mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-16 05:16:52 +01:00
Compare commits
14
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
a784af4026 | ||
|
|
5cbbba254e | ||
|
|
51591b0cec | ||
|
|
d16a52f921 | ||
|
|
82488caa32 | ||
|
|
eccaf1ca23 | ||
|
|
130ef730b4 | ||
|
|
ffb2835f70 | ||
|
|
eb073d6c23 | ||
|
|
e4f659a207 | ||
|
|
db8f9cd2e9 | ||
|
|
f3f98e1690 | ||
|
|
6146f3e4a6 | ||
|
|
6826c04103 |
No files matched your search
@@ -1,2 +0,0 @@
|
||||
# Goldens are compared byte for byte, so they must come out of git the way they went in.
|
||||
*.golden -text
|
||||
@@ -14,8 +14,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
### 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
|
||||
|
||||
+1
-10
@@ -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
|
||||
|
||||
@@ -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)
|
||||
}
|
||||
-710
@@ -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
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
@@ -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"
|
||||
)
|
||||
@@ -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
|
||||
}
|
||||
@@ -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())
|
||||
}
|
||||
@@ -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"`)
|
||||
}
|
||||
@@ -86,21 +86,6 @@ func (c *C) InitialLoad() bool {
|
||||
return c.oldSettings == nil
|
||||
}
|
||||
|
||||
// Render returns keys and their values as yaml, for a subsystem to remember what it applied. Empty means they couldn't
|
||||
// be rendered and should never match.
|
||||
func (c *C) Render(keys ...string) string {
|
||||
m := make(map[string]any, len(keys))
|
||||
for _, k := range keys {
|
||||
m[k] = c.Get(k)
|
||||
}
|
||||
b, err := yaml.Marshal(m)
|
||||
if err != nil {
|
||||
c.l.Debug("Failed to render config", "keys", keys, "error", err)
|
||||
return ""
|
||||
}
|
||||
return string(b)
|
||||
}
|
||||
|
||||
// HasChanged checks if the underlying structure of the provided key has changed after a config reload. The value of
|
||||
// k in both the old and new settings will be serialized, the result of the string comparison is returned.
|
||||
// If k is an empty string the entire config is tested.
|
||||
|
||||
+10
-1
@@ -14,6 +14,9 @@ import (
|
||||
)
|
||||
|
||||
const (
|
||||
// ReplayWindow is the build-time receive window and the assumed peer window
|
||||
// for TX reservation credit. Use a power of two; peers must match or have a
|
||||
// larger receive window. The bitmap costs ReplayWindow/8 bytes per tunnel.
|
||||
ReplayWindow = 8192
|
||||
|
||||
// RehandshakeAfterMessages rolls keys inside the AES-GCM data-volume margin (~2^-36 advantage at 64KB frames).
|
||||
@@ -41,6 +44,7 @@ type ConnectionState struct {
|
||||
peerCert *cert.CachedCertificate
|
||||
initiator bool
|
||||
messageCounter atomic.Uint64
|
||||
txBudget txBudget
|
||||
window *Bits
|
||||
decryptLock sync.Mutex
|
||||
writeLock sync.Mutex
|
||||
@@ -104,7 +108,7 @@ func (cs *ConnectionState) Decrypt(l *slog.Logger, messageCounter uint64, packet
|
||||
return nil, ErrAlreadySeen
|
||||
}
|
||||
|
||||
out, err := cs.dKey.DecryptDanger(packet[header.Len:header.Len], packet[:header.Len], packet[header.Len:], messageCounter, nb)
|
||||
out, err := cs.decryptPacket(messageCounter, packet, nb)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
@@ -118,6 +122,11 @@ func (cs *ConnectionState) Decrypt(l *slog.Logger, messageCounter uint64, packet
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// decryptPacket authenticates and decrypts packet in place, leaving the replay window to the caller.
|
||||
func (cs *ConnectionState) decryptPacket(messageCounter uint64, packet, nb []byte) ([]byte, error) {
|
||||
return cs.dKey.DecryptDanger(packet[header.Len:header.Len], packet[:header.Len], packet[header.Len:], messageCounter, nb)
|
||||
}
|
||||
|
||||
func (cs *ConnectionState) VerifyRelay(l *slog.Logger, messageCounter uint64, packet []byte, nb []byte) error {
|
||||
cs.decryptLock.Lock()
|
||||
result := cs.window.Check(l, messageCounter)
|
||||
|
||||
@@ -23,11 +23,20 @@ import (
|
||||
// runTestHandshake runs a complete IX handshake between two freshly-built
|
||||
// peers and returns the initiator and responder Results. Used to produce
|
||||
// real cipher states for tests that need to exercise post-handshake glue.
|
||||
func runTestHandshake(t *testing.T) (initR, respR *handshake.Result) {
|
||||
func runTestHandshake(t testing.TB) (initR, respR *handshake.Result) {
|
||||
t.Helper()
|
||||
return runTestHandshakeWith(t, noise.CipherChaChaPoly)
|
||||
}
|
||||
|
||||
// runTestHandshakeWith is runTestHandshake with the data plane cipher picked by the caller.
|
||||
func runTestHandshakeWith(t testing.TB, cipher noise.CipherFunc) (initR, respR *handshake.Result) {
|
||||
t.Helper()
|
||||
|
||||
// Valid around now rather than the cert_test default, which is fixed at process start and lapses a minute
|
||||
// later, inside a long -count run
|
||||
now := time.Now()
|
||||
ca, _, caKey, _ := ct.NewTestCaCert(
|
||||
cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil,
|
||||
cert.Version2, cert.Curve_CURVE25519, now.Add(-time.Minute), now.Add(time.Hour), nil, nil, nil,
|
||||
)
|
||||
caPool := ct.NewTestCAPool(ca)
|
||||
|
||||
@@ -40,7 +49,7 @@ func runTestHandshake(t *testing.T) (initR, respR *handshake.Result) {
|
||||
require.NoError(t, err)
|
||||
hsBytes, err := c.MarshalForHandshakes()
|
||||
require.NoError(t, err)
|
||||
ncs := noise.NewCipherSuite(noise.DH25519, noise.CipherChaChaPoly, noise.HashSHA256)
|
||||
ncs := noise.NewCipherSuite(noise.DH25519, cipher, noise.HashSHA256)
|
||||
cred := handshake.NewCredential(c, hsBytes, priv, ncs)
|
||||
return func(v cert.Version) *handshake.Credential {
|
||||
if v == cert.Version2 {
|
||||
|
||||
@@ -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
|
||||
}
|
||||
|
||||
@@ -1,164 +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())
|
||||
}
|
||||
Vendored
-720
@@ -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
|
||||
|
||||
@@ -5,9 +5,11 @@ package e2e
|
||||
import (
|
||||
"fmt"
|
||||
"net/netip"
|
||||
"runtime"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/e2e/router"
|
||||
@@ -570,3 +572,30 @@ func TestCloseTunnelAuthenticated(t *testing.T) {
|
||||
myControl.Stop()
|
||||
theirControl.Stop()
|
||||
}
|
||||
|
||||
// TestStagedTunnel completes a handshake and traffic both ways with staged receive. The test tun cannot hand off
|
||||
// batches, so transmit stays inline; every received packet, handshakes included, uses the receive pipeline on Linux.
|
||||
// Other platforms must do the same over the inline fallback.
|
||||
func TestStagedTunnel(t *testing.T) {
|
||||
t.Parallel()
|
||||
received := metrics.GetOrRegisterCounter("flow.rx.inline", nil)
|
||||
before := received.Count()
|
||||
staged := m{"tun": m{"staged": m{"workers": 2}}}
|
||||
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version1, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
|
||||
myControl, myVpnIpNet, myUdpAddr, _ := newSimpleServer(cert.Version1, ca, caKey, "me", "10.128.0.1/24", staged)
|
||||
theirControl, theirVpnIpNet, theirUdpAddr, _ := newSimpleServer(cert.Version1, ca, caKey, "them", "10.128.0.2/24", staged)
|
||||
myControl.InjectLightHouseAddr(theirVpnIpNet[0].Addr(), theirUdpAddr)
|
||||
theirControl.InjectLightHouseAddr(myVpnIpNet[0].Addr(), myUdpAddr)
|
||||
myControl.Start()
|
||||
theirControl.Start()
|
||||
r := router.NewR(t, myControl, theirControl)
|
||||
defer r.RenderFlow()
|
||||
assertTunnel(t, myVpnIpNet[0].Addr(), theirVpnIpNet[0].Addr(), myControl, theirControl, r)
|
||||
myControl.Stop()
|
||||
theirControl.Stop()
|
||||
if runtime.GOOS != "linux" {
|
||||
assert.Zero(t, received.Count()-before)
|
||||
return
|
||||
}
|
||||
assert.GreaterOrEqual(t, received.Count()-before, int64(2))
|
||||
}
|
||||
+38
-7
@@ -39,9 +39,8 @@ static_host_map:
|
||||
# public address. Other valid options are "ip6" and "ip" (returns both.)
|
||||
#network: ip4
|
||||
|
||||
# lookup_timeout is the DNS query timeout. A failed lookup keeps the last known good addresses, only a not found
|
||||
# answer removes them.
|
||||
#lookup_timeout: 5s
|
||||
# lookup_timeout is the DNS query timeout.
|
||||
#lookup_timeout: 250ms
|
||||
|
||||
lighthouse:
|
||||
# am_lighthouse is used to enable lighthouse functionality for a node. This should ONLY be true on nodes
|
||||
@@ -276,9 +275,42 @@ tun:
|
||||
# the use_offloads setting controls if Nebula will attempt to enable GSO and GRO for the tun device. Linux only, not reloadable.
|
||||
#use_offloads: false
|
||||
|
||||
# Linux only. staged.workers enables staged packet processing: each routine hands its batches to this many crypto
|
||||
# workers per direction, then sends or writes them in order. 0, the default, keeps processing inline. Not reloadable.
|
||||
# Transmit needs use_offloads; BoringCrypto and FIPS builds keep it inline because AES-GCM there needs ordered nonces.
|
||||
# Receive needs a listener that can hand off its batches, which Linux has.
|
||||
# IMPORTANT: staged senders require peers with at least the 8192-entry replay window of this release. Released
|
||||
# v1.11.x peers use 1024 and are incompatible. The window is not negotiated.
|
||||
# Staged reservations may use half the window, the other half absorbs inline and control traffic, relay forwarding
|
||||
# and network reordering; unlimited forwarding or delay can still exceed it. Waiting for credit on a busy tunnel
|
||||
# also delays the other tunnels of the same read, and readers are not guaranteed fairness.
|
||||
# Small batches, below inline_below TX segments or RX packets (default 256), can skip the workers. On transmit each
|
||||
# routine holds one mode, inline on the reader or fanout to the workers and the ordered sender, and switches only
|
||||
# after gate_hold (default 64) reads in a row want the other one. Before going inline it waits for every batch in
|
||||
# flight to be submitted to the socket; flow.tx.gate_switches counts the switches. This does not drain NIC queues.
|
||||
# Relay data always stays on the reader, so gate switches and oversized reads cannot move it between NIC queues.
|
||||
# Direct data retains the adaptive gate and independent sender placement.
|
||||
# On receive a listener with nothing in flight writes a small batch itself. With multiple routines, inline sends
|
||||
# still take tunnel reservation credit. 0 hands direct TX and all RX batches to the workers and ordered stages;
|
||||
# relayed TX and reads too large for a tunnel's whole credit are still sent by the reader.
|
||||
# tx: false keeps transmit inline and stages only receive.
|
||||
# tx_slots and rx_slots bound the batches each routine has in flight per direction, minimum 2. A TX slot holds one
|
||||
# tun read and its ciphertext, about 1.1 MiB; the default is 8, or workers + 2 if more. An RX slot holds one
|
||||
# recvmmsg batch, listen.batch * 64 KiB with udp_offloads or * 9 KiB without; the default keeps up to 384 receive
|
||||
# entries in flight in 4 to 6 slots: 6 slots or 24 MiB at the default listen.batch of 64. Lower them to save memory.
|
||||
#staged:
|
||||
# workers: 0
|
||||
# tx: true
|
||||
# inline_below: 256
|
||||
# gate_hold: 64
|
||||
# tx_slots: 8
|
||||
# rx_slots: 6
|
||||
|
||||
# Linux only. pin_threads pins each tun reader/encrypt OS thread to a single CPU. This keeps every goroutine's
|
||||
# batched sends flowing through one XPS-selected NIC TX ring, so packets within a flow stay ordered on the wire
|
||||
# instead of being sprayed across multiple TX rings and reordered. Not reloadable. Coerced to false if routines <= 1.
|
||||
# Staged senders are only pinned with an explicit cpu_affinity, see below; otherwise the scheduler places them.
|
||||
# Small batches a reader sends itself can use a different TX ring than its sender.
|
||||
#pin_threads: true
|
||||
|
||||
# pin_threads_key helps the CPU-auto-selector shuffle which CPUs are chosen for pinning.
|
||||
@@ -288,7 +320,9 @@ tun:
|
||||
|
||||
# Linux only. cpu_affinity overrides which CPUs the tun reader threads pin to: a list of CPU IDs, one per routine
|
||||
# (see the top-level `routines` setting). Lists shorter than `routines` are modulo-cycled across the queues; extra
|
||||
# entries are ignored. IDs must be within the process's allowed CPU set, so this respects taskset / cgroup cpusets;
|
||||
# entries are ignored. Staged sender i pins to entry i+1, modulo-cycled the same way, unless that is its reader's
|
||||
# CPU, as with a one-entry list: a sender never shares its reader's CPU and stays unpinned instead.
|
||||
# IDs must be within the process's allowed CPU set, so this respects taskset / cgroup cpusets;
|
||||
# a non-integer or not-allowed entry disables the override, leaving the default pin selection described below.
|
||||
# Only meaningful while pin_threads is true. Not reloadable.
|
||||
# When unset (or rejected), the default spread prefers performance cores on heterogeneous CPUs (ARM big.LITTLE,
|
||||
@@ -332,9 +366,6 @@ tun:
|
||||
# `mtu`: will default to tun mtu if this option is not specified
|
||||
# `metric`: will default to 0 if this option is not specified
|
||||
# `install`: will default to true, controls whether this route is installed in the systems routing table.
|
||||
# On macOS, a route whose destination another interface already routes, like the local network, is installed once
|
||||
# that route is removed. One deleted by hand stays deleted until nebula reloads or restarts, or until another
|
||||
# interface routes its destination and lets it go.
|
||||
# This setting is reloadable.
|
||||
unsafe_routes:
|
||||
#- route: 172.16.1.0/24
|
||||
|
||||
@@ -66,9 +66,6 @@ type Firewall struct {
|
||||
rules string
|
||||
rulesVersion uint16
|
||||
|
||||
// source is the rendered firewall config this firewall was built from, the cert networks are kept above
|
||||
source string
|
||||
|
||||
defaultLocalCIDRAny bool
|
||||
incomingMetrics firewallMetrics
|
||||
outgoingMetrics firewallMetrics
|
||||
@@ -249,7 +246,6 @@ func NewFirewallFromConfig(l *slog.Logger, cs *CertState, c *config.C) (*Firewal
|
||||
return nil, err
|
||||
}
|
||||
|
||||
fw.source = c.Render("firewall")
|
||||
return fw, nil
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,123 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"log/slog"
|
||||
"runtime"
|
||||
"sync"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/noiseutil"
|
||||
)
|
||||
|
||||
// Staged processing (tun.staged.workers) moves crypto off each tun reader and udp listener onto worker goroutines,
|
||||
// behind which an ordered stage sends or writes every batch in read order. It reuses the inline packet handlers:
|
||||
// staging changes ownership and scheduling, not policy. Each routine has its own workers and ordered stages, so order
|
||||
// is per routine. Full queues block the reader. A read error drains the batches in flight, while shutdown waits for
|
||||
// the crypto and then drops packets whose destination has closed. A TX slot holds one tun read and its ciphertext,
|
||||
// about 1.1 MiB; there are eight, or two more than the workers. An RX slot holds one recvmmsg batch, listen.batch
|
||||
// times 64 KiB with GRO, and the count keeps up to 384 entries in flight in four to six slots: six and 24 MiB at
|
||||
// listen.batch=64.
|
||||
// tun.staged.tx_slots and rx_slots override the counts. Small-MSS TX arenas can grow.
|
||||
// Relay data stays on the tun reader, regardless of the TX gate, so it never switches between reader and sender
|
||||
// NIC queues. Direct data keeps its adaptive placement; relay and direct batches both share tunnel counter credit.
|
||||
//
|
||||
// Metrics are registered only for active pipelines. flow.{tx,rx}.batches counts reads handed to the ordered stage and
|
||||
// flow.{tx,rx}.inline those the reader handled itself (TX inline also counts oversized reads); their rates show
|
||||
// whether staging is used. flow.tx.gate_switches counts transmit switches between inline and fanout mode.
|
||||
|
||||
// stagedConfig is tun.staged. workers is per routine and direction; zero keeps processing inline.
|
||||
type stagedConfig struct {
|
||||
workers int
|
||||
tx bool
|
||||
rx bool
|
||||
// inlineBelow is the TX segment or RX packet count below which a read may skip the worker handoff, 0 never: a TX
|
||||
// read in inline mode, an RX read with nothing in flight
|
||||
inlineBelow int
|
||||
// txSlots and rxSlots are how many batches each routine can have in flight per direction
|
||||
txSlots, rxSlots int
|
||||
// gateHold is how many TX reads in a row must want the other mode before a routine switches between inline and
|
||||
// fanout transmit
|
||||
gateHold int
|
||||
}
|
||||
|
||||
// stagedGateHold is the default tun.staged.gate_hold
|
||||
const stagedGateHold = 64
|
||||
|
||||
const (
|
||||
// stagedTxSlots is the default TX slot count, unless the workers need more
|
||||
stagedTxSlots = 8
|
||||
// stagedRxEntries is how many recvmmsg entries the RX slots hold in flight by default
|
||||
stagedRxEntries = 6 * 64
|
||||
// stagedMinSlots lets the reader fill one batch while another is in flight
|
||||
stagedMinSlots = 2
|
||||
// stagedMinRxSlots keeps the default RX pipeline deep enough for large listen.batch values
|
||||
stagedMinRxSlots = 4
|
||||
// stagedMaxRxSlots is the measured default, a smaller listen.batch does not take more slots
|
||||
stagedMaxRxSlots = 6
|
||||
)
|
||||
|
||||
// stagedSlots sizes the TX and RX slots. TX reads are bounded by the tun queue, so one slot per worker plus the one
|
||||
// being read and the one being sent, and at least the eight measured. RX slots keep stagedRxEntries in flight, four
|
||||
// to six, so a larger listen.batch means fewer slots and RX memory never exceeds the six measured. A positive override replaces either, down to stagedMinSlots.
|
||||
func stagedSlots(workers, batch, txOverride, rxOverride int) (tx, rx int) {
|
||||
tx = max(stagedTxSlots, workers+2)
|
||||
rx = min(max(stagedMinRxSlots, (stagedRxEntries+batch-1)/max(batch, 1)), stagedMaxRxSlots)
|
||||
if txOverride > 0 {
|
||||
tx = max(txOverride, stagedMinSlots)
|
||||
}
|
||||
if rxOverride > 0 {
|
||||
rx = max(rxOverride, stagedMinSlots)
|
||||
}
|
||||
return tx, rx
|
||||
}
|
||||
|
||||
// parseStagedConfig enables staging on Linux only; queues and conns that cannot hand off batches also stay inline.
|
||||
func parseStagedConfig(c *config.C, l *slog.Logger) stagedConfig {
|
||||
sc := stagedConfig{workers: c.GetInt("tun.staged.workers", 0)}
|
||||
if sc.workers <= 0 {
|
||||
return stagedConfig{}
|
||||
}
|
||||
if runtime.GOOS != "linux" {
|
||||
l.Warn("tun.staged is only supported on Linux; packet processing stays inline")
|
||||
return stagedConfig{}
|
||||
}
|
||||
sc.tx, sc.rx = c.GetBool("tun.staged.tx", true), true
|
||||
// 256 is the measured crossover, 0 hands every batch to the workers
|
||||
sc.inlineBelow = max(c.GetInt("tun.staged.inline_below", 256), 0)
|
||||
if sc.tx && noiseutil.EncryptLockNeeded {
|
||||
l.Warn("tun.staged cannot encrypt in parallel with boringcrypto or fips140; transmit stays inline")
|
||||
sc.tx = false
|
||||
}
|
||||
sc.gateHold = max(c.GetInt("tun.staged.gate_hold", stagedGateHold), 1)
|
||||
sc.txSlots, sc.rxSlots = stagedSlots(sc.workers, c.GetInt("listen.batch", 64),
|
||||
c.GetInt("tun.staged.tx_slots", 0), c.GetInt("tun.staged.rx_slots", 0))
|
||||
l.Info("Staged packet processing enabled", "workers", sc.workers, "tx", sc.tx, "rx", sc.rx,
|
||||
"inlineBelow", sc.inlineBelow, "gateHold", sc.gateHold,
|
||||
"txSlots", sc.txSlots, "rxSlots", sc.rxSlots)
|
||||
return sc
|
||||
}
|
||||
|
||||
// flowJob is one batch of crypto work. It owns its packet buffers until run returns; jobs and queues are reused.
|
||||
type flowJob interface{ run(nb []byte) }
|
||||
|
||||
// flowPool runs one reader's crypto jobs. The reader is the only producer and closes the pool once its ordered stage
|
||||
// has drained.
|
||||
type flowPool struct {
|
||||
jobs chan flowJob
|
||||
wg sync.WaitGroup
|
||||
}
|
||||
|
||||
func newFlowPool(workers, queueLen int) *flowPool {
|
||||
p := &flowPool{jobs: make(chan flowJob, queueLen)}
|
||||
for range workers {
|
||||
p.wg.Go(func() {
|
||||
nb := make([]byte, 12)
|
||||
for job := range p.jobs {
|
||||
job.run(nb)
|
||||
}
|
||||
})
|
||||
}
|
||||
return p
|
||||
}
|
||||
|
||||
func (p *flowPool) close() { close(p.jobs); p.wg.Wait() }
|
||||
+177
@@ -0,0 +1,177 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"sync/atomic"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/overlay/tio"
|
||||
)
|
||||
|
||||
// txBudget is the reservation credit of one tunnel, shared by every staged reader sending on it. The low 24 bits of
|
||||
// state are outstanding counters, the next 24 spent credit, and the top 16 the sole ordered reader (q+1); owner zero
|
||||
// means shared. Readers beyond the owner field's range always take the conservative shared path.
|
||||
//
|
||||
// A cap on outstanding counters alone is not enough: a fast reader could repeatedly send and reacquire credit,
|
||||
// overtaking a paused reader by arbitrarily far. So once readers overlap, or another reader is blocked, spent credit
|
||||
// is only recycled when ALL reservations have drained. A sole reader instead gets each ordered completion refunded,
|
||||
// its later batches cannot overtake its earlier ones. All transitions are one CAS, without locks.
|
||||
//
|
||||
// The credit is half the peer's replay window. The other half is left for uncredited sends and transport reordering:
|
||||
// inline and control traffic, and relay forwarding through SendVia, which takes counters on the relay tunnel without
|
||||
// credit. Unlimited bypass traffic or network delay can still exceed it. The window is not negotiated, so
|
||||
// ci.window.length, from the build-time ReplayWindow, is also the assumed peer window.
|
||||
type txBudget struct{ state atomic.Uint64 }
|
||||
|
||||
const txBudgetMask = uint64(1<<24 - 1)
|
||||
|
||||
// Fail compilation for unsupported build-time windows: a power of two, at least 8192, fitting the credit fields (up
|
||||
// to 16777216).
|
||||
const (
|
||||
_ = uint64(txBudgetMask) - ReplayWindow/2
|
||||
_ = uint64(ReplayWindow) - 8192
|
||||
_ = uint64(0) - (ReplayWindow & (ReplayWindow - 1))
|
||||
)
|
||||
|
||||
func txBudgetOwner(q int) uint64 {
|
||||
if q < 0 || q >= 65535 {
|
||||
return 0
|
||||
}
|
||||
return uint64(q + 1)
|
||||
}
|
||||
|
||||
func (b *txBudget) acquire(n, limit, owner uint64) bool {
|
||||
for {
|
||||
old := b.state.Load()
|
||||
pending, spent, who := old&txBudgetMask, (old>>24)&txBudgetMask, old>>48
|
||||
if n > limit || spent > limit-n {
|
||||
// A blocked reader ends sole ownership so ordered completions stop refunding credit. Otherwise a busy
|
||||
// owner could keep a larger waiter blocked forever without ever sharing a reservation.
|
||||
if who != 0 && who != owner && !b.state.CompareAndSwap(old, old&^(uint64(0xffff)<<48)) {
|
||||
continue
|
||||
}
|
||||
return false
|
||||
}
|
||||
if pending == 0 {
|
||||
who = owner
|
||||
} else if who != owner {
|
||||
who = 0
|
||||
}
|
||||
next := who<<48 | (spent+n)<<24 | (pending + n)
|
||||
if b.state.CompareAndSwap(old, next) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// release runs only after the socket flush or an explicit drop. A rollback returns credit before any message counter
|
||||
// was allocated, as when a later tunnel of a relay or multi-tunnel batch could not acquire its own.
|
||||
func (b *txBudget) release(n uint64, rollback bool) {
|
||||
for {
|
||||
old := b.state.Load()
|
||||
pending, spent, owner := old&txBudgetMask, (old>>24)&txBudgetMask, old>>48
|
||||
pending -= n
|
||||
if rollback || owner != 0 {
|
||||
spent -= n
|
||||
}
|
||||
next := owner<<48 | spent<<24 | pending
|
||||
if pending == 0 {
|
||||
next = 0
|
||||
}
|
||||
if b.state.CompareAndSwap(old, next) {
|
||||
return
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func (ci *ConnectionState) txBudgetLimit() uint64 { return ci.window.length / 2 }
|
||||
|
||||
func (r *txReserver) oversized() bool {
|
||||
for _, t := range r.tunnels {
|
||||
if t.n > t.ci.txBudgetLimit() {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
func (r *txReserver) tryBudget() bool {
|
||||
for i, t := range r.tunnels {
|
||||
if !t.ci.txBudget.acquire(t.n, t.ci.txBudgetLimit(), r.owner) {
|
||||
for _, acquired := range r.tunnels[:i] {
|
||||
acquired.ci.txBudget.release(acquired.n, true)
|
||||
}
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// waitBudget acquires credit for every tunnel of the batch, never holding a partial acquisition while it waits. Each
|
||||
// reader first flushes its own oldest batch, flushes need no credit; with none, another reader holds all outstanding
|
||||
// work and can flush it independently. So there is no circular wait, even with relay tunnels acquired in opposite
|
||||
// orders. The sleep is only for readers with no local work, not the uncontended hot path. Acquisition is
|
||||
// all-or-nothing within each direct or relay batch, so pressure on one tunnel also delays packets for idle tunnels
|
||||
// in that batch. Reader fairness is not guaranteed.
|
||||
func (p *stagedTx) waitBudget(r *txReserver) bool {
|
||||
if r.tryBudget() {
|
||||
return true
|
||||
}
|
||||
for {
|
||||
if p.f.closed.Load() {
|
||||
return false
|
||||
}
|
||||
if !p.flushOldest() {
|
||||
time.Sleep(50 * time.Microsecond)
|
||||
}
|
||||
if r.tryBudget() {
|
||||
return true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func (s *txSlot) releaseBudget() {
|
||||
for _, t := range s.reservations {
|
||||
t.ci.txBudget.release(t.n, false)
|
||||
}
|
||||
clear(s.reservations)
|
||||
s.reservations = s.reservations[:0]
|
||||
}
|
||||
|
||||
// sendLarge handles the unusual reads that exceed a whole tunnel's credit, such as tiny-MSS superpackets. It drains
|
||||
// the pipeline, then segments and sends them synchronously with credit for each segment, never exceeding the cap and
|
||||
// never filtering or running connection manager side effects twice. This deliberately slow path avoids a lone-batch
|
||||
// exception to the shared invariant.
|
||||
func (p *stagedTx) sendLarge(r *txReserver, items []txItem) {
|
||||
for p.flushOldest() {
|
||||
}
|
||||
for _, it := range items {
|
||||
err := tio.SegmentSuperpacket(it.pkt, func(seg []byte) error {
|
||||
if p.f.closed.Load() {
|
||||
return nil
|
||||
}
|
||||
part := it
|
||||
part.pkt, part.segs = tio.Packet{Bytes: seg}, 1
|
||||
r.tunnels = r.tunnels[:0]
|
||||
part.counter = r.need(part.hostinfo, part.ci, 1)
|
||||
if part.relayHI != nil {
|
||||
part.relayCounter = r.need(part.relayHI, part.relayHI.ConnectionState, 1)
|
||||
}
|
||||
if !p.waitBudget(r) {
|
||||
return nil
|
||||
}
|
||||
one := [1]txItem{part}
|
||||
if reserved := r.reserve(one[:]); len(reserved) != 0 {
|
||||
p.f.encryptTxItem(&reserved[0], p.nb, p.sb)
|
||||
p.f.flushSendBatch(p.sb, p.q)
|
||||
}
|
||||
for _, t := range r.tunnels {
|
||||
t.ci.txBudget.release(t.n, false)
|
||||
}
|
||||
return nil
|
||||
})
|
||||
if err != nil {
|
||||
it.hostinfo.logger(p.f.l).Error("Failed to segment superpacket for send", "error", err)
|
||||
}
|
||||
}
|
||||
clear(items)
|
||||
}
|
||||
@@ -0,0 +1,104 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
var budgetWindows = []uint64{8192, 65536}
|
||||
|
||||
// TestTXBudgetOvertaking: a fast sender must not recycle credit around a stalled older reservation. A pure in-flight
|
||||
// count passes the cap assertion but fails this replay test.
|
||||
func TestTXBudgetOvertaking(t *testing.T) {
|
||||
for _, window := range budgetWindows {
|
||||
t.Run(fmt.Sprint(window), func(t *testing.T) {
|
||||
var b txBudget
|
||||
limit := window / 2
|
||||
w := NewBits(window)
|
||||
l := test.NewLogger()
|
||||
require.True(t, b.acquire(1, limit, 1)) // counter 1 stalls
|
||||
for counter := uint64(2); counter <= limit; counter++ {
|
||||
require.True(t, b.acquire(1, limit, 2))
|
||||
require.True(t, w.Update(l, counter))
|
||||
b.release(1, false)
|
||||
}
|
||||
require.Equal(t, uint64(1), b.state.Load()&txBudgetMask)
|
||||
require.False(t, b.acquire(1, limit, 2), "spent credit cannot be recycled while the oldest sender stalls")
|
||||
// The other half of the window allows this many unreserved sends.
|
||||
for counter := limit + 1; counter <= window; counter++ {
|
||||
require.True(t, w.Update(l, counter))
|
||||
}
|
||||
require.True(t, w.Update(l, 1), "oldest reservation must still fit after using the whole margin")
|
||||
b.release(1, false)
|
||||
require.Zero(t, b.state.Load())
|
||||
require.True(t, b.acquire(limit, limit, 2))
|
||||
require.False(t, b.acquire(1, limit, 2))
|
||||
b.release(limit, false)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestTXBudgetBlockedReader models eight 512-segment reads of a busy owner and a 568-segment waiter, without socket
|
||||
// timing. Alone, the owner gets each completion refunded, so it keeps eight batches in flight forever, even across its
|
||||
// own failed acquisitions. But even when the owner always retries first, its completions must stop refunding credit
|
||||
// once the waiter is blocked, and let the budget drain. Waiter 0 is the conservative ID of readers beyond the owner
|
||||
// field's range.
|
||||
func TestTXBudgetBlockedReader(t *testing.T) {
|
||||
for _, waiter := range []uint64{1, 0} {
|
||||
t.Run(fmt.Sprintf("waiter=%d", waiter), func(t *testing.T) {
|
||||
var b txBudget
|
||||
const limit, n, want = uint64(4096), uint64(512), uint64(568)
|
||||
for range 8 {
|
||||
require.True(t, b.acquire(n, limit, 2))
|
||||
}
|
||||
for range 100 {
|
||||
require.False(t, b.acquire(n, limit, 2))
|
||||
b.release(n, false) // the sole sender flushes its oldest batch
|
||||
require.True(t, b.acquire(n, limit, 2))
|
||||
require.Equal(t, 8*n, b.state.Load()&txBudgetMask)
|
||||
}
|
||||
require.False(t, b.acquire(want, limit, waiter))
|
||||
for range 7 {
|
||||
b.release(n, false)
|
||||
require.False(t, b.acquire(n, limit, 2), "blocked reader must stop the owner's credit recycling")
|
||||
require.False(t, b.acquire(want, limit, waiter))
|
||||
}
|
||||
b.release(n, false)
|
||||
require.Zero(t, b.state.Load())
|
||||
// Even if the former owner wins the next acquisition, both now fit.
|
||||
require.True(t, b.acquire(n, limit, 2))
|
||||
require.True(t, b.acquire(want, limit, waiter))
|
||||
b.release(n, false)
|
||||
b.release(want, false)
|
||||
require.Zero(t, b.state.Load())
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestTXBudgetRelayRollback: when a later tunnel of a batch cannot acquire, the earlier ones give their credit back,
|
||||
// spent credit included.
|
||||
func TestTXBudgetRelayRollback(t *testing.T) {
|
||||
for _, window := range budgetWindows {
|
||||
inner := &ConnectionState{window: NewBits(window)}
|
||||
outer := &ConnectionState{window: NewBits(window)}
|
||||
limit := inner.txBudgetLimit()
|
||||
require.True(t, inner.txBudget.acquire(10, limit, 1))
|
||||
require.True(t, outer.txBudget.acquire(limit, limit, 1))
|
||||
r := txReserver{owner: 2, tunnels: []txTunnel{{ci: inner, n: 20}, {ci: outer, n: 20}}}
|
||||
for range 100 {
|
||||
require.False(t, r.tryBudget())
|
||||
require.Equal(t, uint64(10), inner.txBudget.state.Load()&txBudgetMask)
|
||||
require.Equal(t, uint64(10), (inner.txBudget.state.Load()>>24)&txBudgetMask, "rollback must refund spent credit too")
|
||||
}
|
||||
outer.txBudget.release(limit, false)
|
||||
require.True(t, r.tryBudget())
|
||||
inner.txBudget.release(20, false)
|
||||
outer.txBudget.release(20, false)
|
||||
inner.txBudget.release(10, false)
|
||||
require.Zero(t, inner.txBudget.state.Load())
|
||||
require.Zero(t, outer.txBudget.state.Load())
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,135 @@
|
||||
//go:build linux && !android && !e2e_testing
|
||||
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/flynn/noise"
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/overlay/tio"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/require"
|
||||
"go.uber.org/goleak"
|
||||
)
|
||||
|
||||
// gated is staging with an inline threshold of 4 segments and the given gate hold.
|
||||
func gated(hold int) stagedConfig {
|
||||
sc := adaptive(2)
|
||||
sc.inlineBelow, sc.gateHold = 4, hold
|
||||
return sc
|
||||
}
|
||||
|
||||
// gateCounters snapshots the transmit counters a gate test checks.
|
||||
type gateCounters struct{ inline, batches, switches int64 }
|
||||
|
||||
func readGateCounters() gateCounters {
|
||||
return gateCounters{
|
||||
inline: metrics.GetOrRegisterCounter("flow.tx.inline", nil).Count(),
|
||||
batches: metrics.GetOrRegisterCounter("flow.tx.batches", nil).Count(),
|
||||
switches: metrics.GetOrRegisterCounter("flow.tx.gate_switches", nil).Count(),
|
||||
}
|
||||
}
|
||||
|
||||
func (c gateCounters) since(c0 gateCounters) gateCounters {
|
||||
return gateCounters{c.inline - c0.inline, c.batches - c0.batches, c.switches - c0.switches}
|
||||
}
|
||||
|
||||
// gateReads builds reads of small (3 segments, below the threshold) or large (2 superpackets of 9) shape, in order,
|
||||
// for one flow, and the segments they carry.
|
||||
func gateReads(large ...bool) ([][]tio.Packet, []decodedSeg) {
|
||||
var reads [][]tio.Packet
|
||||
var want []decodedSeg
|
||||
seq := uint32(0)
|
||||
for _, l := range large {
|
||||
per, segs := 1, 3
|
||||
if l {
|
||||
per, segs = 2, 9
|
||||
}
|
||||
var b []tio.Packet
|
||||
for range per {
|
||||
b = append(b, flowTCPSuperpacket(0, seq, segs))
|
||||
for s := range segs {
|
||||
want = append(want, decodedSeg{seq: seq, idx: uint16(s)})
|
||||
}
|
||||
seq++
|
||||
}
|
||||
reads = append(reads, b)
|
||||
}
|
||||
return reads, want
|
||||
}
|
||||
|
||||
func repeatBool(v bool, n int) []bool {
|
||||
out := make([]bool, n)
|
||||
for i := range out {
|
||||
out[i] = v
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// TestFlowStagedTXGateSwitch forces the gate from inline to fanout and back, with a slow socket and slow
|
||||
// workers so the fanout batches are still in flight when the small reads arrive: wire order is read order, counters
|
||||
// are contiguous, and each switch happens on exactly the gate_hold-th read that wants it.
|
||||
func TestFlowStagedTXGateSwitch(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
const hold = 3
|
||||
for _, routines := range []int{1, 2} {
|
||||
t.Run(fmt.Sprintf("routines=%d", routines), func(t *testing.T) {
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, gated(hold))
|
||||
sender.f.routines = routines
|
||||
sender.f.writers = []udp.Conn{sender.conn, sender.conn}
|
||||
delayCrypto(sender, func(n uint64) {
|
||||
if n%7 == 0 {
|
||||
time.Sleep(time.Millisecond)
|
||||
}
|
||||
})
|
||||
sender.conn.delay = 4 * time.Millisecond
|
||||
// 4 small inline, 2 large held inline, 6 large fanout from the switch on, 2 small held in fanout, then
|
||||
// the switch back drains and 3 small go inline
|
||||
shape := append(repeatBool(false, 4), repeatBool(true, 8)...)
|
||||
shape = append(shape, repeatBool(false, 5)...)
|
||||
reads, want := gateReads(shape...)
|
||||
ci := sender.hostinfo.ConnectionState
|
||||
start := ci.messageCounter.Load()
|
||||
c0 := readGateCounters()
|
||||
p := newStagedTx(sender.f, newFlowBatchQueue(nil), 0)
|
||||
for i, r := range reads {
|
||||
p.send(r)
|
||||
if i == 13 {
|
||||
require.Positive(t, p.inFlight, "fanout batches must still be in flight when the small reads start")
|
||||
}
|
||||
if i == 14 {
|
||||
require.Zero(t, p.inFlight, "switching to inline drains the pipeline")
|
||||
}
|
||||
}
|
||||
p.close()
|
||||
require.Equal(t, want, decryptWire(t, receiver, sender.conn.captured()), "wire order must match read order")
|
||||
require.Equal(t, start+uint64(len(want)), ci.messageCounter.Load(), "every reserved counter is used once")
|
||||
require.Equal(t, gateCounters{inline: 4 + 2 + 3, batches: 6 + 2, switches: 2}, readGateCounters().since(c0))
|
||||
require.Zero(t, ci.txBudget.state.Load())
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestFlowStagedTXGateHold: the gate never switches before gate_hold consecutive reads want the other mode, and
|
||||
// a read that wants the current mode restarts the count.
|
||||
func TestFlowStagedTXGateHold(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
const hold = 5
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, gated(hold))
|
||||
shape := append(repeatBool(true, hold-1), false)
|
||||
shape = append(shape, repeatBool(true, hold-1)...)
|
||||
reads, want := gateReads(append(shape, true)...)
|
||||
c0 := readGateCounters()
|
||||
p := newStagedTx(sender.f, newFlowBatchQueue(nil), 0)
|
||||
for _, r := range reads[:len(reads)-1] {
|
||||
p.send(r)
|
||||
}
|
||||
require.Equal(t, gateCounters{inline: 2*hold - 1}, readGateCounters().since(c0), "no switch before gate_hold")
|
||||
p.send(reads[len(reads)-1])
|
||||
require.Equal(t, gateCounters{inline: 2*hold - 1, batches: 1, switches: 1}, readGateCounters().since(c0))
|
||||
p.close()
|
||||
require.Equal(t, want, decryptWire(t, receiver, sender.conn.captured()))
|
||||
}
|
||||
+371
@@ -0,0 +1,371 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
"net/netip"
|
||||
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
)
|
||||
|
||||
// handoffConn is a udp conn that can hand each received batch over. The callback returns replacement buffers with
|
||||
// the same count and at least the same lengths.
|
||||
type handoffConn interface {
|
||||
ListenOutHandoff(udp.EncReader, func([][]byte) [][]byte) error
|
||||
}
|
||||
|
||||
const rxChunkMin = 16
|
||||
|
||||
// rxItem is one received packet. A data packet for an established tunnel has ci set; out and err are written by
|
||||
// whoever decrypts it.
|
||||
type rxItem struct {
|
||||
packet []byte
|
||||
hostinfo *HostInfo
|
||||
ci *ConnectionState
|
||||
counter uint64
|
||||
via netip.AddrPort
|
||||
out []byte
|
||||
err error
|
||||
}
|
||||
|
||||
// rxChunk is a contiguous run of a batch's items for one worker to decrypt.
|
||||
type rxChunk struct {
|
||||
items []rxItem
|
||||
done chan struct{}
|
||||
}
|
||||
|
||||
func (c *rxChunk) run(nb []byte) {
|
||||
decryptRxItems(c.items, nb)
|
||||
c.done <- struct{}{}
|
||||
}
|
||||
|
||||
// decryptRxItems decrypts the data packets among items in place. The replay window is left to the ordered stage, as
|
||||
// are packets without a tunnel and the known replays precheck marked.
|
||||
func decryptRxItems(items []rxItem, nb []byte) {
|
||||
for i := range items {
|
||||
it := &items[i]
|
||||
if it.ci == nil || it.err != nil {
|
||||
continue
|
||||
}
|
||||
it.out, it.err = it.ci.decryptPacket(it.counter, it.packet, nb)
|
||||
}
|
||||
}
|
||||
|
||||
// rxBatch is one recvmmsg batch moving through the staged receive pipeline.
|
||||
type rxBatch struct {
|
||||
// items is every packet of the batch in arrival order. Data packets are decrypted by a worker; anything else is
|
||||
// handled whole by the writer, in its place.
|
||||
items []rxItem
|
||||
data int
|
||||
// bufs is the set of recvmmsg buffers the items point into, owned by the batch from handoff until it is reused.
|
||||
bufs [][]byte
|
||||
// chunks are the decrypt jobs, nChunks of them in use. With none the writer decrypts the batch itself.
|
||||
chunks []rxChunk
|
||||
nChunks int
|
||||
}
|
||||
|
||||
func (b *rxBatch) reset() {
|
||||
clear(b.items)
|
||||
b.items = b.items[:0]
|
||||
b.data = 0
|
||||
for i := range b.nChunks {
|
||||
b.chunks[i].items = nil
|
||||
}
|
||||
b.nChunks = 0
|
||||
}
|
||||
|
||||
// stagedRx is the staged receive pipeline of one udp listener. deliver and handoff run on the listener goroutine.
|
||||
type stagedRx struct {
|
||||
f *Interface
|
||||
q int
|
||||
pool *flowPool
|
||||
// h and hostmapCache are the listener's own. wrxc is the commit context: the writer's, or the listener's while
|
||||
// nothing is in flight.
|
||||
h *header.H
|
||||
hostmapCache map[uint32]*HostInfo
|
||||
wrxc *rxContext
|
||||
|
||||
cur *rxBatch
|
||||
free []*rxBatch
|
||||
ordered chan *rxBatch
|
||||
returned chan *rxBatch
|
||||
inFlight int
|
||||
writerDone chan struct{}
|
||||
|
||||
metricBatches metrics.Counter
|
||||
metricInline metrics.Counter
|
||||
}
|
||||
|
||||
func newStagedRx(f *Interface, q int, wrxc *rxContext) *stagedRx {
|
||||
p := &stagedRx{
|
||||
f: f,
|
||||
q: q,
|
||||
h: &header.H{},
|
||||
hostmapCache: map[uint32]*HostInfo{},
|
||||
wrxc: wrxc,
|
||||
ordered: make(chan *rxBatch, f.staged.rxSlots),
|
||||
returned: make(chan *rxBatch, f.staged.rxSlots),
|
||||
writerDone: make(chan struct{}),
|
||||
metricBatches: metrics.GetOrRegisterCounter("flow.rx.batches", nil),
|
||||
metricInline: metrics.GetOrRegisterCounter("flow.rx.inline", nil),
|
||||
}
|
||||
workers := f.staged.workers
|
||||
p.pool = newFlowPool(workers, f.staged.rxSlots*2*workers)
|
||||
for range f.staged.rxSlots {
|
||||
// Two chunks per worker, so the writer can start committing while the workers are still on the rest
|
||||
b := &rxBatch{items: make([]rxItem, 0, 256), chunks: make([]rxChunk, 2*workers)}
|
||||
for i := range b.chunks {
|
||||
b.chunks[i].done = make(chan struct{}, 1)
|
||||
}
|
||||
p.free = append(p.free, b)
|
||||
}
|
||||
p.cur = p.free[len(p.free)-1]
|
||||
p.free = p.free[:len(p.free)-1]
|
||||
go p.writer()
|
||||
return p
|
||||
}
|
||||
|
||||
// listen runs the conn's receive loop through the pipeline until it fails, then drains the pipeline. The conn hands
|
||||
// its buffers over, so a batch moves between stages without a copy.
|
||||
func (p *stagedRx) listen(li handoffConn) error {
|
||||
defer p.close()
|
||||
return li.ListenOutHandoff(p.deliver, p.handoff)
|
||||
}
|
||||
|
||||
// deliver is the listener's per-packet work: classify the packet and add it to the current batch. Nothing here
|
||||
// decrypts or touches the tun.
|
||||
func (p *stagedRx) deliver(via netip.AddrPort, packet []byte) {
|
||||
b := p.cur
|
||||
it := rxItem{packet: packet, via: via}
|
||||
p.classify(&it)
|
||||
if it.ci != nil {
|
||||
b.data++
|
||||
}
|
||||
b.items = append(b.items, it)
|
||||
}
|
||||
|
||||
// classify fills in the tunnel for a plain data packet of an established, non-relayed tunnel, leaving anything else
|
||||
// for the writer to handle whole. The replay pre-check waits for the end of the batch, see precheck.
|
||||
func (p *stagedRx) classify(it *rxItem) {
|
||||
f := p.f
|
||||
h := p.h
|
||||
packet := it.packet
|
||||
if h.Parse(packet) != nil || h.Version != header.Version || h.Type != header.Message || h.Subtype != header.MessageNone {
|
||||
return
|
||||
}
|
||||
if f.myVpnNetworksTable.Contains(it.via.Addr()) {
|
||||
return
|
||||
}
|
||||
hostinfo := f.hostMap.QueryIndexCached(h.RemoteIndex, p.hostmapCache)
|
||||
if hostinfo == nil || hostinfo.ConnectionState == nil {
|
||||
return
|
||||
}
|
||||
ci := hostinfo.ConnectionState
|
||||
if len(packet) < header.Len+ci.dKey.Overhead() {
|
||||
return
|
||||
}
|
||||
it.hostinfo, it.ci, it.counter = hostinfo, ci, h.MessageCounter
|
||||
}
|
||||
|
||||
// precheck marks obvious replays before anything decrypts them, like ConnectionState.Decrypt does, taking each
|
||||
// tunnel's lock once per run of its packets rather than once per packet: the writer takes the same lock for its
|
||||
// window updates, from another core. The writer checks again when it commits. The window only moves forward in
|
||||
// between, so a stale check here can only let a replay through to that second check. Marked packets keep their
|
||||
// place: an earlier RecvError may delete their tunnel, and inline receive then replies with a RecvError rather than
|
||||
// dropping a replay.
|
||||
func (p *stagedRx) precheck(b *rxBatch) {
|
||||
f := p.f
|
||||
items := b.items
|
||||
for i := 0; i < len(items); {
|
||||
ci := items[i].ci
|
||||
if ci == nil {
|
||||
i++
|
||||
continue
|
||||
}
|
||||
ci.decryptLock.Lock()
|
||||
for ; i < len(items) && items[i].ci == ci; i++ {
|
||||
if ci.window.Check(f.l, items[i].counter) {
|
||||
continue
|
||||
}
|
||||
b.data--
|
||||
items[i].err = ErrAlreadySeen
|
||||
}
|
||||
ci.decryptLock.Unlock()
|
||||
}
|
||||
}
|
||||
|
||||
// handoff ends a batch: the batch takes bufs, and the conn reads the next batch into the buffers of the next free
|
||||
// batch.
|
||||
func (p *stagedRx) handoff(bufs [][]byte) [][]byte {
|
||||
p.cur.bufs = bufs
|
||||
p.endBatch()
|
||||
b := p.cur
|
||||
if len(b.bufs) != len(bufs) || len(b.bufs[0]) < len(bufs[0]) {
|
||||
b.bufs = make([][]byte, len(bufs))
|
||||
for i := range b.bufs {
|
||||
b.bufs[i] = make([]byte, len(bufs[0]))
|
||||
}
|
||||
}
|
||||
return b.bufs
|
||||
}
|
||||
|
||||
// endBatch hands the batch to the workers and the ordered writer, then takes a free batch.
|
||||
func (p *stagedRx) endBatch() {
|
||||
clear(p.hostmapCache)
|
||||
p.reap()
|
||||
b := p.cur
|
||||
p.precheck(b)
|
||||
n := len(b.items)
|
||||
if n == 0 {
|
||||
b.reset()
|
||||
return
|
||||
}
|
||||
|
||||
if p.inFlight == 0 && n < p.f.staged.inlineBelow {
|
||||
// The writer is idle with nothing in flight, so the listener may commit with its context and flush the tun
|
||||
p.metricInline.Inc(1)
|
||||
p.process(b, p.wrxc)
|
||||
b.reset()
|
||||
return
|
||||
}
|
||||
|
||||
parts := min(len(b.chunks), b.data/rxChunkMin)
|
||||
p.metricBatches.Inc(1)
|
||||
if parts > 0 {
|
||||
size := (n + parts - 1) / parts
|
||||
for off := 0; off < n; off += size {
|
||||
c := &b.chunks[b.nChunks]
|
||||
c.items = b.items[off:min(off+size, n)]
|
||||
b.nChunks++
|
||||
}
|
||||
}
|
||||
// The jobs go out before the batch does: once the writer has it, it may finish and reset it at any moment
|
||||
for i := range b.nChunks {
|
||||
p.pool.jobs <- &b.chunks[i]
|
||||
}
|
||||
p.inFlight++
|
||||
p.ordered <- b
|
||||
|
||||
if len(p.free) == 0 {
|
||||
// Every batch is in flight, wait for the writer: the socket buffer absorbs the backlog meanwhile.
|
||||
p.release(<-p.returned)
|
||||
}
|
||||
p.cur = p.free[len(p.free)-1]
|
||||
p.free = p.free[:len(p.free)-1]
|
||||
}
|
||||
|
||||
// reap takes back every batch the writer has finished with, without waiting.
|
||||
func (p *stagedRx) reap() {
|
||||
for {
|
||||
select {
|
||||
case b := <-p.returned:
|
||||
p.release(b)
|
||||
default:
|
||||
return
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func (p *stagedRx) release(b *rxBatch) {
|
||||
p.inFlight--
|
||||
p.free = append(p.free, b)
|
||||
}
|
||||
|
||||
// process is the ordered stage for one batch: decrypt whatever no worker is decrypting, commit every item in arrival
|
||||
// order, and flush the tun batcher.
|
||||
func (p *stagedRx) process(b *rxBatch, rxc *rxContext) {
|
||||
if b.nChunks == 0 {
|
||||
decryptRxItems(b.items, rxc.nb)
|
||||
p.commit(b.items, rxc)
|
||||
} else {
|
||||
// Commit chunk by chunk, so the commit overlaps the workers still on later chunks
|
||||
for i := range b.nChunks {
|
||||
c := &b.chunks[i]
|
||||
<-c.done
|
||||
p.commit(c.items, rxc)
|
||||
}
|
||||
}
|
||||
p.f.flushOutside(rxc)
|
||||
}
|
||||
|
||||
// commit runs the ordered stage over items in arrival order. A non-data packet goes through readOutsidePackets in
|
||||
// its place, a run of data packets on one tunnel through commitRun.
|
||||
func (p *stagedRx) commit(items []rxItem, rxc *rxContext) {
|
||||
for i := 0; i < len(items); {
|
||||
ci := items[i].ci
|
||||
if ci == nil {
|
||||
p.f.readOutsidePackets(ViaSender{UdpAddr: items[i].via}, items[i].packet, rxc)
|
||||
i++
|
||||
continue
|
||||
}
|
||||
j := i + 1
|
||||
for j < len(items) && items[j].ci == ci {
|
||||
j++
|
||||
}
|
||||
p.commitRun(items[i:j], rxc)
|
||||
i = j
|
||||
}
|
||||
}
|
||||
|
||||
// commitRun commits a run of decrypted data packets on one tunnel. The window updates go first, under one lock, then
|
||||
// the rest; handling a data packet never touches the window, so that is the same as one packet at a time.
|
||||
func (p *stagedRx) commitRun(run []rxItem, rxc *rxContext) {
|
||||
f := p.f
|
||||
ci := run[0].ci
|
||||
// Classification is speculative: earlier control packets may have removed this tunnel. Resolve it through the
|
||||
// writer's batch-local cache, exactly where inline processing would, before touching replay state.
|
||||
index := binary.BigEndian.Uint32(run[0].packet[4:8])
|
||||
hostinfo := f.hostMap.QueryIndexCached(index, rxc.hostmapCache)
|
||||
if hostinfo != run[0].hostinfo || hostinfo.ConnectionState != ci {
|
||||
if hostinfo == nil {
|
||||
for i := range run {
|
||||
f.maybeSendRecvError(run[i].via, index)
|
||||
}
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
ci.decryptLock.Lock()
|
||||
for i := range run {
|
||||
// A packet that failed to decrypt does not touch the window, like ConnectionState.Decrypt
|
||||
if run[i].err == nil && !ci.window.Update(f.l, run[i].counter) {
|
||||
run[i].err = ErrAlreadySeen
|
||||
}
|
||||
}
|
||||
ci.decryptLock.Unlock()
|
||||
for i := range run {
|
||||
it := &run[i]
|
||||
if f.finishOutsideDecrypt(it.hostinfo, ViaSender{UdpAddr: it.via}, it.counter, it.err) {
|
||||
f.handleOutsideMessagePacket(it.hostinfo, it.counter, it.out, rxc)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// writer is the ordered receive stage: window, firewall, coalescer and tun write, one batch at a time in arrival
|
||||
// order.
|
||||
func (p *stagedRx) writer() {
|
||||
defer close(p.writerDone)
|
||||
for b := range p.ordered {
|
||||
if p.f.closed.Load() {
|
||||
// The tun is going away, a write would only log errors. Still wait out the workers on the batch.
|
||||
for i := range b.nChunks {
|
||||
<-b.chunks[i].done
|
||||
}
|
||||
} else {
|
||||
p.process(b, p.wrxc)
|
||||
}
|
||||
b.reset()
|
||||
p.returned <- b
|
||||
}
|
||||
}
|
||||
|
||||
// close commits anything still in flight, in order, and stops the writer and the workers.
|
||||
func (p *stagedRx) close() {
|
||||
if len(p.cur.items) > 0 {
|
||||
p.endBatch()
|
||||
}
|
||||
close(p.ordered)
|
||||
<-p.writerDone
|
||||
p.pool.close()
|
||||
}
|
||||
+237
@@ -0,0 +1,237 @@
|
||||
//go:build linux && !android && !e2e_testing
|
||||
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"net/netip"
|
||||
"sync/atomic"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/flynn/noise"
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/noiseutil"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/require"
|
||||
"go.uber.org/goleak"
|
||||
)
|
||||
|
||||
// TestFlowStagedRXOrderAndReplay feeds every packet behind a forgery of it, from another address, and a replay of
|
||||
// it, then a test packet that jumps the window and the whole stream again, with shuffled workers and a slow tun,
|
||||
// through small and large batches: the tun sees each segment once, in order, the window marks them all, the forgeries
|
||||
// neither consume a counter nor roam, and the jump does not get the earlier data packets of its batch rejected.
|
||||
func TestFlowStagedRXOrderAndReplay(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
for _, cipher := range []noise.CipherFunc{noiseutil.CipherAESGCM, noise.CipherChaChaPoly} {
|
||||
for _, batchLen := range []int{8, 1000} {
|
||||
t.Run(fmt.Sprintf("%s/batch=%d", cipher.CipherName(), batchLen), func(t *testing.T) {
|
||||
sender, receiver := newFlowTestPair(t, cipher, stagedOn(4))
|
||||
delayCrypto(receiver, func(n uint64) {
|
||||
if n%32 == 0 {
|
||||
time.Sleep(time.Millisecond)
|
||||
}
|
||||
})
|
||||
receiver.tun.delay = 100 * time.Microsecond
|
||||
batches, want := flowTestBatches(30, 4, 1, 10)
|
||||
wire := wireFor(t, sender, batches)
|
||||
var feed [][]byte
|
||||
for i, p := range wire {
|
||||
// Corrupt the tag or the payload
|
||||
bad := append([]byte(nil), p...)
|
||||
bad[[]int{len(p) - 1, header.Len + 3}[i%2]] ^= 1
|
||||
feed = append(feed, bad, p, p)
|
||||
}
|
||||
// The jump lands in a batch with fresh data before it, at batch=1000
|
||||
sender.hostinfo.ConnectionState.messageCounter.Add(2 * ReplayWindow)
|
||||
feed = append(append(feed, sendControl(sender, header.Test, header.TestReply)), wire...)
|
||||
forged := func(i int) netip.AddrPort {
|
||||
if i < 3*len(wire) && i%3 == 0 {
|
||||
return netip.MustParseAddrPort("198.51.100.9:4242")
|
||||
}
|
||||
return flowTestUnder
|
||||
}
|
||||
rx0 := rxBatches.Count()
|
||||
conn := &rxConn{wire: feed, batchLen: batchLen, from: forged}
|
||||
receiver.receive(conn)
|
||||
require.Positive(t, rxBatches.Count()-rx0)
|
||||
require.Equal(t, (len(feed)+batchLen-1)/batchLen, conn.swaps, "every batch is handed off")
|
||||
require.Equal(t, want, receiver.tun.segments(t), "every packet exactly once, in order")
|
||||
require.Equal(t, flowTestUnder, receiver.hostinfo.GetRemote())
|
||||
for _, p := range wire {
|
||||
h := &header.H{}
|
||||
require.NoError(t, h.Parse(p))
|
||||
require.False(t, receiver.hostinfo.ConnectionState.window.Check(receiver.f.l, h.MessageCounter), "counter %d must be marked seen", h.MessageCounter)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestFlowStagedRXClose: a CloseTunnel in the middle of a batch is handled in its place, by the writer. The data after
|
||||
// it in the batch is still delivered from the batch's hostmap cache, as inline receive does.
|
||||
func TestFlowStagedRXClose(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, stagedOn(2))
|
||||
batches, want := flowTestBatches(4, 4, 1, 8)
|
||||
wire := wireFor(t, sender, batches)
|
||||
half := len(wire) / 2
|
||||
feed := append(append(append([][]byte{}, wire[:half]...), sendControl(sender, header.CloseTunnel, 0)), wire[half:]...)
|
||||
receiver.receive(&rxConn{wire: feed, batchLen: len(feed)})
|
||||
require.Equal(t, want, receiver.tun.segments(t))
|
||||
require.Nil(t, receiver.f.hostMap.QueryIndex(receiver.hostinfo.localIndexId))
|
||||
}
|
||||
|
||||
// sendControl returns the wire packet of a control message from sender.
|
||||
func sendControl(sender *flowTestPeer, typ header.MessageType, st header.MessageSubType) []byte {
|
||||
sender.f.sendNoMetrics(typ, st, sender.hostinfo.ConnectionState, sender.hostinfo, flowTestUnder, nil, make([]byte, 12), make([]byte, mtu), 0)
|
||||
wire := sender.conn.captured()
|
||||
sender.conn.pkts, sender.conn.addrs = nil, nil
|
||||
return wire[len(wire)-1]
|
||||
}
|
||||
|
||||
// receivePaths is inline, staged and, with the threshold, adaptive receive.
|
||||
func receivePaths() []stagedConfig {
|
||||
return []stagedConfig{{}, stagedOn(2), adaptive(2)}
|
||||
}
|
||||
|
||||
// TestFlowStagedRXRecvError feeds a RecvError that deletes the tunnel, then a known replay and new data for it, in one
|
||||
// batch. Every receive path must drop the data through its own view of the hostmap, without touching the replay window,
|
||||
// and answer each packet with a RecvError, as inline receive does, without decrypting the replay again.
|
||||
func TestFlowStagedRXRecvError(t *testing.T) {
|
||||
for _, sc := range receivePaths() {
|
||||
t.Run(stagedName(sc), func(t *testing.T) {
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, sc)
|
||||
receiver.f.messageMetrics = newMessageMetrics()
|
||||
receiver.f.acceptRecvErrorConfig = recvErrorAlways
|
||||
receiver.f.sendRecvErrorConfig = recvErrorAlways
|
||||
batches, want := flowTestBatches(1, 1, 1, 33)
|
||||
wire := wireFor(t, sender, batches)
|
||||
rxc := newRxContext(receiver.f, 0)
|
||||
receiver.f.readOutsidePackets(ViaSender{UdpAddr: flowTestUnder}, append([]byte(nil), wire[0]...), rxc)
|
||||
receiver.f.flushOutside(rxc)
|
||||
h := &header.H{}
|
||||
require.NoError(t, h.Parse(wire[0]))
|
||||
replay := h.MessageCounter
|
||||
var decrypts atomic.Int64
|
||||
delayCrypto(receiver, func(n uint64) {
|
||||
if n == replay {
|
||||
decrypts.Add(1)
|
||||
}
|
||||
})
|
||||
ctl := header.Encode(make([]byte, header.Len), header.Version, header.RecvError, 0, receiver.hostinfo.remoteIndexId, 0)
|
||||
conn := &rxConn{wire: append([][]byte{ctl}, wire...), batchLen: len(wire) + 1}
|
||||
receiver.receive(conn)
|
||||
require.Nil(t, receiver.f.hostMap.QueryIndex(receiver.hostinfo.localIndexId))
|
||||
require.Equal(t, want[:1], receiver.tun.segments(t))
|
||||
require.Zero(t, decrypts.Load(), "known replays must not be decrypted again")
|
||||
replies := conn.captured()
|
||||
require.Len(t, replies, len(wire))
|
||||
for i, reply := range replies {
|
||||
require.NoError(t, h.Parse(reply))
|
||||
require.Equal(t, header.RecvError, h.Type)
|
||||
require.NoError(t, h.Parse(wire[i]))
|
||||
require.True(t, i == 0 || receiver.hostinfo.ConnectionState.window.Check(nil, h.MessageCounter), "dropped data must not update replay state")
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestFlowStagedRXReplacedTunnel classifies a data packet, then a close and a new handshake replace its tunnel at the
|
||||
// same index before the writer commits it, as when the listener runs ahead: it must be dropped untouched.
|
||||
func TestFlowStagedRXReplacedTunnel(t *testing.T) {
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, stagedOn(2))
|
||||
receiver.f.messageMetrics = newMessageMetrics()
|
||||
batches, _ := flowTestBatches(1, 1, 1, 1)
|
||||
wire := wireFor(t, sender, batches)
|
||||
closePacket := sendControl(sender, header.CloseTunnel, 0)
|
||||
p := &stagedRx{f: receiver.f, h: &header.H{}, hostmapCache: map[uint32]*HostInfo{}}
|
||||
item := rxItem{packet: wire[0], via: flowTestUnder}
|
||||
p.classify(&item)
|
||||
require.NotNil(t, item.ci)
|
||||
rxc := newRxContext(receiver.f, 0)
|
||||
p.process(&rxBatch{items: []rxItem{{packet: closePacket, via: flowTestUnder}}}, rxc)
|
||||
require.Nil(t, receiver.f.hostMap.QueryIndex(receiver.hostinfo.localIndexId))
|
||||
_, replacement := newFlowTestPair(t, noise.CipherChaChaPoly, stagedOn(2))
|
||||
receiver.f.hostMap.Lock()
|
||||
receiver.f.hostMap.unlockedAddHostInfo(replacement.hostinfo, receiver.f)
|
||||
receiver.f.hostMap.Unlock()
|
||||
p.process(&rxBatch{items: []rxItem{item}}, rxc)
|
||||
require.Empty(t, receiver.tun.writes)
|
||||
require.True(t, item.ci.window.Check(nil, item.counter))
|
||||
require.True(t, replacement.hostinfo.ConnectionState.window.Check(nil, item.counter))
|
||||
}
|
||||
|
||||
// TestFlowStagedRXRealSocket exercises buffer handoff through the real Linux UDP receive loop.
|
||||
func TestFlowStagedRXRealSocket(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, stagedOn(3))
|
||||
batches, want := flowTestBatches(60, 4, 1, 8)
|
||||
wire := wireFor(t, sender, batches)
|
||||
|
||||
l := receiver.f.l
|
||||
conn, err := udp.NewListener(l, udp.Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0"), Batch: 16, Offloads: true})
|
||||
require.NoError(t, err)
|
||||
addr, err := conn.LocalAddr()
|
||||
require.NoError(t, err)
|
||||
out, err := udp.NewListener(l, udp.Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0"), Batch: 16, Offloads: true})
|
||||
require.NoError(t, err)
|
||||
defer out.Close()
|
||||
// The sender's address is the tunnel's remote, so no roaming
|
||||
from, err := out.LocalAddr()
|
||||
require.NoError(t, err)
|
||||
receiver.hostinfo.remote.Store(&from)
|
||||
|
||||
done := make(chan struct{})
|
||||
go func() { receiver.receive(conn); close(done) }()
|
||||
// Send in bursts small enough for the default socket buffer
|
||||
for off := 0; off < len(wire); off += 32 {
|
||||
end := min(off+32, len(wire))
|
||||
addrs := make([]netip.AddrPort, end-off)
|
||||
for i := range addrs {
|
||||
addrs[i] = addr
|
||||
}
|
||||
_, err := out.WriteBatch(wire[off:end], addrs)
|
||||
require.NoError(t, err)
|
||||
require.Eventually(t, func() bool { return len(receiver.tun.segments(t)) >= end }, 5*time.Second, 100*time.Microsecond)
|
||||
}
|
||||
receiver.f.closed.Store(true)
|
||||
require.NoError(t, conn.Close())
|
||||
<-done
|
||||
require.Equal(t, want, receiver.tun.segments(t))
|
||||
}
|
||||
|
||||
// TestFlowStagedRXCloseFlushesPartial: packets the listener holds in a batch it never got to end when the conn fails
|
||||
// are still committed, in order, on a live interface.
|
||||
func TestFlowStagedRXCloseFlushesPartial(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, stagedOn(2))
|
||||
batches, want := flowTestBatches(11, 4, 1, 8)
|
||||
wire := wireFor(t, sender, batches)
|
||||
p := newStagedRx(receiver.f, 0, newRxContext(receiver.f, 0))
|
||||
for i, packet := range wire {
|
||||
p.deliver(flowTestUnder, packet)
|
||||
if (i+1)%64 == 0 {
|
||||
p.endBatch()
|
||||
}
|
||||
}
|
||||
p.close()
|
||||
require.Equal(t, want, receiver.tun.segments(t))
|
||||
}
|
||||
|
||||
// TestFlowStagedRXInlineBelow: small idle batches stay on the listener, larger batches still use the ordered writer.
|
||||
func TestFlowStagedRXInlineBelow(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
sc := adaptive(3)
|
||||
sc.inlineBelow = 16
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, sc)
|
||||
batches, want := flowTestBatches(40, 4, 1, 16)
|
||||
wire := wireFor(t, sender, batches)
|
||||
inline := metrics.GetOrRegisterCounter("flow.rx.inline", nil)
|
||||
inline0, rx0 := inline.Count(), rxBatches.Count()
|
||||
receiver.receive(&rxConn{wire: wire, sizes: []int{8, 8, 8, 128, 128, 8, 8, 128, 4, 128}})
|
||||
require.Equal(t, want, receiver.tun.segments(t))
|
||||
require.Positive(t, inline.Count()-inline0)
|
||||
require.Positive(t, rxBatches.Count()-rx0)
|
||||
}
|
||||
+536
@@ -0,0 +1,536 @@
|
||||
//go:build linux && !android && !e2e_testing
|
||||
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
"io"
|
||||
"math"
|
||||
"net/netip"
|
||||
"os"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/flynn/noise"
|
||||
"github.com/gaissmai/bart"
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/firewall"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/iputil"
|
||||
"github.com/slackhq/nebula/noiseutil"
|
||||
"github.com/slackhq/nebula/overlay/batch"
|
||||
"github.com/slackhq/nebula/overlay/tio"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/require"
|
||||
"go.uber.org/goleak"
|
||||
)
|
||||
|
||||
// flowTestMSS is the segment payload size of the synthetic TSO superpackets.
|
||||
const flowTestMSS = 1200
|
||||
|
||||
var (
|
||||
flowTestLocal = netip.MustParseAddr("10.0.0.1")
|
||||
flowTestRemote = netip.MustParseAddr("10.0.0.2")
|
||||
flowTestUnder = netip.MustParseAddrPort("192.0.2.2:4242")
|
||||
)
|
||||
|
||||
// flowTCPSuperpacket builds an IPv4/TCP TSO superpacket from local to remote carrying segs segments. Segment i's
|
||||
// payload starts with the flow id, the superpacket seq and i, so a receiver can check what it got and in which order.
|
||||
func flowTCPSuperpacket(flow uint16, seq uint32, segs int) tio.Packet {
|
||||
const hdr = 40
|
||||
pay := segs * flowTestMSS
|
||||
b := make([]byte, hdr+pay)
|
||||
b[0] = 0x45
|
||||
binary.BigEndian.PutUint16(b[2:4], uint16(min(hdr+pay, 65535)))
|
||||
b[8] = 64
|
||||
b[9] = iputil.IPProtocolTCP
|
||||
copy(b[12:16], flowTestLocal.AsSlice())
|
||||
copy(b[16:20], flowTestRemote.AsSlice())
|
||||
binary.BigEndian.PutUint16(b[20:22], 10000+flow)
|
||||
binary.BigEndian.PutUint16(b[22:24], 80)
|
||||
binary.BigEndian.PutUint32(b[24:28], seq*uint32(pay))
|
||||
b[32] = 0x50
|
||||
b[33] = 0x10 // ACK
|
||||
binary.BigEndian.PutUint16(b[34:36], 65535)
|
||||
for i := range segs {
|
||||
p := b[hdr+i*flowTestMSS:]
|
||||
binary.BigEndian.PutUint16(p[0:2], flow)
|
||||
binary.BigEndian.PutUint32(p[2:6], seq)
|
||||
binary.BigEndian.PutUint16(p[6:8], uint16(i))
|
||||
}
|
||||
if segs == 1 {
|
||||
return tio.Packet{Bytes: b}
|
||||
}
|
||||
return tio.Packet{Bytes: b, GSO: tio.GSOInfo{Size: flowTestMSS, HdrLen: hdr, CsumStart: 20, Proto: tio.GSOProtoTCP}}
|
||||
}
|
||||
|
||||
// decodedSeg identifies one segment by the marker flowTCPSuperpacket put in its payload.
|
||||
type decodedSeg struct {
|
||||
flow uint16
|
||||
seq uint32
|
||||
idx uint16
|
||||
}
|
||||
|
||||
func decodeSeg(p []byte) decodedSeg {
|
||||
return decodedSeg{flow: binary.BigEndian.Uint16(p[0:2]), seq: binary.BigEndian.Uint32(p[2:6]), idx: binary.BigEndian.Uint16(p[6:8])}
|
||||
}
|
||||
|
||||
// flowTestBatches builds n reads of per superpackets of segs segments, across flows interleaved flows, and the
|
||||
// segments they carry in order.
|
||||
func flowTestBatches(n, per, flows, segs int) ([][]tio.Packet, []decodedSeg) {
|
||||
var batches [][]tio.Packet
|
||||
var want []decodedSeg
|
||||
seq := make([]uint32, flows)
|
||||
for range n {
|
||||
var b []tio.Packet
|
||||
for j := range per {
|
||||
flow := uint16(j % flows)
|
||||
b = append(b, flowTCPSuperpacket(flow, seq[flow], segs))
|
||||
for s := range segs {
|
||||
want = append(want, decodedSeg{flow: flow, seq: seq[flow], idx: uint16(s)})
|
||||
}
|
||||
seq[flow]++
|
||||
}
|
||||
batches = append(batches, b)
|
||||
}
|
||||
return batches, want
|
||||
}
|
||||
|
||||
// flowTestPeer is one end of a tunnel: the interface, the hostinfo for the other end, and its capture points.
|
||||
type flowTestPeer struct {
|
||||
f *Interface
|
||||
hostinfo *HostInfo
|
||||
conn *flowCaptureConn
|
||||
tun *flowTunCapture
|
||||
}
|
||||
|
||||
// newFlowTestPair builds two interfaces joined by one real tunnel (keys from an actual handshake). sender sends from
|
||||
// flowTestLocal to flowTestRemote, receiver is the far side.
|
||||
func newFlowTestPair(t testing.TB, cipher noise.CipherFunc, sc stagedConfig) (sender, receiver *flowTestPeer) {
|
||||
t.Helper()
|
||||
initR, respR := runTestHandshakeWith(t, cipher)
|
||||
sci, err := newConnectionStateFromResult(initR)
|
||||
require.NoError(t, err)
|
||||
rci, err := newConnectionStateFromResult(respR)
|
||||
require.NoError(t, err)
|
||||
sender = newFlowTestPeer(t, flowTestLocal, flowTestRemote, sci, 100, 200)
|
||||
receiver = newFlowTestPeer(t, flowTestRemote, flowTestLocal, rci, 200, 100)
|
||||
sender.f.staged, receiver.f.staged = sc, sc
|
||||
return sender, receiver
|
||||
}
|
||||
|
||||
func newFlowTestPeer(t testing.TB, me, them netip.Addr, ci *ConnectionState, localIdx, remoteIdx uint32) *flowTestPeer {
|
||||
l := test.NewLogger()
|
||||
hm := newHostMap(l)
|
||||
hm.preferredRanges.Store(&[]netip.Prefix{})
|
||||
|
||||
myNets, myAddrs := &bart.Lite{}, &bart.Lite{}
|
||||
myNets.Insert(netip.PrefixFrom(me, 24))
|
||||
myAddrs.Insert(netip.PrefixFrom(me, 32))
|
||||
myCert := &dummyCert{version: cert.Version1, networks: []netip.Prefix{netip.PrefixFrom(me, 24)}}
|
||||
theirCert := &dummyCert{version: cert.Version1, networks: []netip.Prefix{netip.PrefixFrom(them, 24)}, name: "peer"}
|
||||
ci.peerCert = &cert.CachedCertificate{Certificate: theirCert, InvertedGroups: map[string]struct{}{}}
|
||||
|
||||
fw := NewFirewall(l, time.Minute, time.Minute, time.Minute, myCert)
|
||||
require.NoError(t, fw.AddRule(false, firewall.ProtoAny, 0, 0, []string{"any"}, "", "", "", "", ""))
|
||||
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"any"}, "", "", "", "", ""))
|
||||
|
||||
conn, tun := &flowCaptureConn{}, &flowTunCapture{}
|
||||
lh := newTestLighthouse()
|
||||
lh.remoteAllowList.Store(&RemoteAllowList{})
|
||||
|
||||
f := &Interface{
|
||||
hostMap: hm,
|
||||
outside: conn,
|
||||
firewall: fw,
|
||||
lightHouse: lh,
|
||||
pki: &PKI{},
|
||||
myVpnNetworksTable: myNets,
|
||||
myVpnAddrsTable: myAddrs,
|
||||
routines: 1,
|
||||
writers: []udp.Conn{conn},
|
||||
messageMetrics: &MessageMetrics{txExhausted: metrics.NewCounter()},
|
||||
metricTxDropped: metrics.NilCounter{},
|
||||
l: l,
|
||||
}
|
||||
f.ctx = t.Context()
|
||||
f.pki.caPool.Store(cert.NewCAPool())
|
||||
// Never promote or requery, those would put extra test packets on the wire
|
||||
f.tryPromoteEvery.Store(math.MaxUint32)
|
||||
f.reQueryEvery.Store(math.MaxUint32)
|
||||
f.batchers = []*batch.MultiCoalescer{batch.NewMultiCoalescer(tun, l)}
|
||||
f.connectionManager = &connectionManager{
|
||||
intf: f,
|
||||
relayUsed: map[uint32]struct{}{},
|
||||
relayUsedLock: &sync.RWMutex{},
|
||||
trafficTimer: NewLockingTimerWheel[uint32](time.Second, time.Minute),
|
||||
}
|
||||
f.handshakeManager = NewHandshakeManager(l, hm, lh, conn, defaultHandshakeConfig)
|
||||
f.handshakeManager.f = f
|
||||
|
||||
hostinfo := &HostInfo{
|
||||
ConnectionState: ci,
|
||||
vpnAddrs: []netip.Addr{them},
|
||||
localIndexId: localIdx,
|
||||
remoteIndexId: remoteIdx,
|
||||
relayState: RelayState{relayForByAddr: map[netip.Addr]*Relay{}, relayForByIdx: map[uint32]*Relay{}},
|
||||
}
|
||||
hostinfo.remote.Store(&flowTestUnder)
|
||||
hostinfo.buildNetworks(myNets, theirCert)
|
||||
hm.unlockedAddHostInfo(hostinfo, f)
|
||||
|
||||
return &flowTestPeer{f: f, hostinfo: hostinfo, conn: conn, tun: tun}
|
||||
}
|
||||
|
||||
// flowCaptureConn records every packet sent, in order, as copies.
|
||||
type flowCaptureConn struct {
|
||||
udp.NoopConn
|
||||
mu sync.Mutex
|
||||
pkts [][]byte
|
||||
addrs []netip.AddrPort
|
||||
// delay, when set, slows every WriteBatch down so batches pile up in flight
|
||||
delay time.Duration
|
||||
}
|
||||
|
||||
func (c *flowCaptureConn) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error) {
|
||||
time.Sleep(c.delay)
|
||||
c.mu.Lock()
|
||||
defer c.mu.Unlock()
|
||||
for i, b := range bufs {
|
||||
c.pkts = append(c.pkts, append([]byte(nil), b...))
|
||||
c.addrs = append(c.addrs, addrs[i])
|
||||
}
|
||||
return len(bufs), nil
|
||||
}
|
||||
|
||||
func (c *flowCaptureConn) WriteTo(b []byte, addr netip.AddrPort) error {
|
||||
_, err := c.WriteBatch([][]byte{b}, []netip.AddrPort{addr})
|
||||
return err
|
||||
}
|
||||
|
||||
func (c *flowCaptureConn) captured() [][]byte {
|
||||
c.mu.Lock()
|
||||
defer c.mu.Unlock()
|
||||
return append([][]byte(nil), c.pkts...)
|
||||
}
|
||||
|
||||
// flowTunCapture is a tun queue that records every plaintext write.
|
||||
type flowTunCapture struct {
|
||||
mu sync.Mutex
|
||||
writes [][]byte
|
||||
// delay, when set, slows every write down
|
||||
delay time.Duration
|
||||
}
|
||||
|
||||
func (c *flowTunCapture) Read() ([]tio.Packet, error) { return nil, io.EOF }
|
||||
func (c *flowTunCapture) Close() error { return nil }
|
||||
func (c *flowTunCapture) Write(b []byte) (int, error) {
|
||||
time.Sleep(c.delay)
|
||||
c.mu.Lock()
|
||||
defer c.mu.Unlock()
|
||||
c.writes = append(c.writes, append([]byte(nil), b...))
|
||||
return len(b), nil
|
||||
}
|
||||
|
||||
// segments decodes what reached the tun. The coalescer may have merged segments back into superpackets, so this
|
||||
// walks each payload in MSS steps.
|
||||
func (c *flowTunCapture) segments(t testing.TB) []decodedSeg {
|
||||
t.Helper()
|
||||
c.mu.Lock()
|
||||
defer c.mu.Unlock()
|
||||
var out []decodedSeg
|
||||
for _, w := range c.writes {
|
||||
pay := w[40:]
|
||||
require.Zero(t, len(pay)%flowTestMSS, "tun write payload %d bytes", len(pay))
|
||||
for off := 0; off < len(pay); off += flowTestMSS {
|
||||
out = append(out, decodeSeg(pay[off:]))
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// decryptWire checks every wire packet decrypts on the receiver, in order, with strictly increasing counters, and
|
||||
// returns what each one carried. It uses its own replay window and copies, so the wire can still be fed to the
|
||||
// receiver afterwards.
|
||||
func decryptWire(t testing.TB, receiver *flowTestPeer, wire [][]byte) []decodedSeg {
|
||||
t.Helper()
|
||||
peer := receiver.hostinfo.ConnectionState
|
||||
ci := &ConnectionState{dKey: peer.dKey, window: NewBits(peer.window.length)}
|
||||
nb := make([]byte, 12)
|
||||
var last uint64
|
||||
out := make([]decodedSeg, 0, len(wire))
|
||||
for i, pkt := range wire {
|
||||
h := &header.H{}
|
||||
require.NoError(t, h.Parse(pkt))
|
||||
require.Equal(t, header.Message, h.Type)
|
||||
require.Equal(t, receiver.hostinfo.localIndexId, h.RemoteIndex)
|
||||
require.Greater(t, h.MessageCounter, last, "wire packet %d: counter %d after %d", i, h.MessageCounter, last)
|
||||
last = h.MessageCounter
|
||||
plain, err := ci.Decrypt(receiver.f.l, h.MessageCounter, append([]byte(nil), pkt...), nb)
|
||||
require.NoError(t, err, "wire packet %d", i)
|
||||
out = append(out, decodeSeg(plain[40:]))
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// flowBatchQueue is a handoffQueue that hands out scripted Read batches, then fails with io.EOF. Every batch is copied
|
||||
// into the current receive buffer, so a test sees the buffer ownership the Offload queue has.
|
||||
type flowBatchQueue struct {
|
||||
batches [][]tio.Packet
|
||||
rxBuf []byte
|
||||
out []tio.Packet
|
||||
closed chan struct{}
|
||||
// reads counts the batches handed out
|
||||
reads atomic.Int64
|
||||
}
|
||||
|
||||
func newFlowBatchQueue(batches [][]tio.Packet) *flowBatchQueue {
|
||||
return &flowBatchQueue{batches: batches, rxBuf: make([]byte, 8*65536), closed: make(chan struct{})}
|
||||
}
|
||||
|
||||
func (q *flowBatchQueue) Read() ([]tio.Packet, error) {
|
||||
select {
|
||||
case <-q.closed:
|
||||
return nil, os.ErrClosed
|
||||
default:
|
||||
}
|
||||
n := int(q.reads.Load())
|
||||
if n == len(q.batches) {
|
||||
return nil, io.EOF
|
||||
}
|
||||
q.out = q.out[:0]
|
||||
off := 0
|
||||
for _, p := range q.batches[n] {
|
||||
l := copy(q.rxBuf[off:], p.Bytes)
|
||||
q.out = append(q.out, tio.Packet{Bytes: q.rxBuf[off : off+l : off+l], GSO: p.GSO})
|
||||
off += l
|
||||
}
|
||||
q.reads.Add(1)
|
||||
return q.out, nil
|
||||
}
|
||||
|
||||
func (q *flowBatchQueue) SwapRxBuf(buf []byte) []byte {
|
||||
if buf == nil {
|
||||
buf = make([]byte, len(q.rxBuf))
|
||||
}
|
||||
old := q.rxBuf
|
||||
q.rxBuf = buf
|
||||
// Scribble over the buffer we are handed, a staged batch that still pointed into it would be corrupted
|
||||
for i := range buf {
|
||||
buf[i] = 0xa5
|
||||
}
|
||||
return old
|
||||
}
|
||||
|
||||
func (q *flowBatchQueue) Write(b []byte) (int, error) { return len(b), nil }
|
||||
|
||||
func (q *flowBatchQueue) Close() error { close(q.closed); return nil }
|
||||
|
||||
// delayedCipher changes scheduling through the real cipher interface, only in tests.
|
||||
type delayedCipher struct {
|
||||
noiseutil.CipherState
|
||||
before func(uint64)
|
||||
}
|
||||
|
||||
func (c delayedCipher) EncryptDanger(out, ad, plain []byte, n uint64, nb []byte) ([]byte, error) {
|
||||
c.before(n)
|
||||
return c.CipherState.EncryptDanger(out, ad, plain, n, nb)
|
||||
}
|
||||
|
||||
func (c delayedCipher) DecryptDanger(out, ad, ciphertext []byte, n uint64, nb []byte) ([]byte, error) {
|
||||
c.before(n)
|
||||
return c.CipherState.DecryptDanger(out, ad, ciphertext, n, nb)
|
||||
}
|
||||
|
||||
func delayCrypto(peer *flowTestPeer, before func(uint64)) {
|
||||
ci := peer.hostinfo.ConnectionState
|
||||
ci.eKey = delayedCipher{ci.eKey, before}
|
||||
ci.dKey = delayedCipher{ci.dKey, before}
|
||||
}
|
||||
|
||||
// stagedOn enables staging with n workers.
|
||||
func stagedOn(n int) stagedConfig {
|
||||
return stagedConfig{workers: n, tx: true, rx: true, txSlots: stagedTxSlots, rxSlots: 6}
|
||||
}
|
||||
|
||||
// adaptive is staging with the inline threshold and gate hold parseStagedConfig sets.
|
||||
func adaptive(n int) stagedConfig {
|
||||
return stagedConfig{workers: n, tx: true, rx: true, inlineBelow: 256, gateHold: stagedGateHold,
|
||||
txSlots: stagedTxSlots, rxSlots: 6}
|
||||
}
|
||||
|
||||
func stagedName(sc stagedConfig) string {
|
||||
switch {
|
||||
case sc.workers == 0:
|
||||
return "inline"
|
||||
case sc.inlineBelow > 0:
|
||||
return "adaptive"
|
||||
default:
|
||||
return "staged"
|
||||
}
|
||||
}
|
||||
|
||||
// send takes one read through the pipeline, as run does.
|
||||
func (p *stagedTx) send(pkts []tio.Packet) {
|
||||
p.handle(pkts, &firewall.ParsedPacket{}, make([]byte, mtu), nil)
|
||||
}
|
||||
|
||||
// drain waits until every batch p has in flight is on the wire.
|
||||
func (p *stagedTx) drain() {
|
||||
for p.inFlight > 0 {
|
||||
p.release(<-p.returned)
|
||||
}
|
||||
}
|
||||
|
||||
// TestFlowStagedFallback: a tun queue that cannot hand off its buffer, or a conn that cannot hand off its batches,
|
||||
// keeps that direction on the inline path.
|
||||
func TestFlowStagedFallback(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, stagedOn(3))
|
||||
batches, want := flowTestBatches(10, 2, 1, 4)
|
||||
tx := metrics.GetOrRegisterCounter("flow.tx.batches", nil)
|
||||
tx0, rx0 := tx.Count(), rxBatches.Count()
|
||||
sender.f.listenIn(plainQueue{newFlowBatchQueue(batches)}, 0)
|
||||
wire := sender.conn.captured()
|
||||
require.Equal(t, want, decryptWire(t, receiver, wire))
|
||||
require.Equal(t, tx0, tx.Count())
|
||||
receiver.receive(plainConn{&rxConn{wire: wire, batchLen: 16}})
|
||||
require.Equal(t, want, receiver.tun.segments(t))
|
||||
require.Equal(t, rx0, rxBatches.Count())
|
||||
}
|
||||
|
||||
// plainQueue and plainConn hide SwapRxBuf and ListenOutHandoff, so they cannot hand off their batches.
|
||||
type plainQueue struct{ tio.Queue }
|
||||
|
||||
// wireFor produces the wire packets the sender emits for batches, inline.
|
||||
func wireFor(t testing.TB, sender *flowTestPeer, batches [][]tio.Packet) [][]byte {
|
||||
t.Helper()
|
||||
sc := sender.f.staged
|
||||
sender.f.staged = stagedConfig{}
|
||||
sender.f.listenIn(newFlowBatchQueue(batches), 0)
|
||||
sender.f.staged = sc
|
||||
wire := sender.conn.captured()
|
||||
sender.conn.pkts, sender.conn.addrs = nil, nil
|
||||
return wire
|
||||
}
|
||||
|
||||
// rxConn plays wire back to listenOut through the buffer handoff, in batches of batchLen or of the scripted sizes
|
||||
// (the last one repeating), and captures what is sent back. Every buffer handed back is scribbled over before it is
|
||||
// read into, so a stage still using one shows corruption. from, when set, picks each packet's source address by its
|
||||
// index in wire.
|
||||
type rxConn struct {
|
||||
flowCaptureConn
|
||||
wire [][]byte
|
||||
batchLen int
|
||||
sizes []int
|
||||
from func(i int) netip.AddrPort
|
||||
swaps int
|
||||
}
|
||||
|
||||
func (c *rxConn) ListenOut(r udp.EncReader, flush func()) error {
|
||||
return c.ListenOutHandoff(r, func(bufs [][]byte) [][]byte {
|
||||
flush()
|
||||
return bufs
|
||||
})
|
||||
}
|
||||
|
||||
func (c *rxConn) ListenOutHandoff(r udp.EncReader, handoff func(bufs [][]byte) [][]byte) error {
|
||||
n := c.batchLen
|
||||
for _, size := range c.sizes {
|
||||
n = max(n, size)
|
||||
}
|
||||
bufs := make([][]byte, n)
|
||||
for i := range bufs {
|
||||
bufs[i] = make([]byte, udp.MTU)
|
||||
}
|
||||
for off, k := 0, 0; off < len(c.wire); k++ {
|
||||
size := c.batchLen
|
||||
if len(c.sizes) > 0 {
|
||||
size = c.sizes[min(k, len(c.sizes)-1)]
|
||||
}
|
||||
end := min(off+size, len(c.wire))
|
||||
for i, p := range c.wire[off:end] {
|
||||
n := copy(bufs[i], p)
|
||||
from := flowTestUnder
|
||||
if c.from != nil {
|
||||
from = c.from(off + i)
|
||||
}
|
||||
r(from, bufs[i][:n:n])
|
||||
}
|
||||
next := handoff(bufs)
|
||||
if len(next) != len(bufs) {
|
||||
panic("handoff returned the wrong number of buffers")
|
||||
}
|
||||
bufs = next
|
||||
for _, b := range bufs {
|
||||
for j := range b[:udp.MTU] {
|
||||
b[j] = 0x5a
|
||||
}
|
||||
}
|
||||
c.swaps++
|
||||
off = end
|
||||
}
|
||||
return os.ErrClosed
|
||||
}
|
||||
|
||||
type plainConn struct{ udp.Conn }
|
||||
|
||||
var rxBatches = metrics.GetOrRegisterCounter("flow.rx.batches", nil)
|
||||
|
||||
// receive runs the peer's listenOut over conn until conn runs out.
|
||||
func (p *flowTestPeer) receive(conn udp.Conn) {
|
||||
p.f.writers = []udp.Conn{conn}
|
||||
p.f.outside = conn
|
||||
p.f.listenOut(0)
|
||||
}
|
||||
|
||||
// TestFlowStagedFirewallParity: both paths apply the same outbound and inbound policy. An authenticated inbound
|
||||
// denial still consumes its replay counter, exactly as inline Decrypt does.
|
||||
func TestFlowStagedFirewallParity(t *testing.T) {
|
||||
for _, sc := range []stagedConfig{{}, stagedOn(2)} {
|
||||
t.Run(stagedName(sc), func(t *testing.T) {
|
||||
batches, _ := flowTestBatches(4, 3, 1, 8)
|
||||
sender, _ := newFlowTestPair(t, noise.CipherChaChaPoly, sc)
|
||||
sender.f.firewall.OutRules = newFirewallTable()
|
||||
sender.f.listenIn(newFlowBatchQueue(batches), 0)
|
||||
require.Empty(t, sender.conn.captured())
|
||||
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, sc)
|
||||
wire := wireFor(t, sender, batches)
|
||||
receiver.f.firewall.InRules = newFirewallTable()
|
||||
receiver.receive(&rxConn{wire: wire, batchLen: 64})
|
||||
require.Empty(t, receiver.tun.writes)
|
||||
for _, pkt := range wire {
|
||||
h := &header.H{}
|
||||
require.NoError(t, h.Parse(pkt))
|
||||
require.False(t, receiver.hostinfo.ConnectionState.window.Check(receiver.f.l, h.MessageCounter))
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestFlowStagedCipherFallback runs the parsed configuration with the real AES cipher: transmit falls back to inline
|
||||
// when the build needs nonce-ordered encryption (BoringCrypto, FIPS), receive decryption stays staged.
|
||||
func TestFlowStagedCipherFallback(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
c.Settings = map[string]any{"tun": map[string]any{"staged": map[string]any{"workers": 2}}}
|
||||
sender, receiver := newFlowTestPair(t, noiseutil.CipherAESGCM, parseStagedConfig(c, l))
|
||||
require.Equal(t, !noiseutil.EncryptLockNeeded, sender.f.staged.tx)
|
||||
require.True(t, sender.f.staged.rx)
|
||||
batches, want := flowTestBatches(4, 8, 1, 45)
|
||||
tx := metrics.GetOrRegisterCounter("flow.tx.batches", nil)
|
||||
tx0, rx0 := tx.Count(), rxBatches.Count()
|
||||
sender.f.listenIn(newFlowBatchQueue(batches), 0)
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
require.Equal(t, tx0, tx.Count())
|
||||
}
|
||||
receiver.receive(&rxConn{wire: sender.conn.captured(), batchLen: 512})
|
||||
require.Greater(t, rxBatches.Count(), rx0)
|
||||
require.Equal(t, want, receiver.tun.segments(t))
|
||||
}
|
||||
+583
@@ -0,0 +1,583 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"net/netip"
|
||||
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/firewall"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/noiseutil"
|
||||
"github.com/slackhq/nebula/overlay/batch"
|
||||
"github.com/slackhq/nebula/overlay/tio"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
)
|
||||
|
||||
var errFlowSegmentOverrun = errors.New("superpacket has more segments than counters reserved for it")
|
||||
|
||||
// txItem is one firewall-approved inside packet (or superpacket) with everything needed to encrypt it. A nonzero
|
||||
// counter is the first of the segs counters reserved for it on ci, relayCounter the same on the relay tunnel when
|
||||
// relayHI is set. Zero counters are allocated per segment while encrypting, as inline sends do.
|
||||
type txItem struct {
|
||||
pkt tio.Packet
|
||||
hostinfo *HostInfo
|
||||
ci *ConnectionState
|
||||
remote netip.AddrPort
|
||||
segs uint64
|
||||
counter uint64
|
||||
relayHI *HostInfo
|
||||
relay *Relay
|
||||
relayCounter uint64
|
||||
}
|
||||
|
||||
// prepareTxItem does the per-packet work sendInsideMessage does before it encrypts, and resolves where the packet goes.
|
||||
func (f *Interface) prepareTxItem(it *txItem, hostinfo *HostInfo, pkt tio.Packet) bool {
|
||||
ci := hostinfo.ConnectionState
|
||||
if ci.eKey == nil {
|
||||
return false
|
||||
}
|
||||
|
||||
f.recordOutbound(hostinfo)
|
||||
it.pkt, it.hostinfo, it.ci = pkt, hostinfo, ci
|
||||
it.remote = hostinfo.GetRemote()
|
||||
if it.remote.IsValid() {
|
||||
return true
|
||||
}
|
||||
|
||||
it.relayHI, it.relay = f.findRelay(hostinfo)
|
||||
if it.relayHI == nil || it.relay == nil {
|
||||
return false
|
||||
}
|
||||
it.remote = it.relayHI.GetRemote()
|
||||
return true
|
||||
}
|
||||
|
||||
// encryptTxItem segments and encrypts it into sb, for inline and staged sends alike.
|
||||
func (f *Interface) encryptTxItem(it *txItem, nb []byte, sb *batch.SendBatch) {
|
||||
reserved := it.counter != 0
|
||||
c, rc, end := it.counter, it.relayCounter, it.counter+it.segs
|
||||
err := tio.SegmentSuperpacket(it.pkt, func(seg []byte) error {
|
||||
if reserved && c >= end {
|
||||
// More segments than counters reserved for them, never encrypt past the reservation
|
||||
return errFlowSegmentOverrun
|
||||
}
|
||||
if it.relayHI == nil {
|
||||
// header + plaintext + AEAD tag (16 bytes for both AES-GCM and ChaCha20-Poly1305)
|
||||
if out := f.encryptTxSegment(it, c, seg, nb, sb.Reserve(header.Len+len(seg)+16)); out != nil {
|
||||
sb.Commit(out, it.remote)
|
||||
}
|
||||
} else {
|
||||
f.encryptTxSegmentVia(it, c, rc, seg, nb, sb)
|
||||
}
|
||||
if reserved {
|
||||
c++
|
||||
rc++
|
||||
}
|
||||
return nil
|
||||
})
|
||||
if err != nil {
|
||||
it.hostinfo.logger(f.l).Error("Failed to segment superpacket for send", "error", err)
|
||||
}
|
||||
}
|
||||
|
||||
// encryptTxSegment encrypts one segment into out with counter c, or with the next counter of the tunnel when c is
|
||||
// zero. It returns nil when encryption failed, which is already logged.
|
||||
func (f *Interface) encryptTxSegment(it *txItem, c uint64, seg, nb, out []byte) []byte {
|
||||
if c != 0 {
|
||||
// Reserved counters are unique, so the encryption needs no lock
|
||||
return f.encryptMessage(header.Message, 0, it.hostinfo, it.ci, c, seg, nb, out, it.remote)
|
||||
}
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
it.ci.writeLock.Lock()
|
||||
}
|
||||
c = it.ci.messageCounter.Add(1)
|
||||
out = f.encryptMessage(header.Message, 0, it.hostinfo, it.ci, c, seg, nb, out, it.remote)
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
it.ci.writeLock.Unlock()
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// encryptTxSegmentVia encrypts one segment for the relayed tunnel, then wraps it for the relay with counter rc, both
|
||||
// allocated on demand when zero like encryptTxSegment does.
|
||||
func (f *Interface) encryptTxSegmentVia(it *txItem, c, rc uint64, seg, nb []byte, sb *batch.SendBatch) {
|
||||
//relay header + header + plaintext + AEAD tag + relay tag
|
||||
scratch := sb.Reserve(len(seg) + header.MaxOverhead)
|
||||
out := f.encryptTxSegment(it, c, seg, nb, scratch[header.Len:])
|
||||
if out == nil {
|
||||
return
|
||||
}
|
||||
toSend, err := f.prepareSendVia(it.relayHI, it.relay, out, nb, scratch, true, rc)
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
remote := it.remote
|
||||
if rc == 0 {
|
||||
// Unreserved sends follow the relay's current remote, like sendNoMetrics
|
||||
remote = it.relayHI.GetRemote()
|
||||
}
|
||||
sb.Commit(toSend, remote)
|
||||
}
|
||||
|
||||
// txTunnel accumulates one tunnel's counter needs across a batch so the batch reserves them with one atomic add.
|
||||
type txTunnel struct {
|
||||
ci *ConnectionState
|
||||
hostinfo *HostInfo
|
||||
n uint64
|
||||
base uint64
|
||||
exhausted bool
|
||||
}
|
||||
|
||||
// txReserver turns one tun read into txItems with message counters reserved for them. Only the reader goroutine
|
||||
// collects and reserves counters.
|
||||
type txReserver struct {
|
||||
f *Interface
|
||||
tunnels []txTunnel
|
||||
owner uint64
|
||||
// The staged reader separates relay data before reserving direct work. A nil pointer collects both paths.
|
||||
inlineRelays *[]txItem
|
||||
}
|
||||
|
||||
// collect runs the filter over pkts and appends the sendable ones to items, tallying each tunnel's counter needs.
|
||||
func (r *txReserver) collect(items []txItem, pkts []tio.Packet, fwPacket *firewall.ParsedPacket, rejectBuf []byte, q int, localCache firewall.ConntrackCache) []txItem {
|
||||
f := r.f
|
||||
r.tunnels = r.tunnels[:0]
|
||||
for _, pkt := range pkts {
|
||||
hostinfo := f.filterInsidePacket(pkt, fwPacket, rejectBuf, q, localCache)
|
||||
if hostinfo == nil {
|
||||
continue
|
||||
}
|
||||
var it txItem
|
||||
if !f.prepareTxItem(&it, hostinfo, pkt) {
|
||||
continue
|
||||
}
|
||||
it.segs = uint64(pkt.SegmentCount())
|
||||
if it.relayHI != nil {
|
||||
// The relay bookkeeping inline sends do per segment in prepareSendVia, once per item
|
||||
f.connectionManager.OutNoRebind(it.relayHI)
|
||||
f.connectionManager.RelayUsed(it.relay.LocalIndex)
|
||||
if r.inlineRelays != nil {
|
||||
*r.inlineRelays = append(*r.inlineRelays, it)
|
||||
continue
|
||||
}
|
||||
it.relayCounter = r.need(it.relayHI, it.relayHI.ConnectionState, it.segs)
|
||||
}
|
||||
it.counter = r.need(it.hostinfo, it.ci, it.segs)
|
||||
items = append(items, it)
|
||||
}
|
||||
return items
|
||||
}
|
||||
|
||||
// need adds n counters to ci's tally for this batch and returns the offset of the first one within it.
|
||||
func (r *txReserver) need(hostinfo *HostInfo, ci *ConnectionState, n uint64) uint64 {
|
||||
t := r.tunnel(ci)
|
||||
if t == nil {
|
||||
r.tunnels = append(r.tunnels, txTunnel{ci: ci, hostinfo: hostinfo})
|
||||
t = &r.tunnels[len(r.tunnels)-1]
|
||||
}
|
||||
off := t.n
|
||||
t.n += n
|
||||
return off
|
||||
}
|
||||
|
||||
// tunnel finds ci's tally, a batch rarely touches more than a couple of tunnels so a scan beats a map.
|
||||
func (r *txReserver) tunnel(ci *ConnectionState) *txTunnel {
|
||||
for i := range r.tunnels {
|
||||
if r.tunnels[i].ci == ci {
|
||||
return &r.tunnels[i]
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// reserve takes the counters collect tallied and stamps them onto items, dropping the items of any tunnel whose
|
||||
// counter is exhausted. It returns the items that are left.
|
||||
func (r *txReserver) reserve(items []txItem) []txItem {
|
||||
f := r.f
|
||||
// One atomic add per tunnel reserves the whole batch's counters before any worker sees it, so counter order on a
|
||||
// tunnel is dispatch order, which is the order the batches are flushed in. Reservation and the sender's order are
|
||||
// both taken on the reader goroutine, so there is no window for another batch to slip in between.
|
||||
for i := range r.tunnels {
|
||||
t := &r.tunnels[i]
|
||||
end := t.ci.messageCounter.Add(t.n)
|
||||
t.base = end - t.n + 1
|
||||
if end >= RejectAfterMessages {
|
||||
t.ci.messageCounter.Store(RejectAfterMessages)
|
||||
t.exhausted = true
|
||||
f.messageMetrics.TxExhausted(int64(t.n))
|
||||
if t.base <= RejectAfterMessages {
|
||||
t.hostinfo.logger(f.l).Error("Dropping outbound packets, tunnel message counter is exhausted")
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
n := 0
|
||||
for _, it := range items {
|
||||
t := r.tunnel(it.ci)
|
||||
if t.exhausted {
|
||||
continue
|
||||
}
|
||||
it.counter += t.base
|
||||
if it.relayHI != nil {
|
||||
rt := r.tunnel(it.relayHI.ConnectionState)
|
||||
if rt.exhausted {
|
||||
continue
|
||||
}
|
||||
it.relayCounter += rt.base
|
||||
}
|
||||
items[n] = it
|
||||
n++
|
||||
}
|
||||
clear(items[n:])
|
||||
return items[:n]
|
||||
}
|
||||
|
||||
// handoffQueue is a tun queue that can give up the buffer its last Read filled. SwapRxBuf(nil) allocates a
|
||||
// correctly sized replacement; later swaps recycle the buffers handed back.
|
||||
type handoffQueue interface {
|
||||
tio.Queue
|
||||
SwapRxBuf([]byte) []byte
|
||||
}
|
||||
|
||||
// txSlot is one staged batch. The reader fills items, a worker encrypts them into sb and signals done, and the
|
||||
// ordered sender flushes sb.
|
||||
type txSlot struct {
|
||||
f *Interface
|
||||
items []txItem
|
||||
// buf owns the queue receive buffer the items point into, swapped out at dispatch
|
||||
buf []byte
|
||||
sb *batch.SendBatch
|
||||
done chan struct{}
|
||||
// reservations hold shared tunnel credit until the flush, including for dropped counters
|
||||
reservations []txTunnel
|
||||
}
|
||||
|
||||
func (s *txSlot) run(nb []byte) {
|
||||
for i := range s.items {
|
||||
s.f.encryptTxItem(&s.items[i], nb, s.sb)
|
||||
}
|
||||
s.done <- struct{}{}
|
||||
}
|
||||
|
||||
// stagedTx is the staged transmit pipeline of one tun reader. Everything but the workers and the sender runs on the
|
||||
// reader goroutine.
|
||||
type stagedTx struct {
|
||||
txReserver
|
||||
// Relay data always leaves on the reader, including small and oversized reads. Its independent reservation
|
||||
// scratch keeps mixed reads from changing the direct pipeline's counters, gate or sender placement.
|
||||
relayReserver txReserver
|
||||
relaySlot txSlot
|
||||
q int
|
||||
cpu int // reader CPU, inline sends stay here
|
||||
senderCPU int // -1 leaves the sender within its inherited affinity
|
||||
queue handoffQueue
|
||||
pool *flowPool
|
||||
// sb and nb are the reader's own, for the sends it does itself
|
||||
sb *batch.SendBatch
|
||||
nb []byte
|
||||
|
||||
// free holds the reader's idle slots. A dispatched slot goes to the workers and, in the same order, to the
|
||||
// sender on ordered; the sender gives it back on returned once it is on the wire.
|
||||
free []*txSlot
|
||||
ordered chan *txSlot
|
||||
returned chan *txSlot
|
||||
inFlight int
|
||||
senderDone chan struct{}
|
||||
// gateInline is the routine's transmit mode, gateStreak how many reads in a row wanted the other one
|
||||
gateInline bool
|
||||
gateStreak int
|
||||
|
||||
metricGateSwitches metrics.Counter
|
||||
|
||||
metricBatches metrics.Counter
|
||||
metricInline metrics.Counter
|
||||
}
|
||||
|
||||
// newStagedTx needs a queue that hands over whole read batches, the offload (TSO/USO) queue on linux. On any other
|
||||
// queue a read is one packet, and staging it would cost a handoff per packet.
|
||||
func newStagedTx(f *Interface, queue handoffQueue, q int) *stagedTx {
|
||||
p := &stagedTx{
|
||||
txReserver: txReserver{f: f, tunnels: make([]txTunnel, 0, 4), owner: txBudgetOwner(q)},
|
||||
q: q,
|
||||
senderCPU: -1,
|
||||
queue: queue,
|
||||
sb: batch.NewSendBatch(f.writers[q], batch.SendBatchCap, batch.SendBatchCap*(udp.MTU+32)),
|
||||
nb: make([]byte, 12),
|
||||
ordered: make(chan *txSlot, f.staged.txSlots),
|
||||
returned: make(chan *txSlot, f.staged.txSlots),
|
||||
senderDone: make(chan struct{}),
|
||||
metricBatches: metrics.GetOrRegisterCounter("flow.tx.batches", nil),
|
||||
metricInline: metrics.GetOrRegisterCounter("flow.tx.inline", nil),
|
||||
// Starts inline, the pipeline is empty, unless the threshold never allows it
|
||||
gateInline: f.staged.inlineBelow > 0,
|
||||
metricGateSwitches: metrics.GetOrRegisterCounter("flow.tx.gate_switches", nil),
|
||||
}
|
||||
// Inline relay sends can share a tunnel with older direct work on this routine. They are not the ordered
|
||||
// sender's sole owner, so they must not recycle credit around a stalled direct reservation.
|
||||
p.relayReserver = txReserver{f: f, tunnels: make([]txTunnel, 0, 4)}
|
||||
p.inlineRelays = &p.relaySlot.items
|
||||
if f.pinThreads {
|
||||
p.cpu = f.threadCPU(q)
|
||||
// Only an explicit list pins the sender, and never onto its reader's CPU, where the two would serialise.
|
||||
// Automatic placement by queue index can put a busy sender on a slow core; unpinned, the scheduler moves it.
|
||||
if n := len(f.cpuAffinity); n > 0 && f.cpuAffinity[(q+1)%n] != p.cpu {
|
||||
p.senderCPU = f.cpuAffinity[(q+1)%n]
|
||||
}
|
||||
}
|
||||
p.pool = newFlowPool(f.staged.workers, f.staged.txSlots)
|
||||
|
||||
// Ciphertext adds per-segment headers and tags; the arena can grow for small segments.
|
||||
buf := queue.SwapRxBuf(nil)
|
||||
bufSize := len(buf)
|
||||
for i := range f.staged.txSlots {
|
||||
if i > 0 {
|
||||
buf = make([]byte, bufSize)
|
||||
}
|
||||
p.free = append(p.free, &txSlot{
|
||||
f: f,
|
||||
buf: buf,
|
||||
sb: batch.NewSendBatch(f.writers[q], 4*batch.SendBatchCap, bufSize+bufSize/4),
|
||||
done: make(chan struct{}, 1),
|
||||
})
|
||||
}
|
||||
go p.sender()
|
||||
return p
|
||||
}
|
||||
|
||||
// run is listenIn's loop with the staged pipeline: read, then hand each batch on, until the queue fails.
|
||||
func (p *stagedTx) run(fwPacket *firewall.ParsedPacket, rejectBuf []byte, conntrackCache *firewall.ConntrackCacheTicker) error {
|
||||
defer p.close()
|
||||
if p.f.pinThreads {
|
||||
p.f.pinThreadToCPU(p.q, p.cpu)
|
||||
}
|
||||
for {
|
||||
pkts, err := p.queue.Read()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
p.ready()
|
||||
p.handle(pkts, fwPacket, rejectBuf, conntrackCache.Get())
|
||||
}
|
||||
}
|
||||
|
||||
// handle takes one tun read through the pipeline. It returns once the batch is queued, or sent when the reader sent
|
||||
// it itself.
|
||||
func (p *stagedTx) handle(pkts []tio.Packet, fwPacket *firewall.ParsedPacket, rejectBuf []byte, localCache firewall.ConntrackCache) {
|
||||
p.ready()
|
||||
inline := p.gate(p.small(pkts))
|
||||
if inline && p.f.routines == 1 {
|
||||
// With only one reader and an empty pipeline, no other staged reservation can be overtaken. Keep this common
|
||||
// case inexpensive.
|
||||
p.inlineSoleReader(pkts, fwPacket, rejectBuf, localCache)
|
||||
return
|
||||
}
|
||||
|
||||
slot := p.free[len(p.free)-1]
|
||||
p.free = p.free[:len(p.free)-1]
|
||||
items := p.collect(slot.items[:0], pkts, fwPacket, rejectBuf, p.q, localCache)
|
||||
if len(p.relaySlot.items) != 0 {
|
||||
p.sendRelays()
|
||||
}
|
||||
if len(items) == 0 {
|
||||
slot.items = items
|
||||
p.free = append(p.free, slot)
|
||||
return
|
||||
}
|
||||
|
||||
if p.oversized() {
|
||||
p.metricInline.Inc(1)
|
||||
p.sendLarge(&p.txReserver, items)
|
||||
slot.items = items[:0]
|
||||
p.free = append(p.free, slot)
|
||||
return
|
||||
}
|
||||
if !p.waitBudget(&p.txReserver) {
|
||||
clear(items)
|
||||
slot.items = items[:0]
|
||||
p.free = append(p.free, slot)
|
||||
return
|
||||
}
|
||||
slot.reservations = append(slot.reservations[:0], p.tunnels...)
|
||||
items = p.reserve(items)
|
||||
slot.items = items
|
||||
if len(items) == 0 {
|
||||
slot.releaseBudget()
|
||||
p.free = append(p.free, slot)
|
||||
return
|
||||
}
|
||||
|
||||
if inline {
|
||||
p.inline(slot)
|
||||
p.free = append(p.free, slot)
|
||||
return
|
||||
}
|
||||
|
||||
// The packets now live in the slot, and the queue reads into the slot's old buffer
|
||||
slot.buf = p.queue.SwapRxBuf(slot.buf)
|
||||
|
||||
p.inFlight++
|
||||
p.metricBatches.Inc(1)
|
||||
// Counters were reserved above on this goroutine and the slot takes its place in the sender's order right here,
|
||||
// before any other batch can, so the sender puts them on the wire in counter order.
|
||||
p.ordered <- slot
|
||||
p.pool.jobs <- slot
|
||||
}
|
||||
|
||||
// sendRelays keeps relay data on one send path for the lifetime of this routine. The gate's software drain only
|
||||
// waits for socket submission; switching CPUs can still overtake packets on another NIC queue. Direct data retains
|
||||
// the existing gate and sender placement. Relay credit is still shared with all other users of both tunnels.
|
||||
func (p *stagedTx) sendRelays() {
|
||||
r, slot := &p.relayReserver, &p.relaySlot
|
||||
r.tunnels = r.tunnels[:0]
|
||||
for i := range slot.items {
|
||||
it := &slot.items[i]
|
||||
it.counter = r.need(it.hostinfo, it.ci, it.segs)
|
||||
it.relayCounter = r.need(it.relayHI, it.relayHI.ConnectionState, it.segs)
|
||||
}
|
||||
if r.oversized() {
|
||||
p.metricInline.Inc(1)
|
||||
p.sendLarge(r, slot.items)
|
||||
slot.items = slot.items[:0]
|
||||
return
|
||||
}
|
||||
if !p.waitBudget(r) {
|
||||
clear(slot.items)
|
||||
slot.items = slot.items[:0]
|
||||
return
|
||||
}
|
||||
slot.reservations = append(slot.reservations[:0], r.tunnels...)
|
||||
slot.items = r.reserve(slot.items)
|
||||
p.inline(slot)
|
||||
}
|
||||
|
||||
// gate reports whether a read goes inline. Each routine holds one
|
||||
// transmit mode, inline on the reader or fanout to the workers and the sender, until gateHold reads in a row want the
|
||||
// other one, the last of which goes the new way. Choosing per read let small inline sends leave from the reader's CPU
|
||||
// between staged ones leaving from the sender's, and the receiver's TCP saw them reordered. Going inline the reader
|
||||
// first waits until everything in flight has been submitted to the socket and the sender is idle. This does not
|
||||
// drain independent NIC queues; relay data therefore always uses the reader. Going to fanout nothing is in flight:
|
||||
// inline sends finish before the reader moves on.
|
||||
func (p *stagedTx) gate(small bool) bool {
|
||||
if small == p.gateInline {
|
||||
p.gateStreak = 0
|
||||
return small
|
||||
}
|
||||
if p.gateStreak++; p.gateStreak < p.f.staged.gateHold {
|
||||
return p.gateInline
|
||||
}
|
||||
p.gateInline, p.gateStreak = small, 0
|
||||
p.metricGateSwitches.Inc(1)
|
||||
if !small {
|
||||
return false
|
||||
}
|
||||
for p.flushOldest() {
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// ready takes back every slot the sender has finished with, and waits for one when all of them are in flight.
|
||||
func (p *stagedTx) ready() {
|
||||
p.reap()
|
||||
if len(p.free) == 0 {
|
||||
p.release(<-p.returned)
|
||||
}
|
||||
}
|
||||
|
||||
// reap takes back every slot the sender has finished with, without waiting.
|
||||
func (p *stagedTx) reap() {
|
||||
for {
|
||||
select {
|
||||
case s := <-p.returned:
|
||||
p.release(s)
|
||||
default:
|
||||
return
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// flushOldest waits for the oldest batch in flight to reach the wire and takes its slot back. It reports false when
|
||||
// nothing is in flight.
|
||||
func (p *stagedTx) flushOldest() bool {
|
||||
if p.inFlight == 0 {
|
||||
return false
|
||||
}
|
||||
p.release(<-p.returned)
|
||||
return true
|
||||
}
|
||||
|
||||
func (p *stagedTx) release(s *txSlot) {
|
||||
p.inFlight--
|
||||
p.free = append(p.free, s)
|
||||
}
|
||||
|
||||
// sender is the ordered send stage: it puts each batch on the wire once its worker is done, in dispatch order.
|
||||
func (p *stagedTx) sender() {
|
||||
defer close(p.senderDone)
|
||||
if p.senderCPU >= 0 {
|
||||
p.f.pinThreadToCPU(p.q, p.senderCPU)
|
||||
}
|
||||
for s := range p.ordered {
|
||||
<-s.done
|
||||
if p.f.closed.Load() {
|
||||
// The sockets are gone, a flush would only log errors
|
||||
s.sb.Reset()
|
||||
} else {
|
||||
p.f.flushSendBatch(s.sb, p.q)
|
||||
}
|
||||
s.releaseBudget()
|
||||
clear(s.items)
|
||||
s.items = s.items[:0]
|
||||
p.returned <- s
|
||||
}
|
||||
}
|
||||
|
||||
// close sends everything still in flight, in order, and stops the sender and the workers.
|
||||
func (p *stagedTx) close() {
|
||||
close(p.ordered)
|
||||
<-p.senderDone
|
||||
p.pool.close()
|
||||
}
|
||||
|
||||
// small counts segments against the inline threshold.
|
||||
func (p *stagedTx) small(pkts []tio.Packet) bool {
|
||||
below := uint64(p.f.staged.inlineBelow)
|
||||
if below == 0 {
|
||||
return false
|
||||
}
|
||||
var n uint64
|
||||
for _, pkt := range pkts {
|
||||
if n += uint64(pkt.SegmentCount()); n >= below {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// inline encrypts a budgeted batch on the reader, with no worker handoff or buffer swap. The local sender is idle,
|
||||
// but other readers may hold reservations on these tunnels, so keep our credit until the flush completes.
|
||||
func (p *stagedTx) inline(slot *txSlot) {
|
||||
p.metricInline.Inc(1)
|
||||
for i := range slot.items {
|
||||
p.f.encryptTxItem(&slot.items[i], p.nb, p.sb)
|
||||
if p.sb.Len() >= batch.SendBatchCap {
|
||||
p.f.flushSendBatch(p.sb, p.q)
|
||||
}
|
||||
}
|
||||
p.f.flushSendBatch(p.sb, p.q)
|
||||
slot.releaseBudget()
|
||||
clear(slot.items)
|
||||
slot.items = slot.items[:0]
|
||||
}
|
||||
|
||||
// inlineSoleReader needs no credit: the interface has no other tun reader and this reader has drained every
|
||||
// reservation before taking the inline path.
|
||||
func (p *stagedTx) inlineSoleReader(pkts []tio.Packet, fwPacket *firewall.ParsedPacket, rejectBuf []byte, localCache firewall.ConntrackCache) {
|
||||
p.metricInline.Inc(1)
|
||||
for _, pkt := range pkts {
|
||||
p.f.consumeInsidePacket(pkt, fwPacket, p.nb, p.sb, rejectBuf, p.q, localCache)
|
||||
if p.sb.Len() >= batch.SendBatchCap {
|
||||
p.f.flushSendBatch(p.sb, p.q)
|
||||
}
|
||||
}
|
||||
p.f.flushSendBatch(p.sb, p.q)
|
||||
}
|
||||
@@ -0,0 +1,231 @@
|
||||
//go:build linux && !android && !e2e_testing
|
||||
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"net/netip"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"os"
|
||||
"os/exec"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/overlay/tio"
|
||||
|
||||
"github.com/flynn/noise"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/slackhq/nebula/util"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// queuedWire models two CPU-selected NIC queues with independent completion: the reader's
|
||||
// queue is congested, while another CPU's queue drains immediately. WriteBatch returning only
|
||||
// means the kernel accepted the packets; draining staged slots does not drain a NIC queue.
|
||||
// The sampled affinity makes the schedule deterministic without a real socket or NIC. An
|
||||
// unpinned sender alternates between allowed CPUs, even if it happened not to in this run.
|
||||
func (c *affinityConn) queuedWire(readerCPU int) [][]byte {
|
||||
var slow, fast [][]byte
|
||||
wire := c.captured()
|
||||
off := 0
|
||||
for i, n := range c.sizes {
|
||||
mask := c.masks[i]
|
||||
if mask.IsSet(readerCPU) && (mask.Count() == 1 || i%2 == 0) {
|
||||
slow = append(slow, wire[off:off+n]...)
|
||||
} else {
|
||||
fast = append(fast, wire[off:off+n]...)
|
||||
}
|
||||
off += n
|
||||
}
|
||||
return append(fast, slow...)
|
||||
}
|
||||
|
||||
// TestFlowStagedTXRelayQueuedWire reproduces reorder after successful, ordered socket
|
||||
// submissions. Mixed reads switch the sticky gate with an empty software pipeline; relayed
|
||||
// data must stay on the reader throughout, without moving the direct sender. Each routine owns a flow.
|
||||
func TestFlowStagedTXRelayQueuedWire(t *testing.T) {
|
||||
if os.Getenv("NEBULA_FLOW_RING_TEST") != "1" {
|
||||
cmd := exec.Command(os.Args[0], "-test.run=^TestFlowStagedTXRelayQueuedWire$")
|
||||
cmd.Env = append(os.Environ(), "NEBULA_FLOW_RING_TEST=1")
|
||||
out, err := cmd.CombinedOutput()
|
||||
require.NoError(t, err, "%s", out)
|
||||
return
|
||||
}
|
||||
allowed, err := util.AllowedCPUs()
|
||||
require.NoError(t, err)
|
||||
if len(allowed) < 2 {
|
||||
t.Skip("requires two allowed CPUs")
|
||||
}
|
||||
for _, mode := range []string{"gate", "always-staged", "oversized"} {
|
||||
for _, explicit := range []bool{false, true} {
|
||||
for _, routines := range []int{1, 2} {
|
||||
for q := range routines {
|
||||
t.Run(fmt.Sprintf("%s/explicit=%t/routines=%d/q=%d", mode, explicit, routines, q), func(t *testing.T) {
|
||||
sc := gated(stagedGateHold)
|
||||
if mode != "gate" {
|
||||
sc.inlineBelow = 0
|
||||
}
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, sc)
|
||||
f := sender.f
|
||||
f.pinThreads, f.routines = true, routines
|
||||
if explicit {
|
||||
f.cpuAffinity = allowed[:2]
|
||||
}
|
||||
_, relayHI, relayPeer := addTestRelay(t, sender, ReplayWindow)
|
||||
conn := &affinityConn{}
|
||||
f.writers = make([]udp.Conn, routines)
|
||||
for i := range f.writers {
|
||||
f.writers[i] = conn
|
||||
}
|
||||
shape := append(repeatBool(false, 2), repeatBool(true, stagedGateHold+2)...)
|
||||
shape = append(shape, repeatBool(false, stagedGateHold+2)...)
|
||||
if mode != "gate" {
|
||||
shape = []bool{false, true, false, true}
|
||||
}
|
||||
reads, want := gateReads(shape...)
|
||||
if mode == "oversized" {
|
||||
// A deliberately tiny outer budget alone forces the oversized fallback.
|
||||
relayHI.ConnectionState.window = NewBits(16)
|
||||
}
|
||||
queue := &affinityQueue{flowBatchQueue: newFlowBatchQueue(reads), conn: conn}
|
||||
// Each Read waits for all previous socket submissions, making software drain
|
||||
// irrelevant to the independently queued packets in queuedWire.
|
||||
f.listenIn(queue, q)
|
||||
unwrap := func(wire [][]byte) [][]byte {
|
||||
inner := make([][]byte, 0, len(wire))
|
||||
for _, pkt := range wire {
|
||||
inner = append(inner, pkt[header.Len:len(pkt)-relayPeer.dKey.Overhead()])
|
||||
}
|
||||
return inner
|
||||
}
|
||||
require.Equal(t, want, decryptWire(t, receiver, unwrap(conn.captured())), "socket submission order")
|
||||
require.Equal(t, want, decryptWire(t, receiver, unwrap(conn.queuedWire(f.threadCPU(q)))), "NIC queue completion order")
|
||||
})
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Mixed reads must keep direct sends on the original staged sender, including when relay data is present.
|
||||
func TestFlowStagedTXMixedPlacement(t *testing.T) {
|
||||
if os.Getenv("NEBULA_FLOW_MIXED_TEST") != "1" {
|
||||
cmd := exec.Command(os.Args[0], "-test.run=^TestFlowStagedTXMixedPlacement$")
|
||||
cmd.Env = append(os.Environ(), "NEBULA_FLOW_MIXED_TEST=1")
|
||||
out, err := cmd.CombinedOutput()
|
||||
require.NoError(t, err, "%s", out)
|
||||
return
|
||||
}
|
||||
allowed, err := util.AllowedCPUs()
|
||||
require.NoError(t, err)
|
||||
if len(allowed) < 2 {
|
||||
t.Skip("requires two allowed CPUs")
|
||||
}
|
||||
for _, explicit := range []bool{false, true} {
|
||||
t.Run(fmt.Sprintf("explicit=%t", explicit), func(t *testing.T) {
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, stagedOn(2))
|
||||
_, _, relayPeer := addTestRelay(t, sender, ReplayWindow)
|
||||
direct, directReceiver := newFlowTestPair(t, noise.CipherChaChaPoly, stagedOn(2))
|
||||
directAddr := netip.MustParseAddr("10.0.0.4")
|
||||
direct.hostinfo.vpnAddrs = []netip.Addr{directAddr}
|
||||
f := sender.f
|
||||
f.hostMap.Hosts[directAddr] = direct.hostinfo
|
||||
f.pinThreads, f.routines = true, 2
|
||||
sendCPU := -1
|
||||
if explicit {
|
||||
f.cpuAffinity = allowed[:2]
|
||||
sendCPU = allowed[1]
|
||||
}
|
||||
conn := &affinityConn{}
|
||||
f.writers = []udp.Conn{conn, conn}
|
||||
var reads [][]tio.Packet
|
||||
var wantRelay, wantDirect []decodedSeg
|
||||
for seq := range uint32(6) {
|
||||
r := flowTCPSuperpacket(0, seq, 3)
|
||||
d := flowTCPSuperpacket(1, seq, 9)
|
||||
copy(d.Bytes[16:20], directAddr.AsSlice())
|
||||
reads = append(reads, []tio.Packet{r, d})
|
||||
for i := range 3 {
|
||||
wantRelay = append(wantRelay, decodedSeg{seq: seq, idx: uint16(i)})
|
||||
}
|
||||
for i := range 9 {
|
||||
wantDirect = append(wantDirect, decodedSeg{flow: 1, seq: seq, idx: uint16(i)})
|
||||
}
|
||||
}
|
||||
queue := &affinityQueue{flowBatchQueue: newFlowBatchQueue(reads), conn: conn}
|
||||
f.listenIn(queue, 0)
|
||||
wire := conn.captured()
|
||||
var directWire, relayWire [][]byte
|
||||
off := 0
|
||||
for i, n := range conn.sizes {
|
||||
for _, pkt := range wire[off : off+n] {
|
||||
var h header.H
|
||||
require.NoError(t, h.Parse(pkt))
|
||||
cpu := sendCPU
|
||||
if h.Subtype == header.MessageRelay {
|
||||
cpu = f.threadCPU(0)
|
||||
require.NoError(t, relayPeer.VerifyRelay(nil, h.MessageCounter, pkt, make([]byte, 12)))
|
||||
relayWire = append(relayWire, pkt[header.Len:len(pkt)-relayPeer.dKey.Overhead()])
|
||||
} else {
|
||||
directWire = append(directWire, pkt)
|
||||
}
|
||||
requireFlowCPU(t, conn.masks[i:i+1], cpu, allowed)
|
||||
}
|
||||
off += n
|
||||
}
|
||||
require.Equal(t, wantDirect, decryptWire(t, directReceiver, directWire))
|
||||
require.Equal(t, wantRelay, decryptWire(t, receiver, relayWire))
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// A relayed batch shares its outer tunnel with older staged direct data on the SAME routine. Inline completion
|
||||
// must not refund that direct sender's credit while its oldest reservation is stalled.
|
||||
func TestFlowStagedTXRelaySharedBudget(t *testing.T) {
|
||||
sender, _ := newFlowTestPair(t, noise.CipherChaChaPoly, stagedOn(2))
|
||||
_, via, _ := addTestRelay(t, sender, ReplayWindow)
|
||||
// Give the relay host the same ordinary peer metadata as a direct tunnel.
|
||||
direct := newFlowTestPeer(t, flowTestLocal, via.vpnAddrs[0], via.ConnectionState, 300, 400)
|
||||
via.buildNetworks(sender.f.myVpnNetworksTable, direct.hostinfo.ConnectionState.peerCert.Certificate)
|
||||
via.remoteIndexId = direct.hostinfo.remoteIndexId
|
||||
ci := via.ConnectionState
|
||||
ci.window = NewBits(32)
|
||||
start := ci.messageCounter.Load()
|
||||
entered, unblock := make(chan struct{}), make(chan struct{})
|
||||
var release sync.Once
|
||||
delayCrypto(direct, func(n uint64) {
|
||||
if n == start+1 {
|
||||
close(entered)
|
||||
<-unblock
|
||||
}
|
||||
})
|
||||
p := newStagedTx(sender.f, newFlowBatchQueue(nil), 0)
|
||||
defer p.close()
|
||||
defer release.Do(func() { close(unblock) })
|
||||
d := flowTCPSuperpacket(1, 0, 9)
|
||||
copy(d.Bytes[16:20], via.vpnAddrs[0].AsSlice())
|
||||
p.send([]tio.Packet{d})
|
||||
select {
|
||||
case <-entered:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("direct worker did not start")
|
||||
}
|
||||
for seq := range uint32(7) {
|
||||
p.send([]tio.Packet{flowTCPSuperpacket(0, seq, 1)})
|
||||
}
|
||||
require.Equal(t, uint64(16), (ci.txBudget.state.Load()>>24)&txBudgetMask)
|
||||
done := make(chan struct{})
|
||||
go func() { defer close(done); p.send([]tio.Packet{flowTCPSuperpacket(0, 7, 1)}) }()
|
||||
select {
|
||||
case <-done:
|
||||
t.Error("relay recycled credit around a stalled direct reservation")
|
||||
case <-time.After(50 * time.Millisecond):
|
||||
}
|
||||
require.Equal(t, start+16, ci.messageCounter.Load())
|
||||
release.Do(func() { close(unblock) })
|
||||
<-done
|
||||
p.drain()
|
||||
require.Zero(t, ci.txBudget.state.Load())
|
||||
}
|
||||
+604
@@ -0,0 +1,604 @@
|
||||
//go:build linux && !android && !e2e_testing
|
||||
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"net/netip"
|
||||
"os"
|
||||
"os/exec"
|
||||
"slices"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/flynn/noise"
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/cpupick"
|
||||
"github.com/slackhq/nebula/firewall"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/noiseutil"
|
||||
"github.com/slackhq/nebula/overlay/batch"
|
||||
"github.com/slackhq/nebula/overlay/tio"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/slackhq/nebula/util"
|
||||
"github.com/stretchr/testify/require"
|
||||
"go.uber.org/goleak"
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// TestReservedEncryptionMatchesInline encrypts a batch with counters reserved up front: the receiver accepts every
|
||||
// segment, in order.
|
||||
func TestReservedEncryptionMatchesInline(t *testing.T) {
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, stagedConfig{})
|
||||
packets, want := flowTestBatches(1, 3, 3, 9)
|
||||
r := txReserver{f: sender.f}
|
||||
items := r.collect(nil, packets[0], &firewall.ParsedPacket{}, make([]byte, mtu), 0, nil)
|
||||
require.Equal(t, uint64(len(want)), r.tunnels[0].n)
|
||||
sb := batch.NewSendBatch(sender.conn, 128, 65536)
|
||||
for _, it := range r.reserve(items) {
|
||||
sender.f.encryptTxItem(&it, make([]byte, 12), sb)
|
||||
}
|
||||
sender.f.flushSendBatch(sb, 0)
|
||||
require.Equal(t, want, decryptWire(t, receiver, sender.conn.captured()))
|
||||
}
|
||||
|
||||
// TestSegmentCount checks tio.Packet.SegmentCount predicts exactly the segments tio.SegmentSuperpacket cuts, odd tails included.
|
||||
func TestSegmentCount(t *testing.T) {
|
||||
require.Equal(t, 1, tio.Packet{Bytes: make([]byte, 60)}.SegmentCount())
|
||||
for _, segs := range []int{1, 2, 3, 45} {
|
||||
for _, tail := range []int{0, 1, flowTestMSS - 1} {
|
||||
pkt := flowTCPSuperpacket(0, 0, segs)
|
||||
pkt.Bytes = pkt.Bytes[:len(pkt.Bytes)-tail]
|
||||
pkt.GSO = tio.GSOInfo{Size: flowTestMSS, HdrLen: 40, CsumStart: 20, Proto: tio.GSOProtoTCP}
|
||||
want, got := pkt.SegmentCount(), 0
|
||||
require.NoError(t, tio.SegmentSuperpacket(pkt, func([]byte) error { got++; return nil }))
|
||||
require.Equal(t, want, got, "segs %d tail %d", segs, tail)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestFlowStagedTXOrderAndCounters runs the staged transmit pipeline with shuffled workers and a slow socket, so the
|
||||
// sender lags and the reader runs into backpressure, then fails the tun read with batches in flight: the wire must
|
||||
// carry every segment once, in tun read order, under strictly increasing counters that were each reserved exactly
|
||||
// once, and the read error is still reported.
|
||||
func TestFlowStagedTXOrderAndCounters(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
for _, cipher := range []noise.CipherFunc{noiseutil.CipherAESGCM, noise.CipherChaChaPoly} {
|
||||
t.Run(cipher.CipherName(), func(t *testing.T) {
|
||||
if cipher.CipherName() == noiseutil.CipherAESGCM.CipherName() && noiseutil.EncryptLockNeeded {
|
||||
t.Skip("AES-GCM requires encryption in nonce order")
|
||||
}
|
||||
sender, receiver := newFlowTestPair(t, cipher, stagedOn(4))
|
||||
delayCrypto(sender, func(n uint64) {
|
||||
if n%54 == 0 {
|
||||
time.Sleep(time.Millisecond)
|
||||
}
|
||||
})
|
||||
// Far slower than the reader, even under the race detector
|
||||
sender.conn.delay = 8 * time.Millisecond
|
||||
batches, want := flowTestBatches(60, 6, 3, 9)
|
||||
start := sender.hostinfo.ConnectionState.messageCounter.Load()
|
||||
tx := metrics.GetOrRegisterCounter("flow.tx.batches", nil)
|
||||
tx0 := tx.Count()
|
||||
sender.f.listenIn(newFlowBatchQueue(batches), 0)
|
||||
require.Equal(t, int64(len(batches)), tx.Count()-tx0, "every batch uses the ordered sender")
|
||||
require.Equal(t, want, decryptWire(t, receiver, sender.conn.captured()), "wire order must match tun read order")
|
||||
require.Equal(t, start+uint64(len(want)), sender.hostinfo.ConnectionState.messageCounter.Load())
|
||||
require.NotNil(t, sender.f.fatalErr.Load())
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestFlowStagedTXCloseInFlight closes the interface and tun while batches are in flight, 20 times over.
|
||||
func TestFlowStagedTXCloseInFlight(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
for range 20 {
|
||||
sender, _ := newFlowTestPair(t, noise.CipherChaChaPoly, stagedOn(3))
|
||||
sender.conn.delay = time.Millisecond
|
||||
batches, _ := flowTestBatches(400, 4, 2, 8)
|
||||
q := newFlowBatchQueue(batches)
|
||||
done := make(chan struct{})
|
||||
go func() { sender.f.listenIn(q, 0); close(done) }()
|
||||
require.Eventually(t, func() bool { return q.reads.Load() > 5 }, 5*time.Second, 100*time.Microsecond)
|
||||
sender.f.closed.Store(true)
|
||||
require.NoError(t, q.Close())
|
||||
<-done
|
||||
}
|
||||
}
|
||||
|
||||
// TestFlowStagedTXExhausted drops every batch of a tunnel whose counter runs out, like inline sends do.
|
||||
func TestFlowStagedTXExhausted(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
sender, _ := newFlowTestPair(t, noise.CipherChaChaPoly, stagedOn(2))
|
||||
ci := sender.hostinfo.ConnectionState
|
||||
ci.messageCounter.Store(RejectAfterMessages - 3)
|
||||
sender.f.listenIn(newFlowBatchQueue([][]tio.Packet{{flowTCPSuperpacket(0, 0, 10)}, {flowTCPSuperpacket(0, 1, 2)}}), 0)
|
||||
require.Empty(t, sender.conn.captured())
|
||||
require.Equal(t, RejectAfterMessages, ci.messageCounter.Load())
|
||||
require.Equal(t, int64(12), sender.f.messageMetrics.txExhausted.Count())
|
||||
require.Zero(t, ci.txBudget.state.Load())
|
||||
}
|
||||
|
||||
// TestFlowStagedTXRelay sends staged batches, and an empty read, through a relay: outer and inner layers both verify,
|
||||
// in order, and go to the relay.
|
||||
// With a tiny MSS, the middle superpacket alone exceeds the tunnels' whole credit: it must be split, not admitted as an
|
||||
// unbounded lone batch, with either replay window.
|
||||
func TestFlowStagedTXRelay(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
for _, window := range budgetWindows {
|
||||
t.Run(fmt.Sprintf("window=%d", window), func(t *testing.T) {
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, stagedOn(2))
|
||||
sender.hostinfo.ConnectionState.window = NewBits(window)
|
||||
receiver.hostinfo.ConnectionState.window = NewBits(window)
|
||||
relayRemote, relayHI, relayPeer := addTestRelay(t, sender, window)
|
||||
batches, want := flowTestBatches(2, 3, 1, 6)
|
||||
var payload []byte
|
||||
large := flowTCPSuperpacket(0, 9, 45)
|
||||
large.GSO.Size = 1
|
||||
payload = append([]byte(nil), large.Bytes[40:]...)
|
||||
batches = [][]tio.Packet{batches[0], {large}, batches[1]}
|
||||
sender.f.listenIn(newFlowBatchQueue(append(batches, nil)), 0)
|
||||
wire := sender.conn.captured()
|
||||
require.Len(t, wire, len(want)+len(payload))
|
||||
var got []decodedSeg
|
||||
var tiny []byte
|
||||
var lastOuter, lastInner uint64
|
||||
for i, pkt := range wire {
|
||||
require.Equal(t, relayRemote, sender.conn.addrs[i])
|
||||
h := &header.H{}
|
||||
require.NoError(t, h.Parse(pkt))
|
||||
require.Greater(t, h.MessageCounter, lastOuter)
|
||||
lastOuter = h.MessageCounter
|
||||
require.NoError(t, relayPeer.VerifyRelay(nil, h.MessageCounter, pkt, make([]byte, 12)))
|
||||
pkt = pkt[header.Len : len(pkt)-16]
|
||||
require.NoError(t, h.Parse(pkt))
|
||||
require.Greater(t, h.MessageCounter, lastInner)
|
||||
lastInner = h.MessageCounter
|
||||
plain, err := receiver.hostinfo.ConnectionState.Decrypt(receiver.f.l, h.MessageCounter, pkt, make([]byte, 12))
|
||||
require.NoError(t, err)
|
||||
if len(plain) == 41 {
|
||||
tiny = append(tiny, plain[40])
|
||||
} else {
|
||||
got = append(got, decodeSeg(plain[40:]))
|
||||
}
|
||||
}
|
||||
require.Equal(t, want, got)
|
||||
require.Equal(t, payload, tiny)
|
||||
require.Zero(t, sender.hostinfo.ConnectionState.txBudget.state.Load())
|
||||
require.Zero(t, relayHI.ConnectionState.txBudget.state.Load())
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// addTestRelay makes sender reach its peer only through a relay tunnel with replay windows of window. It returns the
|
||||
// relay's underlay address, its hostinfo and the relay's side of the tunnel.
|
||||
func addTestRelay(t testing.TB, sender *flowTestPeer, window uint64) (netip.AddrPort, *HostInfo, *ConnectionState) {
|
||||
relayInit, relayResp := runTestHandshake(t)
|
||||
relayCI, err := newConnectionStateFromResult(relayInit)
|
||||
require.NoError(t, err)
|
||||
relayPeer, err := newConnectionStateFromResult(relayResp)
|
||||
require.NoError(t, err)
|
||||
relayCI.window, relayPeer.window = NewBits(window), NewBits(window)
|
||||
|
||||
relayAddr := netip.MustParseAddr("10.0.0.3")
|
||||
relayRemote := netip.MustParseAddrPort("192.0.2.3:4242")
|
||||
relay := &Relay{Type: TerminalType, State: Established, LocalIndex: 5, RemoteIndex: 6, PeerAddr: flowTestRemote}
|
||||
relayHI := &HostInfo{
|
||||
vpnAddrs: []netip.Addr{relayAddr},
|
||||
ConnectionState: relayCI,
|
||||
relayState: RelayState{
|
||||
relayForByAddr: map[netip.Addr]*Relay{flowTestRemote: relay},
|
||||
relayForByIdx: map[uint32]*Relay{relay.LocalIndex: relay},
|
||||
},
|
||||
}
|
||||
relayHI.remote.Store(&relayRemote)
|
||||
sender.f.hostMap.Hosts[relayAddr] = relayHI
|
||||
sender.hostinfo.remote.Store(&netip.AddrPort{})
|
||||
sender.hostinfo.relayState.relays = []netip.Addr{relayAddr}
|
||||
return relayRemote, relayHI, relayPeer
|
||||
}
|
||||
|
||||
// affinityQueue makes every read start with an idle pipeline: before each read it waits until conn has sent what was
|
||||
// read before, recording how many sends that took, then samples the reader's actual thread affinity.
|
||||
type affinityQueue struct {
|
||||
*flowBatchQueue
|
||||
conn *affinityConn
|
||||
sent int
|
||||
boundaries []int
|
||||
masks []unix.CPUSet
|
||||
}
|
||||
|
||||
func (q *affinityQueue) Read() ([]tio.Packet, error) {
|
||||
if n := q.reads.Load(); n > 0 {
|
||||
for _, p := range q.batches[n-1] {
|
||||
q.sent += p.SegmentCount()
|
||||
}
|
||||
}
|
||||
q.boundaries = append(q.boundaries, q.conn.waitFor(q.sent))
|
||||
q.masks = append(q.masks, threadMask())
|
||||
return q.flowBatchQueue.Read()
|
||||
}
|
||||
|
||||
// affinityConn captures every send, sampling the sending thread's actual affinity in each WriteBatch.
|
||||
type affinityConn struct {
|
||||
flowCaptureConn
|
||||
masks []unix.CPUSet
|
||||
sizes []int
|
||||
}
|
||||
|
||||
func (c *affinityConn) WriteBatch(p [][]byte, addrs []netip.AddrPort) (int, error) {
|
||||
mask := threadMask()
|
||||
c.mu.Lock()
|
||||
c.masks = append(c.masks, mask)
|
||||
c.sizes = append(c.sizes, len(p))
|
||||
c.mu.Unlock()
|
||||
return c.flowCaptureConn.WriteBatch(p, addrs)
|
||||
}
|
||||
|
||||
// waitFor waits until n packets were sent and returns how many WriteBatch calls that took.
|
||||
func (c *affinityConn) waitFor(n int) int {
|
||||
for len(c.captured()) < n {
|
||||
time.Sleep(50 * time.Microsecond)
|
||||
}
|
||||
c.mu.Lock()
|
||||
defer c.mu.Unlock()
|
||||
return len(c.masks)
|
||||
}
|
||||
|
||||
func threadMask() unix.CPUSet {
|
||||
var mask unix.CPUSet
|
||||
if err := unix.SchedGetaffinity(0, &mask); err != nil {
|
||||
panic(err)
|
||||
}
|
||||
return mask
|
||||
}
|
||||
|
||||
// requireFlowCPU checks every mask is just cpu, or with cpu -1, the whole allowed set.
|
||||
func requireFlowCPU(t *testing.T, masks []unix.CPUSet, cpu int, allowed []int) {
|
||||
t.Helper()
|
||||
require.NotEmpty(t, masks)
|
||||
for _, mask := range masks {
|
||||
if cpu >= 0 {
|
||||
require.Equal(t, 1, mask.Count())
|
||||
require.True(t, mask.IsSet(cpu), "expected CPU %d", cpu)
|
||||
continue
|
||||
}
|
||||
require.Equal(t, len(allowed), mask.Count())
|
||||
for _, c := range allowed {
|
||||
require.True(t, mask.IsSet(c))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestFlowStagedTXAffinity sends large, small and large reads, each from an idle pipeline, and checks the order on the
|
||||
// wire and where the reader and each send actually ran, for every CPU placement, with one routine and with several. A
|
||||
// staged sender is only pinned to an explicit entry other than its reader's CPU, and inline sends stay on the reader.
|
||||
// With the threshold, only the small read goes inline.
|
||||
// The reader only reads again once its earlier reads are on the wire, so this also checks the sender never waits for
|
||||
// the reader. Pinning threads changes the process, so the test runs in a child.
|
||||
func TestFlowStagedTXAffinity(t *testing.T) {
|
||||
if os.Getenv("NEBULA_FLOW_AFFINITY_TEST") != "1" {
|
||||
cmd := exec.Command(os.Args[0], "-test.run=^TestFlowStagedTXAffinity$")
|
||||
cmd.Env = append(os.Environ(), "NEBULA_FLOW_AFFINITY_TEST=1")
|
||||
out, err := cmd.CombinedOutput()
|
||||
require.NoError(t, err, "%s", out)
|
||||
return
|
||||
}
|
||||
allowed, err := util.AllowedCPUs()
|
||||
require.NoError(t, err)
|
||||
for _, placement := range []string{"fallback", "automatic", "explicit", "explicit-single"} {
|
||||
for _, pin := range []bool{false, true} {
|
||||
for _, sc := range sendPaths() {
|
||||
for _, routines := range []int{1, 2} {
|
||||
t.Run(fmt.Sprintf("%s/pin=%t/%s/routines=%d", placement, pin, stagedName(sc), routines), func(t *testing.T) {
|
||||
if pin && len(allowed) < 2 {
|
||||
t.Skip("requires at least two allowed CPUs")
|
||||
}
|
||||
if sc.inlineBelow > 0 {
|
||||
// Switch on every read that wants the other mode, so the small read goes inline between
|
||||
// staged ones
|
||||
sc.gateHold = 1
|
||||
}
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, sc)
|
||||
f := sender.f
|
||||
f.pinThreads, f.routines = pin, routines
|
||||
switch placement {
|
||||
case "automatic":
|
||||
f.defaultCpuAffinity = cpupick.Default(routines, 4242, nil)
|
||||
case "explicit":
|
||||
f.cpuAffinity = []int{allowed[len(allowed)-1], allowed[0]}
|
||||
case "explicit-single":
|
||||
f.cpuAffinity = allowed[len(allowed)-1:]
|
||||
}
|
||||
readerCPU, sendCPU := -1, -1
|
||||
if pin {
|
||||
readerCPU = f.threadCPU(0)
|
||||
sendCPU = readerCPU
|
||||
if sc.tx {
|
||||
// Never the reader's CPU, and no automatic choice: unpinned unless an explicit entry fits
|
||||
sendCPU = -1
|
||||
if placement == "explicit" {
|
||||
sendCPU = f.cpuAffinity[1]
|
||||
}
|
||||
}
|
||||
}
|
||||
smallCPU := sendCPU
|
||||
if sc.inlineBelow > 0 {
|
||||
smallCPU = readerCPU
|
||||
}
|
||||
conn := &affinityConn{}
|
||||
f.writers = []udp.Conn{conn}
|
||||
batches, want := flowTestBatches(3, 8, 1, 45)
|
||||
batches[1] = batches[1][:1]
|
||||
want = append(want[:405], want[720:]...)
|
||||
q := &affinityQueue{flowBatchQueue: newFlowBatchQueue(batches), conn: conn}
|
||||
inline := metrics.GetOrRegisterCounter("flow.tx.inline", nil)
|
||||
inline0 := inline.Count()
|
||||
f.listenIn(q, 0)
|
||||
require.Equal(t, want, decryptWire(t, receiver, conn.captured()))
|
||||
if sc.inlineBelow > 0 {
|
||||
require.Equal(t, int64(1), inline.Count()-inline0)
|
||||
}
|
||||
b := q.boundaries
|
||||
requireFlowCPU(t, q.masks, readerCPU, allowed)
|
||||
requireFlowCPU(t, conn.masks[:b[1]], sendCPU, allowed)
|
||||
requireFlowCPU(t, conn.masks[b[1]:b[2]], smallCPU, allowed)
|
||||
requireFlowCPU(t, conn.masks[b[2]:], sendCPU, allowed)
|
||||
})
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// sendPaths is inline, staged and, with the threshold, adaptive transmit.
|
||||
func sendPaths() []stagedConfig {
|
||||
return []stagedConfig{{}, stagedOn(2), adaptive(2)}
|
||||
}
|
||||
|
||||
// requireAccepted checks the receiver accepts every packet of wire in the order given. With several readers the wire
|
||||
// order differs from counter order, but every packet must still authenticate and fit within the replay window.
|
||||
func requireAccepted(t *testing.T, receiver *flowTestPeer, wire [][]byte) {
|
||||
t.Helper()
|
||||
for _, pkt := range wire {
|
||||
h := &header.H{}
|
||||
require.NoError(t, h.Parse(pkt))
|
||||
_, err := receiver.hostinfo.ConnectionState.Decrypt(receiver.f.l, h.MessageCounter, pkt, make([]byte, 12))
|
||||
require.NoError(t, err, "counter %d", h.MessageCounter)
|
||||
}
|
||||
}
|
||||
|
||||
// slowConn delays every WriteBatch, then writes to the shared capture.
|
||||
type slowConn struct {
|
||||
*flowCaptureConn
|
||||
delay time.Duration
|
||||
}
|
||||
|
||||
func (c slowConn) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error) {
|
||||
time.Sleep(c.delay)
|
||||
return c.flowCaptureConn.WriteBatch(bufs, addrs)
|
||||
}
|
||||
|
||||
// TestFlowTXBudgetManyReaders saturates one tunnel from eight readers, one of them on a slow socket that lets the
|
||||
// others overtake it, alongside a burst of unreserved control messages: in the order they reach the wire, every packet
|
||||
// is accepted by the receiver's replay window, so none was sent twice or displaced past the window.
|
||||
func TestFlowTXBudgetManyReaders(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
for _, window := range budgetWindows {
|
||||
t.Run(fmt.Sprintf("window=%d", window), func(t *testing.T) {
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, stagedOn(3))
|
||||
ci := sender.hostinfo.ConnectionState
|
||||
ci.window = NewBits(window)
|
||||
receiver.hostinfo.ConnectionState.window = NewBits(window)
|
||||
sender.f.routines = 8
|
||||
sender.f.writers = append([]udp.Conn{slowConn{sender.conn, 4 * time.Millisecond}}, slices.Repeat(sender.f.writers, 8)...)
|
||||
start := ci.messageCounter.Load()
|
||||
var wg sync.WaitGroup
|
||||
for q := range 8 {
|
||||
wg.Go(func() {
|
||||
batches, _ := flowTestBatches(28, 8, 2, 45)
|
||||
p := newStagedTx(sender.f, newFlowBatchQueue(nil), q)
|
||||
defer p.close()
|
||||
for _, packets := range batches {
|
||||
p.send(packets)
|
||||
}
|
||||
})
|
||||
}
|
||||
// A bounded burst of unreserved control messages uses the documented margin, on writer 8
|
||||
wg.Go(func() {
|
||||
for range 128 {
|
||||
sender.f.sendNoMetrics(header.Test, header.TestRequest, ci, sender.hostinfo, flowTestUnder, []byte("x"), make([]byte, 12), make([]byte, mtu), 8)
|
||||
time.Sleep(100 * time.Microsecond)
|
||||
}
|
||||
})
|
||||
wg.Wait()
|
||||
require.Zero(t, ci.txBudget.state.Load())
|
||||
wire := sender.conn.captured()
|
||||
require.Len(t, wire, 8*28*360+128)
|
||||
require.Equal(t, start+uint64(len(wire)), ci.messageCounter.Load())
|
||||
requireAccepted(t, receiver, wire)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestFlowStagedTXInlineOnlyWhenEmpty: a small read behind a staged batch still in flight must not go inline before
|
||||
// that batch is on the wire, it would overtake it.
|
||||
func TestFlowStagedTXInlineOnlyWhenEmpty(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
sc := adaptive(2)
|
||||
sc.inlineBelow, sc.gateHold = 4, 1
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, sc)
|
||||
p := newStagedTx(sender.f, newFlowBatchQueue(nil), 0)
|
||||
block := make(chan struct{})
|
||||
delayCrypto(sender, func(uint64) { <-block })
|
||||
batches, want := flowTestBatches(1, 4, 1, 3)
|
||||
p.send(batches[0][:3]) // switches to fanout, its worker is blocked
|
||||
require.Equal(t, 1, p.inFlight)
|
||||
unblock := time.AfterFunc(20*time.Millisecond, func() { close(block) })
|
||||
defer unblock.Stop()
|
||||
p.send(batches[0][3:]) // switches to inline, which waits for the staged batch first
|
||||
require.Zero(t, p.inFlight)
|
||||
p.close()
|
||||
require.Equal(t, want, decryptWire(t, receiver, sender.conn.captured()))
|
||||
}
|
||||
|
||||
// TestFlowStagedTXInlineBelowZero: with inline_below 0 an idle reader never sends a batch itself, in either
|
||||
// direction: every read goes through the workers and the ordered sender or writer.
|
||||
func TestFlowStagedTXInlineBelowZero(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
c.Settings = map[string]any{"tun": map[string]any{"staged": map[string]any{"workers": 2, "inline_below": 0}}}
|
||||
sc := parseStagedConfig(c, l)
|
||||
if !sc.tx {
|
||||
t.Skip("transmit stays inline in this build")
|
||||
}
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, sc)
|
||||
batches, want := flowTestBatches(20, 2, 1, 4)
|
||||
txInline := metrics.GetOrRegisterCounter("flow.tx.inline", nil)
|
||||
tx := metrics.GetOrRegisterCounter("flow.tx.batches", nil)
|
||||
rxInline := metrics.GetOrRegisterCounter("flow.rx.inline", nil)
|
||||
txInline0, tx0, rxInline0, rx0 := txInline.Count(), tx.Count(), rxInline.Count(), rxBatches.Count()
|
||||
sender.f.listenIn(newFlowBatchQueue(batches), 0)
|
||||
wire := sender.conn.captured()
|
||||
require.Equal(t, want, decryptWire(t, receiver, wire))
|
||||
require.Zero(t, txInline.Count()-txInline0)
|
||||
require.Equal(t, int64(len(batches)), tx.Count()-tx0)
|
||||
receiver.receive(&rxConn{wire: wire, sizes: []int{1, 2, 4}})
|
||||
require.Equal(t, want, receiver.tun.segments(t))
|
||||
require.Zero(t, rxInline.Count()-rxInline0)
|
||||
require.Positive(t, rxBatches.Count()-rx0)
|
||||
}
|
||||
|
||||
// TestFlowStagedTXDisabled: with tx false the reader never builds a staged pipeline, even on a queue that could hand
|
||||
// off its batches. Receive stays staged.
|
||||
func TestFlowStagedTXDisabled(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
c.Settings = map[string]any{"tun": map[string]any{"staged": map[string]any{"workers": 2, "tx": false}}}
|
||||
sc := parseStagedConfig(c, l)
|
||||
require.False(t, sc.tx)
|
||||
require.True(t, sc.rx)
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, sc)
|
||||
batches, want := flowTestBatches(4, 8, 1, 45)
|
||||
tx := metrics.GetOrRegisterCounter("flow.tx.batches", nil)
|
||||
txInline := metrics.GetOrRegisterCounter("flow.tx.inline", nil)
|
||||
tx0, txInline0, rx0 := tx.Count(), txInline.Count(), rxBatches.Count()
|
||||
q := &swapCountQueue{flowBatchQueue: newFlowBatchQueue(batches)}
|
||||
sender.f.listenIn(q, 0)
|
||||
wire := sender.conn.captured()
|
||||
require.Equal(t, want, decryptWire(t, receiver, wire))
|
||||
require.Zero(t, q.swaps, "newStagedTx always takes the queue's buffer, so it never ran")
|
||||
require.Equal(t, tx0, tx.Count())
|
||||
require.Equal(t, txInline0, txInline.Count())
|
||||
receiver.receive(&rxConn{wire: wire, batchLen: 512})
|
||||
require.Equal(t, want, receiver.tun.segments(t))
|
||||
require.Greater(t, rxBatches.Count(), rx0)
|
||||
}
|
||||
|
||||
// swapCountQueue counts SwapRxBuf calls.
|
||||
type swapCountQueue struct {
|
||||
*flowBatchQueue
|
||||
swaps int
|
||||
}
|
||||
|
||||
func (q *swapCountQueue) SwapRxBuf(buf []byte) []byte {
|
||||
q.swaps++
|
||||
return q.flowBatchQueue.SwapRxBuf(buf)
|
||||
}
|
||||
|
||||
// TestFlowStagedTXAdaptiveBudget: a fast reader's adaptive sends must stop spending credit until another reader's
|
||||
// earlier reservation reaches the wire.
|
||||
func TestFlowStagedTXAdaptiveBudget(t *testing.T) {
|
||||
for _, shape := range []struct {
|
||||
name string
|
||||
packets, segments int
|
||||
}{
|
||||
{"single", 1, 1}, {"batch", 8, 30},
|
||||
} {
|
||||
t.Run(shape.name, func(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
sc := adaptive(2)
|
||||
// p0's large read must go to the workers at once, p1 stays inline
|
||||
sc.gateHold = 1
|
||||
sender, receiver := newFlowTestPair(t, noise.CipherChaChaPoly, sc)
|
||||
sender.f.routines = 2
|
||||
sender.f.writers = []udp.Conn{sender.conn, sender.conn}
|
||||
ci := sender.hostinfo.ConnectionState
|
||||
start := ci.messageCounter.Load()
|
||||
entered, unblock := make(chan struct{}), make(chan struct{})
|
||||
delayCrypto(sender, func(n uint64) {
|
||||
if n == start+1 {
|
||||
close(entered)
|
||||
<-unblock
|
||||
}
|
||||
})
|
||||
p0 := newStagedTx(sender.f, newFlowBatchQueue(nil), 0)
|
||||
p1 := newStagedTx(sender.f, newFlowBatchQueue(nil), 1)
|
||||
defer p0.close()
|
||||
defer p1.close()
|
||||
var release sync.Once
|
||||
defer release.Do(func() { close(unblock) })
|
||||
large, _ := flowTestBatches(1, 8, 1, 45)
|
||||
p0.send(large[0])
|
||||
<-entered
|
||||
perBatch := shape.packets * shape.segments
|
||||
small, _ := flowTestBatches(9600/perBatch, shape.packets, 1, shape.segments)
|
||||
fits := int(ci.txBudgetLimit()-360) / perBatch
|
||||
for _, packets := range small[:fits] {
|
||||
p1.send(packets)
|
||||
}
|
||||
require.Equal(t, uint64(360+fits*perBatch), (ci.txBudget.state.Load()>>24)&txBudgetMask, "inline sends must spend shared credit")
|
||||
done := make(chan struct{})
|
||||
go func() {
|
||||
defer close(done)
|
||||
for _, packets := range small[fits:] {
|
||||
p1.send(packets)
|
||||
}
|
||||
}()
|
||||
select {
|
||||
case <-done:
|
||||
t.Error("adaptive reader bypassed outstanding credit")
|
||||
case <-time.After(50 * time.Millisecond):
|
||||
}
|
||||
require.LessOrEqual(t, ci.messageCounter.Load()-start, ci.txBudgetLimit())
|
||||
release.Do(func() { close(unblock) })
|
||||
<-done
|
||||
p0.drain()
|
||||
p1.drain()
|
||||
wire := sender.conn.captured()
|
||||
require.Len(t, wire, 360+40*240)
|
||||
requireAccepted(t, receiver, wire)
|
||||
require.Zero(t, ci.txBudget.state.Load())
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// BenchmarkFlowStagedTX runs reads of eight 45-segment superpackets through listenIn into a socket that discards
|
||||
// them, inline and staged.
|
||||
func BenchmarkFlowStagedTX(b *testing.B) {
|
||||
for _, cipher := range []noise.CipherFunc{noiseutil.CipherAESGCM, noise.CipherChaChaPoly} {
|
||||
for _, sc := range []stagedConfig{{}, stagedOn(4)} {
|
||||
b.Run(cipher.CipherName()+"/"+stagedName(sc), func(b *testing.B) {
|
||||
if sc.tx && cipher.CipherName() == noiseutil.CipherAESGCM.CipherName() && noiseutil.EncryptLockNeeded {
|
||||
b.Skip("AES-GCM requires encryption in nonce order")
|
||||
}
|
||||
sender, _ := newFlowTestPair(b, cipher, sc)
|
||||
sender.f.writers = []udp.Conn{udp.NoopConn{}}
|
||||
batch, _ := flowTestBatches(1, 8, 4, 45)
|
||||
batches := make([][]tio.Packet, b.N)
|
||||
for i := range batches {
|
||||
batches[i] = batch[0]
|
||||
}
|
||||
b.SetBytes(int64(8 * 45 * flowTestMSS))
|
||||
b.ReportAllocs()
|
||||
b.ResetTimer()
|
||||
sender.f.listenIn(newFlowBatchQueue(batches), 0)
|
||||
})
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -7,6 +7,7 @@ require (
|
||||
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
|
||||
|
||||
@@ -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=
|
||||
|
||||
+23
-35
@@ -61,17 +61,16 @@ type HandshakeManager struct {
|
||||
vpnIps map[netip.Addr]*HandshakeHostInfo
|
||||
indexes map[uint32]*HandshakeHostInfo
|
||||
|
||||
mainHostMap *HostMap
|
||||
lightHouse *LightHouse
|
||||
outside udp.Conn
|
||||
config HandshakeConfig
|
||||
OutboundHandshakeTimer *LockingTimerWheel[netip.Addr]
|
||||
messageMetrics *MessageMetrics
|
||||
metricInitiated metrics.Counter
|
||||
metricTimedOut metrics.Counter
|
||||
metricRejectedBlocklisted metrics.Counter
|
||||
f *Interface
|
||||
l *slog.Logger
|
||||
mainHostMap *HostMap
|
||||
lightHouse *LightHouse
|
||||
outside udp.Conn
|
||||
config HandshakeConfig
|
||||
OutboundHandshakeTimer *LockingTimerWheel[netip.Addr]
|
||||
messageMetrics *MessageMetrics
|
||||
metricInitiated metrics.Counter
|
||||
metricTimedOut metrics.Counter
|
||||
f *Interface
|
||||
l *slog.Logger
|
||||
|
||||
// can be used to trigger outbound handshake for the given vpnIp
|
||||
trigger chan netip.Addr
|
||||
@@ -119,19 +118,18 @@ func (hh *HandshakeHostInfo) cachePacket(l *slog.Logger, t header.MessageType, s
|
||||
|
||||
func NewHandshakeManager(l *slog.Logger, mainHostMap *HostMap, lightHouse *LightHouse, outside udp.Conn, config HandshakeConfig) *HandshakeManager {
|
||||
return &HandshakeManager{
|
||||
vpnIps: map[netip.Addr]*HandshakeHostInfo{},
|
||||
indexes: map[uint32]*HandshakeHostInfo{},
|
||||
mainHostMap: mainHostMap,
|
||||
lightHouse: lightHouse,
|
||||
outside: outside,
|
||||
config: config,
|
||||
trigger: make(chan netip.Addr, config.triggerBuffer),
|
||||
OutboundHandshakeTimer: NewLockingTimerWheel[netip.Addr](config.tryInterval, hsTimeout(config.retries, config.tryInterval)),
|
||||
messageMetrics: config.messageMetrics,
|
||||
metricInitiated: metrics.GetOrRegisterCounter("handshake_manager.initiated", nil),
|
||||
metricTimedOut: metrics.GetOrRegisterCounter("handshake_manager.timed_out", nil),
|
||||
metricRejectedBlocklisted: metrics.GetOrRegisterCounter("handshake_manager.rejected.blocklisted", nil),
|
||||
l: l,
|
||||
vpnIps: map[netip.Addr]*HandshakeHostInfo{},
|
||||
indexes: map[uint32]*HandshakeHostInfo{},
|
||||
mainHostMap: mainHostMap,
|
||||
lightHouse: lightHouse,
|
||||
outside: outside,
|
||||
config: config,
|
||||
trigger: make(chan netip.Addr, config.triggerBuffer),
|
||||
OutboundHandshakeTimer: NewLockingTimerWheel[netip.Addr](config.tryInterval, hsTimeout(config.retries, config.tryInterval)),
|
||||
messageMetrics: config.messageMetrics,
|
||||
metricInitiated: metrics.GetOrRegisterCounter("handshake_manager.initiated", nil),
|
||||
metricTimedOut: metrics.GetOrRegisterCounter("handshake_manager.timed_out", nil),
|
||||
l: l,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -405,8 +403,6 @@ func (hm *HandshakeManager) StartHandshake(vpnAddr netip.Addr, cacheCb func(*Han
|
||||
|
||||
hm.Unlock()
|
||||
hm.lightHouse.QueryServer(vpnAddr)
|
||||
// If this host came from a static_map hostname its addresses may have moved, retries will pick up anything new
|
||||
hostinfo.remotes.ResolveHostnames()
|
||||
return hostinfo
|
||||
}
|
||||
|
||||
@@ -721,12 +717,7 @@ func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *head
|
||||
|
||||
response, result, err := machine.ProcessPacket(nil, packet)
|
||||
if err != nil {
|
||||
level := slog.LevelError
|
||||
if errors.Is(err, cert.ErrBlockListed) {
|
||||
level = slog.LevelDebug
|
||||
hm.metricRejectedBlocklisted.Inc(1)
|
||||
}
|
||||
f.l.Log(context.Background(), level, "Failed to process handshake packet", "from", via, "error", err)
|
||||
f.l.Error("Failed to process handshake packet", "from", via, "error", err)
|
||||
return
|
||||
}
|
||||
|
||||
@@ -858,9 +849,6 @@ func (hm *HandshakeManager) continueHandshake(via ViaSender, hh *HandshakeHostIn
|
||||
|
||||
response, result, err := machine.ProcessPacket(nil, packet)
|
||||
if err != nil {
|
||||
if errors.Is(err, cert.ErrBlockListed) {
|
||||
hm.metricRejectedBlocklisted.Inc(1)
|
||||
}
|
||||
// Recoverable errors are routine noise, log at Debug. Fatal errors get a Warn.
|
||||
if machine.Failed() {
|
||||
f.l.Warn("Failed to process handshake packet, abandoning",
|
||||
|
||||
@@ -1,17 +1,12 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/flynn/noise"
|
||||
"github.com/gaissmai/bart"
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
ct "github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/handshake"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
@@ -240,89 +235,6 @@ func TestHandleIncomingDispatch(t *testing.T) {
|
||||
})
|
||||
}
|
||||
|
||||
func TestBlocklistedHandshakeLogLevelAndCounter(t *testing.T) {
|
||||
ca, _, caKey, _ := ct.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
|
||||
pool := ct.NewTestCAPool(ca)
|
||||
|
||||
newCredential := func(name, network string) (cert.Certificate, *handshake.Credential) {
|
||||
c, _, rawKey, _ := ct.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey,
|
||||
name, ca.NotBefore(), ca.NotAfter(), []netip.Prefix{netip.MustParsePrefix(network)}, nil, nil)
|
||||
privateKey, _, _, err := cert.UnmarshalPrivateKeyFromPEM(rawKey)
|
||||
require.NoError(t, err)
|
||||
certBytes, err := c.MarshalForHandshakes()
|
||||
require.NoError(t, err)
|
||||
cipherSuite := noise.NewCipherSuite(noise.DH25519, noise.CipherChaChaPoly, noise.HashSHA256)
|
||||
return c, handshake.NewCredential(c, certBytes, privateKey, cipherSuite)
|
||||
}
|
||||
|
||||
initiatorCert, initiatorCredential := newCredential("initiator", "10.0.0.1/24")
|
||||
responderCert, responderCredential := newCredential("responder", "10.0.0.2/24")
|
||||
fingerprint, err := initiatorCert.Fingerprint()
|
||||
require.NoError(t, err)
|
||||
pool.BlocklistFingerprint(fingerprint)
|
||||
|
||||
initiator, err := handshake.NewMachine(cert.Version2,
|
||||
func(cert.Version) *handshake.Credential { return initiatorCredential },
|
||||
func(c cert.Certificate) (*cert.CachedCertificate, error) {
|
||||
return pool.VerifyCertificate(time.Now(), c)
|
||||
},
|
||||
func() (uint32, error) { return 1, nil }, true, header.HandshakeIXPSK0)
|
||||
require.NoError(t, err)
|
||||
packet, err := initiator.Initiate(nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
handler := &capturingHandler{}
|
||||
logger := slog.New(handler)
|
||||
pki := &PKI{}
|
||||
pki.cs.Store(&CertState{initiatingVersion: cert.Version2, v2Credential: responderCredential})
|
||||
pki.caPool.Store(pool)
|
||||
hm := NewHandshakeManager(logger, nil, nil, nil, defaultHandshakeConfig)
|
||||
hm.metricRejectedBlocklisted = metrics.NewCounter()
|
||||
hm.f = &Interface{pki: pki, l: logger}
|
||||
via := ViaSender{UdpAddr: netip.MustParseAddrPort("198.51.100.7:4242")}
|
||||
|
||||
hm.beginHandshake(via, packet, nil)
|
||||
entry := findEntry(t, handler.entries, "Failed to process handshake packet")
|
||||
assert.Equal(t, slog.LevelDebug, entry.Level)
|
||||
require.ErrorIs(t, entry.Attrs["error"].(error), cert.ErrBlockListed)
|
||||
assert.Equal(t, int64(1), hm.metricRejectedBlocklisted.Count())
|
||||
|
||||
handler.entries = nil
|
||||
hm.beginHandshake(via, nil, nil)
|
||||
entry = findEntry(t, handler.entries, "Failed to process handshake packet")
|
||||
assert.Equal(t, slog.LevelError, entry.Level)
|
||||
assert.Equal(t, int64(1), hm.metricRejectedBlocklisted.Count())
|
||||
|
||||
// The initiator sees the same rejection in continueHandshake, after a
|
||||
// responder has accepted its first packet and sent a valid reply.
|
||||
cleanPool := ct.NewTestCAPool(ca)
|
||||
responder, err := handshake.NewMachine(cert.Version2,
|
||||
func(cert.Version) *handshake.Credential { return responderCredential },
|
||||
func(c cert.Certificate) (*cert.CachedCertificate, error) {
|
||||
return cleanPool.VerifyCertificate(time.Now(), c)
|
||||
},
|
||||
func() (uint32, error) { return 2, nil }, false, header.HandshakeIXPSK0)
|
||||
require.NoError(t, err)
|
||||
response, _, err := responder.ProcessPacket(nil, packet)
|
||||
require.NoError(t, err)
|
||||
|
||||
responderFingerprint, err := responderCert.Fingerprint()
|
||||
require.NoError(t, err)
|
||||
pool.BlocklistFingerprint(responderFingerprint)
|
||||
|
||||
initiatingHM := NewHandshakeManager(logger, nil, nil, nil, defaultHandshakeConfig)
|
||||
initiatingHM.metricRejectedBlocklisted = metrics.NewCounter()
|
||||
initiatingHM.f = &Interface{l: logger}
|
||||
hh := &HandshakeHostInfo{
|
||||
machine: initiator,
|
||||
hostinfo: &HostInfo{localIndexId: 1, vpnAddrs: []netip.Addr{netip.MustParseAddr("10.0.0.2")}},
|
||||
}
|
||||
initiatingHM.indexes[1] = hh
|
||||
via.IsRelayed = true // skip the remote allow list before certificate validation
|
||||
initiatingHM.continueHandshake(via, hh, response)
|
||||
assert.Equal(t, int64(1), initiatingHM.metricRejectedBlocklisted.Count())
|
||||
}
|
||||
|
||||
// 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.
|
||||
|
||||
@@ -18,12 +18,20 @@ import (
|
||||
)
|
||||
|
||||
func (f *Interface) consumeInsidePacket(pkt tio.Packet, fwPacket *firewall.ParsedPacket, nb []byte, sendBatch *batch.SendBatch, rejectBuf []byte, q int, localCache firewall.ConntrackCache) {
|
||||
if hostinfo := f.filterInsidePacket(pkt, fwPacket, rejectBuf, q, localCache); hostinfo != nil {
|
||||
f.sendInsideMessage(hostinfo, pkt, nb, sendBatch)
|
||||
}
|
||||
}
|
||||
|
||||
// filterInsidePacket parses and filters pkt, handling local traffic, destination lookup, pending handshakes and
|
||||
// the outbound firewall. It returns the hostinfo to send pkt to, or nil when pkt was dropped, rejected, forwarded
|
||||
// to self or cached for a pending handshake.
|
||||
func (f *Interface) filterInsidePacket(pkt tio.Packet, fwPacket *firewall.ParsedPacket, rejectBuf []byte, q int, localCache firewall.ConntrackCache) *HostInfo {
|
||||
// borrowed: pkt.Bytes is owned by the originating tio.Queue and is
|
||||
// only valid until the next Read on that queue. Every consumer below
|
||||
// (parse, self-forward, handshake cache, sendInsideMessage) reads it
|
||||
// synchronously; do not retain pkt outside this call. If a future
|
||||
// caller needs to keep the packet, use pkt.Clone() to detach it from
|
||||
// the borrow.
|
||||
// only valid until the next Read on that queue. Filtering and sending
|
||||
// must finish before then. Self-forwarding writes synchronously and the
|
||||
// handshake cache copies each segment. To retain the packet beyond the
|
||||
// next Read, use pkt.Clone() to detach it from the borrow.
|
||||
//
|
||||
// pkt.Bytes is either one IP datagram (GSO zero) or a TSO/USO
|
||||
// superpacket. In both cases the L3+L4 headers at the start describe
|
||||
@@ -38,13 +46,13 @@ func (f *Interface) consumeInsidePacket(pkt tio.Packet, fwPacket *firewall.Parse
|
||||
"error", err,
|
||||
)
|
||||
}
|
||||
return
|
||||
return nil
|
||||
}
|
||||
|
||||
// Ignore local broadcast packets
|
||||
if f.dropLocalBroadcast {
|
||||
if f.myBroadcastAddrsTable.Contains(fwPacket.RemoteAddr) {
|
||||
return
|
||||
return nil
|
||||
}
|
||||
}
|
||||
|
||||
@@ -71,12 +79,12 @@ func (f *Interface) consumeInsidePacket(pkt tio.Packet, fwPacket *firewall.Parse
|
||||
}
|
||||
// Otherwise, drop. On linux, we should never see these packets - Linux
|
||||
// routes packets from the nebula addr to the nebula addr through the loopback device.
|
||||
return
|
||||
return nil
|
||||
}
|
||||
|
||||
// Ignore multicast packets
|
||||
if f.dropMulticast && fwPacket.RemoteAddr.IsMulticast() {
|
||||
return
|
||||
return nil
|
||||
}
|
||||
|
||||
hostinfo, ready := f.getOrHandshakeConsiderRouting(&fwPacket.Packet, func(hh *HandshakeHostInfo) {
|
||||
@@ -103,50 +111,26 @@ func (f *Interface) consumeInsidePacket(pkt tio.Packet, fwPacket *firewall.Parse
|
||||
"fwPacket", fwPacket,
|
||||
)
|
||||
}
|
||||
return
|
||||
return nil
|
||||
}
|
||||
|
||||
if !ready {
|
||||
return
|
||||
return nil
|
||||
}
|
||||
|
||||
dropReason := f.firewall.Drop(fwPacket.Packet, false, hostinfo, f.pki.GetCAPool(), localCache)
|
||||
if dropReason == nil {
|
||||
f.sendInsideMessage(hostinfo, pkt, nb, sendBatch)
|
||||
} else {
|
||||
f.rejectInside(packet, rejectBuf, q)
|
||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
hostinfo.logger(f.l).Debug("dropping outbound packet",
|
||||
"fwPacket", fwPacket,
|
||||
"reason", dropReason,
|
||||
)
|
||||
}
|
||||
return hostinfo
|
||||
}
|
||||
}
|
||||
|
||||
func (f *Interface) sendInsideEncrypt(hostinfo *HostInfo, ci *ConnectionState, seg, scratch, nb []byte) []byte {
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
ci.writeLock.Lock()
|
||||
}
|
||||
c := ci.messageCounter.Add(1)
|
||||
|
||||
out := header.Encode(scratch, header.Version, header.Message, 0, hostinfo.remoteIndexId, c)
|
||||
|
||||
out, encErr := ci.eKey.EncryptDanger(out, out, seg, c, nb)
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
ci.writeLock.Unlock()
|
||||
}
|
||||
if encErr != nil {
|
||||
hostinfo.logger(f.l).Error("Failed to encrypt outgoing packet",
|
||||
"error", encErr,
|
||||
"udpAddr", hostinfo.GetRemote(),
|
||||
"counter", c,
|
||||
f.rejectInside(packet, rejectBuf, q)
|
||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
hostinfo.logger(f.l).Debug("dropping outbound packet",
|
||||
"fwPacket", fwPacket,
|
||||
"reason", dropReason,
|
||||
)
|
||||
// Skip this segment; the rest of the superpacket can still go out. TCP will retransmit anything we drop here.
|
||||
return nil
|
||||
}
|
||||
|
||||
return out
|
||||
return nil
|
||||
}
|
||||
|
||||
// sendInsideMessage encrypts a firewall-approved inside packet (or every
|
||||
@@ -156,88 +140,46 @@ func (f *Interface) sendInsideEncrypt(hostinfo *HostInfo, ci *ConnectionState, s
|
||||
// scratch arena: SegmentSuperpacket builds each segment's plaintext in
|
||||
// segScratch[:segLen] in turn, and we encrypt directly into a fresh SendBatch slot.
|
||||
func (f *Interface) sendInsideMessage(hostinfo *HostInfo, pkt tio.Packet, nb []byte, sendBatch *batch.SendBatch) {
|
||||
ci := hostinfo.ConnectionState
|
||||
if ci.eKey == nil {
|
||||
return
|
||||
var it txItem
|
||||
if f.prepareTxItem(&it, hostinfo, pkt) {
|
||||
f.encryptTxItem(&it, nb, sendBatch)
|
||||
}
|
||||
}
|
||||
|
||||
// One traffic-out mark covers every segment of the superpacket; doing it
|
||||
// per segment in sendInsideEncrypt paid an atomic store up to ~45 extra
|
||||
// times per TSO packet, inside writeLock under boring crypto.
|
||||
//
|
||||
// We rebound since this tunnel last sent, ask the lighthouse to get the far side punching at us again
|
||||
// recordOutbound marks traffic out on hostinfo, once per packet or superpacket, and when we rebound since this tunnel
|
||||
// last sent, asks the lighthouse to get the far side punching at us again.
|
||||
func (f *Interface) recordOutbound(hostinfo *HostInfo) {
|
||||
if f.connectionManager.Out(hostinfo) {
|
||||
f.lightHouse.QueryServer(hostinfo.vpnAddrs[0])
|
||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
hostinfo.logger(f.l).Debug("Lighthouse update triggered for punch due to rebind epoch",
|
||||
"vpnAddrs", hostinfo.vpnAddrs,
|
||||
)
|
||||
hostinfo.logger(f.l).Debug("Lighthouse update triggered for punch due to rebind epoch", "vpnAddrs", hostinfo.vpnAddrs)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
remote := hostinfo.GetRemote()
|
||||
if !remote.IsValid() { //the relay path
|
||||
//first, find our relay hostinfo:
|
||||
var relayHostInfo *HostInfo
|
||||
var relay *Relay
|
||||
var err error
|
||||
for _, relayIP := range hostinfo.relayState.CopyRelayIps() {
|
||||
relayHostInfo, relay, err = f.hostMap.QueryVpnAddrsRelayFor(hostinfo.vpnAddrs, relayIP)
|
||||
if err != nil {
|
||||
hostinfo.relayState.DeleteRelay(relayIP)
|
||||
hostinfo.logger(f.l).Info("sendNoMetrics failed to find HostInfo",
|
||||
"relay", relayIP,
|
||||
"error", err,
|
||||
)
|
||||
continue
|
||||
}
|
||||
break
|
||||
// findRelay returns the first relay that can reach hostinfo, forgetting the ones that no longer resolve.
|
||||
func (f *Interface) findRelay(hostinfo *HostInfo) (*HostInfo, *Relay) {
|
||||
for _, relayIP := range hostinfo.relayState.CopyRelayIps() {
|
||||
via, relay, err := f.hostMap.QueryVpnAddrsRelayFor(hostinfo.vpnAddrs, relayIP)
|
||||
if err == nil {
|
||||
return via, relay
|
||||
}
|
||||
if relayHostInfo == nil || relay == nil {
|
||||
//failure already logged
|
||||
return
|
||||
}
|
||||
|
||||
err = tio.SegmentSuperpacket(pkt, func(seg []byte) error {
|
||||
//relay header + header + plaintext + AEAD tag + relay tag
|
||||
scratch := sendBatch.Reserve(len(seg) + header.MaxOverhead)
|
||||
|
||||
innerPacket := f.sendInsideEncrypt(hostinfo, ci, seg, scratch[header.Len:], nb)
|
||||
if innerPacket == nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
//now we need to do a relay-encrypt:
|
||||
toSend, err := f.prepareSendVia(relayHostInfo, relay, innerPacket, nb, scratch, true)
|
||||
if err != nil {
|
||||
//already logged
|
||||
return nil
|
||||
}
|
||||
|
||||
sendBatch.Commit(toSend, relayHostInfo.GetRemote())
|
||||
return nil
|
||||
})
|
||||
if err != nil {
|
||||
hostinfo.logger(f.l).Error("Failed to segment superpacket for relay send", "error", err)
|
||||
}
|
||||
return
|
||||
hostinfo.relayState.DeleteRelay(relayIP)
|
||||
hostinfo.logger(f.l).Info("sendNoMetrics failed to find HostInfo", "relay", relayIP, "error", err)
|
||||
}
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
err := tio.SegmentSuperpacket(pkt, func(seg []byte) error {
|
||||
// header + plaintext + AEAD tag (16 bytes for both AES-GCM and ChaCha20-Poly1305)
|
||||
scratch := sendBatch.Reserve(header.Len + len(seg) + 16)
|
||||
|
||||
out := f.sendInsideEncrypt(hostinfo, ci, seg, scratch, nb)
|
||||
if out == nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
sendBatch.Commit(out, remote)
|
||||
return nil
|
||||
})
|
||||
// encryptMessage encodes the header for counter c and encrypts p behind it into out. The caller allocates c and
|
||||
// holds writeLock when the cipher requires encryption in nonce order.
|
||||
func (f *Interface) encryptMessage(t header.MessageType, st header.MessageSubType, hostinfo *HostInfo, ci *ConnectionState, c uint64, p, nb, out []byte, remote netip.AddrPort) []byte {
|
||||
out = header.Encode(out, header.Version, t, st, hostinfo.remoteIndexId, c)
|
||||
out, err := ci.eKey.EncryptDanger(out, out, p, c, nb)
|
||||
if err != nil {
|
||||
hostinfo.logger(f.l).Error("Failed to segment superpacket for send", "error", err)
|
||||
hostinfo.logger(f.l).Error("Failed to encrypt outgoing packet", "error", err, "udpAddr", remote, "counter", c)
|
||||
return nil
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func (f *Interface) rejectInside(packet []byte, out []byte, q int) {
|
||||
@@ -446,27 +388,33 @@ func (f *Interface) prepareSendVia(via *HostInfo,
|
||||
nb,
|
||||
out []byte,
|
||||
nocopy bool,
|
||||
c uint64,
|
||||
) ([]byte, error) {
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
// A nonzero c was reserved by the caller, who also did the connection manager bookkeeping
|
||||
reserved := c != 0
|
||||
locked := !reserved && noiseutil.EncryptLockNeeded
|
||||
if locked {
|
||||
// NOTE: for goboring AESGCMTLS we need to lock because of the nonce check
|
||||
via.ConnectionState.writeLock.Lock()
|
||||
}
|
||||
c, ok := via.ConnectionState.NextMessageCounter()
|
||||
if !ok {
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
via.ConnectionState.writeLock.Unlock()
|
||||
if !reserved {
|
||||
var ok bool
|
||||
c, ok = via.ConnectionState.NextMessageCounter()
|
||||
if !ok {
|
||||
if locked {
|
||||
via.ConnectionState.writeLock.Unlock()
|
||||
}
|
||||
f.dropExhausted(via, c, "Dropping outbound relay packets, tunnel message counter is exhausted")
|
||||
return nil, fmt.Errorf("tunnel message counter is exhausted")
|
||||
}
|
||||
f.dropExhausted(via, c, "Dropping outbound relay packets, tunnel message counter is exhausted")
|
||||
return nil, fmt.Errorf("tunnel message counter is exhausted")
|
||||
f.connectionManager.OutNoRebind(via)
|
||||
}
|
||||
|
||||
out = header.Encode(out, header.Version, header.Message, header.MessageRelay, relay.RemoteIndex, c)
|
||||
f.connectionManager.OutNoRebind(via)
|
||||
|
||||
// Authenticate the header and payload, but do not encrypt for this message type.
|
||||
// The payload consists of the inner, unencrypted Nebula header, as well as the end-to-end encrypted payload.
|
||||
if len(out)+len(ad)+via.ConnectionState.eKey.Overhead() > cap(out) {
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
if locked {
|
||||
via.ConnectionState.writeLock.Unlock()
|
||||
}
|
||||
via.logger(f.l).Error("SendVia out buffer not large enough for relay",
|
||||
@@ -490,14 +438,16 @@ func (f *Interface) prepareSendVia(via *HostInfo,
|
||||
|
||||
var err error
|
||||
out, err = via.ConnectionState.eKey.EncryptDanger(out, out, nil, c, nb)
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
if locked {
|
||||
via.ConnectionState.writeLock.Unlock()
|
||||
}
|
||||
if err != nil {
|
||||
via.logger(f.l).Info("Failed to EncryptDanger in sendVia", "error", err)
|
||||
return nil, err
|
||||
}
|
||||
f.connectionManager.RelayUsed(relay.LocalIndex)
|
||||
if !reserved {
|
||||
f.connectionManager.RelayUsed(relay.LocalIndex)
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
@@ -510,7 +460,7 @@ func (f *Interface) prepareSendVia(via *HostInfo,
|
||||
// out is a buffer used to store the result of the Encrypt operation
|
||||
// q indicates which writer to use to send the packet.
|
||||
func (f *Interface) SendVia(via *HostInfo, relay *Relay, ad, nb, out []byte, nocopy bool, q int) {
|
||||
toSend, err := f.prepareSendVia(via, relay, ad, nb, out, nocopy)
|
||||
toSend, err := f.prepareSendVia(via, relay, ad, nb, out, nocopy, 0)
|
||||
if err != nil {
|
||||
// already logged by prepareSendVia
|
||||
return
|
||||
@@ -564,34 +514,19 @@ func (f *Interface) sendNoMetrics(t header.MessageType, st header.MessageSubType
|
||||
return
|
||||
}
|
||||
|
||||
//l.WithField("trace", string(debug.Stack())).Error("out Header ", &Header{Version, t, st, 0, hostinfo.remoteIndexId, c}, p)
|
||||
out = header.Encode(out, header.Version, t, st, hostinfo.remoteIndexId, c)
|
||||
// A closing tunnel is torn down right after this, so skip the connection manager entirely: no point recording
|
||||
// traffic or asking the lighthouse for a punch. Otherwise, if we rebound since this tunnel last sent, ask the
|
||||
// lighthouse to get the far side punching at us again.
|
||||
if t != header.CloseTunnel && f.connectionManager.Out(hostinfo) {
|
||||
f.lightHouse.QueryServer(hostinfo.vpnAddrs[0])
|
||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
f.l.Debug("Lighthouse update triggered for punch due to rebind epoch",
|
||||
"vpnAddrs", hostinfo.vpnAddrs,
|
||||
)
|
||||
}
|
||||
// A closing tunnel needs neither traffic tracking nor another punch.
|
||||
if t != header.CloseTunnel {
|
||||
f.recordOutbound(hostinfo)
|
||||
}
|
||||
|
||||
var err error
|
||||
out, err = ci.eKey.EncryptDanger(out, out, p, c, nb)
|
||||
out = f.encryptMessage(t, st, hostinfo, ci, c, p, nb, out, remote)
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
ci.writeLock.Unlock()
|
||||
}
|
||||
if err != nil {
|
||||
hostinfo.logger(f.l).Error("Failed to encrypt outgoing packet",
|
||||
"error", err,
|
||||
"udpAddr", remote,
|
||||
"counter", c,
|
||||
)
|
||||
if out == nil {
|
||||
return
|
||||
}
|
||||
|
||||
var err error
|
||||
if remote.IsValid() {
|
||||
err = f.writers[q].WriteTo(out, remote)
|
||||
if err != nil {
|
||||
@@ -613,19 +548,8 @@ func (f *Interface) sendNoMetrics(t header.MessageType, st header.MessageSubType
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// Try to send via a relay
|
||||
for _, relayIP := range hostinfo.relayState.CopyRelayIps() {
|
||||
relayHostInfo, relay, err := f.hostMap.QueryVpnAddrsRelayFor(hostinfo.vpnAddrs, relayIP)
|
||||
if err != nil {
|
||||
hostinfo.relayState.DeleteRelay(relayIP)
|
||||
hostinfo.logger(f.l).Info("sendNoMetrics failed to find HostInfo",
|
||||
"relay", relayIP,
|
||||
"error", err,
|
||||
)
|
||||
continue
|
||||
}
|
||||
f.SendVia(relayHostInfo, relay, out, nb, fullOut[:header.Len+len(out)], true, q)
|
||||
break
|
||||
if via, relay := f.findRelay(hostinfo); via != nil && relay != nil {
|
||||
f.SendVia(via, relay, out, nb, fullOut[:header.Len+len(out)], true, q)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,180 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/gaissmai/bart"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/firewall"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/overlay/batch"
|
||||
"github.com/slackhq/nebula/overlay/overlaytest"
|
||||
"github.com/slackhq/nebula/overlay/tio"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
func newInsideFilterTestInterface(t *testing.T, allow bool) (*Interface, *HostInfo, *capturingTun) {
|
||||
t.Helper()
|
||||
local := netip.MustParseAddr("192.0.2.1")
|
||||
remote := netip.MustParseAddr("192.0.2.2")
|
||||
f, tun := newSelfForwardInterface(local)
|
||||
f.inside = overlaytest.NoopTun{}
|
||||
f.myVpnNetworksTable = &bart.Lite{}
|
||||
f.myVpnNetworksTable.Insert(netip.MustParsePrefix("192.0.2.0/24"))
|
||||
f.myBroadcastAddrsTable.Insert(netip.MustParsePrefix("192.0.2.255/32"))
|
||||
f.dropLocalBroadcast, f.dropMulticast = true, true
|
||||
localCert := &dummyCert{version: cert.Version1, networks: []netip.Prefix{netip.PrefixFrom(local, 24)}}
|
||||
peerCert := &dummyCert{version: cert.Version1, networks: []netip.Prefix{netip.PrefixFrom(remote, 24)}}
|
||||
f.firewall = NewFirewall(f.l, time.Minute, time.Minute, time.Minute, localCert)
|
||||
if allow {
|
||||
require.NoError(t, f.firewall.AddRule(false, firewall.ProtoAny, 0, 0, []string{"any"}, "", "", "", "", ""))
|
||||
}
|
||||
f.pki = &PKI{}
|
||||
f.pki.caPool.Store(cert.NewCAPool())
|
||||
f.hostMap = newHostMap(f.l)
|
||||
f.lightHouse = newTestLighthouse()
|
||||
f.lightHouse.amLighthouse = true // Keep destination lookup from probing other remotes.
|
||||
f.handshakeManager = NewHandshakeManager(f.l, f.hostMap, f.lightHouse, udp.NoopConn{}, defaultHandshakeConfig)
|
||||
f.handshakeManager.f = f
|
||||
f.connectionManager = &connectionManager{intf: f}
|
||||
h := &HostInfo{
|
||||
vpnAddrs: []netip.Addr{remote},
|
||||
ConnectionState: &ConnectionState{
|
||||
peerCert: &cert.CachedCertificate{Certificate: peerCert},
|
||||
},
|
||||
}
|
||||
f.hostMap.Hosts[remote] = h
|
||||
return f, h, tun
|
||||
}
|
||||
|
||||
func TestFilterInsidePacket(t *testing.T) {
|
||||
local := netip.MustParseAddr("192.0.2.1")
|
||||
remote := netip.MustParseAddr("192.0.2.2")
|
||||
for _, tt := range []struct {
|
||||
name string
|
||||
packet []byte
|
||||
allow bool
|
||||
reject bool
|
||||
ready bool
|
||||
writes int
|
||||
}{
|
||||
{name: "allowed", packet: buildIPv4(local, remote, tcpSyn), allow: true, ready: true},
|
||||
{name: "malformed", packet: []byte{0x45}, allow: true},
|
||||
{name: "broadcast", packet: buildIPv4(local, netip.MustParseAddr("192.0.2.255"), udpDatagram), allow: true},
|
||||
{name: "multicast", packet: buildIPv4(local, netip.MustParseAddr("224.0.0.1"), udpDatagram), allow: true},
|
||||
{name: "firewall drop", packet: buildIPv4(local, remote, tcpSyn)},
|
||||
{name: "firewall reject", packet: buildIPv4(local, remote, tcpSyn), reject: true, writes: 1},
|
||||
{name: "unroutable drop", packet: buildIPv4(local, netip.MustParseAddr("198.51.100.1"), tcpSyn), allow: true},
|
||||
{name: "unroutable reject", packet: buildIPv4(local, netip.MustParseAddr("198.51.100.1"), tcpSyn), allow: true, reject: true, writes: 1},
|
||||
} {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
f, h, tun := newInsideFilterTestInterface(t, tt.allow)
|
||||
f.firewall.OutboundSendReject = tt.reject
|
||||
fp := &firewall.ParsedPacket{}
|
||||
got := f.filterInsidePacket(tio.Packet{Bytes: tt.packet}, fp, make([]byte, mtu), 0, nil)
|
||||
if tt.ready {
|
||||
require.Same(t, h, got)
|
||||
assert.Equal(t, local, fp.LocalAddr)
|
||||
assert.Equal(t, remote, fp.RemoteAddr)
|
||||
} else {
|
||||
require.Nil(t, got)
|
||||
}
|
||||
assert.Zero(t, h.ConnectionState.messageCounter.Load(), "filtering must not allocate encryption counters")
|
||||
assert.False(t, h.sentSinceCheck(), "filtering must not mark outbound traffic")
|
||||
require.Len(t, tun.writes, tt.writes)
|
||||
if tt.writes > 0 {
|
||||
require.GreaterOrEqual(t, len(tun.writes[0]), 40)
|
||||
assert.Equal(t, tt.packet[16:20], tun.writes[0][12:16])
|
||||
assert.Equal(t, tt.packet[12:16], tun.writes[0][16:20])
|
||||
assert.NotZero(t, tun.writes[0][33]&0x04, "reject must carry a TCP reset")
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestFilterInsidePacketSelf(t *testing.T) {
|
||||
local := netip.MustParseAddr("192.0.2.1")
|
||||
f, _, tun := newInsideFilterTestInterface(t, true)
|
||||
pkt := buildIPv4(local, local, tcpSyn)
|
||||
require.Nil(t, f.filterInsidePacket(tio.Packet{Bytes: pkt}, &firewall.ParsedPacket{}, nil, 0, nil))
|
||||
if immediatelyForwardToSelf {
|
||||
require.Len(t, tun.writes, 1)
|
||||
assert.Equal(t, pkt, tun.writes[0])
|
||||
} else {
|
||||
assert.Empty(t, tun.writes)
|
||||
}
|
||||
}
|
||||
|
||||
func TestFilterInsidePacketPendingHandshake(t *testing.T) {
|
||||
f, h, tun := newInsideFilterTestInterface(t, true)
|
||||
remote := h.vpnAddrs[0]
|
||||
delete(f.hostMap.Hosts, remote)
|
||||
hh := &HandshakeHostInfo{hostinfo: h}
|
||||
f.handshakeManager.vpnIps[remote] = hh
|
||||
pkt := buildIPv4(netip.MustParseAddr("192.0.2.1"), remote, udpDatagram)
|
||||
want := append([]byte(nil), pkt...)
|
||||
require.Nil(t, f.filterInsidePacket(tio.Packet{Bytes: pkt}, &firewall.ParsedPacket{}, nil, 0, nil))
|
||||
require.Len(t, hh.packetStore, 1)
|
||||
clear(pkt)
|
||||
assert.Equal(t, want, hh.packetStore[0].packet, "the handshake cache must own its packet")
|
||||
assert.Equal(t, header.Message, hh.packetStore[0].messageType)
|
||||
assert.Empty(t, tun.writes)
|
||||
assert.Zero(t, h.ConnectionState.messageCounter.Load())
|
||||
}
|
||||
|
||||
type insideFilterConn struct {
|
||||
udp.NoopConn
|
||||
packets [][]byte
|
||||
}
|
||||
|
||||
func (c *insideFilterConn) WriteBatch(bufs [][]byte, _ []netip.AddrPort) (int, error) {
|
||||
for _, b := range bufs {
|
||||
c.packets = append(c.packets, append([]byte(nil), b...))
|
||||
}
|
||||
return len(bufs), nil
|
||||
}
|
||||
|
||||
func TestConsumeInsidePacketFilterAndSend(t *testing.T) {
|
||||
for _, allow := range []bool{false, true} {
|
||||
t.Run(map[bool]string{false: "denied", true: "allowed"}[allow], func(t *testing.T) {
|
||||
f, h, _ := newInsideFilterTestInterface(t, allow)
|
||||
initR, respR := runTestHandshake(t)
|
||||
ci, err := newConnectionStateFromResult(initR)
|
||||
require.NoError(t, err)
|
||||
rci, err := newConnectionStateFromResult(respR)
|
||||
require.NoError(t, err)
|
||||
ci.peerCert = h.ConnectionState.peerCert
|
||||
h.ConnectionState = ci
|
||||
h.remoteIndexId = 100
|
||||
remote := netip.MustParseAddrPort("198.51.100.2:4242")
|
||||
h.remote.Store(&remote)
|
||||
conn := &insideFilterConn{}
|
||||
sb := batch.NewSendBatch(conn, 1, mtu)
|
||||
pkt := buildIPv4(netip.MustParseAddr("192.0.2.1"), h.vpnAddrs[0], udpDatagram)
|
||||
before := ci.messageCounter.Load()
|
||||
f.consumeInsidePacket(tio.Packet{Bytes: pkt}, &firewall.ParsedPacket{}, make([]byte, 12), sb, nil, 0, nil)
|
||||
_, err = sb.Flush()
|
||||
require.NoError(t, err)
|
||||
if !allow {
|
||||
assert.Empty(t, conn.packets)
|
||||
assert.Equal(t, before, ci.messageCounter.Load())
|
||||
assert.False(t, h.sentSinceCheck())
|
||||
return
|
||||
}
|
||||
require.Len(t, conn.packets, 1)
|
||||
assert.True(t, h.sentSinceCheck())
|
||||
hdr := &header.H{}
|
||||
require.NoError(t, hdr.Parse(conn.packets[0]))
|
||||
assert.Equal(t, header.Message, hdr.Type)
|
||||
assert.Equal(t, h.remoteIndexId, hdr.RemoteIndex)
|
||||
assert.Equal(t, before+1, hdr.MessageCounter)
|
||||
plain, err := rci.Decrypt(f.l, hdr.MessageCounter, conn.packets[0], make([]byte, 12))
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, pkt, plain)
|
||||
})
|
||||
}
|
||||
}
|
||||
+68
-87
@@ -57,14 +57,19 @@ type InterfaceConfig struct {
|
||||
|
||||
// CpuAffinity, when non-empty, names the CPUs each TUN reader goroutine
|
||||
// should pin to. Queue i pins to CpuAffinity[i % len(CpuAffinity)] —
|
||||
// shorter lists than `routines` cycle. Empty list keeps the default
|
||||
// pin-to-(i % NumCPU) behavior. Only consulted when PinThreads is true.
|
||||
// shorter lists than `routines` cycle. Staged sender i uses entry i+1,
|
||||
// unless that is its reader's CPU. Empty uses the automatic order. Only
|
||||
// consulted when PinThreads is true.
|
||||
CpuAffinity []int
|
||||
// defaultCpuAffinity is the automatic pin order for readers, kept apart
|
||||
// from CpuAffinity because staged senders are only pinned to an explicit list.
|
||||
defaultCpuAffinity []int
|
||||
// PinThreads controls whether each TUN reader OS thread is pinned to a
|
||||
// single CPU (via tun.pin_threads, default true). Pinning keeps each
|
||||
// goroutine's sendmmsg on one XPS-selected NIC TX ring so per-flow
|
||||
// packets stay ordered on the wire.
|
||||
PinThreads bool
|
||||
staged stagedConfig
|
||||
|
||||
l *slog.Logger
|
||||
}
|
||||
@@ -94,11 +99,13 @@ type Interface struct {
|
||||
// should pin to. Queue i pins to cpuAffinity[i % len(cpuAffinity)].
|
||||
// Empty falls back to the default pin-to-(allowed CPU) behavior.
|
||||
// Only consulted when pinThreads is true.
|
||||
cpuAffinity []int
|
||||
cpuAffinity []int
|
||||
defaultCpuAffinity []int
|
||||
// pinThreads controls whether listenIn pins each TUN reader OS thread to
|
||||
// a CPU at all (tun.pin_threads, default true). When false, threads are
|
||||
// left free to migrate as on stock nebula.
|
||||
pinThreads bool
|
||||
staged stagedConfig
|
||||
relayManager *relayManager
|
||||
|
||||
tryPromoteEvery atomic.Uint32
|
||||
@@ -124,8 +131,6 @@ type Interface struct {
|
||||
// reused (every udp.Conn ListenOut guarantees that ordering).
|
||||
batchers []*batch.MultiCoalescer
|
||||
wg sync.WaitGroup
|
||||
// readers covers just the listenIn and listenOut goroutines, wg also holds the construction token Close releases
|
||||
readers sync.WaitGroup
|
||||
|
||||
udpTxErrLimiter *ratelimit.Limiter // udp direct transmit error log limiter
|
||||
udpRelayTxErrLimiter *ratelimit.Limiter // udp relay transmit error log limiter
|
||||
@@ -249,7 +254,9 @@ func NewInterface(ctx context.Context, c *InterfaceConfig) (*Interface, error) {
|
||||
connectionManager: c.connectionManager,
|
||||
conntrackCacheTimeout: c.ConntrackCacheTimeout,
|
||||
cpuAffinity: c.CpuAffinity,
|
||||
defaultCpuAffinity: c.defaultCpuAffinity,
|
||||
pinThreads: c.PinThreads,
|
||||
staged: c.staged,
|
||||
udpTxErrLimiter: udpTxErrLimiter,
|
||||
udpRelayTxErrLimiter: udpRelayTxErrLimiter,
|
||||
txOversizeLimiter: txOversizeLimiter,
|
||||
@@ -343,18 +350,14 @@ func (f *Interface) activate() error {
|
||||
func (f *Interface) run() {
|
||||
// Launch n queues to read packets from udp
|
||||
for i := 0; i < f.routines; i++ {
|
||||
f.readers.Add(1)
|
||||
f.wg.Go(func() {
|
||||
defer f.readers.Done()
|
||||
f.listenOut(i)
|
||||
})
|
||||
}
|
||||
|
||||
// Launch n queues to read packets from tun dev
|
||||
for i := 0; i < f.routines; i++ {
|
||||
f.readers.Add(1)
|
||||
f.wg.Go(func() {
|
||||
defer f.readers.Done()
|
||||
f.listenIn(f.queues[i], i)
|
||||
})
|
||||
}
|
||||
@@ -419,14 +422,18 @@ func (f *Interface) listenOut(i int) {
|
||||
f.readOutsidePackets(ViaSender{UdpAddr: fromUdpAddr}, payload, rxc)
|
||||
}
|
||||
|
||||
flusher := func() {
|
||||
if err := f.batchers[i].Flush(); err != nil {
|
||||
f.l.Error("Failed to flush tun coalescer", "error", err)
|
||||
}
|
||||
clear(rxc.hostmapCache)
|
||||
}
|
||||
flusher := func() { f.flushOutside(rxc) }
|
||||
|
||||
err := li.ListenOut(listener, flusher)
|
||||
var err error
|
||||
if hc, ok := li.(handoffConn); ok && f.staged.rx {
|
||||
// Every stage on its own goroutine, see flow_rx.go. rxc becomes the ordered writer's context.
|
||||
err = newStagedRx(f, i, rxc).listen(hc)
|
||||
} else {
|
||||
if f.staged.rx {
|
||||
f.l.Info("udp conn cannot hand off receive batches, receive stays inline", "reader", i)
|
||||
}
|
||||
err = li.ListenOut(listener, flusher)
|
||||
}
|
||||
|
||||
// An error after teardown began is shutdown noise, the closed flag covers resources
|
||||
// Close releases itself and the cancelled ctx covers ones torn down by their owners
|
||||
@@ -439,32 +446,30 @@ func (f *Interface) listenOut(i int) {
|
||||
f.l.Debug("underlay reader is done", "reader", i)
|
||||
}
|
||||
|
||||
func (f *Interface) pinThisThread(i int) {
|
||||
var cpu int
|
||||
// threadCPU is the CPU tun reader i pins to.
|
||||
func (f *Interface) threadCPU(i int) int {
|
||||
if n := len(f.cpuAffinity); n > 0 {
|
||||
// Explicit tun.cpu_affinity list wins; parseCpuAffinity already
|
||||
// validated the entries against the allowed CPU set.
|
||||
cpu = f.cpuAffinity[i%n]
|
||||
return f.cpuAffinity[i%n]
|
||||
} else if n := len(f.defaultCpuAffinity); n > 0 {
|
||||
return f.defaultCpuAffinity[i%n]
|
||||
} else if allowed, err := util.AllowedCPUs(); err == nil && len(allowed) > 0 {
|
||||
// Default: spread queues across the CPUs we're actually allowed to
|
||||
// run on. Under a cpuset/taskset mask these aren't 0..NumCPU-1, so
|
||||
// i % NumCPU would pick unrunnable IDs and every pin would fail.
|
||||
cpu = allowed[i%len(allowed)]
|
||||
} else {
|
||||
cpu = i % runtime.NumCPU()
|
||||
return allowed[i%len(allowed)]
|
||||
}
|
||||
return i % runtime.NumCPU()
|
||||
}
|
||||
|
||||
func (f *Interface) pinThreadToCPU(i, cpu int) {
|
||||
if err := util.PinThreadToCPU(cpu); err != nil {
|
||||
f.l.Warn("failed to pin tun reader to CPU", "queue", i, "cpu", cpu, "err", err)
|
||||
f.l.Warn("failed to pin tun processing thread to CPU", "queue", i, "cpu", cpu, "err", err)
|
||||
}
|
||||
}
|
||||
|
||||
func (f *Interface) listenIn(queue tio.Queue, i int) {
|
||||
// Pinning this thread (and goroutine) to a single CPU keeps every sendmmsg from this goroutine going through the
|
||||
// same TX ring on the nic, so the wire sees per-flow order. Skip entirely when tun.pin_threads is false.
|
||||
if f.pinThreads {
|
||||
f.pinThisThread(i)
|
||||
}
|
||||
|
||||
rejectBuf := make([]byte, mtu)
|
||||
arenaSize := batch.SendBatchCap * (udp.MTU + 32)
|
||||
sb := batch.NewSendBatch(f.writers[i], batch.SendBatchCap, arenaSize)
|
||||
@@ -473,6 +478,26 @@ func (f *Interface) listenIn(queue tio.Queue, i int) {
|
||||
|
||||
conntrackCache := firewall.NewConntrackCacheTicker(f.ctx, f.l, f.conntrackCacheTimeout)
|
||||
|
||||
if sq, ok := queue.(handoffQueue); ok && f.staged.tx {
|
||||
// Every stage on its own goroutine, see flow_tx.go
|
||||
err := newStagedTx(f, sq, i).run(fwPacket, rejectBuf, conntrackCache)
|
||||
if !f.closed.Load() && f.ctx.Err() == nil {
|
||||
f.l.Error("Error while reading outbound packet, closing", "error", err, "reader", i)
|
||||
f.onFatal(err)
|
||||
}
|
||||
f.l.Debug("overlay reader is done", "reader", i)
|
||||
return
|
||||
}
|
||||
if f.staged.tx {
|
||||
f.l.Info("tun queue cannot hand off read batches, transmit stays inline", "reader", i)
|
||||
}
|
||||
|
||||
// Pinning this thread (and goroutine) to a single CPU keeps every sendmmsg from this goroutine going through the
|
||||
// same TX ring on the nic, so the wire sees per-flow order. Skip entirely when tun.pin_threads is false.
|
||||
if f.pinThreads {
|
||||
f.pinThreadToCPU(i, f.threadCPU(i))
|
||||
}
|
||||
|
||||
for {
|
||||
pkts, err := queue.Read()
|
||||
if err != nil {
|
||||
@@ -543,12 +568,11 @@ func (f *Interface) reloadFirewall(c *config.C, r *config.Reload) {
|
||||
curCert = cs.getCertificate(cert.Version1)
|
||||
}
|
||||
|
||||
// Compare with what the running firewall was built from, not the last config, so a firewall that failed to build
|
||||
// is tried again. The cert is the one this reload brought, PKI registers its reload callback before this one
|
||||
src := c.Render("firewall")
|
||||
if src != "" && src == f.firewall.source && curCert != nil &&
|
||||
slices.Equal(curCert.Networks(), f.firewall.assignedNetworks) &&
|
||||
slices.Equal(curCert.UnsafeNetworks(), f.firewall.unsafeNetworks) {
|
||||
// The firewall builds its routableNetworks set from the certificate's UnsafeNetworks at construction.
|
||||
// Check to see if that set has changed, and if so, rebuild the firewall.
|
||||
certUnsafeChanged := curCert != nil && !slices.Equal(curCert.UnsafeNetworks(), f.firewall.unsafeNetworks)
|
||||
|
||||
if !c.HasChanged("firewall") && !certUnsafeChanged {
|
||||
f.l.Debug("No firewall config change detected")
|
||||
return
|
||||
}
|
||||
@@ -689,14 +713,6 @@ func (f *Interface) GetCertState() *CertState {
|
||||
return f.pki.getCertState()
|
||||
}
|
||||
|
||||
// shutdowner is a udp.Conn or overlay.Device whose readers can be woken without releasing their fds
|
||||
type shutdowner interface {
|
||||
Shutdown() error
|
||||
}
|
||||
|
||||
// readerShutdownTimeout bounds how long Close waits on woken readers before releasing their fds anyway
|
||||
const readerShutdownTimeout = 5 * time.Second
|
||||
|
||||
// Close releases the interface's resources: the udp sockets and the tun device.
|
||||
// It is idempotent and safe to call at any point in the lifecycle, including on an interface that never activated,
|
||||
// calls after the first return nil without doing anything.
|
||||
@@ -706,55 +722,20 @@ func (f *Interface) Close() error {
|
||||
}
|
||||
|
||||
var errs []error
|
||||
closeUdp := func(i int, u udp.Conn) {
|
||||
if err := u.Close(); err != nil {
|
||||
|
||||
// Release the udp readers
|
||||
for i, u := range f.writers {
|
||||
err := u.Close()
|
||||
if err != nil {
|
||||
f.l.Error("Error while closing udp socket", "error", err, "writer", i)
|
||||
errs = append(errs, err)
|
||||
}
|
||||
}
|
||||
closeTun := func() {
|
||||
if err := f.inside.Close(); err != nil {
|
||||
errs = append(errs, err)
|
||||
}
|
||||
}
|
||||
|
||||
// Wake every reader before releasing any fd, one that loops back into a syscall on a reused fd number never wakes.
|
||||
// Anything without Shutdown is closed right away, as before.
|
||||
var deferred []func()
|
||||
for i, u := range f.writers {
|
||||
if s, ok := u.(shutdowner); ok {
|
||||
if err := s.Shutdown(); err != nil {
|
||||
f.l.Error("Error while shutting down udp socket", "error", err, "writer", i)
|
||||
errs = append(errs, err)
|
||||
}
|
||||
deferred = append(deferred, func() { closeUdp(i, u) })
|
||||
} else {
|
||||
closeUdp(i, u)
|
||||
}
|
||||
}
|
||||
if s, ok := f.inside.(shutdowner); ok {
|
||||
if err := s.Shutdown(); err != nil {
|
||||
errs = append(errs, err)
|
||||
}
|
||||
deferred = append(deferred, closeTun)
|
||||
} else {
|
||||
closeTun()
|
||||
}
|
||||
|
||||
if len(deferred) > 0 {
|
||||
readersDone := make(chan struct{})
|
||||
go func() {
|
||||
f.readers.Wait()
|
||||
close(readersDone)
|
||||
}()
|
||||
select {
|
||||
case <-readersDone:
|
||||
case <-time.After(readerShutdownTimeout):
|
||||
f.l.Warn("Readers did not stop, closing their fds anyway", "timeout", readerShutdownTimeout)
|
||||
}
|
||||
for _, closeFn := range deferred {
|
||||
closeFn()
|
||||
}
|
||||
// Release the tun device (closing the tun also closes all readers)
|
||||
closeErr := f.inside.Close()
|
||||
if closeErr != nil {
|
||||
errs = append(errs, closeErr)
|
||||
}
|
||||
|
||||
// Release the construction token so waiters know the resources are gone
|
||||
|
||||
+3
-58
@@ -135,63 +135,8 @@ func TestReloadFirewall_BadRulesFailTheReload(t *testing.T) {
|
||||
f := &Interface{pki: pki, firewall: fw, l: l}
|
||||
cfg.RegisterReloadCallback(f.reloadFirewall)
|
||||
|
||||
// The running firewall still isn't built from what the config asks for, so the same reload fails again
|
||||
for range 2 {
|
||||
res := cfg.ReloadConfigString(rules("nope"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.Same(t, fw, f.firewall)
|
||||
}
|
||||
|
||||
res := cfg.ReloadConfigString(rules("tcp"))
|
||||
res := cfg.ReloadConfigString(rules("nope"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.NotSame(t, fw, f.firewall)
|
||||
}
|
||||
|
||||
// Every input the firewall is built from rebuilds it when it changes, and nothing else does
|
||||
func TestReloadFirewall_RebuildsOnAnyInput(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
networks := []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")}
|
||||
base := "firewall:\n inbound:\n - port: any\n proto: any\n host: any\n"
|
||||
setup := func() (*config.C, *Interface, *PKI) {
|
||||
pki := &PKI{}
|
||||
pki.cs.Store(&CertState{v2Cert: &dummyCert{version: cert.Version2, networks: networks}, initiatingVersion: cert.Version2})
|
||||
cfg := config.NewC(l)
|
||||
require.NoError(t, cfg.LoadString(base))
|
||||
fw, err := NewFirewallFromConfig(l, pki.getCertState(), cfg)
|
||||
require.NoError(t, err)
|
||||
f := &Interface{pki: pki, firewall: fw, l: l}
|
||||
cfg.RegisterReloadCallback(f.reloadFirewall)
|
||||
return cfg, f, pki
|
||||
}
|
||||
setCert := func(pki *PKI, networks, unsafe []netip.Prefix) {
|
||||
pki.cs.Store(&CertState{v2Cert: &dummyCert{version: cert.Version2, networks: networks, unsafeNetworks: unsafe}, initiatingVersion: cert.Version2})
|
||||
}
|
||||
|
||||
cases := map[string]struct {
|
||||
cfg string
|
||||
cert func(*PKI)
|
||||
want bool
|
||||
}{
|
||||
"nothing": {base + "punchy:\n punch: true\n", nil, false},
|
||||
"rules": {base + " outbound:\n - port: any\n proto: any\n host: any\n", nil, true},
|
||||
"inbound_action": {base + " inbound_action: reject\n", nil, true},
|
||||
"conntrack": {base + " conntrack:\n tcp_timeout: 1m\n", nil, true},
|
||||
"networks": {base, func(p *PKI) { setCert(p, []netip.Prefix{netip.MustParsePrefix("10.0.0.2/24")}, nil) }, true},
|
||||
"unsafe_networks": {base, func(p *PKI) { setCert(p, networks, []netip.Prefix{netip.MustParsePrefix("192.168.0.0/24")}) }, true},
|
||||
}
|
||||
for name, tc := range cases {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
cfg, f, pki := setup()
|
||||
old := f.firewall
|
||||
if tc.cert != nil {
|
||||
tc.cert(pki)
|
||||
}
|
||||
res := cfg.ReloadConfigString(tc.cfg)
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.Equal(t, tc.want, f.firewall != old)
|
||||
})
|
||||
}
|
||||
assert.True(t, res.Failed)
|
||||
assert.Same(t, fw, f.firewall)
|
||||
}
|
||||
+3
-5
@@ -452,7 +452,7 @@ func getStaticMapCadence(c *config.C) (time.Duration, error) {
|
||||
}
|
||||
|
||||
func getStaticMapLookupTimeout(c *config.C) (time.Duration, error) {
|
||||
lookupTimeout := c.GetString("static_map.lookup_timeout", "5s")
|
||||
lookupTimeout := c.GetString("static_map.lookup_timeout", "250ms")
|
||||
d, err := time.ParseDuration(lookupTimeout)
|
||||
if err != nil {
|
||||
return 0, err
|
||||
@@ -630,8 +630,7 @@ func (lh *LightHouse) addStaticRemotes(i int, d time.Duration, network string, t
|
||||
ctx := lh.ctx
|
||||
lh.Unlock()
|
||||
|
||||
// On reload am.hr is the previous resolver, its last known good addresses carry over in case DNS is down right now
|
||||
hr, err := NewHostnameResults(ctx, lh.l, d, network, timeout, toAddrs, am.hr, func() {
|
||||
hr, err := NewHostnameResults(ctx, lh.l, d, network, timeout, toAddrs, func() {
|
||||
// This callback runs whenever the DNS hostname resolver finds a different set of addr's
|
||||
// in its resolution for hostnames.
|
||||
am.Lock()
|
||||
@@ -643,8 +642,7 @@ func (lh *LightHouse) addStaticRemotes(i int, d time.Duration, network string, t
|
||||
}
|
||||
am.unlockedSetHostnamesResults(hr)
|
||||
|
||||
// Only literals belong in the cache, anything from DNS has to stay in hr where a not found answer can remove it
|
||||
for _, addrPort := range hr.literalAddrs() {
|
||||
for _, addrPort := range hr.GetAddrs() {
|
||||
if !lh.shouldAdd([]netip.Addr{vpnAddr}, addrPort.Addr()) {
|
||||
continue
|
||||
}
|
||||
|
||||
@@ -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"
|
||||
@@ -72,11 +71,7 @@ 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)
|
||||
}
|
||||
@@ -249,6 +244,8 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
|
||||
pinThreads := c.GetBool("tun.pin_threads", true)
|
||||
cpuAffinity := parseCpuAffinity(c, l, routines)
|
||||
var defaultCpuAffinity []int
|
||||
staged := parseStagedConfig(c, l)
|
||||
if pinThreads && routines > 1 && len(cpuAffinity) == 0 && !configTest {
|
||||
// The operator didn't choose pin CPUs, so pick a default set that
|
||||
// prefers performance cores and doesn't stack co-located instances
|
||||
@@ -275,7 +272,7 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
l.Warn("tun.pin_threads_key is invalid, using PID")
|
||||
}
|
||||
|
||||
cpuAffinity = cpupick.Default(routines, key, l)
|
||||
defaultCpuAffinity = cpupick.Default(routines, key, l)
|
||||
}
|
||||
|
||||
ifConfig := &InterfaceConfig{
|
||||
@@ -300,7 +297,9 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
punchy: punchy,
|
||||
ConntrackCacheTimeout: conntrackCacheTimeout,
|
||||
CpuAffinity: cpuAffinity,
|
||||
defaultCpuAffinity: defaultCpuAffinity,
|
||||
PinThreads: pinThreads,
|
||||
staged: staged,
|
||||
l: l,
|
||||
}
|
||||
|
||||
@@ -348,14 +347,13 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
attachCommands(l, c, cmdRegistry, ifce)
|
||||
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,
|
||||
|
||||
@@ -5,12 +5,14 @@ import (
|
||||
"net/netip"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/cert"
|
||||
cert_test "github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/noiseutil"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/util"
|
||||
"github.com/stretchr/testify/assert"
|
||||
@@ -123,3 +125,70 @@ firewall:
|
||||
require.NoError(t, err)
|
||||
require.Nil(t, ctrl, "a config test hands back nothing to stop, so it must stop itself")
|
||||
}
|
||||
|
||||
func TestParseStagedConfig(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
staged := func(workers any) stagedConfig {
|
||||
c := config.NewC(l)
|
||||
if workers != nil {
|
||||
c.Settings["tun"] = map[string]any{"staged": map[string]any{"workers": workers}}
|
||||
}
|
||||
return parseStagedConfig(c, l)
|
||||
}
|
||||
for _, workers := range []any{nil, -1, 0} {
|
||||
require.Equal(t, stagedConfig{}, staged(workers))
|
||||
}
|
||||
if runtime.GOOS != "linux" {
|
||||
require.Equal(t, stagedConfig{}, staged(2))
|
||||
return
|
||||
}
|
||||
want := stagedConfig{workers: 2, tx: !noiseutil.EncryptLockNeeded, rx: true, inlineBelow: 256, gateHold: stagedGateHold,
|
||||
txSlots: 8, rxSlots: 6}
|
||||
require.Equal(t, want, staged(2))
|
||||
|
||||
c := config.NewC(l)
|
||||
c.Settings["listen"] = map[string]any{"batch": 128}
|
||||
c.Settings["tun"] = map[string]any{"staged": map[string]any{"workers": 2, "tx_slots": 3, "rx_slots": 1}}
|
||||
got := parseStagedConfig(c, l)
|
||||
require.Equal(t, []int{3, 2}, []int{got.txSlots, got.rxSlots}, "overrides apply, down to the minimum")
|
||||
|
||||
c = config.NewC(l)
|
||||
c.Settings["tun"] = map[string]any{"staged": map[string]any{"workers": 2, "tx": false, "inline_below": 0}}
|
||||
got = parseStagedConfig(c, l)
|
||||
require.False(t, got.tx, "tx: false keeps transmit inline")
|
||||
require.True(t, got.rx)
|
||||
require.Zero(t, got.inlineBelow, "inline_below: 0 hands every batch off")
|
||||
|
||||
c = config.NewC(l)
|
||||
c.Settings["tun"] = map[string]any{"staged": map[string]any{"workers": 2, "inline_below": 32}}
|
||||
require.Equal(t, 32, parseStagedConfig(c, l).inlineBelow)
|
||||
c.Settings["tun"] = map[string]any{"staged": map[string]any{"workers": 2, "inline_below": -1}}
|
||||
require.Zero(t, parseStagedConfig(c, l).inlineBelow, "a negative threshold is 0")
|
||||
|
||||
for _, tt := range []struct {
|
||||
hold any
|
||||
want int
|
||||
}{{nil, stagedGateHold}, {8, 8}, {0, 1}, {-3, 1}} {
|
||||
c = config.NewC(l)
|
||||
settings := map[string]any{"workers": 2}
|
||||
if tt.hold != nil {
|
||||
settings["gate_hold"] = tt.hold
|
||||
}
|
||||
c.Settings["tun"] = map[string]any{"staged": settings}
|
||||
require.Equal(t, tt.want, parseStagedConfig(c, l).gateHold, "gate_hold %v", tt.hold)
|
||||
}
|
||||
}
|
||||
|
||||
func TestStagedSlots(t *testing.T) {
|
||||
for _, tt := range []struct{ workers, batch, tx, rx int }{
|
||||
{workers: 2, batch: 64, tx: 8, rx: 6},
|
||||
{workers: 12, batch: 64, tx: 14, rx: 6},
|
||||
{workers: 2, batch: 96, tx: 8, rx: 4},
|
||||
{workers: 2, batch: 512, tx: 8, rx: 4},
|
||||
{workers: 2, batch: 32, tx: 8, rx: 6},
|
||||
{workers: 2, batch: 1, tx: 8, rx: 6},
|
||||
} {
|
||||
tx, rx := stagedSlots(tt.workers, tt.batch, 0, 0)
|
||||
require.Equal(t, []int{tt.tx, tt.rx}, []int{tx, rx}, "workers %d batch %d", tt.workers, tt.batch)
|
||||
}
|
||||
}
|
||||
+25
-9
@@ -130,17 +130,10 @@ func (f *Interface) readOutsidePackets(via ViaSender, packet []byte, rxc *rxCont
|
||||
}
|
||||
|
||||
out, err := hostinfo.ConnectionState.Decrypt(f.l, h.MessageCounter, packet, rxc.nb)
|
||||
if err != nil {
|
||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
hostinfo.logger(f.l).Debug("Failed to decrypt packet", "error", err, "from", via, "header", h)
|
||||
}
|
||||
if !f.finishOutsideDecrypt(hostinfo, via, h.MessageCounter, err) {
|
||||
return
|
||||
}
|
||||
|
||||
// Roam before we respond
|
||||
f.handleHostRoaming(hostinfo, via)
|
||||
f.connectionManager.In(hostinfo)
|
||||
|
||||
switch h.Type {
|
||||
case header.Message:
|
||||
switch h.Subtype {
|
||||
@@ -473,13 +466,36 @@ func parseV4(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// finishOutsideDecrypt logs a failed decrypt, or roams and records the traffic for an authenticated packet before it
|
||||
// is handled. It reports whether the packet authenticated.
|
||||
func (f *Interface) finishOutsideDecrypt(hostinfo *HostInfo, via ViaSender, counter uint64, err error) bool {
|
||||
if err != nil {
|
||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
hostinfo.logger(f.l).Debug("Failed to decrypt packet", "error", err, "from", via, "counter", counter)
|
||||
}
|
||||
return false
|
||||
}
|
||||
// Roam before we respond
|
||||
f.handleHostRoaming(hostinfo, via)
|
||||
f.connectionManager.In(hostinfo)
|
||||
return true
|
||||
}
|
||||
|
||||
// flushOutside ends a receive batch: it writes out the tun coalescer and drops the batch's hostmap cache.
|
||||
func (f *Interface) flushOutside(rxc *rxContext) {
|
||||
if err := f.batchers[rxc.q].Flush(); err != nil {
|
||||
f.l.Error("Failed to flush tun coalescer", "error", err)
|
||||
}
|
||||
clear(rxc.hostmapCache)
|
||||
}
|
||||
|
||||
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)
|
||||
return
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
dropReason := f.firewall.Drop(rxc.fwPacket.Packet, true, hostinfo, f.pki.GetCAPool(), rxc.ctCache.Get())
|
||||
|
||||
@@ -43,6 +43,14 @@ func (b *SendBatch) Commit(pkt []byte, dst netip.AddrPort) {
|
||||
b.dsts = append(b.dsts, dst)
|
||||
}
|
||||
|
||||
// Reset drops every queued packet without sending it.
|
||||
func (b *SendBatch) Reset() {
|
||||
clear(b.bufs)
|
||||
b.bufs = b.bufs[:0]
|
||||
b.dsts = b.dsts[:0]
|
||||
b.arena.Reset()
|
||||
}
|
||||
|
||||
// Flush writes every queued packet and reports how many actually went out. A short count means some destinations
|
||||
// were undeliverable; the batch is drained either way.
|
||||
func (b *SendBatch) Flush() (int, error) {
|
||||
@@ -51,9 +59,6 @@ func (b *SendBatch) Flush() (int, error) {
|
||||
if len(b.bufs) > 0 {
|
||||
written, err = b.out.WriteBatch(b.bufs, b.dsts)
|
||||
}
|
||||
clear(b.bufs)
|
||||
b.bufs = b.bufs[:0]
|
||||
b.dsts = b.dsts[:0]
|
||||
b.arena.Reset()
|
||||
b.Reset()
|
||||
return written, err
|
||||
}
|
||||
@@ -20,7 +20,6 @@ type offloadQueueSet struct {
|
||||
// usoEnabled is true when newTun successfully negotiated TUN_F_USO4|6 with the kernel.
|
||||
// Queues created by Add inherit this and surface it via Offload.USOSupported so coalescers can gate USO emission.
|
||||
usoEnabled bool
|
||||
shutdown atomic.Bool
|
||||
closed atomic.Bool
|
||||
// l is handed to each queue for its bad-vnet-header drop logging.
|
||||
l *slog.Logger
|
||||
@@ -70,17 +69,6 @@ func (c *offloadQueueSet) wakeForShutdown() error {
|
||||
return err
|
||||
}
|
||||
|
||||
// Shutdown wakes every reader without releasing any fds, they see POLLIN on the eventfd and return os.ErrClosed
|
||||
func (c *offloadQueueSet) Shutdown() error {
|
||||
if c.shutdown.Swap(true) {
|
||||
return nil
|
||||
}
|
||||
for _, x := range c.pq {
|
||||
x.shutdown.Store(true)
|
||||
}
|
||||
return c.wakeForShutdown()
|
||||
}
|
||||
|
||||
func (c *offloadQueueSet) Close() error {
|
||||
if c.closed.Swap(true) {
|
||||
return nil
|
||||
@@ -88,7 +76,9 @@ func (c *offloadQueueSet) Close() error {
|
||||
|
||||
errs := []error{}
|
||||
|
||||
if err := c.Shutdown(); err != nil {
|
||||
// Signal all readers blocked in poll to wake up and exit.
|
||||
// They observe POLLIN on the shutdown eventfd and return os.ErrClosed.
|
||||
if err := c.wakeForShutdown(); err != nil {
|
||||
errs = append(errs, err)
|
||||
}
|
||||
|
||||
|
||||
@@ -16,7 +16,6 @@ type pollQueueSet struct {
|
||||
// pqi is exactly the same as pq, but stored as the interface type
|
||||
pqi []Queue
|
||||
shutdownFd int
|
||||
shutdown atomic.Bool
|
||||
closed atomic.Bool
|
||||
}
|
||||
|
||||
@@ -60,17 +59,6 @@ func (c *pollQueueSet) wakeForShutdown() error {
|
||||
return err
|
||||
}
|
||||
|
||||
// Shutdown wakes every reader without releasing any fds, they see POLLIN on the eventfd and return os.ErrClosed
|
||||
func (c *pollQueueSet) Shutdown() error {
|
||||
if c.shutdown.Swap(true) {
|
||||
return nil
|
||||
}
|
||||
for _, x := range c.pq {
|
||||
x.shutdown.Store(true)
|
||||
}
|
||||
return c.wakeForShutdown()
|
||||
}
|
||||
|
||||
func (c *pollQueueSet) Close() error {
|
||||
if c.closed.Swap(true) {
|
||||
return nil
|
||||
@@ -78,7 +66,9 @@ func (c *pollQueueSet) Close() error {
|
||||
|
||||
errs := []error{}
|
||||
|
||||
if err := c.Shutdown(); err != nil {
|
||||
// Signal all readers blocked in poll to wake up and exit.
|
||||
// They observe POLLIN on the shutdown eventfd and return os.ErrClosed.
|
||||
if err := c.wakeForShutdown(); err != nil {
|
||||
errs = append(errs, err)
|
||||
}
|
||||
|
||||
|
||||
+9
-2
@@ -7,8 +7,6 @@ import (
|
||||
// QueueSet holds one or many Queue objects and helps close them in an orderly way.
|
||||
type QueueSet interface {
|
||||
io.Closer
|
||||
// Shutdown wakes every reader without releasing any fds, Close only once they have exited
|
||||
Shutdown() error
|
||||
Queues() []Queue
|
||||
|
||||
// Add takes a tun fd, adds it to the set, and prepares it for use as a Queue.
|
||||
@@ -77,6 +75,15 @@ type GSOInfo struct {
|
||||
// superpacket that needs segmentation before its bytes can be encrypted and sent on the wire.
|
||||
func (g GSOInfo) IsSuperpacket() bool { return g.Size > 0 }
|
||||
|
||||
// SegmentCount reports how many segments SegmentSuperpacket will cut p into, without touching its bytes.
|
||||
func (p Packet) SegmentCount() int {
|
||||
if !p.GSO.IsSuperpacket() {
|
||||
return 1
|
||||
}
|
||||
n := (len(p.Bytes) - int(p.GSO.HdrLen) + int(p.GSO.Size) - 1) / int(p.GSO.Size)
|
||||
return max(n, 1)
|
||||
}
|
||||
|
||||
// Clone returns a Packet whose Bytes is a freshly allocated copy of p.Bytes,
|
||||
// safe to retain past the next Read or Close on the originating Queue.
|
||||
// GSO metadata is copied verbatim.
|
||||
|
||||
@@ -66,9 +66,7 @@ type Offload struct {
|
||||
// usoEnabled records whether the kernel agreed to TUN_F_USO* on this FD,
|
||||
// so writers can decide whether emitting GSO_UDP_L4 superpackets is safe.
|
||||
usoEnabled bool
|
||||
// shutdown is set before shutdownFd is signaled, a busy reader never polls to see that
|
||||
shutdown atomic.Bool
|
||||
closed atomic.Bool
|
||||
closed atomic.Bool
|
||||
|
||||
// gsoHdrBuf is a per-queue 10-byte scratch for the virtio_net_hdr emitted
|
||||
// by WriteGSO. Kept separate from the read-only package-level validVnetHdr
|
||||
@@ -178,9 +176,6 @@ func (r *Offload) readPacket(block bool) (int, error) {
|
||||
// This amortizes the poll wake over bursts of small packets (e.g. TCP ACKs).
|
||||
// Packet.Bytes slices point into the Offload's internal buffer and are only valid until the next Read or Close on this Queue.
|
||||
func (r *Offload) Read() ([]Packet, error) {
|
||||
if r.shutdown.Load() {
|
||||
return nil, os.ErrClosed
|
||||
}
|
||||
r.pending = r.pending[:0]
|
||||
r.rxOff = 0
|
||||
|
||||
@@ -224,6 +219,21 @@ func (r *Offload) Read() ([]Packet, error) {
|
||||
return r.pending, nil
|
||||
}
|
||||
|
||||
// SwapRxBuf installs buf as the receive buffer for the following Reads and returns the one backing the packets
|
||||
// of the most recent Read, so the caller can keep them past the next Read. A nil buf allocates a replacement of
|
||||
// the required size. Single-reader only, like Read.
|
||||
func (r *Offload) SwapRxBuf(buf []byte) []byte {
|
||||
if buf == nil {
|
||||
buf = make([]byte, tunRxBufCap)
|
||||
}
|
||||
if len(buf) < tunRxBufCap {
|
||||
panic(fmt.Sprintf("tio: SwapRxBuf buffer is %d bytes, need %d", len(buf), tunRxBufCap))
|
||||
}
|
||||
old := r.rxBuf
|
||||
r.rxBuf = buf
|
||||
return old
|
||||
}
|
||||
|
||||
// logDroppedRead reports a tun packet dropped for a bad/unsupported virtio
|
||||
// header. Debug-gated so the happy path never pays for attribute assembly.
|
||||
func (r *Offload) logDroppedRead(err error) {
|
||||
|
||||
@@ -13,9 +13,7 @@ import (
|
||||
type Poll struct {
|
||||
fd int
|
||||
shutdownFd int
|
||||
// shutdown is set before shutdownFd is signaled, a busy reader never polls to see that
|
||||
shutdown atomic.Bool
|
||||
closed atomic.Bool
|
||||
closed atomic.Bool
|
||||
|
||||
readBuf []byte
|
||||
batchRet [1]Packet
|
||||
@@ -54,9 +52,6 @@ func (t *Poll) blockOnWrite() error {
|
||||
// config currently lose that batching. blockOn and the EAGAIN plumbing are
|
||||
// already shared; kept one-packet-per-Read for now to preserve behavior.
|
||||
func (t *Poll) Read() ([]Packet, error) {
|
||||
if t.shutdown.Load() {
|
||||
return nil, os.ErrClosed
|
||||
}
|
||||
n, err := t.readOne(t.readBuf)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
|
||||
@@ -223,30 +223,3 @@ func TestOffloadQueueSet_Close_ClosesShutdownFd(t *testing.T) {
|
||||
// Second Close must not touch fds (shutdownFd is now -1) and must return nil.
|
||||
require.NoError(t, qs.Close())
|
||||
}
|
||||
|
||||
// A busy reader never polls the shutdown eventfd, so Read has to stop on its own with data still waiting
|
||||
func TestQueueSet_ShutdownStopsReaderWithDataWaiting(t *testing.T) {
|
||||
sets := map[string]func() (QueueSet, error){
|
||||
"poll": NewPollQueueSet,
|
||||
"offload": func() (QueueSet, error) { return NewOffloadQueueSet(false, slog.New(slog.DiscardHandler)) },
|
||||
}
|
||||
for name, newSet := range sets {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
var fds [2]int
|
||||
require.NoError(t, unix.Pipe2(fds[:], unix.O_CLOEXEC))
|
||||
t.Cleanup(func() { _ = unix.Close(fds[1]) })
|
||||
|
||||
qs, err := newSet()
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, qs.Add(fds[0]))
|
||||
t.Cleanup(func() { _ = qs.Close() })
|
||||
|
||||
_, err = unix.Write(fds[1], make([]byte, 64))
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, qs.Shutdown())
|
||||
|
||||
_, err = qs.Queues()[0].Read()
|
||||
require.ErrorIs(t, err, os.ErrClosed)
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -911,6 +911,25 @@ func TestOffloadWriteZeroLength(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// TestOffloadSwapRxBuf: SwapRxBuf hands over the buffer the last Read filled and reads into the one it is given.
|
||||
func TestOffloadSwapRxBuf(t *testing.T) {
|
||||
o := &Offload{rxBuf: make([]byte, tunRxBufCap)}
|
||||
read := o.rxBuf
|
||||
owned := o.SwapRxBuf(nil)
|
||||
if &owned[0] != &read[0] || len(o.rxBuf) != tunRxBufCap || &o.rxBuf[0] == &read[0] {
|
||||
t.Fatal("SwapRxBuf(nil) must hand over the last read buffer and allocate a new one")
|
||||
}
|
||||
if back := o.SwapRxBuf(owned); &back[0] == &owned[0] || &o.rxBuf[0] != &owned[0] {
|
||||
t.Fatal("SwapRxBuf must install the buffer it is given")
|
||||
}
|
||||
defer func() {
|
||||
if recover() == nil {
|
||||
t.Fatal("SwapRxBuf must reject a short buffer")
|
||||
}
|
||||
}()
|
||||
o.SwapRxBuf(make([]byte, 10))
|
||||
}
|
||||
|
||||
// TestWriteGSOSuperpacketGeometry decodes the vnet header the kernel would see for a multi-segment write:
|
||||
// the GSO type must match the proto and IP version
|
||||
// gso_size must be the per-segment size (the kernel rejects a superpacket with gso_size == 0),
|
||||
|
||||
+84
-54
@@ -3,6 +3,7 @@
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"math/bits"
|
||||
@@ -11,7 +12,6 @@ import (
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
"time"
|
||||
"unsafe"
|
||||
|
||||
"github.com/gaissmai/bart"
|
||||
@@ -35,26 +35,6 @@ type tun struct {
|
||||
// and routes for it. NEPacketTunnelProvider on darwin does this.
|
||||
hostOwned bool
|
||||
l *slog.Logger
|
||||
|
||||
// routesMu serializes changes to the system routing table between reload and the route watcher, and guards the
|
||||
// fields below it
|
||||
routesMu sync.Mutex
|
||||
// routeStates is who held each installable unsafe_route prefix when we last looked
|
||||
routeStates map[netip.Prefix]routeState
|
||||
// routeWatch is the routing socket watchRoutes reads, Close closes it
|
||||
routeWatch *os.File
|
||||
// routeSweep reconciles the unsafe_routes every routeSweepEvery
|
||||
routeSweep *time.Timer
|
||||
routeSweepEvery time.Duration
|
||||
closed bool
|
||||
|
||||
// routeMovers is who last changed each unsafe_route prefix since the last reconcile, for its logs. It has its own
|
||||
// lock so the route watcher never waits on a reconcile
|
||||
routeMoversMu sync.Mutex
|
||||
routeMovers map[netip.Prefix]routeMover
|
||||
|
||||
// lastRouteEvent is when the routing socket last reported something that may have moved a prefix, in unix nanos
|
||||
lastRouteEvent atomic.Int64
|
||||
}
|
||||
|
||||
type ifReq struct {
|
||||
@@ -159,12 +139,11 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
}
|
||||
|
||||
t := &tun{
|
||||
f: os.NewFile(uintptr(fd), ""),
|
||||
Device: name,
|
||||
vpnNetworks: vpnNetworks,
|
||||
DefaultMTU: getMTU(l, c),
|
||||
routeSweepEvery: routeSweepInterval,
|
||||
l: l,
|
||||
f: os.NewFile(uintptr(fd), ""),
|
||||
Device: name,
|
||||
vpnNetworks: vpnNetworks,
|
||||
DefaultMTU: getMTU(l, c),
|
||||
l: l,
|
||||
}
|
||||
|
||||
err = t.reload(c, true, nil)
|
||||
@@ -240,16 +219,6 @@ func utunNameFromFd(fd int) string {
|
||||
}
|
||||
|
||||
func (t *tun) Close() error {
|
||||
t.routesMu.Lock()
|
||||
t.closed = true
|
||||
if t.routeWatch != nil {
|
||||
_ = t.routeWatch.Close()
|
||||
}
|
||||
if t.routeSweep != nil {
|
||||
t.routeSweep.Stop()
|
||||
}
|
||||
t.routesMu.Unlock()
|
||||
|
||||
if t.f != nil {
|
||||
return t.f.Close()
|
||||
}
|
||||
@@ -318,22 +287,8 @@ func (t *tun) Activate() error {
|
||||
return fmt.Errorf("failed to run tun device: %s", err)
|
||||
}
|
||||
|
||||
// Watch before adding so a route removed in between is still noticed
|
||||
watch, err := openRouteSocket()
|
||||
if err != nil {
|
||||
t.l.Error("Failed to watch the system routing table, unsafe_routes held by another interface are only retried every minute", "error", err)
|
||||
}
|
||||
|
||||
// Unsafe path routes
|
||||
if err = t.addRoutes(false, nil); err != nil {
|
||||
if watch != nil {
|
||||
_ = watch.Close()
|
||||
}
|
||||
return err
|
||||
}
|
||||
|
||||
t.startRouteWatch(watch)
|
||||
return nil
|
||||
return t.addRoutes(false, nil)
|
||||
}
|
||||
|
||||
// activate4 assigns our vpn address as a /32 and routes the vpn network to the tun explicitly.
|
||||
@@ -438,8 +393,7 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
}
|
||||
|
||||
if !initial && !change {
|
||||
// Any reload puts back the unsafe_routes someone deleted
|
||||
return t.addRoutes(true, r)
|
||||
return nil
|
||||
}
|
||||
|
||||
routeTree, err := makeRouteTree(t.l, routes, false)
|
||||
@@ -557,6 +511,82 @@ func getLinkAddr(name string) (*netroute.LinkAddr, error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) 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 {
|
||||
// We don't allow route MTUs so only install routes with a via
|
||||
continue
|
||||
}
|
||||
|
||||
err := addRoute(r.Cidr, 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)
|
||||
}
|
||||
} 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 {
|
||||
return nil
|
||||
}
|
||||
|
||||
for _, r := range routes {
|
||||
if len(r.Via) == 0 || !r.Install {
|
||||
// addRoutes never installs these
|
||||
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 {
|
||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||
rl.Failed()
|
||||
} else {
|
||||
t.l.Info("Removed route", "route", r)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func addRoute(prefix netip.Prefix, gateway netroute.Addr) error {
|
||||
sock, err := unix.Socket(unix.AF_ROUTE, unix.SOCK_RAW, unix.AF_UNSPEC)
|
||||
if err != nil {
|
||||
|
||||
@@ -3,17 +3,12 @@
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
"encoding/hex"
|
||||
"fmt"
|
||||
"net"
|
||||
"net/netip"
|
||||
"os"
|
||||
"os/exec"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/routing"
|
||||
@@ -109,367 +104,6 @@ func TestTunReloadLeavesRoutesItNeverInstalled(t *testing.T) {
|
||||
assert.Equal(t, lo0.Index, routeInterfaceIn(msgs, netip.MustParsePrefix(cidr)))
|
||||
}
|
||||
|
||||
// Captured on macOS 15.6 while adding and removing 198.51.100.77/24 on a feth
|
||||
const (
|
||||
// The kernel deleting the address's subnet route. It packs its sockaddrs without padding, x/net/route can't parse it
|
||||
kernelSubnetDelete = "870005022300000000010002070000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000010020000c63364000000000000000000141223000600000000000000000000000000000007ffffffffffff"
|
||||
addressRemoved = "5000050db400000001010000230000000000000007020000ffffff00141223000606060066657468373766657468004d10020000c633644d000000000000000010020000c63364ff0000000000000000"
|
||||
// With no interface address, which x/net/route skips
|
||||
interfaceChanged = "7000050e000000004288000023000000060000060e000000dc05000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000073e5ce6a0000000000000000000001000000000000000000"
|
||||
)
|
||||
|
||||
func TestRoutesMayHaveMoved(t *testing.T) {
|
||||
cidr := netip.MustParsePrefix("192.168.1.0/24")
|
||||
via := routing.Gateways{routing.NewGateway(netip.MustParseAddr("10.250.0.2"), 1)}
|
||||
routes := []Route{{Cidr: cidr, Via: via, Install: true}}
|
||||
// A request like route(8) sends, the kernel echoes it to every routing socket
|
||||
request := func(typ, flags int, dst, mask [4]byte) []byte {
|
||||
m := &netroute.RouteMessage{
|
||||
Version: unix.RTM_VERSION,
|
||||
Type: typ,
|
||||
Flags: flags,
|
||||
ID: 1234,
|
||||
Addrs: []netroute.Addr{
|
||||
unix.RTAX_DST: &netroute.Inet4Addr{IP: dst},
|
||||
unix.RTAX_GATEWAY: &netroute.LinkAddr{Index: 4},
|
||||
unix.RTAX_NETMASK: &netroute.Inet4Addr{IP: mask},
|
||||
},
|
||||
}
|
||||
b, err := m.Marshal()
|
||||
require.NoError(t, err)
|
||||
return b
|
||||
}
|
||||
raw := func(s string) []byte {
|
||||
b, err := hex.DecodeString(s)
|
||||
require.NoError(t, err)
|
||||
return b
|
||||
}
|
||||
lan, mask := [4]byte{192, 168, 1, 0}, [4]byte{255, 255, 255, 0}
|
||||
routesMayHaveMoved := func(b []byte, routes []Route) bool {
|
||||
moved, _, _ := routesMayHaveMoved(b, routes)
|
||||
return moved
|
||||
}
|
||||
|
||||
assert.True(t, routesMayHaveMoved(request(unix.RTM_DELETE, unix.RTF_UP, lan, mask), routes))
|
||||
assert.True(t, routesMayHaveMoved(request(unix.RTM_ADD, unix.RTF_UP, lan, mask), routes))
|
||||
assert.True(t, routesMayHaveMoved(request(unix.RTM_CHANGE, unix.RTF_UP, lan, mask), routes))
|
||||
assert.False(t, routesMayHaveMoved(request(unix.RTM_GET, unix.RTF_UP, lan, mask), routes))
|
||||
assert.False(t, routesMayHaveMoved(request(unix.RTM_DELETE, unix.RTF_UP|unix.RTF_IFSCOPE, lan, mask), routes), "a scoped route never held the prefix")
|
||||
assert.False(t, routesMayHaveMoved(request(unix.RTM_ADD, unix.RTF_UP|unix.RTF_IFSCOPE, lan, mask), routes), "configd adds a scoped copy for each interface")
|
||||
assert.False(t, routesMayHaveMoved(request(unix.RTM_DELETE, unix.RTF_UP, lan, [4]byte{255, 255, 0, 0}), routes), "only an exact prefix counts")
|
||||
assert.False(t, routesMayHaveMoved(request(unix.RTM_DELETE, unix.RTF_UP, lan, mask), []Route{{Cidr: cidr, Install: true}}), "a route with no via is never installed")
|
||||
assert.False(t, routesMayHaveMoved(request(unix.RTM_DELETE, unix.RTF_UP, lan, mask), []Route{{Cidr: cidr, Via: via}}), "install: false")
|
||||
|
||||
failed := request(unix.RTM_DELETE, unix.RTF_UP, lan, mask)
|
||||
binary.NativeEndian.PutUint32(failed[24:28], uint32(unix.ESRCH))
|
||||
assert.False(t, routesMayHaveMoved(failed, routes), "a failed request is echoed too")
|
||||
|
||||
_, err := netroute.ParseRIB(unix.NET_RT_DUMP, raw(kernelSubnetDelete))
|
||||
require.Error(t, err, "if x/net/route learns to parse these, match their prefix instead")
|
||||
assert.True(t, routesMayHaveMoved(raw(kernelSubnetDelete), routes), "the kernel's own deletes could be any prefix")
|
||||
neighbor := raw(kernelSubnetDelete)
|
||||
binary.NativeEndian.PutUint32(neighbor[8:12], unix.RTF_UP|unix.RTF_HOST|unix.RTF_LLINFO)
|
||||
assert.False(t, routesMayHaveMoved(neighbor, routes), "a neighbor expiring")
|
||||
|
||||
assert.True(t, routesMayHaveMoved(raw(addressRemoved), routes))
|
||||
assert.True(t, routesMayHaveMoved(raw(interfaceChanged), routes), "detaching an interface deletes its routes without a message for each")
|
||||
}
|
||||
|
||||
// A request names its prefix and who made it, the kernel's own and interface changes name neither
|
||||
func TestRoutesMayHaveMovedSaysWho(t *testing.T) {
|
||||
cidr := netip.MustParsePrefix("192.168.1.0/24")
|
||||
routes := []Route{{Cidr: cidr, Via: routing.Gateways{routing.NewGateway(netip.MustParseAddr("10.250.0.2"), 1)}, Install: true}}
|
||||
m := &netroute.RouteMessage{
|
||||
Version: unix.RTM_VERSION,
|
||||
Type: unix.RTM_CHANGE,
|
||||
Flags: unix.RTF_UP,
|
||||
ID: 1234,
|
||||
Addrs: []netroute.Addr{
|
||||
unix.RTAX_DST: &netroute.Inet4Addr{IP: [4]byte{192, 168, 1, 0}},
|
||||
unix.RTAX_GATEWAY: &netroute.LinkAddr{Index: 4},
|
||||
unix.RTAX_NETMASK: &netroute.Inet4Addr{IP: [4]byte{255, 255, 255, 0}},
|
||||
},
|
||||
}
|
||||
b, err := m.Marshal()
|
||||
require.NoError(t, err)
|
||||
moved, p, pid := routesMayHaveMoved(b, routes)
|
||||
assert.True(t, moved)
|
||||
assert.Equal(t, cidr, p)
|
||||
assert.Equal(t, int32(1234), pid)
|
||||
|
||||
for name, s := range map[string]string{"kernel": kernelSubnetDelete, "ifinfo": interfaceChanged} {
|
||||
b, err := hex.DecodeString(s)
|
||||
require.NoError(t, err)
|
||||
moved, p, pid := routesMayHaveMoved(b, routes)
|
||||
assert.True(t, moved, name)
|
||||
assert.False(t, p.IsValid(), name)
|
||||
assert.Zero(t, pid, name)
|
||||
}
|
||||
}
|
||||
|
||||
func TestProcessName(t *testing.T) {
|
||||
assert.Equal(t, "launchd", processName(1))
|
||||
self := filepath.Base(os.Args[0])
|
||||
assert.Equal(t, self[:min(len(self), 16)], processName(int32(os.Getpid())))
|
||||
assert.Empty(t, processName(-1))
|
||||
}
|
||||
|
||||
// newRouteTestTun is an activated tun for the root tests below with an unsafe_route for each of cidrs. sweep replaces
|
||||
// the minute between sweeps when it isn't zero.
|
||||
func newRouteTestTun(t *testing.T, sweep time.Duration, cidrs ...string) (*tun, *config.C, string) {
|
||||
requireRoot(t)
|
||||
|
||||
cfg := "tun:\n unsafe_routes:\n"
|
||||
for _, cidr := range cidrs {
|
||||
via := "10.250.0.2"
|
||||
if netip.MustParsePrefix(cidr).Addr().Is6() {
|
||||
via = "fd00:250::2"
|
||||
}
|
||||
cfg += " - route: " + cidr + "\n via: " + via + "\n"
|
||||
}
|
||||
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.LoadString(cfg))
|
||||
tn, err := newTun(c, l, []netip.Prefix{netip.MustParsePrefix("10.250.0.1/24"), netip.MustParsePrefix("fd00:250::1/64")}, false)
|
||||
require.NoError(t, err)
|
||||
if sweep != 0 {
|
||||
tn.routeSweepEvery = sweep
|
||||
}
|
||||
t.Cleanup(func() { _ = tn.Close() })
|
||||
require.NoError(t, tn.Activate())
|
||||
return tn, c, cfg
|
||||
}
|
||||
|
||||
func requireRoot(t *testing.T) {
|
||||
if os.Geteuid() != 0 {
|
||||
t.Skip("creating interfaces and adding routes needs root")
|
||||
}
|
||||
}
|
||||
|
||||
// routeVia is the index of the interface that routes cidr, 0 if none does
|
||||
func routeVia(t *testing.T, cidr string) int {
|
||||
msgs, err := fetchRoutes()
|
||||
require.NoError(t, err)
|
||||
return routeInterfaceIn(msgs, netip.MustParsePrefix(cidr))
|
||||
}
|
||||
|
||||
// routeStateOf is what tn made of cidr when it last looked
|
||||
func routeStateOf(tn *tun, cidr string) routeState {
|
||||
tn.routesMu.Lock()
|
||||
defer tn.routesMu.Unlock()
|
||||
return tn.routeStates[netip.MustParsePrefix(cidr)]
|
||||
}
|
||||
|
||||
func routeArgs(action, cidr string, extra ...string) []string {
|
||||
args := []string{"-q", "-n", action}
|
||||
if netip.MustParsePrefix(cidr).Addr().Is6() {
|
||||
args = append(args, "-inet6")
|
||||
}
|
||||
return append(append(args, "-net", cidr), extra...)
|
||||
}
|
||||
|
||||
func routeCmd(t *testing.T, action, cidr string, extra ...string) {
|
||||
requireRouteOK(t, exec.Command("route", routeArgs(action, cidr, extra...)...))
|
||||
}
|
||||
|
||||
// requireRouteOK runs cmd, which runs route(8). route exits 0 when the kernel rejects its request, only what it prints
|
||||
// says so
|
||||
func requireRouteOK(t *testing.T, cmd *exec.Cmd) {
|
||||
out, err := cmd.CombinedOutput()
|
||||
require.NoError(t, err, string(out))
|
||||
require.NotContains(t, string(out), "writing to routing socket")
|
||||
}
|
||||
|
||||
// cleanupRoute deletes cidr's route when the test ends, whoever holds it
|
||||
func cleanupRoute(t *testing.T, cidr string) {
|
||||
t.Cleanup(func() { _ = exec.Command("route", routeArgs("delete", cidr)...).Run() })
|
||||
}
|
||||
|
||||
// routeThroughLo0 routes cidr through lo0, like a lan nebula started on
|
||||
func routeThroughLo0(t *testing.T, cidr string) int {
|
||||
requireRoot(t)
|
||||
routeCmd(t, "add", cidr, "-interface", "lo0")
|
||||
cleanupRoute(t, cidr)
|
||||
lo0, err := net.InterfaceByName("lo0")
|
||||
require.NoError(t, err)
|
||||
return lo0.Index
|
||||
}
|
||||
|
||||
// Leaving the lan that held an unsafe_route's prefix must not need a restart to get the unsafe_route
|
||||
func TestTunAddsRouteOnceItsPrefixIsFree(t *testing.T) {
|
||||
for _, cidr := range []string{"10.251.0.0/24", "2001:db8:251::/64"} {
|
||||
t.Run(cidr, func(t *testing.T) {
|
||||
lo0 := routeThroughLo0(t, cidr)
|
||||
tn, _, _ := newRouteTestTun(t, 0, cidr)
|
||||
require.Equal(t, lo0, routeVia(t, cidr), "an existing route keeps its prefix")
|
||||
|
||||
routeCmd(t, "delete", cidr)
|
||||
assert.Eventually(t, func() bool { return routeVia(t, cidr) == tn.linkAddr.Load().Index }, 5*time.Second, 50*time.Millisecond)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// The kernel deletes a route by prefix alone, so dropping an unsafe_route someone else holds must not delete theirs
|
||||
func TestTunReloadLeavesRouteItYielded(t *testing.T) {
|
||||
cidr := "10.251.1.0/24"
|
||||
lo0 := routeThroughLo0(t, cidr)
|
||||
_, c, _ := newRouteTestTun(t, 0, cidr)
|
||||
|
||||
res := c.ReloadConfigString("tun: {}\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.Equal(t, lo0, routeVia(t, cidr))
|
||||
}
|
||||
|
||||
// configd takes a prefix by deleting the route holding it and adding its own. Ours goes back once theirs is removed
|
||||
func TestTunYieldsToARouteThatReplacesIt(t *testing.T) {
|
||||
cidr := "10.251.3.0/24"
|
||||
tn, _, _ := newRouteTestTun(t, 0, cidr)
|
||||
ours := tn.linkAddr.Load().Index
|
||||
require.Equal(t, ours, routeVia(t, cidr))
|
||||
|
||||
cleanupRoute(t, cidr)
|
||||
requireRouteOK(t, exec.Command("sh", "-c", "route -q -n delete -net "+cidr+" && route -q -n add -net "+cidr+" -interface lo0"))
|
||||
lo0, err := net.InterfaceByName("lo0")
|
||||
require.NoError(t, err)
|
||||
time.Sleep(2 * routeRetryDelay)
|
||||
require.Equal(t, lo0.Index, routeVia(t, cidr))
|
||||
|
||||
routeCmd(t, "delete", cidr)
|
||||
assert.Eventually(t, func() bool { return routeVia(t, cidr) == ours }, 5*time.Second, 50*time.Millisecond)
|
||||
}
|
||||
|
||||
// A route someone deleted, with nothing in its place, stays gone until a reload, so they can put their own there
|
||||
func TestTunLeavesRouteDeletedByHand(t *testing.T) {
|
||||
cidr := "10.251.4.0/24"
|
||||
tn, c, cfg := newRouteTestTun(t, 200*time.Millisecond, cidr)
|
||||
ours := tn.linkAddr.Load().Index
|
||||
require.Equal(t, ours, routeVia(t, cidr))
|
||||
|
||||
routeCmd(t, "delete", cidr)
|
||||
assert.Never(t, func() bool { return routeVia(t, cidr) != 0 }, 3*routeRetryDelay, 50*time.Millisecond)
|
||||
|
||||
// A reload with nothing changed is how to ask for it back
|
||||
res := c.ReloadConfigString(cfg)
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.Equal(t, ours, routeVia(t, cidr))
|
||||
}
|
||||
|
||||
// configd deleting ours and adding the lan's more than routeRetryDelay apart, or a sweep landing in between, looks like
|
||||
// a hand delete. Seeing the lan hold the prefix puts ours back in line, it goes back once theirs is removed
|
||||
func TestTunYieldsAfterLeavingARouteDeletedByHand(t *testing.T) {
|
||||
for name, tc := range map[string]struct {
|
||||
cidr string
|
||||
sweep time.Duration
|
||||
misfile func(t *testing.T, tn *tun, cidr string)
|
||||
}{
|
||||
// The table went quiet with nothing in its place. The minute sweep leaves noticing the lan's route to the watcher
|
||||
"settled": {"10.251.6.0/24", 0, func(t *testing.T, tn *tun, cidr string) {
|
||||
require.Eventually(t, func() bool { return routeStateOf(tn, cidr).kind == routeRemoved }, 5*time.Second, 50*time.Millisecond)
|
||||
}},
|
||||
// The sweep that caps a table that never settles
|
||||
"swept": {"10.251.7.0/24", 200 * time.Millisecond, func(t *testing.T, tn *tun, cidr string) {
|
||||
tn.reconcileRoutes()
|
||||
require.Equal(t, routeRemoved, routeStateOf(tn, cidr).kind)
|
||||
}},
|
||||
} {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
tn, _, _ := newRouteTestTun(t, tc.sweep, tc.cidr)
|
||||
ours := tn.linkAddr.Load().Index
|
||||
require.Equal(t, ours, routeVia(t, tc.cidr))
|
||||
|
||||
routeCmd(t, "delete", tc.cidr)
|
||||
tc.misfile(t, tn, tc.cidr)
|
||||
|
||||
lo0 := routeThroughLo0(t, tc.cidr)
|
||||
require.Eventually(t, func() bool {
|
||||
s := routeStateOf(tn, tc.cidr)
|
||||
return s.kind == routeYielded && s.holder == lo0
|
||||
}, 5*time.Second, 50*time.Millisecond)
|
||||
|
||||
routeCmd(t, "delete", tc.cidr)
|
||||
assert.Eventually(t, func() bool { return routeVia(t, tc.cidr) == ours }, 5*time.Second, 50*time.Millisecond)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Changing our route to another interface hands it the prefix, ours goes back once theirs is removed rather than being
|
||||
// taken for a hand delete
|
||||
func TestTunYieldsToARouteChangedAway(t *testing.T) {
|
||||
for _, cidr := range []string{"10.251.8.0/24", "2001:db8:258::/64"} {
|
||||
t.Run(cidr, func(t *testing.T) {
|
||||
tn, _, _ := newRouteTestTun(t, 0, cidr)
|
||||
ours := tn.linkAddr.Load().Index
|
||||
require.Equal(t, ours, routeVia(t, cidr))
|
||||
|
||||
cleanupRoute(t, cidr)
|
||||
routeCmd(t, "change", cidr, "-interface", "lo0")
|
||||
lo0, err := net.InterfaceByName("lo0")
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, lo0.Index, routeVia(t, cidr))
|
||||
require.Eventually(t, func() bool {
|
||||
s := routeStateOf(tn, cidr)
|
||||
return s.kind == routeYielded && s.holder == lo0.Index
|
||||
}, 5*time.Second, 50*time.Millisecond)
|
||||
|
||||
routeCmd(t, "delete", cidr)
|
||||
assert.Eventually(t, func() bool { return routeVia(t, cidr) == ours }, 5*time.Second, 50*time.Millisecond)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Detaching an interface deletes its routes without a routing socket message for each, like unplugging the dock whose
|
||||
// ethernet configd routed the lan through
|
||||
func TestTunAddsRouteWhenItsInterfaceDetaches(t *testing.T) {
|
||||
requireRoot(t)
|
||||
var feth string
|
||||
for i := 100; i < 200 && feth == ""; i++ {
|
||||
if _, err := net.InterfaceByName(fmt.Sprintf("feth%d", i)); err != nil {
|
||||
feth = fmt.Sprintf("feth%d", i)
|
||||
}
|
||||
}
|
||||
require.NotEmpty(t, feth)
|
||||
require.NoError(t, exec.Command("ifconfig", feth, "create").Run())
|
||||
t.Cleanup(func() { _ = exec.Command("ifconfig", feth, "destroy").Run() })
|
||||
require.NoError(t, exec.Command("ifconfig", feth, "inet", "198.51.100.5/24", "up").Run())
|
||||
|
||||
// Static and cloning with no gateway, like the lan routes configd installs. Named by the feth's address, macOS 27
|
||||
// refuses one named by the feth itself
|
||||
cidr := "10.251.2.0/24"
|
||||
routeCmd(t, "add", cidr, "-interface", "198.51.100.5")
|
||||
cleanupRoute(t, cidr)
|
||||
ifc, err := net.InterfaceByName(feth)
|
||||
require.NoError(t, err)
|
||||
|
||||
tn, _, _ := newRouteTestTun(t, 0, cidr)
|
||||
require.Equal(t, ifc.Index, routeVia(t, cidr))
|
||||
|
||||
// Losing the address first leaves the route, the reconcile finds it still held
|
||||
require.NoError(t, exec.Command("ifconfig", feth, "inet", "198.51.100.5", "-alias").Run())
|
||||
time.Sleep(2 * routeRetryDelay)
|
||||
require.Equal(t, ifc.Index, routeVia(t, cidr))
|
||||
|
||||
// Only RTM_IFINFO says the interface went, its route goes with no message of its own
|
||||
require.NoError(t, exec.Command("ifconfig", feth, "destroy").Run())
|
||||
assert.Eventually(t, func() bool { return routeVia(t, cidr) == tn.linkAddr.Load().Index }, 5*time.Second, 50*time.Millisecond)
|
||||
}
|
||||
|
||||
// The routing socket drops what doesn't fit its buffer without a word, the sweep finds what it missed
|
||||
func TestTunSweepAddsRouteTheWatcherMissed(t *testing.T) {
|
||||
cidr := "10.251.5.0/24"
|
||||
routeThroughLo0(t, cidr)
|
||||
tn, _, _ := newRouteTestTun(t, 200*time.Millisecond, cidr)
|
||||
|
||||
tn.routesMu.Lock()
|
||||
require.NoError(t, tn.routeWatch.Close())
|
||||
tn.routesMu.Unlock()
|
||||
|
||||
routeCmd(t, "delete", cidr)
|
||||
assert.Eventually(t, func() bool { return routeVia(t, cidr) == tn.linkAddr.Load().Index }, 5*time.Second, 50*time.Millisecond)
|
||||
}
|
||||
|
||||
// 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{
|
||||
|
||||
@@ -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)
|
||||
}
|
||||
@@ -832,11 +832,6 @@ func (t *tun) updateRoutes(r netlink.RouteUpdate) {
|
||||
t.routeTree.Store(newTree)
|
||||
}
|
||||
|
||||
// Shutdown wakes the tun readers without releasing their fds, Close releases them
|
||||
func (t *tun) Shutdown() error {
|
||||
return t.readers.Shutdown()
|
||||
}
|
||||
|
||||
func (t *tun) Close() error {
|
||||
t.closeLock.Lock()
|
||||
defer t.closeLock.Unlock()
|
||||
|
||||
@@ -1,451 +0,0 @@
|
||||
//go:build !ios && !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"net"
|
||||
"net/netip"
|
||||
"os"
|
||||
"strconv"
|
||||
"sync/atomic"
|
||||
"time"
|
||||
"unsafe"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/util"
|
||||
netroute "golang.org/x/net/route"
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// Darwin has no route metrics, the routing table holds one unscoped route per prefix. When another interface already
|
||||
// routes an unsafe_route's prefix, like the lan we started on, theirs stays and ours is added once theirs is removed.
|
||||
// Our own route removed by someone else, with nothing in its place, was removed on purpose and stays gone until a reload
|
||||
// or until another interface takes the prefix, after which ours follows theirs like any other.
|
||||
|
||||
const (
|
||||
// routeRetryDelay is how long the system routing table must be quiet before we judge who holds a prefix. configd
|
||||
// replaces a route by deleting and adding, looking in between would find the prefix free
|
||||
routeRetryDelay = time.Second
|
||||
|
||||
// routeSweepInterval bounds how long a freed unsafe_route can go unnoticed. The routing socket drops messages that
|
||||
// don't fit its receive buffer without telling the reader, and detaching an interface deletes its routes without
|
||||
// a message for each
|
||||
routeSweepInterval = time.Minute
|
||||
|
||||
// routeSocketRcvBuf is well past the 8KiB default, which a burst of neighbor routes expiring can fill
|
||||
routeSocketRcvBuf = 1 << 20
|
||||
)
|
||||
|
||||
type routeStateKind int
|
||||
|
||||
const (
|
||||
routeUnknown routeStateKind = iota
|
||||
// routeInstalled is our route holding the prefix
|
||||
routeInstalled
|
||||
// routeYielded is another interface holding the prefix, ours is added once it lets go
|
||||
routeYielded
|
||||
// routeRemoved is our route deleted by someone else with nothing in its place, it is left alone until a reload or
|
||||
// another interface takes the prefix
|
||||
routeRemoved
|
||||
// routeFailed is adding our route failing for some other reason, it is retried
|
||||
routeFailed
|
||||
)
|
||||
|
||||
type routeState struct {
|
||||
kind routeStateKind
|
||||
// holder is the index of the interface holding the prefix when kind is routeYielded
|
||||
holder int
|
||||
}
|
||||
|
||||
// routeMover is the process that last added, changed or deleted a route for an unsafe_route's prefix, for logs. Its name
|
||||
// is looked up as the message arrives, route(8) has exited by the time the table settles
|
||||
type routeMover struct {
|
||||
pid int32
|
||||
name string
|
||||
}
|
||||
|
||||
// logArgs appends m to a log line's args, when we know who it was
|
||||
func (m routeMover) logArgs(args ...any) []any {
|
||||
if m.pid == 0 {
|
||||
return args
|
||||
}
|
||||
args = append(args, "pid", m.pid)
|
||||
if m.name != "" {
|
||||
args = append(args, "process", m.name)
|
||||
}
|
||||
return args
|
||||
}
|
||||
|
||||
// processName is the name of process pid, truncated to 16 bytes, or empty when it has already exited
|
||||
func processName(pid int32) string {
|
||||
kp, err := unix.SysctlKinfoProc("kern.proc.pid", int(pid))
|
||||
if err != nil || kp.Proc.P_pid != pid {
|
||||
return ""
|
||||
}
|
||||
return unix.ByteSliceToString(kp.Proc.P_comm[:])
|
||||
}
|
||||
|
||||
// installRoutes returns the routes we put in the system routing table, one per prefix
|
||||
func installRoutes(routes []Route) []Route {
|
||||
seen := make(map[netip.Prefix]struct{}, len(routes))
|
||||
var out []Route
|
||||
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
|
||||
}
|
||||
p := r.Cidr.Masked()
|
||||
if _, ok := seen[p]; ok {
|
||||
continue
|
||||
}
|
||||
seen[p] = struct{}{}
|
||||
out = append(out, r)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// addRoutes puts every unsafe_route in the system routing table, including ones someone deleted, unless another
|
||||
// interface holds its prefix. It runs on start and on every reload.
|
||||
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
// The route tree is still ours, the system routing table is not
|
||||
if t.hostOwned {
|
||||
return nil
|
||||
}
|
||||
|
||||
t.routesMu.Lock()
|
||||
defer t.routesMu.Unlock()
|
||||
|
||||
// Activate hasn't run yet, it will install the routes
|
||||
linkAddr := t.linkAddr.Load()
|
||||
if linkAddr == nil || t.closed {
|
||||
return nil
|
||||
}
|
||||
|
||||
var msgs []netroute.Message
|
||||
var msgsErr error
|
||||
fetched := false
|
||||
states := make(map[netip.Prefix]routeState)
|
||||
for _, r := range installRoutes(*t.Routes.Load()) {
|
||||
p := r.Cidr.Masked()
|
||||
prev := t.routeStates[p]
|
||||
|
||||
err := addRoute(p, linkAddr)
|
||||
if err == nil {
|
||||
t.l.Info("Added route", "route", r)
|
||||
states[p] = routeState{kind: routeInstalled}
|
||||
continue
|
||||
}
|
||||
|
||||
if !errors.Is(err, unix.EEXIST) {
|
||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||
if !logErrors {
|
||||
return retErr
|
||||
}
|
||||
retErr.Log(t.l)
|
||||
rl.Failed()
|
||||
states[p] = routeState{kind: routeFailed}
|
||||
continue
|
||||
}
|
||||
|
||||
// Every route we added already exists on a reload, only warn about someone else's
|
||||
if !fetched {
|
||||
msgs, msgsErr = fetchRoutes()
|
||||
fetched = true
|
||||
}
|
||||
if msgsErr != nil {
|
||||
t.l.Warn("unable to add unsafe_route, a route already exists but its interface could not be determined", "route", r.Cidr, "error", msgsErr)
|
||||
states[p] = prev
|
||||
continue
|
||||
}
|
||||
|
||||
switch holder := routeInterfaceIn(msgs, p); holder {
|
||||
case linkAddr.Index:
|
||||
states[p] = routeState{kind: routeInstalled}
|
||||
case 0:
|
||||
// Removed since the add, the watcher will see to it
|
||||
states[p] = prev
|
||||
default:
|
||||
if prev.kind != routeYielded || prev.holder != holder {
|
||||
t.l.Warn("unable to add unsafe_route, the destination is already routed through another interface, it will be added once that route is removed", "route", r.Cidr, "interface", interfaceName(holder))
|
||||
}
|
||||
states[p] = routeState{kind: routeYielded, holder: holder}
|
||||
}
|
||||
}
|
||||
|
||||
t.routeStates = states
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
if t.hostOwned {
|
||||
return nil
|
||||
}
|
||||
|
||||
t.routesMu.Lock()
|
||||
defer t.routesMu.Unlock()
|
||||
|
||||
linkAddr := t.linkAddr.Load()
|
||||
if linkAddr == nil || t.closed {
|
||||
return nil
|
||||
}
|
||||
|
||||
// The kernel deletes a route by its prefix alone, whichever interface holds it. Only delete the ones that are ours
|
||||
msgs, err := fetchRoutes()
|
||||
if err != nil {
|
||||
var left []netip.Prefix
|
||||
for _, r := range installRoutes(routes) {
|
||||
left = append(left, r.Cidr)
|
||||
}
|
||||
return fmt.Errorf("failed to read the system routing table, leaving routes %v installed: %w", left, err)
|
||||
}
|
||||
|
||||
for _, r := range installRoutes(routes) {
|
||||
p := r.Cidr.Masked()
|
||||
// Whatever happens next, the prefix is no longer one we know about
|
||||
delete(t.routeStates, p)
|
||||
if routeInterfaceIn(msgs, p) != linkAddr.Index {
|
||||
continue
|
||||
}
|
||||
|
||||
err = delRoute(p, 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 {
|
||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||
rl.Failed()
|
||||
} else {
|
||||
t.l.Info("Removed route", "route", r)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// reconcileRoutes brings the unsafe_routes in line with who holds their prefix now. It is quiet unless something
|
||||
// changed since it last looked, it runs every routeSweepEvery.
|
||||
func (t *tun) reconcileRoutes() {
|
||||
t.routesMu.Lock()
|
||||
defer t.routesMu.Unlock()
|
||||
|
||||
linkAddr := t.linkAddr.Load()
|
||||
if linkAddr == nil || t.closed {
|
||||
return
|
||||
}
|
||||
|
||||
t.routeMoversMu.Lock()
|
||||
movers := t.routeMovers
|
||||
t.routeMovers = nil
|
||||
t.routeMoversMu.Unlock()
|
||||
|
||||
msgs, err := fetchRoutes()
|
||||
if err != nil {
|
||||
t.l.Error("Failed to read the system routing table", "error", err)
|
||||
return
|
||||
}
|
||||
|
||||
states := make(map[netip.Prefix]routeState)
|
||||
for _, r := range installRoutes(*t.Routes.Load()) {
|
||||
p := r.Cidr.Masked()
|
||||
prev := t.routeStates[p]
|
||||
by := movers[p]
|
||||
|
||||
holder := routeInterfaceIn(msgs, p)
|
||||
switch {
|
||||
case holder == linkAddr.Index:
|
||||
states[p] = routeState{kind: routeInstalled}
|
||||
|
||||
case holder != 0:
|
||||
// Another interface taking a prefix we left alone puts ours back in line behind theirs
|
||||
if prev.kind != routeYielded || prev.holder != holder {
|
||||
t.l.Info("unsafe_route is routed through another interface, it will be added back when that route is removed", by.logArgs("route", r.Cidr, "interface", interfaceName(holder))...)
|
||||
}
|
||||
states[p] = routeState{kind: routeYielded, holder: holder}
|
||||
|
||||
case prev.kind == routeInstalled:
|
||||
t.l.Warn("unsafe_route was removed outside nebula, leaving it until a reload or another interface takes its destination", by.logArgs("route", r.Cidr)...)
|
||||
states[p] = routeState{kind: routeRemoved}
|
||||
|
||||
case prev.kind == routeRemoved:
|
||||
states[p] = prev
|
||||
|
||||
default:
|
||||
err := addRoute(p, linkAddr)
|
||||
switch {
|
||||
case err == nil:
|
||||
if prev.kind == routeYielded {
|
||||
t.l.Info("unsafe_route's destination is free again, added it", by.logArgs("route", r)...)
|
||||
} else {
|
||||
t.l.Info("Added route", "route", r)
|
||||
}
|
||||
states[p] = routeState{kind: routeInstalled}
|
||||
case errors.Is(err, unix.EEXIST):
|
||||
// Taken since the fetch, the next look will see by whom
|
||||
states[p] = prev
|
||||
default:
|
||||
if prev.kind != routeFailed {
|
||||
util.NewContextualError("Failed to add route", map[string]any{"route": r}, err).Log(t.l)
|
||||
}
|
||||
states[p] = routeState{kind: routeFailed}
|
||||
}
|
||||
}
|
||||
}
|
||||
t.routeStates = states
|
||||
}
|
||||
|
||||
// startRouteWatch starts reconciling the unsafe_routes, every routeSweepEvery and, when watch isn't nil, once the
|
||||
// routing table settles after anything that may have moved a prefix
|
||||
func (t *tun) startRouteWatch(watch *os.File) {
|
||||
t.routesMu.Lock()
|
||||
defer t.routesMu.Unlock()
|
||||
if t.closed {
|
||||
if watch != nil {
|
||||
_ = watch.Close()
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
t.routeSweep = time.AfterFunc(t.routeSweepEvery, t.sweepRoutes)
|
||||
if watch != nil {
|
||||
t.routeWatch = watch
|
||||
go t.watchRoutes(watch)
|
||||
}
|
||||
}
|
||||
|
||||
func (t *tun) sweepRoutes() {
|
||||
// A table still changing gets reconciled once it settles
|
||||
if time.Since(time.Unix(0, t.lastRouteEvent.Load())) >= routeRetryDelay {
|
||||
t.reconcileRoutes()
|
||||
}
|
||||
|
||||
t.routesMu.Lock()
|
||||
defer t.routesMu.Unlock()
|
||||
if !t.closed {
|
||||
t.routeSweep.Reset(t.routeSweepEvery)
|
||||
}
|
||||
}
|
||||
|
||||
func openRouteSocket() (*os.File, error) {
|
||||
fd, err := unix.Socket(unix.AF_ROUTE, unix.SOCK_RAW, unix.AF_UNSPEC)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("unable to create AF_ROUTE socket: %w", err)
|
||||
}
|
||||
// Fewer drops, the sweep catches the rest
|
||||
_ = unix.SetsockoptInt(fd, unix.SOL_SOCKET, unix.SO_RCVBUF, routeSocketRcvBuf)
|
||||
// Non-blocking puts it on the poller, so Close interrupts a Read
|
||||
if err = unix.SetNonblock(fd, true); err != nil {
|
||||
_ = unix.Close(fd)
|
||||
return nil, fmt.Errorf("failed to set the AF_ROUTE socket to non-blocking mode: %w", err)
|
||||
}
|
||||
return os.NewFile(uintptr(fd), "route"), nil
|
||||
}
|
||||
|
||||
// watchRoutes reconciles the unsafe_routes once the routing table has been quiet for routeRetryDelay after a message
|
||||
// that may have moved a prefix. A table that keeps changing is reconciled every routeSweepEvery regardless.
|
||||
func (t *tun) watchRoutes(f *os.File) {
|
||||
var reconciled atomic.Int64
|
||||
settle := time.AfterFunc(time.Hour, func() {
|
||||
reconciled.Store(time.Now().UnixNano())
|
||||
t.reconcileRoutes()
|
||||
})
|
||||
settle.Stop()
|
||||
defer settle.Stop()
|
||||
|
||||
var burst time.Time
|
||||
self := int32(os.Getpid())
|
||||
b := make([]byte, os.Getpagesize())
|
||||
for {
|
||||
n, err := f.Read(b)
|
||||
if err != nil {
|
||||
if !errors.Is(err, os.ErrClosed) {
|
||||
t.l.Error("Stopped watching the system routing table, unsafe_routes held by another interface are only retried every minute", "error", err)
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
moved, p, pid := routesMayHaveMoved(b[:n], *t.Routes.Load())
|
||||
if !moved {
|
||||
continue
|
||||
}
|
||||
// Our own are already in routeStates
|
||||
if p.IsValid() && pid != self {
|
||||
t.routeMoversMu.Lock()
|
||||
if t.routeMovers == nil {
|
||||
t.routeMovers = make(map[netip.Prefix]routeMover)
|
||||
}
|
||||
t.routeMovers[p] = routeMover{pid: pid, name: processName(pid)}
|
||||
t.routeMoversMu.Unlock()
|
||||
}
|
||||
|
||||
now := time.Now()
|
||||
t.lastRouteEvent.Store(now.UnixNano())
|
||||
if burst.IsZero() || reconciled.Load() >= burst.UnixNano() {
|
||||
burst = now
|
||||
}
|
||||
settle.Reset(max(0, min(routeRetryDelay, time.Until(burst.Add(t.routeSweepEvery)))))
|
||||
}
|
||||
}
|
||||
|
||||
// routesMayHaveMoved reports whether b, one routing socket message, may have freed a prefix one of routes installs or
|
||||
// handed it to another interface. That's a route for it added, changed or removed, or an interface that lost an address
|
||||
// or changed state, since detaching an interface deletes its routes without a message of their own. The header is read
|
||||
// directly, x/net/route skips the RTM_IFINFO the socket sends, which has no interface address, and misreads the
|
||||
// unpadded sockaddrs in messages the kernel makes itself. A request naming one of the prefixes also returns that prefix
|
||||
// and the pid of the process that made it.
|
||||
func routesMayHaveMoved(b []byte, routes []Route) (moved bool, p netip.Prefix, pid int32) {
|
||||
if len(b) < 4 {
|
||||
return false, p, 0
|
||||
}
|
||||
switch int(b[3]) {
|
||||
case unix.RTM_IFINFO, unix.RTM_DELADDR:
|
||||
return true, p, 0
|
||||
case unix.RTM_ADD, unix.RTM_CHANGE, unix.RTM_DELETE:
|
||||
default:
|
||||
return false, p, 0
|
||||
}
|
||||
|
||||
if len(b) < unix.SizeofRtMsghdr {
|
||||
return false, p, 0
|
||||
}
|
||||
hdr := (*unix.RtMsghdr)(unsafe.Pointer(&b[0]))
|
||||
// A failed request is reported too, and a scoped route never held the prefix
|
||||
if hdr.Errno != 0 || hdr.Flags&unix.RTF_IFSCOPE != 0 {
|
||||
return false, p, 0
|
||||
}
|
||||
|
||||
if hdr.Pid == 0 {
|
||||
// The kernel's own, which x/net/route can't parse. Neighbors coming and going are host routes, anything else
|
||||
// could be holding a prefix
|
||||
return hdr.Flags&(unix.RTF_HOST|unix.RTF_LLINFO) == 0, p, 0
|
||||
}
|
||||
|
||||
// Replies to a request carry the requester's padded sockaddrs
|
||||
msgs, err := netroute.ParseRIB(unix.NET_RT_DUMP, b)
|
||||
if err != nil || len(msgs) != 1 {
|
||||
return false, p, 0
|
||||
}
|
||||
m, ok := msgs[0].(*netroute.RouteMessage)
|
||||
if !ok || len(m.Addrs) <= unix.RTAX_NETMASK {
|
||||
return false, p, 0
|
||||
}
|
||||
p, ok = routePrefix(m.Addrs[unix.RTAX_DST], m.Addrs[unix.RTAX_NETMASK])
|
||||
if !ok {
|
||||
return false, netip.Prefix{}, 0
|
||||
}
|
||||
p = p.Masked()
|
||||
for _, r := range installRoutes(routes) {
|
||||
if r.Cidr.Masked() == p {
|
||||
return true, p, hdr.Pid
|
||||
}
|
||||
}
|
||||
return false, netip.Prefix{}, 0
|
||||
}
|
||||
|
||||
// interfaceName is the name of the interface with index i, for logs
|
||||
func interfaceName(i int) string {
|
||||
if ifc, err := net.InterfaceByIndex(i); err == nil {
|
||||
return ifc.Name
|
||||
}
|
||||
return strconv.Itoa(i)
|
||||
}
|
||||
@@ -528,10 +528,6 @@ func (rm *relayManager) handleCreateRelayRequest(v cert.Version, h *HostInfo, f
|
||||
if !rm.GetAmRelay() {
|
||||
return
|
||||
}
|
||||
if !slices.Contains(h.vpnAddrs, from) {
|
||||
logMsg.Info("Discarding relay request where relayFrom is not the sending peer")
|
||||
return
|
||||
}
|
||||
peer := rm.hostmap.QueryVpnAddr(target)
|
||||
if peer == nil {
|
||||
// Try to establish a connection to this host. If we get a future relay request,
|
||||
|
||||
@@ -7,10 +7,8 @@ import (
|
||||
"testing"
|
||||
|
||||
"github.com/gaissmai/bart"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// TestStartRelaysLogDedupe verifies that repeated attempts with the same relay set drop the log
|
||||
@@ -97,58 +95,3 @@ func TestStartRelaysLogDedupe(t *testing.T) {
|
||||
assert.NotContains(t, buf.String(), msg, "should not log when we shortcut out")
|
||||
})
|
||||
}
|
||||
|
||||
// TestHandleCreateRelayRequestRejectsSpoofedFrom verifies that a relay only forwards a CreateRelayRequest
|
||||
// when relayFrom is the peer that sent it. Otherwise any peer could reset another host's established
|
||||
// relay back to Requested, or allocate unbounded relay entries on the target's hostinfo.
|
||||
func TestHandleCreateRelayRequestRejectsSpoofedFrom(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
relayAddr := netip.MustParseAddr("10.128.0.128")
|
||||
malloryAddr := netip.MustParseAddr("10.128.0.3")
|
||||
victimAddr := netip.MustParseAddr("10.128.0.1")
|
||||
targetAddr := netip.MustParseAddr("10.128.0.2")
|
||||
|
||||
addrTable := new(bart.Lite)
|
||||
addrTable.Insert(netip.PrefixFrom(relayAddr, relayAddr.BitLen()))
|
||||
hm := newHostMap(l)
|
||||
f := &Interface{myVpnAddrsTable: addrTable, hostMap: hm}
|
||||
rm := &relayManager{l: l, hostmap: hm}
|
||||
rm.amRelay.Store(true)
|
||||
|
||||
newRelayState := func() RelayState {
|
||||
return RelayState{relayForByAddr: map[netip.Addr]*Relay{}, relayForByIdx: map[uint32]*Relay{}}
|
||||
}
|
||||
mallory := &HostInfo{vpnAddrs: []netip.Addr{malloryAddr}, localIndexId: 1, relayState: newRelayState()}
|
||||
target := &HostInfo{
|
||||
vpnAddrs: []netip.Addr{targetAddr},
|
||||
localIndexId: 2,
|
||||
remotes: NewRemoteList([]netip.Addr{targetAddr}, nil),
|
||||
relayState: newRelayState(),
|
||||
}
|
||||
target.SetRemote(netip.MustParseAddrPort("192.0.2.2:4242"))
|
||||
hm.unlockedAddHostInfo(mallory, f)
|
||||
hm.unlockedAddHostInfo(target, f)
|
||||
|
||||
// The victim already has a working relay to the target through us.
|
||||
_, err := AddRelay(l, target, hm, victimAddr, nil, ForwardingType, Established)
|
||||
require.NoError(t, err)
|
||||
relaysBefore := len(hm.Relays)
|
||||
|
||||
for i := range 10 {
|
||||
spoofed := netip.AddrFrom4([4]byte{10, 128, 1, byte(i)})
|
||||
for _, from := range []netip.Addr{victimAddr, spoofed} {
|
||||
rm.handleCreateRelayRequest(cert.Version2, mallory, f, &NebulaControl{
|
||||
Type: NebulaControl_CreateRelayRequest,
|
||||
InitiatorRelayIndex: uint32(100 + i),
|
||||
RelayFromAddr: netAddrToProtoAddr(from),
|
||||
RelayToAddr: netAddrToProtoAddr(targetAddr),
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
r, ok := target.relayState.QueryRelayForByIp(victimAddr)
|
||||
require.True(t, ok)
|
||||
assert.Equal(t, Established, r.State, "victim's relay must not be reset by a request from another peer")
|
||||
assert.Len(t, hm.Relays, relaysBefore, "spoofed requests must not allocate relay entries")
|
||||
assert.Empty(t, mallory.relayState.CopyAllRelayFor(), "spoofed requests must not create state on the sender")
|
||||
}
|
||||
+19
-124
@@ -2,7 +2,6 @@ package nebula
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
@@ -59,8 +58,6 @@ type cacheV6 struct {
|
||||
type hostnamePort struct {
|
||||
name string
|
||||
port uint16
|
||||
// addr is set when name is an ip literal, these never need a lookup
|
||||
addr netip.Addr
|
||||
}
|
||||
|
||||
type hostnamesResults struct {
|
||||
@@ -68,20 +65,15 @@ type hostnamesResults struct {
|
||||
network string
|
||||
lookupTimeout time.Duration
|
||||
cancelFn func()
|
||||
resolveNow chan struct{}
|
||||
l *slog.Logger
|
||||
ips atomic.Pointer[map[netip.AddrPort]struct{}]
|
||||
// known is the last known good addresses per hostname, kept so a reload can carry them forward
|
||||
known atomic.Pointer[map[hostnamePort][]netip.AddrPort]
|
||||
}
|
||||
|
||||
// NewHostnameResults starts resolving hostPorts. Any hostnames also in prev start with its last known good addresses.
|
||||
func NewHostnameResults(ctx context.Context, l *slog.Logger, d time.Duration, network string, timeout time.Duration, hostPorts []string, prev *hostnamesResults, onUpdate func()) (*hostnamesResults, error) {
|
||||
func NewHostnameResults(ctx context.Context, l *slog.Logger, d time.Duration, network string, timeout time.Duration, hostPorts []string, onUpdate func()) (*hostnamesResults, error) {
|
||||
r := &hostnamesResults{
|
||||
hostnames: make([]hostnamePort, len(hostPorts)),
|
||||
network: network,
|
||||
lookupTimeout: timeout,
|
||||
resolveNow: make(chan struct{}, 1),
|
||||
l: l,
|
||||
}
|
||||
|
||||
@@ -89,13 +81,6 @@ func NewHostnameResults(ctx context.Context, l *slog.Logger, d time.Duration, ne
|
||||
// DNS lookups for hostnames that aren't hardcoded IP's will happen in a background goroutine.
|
||||
performBackgroundLookup := false
|
||||
ips := map[netip.AddrPort]struct{}{}
|
||||
known := make([][]netip.AddrPort, len(hostPorts))
|
||||
var prevKnown map[hostnamePort][]netip.AddrPort
|
||||
if prev != nil && prev.network == network {
|
||||
if p := prev.known.Load(); p != nil {
|
||||
prevKnown = *p
|
||||
}
|
||||
}
|
||||
for idx, hostPort := range hostPorts {
|
||||
|
||||
rIp, sPort, err := net.SplitHostPort(hostPort)
|
||||
@@ -113,19 +98,13 @@ func NewHostnameResults(ctx context.Context, l *slog.Logger, d time.Duration, ne
|
||||
if err != nil {
|
||||
// This address is a hostname, not an IP address
|
||||
performBackgroundLookup = true
|
||||
known[idx] = prevKnown[r.hostnames[idx]]
|
||||
for _, a := range known[idx] {
|
||||
ips[a] = struct{}{}
|
||||
}
|
||||
continue
|
||||
}
|
||||
|
||||
// Save the IP address immediately
|
||||
r.hostnames[idx].addr = addr
|
||||
ips[netip.AddrPortFrom(addr, uint16(iPort))] = struct{}{}
|
||||
}
|
||||
r.ips.Store(&ips)
|
||||
r.storeKnown(known)
|
||||
|
||||
// Time for the DNS lookup goroutine
|
||||
if performBackgroundLookup {
|
||||
@@ -135,12 +114,21 @@ func NewHostnameResults(ctx context.Context, l *slog.Logger, d time.Duration, ne
|
||||
go func() {
|
||||
defer ticker.Stop()
|
||||
for {
|
||||
r.resolve(newCtx, known)
|
||||
r.storeKnown(known)
|
||||
netipAddrs := map[netip.AddrPort]struct{}{}
|
||||
for _, addrs := range known {
|
||||
for _, hostPort := range r.hostnames {
|
||||
timeoutCtx, timeoutCancel := context.WithTimeout(ctx, r.lookupTimeout)
|
||||
addrs, err := net.DefaultResolver.LookupNetIP(timeoutCtx, r.network, hostPort.name)
|
||||
timeoutCancel()
|
||||
if err != nil {
|
||||
l.Error("DNS resolution failed for static_map host",
|
||||
"hostname", hostPort.name,
|
||||
"network", r.network,
|
||||
"error", err,
|
||||
)
|
||||
continue
|
||||
}
|
||||
for _, a := range addrs {
|
||||
netipAddrs[a] = struct{}{}
|
||||
netipAddrs[netip.AddrPortFrom(a.Unmap(), hostPort.port)] = struct{}{}
|
||||
}
|
||||
}
|
||||
origSet := r.ips.Load()
|
||||
@@ -171,7 +159,7 @@ func NewHostnameResults(ctx context.Context, l *slog.Logger, d time.Duration, ne
|
||||
case <-newCtx.Done():
|
||||
return
|
||||
case <-ticker.C:
|
||||
case <-r.resolveNow:
|
||||
continue
|
||||
}
|
||||
}
|
||||
}()
|
||||
@@ -180,84 +168,6 @@ func NewHostnameResults(ctx context.Context, l *slog.Logger, d time.Duration, ne
|
||||
return r, nil
|
||||
}
|
||||
|
||||
// resolve looks up every hostname in parallel and folds the results into known
|
||||
func (hr *hostnamesResults) resolve(ctx context.Context, known [][]netip.AddrPort) {
|
||||
var wg sync.WaitGroup
|
||||
for i, hostPort := range hr.hostnames {
|
||||
if hostPort.addr.IsValid() {
|
||||
known[i] = []netip.AddrPort{netip.AddrPortFrom(hostPort.addr, hostPort.port)}
|
||||
continue
|
||||
}
|
||||
|
||||
wg.Go(func() {
|
||||
timeoutCtx, timeoutCancel := context.WithTimeout(ctx, hr.lookupTimeout)
|
||||
addrs, err := net.DefaultResolver.LookupNetIP(timeoutCtx, hr.network, hostPort.name)
|
||||
timeoutCancel()
|
||||
known[i] = applyLookup(known[i], hostPort.port, addrs, err)
|
||||
// A canceled ctx means we are reloading or shutting down, not that DNS failed
|
||||
if err != nil && ctx.Err() == nil {
|
||||
hr.l.Error("DNS resolution failed for static_map host",
|
||||
"hostname", hostPort.name,
|
||||
"network", hr.network,
|
||||
"error", err,
|
||||
"usingAddrs", known[i],
|
||||
)
|
||||
}
|
||||
})
|
||||
}
|
||||
wg.Wait()
|
||||
}
|
||||
|
||||
// applyLookup returns the addresses to use for a hostname given the previous ones and a lookup result.
|
||||
// Only a not found answer clears them, a stale lighthouse address costs a handshake but an empty set costs everything.
|
||||
// darwin also reports not found while offline, that's harmless since nothing is reachable and the next handshake
|
||||
// triggers a fresh lookup once we're back.
|
||||
func applyLookup(prev []netip.AddrPort, port uint16, addrs []netip.Addr, err error) []netip.AddrPort {
|
||||
if err != nil {
|
||||
var dnsErr *net.DNSError
|
||||
if errors.As(err, &dnsErr) && dnsErr.IsNotFound {
|
||||
return nil
|
||||
}
|
||||
return prev
|
||||
}
|
||||
|
||||
out := make([]netip.AddrPort, 0, len(addrs))
|
||||
for _, a := range addrs {
|
||||
out = append(out, netip.AddrPortFrom(a.Unmap(), port))
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func (hr *hostnamesResults) storeKnown(known [][]netip.AddrPort) {
|
||||
byName := make(map[hostnamePort][]netip.AddrPort, len(known))
|
||||
for i, addrs := range known {
|
||||
byName[hr.hostnames[i]] = addrs
|
||||
}
|
||||
hr.known.Store(&byName)
|
||||
}
|
||||
|
||||
// literalAddrs returns the entries that were configured as ip addresses rather than hostnames
|
||||
func (hr *hostnamesResults) literalAddrs() []netip.AddrPort {
|
||||
var out []netip.AddrPort
|
||||
for _, hostPort := range hr.hostnames {
|
||||
if hostPort.addr.IsValid() {
|
||||
out = append(out, netip.AddrPortFrom(hostPort.addr, hostPort.port))
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// ResolveNow asks the background goroutine to look up the hostnames again without waiting for the next tick
|
||||
func (hr *hostnamesResults) ResolveNow() {
|
||||
if hr == nil || hr.resolveNow == nil {
|
||||
return
|
||||
}
|
||||
select {
|
||||
case hr.resolveNow <- struct{}{}:
|
||||
default:
|
||||
}
|
||||
}
|
||||
|
||||
func (hr *hostnamesResults) Cancel() {
|
||||
if hr != nil && hr.cancelFn != nil {
|
||||
hr.cancelFn()
|
||||
@@ -346,13 +256,6 @@ func (r *RemoteList) ResetForOwner(ownerVpnAddr netip.Addr) {
|
||||
r.shouldRebuild = true
|
||||
}
|
||||
|
||||
// ResolveHostnames kicks a fresh DNS lookup of any static_map hostnames for this host
|
||||
func (r *RemoteList) ResolveHostnames() {
|
||||
r.RLock()
|
||||
defer r.RUnlock()
|
||||
r.hr.ResolveNow()
|
||||
}
|
||||
|
||||
// ClearHostnameResults cancels the in-flight DNS resolver goroutine (if any) and drops the resolved IP cache.
|
||||
func (r *RemoteList) ClearHostnameResults() {
|
||||
r.Lock()
|
||||
@@ -557,14 +460,10 @@ func (r *RemoteList) unlockedSetV4(ownerVpnIp, vpnIp netip.Addr, to []*V4AddrPor
|
||||
// Reset the slice
|
||||
c.reported = c.reported[:0]
|
||||
|
||||
// We can't take their array but we can take their pointers.
|
||||
// Filter before capping so denied addrs do not crowd out allowed ones reported later in the list.
|
||||
for _, v := range to {
|
||||
// We can't take their array but we can take their pointers
|
||||
for _, v := range to[:minInt(len(to), MaxRemotes)] {
|
||||
if check(vpnIp, v) {
|
||||
c.reported = append(c.reported, v)
|
||||
if len(c.reported) == MaxRemotes {
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -609,14 +508,10 @@ func (r *RemoteList) unlockedSetV6(ownerVpnIp, vpnIp netip.Addr, to []*V6AddrPor
|
||||
// Reset the slice
|
||||
c.reported = c.reported[:0]
|
||||
|
||||
// We can't take their array but we can take their pointers.
|
||||
// Filter before capping so denied addrs do not crowd out allowed ones reported later in the list.
|
||||
for _, v := range to {
|
||||
// We can't take their array but we can take their pointers
|
||||
for _, v := range to[:minInt(len(to), MaxRemotes)] {
|
||||
if check(vpnIp, v) {
|
||||
c.reported = append(c.reported, v)
|
||||
if len(c.reported) == MaxRemotes {
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,15 +1,10 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/binary"
|
||||
"fmt"
|
||||
"net"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
@@ -333,55 +328,6 @@ func BenchmarkSortRebuild(b *testing.B) {
|
||||
})
|
||||
}
|
||||
|
||||
func TestApplyLookup(t *testing.T) {
|
||||
prev := []netip.AddrPort{netip.MustParseAddrPort("1.1.1.1:4242")}
|
||||
|
||||
// A successful lookup replaces the previous addresses
|
||||
got := applyLookup(prev, 4242, []netip.Addr{netip.MustParseAddr("::ffff:2.2.2.2")}, nil)
|
||||
assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("2.2.2.2:4242")}, got)
|
||||
|
||||
// A not found answer means the record is gone
|
||||
assert.Empty(t, applyLookup(prev, 4242, nil, &net.DNSError{Err: "no such host", IsNotFound: true}))
|
||||
|
||||
// Anything else is not new information, keep what we had
|
||||
assert.Equal(t, prev, applyLookup(prev, 4242, nil, &net.DNSError{Err: "i/o timeout", IsTimeout: true}))
|
||||
assert.Equal(t, prev, applyLookup(prev, 4242, nil, &net.DNSError{Err: "server misbehaving", IsTemporary: true}))
|
||||
assert.Equal(t, prev, applyLookup(prev, 4242, nil, context.DeadlineExceeded))
|
||||
}
|
||||
|
||||
func TestNewHostnameResults_CarriesKnown(t *testing.T) {
|
||||
// A canceled context keeps the background lookup from learning anything, as if DNS were down
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
cancel()
|
||||
|
||||
known := netip.MustParseAddrPort("1.1.1.1:4242")
|
||||
prev := &hostnamesResults{network: "ip4"}
|
||||
prev.known.Store(&map[hostnamePort][]netip.AddrPort{{name: "lh.invalid", port: 4242}: {known}})
|
||||
|
||||
hostPorts := []string{"lh.invalid:4242", "10.0.0.1:4242"}
|
||||
literal := netip.MustParseAddrPort("10.0.0.1:4242")
|
||||
|
||||
hr, err := NewHostnameResults(ctx, test.NewLogger(), time.Hour, "ip4", time.Second, hostPorts, prev, func() {})
|
||||
require.NoError(t, err)
|
||||
assert.ElementsMatch(t, []netip.AddrPort{known, literal}, hr.GetAddrs())
|
||||
assert.Equal(t, []netip.AddrPort{literal}, hr.literalAddrs())
|
||||
|
||||
// And again from the new one, before it has finished a lookup of its own
|
||||
hr2, err := NewHostnameResults(ctx, test.NewLogger(), time.Hour, "ip4", time.Second, hostPorts, hr, func() {})
|
||||
require.NoError(t, err)
|
||||
assert.ElementsMatch(t, []netip.AddrPort{known, literal}, hr2.GetAddrs())
|
||||
|
||||
// A port change is a different entry
|
||||
hr3, err := NewHostnameResults(ctx, test.NewLogger(), time.Hour, "ip4", time.Second, []string{"lh.invalid:4243"}, prev, func() {})
|
||||
require.NoError(t, err)
|
||||
assert.Empty(t, hr3.GetAddrs())
|
||||
|
||||
// So is a network change
|
||||
hr4, err := NewHostnameResults(ctx, test.NewLogger(), time.Hour, "ip6", time.Second, hostPorts, prev, func() {})
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, []netip.AddrPort{literal}, hr4.GetAddrs())
|
||||
}
|
||||
|
||||
func newIp4AndPortFromString(s string) *V4AddrPort {
|
||||
a := netip.MustParseAddrPort(s)
|
||||
v4Addr := a.Addr().As4()
|
||||
@@ -400,38 +346,3 @@ func newIp6AndPortFromString(s string) *V6AddrPort {
|
||||
Port: uint32(a.Port()),
|
||||
}
|
||||
}
|
||||
|
||||
func TestRemoteList_SetFiltersBeforeCap(t *testing.T) {
|
||||
owner := netip.MustParseAddr("0.0.0.0")
|
||||
rl := NewRemoteList([]netip.Addr{owner}, nil)
|
||||
|
||||
// MaxRemotes denied addrs first, then the only allowed one, then enough allowed to exceed the cap
|
||||
var v4 []*V4AddrPort
|
||||
for i := 0; i < MaxRemotes; i++ {
|
||||
v4 = append(v4, newIp4AndPortFromString(fmt.Sprintf("172.17.0.%d:4242", i+1)))
|
||||
}
|
||||
for i := 0; i < MaxRemotes+1; i++ {
|
||||
v4 = append(v4, newIp4AndPortFromString(fmt.Sprintf("70.199.182.%d:4242", i+1)))
|
||||
}
|
||||
rl.unlockedSetV4(owner, owner, v4, func(_ netip.Addr, a *V4AddrPort) bool {
|
||||
return protoV4AddrPortToNetAddrPort(a).Addr().As4()[0] != 172
|
||||
})
|
||||
|
||||
var v6 []*V6AddrPort
|
||||
for i := 0; i < MaxRemotes; i++ {
|
||||
v6 = append(v6, newIp6AndPortFromString(fmt.Sprintf("[fd00::%d]:4242", i+1)))
|
||||
}
|
||||
for i := 0; i < MaxRemotes+1; i++ {
|
||||
v6 = append(v6, newIp6AndPortFromString(fmt.Sprintf("[2001:db8::%d]:4242", i+1)))
|
||||
}
|
||||
rl.unlockedSetV6(owner, owner, v6, func(_ netip.Addr, a *V6AddrPort) bool {
|
||||
return protoV6AddrPortToNetAddrPort(a).Addr().As16()[0] != 0xfd
|
||||
})
|
||||
|
||||
rl.Rebuild([]netip.Prefix{})
|
||||
assert.Len(t, rl.addrs, MaxRemotes*2)
|
||||
for _, a := range rl.addrs {
|
||||
assert.NotEqual(t, byte(172), a.Addr().As16()[12], "denied v4 addr %v was kept", a)
|
||||
assert.NotEqual(t, byte(0xfd), a.Addr().As16()[0], "denied v6 addr %v was kept", a)
|
||||
}
|
||||
}
|
||||
+2
-4
@@ -36,13 +36,11 @@ func (l *tcpListener) Accept() (net.Conn, error) {
|
||||
|
||||
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()
|
||||
|
||||
close(l.closed)
|
||||
})
|
||||
return nil
|
||||
}
|
||||
|
||||
+7
-70
@@ -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
|
||||
}
|
||||
|
||||
@@ -274,9 +237,6 @@ func (s *Service) Listen(network, address string) (net.Listener, error) {
|
||||
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)
|
||||
}
|
||||
@@ -285,38 +245,15 @@ 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()
|
||||
|
||||
|
||||
@@ -327,162 +327,3 @@ func TestListenerAcceptAfterClose(t *testing.T) {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// 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")
|
||||
}
|
||||
}
|
||||
@@ -1,17 +1,59 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"flag"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"maps"
|
||||
"net"
|
||||
"net/netip"
|
||||
"os"
|
||||
"slices"
|
||||
"sort"
|
||||
"strings"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/logging"
|
||||
"github.com/slackhq/nebula/sshd"
|
||||
)
|
||||
|
||||
type sshListHostMapFlags struct {
|
||||
Json bool
|
||||
Pretty bool
|
||||
ByIndex bool
|
||||
}
|
||||
|
||||
type sshPrintCertFlags struct {
|
||||
Json bool
|
||||
Pretty bool
|
||||
Raw bool
|
||||
}
|
||||
|
||||
type sshPrintTunnelFlags struct {
|
||||
Pretty bool
|
||||
}
|
||||
|
||||
type sshChangeRemoteFlags struct {
|
||||
Address string
|
||||
}
|
||||
|
||||
type sshCloseTunnelFlags struct {
|
||||
LocalOnly bool
|
||||
}
|
||||
|
||||
type sshCreateTunnelFlags struct {
|
||||
Address string
|
||||
}
|
||||
|
||||
type sshDeviceInfoFlags struct {
|
||||
Json bool
|
||||
Pretty bool
|
||||
}
|
||||
|
||||
func wireSSHReload(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) {
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
if c.GetBool("sshd.enabled", false) {
|
||||
@@ -185,3 +227,704 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C, r *config.Reloa
|
||||
|
||||
return runner, nil
|
||||
}
|
||||
|
||||
func attachCommands(l *slog.Logger, c *config.C, ssh *sshd.SSHServer, f *Interface) {
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "list-hostmap",
|
||||
ShortDescription: "List all known previously connected hosts",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := sshListHostMapFlags{}
|
||||
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
|
||||
},
|
||||
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
||||
return sshListHostMap(f.hostMap, fs, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "list-pending-hostmap",
|
||||
ShortDescription: "List all handshaking hosts",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := sshListHostMapFlags{}
|
||||
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
|
||||
},
|
||||
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
||||
return sshListHostMap(f.handshakeManager, fs, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "list-lighthouse-addrmap",
|
||||
ShortDescription: "List all lighthouse map entries",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := sshListHostMapFlags{}
|
||||
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 sshd.StringWriter) error {
|
||||
return sshListLighthouseMap(f.lightHouse, fs, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "reload",
|
||||
ShortDescription: "Reloads configuration from disk, same as sending HUP to the process",
|
||||
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
||||
return sshReload(l, c, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "log-level",
|
||||
ShortDescription: "Gets or sets the current log level",
|
||||
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
||||
return sshLogLevel(l, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "log-format",
|
||||
ShortDescription: "Gets or sets the current log format",
|
||||
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
||||
return sshLogFormat(l, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "version",
|
||||
ShortDescription: "Prints the currently running version of nebula",
|
||||
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
||||
return sshVersion(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "device-info",
|
||||
ShortDescription: "Prints information about the network device.",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := sshDeviceInfoFlags{}
|
||||
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 sshd.StringWriter) error {
|
||||
return sshDeviceInfo(f, fs, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "print-cert",
|
||||
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 := sshPrintCertFlags{}
|
||||
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 sshd.StringWriter) error {
|
||||
return sshPrintCert(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "print-tunnel",
|
||||
ShortDescription: "Prints json details about a tunnel for the provided vpn addr",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := sshPrintTunnelFlags{}
|
||||
fl.BoolVar(&s.Pretty, "pretty", false, "pretty prints json")
|
||||
return fl, &s
|
||||
},
|
||||
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
||||
return sshPrintTunnel(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "print-relays",
|
||||
ShortDescription: "Prints json details about all relay info",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := sshPrintTunnelFlags{}
|
||||
fl.BoolVar(&s.Pretty, "pretty", false, "pretty prints json")
|
||||
return fl, &s
|
||||
},
|
||||
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
||||
return sshPrintRelays(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "change-remote",
|
||||
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 := sshChangeRemoteFlags{}
|
||||
fl.StringVar(&s.Address, "address", "", "The new remote address, ip:port")
|
||||
return fl, &s
|
||||
},
|
||||
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
||||
return sshChangeRemote(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "close-tunnel",
|
||||
ShortDescription: "Closes a tunnel for the provided vpn addr",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := sshCloseTunnelFlags{}
|
||||
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 sshd.StringWriter) error {
|
||||
return sshCloseTunnel(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "create-tunnel",
|
||||
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 := sshCreateTunnelFlags{}
|
||||
fl.StringVar(&s.Address, "address", "", "Optionally provide a real remote address, ip:port ")
|
||||
return fl, &s
|
||||
},
|
||||
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
||||
return sshCreateTunnel(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "query-lighthouse",
|
||||
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 sshd.StringWriter) error {
|
||||
return sshQueryLighthouse(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
}
|
||||
|
||||
func sshListHostMap(hl controlHostLister, a any, w sshd.StringWriter) error {
|
||||
fs, ok := a.(*sshListHostMapFlags)
|
||||
if !ok {
|
||||
return nil
|
||||
}
|
||||
|
||||
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("", " ")
|
||||
}
|
||||
|
||||
err := js.Encode(hm)
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
} else {
|
||||
for _, v := range hm {
|
||||
err := w.WriteLine(fmt.Sprintf("%s: %s", v.VpnAddrs, v.RemoteAddrs))
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
func sshListLighthouseMap(lightHouse *LightHouse, a any, w sshd.StringWriter) error {
|
||||
fs, ok := a.(*sshListHostMapFlags)
|
||||
if !ok {
|
||||
return nil
|
||||
}
|
||||
|
||||
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("", " ")
|
||||
}
|
||||
|
||||
err := js.Encode(addrMap)
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
} 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
|
||||
}
|
||||
|
||||
func sshVersion(ifce *Interface, fs any, a []string, w sshd.StringWriter) error {
|
||||
return w.WriteLine(fmt.Sprintf("%s", ifce.version))
|
||||
}
|
||||
|
||||
func sshQueryLighthouse(ifce *Interface, fs any, a []string, w sshd.StringWriter) error {
|
||||
if len(a) == 0 {
|
||||
return w.WriteLine("No vpn address was provided")
|
||||
}
|
||||
|
||||
vpnAddr, err := netip.ParseAddr(a[0])
|
||||
if err != nil {
|
||||
return w.WriteLine(fmt.Sprintf("The provided vpn address could not be parsed: %s", a[0]))
|
||||
}
|
||||
|
||||
if !vpnAddr.IsValid() {
|
||||
return w.WriteLine(fmt.Sprintf("The provided vpn address could not be parsed: %s", a[0]))
|
||||
}
|
||||
|
||||
var cm *CacheMap
|
||||
rl := ifce.lightHouse.Query(vpnAddr)
|
||||
if rl != nil {
|
||||
cm = rl.CopyCache()
|
||||
}
|
||||
return json.NewEncoder(w.GetWriter()).Encode(cm)
|
||||
}
|
||||
|
||||
func sshCloseTunnel(ifce *Interface, fs any, a []string, w sshd.StringWriter) error {
|
||||
flags, ok := fs.(*sshCloseTunnelFlags)
|
||||
if !ok {
|
||||
return nil
|
||||
}
|
||||
|
||||
if len(a) == 0 {
|
||||
return w.WriteLine("No vpn address was provided")
|
||||
}
|
||||
|
||||
vpnAddr, err := netip.ParseAddr(a[0])
|
||||
if err != nil {
|
||||
return w.WriteLine(fmt.Sprintf("The provided vpn address could not be parsed: %s", a[0]))
|
||||
}
|
||||
|
||||
if !vpnAddr.IsValid() {
|
||||
return w.WriteLine(fmt.Sprintf("The provided vpn address could not be parsed: %s", a[0]))
|
||||
}
|
||||
|
||||
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
|
||||
if hostInfo == nil {
|
||||
return w.WriteLine(fmt.Sprintf("Could not find tunnel for vpn address: %v", a[0]))
|
||||
}
|
||||
|
||||
if !flags.LocalOnly {
|
||||
ifce.send(
|
||||
header.CloseTunnel,
|
||||
0,
|
||||
hostInfo.ConnectionState,
|
||||
hostInfo,
|
||||
[]byte{},
|
||||
make([]byte, 12, 12),
|
||||
make([]byte, mtu),
|
||||
)
|
||||
}
|
||||
|
||||
ifce.closeTunnel(hostInfo)
|
||||
return w.WriteLine("Closed")
|
||||
}
|
||||
|
||||
func sshCreateTunnel(ifce *Interface, fs any, a []string, w sshd.StringWriter) error {
|
||||
flags, ok := fs.(*sshCreateTunnelFlags)
|
||||
if !ok {
|
||||
return nil
|
||||
}
|
||||
|
||||
if len(a) == 0 {
|
||||
return w.WriteLine("No vpn address was provided")
|
||||
}
|
||||
|
||||
vpnAddr, err := netip.ParseAddr(a[0])
|
||||
if err != nil {
|
||||
return w.WriteLine(fmt.Sprintf("The provided vpn address could not be parsed: %s", a[0]))
|
||||
}
|
||||
|
||||
if !vpnAddr.IsValid() {
|
||||
return w.WriteLine(fmt.Sprintf("The provided vpn address could not be parsed: %s", a[0]))
|
||||
}
|
||||
|
||||
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
|
||||
if hostInfo != nil {
|
||||
return w.WriteLine(fmt.Sprintf("Tunnel already exists"))
|
||||
}
|
||||
|
||||
hostInfo = ifce.handshakeManager.QueryVpnAddr(vpnAddr)
|
||||
if hostInfo != nil {
|
||||
return w.WriteLine(fmt.Sprintf("Tunnel already handshaking"))
|
||||
}
|
||||
|
||||
var addr netip.AddrPort
|
||||
if flags.Address != "" {
|
||||
addr, err = netip.ParseAddrPort(flags.Address)
|
||||
if err != nil {
|
||||
return w.WriteLine("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 sshChangeRemote(ifce *Interface, fs any, a []string, w sshd.StringWriter) error {
|
||||
flags, ok := fs.(*sshChangeRemoteFlags)
|
||||
if !ok {
|
||||
return nil
|
||||
}
|
||||
|
||||
if len(a) == 0 {
|
||||
return w.WriteLine("No vpn address was provided")
|
||||
}
|
||||
|
||||
if flags.Address == "" {
|
||||
return w.WriteLine("No address was provided")
|
||||
}
|
||||
|
||||
addr, err := netip.ParseAddrPort(flags.Address)
|
||||
if err != nil {
|
||||
return w.WriteLine("Address could not be parsed")
|
||||
}
|
||||
|
||||
vpnAddr, err := netip.ParseAddr(a[0])
|
||||
if err != nil {
|
||||
return w.WriteLine(fmt.Sprintf("The provided vpn address could not be parsed: %s", a[0]))
|
||||
}
|
||||
|
||||
if !vpnAddr.IsValid() {
|
||||
return w.WriteLine(fmt.Sprintf("The provided vpn address could not be parsed: %s", a[0]))
|
||||
}
|
||||
|
||||
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
|
||||
if hostInfo == nil {
|
||||
return w.WriteLine(fmt.Sprintf("Could not find tunnel for vpn address: %v", a[0]))
|
||||
}
|
||||
|
||||
hostInfo.SetRemote(addr)
|
||||
return w.WriteLine("Changed")
|
||||
}
|
||||
|
||||
func sshLogLevel(l *slog.Logger, fs any, a []string, w sshd.StringWriter) error {
|
||||
ctrl, ok := l.Handler().(interface {
|
||||
GetLevel() slog.Level
|
||||
SetLevel(slog.Level)
|
||||
})
|
||||
if !ok {
|
||||
return w.WriteLine("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 w.WriteLine(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 sshLogFormat(l *slog.Logger, fs any, a []string, w sshd.StringWriter) error {
|
||||
ctrl, ok := l.Handler().(interface {
|
||||
GetFormat() string
|
||||
SetFormat(string) error
|
||||
})
|
||||
if !ok {
|
||||
return w.WriteLine("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 err
|
||||
}
|
||||
return w.WriteLine(fmt.Sprintf("Log format is: %s", ctrl.GetFormat()))
|
||||
}
|
||||
|
||||
func sshPrintCert(ifce *Interface, fs any, a []string, w sshd.StringWriter) error {
|
||||
args, ok := fs.(*sshPrintCertFlags)
|
||||
if !ok {
|
||||
return nil
|
||||
}
|
||||
|
||||
cert := ifce.pki.getCertState().GetDefaultCertificate()
|
||||
if len(a) > 0 {
|
||||
vpnAddr, err := netip.ParseAddr(a[0])
|
||||
if err != nil {
|
||||
return w.WriteLine(fmt.Sprintf("The provided vpn addr could not be parsed: %s", a[0]))
|
||||
}
|
||||
|
||||
if !vpnAddr.IsValid() {
|
||||
return w.WriteLine(fmt.Sprintf("The provided vpn addr could not be parsed: %s", a[0]))
|
||||
}
|
||||
|
||||
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
|
||||
if hostInfo == nil {
|
||||
return w.WriteLine(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 nil
|
||||
}
|
||||
|
||||
if args.Pretty {
|
||||
buf := new(bytes.Buffer)
|
||||
err := json.Indent(buf, b, "", " ")
|
||||
b = buf.Bytes()
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
}
|
||||
|
||||
return w.WriteBytes(b)
|
||||
}
|
||||
|
||||
if args.Raw {
|
||||
b, err := cert.MarshalPEM()
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
return w.WriteBytes(b)
|
||||
}
|
||||
|
||||
return w.WriteLine(cert.String())
|
||||
}
|
||||
|
||||
func sshPrintRelays(ifce *Interface, fs any, a []string, w sshd.StringWriter) error {
|
||||
args, ok := fs.(*sshPrintTunnelFlags)
|
||||
if !ok {
|
||||
w.WriteLine(fmt.Sprintf("sshPrintRelays failed to convert args type"))
|
||||
return nil
|
||||
}
|
||||
|
||||
relays := map[uint32]*HostInfo{}
|
||||
ifce.hostMap.Lock()
|
||||
maps.Copy(relays, ifce.hostMap.Relays)
|
||||
ifce.hostMap.Unlock()
|
||||
|
||||
type RelayFor struct {
|
||||
Error error
|
||||
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: errors.New("could not find hostinfo")})
|
||||
continue
|
||||
}
|
||||
for _, vpnAddr := range relayHI.relayState.CopyRelayForIps() {
|
||||
rf := RelayFor{Error: nil}
|
||||
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.Errorf("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)
|
||||
}
|
||||
}
|
||||
err := enc.Encode(co)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func sshPrintTunnel(ifce *Interface, fs any, a []string, w sshd.StringWriter) error {
|
||||
args, ok := fs.(*sshPrintTunnelFlags)
|
||||
if !ok {
|
||||
return nil
|
||||
}
|
||||
|
||||
if len(a) == 0 {
|
||||
return w.WriteLine("No vpn address was provided")
|
||||
}
|
||||
|
||||
vpnAddr, err := netip.ParseAddr(a[0])
|
||||
if err != nil {
|
||||
return w.WriteLine(fmt.Sprintf("The provided vpn addr could not be parsed: %s", a[0]))
|
||||
}
|
||||
|
||||
if !vpnAddr.IsValid() {
|
||||
return w.WriteLine(fmt.Sprintf("The provided vpn addr could not be parsed: %s", a[0]))
|
||||
}
|
||||
|
||||
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
|
||||
if hostInfo == nil {
|
||||
return w.WriteLine(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 sshDeviceInfo(ifce *Interface, fs any, w sshd.StringWriter) error {
|
||||
|
||||
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())
|
||||
|
||||
flags, ok := fs.(*sshDeviceInfoFlags)
|
||||
if !ok {
|
||||
return fmt.Errorf("internal error: expected flags to be sshDeviceInfoFlags but was %+v", fs)
|
||||
}
|
||||
|
||||
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))
|
||||
}
|
||||
}
|
||||
|
||||
// sshReload reloads the config and writes the result to the client. It reloads even if the client has gone away
|
||||
func sshReload(l *slog.Logger, c *config.C, w sshd.StringWriter) error {
|
||||
writeErr := w.WriteLine("Reloading config")
|
||||
res := c.ReloadConfig()
|
||||
res.Log(l)
|
||||
if err := w.WriteLine(res.String()); writeErr == nil {
|
||||
writeErr = err
|
||||
}
|
||||
return writeErr
|
||||
}
|
||||
@@ -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, "")
|
||||
}
|
||||
+9
-20
@@ -7,7 +7,6 @@ import (
|
||||
"path/filepath"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/commands"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
@@ -27,7 +26,7 @@ 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) {
|
||||
func TestSSHReloadReportsTheResult(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
write := func(body string) {
|
||||
require.NoError(t, os.WriteFile(filepath.Join(dir, "config.yml"), []byte(body), 0o600))
|
||||
@@ -44,42 +43,32 @@ func TestReloadCommandReportsTheResult(t *testing.T) {
|
||||
}
|
||||
})
|
||||
|
||||
// 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 {
|
||||
reload := func() []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)
|
||||
}
|
||||
require.NoError(t, sshReload(l, c, w))
|
||||
return w.lines
|
||||
}
|
||||
|
||||
write("a: 2\nb: 1")
|
||||
assert.Equal(t, []string{"Reloading config", "Config reload complete"}, reload(false))
|
||||
assert.Equal(t, []string{"Reloading config", "Config reload complete"}, reload())
|
||||
|
||||
fail = true
|
||||
write("a: 3\nb: 1")
|
||||
assert.Equal(t, []string{"Reloading config", "Config reload completed with errors, review the logs"}, reload(true))
|
||||
assert.Equal(t, []string{"Reloading config", "Config reload completed with errors, review the logs"}, reload())
|
||||
|
||||
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))
|
||||
assert.Equal(t, []string{"Reloading config", "Config reload was completed but requires a restart to fully apply, keys [b]"}, reload())
|
||||
|
||||
write("a: [")
|
||||
lines := reload(true)
|
||||
lines := reload()
|
||||
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) {
|
||||
func TestSSHReloadReloadsWhenTheClientIsGone(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
require.NoError(t, os.WriteFile(filepath.Join(dir, "config.yml"), []byte("a: 1"), 0o600))
|
||||
l := test.NewLogger()
|
||||
@@ -89,6 +78,6 @@ func TestReloadCommandReloadsWhenTheClientIsGone(t *testing.T) {
|
||||
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)
|
||||
require.ErrorIs(t, sshReload(l, c, &lineWriter{err: gone}), gone)
|
||||
assert.True(t, reloaded)
|
||||
}
|
||||
+161
@@ -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
|
||||
}
|
||||
+23
-9
@@ -10,7 +10,7 @@ import (
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
|
||||
"github.com/slackhq/nebula/commands"
|
||||
"github.com/armon/go-radix"
|
||||
"golang.org/x/crypto/ssh"
|
||||
)
|
||||
|
||||
@@ -29,9 +29,10 @@ type SSHServer struct {
|
||||
trustedKeys map[string]map[string]bool
|
||||
trustedCAs []ssh.PublicKey
|
||||
|
||||
// Available commands.
|
||||
commands *commands.Registry
|
||||
listener atomic.Pointer[net.Listener]
|
||||
// List of available commands
|
||||
helpCommand *Command
|
||||
commands *radix.Tree
|
||||
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
|
||||
@@ -43,14 +44,14 @@ type SSHServer struct {
|
||||
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,
|
||||
}
|
||||
|
||||
@@ -96,6 +97,14 @@ func NewSSHServer(ctx context.Context, l *slog.Logger, reg *commands.Registry) (
|
||||
s.authenticate = cc.Authenticate
|
||||
s.config.Store(s.newConfig())
|
||||
|
||||
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
|
||||
}
|
||||
|
||||
@@ -180,6 +189,11 @@ 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.
|
||||
|
||||
+46
-37
@@ -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() {
|
||||
|
||||
@@ -1,9 +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")
|
||||
}
|
||||
+1
-42
@@ -6,16 +6,13 @@ import (
|
||||
"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"
|
||||
@@ -26,7 +23,6 @@ import (
|
||||
|
||||
type sshdReloadHarness struct {
|
||||
c *config.C
|
||||
reg *commands.Registry
|
||||
server *sshd.SSHServer
|
||||
keyFile string
|
||||
signer ssh.Signer
|
||||
@@ -48,8 +44,7 @@ func newSSHDReloadHarness(t *testing.T) *sshdReloadHarness {
|
||||
|
||||
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)
|
||||
h.server, err = sshd.NewSSHServer(t.Context(), l)
|
||||
require.NoError(t, err)
|
||||
wireSSHReload(l, h.server, h.c)
|
||||
run, err := configSSH(l, h.server, h.c, nil)
|
||||
@@ -243,39 +238,3 @@ func TestSSHDReload_SkippedEntriesFail(t *testing.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))
|
||||
}
|
||||
@@ -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)
|
||||
}
|
||||
Vendored
-94
@@ -1,94 +0,0 @@
|
||||
change-remote
|
||||
short: Changes the remote address used in the tunnel for the provided vpn addr
|
||||
help:
|
||||
flags:
|
||||
-address string
|
||||
The new remote address, ip:port
|
||||
close-tunnel
|
||||
short: Closes a tunnel for the provided vpn addr
|
||||
help:
|
||||
flags:
|
||||
-local-only
|
||||
Disables notifying the remote that the tunnel is shutting down
|
||||
create-tunnel
|
||||
short: 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:
|
||||
-address string
|
||||
Optionally provide a real remote address, ip:port
|
||||
device-info
|
||||
short: Prints information about the network device.
|
||||
help:
|
||||
flags:
|
||||
-json
|
||||
outputs as json with more information
|
||||
-pretty
|
||||
pretty prints json, assumes -json
|
||||
help
|
||||
short: prints available commands or help <command> for specific usage info
|
||||
help:
|
||||
list-hostmap
|
||||
short: List all known previously connected hosts
|
||||
help:
|
||||
flags:
|
||||
-by-index
|
||||
gets all hosts in the hostmap from the index table
|
||||
-json
|
||||
outputs as json with more information
|
||||
-pretty
|
||||
pretty prints json, assumes -json
|
||||
list-lighthouse-addrmap
|
||||
short: List all lighthouse map entries
|
||||
help:
|
||||
flags:
|
||||
-json
|
||||
outputs as json with more information
|
||||
-pretty
|
||||
pretty prints json, assumes -json
|
||||
list-pending-hostmap
|
||||
short: List all handshaking hosts
|
||||
help:
|
||||
flags:
|
||||
-by-index
|
||||
gets all hosts in the hostmap from the index table
|
||||
-json
|
||||
outputs as json with more information
|
||||
-pretty
|
||||
pretty prints json, assumes -json
|
||||
log-format
|
||||
short: Gets or sets the current log format
|
||||
help:
|
||||
log-level
|
||||
short: Gets or sets the current log level
|
||||
help:
|
||||
print-cert
|
||||
short: Prints the current certificate being used or the certificate for the provided vpn addr
|
||||
help:
|
||||
flags:
|
||||
-json
|
||||
outputs as json
|
||||
-pretty
|
||||
pretty prints json, assumes -json
|
||||
-raw
|
||||
raw prints the PEM encoded certificate, not compatible with -json or -pretty
|
||||
print-relays
|
||||
short: Prints json details about all relay info
|
||||
help:
|
||||
flags:
|
||||
-pretty
|
||||
pretty prints json
|
||||
print-tunnel
|
||||
short: Prints json details about a tunnel for the provided vpn addr
|
||||
help:
|
||||
flags:
|
||||
-pretty
|
||||
pretty prints json
|
||||
query-lighthouse
|
||||
short: Query the lighthouses for the provided vpn address
|
||||
help: This command is asynchronous. Only currently known udp addresses will be printed.
|
||||
reload
|
||||
short: Reloads configuration from disk, same as sending HUP to the process
|
||||
help:
|
||||
version
|
||||
short: Prints the currently running version of nebula
|
||||
help:
|
||||
+32
-14
@@ -246,6 +246,18 @@ func getFrom(names [][]byte, i int, isV4 bool) netip.AddrPort {
|
||||
}
|
||||
|
||||
func (u *StdConn) ListenOut(r EncReader, flush func()) error {
|
||||
return u.listenOut(r, flush, nil)
|
||||
}
|
||||
|
||||
// ListenOutHandoff is ListenOut for a reader that keeps the packets: after each batch, handoff takes the batch's
|
||||
// buffers and returns replacements, of the same count and at least the same size, to receive the next one into.
|
||||
func (u *StdConn) ListenOutHandoff(r EncReader, handoff func(bufs [][]byte) [][]byte) error {
|
||||
return u.listenOut(r, nil, handoff)
|
||||
}
|
||||
|
||||
// listenOut is the receive loop. After each batch it calls flush, or with handoff set, hands the batch's buffers
|
||||
// over and points the recvmmsg iovecs at the ones it gets back.
|
||||
func (u *StdConn) listenOut(r EncReader, flush func(), handoff func(bufs [][]byte) [][]byte) error {
|
||||
bufSize := MTU
|
||||
cmsgSpace := 0
|
||||
if u.groSupported {
|
||||
@@ -255,10 +267,6 @@ func (u *StdConn) ListenOut(r EncReader, flush func()) error {
|
||||
msgs, buffers, names, _ := prepareRawMessages(u.batch, bufSize, cmsgSpace)
|
||||
|
||||
for {
|
||||
// A shut down socket still queues and returns datagrams, a busy reader would never see an empty read
|
||||
if u.closed.Load() {
|
||||
return net.ErrClosed
|
||||
}
|
||||
if cmsgSpace > 0 {
|
||||
for i := range msgs {
|
||||
setMsgControllen(&msgs[i].Hdr, cmsgSpace)
|
||||
@@ -287,7 +295,21 @@ func (u *StdConn) ListenOut(r EncReader, flush func()) error {
|
||||
deliverSegments(r, from, payload, segSize)
|
||||
}
|
||||
|
||||
flush()
|
||||
if handoff == nil {
|
||||
flush()
|
||||
continue
|
||||
}
|
||||
next := handoff(buffers)
|
||||
if len(next) != len(buffers) {
|
||||
panic(fmt.Sprintf("udp: handoff returned %d buffers, need %d", len(next), len(buffers)))
|
||||
}
|
||||
for i := range next {
|
||||
if len(next[i]) < bufSize {
|
||||
panic(fmt.Sprintf("udp: handoff buffer is %d bytes, need %d", len(next[i]), bufSize))
|
||||
}
|
||||
msgs[i].Hdr.Iov.Base = &next[i][0]
|
||||
}
|
||||
buffers = next
|
||||
}
|
||||
}
|
||||
|
||||
@@ -450,16 +472,12 @@ func (u *StdConn) getMemInfo(meminfo *[unix.SK_MEMINFO_VARS]uint32) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// Shutdown wakes the reader without releasing the fd, Close only once it has exited
|
||||
func (u *StdConn) Shutdown() error {
|
||||
u.closed.Store(true)
|
||||
// shutdown(2) on an unconnected socket returns ENOTCONN but still wakes the reader, so ignore the error
|
||||
_ = unix.Shutdown(u.sysFd, unix.SHUT_RDWR)
|
||||
return nil
|
||||
}
|
||||
|
||||
func (u *StdConn) Close() error {
|
||||
_ = u.Shutdown()
|
||||
u.closed.Store(true)
|
||||
// Wake the reader parked in recvmmsg. shutdown(2) on an unconnected socket
|
||||
// returns ENOTCONN but still wakes it, so ignore the error.
|
||||
// The reader then sees closed and stops touching the fd, making the Close below safe.
|
||||
_ = unix.Shutdown(u.sysFd, unix.SHUT_RDWR)
|
||||
return unix.Close(u.sysFd)
|
||||
}
|
||||
|
||||
|
||||
+5
-74
@@ -76,7 +76,7 @@ func TestShutdownWakesAfterRx_Mechanism(t *testing.T) {
|
||||
}
|
||||
|
||||
// TestListenOutTeardown_TrafficPatterns reproduces the field report: a blocking
|
||||
// reader must tear down cleanly on Shutdown() regardless of what the socket has
|
||||
// reader must tear down cleanly on Close() regardless of what the socket has
|
||||
// carried. The three cases the report called out:
|
||||
//
|
||||
// no traffic ever -> works (shutdown wakes recvmmsg with n==0)
|
||||
@@ -162,12 +162,11 @@ func runTeardownCase(t *testing.T, batch int, name string, traffic func(send net
|
||||
// empty queue with the socket already having received a packet.
|
||||
time.Sleep(500 * time.Millisecond)
|
||||
|
||||
// Tear down the way Interface.Close does, the fd stays open until the reader is gone
|
||||
start := time.Now()
|
||||
if err := sc.Shutdown(); err != nil {
|
||||
t.Fatalf("Shutdown: %v", err)
|
||||
if err := sc.Close(); err != nil {
|
||||
t.Fatalf("Close: %v", err)
|
||||
}
|
||||
defer func() { _ = sc.Close() }()
|
||||
close(stop)
|
||||
|
||||
select {
|
||||
case err := <-loopDone:
|
||||
@@ -180,75 +179,7 @@ func runTeardownCase(t *testing.T, batch int, name string, traffic func(send net
|
||||
case <-time.After(3 * time.Second):
|
||||
buf := make([]byte, 1<<20)
|
||||
n := runtime.Stack(buf, true)
|
||||
t.Fatalf("%s: HANG, ListenOut did not return within 3s of Shutdown\n%s", name, buf[:n])
|
||||
t.Fatalf("%s: HANG, ListenOut did not return within 3s of Close\n%s", name, buf[:n])
|
||||
}
|
||||
close(stop)
|
||||
<-trafficDone
|
||||
}
|
||||
|
||||
// A shut down socket still returns queued datagrams, so a reader that is behind has to stop on its own within the
|
||||
// batch it was working on
|
||||
func TestListenOutShutdown_BusyReader(t *testing.T) {
|
||||
const batch = 64
|
||||
udpSettings := Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0"), Multi: true, Batch: batch}
|
||||
c, err := NewListener(testLogger(), udpSettings)
|
||||
if err != nil {
|
||||
t.Fatalf("NewListener: %v", err)
|
||||
}
|
||||
sc := c.(*StdConn)
|
||||
defer sc.Close()
|
||||
addr, err := sc.LocalAddr()
|
||||
if err != nil {
|
||||
t.Fatalf("LocalAddr: %v", err)
|
||||
}
|
||||
|
||||
stop := make(chan struct{})
|
||||
defer close(stop)
|
||||
for range 8 {
|
||||
send, err := net.Dial("udp", addr.String())
|
||||
if err != nil {
|
||||
t.Fatalf("dial: %v", err)
|
||||
}
|
||||
defer send.Close()
|
||||
go func() {
|
||||
b := make([]byte, 1200)
|
||||
for {
|
||||
select {
|
||||
case <-stop:
|
||||
return
|
||||
default:
|
||||
_, _ = send.Write(b)
|
||||
}
|
||||
}
|
||||
}()
|
||||
}
|
||||
|
||||
var afterShutdown atomic.Int64
|
||||
loopDone := make(chan error, 1)
|
||||
go func() {
|
||||
loopDone <- sc.ListenOut(func(netip.AddrPort, []byte) {
|
||||
if sc.closed.Load() {
|
||||
afterShutdown.Add(1)
|
||||
}
|
||||
// Slower than the senders so the queue never drains
|
||||
for start := time.Now(); time.Since(start) < 200*time.Microsecond; {
|
||||
}
|
||||
}, func() {})
|
||||
}()
|
||||
|
||||
time.Sleep(200 * time.Millisecond)
|
||||
if err := sc.Shutdown(); err != nil {
|
||||
t.Fatalf("Shutdown: %v", err)
|
||||
}
|
||||
select {
|
||||
case err := <-loopDone:
|
||||
if !errors.Is(err, net.ErrClosed) {
|
||||
t.Fatalf("ListenOut returned %v, want net.ErrClosed", err)
|
||||
}
|
||||
case <-time.After(3 * time.Second):
|
||||
t.Fatalf("ListenOut still running 3s after Shutdown, delivered %d packets since", afterShutdown.Load())
|
||||
}
|
||||
if n := afterShutdown.Load(); n > batch {
|
||||
t.Fatalf("delivered %d packets after Shutdown, more than the one batch in flight", n)
|
||||
}
|
||||
}
|
||||
+12
-3
@@ -183,15 +183,24 @@ func (u *TesterConn) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, err
|
||||
}
|
||||
|
||||
func (u *TesterConn) ListenOut(r EncReader, flush func()) error {
|
||||
// The batcher borrows plaintext decrypted in place inside p.Data
|
||||
// until Flush, so the packet must stay alive across flush()
|
||||
return u.listenOut(r, func(p *Packet) { flush() })
|
||||
}
|
||||
|
||||
// ListenOutHandoff hands each packet's buffer over, the replacement goes back to the pool.
|
||||
func (u *TesterConn) ListenOutHandoff(r EncReader, handoff func(bufs [][]byte) [][]byte) error {
|
||||
return u.listenOut(r, func(p *Packet) { p.Data = handoff([][]byte{p.Data})[0] })
|
||||
}
|
||||
|
||||
func (u *TesterConn) listenOut(r EncReader, finish func(*Packet)) error {
|
||||
for {
|
||||
select {
|
||||
case <-u.done:
|
||||
return os.ErrClosed
|
||||
case p := <-u.RxPackets:
|
||||
r(p.From, p.Data[:len(p.Data):len(p.Data)])
|
||||
// The batcher borrows plaintext decrypted in place inside p.Data
|
||||
// until Flush, so the packet must stay alive across flush()
|
||||
flush()
|
||||
finish(p)
|
||||
p.Release()
|
||||
}
|
||||
}
|
||||
|
||||
Reference in new issue
Block a user