mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-16 07:06:52 +01:00
Compare commits
7
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
556b457389 | ||
|
|
5bba4de3c6 | ||
|
|
06035252b2 | ||
|
|
1fb77bdda5 | ||
|
|
556747d9b7 | ||
|
|
8f34981764 | ||
|
|
4d6f757d1f |
No files matched your search
@@ -14,7 +14,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: Build
|
||||
@@ -40,7 +40,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: Build
|
||||
@@ -83,7 +83,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
# GitHub holds ARNs, not credentials, and ARNs outlive a rotation
|
||||
|
||||
@@ -34,7 +34,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: add hashicorp source
|
||||
@@ -66,7 +66,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: add hashicorp source
|
||||
@@ -92,7 +92,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
# WSL2 + Ubuntu so the smoke can run a real linux peer with its own
|
||||
|
||||
@@ -22,7 +22,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: Smoke Docker
|
||||
@@ -51,7 +51,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: build
|
||||
|
||||
@@ -22,7 +22,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: Install goimports
|
||||
@@ -42,7 +42,7 @@ jobs:
|
||||
- name: golangci-lint
|
||||
uses: golangci/golangci-lint-action@v9
|
||||
with:
|
||||
version: v2.14
|
||||
version: v2.12
|
||||
|
||||
test:
|
||||
name: Test ${{ matrix.name }}
|
||||
@@ -87,7 +87,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: Build
|
||||
@@ -132,7 +132,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: Build ${{ matrix.name }}
|
||||
|
||||
@@ -7,15 +7,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
### Removed
|
||||
|
||||
- The SSH debug server's `start-cpu-profile`, `stop-cpu-profile`, `save-heap-profile`, `save-mutex-profile`, and
|
||||
`mutex-profile-fraction` commands, and `sshd.sandbox_dir`, which is now ignored if set.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Signing a v2 certificate with an empty name, a name longer than 253 bytes, or an empty group now fails.
|
||||
These certificates were signed successfully but could not be loaded.
|
||||
- `create-tunnel -address <ip:port>` panicked on a nil RemoteList and, over the ssh debug server, took nebula
|
||||
down with it. A hostinfo returned by StartHandshake had no RemoteList until the handshake loop's first
|
||||
pass attached one, and `create-tunnel -address` set the remote before that. The list is now attached when
|
||||
|
||||
+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)
|
||||
}
|
||||
@@ -85,10 +85,9 @@ func main() {
|
||||
fmt.Printf("failed to apply logging config: %s", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
if err := logging.ApplyConfig(l, c); err != nil {
|
||||
l.Error("Failed to reconfigure logger on reload", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
|
||||
@@ -34,10 +34,9 @@ func (p *program) Start(s service.Service) error {
|
||||
if err := logging.ApplyConfig(l, c); err != nil {
|
||||
return fmt.Errorf("failed to apply logging config: %s", err)
|
||||
}
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
if err := logging.ApplyConfig(l, c); err != nil {
|
||||
l.Error("Failed to reconfigure logger on reload", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
|
||||
+1
-2
@@ -71,10 +71,9 @@ func main() {
|
||||
fmt.Printf("failed to apply logging config: %s", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
if err := logging.ApplyConfig(l, c); err != nil {
|
||||
l.Error("Failed to reconfigure logger on reload", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
|
||||
+31
-40
@@ -26,12 +26,9 @@ type C struct {
|
||||
files []string
|
||||
Settings map[string]any
|
||||
oldSettings map[string]any
|
||||
callbacks []func(*C, *Reload)
|
||||
callbacks []func(*C)
|
||||
l *slog.Logger
|
||||
reloadLock sync.Mutex
|
||||
|
||||
// Set by the first reload that needs a restart and never cleared. Guarded by reloadLock
|
||||
needsRestart bool
|
||||
}
|
||||
|
||||
func NewC(l *slog.Logger) *C {
|
||||
@@ -75,9 +72,8 @@ func (c *C) LoadString(raw string) error {
|
||||
// RegisterReloadCallback stores a function to be called when a config reload is triggered. The functions registered
|
||||
// here should decide if they need to make a change to the current process before making the change. HasChanged can be
|
||||
// used to help decide if a change is necessary.
|
||||
// These functions should return quickly or spawn their own go routine if they will take a while.
|
||||
// Use r to report anything that failed or needs a restart to apply.
|
||||
func (c *C) RegisterReloadCallback(f func(c *C, r *Reload)) {
|
||||
// These functions should return quickly or spawn their own go routine if they will take a while
|
||||
func (c *C) RegisterReloadCallback(f func(*C)) {
|
||||
c.callbacks = append(c.callbacks, f)
|
||||
}
|
||||
|
||||
@@ -148,55 +144,50 @@ func (c *C) CatchHUP(ctx context.Context) {
|
||||
return
|
||||
case <-ch:
|
||||
c.l.Info("Caught HUP, reloading config")
|
||||
c.ReloadConfig().Log(c.l)
|
||||
c.ReloadConfig()
|
||||
}
|
||||
}
|
||||
}()
|
||||
}
|
||||
|
||||
// ReloadConfig reloads the config from the path provided to Load and runs every registered callback. A config that
|
||||
// fails to load is logged here, like any other failure, and the result carries the error for the summary.
|
||||
func (c *C) ReloadConfig() ReloadResult {
|
||||
func (c *C) ReloadConfig() {
|
||||
c.reloadLock.Lock()
|
||||
defer c.reloadLock.Unlock()
|
||||
|
||||
c.oldSettings = make(map[string]any)
|
||||
maps.Copy(c.oldSettings, c.Settings)
|
||||
|
||||
if err := c.Load(c.path); err != nil {
|
||||
c.l.Error("Error occurred while reloading config", "config_path", c.path, "error", err)
|
||||
return ReloadResult{Err: err, RestartRequired: c.needsRestart}
|
||||
err := c.Load(c.path)
|
||||
if err != nil {
|
||||
c.l.Error("Error occurred while reloading config",
|
||||
"config_path", c.path,
|
||||
"error", err,
|
||||
)
|
||||
return
|
||||
}
|
||||
|
||||
return c.runCallbacks()
|
||||
}
|
||||
|
||||
// ReloadConfigString is ReloadConfig for a config held in memory rather than on disk.
|
||||
func (c *C) ReloadConfigString(raw string) ReloadResult {
|
||||
c.reloadLock.Lock()
|
||||
defer c.reloadLock.Unlock()
|
||||
|
||||
c.oldSettings = make(map[string]any)
|
||||
maps.Copy(c.oldSettings, c.Settings)
|
||||
|
||||
if err := c.LoadString(raw); err != nil {
|
||||
c.l.Error("Error occurred while reloading config", "error", err)
|
||||
return ReloadResult{Err: err, RestartRequired: c.needsRestart}
|
||||
}
|
||||
|
||||
return c.runCallbacks()
|
||||
}
|
||||
|
||||
func (c *C) runCallbacks() ReloadResult {
|
||||
r := &Reload{c: c}
|
||||
for _, v := range c.callbacks {
|
||||
v(c, r)
|
||||
v(c)
|
||||
}
|
||||
}
|
||||
|
||||
func (c *C) ReloadConfigString(raw string) error {
|
||||
c.reloadLock.Lock()
|
||||
defer c.reloadLock.Unlock()
|
||||
|
||||
c.oldSettings = make(map[string]any)
|
||||
maps.Copy(c.oldSettings, c.Settings)
|
||||
|
||||
err := c.LoadString(raw)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
if r.restart {
|
||||
c.needsRestart = true
|
||||
for _, v := range c.callbacks {
|
||||
v(c)
|
||||
}
|
||||
return ReloadResult{Failed: r.failed, RestartRequired: c.needsRestart, RestartKeys: r.keys}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// GetString will get the string for k or return the default d if not found or invalid
|
||||
@@ -400,7 +391,7 @@ func (c *C) parse() error {
|
||||
var nm map[string]any
|
||||
err = yaml.Unmarshal(b, &nm)
|
||||
if err != nil {
|
||||
return fmt.Errorf("%s: %w", path, err)
|
||||
return err
|
||||
}
|
||||
|
||||
// We need to use WithAppendSlice so that firewall rules in separate
|
||||
|
||||
@@ -19,7 +19,7 @@ func TestConfig_Load(t *testing.T) {
|
||||
// invalid yaml
|
||||
c := NewC(l)
|
||||
os.WriteFile(filepath.Join(dir, "01.yaml"), []byte(" invalid yaml"), 0644)
|
||||
require.EqualError(t, c.Load(dir), filepath.Join(dir, "01.yaml")+": yaml: unmarshal errors:\n line 1: cannot unmarshal !!str `invalid...` into map[string]interface {}")
|
||||
require.EqualError(t, c.Load(dir), "yaml: unmarshal errors:\n line 1: cannot unmarshal !!str `invalid...` into map[string]interface {}")
|
||||
|
||||
// simple multi config merge
|
||||
c = NewC(l)
|
||||
@@ -129,7 +129,7 @@ func TestConfig_ReloadConfig(t *testing.T) {
|
||||
|
||||
os.WriteFile(filepath.Join(dir, "01.yaml"), []byte("outer:\n inner: ho"), 0644)
|
||||
|
||||
c.RegisterReloadCallback(func(c *C, _ *Reload) {
|
||||
c.RegisterReloadCallback(func(c *C) {
|
||||
done <- true
|
||||
})
|
||||
|
||||
|
||||
@@ -1,98 +0,0 @@
|
||||
package config
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"slices"
|
||||
)
|
||||
|
||||
// ReloadResult describes how a reload went. Problems are logged where they happen, Log writes a one line summary.
|
||||
type ReloadResult struct {
|
||||
// Err is set when the new config could not be read or parsed, no callbacks ran
|
||||
Err error
|
||||
// Failed is true when a callback could not apply part of the new config
|
||||
Failed bool
|
||||
// RestartRequired is true once any reload has needed a restart, and stays true until the process restarts
|
||||
RestartRequired bool
|
||||
// RestartKeys are the keys this reload changed that only apply on a restart
|
||||
RestartKeys []string
|
||||
}
|
||||
|
||||
// Summary returns a one line summary of the reload and the level to log it at.
|
||||
func (r ReloadResult) Summary() (slog.Level, string) {
|
||||
switch {
|
||||
case r.Err != nil && r.RestartRequired:
|
||||
return slog.LevelError, "Config reload failed, the new config did not load and a restart is still required"
|
||||
case r.Err != nil:
|
||||
return slog.LevelError, "Config reload failed, the new config did not load"
|
||||
case r.Failed && r.RestartRequired:
|
||||
return slog.LevelError, "Config reload completed with errors and requires a restart to fully apply, review the logs"
|
||||
case r.Failed:
|
||||
return slog.LevelError, "Config reload completed with errors, review the logs"
|
||||
case r.RestartRequired:
|
||||
return slog.LevelWarn, "Config reload was completed but requires a restart to fully apply"
|
||||
default:
|
||||
return slog.LevelInfo, "Config reload complete"
|
||||
}
|
||||
}
|
||||
|
||||
// String is the summary with Err and RestartKeys included, for output other than the log.
|
||||
func (r ReloadResult) String() string {
|
||||
_, msg := r.Summary()
|
||||
if r.Err != nil {
|
||||
msg = fmt.Sprintf("%s: %v", msg, r.Err)
|
||||
}
|
||||
if len(r.RestartKeys) > 0 {
|
||||
msg = fmt.Sprintf("%s, keys %v", msg, r.RestartKeys)
|
||||
}
|
||||
return msg
|
||||
}
|
||||
|
||||
// Log writes Summary to l.
|
||||
func (r ReloadResult) Log(l *slog.Logger) {
|
||||
level, msg := r.Summary()
|
||||
if len(r.RestartKeys) > 0 {
|
||||
l.Log(context.Background(), level, msg, "keys", r.RestartKeys)
|
||||
return
|
||||
}
|
||||
l.Log(context.Background(), level, msg)
|
||||
}
|
||||
|
||||
// Reload is passed to each reload callback to report how applying the new config went.
|
||||
type Reload struct {
|
||||
c *C
|
||||
failed bool
|
||||
restart bool
|
||||
// Changed keys that only apply on a restart, from every callback
|
||||
keys []string
|
||||
}
|
||||
|
||||
// Failed marks the reload as failed, the caller logs why. Safe to call on a nil Reload, which is what the initial load
|
||||
// passes.
|
||||
func (r *Reload) Failed() {
|
||||
if r != nil {
|
||||
r.failed = true
|
||||
}
|
||||
}
|
||||
|
||||
// RestartRequired marks the reload as needing a restart, the caller logs why. Safe to call on a nil Reload.
|
||||
func (r *Reload) RestartRequired() {
|
||||
if r != nil {
|
||||
r.restart = true
|
||||
}
|
||||
}
|
||||
|
||||
// RestartRequiredIfChanged marks the reload as needing a restart if any of keys changed, and adds them to RestartKeys.
|
||||
// Use it for keys that are only read at startup. Safe to call on a nil Reload.
|
||||
func (r *Reload) RestartRequiredIfChanged(keys ...string) {
|
||||
if r == nil {
|
||||
return
|
||||
}
|
||||
for _, k := range keys {
|
||||
if r.c.HasChanged(k) && !slices.Contains(r.keys, k) {
|
||||
r.keys = append(r.keys, k)
|
||||
r.restart = true
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,108 +0,0 @@
|
||||
package config
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"log/slog"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
func TestReloadConfigString(t *testing.T) {
|
||||
c := NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("a: 1"))
|
||||
fail := false
|
||||
ran := 0
|
||||
c.RegisterReloadCallback(func(c *C, r *Reload) {
|
||||
ran++
|
||||
if fail {
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
assert.Equal(t, ReloadResult{}, c.ReloadConfigString("a: 2"))
|
||||
fail = true
|
||||
assert.Equal(t, ReloadResult{Failed: true}, c.ReloadConfigString("a: 3"))
|
||||
assert.Equal(t, 2, ran)
|
||||
|
||||
// A config that fails to load runs no callbacks and returns the error
|
||||
res := c.ReloadConfigString("a: [")
|
||||
require.Error(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.Equal(t, 2, ran)
|
||||
assert.Equal(t, 3, c.GetInt("a", 0))
|
||||
}
|
||||
|
||||
func TestReloadRestartRequiredLatches(t *testing.T) {
|
||||
c := NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("a: 1\nb: 1"))
|
||||
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequiredIfChanged("a", "b") })
|
||||
|
||||
// Nothing that needs a restart changed
|
||||
assert.Equal(t, ReloadResult{}, c.ReloadConfigString("a: 1\nb: 1\nc: 1"))
|
||||
assert.Equal(t, ReloadResult{RestartRequired: true, RestartKeys: []string{"a"}}, c.ReloadConfigString("a: 2\nb: 1\nc: 1"))
|
||||
|
||||
// The restart sticks through a reload with no changes, reverting the key and a config that fails to load. Only the
|
||||
// reload that changed the key lists it
|
||||
assert.Equal(t, ReloadResult{RestartRequired: true}, c.ReloadConfigString("a: 2\nb: 1\nc: 1"))
|
||||
assert.Equal(t, ReloadResult{RestartRequired: true, RestartKeys: []string{"a"}}, c.ReloadConfigString("a: 1\nb: 1\nc: 1"))
|
||||
|
||||
res := c.ReloadConfigString("a: [")
|
||||
require.Error(t, res.Err)
|
||||
assert.True(t, res.RestartRequired)
|
||||
}
|
||||
|
||||
// A key reported by more than one callback is listed once
|
||||
func TestReloadRestartKeysDeduped(t *testing.T) {
|
||||
c := NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("a: 1\nb: 1"))
|
||||
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequiredIfChanged("a") })
|
||||
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequiredIfChanged("a", "b") })
|
||||
|
||||
assert.Equal(t, []string{"a", "b"}, c.ReloadConfigString("a: 2\nb: 2").RestartKeys)
|
||||
}
|
||||
|
||||
// A callback can require a restart without a key changing, a file the config points at may have
|
||||
func TestReloadRestartRequiredWithoutAChange(t *testing.T) {
|
||||
c := NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("a: 1"))
|
||||
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequired() })
|
||||
|
||||
assert.Equal(t, ReloadResult{RestartRequired: true}, c.ReloadConfigString("a: 1"))
|
||||
}
|
||||
|
||||
func TestReloadResultSummary(t *testing.T) {
|
||||
cases := []struct {
|
||||
res ReloadResult
|
||||
level slog.Level
|
||||
msg string
|
||||
}{
|
||||
{ReloadResult{}, slog.LevelInfo, "Config reload complete"},
|
||||
{ReloadResult{RestartRequired: true}, slog.LevelWarn, "Config reload was completed but requires a restart to fully apply"},
|
||||
{ReloadResult{Failed: true}, slog.LevelError, "Config reload completed with errors, review the logs"},
|
||||
{ReloadResult{Failed: true, RestartRequired: true}, slog.LevelError, "Config reload completed with errors and requires a restart to fully apply, review the logs"},
|
||||
{ReloadResult{Err: errors.New("bad yaml")}, slog.LevelError, "Config reload failed, the new config did not load"},
|
||||
{ReloadResult{Err: errors.New("bad yaml"), RestartRequired: true}, slog.LevelError, "Config reload failed, the new config did not load and a restart is still required"},
|
||||
}
|
||||
for _, tc := range cases {
|
||||
level, msg := tc.res.Summary()
|
||||
assert.Equal(t, tc.level, level, tc.msg)
|
||||
assert.Equal(t, tc.msg, msg)
|
||||
}
|
||||
|
||||
res := ReloadResult{RestartRequired: true, RestartKeys: []string{"a", "b"}}
|
||||
assert.Equal(t, "Config reload was completed but requires a restart to fully apply, keys [a b]", res.String())
|
||||
|
||||
// String includes the error
|
||||
assert.Equal(t, "Config reload failed, the new config did not load: bad yaml", ReloadResult{Err: errors.New("bad yaml")}.String())
|
||||
}
|
||||
|
||||
// The initial load passes a nil Reload
|
||||
func TestReloadNilIsSafe(t *testing.T) {
|
||||
var r *Reload
|
||||
r.Failed()
|
||||
r.RestartRequired()
|
||||
r.RestartRequiredIfChanged("a")
|
||||
}
|
||||
@@ -57,8 +57,7 @@ func newConnectionManagerFromConfig(l *slog.Logger, c *config.C, hm *HostMap, p
|
||||
}
|
||||
|
||||
cm.reload(c, true)
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("timers.connection_alive_interval", "timers.pending_deletion_interval")
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
cm.reload(c, false)
|
||||
})
|
||||
|
||||
|
||||
+12
-3
@@ -103,14 +103,23 @@ func (cs *ConnectionState) Decrypt(l *slog.Logger, messageCounter uint64, packet
|
||||
if !result {
|
||||
return nil, ErrAlreadySeen
|
||||
}
|
||||
out, err := cs.decryptPacket(messageCounter, packet, nb)
|
||||
return cs.acceptDecrypted(l, messageCounter, out, err)
|
||||
}
|
||||
|
||||
out, err := cs.dKey.DecryptDanger(packet[header.Len:header.Len], packet[:header.Len], packet[header.Len:], messageCounter, nb)
|
||||
// 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)
|
||||
}
|
||||
|
||||
// acceptDecrypted finishes a decryptPacket result: an authenticated packet is recorded in the replay window, and
|
||||
// rejected if its counter was recorded since it was checked.
|
||||
func (cs *ConnectionState) acceptDecrypted(l *slog.Logger, messageCounter uint64, out []byte, err error) ([]byte, error) {
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
cs.decryptLock.Lock()
|
||||
result = cs.window.Update(l, messageCounter)
|
||||
result := cs.window.Update(l, messageCounter)
|
||||
cs.decryptLock.Unlock()
|
||||
if !result {
|
||||
return nil, ErrAlreadySeen
|
||||
|
||||
@@ -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 {
|
||||
|
||||
@@ -144,16 +144,16 @@ type fakeConn struct {
|
||||
rebinds int
|
||||
}
|
||||
|
||||
func (c *fakeConn) Rebind() error { c.rebinds++; return nil }
|
||||
func (c *fakeConn) LocalAddr() (netip.AddrPort, error) { return netip.AddrPort{}, nil }
|
||||
func (c *fakeConn) ListenOut(_ udp.EncReader, _ func()) error { return nil }
|
||||
func (c *fakeConn) WriteTo(_ []byte, _ netip.AddrPort) error { return nil }
|
||||
func (c *fakeConn) Rebind() error { c.rebinds++; return nil }
|
||||
func (c *fakeConn) LocalAddr() (netip.AddrPort, error) { return netip.AddrPort{}, nil }
|
||||
func (c *fakeConn) ListenOut(_ udp.EncReader, _ func([][]byte) [][]byte) error { return nil }
|
||||
func (c *fakeConn) WriteTo(_ []byte, _ netip.AddrPort) error { return nil }
|
||||
func (c *fakeConn) WriteBatch(bufs [][]byte, _ []netip.AddrPort) (int, error) {
|
||||
return len(bufs), nil
|
||||
}
|
||||
func (c *fakeConn) ReloadConfig(_ *config.C, _ *config.Reload) {}
|
||||
func (c *fakeConn) SupportsMultipleReaders() bool { return true }
|
||||
func (c *fakeConn) Close() error { c.closed = true; return nil }
|
||||
func (c *fakeConn) ReloadConfig(_ *config.C) {}
|
||||
func (c *fakeConn) SupportsMultipleReaders() bool { return true }
|
||||
func (c *fakeConn) Close() error { c.closed = true; return nil }
|
||||
|
||||
type multiqueueDevice struct {
|
||||
*fakeDevice
|
||||
|
||||
+1
-2
@@ -69,10 +69,9 @@ func newDnsServerFromConfig(ctx context.Context, l *slog.Logger, pki *PKI, hostM
|
||||
ds.mux = dns.NewServeMux()
|
||||
ds.mux.HandleFunc(".", ds.handleDnsRequest)
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
if err := ds.reload(c, false); err != nil {
|
||||
ds.l.Error("Failed to reload DNS responder from config", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
|
||||
@@ -1513,7 +1513,7 @@ func TestLighthouseUpdateOnReload(t *testing.T) {
|
||||
// Reload the config. The lighthouse.hosts change triggers TriggerUpdate,
|
||||
// which wakes the update worker. It calls SendUpdate, initiating a
|
||||
// handshake to the new lighthouse and caching the HostUpdateNotification.
|
||||
require.NoError(t, myConfig.ReloadConfigString(string(newCfg)).Err)
|
||||
require.NoError(t, myConfig.ReloadConfigString(string(newCfg)))
|
||||
|
||||
// Route until the lighthouse receives the HostUpdateNotification.
|
||||
// This covers: handshake stage 1, stage 2, then the cached update.
|
||||
|
||||
+30
-2
@@ -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"
|
||||
@@ -129,7 +131,7 @@ func TestCertUpgrade(t *testing.T) {
|
||||
}
|
||||
|
||||
r.Logf("reload new v2-only config")
|
||||
err = myC.ReloadConfigString(string(cb)).Err
|
||||
err = myC.ReloadConfigString(string(cb))
|
||||
assert.NoError(t, err)
|
||||
r.Log("yay, spin until their sees it")
|
||||
waitStart := time.Now()
|
||||
@@ -222,7 +224,7 @@ func TestCertDowngrade(t *testing.T) {
|
||||
}
|
||||
|
||||
r.Logf("reload new v1-only config")
|
||||
err = myC.ReloadConfigString(string(cb)).Err
|
||||
err = myC.ReloadConfigString(string(cb))
|
||||
assert.NoError(t, err)
|
||||
r.Log("yay, spin until their sees it")
|
||||
waitStart := time.Now()
|
||||
@@ -570,3 +572,29 @@ func TestCloseTunnelAuthenticated(t *testing.T) {
|
||||
myControl.Stop()
|
||||
theirControl.Stop()
|
||||
}
|
||||
|
||||
// TestStagedTunnel completes a handshake and traffic both ways with staged receive. 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))
|
||||
}
|
||||
+22
-20
@@ -8,7 +8,6 @@ pki:
|
||||
cert: /etc/nebula/host.crt
|
||||
key: /etc/nebula/host.key
|
||||
# blocklist is a list of certificate fingerprints that we will refuse to talk to
|
||||
# Entries are the hex fingerprints shown by `nebula-cert print`, an invalid entry fails startup and reload.
|
||||
#blocklist:
|
||||
# - c99d4e650533b92061b09918e838a5a0a6aaee21eed1d12fd937682865936c72
|
||||
# disconnect_invalid is a toggle to force a client to be disconnected if the certificate is expired or invalid.
|
||||
@@ -44,7 +43,7 @@ static_host_map:
|
||||
|
||||
lighthouse:
|
||||
# am_lighthouse is used to enable lighthouse functionality for a node. This should ONLY be true on nodes
|
||||
# you have configured to be lighthouses in your network. Not reloadable.
|
||||
# you have configured to be lighthouses in your network
|
||||
am_lighthouse: false
|
||||
# serve_dns optionally starts a dns listener that responds to various queries and can even be
|
||||
# delegated to for resolution
|
||||
@@ -127,9 +126,8 @@ lighthouse:
|
||||
# Port Nebula will be listening on. The default here is 4242. For a lighthouse node, the port should be defined,
|
||||
# however using port 0 will dynamically assign a port and is recommended for roaming nodes.
|
||||
listen:
|
||||
# To listen on only ipv4, use "0.0.0.0". Not reloadable.
|
||||
# To listen on only ipv4, use "0.0.0.0"
|
||||
host: "::"
|
||||
# Not reloadable.
|
||||
port: 4242
|
||||
# Sets the max number of packets to pull from the kernel for each syscall (under systems that support recvmmsg)
|
||||
# default is 64, does not support reload
|
||||
@@ -137,8 +135,7 @@ listen:
|
||||
# superpacket, so the receive scratch is batch * 64KiB per listening socket (~4MiB per routine at the
|
||||
# default of 64). Lower this to trade peak per-syscall throughput for memory on constrained hosts.
|
||||
#batch: 64
|
||||
# Linux only. Reloadable, but removing a value leaves the socket at the old size until Nebula restarts.
|
||||
# Configure socket buffers for the udp side (outside), leave unset to use the system defaults. Values will be doubled by the kernel
|
||||
# Linux only. Configure socket buffers for the udp side (outside), leave unset to use the system defaults. Values will be doubled by the kernel
|
||||
# Default is net.core.rmem_default and net.core.wmem_default (/proc/sys/net/core/rmem_default and /proc/sys/net/core/rmem_default)
|
||||
# Maximum is limited by memory in the system, SO_RCVBUFFORCE and SO_SNDBUFFORCE is used to avoid having to raise the system wide
|
||||
# max, net.core.rmem_max and net.core.wmem_max
|
||||
@@ -182,7 +179,7 @@ listen:
|
||||
# Currently, this defaults to 1 which means we have 1 tun queue reader and 1
|
||||
# UDP queue reader. Setting this above one will set IFF_MULTI_QUEUE on the tun
|
||||
# device and SO_REUSEPORT on the UDP socket to allow multiple queues.
|
||||
# This option is only supported on Linux. Not reloadable.
|
||||
# This option is only supported on Linux.
|
||||
#routines: 1
|
||||
|
||||
punchy:
|
||||
@@ -206,7 +203,6 @@ punchy:
|
||||
|
||||
# Cipher allows you to choose between the available ciphers for your network. Options are chachapoly or aes
|
||||
# IMPORTANT: this value must be identical on ALL NODES/LIGHTHOUSES. We do not/will not support use of different ciphers simultaneously!
|
||||
# Not reloadable.
|
||||
#cipher: aes
|
||||
|
||||
# Preferred ranges is used to define a hint about the local network ranges, which speeds up discovering the fastest
|
||||
@@ -233,6 +229,12 @@ punchy:
|
||||
# Trusted SSH CA public keys. These are the public keys of the CAs that are allowed to sign SSH keys for access.
|
||||
#trusted_cas:
|
||||
#- "ssh public key string"
|
||||
# sandbox_dir restricts file paths for profiling commands (start-cpu-profile, save-heap-profile,
|
||||
# save-mutex-profile) to the specified directory. Relative paths will be resolved within this directory,
|
||||
# and absolute paths outside of it will be rejected. Default is $TMP/nebula-debug.
|
||||
# The directory is NOT automatically created.
|
||||
# Overriding this to "" is the same as "/" and will allow overwriting any path on the host.
|
||||
#sandbox_dir: /var/tmp/nebula-debug
|
||||
|
||||
# EXPERIMENTAL: relay support for networks that can't establish direct connections.
|
||||
relay:
|
||||
@@ -251,30 +253,32 @@ relay:
|
||||
# Configure the private interface. Note: addr is baked into the nebula certificate
|
||||
tun:
|
||||
# When tun is disabled, a lighthouse can be started without a local tun interface (and therefore without root)
|
||||
# Not reloadable.
|
||||
disabled: false
|
||||
# Name of the device. If not set, a default will be chosen by the OS.
|
||||
# For macOS: if set, must be in the form `utun[0-9]+`.
|
||||
# For OpenBSD and NetBSD: if set, must be in the form `tun[0-9]+`, otherwise the first free one is used.
|
||||
# Not reloadable.
|
||||
# For NetBSD: Required to be set, must be in the form `tun[0-9]+`
|
||||
dev: nebula1
|
||||
# Toggles forwarding of local broadcast packets, the address of which depends on the ip/mask encoded in pki.cert
|
||||
# Not reloadable.
|
||||
drop_local_broadcast: false
|
||||
# Toggles forwarding of multicast packets. Not reloadable.
|
||||
# Toggles forwarding of multicast packets
|
||||
drop_multicast: false
|
||||
# Sets the transmit queue length, if you notice lots of transmit drops on the tun it may help to raise this number. Default is 5000
|
||||
# Not reloadable.
|
||||
tx_queue: 5000
|
||||
# Default MTU for every packet, safe setting is (and the default) 1300 for internet based traffic
|
||||
# Anything above 8937, here or on a route below, is capped to 8937 with a warning
|
||||
# Reloadable on Linux only. Where the tun is handed to nebula by a host app (iOS, Android, macOS network extensions)
|
||||
# the host app owns the MTU.
|
||||
mtu: 1300
|
||||
|
||||
# the use_offloads setting controls if Nebula will attempt to enable GSO and GRO for the tun device. Linux only, not reloadable.
|
||||
#use_offloads: false
|
||||
|
||||
# Linux only. staged.workers enables staged receive: each routine hands its received batches to this many decrypt
|
||||
# workers, then an ordered writer commits them in arrival order through the same replay, roaming and firewall
|
||||
# handling as inline receive. 0, the default, keeps receive inline. Batches below 256 packets on an idle listener
|
||||
# stay on the listener. Needs no support from peers. Costs about 24 MiB of buffers per routine at listen.batch 64
|
||||
# with GRO. Not reloadable.
|
||||
#staged:
|
||||
# workers: 0
|
||||
|
||||
# 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.
|
||||
@@ -362,7 +366,7 @@ tun:
|
||||
#use_system_route_table: false
|
||||
# Buffer size for reading routes updates. 0 means default system buffer size. (/proc/sys/net/core/rmem_default).
|
||||
# If using massive routes updates, for example BGP, you may need to increase this value to avoid packet loss.
|
||||
# SO_RCVBUFFORCE is used to avoid having to raise the system wide max. Not reloadable.
|
||||
# SO_RCVBUFFORCE is used to avoid having to raise the system wide max
|
||||
#use_system_route_table_buffer_size: 0
|
||||
|
||||
# Configure logging level
|
||||
@@ -412,16 +416,14 @@ logging:
|
||||
# Handshakes are sent to all known addresses at each interval with a linear backoff,
|
||||
# Wait try_interval after the 1st attempt, 2 * try_interval after the 2nd, etc, until the handshake is older than timeout
|
||||
# A 100ms interval with the default 10 retries will give a handshake 5.5 seconds to resolve before timing out
|
||||
# Not reloadable.
|
||||
#try_interval: 100ms
|
||||
#retries: 20
|
||||
|
||||
# query_buffer is the size of the buffer channel for querying lighthouses, drops are recorded in the lighthouse.query.dropped metric.
|
||||
# Not reloadable.
|
||||
#query_buffer: 1024
|
||||
|
||||
# trigger_buffer is the size of the buffer channel for quickly sending handshakes
|
||||
# after receiving the response for lighthouse queries. Not reloadable.
|
||||
# after receiving the response for lighthouse queries
|
||||
#trigger_buffer: 64
|
||||
|
||||
# Tunnel manager settings
|
||||
|
||||
@@ -0,0 +1,40 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"log/slog"
|
||||
"runtime"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
)
|
||||
|
||||
// Staged receive (tun.staged.workers) moves decryption off each udp listener onto worker goroutines, behind which an
|
||||
// ordered writer commits every batch in arrival order. It reuses the inline packet handlers: staging changes ownership
|
||||
// and scheduling, not policy. Each routine has its own workers and writer, so order is per routine. Full queues block
|
||||
// the listener. A read error drains the batches in flight, while shutdown waits for the workers and then drops what
|
||||
// is left. Each routine keeps six batches; at listen.batch=64 with GRO their buffers take about 24 MiB per routine.
|
||||
//
|
||||
// Metrics are registered only for active pipelines. flow.rx.batches counts batches handed to the writer and
|
||||
// flow.rx.inline those an idle listener handled itself; their rates show whether staging is used.
|
||||
|
||||
// stagedConfig is tun.staged. workers is per routine; zero keeps receive inline.
|
||||
type stagedConfig struct {
|
||||
workers int
|
||||
// inlineBelow is the packet count below which an idle listener skips the worker handoff
|
||||
inlineBelow int
|
||||
}
|
||||
|
||||
// parseStagedConfig enables staging on Linux only; 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{}
|
||||
}
|
||||
// 256 is the measured crossover
|
||||
sc.inlineBelow = 256
|
||||
l.Info("Staged receive processing enabled", "workers", sc.workers)
|
||||
return sc
|
||||
}
|
||||
+303
@@ -0,0 +1,303 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
)
|
||||
|
||||
// handoffConn is a udp conn that receives in batches of a fixed shape, so staged receive can have replacement buffers
|
||||
// ready for every batch it keeps.
|
||||
type handoffConn interface {
|
||||
ListenOut(udp.EncReader, func([][]byte) [][]byte) error
|
||||
HandoffShape() (n, size int)
|
||||
}
|
||||
|
||||
const stagedRxSlots = 6
|
||||
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
|
||||
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{}
|
||||
}
|
||||
|
||||
// decryptRxItems decrypts the data packets among items in place, skipping the replays checkReplays marked. Recording
|
||||
// the counters is left to readOutsidePackets on the writer, which also handles the packets without a tunnel.
|
||||
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
|
||||
// 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.
|
||||
chunks []rxChunk
|
||||
nChunks int
|
||||
}
|
||||
|
||||
func (b *rxBatch) reset() {
|
||||
clear(b.items)
|
||||
b.items = b.items[: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
|
||||
conn handoffConn
|
||||
// jobs feeds the decrypt workers. The listener is the only producer and closes it once the writer has drained.
|
||||
jobs chan *rxChunk
|
||||
workers sync.WaitGroup
|
||||
// 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 is the batch the listener is filling. The others wait in free, or travel to the writer on ordered and come
|
||||
// back through free; inFlight counts those, and the writer drops it only once it is done with a batch.
|
||||
cur *rxBatch
|
||||
free chan *rxBatch
|
||||
ordered chan *rxBatch
|
||||
inFlight atomic.Int32
|
||||
writerDone chan struct{}
|
||||
|
||||
metricBatches metrics.Counter
|
||||
metricInline metrics.Counter
|
||||
}
|
||||
|
||||
func newStagedRx(f *Interface, q int, wrxc *rxContext, conn handoffConn) *stagedRx {
|
||||
p := &stagedRx{
|
||||
f: f,
|
||||
q: q,
|
||||
conn: conn,
|
||||
h: &header.H{},
|
||||
hostmapCache: map[uint32]*HostInfo{},
|
||||
wrxc: wrxc,
|
||||
free: make(chan *rxBatch, stagedRxSlots),
|
||||
ordered: make(chan *rxBatch, stagedRxSlots),
|
||||
writerDone: make(chan struct{}),
|
||||
metricBatches: metrics.GetOrRegisterCounter("flow.rx.batches", nil),
|
||||
metricInline: metrics.GetOrRegisterCounter("flow.rx.inline", nil),
|
||||
}
|
||||
n := f.staged.workers
|
||||
p.jobs = make(chan *rxChunk, stagedRxSlots*2*n)
|
||||
for range n {
|
||||
p.workers.Go(p.decrypt)
|
||||
}
|
||||
bufs, size := conn.HandoffShape()
|
||||
for i := range stagedRxSlots {
|
||||
// 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*n)}
|
||||
for j := range b.chunks {
|
||||
b.chunks[j].done = make(chan struct{}, 1)
|
||||
}
|
||||
if i == 0 {
|
||||
// The first batch reads into the conn's own buffers; every other one brings its own
|
||||
p.cur = b
|
||||
continue
|
||||
}
|
||||
b.bufs = make([][]byte, bufs)
|
||||
for j := range b.bufs {
|
||||
b.bufs[j] = make([]byte, size)
|
||||
}
|
||||
p.free <- b
|
||||
}
|
||||
go p.writer()
|
||||
return p
|
||||
}
|
||||
|
||||
// decrypt is a worker: it decrypts the chunks it is handed and signals each one done.
|
||||
func (p *stagedRx) decrypt() {
|
||||
nb := make([]byte, 12)
|
||||
for c := range p.jobs {
|
||||
decryptRxItems(c.items, nb)
|
||||
c.done <- struct{}{}
|
||||
}
|
||||
}
|
||||
|
||||
// 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() error {
|
||||
defer p.close()
|
||||
return p.conn.ListenOut(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) {
|
||||
it := rxItem{packet: packet, via: via}
|
||||
p.classify(&it)
|
||||
p.cur.items = append(p.cur.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. It is speculative: readOutsidePackets resolves the tunnel again on the writer and
|
||||
// uses the worker's result only when it is still the same one.
|
||||
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.ci, it.counter = ci, h.MessageCounter
|
||||
}
|
||||
|
||||
// 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()
|
||||
return p.cur.bufs
|
||||
}
|
||||
|
||||
// endBatch hands the batch to the workers and the ordered writer, then takes a free batch.
|
||||
func (p *stagedRx) endBatch() {
|
||||
clear(p.hostmapCache)
|
||||
b := p.cur
|
||||
n := len(b.items)
|
||||
if n == 0 {
|
||||
b.reset()
|
||||
return
|
||||
}
|
||||
p.checkReplays(b.items)
|
||||
|
||||
if p.inFlight.Load() == 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.processInline(b, p.wrxc)
|
||||
b.reset()
|
||||
return
|
||||
}
|
||||
|
||||
parts := max(1, min(len(b.chunks), n/rxChunkMin))
|
||||
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.jobs <- &b.chunks[i]
|
||||
}
|
||||
p.metricBatches.Inc(1)
|
||||
p.inFlight.Add(1)
|
||||
p.ordered <- b
|
||||
// With every batch in flight this waits for the writer, the socket buffer absorbs the backlog meanwhile
|
||||
p.cur = <-p.free
|
||||
}
|
||||
|
||||
// checkReplays marks the replays among items before anything decrypts them, as Decrypt checks before it decrypts,
|
||||
// taking each tunnel's lock once per run of its packets rather than once per packet. The window only moves forward
|
||||
// until the writer records these counters, so a stale check can only let a replay through to acceptDecrypted, which
|
||||
// rejects it.
|
||||
func (p *stagedRx) checkReplays(items []rxItem) {
|
||||
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(p.f.l, items[i].counter) {
|
||||
items[i].err = ErrAlreadySeen
|
||||
}
|
||||
}
|
||||
ci.decryptLock.Unlock()
|
||||
}
|
||||
}
|
||||
|
||||
// processInline decrypts and commits a batch on the calling goroutine, then flushes the tun.
|
||||
func (p *stagedRx) processInline(b *rxBatch, rxc *rxContext) {
|
||||
decryptRxItems(b.items, rxc.nb)
|
||||
p.commit(b.items, rxc)
|
||||
p.f.flushOutside(rxc)
|
||||
}
|
||||
|
||||
// commit runs every item through readOutsidePackets in arrival order, handing it the worker's result for a data
|
||||
// packet, exactly as inline receive handles them.
|
||||
func (p *stagedRx) commit(items []rxItem, rxc *rxContext) {
|
||||
for i := range items {
|
||||
it := &items[i]
|
||||
if it.ci != nil {
|
||||
rxc.decrypted = it
|
||||
}
|
||||
p.f.readOutsidePackets(ViaSender{UdpAddr: it.via}, it.packet, rxc)
|
||||
rxc.decrypted = nil
|
||||
}
|
||||
}
|
||||
|
||||
// writer is the ordered receive stage: it commits each batch chunk by chunk as the workers finish them, so the commit
|
||||
// overlaps the workers still on later chunks, then flushes the tun and returns the batch.
|
||||
func (p *stagedRx) writer() {
|
||||
defer close(p.writerDone)
|
||||
for b := range p.ordered {
|
||||
// Once the tun is going away a write would only log errors, so only wait out the workers
|
||||
closed := p.f.closed.Load()
|
||||
for i := range b.nChunks {
|
||||
c := &b.chunks[i]
|
||||
<-c.done
|
||||
if !closed {
|
||||
p.commit(c.items, p.wrxc)
|
||||
}
|
||||
}
|
||||
if !closed {
|
||||
p.f.flushOutside(p.wrxc)
|
||||
}
|
||||
b.reset()
|
||||
p.inFlight.Add(-1)
|
||||
p.free <- b
|
||||
}
|
||||
}
|
||||
|
||||
// close stops the writer once it has committed everything in flight, in order, then the workers.
|
||||
func (p *stagedRx) close() {
|
||||
close(p.ordered)
|
||||
<-p.writerDone
|
||||
close(p.jobs)
|
||||
p.workers.Wait()
|
||||
}
|
||||
+219
@@ -0,0 +1,219 @@
|
||||
//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.processInline(&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.processInline(&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))
|
||||
}
|
||||
|
||||
// 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)
|
||||
}
|
||||
+489
@@ -0,0 +1,489 @@
|
||||
//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 tun queue 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) 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}
|
||||
}
|
||||
|
||||
// adaptive is staging with the inline threshold parseStagedConfig sets.
|
||||
func adaptive(n int) stagedConfig {
|
||||
return stagedConfig{workers: n, inlineBelow: 256}
|
||||
}
|
||||
|
||||
func stagedName(sc stagedConfig) string {
|
||||
switch {
|
||||
case sc.workers == 0:
|
||||
return "inline"
|
||||
case sc.inlineBelow > 0:
|
||||
return "adaptive"
|
||||
default:
|
||||
return "staged"
|
||||
}
|
||||
}
|
||||
|
||||
// TestFlowStagedFallback: a conn that cannot hand off its batches keeps receive 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)
|
||||
wire := wireFor(t, sender, batches)
|
||||
require.Equal(t, want, decryptWire(t, receiver, wire))
|
||||
rx0 := rxBatches.Count()
|
||||
receiver.receive(plainConn{&rxConn{wire: wire, batchLen: 16}})
|
||||
require.Equal(t, want, receiver.tun.segments(t))
|
||||
require.Equal(t, rx0, rxBatches.Count())
|
||||
}
|
||||
|
||||
// wireFor produces the wire packets the sender emits for batches.
|
||||
func wireFor(t testing.TB, sender *flowTestPeer, batches [][]tio.Packet) [][]byte {
|
||||
t.Helper()
|
||||
sender.f.listenIn(newFlowBatchQueue(batches), 0)
|
||||
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) HandoffShape() (n, size int) {
|
||||
n = c.batchLen
|
||||
for _, s := range c.sizes {
|
||||
n = max(n, s)
|
||||
}
|
||||
return n, udp.MTU
|
||||
}
|
||||
|
||||
func (c *rxConn) ListenOut(r udp.EncReader, handoff func(bufs [][]byte) [][]byte) error {
|
||||
n, _ := c.HandoffShape()
|
||||
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
|
||||
}
|
||||
|
||||
// plainConn hides HandoffShape, so receive stays inline.
|
||||
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 receive paths apply the same 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, 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))
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestFlowStagedAESGCM runs the parsed configuration with the real AES cipher. Receive decryption has no nonce
|
||||
// ordering requirement, so it stays staged in BoringCrypto and FIPS builds too.
|
||||
func TestFlowStagedAESGCM(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, 2, receiver.f.staged.workers)
|
||||
batches, want := flowTestBatches(4, 8, 1, 45)
|
||||
wire := wireFor(t, sender, batches)
|
||||
rx0 := rxBatches.Count()
|
||||
receiver.receive(&rxConn{wire: wire, batchLen: 512})
|
||||
require.Greater(t, rxBatches.Count(), rx0)
|
||||
require.Equal(t, want, receiver.tun.segments(t))
|
||||
}
|
||||
@@ -1,6 +1,6 @@
|
||||
module github.com/slackhq/nebula
|
||||
|
||||
go 1.27.2
|
||||
go 1.26.0
|
||||
|
||||
require (
|
||||
dario.cat/mergo v1.0.2
|
||||
@@ -33,7 +33,7 @@ require (
|
||||
golang.zx2c4.com/wireguard/windows v1.0.1
|
||||
google.golang.org/protobuf v1.36.12
|
||||
gopkg.in/yaml.v3 v3.0.1
|
||||
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980
|
||||
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe
|
||||
)
|
||||
|
||||
require (
|
||||
@@ -45,6 +45,5 @@ require (
|
||||
github.com/prometheus/common v0.70.1 // indirect
|
||||
github.com/prometheus/procfs v0.21.1 // indirect
|
||||
github.com/vishvananda/netns v0.0.5 // indirect
|
||||
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc // indirect
|
||||
golang.org/x/time v0.15.0 // indirect
|
||||
golang.org/x/time v0.5.0 // indirect
|
||||
)
|
||||
@@ -157,8 +157,6 @@ golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPh
|
||||
golang.org/x/crypto v0.0.0-20210322153248-0c34fe9e7dc2/go.mod h1:T9bdIzuCu7OtxOm1hfPfRQxPLYneinmdGuTeoZ9dtd4=
|
||||
golang.org/x/crypto v0.57.0 h1:3ZVCjf8Ggz7zneR/EHRVx68Ctf+2pmIMP2UFhh9cC6M=
|
||||
golang.org/x/crypto v0.57.0/go.mod h1:Fdz0i5U6CoizGwLda9DttjSk6qlZo25zYNtR+ycvuZA=
|
||||
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc h1:TS73t7x3KarrNd5qAipmspBDS1rkMcgVG/fS1aRb4Rc=
|
||||
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc/go.mod h1:A+z0yzpGtvnG90cToK5n2tu8UJVP2XUATh+r+sfOOOc=
|
||||
golang.org/x/lint v0.0.0-20200302205851-738671d3881b/go.mod h1:3xt1FjdF8hUf6vQPIChWIBhFzV8gjjsPE/fR3IyQdNY=
|
||||
golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
|
||||
golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
|
||||
@@ -205,8 +203,8 @@ golang.org/x/term v0.46.0/go.mod h1:+K02xbkittuwc0Am4abfA3Fc+XRGXkvBXNO88NCXPoc=
|
||||
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
|
||||
golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
|
||||
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
|
||||
golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
|
||||
golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
|
||||
golang.org/x/time v0.5.0 h1:o7cqy6amK/52YcAKIPlM3a+Fpj35zvRj2TP+e1xFSfk=
|
||||
golang.org/x/time v0.5.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
|
||||
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
|
||||
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
|
||||
golang.org/x/tools v0.0.0-20200130002326-2f3ba24bd6e7/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
|
||||
@@ -245,5 +243,5 @@ gopkg.in/yaml.v2 v2.3.0/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
|
||||
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
|
||||
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
|
||||
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
|
||||
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980 h1:ribyrTYQ/QYeUIs8x8bVLYwGyepa7RnHLqJzegT5YYk=
|
||||
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980/go.mod h1:pK/dapF5Bf3KGW7/kd5CI5IC4lYh9FMFY1qETAIGLXk=
|
||||
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe h1:fre4i6mv4iBuz5lCMOzHD1rH1ljqHWSICFmZRbbgp3g=
|
||||
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe/go.mod h1:sxc3Uvk/vHcd3tj7/DHVBoR5wvWT/MmRq2pj7HRJnwU=
|
||||
+5
-7
@@ -316,9 +316,9 @@ type cachedPacketMetrics struct {
|
||||
func NewHostMapFromConfig(l *slog.Logger, c *config.C) *HostMap {
|
||||
hm := newHostMap(l)
|
||||
|
||||
hm.reload(c, true, nil)
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
hm.reload(c, false, r)
|
||||
hm.reload(c, true)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
hm.reload(c, false)
|
||||
})
|
||||
|
||||
l.Info("Main HostMap created", "preferredRanges", hm.GetPreferredRanges())
|
||||
@@ -337,8 +337,7 @@ func newHostMap(l *slog.Logger) *HostMap {
|
||||
}
|
||||
}
|
||||
|
||||
// r is nil on the initial load
|
||||
func (hm *HostMap) reload(c *config.C, initial bool, r *config.Reload) {
|
||||
func (hm *HostMap) reload(c *config.C, initial bool) {
|
||||
if initial || c.HasChanged("preferred_ranges") {
|
||||
var preferredRanges []netip.Prefix
|
||||
rawPreferredRanges := c.GetStringSlice("preferred_ranges", []string{})
|
||||
@@ -349,9 +348,8 @@ func (hm *HostMap) reload(c *config.C, initial bool, r *config.Reload) {
|
||||
if err != nil {
|
||||
hm.l.Warn("Failed to parse preferred ranges, ignoring",
|
||||
"error", err,
|
||||
"range", rawPreferredRange,
|
||||
"range", rawPreferredRanges,
|
||||
)
|
||||
r.Failed()
|
||||
continue
|
||||
}
|
||||
|
||||
|
||||
@@ -447,16 +447,3 @@ func TestHostInfo_markOutOnly(t *testing.T) {
|
||||
assert.True(t, h.markOut(6), "a relayed send must not consume the epoch edge")
|
||||
assert.False(t, h.markOut(6))
|
||||
}
|
||||
|
||||
// A preferred range that doesn't parse is skipped and the rest are used, the reload says one was skipped
|
||||
func TestHostMap_reloadBadPreferredRangeFails(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.LoadString("preferred_ranges: [10.0.0.0/8]\n"))
|
||||
hm := NewHostMapFromConfig(l, c)
|
||||
|
||||
res := c.ReloadConfigString("preferred_ranges: [10.0.0.0/8, nope]\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.Equal(t, []netip.Prefix{netip.MustParsePrefix("10.0.0.0/8")}, hm.GetPreferredRanges())
|
||||
}
|
||||
+23
-17
@@ -65,6 +65,7 @@ type InterfaceConfig struct {
|
||||
// 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
|
||||
}
|
||||
@@ -99,6 +100,7 @@ type Interface struct {
|
||||
// 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
|
||||
@@ -248,6 +250,7 @@ func NewInterface(ctx context.Context, c *InterfaceConfig) (*Interface, error) {
|
||||
conntrackCacheTimeout: c.ConntrackCacheTimeout,
|
||||
cpuAffinity: c.CpuAffinity,
|
||||
pinThreads: c.PinThreads,
|
||||
staged: c.staged,
|
||||
udpTxErrLimiter: udpTxErrLimiter,
|
||||
udpRelayTxErrLimiter: udpRelayTxErrLimiter,
|
||||
txOversizeLimiter: txOversizeLimiter,
|
||||
@@ -384,8 +387,8 @@ type rxContext struct {
|
||||
hostmapCache map[uint32]*HostInfo
|
||||
lhh *LightHouseHandler
|
||||
ctCache *firewall.ConntrackCacheTicker
|
||||
// relayBatch holds forwarded relay packets, which borrow their receive buffers until flushed
|
||||
relayBatch *batch.SendBatch
|
||||
// decrypted is staged receive's result for the packet being handled, decrypted ahead of time on a worker
|
||||
decrypted *rxItem
|
||||
}
|
||||
|
||||
func newRxContext(f *Interface, q int) *rxContext {
|
||||
@@ -398,7 +401,6 @@ func newRxContext(f *Interface, q int) *rxContext {
|
||||
hostmapCache: map[uint32]*HostInfo{},
|
||||
lhh: f.lightHouse.NewRequestHandler(),
|
||||
ctCache: firewall.NewConntrackCacheTicker(f.ctx, f.l, f.conntrackCacheTimeout),
|
||||
relayBatch: batch.NewSendBatch(f.writers[q], batch.SendBatchCap, 0),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -416,15 +418,21 @@ func (f *Interface) listenOut(i int) {
|
||||
f.readOutsidePackets(ViaSender{UdpAddr: fromUdpAddr}, payload, rxc)
|
||||
}
|
||||
|
||||
flusher := func() {
|
||||
f.flushSendBatch(rxc.relayBatch, i)
|
||||
if err := f.batchers[i].Flush(); err != nil {
|
||||
f.l.Error("Failed to flush tun coalescer", "error", err)
|
||||
}
|
||||
clear(rxc.hostmapCache)
|
||||
flusher := func(bufs [][]byte) [][]byte {
|
||||
f.flushOutside(rxc)
|
||||
return bufs
|
||||
}
|
||||
|
||||
err := li.ListenOut(listener, flusher)
|
||||
var err error
|
||||
if hc, ok := li.(handoffConn); ok && f.staged.workers > 0 {
|
||||
// Every stage on its own goroutine, see flow_rx.go. rxc becomes the ordered writer's context.
|
||||
err = newStagedRx(f, i, rxc, hc).listen()
|
||||
} else {
|
||||
if f.staged.workers > 0 {
|
||||
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
|
||||
@@ -513,11 +521,10 @@ func (f *Interface) flushSendBatch(sb *batch.SendBatch, q int) {
|
||||
|
||||
func (f *Interface) RegisterConfigChangeCallbacks(c *config.C) {
|
||||
c.RegisterReloadCallback(f.reloadFirewall)
|
||||
for _, reload := range []func(*config.C){
|
||||
f.reloadSendRecvError, f.reloadAcceptRecvError, f.reloadDisconnectInvalid, f.reloadMisc,
|
||||
} {
|
||||
c.RegisterReloadCallback(func(c *config.C, _ *config.Reload) { reload(c) })
|
||||
}
|
||||
c.RegisterReloadCallback(f.reloadSendRecvError)
|
||||
c.RegisterReloadCallback(f.reloadAcceptRecvError)
|
||||
c.RegisterReloadCallback(f.reloadDisconnectInvalid)
|
||||
c.RegisterReloadCallback(f.reloadMisc)
|
||||
|
||||
for _, udpConn := range f.writers {
|
||||
c.RegisterReloadCallback(udpConn.ReloadConfig)
|
||||
@@ -534,7 +541,7 @@ func (f *Interface) reloadDisconnectInvalid(c *config.C) {
|
||||
}
|
||||
}
|
||||
|
||||
func (f *Interface) reloadFirewall(c *config.C, r *config.Reload) {
|
||||
func (f *Interface) reloadFirewall(c *config.C) {
|
||||
cs := f.pki.getCertState()
|
||||
curCert := cs.getCertificate(cert.Version2)
|
||||
if curCert == nil {
|
||||
@@ -553,7 +560,6 @@ func (f *Interface) reloadFirewall(c *config.C, r *config.Reload) {
|
||||
fw, err := NewFirewallFromConfig(f.l, cs, c)
|
||||
if err != nil {
|
||||
f.l.Error("Error while creating firewall during reload", "error", err)
|
||||
r.Failed()
|
||||
return
|
||||
}
|
||||
|
||||
|
||||
+4
-26
@@ -65,10 +65,10 @@ func TestReloadFirewall_CertUnsafeNetworksChanged(t *testing.T) {
|
||||
pki.cs.Store(&CertState{v2Cert: c2, initiatingVersion: cert.Version2})
|
||||
|
||||
// Reload with the same YAML so HasChanged("firewall") reports false.
|
||||
require.NoError(t, cfg.ReloadConfigString(rawYAML).Err)
|
||||
require.NoError(t, cfg.ReloadConfigString(rawYAML))
|
||||
require.False(t, cfg.HasChanged("firewall"))
|
||||
|
||||
f.reloadFirewall(cfg, nil)
|
||||
f.reloadFirewall(cfg)
|
||||
|
||||
assert.NotSame(t, fw, f.firewall, "firewall pointer should have been replaced")
|
||||
assert.Equal(t, newUnsafe, f.firewall.unsafeNetworks)
|
||||
@@ -113,30 +113,8 @@ func TestReloadFirewall_NoChange(t *testing.T) {
|
||||
l: l,
|
||||
}
|
||||
|
||||
require.NoError(t, cfg.ReloadConfigString(rawYAML).Err)
|
||||
f.reloadFirewall(cfg, nil)
|
||||
require.NoError(t, cfg.ReloadConfigString(rawYAML))
|
||||
f.reloadFirewall(cfg)
|
||||
|
||||
assert.Same(t, fw, f.firewall, "firewall should not have been replaced")
|
||||
}
|
||||
|
||||
// Rules that don't parse keep the old firewall, and the reload says it could not apply them
|
||||
func TestReloadFirewall_BadRulesFailTheReload(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
pki := &PKI{}
|
||||
pki.cs.Store(&CertState{v2Cert: &dummyCert{version: cert.Version2, networks: []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")}}, initiatingVersion: cert.Version2})
|
||||
|
||||
rules := func(proto string) string {
|
||||
return "firewall:\n outbound:\n - port: any\n proto: any\n host: any\n inbound:\n - port: any\n proto: " + proto + "\n host: any\n"
|
||||
}
|
||||
cfg := config.NewC(l)
|
||||
require.NoError(t, cfg.LoadString(rules("any")))
|
||||
fw, err := NewFirewallFromConfig(l, pki.getCertState(), cfg)
|
||||
require.NoError(t, err)
|
||||
f := &Interface{pki: pki, firewall: fw, l: l}
|
||||
cfg.RegisterReloadCallback(f.reloadFirewall)
|
||||
|
||||
res := cfg.ReloadConfigString(rules("nope"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.Same(t, fw, f.firewall)
|
||||
}
|
||||
+4
-10
@@ -138,21 +138,18 @@ func NewLightHouseFromConfig(ctx context.Context, l *slog.Logger, c *config.C, c
|
||||
h.metrics = newLighthouseMetrics()
|
||||
}
|
||||
|
||||
err := h.reload(c, true, nil)
|
||||
err := h.reload(c, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("lighthouse.am_lighthouse", "listen.port", "handshakes.query_buffer", "stats.lighthouse_metrics")
|
||||
err := h.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := h.reload(c, false)
|
||||
switch v := err.(type) {
|
||||
case *util.ContextualError:
|
||||
v.Log(l)
|
||||
r.Failed()
|
||||
case error:
|
||||
l.Error("failed to reload lighthouse", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -193,8 +190,7 @@ func (lh *LightHouse) GetUpdateInterval() int64 {
|
||||
return lh.interval.Load()
|
||||
}
|
||||
|
||||
// r is nil on the initial load
|
||||
func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
func (lh *LightHouse) reload(c *config.C, initial bool) error {
|
||||
if initial || c.HasChanged("lighthouse.advertise_addrs") {
|
||||
rawAdvAddrs := c.GetStringSlice("lighthouse.advertise_addrs", []string{})
|
||||
advAddrs := make([]netip.AddrPort, 0)
|
||||
@@ -229,7 +225,6 @@ func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error
|
||||
"addr", rawAddr,
|
||||
"entry", i+1,
|
||||
)
|
||||
r.Failed()
|
||||
continue
|
||||
}
|
||||
|
||||
@@ -388,7 +383,6 @@ func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error
|
||||
"relay", v,
|
||||
"error", err,
|
||||
)
|
||||
r.Failed()
|
||||
} else {
|
||||
lh.l.Info("Read relay from config", "relay", v)
|
||||
relaysForMe = append(relaysForMe, configRIP)
|
||||
|
||||
+14
-59
@@ -87,15 +87,15 @@ func TestReloadLighthouseInterval(t *testing.T) {
|
||||
lh.ifce = &mockEncWriter{}
|
||||
|
||||
// The first one routine is kicked off by main.go currently, lets make sure that one dies
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 5").Err)
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 5"))
|
||||
assert.Equal(t, int64(5), lh.interval.Load())
|
||||
|
||||
// Subsequent calls are killed off by the LightHouse.Reload function
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 10").Err)
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 10"))
|
||||
assert.Equal(t, int64(10), lh.interval.Load())
|
||||
|
||||
// If this completes then nothing is stealing our reload routine
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 11").Err)
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 11"))
|
||||
assert.Equal(t, int64(11), lh.interval.Load())
|
||||
}
|
||||
|
||||
@@ -296,7 +296,7 @@ func TestLighthouse_reload(t *testing.T) {
|
||||
require.NoError(t, err)
|
||||
c.ReloadConfigString(string(rc))
|
||||
|
||||
err = lh.reload(c, false, nil)
|
||||
err = lh.reload(c, false)
|
||||
require.NoError(t, err)
|
||||
}
|
||||
|
||||
@@ -334,7 +334,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
rc, err := yaml.Marshal(nc)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
|
||||
rl := lh.Query(staticHost)
|
||||
require.NotNil(t, rl)
|
||||
@@ -350,7 +350,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
rc, err = yaml.Marshal(nc)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
|
||||
rl = lh.Query(staticHost)
|
||||
require.NotNil(t, rl)
|
||||
@@ -358,7 +358,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("1.1.1.1:4242")}, rl.CopyAddrs([]netip.Prefix{}))
|
||||
|
||||
// Reload with the same config. An unchanged entry must not duplicate.
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
|
||||
rl = lh.Query(staticHost)
|
||||
require.NotNil(t, rl)
|
||||
@@ -373,7 +373,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
rc, err = yaml.Marshal(nc)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
|
||||
// Add a second host alongside the first. Both should be present, neither duplicated.
|
||||
nc = map[string]any{
|
||||
@@ -384,7 +384,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
rc, err = yaml.Marshal(nc)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
|
||||
rl = lh.Query(staticHost)
|
||||
require.NotNil(t, rl)
|
||||
@@ -406,7 +406,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
rc, err = yaml.Marshal(nc)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
|
||||
_, isStatic := lh.GetStaticHostList()[staticHost]
|
||||
assert.False(t, isStatic)
|
||||
@@ -966,13 +966,13 @@ func TestLighthouse_reloadRelaysTriggersUpdate(t *testing.T) {
|
||||
require.NoError(t, err)
|
||||
assert.Empty(t, lh.updateTrigger)
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6]\n").Err)
|
||||
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6]\n"))
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
|
||||
require.Len(t, lh.updateTrigger, 1)
|
||||
<-lh.updateTrigger
|
||||
|
||||
// The config changed but what we advertise did not, a bad entry is skipped
|
||||
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6, nope]\n").Err)
|
||||
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6, nope]\n"))
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
|
||||
assert.Empty(t, lh.updateTrigger)
|
||||
}
|
||||
@@ -988,57 +988,12 @@ func TestLighthouse_reloadAmRelayAlone(t *testing.T) {
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
|
||||
|
||||
// Relays aren't allowed to have relays, flipping am_relay alone must drop them and tell the lighthouses
|
||||
require.NoError(t, c.ReloadConfigString(base+" am_relay: true\n").Err)
|
||||
require.NoError(t, c.ReloadConfigString(base+" am_relay: true\n"))
|
||||
assert.Empty(t, lh.GetRelaysForMe())
|
||||
require.Len(t, lh.updateTrigger, 1)
|
||||
<-lh.updateTrigger
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(base+" am_relay: false\n").Err)
|
||||
require.NoError(t, c.ReloadConfigString(base+" am_relay: false\n"))
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
|
||||
require.Len(t, lh.updateTrigger, 1)
|
||||
}
|
||||
|
||||
func TestLighthouse_reloadRestartRequired(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
base := "lighthouse:\n am_lighthouse: true\n"
|
||||
require.NoError(t, c.LoadString(base+"listen:\n port: 4242\n"))
|
||||
|
||||
_, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
res := c.ReloadConfigString(base + "listen:\n port: 4242\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.RestartRequired)
|
||||
res = c.ReloadConfigString(base + "listen:\n port: 4243\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.RestartRequired)
|
||||
}
|
||||
|
||||
// A relay that doesn't parse is skipped and the rest are used, the reload says one was skipped
|
||||
func TestLighthouse_reloadBadRelayFails(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.LoadString("listen:\n port: 4242\n"))
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
res := c.ReloadConfigString("listen:\n port: 4242\nrelay:\n relays: [10.128.0.2, nope]\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.2")}, lh.GetRelaysForMe())
|
||||
}
|
||||
|
||||
// An advertise_addrs entry inside our own network is skipped and the rest are used, the reload says one was skipped
|
||||
func TestLighthouse_reloadAdvertiseAddrInNetworkFails(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.LoadString("listen:\n port: 4242\n"))
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
res := c.ReloadConfigString("listen:\n port: 4242\nlighthouse:\n advertise_addrs: [\"1.2.3.4:4242\", \"10.128.0.5:4242\"]\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("1.2.3.4:4242")}, lh.GetAdvertiseAddrs())
|
||||
}
|
||||
@@ -78,7 +78,7 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
wireSSHReload(l, ssh, c)
|
||||
var sshStart func()
|
||||
if c.GetBool("sshd.enabled", false) {
|
||||
sshStart, err = configSSH(l, ssh, c, nil)
|
||||
sshStart, err = configSSH(l, ssh, c)
|
||||
if err != nil {
|
||||
l.Warn("Failed to configure sshd, ssh debugging will not be available", "error", err)
|
||||
sshStart = nil
|
||||
@@ -197,7 +197,7 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
if err != nil {
|
||||
return nil, util.NewContextualError("Failed to open udp listener", m{"queue": i}, err)
|
||||
}
|
||||
udpServer.ReloadConfig(c, nil)
|
||||
udpServer.ReloadConfig(c)
|
||||
udpConns[i] = udpServer
|
||||
|
||||
// If port is dynamic, discover it before the next pass through the for loop
|
||||
@@ -244,6 +244,7 @@ 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)
|
||||
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
|
||||
@@ -296,6 +297,7 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
ConntrackCacheTimeout: conntrackCacheTimeout,
|
||||
CpuAffinity: cpuAffinity,
|
||||
PinThreads: pinThreads,
|
||||
staged: staged,
|
||||
l: l,
|
||||
}
|
||||
|
||||
@@ -311,16 +313,6 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
lightHouse.ifce = ifce
|
||||
|
||||
ifce.RegisterConfigChangeCallbacks(c)
|
||||
// These are only read at startup
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged(
|
||||
"routines", "tun.routines", "listen.routines", "firewall.conntrack.routine_cache_timeout",
|
||||
"listen.port", "listen.host", "stats.message_metrics",
|
||||
"handshakes.try_interval", "handshakes.retries", "handshakes.trigger_buffer",
|
||||
"tun.drop_local_broadcast", "tun.drop_multicast",
|
||||
)
|
||||
r.RestartRequiredIfChanged(osStartupOnlyKeys...)
|
||||
})
|
||||
ifce.reloadDisconnectInvalid(c)
|
||||
ifce.reloadSendRecvError(c)
|
||||
ifce.reloadAcceptRecvError(c)
|
||||
|
||||
@@ -1,6 +0,0 @@
|
||||
//go:build linux && !android && !e2e_testing
|
||||
|
||||
package nebula
|
||||
|
||||
// osStartupOnlyKeys are startup only keys that only matter on linux: udp batch size, udp offloads and thread pinning
|
||||
var osStartupOnlyKeys = []string{"listen.batch", "listen.udp_offloads", "tun.pin_threads", "tun.pin_threads_key", "tun.cpu_affinity"}
|
||||
@@ -1,6 +0,0 @@
|
||||
//go:build !linux || android || e2e_testing
|
||||
|
||||
package nebula
|
||||
|
||||
// osStartupOnlyKeys is empty, none of the OS specific startup keys matter here
|
||||
var osStartupOnlyKeys []string
|
||||
@@ -5,6 +5,7 @@ import (
|
||||
"net/netip"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
@@ -123,3 +124,23 @@ 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, inlineBelow: 256}
|
||||
require.Equal(t, want, staged(2))
|
||||
}
|
||||
+19
-13
@@ -25,7 +25,7 @@ var ErrOutOfWindow = errors.New("out of window packet")
|
||||
|
||||
// readOutsidePackets processes one received underlay packet.
|
||||
// Message payloads are decrypted IN PLACE, so packet must stay untouched
|
||||
// by the caller until the TUN and relay batches for queue q have been flushed.
|
||||
// by the caller until the batcher for queue q has been flushed
|
||||
func (f *Interface) readOutsidePackets(via ViaSender, packet []byte, rxc *rxContext) {
|
||||
h := rxc.h
|
||||
err := h.Parse(packet)
|
||||
@@ -129,7 +129,13 @@ func (f *Interface) readOutsidePackets(via ViaSender, packet []byte, rxc *rxCont
|
||||
return
|
||||
}
|
||||
|
||||
out, err := hostinfo.ConnectionState.Decrypt(f.l, h.MessageCounter, packet, rxc.nb)
|
||||
var out []byte
|
||||
if pre := rxc.decrypted; pre != nil && pre.ci == hostinfo.ConnectionState {
|
||||
// Staged receive already checked and decrypted this packet on a worker, only the replay window is left
|
||||
out, err = pre.ci.acceptDecrypted(f.l, h.MessageCounter, pre.out, pre.err)
|
||||
} else {
|
||||
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)
|
||||
@@ -233,14 +239,8 @@ func (f *Interface) handleOutsideRelayPacket(hostinfo *HostInfo, via ViaSender,
|
||||
// Forward this packet through the relay tunnel, rebuilding it in place.
|
||||
// Encode overwrites the old outer header, and the new AEAD tag lands where the old one was
|
||||
fwdBuf := packet[:0]
|
||||
out, err := f.prepareSendVia(targetHI, targetRelay, signedPayload, rxc.nb, fwdBuf, true)
|
||||
if err == nil {
|
||||
// Borrows the receive buffer, the listener's flush callback drains it before the buffer is reused
|
||||
rxc.relayBatch.Commit(out, targetHI.GetRemote())
|
||||
if rxc.relayBatch.Len() >= batch.SendBatchCap {
|
||||
f.flushSendBatch(rxc.relayBatch, rxc.q)
|
||||
}
|
||||
}
|
||||
//todo it would potentially be nice to batch these
|
||||
f.SendVia(targetHI, targetRelay, signedPayload, rxc.nb, fwdBuf, true, rxc.q)
|
||||
case TerminalType:
|
||||
hostinfo.logger(f.l).Error("Unexpected Relay Type of Terminal")
|
||||
return
|
||||
@@ -479,12 +479,18 @@ func parseV4(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// 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)
|
||||
}
|
||||
hostinfo.logger(f.l).Warn("Error while validating inbound packet", "error", err, "packet", out)
|
||||
return
|
||||
}
|
||||
|
||||
|
||||
@@ -1,242 +0,0 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"net/netip"
|
||||
"sync"
|
||||
"testing"
|
||||
|
||||
"github.com/flynn/noise"
|
||||
"github.com/gaissmai/bart"
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/noiseutil"
|
||||
"github.com/slackhq/nebula/overlay/batch"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
type relayBatchWrite struct {
|
||||
packets [][]byte
|
||||
remotes []netip.AddrPort
|
||||
batched bool
|
||||
}
|
||||
|
||||
type relayBatchConn struct {
|
||||
udp.NoopConn
|
||||
read func(udp.EncReader, func())
|
||||
writes []relayBatchWrite
|
||||
}
|
||||
|
||||
func (c *relayBatchConn) ListenOut(r udp.EncReader, flush func()) error {
|
||||
c.read(r, flush)
|
||||
return nil
|
||||
}
|
||||
|
||||
func (c *relayBatchConn) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error) {
|
||||
w := relayBatchWrite{remotes: append([]netip.AddrPort(nil), addrs...), batched: true}
|
||||
for _, b := range bufs {
|
||||
w.packets = append(w.packets, bytes.Clone(b))
|
||||
}
|
||||
c.writes = append(c.writes, w)
|
||||
return len(bufs), nil
|
||||
}
|
||||
|
||||
func (c *relayBatchConn) WriteTo(b []byte, addr netip.AddrPort) error {
|
||||
c.writes = append(c.writes, relayBatchWrite{packets: [][]byte{bytes.Clone(b)}, remotes: []netip.AddrPort{addr}})
|
||||
return nil
|
||||
}
|
||||
|
||||
func (c *relayBatchConn) packets() [][]byte {
|
||||
var packets [][]byte
|
||||
for _, w := range c.writes {
|
||||
packets = append(packets, w.packets...)
|
||||
}
|
||||
return packets
|
||||
}
|
||||
|
||||
type relayBatchPath struct {
|
||||
f *Interface
|
||||
conn *relayBatchConn
|
||||
source, target *HostInfo
|
||||
incoming, outgoing *Relay
|
||||
sourceKey noiseutil.CipherState
|
||||
cipher noise.CipherFunc
|
||||
counter uint64
|
||||
}
|
||||
|
||||
// Separate cipher instances let the reference SendVia path use the same keys and
|
||||
// counters without rewinding an AEAD instance (including FIPS nonce checks).
|
||||
func relayBatchKey(cipher noise.CipherFunc, id byte) noiseutil.CipherState {
|
||||
suite := noise.NewCipherSuite(noise.DH25519, cipher, noise.HashSHA256)
|
||||
return noiseutil.NewCipherState(noise.UnsafeNewCipherState(suite, [32]byte{id}, 0), cipher)
|
||||
}
|
||||
|
||||
func newRelayBatchPath(t *testing.T, cipher noise.CipherFunc) *relayBatchPath {
|
||||
t.Helper()
|
||||
l := test.NewLogger()
|
||||
conn := &relayBatchConn{}
|
||||
f := &Interface{
|
||||
ctx: t.Context(), l: l, hostMap: newHostMap(l), outside: conn,
|
||||
writers: []udp.Conn{conn}, lightHouse: &LightHouse{l: l},
|
||||
myVpnNetworksTable: &bart.Lite{}, metricTxDropped: metrics.NewCounter(),
|
||||
batchers: []*batch.MultiCoalescer{batch.NewMultiCoalescer(&capturingTun{}, l)},
|
||||
}
|
||||
f.connectionManager = &connectionManager{
|
||||
intf: f, relayUsed: map[uint32]struct{}{}, relayUsedLock: &sync.RWMutex{},
|
||||
}
|
||||
newHost := func(addr string, remote string, id byte) *HostInfo {
|
||||
h := &HostInfo{
|
||||
vpnAddrs: []netip.Addr{netip.MustParseAddr(addr)},
|
||||
ConnectionState: &ConnectionState{
|
||||
eKey: relayBatchKey(cipher, id), dKey: relayBatchKey(cipher, id), window: NewBits(ReplayWindow),
|
||||
},
|
||||
relayState: RelayState{relayForByAddr: map[netip.Addr]*Relay{}, relayForByIdx: map[uint32]*Relay{}},
|
||||
}
|
||||
u := netip.MustParseAddrPort(remote)
|
||||
h.remote.Store(&u)
|
||||
f.hostMap.Hosts[h.vpnAddrs[0]] = h
|
||||
return h
|
||||
}
|
||||
source := newHost("192.0.2.1", "198.51.100.1:4242", 1)
|
||||
target := newHost("192.0.2.2", "198.51.100.2:4242", 2)
|
||||
incoming := &Relay{Type: ForwardingType, State: Established, LocalIndex: 301, RemoteIndex: 302, PeerAddr: target.vpnAddrs[0]}
|
||||
outgoing := &Relay{Type: ForwardingType, State: Established, LocalIndex: 303, RemoteIndex: 304, PeerAddr: source.vpnAddrs[0]}
|
||||
source.relayState.InsertRelay(incoming.PeerAddr, incoming.LocalIndex, incoming)
|
||||
target.relayState.InsertRelay(outgoing.PeerAddr, outgoing.LocalIndex, outgoing)
|
||||
f.hostMap.Relays[incoming.LocalIndex] = source
|
||||
f.hostMap.Indexes[100] = source
|
||||
return &relayBatchPath{f: f, conn: conn, source: source, target: target, incoming: incoming, outgoing: outgoing, sourceKey: relayBatchKey(cipher, 1), cipher: cipher}
|
||||
}
|
||||
|
||||
func (p *relayBatchPath) wrap(t *testing.T, payload []byte) []byte {
|
||||
t.Helper()
|
||||
p.counter++
|
||||
b := header.Encode(make([]byte, header.Len), header.Version, header.Message, header.MessageRelay, p.incoming.LocalIndex, p.counter)
|
||||
b = append(b, payload...)
|
||||
b, err := p.sourceKey.EncryptDanger(b, b, nil, p.counter, make([]byte, 12))
|
||||
require.NoError(t, err)
|
||||
return b
|
||||
}
|
||||
|
||||
func (p *relayBatchPath) reference(payloads [][]byte) [][]byte {
|
||||
conn := &relayBatchConn{}
|
||||
f := &Interface{writers: []udp.Conn{conn}, connectionManager: p.f.connectionManager, l: p.f.l}
|
||||
h := &HostInfo{ConnectionState: &ConnectionState{eKey: relayBatchKey(p.cipher, 2)}}
|
||||
u := p.target.GetRemote()
|
||||
h.remote.Store(&u)
|
||||
for _, payload := range payloads {
|
||||
f.SendVia(h, p.outgoing, payload, make([]byte, 12), make([]byte, 0, len(payload)+header.MaxOverhead), false, 0)
|
||||
}
|
||||
return conn.packets()
|
||||
}
|
||||
|
||||
func TestRelayReceiveBatch(t *testing.T) {
|
||||
for _, cipher := range []noise.CipherFunc{noiseutil.CipherAESGCM, noise.CipherChaChaPoly} {
|
||||
t.Run(cipher.CipherName(), func(t *testing.T) {
|
||||
p := newRelayBatchPath(t, cipher)
|
||||
const count = 8
|
||||
var payloads, wire [][]byte
|
||||
for i := range count * 2 {
|
||||
payload := bytes.Repeat([]byte{byte(i)}, 64)
|
||||
payloads = append(payloads, payload)
|
||||
wire = append(wire, p.wrap(t, payload))
|
||||
}
|
||||
want := p.reference(payloads)
|
||||
// Model a listener reusing the same slots for the next receive batch.
|
||||
buffers := make([][]byte, count)
|
||||
for i := range buffers {
|
||||
buffers[i] = make([]byte, len(wire[i]))
|
||||
}
|
||||
p.conn.read = func(r udp.EncReader, flush func()) {
|
||||
for b := range 2 {
|
||||
for i := range count {
|
||||
copy(buffers[i], wire[b*count+i])
|
||||
r(p.source.GetRemote(), buffers[i])
|
||||
require.Len(t, p.conn.writes, b, "forwarding waits for the batch boundary")
|
||||
}
|
||||
flush()
|
||||
require.Len(t, p.conn.writes, b+1, "flush must send before receive slots are reused")
|
||||
for _, buffer := range buffers {
|
||||
clear(buffer)
|
||||
}
|
||||
}
|
||||
}
|
||||
p.f.listenOut(0)
|
||||
require.Equal(t, want, p.conn.packets())
|
||||
for _, w := range p.conn.writes {
|
||||
require.True(t, w.batched)
|
||||
require.Len(t, w.packets, count)
|
||||
for _, remote := range w.remotes {
|
||||
require.Equal(t, p.target.GetRemote(), remote)
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestRelayBatchMixedDestinations(t *testing.T) {
|
||||
p := newRelayBatchPath(t, noise.CipherChaChaPoly)
|
||||
first, second := p.target.GetRemote(), netip.MustParseAddrPort("198.51.100.3:4242")
|
||||
remotes := []netip.AddrPort{first, first, second, second, first}
|
||||
var payloads, wire [][]byte
|
||||
for i := range remotes {
|
||||
payload := []byte{byte(i)}
|
||||
payloads = append(payloads, payload)
|
||||
wire = append(wire, p.wrap(t, payload))
|
||||
}
|
||||
want := p.reference(payloads)
|
||||
p.conn.read = func(r udp.EncReader, flush func()) {
|
||||
for i, remote := range remotes {
|
||||
p.target.remote.Store(&remote)
|
||||
r(p.source.GetRemote(), wire[i])
|
||||
}
|
||||
flush()
|
||||
}
|
||||
p.f.listenOut(0)
|
||||
require.Equal(t, want, p.conn.packets())
|
||||
require.Len(t, p.conn.writes, 1, "WriteBatch splits runs by destination, the batch does not need to")
|
||||
require.Equal(t, remotes, p.conn.writes[0].remotes)
|
||||
}
|
||||
|
||||
func TestRelayBatchCapacity(t *testing.T) {
|
||||
p := newRelayBatchPath(t, noise.CipherChaChaPoly)
|
||||
p.conn.read = func(r udp.EncReader, flush func()) {
|
||||
for i := range batch.SendBatchCap + 1 {
|
||||
r(p.source.GetRemote(), p.wrap(t, []byte{byte(i)}))
|
||||
}
|
||||
require.Len(t, p.conn.writes, 1)
|
||||
require.Len(t, p.conn.writes[0].packets, batch.SendBatchCap)
|
||||
flush()
|
||||
}
|
||||
p.f.listenOut(0)
|
||||
require.Len(t, p.conn.writes, 2)
|
||||
require.Len(t, p.conn.writes[1].packets, 1)
|
||||
}
|
||||
|
||||
func TestRelayBatchRemovedTarget(t *testing.T) {
|
||||
for _, remove := range []string{"host", "relay", "disestablished"} {
|
||||
t.Run(remove, func(t *testing.T) {
|
||||
p := newRelayBatchPath(t, noise.CipherChaChaPoly)
|
||||
first, removed := p.wrap(t, []byte("first")), p.wrap(t, []byte("removed"))
|
||||
want := p.reference([][]byte{[]byte("first")})
|
||||
p.conn.read = func(r udp.EncReader, flush func()) {
|
||||
r(p.source.GetRemote(), first)
|
||||
switch remove {
|
||||
case "host":
|
||||
delete(p.f.hostMap.Hosts, p.target.vpnAddrs[0])
|
||||
case "relay":
|
||||
delete(p.target.relayState.relayForByAddr, p.source.vpnAddrs[0])
|
||||
case "disestablished":
|
||||
p.target.relayState.UpdateRelayForByIpState(p.source.vpnAddrs[0], Disestablished)
|
||||
}
|
||||
r(p.source.GetRemote(), removed)
|
||||
flush()
|
||||
}
|
||||
p.f.listenOut(0)
|
||||
require.Len(t, p.conn.writes, 1)
|
||||
require.Equal(t, want, p.conn.packets(), "only the packet accepted before removal is sent")
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -10,8 +10,8 @@ type batchWriter interface {
|
||||
}
|
||||
|
||||
// SendBatch accumulates encrypted UDP packets and flushes them via WriteBatch.
|
||||
// Each reader goroutine owns its own SendBatch; no locking is needed.
|
||||
// Slots can borrow receive buffers or be backed by an Arena (see its docs).
|
||||
// One SendBatch is owned by each listenIn goroutine; no locking is needed.
|
||||
// Slots are backed by an Arena (see its docs)
|
||||
type SendBatch struct {
|
||||
out batchWriter
|
||||
bufs [][]byte
|
||||
|
||||
@@ -41,16 +41,9 @@ func (e *NameError) Error() string {
|
||||
type DeviceFactory func(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, routines int) (Device, error)
|
||||
|
||||
func NewDeviceFromConfig(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, routines int) (Device, error) {
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.disabled")
|
||||
})
|
||||
|
||||
switch {
|
||||
case c.GetBool("tun.disabled", false):
|
||||
tun := newDisabledTun(vpnNetworks, c.GetInt("tun.tx_queue", 5000), c.GetBool("stats.message_metrics", false), l)
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.tx_queue", "stats.message_metrics")
|
||||
})
|
||||
return tun, nil
|
||||
|
||||
default:
|
||||
|
||||
@@ -38,17 +38,16 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
|
||||
l: l,
|
||||
}
|
||||
|
||||
err := t.reload(c, true, nil)
|
||||
err := t.reload(c, true)
|
||||
if err != nil {
|
||||
_ = file.Close()
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -68,7 +67,7 @@ func (t *tun) Activate() error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
|
||||
@@ -1,45 +0,0 @@
|
||||
//go:build (openbsd || netbsd) && !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"os"
|
||||
"regexp"
|
||||
"runtime"
|
||||
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
var deviceNameRE = regexp.MustCompile(`^tun[0-9]+$`)
|
||||
|
||||
// tunDevNeedsRestart is true when tun.dev asks for a particular tun that isn't the running one. Anything else takes the
|
||||
// first free one, and the one we have will do
|
||||
func tunDevNeedsRestart(name, running string) bool {
|
||||
return deviceNameRE.MatchString(name) && name != running
|
||||
}
|
||||
|
||||
// openTun opens /dev/name, or the first /dev/tunN nothing else has open when name is empty or not tunN
|
||||
func openTun(l *slog.Logger, name string) (int, string, error) {
|
||||
if name != "" && !deviceNameRE.MatchString(name) {
|
||||
// The name doesn't mean anything here, so like darwin a bad one isn't worth refusing to start over
|
||||
l.Warn("interface name must be tun[0-9]+ on "+runtime.GOOS+", ignoring", "name", name)
|
||||
name = ""
|
||||
}
|
||||
if name != "" {
|
||||
fd, err := unix.Open("/dev/"+name, os.O_RDWR, 0)
|
||||
return fd, name, err
|
||||
}
|
||||
for i := 0; ; i++ {
|
||||
name = fmt.Sprintf("tun%d", i)
|
||||
fd, err := unix.Open("/dev/"+name, os.O_RDWR, 0)
|
||||
if err == nil {
|
||||
return fd, name, nil
|
||||
}
|
||||
if !errors.Is(err, unix.EBUSY) {
|
||||
return -1, "", fmt.Errorf("no free tun device, %s: %w", name, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,80 +0,0 @@
|
||||
//go:build (openbsd || netbsd) && !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// A tun.dev that isn't tunN is ignored like darwin does, and the first free tun is used. Only naming a different tun
|
||||
// asks for a restart
|
||||
func TestTunReloadDevRestart(t *testing.T) {
|
||||
newWithDev := func(dev string) (*config.C, *tun, error) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("tun:\n dev: "+dev+"\n"))
|
||||
tn, err := newTun(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, false)
|
||||
if err == nil {
|
||||
t.Cleanup(func() { _ = tn.Close() })
|
||||
}
|
||||
return c, tn, err
|
||||
}
|
||||
if _, _, err := newWithDev(""); err != nil {
|
||||
t.Skipf("can't create a tun device here: %v", err)
|
||||
}
|
||||
c, tn, err := newWithDev("nope")
|
||||
require.NoError(t, err, "a bad name should fall back to a free tun")
|
||||
require.Regexp(t, `^tun[0-9]+$`, tn.Device)
|
||||
|
||||
for _, dev := range []string{"nope", "", tn.Device, "nope"} {
|
||||
res := c.ReloadConfigString("tun:\n dev: " + dev + "\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed, dev)
|
||||
assert.False(t, res.RestartRequired, dev)
|
||||
}
|
||||
|
||||
other := "tun0"
|
||||
if tn.Device == other {
|
||||
other = "tun1"
|
||||
}
|
||||
res := c.ReloadConfigString("tun:\n dev: " + other + "\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.Equal(t, []string{"tun.dev"}, res.RestartKeys)
|
||||
}
|
||||
|
||||
// An empty tun.dev takes the first tun nothing else has open. Reloading it empty, or naming the one we have, needs
|
||||
// no restart
|
||||
func TestTunEmptyDevPicksAFreeOne(t *testing.T) {
|
||||
newEmpty := func() (*config.C, *tun, error) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("tun: {}\n"))
|
||||
tn, err := newTun(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, false)
|
||||
if err == nil {
|
||||
t.Cleanup(func() { _ = tn.Close() })
|
||||
}
|
||||
return c, tn, err
|
||||
}
|
||||
c, first, err := newEmpty()
|
||||
if err != nil {
|
||||
t.Skipf("can't create a tun device here: %v", err)
|
||||
}
|
||||
_, second, err := newEmpty()
|
||||
require.NoError(t, err, "the second tun should skip the one the first has open")
|
||||
assert.NotEqual(t, first.Device, second.Device)
|
||||
|
||||
for _, cfg := range []string{
|
||||
"tun: {}\npunchy:\n punch: true\n",
|
||||
"tun:\n dev: " + first.Device + "\n",
|
||||
"tun: {}\n",
|
||||
} {
|
||||
res := c.ReloadConfigString(cfg)
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.False(t, res.RestartRequired, cfg)
|
||||
}
|
||||
}
|
||||
@@ -10,9 +10,6 @@ import (
|
||||
"github.com/slackhq/nebula/wfp"
|
||||
)
|
||||
|
||||
// interfaceBypassKeys are only read when the interface bypass is installed
|
||||
var interfaceBypassKeys = []string{"tun.windows_bypass_wdf"}
|
||||
|
||||
// installInterfaceBypass installs a WFP PERMIT filter scoped to the wintun interface LUID so inbound traffic on the
|
||||
// nebula adapter bypasses Windows Defender Firewall.
|
||||
func installInterfaceBypass(l *slog.Logger, luid uint64) closer {
|
||||
|
||||
@@ -4,9 +4,6 @@ package overlay
|
||||
|
||||
import "log/slog"
|
||||
|
||||
// interfaceBypassKeys is empty, windows-386 has no bypass
|
||||
var interfaceBypassKeys []string
|
||||
|
||||
// installInterfaceBypass is a no-op on windows-386 because we don't currently build for it.
|
||||
func installInterfaceBypass(_ *slog.Logger, _ uint64) closer {
|
||||
return nil
|
||||
|
||||
+24
-51
@@ -80,31 +80,17 @@ type ifreqAlias6 struct {
|
||||
Lifetime addrLifetime
|
||||
}
|
||||
|
||||
// utunIndex is the utun tun.dev asks for, or -1 for whichever is free. ok is false for a name that isn't utunN, which
|
||||
// also gets whichever is free
|
||||
func utunIndex(name string) (index int, ok bool) {
|
||||
if name == "" || name == "utun" {
|
||||
return -1, true
|
||||
}
|
||||
if _, err := fmt.Sscanf(name, "utun%d", &index); err != nil || index < 0 {
|
||||
return -1, false
|
||||
}
|
||||
return index, true
|
||||
}
|
||||
|
||||
// tunDevNeedsRestart is true when tun.dev asks for a particular utun that isn't the running one. Anything else takes
|
||||
// whichever is free, and the one we have will do
|
||||
func tunDevNeedsRestart(name, running string) bool {
|
||||
index, _ := utunIndex(name)
|
||||
return index >= 0 && fmt.Sprintf("utun%d", index) != running
|
||||
}
|
||||
|
||||
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
|
||||
ifIndex, ok := utunIndex(c.GetString("tun.dev", ""))
|
||||
if !ok {
|
||||
// NOTE: we don't make this error so we don't break existing
|
||||
// configs that set a name before it was used.
|
||||
l.Warn("interface name must be utun[0-9]+ on Darwin, ignoring")
|
||||
name := c.GetString("tun.dev", "")
|
||||
ifIndex := -1
|
||||
if name != "" && name != "utun" {
|
||||
_, err := fmt.Sscanf(name, "utun%d", &ifIndex)
|
||||
if err != nil || ifIndex < 0 {
|
||||
// NOTE: we don't make this error so we don't break existing
|
||||
// configs that set a name before it was used.
|
||||
l.Warn("interface name must be utun[0-9]+ on Darwin, ignoring")
|
||||
ifIndex = -1
|
||||
}
|
||||
}
|
||||
|
||||
fd, err := unix.Socket(unix.AF_SYSTEM, unix.SOCK_DGRAM, unix.AF_SYS_CONTROL)
|
||||
@@ -128,7 +114,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
return nil, fmt.Errorf("SYS_CONNECT: %v", err)
|
||||
}
|
||||
|
||||
name, err := unix.GetsockoptString(fd, unix.AF_SYS_CONTROL, _UTUN_OPT_IFNAME)
|
||||
name, err = unix.GetsockoptString(fd, unix.AF_SYS_CONTROL, _UTUN_OPT_IFNAME)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to retrieve tun name: %w", err)
|
||||
}
|
||||
@@ -146,20 +132,15 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
l: l,
|
||||
}
|
||||
|
||||
err = t.reload(c, true, nil)
|
||||
err = t.reload(c, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.mtu")
|
||||
if tunDevNeedsRestart(c.GetString("tun.dev", ""), t.Device) {
|
||||
r.RestartRequiredIfChanged("tun.dev")
|
||||
}
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -193,15 +174,14 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
|
||||
l: l,
|
||||
}
|
||||
|
||||
if err := t.reload(c, true, nil); err != nil {
|
||||
if err := t.reload(c, true); err != nil {
|
||||
_ = file.Close()
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
if err := t.reload(c, false, r); err != nil {
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
if err := t.reload(c, false); err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -288,7 +268,7 @@ func (t *tun) Activate() error {
|
||||
}
|
||||
|
||||
// Unsafe path routes
|
||||
return t.addRoutes(false, nil)
|
||||
return t.addRoutes(false)
|
||||
}
|
||||
|
||||
// activate4 assigns our vpn address as a /32 and routes the vpn network to the tun explicitly.
|
||||
@@ -386,7 +366,7 @@ func (t *tun) activate6(network netip.Prefix) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -407,18 +387,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
|
||||
if !initial {
|
||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
|
||||
// Ensure any routes we actually want are installed
|
||||
err = t.addRoutes(true, r)
|
||||
err = t.addRoutes(true)
|
||||
if err != nil {
|
||||
// Catch any stray logs
|
||||
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -511,7 +489,7 @@ func getLinkAddr(name string) (*netroute.LinkAddr, error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
func (t *tun) addRoutes(logErrors bool) error {
|
||||
// The route tree is still ours, the system routing table is not
|
||||
if t.hostOwned {
|
||||
return nil
|
||||
@@ -546,7 +524,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||
if logErrors {
|
||||
retErr.Log(t.l)
|
||||
rl.Failed()
|
||||
} else {
|
||||
return retErr
|
||||
}
|
||||
@@ -561,7 +538,7 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
func (t *tun) removeRoutes(routes []Route) error {
|
||||
linkAddr := t.linkAddr.Load()
|
||||
if t.hostOwned || linkAddr == nil {
|
||||
return nil
|
||||
@@ -574,12 +551,8 @@ func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
}
|
||||
|
||||
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 {
|
||||
if err != nil {
|
||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||
rl.Failed()
|
||||
} else {
|
||||
t.l.Info("Removed route", "route", r)
|
||||
}
|
||||
|
||||
@@ -72,8 +72,8 @@ func TestTunRoutesBeforeActivate(t *testing.T) {
|
||||
}}
|
||||
tn.Routes.Store(&routes)
|
||||
|
||||
assert.NoError(t, tn.addRoutes(true, nil))
|
||||
assert.NoError(t, tn.removeRoutes(routes, nil))
|
||||
assert.NoError(t, tn.addRoutes(true))
|
||||
assert.NoError(t, tn.removeRoutes(routes))
|
||||
}
|
||||
|
||||
// A tun.routes entry with no via is never installed, so removing it must not delete a route for the same cidr that
|
||||
@@ -96,23 +96,8 @@ func TestTunReloadLeavesRoutesItNeverInstalled(t *testing.T) {
|
||||
t.Cleanup(func() { _ = tn.Close() })
|
||||
require.NoError(t, tn.Activate())
|
||||
|
||||
res := c.ReloadConfigString("tun: {}\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed, "removing a route we never installed failed the reload")
|
||||
require.NoError(t, c.ReloadConfigString("tun: {}\n"))
|
||||
msgs, err := fetchRoutes()
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, lo0.Index, routeInterfaceIn(msgs, netip.MustParsePrefix(cidr)))
|
||||
}
|
||||
|
||||
// Only naming a different utun asks for a restart. Empty, plain utun and names that aren't utunN take whichever is free
|
||||
func TestTunDevNeedsRestart(t *testing.T) {
|
||||
for name, want := range map[string]bool{
|
||||
"": false,
|
||||
"utun": false,
|
||||
"nope": false,
|
||||
"utun7": false,
|
||||
"utun3": true,
|
||||
} {
|
||||
assert.Equal(t, want, tunDevNeedsRestart(name, "utun7"), name)
|
||||
}
|
||||
}
|
||||
@@ -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)
|
||||
}
|
||||
+10
-19
@@ -385,18 +385,16 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
},
|
||||
}
|
||||
|
||||
err = t.reload(c, true, nil)
|
||||
err = t.reload(c, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
closeOnErr = false
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.dev", "tun.mtu")
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -495,7 +493,7 @@ func (t *tun) Activate() error {
|
||||
}
|
||||
}
|
||||
|
||||
return t.addRoutes(false, nil)
|
||||
return t.addRoutes(false)
|
||||
}
|
||||
|
||||
func (t *tun) setMTU() error {
|
||||
@@ -511,7 +509,7 @@ func (t *tun) setMTU() error {
|
||||
return err
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -532,18 +530,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
|
||||
if !initial {
|
||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
|
||||
// Ensure any routes we actually want are installed
|
||||
err = t.addRoutes(true, r)
|
||||
err = t.addRoutes(true)
|
||||
if err != nil {
|
||||
// Catch any stray logs
|
||||
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -567,7 +563,7 @@ func (t *tun) Queues(int) ([]tio.Queue, error) {
|
||||
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
||||
}
|
||||
|
||||
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
func (t *tun) addRoutes(logErrors bool) error {
|
||||
routes := *t.Routes.Load()
|
||||
for _, r := range routes {
|
||||
if len(r.Via) == 0 || !r.Install {
|
||||
@@ -580,7 +576,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||
if logErrors {
|
||||
retErr.Log(t.l)
|
||||
rl.Failed()
|
||||
} else {
|
||||
return retErr
|
||||
}
|
||||
@@ -592,7 +587,7 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
func (t *tun) removeRoutes(routes []Route) error {
|
||||
for _, r := range routes {
|
||||
if len(r.Via) == 0 || !r.Install {
|
||||
// addRoutes never installs these
|
||||
@@ -600,12 +595,8 @@ func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
}
|
||||
|
||||
err := delRoute(r.Cidr, t.linkAddr)
|
||||
if errors.Is(err, unix.ESRCH) {
|
||||
// Already gone, which is what we wanted
|
||||
t.l.Info("Route was already removed", "route", r)
|
||||
} else if err != nil {
|
||||
if err != nil {
|
||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||
rl.Failed()
|
||||
} else {
|
||||
t.l.Info("Removed route", "route", r)
|
||||
}
|
||||
|
||||
+4
-5
@@ -47,17 +47,16 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
|
||||
l: l,
|
||||
}
|
||||
|
||||
err := t.reload(c, true, nil)
|
||||
err := t.reload(c, true)
|
||||
if err != nil {
|
||||
_ = file.Close()
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -68,7 +67,7 @@ func (t *tun) Activate() error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
|
||||
+14
-28
@@ -185,10 +185,6 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, multiqueue
|
||||
}
|
||||
|
||||
t.Device = name
|
||||
// Only read when we create the device, an fd handed to us already has its name and offloads
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.dev", "tun.use_offloads")
|
||||
})
|
||||
|
||||
return t, nil
|
||||
}
|
||||
@@ -232,24 +228,22 @@ func newTunGeneric(c *config.C, l *slog.Logger, fd int, vnetHdr bool, offloadFla
|
||||
l: l,
|
||||
}
|
||||
|
||||
if err = t.reload(c, true, nil); err != nil {
|
||||
if err = t.reload(c, true); err != nil {
|
||||
_ = t.Close()
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.tx_queue", "tun.use_system_route_table", "tun.use_system_route_table_buffer_size")
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
return t, nil
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
routeChange, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -303,7 +297,7 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
|
||||
if !initial {
|
||||
if oldMaxMTU != newMaxMTU {
|
||||
t.setMTU(r)
|
||||
t.setMTU()
|
||||
t.l.Info("Set max MTU", "mtu", t.MaxMTU, "oldMTU", oldMaxMTU)
|
||||
}
|
||||
|
||||
@@ -311,8 +305,7 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
for i := range t.vpnNetworks {
|
||||
err := t.setDefaultRoute(t.vpnNetworks[i])
|
||||
if err != nil {
|
||||
t.l.Error(err.Error())
|
||||
r.Failed()
|
||||
t.l.Warn(err.Error())
|
||||
} else {
|
||||
t.l.Info("Set default MTU", "mtu", t.DefaultMTU, "oldMTU", oldDefaultMTU)
|
||||
}
|
||||
@@ -320,14 +313,13 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
}
|
||||
|
||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||
t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
|
||||
t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
||||
|
||||
// Ensure any routes we actually want are installed
|
||||
err = t.addRoutes(true, r)
|
||||
err = t.addRoutes(true)
|
||||
if err != nil {
|
||||
// This should never be called since addRoutes should log its own errors in a reload condition
|
||||
util.LogWithContextIfNeeded("Failed to refresh routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -482,7 +474,7 @@ func (t *tun) Activate() error {
|
||||
t.deviceIndex = link.Attrs().Index
|
||||
|
||||
// Setup our default MTU
|
||||
t.setMTU(nil)
|
||||
t.setMTU()
|
||||
|
||||
// Set the transmit queue length
|
||||
ifrq := ifreqQLEN{Name: devName, Value: int32(t.TXQueueLen)}
|
||||
@@ -514,7 +506,7 @@ func (t *tun) Activate() error {
|
||||
}
|
||||
|
||||
// Set the routes
|
||||
if err = t.addRoutes(false, nil); err != nil {
|
||||
if err = t.addRoutes(false); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
@@ -527,13 +519,12 @@ func (t *tun) Activate() error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) setMTU(r *config.Reload) {
|
||||
func (t *tun) setMTU() {
|
||||
// Set the MTU on the device
|
||||
ifm := ifreqMTU{Name: t.deviceBytes(), MTU: int32(t.MaxMTU)}
|
||||
if err := ioctl(t.ioctlFd, unix.SIOCSIFMTU, uintptr(unsafe.Pointer(&ifm))); err != nil {
|
||||
// This is currently a non fatal condition because the route table must have the MTU set appropriately as well
|
||||
t.l.Error("Failed to set tun mtu", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -586,7 +577,7 @@ func (t *tun) setDefaultRoute(cidr netip.Prefix) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
func (t *tun) addRoutes(logErrors bool) error {
|
||||
// Path routes
|
||||
routes := *t.Routes.Load()
|
||||
for _, r := range routes {
|
||||
@@ -616,7 +607,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||
if logErrors {
|
||||
retErr.Log(t.l)
|
||||
rl.Failed()
|
||||
} else {
|
||||
return retErr
|
||||
}
|
||||
@@ -628,7 +618,7 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) {
|
||||
func (t *tun) removeRoutes(routes []Route) {
|
||||
for _, r := range routes {
|
||||
if !r.Install {
|
||||
continue
|
||||
@@ -652,12 +642,8 @@ func (t *tun) removeRoutes(routes []Route, rl *config.Reload) {
|
||||
}
|
||||
|
||||
err := netlink.RouteDel(&nr)
|
||||
if errors.Is(err, unix.ESRCH) {
|
||||
// Already gone, which is what we wanted
|
||||
t.l.Info("Route was already removed", "route", r)
|
||||
} else if err != nil {
|
||||
if err != nil {
|
||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||
rl.Failed()
|
||||
} else {
|
||||
t.l.Info("Removed route", "route", r)
|
||||
}
|
||||
|
||||
+24
-23
@@ -8,6 +8,7 @@ import (
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"os"
|
||||
"regexp"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
"unsafe"
|
||||
@@ -66,12 +67,24 @@ type tun struct {
|
||||
fd int
|
||||
}
|
||||
|
||||
var deviceNameRE = regexp.MustCompile(`^tun[0-9]+$`)
|
||||
|
||||
func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
|
||||
return nil, fmt.Errorf("newTunFromFd not supported in NetBSD")
|
||||
}
|
||||
|
||||
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
|
||||
fd, deviceName, err := openTun(l, c.GetString("tun.dev", ""))
|
||||
// Try to open tun device
|
||||
var err error
|
||||
deviceName := c.GetString("tun.dev", "")
|
||||
if deviceName == "" {
|
||||
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
|
||||
}
|
||||
if !deviceNameRE.MatchString(deviceName) {
|
||||
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
|
||||
}
|
||||
|
||||
fd, err := unix.Open("/dev/"+deviceName, os.O_RDWR, 0)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
@@ -90,20 +103,15 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
l: l,
|
||||
}
|
||||
|
||||
err = t.reload(c, true, nil)
|
||||
err = t.reload(c, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.mtu")
|
||||
if tunDevNeedsRestart(c.GetString("tun.dev", ""), t.Device) {
|
||||
r.RestartRequiredIfChanged("tun.dev")
|
||||
}
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -316,7 +324,7 @@ func (t *tun) Activate() error {
|
||||
}
|
||||
}
|
||||
|
||||
return t.addRoutes(false, nil)
|
||||
return t.addRoutes(false)
|
||||
}
|
||||
|
||||
func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
||||
@@ -331,7 +339,7 @@ func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
||||
return err
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -352,18 +360,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
|
||||
if !initial {
|
||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
|
||||
// Ensure any routes we actually want are installed
|
||||
err = t.addRoutes(true, r)
|
||||
err = t.addRoutes(true)
|
||||
if err != nil {
|
||||
// Catch any stray logs
|
||||
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -387,7 +393,7 @@ func (t *tun) Queues(int) ([]tio.Queue, error) {
|
||||
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
||||
}
|
||||
|
||||
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
func (t *tun) addRoutes(logErrors bool) error {
|
||||
routes := *t.Routes.Load()
|
||||
|
||||
for _, r := range routes {
|
||||
@@ -401,7 +407,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||
if logErrors {
|
||||
retErr.Log(t.l)
|
||||
rl.Failed()
|
||||
} else {
|
||||
return retErr
|
||||
}
|
||||
@@ -413,7 +418,7 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
func (t *tun) removeRoutes(routes []Route) error {
|
||||
for _, r := range routes {
|
||||
if len(r.Via) == 0 || !r.Install {
|
||||
// addRoutes never installs these
|
||||
@@ -421,12 +426,8 @@ func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
}
|
||||
|
||||
err := delRoute(r.Cidr, t.vpnNetworks)
|
||||
if errors.Is(err, unix.ESRCH) {
|
||||
// Already gone, which is what we wanted
|
||||
t.l.Info("Route was already removed", "route", r)
|
||||
} else if err != nil {
|
||||
if err != nil {
|
||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||
rl.Failed()
|
||||
} else {
|
||||
t.l.Info("Removed route", "route", r)
|
||||
}
|
||||
|
||||
+24
-23
@@ -8,6 +8,7 @@ import (
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"os"
|
||||
"regexp"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
"unsafe"
|
||||
@@ -57,12 +58,24 @@ type tun struct {
|
||||
fd int
|
||||
}
|
||||
|
||||
var deviceNameRE = regexp.MustCompile(`^tun[0-9]+$`)
|
||||
|
||||
func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
|
||||
return nil, fmt.Errorf("newTunFromFd not supported in openbsd")
|
||||
}
|
||||
|
||||
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
|
||||
fd, deviceName, err := openTun(l, c.GetString("tun.dev", ""))
|
||||
// Try to open tun device
|
||||
var err error
|
||||
deviceName := c.GetString("tun.dev", "")
|
||||
if deviceName == "" {
|
||||
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
|
||||
}
|
||||
if !deviceNameRE.MatchString(deviceName) {
|
||||
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
|
||||
}
|
||||
|
||||
fd, err := unix.Open("/dev/"+deviceName, os.O_RDWR, 0)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
@@ -81,20 +94,15 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
l: l,
|
||||
}
|
||||
|
||||
err = t.reload(c, true, nil)
|
||||
err = t.reload(c, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.mtu")
|
||||
if tunDevNeedsRestart(c.GetString("tun.dev", ""), t.Device) {
|
||||
r.RestartRequiredIfChanged("tun.dev")
|
||||
}
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -295,7 +303,7 @@ func (t *tun) Activate() error {
|
||||
}
|
||||
}
|
||||
|
||||
return t.addRoutes(false, nil)
|
||||
return t.addRoutes(false)
|
||||
}
|
||||
|
||||
func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
||||
@@ -310,7 +318,7 @@ func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
||||
return err
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -331,18 +339,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
|
||||
if !initial {
|
||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
|
||||
// Ensure any routes we actually want are installed
|
||||
err = t.addRoutes(true, r)
|
||||
err = t.addRoutes(true)
|
||||
if err != nil {
|
||||
// Catch any stray logs
|
||||
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -366,7 +372,7 @@ func (t *tun) Queues(int) ([]tio.Queue, error) {
|
||||
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
||||
}
|
||||
|
||||
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
func (t *tun) addRoutes(logErrors bool) error {
|
||||
routes := *t.Routes.Load()
|
||||
|
||||
for _, r := range routes {
|
||||
@@ -380,7 +386,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||
if logErrors {
|
||||
retErr.Log(t.l)
|
||||
rl.Failed()
|
||||
} else {
|
||||
return retErr
|
||||
}
|
||||
@@ -392,7 +397,7 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
func (t *tun) removeRoutes(routes []Route) error {
|
||||
for _, r := range routes {
|
||||
if len(r.Via) == 0 || !r.Install {
|
||||
// addRoutes never installs these
|
||||
@@ -400,12 +405,8 @@ func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
}
|
||||
|
||||
err := delRoute(r.Cidr, t.vpnNetworks)
|
||||
if errors.Is(err, unix.ESRCH) {
|
||||
// Already gone, which is what we wanted
|
||||
t.l.Info("Route was already removed", "route", r)
|
||||
} else if err != nil {
|
||||
if err != nil {
|
||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||
rl.Failed()
|
||||
} else {
|
||||
t.l.Info("Removed route", "route", r)
|
||||
}
|
||||
|
||||
@@ -4,7 +4,6 @@ package overlay
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"os"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
@@ -26,10 +25,10 @@ func TestReloadMTUOnlyKeepsRoutes(t *testing.T) {
|
||||
ioctlFd: ^uintptr(0),
|
||||
routesFromSystem: map[netip.Prefix]routing.Gateways{},
|
||||
}
|
||||
require.NoError(t, tn.reload(c, true, nil))
|
||||
require.NoError(t, tn.reload(c, true))
|
||||
|
||||
require.NoError(t, c.ReloadConfigString("tun:\n mtu: 1400\n"+routes).Err)
|
||||
_ = tn.reload(c, false, nil)
|
||||
require.NoError(t, c.ReloadConfigString("tun:\n mtu: 1400\n"+routes))
|
||||
_ = tn.reload(c, false)
|
||||
|
||||
got := *tn.Routes.Load()
|
||||
require.Len(t, got, 1)
|
||||
@@ -51,57 +50,7 @@ func TestReloadMaxMTUIsTheLargestRoute(t *testing.T) {
|
||||
ioctlFd: ^uintptr(0),
|
||||
routesFromSystem: map[netip.Prefix]routing.Gateways{},
|
||||
}
|
||||
require.NoError(t, tn.reload(c, true, nil))
|
||||
require.NoError(t, tn.reload(c, true))
|
||||
assert.Equal(t, 1500, tn.MaxMTU)
|
||||
assert.Equal(t, 1300, tn.DefaultMTU)
|
||||
}
|
||||
|
||||
// There is no device behind this tun, so adding a route always fails. Removing one is refused without root, as root the
|
||||
// kernel answers that the route isn't there, which is what we wanted
|
||||
func TestReloadRouteFailures(t *testing.T) {
|
||||
route := "tun:\n mtu: 1300\n unsafe_routes:\n - route: 192.168.100.0/24\n via: 10.1.0.1\n"
|
||||
cases := []struct {
|
||||
name string
|
||||
from, to string
|
||||
wantFails bool
|
||||
}{
|
||||
{"added", "tun:\n mtu: 1300\n", route, true},
|
||||
{"removed", route, "tun:\n mtu: 1300\n", os.Geteuid() != 0},
|
||||
{"unchanged", route, route + "punchy:\n punch: true\n", false},
|
||||
}
|
||||
for _, tc := range cases {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString(tc.from))
|
||||
tn := &tun{
|
||||
l: test.NewLogger(),
|
||||
vpnNetworks: []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")},
|
||||
ioctlFd: ^uintptr(0),
|
||||
routesFromSystem: map[netip.Prefix]routing.Gateways{},
|
||||
}
|
||||
require.NoError(t, tn.reload(c, true, nil))
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
require.NoError(t, tn.reload(c, false, r))
|
||||
})
|
||||
|
||||
res := c.ReloadConfigString(tc.to)
|
||||
require.NoError(t, res.Err)
|
||||
assert.Equal(t, tc.wantFails, res.Failed)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Keys only read when the device is created need a restart to apply
|
||||
func TestTunReloadRestartKeys(t *testing.T) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("tun:\n dev: nebrk0\n"))
|
||||
tn, err := NewDeviceFromConfig(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, 1)
|
||||
if err != nil {
|
||||
t.Skipf("can't create a tun device here: %v", err)
|
||||
}
|
||||
t.Cleanup(func() { _ = tn.Close() })
|
||||
|
||||
res := c.ReloadConfigString("tun:\n disabled: true\n dev: nebrk1\n tx_queue: 100\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.ElementsMatch(t, []string{"tun.disabled", "tun.dev", "tun.tx_queue"}, res.RestartKeys)
|
||||
}
|
||||
@@ -1,24 +0,0 @@
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// tun.disabled and the disabled tun's settings are only read when the device is made
|
||||
func TestDisabledTunRestartKeys(t *testing.T) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("tun:\n disabled: true\n"))
|
||||
d, err := NewDeviceFromConfig(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, 1)
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() { _ = d.Close() })
|
||||
|
||||
res := c.ReloadConfigString("tun:\n disabled: false\n tx_queue: 100\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.ElementsMatch(t, []string{"tun.disabled", "tun.tx_queue"}, res.RestartKeys)
|
||||
}
|
||||
+10
-28
@@ -84,7 +84,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*w
|
||||
l: l,
|
||||
}
|
||||
|
||||
err = t.reload(c, true, nil)
|
||||
err = t.reload(c, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
@@ -108,28 +108,17 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*w
|
||||
// Disable registration before Activate assigns addresses and triggers it.
|
||||
disableDNSRegistration(l, *guid)
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.dev", "tun.mtu")
|
||||
// Compare with the running category, not the last config. A restart with one we can't parse would fail, so say
|
||||
// that now rather than ask for one, and going back to the running one after a bad reload needs no restart
|
||||
if cat, setCat, err := parseNetworkCategory(c.GetString("tun.network_category", "private")); err != nil {
|
||||
t.l.Error("Invalid tun.network_category, a restart with it would fail", "error", err)
|
||||
r.Failed()
|
||||
} else if cat != t.networkCategory || setCat != t.setCategory {
|
||||
r.RestartRequiredIfChanged("tun.network_category")
|
||||
}
|
||||
r.RestartRequiredIfChanged(interfaceBypassKeys...)
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
return t, nil
|
||||
}
|
||||
|
||||
func (t *winTun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
func (t *winTun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -150,18 +139,16 @@ func (t *winTun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
|
||||
if !initial {
|
||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||
err := t.removeRoutes(findRemovedSystemRoutes(routes, *oldRoutes), r)
|
||||
err := t.removeRoutes(findRemovedSystemRoutes(routes, *oldRoutes))
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
|
||||
// Ensure any routes we actually want are installed
|
||||
err = t.addRoutes(true, r)
|
||||
err = t.addRoutes(true)
|
||||
if err != nil {
|
||||
// Catch any stray logs
|
||||
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -176,7 +163,7 @@ func (t *winTun) Activate() error {
|
||||
return fmt.Errorf("failed to set address: %w", err)
|
||||
}
|
||||
|
||||
err = t.addRoutes(false, nil)
|
||||
err = t.addRoutes(false)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -195,7 +182,7 @@ func (t *winTun) Activate() error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *winTun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
func (t *winTun) addRoutes(logErrors bool) error {
|
||||
luid := winipcfg.LUID(t.tun.LUID())
|
||||
routes := *t.Routes.Load()
|
||||
foundDefault4 := false
|
||||
@@ -226,7 +213,6 @@ func (t *winTun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||
if logErrors {
|
||||
retErr.Log(t.l)
|
||||
rl.Failed()
|
||||
continue
|
||||
} else {
|
||||
return retErr
|
||||
@@ -288,7 +274,7 @@ func (t *winTun) setMTU(luid winipcfg.LUID, foundDefault4, carriesV6 bool) error
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *winTun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
func (t *winTun) removeRoutes(routes []Route) error {
|
||||
luid := winipcfg.LUID(t.tun.LUID())
|
||||
|
||||
for _, r := range routes {
|
||||
@@ -298,12 +284,8 @@ func (t *winTun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
|
||||
// See comment on luid.AddRoute
|
||||
err := luid.DeleteRoute(r.Cidr, unspecifiedNextHop(r.Cidr))
|
||||
if errors.Is(err, windows.ERROR_NOT_FOUND) {
|
||||
// Already gone, which is what we wanted
|
||||
t.l.Info("Route was already removed", "route", r)
|
||||
} else if err != nil {
|
||||
if err != nil {
|
||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||
rl.Failed()
|
||||
} else {
|
||||
t.l.Info("Removed route", "route", r)
|
||||
}
|
||||
|
||||
@@ -53,14 +53,6 @@ func (rt *routeTest) metric(t *testing.T, cidr string) uint32 {
|
||||
return row.Metric
|
||||
}
|
||||
|
||||
// reload applies cfg and expects nothing in it to fail
|
||||
func (rt *routeTest) reload(t *testing.T, cfg string) {
|
||||
t.Helper()
|
||||
res := rt.c.ReloadConfigString(cfg)
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed, "the reload reported a failure")
|
||||
}
|
||||
|
||||
func unsafeRoutes(routes ...string) string {
|
||||
var b strings.Builder
|
||||
b.WriteString("tun:\n dev: nebroutetest\n unsafe_routes:\n")
|
||||
@@ -85,7 +77,7 @@ func TestWinTun_ReloadKeepsInstalledRoutes(t *testing.T) {
|
||||
rt := newRouteTest(t, unsafeRoutes(a))
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
|
||||
rt.reload(t, unsafeRoutes(a, b))
|
||||
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a, b)))
|
||||
assert.NotContains(t, rt.log.String(), "Failed to add route")
|
||||
rt.metric(t, a)
|
||||
rt.metric(t, b)
|
||||
@@ -100,7 +92,7 @@ func TestWinTun_ReloadMetricChangeApplies(t *testing.T) {
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
require.Equal(t, uint32(100), rt.metric(t, a))
|
||||
|
||||
rt.reload(t, unsafeRoutes(a+"@200"))
|
||||
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a+"@200")))
|
||||
assert.NotContains(t, rt.log.String(), "Failed to add route")
|
||||
assert.NotContains(t, rt.log.String(), "Removed route")
|
||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||
@@ -128,7 +120,7 @@ func TestWinTun_DuplicateCidrInstallsTheLastEntry(t *testing.T) {
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||
|
||||
rt.reload(t, unsafeRoutes(a+"@100", a+"@200", b))
|
||||
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a+"@100", a+"@200", b)))
|
||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||
assert.NotContains(t, rt.log.String(), "Updated route metric")
|
||||
assert.NotContains(t, rt.log.String(), "Failed to add route")
|
||||
@@ -142,7 +134,7 @@ func TestWinTun_DroppingAnUninstalledDuplicateKeepsTheRoute(t *testing.T) {
|
||||
rt := newRouteTest(t, unsafeRoutes(a+"@100", a+"@200"))
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
|
||||
rt.reload(t, unsafeRoutes(a+"@200"))
|
||||
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a+"@200")))
|
||||
assert.NotContains(t, rt.log.String(), "Removed route")
|
||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||
})
|
||||
@@ -163,45 +155,12 @@ func TestWinTun_ReloadMatchesAFreshStart(t *testing.T) {
|
||||
|
||||
rt := newRouteTest(t, unsafeRoutes(a+"@100"))
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
rt.reload(t, routes)
|
||||
require.NoError(t, rt.c.ReloadConfigString(routes))
|
||||
_, err = rt.luid.Route(cidr, unspecifiedNextHop(cidr))
|
||||
assert.Error(t, err, "the reload left it installed")
|
||||
})
|
||||
}
|
||||
|
||||
// Removing a route that is already gone is what we wanted, not a failure
|
||||
func TestWinTun_ReloadRouteAlreadyGone(t *testing.T) {
|
||||
forFamilies(t, func(t *testing.T, a, b string) {
|
||||
rt := newRouteTest(t, unsafeRoutes(a, b))
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
p := netip.MustParsePrefix(b)
|
||||
require.NoError(t, rt.luid.DeleteRoute(p, unspecifiedNextHop(p)))
|
||||
|
||||
rt.reload(t, unsafeRoutes(a))
|
||||
})
|
||||
}
|
||||
|
||||
// A network category we can't parse would fail the restart, so it fails the reload instead of asking for one
|
||||
func TestWinTun_ReloadInvalidNetworkCategoryFails(t *testing.T) {
|
||||
rt := newRouteTest(t, unsafeRoutes())
|
||||
for range 2 {
|
||||
res := rt.c.ReloadConfigString(unsafeRoutes() + " network_category: nope\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed, "a bad category that didn't change since the last reload is still bad")
|
||||
assert.False(t, res.RestartRequired)
|
||||
}
|
||||
|
||||
// Fixing it back to the running category needs nothing
|
||||
res := rt.c.ReloadConfigString(unsafeRoutes() + " network_category: private\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.False(t, res.RestartRequired)
|
||||
|
||||
res = rt.c.ReloadConfigString(unsafeRoutes() + " network_category: public\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.Equal(t, []string{"tun.network_category"}, res.RestartKeys)
|
||||
}
|
||||
|
||||
// forFamilies runs f with two unsafe_routes CIDRs of each address family, the tun's own network stays IPv4
|
||||
func forFamilies(t *testing.T, f func(t *testing.T, a, b string)) {
|
||||
t.Run("ipv4", func(t *testing.T) { f(t, "10.251.1.0/24", "10.251.2.0/24") })
|
||||
|
||||
@@ -2,9 +2,7 @@ package nebula
|
||||
|
||||
import (
|
||||
"crypto/fips140"
|
||||
"crypto/sha256"
|
||||
"encoding/binary"
|
||||
"encoding/hex"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
@@ -52,30 +50,15 @@ type CertState struct {
|
||||
myVpnBroadcastAddrsTable *bart.Lite
|
||||
}
|
||||
|
||||
// errCertNeedsRestart marks a new cert that is refused on reload because only a restart can apply it
|
||||
var errCertNeedsRestart = errors.New("a restart is required to use the new cert")
|
||||
|
||||
func NewPKIFromConfig(l *slog.Logger, c *config.C) (*PKI, error) {
|
||||
pki := &PKI{l: l}
|
||||
err := pki.reload(c, true, nil)
|
||||
err := pki.reload(c, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
// Compare with the running cipher, not the last config. A restart with one we can't run would fail, so say that
|
||||
// now rather than ask for one, and going back to the running one after a bad reload needs no restart
|
||||
if cipher := c.GetString("cipher", "aes"); !validCipher(cipher) {
|
||||
l.Error("Unknown cipher, a restart with it would fail", "cipher", cipher)
|
||||
r.Failed()
|
||||
} else if cipher == "chachapoly" && fipsOnly() {
|
||||
// newCipherSuite refuses it at startup
|
||||
l.Error("ChaChaPoly is not allowed in FIPS 140-only mode, a restart with it would fail", "cipher", cipher)
|
||||
r.Failed()
|
||||
} else if cipher != pki.getCertState().cipher {
|
||||
r.RestartRequiredIfChanged("cipher")
|
||||
}
|
||||
rErr := pki.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
rErr := pki.reload(c, false)
|
||||
if rErr != nil {
|
||||
util.LogWithContextIfNeeded("Failed to reload PKI from config", rErr, l)
|
||||
}
|
||||
@@ -92,29 +75,13 @@ func (p *PKI) getCertState() *CertState {
|
||||
return p.cs.Load()
|
||||
}
|
||||
|
||||
// r is nil on the initial load
|
||||
func (p *PKI) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
before := p.cs.Load()
|
||||
func (p *PKI) reload(c *config.C, initial bool) error {
|
||||
err := p.reloadCerts(c, initial)
|
||||
if err != nil {
|
||||
if initial {
|
||||
return err
|
||||
}
|
||||
err.Log(p.l)
|
||||
if errors.Is(err, errCertNeedsRestart) {
|
||||
r.RestartRequired()
|
||||
} else {
|
||||
r.Failed()
|
||||
}
|
||||
} else if !initial {
|
||||
// A cert for a version we weren't running is accepted without comparing its networks to ours. The tun and the
|
||||
// lighthouse keep the networks they started with
|
||||
after := p.cs.Load()
|
||||
if !slices.Equal(before.myVpnNetworks, after.myVpnNetworks) {
|
||||
p.l.Warn("The new cert changes our networks, a restart is required to use them",
|
||||
"old_networks", before.myVpnNetworks, "new_networks", after.myVpnNetworks)
|
||||
r.RestartRequired()
|
||||
}
|
||||
}
|
||||
|
||||
err = p.reloadCAPool(c)
|
||||
@@ -123,27 +90,21 @@ func (p *PKI) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
return err
|
||||
}
|
||||
err.Log(p.l)
|
||||
r.Failed()
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// fipsOnly is fips140.Enforced, a variable so a test can run the FIPS 140-only reload check without GODEBUG
|
||||
var fipsOnly = fips140.Enforced
|
||||
|
||||
// validCipher is true for the ciphers nebula can run. Each post-handshake CipherState in noiseutil hardcodes its own
|
||||
// nonce endianness, so there's nothing to set up for either.
|
||||
func validCipher(cipher string) bool {
|
||||
return cipher == "aes" || cipher == "chachapoly"
|
||||
}
|
||||
|
||||
func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
||||
var cipher string
|
||||
var currentState *CertState
|
||||
if initial {
|
||||
cipher = c.GetString("cipher", "aes")
|
||||
if !validCipher(cipher) {
|
||||
switch cipher {
|
||||
case "aes", "chachapoly":
|
||||
// Each post-handshake CipherState in noiseutil hardcodes its own
|
||||
// nonce endianness now, so there's nothing to set up here.
|
||||
default:
|
||||
return util.NewContextualError(
|
||||
"unknown cipher",
|
||||
m{"cipher": cipher},
|
||||
@@ -171,7 +132,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
||||
return util.NewContextualError(
|
||||
"Networks in new cert was different from old",
|
||||
m{"new_networks": newState.v1Cert.Networks(), "old_networks": currentState.v1Cert.Networks(), "cert_version": cert.Version1},
|
||||
errCertNeedsRestart,
|
||||
nil,
|
||||
)
|
||||
}
|
||||
|
||||
@@ -179,7 +140,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
||||
return util.NewContextualError(
|
||||
"Curve in new v1 cert was different from old",
|
||||
m{"new_curve": newState.v1Cert.Curve(), "old_curve": currentState.v1Cert.Curve(), "cert_version": cert.Version1},
|
||||
errCertNeedsRestart,
|
||||
nil,
|
||||
)
|
||||
}
|
||||
}
|
||||
@@ -194,7 +155,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
||||
return util.NewContextualError(
|
||||
"Networks in new cert was different from old",
|
||||
m{"new_networks": newState.v2Cert.Networks(), "old_networks": currentState.v2Cert.Networks(), "cert_version": cert.Version2},
|
||||
errCertNeedsRestart,
|
||||
nil,
|
||||
)
|
||||
}
|
||||
|
||||
@@ -202,7 +163,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
||||
return util.NewContextualError(
|
||||
"Curve in new cert was different from old",
|
||||
m{"new_curve": newState.v2Cert.Curve(), "old_curve": currentState.v2Cert.Curve(), "cert_version": cert.Version2},
|
||||
errCertNeedsRestart,
|
||||
nil,
|
||||
)
|
||||
}
|
||||
}
|
||||
@@ -217,7 +178,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
||||
return util.NewContextualError(
|
||||
"Removing a V2 cert is not permitted unless it has identical networks to the new V1 cert",
|
||||
m{"new_v1_networks": newState.v1Cert.Networks(), "old_v2_networks": currentState.v2Cert.Networks()},
|
||||
errCertNeedsRestart,
|
||||
nil,
|
||||
)
|
||||
}
|
||||
}
|
||||
@@ -235,14 +196,12 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
||||
|
||||
func (p *PKI) reloadCAPool(c *config.C) *util.ContextualError {
|
||||
caPool, err := loadCAPoolFromConfig(p.l, c)
|
||||
if caPool != nil {
|
||||
p.caPool.Store(caPool)
|
||||
p.l.Debug("Trusted CA fingerprints", "fingerprints", caPool.GetFingerprints())
|
||||
}
|
||||
if err != nil {
|
||||
return util.NewContextualError("Failed to load ca from config", nil, err)
|
||||
}
|
||||
|
||||
p.caPool.Store(caPool)
|
||||
p.l.Debug("Trusted CA fingerprints", "fingerprints", caPool.GetFingerprints())
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -617,22 +576,11 @@ func loadCAPoolFromConfig(l *slog.Logger, c *config.C) (*cert.CAPool, error) {
|
||||
|
||||
bl := c.GetStringSlice("pki.blocklist", []string{})
|
||||
if len(bl) > 0 {
|
||||
var bad []string
|
||||
for i, raw := range bl {
|
||||
// Fingerprints are compared as lowercase hex strings, a malformed entry would silently block nothing
|
||||
fp := strings.ToLower(strings.TrimSpace(raw))
|
||||
if b, err := hex.DecodeString(fp); err != nil || len(b) != sha256.Size {
|
||||
bad = append(bad, fmt.Sprintf("entry %d %q", i+1, raw))
|
||||
continue
|
||||
}
|
||||
for _, fp := range bl {
|
||||
caPool.BlocklistFingerprint(fp)
|
||||
}
|
||||
|
||||
l.Info("Blocklisted certificates", "fingerprintCount", len(bl)-len(bad))
|
||||
if len(bad) > 0 {
|
||||
// The valid entries are still returned so a failed reload blocks them, startup refuses the error
|
||||
return caPool, fmt.Errorf("pki.blocklist entries are not hex certificate fingerprints: %s", strings.Join(bad, ", "))
|
||||
}
|
||||
l.Info("Blocklisted certificates", "fingerprintCount", len(bl))
|
||||
}
|
||||
|
||||
return caPool, nil
|
||||
|
||||
-168
@@ -1,17 +1,10 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"crypto/fips140"
|
||||
"fmt"
|
||||
"net/netip"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
@@ -99,164 +92,3 @@ func TestNewCipherSuiteUnsupportedCurve(t *testing.T) {
|
||||
assert.True(t, strings.HasPrefix(err.Error(), "unsupported curve:"), "got: %v", err)
|
||||
assert.Nil(t, cs)
|
||||
}
|
||||
|
||||
func TestPKIReloadRestartRequired(t *testing.T) {
|
||||
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
|
||||
pkiConfig := func(cipher, network string) string {
|
||||
_, _, keyPEM, certPEM := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix(network)}, nil, nil)
|
||||
return fmt.Sprintf("cipher: %s\npki:\n ca: %q\n cert: %q\n key: %q\n", cipher, caPEM, certPEM, keyPEM)
|
||||
}
|
||||
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString(pkiConfig("aes", "10.1.0.2/24")))
|
||||
p, err := NewPKIFromConfig(test.NewLogger(), c)
|
||||
require.NoError(t, err)
|
||||
|
||||
// A cert that changes our networks is refused and needs a restart, it is not a failure
|
||||
res := c.ReloadConfigString(pkiConfig("aes", "10.1.0.3/24"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.RestartRequired)
|
||||
assert.False(t, res.Failed)
|
||||
assert.Equal(t, []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, p.getCertState().myVpnNetworks)
|
||||
|
||||
// The cipher only applies at startup
|
||||
c2 := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c2.LoadString(pkiConfig("aes", "10.1.0.2/24")))
|
||||
p, err = NewPKIFromConfig(test.NewLogger(), c2)
|
||||
require.NoError(t, err)
|
||||
res = c2.ReloadConfigString(pkiConfig("chachapoly", "10.1.0.2/24"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.RestartRequired)
|
||||
assert.Equal(t, "aes", p.getCertState().cipher)
|
||||
|
||||
// A cipher we can't run would fail the restart, so it fails the reload instead of asking for one
|
||||
c4 := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c4.LoadString(pkiConfig("aes", "10.1.0.2/24")))
|
||||
_, err = NewPKIFromConfig(test.NewLogger(), c4)
|
||||
require.NoError(t, err)
|
||||
for range 2 {
|
||||
res = c4.ReloadConfigString(pkiConfig("nope", "10.1.0.2/24"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed, "a bad cipher that didn't change since the last reload is still bad")
|
||||
assert.False(t, res.RestartRequired)
|
||||
}
|
||||
// Fixing it back to the running cipher needs nothing
|
||||
res = c4.ReloadConfigString(pkiConfig("aes", "10.1.0.2/24"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.False(t, res.RestartRequired)
|
||||
|
||||
// A cert that keeps our networks applies without a restart
|
||||
c3 := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c3.LoadString(pkiConfig("aes", "10.1.0.2/24")))
|
||||
_, err = NewPKIFromConfig(test.NewLogger(), c3)
|
||||
require.NoError(t, err)
|
||||
res = c3.ReloadConfigString(pkiConfig("aes", "10.1.0.2/24"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.RestartRequired)
|
||||
|
||||
// A cert that can't be read is a failure, and a restart wouldn't help
|
||||
res = c3.ReloadConfigString(strings.Replace(pkiConfig("aes", "10.1.0.2/24"), "cert: \"", "cert: \"garbage", 1))
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.False(t, res.RestartRequired)
|
||||
}
|
||||
|
||||
// A cert for a version we weren't running is accepted without comparing networks, so switching to one with different
|
||||
// networks needs a restart. One with the same networks doesn't
|
||||
func TestPKIReloadNewVersionWithOtherNetworks(t *testing.T) {
|
||||
ca1, _, ca1Key, ca1PEM := cert_test.NewTestCaCert(cert.Version1, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
|
||||
ca2, _, ca2Key, ca2PEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
|
||||
caPEM := string(ca1PEM) + string(ca2PEM)
|
||||
pkiConfig := func(v cert.Version, network string) string {
|
||||
ca, caKey := ca1, ca1Key
|
||||
if v == cert.Version2 {
|
||||
ca, caKey = ca2, ca2Key
|
||||
}
|
||||
_, _, keyPEM, certPEM := cert_test.NewTestCert(v, cert.Curve_CURVE25519, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix(network)}, nil, nil)
|
||||
return fmt.Sprintf("pki:\n ca: %q\n cert: %q\n key: %q\n", caPEM, certPEM, keyPEM)
|
||||
}
|
||||
|
||||
for _, tc := range []struct {
|
||||
network string
|
||||
restart bool
|
||||
}{
|
||||
{"10.9.0.7/24", true},
|
||||
{"10.1.0.2/24", false},
|
||||
} {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString(pkiConfig(cert.Version1, "10.1.0.2/24")))
|
||||
p, err := NewPKIFromConfig(test.NewLogger(), c)
|
||||
require.NoError(t, err)
|
||||
|
||||
res := c.ReloadConfigString(pkiConfig(cert.Version2, tc.network))
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed, tc.network)
|
||||
assert.Equal(t, tc.restart, res.RestartRequired, tc.network)
|
||||
assert.Equal(t, []netip.Prefix{netip.MustParsePrefix(tc.network)}, p.getCertState().myVpnNetworks, "accepted either way, as before")
|
||||
}
|
||||
}
|
||||
|
||||
// FIPS 140-only mode refuses chachapoly at startup, so reloading to it fails rather than asks for a restart
|
||||
func TestPKIReloadChachapolyInFIPSOnlyFails(t *testing.T) {
|
||||
fipsOnly = func() bool { return true }
|
||||
t.Cleanup(func() { fipsOnly = fips140.Enforced })
|
||||
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_P256, time.Time{}, time.Time{}, nil, nil, nil)
|
||||
_, _, keyPEM, certPEM := cert_test.NewTestCert(cert.Version2, cert.Curve_P256, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, nil, nil)
|
||||
pkiConfig := func(cipher string) string {
|
||||
return fmt.Sprintf("cipher: %s\npki:\n ca: %q\n cert: %q\n key: %q\n", cipher, caPEM, certPEM, keyPEM)
|
||||
}
|
||||
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString(pkiConfig("aes")))
|
||||
_, err := NewPKIFromConfig(test.NewLogger(), c)
|
||||
require.NoError(t, err)
|
||||
|
||||
res := c.ReloadConfigString(pkiConfig("chachapoly"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.False(t, res.RestartRequired)
|
||||
}
|
||||
|
||||
func TestLoadCAPoolBlocklist(t *testing.T) {
|
||||
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
|
||||
crt, _, _, _ := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, nil, nil)
|
||||
fp, err := crt.Fingerprint()
|
||||
require.NoError(t, err)
|
||||
|
||||
load := func(entry string) (*cert.CAPool, error) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString(fmt.Sprintf("pki:\n ca: %q\n blocklist:\n - %q\n", caPEM, entry)))
|
||||
return loadCAPoolFromConfig(test.NewLogger(), c)
|
||||
}
|
||||
|
||||
for _, entry := range []string{fp, strings.ToUpper(fp), " " + fp + "\t"} {
|
||||
pool, err := load(entry)
|
||||
require.NoError(t, err, entry)
|
||||
assert.True(t, pool.IsBlocklisted(fp), entry)
|
||||
}
|
||||
|
||||
for _, entry := range []string{fp[1:], fp + "00", "sha256:" + fp, "zz" + fp[2:], ""} {
|
||||
_, err := load(entry)
|
||||
require.Error(t, err, entry)
|
||||
}
|
||||
|
||||
// A bad entry on reload fails it, the valid entries are still blocked
|
||||
_, _, keyPEM, certPEM := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "me", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.1/24")}, nil, nil)
|
||||
pkiConfig := func(entry string) string {
|
||||
return fmt.Sprintf("pki:\n ca: %q\n cert: %q\n key: %q\n blocklist:\n - %q\n", caPEM, certPEM, keyPEM, entry)
|
||||
}
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString(pkiConfig(fp)))
|
||||
p, err := NewPKIFromConfig(test.NewLogger(), c)
|
||||
require.NoError(t, err)
|
||||
|
||||
other, _, _, _ := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "other", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.3/24")}, nil, nil)
|
||||
otherFp, err := other.Fingerprint()
|
||||
require.NoError(t, err)
|
||||
|
||||
res := c.ReloadConfigString(pkiConfig(fp) + fmt.Sprintf(" - %q\n - %q\n", otherFp, fp[1:]))
|
||||
assert.True(t, res.Failed)
|
||||
assert.True(t, p.GetCAPool().IsBlocklisted(fp))
|
||||
assert.True(t, p.GetCAPool().IsBlocklisted(otherFp))
|
||||
}
|
||||
@@ -67,8 +67,7 @@ func NewPunchyFromConfig(l *slog.Logger, c *config.C, punchConn udp.Conn) *Punch
|
||||
}
|
||||
|
||||
p.reload(c, true)
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("stats.lighthouse_metrics")
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
p.reload(c, false)
|
||||
})
|
||||
|
||||
|
||||
+6
-16
@@ -76,7 +76,7 @@ punchy:
|
||||
punch: true
|
||||
delay: 10m
|
||||
respond: true
|
||||
`).Err)
|
||||
`))
|
||||
p.reload(c, false)
|
||||
assert.True(t, p.punch.Load())
|
||||
assert.Equal(t, newDelay, time.Duration(p.delay.Load()))
|
||||
@@ -170,7 +170,7 @@ func TestPunchy_LogFormat_ReloadPunch(t *testing.T) {
|
||||
NewPunchyFromConfig(l, c, nil)
|
||||
hook.entries = nil
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {punch: true}`).Err)
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {punch: true}`))
|
||||
|
||||
entry := findEntry(t, hook.entries, "punchy.punch changed")
|
||||
assert.Equal(t, slog.LevelInfo, entry.Level)
|
||||
@@ -184,7 +184,7 @@ func TestPunchy_LogFormat_ReloadRespond(t *testing.T) {
|
||||
NewPunchyFromConfig(l, c, nil)
|
||||
hook.entries = nil
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {respond: true}`).Err)
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {respond: true}`))
|
||||
|
||||
entry := findEntry(t, hook.entries, "punchy.respond changed")
|
||||
assert.Equal(t, slog.LevelInfo, entry.Level)
|
||||
@@ -198,7 +198,7 @@ func TestPunchy_LogFormat_ReloadDelay(t *testing.T) {
|
||||
NewPunchyFromConfig(l, c, nil)
|
||||
hook.entries = nil
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {delay: 10s}`).Err)
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {delay: 10s}`))
|
||||
|
||||
entry := findEntry(t, hook.entries, "punchy.delay changed")
|
||||
assert.Equal(t, slog.LevelInfo, entry.Level)
|
||||
@@ -212,7 +212,7 @@ func TestPunchy_LogFormat_ReloadTargetAllRemotes(t *testing.T) {
|
||||
NewPunchyFromConfig(l, c, nil)
|
||||
hook.entries = nil
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {target_all_remotes: true}`).Err)
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {target_all_remotes: true}`))
|
||||
|
||||
entry := findEntry(t, hook.entries, "punchy.target_all_remotes changed")
|
||||
assert.Equal(t, slog.LevelInfo, entry.Level)
|
||||
@@ -226,19 +226,9 @@ func TestPunchy_LogFormat_ReloadRespondDelay(t *testing.T) {
|
||||
NewPunchyFromConfig(l, c, nil)
|
||||
hook.entries = nil
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {respond_delay: 15s}`).Err)
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {respond_delay: 15s}`))
|
||||
|
||||
entry := findEntry(t, hook.entries, "punchy.respond_delay changed")
|
||||
assert.Equal(t, slog.LevelInfo, entry.Level)
|
||||
assert.Equal(t, map[string]any{"respond_delay": 15 * time.Second}, entry.Attrs)
|
||||
}
|
||||
|
||||
func TestPunchyReloadRestartRequired(t *testing.T) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("stats:\n lighthouse_metrics: false\n"))
|
||||
NewPunchyFromConfig(test.NewLogger(), c, nil)
|
||||
|
||||
res := c.ReloadConfigString("stats:\n lighthouse_metrics: true\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.RestartRequired)
|
||||
}
|
||||
+1
-2
@@ -28,11 +28,10 @@ func NewRelayManager(ctx context.Context, l *slog.Logger, hostmap *HostMap, c *c
|
||||
hostmap: hostmap,
|
||||
}
|
||||
rm.reload(c, true)
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := rm.reload(c, false)
|
||||
if err != nil {
|
||||
rm.l.Error("Failed to reload relay_manager", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
return rm
|
||||
|
||||
+10
-27
@@ -1,8 +1,8 @@
|
||||
package service
|
||||
|
||||
import (
|
||||
"io"
|
||||
"net"
|
||||
"sync"
|
||||
)
|
||||
|
||||
type tcpListener struct {
|
||||
@@ -10,40 +10,23 @@ type tcpListener struct {
|
||||
s *Service
|
||||
addr *net.TCPAddr
|
||||
accept chan net.Conn
|
||||
|
||||
// closed is closed instead of accept so a handler blocked handing off a
|
||||
// connection can't send on a closed channel.
|
||||
closed chan struct{}
|
||||
closeOnce sync.Once
|
||||
}
|
||||
|
||||
func (l *tcpListener) Accept() (net.Conn, error) {
|
||||
// select picks randomly among ready cases, so without this a handler still
|
||||
// waiting to hand off could win over closed after Close has returned.
|
||||
select {
|
||||
case <-l.closed:
|
||||
return nil, net.ErrClosed
|
||||
default:
|
||||
}
|
||||
|
||||
select {
|
||||
case conn := <-l.accept:
|
||||
return conn, nil
|
||||
case <-l.closed:
|
||||
return nil, net.ErrClosed
|
||||
conn, ok := <-l.accept
|
||||
if !ok {
|
||||
return nil, io.EOF
|
||||
}
|
||||
return conn, nil
|
||||
}
|
||||
|
||||
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()
|
||||
defer l.s.mu.Unlock()
|
||||
delete(l.s.mu.listeners, uint16(l.addr.Port))
|
||||
|
||||
close(l.accept)
|
||||
|
||||
l.s.mu.Lock()
|
||||
delete(l.s.mu.listeners, l.port)
|
||||
l.s.mu.Unlock()
|
||||
})
|
||||
return nil
|
||||
}
|
||||
|
||||
|
||||
+10
-79
@@ -32,18 +32,13 @@ import (
|
||||
const nicID = 1
|
||||
|
||||
type Service struct {
|
||||
eg *errgroup.Group
|
||||
control *nebula.Control
|
||||
ipstack *stack.Stack
|
||||
|
||||
// done is closed once the forwarding goroutines have exited and the
|
||||
// netstack is torn down, at which point err holds the first fatal error.
|
||||
done chan struct{}
|
||||
err error
|
||||
|
||||
mu struct {
|
||||
sync.Mutex
|
||||
|
||||
closed bool
|
||||
listeners map[uint16]*tcpListener
|
||||
}
|
||||
}
|
||||
@@ -70,6 +65,7 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
||||
ctx := control.Context()
|
||||
eg, ctx := errgroup.WithContext(ctx)
|
||||
s := Service{
|
||||
eg: eg,
|
||||
control: control,
|
||||
}
|
||||
s.mu.listeners = map[uint16]*tcpListener{}
|
||||
@@ -78,12 +74,6 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
||||
NetworkProtocols: []stack.NetworkProtocolFactory{ipv4.NewProtocol, ipv6.NewProtocol},
|
||||
TransportProtocols: []stack.TransportProtocolFactory{tcp.NewProtocol, udp.NewProtocol, icmp.NewProtocol4, icmp.NewProtocol6},
|
||||
})
|
||||
// The teardown goroutine only owns the stack once New succeeds
|
||||
defer func() {
|
||||
if reterr != nil {
|
||||
s.ipstack.Destroy()
|
||||
}
|
||||
}()
|
||||
sackEnabledOpt := tcpip.TCPSACKEnabled(true) // TCP SACK is disabled by default
|
||||
tcpipErr := s.ipstack.SetTransportProtocolOption(tcp.ProtocolNumber, &sackEnabledOpt)
|
||||
if tcpipErr != nil {
|
||||
@@ -133,12 +123,6 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
||||
// this will read exactly one packet
|
||||
n, err := reader.Read(buf)
|
||||
if err != nil {
|
||||
// An error after shutdown began is noise from the device pipes
|
||||
// closing, anything else is fatal and must stop nebula too
|
||||
if ctx.Err() != nil {
|
||||
return nil
|
||||
}
|
||||
s.control.Stop()
|
||||
return err
|
||||
}
|
||||
packetBuf := stack.NewPacketBuffer(stack.PacketBufferOptions{
|
||||
@@ -146,8 +130,8 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
||||
})
|
||||
linkEP.InjectInbound(header.IPv4ProtocolNumber, packetBuf)
|
||||
|
||||
if ctx.Err() != nil {
|
||||
return nil
|
||||
if err := ctx.Err(); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
})
|
||||
@@ -155,18 +139,13 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
||||
for {
|
||||
packet := linkEP.ReadContext(ctx)
|
||||
if packet == nil {
|
||||
if ctx.Err() != nil {
|
||||
return nil
|
||||
if err := ctx.Err(); err != nil {
|
||||
return err
|
||||
}
|
||||
continue
|
||||
}
|
||||
bufView := packet.ToView()
|
||||
if _, err := bufView.WriteTo(writer); err != nil {
|
||||
// Same shutdown noise handling as the inbound reader
|
||||
if ctx.Err() != nil {
|
||||
return nil
|
||||
}
|
||||
s.control.Stop()
|
||||
return err
|
||||
}
|
||||
bufView.Release()
|
||||
@@ -179,22 +158,6 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
||||
return control.Wait()
|
||||
})
|
||||
|
||||
// Tear down here rather than in Close so it also happens when nebula stops
|
||||
// on its own. The forwarding goroutines must exit before the stack they feed
|
||||
// is destroyed.
|
||||
s.done = make(chan struct{})
|
||||
go func() {
|
||||
s.err = eg.Wait()
|
||||
s.closeListeners()
|
||||
// Destroy aborts the endpoints that exist when it starts, then waits on
|
||||
// every endpoint, so a Dial registering in between would hold Wait until
|
||||
// its connect timed out. Without the NIC new dials fail route lookup.
|
||||
// RemoveNIC also closes linkEP.
|
||||
_ = s.ipstack.RemoveNIC(nicID)
|
||||
s.ipstack.Destroy()
|
||||
close(s.done)
|
||||
}()
|
||||
|
||||
return &s, nil
|
||||
}
|
||||
|
||||
@@ -268,15 +231,11 @@ func (s *Service) Listen(network, address string) (net.Listener, error) {
|
||||
s: s,
|
||||
addr: addr,
|
||||
accept: make(chan net.Conn),
|
||||
closed: make(chan struct{}),
|
||||
}
|
||||
|
||||
s.mu.Lock()
|
||||
defer s.mu.Unlock()
|
||||
|
||||
if s.mu.closed {
|
||||
return nil, net.ErrClosed
|
||||
}
|
||||
if _, ok := s.mu.listeners[port]; ok {
|
||||
return nil, fmt.Errorf("already listening on port %d", port)
|
||||
}
|
||||
@@ -285,44 +244,22 @@ func (s *Service) Listen(network, address string) (net.Listener, error) {
|
||||
return l, nil
|
||||
}
|
||||
|
||||
// Wait blocks until the service has fully stopped, either via Close or a fatal
|
||||
// error, and returns the first fatal error if there was one.
|
||||
func (s *Service) Wait() error {
|
||||
<-s.done
|
||||
return s.err
|
||||
return s.eg.Wait()
|
||||
}
|
||||
|
||||
// Close closes all listeners and stops nebula. Use Wait to block until
|
||||
// shutdown has completed.
|
||||
func (s *Service) Close() error {
|
||||
s.closeListeners()
|
||||
s.control.Stop()
|
||||
return nil
|
||||
}
|
||||
|
||||
// closeListeners unblocks pending Accept calls and rejects new listeners.
|
||||
func (s *Service) closeListeners() {
|
||||
// Every caller closes every listener rather than returning early once
|
||||
// closed is set, so none returns while another is still closing them.
|
||||
s.mu.Lock()
|
||||
s.mu.closed = true
|
||||
listeners := make([]*tcpListener, 0, len(s.mu.listeners))
|
||||
for _, l := range s.mu.listeners {
|
||||
listeners = append(listeners, l)
|
||||
}
|
||||
s.mu.Unlock()
|
||||
|
||||
for _, l := range listeners {
|
||||
_ = l.Close()
|
||||
}
|
||||
}
|
||||
|
||||
func (s *Service) tcpHandler(r *tcp.ForwarderRequest) {
|
||||
endpointID := r.ID()
|
||||
|
||||
s.mu.Lock()
|
||||
defer s.mu.Unlock()
|
||||
|
||||
l, ok := s.mu.listeners[endpointID.LocalPort]
|
||||
s.mu.Unlock()
|
||||
if !ok {
|
||||
r.Complete(true)
|
||||
return
|
||||
@@ -338,12 +275,6 @@ func (s *Service) tcpHandler(r *tcp.ForwarderRequest) {
|
||||
r.Complete(false)
|
||||
ep.SocketOptions().SetKeepAlive(true)
|
||||
|
||||
// The handoff blocks until Accept is called, so it must not hold s.mu or a
|
||||
// listener nobody accepts from stalls every other port.
|
||||
conn := gonet.NewTCPConn(&wq, ep)
|
||||
select {
|
||||
case l.accept <- conn:
|
||||
case <-l.closed:
|
||||
_ = conn.Close()
|
||||
}
|
||||
l.accept <- conn
|
||||
}
|
||||
@@ -188,301 +188,3 @@ func TestService(t *testing.T) {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
|
||||
// A listener that is never accepted from must not stall connections to other
|
||||
// ports, and closing it must not block.
|
||||
func TestServiceUnacceptedListener(t *testing.T) {
|
||||
lighthousePort := ephemeralUDPPort(t)
|
||||
|
||||
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
|
||||
a := newSimpleService(ca, caKey, "a", netip.MustParseAddr("10.0.0.1"), m{
|
||||
"static_host_map": m{},
|
||||
"lighthouse": m{
|
||||
"am_lighthouse": true,
|
||||
},
|
||||
"listen": m{
|
||||
"host": "0.0.0.0",
|
||||
"port": lighthousePort,
|
||||
},
|
||||
})
|
||||
t.Cleanup(func() { _ = a.Close() })
|
||||
b := newSimpleService(ca, caKey, "b", netip.MustParseAddr("10.0.0.2"), m{
|
||||
"static_host_map": m{
|
||||
"10.0.0.1": []string{fmt.Sprintf("127.0.0.1:%d", lighthousePort)},
|
||||
},
|
||||
"lighthouse": m{
|
||||
"hosts": []string{"10.0.0.1"},
|
||||
"interval": 1,
|
||||
},
|
||||
})
|
||||
t.Cleanup(func() { _ = b.Close() })
|
||||
|
||||
idle, err := a.Listen("tcp", ":1234")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
active, err := a.Listen("tcp", ":1235")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
|
||||
defer cancel()
|
||||
idleConn, err := b.DialContext(ctx, "tcp", "10.0.0.1:1234")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
defer idleConn.Close()
|
||||
|
||||
accepted := make(chan error, 1)
|
||||
go func() {
|
||||
conn, err := active.Accept()
|
||||
if err == nil {
|
||||
err = conn.Close()
|
||||
}
|
||||
accepted <- err
|
||||
}()
|
||||
|
||||
ctx, cancel = context.WithTimeout(context.Background(), 5*time.Second)
|
||||
defer cancel()
|
||||
activeConn, err := b.DialContext(ctx, "tcp", "10.0.0.1:1235")
|
||||
if err != nil {
|
||||
t.Fatalf("dial to accepted port stalled behind idle listener: %v", err)
|
||||
}
|
||||
defer activeConn.Close()
|
||||
|
||||
select {
|
||||
case err := <-accepted:
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("accept stalled behind idle listener")
|
||||
}
|
||||
|
||||
closed := make(chan error, 1)
|
||||
go func() { closed <- idle.Close() }()
|
||||
select {
|
||||
case err := <-closed:
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("closing idle listener blocked")
|
||||
}
|
||||
|
||||
if _, err := idle.Accept(); !errors.Is(err, net.ErrClosed) {
|
||||
t.Fatalf("expected net.ErrClosed from closed listener, got %v", err)
|
||||
}
|
||||
if err := idle.Close(); err != nil {
|
||||
t.Fatalf("second close: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// Accept must report net.ErrClosed after Close even while a handler is still
|
||||
// trying to hand off a connection.
|
||||
func TestListenerAcceptAfterClose(t *testing.T) {
|
||||
s := &Service{}
|
||||
s.mu.listeners = map[uint16]*tcpListener{}
|
||||
l := &tcpListener{
|
||||
port: 1234,
|
||||
s: s,
|
||||
accept: make(chan net.Conn),
|
||||
closed: make(chan struct{}),
|
||||
}
|
||||
s.mu.listeners[l.port] = l
|
||||
if err := l.Close(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
// Keep a send pending so every Accept has a connection ready alongside closed.
|
||||
stop := make(chan struct{})
|
||||
done := make(chan struct{})
|
||||
go func() {
|
||||
defer close(done)
|
||||
for {
|
||||
server, client := net.Pipe()
|
||||
_ = client.Close()
|
||||
select {
|
||||
case l.accept <- server:
|
||||
case <-stop:
|
||||
_ = server.Close()
|
||||
return
|
||||
}
|
||||
}
|
||||
}()
|
||||
defer func() {
|
||||
close(stop)
|
||||
<-done
|
||||
}()
|
||||
|
||||
for range 100 {
|
||||
time.Sleep(time.Millisecond)
|
||||
conn, err := l.Accept()
|
||||
if conn != nil {
|
||||
_ = conn.Close()
|
||||
}
|
||||
if !errors.Is(err, net.ErrClosed) {
|
||||
t.Fatalf("Accept after Close: got err %v, want net.ErrClosed", err)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Close must release blocked Accept calls and let Wait report a clean shutdown.
|
||||
func TestServiceClose(t *testing.T) {
|
||||
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
|
||||
a := newSimpleService(ca, caKey, "a", netip.MustParseAddr("10.0.0.1"), m{
|
||||
"static_host_map": m{},
|
||||
"listen": m{
|
||||
"host": "127.0.0.1",
|
||||
"port": 0,
|
||||
},
|
||||
})
|
||||
|
||||
ln, err := a.Listen("tcp", ":1234")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
accepted := make(chan error, 1)
|
||||
go func() {
|
||||
_, err := ln.Accept()
|
||||
accepted <- err
|
||||
}()
|
||||
|
||||
if err := a.Close(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
select {
|
||||
case err := <-accepted:
|
||||
if !errors.Is(err, net.ErrClosed) {
|
||||
t.Fatalf("expected net.ErrClosed from Accept, got %v", err)
|
||||
}
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("Accept still blocked after Close")
|
||||
}
|
||||
|
||||
waited := make(chan error, 1)
|
||||
go func() { waited <- a.Wait() }()
|
||||
select {
|
||||
case err := <-waited:
|
||||
if err != nil {
|
||||
t.Fatalf("expected clean shutdown from Wait, got %v", err)
|
||||
}
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("Wait still blocked after Close")
|
||||
}
|
||||
|
||||
if a.ipstack.HasNIC(nicID) {
|
||||
t.Fatal("netstack not torn down after Wait")
|
||||
}
|
||||
if err := a.Close(); err != nil {
|
||||
t.Fatalf("second close: %v", err)
|
||||
}
|
||||
if _, err := a.Listen("tcp", ":1235"); !errors.Is(err, net.ErrClosed) {
|
||||
t.Fatalf("expected net.ErrClosed from Listen after Close, got %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// If nebula stops without Close being called, the service must still release
|
||||
// Accept and tear down the netstack.
|
||||
func TestServiceNebulaStopped(t *testing.T) {
|
||||
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
|
||||
a := newSimpleService(ca, caKey, "a", netip.MustParseAddr("10.0.0.1"), m{
|
||||
"static_host_map": m{},
|
||||
"listen": m{
|
||||
"host": "127.0.0.1",
|
||||
"port": 0,
|
||||
},
|
||||
})
|
||||
|
||||
ln, err := a.Listen("tcp", ":1234")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
accepted := make(chan error, 1)
|
||||
go func() {
|
||||
_, err := ln.Accept()
|
||||
accepted <- err
|
||||
}()
|
||||
|
||||
a.control.Stop()
|
||||
|
||||
waited := make(chan error, 1)
|
||||
go func() { waited <- a.Wait() }()
|
||||
select {
|
||||
case err := <-waited:
|
||||
if err != nil {
|
||||
t.Fatalf("expected clean shutdown from Wait, got %v", err)
|
||||
}
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("Wait still blocked after nebula stopped")
|
||||
}
|
||||
|
||||
select {
|
||||
case err := <-accepted:
|
||||
if !errors.Is(err, net.ErrClosed) {
|
||||
t.Fatalf("expected net.ErrClosed from Accept, got %v", err)
|
||||
}
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("Accept still blocked after nebula stopped")
|
||||
}
|
||||
|
||||
if a.ipstack.HasNIC(nicID) {
|
||||
t.Fatal("netstack not torn down after Wait")
|
||||
}
|
||||
}
|
||||
|
||||
// Dials racing Close must not hold Wait until their connect times out.
|
||||
func TestServiceDialDuringClose(t *testing.T) {
|
||||
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
|
||||
a := newSimpleService(ca, caKey, "a", netip.MustParseAddr("10.0.0.1"), m{
|
||||
"static_host_map": m{},
|
||||
"listen": m{
|
||||
"host": "127.0.0.1",
|
||||
"port": 0,
|
||||
},
|
||||
})
|
||||
|
||||
stop := make(chan struct{})
|
||||
var eg errgroup.Group
|
||||
for range 8 {
|
||||
eg.Go(func() error {
|
||||
for {
|
||||
select {
|
||||
case <-stop:
|
||||
return nil
|
||||
default:
|
||||
}
|
||||
// 10.0.0.2 has no tunnel, so each dial sits in SYN-SENT until aborted
|
||||
if c, err := a.Dial("tcp", "10.0.0.2:80"); err == nil {
|
||||
_ = c.Close()
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
time.Sleep(50 * time.Millisecond)
|
||||
|
||||
if err := a.Close(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
waited := make(chan error, 1)
|
||||
go func() { waited <- a.Wait() }()
|
||||
select {
|
||||
case err := <-waited:
|
||||
if err != nil {
|
||||
t.Fatalf("expected clean shutdown from Wait, got %v", err)
|
||||
}
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("Wait blocked behind a dial that raced Close")
|
||||
}
|
||||
|
||||
close(stop)
|
||||
dialersDone := make(chan error, 1)
|
||||
go func() { dialersDone <- eg.Wait() }()
|
||||
select {
|
||||
case <-dialersDone:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("Dial still blocked after Wait")
|
||||
}
|
||||
}
|
||||
@@ -11,8 +11,11 @@ import (
|
||||
"net"
|
||||
"net/netip"
|
||||
"os"
|
||||
"slices"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"runtime/pprof"
|
||||
"sort"
|
||||
"strconv"
|
||||
"strings"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
@@ -55,12 +58,12 @@ type sshDeviceInfoFlags struct {
|
||||
}
|
||||
|
||||
func wireSSHReload(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) {
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
if c.GetBool("sshd.enabled", false) {
|
||||
// Restarting the server drops every open session, the one that asked for this reload included. Only restart
|
||||
// when it isn't running or its config changed. The host key file can change under the same config, new
|
||||
// handshakes use the new key without a restart
|
||||
if ssh.Running() && !slices.ContainsFunc(sshdServerKeys, c.HasChanged) {
|
||||
if ssh.Running() && !c.HasChanged("sshd") {
|
||||
key, err := loadSSHHostKey(c)
|
||||
if err == nil {
|
||||
err = ssh.SetHostKey(key)
|
||||
@@ -68,15 +71,13 @@ func wireSSHReload(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) {
|
||||
if err != nil {
|
||||
l.Error("Failed to reconfigure the sshd", "error", err)
|
||||
ssh.Stop()
|
||||
r.Failed()
|
||||
}
|
||||
return
|
||||
}
|
||||
sshRun, err := configSSH(l, ssh, c, r)
|
||||
sshRun, err := configSSH(l, ssh, c)
|
||||
if err != nil {
|
||||
l.Error("Failed to reconfigure the sshd", "error", err)
|
||||
ssh.Stop()
|
||||
r.Failed()
|
||||
}
|
||||
if sshRun != nil {
|
||||
go sshRun()
|
||||
@@ -87,9 +88,6 @@ func wireSSHReload(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) {
|
||||
})
|
||||
}
|
||||
|
||||
// sshdServerKeys are what configSSH reads
|
||||
var sshdServerKeys = []string{"sshd.enabled", "sshd.listen", "sshd.host_key", "sshd.trusted_cas", "sshd.authorized_users"}
|
||||
|
||||
// loadSSHHostKey returns sshd.host_key, read from its file when it names one.
|
||||
func loadSSHHostKey(c *config.C) ([]byte, error) {
|
||||
hostKeyPathOrKey := c.GetString("sshd.host_key", "")
|
||||
@@ -110,8 +108,7 @@ func loadSSHHostKey(c *config.C) ([]byte, error) {
|
||||
// updates the passed-in SSHServer. On success, it returns a function
|
||||
// that callers may invoke to run the configured ssh server. On
|
||||
// failure, it returns nil, error.
|
||||
// r is nil at startup, entries that are skipped with a warning fail it on a reload
|
||||
func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C, r *config.Reload) (func(), error) {
|
||||
func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) (func(), error) {
|
||||
listen := c.GetString("sshd.listen", "")
|
||||
if listen == "" {
|
||||
return nil, fmt.Errorf("sshd.listen must be provided")
|
||||
@@ -144,7 +141,6 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C, r *config.Reloa
|
||||
err := ssh.AddTrustedCA(caAuthorizedKey)
|
||||
if err != nil {
|
||||
l.Warn("SSH CA had an error, ignoring", "error", err, "sshCA", caAuthorizedKey)
|
||||
r.Failed()
|
||||
continue
|
||||
}
|
||||
}
|
||||
@@ -156,14 +152,12 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C, r *config.Reloa
|
||||
kDef, ok := rk.(map[string]any)
|
||||
if !ok {
|
||||
l.Warn("Authorized user had an error, ignoring", "sshKeyConfig", rk)
|
||||
r.Failed()
|
||||
continue
|
||||
}
|
||||
|
||||
user, ok := kDef["user"].(string)
|
||||
if !ok {
|
||||
l.Warn("Authorized user is missing the user field", "sshKeyConfig", rk)
|
||||
r.Failed()
|
||||
continue
|
||||
}
|
||||
|
||||
@@ -177,7 +171,6 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C, r *config.Reloa
|
||||
"sshKeyConfig", rk,
|
||||
"sshKey", v,
|
||||
)
|
||||
r.Failed()
|
||||
continue
|
||||
}
|
||||
|
||||
@@ -189,7 +182,6 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C, r *config.Reloa
|
||||
"sshKeyConfig", rk,
|
||||
"sshKey", subK,
|
||||
)
|
||||
r.Failed()
|
||||
continue
|
||||
}
|
||||
|
||||
@@ -199,14 +191,12 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C, r *config.Reloa
|
||||
"error", err,
|
||||
"sshKeyConfig", sk,
|
||||
)
|
||||
r.Failed()
|
||||
continue
|
||||
}
|
||||
}
|
||||
|
||||
default:
|
||||
l.Warn("Authorized user is missing the keys field or was not understood", "sshKeyConfig", rk)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
} else {
|
||||
@@ -229,6 +219,12 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C, r *config.Reloa
|
||||
}
|
||||
|
||||
func attachCommands(l *slog.Logger, c *config.C, ssh *sshd.SSHServer, f *Interface) {
|
||||
// sandboxDir defaults to a dir in temp. The intention is that end user will
|
||||
// create this dir as needed. Overriding this config value to "" allows
|
||||
// writing to anywhere in the system.
|
||||
defaultDir := filepath.Join(os.TempDir(), "nebula-debug")
|
||||
sandboxDir := c.GetString("sshd.sandbox_dir", defaultDir)
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "list-hostmap",
|
||||
ShortDescription: "List all known previously connected hosts",
|
||||
@@ -280,7 +276,46 @@ func attachCommands(l *slog.Logger, c *config.C, ssh *sshd.SSHServer, f *Interfa
|
||||
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)
|
||||
return sshReload(c, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "start-cpu-profile",
|
||||
ShortDescription: "Starts a cpu profile and write output to the provided file, ex: `cpu-profile.pb.gz`",
|
||||
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
||||
return sshStartCpuProfile(sandboxDir, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "stop-cpu-profile",
|
||||
ShortDescription: "Stops a cpu profile and writes output to the previously provided file",
|
||||
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
||||
pprof.StopCPUProfile()
|
||||
return w.WriteLine("If a CPU profile was running it is now stopped")
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "save-heap-profile",
|
||||
ShortDescription: "Saves a heap profile to the provided path, ex: `heap-profile.pb.gz`",
|
||||
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
||||
return sshGetHeapProfile(sandboxDir, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "mutex-profile-fraction",
|
||||
ShortDescription: "Gets or sets runtime.SetMutexProfileFraction",
|
||||
Callback: sshMutexProfileFraction,
|
||||
})
|
||||
|
||||
ssh.RegisterCommand(&sshd.Command{
|
||||
Name: "save-mutex-profile",
|
||||
ShortDescription: "Saves a mutex profile to the provided path, ex: `mutex-profile.pb.gz`",
|
||||
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
||||
return sshGetMutexProfile(sandboxDir, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
@@ -514,6 +549,58 @@ func sshListLighthouseMap(lightHouse *LightHouse, a any, w sshd.StringWriter) er
|
||||
return nil
|
||||
}
|
||||
|
||||
// sshSanitizeFilePath validates that the given file path is within the sandbox directory.
|
||||
// If sandboxDir is empty, the path is returned as-is for backwards compatibility.
|
||||
func sshSanitizeFilePath(sandboxDir, filePath string) (string, error) {
|
||||
if sandboxDir == "" {
|
||||
return filePath, nil
|
||||
}
|
||||
|
||||
// Clean and resolve the path relative to the sandbox directory
|
||||
if !filepath.IsAbs(filePath) {
|
||||
filePath = filepath.Join(sandboxDir, filePath)
|
||||
}
|
||||
cleaned := filepath.Clean(filePath)
|
||||
|
||||
// Ensure the resolved path is within the sandbox directory
|
||||
cleanedSandbox := filepath.Clean(sandboxDir)
|
||||
if cleaned == cleanedSandbox {
|
||||
return "", fmt.Errorf("path %q resolves to the sandbox directory itself %q", filePath, sandboxDir)
|
||||
}
|
||||
if !strings.HasPrefix(cleaned, cleanedSandbox+string(filepath.Separator)) {
|
||||
return "", fmt.Errorf("path %q is outside the sandbox directory %q", filePath, sandboxDir)
|
||||
}
|
||||
|
||||
return cleaned, nil
|
||||
}
|
||||
|
||||
func sshStartCpuProfile(sandboxDir string, fs any, a []string, w sshd.StringWriter) error {
|
||||
if len(a) == 0 {
|
||||
err := w.WriteLine("No path to write profile provided")
|
||||
return err
|
||||
}
|
||||
|
||||
filePath, err := sshSanitizeFilePath(sandboxDir, a[0])
|
||||
if err != nil {
|
||||
return w.WriteLine(err.Error())
|
||||
}
|
||||
|
||||
file, err := os.Create(filePath)
|
||||
if err != nil {
|
||||
err = w.WriteLine(fmt.Sprintf("Unable to create profile file: %s", err))
|
||||
return err
|
||||
}
|
||||
|
||||
err = pprof.StartCPUProfile(file)
|
||||
if err != nil {
|
||||
err = w.WriteLine(fmt.Sprintf("Unable to start cpu profile: %s", err))
|
||||
return err
|
||||
}
|
||||
|
||||
err = w.WriteLine(fmt.Sprintf("Started cpu profile, issue stop-cpu-profile to write the output to %s", a))
|
||||
return err
|
||||
}
|
||||
|
||||
func sshVersion(ifce *Interface, fs any, a []string, w sshd.StringWriter) error {
|
||||
return w.WriteLine(fmt.Sprintf("%s", ifce.version))
|
||||
}
|
||||
@@ -666,6 +753,76 @@ func sshChangeRemote(ifce *Interface, fs any, a []string, w sshd.StringWriter) e
|
||||
return w.WriteLine("Changed")
|
||||
}
|
||||
|
||||
func sshGetHeapProfile(sandboxDir string, fs any, a []string, w sshd.StringWriter) error {
|
||||
if len(a) == 0 {
|
||||
return w.WriteLine("No path to write profile provided")
|
||||
}
|
||||
|
||||
filePath, err := sshSanitizeFilePath(sandboxDir, a[0])
|
||||
if err != nil {
|
||||
return w.WriteLine(err.Error())
|
||||
}
|
||||
|
||||
file, err := os.Create(filePath)
|
||||
if err != nil {
|
||||
err = w.WriteLine(fmt.Sprintf("Unable to create profile file: %s", err))
|
||||
return err
|
||||
}
|
||||
|
||||
err = pprof.WriteHeapProfile(file)
|
||||
if err != nil {
|
||||
err = w.WriteLine(fmt.Sprintf("Unable to write profile: %s", err))
|
||||
return err
|
||||
}
|
||||
|
||||
err = w.WriteLine(fmt.Sprintf("Mem profile created at %s", a))
|
||||
return err
|
||||
}
|
||||
|
||||
func sshMutexProfileFraction(fs any, a []string, w sshd.StringWriter) error {
|
||||
if len(a) == 0 {
|
||||
rate := runtime.SetMutexProfileFraction(-1)
|
||||
return w.WriteLine(fmt.Sprintf("Current value: %d", rate))
|
||||
}
|
||||
|
||||
newRate, err := strconv.Atoi(a[0])
|
||||
if err != nil {
|
||||
return w.WriteLine(fmt.Sprintf("Invalid argument: %s", a[0]))
|
||||
}
|
||||
|
||||
oldRate := runtime.SetMutexProfileFraction(newRate)
|
||||
return w.WriteLine(fmt.Sprintf("New value: %d. Old value: %d", newRate, oldRate))
|
||||
}
|
||||
|
||||
func sshGetMutexProfile(sandboxDir string, fs any, a []string, w sshd.StringWriter) error {
|
||||
if len(a) == 0 {
|
||||
return w.WriteLine("No path to write profile provided")
|
||||
}
|
||||
|
||||
filePath, err := sshSanitizeFilePath(sandboxDir, a[0])
|
||||
if err != nil {
|
||||
return w.WriteLine(err.Error())
|
||||
}
|
||||
|
||||
file, err := os.Create(filePath)
|
||||
if err != nil {
|
||||
return w.WriteLine(fmt.Sprintf("Unable to create profile file: %s", err))
|
||||
}
|
||||
defer file.Close()
|
||||
|
||||
mutexProfile := pprof.Lookup("mutex")
|
||||
if mutexProfile == nil {
|
||||
return w.WriteLine("Unable to get pprof.Lookup(\"mutex\")")
|
||||
}
|
||||
|
||||
err = mutexProfile.WriteTo(file, 0)
|
||||
if err != nil {
|
||||
return w.WriteLine(fmt.Sprintf("Unable to write profile: %s", err))
|
||||
}
|
||||
|
||||
return w.WriteLine(fmt.Sprintf("Mutex profile created at %s", a))
|
||||
}
|
||||
|
||||
func sshLogLevel(l *slog.Logger, fs any, a []string, w sshd.StringWriter) error {
|
||||
ctrl, ok := l.Handler().(interface {
|
||||
GetLevel() slog.Level
|
||||
@@ -918,13 +1075,8 @@ func sshDeviceInfo(ifce *Interface, fs any, w sshd.StringWriter) error {
|
||||
}
|
||||
}
|
||||
|
||||
// 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
|
||||
func sshReload(c *config.C, w sshd.StringWriter) error {
|
||||
err := w.WriteLine("Reloading config")
|
||||
c.ReloadConfig()
|
||||
return err
|
||||
}
|
||||
@@ -1,83 +0,0 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"io"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
type lineWriter struct {
|
||||
lines []string
|
||||
err error
|
||||
}
|
||||
|
||||
func (w *lineWriter) WriteLine(s string) error {
|
||||
w.lines = append(w.lines, s)
|
||||
return w.err
|
||||
}
|
||||
func (w *lineWriter) Write(s string) error { return w.WriteLine(s) }
|
||||
func (w *lineWriter) WriteBytes(b []byte) error { return w.WriteLine(string(b)) }
|
||||
func (w *lineWriter) GetWriter() io.Writer { return io.Discard }
|
||||
|
||||
func TestSSHReloadReportsTheResult(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
write := func(body string) {
|
||||
require.NoError(t, os.WriteFile(filepath.Join(dir, "config.yml"), []byte(body), 0o600))
|
||||
}
|
||||
write("a: 1\nb: 1")
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.Load(dir))
|
||||
fail := false
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("b")
|
||||
if fail {
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
reload := func() []string {
|
||||
w := &lineWriter{}
|
||||
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())
|
||||
|
||||
fail = true
|
||||
write("a: 3\nb: 1")
|
||||
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())
|
||||
|
||||
write("a: [")
|
||||
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 TestSSHReloadReloadsWhenTheClientIsGone(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
require.NoError(t, os.WriteFile(filepath.Join(dir, "config.yml"), []byte("a: 1"), 0o600))
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.Load(dir))
|
||||
reloaded := false
|
||||
c.RegisterReloadCallback(func(*config.C, *config.Reload) { reloaded = true })
|
||||
|
||||
gone := errors.New("client is gone")
|
||||
require.ErrorIs(t, sshReload(l, c, &lineWriter{err: gone}), gone)
|
||||
assert.True(t, reloaded)
|
||||
}
|
||||
+16
-60
@@ -26,15 +26,13 @@ type sshdReloadHarness struct {
|
||||
server *sshd.SSHServer
|
||||
keyFile string
|
||||
signer ssh.Signer
|
||||
listen string
|
||||
users []string
|
||||
extra string
|
||||
}
|
||||
|
||||
func newSSHDReloadHarness(t *testing.T) *sshdReloadHarness {
|
||||
t.Helper()
|
||||
l := test.NewLogger()
|
||||
h := &sshdReloadHarness{keyFile: filepath.Join(t.TempDir(), "host_key"), listen: "127.0.0.1:0", users: []string{"test"}}
|
||||
h := &sshdReloadHarness{keyFile: filepath.Join(t.TempDir(), "host_key")}
|
||||
h.writeHostKey(t, newEd25519Key(t))
|
||||
|
||||
_, userKey, err := ed25519.GenerateKey(rand.Reader)
|
||||
@@ -47,7 +45,7 @@ func newSSHDReloadHarness(t *testing.T) *sshdReloadHarness {
|
||||
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)
|
||||
run, err := configSSH(l, h.server, h.c)
|
||||
require.NoError(t, err)
|
||||
go run()
|
||||
t.Cleanup(h.server.Stop)
|
||||
@@ -73,12 +71,8 @@ func (h *sshdReloadHarness) writeHostKey(t *testing.T, key crypto.Signer) ssh.Pu
|
||||
}
|
||||
|
||||
func (h *sshdReloadHarness) config() string {
|
||||
users := ""
|
||||
for _, u := range h.users {
|
||||
users += fmt.Sprintf(" - user: %s\n keys: [%q]\n", u, string(ssh.MarshalAuthorizedKey(h.signer.PublicKey())))
|
||||
}
|
||||
return fmt.Sprintf("sshd:\n enabled: true\n listen: %s\n host_key: %s\n authorized_users:\n%s%s",
|
||||
h.listen, h.keyFile, users, h.extra)
|
||||
return fmt.Sprintf("sshd:\n enabled: true\n listen: 127.0.0.1:0\n host_key: %s\n authorized_users:\n - user: test\n keys: [%q]\n%s",
|
||||
h.keyFile, string(ssh.MarshalAuthorizedKey(h.signer.PublicKey())), h.extra)
|
||||
}
|
||||
|
||||
// dial connects to wherever the server listens now, a restart on :0 moves it. hostKeyAlgorithms limits which host keys
|
||||
@@ -136,33 +130,19 @@ func TestSSHDReload_UnchangedKeepsSessions(t *testing.T) {
|
||||
h := newSSHDReloadHarness(t)
|
||||
client, _ := h.connect(t)
|
||||
|
||||
require.NoError(t, h.c.ReloadConfigString(h.config()+"punchy:\n punch: true\n").Err)
|
||||
require.NoError(t, h.c.ReloadConfigString(h.config()+"punchy:\n punch: true\n"))
|
||||
assert.False(t, dropped(client, 500*time.Millisecond), "an unchanged sshd was restarted")
|
||||
}
|
||||
|
||||
// Every key the server reads restarts it when it changes
|
||||
func TestSSHDReload_ChangedConfigRestarts(t *testing.T) {
|
||||
cases := map[string]func(t *testing.T, h *sshdReloadHarness){
|
||||
"listen": func(t *testing.T, h *sshdReloadHarness) { h.listen = "localhost:0" },
|
||||
"authorized_users": func(t *testing.T, h *sshdReloadHarness) { h.users = append(h.users, "other") },
|
||||
"trusted_cas": func(t *testing.T, h *sshdReloadHarness) { h.extra = " trusted_cas: []\n" },
|
||||
"host_key": func(t *testing.T, h *sshdReloadHarness) {
|
||||
h.keyFile = filepath.Join(t.TempDir(), "other_host_key")
|
||||
h.writeHostKey(t, newEd25519Key(t))
|
||||
},
|
||||
}
|
||||
for name, change := range cases {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
h := newSSHDReloadHarness(t)
|
||||
client, _ := h.connect(t)
|
||||
h := newSSHDReloadHarness(t)
|
||||
client, _ := h.connect(t)
|
||||
|
||||
change(t, h)
|
||||
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
|
||||
assert.True(t, dropped(client, 5*time.Second), "a changed sshd config was not applied")
|
||||
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
|
||||
h.connect(t)
|
||||
})
|
||||
}
|
||||
h.extra = " trusted_cas: []\n"
|
||||
require.NoError(t, h.c.ReloadConfigString(h.config()))
|
||||
assert.True(t, dropped(client, 5*time.Second), "a changed sshd config was not applied")
|
||||
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
|
||||
h.connect(t)
|
||||
}
|
||||
|
||||
// The config can stay the same while the host key file it names changes. New connections get the new key, open
|
||||
@@ -172,7 +152,7 @@ func TestSSHDReload_ChangedHostKeyFile(t *testing.T) {
|
||||
client, _ := h.connect(t)
|
||||
|
||||
want := h.writeHostKey(t, newEd25519Key(t))
|
||||
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
|
||||
require.NoError(t, h.c.ReloadConfigString(h.config()))
|
||||
_, got := h.connect(t)
|
||||
assert.Equal(t, want.Marshal(), got.Marshal(), "a new host key was not applied")
|
||||
assert.False(t, dropped(client, 500*time.Millisecond), "a new host key restarted sshd")
|
||||
@@ -186,7 +166,7 @@ func TestSSHDReload_HostKeyAlgorithmChange(t *testing.T) {
|
||||
rsaKey, err := rsa.GenerateKey(rand.Reader, 2048)
|
||||
require.NoError(t, err)
|
||||
want := h.writeHostKey(t, rsaKey)
|
||||
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
|
||||
require.NoError(t, h.c.ReloadConfigString(h.config()))
|
||||
|
||||
_, got := h.connect(t)
|
||||
assert.Equal(t, want.Marshal(), got.Marshal())
|
||||
@@ -200,7 +180,7 @@ func TestSSHDReload_NotRunningRestarts(t *testing.T) {
|
||||
h.server.Stop()
|
||||
require.Eventually(t, func() bool { return !h.server.Running() }, 5*time.Second, 10*time.Millisecond)
|
||||
|
||||
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
|
||||
require.NoError(t, h.c.ReloadConfigString(h.config()))
|
||||
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
|
||||
h.connect(t)
|
||||
}
|
||||
@@ -211,30 +191,6 @@ func TestSSHDReload_BadHostKeyFileStops(t *testing.T) {
|
||||
h.connect(t)
|
||||
|
||||
require.NoError(t, os.WriteFile(h.keyFile, []byte("not a key"), 0o600))
|
||||
assert.True(t, h.c.ReloadConfigString(h.config()).Failed)
|
||||
require.NoError(t, h.c.ReloadConfigString(h.config()))
|
||||
require.Eventually(t, func() bool { return !h.server.Running() }, 5*time.Second, 10*time.Millisecond)
|
||||
}
|
||||
|
||||
// A trusted CA or authorized user that is skipped with a warning fails the reload, the valid ones are still used
|
||||
func TestSSHDReload_SkippedEntriesFail(t *testing.T) {
|
||||
cases := map[string]string{
|
||||
"bad trusted ca": " trusted_cas: [nope]\n",
|
||||
"user entry not a map": " - nope\n",
|
||||
"user missing": " - keys: [nope]\n",
|
||||
"bad key": " - user: other\n keys: nope\n",
|
||||
"key in a list not a string": " - user: other\n keys: [5]\n",
|
||||
"bad key in a list": " - user: other\n keys: [nope]\n",
|
||||
"keys missing": " - user: other\n",
|
||||
}
|
||||
for name, extra := range cases {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
h := newSSHDReloadHarness(t)
|
||||
h.extra = extra
|
||||
res := h.c.ReloadConfigString(h.config())
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
|
||||
h.connect(t)
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -99,10 +99,9 @@ func newStatsServerFromConfig(ctx context.Context, l *slog.Logger, c *config.C,
|
||||
emitStats: emitStats,
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
if err := s.reload(c, false); err != nil {
|
||||
s.l.Error("Failed to reload stats from config", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
|
||||
+10
-10
@@ -29,11 +29,12 @@ type Settings struct {
|
||||
type Conn interface {
|
||||
Rebind() error
|
||||
LocalAddr() (netip.AddrPort, error)
|
||||
// ListenOut invokes r for each received packet.
|
||||
// On batch-capable backends (recvmmsg), flush is called after each batch is fully delivered.
|
||||
// Callers use it to flush per-batch accumulators such as TUN write coalescers.
|
||||
// Single-packet backends call flush after each packet. flush must not be nil.
|
||||
ListenOut(r EncReader, flush func()) error
|
||||
// ListenOut invokes r for each received packet. The packets alias the receive buffers.
|
||||
// After each batch is fully delivered (after each packet on single-packet backends), handoff takes the batch's
|
||||
// buffers and returns the ones to receive the next batch into: the same ones once the caller is done with the
|
||||
// packets, after flushing per-batch accumulators such as TUN write coalescers, or replacements of the same count
|
||||
// and size to keep them. handoff must not be nil.
|
||||
ListenOut(r EncReader, handoff func(bufs [][]byte) [][]byte) error
|
||||
WriteTo(b []byte, addr netip.AddrPort) error
|
||||
// WriteBatch sends a contiguous batch of packets, each with its own
|
||||
// destination. bufs and addrs must have the same length. Linux uses
|
||||
@@ -41,10 +42,9 @@ type Conn interface {
|
||||
//
|
||||
// Returns the number of packets successfully written. A destination the kernel rejects costs only
|
||||
// its own packet, so a short count means some peers were undeliverable, not that the batch failed.
|
||||
// Safe for concurrent use on the same Conn.
|
||||
// Not safe for concurrent use on the same Conn.
|
||||
WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error)
|
||||
// ReloadConfig applies the listen settings that can change, r is nil at startup
|
||||
ReloadConfig(c *config.C, r *config.Reload)
|
||||
ReloadConfig(c *config.C)
|
||||
SupportsMultipleReaders() bool
|
||||
Close() error
|
||||
}
|
||||
@@ -57,7 +57,7 @@ func (NoopConn) Rebind() error {
|
||||
func (NoopConn) LocalAddr() (netip.AddrPort, error) {
|
||||
return netip.AddrPort{}, nil
|
||||
}
|
||||
func (NoopConn) ListenOut(_ EncReader, _ func()) error {
|
||||
func (NoopConn) ListenOut(_ EncReader, _ func([][]byte) [][]byte) error {
|
||||
return nil
|
||||
}
|
||||
func (NoopConn) SupportsMultipleReaders() bool {
|
||||
@@ -69,7 +69,7 @@ func (NoopConn) WriteTo(_ []byte, _ netip.AddrPort) error {
|
||||
func (NoopConn) WriteBatch(bufs [][]byte, _ []netip.AddrPort) (int, error) {
|
||||
return len(bufs), nil
|
||||
}
|
||||
func (NoopConn) ReloadConfig(_ *config.C, _ *config.Reload) {
|
||||
func (NoopConn) ReloadConfig(_ *config.C) {
|
||||
return
|
||||
}
|
||||
func (NoopConn) Close() error {
|
||||
|
||||
@@ -24,12 +24,6 @@ type NetworkChangeMonitor struct {
|
||||
// NewNetworkChangeMonitor builds a monitor for local network changes. The returned monitor is always usable: Start
|
||||
// is safe to call unconditionally, it no-ops when disabled or on a platform that does not need it.
|
||||
func NewNetworkChangeMonitor(ctx context.Context, l *slog.Logger, c *config.C) *NetworkChangeMonitor {
|
||||
if watchesNetworkChanges {
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("listen.rebind_on_network_change")
|
||||
})
|
||||
}
|
||||
|
||||
return &NetworkChangeMonitor{
|
||||
l: l,
|
||||
ctx: ctx,
|
||||
|
||||
@@ -13,9 +13,6 @@ import (
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// watchesNetworkChanges is true where Start does anything
|
||||
const watchesNetworkChanges = true
|
||||
|
||||
const (
|
||||
// netChangeSettleWindow is how long we keep swallowing routing messages after the first interesting one. A
|
||||
// single network change is never a single message, it is a burst: the link drops, addresses go away, new ones
|
||||
|
||||
@@ -7,9 +7,6 @@ import (
|
||||
"log/slog"
|
||||
)
|
||||
|
||||
// watchesNetworkChanges is true where Start does anything
|
||||
const watchesNetworkChanges = false
|
||||
|
||||
// watchNetworkChanges is a no-op outside of darwin.
|
||||
//
|
||||
// Darwin is the platform that scopes a udp socket to the interface it came up on, so it is the platform whose socket
|
||||
|
||||
@@ -37,19 +37,3 @@ func TestNetworkChangeMonitorNilRebindIsANoOp(t *testing.T) {
|
||||
m := newMonitor(t, context.Background(), "listen:\n rebind_on_network_change: true\n")
|
||||
m.Start(nil)
|
||||
}
|
||||
|
||||
// The monitor only reads listen.rebind_on_network_change when it is made
|
||||
func TestNetworkChangeMonitorRestartKey(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.LoadString("listen:\n rebind_on_network_change: true\n"))
|
||||
NewNetworkChangeMonitor(context.Background(), l, c)
|
||||
|
||||
res := c.ReloadConfigString("listen:\n rebind_on_network_change: false\n")
|
||||
require.NoError(t, res.Err)
|
||||
if watchesNetworkChanges {
|
||||
assert.Equal(t, []string{"listen.rebind_on_network_change"}, res.RestartKeys)
|
||||
} else {
|
||||
assert.Empty(t, res.RestartKeys, "the setting does nothing here")
|
||||
}
|
||||
}
|
||||
@@ -26,9 +26,7 @@ type bypassConn struct {
|
||||
session *wfp.Session
|
||||
}
|
||||
|
||||
func (b *bypassConn) ReloadConfig(c *config.C, r *config.Reload) {
|
||||
// Only read on the first call, at startup
|
||||
r.RestartRequiredIfChanged("listen.windows_bypass_wdf")
|
||||
func (b *bypassConn) ReloadConfig(c *config.C) {
|
||||
b.installOnce.Do(func() {
|
||||
if !c.GetBool("listen.windows_bypass_wdf", true) {
|
||||
return
|
||||
@@ -47,7 +45,7 @@ func (b *bypassConn) ReloadConfig(c *config.C, r *config.Reload) {
|
||||
"port", addr.Port())
|
||||
b.session = s
|
||||
})
|
||||
b.Conn.ReloadConfig(c, r)
|
||||
b.Conn.ReloadConfig(c)
|
||||
}
|
||||
|
||||
func (b *bypassConn) Close() error {
|
||||
|
||||
+6
-4
@@ -171,7 +171,7 @@ func (u *StdConn) LocalAddr() (netip.AddrPort, error) {
|
||||
}
|
||||
}
|
||||
|
||||
func (u *StdConn) ReloadConfig(c *config.C, r *config.Reload) {
|
||||
func (u *StdConn) ReloadConfig(c *config.C) {
|
||||
// TODO
|
||||
}
|
||||
|
||||
@@ -180,8 +180,9 @@ func NewUDPStatsEmitter(udpConns []Conn) func() {
|
||||
return func() {}
|
||||
}
|
||||
|
||||
func (u *StdConn) ListenOut(r EncReader, flush func()) error {
|
||||
buffer := make([]byte, MTU)
|
||||
func (u *StdConn) ListenOut(r EncReader, handoff func(bufs [][]byte) [][]byte) error {
|
||||
bufs := [][]byte{make([]byte, MTU)}
|
||||
buffer := bufs[0]
|
||||
|
||||
for {
|
||||
// Just read one packet at a time
|
||||
@@ -195,7 +196,8 @@ func (u *StdConn) ListenOut(r EncReader, flush func()) error {
|
||||
}
|
||||
|
||||
r(netip.AddrPortFrom(rua.Addr().Unmap(), rua.Port()), buffer[:n:n])
|
||||
flush()
|
||||
bufs = handoff(bufs)
|
||||
buffer = bufs[0]
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
+6
-4
@@ -73,7 +73,7 @@ func (u *GenericConn) LocalAddr() (netip.AddrPort, error) {
|
||||
}
|
||||
}
|
||||
|
||||
func (u *GenericConn) ReloadConfig(c *config.C, r *config.Reload) {
|
||||
func (u *GenericConn) ReloadConfig(c *config.C) {
|
||||
|
||||
}
|
||||
|
||||
@@ -86,8 +86,9 @@ type rawMessage struct {
|
||||
Len uint32
|
||||
}
|
||||
|
||||
func (u *GenericConn) ListenOut(r EncReader, flush func()) error {
|
||||
buffer := make([]byte, MTU)
|
||||
func (u *GenericConn) ListenOut(r EncReader, handoff func(bufs [][]byte) [][]byte) error {
|
||||
bufs := [][]byte{make([]byte, MTU)}
|
||||
buffer := bufs[0]
|
||||
|
||||
var lastRecvErr time.Time
|
||||
|
||||
@@ -107,7 +108,8 @@ func (u *GenericConn) ListenOut(r EncReader, flush func()) error {
|
||||
}
|
||||
|
||||
r(netip.AddrPortFrom(rua.Addr().Unmap(), rua.Port()), buffer[:n:n])
|
||||
flush()
|
||||
bufs = handoff(bufs)
|
||||
buffer = bufs[0]
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
+25
-8
@@ -245,11 +245,18 @@ func getFrom(names [][]byte, i int, isV4 bool) netip.AddrPort {
|
||||
return netip.AddrPortFrom(ip.Unmap(), binary.BigEndian.Uint16(names[i][2:4]))
|
||||
}
|
||||
|
||||
func (u *StdConn) ListenOut(r EncReader, flush func()) error {
|
||||
bufSize := MTU
|
||||
// HandoffShape is the count and size of the buffers ListenOut hands over after each batch.
|
||||
func (u *StdConn) HandoffShape() (n, size int) {
|
||||
if u.groSupported {
|
||||
return u.batch, udpGROBufferSize
|
||||
}
|
||||
return u.batch, MTU
|
||||
}
|
||||
|
||||
func (u *StdConn) ListenOut(r EncReader, handoff func(bufs [][]byte) [][]byte) error {
|
||||
_, bufSize := u.HandoffShape()
|
||||
cmsgSpace := 0
|
||||
if u.groSupported {
|
||||
bufSize = udpGROBufferSize
|
||||
cmsgSpace = unix.CmsgSpace(udpGROCmsgPayload)
|
||||
}
|
||||
msgs, buffers, names, _ := prepareRawMessages(u.batch, bufSize, cmsgSpace)
|
||||
@@ -283,7 +290,20 @@ func (u *StdConn) ListenOut(r EncReader, flush func()) error {
|
||||
deliverSegments(r, from, payload, segSize)
|
||||
}
|
||||
|
||||
flush()
|
||||
next := handoff(buffers)
|
||||
if len(next) != len(buffers) {
|
||||
panic(fmt.Sprintf("udp: handoff returned %d buffers, need %d", len(next), len(buffers)))
|
||||
}
|
||||
if &next[0] != &buffers[0] {
|
||||
// Replacements, point the recvmmsg iovecs at them
|
||||
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
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -392,7 +412,7 @@ func writeSockaddr(buf []byte, addr netip.AddrPort, isV4 bool) (int, error) {
|
||||
return unix.SizeofSockaddrInet6, nil
|
||||
}
|
||||
|
||||
func (u *StdConn) ReloadConfig(c *config.C, r *config.Reload) {
|
||||
func (u *StdConn) ReloadConfig(c *config.C) {
|
||||
b := c.GetInt("listen.read_buffer", 0)
|
||||
if b > 0 {
|
||||
if err := u.SetRecvBuffer(b); err == nil {
|
||||
@@ -403,7 +423,6 @@ func (u *StdConn) ReloadConfig(c *config.C, r *config.Reload) {
|
||||
}
|
||||
} else {
|
||||
u.l.Error("Failed to set listen.read_buffer", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -417,7 +436,6 @@ func (u *StdConn) ReloadConfig(c *config.C, r *config.Reload) {
|
||||
}
|
||||
} else {
|
||||
u.l.Error("Failed to set listen.write_buffer", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -432,7 +450,6 @@ func (u *StdConn) ReloadConfig(c *config.C, r *config.Reload) {
|
||||
}
|
||||
} else {
|
||||
u.l.Error("Failed to set listen.so_mark", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -226,7 +226,7 @@ func TestOffloadsDisabledRxDelivers(t *testing.T) {
|
||||
_ = sc.ListenOut(func(from netip.AddrPort, payload []byte) {
|
||||
// payload aliases the shared recv buffer row; copy before handing off.
|
||||
rxCh <- rxPkt{from, slices.Clone(payload)}
|
||||
}, func() {})
|
||||
}, func(bufs [][]byte) [][]byte { return bufs })
|
||||
}()
|
||||
|
||||
tx, err := net.DialUDP("udp4", nil, net.UDPAddrFromAddrPort(addr))
|
||||
|
||||
@@ -1,31 +0,0 @@
|
||||
//go:build linux && !android && !e2e_testing
|
||||
|
||||
package udp
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"os"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// A setting the kernel refuses fails the reload
|
||||
func TestReloadConfig_RefusedSettingFailsTheReload(t *testing.T) {
|
||||
if os.Geteuid() == 0 {
|
||||
t.Skip("root may set listen.so_mark, run as an unprivileged user")
|
||||
}
|
||||
conn, err := NewListener(testLogger(), Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0"), Batch: 1})
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() { _ = conn.Close() })
|
||||
|
||||
c := config.NewC(testLogger())
|
||||
require.NoError(t, c.LoadString("listen:\n port: 0\n"))
|
||||
c.RegisterReloadCallback(conn.ReloadConfig)
|
||||
|
||||
res := c.ReloadConfigString("listen:\n port: 0\n so_mark: 42\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
}
|
||||
@@ -142,7 +142,7 @@ func runTeardownCase(t *testing.T, batch int, name string, traffic func(send net
|
||||
go func() {
|
||||
loopDone <- sc.ListenOut(func(netip.AddrPort, []byte) {
|
||||
received.Add(1)
|
||||
}, func() {})
|
||||
}, func(bufs [][]byte) [][]byte { return bufs })
|
||||
}()
|
||||
|
||||
send, err := net.Dial("udp", addr.String())
|
||||
|
||||
@@ -12,7 +12,6 @@ import (
|
||||
"net/netip"
|
||||
"strconv"
|
||||
"strings"
|
||||
"sync"
|
||||
"unsafe"
|
||||
|
||||
"golang.org/x/sys/unix"
|
||||
@@ -21,7 +20,7 @@ import (
|
||||
// batchWriter owns the sendmmsg(2)/UDP-GSO transmit path for a StdConn: the
|
||||
// scratch WriteBatch packs mmsghdr entries into, plus the GSO capability
|
||||
// state probed at socket creation. Each queue has its own StdConn and
|
||||
// batchWriter; mu serializes batches from the TUN reader and relay forwarding.
|
||||
// batchWriter, so no locking is needed.
|
||||
//
|
||||
// Terminology, smallest to largest:
|
||||
//
|
||||
@@ -40,7 +39,6 @@ import (
|
||||
// chunk the entries packed for one sendmmsg call, at most MaxWriteBatch.
|
||||
// batch the caller's whole bufs/addrs pair, processed as one or more chunks.
|
||||
type batchWriter struct {
|
||||
mu sync.Mutex
|
||||
fd int
|
||||
isV4 bool
|
||||
|
||||
@@ -194,9 +192,6 @@ func parseRelease(r string) (major, minor int) {
|
||||
// Returns the number of packets sent. An error means the call itself failed.
|
||||
// A short count means some destinations were undeliverable.
|
||||
func (w *batchWriter) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error) {
|
||||
w.mu.Lock()
|
||||
defer w.mu.Unlock()
|
||||
|
||||
if len(bufs) != len(addrs) {
|
||||
return 0, fmt.Errorf("WriteBatch: len(bufs)=%d != len(addrs)=%d", len(bufs), len(addrs))
|
||||
}
|
||||
|
||||
@@ -1,61 +0,0 @@
|
||||
//go:build linux && !android && !e2e_testing
|
||||
|
||||
package udp
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"runtime"
|
||||
"sync"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// The TUN reader and relay forwarding share a socket. Exercise their concurrent
|
||||
// batches against the actual GSO planner and scratch, without relying on a NIC.
|
||||
func TestWriteBatchConcurrent(t *testing.T) {
|
||||
const batches = 64
|
||||
w := newRewindTestWriter()
|
||||
sent := make(chan [][]byte, 2*batches)
|
||||
w.sendFn = func(start, n int) (int, error) {
|
||||
runtime.Gosched()
|
||||
sent <- capturePrepared(w, start, n)
|
||||
return n, nil
|
||||
}
|
||||
conn := &StdConn{bw: w}
|
||||
remote := netip.MustParseAddrPort("192.0.2.1:4242")
|
||||
var wg sync.WaitGroup
|
||||
start := make(chan struct{})
|
||||
for producer := range 2 {
|
||||
wg.Go(func() {
|
||||
<-start
|
||||
for i := range batches {
|
||||
var bufs [][]byte
|
||||
var addrs []netip.AddrPort
|
||||
for j := range 4 {
|
||||
bufs = append(bufs, []byte{byte(producer), byte(i), byte(j), 0})
|
||||
addrs = append(addrs, remote)
|
||||
}
|
||||
n, err := conn.WriteBatch(bufs, addrs)
|
||||
if err != nil || n != len(bufs) {
|
||||
t.Errorf("WriteBatch = %d, %v; want %d, nil", n, err, len(bufs))
|
||||
return
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
close(start)
|
||||
wg.Wait()
|
||||
close(sent)
|
||||
var counts [2]int
|
||||
for packets := range sent {
|
||||
require.Len(t, packets, 4)
|
||||
producer := packets[0][0]
|
||||
require.Less(t, int(producer), len(counts))
|
||||
for j, packet := range packets {
|
||||
require.Equal(t, []byte{producer, byte(counts[producer]), byte(j), 0}, packet)
|
||||
}
|
||||
counts[producer]++
|
||||
}
|
||||
require.Equal(t, [2]int{batches, batches}, counts)
|
||||
}
|
||||
@@ -142,8 +142,9 @@ func (u *RIOConn) bind(l *slog.Logger, sa windows.Sockaddr) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (u *RIOConn) ListenOut(r EncReader, flush func()) error {
|
||||
buffer := make([]byte, MTU)
|
||||
func (u *RIOConn) ListenOut(r EncReader, handoff func(bufs [][]byte) [][]byte) error {
|
||||
bufs := [][]byte{make([]byte, MTU)}
|
||||
buffer := bufs[0]
|
||||
|
||||
var lastRecvErr time.Time
|
||||
|
||||
@@ -164,7 +165,8 @@ func (u *RIOConn) ListenOut(r EncReader, flush func()) error {
|
||||
}
|
||||
|
||||
r(netip.AddrPortFrom(netip.AddrFrom16(rua.Addr).Unmap(), (rua.Port>>8)|((rua.Port&0xff)<<8)), buffer[:n:n])
|
||||
flush()
|
||||
bufs = handoff(bufs)
|
||||
buffer = bufs[0]
|
||||
}
|
||||
}
|
||||
|
||||
@@ -351,7 +353,7 @@ func (u *RIOConn) Rebind() error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (u *RIOConn) ReloadConfig(*config.C, *config.Reload) {}
|
||||
func (u *RIOConn) ReloadConfig(*config.C) {}
|
||||
|
||||
func (u *RIOConn) Close() error {
|
||||
if !u.isOpen.CompareAndSwap(true, false) {
|
||||
|
||||
+13
-5
@@ -182,22 +182,30 @@ func (u *TesterConn) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, err
|
||||
return written, nil
|
||||
}
|
||||
|
||||
func (u *TesterConn) ListenOut(r EncReader, flush func()) error {
|
||||
// HandoffShape is one buffer per handoff; the pool resizes the replacements it gets back as it needs.
|
||||
func (u *TesterConn) HandoffShape() (n, size int) { return 1, MTU }
|
||||
|
||||
// ListenOut hands each packet's buffer over as a batch of one, the buffer it gets back goes to the pool. Like StdConn
|
||||
// it carries on with the slice handoff returns, since a reader that keeps the packets keeps the one it was given.
|
||||
// The batcher borrows plaintext decrypted in place inside p.Data until it flushes, inside handoff, so the packet
|
||||
// must stay alive until handoff returns.
|
||||
func (u *TesterConn) ListenOut(r EncReader, handoff func(bufs [][]byte) [][]byte) error {
|
||||
bufs := make([][]byte, 1)
|
||||
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()
|
||||
bufs[0] = p.Data
|
||||
bufs = handoff(bufs)
|
||||
p.Data = bufs[0]
|
||||
p.Release()
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func (u *TesterConn) ReloadConfig(*config.C, *config.Reload) {}
|
||||
func (u *TesterConn) ReloadConfig(*config.C) {}
|
||||
|
||||
func NewUDPStatsEmitter(_ []Conn) func() {
|
||||
// No UDP stats for non-linux
|
||||
|
||||
Reference in new issue
Block a user