Compare commits

..
Author SHA1 Message Date
JackDoan 1519dbbf8e ipv6: tighten handling of fragments wrt extension headers 2026-09-29 13:20:22 -05:00
JackDoan d576827ade checkpt 2026-09-29 12:50:27 -05:00
113 changed files with 1736 additions and 7292 deletions

No files matched your search

-2
View File
@@ -1,2 +0,0 @@
# Goldens are compared byte for byte, so they must come out of git the way they went in.
*.golden -text
+3 -3
View File
@@ -14,7 +14,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: Build
@@ -40,7 +40,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: Build
@@ -83,7 +83,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
# GitHub holds ARNs, not credentials, and ARNs outlive a rotation
+3 -3
View File
@@ -34,7 +34,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: add hashicorp source
@@ -66,7 +66,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: add hashicorp source
@@ -92,7 +92,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
# WSL2 + Ubuntu so the smoke can run a real linux peer with its own
+2 -2
View File
@@ -22,7 +22,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: Smoke Docker
@@ -51,7 +51,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: build
+4 -4
View File
@@ -22,7 +22,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: Install goimports
@@ -42,7 +42,7 @@ jobs:
- name: golangci-lint
uses: golangci/golangci-lint-action@v9
with:
version: v2.14
version: v2.12
test:
name: Test ${{ matrix.name }}
@@ -87,7 +87,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: Build
@@ -132,7 +132,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: Build ${{ matrix.name }}
-14
View File
@@ -7,20 +7,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
### Removed
- The SSH debug server's `start-cpu-profile`, `stop-cpu-profile`, `save-heap-profile`, `save-mutex-profile`, and
`mutex-profile-fraction` commands, and `sshd.sandbox_dir`, which is now ignored if set.
### Fixed
- Signing a v2 certificate with an empty name, a name longer than 253 bytes, or an empty group now fails.
These certificates were signed successfully but could not be loaded.
- `create-tunnel -address <ip:port>` panicked on a nil RemoteList and, over the ssh debug server, took nebula
down with it. A hostinfo returned by StartHandshake had no RemoteList until the handshake loop's first
pass attached one, and `create-tunnel -address` set the remote before that. The list is now attached when
the handshake starts, so a pending hostinfo never exists without one.
## [1.11.1] - 2026-08-21
See the [v1.11.1](https://github.com/slackhq/nebula/milestone/30?closed=1) milestone for a complete list of changes.
+1 -10
View File
@@ -389,16 +389,7 @@ func (c *certificateV2) fromTBSCertificate(t *TBSCertificate) error {
}
func (c *certificateV2) validate() error {
// Mirror the name and group rules in unmarshalDetails so signing fails instead of producing an unparseable certificate
if c.details.name == "" || len(c.details.name) > MaxNameLength {
return NewErrInvalidCertificateProperties("name must be between 1 and %d bytes", MaxNameLength)
}
for _, group := range c.details.groups {
if group == "" {
return NewErrInvalidCertificateProperties("groups may not be empty")
}
}
// Empty names are allowed
if len(c.publicKey) == 0 {
return ErrInvalidPublicKey
-45
View File
@@ -6,7 +6,6 @@ import (
"crypto/elliptic"
"crypto/rand"
"net/netip"
"strings"
"testing"
"time"
@@ -136,47 +135,3 @@ func TestCertificate_SignP256_AlwaysNormalized(t *testing.T) {
assert.True(t, normie)
}
}
func TestCertificateV2_SignRejectsUnparseable(t *testing.T) {
_, priv, err := ed25519.GenerateKey(rand.Reader)
require.NoError(t, err)
var invalid *ErrInvalidCertificateProperties
newTBS := func() TBSCertificate {
return TBSCertificate{
Version: Version2,
Name: "testing",
Networks: []netip.Prefix{mustParsePrefixUnmapped("10.1.1.1/24")},
Groups: []string{"test-group1"},
NotBefore: time.Now().Add(-time.Minute),
NotAfter: time.Now().Add(time.Minute),
PublicKey: []byte("1234567890abcedfghij1234567890ab"),
Curve: Curve_CURVE25519,
IsCA: true,
}
}
tbs := newTBS()
tbs.Name = strings.Repeat("a", MaxNameLength)
c, err := tbs.Sign(nil, Curve_CURVE25519, priv)
require.NoError(t, err)
b, err := c.Marshal()
require.NoError(t, err)
_, err = unmarshalCertificateV2(b, nil, Curve_CURVE25519)
require.NoError(t, err)
tbs = newTBS()
tbs.Name = strings.Repeat("a", MaxNameLength+1)
_, err = tbs.Sign(nil, Curve_CURVE25519, priv)
require.ErrorAs(t, err, &invalid)
tbs = newTBS()
tbs.Name = ""
_, err = tbs.Sign(nil, Curve_CURVE25519, priv)
require.ErrorAs(t, err, &invalid)
tbs = newTBS()
tbs.Groups = []string{"test-group1", ""}
_, err = tbs.Sign(nil, Curve_CURVE25519, priv)
require.ErrorAs(t, err, &invalid)
}
+1 -2
View File
@@ -85,10 +85,9 @@ func main() {
fmt.Printf("failed to apply logging config: %s", err)
os.Exit(1)
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
c.RegisterReloadCallback(func(c *config.C) {
if err := logging.ApplyConfig(l, c); err != nil {
l.Error("Failed to reconfigure logger on reload", "error", err)
r.Failed()
}
})
+1 -2
View File
@@ -34,10 +34,9 @@ func (p *program) Start(s service.Service) error {
if err := logging.ApplyConfig(l, c); err != nil {
return fmt.Errorf("failed to apply logging config: %s", err)
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
c.RegisterReloadCallback(func(c *config.C) {
if err := logging.ApplyConfig(l, c); err != nil {
l.Error("Failed to reconfigure logger on reload", "error", err)
r.Failed()
}
})
+1 -2
View File
@@ -71,10 +71,9 @@ func main() {
fmt.Printf("failed to apply logging config: %s", err)
os.Exit(1)
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
c.RegisterReloadCallback(func(c *config.C) {
if err := logging.ApplyConfig(l, c); err != nil {
l.Error("Failed to reconfigure logger on reload", "error", err)
r.Failed()
}
})
-710
View File
@@ -1,710 +0,0 @@
package nebula
import (
"bytes"
"encoding/json"
"flag"
"fmt"
"log/slog"
"maps"
"net/netip"
"sort"
"strings"
"github.com/slackhq/nebula/commands"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/logging"
)
// The commands nebula serves. attachCommands builds the one registry every surface
// reads. See the commands package for what a Command is.
type listHostMapFlags struct {
Json bool
Pretty bool
ByIndex bool
}
// listHostMapFlagSet is the flag set list-hostmap and list-pending-hostmap share.
func listHostMapFlagSet() (*flag.FlagSet, any) {
fl := flag.NewFlagSet("", flag.ContinueOnError)
s := listHostMapFlags{}
fl.BoolVar(&s.Json, "json", false, "outputs as json with more information")
fl.BoolVar(&s.Pretty, "pretty", false, "pretty prints json, assumes -json")
fl.BoolVar(&s.ByIndex, "by-index", false, "gets all hosts in the hostmap from the index table")
return fl, &s
}
type printCertFlags struct {
Json bool
Pretty bool
Raw bool
}
type printTunnelFlags struct {
Pretty bool
}
type changeRemoteFlags struct {
Address string
}
type closeTunnelFlags struct {
LocalOnly bool
}
type createTunnelFlags struct {
Address string
}
type deviceInfoFlags struct {
Json bool
Pretty bool
}
func attachCommands(l *slog.Logger, c *config.C, reg *commands.Registry, f *Interface) {
reg.Register(&commands.Command{
Name: commands.ListHostmap,
ShortDescription: "List all known previously connected hosts",
Flags: listHostMapFlagSet,
Callback: func(fs any, a []string, w commands.StringWriter) error {
return listHostMapCommand(f.hostMap, fs, w)
},
})
reg.Register(&commands.Command{
Name: commands.ListPendingHostmap,
ShortDescription: "List all handshaking hosts",
Flags: listHostMapFlagSet,
Callback: func(fs any, a []string, w commands.StringWriter) error {
return listHostMapCommand(f.handshakeManager, fs, w)
},
})
reg.Register(&commands.Command{
Name: commands.ListLighthouseAddrmap,
ShortDescription: "List all lighthouse map entries",
Flags: func() (*flag.FlagSet, any) {
fl := flag.NewFlagSet("", flag.ContinueOnError)
s := listHostMapFlags{}
fl.BoolVar(&s.Json, "json", false, "outputs as json with more information")
fl.BoolVar(&s.Pretty, "pretty", false, "pretty prints json, assumes -json")
return fl, &s
},
Callback: func(fs any, a []string, w commands.StringWriter) error {
return listLighthouseAddrmapCommand(f.lightHouse, fs, w)
},
})
reg.Register(&commands.Command{
Name: commands.Reload,
ShortDescription: "Reloads configuration from disk, same as sending HUP to the process",
Callback: func(fs any, a []string, w commands.StringWriter) error {
return reloadCommand(l, c, w)
},
})
reg.Register(&commands.Command{
Name: commands.LogLevel,
ShortDescription: "Gets or sets the current log level",
Callback: func(fs any, a []string, w commands.StringWriter) error {
return logLevelCommand(l, fs, a, w)
},
})
reg.Register(&commands.Command{
Name: commands.LogFormat,
ShortDescription: "Gets or sets the current log format",
Callback: func(fs any, a []string, w commands.StringWriter) error {
return logFormatCommand(l, fs, a, w)
},
})
reg.Register(&commands.Command{
Name: commands.Version,
ShortDescription: "Prints the currently running version of nebula",
Callback: func(fs any, a []string, w commands.StringWriter) error {
return versionCommand(f, fs, a, w)
},
})
reg.Register(&commands.Command{
Name: commands.DeviceInfo,
ShortDescription: "Prints information about the network device.",
Flags: func() (*flag.FlagSet, any) {
fl := flag.NewFlagSet("", flag.ContinueOnError)
s := deviceInfoFlags{}
fl.BoolVar(&s.Json, "json", false, "outputs as json with more information")
fl.BoolVar(&s.Pretty, "pretty", false, "pretty prints json, assumes -json")
return fl, &s
},
Callback: func(fs any, a []string, w commands.StringWriter) error {
return deviceInfoCommand(f, fs, w)
},
})
reg.Register(&commands.Command{
Name: commands.PrintCert,
ShortDescription: "Prints the current certificate being used or the certificate for the provided vpn addr",
Flags: func() (*flag.FlagSet, any) {
fl := flag.NewFlagSet("", flag.ContinueOnError)
s := printCertFlags{}
fl.BoolVar(&s.Json, "json", false, "outputs as json")
fl.BoolVar(&s.Pretty, "pretty", false, "pretty prints json, assumes -json")
fl.BoolVar(&s.Raw, "raw", false, "raw prints the PEM encoded certificate, not compatible with -json or -pretty")
return fl, &s
},
Callback: func(fs any, a []string, w commands.StringWriter) error {
return printCertCommand(f, fs, a, w)
},
})
reg.Register(&commands.Command{
Name: commands.PrintTunnel,
ShortDescription: "Prints json details about a tunnel for the provided vpn addr",
Flags: func() (*flag.FlagSet, any) {
fl := flag.NewFlagSet("", flag.ContinueOnError)
s := printTunnelFlags{}
fl.BoolVar(&s.Pretty, "pretty", false, "pretty prints json")
return fl, &s
},
Callback: func(fs any, a []string, w commands.StringWriter) error {
return printTunnelCommand(f, fs, a, w)
},
})
reg.Register(&commands.Command{
Name: commands.PrintRelays,
ShortDescription: "Prints json details about all relay info",
Flags: func() (*flag.FlagSet, any) {
fl := flag.NewFlagSet("", flag.ContinueOnError)
s := printTunnelFlags{}
fl.BoolVar(&s.Pretty, "pretty", false, "pretty prints json")
return fl, &s
},
Callback: func(fs any, a []string, w commands.StringWriter) error {
return printRelaysCommand(f, fs, a, w)
},
})
reg.Register(&commands.Command{
Name: commands.ChangeRemote,
ShortDescription: "Changes the remote address used in the tunnel for the provided vpn addr",
Flags: func() (*flag.FlagSet, any) {
fl := flag.NewFlagSet("", flag.ContinueOnError)
s := changeRemoteFlags{}
fl.StringVar(&s.Address, "address", "", "The new remote address, ip:port")
return fl, &s
},
Callback: func(fs any, a []string, w commands.StringWriter) error {
return changeRemoteCommand(f, fs, a, w)
},
})
reg.Register(&commands.Command{
Name: commands.CloseTunnel,
ShortDescription: "Closes a tunnel for the provided vpn addr",
Flags: func() (*flag.FlagSet, any) {
fl := flag.NewFlagSet("", flag.ContinueOnError)
s := closeTunnelFlags{}
fl.BoolVar(&s.LocalOnly, "local-only", false, "Disables notifying the remote that the tunnel is shutting down")
return fl, &s
},
Callback: func(fs any, a []string, w commands.StringWriter) error {
return closeTunnelCommand(f, fs, a, w)
},
})
reg.Register(&commands.Command{
Name: commands.CreateTunnel,
ShortDescription: "Creates a tunnel for the provided vpn address",
Help: "The lighthouses will be queried for real addresses but you can provide one as well.",
Flags: func() (*flag.FlagSet, any) {
fl := flag.NewFlagSet("", flag.ContinueOnError)
s := createTunnelFlags{}
fl.StringVar(&s.Address, "address", "", "Optionally provide a real remote address, ip:port ")
return fl, &s
},
Callback: func(fs any, a []string, w commands.StringWriter) error {
return createTunnelCommand(f, fs, a, w)
},
})
reg.Register(&commands.Command{
Name: commands.QueryLighthouse,
ShortDescription: "Query the lighthouses for the provided vpn address",
Help: "This command is asynchronous. Only currently known udp addresses will be printed.",
Callback: func(fs any, a []string, w commands.StringWriter) error {
return queryLighthouseCommand(f, fs, a, w)
},
})
}
func listHostMapCommand(hl controlHostLister, a any, w commands.StringWriter) error {
fs, ok := a.(*listHostMapFlags)
if !ok {
return fmt.Errorf("internal error: expected *listHostMapFlags but was %T", a)
}
var hm []ControlHostInfo
if fs.ByIndex {
hm = listHostMapIndexes(hl)
} else {
hm = listHostMapHosts(hl)
}
sort.Slice(hm, func(i, j int) bool {
return hm[i].VpnAddrs[0].Compare(hm[j].VpnAddrs[0]) < 0
})
if fs.Json || fs.Pretty {
js := json.NewEncoder(w.GetWriter())
if fs.Pretty {
js.SetIndent("", " ")
}
if err := js.Encode(hm); err != nil {
return err
}
} else {
for _, v := range hm {
err := w.WriteLine(fmt.Sprintf("%s: %s", v.VpnAddrs, v.RemoteAddrs))
if err != nil {
return err
}
}
}
return nil
}
func listLighthouseAddrmapCommand(lightHouse *LightHouse, a any, w commands.StringWriter) error {
fs, ok := a.(*listHostMapFlags)
if !ok {
return fmt.Errorf("internal error: expected *listHostMapFlags but was %T", a)
}
type lighthouseInfo struct {
VpnAddr string `json:"vpnAddr"`
Addrs *CacheMap `json:"addrs"`
}
lightHouse.RLock()
addrMap := make([]lighthouseInfo, len(lightHouse.addrMap))
x := 0
for k, v := range lightHouse.addrMap {
addrMap[x] = lighthouseInfo{
VpnAddr: k.String(),
Addrs: v.CopyCache(),
}
x++
}
lightHouse.RUnlock()
sort.Slice(addrMap, func(i, j int) bool {
return strings.Compare(addrMap[i].VpnAddr, addrMap[j].VpnAddr) < 0
})
if fs.Json || fs.Pretty {
js := json.NewEncoder(w.GetWriter())
if fs.Pretty {
js.SetIndent("", " ")
}
if err := js.Encode(addrMap); err != nil {
return err
}
} else {
for _, v := range addrMap {
b, err := json.Marshal(v.Addrs)
if err != nil {
return err
}
err = w.WriteLine(fmt.Sprintf("%s: %s", v.VpnAddr, string(b)))
if err != nil {
return err
}
}
}
return nil
}
// parseVpnAddr parses the vpn address a command takes as its first operand, failing to w
// when there is none or it does not parse. noun is how the command's messages name it,
// "vpn address" or "vpn addr", which the output golden pins per command.
func parseVpnAddr(a []string, noun string, w commands.StringWriter) (netip.Addr, error) {
if len(a) == 0 {
return netip.Addr{}, commands.Fail(w, "No vpn address was provided")
}
vpnAddr, err := netip.ParseAddr(a[0])
if err != nil {
return netip.Addr{}, commands.Fail(w, fmt.Sprintf("The provided %s could not be parsed: %s", noun, a[0]))
}
return vpnAddr, nil
}
func versionCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
return w.WriteLine(ifce.version)
}
func queryLighthouseCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
vpnAddr, err := parseVpnAddr(a, "vpn address", w)
if err != nil {
return err
}
var cm *CacheMap
rl := ifce.lightHouse.Query(vpnAddr)
if rl != nil {
cm = rl.CopyCache()
}
return json.NewEncoder(w.GetWriter()).Encode(cm)
}
func closeTunnelCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
flags, ok := fs.(*closeTunnelFlags)
if !ok {
return fmt.Errorf("internal error: expected *closeTunnelFlags but was %T", fs)
}
vpnAddr, err := parseVpnAddr(a, "vpn address", w)
if err != nil {
return err
}
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
if hostInfo == nil {
return commands.Fail(w, fmt.Sprintf("Could not find tunnel for vpn address: %v", a[0]))
}
if !flags.LocalOnly {
ifce.sendCloseTunnel(hostInfo)
}
ifce.closeTunnel(hostInfo)
return w.WriteLine("Closed")
}
func createTunnelCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
flags, ok := fs.(*createTunnelFlags)
if !ok {
return fmt.Errorf("internal error: expected *createTunnelFlags but was %T", fs)
}
vpnAddr, err := parseVpnAddr(a, "vpn address", w)
if err != nil {
return err
}
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
if hostInfo != nil {
return commands.Fail(w, "Tunnel already exists")
}
hostInfo = ifce.handshakeManager.QueryVpnAddr(vpnAddr)
if hostInfo != nil {
return commands.Fail(w, "Tunnel already handshaking")
}
var addr netip.AddrPort
if flags.Address != "" {
addr, err = netip.ParseAddrPort(flags.Address)
if err != nil {
return commands.Fail(w, "Address could not be parsed")
}
}
// Set the remote from the callback, which StartHandshake runs under the handshake manager lock
// before the hostinfo reaches the handshake loop or the static-host trigger, so the address is
// in the RemoteList before the first handshake is sent.
ifce.handshakeManager.StartHandshake(vpnAddr, func(hh *HandshakeHostInfo) {
if addr.IsValid() {
hh.hostinfo.SetRemote(addr)
}
})
return w.WriteLine("Created")
}
func changeRemoteCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
flags, ok := fs.(*changeRemoteFlags)
if !ok {
return fmt.Errorf("internal error: expected *changeRemoteFlags but was %T", fs)
}
vpnAddr, err := parseVpnAddr(a, "vpn address", w)
if err != nil {
return err
}
if flags.Address == "" {
return commands.Fail(w, "No address was provided")
}
addr, err := netip.ParseAddrPort(flags.Address)
if err != nil {
return commands.Fail(w, "Address could not be parsed")
}
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
if hostInfo == nil {
return commands.Fail(w, fmt.Sprintf("Could not find tunnel for vpn address: %v", a[0]))
}
hostInfo.SetRemote(addr)
return w.WriteLine("Changed")
}
func logLevelCommand(l *slog.Logger, fs any, a []string, w commands.StringWriter) error {
ctrl, ok := l.Handler().(interface {
GetLevel() slog.Level
SetLevel(slog.Level)
})
if !ok {
return commands.Fail(w, "Log level is not reconfigurable on this logger")
}
if len(a) == 0 {
return w.WriteLine(fmt.Sprintf("Log level is: %s", logging.LevelName(ctrl.GetLevel())))
}
level, err := logging.ParseLevel(strings.ToLower(a[0]))
if err != nil {
return commands.Fail(w, fmt.Sprintf("Unknown log level %s. Possible log levels: trace, debug, info, warn, error", a))
}
ctrl.SetLevel(level)
return w.WriteLine(fmt.Sprintf("Log level is: %s", logging.LevelName(ctrl.GetLevel())))
}
func logFormatCommand(l *slog.Logger, fs any, a []string, w commands.StringWriter) error {
ctrl, ok := l.Handler().(interface {
GetFormat() string
SetFormat(string) error
})
if !ok {
return commands.Fail(w, "Log format is not reconfigurable on this logger")
}
if len(a) == 0 {
return w.WriteLine(fmt.Sprintf("Log format is: %s", ctrl.GetFormat()))
}
if err := ctrl.SetFormat(strings.ToLower(a[0])); err != nil {
return commands.Fail(w, fmt.Sprintf("Unable to set log format: %s", err))
}
return w.WriteLine(fmt.Sprintf("Log format is: %s", ctrl.GetFormat()))
}
func printCertCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
args, ok := fs.(*printCertFlags)
if !ok {
return fmt.Errorf("internal error: expected *printCertFlags but was %T", fs)
}
cert := ifce.pki.getCertState().GetDefaultCertificate()
if len(a) > 0 {
vpnAddr, err := parseVpnAddr(a, "vpn addr", w)
if err != nil {
return err
}
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
if hostInfo == nil {
return commands.Fail(w, fmt.Sprintf("Could not find tunnel for vpn addr: %v", a[0]))
}
cert = hostInfo.GetCert().Certificate
}
if args.Json || args.Pretty {
b, err := cert.MarshalJSON()
if err != nil {
return commands.Fail(w, fmt.Sprintf("Unable to marshal the certificate: %s", err))
}
if args.Pretty {
buf := new(bytes.Buffer)
if err := json.Indent(buf, b, "", " "); err != nil {
return commands.Fail(w, fmt.Sprintf("Unable to marshal the certificate: %s", err))
}
b = buf.Bytes()
}
return w.WriteBytes(b)
}
if args.Raw {
b, err := cert.MarshalPEM()
if err != nil {
return commands.Fail(w, fmt.Sprintf("Unable to marshal the certificate: %s", err))
}
return w.WriteBytes(b)
}
return w.WriteLine(cert.String())
}
func printRelaysCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
args, ok := fs.(*printTunnelFlags)
if !ok {
return fmt.Errorf("internal error: expected *printTunnelFlags but was %T", fs)
}
ifce.hostMap.RLock()
relays := maps.Clone(ifce.hostMap.Relays)
ifce.hostMap.RUnlock()
type RelayFor struct {
Error string `json:",omitempty"`
Type string
State string
PeerAddr netip.Addr
LocalIndex uint32
RemoteIndex uint32
RelayedThrough []netip.Addr
}
type RelayOutput struct {
NebulaAddr netip.Addr
RelayForAddrs []RelayFor
}
type CmdOutput struct {
Relays []*RelayOutput
}
co := CmdOutput{}
enc := json.NewEncoder(w.GetWriter())
if args.Pretty {
enc.SetIndent("", " ")
}
for k, v := range relays {
ro := RelayOutput{NebulaAddr: v.vpnAddrs[0]}
co.Relays = append(co.Relays, &ro)
relayHI := ifce.hostMap.QueryVpnAddr(v.vpnAddrs[0])
if relayHI == nil {
ro.RelayForAddrs = append(ro.RelayForAddrs, RelayFor{Error: "could not find hostinfo"})
continue
}
for _, vpnAddr := range relayHI.relayState.CopyRelayForIps() {
rf := RelayFor{}
r, ok := relayHI.relayState.GetRelayForByAddr(vpnAddr)
if ok {
t := ""
switch r.Type {
case ForwardingType:
t = "forwarding"
case TerminalType:
t = "terminal"
default:
t = "unknown"
}
s := ""
switch r.State {
case Requested:
s = "requested"
case Established:
s = "established"
default:
s = "unknown"
}
rf.LocalIndex = r.LocalIndex
rf.RemoteIndex = r.RemoteIndex
rf.PeerAddr = r.PeerAddr
rf.Type = t
rf.State = s
if rf.LocalIndex != k {
rf.Error = fmt.Sprintf("hostmap LocalIndex '%v' does not match RelayState LocalIndex", k)
}
}
relayedHI := ifce.hostMap.QueryVpnAddr(vpnAddr)
if relayedHI != nil {
rf.RelayedThrough = append(rf.RelayedThrough, relayedHI.relayState.CopyRelayIps()...)
}
ro.RelayForAddrs = append(ro.RelayForAddrs, rf)
}
}
return enc.Encode(co)
}
func printTunnelCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
args, ok := fs.(*printTunnelFlags)
if !ok {
return fmt.Errorf("internal error: expected *printTunnelFlags but was %T", fs)
}
vpnAddr, err := parseVpnAddr(a, "vpn addr", w)
if err != nil {
return err
}
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
if hostInfo == nil {
return commands.Fail(w, fmt.Sprintf("Could not find tunnel for vpn addr: %v", a[0]))
}
enc := json.NewEncoder(w.GetWriter())
if args.Pretty {
enc.SetIndent("", " ")
}
return enc.Encode(copyHostInfo(hostInfo, ifce.hostMap.GetPreferredRanges()))
}
func deviceInfoCommand(ifce *Interface, fs any, w commands.StringWriter) error {
flags, ok := fs.(*deviceInfoFlags)
if !ok {
return fmt.Errorf("internal error: expected flags to be deviceInfoFlags but was %+v", fs)
}
data := struct {
Name string `json:"name"`
Cidr []netip.Prefix `json:"cidr"`
}{
Name: ifce.inside.Name(),
Cidr: make([]netip.Prefix, len(ifce.inside.Networks())),
}
copy(data.Cidr, ifce.inside.Networks())
if flags.Json || flags.Pretty {
js := json.NewEncoder(w.GetWriter())
if flags.Pretty {
js.SetIndent("", " ")
}
return js.Encode(data)
} else {
return w.WriteLine(fmt.Sprintf("name=%v cidr=%v", data.Name, data.Cidr))
}
}
// reloadCommand reloads the config and writes the result to the client. It reloads even if the client has gone away
func reloadCommand(l *slog.Logger, c *config.C, w commands.StringWriter) error {
writeErr := w.WriteLine("Reloading config")
res := c.ReloadConfig()
res.Log(l)
if err := w.WriteLine(res.String()); writeErr == nil {
writeErr = err
}
if writeErr != nil {
return writeErr
}
if res.Err != nil || res.Failed {
return &commands.Failure{Msg: res.String()}
}
return nil
}
-83
View File
@@ -1,83 +0,0 @@
package commands
import (
"flag"
)
// CommandFlags is called before help or command execution to parse command line flags.
// It should return a flag.FlagSet instance and a pointer to the struct that will contain parsed flags
type CommandFlags func() (*flag.FlagSet, any)
// CommandCallback is called when your command should execute.
// fs will be a pointer to the struct provided by Command.Flags callback, if there was one. -h and -help are reserved
// and handled automatically for you.
// a will be any unconsumed arguments, if no Command.Flags was available this will be all the flags passed in.
// w is the writer to use when sending messages back to the client.
// An error returned by the callback is handed back to whoever dispatched the command, which reports a failure: exit
// status 1 over ssh. The error is not shown to the user. For a failure the user caused or can act on, write the
// message and return it as a *Failure, which Fail does in one step; the surface then reports the failure without
// logging what the user was already told. Any other error is logged by the surface as well.
type CommandCallback func(fs any, a []string, w StringWriter) error
type Command struct {
Name Name
ShortDescription string
Help string
Flags CommandFlags
Callback CommandCallback
}
// Failure is the error a command returns for a failure it has already explained to the user:
// the message it wrote is the whole story. A surface reports it as a failure and does not
// log it.
type Failure struct {
Msg string
}
func (f *Failure) Error() string {
return f.Msg
}
// Fail writes msg to w and returns it as a *Failure, so a command reports a failure to the
// user and to its surface in one line. If the write itself fails, that error is returned
// instead: the user was not told anything.
func Fail(w StringWriter, msg string) error {
if err := w.WriteLine(msg); err != nil {
return err
}
return &Failure{Msg: msg}
}
func execCommand(c *Command, args []string, w StringWriter) error {
var (
fl *flag.FlagSet
fs any
)
if c.Flags != nil {
fl, fs = c.Flags()
if fl != nil {
// SetOutput() here in case fl.Parse dumps usage.
fl.SetOutput(w.GetWriter())
err := fl.Parse(args)
if err != nil {
// fl.Parse has dumped error information to the user via the w writer.
return err
}
args = fl.Args()
}
}
return c.Callback(fs, args, w)
}
func checkHelpArgs(args []string) bool {
for _, a := range args {
if a == "-h" || a == "-help" {
return true
}
}
return false
}
-28
View File
@@ -1,28 +0,0 @@
package commands
// Name identifies a command. Every command nebula serves is a constant here, so a
// surface, a client and a test spell it the same way and are told at compile time when
// they do not. It is a string rather than an integer so a test can register a throwaway
// command without adding it here, and so the wire carries the name as the string it has
// always been.
type Name string
const (
ChangeRemote Name = "change-remote"
CloseTunnel Name = "close-tunnel"
CreateTunnel Name = "create-tunnel"
DeviceInfo Name = "device-info"
Help Name = "help"
ListHostmap Name = "list-hostmap"
ListLighthouseAddrmap Name = "list-lighthouse-addrmap"
ListPendingHostmap Name = "list-pending-hostmap"
LogFormat Name = "log-format"
LogLevel Name = "log-level"
Logout Name = "logout"
PrintCert Name = "print-cert"
PrintRelays Name = "print-relays"
PrintTunnel Name = "print-tunnel"
QueryLighthouse Name = "query-lighthouse"
Reload Name = "reload"
Version Name = "version"
)
-181
View File
@@ -1,181 +0,0 @@
package commands
import (
"cmp"
"fmt"
"maps"
"slices"
"strings"
"sync"
"github.com/anmitsu/go-shlex"
)
// Registry holds a set of commands. New is the only way to make one.
//
// It is safe for concurrent use. Commands may be registered while a surface is serving
// from the registry: the ssh server clones it per session, and a clone may overlap a
// Register.
type Registry struct {
mu sync.RWMutex
commands map[Name]*Command
}
// New returns an empty Registry with only `help` available.
func New() *Registry {
r := &Registry{commands: map[Name]*Command{}}
r.registerHelp()
return r
}
func (r *Registry) registerHelp() {
r.Register(&Command{
Name: Help,
ShortDescription: "prints available commands or help <command> for specific usage info",
Callback: func(a any, args []string, w StringWriter) error {
return r.help(args, w)
},
})
}
// Register adds a command that can be run by a user. A command registered under a name
// already held replaces it; see Clone for what that means for Help.
func (r *Registry) Register(c *Command) {
r.mu.Lock()
defer r.mu.Unlock()
r.commands[c.Name] = c
}
// Get returns the command registered under name, or nil if there is no such command.
func (r *Registry) Get(name Name) *Command {
r.mu.RLock()
defer r.mu.RUnlock()
return r.commands[name]
}
// Match returns the names of every command starting with prefix, sorted, as strings for
// a prompt to complete and print.
func (r *Registry) Match(prefix string) []string {
cmds := make([]string, 0)
r.mu.RLock()
for n := range r.commands {
if strings.HasPrefix(string(n), prefix) {
cmds = append(cmds, string(n))
}
}
r.mu.RUnlock()
slices.Sort(cmds)
return cmds
}
// All returns every registered command sorted by name, which is the order help lists them.
func (r *Registry) All() []*Command {
r.mu.RLock()
defer r.mu.RUnlock()
cmds := slices.Collect(maps.Values(r.commands))
slices.SortFunc(cmds, func(a, b *Command) int { return cmp.Compare(a.Name, b.Name) })
return cmds
}
// Clone returns a copy holding the same commands, with help bound to the copy: a
// command registered on the clone alone is listed and described there, and one the
// clone withholds is not. That rebinding replaces whatever was registered under Help on
// the source, built-in or not.
func (r *Registry) Clone() *Registry {
r.mu.RLock()
c := &Registry{commands: maps.Clone(r.commands)}
r.mu.RUnlock()
c.registerHelp()
return c
}
// Dispatch parses a command line and runs it, reporting problems to w. The error is for
// the caller to log, not to show; see CommandCallback.
func (r *Registry) Dispatch(line string, w StringWriter) error {
// A line shlex cannot split, an unbalanced quote.
args, err := shlex.Split(line, true)
if err != nil {
return Fail(w, "could not parse the command line: "+err.Error())
}
return r.DispatchArgs(args, w)
}
// DispatchArgs runs an already tokenized command line. The error is as for Dispatch.
func (r *Registry) DispatchArgs(args []string, w StringWriter) error {
if len(args) == 0 {
r.dumpCommands(w)
return nil
}
c := r.Get(Name(args[0]))
if c == nil {
// Only the first word was looked up, so only it is named.
msg := fmt.Sprintf("did not understand: %s", args[0])
if err := w.WriteLine(msg); err != nil {
return err
}
r.dumpCommands(w)
return &Failure{Msg: msg}
}
if checkHelpArgs(args) {
// Through the registered help command, so -h and `help <name>` are one path.
return execCommand(r.Get(Help), []string{string(c.Name)}, w)
}
return execCommand(c, args[1:], w)
}
// dumpCommands writes the list of available commands to w.
func (r *Registry) dumpCommands(w StringWriter) {
err := w.WriteLine("Available commands:")
if err != nil {
return
}
// In the order All gives, which is the display order.
cmds := make([]string, 0)
for _, l := range r.All() {
cmds = append(cmds, fmt.Sprintf("%s - %s", l.Name, l.ShortDescription))
}
_ = w.Write(strings.Join(cmds, "\n") + "\n\n")
}
// help writes the command list, or usage for the single command named in a.
func (r *Registry) help(a []string, w StringWriter) error {
// Just typed help
if len(a) == 0 {
r.dumpCommands(w)
return nil
}
// We are printing a specific commands help text
cmd := r.Get(Name(a[0]))
if cmd == nil {
return Fail(w, "Command not available "+a[0])
}
if err := w.WriteLine(fmt.Sprintf("%s - %s", cmd.Name, cmd.ShortDescription)); err != nil {
return err
}
if cmd.Help != "" {
if err := w.WriteLine(fmt.Sprintf(" %s", cmd.Help)); err != nil {
return err
}
}
if cmd.Flags != nil {
fs, _ := cmd.Flags()
if fs != nil {
fs.SetOutput(w.GetWriter())
fs.PrintDefaults()
}
}
return nil
}
-176
View File
@@ -1,176 +0,0 @@
package commands
import (
"bytes"
"errors"
"flag"
"strings"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func testRegistry() *Registry {
r := New()
r.Register(&Command{
Name: "served",
ShortDescription: "a command this surface serves",
Callback: func(fs any, a []string, w StringWriter) error {
return w.WriteLine("read " + strings.Join(a, ","))
},
})
r.Register(&Command{
Name: "withheld",
ShortDescription: "a command this surface withholds",
Callback: func(fs any, a []string, w StringWriter) error {
return w.WriteLine("wrote")
},
})
return r
}
// TestFlagUsageGoesToTheWriter pins that a parse failure's usage lands on the command's
// writer.
func TestFlagUsageGoesToTheWriter(t *testing.T) {
r := New()
r.Register(&Command{
Name: "emit",
ShortDescription: "emits",
Flags: func() (*flag.FlagSet, any) {
fl := flag.NewFlagSet("", flag.ContinueOnError)
fl.Bool("json", false, "emit json")
return fl, nil
},
Callback: func(fs any, a []string, w StringWriter) error { return nil },
})
merged := &bytes.Buffer{}
require.Error(t, r.DispatchArgs([]string{"emit", "-nope"}, NewStringWriter(merged)))
assert.Contains(t, merged.String(), "flag provided but not defined")
}
// TestDispatchReportsUnparseableLine: a line shlex rejects, an unbalanced quote, is a
// failure the user is told about.
func TestDispatchReportsUnparseableLine(t *testing.T) {
out := &bytes.Buffer{}
err := testRegistry().Dispatch(`served "unterminated`, NewStringWriter(out))
var f *Failure
require.ErrorAs(t, err, &f)
assert.Equal(t, f.Msg+"\n", out.String())
assert.Contains(t, out.String(), "could not parse the command line: ")
}
// TestFailTellsTheUserAndTheSurface: Fail writes the message and returns it as a Failure;
// when the write fails, the user heard nothing, so the write error is what comes back.
func TestFailTellsTheUserAndTheSurface(t *testing.T) {
out := &bytes.Buffer{}
err := Fail(NewStringWriter(out), "no such tunnel")
var f *Failure
require.ErrorAs(t, err, &f)
assert.Equal(t, "no such tunnel", f.Msg)
assert.Equal(t, "no such tunnel\n", out.String())
err = Fail(NewStringWriter(failingWriter{}), "no such tunnel")
require.EqualError(t, err, "gone")
assert.NotErrorAs(t, err, &f)
}
type failingWriter struct{}
func (failingWriter) Write([]byte) (int, error) { return 0, errors.New("gone") }
// TestAllSortsByName: registration order does not matter.
func TestAllSortsByName(t *testing.T) {
r := New()
for _, n := range []Name{"zz", Version, "aa", ChangeRemote} {
r.Register(&Command{Name: n})
}
var got []Name
for _, c := range r.All() {
got = append(got, c.Name)
}
assert.Equal(t, []Name{"aa", ChangeRemote, Help, Version, "zz"}, got)
}
// TestHelpFlagAgreesWithHelpCommand pins that -h answers through the registered help
// command, and that help on a clone describes the clone: a command registered only there
// is known to both -h and `help <name>`, and one withheld from it is known to neither.
func TestHelpFlagAgreesWithHelpCommand(t *testing.T) {
r := testRegistry()
c := r.Clone()
c.Register(&Command{
Name: Logout,
ShortDescription: "ends the session",
Callback: func(fs any, a []string, w StringWriter) error { return nil },
})
flag := &bytes.Buffer{}
c.Dispatch("logout -h", NewStringWriter(flag))
cmd := &bytes.Buffer{}
c.Dispatch("help logout", NewStringWriter(cmd))
assert.Equal(t, cmd.String(), flag.String())
assert.Equal(t, "logout - ends the session\n", flag.String())
// The source never learns of it.
src := &bytes.Buffer{}
r.Dispatch("help logout", NewStringWriter(src))
assert.Equal(t, "Command not available logout\n", src.String())
// And a command both hold is described either way.
flag.Reset()
c.Dispatch("served -h", NewStringWriter(flag))
assert.Equal(t, "served - a command this surface serves\n", flag.String())
}
// TestCloneHelpListsTheClone: the command list help prints is the clone's, so a clone
// that withholds a command does not name it, and the source still does.
func TestCloneHelpListsTheClone(t *testing.T) {
r := testRegistry()
c := New()
c.Register(r.Get("served"))
c = c.Clone()
out := &bytes.Buffer{}
c.Dispatch("help", NewStringWriter(out))
assert.Equal(t, "Available commands:\n"+
"help - prints available commands or help <command> for specific usage info\n"+
"served - a command this surface serves\n\n", out.String())
out.Reset()
c.Dispatch("help withheld", NewStringWriter(out))
assert.Equal(t, "Command not available withheld\n", out.String())
out.Reset()
r.Dispatch("help withheld", NewStringWriter(out))
assert.Equal(t, "withheld - a command this surface withholds\n", out.String())
}
// TestDispatchReturnsTheCommandsError: what the callback returns reaches the caller, so
// a surface can log it.
func TestDispatchReturnsTheCommandsError(t *testing.T) {
r := New()
r.Register(&Command{
Name: "fails",
Callback: func(fs any, a []string, w StringWriter) error {
return errors.New("boom")
},
})
out := &bytes.Buffer{}
require.EqualError(t, r.Dispatch("fails", NewStringWriter(out)), "boom")
assert.Empty(t, out.String(), "a command's own error is not shown; the command speaks for itself")
}
// TestUnknownCommandNamesTheWord: only the first word is looked up, so only it is
// reported, followed by the command list, and the line is a failure to the surface.
func TestUnknownCommandNamesTheWord(t *testing.T) {
out := &bytes.Buffer{}
err := testRegistry().Dispatch(`nope "with args"`, NewStringWriter(out))
var f *Failure
require.ErrorAs(t, err, &f)
assert.Equal(t, "did not understand: nope", f.Msg)
assert.True(t, strings.HasPrefix(out.String(), "did not understand: nope\nAvailable commands:\n"), out.String())
}
-67
View File
@@ -1,67 +0,0 @@
package nebula
import (
"bytes"
"io"
"net/netip"
"testing"
"github.com/slackhq/nebula/commands"
"github.com/slackhq/nebula/logging"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// TestLogFormatRefusalIsShown: a format the logger does not know is reported to the user
// as a failure, rather than returned bare, which over ssh was silence.
func TestLogFormatRefusalIsShown(t *testing.T) {
l := logging.NewLogger(io.Discard)
out := &bytes.Buffer{}
w := commands.NewStringWriter(out)
var f *commands.Failure
require.ErrorAs(t, logFormatCommand(l, nil, []string{"bogus"}, w), &f)
assert.Equal(t, "Unable to set log format: unknown log format `bogus`. possible formats: [text json]\n", out.String())
out.Reset()
require.NoError(t, logFormatCommand(l, nil, []string{"JSON"}, w))
assert.Equal(t, "Log format is: json\n", out.String())
}
// TestPrintRelaysReportsErrorsAsText: the Error field was an error value, which encodes
// as {} and lost the message. It is the message now, and absent when there is none.
func TestPrintRelaysReportsErrorsAsText(t *testing.T) {
l := test.NewLogger()
hm := newHostMap(l)
relay := netip.MustParseAddr("10.0.0.1")
peer := netip.MustParseAddr("10.0.0.2")
// A relay host that is in Relays but not in Hosts, so its hostinfo cannot be found.
hm.Relays[1] = &HostInfo{vpnAddrs: []netip.Addr{relay}}
ifce := &Interface{hostMap: hm}
out := &bytes.Buffer{}
require.NoError(t, printRelaysCommand(ifce, &printTunnelFlags{}, nil, commands.NewStringWriter(out)))
assert.JSONEq(t, `{"Relays":[{"NebulaAddr":"10.0.0.1","RelayForAddrs":[{"Error":"could not find hostinfo","Type":"","State":"","PeerAddr":"","LocalIndex":0,"RemoteIndex":0,"RelayedThrough":null}]}]}`, out.String())
// The same relay host, found, relaying for a peer whose index matches: no Error key.
hi := hm.Relays[1]
r := &Relay{Type: ForwardingType, State: Established, PeerAddr: peer, LocalIndex: 1, RemoteIndex: 2}
hi.relayState = RelayState{
relayForByAddr: map[netip.Addr]*Relay{peer: r},
relayForByIdx: map[uint32]*Relay{r.LocalIndex: r},
}
hm.Hosts[relay] = hi
out.Reset()
require.NoError(t, printRelaysCommand(ifce, &printTunnelFlags{}, nil, commands.NewStringWriter(out)))
assert.JSONEq(t, `{"Relays":[{"NebulaAddr":"10.0.0.1","RelayForAddrs":[{"Type":"forwarding","State":"established","PeerAddr":"10.0.0.2","LocalIndex":1,"RemoteIndex":2,"RelayedThrough":null}]}]}`, out.String())
// And an index mismatch names it.
hm.Relays[7] = hi
delete(hm.Relays, 1)
out.Reset()
require.NoError(t, printRelaysCommand(ifce, &printTunnelFlags{}, nil, commands.NewStringWriter(out)))
assert.Contains(t, out.String(), `"Error":"hostmap LocalIndex '7' does not match RelayState LocalIndex"`)
}
+31 -40
View File
@@ -26,12 +26,9 @@ type C struct {
files []string
Settings map[string]any
oldSettings map[string]any
callbacks []func(*C, *Reload)
callbacks []func(*C)
l *slog.Logger
reloadLock sync.Mutex
// Set by the first reload that needs a restart and never cleared. Guarded by reloadLock
needsRestart bool
}
func NewC(l *slog.Logger) *C {
@@ -75,9 +72,8 @@ func (c *C) LoadString(raw string) error {
// RegisterReloadCallback stores a function to be called when a config reload is triggered. The functions registered
// here should decide if they need to make a change to the current process before making the change. HasChanged can be
// used to help decide if a change is necessary.
// These functions should return quickly or spawn their own go routine if they will take a while.
// Use r to report anything that failed or needs a restart to apply.
func (c *C) RegisterReloadCallback(f func(c *C, r *Reload)) {
// These functions should return quickly or spawn their own go routine if they will take a while
func (c *C) RegisterReloadCallback(f func(*C)) {
c.callbacks = append(c.callbacks, f)
}
@@ -148,55 +144,50 @@ func (c *C) CatchHUP(ctx context.Context) {
return
case <-ch:
c.l.Info("Caught HUP, reloading config")
c.ReloadConfig().Log(c.l)
c.ReloadConfig()
}
}
}()
}
// ReloadConfig reloads the config from the path provided to Load and runs every registered callback. A config that
// fails to load is logged here, like any other failure, and the result carries the error for the summary.
func (c *C) ReloadConfig() ReloadResult {
func (c *C) ReloadConfig() {
c.reloadLock.Lock()
defer c.reloadLock.Unlock()
c.oldSettings = make(map[string]any)
maps.Copy(c.oldSettings, c.Settings)
if err := c.Load(c.path); err != nil {
c.l.Error("Error occurred while reloading config", "config_path", c.path, "error", err)
return ReloadResult{Err: err, RestartRequired: c.needsRestart}
err := c.Load(c.path)
if err != nil {
c.l.Error("Error occurred while reloading config",
"config_path", c.path,
"error", err,
)
return
}
return c.runCallbacks()
}
// ReloadConfigString is ReloadConfig for a config held in memory rather than on disk.
func (c *C) ReloadConfigString(raw string) ReloadResult {
c.reloadLock.Lock()
defer c.reloadLock.Unlock()
c.oldSettings = make(map[string]any)
maps.Copy(c.oldSettings, c.Settings)
if err := c.LoadString(raw); err != nil {
c.l.Error("Error occurred while reloading config", "error", err)
return ReloadResult{Err: err, RestartRequired: c.needsRestart}
}
return c.runCallbacks()
}
func (c *C) runCallbacks() ReloadResult {
r := &Reload{c: c}
for _, v := range c.callbacks {
v(c, r)
v(c)
}
}
func (c *C) ReloadConfigString(raw string) error {
c.reloadLock.Lock()
defer c.reloadLock.Unlock()
c.oldSettings = make(map[string]any)
maps.Copy(c.oldSettings, c.Settings)
err := c.LoadString(raw)
if err != nil {
return err
}
if r.restart {
c.needsRestart = true
for _, v := range c.callbacks {
v(c)
}
return ReloadResult{Failed: r.failed, RestartRequired: c.needsRestart, RestartKeys: r.keys}
return nil
}
// GetString will get the string for k or return the default d if not found or invalid
@@ -400,7 +391,7 @@ func (c *C) parse() error {
var nm map[string]any
err = yaml.Unmarshal(b, &nm)
if err != nil {
return fmt.Errorf("%s: %w", path, err)
return err
}
// We need to use WithAppendSlice so that firewall rules in separate
+2 -2
View File
@@ -19,7 +19,7 @@ func TestConfig_Load(t *testing.T) {
// invalid yaml
c := NewC(l)
os.WriteFile(filepath.Join(dir, "01.yaml"), []byte(" invalid yaml"), 0644)
require.EqualError(t, c.Load(dir), filepath.Join(dir, "01.yaml")+": yaml: unmarshal errors:\n line 1: cannot unmarshal !!str `invalid...` into map[string]interface {}")
require.EqualError(t, c.Load(dir), "yaml: unmarshal errors:\n line 1: cannot unmarshal !!str `invalid...` into map[string]interface {}")
// simple multi config merge
c = NewC(l)
@@ -129,7 +129,7 @@ func TestConfig_ReloadConfig(t *testing.T) {
os.WriteFile(filepath.Join(dir, "01.yaml"), []byte("outer:\n inner: ho"), 0644)
c.RegisterReloadCallback(func(c *C, _ *Reload) {
c.RegisterReloadCallback(func(c *C) {
done <- true
})
-98
View File
@@ -1,98 +0,0 @@
package config
import (
"context"
"fmt"
"log/slog"
"slices"
)
// ReloadResult describes how a reload went. Problems are logged where they happen, Log writes a one line summary.
type ReloadResult struct {
// Err is set when the new config could not be read or parsed, no callbacks ran
Err error
// Failed is true when a callback could not apply part of the new config
Failed bool
// RestartRequired is true once any reload has needed a restart, and stays true until the process restarts
RestartRequired bool
// RestartKeys are the keys this reload changed that only apply on a restart
RestartKeys []string
}
// Summary returns a one line summary of the reload and the level to log it at.
func (r ReloadResult) Summary() (slog.Level, string) {
switch {
case r.Err != nil && r.RestartRequired:
return slog.LevelError, "Config reload failed, the new config did not load and a restart is still required"
case r.Err != nil:
return slog.LevelError, "Config reload failed, the new config did not load"
case r.Failed && r.RestartRequired:
return slog.LevelError, "Config reload completed with errors and requires a restart to fully apply, review the logs"
case r.Failed:
return slog.LevelError, "Config reload completed with errors, review the logs"
case r.RestartRequired:
return slog.LevelWarn, "Config reload was completed but requires a restart to fully apply"
default:
return slog.LevelInfo, "Config reload complete"
}
}
// String is the summary with Err and RestartKeys included, for output other than the log.
func (r ReloadResult) String() string {
_, msg := r.Summary()
if r.Err != nil {
msg = fmt.Sprintf("%s: %v", msg, r.Err)
}
if len(r.RestartKeys) > 0 {
msg = fmt.Sprintf("%s, keys %v", msg, r.RestartKeys)
}
return msg
}
// Log writes Summary to l.
func (r ReloadResult) Log(l *slog.Logger) {
level, msg := r.Summary()
if len(r.RestartKeys) > 0 {
l.Log(context.Background(), level, msg, "keys", r.RestartKeys)
return
}
l.Log(context.Background(), level, msg)
}
// Reload is passed to each reload callback to report how applying the new config went.
type Reload struct {
c *C
failed bool
restart bool
// Changed keys that only apply on a restart, from every callback
keys []string
}
// Failed marks the reload as failed, the caller logs why. Safe to call on a nil Reload, which is what the initial load
// passes.
func (r *Reload) Failed() {
if r != nil {
r.failed = true
}
}
// RestartRequired marks the reload as needing a restart, the caller logs why. Safe to call on a nil Reload.
func (r *Reload) RestartRequired() {
if r != nil {
r.restart = true
}
}
// RestartRequiredIfChanged marks the reload as needing a restart if any of keys changed, and adds them to RestartKeys.
// Use it for keys that are only read at startup. Safe to call on a nil Reload.
func (r *Reload) RestartRequiredIfChanged(keys ...string) {
if r == nil {
return
}
for _, k := range keys {
if r.c.HasChanged(k) && !slices.Contains(r.keys, k) {
r.keys = append(r.keys, k)
r.restart = true
}
}
}
-108
View File
@@ -1,108 +0,0 @@
package config
import (
"errors"
"log/slog"
"testing"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestReloadConfigString(t *testing.T) {
c := NewC(test.NewLogger())
require.NoError(t, c.LoadString("a: 1"))
fail := false
ran := 0
c.RegisterReloadCallback(func(c *C, r *Reload) {
ran++
if fail {
r.Failed()
}
})
assert.Equal(t, ReloadResult{}, c.ReloadConfigString("a: 2"))
fail = true
assert.Equal(t, ReloadResult{Failed: true}, c.ReloadConfigString("a: 3"))
assert.Equal(t, 2, ran)
// A config that fails to load runs no callbacks and returns the error
res := c.ReloadConfigString("a: [")
require.Error(t, res.Err)
assert.False(t, res.Failed)
assert.Equal(t, 2, ran)
assert.Equal(t, 3, c.GetInt("a", 0))
}
func TestReloadRestartRequiredLatches(t *testing.T) {
c := NewC(test.NewLogger())
require.NoError(t, c.LoadString("a: 1\nb: 1"))
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequiredIfChanged("a", "b") })
// Nothing that needs a restart changed
assert.Equal(t, ReloadResult{}, c.ReloadConfigString("a: 1\nb: 1\nc: 1"))
assert.Equal(t, ReloadResult{RestartRequired: true, RestartKeys: []string{"a"}}, c.ReloadConfigString("a: 2\nb: 1\nc: 1"))
// The restart sticks through a reload with no changes, reverting the key and a config that fails to load. Only the
// reload that changed the key lists it
assert.Equal(t, ReloadResult{RestartRequired: true}, c.ReloadConfigString("a: 2\nb: 1\nc: 1"))
assert.Equal(t, ReloadResult{RestartRequired: true, RestartKeys: []string{"a"}}, c.ReloadConfigString("a: 1\nb: 1\nc: 1"))
res := c.ReloadConfigString("a: [")
require.Error(t, res.Err)
assert.True(t, res.RestartRequired)
}
// A key reported by more than one callback is listed once
func TestReloadRestartKeysDeduped(t *testing.T) {
c := NewC(test.NewLogger())
require.NoError(t, c.LoadString("a: 1\nb: 1"))
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequiredIfChanged("a") })
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequiredIfChanged("a", "b") })
assert.Equal(t, []string{"a", "b"}, c.ReloadConfigString("a: 2\nb: 2").RestartKeys)
}
// A callback can require a restart without a key changing, a file the config points at may have
func TestReloadRestartRequiredWithoutAChange(t *testing.T) {
c := NewC(test.NewLogger())
require.NoError(t, c.LoadString("a: 1"))
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequired() })
assert.Equal(t, ReloadResult{RestartRequired: true}, c.ReloadConfigString("a: 1"))
}
func TestReloadResultSummary(t *testing.T) {
cases := []struct {
res ReloadResult
level slog.Level
msg string
}{
{ReloadResult{}, slog.LevelInfo, "Config reload complete"},
{ReloadResult{RestartRequired: true}, slog.LevelWarn, "Config reload was completed but requires a restart to fully apply"},
{ReloadResult{Failed: true}, slog.LevelError, "Config reload completed with errors, review the logs"},
{ReloadResult{Failed: true, RestartRequired: true}, slog.LevelError, "Config reload completed with errors and requires a restart to fully apply, review the logs"},
{ReloadResult{Err: errors.New("bad yaml")}, slog.LevelError, "Config reload failed, the new config did not load"},
{ReloadResult{Err: errors.New("bad yaml"), RestartRequired: true}, slog.LevelError, "Config reload failed, the new config did not load and a restart is still required"},
}
for _, tc := range cases {
level, msg := tc.res.Summary()
assert.Equal(t, tc.level, level, tc.msg)
assert.Equal(t, tc.msg, msg)
}
res := ReloadResult{RestartRequired: true, RestartKeys: []string{"a", "b"}}
assert.Equal(t, "Config reload was completed but requires a restart to fully apply, keys [a b]", res.String())
// String includes the error
assert.Equal(t, "Config reload failed, the new config did not load: bad yaml", ReloadResult{Err: errors.New("bad yaml")}.String())
}
// The initial load passes a nil Reload
func TestReloadNilIsSafe(t *testing.T) {
var r *Reload
r.Failed()
r.RestartRequired()
r.RestartRequiredIfChanged("a")
}
+5 -4
View File
@@ -57,8 +57,7 @@ func newConnectionManagerFromConfig(l *slog.Logger, c *config.C, hm *HostMap, p
}
cm.reload(c, true)
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("timers.connection_alive_interval", "timers.pending_deletion_interval")
c.RegisterReloadCallback(func(c *config.C) {
cm.reload(c, false)
})
@@ -175,8 +174,10 @@ func (cm *connectionManager) doTrafficCheck(localIndex uint32, p, nb, out []byte
switch decision {
case deleteTunnel:
// Local delete only, clearing the lighthouse cache if this was the last hostinfo for the vpn addr
cm.intf.closeTunnel(hostinfo)
if cm.hostMap.DeleteHostInfo(hostinfo) {
// Only clearing the lighthouse cache if this is the last hostinfo for this vpn ip in the hostmap
cm.intf.lightHouse.DeleteVpnAddrs(hostinfo.vpnAddrs)
}
case closeTunnel:
cm.intf.sendCloseTunnel(hostinfo)
-3
View File
@@ -7,7 +7,6 @@ import (
"testing"
"time"
"github.com/rcrowley/go-metrics"
"github.com/slackhq/nebula/cert"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/overlay/overlaytest"
@@ -22,8 +21,6 @@ func newTestLighthouse() *LightHouse {
l: test.NewLogger(),
addrMap: map[netip.Addr]*RemoteList{},
queryChan: make(chan netip.Addr, 10),
// Nothing drains queryChan here, so an 11th query is dropped.
queryDropped: metrics.NilCounter{},
}
lighthouses := []netip.Addr{}
staticList := map[netip.Addr]struct{}{}
-119
View File
@@ -2,8 +2,6 @@ package nebula
import (
"net/netip"
"strconv"
"sync"
"testing"
"time"
@@ -13,7 +11,6 @@ import (
ct "github.com/slackhq/nebula/cert_test"
"github.com/slackhq/nebula/handshake"
"github.com/slackhq/nebula/header"
"github.com/slackhq/nebula/overlay"
"github.com/slackhq/nebula/test"
"github.com/slackhq/nebula/udp"
"github.com/stretchr/testify/assert"
@@ -150,122 +147,6 @@ func TestSendNoMetricsCloseTunnelKeepsRebindEpoch(t *testing.T) {
assert.True(t, hostinfo.markOut(1), "a CloseTunnel send must not consume the rebind epoch")
}
// capturingConn is a udp.Conn that records every WriteTo.
type capturingConn struct {
udp.NoopConn
writes [][]byte
addrs []netip.AddrPort
}
func (c *capturingConn) WriteTo(b []byte, addr netip.AddrPort) error {
c.writes = append(c.writes, append([]byte(nil), b...))
c.addrs = append(c.addrs, addr)
return nil
}
// TestSendNoMetricsViaRelay sends through a relay from the mtu sized buffer the cached packet flush uses. Payloads up
// to overlay.MaxMTU go out intact, anything bigger is dropped rather than outgrowing the buffer, which once panicked.
func TestSendNoMetricsViaRelay(t *testing.T) {
tests := []struct {
n int
sent bool
}{
{0, true},
{1300, true},
{overlay.MaxMTU, true},
{overlay.MaxMTU + 1, false}, // too big for the relay's tag
{mtu - 47, false}, // too big for the inner tag, this panicked
{9000, false}, // a full packet at tun.mtu 9000
}
for _, tt := range tests {
t.Run(strconv.Itoa(tt.n), func(t *testing.T) {
// One tunnel to the target, carried end to end, and one to the relay that wraps it
targetInit, targetResp := runTestHandshake(t)
relayInit, relayResp := runTestHandshake(t)
ci, err := newConnectionStateFromResult(targetInit)
require.NoError(t, err)
relayCI, err := newConnectionStateFromResult(relayInit)
require.NoError(t, err)
targetAddr := netip.MustParseAddr("10.0.0.2")
relayAddr := netip.MustParseAddr("10.0.0.3")
relayRemote := netip.MustParseAddrPort("192.0.2.1:4242")
relay := &Relay{Type: TerminalType, State: Established, LocalIndex: 5, RemoteIndex: 6, PeerAddr: targetAddr}
relayHI := &HostInfo{
vpnAddrs: []netip.Addr{relayAddr},
ConnectionState: relayCI,
relayState: RelayState{
relayForByAddr: map[netip.Addr]*Relay{targetAddr: relay},
relayForByIdx: map[uint32]*Relay{relay.LocalIndex: relay},
},
}
relayHI.remote.Store(&relayRemote)
// No remote of its own, so the send has to go via the relay
hostinfo := &HostInfo{
vpnAddrs: []netip.Addr{targetAddr},
ConnectionState: ci,
remoteIndexId: 7,
relayState: RelayState{
relays: []netip.Addr{relayAddr},
relayForByAddr: map[netip.Addr]*Relay{},
relayForByIdx: map[uint32]*Relay{},
},
}
l := test.NewLogger()
hm := newHostMap(l)
hm.Hosts[relayAddr] = relayHI
conn := &capturingConn{}
f := &Interface{
l: l,
hostMap: hm,
messageMetrics: &MessageMetrics{txExhausted: metrics.NewCounter()},
writers: []udp.Conn{conn},
}
f.connectionManager = &connectionManager{intf: f, relayUsed: map[uint32]struct{}{}, relayUsedLock: &sync.RWMutex{}}
payload := make([]byte, tt.n)
for i := range payload {
payload[i] = byte(i)
}
counter := ci.messageCounter.Load()
f.sendNoMetrics(header.Message, 0, ci, hostinfo, netip.AddrPort{}, payload, make([]byte, 12), make([]byte, mtu), 0)
if !tt.sent {
assert.Empty(t, conn.writes)
assert.Equal(t, counter, ci.messageCounter.Load(), "a dropped packet must not spend a counter")
return
}
require.Len(t, conn.writes, 1)
assert.Equal(t, relayRemote, conn.addrs[0])
pkt := conn.writes[0]
// The relay authenticates the whole packet under its own header
outer := &header.H{}
require.NoError(t, outer.Parse(pkt))
assert.Equal(t, header.MessageRelay, outer.Subtype)
assert.Equal(t, relay.RemoteIndex, outer.RemoteIndex)
relayPeer, err := newConnectionStateFromResult(relayResp)
require.NoError(t, err)
require.NoError(t, relayPeer.VerifyRelay(l, outer.MessageCounter, pkt, make([]byte, 12)))
// Inside it, the target decrypts the end to end packet back to the payload
inner := pkt[header.Len : len(pkt)-relayPeer.dKey.Overhead()]
h := &header.H{}
require.NoError(t, h.Parse(inner))
assert.Equal(t, header.Message, h.Type)
assert.Equal(t, hostinfo.remoteIndexId, h.RemoteIndex)
targetPeer, err := newConnectionStateFromResult(targetResp)
require.NoError(t, err)
got, err := targetPeer.Decrypt(l, h.MessageCounter, inner, make([]byte, 12))
require.NoError(t, err)
assert.Equal(t, payload, got)
})
}
}
func TestNewConnectionStateFromResult(t *testing.T) {
initR, respR := runTestHandshake(t)
-9
View File
@@ -11,7 +11,6 @@ import (
"syscall"
"github.com/slackhq/nebula/cert"
"github.com/slackhq/nebula/commands"
"github.com/slackhq/nebula/header"
"github.com/slackhq/nebula/overlay"
)
@@ -48,7 +47,6 @@ type Control struct {
f *Interface
l *slog.Logger
commands *commands.Registry
ctx context.Context
cancel context.CancelFunc
sshStart func()
@@ -374,13 +372,6 @@ func (c *Control) CloseAllTunnels(excludeLighthouses bool) (closed int) {
return
}
// Commands returns the registry the daemon's surfaces serve from. It is the live
// registry, not a copy: a command registered on it is served to every ssh session that
// starts afterwards. Clone it to run commands without that reach.
func (c *Control) Commands() *commands.Registry {
return c.commands
}
func (c *Control) Device() overlay.Device {
return c.f.inside
}
+1 -1
View File
@@ -151,7 +151,7 @@ func (c *fakeConn) WriteTo(_ []byte, _ netip.AddrPort) error { return nil }
func (c *fakeConn) WriteBatch(bufs [][]byte, _ []netip.AddrPort) (int, error) {
return len(bufs), nil
}
func (c *fakeConn) ReloadConfig(_ *config.C, _ *config.Reload) {}
func (c *fakeConn) ReloadConfig(_ *config.C) {}
func (c *fakeConn) SupportsMultipleReaders() bool { return true }
func (c *fakeConn) Close() error { c.closed = true; return nil }
+23 -51
View File
@@ -38,8 +38,8 @@ type dnsServer struct {
serverMu sync.Mutex
server *dns.Server
// started is closed once `server` is serving (or after serve returns
// without ever starting). Stop waits on it before
// started is closed once `server` has finished binding (or after
// ListenAndServe returns on a bind failure). Stop waits on it before
// calling Shutdown to avoid the miekg/dns "server not started" race
// where a Shutdown that arrives before bind completes is silently
// ignored, leaving the listener running forever.
@@ -69,10 +69,9 @@ func newDnsServerFromConfig(ctx context.Context, l *slog.Logger, pki *PKI, hostM
ds.mux = dns.NewServeMux()
ds.mux.HandleFunc(".", ds.handleDnsRequest)
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
c.RegisterReloadCallback(func(c *config.C) {
if err := ds.reload(c, false); err != nil {
ds.l.Error("Failed to reload DNS responder from config", "error", err)
r.Failed()
}
})
@@ -84,7 +83,7 @@ func newDnsServerFromConfig(ctx context.Context, l *slog.Logger, pki *PKI, hostM
}
// reload applies the latest config and reconciles the running state with it:
// - enabled toggled on -> bind, then serve in the background
// - enabled toggled on -> spawn a runner
// - enabled toggled off -> stop the runner
// - listen address changed (while running) -> restart on the new address
// - everything else -> no-op
@@ -121,20 +120,13 @@ func (d *dnsServer) reload(c *config.C, initial bool) error {
return nil
}
if running && !sameAddr {
// Stop clears the slot before shutting down, otherwise the listen below can find the dying server and refuse
d.Stop()
running = false
}
if !running {
// Bind here rather than in the background, so a reload that can't listen says so
server, started, err := d.listen()
if err != nil {
return err
}
if server != nil {
go d.serve(server, started)
}
// Was disabled (or never started); bring it up now.
go d.Start()
} else if !sameAddr {
// Stop clears the slot before shutting down, otherwise the Start below can find the dying server and refuse
d.Stop()
go d.Start()
}
// Refresh the self entry every enabled reload so cert renewals that change our name or VPN addresses are picked up.
@@ -163,50 +155,30 @@ func (d *dnsServer) shutdownServer(srv *dns.Server, started chan struct{}, reaso
// Must be invoked after the tun device is active so that lighthouse.dns.host
// may bind to a nebula IP.
func (d *dnsServer) Start() {
server, started, err := d.listen()
if err != nil {
d.l.Warn("Failed to run the DNS responder", "error", err)
return
}
if server != nil {
d.serve(server, started)
}
}
// listen binds the responder and claims the server slot for serve. It returns a nil server, and no error, when DNS is
// disabled or a server is already running.
func (d *dnsServer) listen() (*dns.Server, chan struct{}, error) {
if !d.enabled.Load() {
return nil, nil, nil
return
}
started := make(chan struct{})
d.serverMu.Lock()
defer d.serverMu.Unlock()
// Re-check enabled under the lock, a disable that raced our check above snapshots the slot under it too.
// A reload and Control.Start can both get here, the loser would orphan the live listener past Stop
// Two reloads in quick succession can both spawn a Start, the loser would orphan the live listener past Stop
if d.ctx.Err() != nil || d.server != nil || !d.enabled.Load() {
return nil, nil, nil
}
pc, err := net.ListenPacket("udp", d.addr)
if err != nil {
return nil, nil, err
d.serverMu.Unlock()
return
}
addr := d.addr
server := &dns.Server{
Addr: d.addr,
PacketConn: pc,
Addr: addr,
Net: "udp",
Handler: d.mux,
NotifyStartedFunc: func() { close(started) },
}
d.server = server
d.started = started
d.l.Info("Starting DNS responder", "dnsListener", pc.LocalAddr())
return server, started, nil
}
d.serverMu.Unlock()
// serve answers queries on a server from listen until Stop or the context ends it.
func (d *dnsServer) serve(server *dns.Server, started chan struct{}) {
// Per-invocation ctx watcher. Exits when serve does, so we don't leak a
// Per-invocation ctx watcher. Exits when Start does, so we don't leak a
// watcher per reload-driven restart.
done := make(chan struct{})
go func() {
@@ -217,16 +189,16 @@ func (d *dnsServer) serve(server *dns.Server, started chan struct{}) {
}
}()
err := server.ActivateAndServe()
d.l.Info("Starting DNS responder", "dnsListener", addr)
err := server.ListenAndServe()
close(done)
// If serving failed before it started NotifyStartedFunc never fires, so close started here to release any Stop
// caller waiting on it. ActivateAndServe doesn't close the socket on that path either
// If the listener never bound (bind error) NotifyStartedFunc never fires,
// so close started here to release any Stop caller waiting on it.
select {
case <-started:
default:
close(started)
_ = server.PacketConn.Close()
}
// Release our slot, unless a reload already replaced us, so a dead listener can't block a future Start
-19
View File
@@ -629,22 +629,3 @@ func TestDnsServer_Start_refusesWhenDisabledUnderLock(t *testing.T) {
require.NoError(t, err, "an orphaned listener is still holding the port")
_ = pc.Close()
}
// A reload that can't bind says so, rather than finding out in the background
func TestDnsServer_reload_busyPortFails(t *testing.T) {
busy, err := net.ListenPacket("udp", "127.0.0.1:0")
require.NoError(t, err)
t.Cleanup(func() { _ = busy.Close() })
_, port, err := net.SplitHostPort(busy.LocalAddr().String())
require.NoError(t, err)
ds, c := newTestDnsServer(t)
setDnsConfig(c, "127.0.0.1", port, false, true)
require.NoError(t, ds.reload(c, true))
setDnsConfig(c, "127.0.0.1", port, true, true)
require.Error(t, ds.reload(c, false))
ds.serverMu.Lock()
assert.Nil(t, ds.server, "a failed bind kept the slot")
ds.serverMu.Unlock()
}
-164
View File
@@ -1,164 +0,0 @@
//go:build e2e_testing
package e2e
import (
"bytes"
"fmt"
"path/filepath"
"regexp"
"strings"
"testing"
"time"
"github.com/slackhq/nebula/cert"
"github.com/slackhq/nebula/cert_test"
"github.com/slackhq/nebula/commands"
"github.com/slackhq/nebula/sshd"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/require"
)
// volatile lists everything in command output that legitimately differs between runs.
// Each run mints fresh certificates and indexes, so these are replaced with a marker
// before comparison. Keep the list short: anything added here is something the golden
// stops guarding.
var volatile = []struct {
re *regexp.Regexp
with string
}{
{regexp.MustCompile(`[0-9a-f]{40,}`), "<hex>"}, // fingerprints, keys, signatures
{regexp.MustCompile(`\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(?:\.\d+)?(?:Z|[+-]\d{2}:\d{2})`), "<time>"}, // RFC 3339
{regexp.MustCompile(`\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}(?:\.\d+)? [+-]\d{4} \w+`), "<time>"}, // time.Time.String()
{regexp.MustCompile(`(?s)(-----BEGIN [A-Z ]+-----\n).*?(\n-----END [A-Z ]+-----)`), "${1}<pem>${2}"}, // print-cert -raw
{regexp.MustCompile(`(-----BEGIN [A-Z ]+-----\\n).*?(\\n-----END [A-Z ]+-----)`), "${1}<pem>${2}"}, // the same, inside a JSON string
{regexp.MustCompile(`"(localIndex|remoteIndex|messageCounter)":\d+`), `"$1":<n>`},
{regexp.MustCompile(`(?m)^(\s*"?(?:LocalIndex|RemoteIndex|localIndex|remoteIndex|messageCounter)"?:?\s*)\d+`), "${1}<n>"}, // and the -pretty form
}
func normalise(s string) string {
for _, v := range volatile {
s = v.re.ReplaceAllString(s, v.with)
}
return s
}
// outputCase is one command line to run through the ssh dispatch path.
type outputCase struct {
name string
args []string
}
// TestCommandOutput pins the bytes every command produces, in every format, through the
// ssh dispatch path. It is the safety net for moving rendering out of the commands: a
// change here is a change someone at an ssh prompt would see. Regenerate with:
//
// go test -tags e2e_testing ./e2e -run TestCommandOutput -update
func TestCommandOutput(t *testing.T) {
ca, _, caKey, _ := cert_test.NewTestCaCert(
cert.Version1, cert.Curve_CURVE25519,
time.Now(), time.Now().Add(10*time.Minute),
nil, nil, []string{},
)
control, _, _, _ := newSimpleServer(cert.Version1, ca, caKey, "output-golden", "10.222.0.1/24", nil)
control.Start()
t.Cleanup(func() { control.Stop() })
// As an ssh session does: a clone of the daemon's registry with logout added, which
// help on the clone lists and describes. There is no session to end here.
reg := control.Commands().Clone()
reg.Register(sshd.LogoutCommand(func() {}))
// run dispatches as the ssh exec path does and returns the output and the error, which
// over ssh is exit status 1.
run := func(args ...string) (string, error) {
buf := &bytes.Buffer{}
err := reg.DispatchArgs(args, commands.NewStringWriter(buf))
return buf.String(), err
}
// Seed a pending tunnel so the listing and per-address commands have something to show.
seed, err := run("create-tunnel", "10.222.0.9")
require.NoError(t, err)
require.Equal(t, "Created\n", seed, "seeding a tunnel should succeed before anything else is recorded")
cases := []outputCase{
{"version", nil},
{"device-info", nil},
{"list-hostmap", nil},
{"list-hostmap", []string{"-by-index"}},
{"list-pending-hostmap", nil},
{"list-pending-hostmap", []string{"-by-index"}},
{"list-lighthouse-addrmap", nil},
{"print-cert", nil},
{"print-cert", []string{"-raw"}},
{"print-cert", []string{"10.222.0.9"}},
{"print-cert", []string{"10.222.0.250"}},
{"print-cert", []string{"not-an-address"}},
{"print-tunnel", nil},
{"print-tunnel", []string{"10.222.0.9"}},
{"print-tunnel", []string{"10.222.0.250"}},
{"print-relays", nil},
{"query-lighthouse", nil},
{"query-lighthouse", []string{"10.222.0.9"}},
{"query-lighthouse", []string{"not-an-address"}},
// The test logger cannot change level or format, so these cases record the
// refusal each command prints on it, not a successful change.
{"log-level", nil},
{"log-level", []string{"debug"}},
{"log-level", []string{"bogus"}},
{"log-level", []string{"info"}},
{"log-format", nil},
{"log-format", []string{"json"}},
{"log-format", []string{"text"}},
{"change-remote", nil},
{"change-remote", []string{"10.222.0.9"}},
{"change-remote", []string{"-address", "10.94.0.10:4242", "10.222.0.9"}},
{"change-remote", []string{"-address", "10.94.0.10:4242", "10.222.0.250"}},
{"create-tunnel", nil},
{"create-tunnel", []string{"10.222.0.9"}},
// A fresh address, so this exercises the handshake start with a remote attached
// rather than the "already handshaking" path above.
{"create-tunnel", []string{"-address", "10.94.0.10:4242", "10.222.0.10"}},
{"create-tunnel", []string{"not-an-address"}},
{"close-tunnel", nil},
{"close-tunnel", []string{"10.222.0.250"}},
{"close-tunnel", []string{"not-an-address"}},
{"help", nil},
{"help", []string{"print-cert"}},
{"help", []string{"logout"}},
{"logout", []string{"-h"}},
{"not-a-command", []string{"10.222.0.9"}},
// reload is last so that whatever a reload does to the daemon cannot leak into an
// earlier case. In this harness it fails: the config was loaded from a string and
// has no path to re-read, which is what the recorded result says.
{"reload", nil},
}
got := &strings.Builder{}
for _, c := range cases {
for _, fmtFlags := range [][]string{nil, {"-json"}, {"-pretty"}} {
args := append([]string{c.name}, fmtFlags...)
args = append(args, c.args...)
fmt.Fprintf(got, "$ %s\n", strings.Join(args, " "))
out, err := run(args...)
out = normalise(out)
got.WriteString(out)
// Output that does not end in a newline is recorded as such, the way diff marks
// it, so the golden sees that byte too and the next prompt still starts a line.
if out != "" && !strings.HasSuffix(out, "\n") {
got.WriteString("\\ No newline at end of output\n")
}
// A failed command is recorded as the exit status an ssh caller sees, so the
// golden pins which outcomes count as failures.
if err != nil {
got.WriteString("exit status 1\n")
}
got.WriteString("\n")
}
}
test.Golden(t, filepath.Join("testdata", "commands_output.golden"), got.String())
}
+1 -1
View File
@@ -1513,7 +1513,7 @@ func TestLighthouseUpdateOnReload(t *testing.T) {
// Reload the config. The lighthouse.hosts change triggers TriggerUpdate,
// which wakes the update worker. It calls SendUpdate, initiating a
// handshake to the new lighthouse and caching the HostUpdateNotification.
require.NoError(t, myConfig.ReloadConfigString(string(newCfg)).Err)
require.NoError(t, myConfig.ReloadConfigString(string(newCfg)))
// Route until the lighthouse receives the HostUpdateNotification.
// This covers: handshake stage 1, stage 2, then the cached update.
-720
View File
@@ -1,720 +0,0 @@
$ version
e2e-test
$ version -json
e2e-test
$ version -pretty
e2e-test
$ device-info
name= cidr=[10.222.0.1/24]
$ device-info -json
{"name":"","cidr":["10.222.0.1/24"]}
$ device-info -pretty
{
"name": "",
"cidr": [
"10.222.0.1/24"
]
}
$ list-hostmap
$ list-hostmap -json
[]
$ list-hostmap -pretty
[]
$ list-hostmap -by-index
$ list-hostmap -json -by-index
[]
$ list-hostmap -pretty -by-index
[]
$ list-pending-hostmap
[10.222.0.9]: []
$ list-pending-hostmap -json
[{"vpnAddrs":["10.222.0.9"],"localIndex":<n>,"remoteIndex":<n>,"remoteAddrs":[],"cert":null,"messageCounter":<n>,"currentRemote":"","currentRelaysToMe":[],"currentRelaysThroughMe":[]}]
$ list-pending-hostmap -pretty
[
{
"vpnAddrs": [
"10.222.0.9"
],
"localIndex": <n>,
"remoteIndex": <n>,
"remoteAddrs": [],
"cert": null,
"messageCounter": <n>,
"currentRemote": "",
"currentRelaysToMe": [],
"currentRelaysThroughMe": []
}
]
$ list-pending-hostmap -by-index
$ list-pending-hostmap -json -by-index
[]
$ list-pending-hostmap -pretty -by-index
[]
$ list-lighthouse-addrmap
10.222.0.9: {}
$ list-lighthouse-addrmap -json
[{"vpnAddr":"10.222.0.9","addrs":{}}]
$ list-lighthouse-addrmap -pretty
[
{
"vpnAddr": "10.222.0.9",
"addrs": {}
}
]
$ print-cert
{
"details": {
"curve": "CURVE25519",
"groups": [],
"isCa": false,
"issuer": "<hex>",
"name": "output-golden",
"networks": [
"10.222.0.1/24"
],
"notAfter": "<time>",
"notBefore": "<time>",
"publicKey": "<hex>",
"unsafeNetworks": []
},
"fingerprint": "<hex>",
"signature": "<hex>",
"version": 1
}
$ print-cert -json
{"details":{"curve":"CURVE25519","groups":[],"isCa":false,"issuer":"<hex>","name":"output-golden","networks":["10.222.0.1/24"],"notAfter":"<time>","notBefore":"<time>","publicKey":"<hex>","unsafeNetworks":[]},"fingerprint":"<hex>","signature":"<hex>","version":1}\ No newline at end of output
$ print-cert -pretty
{
"details": {
"curve": "CURVE25519",
"groups": [],
"isCa": false,
"issuer": "<hex>",
"name": "output-golden",
"networks": [
"10.222.0.1/24"
],
"notAfter": "<time>",
"notBefore": "<time>",
"publicKey": "<hex>",
"unsafeNetworks": []
},
"fingerprint": "<hex>",
"signature": "<hex>",
"version": 1
}\ No newline at end of output
$ print-cert -raw
-----BEGIN NEBULA CERTIFICATE-----
<pem>
-----END NEBULA CERTIFICATE-----
$ print-cert -json -raw
{"details":{"curve":"CURVE25519","groups":[],"isCa":false,"issuer":"<hex>","name":"output-golden","networks":["10.222.0.1/24"],"notAfter":"<time>","notBefore":"<time>","publicKey":"<hex>","unsafeNetworks":[]},"fingerprint":"<hex>","signature":"<hex>","version":1}\ No newline at end of output
$ print-cert -pretty -raw
{
"details": {
"curve": "CURVE25519",
"groups": [],
"isCa": false,
"issuer": "<hex>",
"name": "output-golden",
"networks": [
"10.222.0.1/24"
],
"notAfter": "<time>",
"notBefore": "<time>",
"publicKey": "<hex>",
"unsafeNetworks": []
},
"fingerprint": "<hex>",
"signature": "<hex>",
"version": 1
}\ No newline at end of output
$ print-cert 10.222.0.9
Could not find tunnel for vpn addr: 10.222.0.9
exit status 1
$ print-cert -json 10.222.0.9
Could not find tunnel for vpn addr: 10.222.0.9
exit status 1
$ print-cert -pretty 10.222.0.9
Could not find tunnel for vpn addr: 10.222.0.9
exit status 1
$ print-cert 10.222.0.250
Could not find tunnel for vpn addr: 10.222.0.250
exit status 1
$ print-cert -json 10.222.0.250
Could not find tunnel for vpn addr: 10.222.0.250
exit status 1
$ print-cert -pretty 10.222.0.250
Could not find tunnel for vpn addr: 10.222.0.250
exit status 1
$ print-cert not-an-address
The provided vpn addr could not be parsed: not-an-address
exit status 1
$ print-cert -json not-an-address
The provided vpn addr could not be parsed: not-an-address
exit status 1
$ print-cert -pretty not-an-address
The provided vpn addr could not be parsed: not-an-address
exit status 1
$ print-tunnel
No vpn address was provided
exit status 1
$ print-tunnel -json
flag provided but not defined: -json
Usage:
-pretty
pretty prints json
exit status 1
$ print-tunnel -pretty
No vpn address was provided
exit status 1
$ print-tunnel 10.222.0.9
Could not find tunnel for vpn addr: 10.222.0.9
exit status 1
$ print-tunnel -json 10.222.0.9
flag provided but not defined: -json
Usage:
-pretty
pretty prints json
exit status 1
$ print-tunnel -pretty 10.222.0.9
Could not find tunnel for vpn addr: 10.222.0.9
exit status 1
$ print-tunnel 10.222.0.250
Could not find tunnel for vpn addr: 10.222.0.250
exit status 1
$ print-tunnel -json 10.222.0.250
flag provided but not defined: -json
Usage:
-pretty
pretty prints json
exit status 1
$ print-tunnel -pretty 10.222.0.250
Could not find tunnel for vpn addr: 10.222.0.250
exit status 1
$ print-relays
{"Relays":null}
$ print-relays -json
flag provided but not defined: -json
Usage:
-pretty
pretty prints json
exit status 1
$ print-relays -pretty
{
"Relays": null
}
$ query-lighthouse
No vpn address was provided
exit status 1
$ query-lighthouse -json
The provided vpn address could not be parsed: -json
exit status 1
$ query-lighthouse -pretty
The provided vpn address could not be parsed: -pretty
exit status 1
$ query-lighthouse 10.222.0.9
{}
$ query-lighthouse -json 10.222.0.9
The provided vpn address could not be parsed: -json
exit status 1
$ query-lighthouse -pretty 10.222.0.9
The provided vpn address could not be parsed: -pretty
exit status 1
$ query-lighthouse not-an-address
The provided vpn address could not be parsed: not-an-address
exit status 1
$ query-lighthouse -json not-an-address
The provided vpn address could not be parsed: -json
exit status 1
$ query-lighthouse -pretty not-an-address
The provided vpn address could not be parsed: -pretty
exit status 1
$ log-level
Log level is not reconfigurable on this logger
exit status 1
$ log-level -json
Log level is not reconfigurable on this logger
exit status 1
$ log-level -pretty
Log level is not reconfigurable on this logger
exit status 1
$ log-level debug
Log level is not reconfigurable on this logger
exit status 1
$ log-level -json debug
Log level is not reconfigurable on this logger
exit status 1
$ log-level -pretty debug
Log level is not reconfigurable on this logger
exit status 1
$ log-level bogus
Log level is not reconfigurable on this logger
exit status 1
$ log-level -json bogus
Log level is not reconfigurable on this logger
exit status 1
$ log-level -pretty bogus
Log level is not reconfigurable on this logger
exit status 1
$ log-level info
Log level is not reconfigurable on this logger
exit status 1
$ log-level -json info
Log level is not reconfigurable on this logger
exit status 1
$ log-level -pretty info
Log level is not reconfigurable on this logger
exit status 1
$ log-format
Log format is not reconfigurable on this logger
exit status 1
$ log-format -json
Log format is not reconfigurable on this logger
exit status 1
$ log-format -pretty
Log format is not reconfigurable on this logger
exit status 1
$ log-format json
Log format is not reconfigurable on this logger
exit status 1
$ log-format -json json
Log format is not reconfigurable on this logger
exit status 1
$ log-format -pretty json
Log format is not reconfigurable on this logger
exit status 1
$ log-format text
Log format is not reconfigurable on this logger
exit status 1
$ log-format -json text
Log format is not reconfigurable on this logger
exit status 1
$ log-format -pretty text
Log format is not reconfigurable on this logger
exit status 1
$ change-remote
No vpn address was provided
exit status 1
$ change-remote -json
flag provided but not defined: -json
Usage:
-address string
The new remote address, ip:port
exit status 1
$ change-remote -pretty
flag provided but not defined: -pretty
Usage:
-address string
The new remote address, ip:port
exit status 1
$ change-remote 10.222.0.9
No address was provided
exit status 1
$ change-remote -json 10.222.0.9
flag provided but not defined: -json
Usage:
-address string
The new remote address, ip:port
exit status 1
$ change-remote -pretty 10.222.0.9
flag provided but not defined: -pretty
Usage:
-address string
The new remote address, ip:port
exit status 1
$ change-remote -address 10.94.0.10:4242 10.222.0.9
Could not find tunnel for vpn address: 10.222.0.9
exit status 1
$ change-remote -json -address 10.94.0.10:4242 10.222.0.9
flag provided but not defined: -json
Usage:
-address string
The new remote address, ip:port
exit status 1
$ change-remote -pretty -address 10.94.0.10:4242 10.222.0.9
flag provided but not defined: -pretty
Usage:
-address string
The new remote address, ip:port
exit status 1
$ change-remote -address 10.94.0.10:4242 10.222.0.250
Could not find tunnel for vpn address: 10.222.0.250
exit status 1
$ change-remote -json -address 10.94.0.10:4242 10.222.0.250
flag provided but not defined: -json
Usage:
-address string
The new remote address, ip:port
exit status 1
$ change-remote -pretty -address 10.94.0.10:4242 10.222.0.250
flag provided but not defined: -pretty
Usage:
-address string
The new remote address, ip:port
exit status 1
$ create-tunnel
No vpn address was provided
exit status 1
$ create-tunnel -json
flag provided but not defined: -json
Usage:
-address string
Optionally provide a real remote address, ip:port
exit status 1
$ create-tunnel -pretty
flag provided but not defined: -pretty
Usage:
-address string
Optionally provide a real remote address, ip:port
exit status 1
$ create-tunnel 10.222.0.9
Tunnel already handshaking
exit status 1
$ create-tunnel -json 10.222.0.9
flag provided but not defined: -json
Usage:
-address string
Optionally provide a real remote address, ip:port
exit status 1
$ create-tunnel -pretty 10.222.0.9
flag provided but not defined: -pretty
Usage:
-address string
Optionally provide a real remote address, ip:port
exit status 1
$ create-tunnel -address 10.94.0.10:4242 10.222.0.10
Created
$ create-tunnel -json -address 10.94.0.10:4242 10.222.0.10
flag provided but not defined: -json
Usage:
-address string
Optionally provide a real remote address, ip:port
exit status 1
$ create-tunnel -pretty -address 10.94.0.10:4242 10.222.0.10
flag provided but not defined: -pretty
Usage:
-address string
Optionally provide a real remote address, ip:port
exit status 1
$ create-tunnel not-an-address
The provided vpn address could not be parsed: not-an-address
exit status 1
$ create-tunnel -json not-an-address
flag provided but not defined: -json
Usage:
-address string
Optionally provide a real remote address, ip:port
exit status 1
$ create-tunnel -pretty not-an-address
flag provided but not defined: -pretty
Usage:
-address string
Optionally provide a real remote address, ip:port
exit status 1
$ close-tunnel
No vpn address was provided
exit status 1
$ close-tunnel -json
flag provided but not defined: -json
Usage:
-local-only
Disables notifying the remote that the tunnel is shutting down
exit status 1
$ close-tunnel -pretty
flag provided but not defined: -pretty
Usage:
-local-only
Disables notifying the remote that the tunnel is shutting down
exit status 1
$ close-tunnel 10.222.0.250
Could not find tunnel for vpn address: 10.222.0.250
exit status 1
$ close-tunnel -json 10.222.0.250
flag provided but not defined: -json
Usage:
-local-only
Disables notifying the remote that the tunnel is shutting down
exit status 1
$ close-tunnel -pretty 10.222.0.250
flag provided but not defined: -pretty
Usage:
-local-only
Disables notifying the remote that the tunnel is shutting down
exit status 1
$ close-tunnel not-an-address
The provided vpn address could not be parsed: not-an-address
exit status 1
$ close-tunnel -json not-an-address
flag provided but not defined: -json
Usage:
-local-only
Disables notifying the remote that the tunnel is shutting down
exit status 1
$ close-tunnel -pretty not-an-address
flag provided but not defined: -pretty
Usage:
-local-only
Disables notifying the remote that the tunnel is shutting down
exit status 1
$ help
Available commands:
change-remote - Changes the remote address used in the tunnel for the provided vpn addr
close-tunnel - Closes a tunnel for the provided vpn addr
create-tunnel - Creates a tunnel for the provided vpn address
device-info - Prints information about the network device.
help - prints available commands or help <command> for specific usage info
list-hostmap - List all known previously connected hosts
list-lighthouse-addrmap - List all lighthouse map entries
list-pending-hostmap - List all handshaking hosts
log-format - Gets or sets the current log format
log-level - Gets or sets the current log level
logout - Ends the current session
print-cert - Prints the current certificate being used or the certificate for the provided vpn addr
print-relays - Prints json details about all relay info
print-tunnel - Prints json details about a tunnel for the provided vpn addr
query-lighthouse - Query the lighthouses for the provided vpn address
reload - Reloads configuration from disk, same as sending HUP to the process
version - Prints the currently running version of nebula
$ help -json
Command not available -json
exit status 1
$ help -pretty
Command not available -pretty
exit status 1
$ help print-cert
print-cert - Prints the current certificate being used or the certificate for the provided vpn addr
-json
outputs as json
-pretty
pretty prints json, assumes -json
-raw
raw prints the PEM encoded certificate, not compatible with -json or -pretty
$ help -json print-cert
Command not available -json
exit status 1
$ help -pretty print-cert
Command not available -pretty
exit status 1
$ help logout
logout - Ends the current session
$ help -json logout
Command not available -json
exit status 1
$ help -pretty logout
Command not available -pretty
exit status 1
$ logout -h
logout - Ends the current session
$ logout -json -h
logout - Ends the current session
$ logout -pretty -h
logout - Ends the current session
$ not-a-command 10.222.0.9
did not understand: not-a-command
Available commands:
change-remote - Changes the remote address used in the tunnel for the provided vpn addr
close-tunnel - Closes a tunnel for the provided vpn addr
create-tunnel - Creates a tunnel for the provided vpn address
device-info - Prints information about the network device.
help - prints available commands or help <command> for specific usage info
list-hostmap - List all known previously connected hosts
list-lighthouse-addrmap - List all lighthouse map entries
list-pending-hostmap - List all handshaking hosts
log-format - Gets or sets the current log format
log-level - Gets or sets the current log level
logout - Ends the current session
print-cert - Prints the current certificate being used or the certificate for the provided vpn addr
print-relays - Prints json details about all relay info
print-tunnel - Prints json details about a tunnel for the provided vpn addr
query-lighthouse - Query the lighthouses for the provided vpn address
reload - Reloads configuration from disk, same as sending HUP to the process
version - Prints the currently running version of nebula
exit status 1
$ not-a-command -json 10.222.0.9
did not understand: not-a-command
Available commands:
change-remote - Changes the remote address used in the tunnel for the provided vpn addr
close-tunnel - Closes a tunnel for the provided vpn addr
create-tunnel - Creates a tunnel for the provided vpn address
device-info - Prints information about the network device.
help - prints available commands or help <command> for specific usage info
list-hostmap - List all known previously connected hosts
list-lighthouse-addrmap - List all lighthouse map entries
list-pending-hostmap - List all handshaking hosts
log-format - Gets or sets the current log format
log-level - Gets or sets the current log level
logout - Ends the current session
print-cert - Prints the current certificate being used or the certificate for the provided vpn addr
print-relays - Prints json details about all relay info
print-tunnel - Prints json details about a tunnel for the provided vpn addr
query-lighthouse - Query the lighthouses for the provided vpn address
reload - Reloads configuration from disk, same as sending HUP to the process
version - Prints the currently running version of nebula
exit status 1
$ not-a-command -pretty 10.222.0.9
did not understand: not-a-command
Available commands:
change-remote - Changes the remote address used in the tunnel for the provided vpn addr
close-tunnel - Closes a tunnel for the provided vpn addr
create-tunnel - Creates a tunnel for the provided vpn address
device-info - Prints information about the network device.
help - prints available commands or help <command> for specific usage info
list-hostmap - List all known previously connected hosts
list-lighthouse-addrmap - List all lighthouse map entries
list-pending-hostmap - List all handshaking hosts
log-format - Gets or sets the current log format
log-level - Gets or sets the current log level
logout - Ends the current session
print-cert - Prints the current certificate being used or the certificate for the provided vpn addr
print-relays - Prints json details about all relay info
print-tunnel - Prints json details about a tunnel for the provided vpn addr
query-lighthouse - Query the lighthouses for the provided vpn address
reload - Reloads configuration from disk, same as sending HUP to the process
version - Prints the currently running version of nebula
exit status 1
$ reload
Reloading config
Config reload failed, the new config did not load: no config files found at
exit status 1
$ reload -json
Reloading config
Config reload failed, the new config did not load: no config files found at
exit status 1
$ reload -pretty
Reloading config
Config reload failed, the new config did not load: no config files found at
exit status 1
+2 -2
View File
@@ -129,7 +129,7 @@ func TestCertUpgrade(t *testing.T) {
}
r.Logf("reload new v2-only config")
err = myC.ReloadConfigString(string(cb)).Err
err = myC.ReloadConfigString(string(cb))
assert.NoError(t, err)
r.Log("yay, spin until their sees it")
waitStart := time.Now()
@@ -222,7 +222,7 @@ func TestCertDowngrade(t *testing.T) {
}
r.Logf("reload new v1-only config")
err = myC.ReloadConfigString(string(cb)).Err
err = myC.ReloadConfigString(string(cb))
assert.NoError(t, err)
r.Log("yay, spin until their sees it")
waitStart := time.Now()
+22 -26
View File
@@ -8,7 +8,6 @@ pki:
cert: /etc/nebula/host.crt
key: /etc/nebula/host.key
# blocklist is a list of certificate fingerprints that we will refuse to talk to
# Entries are the hex fingerprints shown by `nebula-cert print`, an invalid entry fails startup and reload.
#blocklist:
# - c99d4e650533b92061b09918e838a5a0a6aaee21eed1d12fd937682865936c72
# disconnect_invalid is a toggle to force a client to be disconnected if the certificate is expired or invalid.
@@ -44,7 +43,7 @@ static_host_map:
lighthouse:
# am_lighthouse is used to enable lighthouse functionality for a node. This should ONLY be true on nodes
# you have configured to be lighthouses in your network. Not reloadable.
# you have configured to be lighthouses in your network
am_lighthouse: false
# serve_dns optionally starts a dns listener that responds to various queries and can even be
# delegated to for resolution
@@ -127,9 +126,8 @@ lighthouse:
# Port Nebula will be listening on. The default here is 4242. For a lighthouse node, the port should be defined,
# however using port 0 will dynamically assign a port and is recommended for roaming nodes.
listen:
# To listen on only ipv4, use "0.0.0.0". Not reloadable.
# To listen on only ipv4, use "0.0.0.0"
host: "::"
# Not reloadable.
port: 4242
# Sets the max number of packets to pull from the kernel for each syscall (under systems that support recvmmsg)
# default is 64, does not support reload
@@ -137,13 +135,12 @@ listen:
# superpacket, so the receive scratch is batch * 64KiB per listening socket (~4MiB per routine at the
# default of 64). Lower this to trade peak per-syscall throughput for memory on constrained hosts.
#batch: 64
# Linux only. Reloadable, but removing a value leaves the socket at the old size until Nebula restarts.
# Configure socket buffers for the udp side (outside), leave unset to use the system defaults. Values will be doubled by the kernel
# Default is net.core.rmem_default and net.core.wmem_default (/proc/sys/net/core/rmem_default and /proc/sys/net/core/rmem_default)
# Maximum is limited by memory in the system, SO_RCVBUFFORCE and SO_SNDBUFFORCE is used to avoid having to raise the system wide
# max, net.core.rmem_max and net.core.wmem_max
read_buffer: 3412512
write_buffer: 3412512
#read_buffer: 10485760
#write_buffer: 10485760
# On Windows only
# When true, Nebula installs a WFP (Windows Filtering Platform) PERMIT filter scoped to UDP at the listener port.
@@ -182,7 +179,7 @@ listen:
# Currently, this defaults to 1 which means we have 1 tun queue reader and 1
# UDP queue reader. Setting this above one will set IFF_MULTI_QUEUE on the tun
# device and SO_REUSEPORT on the UDP socket to allow multiple queues.
# This option is only supported on Linux. Not reloadable.
# This option is only supported on Linux.
#routines: 1
punchy:
@@ -206,7 +203,6 @@ punchy:
# Cipher allows you to choose between the available ciphers for your network. Options are chachapoly or aes
# IMPORTANT: this value must be identical on ALL NODES/LIGHTHOUSES. We do not/will not support use of different ciphers simultaneously!
# Not reloadable.
#cipher: aes
# Preferred ranges is used to define a hint about the local network ranges, which speeds up discovering the fastest
@@ -233,6 +229,12 @@ punchy:
# Trusted SSH CA public keys. These are the public keys of the CAs that are allowed to sign SSH keys for access.
#trusted_cas:
#- "ssh public key string"
# sandbox_dir restricts file paths for profiling commands (start-cpu-profile, save-heap-profile,
# save-mutex-profile) to the specified directory. Relative paths will be resolved within this directory,
# and absolute paths outside of it will be rejected. Default is $TMP/nebula-debug.
# The directory is NOT automatically created.
# Overriding this to "" is the same as "/" and will allow overwriting any path on the host.
#sandbox_dir: /var/tmp/nebula-debug
# EXPERIMENTAL: relay support for networks that can't establish direct connections.
relay:
@@ -251,25 +253,18 @@ relay:
# Configure the private interface. Note: addr is baked into the nebula certificate
tun:
# When tun is disabled, a lighthouse can be started without a local tun interface (and therefore without root)
# Not reloadable.
disabled: false
# Name of the device. If not set, a default will be chosen by the OS.
# For macOS: if set, must be in the form `utun[0-9]+`.
# For OpenBSD and NetBSD: if set, must be in the form `tun[0-9]+`, otherwise the first free one is used.
# Not reloadable.
# For NetBSD: Required to be set, must be in the form `tun[0-9]+`
dev: nebula1
# Toggles forwarding of local broadcast packets, the address of which depends on the ip/mask encoded in pki.cert
# Not reloadable.
drop_local_broadcast: false
# Toggles forwarding of multicast packets. Not reloadable.
# Toggles forwarding of multicast packets
drop_multicast: false
# Sets the transmit queue length, if you notice lots of transmit drops on the tun it may help to raise this number. Default is 5000
# Not reloadable.
tx_queue: 5000
# Sets the transmit queue length, if you notice lots of transmit drops on the tun it may help to raise this number. Default is 500
tx_queue: 500
# Default MTU for every packet, safe setting is (and the default) 1300 for internet based traffic
# Anything above 8937, here or on a route below, is capped to 8937 with a warning
# Reloadable on Linux only. Where the tun is handed to nebula by a host app (iOS, Android, macOS network extensions)
# the host app owns the MTU.
mtu: 1300
# the use_offloads setting controls if Nebula will attempt to enable GSO and GRO for the tun device. Linux only, not reloadable.
@@ -362,7 +357,7 @@ tun:
#use_system_route_table: false
# Buffer size for reading routes updates. 0 means default system buffer size. (/proc/sys/net/core/rmem_default).
# If using massive routes updates, for example BGP, you may need to increase this value to avoid packet loss.
# SO_RCVBUFFORCE is used to avoid having to raise the system wide max. Not reloadable.
# SO_RCVBUFFORCE is used to avoid having to raise the system wide max
#use_system_route_table_buffer_size: 0
# Configure logging level
@@ -412,16 +407,14 @@ logging:
# Handshakes are sent to all known addresses at each interval with a linear backoff,
# Wait try_interval after the 1st attempt, 2 * try_interval after the 2nd, etc, until the handshake is older than timeout
# A 100ms interval with the default 10 retries will give a handshake 5.5 seconds to resolve before timing out
# Not reloadable.
#try_interval: 100ms
#retries: 20
# query_buffer is the size of the buffer channel for querying lighthouses, drops are recorded in the lighthouse.query.dropped metric.
# Not reloadable.
#query_buffer: 1024
# query_buffer is the size of the buffer channel for querying lighthouses
#query_buffer: 64
# trigger_buffer is the size of the buffer channel for quickly sending handshakes
# after receiving the response for lighthouse queries. Not reloadable.
# after receiving the response for lighthouse queries
#trigger_buffer: 64
# Tunnel manager settings
@@ -464,6 +457,9 @@ firewall:
# Rules are comprised of a protocol, port, and one or more of host, group, or CIDR
# Logical evaluation is roughly: port AND proto AND (ca_sha OR ca_name) AND (host OR group OR groups OR cidr) AND (local cidr)
# - port: Takes `0` or `any` as any, a single number `80`, a range `200-901`, or `fragment` to match second and further fragments of fragmented packets (since there is no port available).
# For IPv6, Nebula can't tell which protocol a second or further fragment belongs to. Any rule that allows them (port `any` or `fragment`,
# and every icmp rule, since icmp ignores ports) allows them for every protocol, not just the rule's. The first fragment, which carries
# the ports, is always checked against its real protocol and port, so this never opens a port the rules don't allow.
# proto: `any`, `tcp`, `udp`, or `icmp`
# a port specification is ignored if proto is `icmp`
# host: `any` or a literal hostname, ie `test-host`
+4 -4
View File
@@ -1,12 +1,13 @@
module github.com/slackhq/nebula
go 1.27.2
go 1.26.0
require (
dario.cat/mergo v1.0.2
filippo.io/bigmod v0.1.0
github.com/DefinedNet/netlink v1.3.2-dn.1
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be
github.com/armon/go-radix v1.0.0
github.com/flynn/noise v1.1.0
github.com/gaissmai/bart v0.29.0
github.com/gogo/protobuf v1.3.2
@@ -32,7 +33,7 @@ require (
golang.zx2c4.com/wireguard/windows v1.0.1
google.golang.org/protobuf v1.36.12
gopkg.in/yaml.v3 v3.0.1
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe
)
require (
@@ -44,6 +45,5 @@ require (
github.com/prometheus/common v0.70.1 // indirect
github.com/prometheus/procfs v0.21.1 // indirect
github.com/vishvananda/netns v0.0.5 // indirect
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc // indirect
golang.org/x/time v0.15.0 // indirect
golang.org/x/time v0.5.0 // indirect
)
+6 -6
View File
@@ -12,6 +12,8 @@ github.com/alecthomas/units v0.0.0-20190717042225-c3de453c63f4/go.mod h1:ybxpYRF
github.com/alecthomas/units v0.0.0-20190924025748-f65c72e2690d/go.mod h1:rBZYJk541a8SKzHPHnH3zbiI+7dagKZ0cgpgrD7Fyho=
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be h1:9AeTilPcZAjCFIImctFaOjnTIavg87rW78vTPkQqLI8=
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be/go.mod h1:ySMOLuWl6zY27l47sB3qLNK6tF2fkHG55UZxx8oIVo4=
github.com/armon/go-radix v1.0.0 h1:F4z6KzEeeQIMeLFa97iZU6vupzoecKdU5TX24SNppXI=
github.com/armon/go-radix v1.0.0/go.mod h1:ufUuZ+zHj4x4TnLV4JWEpy2hxWSpsRywHrMgIH9cCH8=
github.com/beorn7/perks v0.0.0-20180321164747-3a771d992973/go.mod h1:Dwedo/Wpr24TaqPxmxbtue+5NUziq4I4S80YR8gNf3Q=
github.com/beorn7/perks v1.0.0/go.mod h1:KWe93zE9D1o94FZ5RNwFwVgaQK1VOXiVxmqh+CedLV8=
github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
@@ -155,8 +157,6 @@ golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPh
golang.org/x/crypto v0.0.0-20210322153248-0c34fe9e7dc2/go.mod h1:T9bdIzuCu7OtxOm1hfPfRQxPLYneinmdGuTeoZ9dtd4=
golang.org/x/crypto v0.57.0 h1:3ZVCjf8Ggz7zneR/EHRVx68Ctf+2pmIMP2UFhh9cC6M=
golang.org/x/crypto v0.57.0/go.mod h1:Fdz0i5U6CoizGwLda9DttjSk6qlZo25zYNtR+ycvuZA=
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc h1:TS73t7x3KarrNd5qAipmspBDS1rkMcgVG/fS1aRb4Rc=
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc/go.mod h1:A+z0yzpGtvnG90cToK5n2tu8UJVP2XUATh+r+sfOOOc=
golang.org/x/lint v0.0.0-20200302205851-738671d3881b/go.mod h1:3xt1FjdF8hUf6vQPIChWIBhFzV8gjjsPE/fR3IyQdNY=
golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
@@ -203,8 +203,8 @@ golang.org/x/term v0.46.0/go.mod h1:+K02xbkittuwc0Am4abfA3Fc+XRGXkvBXNO88NCXPoc=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
golang.org/x/time v0.5.0 h1:o7cqy6amK/52YcAKIPlM3a+Fpj35zvRj2TP+e1xFSfk=
golang.org/x/time v0.5.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/tools v0.0.0-20200130002326-2f3ba24bd6e7/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
@@ -243,5 +243,5 @@ gopkg.in/yaml.v2 v2.3.0/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980 h1:ribyrTYQ/QYeUIs8x8bVLYwGyepa7RnHLqJzegT5YYk=
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980/go.mod h1:pK/dapF5Bf3KGW7/kd5CI5IC4lYh9FMFY1qETAIGLXk=
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe h1:fre4i6mv4iBuz5lCMOzHD1rH1ljqHWSICFmZRbbgp3g=
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe/go.mod h1:sxc3Uvk/vHcd3tj7/DHVBoR5wvWT/MmRq2pj7HRJnwU=
+5 -18
View File
@@ -31,7 +31,6 @@ package nebula
import (
"bufio"
"context"
"fmt"
"net"
"strconv"
@@ -52,29 +51,17 @@ type graphiteConfigExport struct {
Percentiles []float64 // Percentiles to export from timers and histograms
}
// graphiteTimeout bounds one submission, the connect and the write together. An export is a few KB, a host that can't
// take that in this long isn't going to.
const graphiteTimeout = 30 * time.Second
// graphiteOnce performs a single submission to Graphite, returning a non-nil
// error if it could not connect or write all of it within timeout. It gives up
// as soon as ctx is done.
func graphiteOnce(ctx context.Context, c graphiteConfigExport, timeout time.Duration) error {
// error on failed connections.
func graphiteOnce(c graphiteConfigExport) error {
now := time.Now().Unix()
du := float64(c.DurationUnit)
flushSeconds := float64(c.FlushInterval) / float64(time.Second)
deadline := time.Now().Add(timeout)
d := net.Dialer{Deadline: deadline}
conn, err := d.DialContext(ctx, "tcp", c.Addr.String())
conn, err := net.DialTCP("tcp", nil, c.Addr)
if err != nil {
return err
}
defer conn.Close()
if err := conn.SetDeadline(deadline); err != nil {
return err
}
stop := context.AfterFunc(ctx, func() { _ = conn.Close() })
defer stop()
w := bufio.NewWriter(conn)
c.Registry.Each(func(name string, i any) {
switch metric := i.(type) {
@@ -124,7 +111,7 @@ func graphiteOnce(ctx context.Context, c graphiteConfigExport, timeout time.Dura
fmt.Fprintf(w, "%s.%s.fifteen-minute %.2f %d\n", c.Prefix, name, t.Rate15(), now)
fmt.Fprintf(w, "%s.%s.mean-rate %.2f %d\n", c.Prefix, name, t.RateMean(), now)
}
w.Flush()
})
// A failed write sticks, so this reports the first one
return w.Flush()
return nil
}
-315
View File
@@ -1,315 +0,0 @@
package nebula
import (
"bytes"
"context"
"errors"
"fmt"
"io"
"net"
"strings"
"sync"
"testing"
"time"
"github.com/rcrowley/go-metrics"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// graphiteHost accepts connections and hands each one to the test
type graphiteHost struct {
ln net.Listener
conns chan net.Conn
mu sync.Mutex
closed bool
open []net.Conn
}
// newGraphiteHost accepts connections for the test. A non-zero window shrinks each connection's receive buffer, so a
// sender that is not read from blocks after a little whatever the host's TCP tuning. Only for tests that need a stall,
// a small window makes reading very slow on Linux.
func newGraphiteHost(t *testing.T, window int) *graphiteHost {
t.Helper()
ln, err := net.Listen("tcp", "127.0.0.1:0")
require.NoError(t, err)
h := &graphiteHost{ln: ln, conns: make(chan net.Conn, 8)}
done := make(chan struct{})
t.Cleanup(func() {
_ = ln.Close()
h.mu.Lock()
h.closed = true
for _, c := range h.open {
_ = c.Close()
}
h.mu.Unlock()
close(done)
})
go func() {
for {
c, err := ln.Accept()
if err != nil {
return
}
h.mu.Lock()
if h.closed {
h.mu.Unlock()
_ = c.Close()
return
}
h.open = append(h.open, c)
h.mu.Unlock()
if tc, ok := c.(*net.TCPConn); ok && window > 0 {
_ = tc.SetReadBuffer(window)
}
select {
case h.conns <- c:
case <-done:
return
}
}
}()
return h
}
func (h *graphiteHost) addr(t *testing.T) *net.TCPAddr {
a, err := net.ResolveTCPAddr("tcp", h.ln.Addr().String())
require.NoError(t, err)
return a
}
// readExport reads what one send wrote, bounded so a send that never finishes fails the test rather than hanging it
func readExport(t *testing.T, c net.Conn) []byte {
t.Helper()
require.NoError(t, c.SetReadDeadline(time.Now().Add(10*time.Second)))
b, err := io.ReadAll(c)
require.NoError(t, err)
return b
}
func (h *graphiteHost) next(t *testing.T, wait time.Duration) net.Conn {
t.Helper()
select {
case c := <-h.conns:
return c
case <-time.After(wait):
t.Fatal("no connection")
return nil
}
}
// lockedBuffer is a log destination a test can read while the code under test writes to it from another goroutine
type lockedBuffer struct {
mu sync.Mutex
buf bytes.Buffer
}
func (b *lockedBuffer) Write(p []byte) (int, error) {
b.mu.Lock()
defer b.mu.Unlock()
return b.buf.Write(p)
}
func (b *lockedBuffer) String() string {
b.mu.Lock()
defer b.mu.Unlock()
return b.buf.String()
}
func testGraphiteConfig(addr *net.TCPAddr, r metrics.Registry) graphiteConfigExport {
return graphiteConfigExport{Addr: addr, Registry: r, FlushInterval: time.Second, DurationUnit: time.Nanosecond, Prefix: "nebula"}
}
// Enough metrics that one export overflows the socket buffers on any platform, so a send to a host that stops
// reading blocks
func bigGraphiteRegistry(r metrics.Registry, t *testing.T) {
for i := range 200000 {
name := fmt.Sprintf("big.gauge.%d", i)
metrics.GetOrRegisterGauge(name, r).Update(int64(i))
t.Cleanup(func() { r.Unregister(name) })
}
}
func TestGraphiteOnce_sends(t *testing.T) {
r := metrics.NewRegistry()
metrics.GetOrRegisterGauge("g", r).Update(7)
metrics.GetOrRegisterCounter("c", r).Inc(3)
h := newGraphiteHost(t, 0)
require.NoError(t, graphiteOnce(t.Context(), testGraphiteConfig(h.addr(t), r), time.Minute))
b := readExport(t, h.next(t, 5*time.Second))
assert.Contains(t, string(b), "nebula.g.value 7 ")
assert.Contains(t, string(b), "nebula.c.count 3 ")
assert.Contains(t, string(b), "nebula.c.count_ps 3.00 ")
}
// A host that accepts and never reads is given up on, and the failed write is reported
func TestGraphiteOnce_stalledHostTimesOut(t *testing.T) {
r := metrics.NewRegistry()
bigGraphiteRegistry(r, t)
h := newGraphiteHost(t, 4096)
done := make(chan error, 1)
cfg := testGraphiteConfig(h.addr(t), r)
go func() { done <- graphiteOnce(t.Context(), cfg, 300*time.Millisecond) }()
h.next(t, 5*time.Second) // accepted, never read
select {
case err := <-done:
require.Error(t, err)
case <-time.After(10 * time.Second):
t.Fatal("the send did not give up on a host that stopped reading")
}
}
// The timeout covers the whole send, a host that keeps reading but too slowly is still given up on
func TestGraphiteOnce_timeoutCoversTheWholeSend(t *testing.T) {
r := metrics.NewRegistry()
bigGraphiteRegistry(r, t)
h := newGraphiteHost(t, 0)
done := make(chan error, 1)
start := time.Now()
cfg := testGraphiteConfig(h.addr(t), r)
go func() { done <- graphiteOnce(t.Context(), cfg, 500*time.Millisecond) }()
c := h.next(t, 5*time.Second)
stopReading := make(chan struct{})
defer close(stopReading)
// 32KB every 10ms keeps every write well inside the timeout, the whole export takes seconds
go func() {
buf := make([]byte, 32<<10)
for {
select {
case <-stopReading:
return
case <-time.After(10 * time.Millisecond):
}
if _, err := c.Read(buf); err != nil {
return
}
}
}()
select {
case err := <-done:
require.Error(t, err)
assert.Less(t, time.Since(start), 5*time.Second)
case <-time.After(10 * time.Second):
t.Fatal("a host that kept reading slowly held the send past its timeout")
}
}
func TestGraphiteOnce_cancelledCtxDoesNotConnect(t *testing.T) {
h := newGraphiteHost(t, 0)
ctx, cancel := context.WithCancel(t.Context())
cancel()
require.Error(t, graphiteOnce(ctx, testGraphiteConfig(h.addr(t), metrics.NewRegistry()), time.Minute))
select {
case <-h.conns:
t.Fatal("connected on a cancelled ctx")
case <-time.After(200 * time.Millisecond):
}
}
// A stop or reload abandons a stuck send rather than waiting out its timeout
func TestGraphiteOnce_cancelAbandonsSend(t *testing.T) {
r := metrics.NewRegistry()
bigGraphiteRegistry(r, t)
h := newGraphiteHost(t, 4096)
ctx, cancel := context.WithCancel(t.Context())
done := make(chan error, 1)
cfg := testGraphiteConfig(h.addr(t), r)
go func() { done <- graphiteOnce(ctx, cfg, time.Minute) }()
h.next(t, 5*time.Second)
select {
case err := <-done:
t.Fatalf("the send should be stuck on a host that is not reading, it ended with %v", err)
case <-time.After(200 * time.Millisecond):
}
cancel()
select {
case err := <-done:
require.Error(t, err)
case <-time.After(5 * time.Second):
t.Fatal("the send is still stuck after its ctx was cancelled")
}
}
// buildRuntime hands graphite the configured prefix and interval
func TestStatsServer_graphiteExportUsesConfig(t *testing.T) {
const name = "graphite.wiring.test"
metrics.GetOrRegisterCounter(name, nil).Inc(8)
t.Cleanup(func() { metrics.DefaultRegistry.Unregister(name) })
h := newGraphiteHost(t, 0)
s, c := newTestStatsServer(t)
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "4s", "prefix": "pfx", "host": h.ln.Addr().String()})
cfg, err := loadStatsConfig(c)
require.NoError(t, err)
s.runMu.Lock()
fns, _ := s.buildRuntime(t.Context(), cfg)
s.runMu.Unlock()
for _, fn := range fns {
fn()
}
b := readExport(t, h.next(t, 5*time.Second))
assert.Contains(t, string(b), "pfx."+name+".count 8 ")
assert.Contains(t, string(b), "pfx."+name+".count_ps 2.00 ")
}
func TestStatsServer_graphiteFailureIsLogged(t *testing.T) {
logs := &lockedBuffer{}
s, c := newTestStatsServer(t)
s.l = test.NewLoggerWithOutput(logs)
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": "127.0.0.1:" + freeTCPPort(t)})
cfg, err := loadStatsConfig(c)
require.NoError(t, err)
s.runMu.Lock()
fns, _ := s.buildRuntime(t.Context(), cfg)
s.runMu.Unlock()
for _, fn := range fns {
fn()
}
assert.Contains(t, logs.String(), "Graphite export failed")
}
// Stop abandons the running export, so it goes through Start rather than handing buildRuntime a ctx, and a stop is
// not logged as a failure
func TestStatsServer_stopAbandonsGraphiteSend(t *testing.T) {
bigGraphiteRegistry(metrics.DefaultRegistry, t)
h := newGraphiteHost(t, 4096)
logs := &lockedBuffer{}
s, c := newTestStatsServer(t)
s.l = test.NewLoggerWithOutput(logs)
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "50ms", "host": h.ln.Addr().String()})
require.NoError(t, s.reload(c, true))
started := make(chan struct{})
go func() {
s.Start()
close(started)
}()
stuck := h.next(t, 30*time.Second)
s.Stop()
select {
case <-started:
case <-time.After(5 * time.Second):
t.Fatal("Start did not return after Stop")
}
// A closed sender resets the connection once it sees this, one still sending just buffers it. Either way the
// read below doesn't have to drain the export through the small window to find out
_, err := stuck.Write([]byte("x"))
require.NoError(t, err)
require.NoError(t, stuck.SetReadDeadline(time.Now().Add(10*time.Second)))
n, err := io.Copy(io.Discard, stuck)
var ne net.Error
if errors.As(err, &ne) && ne.Timeout() {
t.Fatalf("the send kept the connection after Stop, read %d bytes", n)
}
assert.Less(t, n, int64(1<<20), "the send kept going after Stop")
// The capture loop logs on its own goroutine after Start has returned, give it the chance
assert.Never(t, func() bool { return strings.Contains(logs.String(), "Graphite export failed") }, 500*time.Millisecond, 10*time.Millisecond, "a stop is not a failure")
}
+11 -8
View File
@@ -54,8 +54,7 @@ type HandshakeConfig struct {
}
type HandshakeManager struct {
// Mutex for interacting with the vpnIps and indexes maps.
// Lock order is hostmap, then this lock, then the lighthouse, then a RemoteList.
// Mutex for interacting with the vpnIps and indexes maps
sync.RWMutex
vpnIps map[netip.Addr]*HandshakeHostInfo
@@ -260,6 +259,14 @@ func (hm *HandshakeManager) handleOutbound(vpnIp netip.Addr, lighthouseTriggered
"style": header.SubTypeName(header.Handshake, hh.machine.Subtype()),
}
// Get a remotes object if we don't already have one.
// This is mainly to protect us as this should never be the case
// NB ^ This comment doesn't jive. It's how the thing gets initialized.
// It's the common path. Should it update every time, in case a future LH query/queries give us more info?
if hostinfo.remotes == nil {
hostinfo.remotes = hm.lightHouse.QueryCache([]netip.Addr{vpnIp})
}
remotes := hostinfo.remotes.CopyAddrs(hm.mainHostMap.GetPreferredRanges())
remotesHaveChanged := !slices.Equal(remotes, hh.lastRemotes)
@@ -364,9 +371,6 @@ func (hm *HandshakeManager) StartHandshake(vpnAddr netip.Addr, cacheCb func(*Han
hostinfo := &HostInfo{
vpnAddrs: []netip.Addr{vpnAddr},
HandshakePacket: make(map[uint8][]byte, 0),
// Attached here so a pending hostinfo never exists without one: SetRemote dereferences
// it, and create-tunnel -address can reach SetRemote before the handshake loop runs.
remotes: hm.lightHouse.QueryCache([]netip.Addr{vpnAddr}),
relayState: RelayState{
relays: nil,
relayForByAddr: map[netip.Addr]*Relay{},
@@ -942,14 +946,13 @@ func (hm *HandshakeManager) continueHandshake(via ViaSender, hh *HandshakeHostIn
hm.DeleteHostInfo(hostinfo)
hm.StartHandshake(hostinfo.vpnAddrs[0], func(newHH *HandshakeHostInfo) {
newHH.hostinfo.remotes = hostinfo.remotes
newHH.hostinfo.remotes.BlockRemote(via)
newHH.packetStore = hh.packetStore
hh.packetStore = []*cachedPacket{}
})
// sendCloseTunnel may take the hostmap lock, so it must not run under the handshake
// manager lock that StartHandshake holds around the callback.
hostinfo.vpnAddrs = vpnAddrs
f.sendCloseTunnel(hostinfo)
})
return
}
+2 -68
View File
@@ -11,7 +11,6 @@ import (
"github.com/slackhq/nebula/test"
"github.com/slackhq/nebula/udp"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func Test_NewHandshakeManagerVpnIp(t *testing.T) {
@@ -43,6 +42,8 @@ func Test_NewHandshakeManagerVpnIp(t *testing.T) {
i2 := blah.StartHandshake(ip, nil)
assert.Same(t, i, i2)
i.remotes = NewRemoteList([]netip.Addr{}, nil)
// Adding something to pending should not affect the main hostmap
assert.Empty(t, mainHM.Hosts)
@@ -234,70 +235,3 @@ func TestHandleIncomingDispatch(t *testing.T) {
assert.Empty(t, hm.indexes, "orphan stage-2 must not create state")
})
}
// Test_PendingHandshakeHasRemotes covers create-tunnel -address: a pending hostinfo must already
// carry its RemoteList when StartHandshake runs its callback, so SetRemote there, before the
// handshake loop has run, is safe and the address becomes one the handshake is sent to.
func Test_PendingHandshakeHasRemotes(t *testing.T) {
l := test.NewLogger()
mainHM := newHostMap(l)
preferredRanges := []netip.Prefix{}
mainHM.preferredRanges.Store(&preferredRanges)
hm := NewHandshakeManager(l, mainHM, newTestLighthouse(), &udp.NoopConn{}, defaultHandshakeConfig)
vpnIp := netip.MustParseAddr("172.1.1.2")
remote := netip.MustParseAddrPort("192.168.1.9:4242")
hi := hm.StartHandshake(vpnIp, func(hh *HandshakeHostInfo) {
require.NotNil(t, hh.hostinfo.remotes, "a pending handshake must never be without its RemoteList")
hh.hostinfo.SetRemote(remote)
})
assert.Contains(t, hi.remotes.CopyAddrs(preferredRanges), remote, "the handshake must be sent to the supplied remote")
assert.Equal(t, remote, hi.GetRemote())
// A RemoteList keeps one learned address per host, so a second remote replaces the
// first — the same behaviour change-remote has on an established tunnel.
other := netip.MustParseAddrPort("192.168.1.10:4242")
hi.SetRemote(other)
assert.Equal(t, []netip.AddrPort{other}, hi.remotes.CopyAddrs(preferredRanges))
assert.Equal(t, other, hi.GetRemote())
}
// newRemotesRaceFixture builds a handshake manager with an established tunnel to vpnAddr whose
// RemoteList is the lighthouse's cached list, the state every teardown-during-handshake race starts from.
func newRemotesRaceFixture(t *testing.T, vpnAddr netip.Addr) (*HandshakeManager, *Interface, *HostInfo) {
t.Helper()
l := test.NewLogger()
mainHM := newHostMap(l)
preferredRanges := []netip.Prefix{}
mainHM.preferredRanges.Store(&preferredRanges)
lh := newTestLighthouse()
hm := NewHandshakeManager(l, mainHM, lh, &udp.NoopConn{}, defaultHandshakeConfig)
f := &Interface{hostMap: mainHM, lightHouse: lh, handshakeManager: hm, l: l}
hm.f = f
established := &HostInfo{
vpnAddrs: []netip.Addr{vpnAddr},
localIndexId: 1,
remoteIndexId: 101,
remotes: lh.QueryCache([]netip.Addr{vpnAddr}),
HandshakePacket: map[uint8][]byte{},
}
mainHM.Lock()
mainHM.unlockedAddHostInfo(established, f)
mainHM.Unlock()
return hm, f, established
}
// With no handshake pending, tearing down the last tunnel still evicts the list.
func Test_CloseTunnelEvictsWithoutPendingHandshake(t *testing.T) {
vpnAddr := netip.MustParseAddr("172.1.1.2")
_, f, established := newRemotesRaceFixture(t, vpnAddr)
f.closeTunnel(established)
assert.NotContains(t, f.hostMap.Hosts, vpnAddr)
assert.NotContains(t, f.lightHouse.addrMap, vpnAddr)
}
-5
View File
@@ -24,11 +24,6 @@ type m = map[string]any
const (
Version uint8 = 1
Len = 16
// MaxOverhead is the most a payload grows on its way to the underlay.
// A relayed packet has two headers and two AEAD tags, one for the inner tunnel and another for the relay tunnel.
// Every supported cipher (today) has a 16 byte tag.
MaxOverhead = 2 * (Len + 16)
)
type MessageType uint8
+5 -7
View File
@@ -316,9 +316,9 @@ type cachedPacketMetrics struct {
func NewHostMapFromConfig(l *slog.Logger, c *config.C) *HostMap {
hm := newHostMap(l)
hm.reload(c, true, nil)
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
hm.reload(c, false, r)
hm.reload(c, true)
c.RegisterReloadCallback(func(c *config.C) {
hm.reload(c, false)
})
l.Info("Main HostMap created", "preferredRanges", hm.GetPreferredRanges())
@@ -337,8 +337,7 @@ func newHostMap(l *slog.Logger) *HostMap {
}
}
// r is nil on the initial load
func (hm *HostMap) reload(c *config.C, initial bool, r *config.Reload) {
func (hm *HostMap) reload(c *config.C, initial bool) {
if initial || c.HasChanged("preferred_ranges") {
var preferredRanges []netip.Prefix
rawPreferredRanges := c.GetStringSlice("preferred_ranges", []string{})
@@ -349,9 +348,8 @@ func (hm *HostMap) reload(c *config.C, initial bool, r *config.Reload) {
if err != nil {
hm.l.Warn("Failed to parse preferred ranges, ignoring",
"error", err,
"range", rawPreferredRange,
"range", rawPreferredRanges,
)
r.Failed()
continue
}
-13
View File
@@ -447,16 +447,3 @@ func TestHostInfo_markOutOnly(t *testing.T) {
assert.True(t, h.markOut(6), "a relayed send must not consume the epoch edge")
assert.False(t, h.markOut(6))
}
// A preferred range that doesn't parse is skipped and the rest are used, the reload says one was skipped
func TestHostMap_reloadBadPreferredRangeFails(t *testing.T) {
l := test.NewLogger()
c := config.NewC(l)
require.NoError(t, c.LoadString("preferred_ranges: [10.0.0.0/8]\n"))
hm := NewHostMapFromConfig(l, c)
res := c.ReloadConfigString("preferred_ranges: [10.0.0.0/8, nope]\n")
require.NoError(t, res.Err)
assert.True(t, res.Failed)
assert.Equal(t, []netip.Prefix{netip.MustParsePrefix("10.0.0.0/8")}, hm.GetPreferredRanges())
}
+12 -29
View File
@@ -10,7 +10,6 @@ import (
"github.com/slackhq/nebula/firewall"
"github.com/slackhq/nebula/header"
"github.com/slackhq/nebula/iputil"
"github.com/slackhq/nebula/logging"
"github.com/slackhq/nebula/noiseutil"
"github.com/slackhq/nebula/overlay/batch"
"github.com/slackhq/nebula/overlay/tio"
@@ -199,8 +198,8 @@ func (f *Interface) sendInsideMessage(hostinfo *HostInfo, pkt tio.Packet, nb []b
}
err = tio.SegmentSuperpacket(pkt, func(seg []byte) error {
//relay header + header + plaintext + AEAD tag + relay tag
scratch := sendBatch.Reserve(len(seg) + header.MaxOverhead)
//relay header + header + plaintext + AEAD tag (16 bytes for both AES-GCM and ChaCha20-Poly1305) + relay tag
scratch := sendBatch.Reserve(header.Len + header.Len + len(seg) + 16 + 16)
innerPacket := f.sendInsideEncrypt(hostinfo, ci, seg, scratch[header.Len:], nb)
if innerPacket == nil {
@@ -518,9 +517,7 @@ func (f *Interface) SendVia(via *HostInfo, relay *Relay, ad, nb, out []byte, noc
err = f.writers[q].WriteTo(toSend, via.GetRemote())
if err != nil {
if l, ok := logging.RateLimited(f.l, f.udpRelayTxErrLimiter); ok {
via.logger(l).Info("Failed to WriteTo in sendVia", "error", err)
}
via.logger(f.l).Info("Failed to WriteTo in sendVia", "error", err)
}
}
@@ -529,26 +526,16 @@ func (f *Interface) sendNoMetrics(t header.MessageType, st header.MessageSubType
return
}
useRelay := !remote.IsValid() && !hostinfo.GetRemote().IsValid()
// The encrypt appends to out in place and a relayed packet is then wrapped in place,
// so out has to fit the whole packet up front or the encrypt reallocates out from under SendVia.
// We cap the MTU of tun devices and routes we create ourselves, so only a host that set a bigger MTU than we allow gets here.
need := header.Len + len(p) + ci.eKey.Overhead()
if useRelay {
// The relay tunnel runs the same cipher, and adds its own header and tag
need += header.Len + ci.eKey.Overhead()
}
if cap(out) < need {
if l, ok := logging.RateLimited(f.l, f.txOversizeLimiter); ok {
hostinfo.logger(l).Error("Dropping outbound packet, out buffer not large enough", "outCap", cap(out), "payloadLen", len(p), "relayed", useRelay)
}
return
}
fullOut := out
if useRelay {
if len(out) < header.Len {
// out always has a capacity of mtu, but not always a length greater than the header.Len.
// Grow it to make sure the next operation works.
out = out[:header.Len]
}
// Save a header's worth of data at the front of the 'out' buffer.
out = out[header.Len:header.Len]
out = out[header.Len:]
}
if noiseutil.EncryptLockNeeded {
@@ -595,23 +582,19 @@ func (f *Interface) sendNoMetrics(t header.MessageType, st header.MessageSubType
if remote.IsValid() {
err = f.writers[q].WriteTo(out, remote)
if err != nil {
if l, ok := logging.RateLimited(f.l, f.udpTxErrLimiter); ok {
hostinfo.logger(l).Error("Failed to write outgoing packet",
hostinfo.logger(f.l).Error("Failed to write outgoing packet",
"error", err,
"udpAddr", remote,
)
}
}
} else if hr := hostinfo.GetRemote(); hr.IsValid() {
err = f.writers[q].WriteTo(out, hr)
if err != nil {
if l, ok := logging.RateLimited(f.l, f.udpTxErrLimiter); ok {
hostinfo.logger(l).Error("Failed to write outgoing packet",
hostinfo.logger(f.l).Error("Failed to write outgoing packet",
"error", err,
"udpAddr", hr,
)
}
}
} else {
// Try to send via a relay
for _, relayIP := range hostinfo.relayState.CopyRelayIps() {
+23 -31
View File
@@ -24,7 +24,6 @@ import (
"github.com/slackhq/nebula/overlay"
"github.com/slackhq/nebula/overlay/batch"
"github.com/slackhq/nebula/overlay/tio"
"github.com/slackhq/nebula/ratelimit"
"github.com/slackhq/nebula/udp"
)
@@ -125,10 +124,6 @@ type Interface struct {
batchers []*batch.MultiCoalescer
wg sync.WaitGroup
udpTxErrLimiter *ratelimit.Limiter // udp direct transmit error log limiter
udpRelayTxErrLimiter *ratelimit.Limiter // udp relay transmit error log limiter
txOversizeLimiter *ratelimit.Limiter // oversized outbound packet drop log limiter
// fatalErr holds the first unexpected reader error that caused shutdown.
// nil means "no fatal error" (yet)
fatalErr atomic.Pointer[error]
@@ -203,19 +198,6 @@ func NewInterface(ctx context.Context, c *InterfaceConfig) (*Interface, error) {
return nil, errors.New("no connection manager")
}
udpTxErrLimiter, err := ratelimit.New(1, time.Second)
if err != nil {
return nil, err
}
udpRelayTxErrLimiter, err := ratelimit.New(1, time.Second)
if err != nil {
return nil, err
}
txOversizeLimiter, err := ratelimit.New(1, time.Second)
if err != nil {
return nil, err
}
if c.routines <= 1 {
c.PinThreads = false //pinning is not useful unless there's more than one tun reader
}
@@ -248,9 +230,6 @@ func NewInterface(ctx context.Context, c *InterfaceConfig) (*Interface, error) {
conntrackCacheTimeout: c.ConntrackCacheTimeout,
cpuAffinity: c.CpuAffinity,
pinThreads: c.PinThreads,
udpTxErrLimiter: udpTxErrLimiter,
udpRelayTxErrLimiter: udpRelayTxErrLimiter,
txOversizeLimiter: txOversizeLimiter,
metricHandshakes: metrics.GetOrRegisterHistogram("handshakes", nil, metrics.NewExpDecaySample(1028, 0.015)),
metricTxDropped: metrics.GetOrRegisterCounter("udp.tx.dropped", nil),
@@ -509,11 +488,10 @@ func (f *Interface) flushSendBatch(sb *batch.SendBatch, q int) {
func (f *Interface) RegisterConfigChangeCallbacks(c *config.C) {
c.RegisterReloadCallback(f.reloadFirewall)
for _, reload := range []func(*config.C){
f.reloadSendRecvError, f.reloadAcceptRecvError, f.reloadDisconnectInvalid, f.reloadMisc,
} {
c.RegisterReloadCallback(func(c *config.C, _ *config.Reload) { reload(c) })
}
c.RegisterReloadCallback(f.reloadSendRecvError)
c.RegisterReloadCallback(f.reloadAcceptRecvError)
c.RegisterReloadCallback(f.reloadDisconnectInvalid)
c.RegisterReloadCallback(f.reloadMisc)
for _, udpConn := range f.writers {
c.RegisterReloadCallback(udpConn.ReloadConfig)
@@ -530,7 +508,7 @@ func (f *Interface) reloadDisconnectInvalid(c *config.C) {
}
}
func (f *Interface) reloadFirewall(c *config.C, r *config.Reload) {
func (f *Interface) reloadFirewall(c *config.C) {
cs := f.pki.getCertState()
curCert := cs.getCertificate(cert.Version2)
if curCert == nil {
@@ -549,7 +527,6 @@ func (f *Interface) reloadFirewall(c *config.C, r *config.Reload) {
fw, err := NewFirewallFromConfig(f.l, cs, c)
if err != nil {
f.l.Error("Error while creating firewall during reload", "error", err)
r.Failed()
return
}
@@ -647,15 +624,17 @@ func (f *Interface) reloadMisc(c *config.C) {
}
}
// statsEmitter updates the interface's gauges, the stats server runs it on its capture loop.
func (f *Interface) statsEmitter() func() {
func (f *Interface) emitStats(ctx context.Context, i time.Duration) {
ticker := time.NewTicker(i)
defer ticker.Stop()
udpStats := udp.NewUDPStatsEmitter(f.writers)
certExpirationGauge := metrics.GetOrRegisterGauge("certificate.ttl_seconds", nil)
certInitiatingVersion := metrics.GetOrRegisterGauge("certificate.initiating_version", nil)
certMaxVersion := metrics.GetOrRegisterGauge("certificate.max_version", nil)
return func() {
emit := func() {
f.firewall.EmitStats()
f.handshakeManager.EmitStats()
udpStats()
@@ -672,6 +651,19 @@ func (f *Interface) statsEmitter() func() {
certMaxVersion.Update(int64(certState.v1Cert.Version()))
}
}
// Prime gauges so a Prometheus scrape that lands before the first tick
// sees real values instead of the zero defaults (issue #907).
emit()
for {
select {
case <-ctx.Done():
return
case <-ticker.C:
emit()
}
}
}
func (f *Interface) GetHostInfo(vpnIp netip.Addr) *HostInfo {
+14 -5
View File
@@ -3,6 +3,7 @@
package nebula
import (
"context"
"net/netip"
"testing"
"time"
@@ -17,8 +18,11 @@ import (
"github.com/stretchr/testify/require"
)
// Priming before the first tick (issue #907) is Start's job, see TestStatsServer_Start_primes.
func Test_statsEmitter_setsGauges(t *testing.T) {
// Test_emitStats_primesGauges covers issue #907: a Prometheus scrape that
// landed before the first ticker fire used to read 0 for the cert gauges.
// emitStats now primes the gauges before entering the ticker loop. We assert
// the gauge is zero before the first call and non-zero after.
func Test_emitStats_primesGauges(t *testing.T) {
defer metrics.DefaultRegistry.UnregisterAll()
l := test.NewLogger()
@@ -52,12 +56,17 @@ func Test_statsEmitter_setsGauges(t *testing.T) {
ifce.pki.cs.Store(cs)
ttlGauge := metrics.GetOrRegisterGauge("certificate.ttl_seconds", nil)
require.Zero(t, ttlGauge.Value(), "gauge should be zero before the emitter runs")
require.Zero(t, ttlGauge.Value(), "gauge should be zero before emitStats runs")
ifce.statsEmitter()()
// Pre-cancel the context so emitStats returns after priming the gauges
// without ever reading from ticker.C. The one hour interval is just a
// belt-and-suspenders, the test does not expect the ticker to fire.
ctx, cancel := context.WithCancel(context.Background())
cancel()
ifce.emitStats(ctx, time.Hour)
ttl := ttlGauge.Value()
assert.Positive(t, ttl, "ttl gauge should be set by one run of the emitter")
assert.Positive(t, ttl, "ttl gauge should be primed by emitStats before its first tick")
assert.LessOrEqual(t, ttl, int64(3600))
assert.Equal(t, int64(cert.Version1), metrics.GetOrRegisterGauge("certificate.initiating_version", nil).Value())
assert.Equal(t, int64(cert.Version1), metrics.GetOrRegisterGauge("certificate.max_version", nil).Value())
+4 -26
View File
@@ -65,10 +65,10 @@ func TestReloadFirewall_CertUnsafeNetworksChanged(t *testing.T) {
pki.cs.Store(&CertState{v2Cert: c2, initiatingVersion: cert.Version2})
// Reload with the same YAML so HasChanged("firewall") reports false.
require.NoError(t, cfg.ReloadConfigString(rawYAML).Err)
require.NoError(t, cfg.ReloadConfigString(rawYAML))
require.False(t, cfg.HasChanged("firewall"))
f.reloadFirewall(cfg, nil)
f.reloadFirewall(cfg)
assert.NotSame(t, fw, f.firewall, "firewall pointer should have been replaced")
assert.Equal(t, newUnsafe, f.firewall.unsafeNetworks)
@@ -113,30 +113,8 @@ func TestReloadFirewall_NoChange(t *testing.T) {
l: l,
}
require.NoError(t, cfg.ReloadConfigString(rawYAML).Err)
f.reloadFirewall(cfg, nil)
require.NoError(t, cfg.ReloadConfigString(rawYAML))
f.reloadFirewall(cfg)
assert.Same(t, fw, f.firewall, "firewall should not have been replaced")
}
// Rules that don't parse keep the old firewall, and the reload says it could not apply them
func TestReloadFirewall_BadRulesFailTheReload(t *testing.T) {
l := test.NewLogger()
pki := &PKI{}
pki.cs.Store(&CertState{v2Cert: &dummyCert{version: cert.Version2, networks: []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")}}, initiatingVersion: cert.Version2})
rules := func(proto string) string {
return "firewall:\n outbound:\n - port: any\n proto: any\n host: any\n inbound:\n - port: any\n proto: " + proto + "\n host: any\n"
}
cfg := config.NewC(l)
require.NoError(t, cfg.LoadString(rules("any")))
fw, err := NewFirewallFromConfig(l, pki.getCertState(), cfg)
require.NoError(t, err)
f := &Interface{pki: pki, firewall: fw, l: l}
cfg.RegisterReloadCallback(f.reloadFirewall)
res := cfg.ReloadConfigString(rules("nope"))
require.NoError(t, res.Err)
assert.True(t, res.Failed)
assert.Same(t, fw, f.firewall)
}
+35 -4
View File
@@ -11,6 +11,8 @@ import (
// ErrIPv6CouldNotFindPayload is returned when the ipv6 extension header chain is truncated before a terminal
// upper layer protocol is reached.
var ErrIPv6CouldNotFindPayload = errors.New("could not find payload in ipv6 packet")
var ErrIPv6ExtensionHeaderAfterFragment = errors.New("extension header after fragment header in packet")
var ErrIPv6HopByHopHeadersMustBeFirst = errors.New("hop-by-hop header must be first extension header")
const (
// MaxIPv4RejectPacketSize is the largest IPv4 reject packet:
@@ -28,6 +30,13 @@ const (
MaxRejectPacketSize = maxIPv6RejectPacketSize
IPv6HeaderHopByHop = 0
IPv6HeaderRouting = 43
IPv6HeaderFragment = 44
IPv6NoNextHeader = 59
IPv6HeaderDestination = 60
IPv6HeaderAuthentication = 51
IPProtocolICMP = 1
IPProtocolICMPv6 = 58
IPProtocolTCP = 6
@@ -350,6 +359,10 @@ func ipv6CreateRejectTCPPacket(packet []byte, out []byte, offset int) []byte {
// Everything else, including Mobility (135), HIP (139), Shim6 (140), experimental 253/254, and real upper layer protocols like SCTP or GRE, is terminal.
// For a non-first fragment the returned protocol is the fragmented protocol and offset points at the fragment header, there is no transport header to locate.
// Returns ErrIPv6CouldNotFindPayload if packet is smaller than an ipv6 header, or the chain is truncated, or if more than 8 extension headers are present.
// Returns ErrIPv6HopByHopHeadersMustBeFirst if a hop-by-hop header appears anywhere but directly after the ipv6 header (RFC 8200 section 4.1).
// Returns ErrIPv6ExtensionHeaderAfterFragment if any walked extension header, including a second fragment header, follows the fragment header of a
// first fragment. The upper layer header must then begin at byte 0 of the fragmentable part, beyond the reach of any non-first fragment,
// whose offset is at least 8, so overlapping fragments cannot rewrite the ports or protocol the firewall read from the first fragment.
func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragment bool, anyFragment bool, err error) {
const maxIPv6ExtHeaders = 8
if len(packet) < ipv6.HeaderLen {
@@ -360,26 +373,44 @@ func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragm
for range maxIPv6ExtHeaders {
switch nextHeader {
case 0, 43, 60: // Hop-by-Hop, Routing, Destination
case IPv6HeaderHopByHop, IPv6HeaderRouting, IPv6HeaderDestination:
if anyFragment {
return 0, 0, false, false, ErrIPv6ExtensionHeaderAfterFragment
}
if len(packet) < offset+2 {
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
}
if nextHeader == IPv6HeaderHopByHop && offset != ipv6.HeaderLen {
//hop-by-hop must appear first, and only once, if it exists.
return 0, 0, false, false, ErrIPv6HopByHopHeadersMustBeFirst
}
nextHeader = packet[offset]
offset += (int(packet[offset+1]) + 1) << 3
case 44: // Fragment
case IPv6HeaderFragment:
if anyFragment {
return 0, 0, false, false, ErrIPv6ExtensionHeaderAfterFragment
}
if len(packet) < offset+8 {
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
}
anyFragment = true
// Non-first fragments carry no transport header, report the fragmented protocol and stop
// Non-first fragments carry no transport header, report the fragmented protocol and stop.
// Per RFC 8200 section 4.5 the receiver only uses the offset zero fragment's next header, so the value
// returned here can't be verified.
if packet[offset+2] != 0 || packet[offset+3]&0xf8 != 0 {
return packet[offset], offset, true, anyFragment, nil
}
nextHeader = packet[offset]
offset += 8
case 51: // AH
case IPv6HeaderAuthentication: // AH
if anyFragment {
return 0, 0, false, false, ErrIPv6ExtensionHeaderAfterFragment
}
if len(packet) < offset+2 {
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
}
+20 -3
View File
@@ -530,13 +530,21 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
nonFirstFrag := []byte{17, 0, 0, 9, 0, 0, 0, 1} // frag offset non-zero, next = UDP
transport := []byte{0, 80, 1, 187, 0, 0, 0, 0} // stand-in bytes, IPv6FindUpperProtocol never reads ports
extToHbH := []byte{0, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = Hop-by-Hop
extToDst := []byte{60, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = Destination
extToFrag := []byte{44, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = Fragment
firstFragToDst := []byte{60, 0, 0, 1, 0, 0, 0, 1} // frag offset 0, M=1, next = Destination
firstFragToAH := []byte{51, 0, 0, 1, 0, 0, 0, 1} // frag offset 0, M=1, next = AH
firstFragToFrag := []byte{44, 0, 0, 1, 0, 0, 0, 1} // frag offset 0, M=1, next = Fragment
firstFragToESP := []byte{50, 0, 0, 1, 0, 0, 0, 1} // frag offset 0, M=1, next = ESP
atomicFragToDst := []byte{60, 0, 0, 0, 0, 0, 0, 1} // frag offset 0, M=0, next = Destination
nonFirstFragToDst := []byte{60, 0, 0, 9, 0, 0, 0, 1} // frag offset non-zero, next = Destination
// 8 walked headers spend the budget before the 9th slot's terminal is ever classified. This is the
// report 4040546 shape: without failing closed the walk hands back offset 104, and a caller reads ports
// from the attacker's bytes there.
// from the attacker's bytes there. Destination is the header that may legally repeat.
var budgetChain []byte
for range 7 {
budgetChain = append(budgetChain, extToHbH...)
budgetChain = append(budgetChain, extToDst...)
}
budgetChain = append(budgetChain, extToTCP...)
budgetChain = append(budgetChain, transport...)
@@ -559,11 +567,20 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
{"ah then udp", 51, append(ahToUDP, transport...), 17, ipv6.HeaderLen + 8, false, false, nil},
{"first fragment walks to transport", 44, append(firstFragToUDP, transport...), 17, ipv6.HeaderLen + 8, false, true, nil},
{"non-first fragment stops", 44, append(nonFirstFrag, transport...), 17, ipv6.HeaderLen, true, true, nil},
{"non-first fragment reports its claimed protocol", 44, append(nonFirstFragToDst, transport...), 60, ipv6.HeaderLen, true, true, nil},
{"routing then first fragment", 43, append(append(extToFrag, firstFragToUDP...), transport...), 17, ipv6.HeaderLen + 16, false, true, nil},
{"first fragment of a non-transport protocol is terminal", 44, append(firstFragToESP, transport...), 50, ipv6.HeaderLen + 8, false, true, nil},
{"destination after first fragment", 44, append(append(firstFragToDst, extToTCP...), transport...), 0, 0, false, false, ErrIPv6ExtensionHeaderAfterFragment},
{"ah after first fragment", 44, append(append(firstFragToAH, ahToUDP...), transport...), 0, 0, false, false, ErrIPv6ExtensionHeaderAfterFragment},
{"fragment after first fragment", 44, append(append(firstFragToFrag, nonFirstFrag...), transport...), 0, 0, false, false, ErrIPv6ExtensionHeaderAfterFragment},
{"destination after atomic fragment", 44, append(append(atomicFragToDst, extToTCP...), transport...), 0, 0, false, false, ErrIPv6ExtensionHeaderAfterFragment},
{"hop-by-hop after destination", 60, append(append(extToHbH, extToTCP...), transport...), 0, 0, false, false, ErrIPv6HopByHopHeadersMustBeFirst},
{"hop-by-hop twice", 0, append(append(extToHbH, extToTCP...), transport...), 0, 0, false, false, ErrIPv6HopByHopHeadersMustBeFirst},
{"unknown protocol is terminal", 132, transport, 132, ipv6.HeaderLen, false, false, nil}, // SCTP
{"truncated extension header", 0, nil, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
// Destination Options with a declared length (255+1)*8 = 2048 that runs past the 48 byte buffer, next = SCTP
{"extension length past buffer", 0, []byte{132, 255, 0, 0, 0, 0, 0, 0}, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
{"budget exhausted fails closed", 0, budgetChain, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
{"budget exhausted fails closed", 60, budgetChain, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
}
for _, tt := range tests {
+9 -38
View File
@@ -15,7 +15,6 @@ import (
"time"
"github.com/gaissmai/bart"
"github.com/rcrowley/go-metrics"
"github.com/slackhq/nebula/cert"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/header"
@@ -82,8 +81,6 @@ type LightHouse struct {
updateTrigger chan struct{}
queryChan chan netip.Addr
// queryDropped counts queries QueryServer dropped because queryChan was full.
queryDropped metrics.Counter
calculatedRemotes atomic.Pointer[bart.Table[[]*calculatedRemote]] // Maps VpnAddr to []*calculatedRemote
@@ -119,8 +116,7 @@ func NewLightHouseFromConfig(ctx context.Context, l *slog.Logger, c *config.C, c
nebulaPort: nebulaPort,
punchy: p,
updateTrigger: make(chan struct{}, 1),
queryChan: make(chan netip.Addr, c.GetUint32("handshakes.query_buffer", 1024)),
queryDropped: metrics.GetOrRegisterCounter("lighthouse.query.dropped", nil),
queryChan: make(chan netip.Addr, c.GetUint32("handshakes.query_buffer", 64)),
l: l,
}
h.localAddrsFn = func(al *LocalAllowList) []netip.Addr {
@@ -138,21 +134,18 @@ func NewLightHouseFromConfig(ctx context.Context, l *slog.Logger, c *config.C, c
h.metrics = newLighthouseMetrics()
}
err := h.reload(c, true, nil)
err := h.reload(c, true)
if err != nil {
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("lighthouse.am_lighthouse", "listen.port", "handshakes.query_buffer", "stats.lighthouse_metrics")
err := h.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := h.reload(c, false)
switch v := err.(type) {
case *util.ContextualError:
v.Log(l)
r.Failed()
case error:
l.Error("failed to reload lighthouse", "error", err)
r.Failed()
}
})
@@ -193,8 +186,7 @@ func (lh *LightHouse) GetUpdateInterval() int64 {
return lh.interval.Load()
}
// r is nil on the initial load
func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error {
func (lh *LightHouse) reload(c *config.C, initial bool) error {
if initial || c.HasChanged("lighthouse.advertise_addrs") {
rawAdvAddrs := c.GetStringSlice("lighthouse.advertise_addrs", []string{})
advAddrs := make([]netip.AddrPort, 0)
@@ -229,7 +221,6 @@ func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error
"addr", rawAddr,
"entry", i+1,
)
r.Failed()
continue
}
@@ -364,13 +355,7 @@ func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error
}
}
// am_relay decides whether relay.relays applies to us at all
if initial || c.HasChanged("relay.relays") || c.HasChanged("relay.am_relay") {
var before []netip.Addr
if !initial {
before = lh.GetRelaysForMe()
}
if initial || c.HasChanged("relay.relays") {
switch c.GetBool("relay.am_relay", false) {
case true:
// Relays aren't allowed to specify other relays
@@ -388,7 +373,6 @@ func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error
"relay", v,
"error", err,
)
r.Failed()
} else {
lh.l.Info("Read relay from config", "relay", v)
relaysForMe = append(relaysForMe, configRIP)
@@ -396,11 +380,6 @@ func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error
}
lh.relaysForMe.Store(&relaysForMe)
}
// Tell the lighthouses now rather than at the next interval, but only when what we advertise changed
if !initial && !slices.Equal(before, lh.GetRelaysForMe()) {
lh.TriggerUpdate()
}
}
return nil
@@ -533,19 +512,14 @@ func (lh *LightHouse) Query(vpnAddr netip.Addr) *RemoteList {
return nil
}
// QueryServer is asynchronous and non-blocking, no reply should be expected.
// If the query channel is full, the query is dropped.
// QueryServer is asynchronous so no reply should be expected
func (lh *LightHouse) QueryServer(vpnAddr netip.Addr) {
// Don't put lighthouse addrs in the query channel because we can't query lighthouses about lighthouses
if lh.amLighthouse || lh.IsLighthouseAddr(vpnAddr) {
return
}
select {
case lh.queryChan <- vpnAddr:
default:
lh.queryDropped.Inc(1)
}
lh.queryChan <- vpnAddr
}
func (lh *LightHouse) QueryCache(vpnAddrs []netip.Addr) *RemoteList {
@@ -1261,13 +1235,10 @@ func (lhh *LightHouseHandler) handleHostQuery(n *NebulaMeta, fromVpnAddrs []neti
// sendHostPunchNotification signals the other side to punch some zero byte udp packets
func (lhh *LightHouseHandler) sendHostPunchNotification(n *NebulaMeta, fromVpnAddrs []netip.Addr, punchNotifDest netip.Addr, w EncWriter) {
whereToPunch := fromVpnAddrs[0]
// Resolve the target before taking the querier's RemoteList lock below. GetHostInfo takes the
// hostmap lock, and the hostmap is taken before the lighthouse, which is taken before a
// RemoteList, so looking it up inside the callback would deadlock.
targetHI := lhh.lh.ifce.GetHostInfo(punchNotifDest)
found, ln, err := lhh.lh.queryAndPrepMessage(whereToPunch, func(c *cache) (int, error) {
n = lhh.resetMeta()
n.Type = NebulaMeta_HostPunchNotification
targetHI := lhh.lh.ifce.GetHostInfo(punchNotifDest)
var useVersion cert.Version
if targetHI == nil {
useVersion = lhh.lh.ifce.GetCertState().initiatingVersion
+10 -257
View File
@@ -6,16 +6,13 @@ import (
"errors"
"fmt"
"net/netip"
"sync"
"testing"
"time"
"github.com/gaissmai/bart"
"github.com/slackhq/nebula/cert"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/header"
"github.com/slackhq/nebula/test"
"github.com/slackhq/nebula/udp"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"go.yaml.in/yaml/v3"
@@ -87,15 +84,15 @@ func TestReloadLighthouseInterval(t *testing.T) {
lh.ifce = &mockEncWriter{}
// The first one routine is kicked off by main.go currently, lets make sure that one dies
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 5").Err)
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 5"))
assert.Equal(t, int64(5), lh.interval.Load())
// Subsequent calls are killed off by the LightHouse.Reload function
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 10").Err)
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 10"))
assert.Equal(t, int64(10), lh.interval.Load())
// If this completes then nothing is stealing our reload routine
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 11").Err)
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 11"))
assert.Equal(t, int64(11), lh.interval.Load())
}
@@ -296,7 +293,7 @@ func TestLighthouse_reload(t *testing.T) {
require.NoError(t, err)
c.ReloadConfigString(string(rc))
err = lh.reload(c, false, nil)
err = lh.reload(c, false)
require.NoError(t, err)
}
@@ -334,7 +331,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
}
rc, err := yaml.Marshal(nc)
require.NoError(t, err)
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
require.NoError(t, c.ReloadConfigString(string(rc)))
rl := lh.Query(staticHost)
require.NotNil(t, rl)
@@ -350,7 +347,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
}
rc, err = yaml.Marshal(nc)
require.NoError(t, err)
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
require.NoError(t, c.ReloadConfigString(string(rc)))
rl = lh.Query(staticHost)
require.NotNil(t, rl)
@@ -358,7 +355,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("1.1.1.1:4242")}, rl.CopyAddrs([]netip.Prefix{}))
// Reload with the same config. An unchanged entry must not duplicate.
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
require.NoError(t, c.ReloadConfigString(string(rc)))
rl = lh.Query(staticHost)
require.NotNil(t, rl)
@@ -373,7 +370,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
}
rc, err = yaml.Marshal(nc)
require.NoError(t, err)
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
require.NoError(t, c.ReloadConfigString(string(rc)))
// Add a second host alongside the first. Both should be present, neither duplicated.
nc = map[string]any{
@@ -384,7 +381,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
}
rc, err = yaml.Marshal(nc)
require.NoError(t, err)
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
require.NoError(t, c.ReloadConfigString(string(rc)))
rl = lh.Query(staticHost)
require.NotNil(t, rl)
@@ -406,7 +403,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
}
rc, err = yaml.Marshal(nc)
require.NoError(t, err)
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
require.NoError(t, c.ReloadConfigString(string(rc)))
_, isStatic := lh.GetStaticHostList()[staticHost]
assert.False(t, isStatic)
@@ -798,247 +795,3 @@ func TestLightHouse_logLocalAddrsErr(t *testing.T) {
lh.logLocalAddrsErr(errors.New("something else"))
assert.Contains(t, out.String(), "level=WARN")
}
// heldEncWriter holds the query worker in its first GetHostInfo until release closes.
type heldEncWriter struct {
mockEncWriter
once sync.Once
held chan struct{}
release chan struct{}
}
func (w *heldEncWriter) GetHostInfo(netip.Addr) *HostInfo {
w.once.Do(func() { close(w.held) })
<-w.release
return nil
}
// QueryServer never waits on the query worker, since the packet readers call it and nothing drains the channel at
// shutdown; a query that finds the channel full is dropped and counted. The worker is held on its first query so the
// channel fills.
func TestLighthouse_QueryServerDoesNotBlock(t *testing.T) {
l := test.NewLogger()
cs := testCertState(netip.MustParsePrefix("10.128.0.1/16"))
lh1 := "10.128.0.2"
c := config.NewC(l)
c.Settings["lighthouse"] = map[string]any{"hosts": []any{lh1}}
c.Settings["static_host_map"] = map[string]any{lh1: []any{"1.1.1.1:4242"}}
c.Settings["handshakes"] = map[string]any{"query_buffer": 1}
lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
require.NoError(t, err)
w := &heldEncWriter{held: make(chan struct{}), release: make(chan struct{})}
lh.ifce = w
t.Cleanup(func() { close(w.release) })
lh.QueryServer(netip.MustParseAddr("10.128.0.10"))
select {
case <-w.held:
case <-time.After(5 * time.Second):
t.Fatal("the query worker never took the first query")
}
dropped := lh.queryDropped.Count()
done := make(chan struct{})
go func() {
lh.QueryServer(netip.MustParseAddr("10.128.0.11"))
lh.QueryServer(netip.MustParseAddr("10.128.0.12"))
close(done)
}()
select {
case <-done:
case <-time.After(5 * time.Second):
t.Fatal("QueryServer blocked on a full query channel")
}
assert.EqualValues(t, 1, lh.queryDropped.Count()-dropped)
}
// hostmapEncWriter answers GetHostInfo from a real hostmap, the way Interface does.
type hostmapEncWriter struct {
mockEncWriter
hm *HostMap
}
func (w *hostmapEncWriter) GetHostInfo(a netip.Addr) *HostInfo { return w.hm.QueryVpnAddr(a) }
func (w *hostmapEncWriter) GetCertState() *CertState {
return &CertState{initiatingVersion: cert.Version1}
}
// A lighthouse runs four paths that each hold one lock while waiting for the next: CheckAndComplete
// holds the hostmap and takes the handshake manager, StartHandshake holds the handshake manager and
// takes the lighthouse, a host update holds the lighthouse and takes the sender's RemoteList, and a
// punch notification holds the querier's RemoteList while it resolves the target. If that last step
// reaches the hostmap under the RemoteList lock, the four deadlock. Drive them all at once.
func TestLighthouse_PunchNotificationDoesNotCloseLockCycle(t *testing.T) {
l := test.NewLogger()
myVpnNet := netip.MustParsePrefix("10.128.0.1/24")
c := config.NewC(l)
c.Settings["lighthouse"] = map[string]any{"am_lighthouse": true}
c.Settings["listen"] = map[string]any{"port": 4242}
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(myVpnNet), nil, nil)
require.NoError(t, err)
mainHM := newHostMap(l)
pr := []netip.Prefix{}
mainHM.preferredRanges.Store(&pr)
lh.ifce = &hostmapEncWriter{hm: mainHM}
hm := NewHandshakeManager(l, mainHM, lh, &udp.NoopConn{}, defaultHandshakeConfig)
f := &Interface{hostMap: mainHM, lightHouse: lh, handshakeManager: hm, l: l}
hm.f = f
peer := netip.MustParseAddr("10.128.0.2")
peerUdp := netip.MustParseAddrPort("10.0.0.2:4242")
target := netip.MustParseAddr("10.128.0.3")
targetUdp := netip.MustParseAddrPort("10.0.0.3:4242")
outbound := netip.MustParseAddr("10.128.0.4")
inbound := netip.MustParseAddr("10.128.0.5")
seed := lh.NewRequestHandler()
newLHHostUpdate(peerUdp, peer, []netip.AddrPort{peerUdp}, seed)
newLHHostUpdate(targetUdp, target, []netip.AddrPort{targetUdp}, seed)
stop := make(chan struct{})
var wg sync.WaitGroup
loop := func(body func()) {
defer wg.Done()
for {
select {
case <-stop:
return
default:
body()
}
}
}
wg.Add(4)
// Outbound handshakes keep starting and being dropped.
go loop(func() {
hm.DeleteHostInfo(hm.StartHandshake(outbound, nil))
})
// Inbound handshakes keep completing and being torn down.
var idx uint32
go loop(func() {
idx++
hi := &HostInfo{
vpnAddrs: []netip.Addr{inbound},
localIndexId: idx,
remoteIndexId: idx,
remotes: lh.QueryCache([]netip.Addr{inbound}),
HandshakePacket: map[uint8][]byte{handshakePacketStage0: {byte(idx)}},
}
if _, err := hm.CheckAndComplete(hi, handshakePacketStage0, f); err == nil {
mainHM.DeleteHostInfo(hi)
}
})
// The peer keeps sending host updates.
updates := lh.NewRequestHandler()
go loop(func() {
newLHHostUpdate(peerUdp, peer, []netip.AddrPort{peerUdp}, updates)
})
// The same peer keeps querying for the target, which ends in a punch notification.
queries := lh.NewRequestHandler()
go loop(func() {
sendLHHostRequest(peerUdp, peer, target, queries, nil)
})
time.Sleep(time.Second)
close(stop)
done := make(chan struct{})
go func() { wg.Wait(); close(done) }()
select {
case <-done:
case <-time.After(5 * time.Second):
t.Fatal("deadlock: the lighthouse paths never finished after stop was signalled")
}
}
func TestLighthouse_reloadRelaysTriggersUpdate(t *testing.T) {
l := test.NewLogger()
c := config.NewC(l)
base := "lighthouse:\n am_lighthouse: true\nlisten:\n port: 4242\n"
require.NoError(t, c.LoadString(base+"relay:\n relays: [10.128.0.5]\n"))
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
require.NoError(t, err)
assert.Empty(t, lh.updateTrigger)
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6]\n").Err)
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
require.Len(t, lh.updateTrigger, 1)
<-lh.updateTrigger
// The config changed but what we advertise did not, a bad entry is skipped
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6, nope]\n").Err)
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
assert.Empty(t, lh.updateTrigger)
}
func TestLighthouse_reloadAmRelayAlone(t *testing.T) {
l := test.NewLogger()
c := config.NewC(l)
base := "lighthouse:\n am_lighthouse: true\nlisten:\n port: 4242\nrelay:\n relays: [10.128.0.5]\n"
require.NoError(t, c.LoadString(base+" am_relay: false\n"))
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
require.NoError(t, err)
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
// Relays aren't allowed to have relays, flipping am_relay alone must drop them and tell the lighthouses
require.NoError(t, c.ReloadConfigString(base+" am_relay: true\n").Err)
assert.Empty(t, lh.GetRelaysForMe())
require.Len(t, lh.updateTrigger, 1)
<-lh.updateTrigger
require.NoError(t, c.ReloadConfigString(base+" am_relay: false\n").Err)
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
require.Len(t, lh.updateTrigger, 1)
}
func TestLighthouse_reloadRestartRequired(t *testing.T) {
l := test.NewLogger()
c := config.NewC(l)
base := "lighthouse:\n am_lighthouse: true\n"
require.NoError(t, c.LoadString(base+"listen:\n port: 4242\n"))
_, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
require.NoError(t, err)
res := c.ReloadConfigString(base + "listen:\n port: 4242\n")
require.NoError(t, res.Err)
assert.False(t, res.RestartRequired)
res = c.ReloadConfigString(base + "listen:\n port: 4243\n")
require.NoError(t, res.Err)
assert.True(t, res.RestartRequired)
}
// A relay that doesn't parse is skipped and the rest are used, the reload says one was skipped
func TestLighthouse_reloadBadRelayFails(t *testing.T) {
l := test.NewLogger()
c := config.NewC(l)
require.NoError(t, c.LoadString("listen:\n port: 4242\n"))
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
require.NoError(t, err)
res := c.ReloadConfigString("listen:\n port: 4242\nrelay:\n relays: [10.128.0.2, nope]\n")
require.NoError(t, res.Err)
assert.True(t, res.Failed)
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.2")}, lh.GetRelaysForMe())
}
// An advertise_addrs entry inside our own network is skipped and the rest are used, the reload says one was skipped
func TestLighthouse_reloadAdvertiseAddrInNetworkFails(t *testing.T) {
l := test.NewLogger()
c := config.NewC(l)
require.NoError(t, c.LoadString("listen:\n port: 4242\n"))
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
require.NoError(t, err)
res := c.ReloadConfigString("listen:\n port: 4242\nlighthouse:\n advertise_addrs: [\"1.2.3.4:4242\", \"10.128.0.5:4242\"]\n")
require.NoError(t, res.Err)
assert.True(t, res.Failed)
assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("1.2.3.4:4242")}, lh.GetAdvertiseAddrs())
}
-31
View File
@@ -1,31 +0,0 @@
package logging
import "log/slog"
// RateLimiter is what RateLimited needs from a rate limiter, such as a *ratelimit.Limiter.
// Allow reports whether this call may proceed, and how many calls were denied since the last one that did.
type RateLimiter interface {
Allow() (denied uint64, ok bool)
}
// RateLimited checks lim before anything is built.
// When allowed it returns l, with a "suppressed" count attached if lim denied calls since its last allowed one.
// A nil lim allows everything.
//
// if l, ok := logging.RateLimited(f.l, f.udpTxErrLimiter); ok {
// hostinfo.logger(l).Error("Failed to write outgoing packet", "error", err)
// }
func RateLimited(l *slog.Logger, lim RateLimiter) (*slog.Logger, bool) {
if lim == nil {
return l, true
}
denied, ok := lim.Allow()
if !ok {
return nil, false
}
if denied > 0 {
return l.With("suppressed", denied), true
}
return l, true
}
-106
View File
@@ -1,106 +0,0 @@
package logging
import (
"bytes"
"errors"
"io"
"log/slog"
"net/netip"
"strings"
"testing"
"time"
"github.com/slackhq/nebula/ratelimit"
)
type fakeLimiter struct {
denied uint64
ok bool
}
func (f fakeLimiter) Allow() (uint64, bool) { return f.denied, f.ok }
func TestRateLimited(t *testing.T) {
var buf bytes.Buffer
base := NewLogger(&buf)
if l, ok := RateLimited(base, fakeLimiter{ok: false}); ok || l != nil {
t.Fatalf("denied call: ok=%v logger=%v", ok, l)
}
if l, ok := RateLimited(base, fakeLimiter{ok: true}); !ok || l != base {
t.Fatal("nothing denied should hand back the same logger")
}
if l, ok := RateLimited(base, nil); !ok || l != base {
t.Fatal("a nil limiter should allow with the same logger")
}
l, ok := RateLimited(base, fakeLimiter{denied: 7, ok: true})
if !ok {
t.Fatal("allowed call denied")
}
l.Info("hello", "k", "v")
if !strings.Contains(buf.String(), "suppressed=7") {
t.Fatalf("want suppressed=7, got %q", buf.String())
}
}
// The benchmarks compare a log line through slog directly against the same line behind RateLimited: logged with
// nothing denied, denied, and logged after denials.
var (
benchErr = errors.New("sendto: no buffer space available")
benchAddr = netip.MustParseAddrPort("192.0.2.1:4242")
)
func benchLogger() *slog.Logger {
return NewLogger(io.Discard).With("localIndex", 1234, "remoteIndex", 5678)
}
func BenchmarkRateLimitedBaseline(b *testing.B) {
lg := benchLogger()
b.ReportAllocs()
for i := 0; i < b.N; i++ {
lg.Error("Failed to write outgoing packet", "error", benchErr, "udpAddr", benchAddr)
}
}
func BenchmarkRateLimitedAllowed(b *testing.B) {
lg, lim := benchLogger(), mustLimiter(b, 1, 0)
b.ReportAllocs()
for i := 0; i < b.N; i++ {
if l, ok := RateLimited(lg, lim); ok {
l.Error("Failed to write outgoing packet", "error", benchErr, "udpAddr", benchAddr)
}
}
}
func BenchmarkRateLimitedDenied(b *testing.B) {
lg, lim := benchLogger(), mustLimiter(b, 1, time.Hour)
lim.Allow()
b.ReportAllocs()
for i := 0; i < b.N; i++ {
if l, ok := RateLimited(lg, lim); ok {
l.Error("Failed to write outgoing packet", "error", benchErr, "udpAddr", benchAddr)
}
}
}
func BenchmarkRateLimitedAfterDenied(b *testing.B) {
lg, lim := benchLogger(), fakeLimiter{denied: 5, ok: true}
b.ReportAllocs()
for i := 0; i < b.N; i++ {
if l, ok := RateLimited(lg, lim); ok {
l.Error("Failed to write outgoing packet", "error", benchErr, "udpAddr", benchAddr)
}
}
}
func mustLimiter(b *testing.B, burst int, every time.Duration) *ratelimit.Limiter {
l, err := ratelimit.New(burst, every)
if err != nil {
b.Fatal(err)
}
return l
}
+7 -25
View File
@@ -12,7 +12,6 @@ import (
"strings"
"time"
"github.com/slackhq/nebula/commands"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/cpupick"
"github.com/slackhq/nebula/noiseutil"
@@ -72,18 +71,14 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
}
l.Info("Firewall started", "firewallHashes", fw.GetRuleHashes())
// The command registry is shared by every surface that exposes these commands, so a
// command cannot reach one of them without reaching the others.
cmdRegistry := commands.New()
ssh, err := sshd.NewSSHServer(ctx, l.With("subsystem", "sshd"), cmdRegistry)
ssh, err := sshd.NewSSHServer(ctx, l.With("subsystem", "sshd"))
if err != nil {
return nil, util.ContextualizeIfNeeded("Error while creating SSH server", err)
}
wireSSHReload(l, ssh, c)
var sshStart func()
if c.GetBool("sshd.enabled", false) {
sshStart, err = configSSH(l, ssh, c, nil)
sshStart, err = configSSH(l, ssh, c)
if err != nil {
l.Warn("Failed to configure sshd, ssh debugging will not be available", "error", err)
sshStart = nil
@@ -202,7 +197,7 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
if err != nil {
return nil, util.NewContextualError("Failed to open udp listener", m{"queue": i}, err)
}
udpServer.ReloadConfig(c, nil)
udpServer.ReloadConfig(c)
udpConns[i] = udpServer
// If port is dynamic, discover it before the next pass through the for loop
@@ -305,7 +300,6 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
}
var ifce *Interface
var emitStats func()
if !configTest {
ifce, err = NewInterface(ctx, ifConfig)
if err != nil {
@@ -316,16 +310,6 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
lightHouse.ifce = ifce
ifce.RegisterConfigChangeCallbacks(c)
// These are only read at startup
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged(
"routines", "tun.routines", "listen.routines", "firewall.conntrack.routine_cache_timeout",
"listen.port", "listen.host", "stats.message_metrics",
"handshakes.try_interval", "handshakes.retries", "handshakes.trigger_buffer",
"tun.drop_local_broadcast", "tun.drop_multicast",
)
r.RestartRequiredIfChanged(osStartupOnlyKeys...)
})
ifce.reloadDisconnectInvalid(c)
ifce.reloadSendRecvError(c)
ifce.reloadAcceptRecvError(c)
@@ -334,12 +318,9 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
go handshakeManager.Run(ctx)
punchy.Start(ctx, ifce, hostMap, lightHouse)
// On the stats server's loop, so the gauges follow the interval it accepted
emitStats = ifce.statsEmitter()
}
stats, err := newStatsServerFromConfig(ctx, l, c, buildVersion, configTest, emitStats)
stats, err := newStatsServerFromConfig(ctx, l, c, buildVersion, configTest)
if err != nil {
return nil, util.ContextualizeIfNeeded("Failed to start stats emitter", err)
}
@@ -348,14 +329,15 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
return nil, nil
}
attachCommands(l, c, cmdRegistry, ifce)
go ifce.emitStats(ctx, c.GetDuration("stats.interval", time.Second*10))
attachCommands(l, c, ssh, ifce)
networkChanges := udp.NewNetworkChangeMonitor(ctx, l, c)
return &Control{
state: StateReady,
f: ifce,
commands: cmdRegistry,
l: l,
ctx: ctx,
cancel: cancel,
-6
View File
@@ -1,6 +0,0 @@
//go:build linux && !android && !e2e_testing
package nebula
// osStartupOnlyKeys are startup only keys that only matter on linux: udp batch size, udp offloads and thread pinning
var osStartupOnlyKeys = []string{"listen.batch", "listen.udp_offloads", "tun.pin_threads", "tun.pin_threads_key", "tun.cpu_affinity"}
-6
View File
@@ -1,6 +0,0 @@
//go:build !linux || android || e2e_testing
package nebula
// osStartupOnlyKeys is empty, none of the OS specific startup keys matter here
var osStartupOnlyKeys []string
+7 -12
View File
@@ -160,7 +160,9 @@ func (f *Interface) readOutsidePackets(via ViaSender, packet []byte, rxc *rxCont
case header.TestReply:
// No-op, useful for the Roaming and connectionManager side-effects above
case header.TestRequest:
if header.MaxOverhead+len(out) > len(rxc.scratch) {
const maxCipherOverhead = 16 //todo we use this too often, needs a real importable const
const maxOverhead = header.Len + header.Len + maxCipherOverhead + maxCipherOverhead
if maxOverhead+len(out) > len(rxc.scratch) {
// A reply that cannot fit in scratch is dropped no matter the log level.
if f.l.Enabled(context.Background(), slog.LevelDebug) {
hostinfo.logger(f.l).Debug("dropping oversized test request", "payloadLen", len(out), "from", via)
@@ -261,16 +263,11 @@ func (f *Interface) handleOutsideRelayPacket(hostinfo *HostInfo, via ViaSender,
// closeTunnel closes a tunnel locally, it does not send a closeTunnel packet to the remote
func (f *Interface) closeTunnel(hostInfo *HostInfo) {
// Hold the hostmap lock across both the delete and the lighthouse eviction,
// to avoid a race with handshake completion.
f.hostMap.Lock()
defer f.hostMap.Unlock()
if !f.hostMap.unlockedDeleteHostInfo(hostInfo) {
return
}
final := f.hostMap.DeleteHostInfo(hostInfo)
if final {
// We no longer have any tunnels with this vpn addr, clear learned lighthouse state to lower memory usage
f.lightHouse.DeleteVpnAddrs(hostInfo.vpnAddrs)
}
}
// sendCloseTunnel is a helper function to send a proper close tunnel packet to a remote
@@ -476,9 +473,7 @@ func parseV4(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
func (f *Interface) handleOutsideMessagePacket(hostinfo *HostInfo, messageCounter uint64, out []byte, rxc *rxContext) {
err := newPacket(out, true, rxc.fwPacket)
if err != nil {
if f.l.Enabled(context.Background(), slog.LevelDebug) {
hostinfo.logger(f.l).Debug("Error while validating inbound packet", "error", err, "packet", out)
}
hostinfo.logger(f.l).Warn("Error while validating inbound packet", "error", err, "packet", out)
return
}
+20
View File
@@ -710,6 +710,26 @@ func Test_newPacket_v6ExtHeaderPastBuffer(t *testing.T) {
require.ErrorIs(t, newPacket(pkt, true, p), iputil.ErrIPv6CouldNotFindPayload)
}
// Test_newPacket_v6ExtHeaderAfterFragment rejects a first fragment whose transport header sits behind another extension
// header. The ports would then start 8 or more bytes into the fragmentable part, where a non-first fragment, filtered
// only as `port: fragment`, could overlap them on a receiver that splices overlapping fragments.
func Test_newPacket_v6ExtHeaderAfterFragment(t *testing.T) {
p := &firewall.ParsedPacket{}
pkt := make([]byte, 60)
pkt[0] = 0x60 // version 6
pkt[6] = byte(layers.IPProtocolIPv6Fragment) // NextHeader -> Fragment
pkt[7] = 64 // hop limit
pkt[40] = byte(layers.IPProtocolIPv6Destination) // Fragment NextHeader -> Destination Options
pkt[43] = 0x01 // offset 0, M=1: a first fragment
pkt[48] = byte(iputil.IPProtocolTCP) // Destination Options NextHeader -> TCP
pkt[49] = 0 // HdrExtLen 0 -> 8 bytes, TCP begins at 56
binary.BigEndian.PutUint16(pkt[58:60], 443) // TCP dst port, reachable by a fragment at offset 8
require.ErrorIs(t, newPacket(pkt, true, p), iputil.ErrIPv6ExtensionHeaderAfterFragment)
require.ErrorIs(t, newPacket(pkt, false, p), iputil.ErrIPv6ExtensionHeaderAfterFragment)
}
// Test_newPacket_v6ExtHeaderConfusion is a regression test for parseV6 walking any unrecognized
// Next Header as if it were an ipv6 extension header. A real upper layer protocol Nebula doesn't
// dissect (SCTP here) is not walkable, so applying the (len+1)*8 formula marched into the SCTP
-57
View File
@@ -1,57 +0,0 @@
//go:build !e2e_testing
package overlay
import (
"fmt"
"log/slog"
"golang.org/x/sys/windows"
"golang.org/x/sys/windows/registry"
)
var tcpipInterfaceKeys = []string{
`SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces`,
`SYSTEM\CurrentControlSet\Services\Tcpip6\Parameters\Interfaces`,
}
// disableDNSRegistration prevents publishing overlay addresses in the host's
// DNS records, where clients outside the overlay cannot reach them.
// Failures are non-fatal so registry access cannot prevent tunnel creation.
func disableDNSRegistration(l *slog.Logger, guid windows.GUID) {
id := guid.String()
for _, base := range tcpipInterfaceKeys {
path := base + `\` + id
if err := setDNSRegistrationValues(path); err != nil {
l.Warn("Failed to disable DNS registration on the tun adapter", "error", err, "key", path)
continue
}
l.Debug("Disabled DNS registration on the tun adapter", "key", path)
}
}
func setDNSRegistrationValues(path string) error {
// The stack may not have created the adapter's interface key yet.
k, _, err := registry.CreateKey(registry.LOCAL_MACHINE, path, registry.SET_VALUE)
if err != nil {
return fmt.Errorf("open HKLM\\%s: %w", path, err)
}
defer k.Close()
// Neither RegistrationEnabled nor DisableDynamicUpdate alone reliably
// prevents registration, so all three settings are required.
values := []struct {
name string
data uint32
}{
{"RegistrationEnabled", 0},
{"DisableDynamicUpdate", 1},
{"MaxNumberOfAddressesToRegister", 0},
}
for _, v := range values {
if err := k.SetDWordValue(v.name, v.data); err != nil {
return fmt.Errorf("set %s: %w", v.name, err)
}
}
return nil
}
+4 -28
View File
@@ -50,13 +50,7 @@ func (r Route) String() string {
func makeRouteTree(l *slog.Logger, routes []Route, allowMTU bool) (*bart.Table[routing.Gateways], error) {
routeTree := new(bart.Table[routing.Gateways])
seen := make(map[netip.Prefix]bool, len(routes))
for _, r := range routes {
if seen[r.Cidr] {
l.Warn("route is listed more than once, only the last entry's via is used", "route", r)
}
seen[r.Cidr] = true
if !allowMTU && r.MTU > 0 {
l.Warn("route MTU is not supported on this platform",
"goos", runtime.GOOS,
@@ -104,11 +98,7 @@ func parseRoutes(c *config.C, networks []netip.Prefix) ([]Route, error) {
mtu, ok := rMtu.(int)
if !ok {
s, ok := rMtu.(string)
if !ok {
return nil, fmt.Errorf("entry %v.mtu in tun.routes is not an integer: %v", i+1, rMtu)
}
mtu, err = strconv.Atoi(s)
mtu, err = strconv.Atoi(rMtu.(string))
if err != nil {
return nil, fmt.Errorf("entry %v.mtu in tun.routes is not an integer: %v", i+1, err)
}
@@ -184,11 +174,7 @@ func parseUnsafeRoutes(c *config.C, networks []netip.Prefix) ([]Route, error) {
if rMtu, ok := m["mtu"]; ok {
mtu, ok = rMtu.(int)
if !ok {
s, ok := rMtu.(string)
if !ok {
return nil, fmt.Errorf("entry %v.mtu in tun.unsafe_routes is not an integer: %v", i+1, rMtu)
}
mtu, err = strconv.Atoi(s)
mtu, err = strconv.Atoi(rMtu.(string))
if err != nil {
return nil, fmt.Errorf("entry %v.mtu in tun.unsafe_routes is not an integer: %v", i+1, err)
}
@@ -206,15 +192,10 @@ func parseUnsafeRoutes(c *config.C, networks []netip.Prefix) ([]Route, error) {
metric, ok := rMetric.(int)
if !ok {
s, ok := rMetric.(string)
if !ok {
return nil, fmt.Errorf("entry %v.metric in tun.unsafe_routes is not an integer: %v", i+1, rMetric)
}
n, err := strconv.ParseInt(s, 10, 32)
_, err = strconv.ParseInt(rMetric.(string), 10, 32)
if err != nil {
return nil, fmt.Errorf("entry %v.metric in tun.unsafe_routes is not an integer: %v", i+1, err)
}
metric = int(n)
}
if metric < 0 || metric > math.MaxInt32 {
@@ -267,15 +248,10 @@ func parseUnsafeRoutes(c *config.C, networks []netip.Prefix) ([]Route, error) {
gatewayWeight, ok := rGatewayWeight.(int)
if !ok {
s, ok := rGatewayWeight.(string)
if !ok {
return nil, fmt.Errorf("entry .weight in tun.unsafe_routes[%v].via[%v] is not an integer", i+1, ig+1)
}
w, err := strconv.ParseInt(s, 10, 32)
_, err = strconv.ParseInt(rGatewayWeight.(string), 10, 32)
if err != nil {
return nil, fmt.Errorf("entry .weight in tun.unsafe_routes[%v].via[%v] is not an integer", i+1, ig+1)
}
gatewayWeight = int(w)
}
if gatewayWeight < 1 || gatewayWeight > math.MaxInt32 {
-116
View File
@@ -1,17 +1,13 @@
package overlay
import (
"bytes"
"fmt"
"net/netip"
"strings"
"testing"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/header"
"github.com/slackhq/nebula/routing"
"github.com/slackhq/nebula/test"
"github.com/slackhq/nebula/udp"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
@@ -406,115 +402,3 @@ func Test_makeMultipathUnsafeRouteTree(t *testing.T) {
routing.CalculateBucketsForGateways(expectedGateways)
assert.ElementsMatch(t, expectedGateways, r)
}
func Test_getMTU(t *testing.T) {
l := test.NewLogger()
c := config.NewC(l)
// unset
assert.Equal(t, DefaultMTU, getMTU(l, c))
// the largest a relayed packet can carry in one underlay buffer
require.Equal(t, udp.MTU, MaxMTU+header.MaxOverhead)
c.Settings["tun"] = map[string]any{"mtu": MaxMTU}
assert.Equal(t, MaxMTU, getMTU(l, c))
// too big is capped
c.Settings["tun"] = map[string]any{"mtu": 9000}
assert.Equal(t, MaxMTU, getMTU(l, c))
}
func Test_getAllRoutesFromConfigCapsMTU(t *testing.T) {
l := test.NewLogger()
c := config.NewC(l)
c.Settings["tun"] = map[string]any{
"routes": []any{
map[string]any{"mtu": "9000", "route": "10.0.0.0/29"},
map[string]any{"mtu": "1300", "route": "10.0.0.8/29"},
},
"unsafe_routes": []any{
map[string]any{"via": "127.0.0.1", "mtu": "9000", "route": "1.0.0.0/29"},
},
}
changed, routes, err := getAllRoutesFromConfig(l, c, []netip.Prefix{netip.MustParsePrefix("10.0.0.0/24")}, true)
require.NoError(t, err)
assert.True(t, changed)
mtus := map[string]int{}
for _, r := range routes {
mtus[r.Cidr.String()] = r.MTU
}
assert.Equal(t, map[string]int{"10.0.0.0/29": MaxMTU, "10.0.0.8/29": 1300, "1.0.0.0/29": MaxMTU}, mtus)
}
// The route tree keeps one entry per CIDR, so a CIDR listed twice only routes by the last one. Say so instead of
// letting the earlier via, or on Windows the earlier metric, quietly lose
func Test_makeRouteTree_WarnsOnDuplicate(t *testing.T) {
buf := &bytes.Buffer{}
l := test.NewLoggerWithOutput(buf)
via := func(s string) routing.Gateways {
return routing.Gateways{routing.NewGateway(netip.MustParseAddr(s), 1)}
}
cidr := netip.MustParsePrefix("10.251.1.0/24")
_, err := makeRouteTree(l, []Route{
{Cidr: cidr, Via: via("10.250.0.2"), Install: true, Metric: 100},
{Cidr: netip.MustParsePrefix("10.251.2.0/24"), Via: via("10.250.0.2"), Install: true},
}, false)
require.NoError(t, err)
assert.Empty(t, buf.String())
tree, err := makeRouteTree(l, []Route{
{Cidr: cidr, Via: via("10.250.0.2"), Install: true, Metric: 100},
{Cidr: cidr, Via: via("10.250.0.3"), Install: true, Metric: 200},
}, false)
require.NoError(t, err)
assert.Equal(t, 1, strings.Count(buf.String(), "route is listed more than once, only the last entry's via is used"))
gw, ok := tree.Lookup(netip.MustParseAddr("10.251.1.1"))
require.True(t, ok)
assert.Equal(t, netip.MustParseAddr("10.250.0.3"), gw[0].Addr(), "the last entry wins")
}
// A quoted metric or weight is a number written as a string, it means that number. Anything else is an error, not a
// panic
func Test_parseUnsafeRoutes_QuotedNumbers(t *testing.T) {
c := config.NewC(test.NewLogger())
n := netip.MustParsePrefix("10.0.0.1/24")
route := func(metric, weight any) {
c.Settings["tun"] = map[string]any{"unsafe_routes": []any{map[string]any{
"route": "1.0.0.0/8",
"metric": metric,
"via": []any{map[string]any{"gateway": "10.0.0.2", "weight": weight}},
}}}
}
route("100", "5")
routes, err := parseUnsafeRoutes(c, []netip.Prefix{n})
require.NoError(t, err)
require.Len(t, routes, 1)
assert.Equal(t, 100, routes[0].Metric)
assert.Equal(t, "{addr: 10.0.0.2, weight: 5}", routes[0].Via[0].String())
route(1.5, 1)
_, err = parseUnsafeRoutes(c, []netip.Prefix{n})
require.EqualError(t, err, "entry 1.metric in tun.unsafe_routes is not an integer: 1.5")
route(1, true)
_, err = parseUnsafeRoutes(c, []netip.Prefix{n})
require.EqualError(t, err, "entry .weight in tun.unsafe_routes[1].via[1] is not an integer")
}
// An mtu that is neither a number nor a quoted one is an error, not a panic
func Test_parseRoutes_MTUNotANumber(t *testing.T) {
c := config.NewC(test.NewLogger())
n := netip.MustParsePrefix("10.0.0.1/24")
c.Settings["tun"] = map[string]any{"routes": []any{map[string]any{"route": "1.0.0.0/8", "mtu": 1500.5}}}
_, err := parseRoutes(c, []netip.Prefix{n})
require.EqualError(t, err, "entry 1.mtu in tun.routes is not an integer: 1500.5")
c.Settings["tun"] = map[string]any{"unsafe_routes": []any{map[string]any{"route": "1.0.0.0/8", "via": "10.0.0.2", "mtu": 1500.5}}}
_, err = parseUnsafeRoutes(c, []netip.Prefix{n})
require.EqualError(t, err, "entry 1.mtu in tun.unsafe_routes is not an integer: 1500.5")
}
+2 -31
View File
@@ -7,27 +7,11 @@ import (
"net/netip"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/header"
"github.com/slackhq/nebula/udp"
"github.com/slackhq/nebula/util"
)
const DefaultMTU = 1300
// MaxMTU is the largest tun.mtu, or route mtu, the underlay can carry.
// Every underlay buffer is udp.MTU bytes, and a relayed packet adds header.MaxOverhead to its plaintext.
const MaxMTU = udp.MTU - header.MaxOverhead
// getMTU reads tun.mtu, capping a value too big for the underlay to carry.
func getMTU(l *slog.Logger, c *config.C) int {
mtu := c.GetInt("tun.mtu", DefaultMTU)
if mtu > MaxMTU {
l.Warn("tun.mtu is too big for the underlay to carry, capping it", "mtu", mtu, "maxMTU", MaxMTU)
return MaxMTU
}
return mtu
}
type NameError struct {
Name string
Underlying error
@@ -41,16 +25,9 @@ func (e *NameError) Error() string {
type DeviceFactory func(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, routines int) (Device, error)
func NewDeviceFromConfig(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, routines int) (Device, error) {
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.disabled")
})
switch {
case c.GetBool("tun.disabled", false):
tun := newDisabledTun(vpnNetworks, c.GetInt("tun.tx_queue", 5000), c.GetBool("stats.message_metrics", false), l)
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.tx_queue", "stats.message_metrics")
})
tun := newDisabledTun(vpnNetworks, c.GetInt("tun.tx_queue", 500), c.GetBool("stats.message_metrics", false), l)
return tun, nil
default:
@@ -64,7 +41,7 @@ func NewFdDeviceFromConfig(fd *int) DeviceFactory {
}
}
func getAllRoutesFromConfig(l *slog.Logger, c *config.C, vpnNetworks []netip.Prefix, initial bool) (bool, []Route, error) {
func getAllRoutesFromConfig(c *config.C, vpnNetworks []netip.Prefix, initial bool) (bool, []Route, error) {
if !initial && !c.HasChanged("tun.routes") && !c.HasChanged("tun.unsafe_routes") {
return false, nil, nil
}
@@ -80,12 +57,6 @@ func getAllRoutesFromConfig(l *slog.Logger, c *config.C, vpnNetworks []netip.Pre
}
routes = append(routes, unsafeRoutes...)
for i, r := range routes {
if r.MTU > MaxMTU {
l.Warn("route mtu is too big for the underlay to carry, capping it", "route", r.Cidr, "mtu", r.MTU, "maxMTU", MaxMTU)
routes[i].MTU = MaxMTU
}
}
return true, routes, nil
}
+5 -6
View File
@@ -38,17 +38,16 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
l: l,
}
err := t.reload(c, true, nil)
err := t.reload(c, true)
if err != nil {
_ = file.Close()
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
@@ -68,8 +67,8 @@ func (t *tun) Activate() error {
return nil
}
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
func (t *tun) reload(c *config.C, initial bool) error {
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
if err != nil {
return err
}
-45
View File
@@ -1,45 +0,0 @@
//go:build (openbsd || netbsd) && !e2e_testing
package overlay
import (
"errors"
"fmt"
"log/slog"
"os"
"regexp"
"runtime"
"golang.org/x/sys/unix"
)
var deviceNameRE = regexp.MustCompile(`^tun[0-9]+$`)
// tunDevNeedsRestart is true when tun.dev asks for a particular tun that isn't the running one. Anything else takes the
// first free one, and the one we have will do
func tunDevNeedsRestart(name, running string) bool {
return deviceNameRE.MatchString(name) && name != running
}
// openTun opens /dev/name, or the first /dev/tunN nothing else has open when name is empty or not tunN
func openTun(l *slog.Logger, name string) (int, string, error) {
if name != "" && !deviceNameRE.MatchString(name) {
// The name doesn't mean anything here, so like darwin a bad one isn't worth refusing to start over
l.Warn("interface name must be tun[0-9]+ on "+runtime.GOOS+", ignoring", "name", name)
name = ""
}
if name != "" {
fd, err := unix.Open("/dev/"+name, os.O_RDWR, 0)
return fd, name, err
}
for i := 0; ; i++ {
name = fmt.Sprintf("tun%d", i)
fd, err := unix.Open("/dev/"+name, os.O_RDWR, 0)
if err == nil {
return fd, name, nil
}
if !errors.Is(err, unix.EBUSY) {
return -1, "", fmt.Errorf("no free tun device, %s: %w", name, err)
}
}
}
-80
View File
@@ -1,80 +0,0 @@
//go:build (openbsd || netbsd) && !e2e_testing
package overlay
import (
"net/netip"
"testing"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// A tun.dev that isn't tunN is ignored like darwin does, and the first free tun is used. Only naming a different tun
// asks for a restart
func TestTunReloadDevRestart(t *testing.T) {
newWithDev := func(dev string) (*config.C, *tun, error) {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString("tun:\n dev: "+dev+"\n"))
tn, err := newTun(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, false)
if err == nil {
t.Cleanup(func() { _ = tn.Close() })
}
return c, tn, err
}
if _, _, err := newWithDev(""); err != nil {
t.Skipf("can't create a tun device here: %v", err)
}
c, tn, err := newWithDev("nope")
require.NoError(t, err, "a bad name should fall back to a free tun")
require.Regexp(t, `^tun[0-9]+$`, tn.Device)
for _, dev := range []string{"nope", "", tn.Device, "nope"} {
res := c.ReloadConfigString("tun:\n dev: " + dev + "\n")
require.NoError(t, res.Err)
assert.False(t, res.Failed, dev)
assert.False(t, res.RestartRequired, dev)
}
other := "tun0"
if tn.Device == other {
other = "tun1"
}
res := c.ReloadConfigString("tun:\n dev: " + other + "\n")
require.NoError(t, res.Err)
assert.Equal(t, []string{"tun.dev"}, res.RestartKeys)
}
// An empty tun.dev takes the first tun nothing else has open. Reloading it empty, or naming the one we have, needs
// no restart
func TestTunEmptyDevPicksAFreeOne(t *testing.T) {
newEmpty := func() (*config.C, *tun, error) {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString("tun: {}\n"))
tn, err := newTun(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, false)
if err == nil {
t.Cleanup(func() { _ = tn.Close() })
}
return c, tn, err
}
c, first, err := newEmpty()
if err != nil {
t.Skipf("can't create a tun device here: %v", err)
}
_, second, err := newEmpty()
require.NoError(t, err, "the second tun should skip the one the first has open")
assert.NotEqual(t, first.Device, second.Device)
for _, cfg := range []string{
"tun: {}\npunchy:\n punch: true\n",
"tun:\n dev: " + first.Device + "\n",
"tun: {}\n",
} {
res := c.ReloadConfigString(cfg)
require.NoError(t, res.Err)
assert.False(t, res.Failed)
assert.False(t, res.RestartRequired, cfg)
}
}
-3
View File
@@ -10,9 +10,6 @@ import (
"github.com/slackhq/nebula/wfp"
)
// interfaceBypassKeys are only read when the interface bypass is installed
var interfaceBypassKeys = []string{"tun.windows_bypass_wdf"}
// installInterfaceBypass installs a WFP PERMIT filter scoped to the wintun interface LUID so inbound traffic on the
// nebula adapter bypasses Windows Defender Firewall.
func installInterfaceBypass(l *slog.Logger, luid uint64) closer {
-3
View File
@@ -4,9 +4,6 @@ package overlay
import "log/slog"
// interfaceBypassKeys is empty, windows-386 has no bypass
var interfaceBypassKeys []string
// installInterfaceBypass is a no-op on windows-386 because we don't currently build for it.
func installInterfaceBypass(_ *slog.Logger, _ uint64) closer {
return nil
+38 -149
View File
@@ -6,10 +6,8 @@ import (
"errors"
"fmt"
"log/slog"
"math/bits"
"net/netip"
"os"
"sync"
"sync/atomic"
"syscall"
"unsafe"
@@ -30,7 +28,7 @@ type tun struct {
DefaultMTU int
Routes atomic.Pointer[[]Route]
routeTree atomic.Pointer[bart.Table[routing.Gateways]]
linkAddr atomic.Pointer[netroute.LinkAddr]
linkAddr *netroute.LinkAddr
// hostOwned means the fd arrived from the OS, which has already configured addressing, mtu
// and routes for it. NEPacketTunnelProvider on darwin does this.
hostOwned bool
@@ -80,31 +78,17 @@ type ifreqAlias6 struct {
Lifetime addrLifetime
}
// utunIndex is the utun tun.dev asks for, or -1 for whichever is free. ok is false for a name that isn't utunN, which
// also gets whichever is free
func utunIndex(name string) (index int, ok bool) {
if name == "" || name == "utun" {
return -1, true
}
if _, err := fmt.Sscanf(name, "utun%d", &index); err != nil || index < 0 {
return -1, false
}
return index, true
}
// tunDevNeedsRestart is true when tun.dev asks for a particular utun that isn't the running one. Anything else takes
// whichever is free, and the one we have will do
func tunDevNeedsRestart(name, running string) bool {
index, _ := utunIndex(name)
return index >= 0 && fmt.Sprintf("utun%d", index) != running
}
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
ifIndex, ok := utunIndex(c.GetString("tun.dev", ""))
if !ok {
name := c.GetString("tun.dev", "")
ifIndex := -1
if name != "" && name != "utun" {
_, err := fmt.Sscanf(name, "utun%d", &ifIndex)
if err != nil || ifIndex < 0 {
// NOTE: we don't make this error so we don't break existing
// configs that set a name before it was used.
l.Warn("interface name must be utun[0-9]+ on Darwin, ignoring")
ifIndex = -1
}
}
fd, err := unix.Socket(unix.AF_SYSTEM, unix.SOCK_DGRAM, unix.AF_SYS_CONTROL)
@@ -128,7 +112,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
return nil, fmt.Errorf("SYS_CONNECT: %v", err)
}
name, err := unix.GetsockoptString(fd, unix.AF_SYS_CONTROL, _UTUN_OPT_IFNAME)
name, err = unix.GetsockoptString(fd, unix.AF_SYS_CONTROL, _UTUN_OPT_IFNAME)
if err != nil {
return nil, fmt.Errorf("failed to retrieve tun name: %w", err)
}
@@ -142,24 +126,19 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
f: os.NewFile(uintptr(fd), ""),
Device: name,
vpnNetworks: vpnNetworks,
DefaultMTU: getMTU(l, c),
DefaultMTU: c.GetInt("tun.mtu", DefaultMTU),
l: l,
}
err = t.reload(c, true, nil)
err = t.reload(c, true)
if err != nil {
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.mtu")
if tunDevNeedsRestart(c.GetString("tun.dev", ""), t.Device) {
r.RestartRequiredIfChanged("tun.dev")
}
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
@@ -188,20 +167,19 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
f: file,
Device: utunNameFromFd(deviceFd),
vpnNetworks: vpnNetworks,
DefaultMTU: getMTU(l, c),
DefaultMTU: c.GetInt("tun.mtu", DefaultMTU),
hostOwned: true,
l: l,
}
if err := t.reload(c, true, nil); err != nil {
if err := t.reload(c, true); err != nil {
_ = file.Close()
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
if err := t.reload(c, false, r); err != nil {
c.RegisterReloadCallback(func(c *config.C) {
if err := t.reload(c, false); err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
@@ -265,7 +243,7 @@ func (t *tun) Activate() error {
if linkAddr == nil {
return fmt.Errorf("unable to discover link_addr for tun interface")
}
t.linkAddr.Store(linkAddr)
t.linkAddr = linkAddr
for _, network := range t.vpnNetworks {
if network.Addr().Is4() {
@@ -288,10 +266,9 @@ func (t *tun) Activate() error {
}
// Unsafe path routes
return t.addRoutes(false, nil)
return t.addRoutes(false)
}
// activate4 assigns our vpn address as a /32 and routes the vpn network to the tun explicitly.
func (t *tun) activate4(network netip.Prefix) error {
s, err := unix.Socket(
unix.AF_INET,
@@ -318,32 +295,22 @@ func (t *tun) activate4(network netip.Prefix) error {
MaskAddr: unix.RawSockaddrInet4{
Len: unix.SizeofSockaddrInet4,
Family: unix.AF_INET,
Addr: [4]byte{255, 255, 255, 255}, //always make the address a /32
Addr: prefixToMask(network).As4(),
},
}
// On Darwin, VPNs don't edit the routing table directly.
// A network extension hands its routes to the system, and configd installs them.
// configd replaces any route already holding the same prefix, including ours.
// As an example, Tailscale with an exit node treats any interface prefix wider than one address as a LAN.
// With LAN access off, it routes each LAN into Tailscale's utun.
// With LAN access on, it excludes each LAN from its tunnel.
// configd routes an excluded prefix like its own routes would, ignoring ours, so it goes out the default route.
// Either way our route is replaced, and traffic for the vpn network no longer reaches nebula.
// A single address isn't a LAN to Tailscale, so our route is left alone.
// We route the vpn network to the tun explicitly instead.
if err := ioctl(uintptr(s), unix.SIOCAIFADDR, uintptr(unsafe.Pointer(&ifr))); err != nil {
return fmt.Errorf("failed to set tun v4 address: %s", err)
}
if err := addRoute(network, t.linkAddr.Load()); err != nil {
return fmt.Errorf("failed to add route for %v: %w", network.Masked(), err)
err = addRoute(network, t.linkAddr)
if err != nil {
return err
}
return nil
}
// activate6 is activate4 for IPv6
func (t *tun) activate6(network netip.Prefix) error {
s, err := unix.Socket(
unix.AF_INET6,
@@ -365,29 +332,25 @@ func (t *tun) activate6(network netip.Prefix) error {
PrefixMask: unix.RawSockaddrInet6{
Len: unix.SizeofSockaddrInet6,
Family: unix.AF_INET6,
// Always set the netmask to be a /128. See activate4 for why we do this.
Addr: [16]byte{255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255},
Addr: prefixToMask(network).As16(),
},
Lifetime: addrLifetime{
// never expires
Vltime: 0xffffffff,
Pltime: 0xffffffff,
},
Flags: _IN6_IFF_NODAD, // No DAD, a utun has no neighbors.
Flags: _IN6_IFF_NODAD,
}
if err := ioctl(uintptr(s), _SIOCAIFADDR_IN6, uintptr(unsafe.Pointer(&ifr))); err != nil {
return fmt.Errorf("failed to set tun address: %s", err)
}
if err := addRoute(network, t.linkAddr.Load()); err != nil {
return fmt.Errorf("failed to add route for %v: %w", network.Masked(), err)
}
return nil
}
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
func (t *tun) reload(c *config.C, initial bool) error {
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
if err != nil {
return err
}
@@ -407,18 +370,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
if !initial {
// Remove first, if the system removes a wanted route hopefully it will be re-added next
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
if err != nil {
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
r.Failed()
}
// Ensure any routes we actually want are installed
err = t.addRoutes(true, r)
err = t.addRoutes(true)
if err != nil {
// Catch any stray logs
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
r.Failed()
}
}
@@ -433,56 +394,6 @@ func (t *tun) RoutesFor(ip netip.Addr) routing.Gateways {
return routing.Gateways{}
}
func fetchRoutes() ([]netroute.Message, error) {
rib, err := netroute.FetchRIB(unix.AF_UNSPEC, unix.NET_RT_DUMP, 0)
if err != nil {
return nil, err
}
return netroute.ParseRIB(unix.NET_RT_DUMP, rib)
}
// routeInterfaceIn returns the index of the interface prefix is routed through, or 0 if msgs has no route for exactly
// that prefix. Routes scoped to an interface are skipped, they don't stop us adding ours.
func routeInterfaceIn(msgs []netroute.Message, prefix netip.Prefix) int {
for _, msg := range msgs {
m, ok := msg.(*netroute.RouteMessage)
if !ok || len(m.Addrs) <= unix.RTAX_NETMASK || m.Flags&unix.RTF_IFSCOPE != 0 {
continue
}
if p, ok := routePrefix(m.Addrs[unix.RTAX_DST], m.Addrs[unix.RTAX_NETMASK]); ok && p == prefix.Masked() {
return m.Index
}
}
return 0
}
// routePrefix returns the prefix a route covers. Host routes have no netmask.
func routePrefix(dst, mask netroute.Addr) (netip.Prefix, bool) {
switch d := dst.(type) {
case *netroute.Inet4Addr:
bits := 32
if m, ok := mask.(*netroute.Inet4Addr); ok {
bits = maskBits(m.IP[:])
}
return netip.PrefixFrom(netip.AddrFrom4(d.IP), bits), true
case *netroute.Inet6Addr:
bits := 128
if m, ok := mask.(*netroute.Inet6Addr); ok {
bits = maskBits(m.IP[:])
}
return netip.PrefixFrom(netip.AddrFrom16(d.IP), bits), true
}
return netip.Prefix{}, false
}
func maskBits(mask []byte) int {
n := 0
for _, b := range mask {
n += bits.OnesCount8(b)
}
return n
}
// Get the LinkAddr for the interface of the given name
// Is there an easier way to fetch this when we create the interface?
// Maybe SIOCGIFINDEX? but this doesn't appear to exist in the darwin headers.
@@ -511,20 +422,13 @@ func getLinkAddr(name string) (*netroute.LinkAddr, error) {
return nil, nil
}
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
func (t *tun) addRoutes(logErrors bool) error {
// The route tree is still ours, the system routing table is not
if t.hostOwned {
return nil
}
// Activate hasn't run yet, it will install the routes
linkAddr := t.linkAddr.Load()
if linkAddr == nil {
return nil
}
routes := *t.Routes.Load()
systemRoutes := sync.OnceValues(fetchRoutes)
for _, r := range routes {
if len(r.Via) == 0 || !r.Install {
@@ -532,54 +436,39 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
continue
}
err := addRoute(r.Cidr, linkAddr)
err := addRoute(r.Cidr, t.linkAddr)
if err != nil {
if errors.Is(err, unix.EEXIST) {
// Every route we added already exists on a reload, only warn about someone else's
msgs, err := systemRoutes()
if err != nil {
t.l.Warn("unable to add unsafe_route, a route already exists but its interface could not be determined", "route", r.Cidr, "error", err)
} else if routeInterfaceIn(msgs, r.Cidr) != linkAddr.Index {
t.l.Warn("unable to add unsafe_route, the destination is already routed through another interface", "route", r.Cidr)
}
t.l.Warn("unable to add unsafe_route, identical route already exists", "route", r.Cidr)
} else {
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
if logErrors {
retErr.Log(t.l)
rl.Failed()
} else {
return retErr
}
}
} else {
t.l.Info("Added route", "route", r)
// A cidr listed twice would otherwise find our own route missing from an older fetch
systemRoutes = sync.OnceValues(fetchRoutes)
}
}
return nil
}
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
linkAddr := t.linkAddr.Load()
if t.hostOwned || linkAddr == nil {
func (t *tun) removeRoutes(routes []Route) error {
if t.hostOwned {
return nil
}
for _, r := range routes {
if len(r.Via) == 0 || !r.Install {
// addRoutes never installs these
if !r.Install {
continue
}
err := delRoute(r.Cidr, linkAddr)
if errors.Is(err, unix.ESRCH) {
// Already gone, which is what we wanted
t.l.Info("Route was already removed", "route", r)
} else if err != nil {
err := delRoute(r.Cidr, t.linkAddr)
if err != nil {
t.l.Error("Failed to remove route", "error", err, "route", r)
rl.Failed()
} else {
t.l.Info("Removed route", "route", r)
}
-118
View File
@@ -1,118 +0,0 @@
//go:build darwin && !ios && !e2e_testing
package overlay
import (
"net"
"net/netip"
"os"
"os/exec"
"strings"
"testing"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/routing"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
netroute "golang.org/x/net/route"
"golang.org/x/sys/unix"
)
// Every mac routes loopback through lo0
func TestRouteInterfaceIn(t *testing.T) {
msgs, err := fetchRoutes()
require.NoError(t, err)
routeInterface := func(s string) int { return routeInterfaceIn(msgs, netip.MustParsePrefix(s)) }
lo0, err := net.InterfaceByName("lo0")
require.NoError(t, err)
assert.Equal(t, lo0.Index, routeInterface("127.0.0.0/8"))
assert.Equal(t, lo0.Index, routeInterface("127.0.0.1/32"), "a host route has no netmask")
assert.Equal(t, lo0.Index, routeInterface("::1/128"))
assert.Equal(t, 0, routeInterface("127.0.0.0/16"), "only an exact prefix counts")
// Most macs also list the default route scoped to their other interfaces
out, err := exec.Command("route", "-n", "get", "default").Output()
require.NoError(t, err)
var name string
for _, line := range strings.Split(string(out), "\n") {
if v, ok := strings.CutPrefix(strings.TrimSpace(line), "interface: "); ok {
name = v
}
}
if name == "" {
t.Skip("no default route")
}
def, err := net.InterfaceByName(name)
require.NoError(t, err)
assert.Equal(t, def.Index, routeInterface("0.0.0.0/0"))
}
func TestRouteInterfaceIn_SkipsScopedCopies(t *testing.T) {
route := func(index, flags int) netroute.Message {
addrs := make([]netroute.Addr, unix.RTAX_MAX)
addrs[unix.RTAX_DST] = &netroute.Inet4Addr{IP: [4]byte{192, 168, 1, 0}}
addrs[unix.RTAX_NETMASK] = &netroute.Inet4Addr{IP: [4]byte{255, 255, 255, 0}}
return &netroute.RouteMessage{Index: index, Flags: flags, Addrs: addrs}
}
p := netip.MustParsePrefix("192.168.1.0/24")
assert.Equal(t, 7, routeInterfaceIn([]netroute.Message{route(4, unix.RTF_UP|unix.RTF_IFSCOPE), route(7, unix.RTF_UP)}, p))
assert.Equal(t, 0, routeInterfaceIn([]netroute.Message{route(4, unix.RTF_UP|unix.RTF_IFSCOPE)}, p))
}
// A reload can happen before Activate
func TestTunRoutesBeforeActivate(t *testing.T) {
tn := &tun{l: test.NewLogger()}
routes := []Route{{
Cidr: netip.MustParsePrefix("10.253.1.0/24"),
Via: routing.Gateways{routing.NewGateway(netip.MustParseAddr("10.250.0.2"), 1)},
Install: true,
}}
tn.Routes.Store(&routes)
assert.NoError(t, tn.addRoutes(true, nil))
assert.NoError(t, tn.removeRoutes(routes, nil))
}
// A tun.routes entry with no via is never installed, so removing it must not delete a route for the same cidr that
// belongs to someone else
func TestTunReloadLeavesRoutesItNeverInstalled(t *testing.T) {
if os.Geteuid() != 0 {
t.Skip("creating a utun and adding routes needs root")
}
lo0, err := net.InterfaceByName("lo0")
require.NoError(t, err)
cidr := "10.250.0.128/25"
require.NoError(t, exec.Command("route", "-q", "-n", "add", "-net", cidr, "-interface", "lo0").Run())
t.Cleanup(func() { _ = exec.Command("route", "-q", "-n", "delete", "-net", cidr).Run() })
l := test.NewLogger()
c := config.NewC(l)
require.NoError(t, c.LoadString("tun:\n routes:\n - route: "+cidr+"\n mtu: 1300\n"))
tn, err := newTun(c, l, []netip.Prefix{netip.MustParsePrefix("10.250.0.1/24")}, false)
require.NoError(t, err)
t.Cleanup(func() { _ = tn.Close() })
require.NoError(t, tn.Activate())
res := c.ReloadConfigString("tun: {}\n")
require.NoError(t, res.Err)
assert.False(t, res.Failed, "removing a route we never installed failed the reload")
msgs, err := fetchRoutes()
require.NoError(t, err)
assert.Equal(t, lo0.Index, routeInterfaceIn(msgs, netip.MustParsePrefix(cidr)))
}
// Only naming a different utun asks for a restart. Empty, plain utun and names that aren't utunN take whichever is free
func TestTunDevNeedsRestart(t *testing.T) {
for name, want := range map[string]bool{
"": false,
"utun": false,
"nope": false,
"utun7": false,
"utun3": true,
} {
assert.Equal(t, want, tunDevNeedsRestart(name, "utun7"), name)
}
}
-121
View File
@@ -1,121 +0,0 @@
//go:build !ios && !e2e_testing
package overlay
import (
"bytes"
"os"
"syscall"
"testing"
"github.com/stretchr/testify/require"
)
func TestTun_WriteFraming(t *testing.T) {
r, w, err := os.Pipe()
require.NoError(t, err)
defer r.Close()
defer w.Close()
tn := &tun{f: w}
for _, tc := range []struct {
name string
pkt []byte
af byte
}{
// Literal families rather than syscall.AF_*, so a wrong constant in Write can't also fix the expectation.
{"ipv4", []byte{0x45, 1, 2, 3, 4, 5}, 2},
{"ipv6", []byte{0x60, 1, 2, 3, 4, 5}, 30},
} {
t.Run(tc.name, func(t *testing.T) {
n, err := tn.Write(tc.pkt)
require.NoError(t, err)
require.Equal(t, len(tc.pkt), n)
got := make([]byte, 64)
n, err = r.Read(got)
require.NoError(t, err)
require.Equal(t, append([]byte{0, 0, 0, tc.af}, tc.pkt...), got[:n])
})
}
_, err = tn.Write([]byte{0x10, 1, 2, 3})
require.Error(t, err)
_, err = tn.Write([]byte{})
require.ErrorIs(t, err, syscall.EIO)
// The rejected writes must not have put anything on the fd, so the next read sees only this packet.
pkt := []byte{0x45, 9, 9}
_, err = tn.Write(pkt)
require.NoError(t, err)
got := make([]byte, 64)
n, err := r.Read(got)
require.NoError(t, err)
require.Equal(t, append([]byte{0, 0, 0, 2}, pkt...), got[:n])
}
func TestTun_ReadStripsHeader(t *testing.T) {
r, w, err := os.Pipe()
require.NoError(t, err)
defer r.Close()
defer w.Close()
tn := &tun{f: r}
pkt := []byte{0x45, 1, 2, 3, 4, 5}
_, err = w.Write(append([]byte{0, 0, 0, syscall.AF_INET}, pkt...))
require.NoError(t, err)
got := make([]byte, 64)
n, err := tn.Read(got)
require.NoError(t, err)
require.Equal(t, pkt, got[:n])
}
func TestTun_ReadShort(t *testing.T) {
r, w, err := os.Pipe()
require.NoError(t, err)
defer r.Close()
defer w.Close()
tn := &tun{f: r}
// Fewer bytes than the protocol header is not a packet.
_, err = w.Write([]byte{0, 0})
require.NoError(t, err)
n, err := tn.Read(make([]byte, 64))
require.NoError(t, err)
require.Zero(t, n)
// The next packet reads cleanly only if the short read consumed exactly what was written.
pkt := []byte{0x45, 1, 2, 3}
_, err = w.Write(append([]byte{0, 0, 0, syscall.AF_INET}, pkt...))
require.NoError(t, err)
got := make([]byte, 64)
n, err = tn.Read(got)
require.NoError(t, err)
require.Equal(t, pkt, got[:n])
}
// A heap allocation per packet rarely shows in a short throughput run, only across GC pauses, so
// this pins Read and Write to zero allocations directly.
func TestTun_ReadWriteDoNotAllocate(t *testing.T) {
r, w, err := os.Pipe()
require.NoError(t, err)
defer r.Close()
defer w.Close()
tw := &tun{f: w}
tr := &tun{f: r}
pkts := [][]byte{bytes.Repeat([]byte{0x45}, 1300), bytes.Repeat([]byte{0x60}, 1300)}
buf := make([]byte, 1500)
i := 0
allocs := testing.AllocsPerRun(1000, func() {
i++
if _, err := tw.Write(pkts[i%len(pkts)]); err != nil {
t.Fatal(err)
}
if _, err := tr.Read(buf); err != nil {
t.Fatal(err)
}
})
require.Zero(t, allocs)
}
+13 -23
View File
@@ -370,7 +370,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
t := &tun{
Device: deviceName,
vpnNetworks: vpnNetworks,
MTU: getMTU(l, c),
MTU: c.GetInt("tun.mtu", DefaultMTU),
l: l,
fd: fd,
shutdownR: shutdownR,
@@ -385,18 +385,16 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
},
}
err = t.reload(c, true, nil)
err = t.reload(c, true)
if err != nil {
return nil, err
}
closeOnErr = false
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.dev", "tun.mtu")
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
@@ -495,7 +493,7 @@ func (t *tun) Activate() error {
}
}
return t.addRoutes(false, nil)
return t.addRoutes(false)
}
func (t *tun) setMTU() error {
@@ -511,8 +509,8 @@ func (t *tun) setMTU() error {
return err
}
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
func (t *tun) reload(c *config.C, initial bool) error {
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
if err != nil {
return err
}
@@ -532,18 +530,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
if !initial {
// Remove first, if the system removes a wanted route hopefully it will be re-added next
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
if err != nil {
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
r.Failed()
}
// Ensure any routes we actually want are installed
err = t.addRoutes(true, r)
err = t.addRoutes(true)
if err != nil {
// Catch any stray logs
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
r.Failed()
}
}
@@ -567,7 +563,7 @@ func (t *tun) Queues(int) ([]tio.Queue, error) {
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
}
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
func (t *tun) addRoutes(logErrors bool) error {
routes := *t.Routes.Load()
for _, r := range routes {
if len(r.Via) == 0 || !r.Install {
@@ -580,7 +576,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
if logErrors {
retErr.Log(t.l)
rl.Failed()
} else {
return retErr
}
@@ -592,20 +587,15 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
return nil
}
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
func (t *tun) removeRoutes(routes []Route) error {
for _, r := range routes {
if len(r.Via) == 0 || !r.Install {
// addRoutes never installs these
if !r.Install {
continue
}
err := delRoute(r.Cidr, t.linkAddr)
if errors.Is(err, unix.ESRCH) {
// Already gone, which is what we wanted
t.l.Info("Route was already removed", "route", r)
} else if err != nil {
if err != nil {
t.l.Error("Failed to remove route", "error", err, "route", r)
rl.Failed()
} else {
t.l.Info("Removed route", "route", r)
}
+5 -6
View File
@@ -47,17 +47,16 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
l: l,
}
err := t.reload(c, true, nil)
err := t.reload(c, true)
if err != nil {
_ = file.Close()
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
@@ -68,8 +67,8 @@ func (t *tun) Activate() error {
return nil
}
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
func (t *tun) reload(c *config.C, initial bool) error {
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
if err != nil {
return err
}
+18 -41
View File
@@ -185,10 +185,6 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, multiqueue
}
t.Device = name
// Only read when we create the device, an fd handed to us already has its name and offloads
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.dev", "tun.use_offloads")
})
return t, nil
}
@@ -225,32 +221,30 @@ func newTunGeneric(c *config.C, l *slog.Logger, fd int, vnetHdr bool, offloadFla
vnetHdr: vnetHdr,
offloadFlags: offloadFlags,
vpnNetworks: vpnNetworks,
TXQueueLen: c.GetInt("tun.tx_queue", 5000),
TXQueueLen: c.GetInt("tun.tx_queue", 500),
useSystemRoutes: c.GetBool("tun.use_system_route_table", false),
useSystemRoutesBufferSize: c.GetInt("tun.use_system_route_table_buffer_size", 0),
routesFromSystem: map[netip.Prefix]routing.Gateways{},
l: l,
}
if err = t.reload(c, true, nil); err != nil {
if err = t.reload(c, true); err != nil {
_ = t.Close()
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.tx_queue", "tun.use_system_route_table", "tun.use_system_route_table_buffer_size")
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
return t, nil
}
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
routeChange, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
func (t *tun) reload(c *config.C, initial bool) error {
routeChange, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
if err != nil {
return err
}
@@ -259,15 +253,6 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
return nil
}
// Only the mtu changed. The routes are the same, parse them again so the ones without their own mtu pick up the
// new default. Without this an mtu change would remove them all
if !routeChange {
_, routes, err = getAllRoutesFromConfig(t.l, c, t.vpnNetworks, true)
if err != nil {
return err
}
}
routeTree, err := makeRouteTree(t.l, routes, true)
if err != nil {
return err
@@ -282,14 +267,14 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
oldDefaultMTU := t.DefaultMTU
oldMaxMTU := t.MaxMTU
newDefaultMTU := getMTU(t.l, c)
newDefaultMTU := c.GetInt("tun.mtu", DefaultMTU)
newMaxMTU := newDefaultMTU
for i, r := range routes {
if r.MTU == 0 {
routes[i].MTU = newDefaultMTU
}
if r.MTU > newMaxMTU {
if r.MTU > t.MaxMTU {
newMaxMTU = r.MTU
}
}
@@ -303,7 +288,7 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
if !initial {
if oldMaxMTU != newMaxMTU {
t.setMTU(r)
t.setMTU()
t.l.Info("Set max MTU", "mtu", t.MaxMTU, "oldMTU", oldMaxMTU)
}
@@ -311,8 +296,7 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
for i := range t.vpnNetworks {
err := t.setDefaultRoute(t.vpnNetworks[i])
if err != nil {
t.l.Error(err.Error())
r.Failed()
t.l.Warn(err.Error())
} else {
t.l.Info("Set default MTU", "mtu", t.DefaultMTU, "oldMTU", oldDefaultMTU)
}
@@ -320,14 +304,13 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
}
// Remove first, if the system removes a wanted route hopefully it will be re-added next
t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
// Ensure any routes we actually want are installed
err = t.addRoutes(true, r)
err = t.addRoutes(true)
if err != nil {
// This should never be called since addRoutes should log its own errors in a reload condition
util.LogWithContextIfNeeded("Failed to refresh routes", err, t.l)
r.Failed()
}
}
@@ -482,7 +465,7 @@ func (t *tun) Activate() error {
t.deviceIndex = link.Attrs().Index
// Setup our default MTU
t.setMTU(nil)
t.setMTU()
// Set the transmit queue length
ifrq := ifreqQLEN{Name: devName, Value: int32(t.TXQueueLen)}
@@ -514,7 +497,7 @@ func (t *tun) Activate() error {
}
// Set the routes
if err = t.addRoutes(false, nil); err != nil {
if err = t.addRoutes(false); err != nil {
return err
}
@@ -527,13 +510,12 @@ func (t *tun) Activate() error {
return nil
}
func (t *tun) setMTU(r *config.Reload) {
func (t *tun) setMTU() {
// Set the MTU on the device
ifm := ifreqMTU{Name: t.deviceBytes(), MTU: int32(t.MaxMTU)}
if err := ioctl(t.ioctlFd, unix.SIOCSIFMTU, uintptr(unsafe.Pointer(&ifm))); err != nil {
// This is currently a non fatal condition because the route table must have the MTU set appropriately as well
t.l.Error("Failed to set tun mtu", "error", err)
r.Failed()
}
}
@@ -586,7 +568,7 @@ func (t *tun) setDefaultRoute(cidr netip.Prefix) error {
return nil
}
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
func (t *tun) addRoutes(logErrors bool) error {
// Path routes
routes := *t.Routes.Load()
for _, r := range routes {
@@ -616,7 +598,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
if logErrors {
retErr.Log(t.l)
rl.Failed()
} else {
return retErr
}
@@ -628,7 +609,7 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
return nil
}
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) {
func (t *tun) removeRoutes(routes []Route) {
for _, r := range routes {
if !r.Install {
continue
@@ -652,12 +633,8 @@ func (t *tun) removeRoutes(routes []Route, rl *config.Reload) {
}
err := netlink.RouteDel(&nr)
if errors.Is(err, unix.ESRCH) {
// Already gone, which is what we wanted
t.l.Info("Route was already removed", "route", r)
} else if err != nil {
if err != nil {
t.l.Error("Failed to remove route", "error", err, "route", r)
rl.Failed()
} else {
t.l.Info("Removed route", "route", r)
}
+27 -27
View File
@@ -8,6 +8,7 @@ import (
"log/slog"
"net/netip"
"os"
"regexp"
"sync/atomic"
"syscall"
"unsafe"
@@ -66,12 +67,24 @@ type tun struct {
fd int
}
var deviceNameRE = regexp.MustCompile(`^tun[0-9]+$`)
func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
return nil, fmt.Errorf("newTunFromFd not supported in NetBSD")
}
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
fd, deviceName, err := openTun(l, c.GetString("tun.dev", ""))
// Try to open tun device
var err error
deviceName := c.GetString("tun.dev", "")
if deviceName == "" {
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
}
if !deviceNameRE.MatchString(deviceName) {
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
}
fd, err := unix.Open("/dev/"+deviceName, os.O_RDWR, 0)
if err != nil {
return nil, err
}
@@ -86,24 +99,19 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
fd: fd,
Device: deviceName,
vpnNetworks: vpnNetworks,
MTU: getMTU(l, c),
MTU: c.GetInt("tun.mtu", DefaultMTU),
l: l,
}
err = t.reload(c, true, nil)
err = t.reload(c, true)
if err != nil {
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.mtu")
if tunDevNeedsRestart(c.GetString("tun.dev", ""), t.Device) {
r.RestartRequiredIfChanged("tun.dev")
}
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
@@ -316,7 +324,7 @@ func (t *tun) Activate() error {
}
}
return t.addRoutes(false, nil)
return t.addRoutes(false)
}
func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
@@ -331,8 +339,8 @@ func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
return err
}
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
func (t *tun) reload(c *config.C, initial bool) error {
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
if err != nil {
return err
}
@@ -352,18 +360,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
if !initial {
// Remove first, if the system removes a wanted route hopefully it will be re-added next
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
if err != nil {
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
r.Failed()
}
// Ensure any routes we actually want are installed
err = t.addRoutes(true, r)
err = t.addRoutes(true)
if err != nil {
// Catch any stray logs
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
r.Failed()
}
}
@@ -387,7 +393,7 @@ func (t *tun) Queues(int) ([]tio.Queue, error) {
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
}
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
func (t *tun) addRoutes(logErrors bool) error {
routes := *t.Routes.Load()
for _, r := range routes {
@@ -401,7 +407,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
if logErrors {
retErr.Log(t.l)
rl.Failed()
} else {
return retErr
}
@@ -413,20 +418,15 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
return nil
}
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
func (t *tun) removeRoutes(routes []Route) error {
for _, r := range routes {
if len(r.Via) == 0 || !r.Install {
// addRoutes never installs these
if !r.Install {
continue
}
err := delRoute(r.Cidr, t.vpnNetworks)
if errors.Is(err, unix.ESRCH) {
// Already gone, which is what we wanted
t.l.Info("Route was already removed", "route", r)
} else if err != nil {
if err != nil {
t.l.Error("Failed to remove route", "error", err, "route", r)
rl.Failed()
} else {
t.l.Info("Removed route", "route", r)
}
+27 -27
View File
@@ -8,6 +8,7 @@ import (
"log/slog"
"net/netip"
"os"
"regexp"
"sync/atomic"
"syscall"
"unsafe"
@@ -57,12 +58,24 @@ type tun struct {
fd int
}
var deviceNameRE = regexp.MustCompile(`^tun[0-9]+$`)
func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
return nil, fmt.Errorf("newTunFromFd not supported in openbsd")
}
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
fd, deviceName, err := openTun(l, c.GetString("tun.dev", ""))
// Try to open tun device
var err error
deviceName := c.GetString("tun.dev", "")
if deviceName == "" {
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
}
if !deviceNameRE.MatchString(deviceName) {
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
}
fd, err := unix.Open("/dev/"+deviceName, os.O_RDWR, 0)
if err != nil {
return nil, err
}
@@ -77,24 +90,19 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
fd: fd,
Device: deviceName,
vpnNetworks: vpnNetworks,
MTU: getMTU(l, c),
MTU: c.GetInt("tun.mtu", DefaultMTU),
l: l,
}
err = t.reload(c, true, nil)
err = t.reload(c, true)
if err != nil {
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.mtu")
if tunDevNeedsRestart(c.GetString("tun.dev", ""), t.Device) {
r.RestartRequiredIfChanged("tun.dev")
}
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
@@ -295,7 +303,7 @@ func (t *tun) Activate() error {
}
}
return t.addRoutes(false, nil)
return t.addRoutes(false)
}
func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
@@ -310,8 +318,8 @@ func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
return err
}
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
func (t *tun) reload(c *config.C, initial bool) error {
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
if err != nil {
return err
}
@@ -331,18 +339,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
if !initial {
// Remove first, if the system removes a wanted route hopefully it will be re-added next
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
if err != nil {
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
r.Failed()
}
// Ensure any routes we actually want are installed
err = t.addRoutes(true, r)
err = t.addRoutes(true)
if err != nil {
// Catch any stray logs
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
r.Failed()
}
}
@@ -366,7 +372,7 @@ func (t *tun) Queues(int) ([]tio.Queue, error) {
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
}
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
func (t *tun) addRoutes(logErrors bool) error {
routes := *t.Routes.Load()
for _, r := range routes {
@@ -380,7 +386,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
if logErrors {
retErr.Log(t.l)
rl.Failed()
} else {
return retErr
}
@@ -392,20 +397,15 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
return nil
}
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
func (t *tun) removeRoutes(routes []Route) error {
for _, r := range routes {
if len(r.Via) == 0 || !r.Install {
// addRoutes never installs these
if !r.Install {
continue
}
err := delRoute(r.Cidr, t.vpnNetworks)
if errors.Is(err, unix.ESRCH) {
// Already gone, which is what we wanted
t.l.Info("Route was already removed", "route", r)
} else if err != nil {
if err != nil {
t.l.Error("Failed to remove route", "error", err, "route", r)
rl.Failed()
} else {
t.l.Info("Removed route", "route", r)
}
-107
View File
@@ -1,107 +0,0 @@
//go:build !e2e_testing
package overlay
import (
"net/netip"
"os"
"testing"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/routing"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// Only tun.mtu changes. The system calls fail without a real device, what matters is the routes nebula keeps
func TestReloadMTUOnlyKeepsRoutes(t *testing.T) {
routes := " unsafe_routes:\n - route: 192.168.100.0/24\n via: 10.1.0.1\n"
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString("tun:\n mtu: 1300\n"+routes))
tn := &tun{
l: test.NewLogger(),
vpnNetworks: []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")},
ioctlFd: ^uintptr(0),
routesFromSystem: map[netip.Prefix]routing.Gateways{},
}
require.NoError(t, tn.reload(c, true, nil))
require.NoError(t, c.ReloadConfigString("tun:\n mtu: 1400\n"+routes).Err)
_ = tn.reload(c, false, nil)
got := *tn.Routes.Load()
require.Len(t, got, 1)
assert.Equal(t, netip.MustParsePrefix("192.168.100.0/24"), got[0].Cidr)
assert.Equal(t, 1400, got[0].MTU)
assert.Equal(t, 1400, tn.DefaultMTU)
}
// The device mtu has to fit the largest route mtu, wherever it sits in the list
func TestReloadMaxMTUIsTheLargestRoute(t *testing.T) {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString("tun:\n mtu: 1300\n unsafe_routes:\n"+
" - route: 192.168.100.0/24\n via: 10.1.0.1\n mtu: 1500\n"+
" - route: 192.168.101.0/24\n via: 10.1.0.1\n mtu: 1400\n"))
tn := &tun{
l: test.NewLogger(),
vpnNetworks: []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")},
ioctlFd: ^uintptr(0),
routesFromSystem: map[netip.Prefix]routing.Gateways{},
}
require.NoError(t, tn.reload(c, true, nil))
assert.Equal(t, 1500, tn.MaxMTU)
assert.Equal(t, 1300, tn.DefaultMTU)
}
// There is no device behind this tun, so adding a route always fails. Removing one is refused without root, as root the
// kernel answers that the route isn't there, which is what we wanted
func TestReloadRouteFailures(t *testing.T) {
route := "tun:\n mtu: 1300\n unsafe_routes:\n - route: 192.168.100.0/24\n via: 10.1.0.1\n"
cases := []struct {
name string
from, to string
wantFails bool
}{
{"added", "tun:\n mtu: 1300\n", route, true},
{"removed", route, "tun:\n mtu: 1300\n", os.Geteuid() != 0},
{"unchanged", route, route + "punchy:\n punch: true\n", false},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString(tc.from))
tn := &tun{
l: test.NewLogger(),
vpnNetworks: []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")},
ioctlFd: ^uintptr(0),
routesFromSystem: map[netip.Prefix]routing.Gateways{},
}
require.NoError(t, tn.reload(c, true, nil))
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
require.NoError(t, tn.reload(c, false, r))
})
res := c.ReloadConfigString(tc.to)
require.NoError(t, res.Err)
assert.Equal(t, tc.wantFails, res.Failed)
})
}
}
// Keys only read when the device is created need a restart to apply
func TestTunReloadRestartKeys(t *testing.T) {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString("tun:\n dev: nebrk0\n"))
tn, err := NewDeviceFromConfig(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, 1)
if err != nil {
t.Skipf("can't create a tun device here: %v", err)
}
t.Cleanup(func() { _ = tn.Close() })
res := c.ReloadConfigString("tun:\n disabled: true\n dev: nebrk1\n tx_queue: 100\n")
require.NoError(t, res.Err)
assert.ElementsMatch(t, []string{"tun.disabled", "tun.dev", "tun.tx_queue"}, res.RestartKeys)
}
-24
View File
@@ -1,24 +0,0 @@
package overlay
import (
"net/netip"
"testing"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// tun.disabled and the disabled tun's settings are only read when the device is made
func TestDisabledTunRestartKeys(t *testing.T) {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString("tun:\n disabled: true\n"))
d, err := NewDeviceFromConfig(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, 1)
require.NoError(t, err)
t.Cleanup(func() { _ = d.Close() })
res := c.ReloadConfigString("tun:\n disabled: false\n tx_queue: 100\n")
require.NoError(t, res.Err)
assert.ElementsMatch(t, []string{"tun.disabled", "tun.tx_queue"}, res.RestartKeys)
}
+1 -1
View File
@@ -31,7 +31,7 @@ type TestTun struct {
}
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*TestTun, error) {
_, routes, err := getAllRoutesFromConfig(l, c, vpnNetworks, true)
_, routes, err := getAllRoutesFromConfig(c, vpnNetworks, true)
if err != nil {
return nil, err
}
+14 -106
View File
@@ -4,7 +4,6 @@ package overlay
import (
"crypto"
"errors"
"fmt"
"log/slog"
"net/netip"
@@ -76,7 +75,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*w
t := &winTun{
Device: deviceName,
vpnNetworks: vpnNetworks,
MTU: getMTU(l, c),
MTU: c.GetInt("tun.mtu", DefaultMTU),
guid: *guid,
networkCategory: cat,
setCategory: setCat,
@@ -84,7 +83,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*w
l: l,
}
err = t.reload(c, true, nil)
err = t.reload(c, true)
if err != nil {
return nil, err
}
@@ -105,32 +104,18 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*w
}
t.tun = tunDevice.(*wintun.NativeTun)
// Disable registration before Activate assigns addresses and triggers it.
disableDNSRegistration(l, *guid)
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.dev", "tun.mtu")
// Compare with the running category, not the last config. A restart with one we can't parse would fail, so say
// that now rather than ask for one, and going back to the running one after a bad reload needs no restart
if cat, setCat, err := parseNetworkCategory(c.GetString("tun.network_category", "private")); err != nil {
t.l.Error("Invalid tun.network_category, a restart with it would fail", "error", err)
r.Failed()
} else if cat != t.networkCategory || setCat != t.setCategory {
r.RestartRequiredIfChanged("tun.network_category")
}
r.RestartRequiredIfChanged(interfaceBypassKeys...)
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
return t, nil
}
func (t *winTun) reload(c *config.C, initial bool, r *config.Reload) error {
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
func (t *winTun) reload(c *config.C, initial bool) error {
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
if err != nil {
return err
}
@@ -150,18 +135,16 @@ func (t *winTun) reload(c *config.C, initial bool, r *config.Reload) error {
if !initial {
// Remove first, if the system removes a wanted route hopefully it will be re-added next
err := t.removeRoutes(findRemovedSystemRoutes(routes, *oldRoutes), r)
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
if err != nil {
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
r.Failed()
}
// Ensure any routes we actually want are installed
err = t.addRoutes(true, r)
err = t.addRoutes(true)
if err != nil {
// Catch any stray logs
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
r.Failed()
}
}
@@ -176,7 +159,7 @@ func (t *winTun) Activate() error {
return fmt.Errorf("failed to set address: %w", err)
}
err = t.addRoutes(false, nil)
err = t.addRoutes(false)
if err != nil {
return err
}
@@ -195,49 +178,33 @@ func (t *winTun) Activate() error {
return nil
}
func (t *winTun) addRoutes(logErrors bool, rl *config.Reload) error {
func (t *winTun) addRoutes(logErrors bool) error {
luid := winipcfg.LUID(t.tun.LUID())
routes := *t.Routes.Load()
foundDefault4 := false
carriesV6 := slices.ContainsFunc(t.vpnNetworks, func(p netip.Prefix) bool { return p.Addr().Is6() })
// A CIDR listed twice routes by its last entry, install only that one or each reload would flip between them. The
// same rule as systemRoutes
last := make(map[netip.Prefix]int, len(routes))
for i, r := range routes {
last[r.Cidr] = i
}
for i, r := range routes {
for _, r := range routes {
if len(r.Via) == 0 || !r.Install {
// We don't allow route MTUs so only install routes with a via
continue
}
if last[r.Cidr] != i {
continue
}
// A v6 unsafe_route is legal under a v4-only cert; uninstalled ones put nothing on the adapter.
carriesV6 = carriesV6 || r.Cidr.Addr().Is6()
// Add our unsafe route as an on-link route to the nebula tun device.
result, err := addRoute(luid, r)
err := luid.AddRoute(r.Cidr, unspecifiedNextHop(r.Cidr), uint32(r.Metric))
if err != nil {
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
if logErrors {
retErr.Log(t.l)
rl.Failed()
continue
} else {
return retErr
}
} else {
switch result {
case routeAdded:
t.l.Info("Added route", "route", r)
case routeMetricUpdated:
t.l.Info("Updated route metric", "route", r)
}
}
if !foundDefault4 {
@@ -288,7 +255,7 @@ func (t *winTun) setMTU(luid winipcfg.LUID, foundDefault4, carriesV6 bool) error
return nil
}
func (t *winTun) removeRoutes(routes []Route, rl *config.Reload) error {
func (t *winTun) removeRoutes(routes []Route) error {
luid := winipcfg.LUID(t.tun.LUID())
for _, r := range routes {
@@ -298,12 +265,8 @@ func (t *winTun) removeRoutes(routes []Route, rl *config.Reload) error {
// See comment on luid.AddRoute
err := luid.DeleteRoute(r.Cidr, unspecifiedNextHop(r.Cidr))
if errors.Is(err, windows.ERROR_NOT_FOUND) {
// Already gone, which is what we wanted
t.l.Info("Route was already removed", "route", r)
} else if err != nil {
if err != nil {
t.l.Error("Failed to remove route", "error", err, "route", r)
rl.Failed()
} else {
t.l.Info("Removed route", "route", r)
}
@@ -353,61 +316,6 @@ func (t *winTun) Close() error {
return t.tun.Close()
}
// systemRoutes maps each CIDR to the route that puts it in the system table. A CIDR's last entry decides, including
// one that says not to install it
func systemRoutes(routes []Route) map[netip.Prefix]Route {
out := make(map[netip.Prefix]Route, len(routes))
for _, r := range routes {
if len(r.Via) > 0 && r.Install {
out[r.Cidr] = r
} else {
delete(out, r.Cidr)
}
}
return out
}
// findRemovedSystemRoutes is the routes to delete from the system table. Windows deletes by destination and next hop,
// so only a CIDR nothing installs anymore goes, a changed metric is set on the route in place by addRoute
func findRemovedSystemRoutes(newRoutes, oldRoutes []Route) []Route {
keep := systemRoutes(newRoutes)
var removed []Route
for _, r := range systemRoutes(oldRoutes) {
if _, ok := keep[r.Cidr]; !ok {
removed = append(removed, r)
}
}
return removed
}
type routeResult int
const (
routeAdded routeResult = iota
routeMetricUpdated
routeAlreadyInstalled
)
// addRoute installs r on the interface. A reload re-adds every route to catch any the system dropped, and Windows
// refuses one it has with the same destination and next hop whatever its metric. One that is there with another
// metric, ours from before a metric change or someone else's, is brought to ours in place
func addRoute(luid winipcfg.LUID, r Route) (routeResult, error) {
nextHop := unspecifiedNextHop(r.Cidr)
err := luid.AddRoute(r.Cidr, nextHop, uint32(r.Metric))
if !errors.Is(err, windows.ERROR_OBJECT_ALREADY_EXISTS) {
return routeAdded, err
}
row, err := luid.Route(r.Cidr, nextHop)
if err != nil {
return routeAlreadyInstalled, err
}
if row.Metric != uint32(r.Metric) {
row.Metric = uint32(r.Metric)
return routeMetricUpdated, row.Set()
}
return routeAlreadyInstalled, nil
}
func unspecifiedNextHop(p netip.Prefix) netip.Addr {
if p.Addr().Is4() {
return netip.IPv4Unspecified()
-209
View File
@@ -1,209 +0,0 @@
//go:build windows && !e2e_testing
package overlay
import (
"bytes"
"fmt"
"net/netip"
"strings"
"testing"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"golang.org/x/sys/windows"
"golang.zx2c4.com/wireguard/windows/tunnel/winipcfg"
)
type routeTest struct {
c *config.C
tun *winTun
luid winipcfg.LUID
log *bytes.Buffer
}
// newRouteTest makes a wintun device of its own, before installing tun.unsafe_routes from cfg
func newRouteTest(t *testing.T, cfg string) *routeTest {
t.Helper()
if !windows.GetCurrentProcessToken().IsElevated() {
t.Skip("creating a wintun device needs an elevated process")
}
if err := checkWinTunExists(); err != nil {
t.Skipf("wintun.dll is not where nebula looks for it: %v", err)
}
rt := &routeTest{log: &bytes.Buffer{}}
l := test.NewLoggerWithOutput(rt.log)
rt.c = config.NewC(l)
require.NoError(t, rt.c.LoadString(cfg))
var err error
rt.tun, err = newTun(rt.c, l, []netip.Prefix{netip.MustParsePrefix("10.250.0.1/24")}, false)
require.NoError(t, err)
t.Cleanup(func() { _ = rt.tun.Close() })
rt.luid = winipcfg.LUID(rt.tun.tun.LUID())
return rt
}
func (rt *routeTest) metric(t *testing.T, cidr string) uint32 {
t.Helper()
p := netip.MustParsePrefix(cidr)
row, err := rt.luid.Route(p, unspecifiedNextHop(p))
require.NoError(t, err)
return row.Metric
}
// reload applies cfg and expects nothing in it to fail
func (rt *routeTest) reload(t *testing.T, cfg string) {
t.Helper()
res := rt.c.ReloadConfigString(cfg)
require.NoError(t, res.Err)
assert.False(t, res.Failed, "the reload reported a failure")
}
func unsafeRoutes(routes ...string) string {
var b strings.Builder
b.WriteString("tun:\n dev: nebroutetest\n unsafe_routes:\n")
// cidr[@metric][!], the ! for install: false
for _, r := range routes {
r, noInstall := strings.CutSuffix(r, "!")
cidr, metric, _ := strings.Cut(r, "@")
fmt.Fprintf(&b, " - route: %s\n via: 10.250.0.2\n", cidr)
if metric != "" {
fmt.Fprintf(&b, " metric: %s\n", metric)
}
if noInstall {
b.WriteString(" install: false\n")
}
}
return b.String()
}
// A reload that adds a route re-adds the ones already installed, Windows refusing those as already there isn't a failure
func TestWinTun_ReloadKeepsInstalledRoutes(t *testing.T) {
forFamilies(t, func(t *testing.T, a, b string) {
rt := newRouteTest(t, unsafeRoutes(a))
require.NoError(t, rt.tun.Activate())
rt.reload(t, unsafeRoutes(a, b))
assert.NotContains(t, rt.log.String(), "Failed to add route")
rt.metric(t, a)
rt.metric(t, b)
})
}
// Windows calls a route the same by destination and next hop, so a changed metric is set on the installed route in
// place rather than deleted and added, which would leave a moment with no route
func TestWinTun_ReloadMetricChangeApplies(t *testing.T) {
forFamilies(t, func(t *testing.T, a, b string) {
rt := newRouteTest(t, unsafeRoutes(a+"@100"))
require.NoError(t, rt.tun.Activate())
require.Equal(t, uint32(100), rt.metric(t, a))
rt.reload(t, unsafeRoutes(a+"@200"))
assert.NotContains(t, rt.log.String(), "Failed to add route")
assert.NotContains(t, rt.log.String(), "Removed route")
assert.Equal(t, uint32(200), rt.metric(t, a))
})
}
// A route someone else put on the device with another metric is brought to ours, at startup too
func TestWinTun_ForeignRouteGetsOurMetric(t *testing.T) {
forFamilies(t, func(t *testing.T, a, b string) {
rt := newRouteTest(t, unsafeRoutes(a+"@100"))
p := netip.MustParsePrefix(a)
require.NoError(t, rt.luid.AddRoute(p, unspecifiedNextHop(p), 50))
require.NoError(t, rt.tun.Activate())
assert.Equal(t, uint32(100), rt.metric(t, a))
assert.Contains(t, rt.log.String(), "level=INFO msg=\"Updated route metric\"")
})
}
// A CIDR listed twice is installed once, by its last entry, and reloads leave it there instead of flipping between the
// two metrics
func TestWinTun_DuplicateCidrInstallsTheLastEntry(t *testing.T) {
forFamilies(t, func(t *testing.T, a, b string) {
rt := newRouteTest(t, unsafeRoutes(a+"@100", a+"@200"))
require.NoError(t, rt.tun.Activate())
assert.Equal(t, uint32(200), rt.metric(t, a))
rt.reload(t, unsafeRoutes(a+"@100", a+"@200", b))
assert.Equal(t, uint32(200), rt.metric(t, a))
assert.NotContains(t, rt.log.String(), "Updated route metric")
assert.NotContains(t, rt.log.String(), "Failed to add route")
})
}
// Dropping the duplicate that wasn't installed leaves the installed route alone. Windows deletes by destination and
// next hop, deleting the dropped one would take the live route with it
func TestWinTun_DroppingAnUninstalledDuplicateKeepsTheRoute(t *testing.T) {
forFamilies(t, func(t *testing.T, a, b string) {
rt := newRouteTest(t, unsafeRoutes(a+"@100", a+"@200"))
require.NoError(t, rt.tun.Activate())
rt.reload(t, unsafeRoutes(a+"@200"))
assert.NotContains(t, rt.log.String(), "Removed route")
assert.Equal(t, uint32(200), rt.metric(t, a))
})
}
// A reload ends where a fresh start with the same config would, a CIDR whose last entry says not to install it is
// removed
func TestWinTun_ReloadMatchesAFreshStart(t *testing.T) {
forFamilies(t, func(t *testing.T, a, b string) {
cidr := netip.MustParsePrefix(a)
routes := unsafeRoutes(a+"@100", a+"@100!")
fresh := newRouteTest(t, routes)
require.NoError(t, fresh.tun.Activate())
_, err := fresh.luid.Route(cidr, unspecifiedNextHop(cidr))
require.Error(t, err, "a fresh start installed it")
require.NoError(t, fresh.tun.Close())
rt := newRouteTest(t, unsafeRoutes(a+"@100"))
require.NoError(t, rt.tun.Activate())
rt.reload(t, routes)
_, err = rt.luid.Route(cidr, unspecifiedNextHop(cidr))
assert.Error(t, err, "the reload left it installed")
})
}
// Removing a route that is already gone is what we wanted, not a failure
func TestWinTun_ReloadRouteAlreadyGone(t *testing.T) {
forFamilies(t, func(t *testing.T, a, b string) {
rt := newRouteTest(t, unsafeRoutes(a, b))
require.NoError(t, rt.tun.Activate())
p := netip.MustParsePrefix(b)
require.NoError(t, rt.luid.DeleteRoute(p, unspecifiedNextHop(p)))
rt.reload(t, unsafeRoutes(a))
})
}
// A network category we can't parse would fail the restart, so it fails the reload instead of asking for one
func TestWinTun_ReloadInvalidNetworkCategoryFails(t *testing.T) {
rt := newRouteTest(t, unsafeRoutes())
for range 2 {
res := rt.c.ReloadConfigString(unsafeRoutes() + " network_category: nope\n")
require.NoError(t, res.Err)
assert.True(t, res.Failed, "a bad category that didn't change since the last reload is still bad")
assert.False(t, res.RestartRequired)
}
// Fixing it back to the running category needs nothing
res := rt.c.ReloadConfigString(unsafeRoutes() + " network_category: private\n")
require.NoError(t, res.Err)
assert.False(t, res.Failed)
assert.False(t, res.RestartRequired)
res = rt.c.ReloadConfigString(unsafeRoutes() + " network_category: public\n")
require.NoError(t, res.Err)
assert.Equal(t, []string{"tun.network_category"}, res.RestartKeys)
}
// forFamilies runs f with two unsafe_routes CIDRs of each address family, the tun's own network stays IPv4
func forFamilies(t *testing.T, f func(t *testing.T, a, b string)) {
t.Run("ipv4", func(t *testing.T) { f(t, "10.251.1.0/24", "10.251.2.0/24") })
t.Run("ipv6", func(t *testing.T) { f(t, "fd00:251:1::/64", "fd00:251:2::/64") })
}
+18 -70
View File
@@ -2,9 +2,7 @@ package nebula
import (
"crypto/fips140"
"crypto/sha256"
"encoding/binary"
"encoding/hex"
"encoding/json"
"errors"
"fmt"
@@ -52,30 +50,15 @@ type CertState struct {
myVpnBroadcastAddrsTable *bart.Lite
}
// errCertNeedsRestart marks a new cert that is refused on reload because only a restart can apply it
var errCertNeedsRestart = errors.New("a restart is required to use the new cert")
func NewPKIFromConfig(l *slog.Logger, c *config.C) (*PKI, error) {
pki := &PKI{l: l}
err := pki.reload(c, true, nil)
err := pki.reload(c, true)
if err != nil {
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
// Compare with the running cipher, not the last config. A restart with one we can't run would fail, so say that
// now rather than ask for one, and going back to the running one after a bad reload needs no restart
if cipher := c.GetString("cipher", "aes"); !validCipher(cipher) {
l.Error("Unknown cipher, a restart with it would fail", "cipher", cipher)
r.Failed()
} else if cipher == "chachapoly" && fipsOnly() {
// newCipherSuite refuses it at startup
l.Error("ChaChaPoly is not allowed in FIPS 140-only mode, a restart with it would fail", "cipher", cipher)
r.Failed()
} else if cipher != pki.getCertState().cipher {
r.RestartRequiredIfChanged("cipher")
}
rErr := pki.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
rErr := pki.reload(c, false)
if rErr != nil {
util.LogWithContextIfNeeded("Failed to reload PKI from config", rErr, l)
}
@@ -92,29 +75,13 @@ func (p *PKI) getCertState() *CertState {
return p.cs.Load()
}
// r is nil on the initial load
func (p *PKI) reload(c *config.C, initial bool, r *config.Reload) error {
before := p.cs.Load()
func (p *PKI) reload(c *config.C, initial bool) error {
err := p.reloadCerts(c, initial)
if err != nil {
if initial {
return err
}
err.Log(p.l)
if errors.Is(err, errCertNeedsRestart) {
r.RestartRequired()
} else {
r.Failed()
}
} else if !initial {
// A cert for a version we weren't running is accepted without comparing its networks to ours. The tun and the
// lighthouse keep the networks they started with
after := p.cs.Load()
if !slices.Equal(before.myVpnNetworks, after.myVpnNetworks) {
p.l.Warn("The new cert changes our networks, a restart is required to use them",
"old_networks", before.myVpnNetworks, "new_networks", after.myVpnNetworks)
r.RestartRequired()
}
}
err = p.reloadCAPool(c)
@@ -123,27 +90,21 @@ func (p *PKI) reload(c *config.C, initial bool, r *config.Reload) error {
return err
}
err.Log(p.l)
r.Failed()
}
return nil
}
// fipsOnly is fips140.Enforced, a variable so a test can run the FIPS 140-only reload check without GODEBUG
var fipsOnly = fips140.Enforced
// validCipher is true for the ciphers nebula can run. Each post-handshake CipherState in noiseutil hardcodes its own
// nonce endianness, so there's nothing to set up for either.
func validCipher(cipher string) bool {
return cipher == "aes" || cipher == "chachapoly"
}
func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
var cipher string
var currentState *CertState
if initial {
cipher = c.GetString("cipher", "aes")
if !validCipher(cipher) {
switch cipher {
case "aes", "chachapoly":
// Each post-handshake CipherState in noiseutil hardcodes its own
// nonce endianness now, so there's nothing to set up here.
default:
return util.NewContextualError(
"unknown cipher",
m{"cipher": cipher},
@@ -171,7 +132,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
return util.NewContextualError(
"Networks in new cert was different from old",
m{"new_networks": newState.v1Cert.Networks(), "old_networks": currentState.v1Cert.Networks(), "cert_version": cert.Version1},
errCertNeedsRestart,
nil,
)
}
@@ -179,7 +140,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
return util.NewContextualError(
"Curve in new v1 cert was different from old",
m{"new_curve": newState.v1Cert.Curve(), "old_curve": currentState.v1Cert.Curve(), "cert_version": cert.Version1},
errCertNeedsRestart,
nil,
)
}
}
@@ -194,7 +155,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
return util.NewContextualError(
"Networks in new cert was different from old",
m{"new_networks": newState.v2Cert.Networks(), "old_networks": currentState.v2Cert.Networks(), "cert_version": cert.Version2},
errCertNeedsRestart,
nil,
)
}
@@ -202,7 +163,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
return util.NewContextualError(
"Curve in new cert was different from old",
m{"new_curve": newState.v2Cert.Curve(), "old_curve": currentState.v2Cert.Curve(), "cert_version": cert.Version2},
errCertNeedsRestart,
nil,
)
}
}
@@ -217,7 +178,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
return util.NewContextualError(
"Removing a V2 cert is not permitted unless it has identical networks to the new V1 cert",
m{"new_v1_networks": newState.v1Cert.Networks(), "old_v2_networks": currentState.v2Cert.Networks()},
errCertNeedsRestart,
nil,
)
}
}
@@ -235,14 +196,12 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
func (p *PKI) reloadCAPool(c *config.C) *util.ContextualError {
caPool, err := loadCAPoolFromConfig(p.l, c)
if caPool != nil {
p.caPool.Store(caPool)
p.l.Debug("Trusted CA fingerprints", "fingerprints", caPool.GetFingerprints())
}
if err != nil {
return util.NewContextualError("Failed to load ca from config", nil, err)
}
p.caPool.Store(caPool)
p.l.Debug("Trusted CA fingerprints", "fingerprints", caPool.GetFingerprints())
return nil
}
@@ -617,22 +576,11 @@ func loadCAPoolFromConfig(l *slog.Logger, c *config.C) (*cert.CAPool, error) {
bl := c.GetStringSlice("pki.blocklist", []string{})
if len(bl) > 0 {
var bad []string
for i, raw := range bl {
// Fingerprints are compared as lowercase hex strings, a malformed entry would silently block nothing
fp := strings.ToLower(strings.TrimSpace(raw))
if b, err := hex.DecodeString(fp); err != nil || len(b) != sha256.Size {
bad = append(bad, fmt.Sprintf("entry %d %q", i+1, raw))
continue
}
for _, fp := range bl {
caPool.BlocklistFingerprint(fp)
}
l.Info("Blocklisted certificates", "fingerprintCount", len(bl)-len(bad))
if len(bad) > 0 {
// The valid entries are still returned so a failed reload blocks them, startup refuses the error
return caPool, fmt.Errorf("pki.blocklist entries are not hex certificate fingerprints: %s", strings.Join(bad, ", "))
}
l.Info("Blocklisted certificates", "fingerprintCount", len(bl))
}
return caPool, nil
-168
View File
@@ -1,17 +1,10 @@
package nebula
import (
"crypto/fips140"
"fmt"
"net/netip"
"strings"
"testing"
"time"
"github.com/slackhq/nebula/cert"
"github.com/slackhq/nebula/cert_test"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
@@ -99,164 +92,3 @@ func TestNewCipherSuiteUnsupportedCurve(t *testing.T) {
assert.True(t, strings.HasPrefix(err.Error(), "unsupported curve:"), "got: %v", err)
assert.Nil(t, cs)
}
func TestPKIReloadRestartRequired(t *testing.T) {
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
pkiConfig := func(cipher, network string) string {
_, _, keyPEM, certPEM := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix(network)}, nil, nil)
return fmt.Sprintf("cipher: %s\npki:\n ca: %q\n cert: %q\n key: %q\n", cipher, caPEM, certPEM, keyPEM)
}
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString(pkiConfig("aes", "10.1.0.2/24")))
p, err := NewPKIFromConfig(test.NewLogger(), c)
require.NoError(t, err)
// A cert that changes our networks is refused and needs a restart, it is not a failure
res := c.ReloadConfigString(pkiConfig("aes", "10.1.0.3/24"))
require.NoError(t, res.Err)
assert.True(t, res.RestartRequired)
assert.False(t, res.Failed)
assert.Equal(t, []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, p.getCertState().myVpnNetworks)
// The cipher only applies at startup
c2 := config.NewC(test.NewLogger())
require.NoError(t, c2.LoadString(pkiConfig("aes", "10.1.0.2/24")))
p, err = NewPKIFromConfig(test.NewLogger(), c2)
require.NoError(t, err)
res = c2.ReloadConfigString(pkiConfig("chachapoly", "10.1.0.2/24"))
require.NoError(t, res.Err)
assert.True(t, res.RestartRequired)
assert.Equal(t, "aes", p.getCertState().cipher)
// A cipher we can't run would fail the restart, so it fails the reload instead of asking for one
c4 := config.NewC(test.NewLogger())
require.NoError(t, c4.LoadString(pkiConfig("aes", "10.1.0.2/24")))
_, err = NewPKIFromConfig(test.NewLogger(), c4)
require.NoError(t, err)
for range 2 {
res = c4.ReloadConfigString(pkiConfig("nope", "10.1.0.2/24"))
require.NoError(t, res.Err)
assert.True(t, res.Failed, "a bad cipher that didn't change since the last reload is still bad")
assert.False(t, res.RestartRequired)
}
// Fixing it back to the running cipher needs nothing
res = c4.ReloadConfigString(pkiConfig("aes", "10.1.0.2/24"))
require.NoError(t, res.Err)
assert.False(t, res.Failed)
assert.False(t, res.RestartRequired)
// A cert that keeps our networks applies without a restart
c3 := config.NewC(test.NewLogger())
require.NoError(t, c3.LoadString(pkiConfig("aes", "10.1.0.2/24")))
_, err = NewPKIFromConfig(test.NewLogger(), c3)
require.NoError(t, err)
res = c3.ReloadConfigString(pkiConfig("aes", "10.1.0.2/24"))
require.NoError(t, res.Err)
assert.False(t, res.RestartRequired)
// A cert that can't be read is a failure, and a restart wouldn't help
res = c3.ReloadConfigString(strings.Replace(pkiConfig("aes", "10.1.0.2/24"), "cert: \"", "cert: \"garbage", 1))
require.NoError(t, res.Err)
assert.True(t, res.Failed)
assert.False(t, res.RestartRequired)
}
// A cert for a version we weren't running is accepted without comparing networks, so switching to one with different
// networks needs a restart. One with the same networks doesn't
func TestPKIReloadNewVersionWithOtherNetworks(t *testing.T) {
ca1, _, ca1Key, ca1PEM := cert_test.NewTestCaCert(cert.Version1, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
ca2, _, ca2Key, ca2PEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
caPEM := string(ca1PEM) + string(ca2PEM)
pkiConfig := func(v cert.Version, network string) string {
ca, caKey := ca1, ca1Key
if v == cert.Version2 {
ca, caKey = ca2, ca2Key
}
_, _, keyPEM, certPEM := cert_test.NewTestCert(v, cert.Curve_CURVE25519, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix(network)}, nil, nil)
return fmt.Sprintf("pki:\n ca: %q\n cert: %q\n key: %q\n", caPEM, certPEM, keyPEM)
}
for _, tc := range []struct {
network string
restart bool
}{
{"10.9.0.7/24", true},
{"10.1.0.2/24", false},
} {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString(pkiConfig(cert.Version1, "10.1.0.2/24")))
p, err := NewPKIFromConfig(test.NewLogger(), c)
require.NoError(t, err)
res := c.ReloadConfigString(pkiConfig(cert.Version2, tc.network))
require.NoError(t, res.Err)
assert.False(t, res.Failed, tc.network)
assert.Equal(t, tc.restart, res.RestartRequired, tc.network)
assert.Equal(t, []netip.Prefix{netip.MustParsePrefix(tc.network)}, p.getCertState().myVpnNetworks, "accepted either way, as before")
}
}
// FIPS 140-only mode refuses chachapoly at startup, so reloading to it fails rather than asks for a restart
func TestPKIReloadChachapolyInFIPSOnlyFails(t *testing.T) {
fipsOnly = func() bool { return true }
t.Cleanup(func() { fipsOnly = fips140.Enforced })
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_P256, time.Time{}, time.Time{}, nil, nil, nil)
_, _, keyPEM, certPEM := cert_test.NewTestCert(cert.Version2, cert.Curve_P256, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, nil, nil)
pkiConfig := func(cipher string) string {
return fmt.Sprintf("cipher: %s\npki:\n ca: %q\n cert: %q\n key: %q\n", cipher, caPEM, certPEM, keyPEM)
}
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString(pkiConfig("aes")))
_, err := NewPKIFromConfig(test.NewLogger(), c)
require.NoError(t, err)
res := c.ReloadConfigString(pkiConfig("chachapoly"))
require.NoError(t, res.Err)
assert.True(t, res.Failed)
assert.False(t, res.RestartRequired)
}
func TestLoadCAPoolBlocklist(t *testing.T) {
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
crt, _, _, _ := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, nil, nil)
fp, err := crt.Fingerprint()
require.NoError(t, err)
load := func(entry string) (*cert.CAPool, error) {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString(fmt.Sprintf("pki:\n ca: %q\n blocklist:\n - %q\n", caPEM, entry)))
return loadCAPoolFromConfig(test.NewLogger(), c)
}
for _, entry := range []string{fp, strings.ToUpper(fp), " " + fp + "\t"} {
pool, err := load(entry)
require.NoError(t, err, entry)
assert.True(t, pool.IsBlocklisted(fp), entry)
}
for _, entry := range []string{fp[1:], fp + "00", "sha256:" + fp, "zz" + fp[2:], ""} {
_, err := load(entry)
require.Error(t, err, entry)
}
// A bad entry on reload fails it, the valid entries are still blocked
_, _, keyPEM, certPEM := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "me", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.1/24")}, nil, nil)
pkiConfig := func(entry string) string {
return fmt.Sprintf("pki:\n ca: %q\n cert: %q\n key: %q\n blocklist:\n - %q\n", caPEM, certPEM, keyPEM, entry)
}
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString(pkiConfig(fp)))
p, err := NewPKIFromConfig(test.NewLogger(), c)
require.NoError(t, err)
other, _, _, _ := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "other", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.3/24")}, nil, nil)
otherFp, err := other.Fingerprint()
require.NoError(t, err)
res := c.ReloadConfigString(pkiConfig(fp) + fmt.Sprintf(" - %q\n - %q\n", otherFp, fp[1:]))
assert.True(t, res.Failed)
assert.True(t, p.GetCAPool().IsBlocklisted(fp))
assert.True(t, p.GetCAPool().IsBlocklisted(otherFp))
}
+1 -2
View File
@@ -67,8 +67,7 @@ func NewPunchyFromConfig(l *slog.Logger, c *config.C, punchConn udp.Conn) *Punch
}
p.reload(c, true)
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("stats.lighthouse_metrics")
c.RegisterReloadCallback(func(c *config.C) {
p.reload(c, false)
})
+6 -16
View File
@@ -76,7 +76,7 @@ punchy:
punch: true
delay: 10m
respond: true
`).Err)
`))
p.reload(c, false)
assert.True(t, p.punch.Load())
assert.Equal(t, newDelay, time.Duration(p.delay.Load()))
@@ -170,7 +170,7 @@ func TestPunchy_LogFormat_ReloadPunch(t *testing.T) {
NewPunchyFromConfig(l, c, nil)
hook.entries = nil
require.NoError(t, c.ReloadConfigString(`punchy: {punch: true}`).Err)
require.NoError(t, c.ReloadConfigString(`punchy: {punch: true}`))
entry := findEntry(t, hook.entries, "punchy.punch changed")
assert.Equal(t, slog.LevelInfo, entry.Level)
@@ -184,7 +184,7 @@ func TestPunchy_LogFormat_ReloadRespond(t *testing.T) {
NewPunchyFromConfig(l, c, nil)
hook.entries = nil
require.NoError(t, c.ReloadConfigString(`punchy: {respond: true}`).Err)
require.NoError(t, c.ReloadConfigString(`punchy: {respond: true}`))
entry := findEntry(t, hook.entries, "punchy.respond changed")
assert.Equal(t, slog.LevelInfo, entry.Level)
@@ -198,7 +198,7 @@ func TestPunchy_LogFormat_ReloadDelay(t *testing.T) {
NewPunchyFromConfig(l, c, nil)
hook.entries = nil
require.NoError(t, c.ReloadConfigString(`punchy: {delay: 10s}`).Err)
require.NoError(t, c.ReloadConfigString(`punchy: {delay: 10s}`))
entry := findEntry(t, hook.entries, "punchy.delay changed")
assert.Equal(t, slog.LevelInfo, entry.Level)
@@ -212,7 +212,7 @@ func TestPunchy_LogFormat_ReloadTargetAllRemotes(t *testing.T) {
NewPunchyFromConfig(l, c, nil)
hook.entries = nil
require.NoError(t, c.ReloadConfigString(`punchy: {target_all_remotes: true}`).Err)
require.NoError(t, c.ReloadConfigString(`punchy: {target_all_remotes: true}`))
entry := findEntry(t, hook.entries, "punchy.target_all_remotes changed")
assert.Equal(t, slog.LevelInfo, entry.Level)
@@ -226,19 +226,9 @@ func TestPunchy_LogFormat_ReloadRespondDelay(t *testing.T) {
NewPunchyFromConfig(l, c, nil)
hook.entries = nil
require.NoError(t, c.ReloadConfigString(`punchy: {respond_delay: 15s}`).Err)
require.NoError(t, c.ReloadConfigString(`punchy: {respond_delay: 15s}`))
entry := findEntry(t, hook.entries, "punchy.respond_delay changed")
assert.Equal(t, slog.LevelInfo, entry.Level)
assert.Equal(t, map[string]any{"respond_delay": 15 * time.Second}, entry.Attrs)
}
func TestPunchyReloadRestartRequired(t *testing.T) {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString("stats:\n lighthouse_metrics: false\n"))
NewPunchyFromConfig(test.NewLogger(), c, nil)
res := c.ReloadConfigString("stats:\n lighthouse_metrics: true\n")
require.NoError(t, res.Err)
assert.True(t, res.RestartRequired)
}
-91
View File
@@ -1,91 +0,0 @@
package ratelimit
import (
"fmt"
"math"
"sync/atomic"
"time"
)
// Limiter is a token bucket: `burst` calls are allowed at once, then one more per `every`.
// It counts the calls it denies and hands that count to the next allowed call.
//
// The budget belongs to the Limiter instance.
// Every Allow that returns true spends from it, whatever the caller then does.
//
// Time follows Go's monotonic clock.
//
// Create one Limiter for each thing you want to limit,
// sharing one between unrelated events lets the noisy one starve the quiet one.
//
// Check Allow before doing the work being limited, so a denied call stays cheap:
//
// if denied, ok := probeLimiter.Allow(); ok {
// sendProbe()
// probesDenied.Inc(int64(denied))
// }
//
// For log lines use logging.RateLimited, which attaches the denied count to the logger as "suppressed".
type Limiter struct {
every int64
slack int64
tat atomic.Int64
denied atomic.Uint64
}
// maxSpan bounds `burst` * `every` to half of int64, leaving the other half for process uptime so the bucket
// math can't overflow.
const maxSpan = math.MaxInt64 / 2
// New returns a Limiter allowing `burst` calls at once and one more per `every`.
// A `burst` under 1 is 1, and an `every` of 0 or less never limits.
// It returns an error if `burst` * `every` is over about 146 years.
func New(burst int, every time.Duration) (*Limiter, error) {
l := &Limiter{}
if every > 0 {
burst = max(burst, 1)
if int64(burst) > maxSpan/int64(every) {
return nil, fmt.Errorf("ratelimit: burst %d * every %v is too long", burst, every)
}
l.every = int64(every)
l.slack = int64(burst-1) * l.every
}
return l, nil
}
var monoStart = time.Now()
func monoNow() int64 { return int64(time.Since(monoStart)) }
// Allow reports whether this call is allowed.
// If a token is available it spends it and returns the calls denied since the last allowed one, and true.
// Otherwise it returns 0 and false, and counts the denial.
// A nil Limiter allows everything.
func (l *Limiter) Allow() (uint64, bool) {
if l == nil {
return 0, true
}
return l.allow(monoNow())
}
// allow is Allow at a given monotonic time.
func (l *Limiter) allow(now int64) (uint64, bool) {
// Concurrent Allow calls read the clock before racing for the bucket, so one can see a time another already spent
// past and be denied. An unlimited Limiter must never deny, so it skips the bucket.
if l.every == 0 {
return 0, true
}
for {
tat := l.tat.Load()
next := max(tat, now)
if next-now > l.slack {
l.denied.Add(1)
return 0, false
}
if l.tat.CompareAndSwap(tat, next+l.every) {
return l.denied.Swap(0), true
}
}
}
-264
View File
@@ -1,264 +0,0 @@
package ratelimit
import (
"math"
"sync"
"sync/atomic"
"testing"
"time"
)
func mustLimiter(t testing.TB, burst int, every time.Duration) *Limiter {
t.Helper()
l, err := New(burst, every)
if err != nil {
t.Fatal(err)
}
return l
}
func TestLimiterBurstAndRefill(t *testing.T) {
l, now := mustLimiter(t, 3, time.Second), int64(0)
for i := 0; i < 3; i++ {
if n, ok := l.allow(now); !ok || n != 0 {
t.Fatalf("burst line %d: ok=%v denied=%d", i, ok, n)
}
}
for i := 0; i < 5; i++ {
if _, ok := l.allow(now); ok {
t.Fatalf("line %d past the burst logged", i)
}
}
now += int64(time.Second)
if n, ok := l.allow(now); !ok || n != 5 {
t.Fatalf("after one refill: ok=%v denied=%d, want true 5", ok, n)
}
if _, ok := l.allow(now); ok {
t.Fatal("one refill earned more than one line")
}
// A long quiet spell refills to burst, not past it, and the count reported above does not carry over.
now += int64(time.Hour)
for i, want := range []uint64{1, 0, 0} {
if n, ok := l.allow(now); !ok || n != want {
t.Fatalf("refilled line %d: ok=%v denied=%d, want true %d", i, ok, n, want)
}
}
if _, ok := l.allow(now); ok {
t.Fatal("bucket refilled past burst")
}
}
func TestLimiterBounds(t *testing.T) {
for _, every := range []time.Duration{0, -time.Second} {
l := mustLimiter(t, 1, every)
for i := 0; i < 100; i++ {
if _, ok := l.allow(0); !ok {
t.Fatalf("every=%v limited line %d", every, i)
}
}
}
l := mustLimiter(t, 0, time.Second)
if _, ok := l.allow(0); !ok {
t.Fatal("burst 0 should allow one line")
}
if _, ok := l.allow(0); ok {
t.Fatal("burst 0 should allow only one line")
}
}
func TestLimiterOverflow(t *testing.T) {
for _, c := range []struct {
burst int
every time.Duration
}{
{math.MaxInt, time.Second},
{1, math.MaxInt64},
{2, maxSpan/2 + 1},
} {
if _, err := New(c.burst, c.every); err == nil {
t.Fatalf("burst %d every %d should not fit", c.burst, c.every)
}
}
l := mustLimiter(t, 2, maxSpan/2)
for i := 0; i < 2; i++ {
if _, ok := l.allow(0); !ok {
t.Fatalf("the largest span should allow its burst, denied call %d", i)
}
}
if _, ok := l.allow(0); ok {
t.Fatal("the largest span allowed past its burst")
}
}
// Concurrent callers read the clock at slightly different times, which must not limit a Limiter that never limits.
func TestLimiterUnlimitedConcurrent(t *testing.T) {
l := mustLimiter(t, 1, 0)
var denied atomic.Int64
var wg sync.WaitGroup
for i := 0; i < 16; i++ {
wg.Add(1)
go func() {
defer wg.Done()
for j := 0; j < 10000; j++ {
if _, ok := l.Allow(); !ok {
denied.Add(1)
}
}
}()
}
wg.Wait()
if got := denied.Load(); got != 0 {
t.Fatalf("denied %d lines", got)
}
}
func TestLimiterNil(t *testing.T) {
var l *Limiter
for i := 0; i < 10; i++ {
if _, ok := l.Allow(); !ok {
t.Fatal("nil limiter limited")
}
}
}
func TestLimiterConcurrent(t *testing.T) {
l := mustLimiter(t, 10, time.Hour)
var allowed atomic.Int64
var reported atomic.Uint64
var wg sync.WaitGroup
for i := 0; i < 16; i++ {
wg.Add(1)
go func() {
defer wg.Done()
for j := 0; j < 1000; j++ {
if n, ok := l.allow(0); ok {
allowed.Add(1)
reported.Add(n)
}
}
}()
}
wg.Wait()
if got := allowed.Load(); got != 10 {
t.Fatalf("allowed %d lines, want the burst of 10", got)
}
// An allowed call that lands after some denials reports them, so the rest are still pending.
if got := reported.Load() + l.denied.Load(); got != 16*1000-10 {
t.Fatalf("denied %d, want %d", got, 16*1000-10)
}
}
func BenchmarkAllowAllowed(b *testing.B) {
l := mustLimiter(b, 1, time.Nanosecond)
b.ReportAllocs()
for i := 0; i < b.N; i++ {
l.tat.Store(0)
l.Allow()
}
}
func BenchmarkAllowDenied(b *testing.B) {
l := mustLimiter(b, 1, time.Hour)
l.Allow()
b.ReportAllocs()
for i := 0; i < b.N; i++ {
l.Allow()
}
}
func BenchmarkAllowDeniedParallel(b *testing.B) {
l := mustLimiter(b, 1, time.Hour)
l.Allow()
b.ReportAllocs()
b.RunParallel(func(pb *testing.PB) {
for pb.Next() {
l.Allow()
}
})
}
// FuzzLimiter checks the bucket against its exact definition over arbitrary call timings.
// A call is denied if and only if some allowed call a would leave too many calls for the time since a:
// (allowed calls since a, plus this one) * every > burst * every + (now - a).
// Every denied call must also be reported exactly once, by a later allowed call or still pending.
func FuzzLimiter(f *testing.F) {
f.Add(uint8(3), uint16(1000), []byte{0, 0, 0, 0, 16, 0, 0, 200, 1, 1, 1, 15, 17, 0})
f.Add(uint8(1), uint16(1), []byte{0, 16, 15, 16, 0, 255, 0, 0})
f.Fuzz(func(t *testing.T, burst uint8, everyUs uint16, steps []byte) {
if len(steps) > 512 {
steps = steps[:512]
}
b := int64(burst%16) + 1
every := int64(everyUs%1000+1) * int64(time.Microsecond)
l := mustLimiter(t, int(b), time.Duration(every))
var now int64
var allowedAt []int64
var denied, reported uint64
for _, s := range steps {
// Each step advances by a sixteenth of every, so timings land on and around the refill.
now += int64(s) * every / 16
over := false
for i, a := range allowedAt {
if int64(len(allowedAt)-i+1)*every > b*every+now-a {
over = true
break
}
}
n, ok := l.allow(now)
if ok == over {
t.Fatalf("at %d with %d allowed before: ok=%v, the definition says %v", now, len(allowedAt), ok, !over)
}
if !ok {
denied++
continue
}
reported += n
allowedAt = append(allowedAt, now)
}
if got := reported + l.denied.Load(); got != denied {
t.Fatalf("reported %d denied calls, made %d", got, denied)
}
})
}
// Concurrent callers on the real clock must account for every denied call exactly once.
func TestLimiterDeniedConservedConcurrent(t *testing.T) {
l := mustLimiter(t, 4, time.Microsecond)
var denied, reported atomic.Uint64
var wg sync.WaitGroup
for i := 0; i < 16; i++ {
wg.Add(1)
go func() {
defer wg.Done()
for j := 0; j < 20000; j++ {
if n, ok := l.Allow(); ok {
reported.Add(n)
} else {
denied.Add(1)
}
}
}()
}
wg.Wait()
if denied.Load() == 0 {
t.Fatal("nothing was denied, the test proves nothing")
}
if got := reported.Load() + l.denied.Load(); got != denied.Load() {
t.Fatalf("reported %d denied calls, made %d", got, denied.Load())
}
}
+1 -2
View File
@@ -28,11 +28,10 @@ func NewRelayManager(ctx context.Context, l *slog.Logger, hostmap *HostMap, c *c
hostmap: hostmap,
}
rm.reload(c, true)
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
c.RegisterReloadCallback(func(c *config.C) {
err := rm.reload(c, false)
if err != nil {
rm.l.Error("Failed to reload relay_manager", "error", err)
r.Failed()
}
})
return rm
+9 -26
View File
@@ -1,8 +1,8 @@
package service
import (
"io"
"net"
"sync"
)
type tcpListener struct {
@@ -10,40 +10,23 @@ type tcpListener struct {
s *Service
addr *net.TCPAddr
accept chan net.Conn
// closed is closed instead of accept so a handler blocked handing off a
// connection can't send on a closed channel.
closed chan struct{}
closeOnce sync.Once
}
func (l *tcpListener) Accept() (net.Conn, error) {
// select picks randomly among ready cases, so without this a handler still
// waiting to hand off could win over closed after Close has returned.
select {
case <-l.closed:
return nil, net.ErrClosed
default:
conn, ok := <-l.accept
if !ok {
return nil, io.EOF
}
select {
case conn := <-l.accept:
return conn, nil
case <-l.closed:
return nil, net.ErrClosed
}
}
func (l *tcpListener) Close() error {
l.closeOnce.Do(func() {
// Close before leaving the map so a concurrent closeListeners that
// no longer sees this listener knows Accept is already released.
close(l.closed)
l.s.mu.Lock()
delete(l.s.mu.listeners, l.port)
l.s.mu.Unlock()
})
defer l.s.mu.Unlock()
delete(l.s.mu.listeners, uint16(l.addr.Port))
close(l.accept)
return nil
}
+10 -79
View File
@@ -32,18 +32,13 @@ import (
const nicID = 1
type Service struct {
eg *errgroup.Group
control *nebula.Control
ipstack *stack.Stack
// done is closed once the forwarding goroutines have exited and the
// netstack is torn down, at which point err holds the first fatal error.
done chan struct{}
err error
mu struct {
sync.Mutex
closed bool
listeners map[uint16]*tcpListener
}
}
@@ -70,6 +65,7 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
ctx := control.Context()
eg, ctx := errgroup.WithContext(ctx)
s := Service{
eg: eg,
control: control,
}
s.mu.listeners = map[uint16]*tcpListener{}
@@ -78,12 +74,6 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
NetworkProtocols: []stack.NetworkProtocolFactory{ipv4.NewProtocol, ipv6.NewProtocol},
TransportProtocols: []stack.TransportProtocolFactory{tcp.NewProtocol, udp.NewProtocol, icmp.NewProtocol4, icmp.NewProtocol6},
})
// The teardown goroutine only owns the stack once New succeeds
defer func() {
if reterr != nil {
s.ipstack.Destroy()
}
}()
sackEnabledOpt := tcpip.TCPSACKEnabled(true) // TCP SACK is disabled by default
tcpipErr := s.ipstack.SetTransportProtocolOption(tcp.ProtocolNumber, &sackEnabledOpt)
if tcpipErr != nil {
@@ -133,12 +123,6 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
// this will read exactly one packet
n, err := reader.Read(buf)
if err != nil {
// An error after shutdown began is noise from the device pipes
// closing, anything else is fatal and must stop nebula too
if ctx.Err() != nil {
return nil
}
s.control.Stop()
return err
}
packetBuf := stack.NewPacketBuffer(stack.PacketBufferOptions{
@@ -146,8 +130,8 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
})
linkEP.InjectInbound(header.IPv4ProtocolNumber, packetBuf)
if ctx.Err() != nil {
return nil
if err := ctx.Err(); err != nil {
return err
}
}
})
@@ -155,18 +139,13 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
for {
packet := linkEP.ReadContext(ctx)
if packet == nil {
if ctx.Err() != nil {
return nil
if err := ctx.Err(); err != nil {
return err
}
continue
}
bufView := packet.ToView()
if _, err := bufView.WriteTo(writer); err != nil {
// Same shutdown noise handling as the inbound reader
if ctx.Err() != nil {
return nil
}
s.control.Stop()
return err
}
bufView.Release()
@@ -179,22 +158,6 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
return control.Wait()
})
// Tear down here rather than in Close so it also happens when nebula stops
// on its own. The forwarding goroutines must exit before the stack they feed
// is destroyed.
s.done = make(chan struct{})
go func() {
s.err = eg.Wait()
s.closeListeners()
// Destroy aborts the endpoints that exist when it starts, then waits on
// every endpoint, so a Dial registering in between would hold Wait until
// its connect timed out. Without the NIC new dials fail route lookup.
// RemoveNIC also closes linkEP.
_ = s.ipstack.RemoveNIC(nicID)
s.ipstack.Destroy()
close(s.done)
}()
return &s, nil
}
@@ -268,15 +231,11 @@ func (s *Service) Listen(network, address string) (net.Listener, error) {
s: s,
addr: addr,
accept: make(chan net.Conn),
closed: make(chan struct{}),
}
s.mu.Lock()
defer s.mu.Unlock()
if s.mu.closed {
return nil, net.ErrClosed
}
if _, ok := s.mu.listeners[port]; ok {
return nil, fmt.Errorf("already listening on port %d", port)
}
@@ -285,44 +244,22 @@ func (s *Service) Listen(network, address string) (net.Listener, error) {
return l, nil
}
// Wait blocks until the service has fully stopped, either via Close or a fatal
// error, and returns the first fatal error if there was one.
func (s *Service) Wait() error {
<-s.done
return s.err
return s.eg.Wait()
}
// Close closes all listeners and stops nebula. Use Wait to block until
// shutdown has completed.
func (s *Service) Close() error {
s.closeListeners()
s.control.Stop()
return nil
}
// closeListeners unblocks pending Accept calls and rejects new listeners.
func (s *Service) closeListeners() {
// Every caller closes every listener rather than returning early once
// closed is set, so none returns while another is still closing them.
s.mu.Lock()
s.mu.closed = true
listeners := make([]*tcpListener, 0, len(s.mu.listeners))
for _, l := range s.mu.listeners {
listeners = append(listeners, l)
}
s.mu.Unlock()
for _, l := range listeners {
_ = l.Close()
}
}
func (s *Service) tcpHandler(r *tcp.ForwarderRequest) {
endpointID := r.ID()
s.mu.Lock()
defer s.mu.Unlock()
l, ok := s.mu.listeners[endpointID.LocalPort]
s.mu.Unlock()
if !ok {
r.Complete(true)
return
@@ -338,12 +275,6 @@ func (s *Service) tcpHandler(r *tcp.ForwarderRequest) {
r.Complete(false)
ep.SocketOptions().SetKeepAlive(true)
// The handoff blocks until Accept is called, so it must not hold s.mu or a
// listener nobody accepts from stalls every other port.
conn := gonet.NewTCPConn(&wq, ep)
select {
case l.accept <- conn:
case <-l.closed:
_ = conn.Close()
}
l.accept <- conn
}
-298
View File
@@ -188,301 +188,3 @@ func TestService(t *testing.T) {
t.Fatal(err)
}
}
// A listener that is never accepted from must not stall connections to other
// ports, and closing it must not block.
func TestServiceUnacceptedListener(t *testing.T) {
lighthousePort := ephemeralUDPPort(t)
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
a := newSimpleService(ca, caKey, "a", netip.MustParseAddr("10.0.0.1"), m{
"static_host_map": m{},
"lighthouse": m{
"am_lighthouse": true,
},
"listen": m{
"host": "0.0.0.0",
"port": lighthousePort,
},
})
t.Cleanup(func() { _ = a.Close() })
b := newSimpleService(ca, caKey, "b", netip.MustParseAddr("10.0.0.2"), m{
"static_host_map": m{
"10.0.0.1": []string{fmt.Sprintf("127.0.0.1:%d", lighthousePort)},
},
"lighthouse": m{
"hosts": []string{"10.0.0.1"},
"interval": 1,
},
})
t.Cleanup(func() { _ = b.Close() })
idle, err := a.Listen("tcp", ":1234")
if err != nil {
t.Fatal(err)
}
active, err := a.Listen("tcp", ":1235")
if err != nil {
t.Fatal(err)
}
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
defer cancel()
idleConn, err := b.DialContext(ctx, "tcp", "10.0.0.1:1234")
if err != nil {
t.Fatal(err)
}
defer idleConn.Close()
accepted := make(chan error, 1)
go func() {
conn, err := active.Accept()
if err == nil {
err = conn.Close()
}
accepted <- err
}()
ctx, cancel = context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
activeConn, err := b.DialContext(ctx, "tcp", "10.0.0.1:1235")
if err != nil {
t.Fatalf("dial to accepted port stalled behind idle listener: %v", err)
}
defer activeConn.Close()
select {
case err := <-accepted:
if err != nil {
t.Fatal(err)
}
case <-time.After(5 * time.Second):
t.Fatal("accept stalled behind idle listener")
}
closed := make(chan error, 1)
go func() { closed <- idle.Close() }()
select {
case err := <-closed:
if err != nil {
t.Fatal(err)
}
case <-time.After(5 * time.Second):
t.Fatal("closing idle listener blocked")
}
if _, err := idle.Accept(); !errors.Is(err, net.ErrClosed) {
t.Fatalf("expected net.ErrClosed from closed listener, got %v", err)
}
if err := idle.Close(); err != nil {
t.Fatalf("second close: %v", err)
}
}
// Accept must report net.ErrClosed after Close even while a handler is still
// trying to hand off a connection.
func TestListenerAcceptAfterClose(t *testing.T) {
s := &Service{}
s.mu.listeners = map[uint16]*tcpListener{}
l := &tcpListener{
port: 1234,
s: s,
accept: make(chan net.Conn),
closed: make(chan struct{}),
}
s.mu.listeners[l.port] = l
if err := l.Close(); err != nil {
t.Fatal(err)
}
// Keep a send pending so every Accept has a connection ready alongside closed.
stop := make(chan struct{})
done := make(chan struct{})
go func() {
defer close(done)
for {
server, client := net.Pipe()
_ = client.Close()
select {
case l.accept <- server:
case <-stop:
_ = server.Close()
return
}
}
}()
defer func() {
close(stop)
<-done
}()
for range 100 {
time.Sleep(time.Millisecond)
conn, err := l.Accept()
if conn != nil {
_ = conn.Close()
}
if !errors.Is(err, net.ErrClosed) {
t.Fatalf("Accept after Close: got err %v, want net.ErrClosed", err)
}
}
}
// Close must release blocked Accept calls and let Wait report a clean shutdown.
func TestServiceClose(t *testing.T) {
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
a := newSimpleService(ca, caKey, "a", netip.MustParseAddr("10.0.0.1"), m{
"static_host_map": m{},
"listen": m{
"host": "127.0.0.1",
"port": 0,
},
})
ln, err := a.Listen("tcp", ":1234")
if err != nil {
t.Fatal(err)
}
accepted := make(chan error, 1)
go func() {
_, err := ln.Accept()
accepted <- err
}()
if err := a.Close(); err != nil {
t.Fatal(err)
}
select {
case err := <-accepted:
if !errors.Is(err, net.ErrClosed) {
t.Fatalf("expected net.ErrClosed from Accept, got %v", err)
}
case <-time.After(5 * time.Second):
t.Fatal("Accept still blocked after Close")
}
waited := make(chan error, 1)
go func() { waited <- a.Wait() }()
select {
case err := <-waited:
if err != nil {
t.Fatalf("expected clean shutdown from Wait, got %v", err)
}
case <-time.After(5 * time.Second):
t.Fatal("Wait still blocked after Close")
}
if a.ipstack.HasNIC(nicID) {
t.Fatal("netstack not torn down after Wait")
}
if err := a.Close(); err != nil {
t.Fatalf("second close: %v", err)
}
if _, err := a.Listen("tcp", ":1235"); !errors.Is(err, net.ErrClosed) {
t.Fatalf("expected net.ErrClosed from Listen after Close, got %v", err)
}
}
// If nebula stops without Close being called, the service must still release
// Accept and tear down the netstack.
func TestServiceNebulaStopped(t *testing.T) {
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
a := newSimpleService(ca, caKey, "a", netip.MustParseAddr("10.0.0.1"), m{
"static_host_map": m{},
"listen": m{
"host": "127.0.0.1",
"port": 0,
},
})
ln, err := a.Listen("tcp", ":1234")
if err != nil {
t.Fatal(err)
}
accepted := make(chan error, 1)
go func() {
_, err := ln.Accept()
accepted <- err
}()
a.control.Stop()
waited := make(chan error, 1)
go func() { waited <- a.Wait() }()
select {
case err := <-waited:
if err != nil {
t.Fatalf("expected clean shutdown from Wait, got %v", err)
}
case <-time.After(5 * time.Second):
t.Fatal("Wait still blocked after nebula stopped")
}
select {
case err := <-accepted:
if !errors.Is(err, net.ErrClosed) {
t.Fatalf("expected net.ErrClosed from Accept, got %v", err)
}
case <-time.After(5 * time.Second):
t.Fatal("Accept still blocked after nebula stopped")
}
if a.ipstack.HasNIC(nicID) {
t.Fatal("netstack not torn down after Wait")
}
}
// Dials racing Close must not hold Wait until their connect times out.
func TestServiceDialDuringClose(t *testing.T) {
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
a := newSimpleService(ca, caKey, "a", netip.MustParseAddr("10.0.0.1"), m{
"static_host_map": m{},
"listen": m{
"host": "127.0.0.1",
"port": 0,
},
})
stop := make(chan struct{})
var eg errgroup.Group
for range 8 {
eg.Go(func() error {
for {
select {
case <-stop:
return nil
default:
}
// 10.0.0.2 has no tunnel, so each dial sits in SYN-SENT until aborted
if c, err := a.Dial("tcp", "10.0.0.2:80"); err == nil {
_ = c.Close()
}
}
})
}
time.Sleep(50 * time.Millisecond)
if err := a.Close(); err != nil {
t.Fatal(err)
}
waited := make(chan error, 1)
go func() { waited <- a.Wait() }()
select {
case err := <-waited:
if err != nil {
t.Fatalf("expected clean shutdown from Wait, got %v", err)
}
case <-time.After(5 * time.Second):
t.Fatal("Wait blocked behind a dial that raced Close")
}
close(stop)
dialersDone := make(chan error, 1)
go func() { dialersDone <- eg.Wait() }()
select {
case <-dialersDone:
case <-time.After(5 * time.Second):
t.Fatal("Dial still blocked after Wait")
}
}
+922 -56
View File
File diff suppressed because it is too large. Load diff
-57
View File
@@ -1,57 +0,0 @@
package nebula
import (
"bytes"
"fmt"
"path/filepath"
"strings"
"testing"
"github.com/slackhq/nebula/commands"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/test"
)
// TestSSHCommandSurface is a characterization test for the ssh command surface.
// It pins the registered command set, their descriptions, help text and flag definitions
// so that moving the registry to a transport neutral package is provably a relocation
// rather than a rewrite. Regenerate with `go test . -run TestSSHCommandSurface -update`.
func TestSSHCommandSurface(t *testing.T) {
got := renderCommandSurface(registeredCommands(t).All())
test.Golden(t, filepath.Join("testdata", "ssh_commands.golden"), got)
}
// registeredCommands returns a registry holding every command nebula serves. The
// Interface is never dereferenced: attachCommands only closes over it.
func registeredCommands(t *testing.T) *commands.Registry {
t.Helper()
l := test.NewLogger()
reg := commands.New()
attachCommands(l, config.NewC(l), reg, &Interface{})
return reg
}
func renderCommandSurface(cmds []*commands.Command) string {
lines := make([]string, 0, len(cmds))
for _, cmd := range cmds {
b := &bytes.Buffer{}
fmt.Fprintf(b, "%s\n", cmd.Name)
fmt.Fprintf(b, " short: %s\n", cmd.ShortDescription)
fmt.Fprintf(b, " help: %s\n", cmd.Help)
if cmd.Flags != nil {
fl, _ := cmd.Flags()
if fl != nil {
fb := &bytes.Buffer{}
fl.SetOutput(fb)
fl.PrintDefaults()
fmt.Fprintf(b, " flags:\n%s", fb.String())
}
}
lines = append(lines, b.String())
}
// In the order All gives, so the golden pins display order too.
return strings.Join(lines, "")
}
-94
View File
@@ -1,94 +0,0 @@
package nebula
import (
"errors"
"io"
"os"
"path/filepath"
"testing"
"github.com/slackhq/nebula/commands"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
type lineWriter struct {
lines []string
err error
}
func (w *lineWriter) WriteLine(s string) error {
w.lines = append(w.lines, s)
return w.err
}
func (w *lineWriter) Write(s string) error { return w.WriteLine(s) }
func (w *lineWriter) WriteBytes(b []byte) error { return w.WriteLine(string(b)) }
func (w *lineWriter) GetWriter() io.Writer { return io.Discard }
func TestReloadCommandReportsTheResult(t *testing.T) {
dir := t.TempDir()
write := func(body string) {
require.NoError(t, os.WriteFile(filepath.Join(dir, "config.yml"), []byte(body), 0o600))
}
write("a: 1\nb: 1")
l := test.NewLogger()
c := config.NewC(l)
require.NoError(t, c.Load(dir))
fail := false
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("b")
if fail {
r.Failed()
}
})
// reload returns what the client was told. A reload that failed is a commands.Failure
// to the surface, exit 1 over ssh, with the result line as its message; one that
// merely needs a restart is not.
reload := func(failed bool) []string {
w := &lineWriter{}
err := reloadCommand(l, c, w)
if failed {
var f *commands.Failure
require.ErrorAs(t, err, &f)
assert.Equal(t, w.lines[len(w.lines)-1], f.Msg)
} else {
require.NoError(t, err)
}
return w.lines
}
write("a: 2\nb: 1")
assert.Equal(t, []string{"Reloading config", "Config reload complete"}, reload(false))
fail = true
write("a: 3\nb: 1")
assert.Equal(t, []string{"Reloading config", "Config reload completed with errors, review the logs"}, reload(true))
fail = false
write("a: 3\nb: 2")
assert.Equal(t, []string{"Reloading config", "Config reload was completed but requires a restart to fully apply, keys [b]"}, reload(false))
write("a: [")
lines := reload(true)
require.Len(t, lines, 2)
assert.Contains(t, lines[1], "Config reload failed, the new config did not load")
assert.Contains(t, lines[1], dir, "names the config that did not load")
}
// A client that went away still gets the reload it asked for
func TestReloadCommandReloadsWhenTheClientIsGone(t *testing.T) {
dir := t.TempDir()
require.NoError(t, os.WriteFile(filepath.Join(dir, "config.yml"), []byte("a: 1"), 0o600))
l := test.NewLogger()
c := config.NewC(l)
require.NoError(t, c.Load(dir))
reloaded := false
c.RegisterReloadCallback(func(*config.C, *config.Reload) { reloaded = true })
gone := errors.New("client is gone")
require.ErrorIs(t, reloadCommand(l, c, &lineWriter{err: gone}), gone)
assert.True(t, reloaded)
}
+161
View File
@@ -0,0 +1,161 @@
package sshd
import (
"errors"
"flag"
"fmt"
"sort"
"strings"
"github.com/armon/go-radix"
)
// CommandFlags is a function called before help or command execution to parse command line flags
// It should return a flag.FlagSet instance and a pointer to the struct that will contain parsed flags
type CommandFlags func() (*flag.FlagSet, any)
// CommandCallback is the function called when your command should execute.
// fs will be a a pointer to the struct provided by Command.Flags callback, if there was one. -h and -help are reserved
// and handled automatically for you.
// a will be any unconsumed arguments, if no Command.Flags was available this will be all the flags passed in.
// w is the writer to use when sending messages back to the client.
// If an error is returned by the callback it is logged locally, the callback should handle messaging errors to the user
// where appropriate
type CommandCallback func(fs any, a []string, w StringWriter) error
type Command struct {
Name string
ShortDescription string
Help string
Flags CommandFlags
Callback CommandCallback
}
func execCommand(c *Command, args []string, w StringWriter) error {
var (
fl *flag.FlagSet
fs any
)
if c.Flags != nil {
fl, fs = c.Flags()
if fl != nil {
// SetOutput() here in case fl.Parse dumps usage.
fl.SetOutput(w.GetWriter())
err := fl.Parse(args)
if err != nil {
// fl.Parse has dumped error information to the user via the w writer.
return err
}
args = fl.Args()
}
}
return c.Callback(fs, args, w)
}
func dumpCommands(c *radix.Tree, w StringWriter) {
err := w.WriteLine("Available commands:")
if err != nil {
return
}
cmds := make([]string, 0)
for _, l := range allCommands(c) {
cmds = append(cmds, fmt.Sprintf("%s - %s", l.Name, l.ShortDescription))
}
sort.Strings(cmds)
_ = w.Write(strings.Join(cmds, "\n") + "\n\n")
}
func lookupCommand(c *radix.Tree, sCmd string) (*Command, error) {
cmd, ok := c.Get(sCmd)
if !ok {
return nil, nil
}
command, ok := cmd.(*Command)
if !ok {
return nil, errors.New("failed to cast command")
}
return command, nil
}
func matchCommand(c *radix.Tree, cmd string) []string {
cmds := make([]string, 0)
c.WalkPrefix(cmd, func(found string, v any) bool {
cmds = append(cmds, found)
return false
})
sort.Strings(cmds)
return cmds
}
func allCommands(c *radix.Tree) []*Command {
cmds := make([]*Command, 0)
c.WalkPrefix("", func(found string, v any) bool {
cmd, ok := v.(*Command)
if ok {
cmds = append(cmds, cmd)
}
return false
})
return cmds
}
func helpCallback(commands *radix.Tree, a []string, w StringWriter) (err error) {
// Just typed help
if len(a) == 0 {
dumpCommands(commands, w)
return nil
}
// We are printing a specific commands help text
cmd, err := lookupCommand(commands, a[0])
if err != nil {
return
}
if cmd != nil {
err = w.WriteLine(fmt.Sprintf("%s - %s", cmd.Name, cmd.ShortDescription))
if err != nil {
return err
}
if cmd.Help != "" {
err = w.WriteLine(fmt.Sprintf(" %s", cmd.Help))
if err != nil {
return err
}
}
if cmd.Flags != nil {
fs, _ := cmd.Flags()
if fs != nil {
fs.SetOutput(w.GetWriter())
fs.PrintDefaults()
}
}
return nil
}
err = w.WriteLine("Command not available " + a[0])
if err != nil {
return err
}
return nil
}
func checkHelpArgs(args []string) bool {
for _, a := range args {
if a == "-h" || a == "-help" {
return true
}
}
return false
}
+39 -73
View File
@@ -8,17 +8,13 @@ import (
"log/slog"
"net"
"sync"
"sync/atomic"
"github.com/slackhq/nebula/commands"
"github.com/armon/go-radix"
"golang.org/x/crypto/ssh"
)
type SSHServer struct {
// config is replaced whole when the host key changes, ssh.ServerConfig.AddHostKey only replaces a key of the same
// algorithm and appends any other
config atomic.Pointer[ssh.ServerConfig]
authenticate func(ssh.ConnMetadata, ssh.PublicKey) (*ssh.Permissions, error)
config *ssh.ServerConfig
l *slog.Logger
certChecker *ssh.CertChecker
@@ -29,28 +25,24 @@ type SSHServer struct {
trustedKeys map[string]map[string]bool
trustedCAs []ssh.PublicKey
// Available commands.
commands *commands.Registry
listener atomic.Pointer[net.Listener]
// runs counts the Runs that are listening. A reload's Run can start before the one it replaced has returned
runs atomic.Int32
// addr is where the newest Run listens, nil when none is
addr atomic.Pointer[net.Addr]
// List of available commands
helpCommand *Command
commands *radix.Tree
listener net.Listener
// ctx parents per-Run contexts. Cancelling it (e.g. via Control.Stop) tears the server down even
// across reloads, since each Run derives a fresh child rather than reusing this one directly.
ctx context.Context
}
// NewSSHServer creates a new ssh server serving the supplied command registry and
// prepares to listen. The ssh server's context is parented off the supplied ctx so
// cancelling it (e.g. on Control.Stop) tears down active sessions and closes the listener.
func NewSSHServer(ctx context.Context, l *slog.Logger, reg *commands.Registry) (*SSHServer, error) {
// NewSSHServer creates a new ssh server rigged with default commands and prepares to listen.
// The ssh server's context is parented off the supplied ctx so cancelling it
// (e.g. on Control.Stop) tears down active sessions and closes the listener.
func NewSSHServer(ctx context.Context, l *slog.Logger) (*SSHServer, error) {
s := &SSHServer{
trustedKeys: make(map[string]map[string]bool),
l: l,
commands: reg,
commands: radix.New(),
ctx: ctx,
}
@@ -93,8 +85,18 @@ func NewSSHServer(ctx context.Context, l *slog.Logger, reg *commands.Registry) (
},
}
s.authenticate = cc.Authenticate
s.config.Store(s.newConfig())
s.config = &ssh.ServerConfig{
PublicKeyCallback: cc.Authenticate,
ServerVersion: fmt.Sprintf("SSH-2.0-Nebula???"),
}
s.RegisterCommand(&Command{
Name: "help",
ShortDescription: "prints available commands or help <command> for specific usage info",
Callback: func(a any, args []string, w StringWriter) error {
return helpCallback(s.commands, args, w)
},
})
return s, nil
}
@@ -105,32 +107,10 @@ func (s *SSHServer) SetHostKey(hostPrivateKey []byte) error {
return fmt.Errorf("failed to parse private key: %s", err)
}
config := s.newConfig()
config.AddHostKey(private)
s.config.Store(config)
s.config.AddHostKey(private)
return nil
}
func (s *SSHServer) newConfig() *ssh.ServerConfig {
return &ssh.ServerConfig{
PublicKeyCallback: s.authenticate,
ServerVersion: fmt.Sprintf("SSH-2.0-Nebula???"),
}
}
// Addr is the address the newest Run listens on, nil when none is.
func (s *SSHServer) Addr() net.Addr {
if a := s.addr.Load(); a != nil {
return *a
}
return nil
}
// Running is true while a Run is listening.
func (s *SSHServer) Running() bool {
return s.runs.Load() > 0
}
func (s *SSHServer) ClearTrustedCAs() {
s.authLock.Lock()
s.trustedCAs = []ssh.PublicKey{}
@@ -180,47 +160,31 @@ func (s *SSHServer) AddAuthorizedKey(user, pubKey string) error {
return nil
}
// RegisterCommand adds a command that can be run by a user, by default only `help` is available
func (s *SSHServer) RegisterCommand(c *Command) {
s.commands.Insert(c.Name, c)
}
// Run begins listening and accepting connections. Each invocation derives a fresh per-Run context
// from the constructor-supplied ctx so a Stop+Run sequence (used by config reload) starts clean
// rather than carrying a permanently-cancelled context across runs.
func (s *SSHServer) Run(addr string) error {
listener, err := s.Listen(addr)
if err != nil {
return err
}
s.Serve(listener)
return nil
}
// Listen binds addr for Serve, so a caller can tell the bind failed before serving in the background. Stop can close
// the listener from here on, Serve then returns as soon as it starts.
func (s *SSHServer) Listen(addr string) (net.Listener, error) {
if s.ctx.Err() != nil {
return nil, s.ctx.Err()
return s.ctx.Err()
}
listener, err := net.Listen("tcp", addr)
if err != nil {
return nil, err
return err
}
// s.listener is the public handle Stop uses to interrupt the active run; listener (the local) is what
// this run owns. They start equal but a fast reload may overwrite s.listener with the next run's
// listener before this run's watcher fires, so each run must close its own listener via the local
// reference.
s.listener.Store(&listener)
return listener, nil
}
// Serve accepts connections on a listener from Listen until Stop, or the context passed to NewSSHServer, ends it.
func (s *SSHServer) Serve(listener net.Listener) {
s.runs.Add(1)
bound := listener.Addr()
s.addr.Store(&bound)
s.listener = listener
runCtx, cancel := context.WithCancel(s.ctx)
defer cancel()
// Deferred after cancel so they run first, a run on its way out no longer counts as listening
defer s.runs.Add(-1)
defer s.addr.CompareAndSwap(&bound, nil)
// Close the listener when this run's context is cancelled. That can come from the parent
// (Control.Stop), from Run returning normally (defer cancel above), or transitively when a sibling
@@ -233,12 +197,14 @@ func (s *SSHServer) Serve(listener net.Listener) {
}
}()
s.l.Info("SSH server is listening", "sshListener", bound)
s.l.Info("SSH server is listening", "sshListener", addr)
// Run loops until there is an error
s.run(runCtx, listener)
s.l.Info("SSH server stopped listening")
// We don't return an error because run logs for us
return nil
}
func (s *SSHServer) run(ctx context.Context, listener net.Listener) {
@@ -260,7 +226,7 @@ func (s *SSHServer) run(ctx context.Context, listener net.Listener) {
<-sessionContext.Done()
c.Close()
}()
conn, chans, reqs, err := ssh.NewServerConn(c, s.config.Load())
conn, chans, reqs, err := ssh.NewServerConn(c, s.config)
fp := ""
if conn != nil {
fp = conn.Permissions.Extensions["fp"]
@@ -298,8 +264,8 @@ func (s *SSHServer) run(ctx context.Context, listener net.Listener) {
}
func (s *SSHServer) Stop() {
if l := s.listener.Load(); l != nil {
if err := (*l).Close(); err != nil && !errors.Is(err, net.ErrClosed) {
if s.listener != nil {
if err := s.listener.Close(); err != nil {
s.l.Warn("Failed to close the sshd listener", "error", err)
}
}
+46 -37
View File
@@ -1,11 +1,13 @@
package sshd
import (
"errors"
"fmt"
"log/slog"
"sort"
"strings"
"github.com/slackhq/nebula/commands"
"github.com/anmitsu/go-shlex"
"github.com/armon/go-radix"
"golang.org/x/crypto/ssh"
"golang.org/x/term"
)
@@ -14,37 +16,31 @@ type session struct {
l *slog.Logger
c *ssh.ServerConn
term *term.Terminal
commands *commands.Registry
commands *radix.Tree
cancel func()
}
func NewSession(reg *commands.Registry, conn *ssh.ServerConn, chans <-chan ssh.NewChannel, cancel func(), l *slog.Logger) *session {
func NewSession(commands *radix.Tree, conn *ssh.ServerConn, chans <-chan ssh.NewChannel, cancel func(), l *slog.Logger) *session {
s := &session{
commands: reg.Clone(),
commands: radix.NewFromMap(commands.ToMap()),
l: l,
c: conn,
cancel: cancel,
}
s.commands.Register(LogoutCommand(s.Close))
s.commands.Insert("logout", &Command{
Name: "logout",
ShortDescription: "Ends the current session",
Callback: func(a any, args []string, w StringWriter) error {
s.Close()
return nil
},
})
go s.handleChannels(chans)
return s
}
// LogoutCommand is the logout command a session registers on its clone of the registry,
// with end as what it does. Exported so a test can serve what a session serves.
func LogoutCommand(end func()) *commands.Command {
return &commands.Command{
Name: commands.Logout,
ShortDescription: "Ends the current session",
Callback: func(fs any, a []string, w commands.StringWriter) error {
end()
return nil
},
}
}
func (s *session) handleChannels(chans <-chan ssh.NewChannel) {
defer s.Close()
for newChannel := range chans {
@@ -91,13 +87,9 @@ func (s *session) handleRequests(in <-chan *ssh.Request, channel ssh.Channel) {
}
req.Reply(true, nil)
err := s.dispatchCommand(payload.Value, commands.NewStringWriter(channel))
s.dispatchCommand(payload.Value, &stringWriter{channel})
// A command that failed exits 1, so `ssh host cmd` callers can tell.
status := struct{ Status uint32 }{uint32(0)}
if err != nil {
status.Status = 1
}
channel.SendRequest("exit-status", false, ssh.Marshal(status))
channel.Close()
return
@@ -119,11 +111,12 @@ func (s *session) createTerm(channel ssh.Channel) *term.Terminal {
term.AutoCompleteCallback = func(line string, pos int, key rune) (newLine string, newPos int, ok bool) {
// key 9 is tab
if key == 9 {
cmds := s.commands.Match(line)
cmds := matchCommand(s.commands, line)
if len(cmds) == 1 {
return cmds[0] + " ", len(cmds[0]) + 1, true
}
sort.Strings(cmds)
term.Write([]byte(strings.Join(cmds, "\n") + "\n\n"))
}
@@ -135,7 +128,7 @@ func (s *session) createTerm(channel ssh.Channel) *term.Terminal {
}
func (s *session) handleInput() {
w := commands.NewStringWriter(s.term)
w := &stringWriter{w: s.term}
for {
line, err := s.term.ReadLine()
if err != nil {
@@ -146,20 +139,36 @@ func (s *session) handleInput() {
}
}
// dispatchCommand runs line and returns the command's error, which it has logged unless
// the command already told the user everything: the log line is for the operator reading
// the daemon's log, who learns nothing from a failure the user caused.
func (s *session) dispatchCommand(line string, w commands.StringWriter) error {
err := s.commands.Dispatch(line, w)
if err == nil {
return nil
func (s *session) dispatchCommand(line string, w StringWriter) {
args, err := shlex.Split(line, true)
if err != nil {
return
}
var f *commands.Failure
if !errors.As(err, &f) {
s.l.Debug("Command returned an error", "line", line, "error", err)
if len(args) == 0 {
dumpCommands(s.commands, w)
return
}
return err
c, err := lookupCommand(s.commands, args[0])
if err != nil {
return
}
if c == nil {
err := w.WriteLine(fmt.Sprintf("did not understand: %s", line))
_ = err
dumpCommands(s.commands, w)
return
}
if checkHelpArgs(args) {
s.dispatchCommand(fmt.Sprintf("%s %s", "help", c.Name), w)
return
}
_ = execCommand(c, args[1:], w)
}
func (s *session) Close() {
+1 -8
View File
@@ -1,9 +1,7 @@
package commands
package sshd
import "io"
// StringWriter is how a command talks back to whoever invoked it: one stream, which the
// ssh surface points at its channel.
type StringWriter interface {
WriteLine(string) error
Write(string) error
@@ -15,11 +13,6 @@ type stringWriter struct {
w io.Writer
}
// NewStringWriter returns a StringWriter that writes to w.
func NewStringWriter(w io.Writer) StringWriter {
return &stringWriter{w: w}
}
func (w *stringWriter) WriteLine(s string) error {
return w.Write(s + "\n")
}
-293
View File
@@ -1,293 +0,0 @@
package nebula
import (
"crypto"
"crypto/ed25519"
"crypto/rand"
"crypto/rsa"
"encoding/pem"
"errors"
"fmt"
"net"
"os"
"path/filepath"
"strings"
"testing"
"time"
"github.com/slackhq/nebula/commands"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/sshd"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"golang.org/x/crypto/ssh"
)
type sshdReloadHarness struct {
c *config.C
reg *commands.Registry
server *sshd.SSHServer
keyFile string
signer ssh.Signer
listen string
users []string
extra string
}
func newSSHDReloadHarness(t *testing.T) *sshdReloadHarness {
t.Helper()
l := test.NewLogger()
h := &sshdReloadHarness{keyFile: filepath.Join(t.TempDir(), "host_key"), listen: "127.0.0.1:0", users: []string{"test"}}
h.writeHostKey(t, newEd25519Key(t))
_, userKey, err := ed25519.GenerateKey(rand.Reader)
require.NoError(t, err)
h.signer, err = ssh.NewSignerFromKey(userKey)
require.NoError(t, err)
h.c = config.NewC(l)
require.NoError(t, h.c.LoadString(h.config()))
h.reg = commands.New()
h.server, err = sshd.NewSSHServer(t.Context(), l, h.reg)
require.NoError(t, err)
wireSSHReload(l, h.server, h.c)
run, err := configSSH(l, h.server, h.c, nil)
require.NoError(t, err)
go run()
t.Cleanup(h.server.Stop)
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
return h
}
func newEd25519Key(t *testing.T) crypto.Signer {
_, key, err := ed25519.GenerateKey(rand.Reader)
require.NoError(t, err)
return key
}
// writeHostKey replaces the host key file and returns the public key a client should now see
func (h *sshdReloadHarness) writeHostKey(t *testing.T, key crypto.Signer) ssh.PublicKey {
t.Helper()
block, err := ssh.MarshalPrivateKey(key, "")
require.NoError(t, err)
require.NoError(t, os.WriteFile(h.keyFile, pem.EncodeToMemory(block), 0o600))
pub, err := ssh.NewPublicKey(key.Public())
require.NoError(t, err)
return pub
}
func (h *sshdReloadHarness) config() string {
users := ""
for _, u := range h.users {
users += fmt.Sprintf(" - user: %s\n keys: [%q]\n", u, string(ssh.MarshalAuthorizedKey(h.signer.PublicKey())))
}
return fmt.Sprintf("sshd:\n enabled: true\n listen: %s\n host_key: %s\n authorized_users:\n%s%s",
h.listen, h.keyFile, users, h.extra)
}
// dial connects to wherever the server listens now, a restart on :0 moves it. hostKeyAlgorithms limits which host keys
// the client accepts, none means any
func (h *sshdReloadHarness) dial(hostKeyAlgorithms ...string) (*ssh.Client, ssh.PublicKey, error) {
addr := h.server.Addr()
if addr == nil {
return nil, nil, fmt.Errorf("not listening")
}
var hostKey ssh.PublicKey
c, err := ssh.Dial("tcp", addr.String(), &ssh.ClientConfig{
User: "test",
Auth: []ssh.AuthMethod{ssh.PublicKeys(h.signer)},
HostKeyCallback: func(_ string, _ net.Addr, key ssh.PublicKey) error {
hostKey = key
return nil
},
HostKeyAlgorithms: hostKeyAlgorithms,
Timeout: time.Second,
})
return c, hostKey, err
}
func (h *sshdReloadHarness) connect(t *testing.T) (*ssh.Client, ssh.PublicKey) {
t.Helper()
var client *ssh.Client
var hostKey ssh.PublicKey
require.Eventually(t, func() bool {
var err error
client, hostKey, err = h.dial()
return err == nil
}, 5*time.Second, 20*time.Millisecond)
t.Cleanup(func() { _ = client.Close() })
return client, hostKey
}
// dropped is true when the server closed the client's connection within wait
func dropped(client *ssh.Client, wait time.Duration) bool {
done := make(chan struct{})
go func() {
_ = client.Wait()
close(done)
}()
select {
case <-done:
return true
case <-time.After(wait):
return false
}
}
// Restarting sshd drops every open session, the one that asked for the reload included. A reload that touches nothing
// sshd reads leaves it alone
func TestSSHDReload_UnchangedKeepsSessions(t *testing.T) {
h := newSSHDReloadHarness(t)
client, _ := h.connect(t)
require.NoError(t, h.c.ReloadConfigString(h.config()+"punchy:\n punch: true\n").Err)
assert.False(t, dropped(client, 500*time.Millisecond), "an unchanged sshd was restarted")
}
// Every key the server reads restarts it when it changes
func TestSSHDReload_ChangedConfigRestarts(t *testing.T) {
cases := map[string]func(t *testing.T, h *sshdReloadHarness){
"listen": func(t *testing.T, h *sshdReloadHarness) { h.listen = "localhost:0" },
"authorized_users": func(t *testing.T, h *sshdReloadHarness) { h.users = append(h.users, "other") },
"trusted_cas": func(t *testing.T, h *sshdReloadHarness) { h.extra = " trusted_cas: []\n" },
"host_key": func(t *testing.T, h *sshdReloadHarness) {
h.keyFile = filepath.Join(t.TempDir(), "other_host_key")
h.writeHostKey(t, newEd25519Key(t))
},
}
for name, change := range cases {
t.Run(name, func(t *testing.T) {
h := newSSHDReloadHarness(t)
client, _ := h.connect(t)
change(t, h)
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
assert.True(t, dropped(client, 5*time.Second), "a changed sshd config was not applied")
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
h.connect(t)
})
}
}
// The config can stay the same while the host key file it names changes. New connections get the new key, open
// sessions are left alone
func TestSSHDReload_ChangedHostKeyFile(t *testing.T) {
h := newSSHDReloadHarness(t)
client, _ := h.connect(t)
want := h.writeHostKey(t, newEd25519Key(t))
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
_, got := h.connect(t)
assert.Equal(t, want.Marshal(), got.Marshal(), "a new host key was not applied")
assert.False(t, dropped(client, 500*time.Millisecond), "a new host key restarted sshd")
}
// A host key of another algorithm replaces the old one rather than being offered next to it
func TestSSHDReload_HostKeyAlgorithmChange(t *testing.T) {
h := newSSHDReloadHarness(t)
h.connect(t)
rsaKey, err := rsa.GenerateKey(rand.Reader, 2048)
require.NoError(t, err)
want := h.writeHostKey(t, rsaKey)
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
_, got := h.connect(t)
assert.Equal(t, want.Marshal(), got.Marshal())
_, _, err = h.dial(ssh.KeyAlgoED25519)
assert.Error(t, err, "the old ed25519 host key is still offered")
}
// A server that isn't running, say its port was busy, is tried again on every reload as before
func TestSSHDReload_NotRunningRestarts(t *testing.T) {
h := newSSHDReloadHarness(t)
h.server.Stop()
require.Eventually(t, func() bool { return !h.server.Running() }, 5*time.Second, 10*time.Millisecond)
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
h.connect(t)
}
// A host key that no longer loads stops sshd, the same as a config that doesn't
func TestSSHDReload_BadHostKeyFileStops(t *testing.T) {
h := newSSHDReloadHarness(t)
h.connect(t)
require.NoError(t, os.WriteFile(h.keyFile, []byte("not a key"), 0o600))
assert.True(t, h.c.ReloadConfigString(h.config()).Failed)
require.Eventually(t, func() bool { return !h.server.Running() }, 5*time.Second, 10*time.Millisecond)
}
// A trusted CA or authorized user that is skipped with a warning fails the reload, the valid ones are still used
func TestSSHDReload_SkippedEntriesFail(t *testing.T) {
cases := map[string]string{
"bad trusted ca": " trusted_cas: [nope]\n",
"user entry not a map": " - nope\n",
"user missing": " - keys: [nope]\n",
"bad key": " - user: other\n keys: nope\n",
"key in a list not a string": " - user: other\n keys: [5]\n",
"bad key in a list": " - user: other\n keys: [nope]\n",
"keys missing": " - user: other\n",
}
for name, extra := range cases {
t.Run(name, func(t *testing.T) {
h := newSSHDReloadHarness(t)
h.extra = extra
res := h.c.ReloadConfigString(h.config())
require.NoError(t, res.Err)
assert.True(t, res.Failed)
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
h.connect(t)
})
}
}
// TestSSHExecExitStatusReflectsTheCommand: an exec request exits 1 when the command
// returned an error and 0 otherwise, with the command's output either way.
func TestSSHExecExitStatusReflectsTheCommand(t *testing.T) {
h := newSSHDReloadHarness(t)
h.reg.Register(&commands.Command{
Name: "fails",
Callback: func(fs any, a []string, w commands.StringWriter) error {
_ = w.WriteLine("nope")
return errors.New("failed")
},
})
client, _ := h.connect(t)
sess, err := client.NewSession()
require.NoError(t, err)
out, err := sess.CombinedOutput("fails")
var exit *ssh.ExitError
require.ErrorAs(t, err, &exit)
assert.Equal(t, 1, exit.ExitStatus())
assert.Equal(t, "nope\n", string(out))
sess, err = client.NewSession()
require.NoError(t, err)
out, err = sess.CombinedOutput("help fails")
require.NoError(t, err)
assert.Equal(t, "fails - \n", string(out))
// A word that is not a command is a failure too, with the command list as before.
sess, err = client.NewSession()
require.NoError(t, err)
out, err = sess.CombinedOutput("nope")
require.ErrorAs(t, err, &exit)
assert.Equal(t, 1, exit.ExitStatus())
assert.True(t, strings.HasPrefix(string(out), "did not understand: nope\nAvailable commands:\n"), string(out))
}
// A reload that can't bind the new address says so, rather than finding out in the background
func TestSSHDReload_BusyPortFails(t *testing.T) {
h := newSSHDReloadHarness(t)
busy, err := net.Listen("tcp", "127.0.0.1:0")
require.NoError(t, err)
t.Cleanup(func() { _ = busy.Close() })
res := h.c.ReloadConfigString(strings.Replace(h.config(), "127.0.0.1:0", busy.Addr().String(), 1))
require.NoError(t, res.Err)
assert.True(t, res.Failed)
}
+31 -88
View File
@@ -38,11 +38,6 @@ type statsServer struct {
runMu sync.Mutex
runCfg *statsConfig
run *statsRuntime // non-nil while a runtime is live
// Closed when the last runtime's capture loop has returned. Stop waits on it so nothing captures once it returns,
// and a reload's new runtime never overlaps the old one, go-metrics keeps its GC capture state in unguarded globals
loopDone chan struct{}
// See newStatsServerFromConfig, never changes after it
emitStats func()
}
// statsRuntime is the live state owned by a single Start invocation. Start
@@ -87,22 +82,17 @@ type promConfig struct {
//
// Start is safe to call unconditionally: it no-ops when stats are disabled.
// The returned pointer is always non-nil, even on error.
//
// emitStats, if set, updates metrics on every capture, ahead of the exporters so each export sees what it just set. It
// is fixed here, before the reload callback exists, so every runtime has it.
func newStatsServerFromConfig(ctx context.Context, l *slog.Logger, c *config.C, buildVersion string, configTest bool, emitStats func()) (*statsServer, error) {
func newStatsServerFromConfig(ctx context.Context, l *slog.Logger, c *config.C, buildVersion string, configTest bool) (*statsServer, error) {
s := &statsServer{
l: l,
ctx: ctx,
buildVersion: buildVersion,
configTest: configTest,
emitStats: emitStats,
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
c.RegisterReloadCallback(func(c *config.C) {
if err := s.reload(c, false); err != nil {
s.l.Error("Failed to reload stats from config", "error", err)
r.Failed()
}
})
@@ -130,6 +120,7 @@ func (s *statsServer) reload(c *config.C, initial bool) error {
s.runMu.Lock()
sameCfg := s.runCfg != nil && *s.runCfg == newCfg
s.runCfg = &newCfg
running := s.run != nil
s.runMu.Unlock()
s.enabled.Store(enabled)
@@ -138,15 +129,11 @@ func (s *statsServer) reload(c *config.C, initial bool) error {
return nil
}
// Even with nothing running, a runtime whose listener failed can still be finishing its last pass
if running {
s.Stop()
// Bind here rather than in the background, so a reload that can't listen says so
run, err := s.start()
if err != nil {
return err
}
if run != nil {
go run()
if enabled && !s.configTest {
go s.Start()
}
return nil
}
@@ -156,64 +143,30 @@ func (s *statsServer) reload(c *config.C, initial bool) error {
// the HTTP listener. For graphite it blocks on the capture loop's context.
// Safe to call when stats are disabled or already running (both no-op).
func (s *statsServer) Start() {
run, err := s.start()
if err != nil {
s.l.Error("Failed to start the prometheus stats listener", "error", err)
return
}
if run != nil {
run()
}
}
// start claims the runtime and binds the prometheus listener. The returned run serves it and blocks until Stop or ctx
// ends it. A nil run and no error means stats are off or already running.
func (s *statsServer) start() (func(), error) {
if !s.enabled.Load() || s.configTest {
return nil, nil
return
}
s.runMu.Lock()
defer s.runMu.Unlock()
if s.ctx.Err() != nil || s.run != nil || s.runCfg == nil {
return nil, nil
s.runMu.Unlock()
return
}
cfg := *s.runCfg
captureFns, listener := s.buildRuntime(cfg)
runCtx, cancel := context.WithCancel(s.ctx)
captureFns, listener := s.buildRuntime(runCtx, cfg)
var ln net.Listener
if listener != nil {
var err error
ln, err = net.Listen("tcp", listener.Addr)
if err != nil {
cancel()
// Drop the config so a SIGHUP with the same one tries again once the problem is fixed
s.runCfg = nil
return nil, err
}
}
rt := &statsRuntime{cancel: cancel, listener: listener}
s.run = rt
done := make(chan struct{})
s.loopDone = done
s.runMu.Unlock()
return func() { s.serve(runCtx, rt, captureFns, cfg.interval, ln, done) }, nil
}
// serve runs the capture loop, and the prometheus listener on ln, until Stop or ctx ends them.
func (s *statsServer) serve(runCtx context.Context, rt *statsRuntime, captureFns []func(), interval time.Duration, ln net.Listener, done chan struct{}) {
// Prime before serving, so a scrape that lands before the first tick sees real values instead of zeros (issue #907)
for _, fn := range captureFns {
fn()
}
go captureStatsLoop(runCtx, interval, captureFns, done)
go captureStatsLoop(runCtx, cfg.interval, captureFns)
cleanExit := true
if rt.listener == nil {
if listener == nil {
// Graphite: no HTTP listener to serve; block until teardown.
<-runCtx.Done()
} else {
cleanExit = s.serveListener(rt.listener, ln)
cleanExit = s.serveListener(listener)
}
// Clear our runtime only if nothing has replaced it. Stop races through
@@ -222,9 +175,10 @@ func (s *statsServer) serve(runCtx context.Context, rt *statsRuntime, captureFns
if s.run == rt {
rt.cancel()
s.run = nil
// A listener that exited with an error leaves runCfg cached as if it
// were applied. Drop it so a SIGHUP with the same config re-triggers
// Start once the user fixes the underlying problem.
// A listener that exited with an error (e.g., bind conflict) leaves
// runCfg cached as if it were applied. Drop it so a SIGHUP with the
// same config re-triggers Start once the user fixes the underlying
// problem.
if !cleanExit {
s.runCfg = nil
}
@@ -232,12 +186,12 @@ func (s *statsServer) serve(runCtx context.Context, rt *statsRuntime, captureFns
s.runMu.Unlock()
}
// serveListener serves listener on ln and ensures ctx cancellation unblocks it.
// serveListener runs ListenAndServe and ensures ctx cancellation unblocks it.
// Returns true if the listener exited cleanly (Stop, ctx cancellation, or any
// other http.ErrServerClosed path), false on an unexpected error.
func (s *statsServer) serveListener(listener *http.Server, ln net.Listener) bool {
func (s *statsServer) serveListener(listener *http.Server) bool {
// Per-invocation watcher: ctx cancellation triggers a listener shutdown
// which in turn unblocks Serve. Closing `done` on exit keeps
// which in turn unblocks ListenAndServe. Closing `done` on exit keeps
// the watcher from outliving this call.
done := make(chan struct{})
go func() {
@@ -253,8 +207,8 @@ func (s *statsServer) serveListener(listener *http.Server, ln net.Listener) bool
}()
defer close(done)
s.l.Info("Starting prometheus stats listener", "addr", ln.Addr())
err := listener.Serve(ln)
s.l.Info("Starting prometheus stats listener", "addr", listener.Addr)
err := listener.ListenAndServe()
if err == nil || errors.Is(err, http.ErrServerClosed) {
return true
}
@@ -264,12 +218,13 @@ func (s *statsServer) serveListener(listener *http.Server, ln net.Listener) bool
// Stop tears down the active runtime, if any. Idempotent.
func (s *statsServer) Stop() {
// Held until the last pass is done, a Start that slipped in after s.run cleared would capture alongside it
s.runMu.Lock()
defer s.runMu.Unlock()
rt := s.run
s.run = nil
if rt != nil {
s.runMu.Unlock()
if rt == nil {
return
}
rt.cancel()
if rt.listener != nil {
shutdownCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
@@ -278,18 +233,11 @@ func (s *statsServer) Stop() {
}
cancel()
}
}
// Nothing captures once Stop returns. The last runtime is cancelled by now, whoever cleared it, so this is at most
// the pass it was in. Nothing in a pass takes runMu
if s.loopDone != nil {
<-s.loopDone
}
}
// buildRuntime produces the capture functions and, for prometheus, an un-served
// http.Server from cfg. cfg has already been validated by loadStatsConfig.
// A graphite send in progress is abandoned when ctx is done.
func (s *statsServer) buildRuntime(ctx context.Context, cfg statsConfig) ([]func(), *http.Server) {
func (s *statsServer) buildRuntime(cfg statsConfig) ([]func(), *http.Server) {
// rcrowley/go-metrics guards these registrations with a private sync.Once,
// so subsequent reloads are no-ops.
metrics.RegisterDebugGCStats(metrics.DefaultRegistry)
@@ -299,9 +247,6 @@ func (s *statsServer) buildRuntime(ctx context.Context, cfg statsConfig) ([]func
func() { metrics.CaptureDebugGCStatsOnce(metrics.DefaultRegistry) },
func() { metrics.CaptureRuntimeMemStatsOnce(metrics.DefaultRegistry) },
}
if s.emitStats != nil {
captureFns = append(captureFns, s.emitStats)
}
switch cfg.typ {
case "graphite":
@@ -317,7 +262,7 @@ func (s *statsServer) buildRuntime(ctx context.Context, cfg statsConfig) ([]func
Percentiles: []float64{0.5, 0.75, 0.95, 0.99, 0.999},
}
captureFns = append(captureFns, func() {
if err := graphiteOnce(ctx, gcfg, graphiteTimeout); err != nil && ctx.Err() == nil {
if err := graphiteOnce(gcfg); err != nil {
s.l.Error("Graphite export failed", "error", err)
}
})
@@ -364,10 +309,8 @@ func (s *statsServer) buildRuntime(ctx context.Context, cfg statsConfig) ([]func
return captureFns, nil
}
// captureStatsLoop runs each fn on every tick of d until ctx is cancelled, then
// closes done.
func captureStatsLoop(ctx context.Context, d time.Duration, fns []func(), done chan struct{}) {
defer close(done)
// captureStatsLoop runs each fn on every tick of d until ctx is cancelled.
func captureStatsLoop(ctx context.Context, d time.Duration, fns []func()) {
t := time.NewTicker(d)
defer t.Stop()
for {
+30 -320
View File
@@ -2,18 +2,13 @@ package nebula
import (
"context"
"fmt"
"io"
"log/slog"
"net"
"net/http"
"net/http/httptest"
"strconv"
"sync/atomic"
"testing"
"time"
"github.com/rcrowley/go-metrics"
"github.com/slackhq/nebula/config"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
@@ -115,14 +110,15 @@ func TestStatsServer_reload_initial_prometheus(t *testing.T) {
}
func TestStatsServer_Start_graphite_blocksUntilStop(t *testing.T) {
h := newGraphiteHost(t, 0)
sink := newGraphiteSink(t)
defer sink.Close()
s, c := newTestStatsServer(t)
setStatsConfig(c, map[string]any{
"type": "graphite",
"interval": "1s",
"protocol": "tcp",
"host": h.ln.Addr().String(),
"host": sink.Addr(),
"prefix": "test",
})
require.NoError(t, s.reload(c, true))
@@ -375,19 +371,35 @@ func waitForListening(t *testing.T, addr string) {
})
}
// stopAtCleanup returns the ctx to build *s with, and stops it when the test ends. Cancelling first turns away a Start
// a reload spawned that hasn't run yet, then Stop waits out the last pass, so nothing captures into the next test
func stopAtCleanup(t *testing.T, s **statsServer) context.Context {
ctx, cancel := context.WithCancel(context.Background())
t.Cleanup(func() {
cancel()
if *s != nil {
(*s).Stop()
}
})
return ctx
// graphiteSink is a minimal TCP accept-and-discard server so graphiteOnce
// calls in tests don't spam error logs or wedge on connection refused.
type graphiteSink struct {
ln net.Listener
}
func newGraphiteSink(t *testing.T) *graphiteSink {
t.Helper()
ln, err := net.Listen("tcp", "127.0.0.1:0")
require.NoError(t, err)
g := &graphiteSink{ln: ln}
go func() {
for {
conn, err := ln.Accept()
if err != nil {
return
}
go func(c net.Conn) {
_, _ = io.Copy(io.Discard, c)
_ = c.Close()
}(conn)
}
}()
return g
}
func (g *graphiteSink) Addr() string { return g.ln.Addr().String() }
func (g *graphiteSink) Close() { _ = g.ln.Close() }
func freeTCPPort(t *testing.T) string {
t.Helper()
ln, err := net.Listen("tcp", "127.0.0.1:0")
@@ -396,305 +408,3 @@ func freeTCPPort(t *testing.T) string {
require.NoError(t, ln.Close())
return strconv.Itoa(port)
}
// Each export has to see what emitStats set in the same pass
func TestStatsServer_emitStatsRunsBeforeExport(t *testing.T) {
defer metrics.DefaultRegistry.Unregister("emitter.order.test")
l := slog.New(slog.DiscardHandler)
c := config.NewC(l)
setStatsConfig(c, map[string]any{
"type": "prometheus",
"interval": "1s",
"listen": "127.0.0.1:0",
"path": "/metrics",
})
gauge := metrics.GetOrRegisterGauge("emitter.order.test", nil)
s, err := newStatsServerFromConfig(t.Context(), l, c, "", false, func() { gauge.Update(42) })
require.NoError(t, err)
s.runMu.Lock()
fns, srv := s.buildRuntime(t.Context(), *s.runCfg)
s.runMu.Unlock()
require.NotNil(t, srv)
for _, fn := range fns {
fn()
}
rec := httptest.NewRecorder()
srv.Handler.ServeHTTP(rec, httptest.NewRequest("GET", "/metrics", nil))
assert.Contains(t, rec.Body.String(), "emitter_order_test 42")
}
// A scrape that lands the moment the listener is up already sees what emitStats set (issue #907)
func TestStatsServer_Start_primesBeforeServing(t *testing.T) {
defer metrics.DefaultRegistry.Unregister("prime.before.serving")
port := freeTCPPort(t)
l := slog.New(slog.DiscardHandler)
c := config.NewC(l)
setStatsConfig(c, map[string]any{
"type": "prometheus",
"interval": "1h",
"listen": "127.0.0.1:" + port,
"path": "/metrics",
})
gauge := metrics.GetOrRegisterGauge("prime.before.serving", nil)
// The pause would let a listener that came up before the prime serve the zero value
var s *statsServer
ctx := stopAtCleanup(t, &s)
s, err := newStatsServerFromConfig(ctx, l, c, "", false, func() {
time.Sleep(200 * time.Millisecond)
gauge.Update(42)
})
require.NoError(t, err)
go s.Start()
waitForListening(t, "127.0.0.1:"+port)
resp, err := http.Get("http://127.0.0.1:" + port + "/metrics")
require.NoError(t, err)
defer resp.Body.Close()
body, err := io.ReadAll(resp.Body)
require.NoError(t, err)
assert.Contains(t, string(body), "prime_before_serving 42")
}
// Start captures once before the first tick, the interval here is an hour
func TestStatsServer_Start_primes(t *testing.T) {
ln, err := net.Listen("tcp", "127.0.0.1:0")
require.NoError(t, err)
defer ln.Close()
l := slog.New(slog.DiscardHandler)
c := config.NewC(l)
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": ln.Addr().String()})
primed := make(chan struct{}, 1)
var s *statsServer
ctx := stopAtCleanup(t, &s)
s, err = newStatsServerFromConfig(ctx, l, c, "", false, func() {
select {
case primed <- struct{}{}:
default:
}
})
require.NoError(t, err)
go s.Start()
select {
case <-primed:
case <-time.After(5 * time.Second):
t.Fatal("nothing was captured before the first tick")
}
}
// Graphite has to ship what emitStats set in the same pass, not the pass before
func TestStatsServer_emitStatsRunsBeforeGraphiteExport(t *testing.T) {
defer metrics.DefaultRegistry.Unregister("emitter.graphite.test")
ln, err := net.Listen("tcp", "127.0.0.1:0")
require.NoError(t, err)
defer ln.Close()
received := make(chan string, 1)
go func() {
conn, err := ln.Accept()
if err != nil {
return
}
defer conn.Close()
b, _ := io.ReadAll(conn)
received <- string(b)
}()
l := slog.New(slog.DiscardHandler)
c := config.NewC(l)
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": ln.Addr().String()})
gauge := metrics.GetOrRegisterGauge("emitter.graphite.test", nil)
s, err := newStatsServerFromConfig(t.Context(), l, c, "", false, func() { gauge.Update(42) })
require.NoError(t, err)
s.runMu.Lock()
fns, _ := s.buildRuntime(t.Context(), *s.runCfg)
s.runMu.Unlock()
for _, fn := range fns {
fn()
}
select {
case body := <-received:
assert.Contains(t, body, ".emitter.graphite.test.value 42 ")
case <-time.After(5 * time.Second):
t.Fatal("graphite sent nothing")
}
}
// stats.interval reloads, and the runtime a reload starts still has emitStats
func TestStatsServer_reloadMovesTheInterval(t *testing.T) {
var passes atomic.Int64
l := slog.New(slog.DiscardHandler)
c := config.NewC(l)
// Nothing listens here, each export fails at once
host := "127.0.0.1:" + freeTCPPort(t)
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": host})
var s *statsServer
ctx := stopAtCleanup(t, &s)
s, err := newStatsServerFromConfig(ctx, l, c, "", false, func() { passes.Add(1) })
require.NoError(t, err)
go s.Start()
waitFor(t, func() bool { return passes.Load() == 1 })
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "20ms", "host": host})
require.NoError(t, s.reload(c, false))
waitFor(t, func() bool { return passes.Load() >= 6 })
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": host})
require.NoError(t, s.reload(c, false))
// The reload's Stop waited out the 20ms loop. The new runtime's prime may land either side of this read, it is the
// only pass left to come
stopped := passes.Load()
time.Sleep(300 * time.Millisecond)
assert.LessOrEqual(t, passes.Load()-stopped, int64(1), "the 20ms loop kept running after the reload")
}
// A reload's new runtime never captures while the old one is still in a pass, go-metrics keeps its GC capture state
// in unguarded globals
func TestStatsServer_reloadWaitsForTheLastPass(t *testing.T) {
var active, most atomic.Int64
l := slog.New(slog.DiscardHandler)
c := config.NewC(l)
host := "127.0.0.1:" + freeTCPPort(t)
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "10ms", "host": host})
var s *statsServer
ctx := stopAtCleanup(t, &s)
s, err := newStatsServerFromConfig(ctx, l, c, "", false, func() {
n := active.Add(1)
for {
m := most.Load()
if n <= m || most.CompareAndSwap(m, n) {
break
}
}
// Long enough that a reload almost always lands mid pass
time.Sleep(50 * time.Millisecond)
active.Add(-1)
})
require.NoError(t, err)
go s.Start()
for i := range 6 {
setStatsConfig(c, map[string]any{"type": "graphite", "interval": fmt.Sprintf("%dms", 11-i%2), "host": host})
require.NoError(t, s.reload(c, false))
time.Sleep(30 * time.Millisecond)
}
assert.Equal(t, int64(1), most.Load())
}
// Nothing captures once Stop returns, a pass in progress is waited out
func TestStatsServer_Stop_waitsForThePass(t *testing.T) {
var inPass atomic.Bool
entered := make(chan struct{}, 1)
l := slog.New(slog.DiscardHandler)
c := config.NewC(l)
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": "127.0.0.1:" + freeTCPPort(t)})
var s *statsServer
ctx := stopAtCleanup(t, &s)
s, err := newStatsServerFromConfig(ctx, l, c, "", false, func() {
inPass.Store(true)
select {
case entered <- struct{}{}:
default:
}
time.Sleep(100 * time.Millisecond)
inPass.Store(false)
})
require.NoError(t, err)
go s.Start()
select {
case <-entered:
case <-time.After(5 * time.Second):
t.Fatal("never captured")
}
s.Stop()
assert.False(t, inPass.Load(), "Stop returned with a pass still running")
}
// A Start that arrives while Stop waits out the last pass doesn't capture alongside it
func TestStatsServer_Start_duringStopWaitsForThePass(t *testing.T) {
var active, most atomic.Int64
entered := make(chan struct{}, 1)
l := slog.New(slog.DiscardHandler)
c := config.NewC(l)
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": "127.0.0.1:" + freeTCPPort(t)})
var s *statsServer
ctx := stopAtCleanup(t, &s)
s, err := newStatsServerFromConfig(ctx, l, c, "", false, func() {
n := active.Add(1)
for {
m := most.Load()
if n <= m || most.CompareAndSwap(m, n) {
break
}
}
select {
case entered <- struct{}{}:
default:
}
time.Sleep(200 * time.Millisecond)
active.Add(-1)
})
require.NoError(t, err)
go s.Start()
select {
case <-entered:
case <-time.After(5 * time.Second):
t.Fatal("never captured")
}
stopped := make(chan struct{})
go func() {
s.Stop()
close(stopped)
}()
// Stop holds runMu for its whole wait, the next Start has to arrive after it took it
waitFor(t, func() bool {
if s.runMu.TryLock() {
s.runMu.Unlock()
return false
}
return true
})
go s.Start()
select {
case <-stopped:
case <-time.After(5 * time.Second):
t.Fatal("Stop did not return")
}
waitFor(t, func() bool { return len(entered) == 1 })
assert.Equal(t, int64(1), most.Load(), "a Start captured alongside the pass Stop was waiting out")
}
// A reload that can't bind says so rather than finding out in the background, and the same config tries again once
// the port is free
func TestStatsServer_reload_bindFailureFails(t *testing.T) {
blocker, err := net.Listen("tcp", "127.0.0.1:0")
require.NoError(t, err)
port := strconv.Itoa(blocker.Addr().(*net.TCPAddr).Port)
s, c := newTestStatsServer(t)
stopAtCleanup(t, &s)
require.NoError(t, s.reload(c, true))
setStatsConfig(c, map[string]any{
"type": "prometheus",
"interval": "1s",
"listen": "127.0.0.1:" + port,
"path": "/metrics",
})
require.Error(t, s.reload(c, false))
assert.Nil(t, currentRuntime(s))
require.NoError(t, blocker.Close())
require.NoError(t, s.reload(c, false))
waitForListening(t, "127.0.0.1:"+port)
}
-29
View File
@@ -1,29 +0,0 @@
package test
import (
"flag"
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// Update is the -update flag: Golden rewrites its file instead of comparing against it.
var Update = flag.Bool("update", false, "rewrite golden files instead of comparing against them")
// Golden compares got with the file at path, or rewrites the file when -update is set.
func Golden(t *testing.T, path, got string) {
t.Helper()
if *Update {
require.NoError(t, os.MkdirAll(filepath.Dir(path), 0755))
require.NoError(t, os.WriteFile(path, []byte(got), 0644))
return
}
want, err := os.ReadFile(path)
require.NoError(t, err, "missing golden file, run with -update")
assert.Equal(t, string(want), got)
}
Loaded 100 of 113 files, more files were not shown because too many files have changed in this diff. Show more