive(ctx context.Context, p ProfileRef, connec
}
}
if connect {
if wasActive {
if err := s.connection.Up(ctx, UpParams(p)); err != nil {
return fmt.Errorf("connect %q: %w", p.ProfileName, err)
return fmt.Errorf("reconnect %q: %w", p.ProfileName, err)
}
}

View File

@@ -20,12 +20,11 @@ type MDMFields struct {
DisableServerRoutes bool `json:"disableServerRoutes"`
AllowServerSSH *bool `json:"allowServerSSH"`
DisableAutoConnect bool `json:"disableAutoConnect"`
DisableAutostart bool `json:"disableAutostart"`
BlockInbound bool `json:"blockInbound"`
DisableMetricsCollection bool `json:"disableMetricsCollection"`
SplitTunnelMode bool `json:"splitTunnelMode"`
SplitTunnelApps bool `json:"splitTunnelApps"`
DisableAdvancedView bool `json:"disableAdvancedView"`
DisableAdvancedView bool `json:"disableAdvancedView"`
}
type Features struct {

View File

@@ -185,38 +185,37 @@ func (s *WindowManager) OpenBrowserLogin(uri string) {
startURL = "/#/dialog/browser-login?uri=" + url.QueryEscape(uri)
}
s.hideOtherWindowsLocked("browser-login")
// Prefer the main window's screen (multi-monitor); falls back to OS-default centering.
var screen *application.Screen
if s.mainWindow != nil {
if sc, err := s.mainWindow.GetScreen(); err == nil {
screen = sc
}
}
opts := DialogWindowOptions("browser-login", s.title("window.title.signIn"), startURL, s.linuxIcon)
// Not always-on-top: it would obscure the browser tab the user logs in through.
opts.AlwaysOnTop = false
opts.InitialPosition = application.WindowCentered
// Open on the active (where users cursor is) display, like the session-expiration dialog.
opts.Screen = s.getScreenBasedOnCursorPosition()
opts.Screen = screen
s.browserLogin = s.app.Window.NewWithOptions(opts)
bl := s.browserLogin
// Red-X close means cancel: emit the event so startLogin() tears down the SSO wait.
bl.OnWindowEvent(events.Common.WindowClosing, func(_ *application.WindowEvent) {
s.app.Event.Emit(EventBrowserLoginCancel)
s.mu.Lock()
// Only a live user red-X still has this registered; programmatic closers
// nil s.browserLogin first and clean up themselves. Guarding here stops a
// stale close event from wiping a replacement popup's state.
userClosed := s.browserLogin == bl
if userClosed {
s.browserLogin = nil
s.restoreHiddenWindowsLocked()
}
s.browserLogin = nil
s.restoreHiddenWindowsLocked()
s.mu.Unlock()
if userClosed {
s.app.Event.Emit(EventBrowserLoginCancel)
}
})
s.centerOnCursorScreen(s.browserLogin)
s.centerWhenReady(s.browserLogin)
return
}
if uri != "" {
s.browserLogin.SetURL("/#/dialog/browser-login?uri=" + url.QueryEscape(uri))
}
s.centerOnCursorScreen(s.browserLogin)
s.browserLogin.Show()
s.browserLogin.Focus()
s.centerWhenReady(s.browserLogin)
}
// BrowserLoginWindow returns the live SSO popup, or nil. While non-nil it is the
@@ -239,15 +238,6 @@ func (s *WindowManager) CloseBrowserLogin() {
s.mu.Lock()
w := s.browserLogin
s.browserLogin = nil
// The WindowClosing hook no-ops on a programmatic close, so restore here —
// but only if a popup was actually open. The frontend calls this even when no
// popup was ever shown (e.g. resetDialog() after an early RequestExtend failure,
// or connection.ts's catch path), and hiddenForLogin is shared with
// OpenInstallProgress, so an unconditional restore could re-show windows a
// still-running install-progress is hiding.
if w != nil {
s.restoreHiddenWindowsLocked()
}
s.mu.Unlock()
if w != nil {
w.Close()
@@ -289,35 +279,6 @@ func (s *WindowManager) CloseSessionExpiration() {
}
}
// CloseRenewFlow tears down the SSO session-renewal UI in a single call: it
// closes the browser-login popup and the session-expiration window together.
func (s *WindowManager) CloseRenewFlow() {
s.mu.Lock()
bl := s.browserLogin
se := s.sessionExpiration
s.browserLogin = nil
s.sessionExpiration = nil
if se != nil {
kept := s.hiddenForLogin[:0]
for _, w := range s.hiddenForLogin {
if w != se {
kept = append(kept, w)
}
}
s.hiddenForLogin = kept
}
s.restoreHiddenWindowsLocked()
s.mu.Unlock()
// Close after unlock so the re-entrant handlers can take s.mu.
if bl != nil {
bl.Close()
}
if se != nil {
se.Close()
}
}
// OpenInstallProgress shows the install-progress window and hides the rest for the duration
// (restored on close). It owns its own result polling since the daemon restarts mid-install.
func (s *WindowManager) OpenInstallProgress(version string) {

View File

@@ -30,8 +30,6 @@ const (
statusError = "Error"
quitDownTimeout = 5 * time.Second
urlGitHubRepo = "https://github.com/netbirdio/netbird"
urlGitHubReleases = "https://github.com/netbirdio/netbird/releases/latest"
urlDocs = "https://docs.netbird.io"
@@ -317,7 +315,8 @@ func (t *Tray) relayoutMenu() {
if sessionDeadline.IsZero() {
t.sessionExpiresItem.SetHidden(true)
} else {
t.sessionExpiresItem.SetLabel(t.sessionRowLabel(sessionDeadline))
remaining := t.formatSessionRemaining(time.Until(sessionDeadline))
t.sessionExpiresItem.SetLabel(t.loc.T("tray.session.expiresIn", "remaining", remaining))
t.sessionExpiresItem.SetHidden(false)
}
}
@@ -447,28 +446,11 @@ func (t *Tray) buildMenu() *application.Menu {
menu.AddSeparator()
menu.Add(t.loc.T("tray.menu.quit")).
SetAccelerator("CmdOrCtrl+Q").
OnClick(func(*application.Context) { t.handleQuit() })
OnClick(func(*application.Context) { t.app.Quit() })
return menu
}
func (t *Tray) handleQuit() {
t.profileMu.Lock()
if t.switchCancel != nil {
t.switchCancel()
t.switchCancel = nil
}
t.profileMu.Unlock()
t.svc.DaemonFeed.CancelProfileSwitch()
ctx, cancel := context.WithTimeout(context.Background(), quitDownTimeout)
defer cancel()
if err := t.svc.Connection.Down(ctx); err != nil {
log.Errorf("disconnect on quit: %v", err)
}
t.app.Quit()
}
// handleConnect receives the clicked item from the buildMenu closure —
// t.upItem is menuMu-guarded and must not be read here.
func (t *Tray) handleConnect(upItem *application.MenuItem) {

View File

@@ -64,42 +64,11 @@ func (t *Tray) applySessionExpiry(deadline *time.Time, connected bool) bool {
return changed
}
// runSessionExpiryTicker recomputes the "Expires in …" row label until process exit.
// The interval scales with the remaining time: coarse when the deadline is far off,
// down to 10s in the final two minutes so the label doesn't lag the ceiling-rounded
// countdown near expiry. The cached deadline is re-read every iteration, so an extend
// or reconnect that moves it is picked up on the next tick.
// runSessionExpiryTicker recomputes the "Expires in …" row label every 30s. Runs until process exit.
func (t *Tray) runSessionExpiryTicker() {
tm := time.NewTimer(sessionRefreshInterval(t.sessionRemaining()))
defer tm.Stop()
for range tm.C {
tk := time.NewTicker(30 * time.Second)
for range tk.C {
t.refreshSessionExpiresLabel()
tm.Reset(sessionRefreshInterval(t.sessionRemaining()))
}
}
// sessionRemaining returns the time left on the cached SSO deadline, or 0 when unknown.
func (t *Tray) sessionRemaining() time.Duration {
t.sessionMu.Lock()
deadline := t.sessionExpiresAt
t.sessionMu.Unlock()
if deadline.IsZero() {
return 0
}
return time.Until(deadline)
}
// sessionRefreshInterval picks how long to wait before the next label recompute.
func sessionRefreshInterval(remaining time.Duration) time.Duration {
switch {
case remaining <= 0:
return 30 * time.Second
case remaining <= 2*time.Minute:
return 10 * time.Second
case remaining <= time.Hour:
return 30 * time.Second
default:
return time.Minute
}
}
@@ -118,39 +87,30 @@ func (t *Tray) refreshSessionExpiresLabel() {
if deadline.IsZero() {
return
}
item.SetLabel(t.sessionRowLabel(deadline))
}
func (t *Tray) sessionRowLabel(deadline time.Time) string {
remaining := time.Until(deadline)
if remaining <= 0 {
return t.loc.T("tray.status.sessionExpired")
}
return t.loc.T("tray.session.expiresIn", "remaining", t.formatSessionRemaining(remaining))
remaining := t.formatSessionRemaining(time.Until(deadline))
item.SetLabel(t.loc.T("tray.session.expiresIn", "remaining", remaining))
}
// formatSessionRemaining renders d as a localised long-form string picking the largest non-zero unit.
// Each unit is rounded up so the label never claims less time than actually remains, matching the
// upper-bound sense of the sub-minute "less than a minute" fragment.
// Singular/plural keys are split per language for proper translation.
func (t *Tray) formatSessionRemaining(d time.Duration) string {
switch {
case d < time.Minute:
return t.loc.T("tray.session.unit.lessThanMinute")
case d <= 59*time.Minute:
m := ceilDiv(d, time.Minute)
case d < time.Hour:
m := int(d / time.Minute)
if m == 1 {
return t.loc.T("tray.session.unit.minute")
}
return t.loc.T("tray.session.unit.minutes", "count", strconv.Itoa(m))
case d <= 23*time.Hour:
h := ceilDiv(d, time.Hour)
case d < 24*time.Hour:
h := int((d + 30*time.Minute) / time.Hour)
if h == 1 {
return t.loc.T("tray.session.unit.hour")
}
return t.loc.T("tray.session.unit.hours", "count", strconv.Itoa(h))
default:
days := ceilDiv(d, 24*time.Hour)
days := int((d + 12*time.Hour) / (24 * time.Hour))
if days == 1 {
return t.loc.T("tray.session.unit.day")
}
@@ -158,11 +118,6 @@ func (t *Tray) formatSessionRemaining(d time.Duration) string {
}
}
// ceilDiv divides d by unit rounding up, assuming d > 0.
func ceilDiv(d, unit time.Duration) int {
return int((d + unit - time.Nanosecond) / unit)
}
// registerSessionWarningCategory wires the OS notification category and response handler for the expiry warning.
// Errors are swallowed since the worst case is a plain notification without buttons.
func (t *Tray) registerSessionWarningCategory() {
@@ -297,9 +252,11 @@ func (t *Tray) openSessionExpiration() {
}
// openSessionExtendFlow opens the SessionExpiration window seeded with the cached deadline's remaining time,
// for the "Expires in …" tray row. Once the deadline has elapsed the row reads "Session expired" and the
// click routes to the login flow instead. No-op when the deadline is unknown.
// for the "Expires in …" tray row. No-ops when the deadline is unknown or elapsed.
func (t *Tray) openSessionExtendFlow() {
if t.svc.WindowManager == nil {
return
}
t.sessionMu.Lock()
deadline := t.sessionExpiresAt
t.sessionMu.Unlock()
@@ -308,14 +265,6 @@ func (t *Tray) openSessionExtendFlow() {
}
seconds := int(time.Until(deadline).Seconds())
if seconds <= 0 {
if t.window != nil {
t.window.SetURL("/#/login")
t.window.Show()
t.window.Focus()
}
return
}
if t.svc.WindowManager == nil {
return
}
t.svc.WindowManager.OpenSessionExpiration(seconds)

View File

@@ -23,7 +23,7 @@ const (
RDCleanPathProxyHost = "rdcleanpath.proxy.local"
RDCleanPathProxyScheme = "ws"
rdpDialTimeout = 30 * time.Second
rdpDialTimeout = 15 * time.Second
GeneralErrorCode = 1
WSAETimedOut = 10060

View File

@@ -145,7 +145,6 @@ type AuthConfig struct {
CLIRedirectURIs []string `yaml:"cliRedirectURIs"`
Owner *AuthOwnerConfig `yaml:"owner,omitempty"`
DashboardPostLogoutRedirectURIs []string `yaml:"dashboardPostLogoutRedirectURIs"`
GrantTypes []string `yaml:"grantTypes"`
}
// AuthStorageConfig contains auth storage settings
@@ -605,7 +604,6 @@ func (c *CombinedConfig) buildEmbeddedIdPConfig(mgmt ManagementConfig) (*idp.Emb
DashboardRedirectURIs: mgmt.Auth.DashboardRedirectURIs,
CLIRedirectURIs: mgmt.Auth.CLIRedirectURIs,
DashboardPostLogoutRedirectURIs: mgmt.Auth.DashboardPostLogoutRedirectURIs,
GrantTypes: mgmt.Auth.GrantTypes,
}
if mgmt.Auth.Owner != nil && mgmt.Auth.Owner.Email != "" {

View File

@@ -226,7 +226,7 @@ func (s *serverInstances) createRelayServer(cfg *CombinedConfig, tlsSupport bool
}
hashedSecret := sha256.Sum256([]byte(cfg.Relay.AuthSecret))
authenticator := auth.NewTimedHMACValidator(hashedSecret[:])
authenticator := auth.NewTimedHMACValidator(hashedSecret[:], 24*time.Hour)
relayCfg := relayServer.Config{
Meter: s.metricsServer.Meter,

View File

@@ -66,9 +66,6 @@
<key>disableAutoConnect</key>
<false/>
<key>disableAutostart</key>
<false/>
<key>disableClientRoutes</key>
<false/>

View File

@@ -103,8 +103,6 @@
<!--
<key>disableAutoConnect</key>
<false/>
<key>disableAutostart</key>
<false/>
<key>disableClientRoutes</key>
<false/>
<key>disableServerRoutes</key>

View File

@@ -58,7 +58,6 @@ preSharedKey="$NULL" # secret; redacted in log
allowServerSSH='true'
blockInbound="$NULL"
disableAutoConnect="$NULL"
disableAutostart="$NULL"
disableClientRoutes="$NULL"
disableServerRoutes="$NULL"
disableMetricsCollection="$NULL"
@@ -156,7 +155,6 @@ main() {
is_set "$allowServerSSH" && emit_bool allowServerSSH "$allowServerSSH"
is_set "$blockInbound" && emit_bool blockInbound "$blockInbound"
is_set "$disableAutoConnect" && emit_bool disableAutoConnect "$disableAutoConnect"
is_set "$disableAutostart" && emit_bool disableAutostart "$disableAutostart"
is_set "$disableClientRoutes" && emit_bool disableClientRoutes "$disableClientRoutes"
is_set "$disableServerRoutes" && emit_bool disableServerRoutes "$disableServerRoutes"
is_set "$disableMetricsCollection" && emit_bool disableMetricsCollection "$disableMetricsCollection"

Binary file not shown.

View File

@@ -24,9 +24,6 @@
<string id="DisableAutoConnect_Name">Disable auto-connect</string>
<string id="DisableAutoConnect_Help">When enabled, the NetBird tunnel does not auto-connect at daemon startup. Equivalent to --disable-auto-connect.</string>
<string id="DisableAutostart_Name">Disable autostart</string>
<string id="DisableAutostart_Help">When enabled, the NetBird GUI is prevented from registering itself as an OS autostart entry on fresh installs, and any existing OS autostart entry registration is removed on the next GUI launch (Windows Registry Run key, macOS Login Item, Linux .desktop). Once the admin lifts the policy, the setting stays off until the user re-enables it in Settings.</string>
<string id="DisableClientRoutes_Name">Disable client routes</string>
<string id="DisableClientRoutes_Help">When enabled, this client will not consume routes advertised by routing peers. Equivalent to --disable-client-routes.</string>

View File

@@ -64,18 +64,6 @@
<disabledValue><decimal value="0" /></disabledValue>
</policy>
<policy name="DisableAutostart"
class="Machine"
displayName="$(string.DisableAutostart_Name)"
explainText="$(string.DisableAutostart_Help)"
key="Software\Policies\NetBird"
valueName="DisableAutostart">
<parentCategory ref="NetBird" />
<supportedOn ref="SUPPORTED_NetBird_All" />
<enabledValue><decimal value="1" /></enabledValue>
<disabledValue><decimal value="0" /></disabledValue>
</policy>
<policy name="DisableClientRoutes"
class="Machine"
displayName="$(string.DisableClientRoutes_Name)"

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