mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-16 16:46:52 +01:00
Compare commits
18
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
d3e21a8fc8 | ||
|
|
cda3710d5a | ||
|
|
c26871fe08 | ||
|
|
7daacc6a48 | ||
|
|
428dad94b3 | ||
|
|
5bf666dd90 | ||
|
|
49207da077 | ||
|
|
bbc49669b7 | ||
|
|
915495d5f4 | ||
|
|
a203d044bb | ||
|
|
316bf87780 | ||
|
|
1a0ac25db0 | ||
|
|
42597dda7d | ||
|
|
afbdc87ed9 | ||
|
|
94372f4f51 | ||
|
|
42280f04ce | ||
|
|
11c1917387 | ||
|
|
5ba7aff4b3 |
No files matched your search
@@ -14,7 +14,7 @@ jobs:
|
|||||||
|
|
||||||
- uses: actions/setup-go@v7
|
- uses: actions/setup-go@v7
|
||||||
with:
|
with:
|
||||||
go-version: '1.26'
|
go-version: '1.27'
|
||||||
check-latest: true
|
check-latest: true
|
||||||
|
|
||||||
- name: Build
|
- name: Build
|
||||||
@@ -40,7 +40,7 @@ jobs:
|
|||||||
|
|
||||||
- uses: actions/setup-go@v7
|
- uses: actions/setup-go@v7
|
||||||
with:
|
with:
|
||||||
go-version: '1.26'
|
go-version: '1.27'
|
||||||
check-latest: true
|
check-latest: true
|
||||||
|
|
||||||
- name: Build
|
- name: Build
|
||||||
@@ -83,7 +83,7 @@ jobs:
|
|||||||
|
|
||||||
- uses: actions/setup-go@v7
|
- uses: actions/setup-go@v7
|
||||||
with:
|
with:
|
||||||
go-version: '1.26'
|
go-version: '1.27'
|
||||||
check-latest: true
|
check-latest: true
|
||||||
|
|
||||||
# GitHub holds ARNs, not credentials, and ARNs outlive a rotation
|
# GitHub holds ARNs, not credentials, and ARNs outlive a rotation
|
||||||
|
|||||||
@@ -34,7 +34,7 @@ jobs:
|
|||||||
|
|
||||||
- uses: actions/setup-go@v7
|
- uses: actions/setup-go@v7
|
||||||
with:
|
with:
|
||||||
go-version: '1.26'
|
go-version: '1.27'
|
||||||
check-latest: true
|
check-latest: true
|
||||||
|
|
||||||
- name: add hashicorp source
|
- name: add hashicorp source
|
||||||
@@ -66,7 +66,7 @@ jobs:
|
|||||||
|
|
||||||
- uses: actions/setup-go@v7
|
- uses: actions/setup-go@v7
|
||||||
with:
|
with:
|
||||||
go-version: '1.26'
|
go-version: '1.27'
|
||||||
check-latest: true
|
check-latest: true
|
||||||
|
|
||||||
- name: add hashicorp source
|
- name: add hashicorp source
|
||||||
@@ -92,7 +92,7 @@ jobs:
|
|||||||
|
|
||||||
- uses: actions/setup-go@v7
|
- uses: actions/setup-go@v7
|
||||||
with:
|
with:
|
||||||
go-version: '1.26'
|
go-version: '1.27'
|
||||||
check-latest: true
|
check-latest: true
|
||||||
|
|
||||||
# WSL2 + Ubuntu so the smoke can run a real linux peer with its own
|
# WSL2 + Ubuntu so the smoke can run a real linux peer with its own
|
||||||
|
|||||||
@@ -22,7 +22,7 @@ jobs:
|
|||||||
|
|
||||||
- uses: actions/setup-go@v7
|
- uses: actions/setup-go@v7
|
||||||
with:
|
with:
|
||||||
go-version: '1.26'
|
go-version: '1.27'
|
||||||
check-latest: true
|
check-latest: true
|
||||||
|
|
||||||
- name: Smoke Docker
|
- name: Smoke Docker
|
||||||
@@ -51,7 +51,7 @@ jobs:
|
|||||||
|
|
||||||
- uses: actions/setup-go@v7
|
- uses: actions/setup-go@v7
|
||||||
with:
|
with:
|
||||||
go-version: '1.26'
|
go-version: '1.27'
|
||||||
check-latest: true
|
check-latest: true
|
||||||
|
|
||||||
- name: build
|
- name: build
|
||||||
|
|||||||
@@ -22,7 +22,7 @@ jobs:
|
|||||||
|
|
||||||
- uses: actions/setup-go@v7
|
- uses: actions/setup-go@v7
|
||||||
with:
|
with:
|
||||||
go-version: '1.26'
|
go-version: '1.27'
|
||||||
check-latest: true
|
check-latest: true
|
||||||
|
|
||||||
- name: Install goimports
|
- name: Install goimports
|
||||||
@@ -42,7 +42,7 @@ jobs:
|
|||||||
- name: golangci-lint
|
- name: golangci-lint
|
||||||
uses: golangci/golangci-lint-action@v9
|
uses: golangci/golangci-lint-action@v9
|
||||||
with:
|
with:
|
||||||
version: v2.12
|
version: v2.14
|
||||||
|
|
||||||
test:
|
test:
|
||||||
name: Test ${{ matrix.name }}
|
name: Test ${{ matrix.name }}
|
||||||
@@ -87,7 +87,7 @@ jobs:
|
|||||||
|
|
||||||
- uses: actions/setup-go@v7
|
- uses: actions/setup-go@v7
|
||||||
with:
|
with:
|
||||||
go-version: '1.26'
|
go-version: '1.27'
|
||||||
check-latest: true
|
check-latest: true
|
||||||
|
|
||||||
- name: Build
|
- name: Build
|
||||||
@@ -132,7 +132,7 @@ jobs:
|
|||||||
|
|
||||||
- uses: actions/setup-go@v7
|
- uses: actions/setup-go@v7
|
||||||
with:
|
with:
|
||||||
go-version: '1.26'
|
go-version: '1.27'
|
||||||
check-latest: true
|
check-latest: true
|
||||||
|
|
||||||
- name: Build ${{ matrix.name }}
|
- name: Build ${{ matrix.name }}
|
||||||
|
|||||||
@@ -7,8 +7,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
|||||||
|
|
||||||
## [Unreleased]
|
## [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
|
### 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
|
- `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
|
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
|
pass attached one, and `create-tunnel -address` set the remote before that. The list is now attached when
|
||||||
|
|||||||
+10
-1
@@ -389,7 +389,16 @@ func (c *certificateV2) fromTBSCertificate(t *TBSCertificate) error {
|
|||||||
}
|
}
|
||||||
|
|
||||||
func (c *certificateV2) validate() error {
|
func (c *certificateV2) validate() error {
|
||||||
// Empty names are allowed
|
// 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")
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
if len(c.publicKey) == 0 {
|
if len(c.publicKey) == 0 {
|
||||||
return ErrInvalidPublicKey
|
return ErrInvalidPublicKey
|
||||||
|
|||||||
@@ -6,6 +6,7 @@ import (
|
|||||||
"crypto/elliptic"
|
"crypto/elliptic"
|
||||||
"crypto/rand"
|
"crypto/rand"
|
||||||
"net/netip"
|
"net/netip"
|
||||||
|
"strings"
|
||||||
"testing"
|
"testing"
|
||||||
"time"
|
"time"
|
||||||
|
|
||||||
@@ -135,3 +136,47 @@ func TestCertificate_SignP256_AlwaysNormalized(t *testing.T) {
|
|||||||
assert.True(t, normie)
|
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)
|
||||||
|
}
|
||||||
@@ -85,9 +85,10 @@ func main() {
|
|||||||
fmt.Printf("failed to apply logging config: %s", err)
|
fmt.Printf("failed to apply logging config: %s", err)
|
||||||
os.Exit(1)
|
os.Exit(1)
|
||||||
}
|
}
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
if err := logging.ApplyConfig(l, c); err != nil {
|
if err := logging.ApplyConfig(l, c); err != nil {
|
||||||
l.Error("Failed to reconfigure logger on reload", "error", err)
|
l.Error("Failed to reconfigure logger on reload", "error", err)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
|
||||||
|
|||||||
@@ -34,9 +34,10 @@ func (p *program) Start(s service.Service) error {
|
|||||||
if err := logging.ApplyConfig(l, c); err != nil {
|
if err := logging.ApplyConfig(l, c); err != nil {
|
||||||
return fmt.Errorf("failed to apply logging config: %s", err)
|
return fmt.Errorf("failed to apply logging config: %s", err)
|
||||||
}
|
}
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
if err := logging.ApplyConfig(l, c); err != nil {
|
if err := logging.ApplyConfig(l, c); err != nil {
|
||||||
l.Error("Failed to reconfigure logger on reload", "error", err)
|
l.Error("Failed to reconfigure logger on reload", "error", err)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
|
||||||
|
|||||||
+2
-1
@@ -71,9 +71,10 @@ func main() {
|
|||||||
fmt.Printf("failed to apply logging config: %s", err)
|
fmt.Printf("failed to apply logging config: %s", err)
|
||||||
os.Exit(1)
|
os.Exit(1)
|
||||||
}
|
}
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
if err := logging.ApplyConfig(l, c); err != nil {
|
if err := logging.ApplyConfig(l, c); err != nil {
|
||||||
l.Error("Failed to reconfigure logger on reload", "error", err)
|
l.Error("Failed to reconfigure logger on reload", "error", err)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
|
||||||
|
|||||||
+31
-22
@@ -26,9 +26,12 @@ type C struct {
|
|||||||
files []string
|
files []string
|
||||||
Settings map[string]any
|
Settings map[string]any
|
||||||
oldSettings map[string]any
|
oldSettings map[string]any
|
||||||
callbacks []func(*C)
|
callbacks []func(*C, *Reload)
|
||||||
l *slog.Logger
|
l *slog.Logger
|
||||||
reloadLock sync.Mutex
|
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 {
|
func NewC(l *slog.Logger) *C {
|
||||||
@@ -72,8 +75,9 @@ func (c *C) LoadString(raw string) error {
|
|||||||
// RegisterReloadCallback stores a function to be called when a config reload is triggered. The functions registered
|
// 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
|
// 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.
|
// 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
|
// These functions should return quickly or spawn their own go routine if they will take a while.
|
||||||
func (c *C) RegisterReloadCallback(f func(*C)) {
|
// Use r to report anything that failed or needs a restart to apply.
|
||||||
|
func (c *C) RegisterReloadCallback(f func(c *C, r *Reload)) {
|
||||||
c.callbacks = append(c.callbacks, f)
|
c.callbacks = append(c.callbacks, f)
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -144,50 +148,55 @@ func (c *C) CatchHUP(ctx context.Context) {
|
|||||||
return
|
return
|
||||||
case <-ch:
|
case <-ch:
|
||||||
c.l.Info("Caught HUP, reloading config")
|
c.l.Info("Caught HUP, reloading config")
|
||||||
c.ReloadConfig()
|
c.ReloadConfig().Log(c.l)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}()
|
}()
|
||||||
}
|
}
|
||||||
|
|
||||||
func (c *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 {
|
||||||
c.reloadLock.Lock()
|
c.reloadLock.Lock()
|
||||||
defer c.reloadLock.Unlock()
|
defer c.reloadLock.Unlock()
|
||||||
|
|
||||||
c.oldSettings = make(map[string]any)
|
c.oldSettings = make(map[string]any)
|
||||||
maps.Copy(c.oldSettings, c.Settings)
|
maps.Copy(c.oldSettings, c.Settings)
|
||||||
|
|
||||||
err := c.Load(c.path)
|
if err := c.Load(c.path); err != nil {
|
||||||
if err != nil {
|
c.l.Error("Error occurred while reloading config", "config_path", c.path, "error", err)
|
||||||
c.l.Error("Error occurred while reloading config",
|
return ReloadResult{Err: err, RestartRequired: c.needsRestart}
|
||||||
"config_path", c.path,
|
|
||||||
"error", err,
|
|
||||||
)
|
|
||||||
return
|
|
||||||
}
|
}
|
||||||
|
|
||||||
for _, v := range c.callbacks {
|
return c.runCallbacks()
|
||||||
v(c)
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
func (c *C) ReloadConfigString(raw string) error {
|
// ReloadConfigString is ReloadConfig for a config held in memory rather than on disk.
|
||||||
|
func (c *C) ReloadConfigString(raw string) ReloadResult {
|
||||||
c.reloadLock.Lock()
|
c.reloadLock.Lock()
|
||||||
defer c.reloadLock.Unlock()
|
defer c.reloadLock.Unlock()
|
||||||
|
|
||||||
c.oldSettings = make(map[string]any)
|
c.oldSettings = make(map[string]any)
|
||||||
maps.Copy(c.oldSettings, c.Settings)
|
maps.Copy(c.oldSettings, c.Settings)
|
||||||
|
|
||||||
err := c.LoadString(raw)
|
if err := c.LoadString(raw); err != nil {
|
||||||
if err != nil {
|
c.l.Error("Error occurred while reloading config", "error", err)
|
||||||
return 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 {
|
for _, v := range c.callbacks {
|
||||||
v(c)
|
v(c, r)
|
||||||
}
|
}
|
||||||
|
|
||||||
return nil
|
if r.restart {
|
||||||
|
c.needsRestart = true
|
||||||
|
}
|
||||||
|
return ReloadResult{Failed: r.failed, RestartRequired: c.needsRestart, RestartKeys: r.keys}
|
||||||
}
|
}
|
||||||
|
|
||||||
// GetString will get the string for k or return the default d if not found or invalid
|
// GetString will get the string for k or return the default d if not found or invalid
|
||||||
@@ -391,7 +400,7 @@ func (c *C) parse() error {
|
|||||||
var nm map[string]any
|
var nm map[string]any
|
||||||
err = yaml.Unmarshal(b, &nm)
|
err = yaml.Unmarshal(b, &nm)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return fmt.Errorf("%s: %w", path, err)
|
||||||
}
|
}
|
||||||
|
|
||||||
// We need to use WithAppendSlice so that firewall rules in separate
|
// We need to use WithAppendSlice so that firewall rules in separate
|
||||||
|
|||||||
@@ -19,7 +19,7 @@ func TestConfig_Load(t *testing.T) {
|
|||||||
// invalid yaml
|
// invalid yaml
|
||||||
c := NewC(l)
|
c := NewC(l)
|
||||||
os.WriteFile(filepath.Join(dir, "01.yaml"), []byte(" invalid yaml"), 0644)
|
os.WriteFile(filepath.Join(dir, "01.yaml"), []byte(" invalid yaml"), 0644)
|
||||||
require.EqualError(t, c.Load(dir), "yaml: unmarshal errors:\n line 1: cannot unmarshal !!str `invalid...` into map[string]interface {}")
|
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 {}")
|
||||||
|
|
||||||
// simple multi config merge
|
// simple multi config merge
|
||||||
c = NewC(l)
|
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)
|
os.WriteFile(filepath.Join(dir, "01.yaml"), []byte("outer:\n inner: ho"), 0644)
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *C) {
|
c.RegisterReloadCallback(func(c *C, _ *Reload) {
|
||||||
done <- true
|
done <- true
|
||||||
})
|
})
|
||||||
|
|
||||||
|
|||||||
@@ -0,0 +1,98 @@
|
|||||||
|
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
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,108 @@
|
|||||||
|
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")
|
||||||
|
}
|
||||||
@@ -57,7 +57,8 @@ func newConnectionManagerFromConfig(l *slog.Logger, c *config.C, hm *HostMap, p
|
|||||||
}
|
}
|
||||||
|
|
||||||
cm.reload(c, true)
|
cm.reload(c, true)
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
|
r.RestartRequiredIfChanged("timers.connection_alive_interval", "timers.pending_deletion_interval")
|
||||||
cm.reload(c, false)
|
cm.reload(c, false)
|
||||||
})
|
})
|
||||||
|
|
||||||
|
|||||||
@@ -151,7 +151,7 @@ func (c *fakeConn) WriteTo(_ []byte, _ netip.AddrPort) error { return nil }
|
|||||||
func (c *fakeConn) WriteBatch(bufs [][]byte, _ []netip.AddrPort) (int, error) {
|
func (c *fakeConn) WriteBatch(bufs [][]byte, _ []netip.AddrPort) (int, error) {
|
||||||
return len(bufs), nil
|
return len(bufs), nil
|
||||||
}
|
}
|
||||||
func (c *fakeConn) ReloadConfig(_ *config.C) {}
|
func (c *fakeConn) ReloadConfig(_ *config.C, _ *config.Reload) {}
|
||||||
func (c *fakeConn) SupportsMultipleReaders() bool { return true }
|
func (c *fakeConn) SupportsMultipleReaders() bool { return true }
|
||||||
func (c *fakeConn) Close() error { c.closed = true; return nil }
|
func (c *fakeConn) Close() error { c.closed = true; return nil }
|
||||||
|
|
||||||
|
|||||||
+2
-1
@@ -69,9 +69,10 @@ func newDnsServerFromConfig(ctx context.Context, l *slog.Logger, pki *PKI, hostM
|
|||||||
ds.mux = dns.NewServeMux()
|
ds.mux = dns.NewServeMux()
|
||||||
ds.mux.HandleFunc(".", ds.handleDnsRequest)
|
ds.mux.HandleFunc(".", ds.handleDnsRequest)
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
if err := ds.reload(c, false); err != nil {
|
if err := ds.reload(c, false); err != nil {
|
||||||
ds.l.Error("Failed to reload DNS responder from config", "error", err)
|
ds.l.Error("Failed to reload DNS responder from config", "error", err)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
|
||||||
|
|||||||
@@ -1,131 +0,0 @@
|
|||||||
# Post-quantum handshake transport compared with QUIC
|
|
||||||
|
|
||||||
Status: analysis, 2026-10-14. Compares the fragment transport in
|
|
||||||
[pq-handshake.md](pq-handshake.md) with how QUIC makes its handshake reliable. TLS is out of
|
|
||||||
scope; only the transport mechanics are compared.
|
|
||||||
|
|
||||||
## Summary
|
|
||||||
|
|
||||||
QUIC's handshake reliability is closed-loop: the receiver acknowledges, and the sender
|
|
||||||
repairs exactly what is missing. Ours is open-loop: repair symbols are sent up front, and a
|
|
||||||
timer sends fresh symbols. At handshake sizes (K <= 15) a QUIC-style acknowledgement
|
|
||||||
shrinks to a 16-bit bitmap, and with an MDS code to a single count. So the real comparison
|
|
||||||
is forward error correction versus acknowledgements, not QUIC versus us.
|
|
||||||
|
|
||||||
FEC is the right core. One piece of feedback is worth adding, initiator to responder and for
|
|
||||||
msg2 only (see [Worth taking from QUIC](#worth-taking-from-quic)).
|
|
||||||
|
|
||||||
## What QUIC does
|
|
||||||
|
|
||||||
- **Messages as a stream.** Handshake bytes travel as `CRYPTO` frames (offset and length)
|
|
||||||
and are reassembled in order. Initial and Handshake packets each have their own packet
|
|
||||||
number space.
|
|
||||||
- **Immediate acknowledgements.** Receivers must acknowledge Initial and Handshake packets
|
|
||||||
without delay. ACK frames list ranges of received packet numbers.
|
|
||||||
- **Loss detection** (RFC 9002). A packet is lost once 3 later packets are acknowledged, or
|
|
||||||
after 9/8 of the round-trip time. Lost bytes are resent in new packets.
|
|
||||||
- **Probe timeout (PTO).** If a whole flight vanishes, a probe timer fires. Before any RTT
|
|
||||||
sample it starts at about 1 s (333 ms initial RTT plus 4x its variance) and doubles each
|
|
||||||
time. Both endpoints run it.
|
|
||||||
- **Amplification limit and anti-deadlock.** The server may send at most 3x what it
|
|
||||||
received until the client's address is validated. The client must keep probing so a
|
|
||||||
server stuck at that limit cannot deadlock.
|
|
||||||
- **Retry.** A stateless round trip to validate the address. `NEW_TOKEN` lets later
|
|
||||||
connections skip it.
|
|
||||||
- **Congestion control from the first packet.** The initial window is 10 packets of 1200
|
|
||||||
bytes.
|
|
||||||
|
|
||||||
## Side by side
|
|
||||||
|
|
||||||
| | QUIC | pq-handshake |
|
|
||||||
|---|---|---|
|
|
||||||
| Receiver feedback | ACK ranges, sent immediately | None; the next handshake message is the only acknowledgement |
|
|
||||||
| Partial loss | +1 to 2 RTT (ACK, detect, resend) | 0 RTT while at most m symbols are lost |
|
|
||||||
| Total loss | PTO: about 1 s, then doubling | Next PQ tick: 300 ms, then 1 s (alternating), or 100/300/600 ms (sticky) |
|
|
||||||
| Spurious retransmit | Wasted bytes | Still useful: fresh repair indexes add to what the receiver holds |
|
|
||||||
| Reassembly | Every byte offset, in order | Any K of up to 256 symbols |
|
|
||||||
| Who retransmits | Both sides on their own timers | Initiator on a timer; the responder resends msg2 only when a repeat msg1 arrives (rate limited) |
|
|
||||||
| State from the first packet | Server buffers and acknowledges partial flights | Capped pre-authentication table that never acknowledges |
|
|
||||||
| Address validation | Retry, 1 RTT | Cookie under load, 1 RTT |
|
|
||||||
|
|
||||||
From the [simulation results](pq-handshake.md#simulation-results): phase 2 at 5% random
|
|
||||||
loss with no FEC completes on the first attempt 39.8% of the time. Under
|
|
||||||
acknowledgement-based recovery roughly 60% of handshakes would pay at least one extra round
|
|
||||||
trip. With FEC, 0.4% wait for a retry. Spending bandwidth to save round trips is the stated
|
|
||||||
design preference, and open-loop recovery delivers it.
|
|
||||||
|
|
||||||
## Where the designs already agree
|
|
||||||
|
|
||||||
- **1200-byte floor and the 3x amplification budget**, both taken directly from QUIC.
|
|
||||||
- **Cookie and Retry.** Both cost one round trip and both can be forged by an on-path
|
|
||||||
attacker. QUIC's Retry integrity tag uses a fixed, published key.
|
|
||||||
- **On-path injection.** QUIC's Initial keys are derived from the client's connection ID,
|
|
||||||
which an observer can read, so QUIC accepts the same handshake-blocking injection
|
|
||||||
weakness documented for our symbols in
|
|
||||||
[Injected symbols](pq-handshake.md#injected-symbols).
|
|
||||||
- **Phase 2 msg3 confirmation.** Resending msg3 until any authenticated packet arrives,
|
|
||||||
with a `Test` from the responder on completion, is QUIC's handshake confirmation and
|
|
||||||
`HANDSHAKE_DONE`.
|
|
||||||
|
|
||||||
## Worth taking from QUIC
|
|
||||||
|
|
||||||
### 1. A msg2 progress probe from the initiator
|
|
||||||
|
|
||||||
This is the main gap. Today, recovering a partially lost msg2 means the initiator resends a
|
|
||||||
full msg1 attempt; the responder decodes it, matches it in the answered-msg1 cache, and
|
|
||||||
resends msg2. In phase 2 that is about 12 fragments (~13 KB) uploaded just to act as an
|
|
||||||
acknowledgement, and recovery waits for the 300 ms or 1 s tick.
|
|
||||||
|
|
||||||
- The initiator already knows the responder's index: msg2 fragments carry it as `FragID`
|
|
||||||
(`sendFragmentedResponse` passes `hostinfo.localIndexId`).
|
|
||||||
- A one-packet probe, "msg2: have n of K", sent to that index would recover in about one
|
|
||||||
round trip. The responder finds it the way phase 2 plans to find msg3.
|
|
||||||
- Timing comes for free: msg1 send to first msg2 fragment is an RTT sample. Probe at
|
|
||||||
roughly RTT/8 plus the repair delay after the first msg2 fragment if decoding has not
|
|
||||||
completed.
|
|
||||||
- Forging a probe needs the 32-bit responder index, so only an on-path attacker can, and
|
|
||||||
the existing 3x budget bounds the reply.
|
|
||||||
- If no msg2 fragment arrived at all, the initiator keeps today's msg1 resend. That is the
|
|
||||||
same tail-loss case QUIC's PTO covers.
|
|
||||||
|
|
||||||
The reverse direction, the responder reporting progress on msg1, should not be added. It
|
|
||||||
needs per-entry timers on the pre-authentication path, which is exactly the state QUIC
|
|
||||||
servers carry and the reason QUIC needs Retry.
|
|
||||||
|
|
||||||
### 2. Buffer early data in phase 2
|
|
||||||
|
|
||||||
QUIC stacks hold a few packets they cannot decrypt yet. The phase 2 plan drops data that
|
|
||||||
reaches the responder before msg3 decodes. Because repair fragments trail by
|
|
||||||
`handshakes.pq.repair_delay` (10 ms), losing one msg3 data fragment drops about 10 ms of
|
|
||||||
the initiator's first data while the repair is in flight. A small queue on the pending
|
|
||||||
responder entry, replayed once msg3 verifies, avoids this.
|
|
||||||
|
|
||||||
### 3. Burst size across remotes
|
|
||||||
|
|
||||||
QUIC handshakes on a single path. `handleOutbound` sends the same `now` and `later` sets to
|
|
||||||
every known remote and to relays (`StartRelays`).
|
|
||||||
|
|
||||||
- Phase 1 is fine.
|
|
||||||
- In phase 2, four remotes means about 48 packets (~54 KB) leaving one uplink at once,
|
|
||||||
every PQ tick, about 4x QUIC's initial window.
|
|
||||||
- The Gilbert-Elliott simulation treats each path independently, so it does not capture
|
|
||||||
this self-inflicted burst on a constrained uplink such as cellular.
|
|
||||||
- Options: send the full FEC set only to the most likely remote and a reduced set to the
|
|
||||||
others, or interleave packets across remotes.
|
|
||||||
|
|
||||||
## Not worth taking
|
|
||||||
|
|
||||||
- **Packet numbers, ACK ranges, an RTT estimator, loss thresholds, congestion control.**
|
|
||||||
QUIC pays for this machinery because it also serves a data transport. Nebula carries
|
|
||||||
packets and leaves reliability to the overlay's own transports. Building it only for
|
|
||||||
handshakes of at most 15 fragments buys nothing a symbol count cannot.
|
|
||||||
- **Offset-based reassembly.** It gives up the any-K-of-256 property and makes spurious
|
|
||||||
retransmits wasteful again.
|
|
||||||
- **An RTT-adaptive retry timer.** Low value. The fixed 100 ms linear schedule already fires
|
|
||||||
sooner than QUIC's 1 s first PTO, and a spurious resend costs bandwidth, not correctness.
|
|
||||||
|
|
||||||
## Conclusion
|
|
||||||
|
|
||||||
Keep FEC as the core and add the msg2 progress probe. That gets QUIC's roughly one round
|
|
||||||
trip tail recovery without pre-authentication state, and cuts phase 2's retry cost on the
|
|
||||||
uplink by about 10x. Items 2 and 3 are phase 2 concerns; item 1 also helps phase 1.
|
|
||||||
@@ -1,348 +0,0 @@
|
|||||||
# Post-quantum handshakes
|
|
||||||
|
|
||||||
Status: draft. Decisions below were made on 2026-10-13; open items are listed at the end.
|
|
||||||
Phase 1 is implemented (see [Implementation](#implementation-phase-1)).
|
|
||||||
|
|
||||||
## Goals
|
|
||||||
|
|
||||||
1. **Confidentiality against harvest-now-decrypt-later.** Traffic recorded today must stay
|
|
||||||
secret after a cryptographically relevant quantum computer exists. This needs a
|
|
||||||
post-quantum key exchange now.
|
|
||||||
2. **Post-quantum authentication, later.** Needs certificates whose CA signature and host
|
|
||||||
keys are post-quantum. This requires reissuing certificates, so it ships second.
|
|
||||||
3. **Never rely on IP fragmentation.** ML-KEM and ML-DSA do not fit in one packet, so the
|
|
||||||
handshake must carry messages larger than the path MTU itself.
|
|
||||||
|
|
||||||
Non-goals: identity hiding beyond what IX offers today, and signatures at handshake time.
|
|
||||||
The only signature in the system stays the CA signature inside the certificate.
|
|
||||||
|
|
||||||
## Primitives and sizes
|
|
||||||
|
|
||||||
| Primitive | Size |
|
|
||||||
|---|---|
|
|
||||||
| ML-KEM-1024 encapsulation key | 1568 B |
|
|
||||||
| ML-KEM-1024 ciphertext | 1568 B |
|
|
||||||
| ML-DSA-87 public key / signature | 2592 B / 4627 B |
|
|
||||||
| Today's IX msg1 / msg2 (v2 cert, 151 B) | 252 B / 287 B |
|
|
||||||
|
|
||||||
`crypto/mlkem` is available in Go 1.26 (the current `go.mod`); `crypto/mldsa` arrives in
|
|
||||||
Go 1.27 and is only needed for phase 2.
|
|
||||||
|
|
||||||
## Phase 1: ephemeral ML-KEM on today's certificates
|
|
||||||
|
|
||||||
A new handshake subtype, `ix_psk2_mlkem1024` (2), IX-shaped (2 messages; the responder
|
|
||||||
completes on msg1 as today), using the flynn/noise `psk2` modifier. The Noise protocol name
|
|
||||||
becomes `Noise_IXpsk2_...`, which separates it from the classical subtype.
|
|
||||||
|
|
||||||
- **msg1**: the initiator generates a fresh ML-KEM-1024 key pair and places the
|
|
||||||
encapsulation key in `NebulaHandshakeDetails.KEMKey` (field 9). msg1's payload is mixed
|
|
||||||
into the Noise transcript, so it cannot be stripped or replaced without msg2 failing.
|
|
||||||
With the psk modifier Noise also mixes `e` into the cipher key, so msg1's static key and
|
|
||||||
payload are encrypted, though only under a key derived from the public ephemeral.
|
|
||||||
- **Responder**: after `ReadMessage(msg1)` it encapsulates to that key, obtaining
|
|
||||||
`(ct, ss)`, and calls `HandshakeState.SetPresharedKey(psk)` before writing msg2, with
|
|
||||||
`psk = HKDF-Extract(SHA-256, salt = "nebula ix_psk2_mlkem1024 v1", ikm = ss || ct)`.
|
|
||||||
The ciphertext is bound in because, unlike the encapsulation key, it is not part of the
|
|
||||||
Noise transcript.
|
|
||||||
- **msg2** on the wire is `ct || noise_msg2`. The ciphertext travels outside the Noise
|
|
||||||
message because the initiator needs `ss` before processing msg2's `psk` token. Any change
|
|
||||||
to `ct` yields a different `ss` (ML-KEM implicit rejection) and the handshake fails.
|
|
||||||
|
|
||||||
Transport keys depend on both the X25519 DH outputs and the ML-KEM shared secret.
|
|
||||||
Authentication is unchanged and classical. With a minimal v2 certificate msg1 and msg2 are
|
|
||||||
about 1.84 KB each, so each travels as 2 data and 2 repair fragments of about 936 bytes.
|
|
||||||
A KEM key on the classical subtype, or a missing or malformed one on this subtype, is a fatal
|
|
||||||
protocol error; a forged ciphertext only fails that packet.
|
|
||||||
|
|
||||||
## Phase 2: pqIX hybrid with certificate v3
|
|
||||||
|
|
||||||
Certificate v3 is hybrid: the classical static key and CA signature plus a static
|
|
||||||
ML-KEM-1024 key and an ML-DSA-87 CA signature. Host authentication is by KEM rather than by
|
|
||||||
signature, following PQNoise's pqIX, while keeping the classical DH tokens:
|
|
||||||
|
|
||||||
- **msg1** (I to R): `e, s`, ephemeral ML-KEM key, initiator cert.
|
|
||||||
- **msg2** (R to I): `e, s`, ciphertext to I's ephemeral KEM key, ciphertext to I's static
|
|
||||||
KEM key, responder cert.
|
|
||||||
- **msg3** (I to R): ciphertext to R's static KEM key, plus first data. R authenticates I
|
|
||||||
when msg3 decrypts; I authenticates R implicitly when R's first reply decrypts.
|
|
||||||
|
|
||||||
msg3 is about 1.6 KB, 2 data and 2 repair fragments, and adds no new message types:
|
|
||||||
|
|
||||||
- **Responder.** After sending msg2 the responder keeps a pending Machine, found by its
|
|
||||||
local index like the initiator's today; this is the multi-message responder support the
|
|
||||||
manager lacks now. A repeat msg1 maps to it through the answered-msg1 cache and gets msg2
|
|
||||||
resent with fresh symbols, exactly as in phase 1. Until msg3 verifies, data for that
|
|
||||||
index is dropped silently: it must not draw a RecvError, which would tear down the
|
|
||||||
initiator's new tunnel. On completing it sends an empty `Test`/`TestReply` under the
|
|
||||||
new keys, so the initiator hears back even when there is no traffic.
|
|
||||||
- **Initiator.** Writing msg3 yields the transport keys, so the hostinfo moves to the main
|
|
||||||
hostmap and data flows at once, readable only by the real responder. The handshake entry
|
|
||||||
stays behind in a confirming state: each retry tick resends msg3 with fresh symbols until
|
|
||||||
any packet from the responder decrypts on the new tunnel, and if that never happens
|
|
||||||
within the handshake timeout the tunnel is torn down. Losing msg3 costs the data sent
|
|
||||||
behind it, which the overlay's own transport retransmits.
|
|
||||||
- msg3's fragments use the responder's index as RemoteIndex and land on the responder's
|
|
||||||
pending entry, so they never enter the pre-authentication table.
|
|
||||||
|
|
||||||
The initiator never caches the responder's certificate, so every handshake has three
|
|
||||||
messages and carries both full certificates. With ML-DSA-87:
|
|
||||||
|
|
||||||
| Message | Size | Data fragments (k) |
|
|
||||||
|---|---|---|
|
|
||||||
| msg1 | ~8.2 KB | 8 |
|
|
||||||
| msg2 | ~9.8 KB | 9 |
|
|
||||||
| msg3 | ~1.6 KB | 2 |
|
|
||||||
|
|
||||||
flynn/noise cannot mix multiple KEM secrets into the chaining key, so phase 2 needs a
|
|
||||||
KEM-aware Noise symmetric state written in this repository. Both subtypes coexist.
|
|
||||||
|
|
||||||
Cryptographic review of the hybrid composition will be done by in-house cryptographers.
|
|
||||||
|
|
||||||
## Fragment transport
|
|
||||||
|
|
||||||
### Requirements
|
|
||||||
|
|
||||||
- No IP fragmentation: every datagram's UDP payload is at most 1232 bytes **after** relay
|
|
||||||
wrapping (16 B header + 16 B tag), the IPv6 minimum MTU budget also used by DNS Flag Day
|
|
||||||
2020 and Solana's Turbine.
|
|
||||||
- Every fragment of a handshake uses the same 5-tuple.
|
|
||||||
- Bounded pre-authentication state, bounded amplification, selective loss recovery,
|
|
||||||
tolerance of reordering and duplication, and a strictly validated, fuzzable parser.
|
|
||||||
|
|
||||||
### Wire format
|
|
||||||
|
|
||||||
Every packet of a fragmented handshake subtype is:
|
|
||||||
|
|
||||||
```
|
|
||||||
Nebula header (16) Version | Type=Handshake | Subtype | Reserved=0 | RemoteIndex | Counter
|
|
||||||
Fragment header (8) FragID u32 | MsgLen u16 | Index u8 | Flags u8
|
|
||||||
Cookie (16) only when Flags has 0x01
|
|
||||||
Symbol SymbolSize bytes
|
|
||||||
```
|
|
||||||
|
|
||||||
- `Counter` is the Noise message number (1, 2, 3). `RemoteIndex` is 0 for msg1, as today.
|
|
||||||
- `FragID` is the sender's local index (random, non-zero).
|
|
||||||
- `MsgLen` is the length of the whole message. Both ends derive the layout from it:
|
|
||||||
`K = ceil(MsgLen / 1160)`, `SymbolSize = ceil(MsgLen / K)`. Every symbol has the same
|
|
||||||
size. Room for a cookie is always reserved, so a packet is at most
|
|
||||||
16 + 8 + 16 + 1160 = 1200 bytes with or without one.
|
|
||||||
- `Index < K` is a data symbol (a slice of the message, the last one zero padded);
|
|
||||||
`Index >= K` is a repair symbol.
|
|
||||||
- `Flags` bit 0x01 means a cookie follows the fragment header. Other bits must be zero.
|
|
||||||
|
|
||||||
A cookie reply, sent by a responder under load, is a bare 32 byte packet:
|
|
||||||
|
|
||||||
```
|
|
||||||
Nebula header (16) Version | Type=Handshake | Subtype | Reserved=0 | RemoteIndex=FragID | Counter=0
|
|
||||||
Cookie (16)
|
|
||||||
```
|
|
||||||
|
|
||||||
It names the initiator's FragID, so the initiator finds its attempt the same way it finds
|
|
||||||
msg2.
|
|
||||||
|
|
||||||
### Forward error correction
|
|
||||||
|
|
||||||
Messages are protected with a systematic Reed-Solomon code over GF(2^8), implemented in
|
|
||||||
`handshake/fec`:
|
|
||||||
|
|
||||||
- The repair rows form a Cauchy matrix, `coefficient(row, col) = 1 / (row XOR col)` with
|
|
||||||
`row >= K > col`, so every square submatrix is invertible and **any K distinct symbols
|
|
||||||
reconstruct the message**. Naive identity-over-Vandermonde constructions are not MDS
|
|
||||||
(the PAR1 flaw and the 1997 Plank tutorial erratum).
|
|
||||||
- A repair row depends only on its index, so repair symbols are generated on demand and
|
|
||||||
their indexes never need to be agreed in advance. Up to 256 symbols exist per message.
|
|
||||||
- Known-answer vectors in `fec_test.go` pin the encoding and were cross-checked against an
|
|
||||||
independent implementation; changing them is a wire format change.
|
|
||||||
- Cost for a 9.8 KB message (k=9): about 13 µs for three repair symbols, about 19 µs to
|
|
||||||
decode with three data symbols missing.
|
|
||||||
|
|
||||||
**The sender chooses m**, the number of repair symbols per attempt. The receiver only needs
|
|
||||||
any K symbols, so this is policy and can change without a protocol change. The starting
|
|
||||||
rule is `m = max(2, ceil(K/3))`.
|
|
||||||
|
|
||||||
**Retries send fresh symbols.** Attempt 0 sends indexes `0 .. K+m-1`; each retry sends
|
|
||||||
the next `K+m` unused indexes. The receiver merges all distinct symbols across attempts,
|
|
||||||
so no received fragment is wasted. Indexes are a deterministic function of the message,
|
|
||||||
so retransmits stay idempotent: the responder caches msg2 itself and regenerates any
|
|
||||||
symbol.
|
|
||||||
|
|
||||||
**Repair symbols trail the data.** Data symbols go out back to back; repair symbols follow
|
|
||||||
after a short delay, so a queue tail-drop at the end of the data run does not also take the
|
|
||||||
repair. In simulation this lifts small messages substantially (k=2 at 10% loss, burst 8:
|
|
||||||
91.4% to 98.2% first-attempt success). Pacing every fragment was also evaluated; it gains
|
|
||||||
about 5 more points for k=7..9 on bursty paths, which is not worth the extra machinery,
|
|
||||||
and the retry with fresh symbols covers the remainder.
|
|
||||||
|
|
||||||
### Receiver rules
|
|
||||||
|
|
||||||
Implemented in `handshake/fragment` (`Sender`, `Assembly`, and the capped `Table`).
|
|
||||||
|
|
||||||
- Fragments are stored individually as they arrive and charged against a memory cap.
|
|
||||||
Nothing is allocated from a claimed size alone (FragmentSmack, game-engine "fragment
|
|
||||||
bombs").
|
|
||||||
- `MsgLen` must be identical for every fragment of a `FragID`; a mismatch drops the whole
|
|
||||||
entry. msg1 is capped at `MsgLen <= 16384` (K <= 15).
|
|
||||||
- The decoder keeps at most K distinct symbols, so an entry never exceeds about MsgLen bytes
|
|
||||||
however many repair symbols arrive.
|
|
||||||
- When K symbols are present the message is decoded and handed to the handshake `Machine`
|
|
||||||
as a synthetic `[header | message]`. The Machine never sees fragments.
|
|
||||||
- A completed entry is forgotten immediately. A late duplicate fragment starts a new entry
|
|
||||||
and, once enough arrive, reconstructs the same message again; the handshake layer's
|
|
||||||
duplicate detection recognises it.
|
|
||||||
- If Noise rejects a decoded message, the entry is discarded and the next attempt
|
|
||||||
supplies fresh symbols. (Possible refinement: keep a few spare symbols so an injected
|
|
||||||
bad symbol can be identified by re-encoding instead of waiting for a retry.)
|
|
||||||
- Pre-authentication msg1 entries live in a table keyed by (source address or relay index,
|
|
||||||
FragID) with a total memory cap, per-source quotas (/32 for IPv4, /64 for IPv6), a
|
|
||||||
sliding TTL of about 2 s refreshed by progress, and random eviction under pressure.
|
|
||||||
msg2 and msg3 reassembly attaches to the existing pending handshake found by RemoteIndex.
|
|
||||||
|
|
||||||
### Retransmission and amplification
|
|
||||||
|
|
||||||
- Only timers cause transmission. Reactive resends (the responder resending its cached
|
|
||||||
msg2 when a duplicate msg1 completes) are rate limited to one per handshake per retry
|
|
||||||
interval, to avoid TFTP's Sorcerer's Apprentice amplification.
|
|
||||||
- Duplicate msg1 detection compares the decoded message to the cached one **before**
|
|
||||||
running Noise or certificate verification.
|
|
||||||
- Before an address is validated, a responder sends at most 3x the bytes it received from
|
|
||||||
it (QUIC's rule). Normal handshakes sit near 1.1-1.2x.
|
|
||||||
- In phase 2 the initiator retransmits msg3 until any authenticated packet arrives from
|
|
||||||
the responder; the responder sends a small confirmation on completion and holds tunnel
|
|
||||||
traffic until msg3 verifies.
|
|
||||||
|
|
||||||
### Denial of service
|
|
||||||
|
|
||||||
The responder can no longer complete statelessly on msg1, since msg1 arrives in pieces.
|
|
||||||
Defenses are the capped table above plus a **cookie under load**, in the style of
|
|
||||||
WireGuard's mac2, QUIC Retry and the SCTP state cookie:
|
|
||||||
|
|
||||||
- Once the msg1 table is at least half full (by bytes or by entries), every msg1 fragment
|
|
||||||
must carry a valid cookie. One without is answered with a cookie reply and leaves no
|
|
||||||
state. Fragments that already belong to an entry need one too, so an attacker cannot
|
|
||||||
hold old entries open.
|
|
||||||
- A cookie is `HMAC-SHA256(secret, source address and port, relay channel, FragID)`
|
|
||||||
truncated to 16 bytes. The secret rotates every 2 minutes and the previous one is still
|
|
||||||
accepted, so a cookie is good for 2 to 4 minutes.
|
|
||||||
- Replies are never larger than the packet that prompted them (no amplification) and are
|
|
||||||
rate limited as a whole (a burst of 256, then 1000 per second), so spoofed floods cannot
|
|
||||||
turn the responder into a reflector.
|
|
||||||
- The initiator attaches the cookie to its PQ attempt, so every later packet carries it,
|
|
||||||
and immediately resends fresh symbols to the address the reply came from, at most once
|
|
||||||
per retry interval. Under load a PQ handshake costs one extra round trip, which in
|
|
||||||
practice still beats the classical attempt on the next retry tick.
|
|
||||||
- An attacker on the path can forge a cookie reply; the bogus cookie is simply rejected
|
|
||||||
and answered with a real one.
|
|
||||||
|
|
||||||
A CA-keyed pre-filter MAC was considered and rejected: networks commonly trust many CAs.
|
|
||||||
|
|
||||||
#### Injected symbols
|
|
||||||
|
|
||||||
The decoder keeps the first K distinct symbols it sees, so one forged symbol in those K
|
|
||||||
spoils that attempt's decode; Noise rejects the result and the next attempt brings fresh
|
|
||||||
symbols. Forging one needs the attempt's FragID or index, which are random 32 bit values,
|
|
||||||
and for msg1 the initiator's exact address and port too, so in practice only an attacker
|
|
||||||
who sees the traffic can do it. An attacker who can also drop packets gains nothing new.
|
|
||||||
One who can only inject, and races a forged symbol into every attempt, can stop a PQ
|
|
||||||
handshake where it could not stop a classical one, since classical msg2s are tried one
|
|
||||||
packet at a time. Keeping spare symbols to find a consistent subset only raises the number
|
|
||||||
of forgeries needed per attempt, and authenticating symbols is impossible for msg1, which
|
|
||||||
travels before any key exists. So the decoder deliberately does neither. A non-sticky
|
|
||||||
initiator still gets a classical tunnel from its next attempt; a sticky one, by design,
|
|
||||||
does not downgrade.
|
|
||||||
|
|
||||||
## Rollout
|
|
||||||
|
|
||||||
- Separate settings for initiating and accepting PQ handshakes, both off by default:
|
|
||||||
`handshakes.pq.initiate`, `handshakes.pq.accept`. `handshakes.pq.repair_delay` (default
|
|
||||||
10ms) sets how long repair fragments trail the data fragments.
|
|
||||||
- `handshakes.pq.require` makes every handshake PQ: it implies `initiate` and `accept`,
|
|
||||||
never offers a classical attempt, and drops classical msg1s.
|
|
||||||
- Old nodes silently drop unknown subtypes, so discovery is speculative: an initiator with
|
|
||||||
`initiate` enabled alternates PQ and classical attempts on successive timer retries,
|
|
||||||
keeping both pending, and the first to complete wins. A path nothing has been sent over
|
|
||||||
yet gets the PQ attempt first: an early resend triggered by a lighthouse reply is PQ, and
|
|
||||||
a relay that comes up pushes the PQ attempt through at once, counting as the PQ turn.
|
|
||||||
Without that, relays set up during the first attempt handed every relayed handshake to
|
|
||||||
the classical retry (seen on real hosts: 11 of 11). Once a msg2 fragment or cookie reply
|
|
||||||
arrives for the PQ attempt the peer evidently speaks PQ, and classical stops getting
|
|
||||||
turns.
|
|
||||||
- All `handshakes.pq` settings reload without a restart. Handshakes in flight carry on;
|
|
||||||
the new settings apply to the next attempt and the next packet.
|
|
||||||
- `handshakes.pq.sticky` (default off): once a peer has completed a PQ handshake, never fall
|
|
||||||
back to classical for it again during this process lifetime. This resists active
|
|
||||||
downgrade after first contact.
|
|
||||||
- No lighthouse capability advertisement.
|
|
||||||
|
|
||||||
## Simulation results
|
|
||||||
|
|
||||||
Gilbert-Elliott channel (bad state drops everything), losses expressed as average rate and
|
|
||||||
mean burst length in packets. First-attempt success for the whole handshake with
|
|
||||||
`m = max(2, ceil(K/3))` and repair delayed 16 packet slots, compared with no FEC:
|
|
||||||
|
|
||||||
| Handshake | Loss | Burst 1 | Burst 2 | Burst 4 | Burst 8 |
|
|
||||||
|---|---|---|---|---|---|
|
|
||||||
| phase 1 (2, 2) no FEC | 5% | 81.4% | 85.6% | 87.9% | 89.0% |
|
|
||||||
| phase 1 (2, 2) FEC | 5% | 99.9% | 99.4% | 99.3% | 98.6% |
|
|
||||||
| phase 1 (2, 2) FEC | 10% | 99.3% | 97.5% | 97.4% | 96.3% |
|
|
||||||
| phase 2 (8, 9, 2) no FEC | 5% | 37.8% | 56.0% | 69.3% | 77.1% |
|
|
||||||
| phase 2 (8, 9, 2) FEC | 5% | 99.6% | 93.7% | 89.9% | 88.4% |
|
|
||||||
| phase 2 (8, 9, 2) FEC | 10% | 95.3% | 83.5% | 77.9% | 76.7% |
|
|
||||||
|
|
||||||
With fresh repair symbols, phase 2 completes within two attempts at least 99.1% of the time
|
|
||||||
in every scenario above, and within three at least 99.98%.
|
|
||||||
|
|
||||||
The simulators and their outputs are in [pq-handshake-sim](pq-handshake-sim/README.md),
|
|
||||||
including a comparison with classical handshakes and a model of time to a working tunnel
|
|
||||||
under Nebula's retry schedule.
|
|
||||||
|
|
||||||
## Prior art
|
|
||||||
|
|
||||||
- **WireGuard / Rosenpass**: fit every message in one packet; cookies and biscuits for
|
|
||||||
statelessness. Not possible at our sizes.
|
|
||||||
- **IKEv2**: RFC 7383 fragments only after keys exist, with each fragment authenticated;
|
|
||||||
RFC 9242/9370 move PQ key exchange into intermediate exchanges for that reason.
|
|
||||||
- **QUIC / DTLS 1.3**: offset-based reassembly with ACKs; QUIC's 3x amplification limit and
|
|
||||||
1200-byte floor.
|
|
||||||
- **Solana Turbine**: Reed-Solomon over 1232-byte UDP packets through untrusted relays;
|
|
||||||
moved to Merkle-authenticated shreds after unauthenticated repair symbols enabled
|
|
||||||
poisoning.
|
|
||||||
- **kcp-go, UDPspeeder, CM256**: RS FEC over UDP; parity must scale up for small groups.
|
|
||||||
- **gQUIC FEC (removed)**: FEC does not pay for bulk transfer under bursty loss; it does
|
|
||||||
for short, latency-critical transfers such as handshakes.
|
|
||||||
- **TFTP, NFS duplicate request cache, memcached UDP, IP reassembly bugs**: retransmit
|
|
||||||
storms, ID-wrap misassembly, reflection amplification, and allocation from claimed sizes.
|
|
||||||
|
|
||||||
## Implementation (phase 1)
|
|
||||||
|
|
||||||
- `handshake`: the `ix_psk2_mlkem1024` subtype (`patterns.go`, `kem.go`), the `KEMKey`
|
|
||||||
payload field, and the psk2 plumbing in `Machine`.
|
|
||||||
- `handshake/fec`, `handshake/fragment`: the code and the fragment transport.
|
|
||||||
- `handshake_manager_pq.go` and the manager:
|
|
||||||
- **Initiator.** Attempts alternate PQ and classical, starting with PQ (sticky peers get
|
|
||||||
only PQ). The PQ attempt has its own local index registered alongside the classical
|
|
||||||
one; whichever response completes first wins, and the other index is released
|
|
||||||
(`settleIndex`). A timed out or deleted pending handshake releases both.
|
|
||||||
- **Responder.** msg1 fragments go into the capped pre-authentication table. A decoded
|
|
||||||
msg1 is looked up by hash among recently answered ones before any Noise, KEM or
|
|
||||||
certificate work: the trailing repair fragments of an attempt rebuild a msg1 its data
|
|
||||||
fragments already completed, and a retrying initiator offers fresh symbols for the
|
|
||||||
same msg1. A repeat goes straight to the cached-response resend, which offers fresh
|
|
||||||
msg2 symbols, is rate limited to one per retry interval and is held to the 3x
|
|
||||||
amplification budget.
|
|
||||||
- **Relays** carry fragments unchanged; repair fragments trail via a timer.
|
|
||||||
- The pre-authentication table is capped at 4 MiB, 1024 entries, 4 per source (IPv4 /32,
|
|
||||||
IPv6 /64, or relay channel), 16 KiB messages and a 3 s idle timeout. Cookies are
|
|
||||||
demanded from half full.
|
|
||||||
- Tests: Noise-level KEM tests, codec and fragment tests and fuzzers, manager unit tests
|
|
||||||
for the response budget and rate limit, and e2e tests for a clean handshake, loss of
|
|
||||||
data fragments in both directions, fallback to a peer that does not accept PQ, a lost
|
|
||||||
msg2 recovered by fresh symbols, sticky mode under an attacker dropping PQ packets,
|
|
||||||
relays, index cleanup on completion, fallback and timeout, and a responder flooded from
|
|
||||||
spoofed sources demanding and accepting a cookie. Unit tests cover cookie binding and
|
|
||||||
rotation, the never-amplify rule, the initiator's rate limited resend, and reload. ML-KEM and HKDF also
|
|
||||||
pass under `GOEXPERIMENT=boringcrypto` and `GODEBUG=fips140=on`.
|
|
||||||
|
|
||||||
## Open items
|
|
||||||
|
|
||||||
None for phase 1. Phase 2 needs certificate v3, the KEM-aware Noise symmetric state, and
|
|
||||||
the msg3 design above.
|
|
||||||
@@ -1513,7 +1513,7 @@ func TestLighthouseUpdateOnReload(t *testing.T) {
|
|||||||
// Reload the config. The lighthouse.hosts change triggers TriggerUpdate,
|
// Reload the config. The lighthouse.hosts change triggers TriggerUpdate,
|
||||||
// which wakes the update worker. It calls SendUpdate, initiating a
|
// which wakes the update worker. It calls SendUpdate, initiating a
|
||||||
// handshake to the new lighthouse and caching the HostUpdateNotification.
|
// handshake to the new lighthouse and caching the HostUpdateNotification.
|
||||||
require.NoError(t, myConfig.ReloadConfigString(string(newCfg)))
|
require.NoError(t, myConfig.ReloadConfigString(string(newCfg)).Err)
|
||||||
|
|
||||||
// Route until the lighthouse receives the HostUpdateNotification.
|
// Route until the lighthouse receives the HostUpdateNotification.
|
||||||
// This covers: handshake stage 1, stage 2, then the cached update.
|
// This covers: handshake stage 1, stage 2, then the cached update.
|
||||||
|
|||||||
@@ -1,476 +0,0 @@
|
|||||||
//go:build e2e_testing
|
|
||||||
|
|
||||||
package e2e
|
|
||||||
|
|
||||||
import (
|
|
||||||
"net/netip"
|
|
||||||
"sync"
|
|
||||||
"testing"
|
|
||||||
"time"
|
|
||||||
|
|
||||||
"github.com/slackhq/nebula"
|
|
||||||
"github.com/slackhq/nebula/cert"
|
|
||||||
"github.com/slackhq/nebula/cert_test"
|
|
||||||
"github.com/slackhq/nebula/e2e/router"
|
|
||||||
"github.com/slackhq/nebula/handshake/fragment"
|
|
||||||
"github.com/slackhq/nebula/header"
|
|
||||||
"github.com/slackhq/nebula/udp"
|
|
||||||
"github.com/stretchr/testify/assert"
|
|
||||||
"github.com/stretchr/testify/require"
|
|
||||||
)
|
|
||||||
|
|
||||||
func pqRequire() m {
|
|
||||||
return m{"handshakes": m{"pq": m{"require": true, "repair_delay": "0s"}}}
|
|
||||||
}
|
|
||||||
|
|
||||||
func pqConfig(initiate, accept, sticky bool) m {
|
|
||||||
return m{"handshakes": m{"pq": m{
|
|
||||||
"initiate": initiate,
|
|
||||||
"accept": accept,
|
|
||||||
"sticky": sticky,
|
|
||||||
"repair_delay": "0s",
|
|
||||||
}}}
|
|
||||||
}
|
|
||||||
|
|
||||||
// handshakeOf returns the handshake header p carries, looking inside relay
|
|
||||||
// wrapping, plus the fragment header when the handshake is fragmented.
|
|
||||||
func handshakeOf(p *udp.Packet) (*header.H, *fragment.Header) {
|
|
||||||
b := p.Data
|
|
||||||
h := &header.H{}
|
|
||||||
if h.Parse(b) != nil {
|
|
||||||
return nil, nil
|
|
||||||
}
|
|
||||||
if h.Type == header.Message && h.Subtype == header.MessageRelay {
|
|
||||||
// Relays authenticate but do not encrypt the inner packet.
|
|
||||||
b = b[header.Len:]
|
|
||||||
if h.Parse(b) != nil {
|
|
||||||
return nil, nil
|
|
||||||
}
|
|
||||||
}
|
|
||||||
if h.Type != header.Handshake {
|
|
||||||
return nil, nil
|
|
||||||
}
|
|
||||||
if !header.IsFragmented(h.Subtype) {
|
|
||||||
return h, nil
|
|
||||||
}
|
|
||||||
// A relayed packet still has the relay's AEAD tag on the end.
|
|
||||||
for _, tag := range []int{0, 16} {
|
|
||||||
if len(b) < header.Len+tag {
|
|
||||||
break
|
|
||||||
}
|
|
||||||
if fh, _, err := fragment.Parse(b[header.Len : len(b)-tag]); err == nil {
|
|
||||||
return h, &fh
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return h, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
// handshakeTally counts handshake packets by style as the router moves them.
|
|
||||||
type handshakeTally struct {
|
|
||||||
sync.Mutex
|
|
||||||
pq, classical int
|
|
||||||
maxPQLen int
|
|
||||||
}
|
|
||||||
|
|
||||||
func (ht *handshakeTally) observe(p *udp.Packet) {
|
|
||||||
h, _ := handshakeOf(p)
|
|
||||||
if h == nil {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
ht.Lock()
|
|
||||||
defer ht.Unlock()
|
|
||||||
if h.Subtype == header.HandshakeIXPSK2MLKEM1024 {
|
|
||||||
ht.pq++
|
|
||||||
ht.maxPQLen = max(ht.maxPQLen, len(p.Data))
|
|
||||||
} else {
|
|
||||||
ht.classical++
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// isTunnelData reports whether p is ordinary tunnel traffic headed for to,
|
|
||||||
// directly or as the last hop of a relay.
|
|
||||||
func isTunnelData(p *udp.Packet, receiver, to *nebula.Control) bool {
|
|
||||||
h := &header.H{}
|
|
||||||
if receiver != to || h.Parse(p.Data) != nil || h.Type != header.Message {
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
if h.Subtype == header.MessageRelay {
|
|
||||||
if h.Parse(p.Data[header.Len:]) != nil {
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return h.Type == header.Message && h.Subtype == header.MessageNone
|
|
||||||
}
|
|
||||||
|
|
||||||
func newPQPair(t *testing.T, mine, theirs m) (myControl, theirControl *nebula.Control, myVpn, theirVpn []netip.Prefix, myUdp, theirUdp netip.AddrPort, r *router.R) {
|
|
||||||
t.Helper()
|
|
||||||
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
|
|
||||||
myControl, myVpn, myUdp, _ = newSimpleServer(cert.Version2, ca, caKey, "me", "10.128.0.1/24", mine)
|
|
||||||
theirControl, theirVpn, theirUdp, _ = newSimpleServer(cert.Version2, ca, caKey, "them", "10.128.0.2/24", theirs)
|
|
||||||
myControl.InjectLightHouseAddr(theirVpn[0].Addr(), theirUdp)
|
|
||||||
r = router.NewR(t, myControl, theirControl)
|
|
||||||
myControl.Start()
|
|
||||||
theirControl.Start()
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestPQHandshake(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
// They only accept, which is all a PQ initiator needs.
|
|
||||||
myControl, theirControl, myVpn, theirVpn, myUdp, theirUdp, r := newPQPair(t, pqConfig(true, true, false), pqConfig(false, true, false))
|
|
||||||
defer r.RenderFlow()
|
|
||||||
|
|
||||||
var tally handshakeTally
|
|
||||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
|
||||||
require.True(t, r.RouteForAllExitFuncOrTimeout(5*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
|
||||||
tally.observe(p)
|
|
||||||
if isTunnelData(p, receiver, theirControl) {
|
|
||||||
return router.RouteAndExit
|
|
||||||
}
|
|
||||||
return router.KeepRouting
|
|
||||||
}), "tunnel never came up")
|
|
||||||
|
|
||||||
assertUdpPacket(t, []byte("Hi from me"), theirControl.GetFromTun(true), myVpn[0].Addr(), theirVpn[0].Addr(), 80, 80)
|
|
||||||
assert.Zero(t, tally.classical, "no classical handshake should be needed")
|
|
||||||
assert.GreaterOrEqual(t, tally.pq, 4, "both messages travel as several fragments")
|
|
||||||
assert.LessOrEqual(t, tally.maxPQLen, fragment.MaxPacketLen)
|
|
||||||
|
|
||||||
assertHostInfoPair(t, myUdp, theirUdp, myVpn, theirVpn, myControl, theirControl)
|
|
||||||
assertTunnel(t, myVpn[0].Addr(), theirVpn[0].Addr(), myControl, theirControl, r)
|
|
||||||
assert.Empty(t, myControl.ListHostmapIndexes(true), "no pending index may outlive the handshake")
|
|
||||||
assert.Empty(t, theirControl.ListHostmapIndexes(true))
|
|
||||||
|
|
||||||
myControl.Stop()
|
|
||||||
theirControl.Stop()
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestPQHandshakeLoss drops data fragments of both messages; the repair
|
|
||||||
// fragments must carry the handshake without a retry.
|
|
||||||
func TestPQHandshakeLoss(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
myControl, theirControl, myVpn, theirVpn, _, _, r := newPQPair(t, pqConfig(true, true, false), pqConfig(false, true, false))
|
|
||||||
defer r.RenderFlow()
|
|
||||||
|
|
||||||
var tally handshakeTally
|
|
||||||
dropped := 0
|
|
||||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
|
||||||
require.True(t, r.RouteForAllExitFuncOrTimeout(5*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
|
||||||
if h, fh := handshakeOf(p); fh != nil {
|
|
||||||
// Every data fragment of msg1, and the first of msg2.
|
|
||||||
if (h.MessageCounter == 1 && int(fh.Index) < 2) || (h.MessageCounter == 2 && fh.Index == 0) {
|
|
||||||
dropped++
|
|
||||||
return router.Drop
|
|
||||||
}
|
|
||||||
}
|
|
||||||
tally.observe(p)
|
|
||||||
if isTunnelData(p, receiver, theirControl) {
|
|
||||||
return router.RouteAndExit
|
|
||||||
}
|
|
||||||
return router.KeepRouting
|
|
||||||
}), "tunnel never came up")
|
|
||||||
|
|
||||||
assertUdpPacket(t, []byte("Hi from me"), theirControl.GetFromTun(true), myVpn[0].Addr(), theirVpn[0].Addr(), 80, 80)
|
|
||||||
assert.Equal(t, 3, dropped)
|
|
||||||
assert.Zero(t, tally.classical, "the first attempt should succeed from repair fragments")
|
|
||||||
assertTunnel(t, myVpn[0].Addr(), theirVpn[0].Addr(), myControl, theirControl, r)
|
|
||||||
|
|
||||||
myControl.Stop()
|
|
||||||
theirControl.Stop()
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestPQFallback has a peer that does not accept PQ handshakes. The initiator's
|
|
||||||
// next attempt is classical and the tunnel comes up anyway.
|
|
||||||
func TestPQFallback(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
myControl, theirControl, myVpn, theirVpn, myUdp, theirUdp, r := newPQPair(t, pqConfig(true, true, false), nil)
|
|
||||||
defer r.RenderFlow()
|
|
||||||
|
|
||||||
var tally handshakeTally
|
|
||||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
|
||||||
require.True(t, r.RouteForAllExitFuncOrTimeout(5*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
|
||||||
tally.observe(p)
|
|
||||||
if isTunnelData(p, receiver, theirControl) {
|
|
||||||
return router.RouteAndExit
|
|
||||||
}
|
|
||||||
return router.KeepRouting
|
|
||||||
}), "tunnel never came up")
|
|
||||||
|
|
||||||
assertUdpPacket(t, []byte("Hi from me"), theirControl.GetFromTun(true), myVpn[0].Addr(), theirVpn[0].Addr(), 80, 80)
|
|
||||||
assert.Positive(t, tally.pq, "a PQ attempt comes first")
|
|
||||||
assert.Positive(t, tally.classical, "then a classical one")
|
|
||||||
|
|
||||||
assertHostInfoPair(t, myUdp, theirUdp, myVpn, theirVpn, myControl, theirControl)
|
|
||||||
assertTunnel(t, myVpn[0].Addr(), theirVpn[0].Addr(), myControl, theirControl, r)
|
|
||||||
assert.Empty(t, myControl.ListHostmapIndexes(true), "the losing PQ attempt's index must be released")
|
|
||||||
|
|
||||||
myControl.Stop()
|
|
||||||
theirControl.Stop()
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestPQResendFreshSymbols loses the responder's whole first msg2. The
|
|
||||||
// initiator's next PQ attempt offers fresh msg1 symbols, the responder
|
|
||||||
// recognises the repeat and resends msg2 with symbols it has not sent before.
|
|
||||||
func TestPQResendFreshSymbols(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
myControl, theirControl, myVpn, theirVpn, _, _, r := newPQPair(t, pqConfig(true, true, false), pqConfig(false, true, false))
|
|
||||||
defer r.RenderFlow()
|
|
||||||
|
|
||||||
var firstMsg2, freshMsg2, freshMsg1 int
|
|
||||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
|
||||||
require.True(t, r.RouteForAllExitFuncOrTimeout(10*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
|
||||||
h, fh := handshakeOf(p)
|
|
||||||
switch {
|
|
||||||
case h != nil && fh == nil:
|
|
||||||
// Keep the classical fallback out of the way.
|
|
||||||
return router.Drop
|
|
||||||
case fh != nil && h.MessageCounter == 2 && fh.Index < 4:
|
|
||||||
firstMsg2++
|
|
||||||
return router.Drop
|
|
||||||
case fh != nil && h.MessageCounter == 2:
|
|
||||||
freshMsg2++
|
|
||||||
case fh != nil && h.MessageCounter == 1 && fh.Index >= 4:
|
|
||||||
freshMsg1++
|
|
||||||
}
|
|
||||||
if isTunnelData(p, receiver, theirControl) {
|
|
||||||
return router.RouteAndExit
|
|
||||||
}
|
|
||||||
return router.KeepRouting
|
|
||||||
}), "tunnel never came up")
|
|
||||||
|
|
||||||
assertUdpPacket(t, []byte("Hi from me"), theirControl.GetFromTun(true), myVpn[0].Addr(), theirVpn[0].Addr(), 80, 80)
|
|
||||||
assert.Equal(t, 4, firstMsg2, "the first msg2 is 2 data and 2 repair fragments")
|
|
||||||
assert.Positive(t, freshMsg1, "the retry offers fresh msg1 symbols")
|
|
||||||
assert.Positive(t, freshMsg2, "the resend offers fresh msg2 symbols")
|
|
||||||
assertTunnel(t, myVpn[0].Addr(), theirVpn[0].Addr(), myControl, theirControl, r)
|
|
||||||
|
|
||||||
myControl.Stop()
|
|
||||||
theirControl.Stop()
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestPQSticky checks a sticky initiator never offers a classical handshake to a
|
|
||||||
// peer it has already completed a PQ handshake with.
|
|
||||||
func TestPQSticky(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
myControl, theirControl, myVpn, theirVpn, _, _, r := newPQPair(t, pqConfig(true, true, true), pqConfig(false, true, false))
|
|
||||||
defer r.RenderFlow()
|
|
||||||
|
|
||||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
|
||||||
require.True(t, r.RouteForAllExitFuncOrTimeout(5*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
|
||||||
if isTunnelData(p, receiver, theirControl) {
|
|
||||||
return router.RouteAndExit
|
|
||||||
}
|
|
||||||
return router.KeepRouting
|
|
||||||
}), "tunnel never came up")
|
|
||||||
theirControl.GetFromTun(true)
|
|
||||||
|
|
||||||
t.Log("Rehandshake while an attacker drops every PQ packet")
|
|
||||||
var tally handshakeTally
|
|
||||||
myControl.ReHandshake(theirVpn[0].Addr())
|
|
||||||
r.RouteForAllExitFuncOrTimeout(time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
|
||||||
tally.observe(p)
|
|
||||||
if h, _ := handshakeOf(p); h != nil && h.Subtype == header.HandshakeIXPSK2MLKEM1024 {
|
|
||||||
return router.Drop
|
|
||||||
}
|
|
||||||
return router.KeepRouting
|
|
||||||
})
|
|
||||||
assert.Positive(t, tally.pq, "PQ attempts keep being made")
|
|
||||||
assert.Zero(t, tally.classical, "sticky must never fall back")
|
|
||||||
|
|
||||||
myControl.Stop()
|
|
||||||
theirControl.Stop()
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestPQRelays(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version1, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
|
|
||||||
useRelays := pqConfig(true, true, false)
|
|
||||||
useRelays["relay"] = m{"use_relays": true}
|
|
||||||
amRelay := pqConfig(true, true, false)
|
|
||||||
amRelay["relay"] = m{"am_relay": true}
|
|
||||||
myControl, myVpnIpNet, _, _ := newSimpleServer(cert.Version1, ca, caKey, "me ", "10.128.0.1/24", useRelays)
|
|
||||||
relayControl, relayVpnIpNet, relayUdpAddr, _ := newSimpleServer(cert.Version1, ca, caKey, "relay ", "10.128.0.128/24", amRelay)
|
|
||||||
theirControl, theirVpnIpNet, theirUdpAddr, _ := newSimpleServer(cert.Version1, ca, caKey, "them ", "10.128.0.2/24", useRelays)
|
|
||||||
|
|
||||||
myControl.InjectLightHouseAddr(relayVpnIpNet[0].Addr(), relayUdpAddr)
|
|
||||||
myControl.InjectRelays(theirVpnIpNet[0].Addr(), []netip.Addr{relayVpnIpNet[0].Addr()})
|
|
||||||
relayControl.InjectLightHouseAddr(theirVpnIpNet[0].Addr(), theirUdpAddr)
|
|
||||||
|
|
||||||
r := router.NewR(t, myControl, relayControl, theirControl)
|
|
||||||
defer r.RenderFlow()
|
|
||||||
|
|
||||||
myControl.Start()
|
|
||||||
relayControl.Start()
|
|
||||||
theirControl.Start()
|
|
||||||
|
|
||||||
var tally handshakeTally
|
|
||||||
var relayedPQ, relayedClassical int
|
|
||||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpnIpNet[0].Addr(), 80, myVpnIpNet[0].Addr(), 80, []byte("Hi from me")))
|
|
||||||
require.True(t, r.RouteForAllExitFuncOrTimeout(10*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
|
||||||
tally.observe(p)
|
|
||||||
outer := &header.H{}
|
|
||||||
if outer.Parse(p.Data) == nil && outer.Type == header.Message && outer.Subtype == header.MessageRelay {
|
|
||||||
if h, fh := handshakeOf(p); h != nil && fh != nil {
|
|
||||||
relayedPQ++
|
|
||||||
assert.LessOrEqual(t, len(p.Data), fragment.MaxPacketLen+32, "a relayed fragment fits the IPv6 minimum MTU")
|
|
||||||
} else if h != nil {
|
|
||||||
relayedClassical++
|
|
||||||
}
|
|
||||||
}
|
|
||||||
if isTunnelData(p, receiver, theirControl) {
|
|
||||||
return router.RouteAndExit
|
|
||||||
}
|
|
||||||
return router.KeepRouting
|
|
||||||
}), "tunnel never came up")
|
|
||||||
|
|
||||||
assertUdpPacket(t, []byte("Hi from me"), theirControl.GetFromTun(true), myVpnIpNet[0].Addr(), theirVpnIpNet[0].Addr(), 80, 80)
|
|
||||||
assert.Positive(t, relayedPQ, "the end to end handshake is PQ through the relay")
|
|
||||||
assert.Zero(t, relayedClassical, "the relay coming up carries the PQ attempt, not the classical retry")
|
|
||||||
r.RenderHostmaps("Final hostmaps", myControl, relayControl, theirControl)
|
|
||||||
|
|
||||||
myControl.Stop()
|
|
||||||
relayControl.Stop()
|
|
||||||
theirControl.Stop()
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestPQTimeoutReleasesIndexes lets a handshake with both a PQ and a classical
|
|
||||||
// attempt pending time out, and checks neither index is left behind.
|
|
||||||
func TestPQTimeoutReleasesIndexes(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
mine := pqConfig(true, true, false)
|
|
||||||
mine["handshakes"].(m)["retries"] = 2
|
|
||||||
myControl, theirControl, myVpn, theirVpn, _, _, r := newPQPair(t, mine, pqConfig(false, true, false))
|
|
||||||
defer r.RenderFlow()
|
|
||||||
|
|
||||||
var tally handshakeTally
|
|
||||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
|
||||||
r.RouteForAllExitFuncOrTimeout(1500*time.Millisecond, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
|
||||||
tally.observe(p)
|
|
||||||
return router.Drop
|
|
||||||
})
|
|
||||||
|
|
||||||
assert.Positive(t, tally.pq)
|
|
||||||
assert.Positive(t, tally.classical)
|
|
||||||
assert.Nil(t, myControl.GetHostInfoByVpnAddr(theirVpn[0].Addr(), true), "the handshake should have timed out")
|
|
||||||
assert.Empty(t, myControl.ListHostmapIndexes(true))
|
|
||||||
|
|
||||||
myControl.Stop()
|
|
||||||
theirControl.Stop()
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestPQCookieUnderLoad floods the responder with msg1 fragments from spoofed
|
|
||||||
// sources until it demands cookies, then checks a real initiator picks up the
|
|
||||||
// cookie and still completes a PQ handshake.
|
|
||||||
func TestPQCookieUnderLoad(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
myControl, theirControl, myVpn, theirVpn, _, theirUdp, r := newPQPair(t, pqConfig(true, true, false), pqConfig(false, true, false))
|
|
||||||
defer r.RenderFlow()
|
|
||||||
|
|
||||||
// Half of the 1024 entry table is the cookie threshold. Stopping exactly there
|
|
||||||
// keeps them from answering the spoofed sources, which the router cannot reach.
|
|
||||||
t.Log("Flood them with the first fragment of msg1s nobody will finish")
|
|
||||||
for i := range 512 {
|
|
||||||
from := netip.AddrPortFrom(netip.AddrFrom4([4]byte{198, 18, byte(i >> 8), byte(i)}), 4242)
|
|
||||||
s, err := fragment.NewSender(make([]byte, 2000), header.HandshakeIXPSK2MLKEM1024, 0, 1, uint32(i+1))
|
|
||||||
require.NoError(t, err)
|
|
||||||
pkts, _, err := s.Attempt(0)
|
|
||||||
require.NoError(t, err)
|
|
||||||
theirControl.InjectUDPPacket(&udp.Packet{From: from, To: theirUdp, Data: pkts[0]})
|
|
||||||
}
|
|
||||||
|
|
||||||
var tally handshakeTally
|
|
||||||
var cookieReplies, msg2, withCookie int
|
|
||||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
|
||||||
require.True(t, r.RouteForAllExitFuncOrTimeout(5*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
|
||||||
tally.observe(p)
|
|
||||||
if h, fh := handshakeOf(p); h != nil && h.Subtype == header.HandshakeIXPSK2MLKEM1024 {
|
|
||||||
switch {
|
|
||||||
case h.MessageCounter == 0:
|
|
||||||
cookieReplies++
|
|
||||||
case h.MessageCounter == 2:
|
|
||||||
msg2++
|
|
||||||
case fh != nil && fh.HasCookie():
|
|
||||||
withCookie++
|
|
||||||
}
|
|
||||||
}
|
|
||||||
if isTunnelData(p, receiver, theirControl) {
|
|
||||||
return router.RouteAndExit
|
|
||||||
}
|
|
||||||
return router.KeepRouting
|
|
||||||
}), "tunnel never came up")
|
|
||||||
|
|
||||||
assertUdpPacket(t, []byte("Hi from me"), theirControl.GetFromTun(true), myVpn[0].Addr(), theirVpn[0].Addr(), 80, 80)
|
|
||||||
assert.Positive(t, cookieReplies, "a loaded responder asks for a cookie")
|
|
||||||
assert.Positive(t, withCookie, "the initiator resends with it")
|
|
||||||
assert.Positive(t, msg2, "and the handshake completes post-quantum")
|
|
||||||
assert.Zero(t, tally.classical, "the cookie round trip beats the classical fallback")
|
|
||||||
assertTunnel(t, myVpn[0].Addr(), theirVpn[0].Addr(), myControl, theirControl, r)
|
|
||||||
|
|
||||||
myControl.Stop()
|
|
||||||
theirControl.Stop()
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestPQRequire checks require mode never handshakes classically, in either
|
|
||||||
// direction.
|
|
||||||
func TestPQRequire(t *testing.T) {
|
|
||||||
t.Parallel()
|
|
||||||
|
|
||||||
t.Run("initiator", func(t *testing.T) {
|
|
||||||
// They neither speak PQ nor require it; we never fall back.
|
|
||||||
myControl, theirControl, myVpn, theirVpn, _, _, r := newPQPair(t, pqRequire(), nil)
|
|
||||||
defer r.RenderFlow()
|
|
||||||
|
|
||||||
var tally handshakeTally
|
|
||||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
|
||||||
r.RouteForAllExitFuncOrTimeout(time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
|
||||||
tally.observe(p)
|
|
||||||
return router.KeepRouting
|
|
||||||
})
|
|
||||||
assert.Positive(t, tally.pq)
|
|
||||||
assert.Zero(t, tally.classical)
|
|
||||||
assert.Nil(t, theirControl.GetHostInfoByVpnAddr(myVpn[0].Addr(), false), "no tunnel without PQ")
|
|
||||||
|
|
||||||
myControl.Stop()
|
|
||||||
theirControl.Stop()
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("responder", func(t *testing.T) {
|
|
||||||
// We only speak classical; they refuse it.
|
|
||||||
myControl, theirControl, myVpn, theirVpn, _, _, r := newPQPair(t, nil, pqRequire())
|
|
||||||
defer r.RenderFlow()
|
|
||||||
|
|
||||||
var answers int
|
|
||||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
|
||||||
r.RouteForAllExitFuncOrTimeout(time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
|
||||||
if h, _ := handshakeOf(p); h != nil && h.MessageCounter == 2 {
|
|
||||||
answers++
|
|
||||||
}
|
|
||||||
return router.KeepRouting
|
|
||||||
})
|
|
||||||
assert.Zero(t, answers, "a classical msg1 gets no answer")
|
|
||||||
assert.Nil(t, theirControl.GetHostInfoByVpnAddr(myVpn[0].Addr(), false))
|
|
||||||
|
|
||||||
myControl.Stop()
|
|
||||||
theirControl.Stop()
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("both", func(t *testing.T) {
|
|
||||||
myControl, theirControl, myVpn, theirVpn, _, _, r := newPQPair(t, pqRequire(), pqRequire())
|
|
||||||
defer r.RenderFlow()
|
|
||||||
|
|
||||||
var tally handshakeTally
|
|
||||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
|
||||||
require.True(t, r.RouteForAllExitFuncOrTimeout(5*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
|
||||||
tally.observe(p)
|
|
||||||
if isTunnelData(p, receiver, theirControl) {
|
|
||||||
return router.RouteAndExit
|
|
||||||
}
|
|
||||||
return router.KeepRouting
|
|
||||||
}), "tunnel never came up")
|
|
||||||
assertUdpPacket(t, []byte("Hi from me"), theirControl.GetFromTun(true), myVpn[0].Addr(), theirVpn[0].Addr(), 80, 80)
|
|
||||||
assert.Zero(t, tally.classical)
|
|
||||||
assertTunnel(t, myVpn[0].Addr(), theirVpn[0].Addr(), myControl, theirControl, r)
|
|
||||||
|
|
||||||
myControl.Stop()
|
|
||||||
theirControl.Stop()
|
|
||||||
})
|
|
||||||
}
|
|
||||||
+2
-2
@@ -129,7 +129,7 @@ func TestCertUpgrade(t *testing.T) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
r.Logf("reload new v2-only config")
|
r.Logf("reload new v2-only config")
|
||||||
err = myC.ReloadConfigString(string(cb))
|
err = myC.ReloadConfigString(string(cb)).Err
|
||||||
assert.NoError(t, err)
|
assert.NoError(t, err)
|
||||||
r.Log("yay, spin until their sees it")
|
r.Log("yay, spin until their sees it")
|
||||||
waitStart := time.Now()
|
waitStart := time.Now()
|
||||||
@@ -222,7 +222,7 @@ func TestCertDowngrade(t *testing.T) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
r.Logf("reload new v1-only config")
|
r.Logf("reload new v1-only config")
|
||||||
err = myC.ReloadConfigString(string(cb))
|
err = myC.ReloadConfigString(string(cb)).Err
|
||||||
assert.NoError(t, err)
|
assert.NoError(t, err)
|
||||||
r.Log("yay, spin until their sees it")
|
r.Log("yay, spin until their sees it")
|
||||||
waitStart := time.Now()
|
waitStart := time.Now()
|
||||||
|
|||||||
+20
-32
@@ -8,6 +8,7 @@ pki:
|
|||||||
cert: /etc/nebula/host.crt
|
cert: /etc/nebula/host.crt
|
||||||
key: /etc/nebula/host.key
|
key: /etc/nebula/host.key
|
||||||
# blocklist is a list of certificate fingerprints that we will refuse to talk to
|
# 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:
|
#blocklist:
|
||||||
# - c99d4e650533b92061b09918e838a5a0a6aaee21eed1d12fd937682865936c72
|
# - c99d4e650533b92061b09918e838a5a0a6aaee21eed1d12fd937682865936c72
|
||||||
# disconnect_invalid is a toggle to force a client to be disconnected if the certificate is expired or invalid.
|
# disconnect_invalid is a toggle to force a client to be disconnected if the certificate is expired or invalid.
|
||||||
@@ -43,7 +44,7 @@ static_host_map:
|
|||||||
|
|
||||||
lighthouse:
|
lighthouse:
|
||||||
# am_lighthouse is used to enable lighthouse functionality for a node. This should ONLY be true on nodes
|
# 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
|
# you have configured to be lighthouses in your network. Not reloadable.
|
||||||
am_lighthouse: false
|
am_lighthouse: false
|
||||||
# serve_dns optionally starts a dns listener that responds to various queries and can even be
|
# serve_dns optionally starts a dns listener that responds to various queries and can even be
|
||||||
# delegated to for resolution
|
# delegated to for resolution
|
||||||
@@ -126,8 +127,9 @@ lighthouse:
|
|||||||
# Port Nebula will be listening on. The default here is 4242. For a lighthouse node, the port should be defined,
|
# 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.
|
# however using port 0 will dynamically assign a port and is recommended for roaming nodes.
|
||||||
listen:
|
listen:
|
||||||
# To listen on only ipv4, use "0.0.0.0"
|
# To listen on only ipv4, use "0.0.0.0". Not reloadable.
|
||||||
host: "::"
|
host: "::"
|
||||||
|
# Not reloadable.
|
||||||
port: 4242
|
port: 4242
|
||||||
# Sets the max number of packets to pull from the kernel for each syscall (under systems that support recvmmsg)
|
# 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
|
# default is 64, does not support reload
|
||||||
@@ -135,7 +137,8 @@ listen:
|
|||||||
# superpacket, so the receive scratch is batch * 64KiB per listening socket (~4MiB per routine at the
|
# 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.
|
# default of 64). Lower this to trade peak per-syscall throughput for memory on constrained hosts.
|
||||||
#batch: 64
|
#batch: 64
|
||||||
# Linux only. Configure socket buffers for the udp side (outside), leave unset to use the system defaults. Values will be doubled by the kernel
|
# Linux only. Reloadable, but removing a value leaves the socket at the old size until Nebula restarts.
|
||||||
|
# Configure socket buffers for the udp side (outside), leave unset to use the system defaults. Values will be doubled by the kernel
|
||||||
# Default is net.core.rmem_default and net.core.wmem_default (/proc/sys/net/core/rmem_default and /proc/sys/net/core/rmem_default)
|
# 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
|
# 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
|
# max, net.core.rmem_max and net.core.wmem_max
|
||||||
@@ -179,7 +182,7 @@ listen:
|
|||||||
# Currently, this defaults to 1 which means we have 1 tun queue reader and 1
|
# 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
|
# 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.
|
# device and SO_REUSEPORT on the UDP socket to allow multiple queues.
|
||||||
# This option is only supported on Linux.
|
# This option is only supported on Linux. Not reloadable.
|
||||||
#routines: 1
|
#routines: 1
|
||||||
|
|
||||||
punchy:
|
punchy:
|
||||||
@@ -203,6 +206,7 @@ punchy:
|
|||||||
|
|
||||||
# Cipher allows you to choose between the available ciphers for your network. Options are chachapoly or aes
|
# 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!
|
# 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
|
#cipher: aes
|
||||||
|
|
||||||
# Preferred ranges is used to define a hint about the local network ranges, which speeds up discovering the fastest
|
# Preferred ranges is used to define a hint about the local network ranges, which speeds up discovering the fastest
|
||||||
@@ -229,12 +233,6 @@ punchy:
|
|||||||
# Trusted SSH CA public keys. These are the public keys of the CAs that are allowed to sign SSH keys for access.
|
# Trusted SSH CA public keys. These are the public keys of the CAs that are allowed to sign SSH keys for access.
|
||||||
#trusted_cas:
|
#trusted_cas:
|
||||||
#- "ssh public key string"
|
#- "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.
|
# EXPERIMENTAL: relay support for networks that can't establish direct connections.
|
||||||
relay:
|
relay:
|
||||||
@@ -253,19 +251,25 @@ relay:
|
|||||||
# Configure the private interface. Note: addr is baked into the nebula certificate
|
# Configure the private interface. Note: addr is baked into the nebula certificate
|
||||||
tun:
|
tun:
|
||||||
# When tun is disabled, a lighthouse can be started without a local tun interface (and therefore without root)
|
# When tun is disabled, a lighthouse can be started without a local tun interface (and therefore without root)
|
||||||
|
# Not reloadable.
|
||||||
disabled: false
|
disabled: false
|
||||||
# Name of the device. If not set, a default will be chosen by the OS.
|
# 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 macOS: if set, must be in the form `utun[0-9]+`.
|
||||||
# For NetBSD: Required to be set, must be in the form `tun[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.
|
||||||
dev: nebula1
|
dev: nebula1
|
||||||
# Toggles forwarding of local broadcast packets, the address of which depends on the ip/mask encoded in pki.cert
|
# 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
|
drop_local_broadcast: false
|
||||||
# Toggles forwarding of multicast packets
|
# Toggles forwarding of multicast packets. Not reloadable.
|
||||||
drop_multicast: false
|
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
|
# 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
|
tx_queue: 5000
|
||||||
# Default MTU for every packet, safe setting is (and the default) 1300 for internet based traffic
|
# 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
|
# 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
|
mtu: 1300
|
||||||
|
|
||||||
# the use_offloads setting controls if Nebula will attempt to enable GSO and GRO for the tun device. Linux only, not reloadable.
|
# the use_offloads setting controls if Nebula will attempt to enable GSO and GRO for the tun device. Linux only, not reloadable.
|
||||||
@@ -358,7 +362,7 @@ tun:
|
|||||||
#use_system_route_table: false
|
#use_system_route_table: false
|
||||||
# Buffer size for reading routes updates. 0 means default system buffer size. (/proc/sys/net/core/rmem_default).
|
# 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.
|
# 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
|
# SO_RCVBUFFORCE is used to avoid having to raise the system wide max. Not reloadable.
|
||||||
#use_system_route_table_buffer_size: 0
|
#use_system_route_table_buffer_size: 0
|
||||||
|
|
||||||
# Configure logging level
|
# Configure logging level
|
||||||
@@ -408,34 +412,18 @@ logging:
|
|||||||
# Handshakes are sent to all known addresses at each interval with a linear backoff,
|
# 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
|
# 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
|
# 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
|
#try_interval: 100ms
|
||||||
#retries: 20
|
#retries: 20
|
||||||
|
|
||||||
# query_buffer is the size of the buffer channel for querying lighthouses, drops are recorded in the lighthouse.query.dropped metric.
|
# query_buffer is the size of the buffer channel for querying lighthouses, drops are recorded in the lighthouse.query.dropped metric.
|
||||||
|
# Not reloadable.
|
||||||
#query_buffer: 1024
|
#query_buffer: 1024
|
||||||
|
|
||||||
# trigger_buffer is the size of the buffer channel for quickly sending handshakes
|
# trigger_buffer is the size of the buffer channel for quickly sending handshakes
|
||||||
# after receiving the response for lighthouse queries
|
# after receiving the response for lighthouse queries. Not reloadable.
|
||||||
#trigger_buffer: 64
|
#trigger_buffer: 64
|
||||||
|
|
||||||
# pq enables handshakes that mix an ephemeral ML-KEM-1024 key exchange into the session keys, protecting
|
|
||||||
# recorded traffic against a future quantum computer. Authentication is unchanged. These handshakes are too
|
|
||||||
# large for one packet and travel as fragments with forward error correction.
|
|
||||||
#pq:
|
|
||||||
# initiate starts post-quantum handshakes. Attempts alternate between post-quantum and classical until one is
|
|
||||||
# answered, so peers that do not support them still connect.
|
|
||||||
#initiate: false
|
|
||||||
# accept answers post-quantum handshakes from peers.
|
|
||||||
#accept: false
|
|
||||||
# require makes every handshake post-quantum: it implies initiate and accept, never offers a classical handshake
|
|
||||||
# and refuses classical handshakes from peers. Only enable it once every host can speak post-quantum handshakes.
|
|
||||||
#require: false
|
|
||||||
# sticky never falls back to a classical handshake with a peer that has completed a post-quantum one since
|
|
||||||
# nebula started, which defeats an attacker who drops post-quantum handshakes to force a downgrade.
|
|
||||||
#sticky: false
|
|
||||||
# repair_delay is how long the forward error correction fragments trail the rest of a handshake message.
|
|
||||||
#repair_delay: 10ms
|
|
||||||
|
|
||||||
# Tunnel manager settings
|
# Tunnel manager settings
|
||||||
#tunnels:
|
#tunnels:
|
||||||
# drop_inactive controls whether inactive tunnels are maintained or dropped after the inactive_timeout period has
|
# drop_inactive controls whether inactive tunnels are maintained or dropped after the inactive_timeout period has
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
module github.com/slackhq/nebula
|
module github.com/slackhq/nebula
|
||||||
|
|
||||||
go 1.26.0
|
go 1.27.2
|
||||||
|
|
||||||
require (
|
require (
|
||||||
dario.cat/mergo v1.0.2
|
dario.cat/mergo v1.0.2
|
||||||
@@ -33,7 +33,7 @@ require (
|
|||||||
golang.zx2c4.com/wireguard/windows v1.0.1
|
golang.zx2c4.com/wireguard/windows v1.0.1
|
||||||
google.golang.org/protobuf v1.36.12
|
google.golang.org/protobuf v1.36.12
|
||||||
gopkg.in/yaml.v3 v3.0.1
|
gopkg.in/yaml.v3 v3.0.1
|
||||||
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe
|
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980
|
||||||
)
|
)
|
||||||
|
|
||||||
require (
|
require (
|
||||||
@@ -45,5 +45,6 @@ require (
|
|||||||
github.com/prometheus/common v0.70.1 // indirect
|
github.com/prometheus/common v0.70.1 // indirect
|
||||||
github.com/prometheus/procfs v0.21.1 // indirect
|
github.com/prometheus/procfs v0.21.1 // indirect
|
||||||
github.com/vishvananda/netns v0.0.5 // indirect
|
github.com/vishvananda/netns v0.0.5 // indirect
|
||||||
golang.org/x/time v0.5.0 // indirect
|
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc // indirect
|
||||||
|
golang.org/x/time v0.15.0 // indirect
|
||||||
)
|
)
|
||||||
@@ -157,6 +157,8 @@ 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 v0.0.0-20210322153248-0c34fe9e7dc2/go.mod h1:T9bdIzuCu7OtxOm1hfPfRQxPLYneinmdGuTeoZ9dtd4=
|
||||||
golang.org/x/crypto v0.57.0 h1:3ZVCjf8Ggz7zneR/EHRVx68Ctf+2pmIMP2UFhh9cC6M=
|
golang.org/x/crypto v0.57.0 h1:3ZVCjf8Ggz7zneR/EHRVx68Ctf+2pmIMP2UFhh9cC6M=
|
||||||
golang.org/x/crypto v0.57.0/go.mod h1:Fdz0i5U6CoizGwLda9DttjSk6qlZo25zYNtR+ycvuZA=
|
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/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 v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
|
||||||
golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
|
golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
|
||||||
@@ -203,8 +205,8 @@ 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 v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
|
||||||
golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
|
golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
|
||||||
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
|
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
|
||||||
golang.org/x/time v0.5.0 h1:o7cqy6amK/52YcAKIPlM3a+Fpj35zvRj2TP+e1xFSfk=
|
golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
|
||||||
golang.org/x/time v0.5.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
|
golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
|
||||||
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
|
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 v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
|
||||||
golang.org/x/tools v0.0.0-20200130002326-2f3ba24bd6e7/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
|
golang.org/x/tools v0.0.0-20200130002326-2f3ba24bd6e7/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
|
||||||
@@ -243,5 +245,5 @@ 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 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
|
||||||
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
|
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
|
||||||
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
|
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
|
||||||
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe h1:fre4i6mv4iBuz5lCMOzHD1rH1ljqHWSICFmZRbbgp3g=
|
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980 h1:ribyrTYQ/QYeUIs8x8bVLYwGyepa7RnHLqJzegT5YYk=
|
||||||
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe/go.mod h1:sxc3Uvk/vHcd3tj7/DHVBoR5wvWT/MmRq2pj7HRJnwU=
|
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980/go.mod h1:pK/dapF5Bf3KGW7/kd5CI5IC4lYh9FMFY1qETAIGLXk=
|
||||||
@@ -35,9 +35,7 @@ func NewCredential(
|
|||||||
}
|
}
|
||||||
|
|
||||||
// buildHandshakeState creates a noise.HandshakeState from this credential.
|
// buildHandshakeState creates a noise.HandshakeState from this credential.
|
||||||
// pskPlacement selects the noise psk modifier; 0 means none. A psk for
|
func (hc *Credential) buildHandshakeState(initiator bool, pattern noise.HandshakePattern) (*noise.HandshakeState, error) {
|
||||||
// placements 2 and up is supplied later with SetPresharedKey.
|
|
||||||
func (hc *Credential) buildHandshakeState(initiator bool, pattern noise.HandshakePattern, pskPlacement int) (*noise.HandshakeState, error) {
|
|
||||||
return noise.NewHandshakeState(noise.Config{
|
return noise.NewHandshakeState(noise.Config{
|
||||||
CipherSuite: hc.cipherSuite,
|
CipherSuite: hc.cipherSuite,
|
||||||
Random: rand.Reader,
|
Random: rand.Reader,
|
||||||
@@ -45,7 +43,7 @@ func (hc *Credential) buildHandshakeState(initiator bool, pattern noise.Handshak
|
|||||||
Initiator: initiator,
|
Initiator: initiator,
|
||||||
StaticKeypair: noise.DHKey{Private: hc.privateKey, Public: hc.Cert.PublicKey()},
|
StaticKeypair: noise.DHKey{Private: hc.privateKey, Public: hc.Cert.PublicKey()},
|
||||||
PresharedKey: []byte{},
|
PresharedKey: []byte{},
|
||||||
PresharedKeyPlacement: pskPlacement,
|
PresharedKeyPlacement: 0,
|
||||||
})
|
})
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -1,216 +0,0 @@
|
|||||||
// Package fec implements the systematic Reed-Solomon erasure code used to carry
|
|
||||||
// handshake messages that do not fit in a single UDP packet.
|
|
||||||
//
|
|
||||||
// A message is split into K equally sized data symbols (the last one zero
|
|
||||||
// padded). Symbol indexes 0..K-1 are the data symbols themselves; indexes
|
|
||||||
// K..MaxSymbols-1 are repair symbols. Any K distinct symbols reconstruct the
|
|
||||||
// message. Repair symbols are generated on demand, so a sender can emit fresh
|
|
||||||
// ones on every retransmit and a receiver can merge everything it has seen.
|
|
||||||
package fec
|
|
||||||
|
|
||||||
import (
|
|
||||||
"errors"
|
|
||||||
"fmt"
|
|
||||||
)
|
|
||||||
|
|
||||||
// MaxSymbols is the number of distinct symbols, data and repair together, one
|
|
||||||
// message can be encoded into. It is bounded by the size of GF(2^8).
|
|
||||||
const MaxSymbols = 256
|
|
||||||
|
|
||||||
var (
|
|
||||||
ErrInvalidLayout = errors.New("invalid fec layout")
|
|
||||||
ErrIndexRange = errors.New("symbol index out of range")
|
|
||||||
ErrSymbolSize = errors.New("symbol has the wrong size")
|
|
||||||
ErrNotEnough = errors.New("not enough symbols to decode")
|
|
||||||
ErrCorrupt = errors.New("decoded message has non-zero padding")
|
|
||||||
)
|
|
||||||
|
|
||||||
// Layout describes how a message is split into symbols. Both ends derive it
|
|
||||||
// from the message length alone, so it never has to be sent.
|
|
||||||
type Layout struct {
|
|
||||||
MsgLen int // length of the message in bytes
|
|
||||||
K int // number of data symbols
|
|
||||||
SymbolSize int // size of every symbol, data and repair
|
|
||||||
}
|
|
||||||
|
|
||||||
// NewLayout returns the layout for a message of msgLen bytes carried in symbols
|
|
||||||
// of at most maxSymbolSize bytes. Symbols are balanced, so padding is always
|
|
||||||
// less than K bytes.
|
|
||||||
func NewLayout(msgLen, maxSymbolSize int) (Layout, error) {
|
|
||||||
if msgLen <= 0 || maxSymbolSize <= 0 {
|
|
||||||
return Layout{}, ErrInvalidLayout
|
|
||||||
}
|
|
||||||
k := (msgLen + maxSymbolSize - 1) / maxSymbolSize
|
|
||||||
if k >= MaxSymbols {
|
|
||||||
return Layout{}, fmt.Errorf("%w: %d data symbols", ErrInvalidLayout, k)
|
|
||||||
}
|
|
||||||
return Layout{
|
|
||||||
MsgLen: msgLen,
|
|
||||||
K: k,
|
|
||||||
SymbolSize: (msgLen + k - 1) / k,
|
|
||||||
}, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
// Encoder produces symbols for one message.
|
|
||||||
type Encoder struct {
|
|
||||||
layout Layout
|
|
||||||
data [][]byte
|
|
||||||
}
|
|
||||||
|
|
||||||
// NewEncoder copies msg into padded data symbols.
|
|
||||||
func NewEncoder(msg []byte, maxSymbolSize int) (*Encoder, error) {
|
|
||||||
l, err := NewLayout(len(msg), maxSymbolSize)
|
|
||||||
if err != nil {
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
|
|
||||||
buf := make([]byte, l.K*l.SymbolSize)
|
|
||||||
copy(buf, msg)
|
|
||||||
data := make([][]byte, l.K)
|
|
||||||
for i := range data {
|
|
||||||
data[i] = buf[i*l.SymbolSize : (i+1)*l.SymbolSize]
|
|
||||||
}
|
|
||||||
return &Encoder{layout: l, data: data}, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
func (e *Encoder) Layout() Layout {
|
|
||||||
return e.layout
|
|
||||||
}
|
|
||||||
|
|
||||||
// Symbol appends the symbol with the given index to dst and returns the result.
|
|
||||||
func (e *Encoder) Symbol(dst []byte, index int) ([]byte, error) {
|
|
||||||
if index < 0 || index >= MaxSymbols {
|
|
||||||
return nil, ErrIndexRange
|
|
||||||
}
|
|
||||||
if index < e.layout.K {
|
|
||||||
return append(dst, e.data[index]...), nil
|
|
||||||
}
|
|
||||||
|
|
||||||
start := len(dst)
|
|
||||||
dst = append(dst, make([]byte, e.layout.SymbolSize)...)
|
|
||||||
out := dst[start:]
|
|
||||||
for col, d := range e.data {
|
|
||||||
mulAdd(out, d, coefficient(index, col))
|
|
||||||
}
|
|
||||||
return dst, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
// Decoder collects symbols for one message until it can reconstruct it.
|
|
||||||
// It stores at most K symbols, so its memory is bounded by the layout no matter
|
|
||||||
// how many symbols arrive.
|
|
||||||
type Decoder struct {
|
|
||||||
layout Layout
|
|
||||||
have [MaxSymbols]bool
|
|
||||||
syms map[int][]byte
|
|
||||||
}
|
|
||||||
|
|
||||||
// NewDecoder returns a decoder for a message of msgLen bytes that was encoded
|
|
||||||
// with the same maxSymbolSize.
|
|
||||||
func NewDecoder(msgLen, maxSymbolSize int) (*Decoder, error) {
|
|
||||||
l, err := NewLayout(msgLen, maxSymbolSize)
|
|
||||||
if err != nil {
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
return &Decoder{layout: l, syms: make(map[int][]byte, l.K)}, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
func (d *Decoder) Layout() Layout {
|
|
||||||
return d.layout
|
|
||||||
}
|
|
||||||
|
|
||||||
// Stored returns the number of symbols held.
|
|
||||||
func (d *Decoder) Stored() int {
|
|
||||||
return len(d.syms)
|
|
||||||
}
|
|
||||||
|
|
||||||
// Has reports whether the symbol with the given index is held.
|
|
||||||
func (d *Decoder) Has(index int) bool {
|
|
||||||
return index >= 0 && index < MaxSymbols && d.have[index]
|
|
||||||
}
|
|
||||||
|
|
||||||
// Ready reports whether enough symbols have arrived to decode.
|
|
||||||
func (d *Decoder) Ready() bool {
|
|
||||||
return len(d.syms) >= d.layout.K
|
|
||||||
}
|
|
||||||
|
|
||||||
// Add stores a copy of the symbol. Duplicates, and anything beyond the first K
|
|
||||||
// distinct symbols, are ignored. It returns whether the decoder is ready.
|
|
||||||
func (d *Decoder) Add(index int, sym []byte) (bool, error) {
|
|
||||||
if index < 0 || index >= MaxSymbols {
|
|
||||||
return d.Ready(), ErrIndexRange
|
|
||||||
}
|
|
||||||
if len(sym) != d.layout.SymbolSize {
|
|
||||||
return d.Ready(), ErrSymbolSize
|
|
||||||
}
|
|
||||||
if d.have[index] || d.Ready() {
|
|
||||||
return d.Ready(), nil
|
|
||||||
}
|
|
||||||
d.have[index] = true
|
|
||||||
d.syms[index] = append([]byte(nil), sym...)
|
|
||||||
return d.Ready(), nil
|
|
||||||
}
|
|
||||||
|
|
||||||
// Decode reconstructs the message from the stored symbols.
|
|
||||||
func (d *Decoder) Decode() ([]byte, error) {
|
|
||||||
if !d.Ready() {
|
|
||||||
return nil, ErrNotEnough
|
|
||||||
}
|
|
||||||
l := d.layout
|
|
||||||
|
|
||||||
out := make([]byte, l.K*l.SymbolSize)
|
|
||||||
var missing, repair []int
|
|
||||||
for i := range l.K {
|
|
||||||
if s, ok := d.syms[i]; ok {
|
|
||||||
copy(out[i*l.SymbolSize:], s)
|
|
||||||
} else {
|
|
||||||
missing = append(missing, i)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if len(missing) > 0 {
|
|
||||||
for i := l.K; i < MaxSymbols && len(repair) < len(missing); i++ {
|
|
||||||
if d.have[i] {
|
|
||||||
repair = append(repair, i)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
if len(repair) < len(missing) {
|
|
||||||
return nil, ErrNotEnough
|
|
||||||
}
|
|
||||||
|
|
||||||
// Each repair symbol r satisfies r = sum_col coefficient(r, col) * data[col].
|
|
||||||
// Move the known data columns to the left hand side, leaving a square
|
|
||||||
// Cauchy system in the missing columns.
|
|
||||||
rhs := make([][]byte, len(repair))
|
|
||||||
m := make([][]byte, len(repair))
|
|
||||||
for ri, row := range repair {
|
|
||||||
rhs[ri] = append([]byte(nil), d.syms[row]...)
|
|
||||||
m[ri] = make([]byte, len(missing))
|
|
||||||
mi := 0
|
|
||||||
for col := range l.K {
|
|
||||||
if mi < len(missing) && missing[mi] == col {
|
|
||||||
m[ri][mi] = coefficient(row, col)
|
|
||||||
mi++
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
mulAdd(rhs[ri], out[col*l.SymbolSize:(col+1)*l.SymbolSize], coefficient(row, col))
|
|
||||||
}
|
|
||||||
}
|
|
||||||
if !invert(m) {
|
|
||||||
// Unreachable for a Cauchy matrix; kept so a broken invariant fails loudly.
|
|
||||||
return nil, errors.New("fec: singular decode matrix")
|
|
||||||
}
|
|
||||||
for mi, col := range missing {
|
|
||||||
dst := out[col*l.SymbolSize : (col+1)*l.SymbolSize]
|
|
||||||
for ri := range repair {
|
|
||||||
mulAdd(dst, rhs[ri], m[mi][ri])
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
for _, b := range out[l.MsgLen:] {
|
|
||||||
if b != 0 {
|
|
||||||
return nil, ErrCorrupt
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return out[:l.MsgLen], nil
|
|
||||||
}
|
|
||||||
@@ -1,318 +0,0 @@
|
|||||||
package fec
|
|
||||||
|
|
||||||
import (
|
|
||||||
"crypto/sha256"
|
|
||||||
"encoding/hex"
|
|
||||||
"math/rand/v2"
|
|
||||||
"testing"
|
|
||||||
|
|
||||||
"github.com/stretchr/testify/assert"
|
|
||||||
"github.com/stretchr/testify/require"
|
|
||||||
)
|
|
||||||
|
|
||||||
// slowMul is carry-less multiplication reduced by gfPoly, used to check the tables.
|
|
||||||
func slowMul(a, b byte) byte {
|
|
||||||
var p int
|
|
||||||
x, y := int(a), int(b)
|
|
||||||
for y > 0 {
|
|
||||||
if y&1 != 0 {
|
|
||||||
p ^= x
|
|
||||||
}
|
|
||||||
x <<= 1
|
|
||||||
if x&0x100 != 0 {
|
|
||||||
x ^= gfPoly
|
|
||||||
}
|
|
||||||
y >>= 1
|
|
||||||
}
|
|
||||||
return byte(p)
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestGF(t *testing.T) {
|
|
||||||
for a := range 256 {
|
|
||||||
for b := range 256 {
|
|
||||||
require.Equal(t, slowMul(byte(a), byte(b)), gfMul(byte(a), byte(b)), "%d*%d", a, b)
|
|
||||||
}
|
|
||||||
if a != 0 {
|
|
||||||
require.Equal(t, byte(1), gfMul(byte(a), gfInv(byte(a))), "inv(%d)", a)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
src := make([]byte, 256)
|
|
||||||
for i := range src {
|
|
||||||
src[i] = byte(i)
|
|
||||||
}
|
|
||||||
for c := range 256 {
|
|
||||||
dst := make([]byte, 256)
|
|
||||||
mulAdd(dst, src, byte(c))
|
|
||||||
for i := range src {
|
|
||||||
require.Equal(t, gfMul(byte(c), src[i]), dst[i])
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestLayout(t *testing.T) {
|
|
||||||
for msgLen := 1; msgLen <= 20000; msgLen++ {
|
|
||||||
l, err := NewLayout(msgLen, 1176)
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.Equal(t, (msgLen+1175)/1176, l.K)
|
|
||||||
require.LessOrEqual(t, l.SymbolSize, 1176)
|
|
||||||
require.GreaterOrEqual(t, l.K*l.SymbolSize, msgLen)
|
|
||||||
require.Less(t, l.K*l.SymbolSize-msgLen, l.K, "padding must be less than one byte per symbol")
|
|
||||||
}
|
|
||||||
|
|
||||||
l, err := NewLayout(65535, 1176)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, 56, l.K)
|
|
||||||
|
|
||||||
_, err = NewLayout(0, 1176)
|
|
||||||
require.ErrorIs(t, err, ErrInvalidLayout)
|
|
||||||
_, err = NewLayout(100, 0)
|
|
||||||
require.ErrorIs(t, err, ErrInvalidLayout)
|
|
||||||
_, err = NewLayout(256, 1)
|
|
||||||
require.ErrorIs(t, err, ErrInvalidLayout)
|
|
||||||
_, err = NewLayout(255, 1)
|
|
||||||
require.NoError(t, err)
|
|
||||||
}
|
|
||||||
|
|
||||||
func randMsg(r *rand.Rand, n int) []byte {
|
|
||||||
b := make([]byte, n)
|
|
||||||
for i := range b {
|
|
||||||
b[i] = byte(r.Uint32())
|
|
||||||
}
|
|
||||||
return b
|
|
||||||
}
|
|
||||||
|
|
||||||
func decodeWith(t *testing.T, enc *Encoder, msgLen, maxSym int, indexes []int) []byte {
|
|
||||||
t.Helper()
|
|
||||||
dec, err := NewDecoder(msgLen, maxSym)
|
|
||||||
require.NoError(t, err)
|
|
||||||
for _, idx := range indexes {
|
|
||||||
sym, err := enc.Symbol(nil, idx)
|
|
||||||
require.NoError(t, err)
|
|
||||||
_, err = dec.Add(idx, sym)
|
|
||||||
require.NoError(t, err)
|
|
||||||
}
|
|
||||||
require.True(t, dec.Ready())
|
|
||||||
out, err := dec.Decode()
|
|
||||||
require.NoError(t, err)
|
|
||||||
return out
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestExhaustiveSubsets decodes every k-subset of the first k+m symbols for
|
|
||||||
// small codes, which checks the MDS property directly.
|
|
||||||
func TestExhaustiveSubsets(t *testing.T) {
|
|
||||||
r := rand.New(rand.NewPCG(1, 2))
|
|
||||||
const maxSym = 16
|
|
||||||
for k := 1; k <= 10; k++ {
|
|
||||||
for m := 1; m <= 5; m++ {
|
|
||||||
msgLen := (k-1)*maxSym + 1 + r.IntN(maxSym)
|
|
||||||
msg := randMsg(r, msgLen)
|
|
||||||
enc, err := NewEncoder(msg, maxSym)
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.Equal(t, k, enc.Layout().K)
|
|
||||||
|
|
||||||
n := k + m
|
|
||||||
for mask := 0; mask < 1<<n; mask++ {
|
|
||||||
var idx []int
|
|
||||||
for i := range n {
|
|
||||||
if mask&(1<<i) != 0 {
|
|
||||||
idx = append(idx, i)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
if len(idx) != k {
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
require.Equal(t, msg, decodeWith(t, enc, msgLen, maxSym, idx), "k=%d m=%d idx=%v", k, m, idx)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestRandomHighIndexes draws symbols from the whole index space, the shape
|
|
||||||
// retransmits produce once fresh repair symbols are in play.
|
|
||||||
func TestRandomHighIndexes(t *testing.T) {
|
|
||||||
r := rand.New(rand.NewPCG(3, 4))
|
|
||||||
for range 2000 {
|
|
||||||
msgLen := 1 + r.IntN(65535)
|
|
||||||
msg := randMsg(r, msgLen)
|
|
||||||
enc, err := NewEncoder(msg, 1176)
|
|
||||||
require.NoError(t, err)
|
|
||||||
k := enc.Layout().K
|
|
||||||
|
|
||||||
idx := r.Perm(MaxSymbols)[:k]
|
|
||||||
require.Equal(t, msg, decodeWith(t, enc, msgLen, 1176, idx), "k=%d idx=%v", k, idx)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestDecoderBounds(t *testing.T) {
|
|
||||||
r := rand.New(rand.NewPCG(5, 6))
|
|
||||||
msg := randMsg(r, 3000)
|
|
||||||
enc, err := NewEncoder(msg, 1176)
|
|
||||||
require.NoError(t, err)
|
|
||||||
l := enc.Layout()
|
|
||||||
require.Equal(t, 3, l.K)
|
|
||||||
require.Equal(t, 1000, l.SymbolSize)
|
|
||||||
|
|
||||||
dec, err := NewDecoder(3000, 1176)
|
|
||||||
require.NoError(t, err)
|
|
||||||
|
|
||||||
_, err = dec.Decode()
|
|
||||||
require.ErrorIs(t, err, ErrNotEnough)
|
|
||||||
|
|
||||||
_, err = dec.Add(-1, make([]byte, 1000))
|
|
||||||
require.ErrorIs(t, err, ErrIndexRange)
|
|
||||||
_, err = dec.Add(MaxSymbols, make([]byte, 1000))
|
|
||||||
require.ErrorIs(t, err, ErrIndexRange)
|
|
||||||
_, err = dec.Add(0, make([]byte, 999))
|
|
||||||
require.ErrorIs(t, err, ErrSymbolSize)
|
|
||||||
|
|
||||||
s5, _ := enc.Symbol(nil, 5)
|
|
||||||
ready, err := dec.Add(5, s5)
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.False(t, ready)
|
|
||||||
|
|
||||||
// A duplicate index is ignored, even with different contents.
|
|
||||||
ready, err = dec.Add(5, make([]byte, 1000))
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.False(t, ready)
|
|
||||||
|
|
||||||
s0, _ := enc.Symbol(nil, 0)
|
|
||||||
s9, _ := enc.Symbol(nil, 9)
|
|
||||||
_, err = dec.Add(0, s0)
|
|
||||||
require.NoError(t, err)
|
|
||||||
ready, err = dec.Add(9, s9)
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.True(t, ready)
|
|
||||||
|
|
||||||
// Symbols beyond K are not stored.
|
|
||||||
ready, err = dec.Add(1, make([]byte, 1000))
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.True(t, ready)
|
|
||||||
require.Len(t, dec.syms, 3)
|
|
||||||
|
|
||||||
out, err := dec.Decode()
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.Equal(t, msg, out)
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestCorruptPadding(t *testing.T) {
|
|
||||||
// 3001 bytes in 3 symbols of 1001 leaves 2 bytes of padding in the last one.
|
|
||||||
dec, err := NewDecoder(3001, 1176)
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.Equal(t, 1001, dec.Layout().SymbolSize)
|
|
||||||
|
|
||||||
last := make([]byte, 1001)
|
|
||||||
last[1000] = 1
|
|
||||||
for i, s := range [][]byte{make([]byte, 1001), make([]byte, 1001), last} {
|
|
||||||
_, err = dec.Add(i, s)
|
|
||||||
require.NoError(t, err)
|
|
||||||
}
|
|
||||||
_, err = dec.Decode()
|
|
||||||
require.ErrorIs(t, err, ErrCorrupt)
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestKnownAnswer pins the encoding. Both ends of a handshake must produce
|
|
||||||
// identical repair symbols, so any change here is a wire format change.
|
|
||||||
func TestKnownAnswer(t *testing.T) {
|
|
||||||
msg := make([]byte, 3000)
|
|
||||||
for i := range msg {
|
|
||||||
msg[i] = byte(i*7 + 3)
|
|
||||||
}
|
|
||||||
enc, err := NewEncoder(msg, 1176)
|
|
||||||
require.NoError(t, err)
|
|
||||||
|
|
||||||
// Cross-checked against an independent bit-serial GF(2^8) implementation.
|
|
||||||
want := map[int]string{
|
|
||||||
3: "52124f58276ec6338d3b3f4eed273bc7cabfe4f0f467928962b046ad1b348f50",
|
|
||||||
4: "a50928b04738981985a7d4a17ffaf8d7e30014ca64fc53c99800ffb61aec4aa7",
|
|
||||||
5: "ada4c95a7facbc542aaef584e6f0d081b7b0d0eed69ded03b57d0753a119cfc9",
|
|
||||||
255: "839066cdf94f963b223fb1c1c1360f698c14f6349b25653ff5b521791a4021b1",
|
|
||||||
}
|
|
||||||
for idx, h := range want {
|
|
||||||
sym, err := enc.Symbol(nil, idx)
|
|
||||||
require.NoError(t, err)
|
|
||||||
sum := sha256.Sum256(sym)
|
|
||||||
assert.Equal(t, h, hex.EncodeToString(sum[:]), "symbol %d", idx)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
func FuzzRoundTrip(f *testing.F) {
|
|
||||||
f.Add([]byte("hello"), uint16(2), uint64(0))
|
|
||||||
f.Add(make([]byte, 9000), uint16(1176), uint64(7))
|
|
||||||
f.Fuzz(func(t *testing.T, msg []byte, maxSym uint16, seed uint64) {
|
|
||||||
if len(msg) == 0 || maxSym == 0 {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
enc, err := NewEncoder(msg, int(maxSym))
|
|
||||||
if err != nil {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
r := rand.New(rand.NewPCG(seed, seed))
|
|
||||||
idx := r.Perm(MaxSymbols)[:enc.Layout().K]
|
|
||||||
require.Equal(t, msg, decodeWith(t, enc, len(msg), int(maxSym), idx))
|
|
||||||
})
|
|
||||||
}
|
|
||||||
|
|
||||||
// FuzzDecoder feeds arbitrary symbols to a decoder; it must never panic and
|
|
||||||
// must either fail or return a message of the declared length.
|
|
||||||
func FuzzDecoder(f *testing.F) {
|
|
||||||
f.Add(uint16(3000), []byte{0, 5, 9, 200}, []byte("some symbol bytes"))
|
|
||||||
f.Fuzz(func(t *testing.T, msgLen uint16, indexes []byte, fill []byte) {
|
|
||||||
dec, err := NewDecoder(int(msgLen), 1176)
|
|
||||||
if err != nil {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
size := dec.Layout().SymbolSize
|
|
||||||
for i, idx := range indexes {
|
|
||||||
sym := make([]byte, size)
|
|
||||||
for j := range sym {
|
|
||||||
if len(fill) > 0 {
|
|
||||||
sym[j] = fill[(i+j)%len(fill)]
|
|
||||||
}
|
|
||||||
}
|
|
||||||
if _, err := dec.Add(int(idx), sym); err != nil {
|
|
||||||
t.Fatal(err)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
out, err := dec.Decode()
|
|
||||||
if err == nil {
|
|
||||||
require.Len(t, out, int(msgLen))
|
|
||||||
}
|
|
||||||
})
|
|
||||||
}
|
|
||||||
|
|
||||||
// BenchmarkRepair and BenchmarkDecode use a v3-sized msg2 (~9.8KB, k=9) with
|
|
||||||
// three repair symbols, decoding with three data symbols missing.
|
|
||||||
func BenchmarkRepair(b *testing.B) {
|
|
||||||
msg := randMsg(rand.New(rand.NewPCG(7, 8)), 9800)
|
|
||||||
enc, err := NewEncoder(msg, 1176)
|
|
||||||
require.NoError(b, err)
|
|
||||||
buf := make([]byte, 0, 1176)
|
|
||||||
b.SetBytes(int64(len(msg)))
|
|
||||||
for b.Loop() {
|
|
||||||
for idx := 9; idx < 12; idx++ {
|
|
||||||
buf, _ = enc.Symbol(buf[:0], idx)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
func BenchmarkDecode(b *testing.B) {
|
|
||||||
msg := randMsg(rand.New(rand.NewPCG(7, 8)), 9800)
|
|
||||||
enc, err := NewEncoder(msg, 1176)
|
|
||||||
require.NoError(b, err)
|
|
||||||
idx := []int{0, 1, 2, 3, 5, 6, 9, 10, 11}
|
|
||||||
syms := make([][]byte, len(idx))
|
|
||||||
for i, x := range idx {
|
|
||||||
syms[i], _ = enc.Symbol(nil, x)
|
|
||||||
}
|
|
||||||
b.SetBytes(int64(len(msg)))
|
|
||||||
for b.Loop() {
|
|
||||||
dec, _ := NewDecoder(len(msg), 1176)
|
|
||||||
for i, x := range idx {
|
|
||||||
_, _ = dec.Add(x, syms[i])
|
|
||||||
}
|
|
||||||
if _, err := dec.Decode(); err != nil {
|
|
||||||
b.Fatal(err)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
@@ -1,115 +0,0 @@
|
|||||||
package fec
|
|
||||||
|
|
||||||
// Arithmetic over GF(2^8) with the reducing polynomial x^8+x^4+x^3+x^2+1 (0x11d).
|
|
||||||
// Addition is XOR. Multiplication uses log/exp tables; the exp table is doubled so
|
|
||||||
// the sum of two logs never needs reducing mod 255.
|
|
||||||
|
|
||||||
const gfPoly = 0x11d
|
|
||||||
|
|
||||||
var (
|
|
||||||
gfExp [510]byte
|
|
||||||
gfLog [256]byte
|
|
||||||
)
|
|
||||||
|
|
||||||
func init() {
|
|
||||||
x := 1
|
|
||||||
for i := range 255 {
|
|
||||||
gfExp[i] = byte(x)
|
|
||||||
gfExp[i+255] = byte(x)
|
|
||||||
gfLog[x] = byte(i)
|
|
||||||
x <<= 1
|
|
||||||
if x&0x100 != 0 {
|
|
||||||
x ^= gfPoly
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
func gfMul(a, b byte) byte {
|
|
||||||
if a == 0 || b == 0 {
|
|
||||||
return 0
|
|
||||||
}
|
|
||||||
return gfExp[int(gfLog[a])+int(gfLog[b])]
|
|
||||||
}
|
|
||||||
|
|
||||||
// gfInv returns the multiplicative inverse of a. a must be non-zero.
|
|
||||||
func gfInv(a byte) byte {
|
|
||||||
return gfExp[255-int(gfLog[a])]
|
|
||||||
}
|
|
||||||
|
|
||||||
// mulAdd computes dst ^= c*src element-wise. dst must be at least as long as src.
|
|
||||||
func mulAdd(dst, src []byte, c byte) {
|
|
||||||
switch c {
|
|
||||||
case 0:
|
|
||||||
return
|
|
||||||
case 1:
|
|
||||||
for i, s := range src {
|
|
||||||
dst[i] ^= s
|
|
||||||
}
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
var t [256]byte
|
|
||||||
lc := int(gfLog[c])
|
|
||||||
for s := 1; s < 256; s++ {
|
|
||||||
t[s] = gfExp[int(gfLog[s])+lc]
|
|
||||||
}
|
|
||||||
for i, s := range src {
|
|
||||||
dst[i] ^= t[s]
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// coefficient returns the generator matrix entry for repair symbol index row and
|
|
||||||
// data symbol index col. Repair rows are a Cauchy matrix 1/(x_row + y_col) with
|
|
||||||
// x_row = row and y_col = col: rows are always >= k and columns < k so the two
|
|
||||||
// sets are disjoint, which makes every square submatrix invertible and the
|
|
||||||
// systematic code [I; C] MDS. A row depends only on its index, never on how many
|
|
||||||
// repair symbols exist, so new repair symbols can be generated at any time.
|
|
||||||
func coefficient(row, col int) byte {
|
|
||||||
return gfInv(byte(row) ^ byte(col))
|
|
||||||
}
|
|
||||||
|
|
||||||
// invert inverts the n x n matrix m in place with Gauss-Jordan elimination.
|
|
||||||
// It returns false if m is singular.
|
|
||||||
func invert(m [][]byte) bool {
|
|
||||||
n := len(m)
|
|
||||||
inv := make([][]byte, n)
|
|
||||||
for i := range inv {
|
|
||||||
inv[i] = make([]byte, n)
|
|
||||||
inv[i][i] = 1
|
|
||||||
}
|
|
||||||
|
|
||||||
for col := range n {
|
|
||||||
pivot := -1
|
|
||||||
for r := col; r < n; r++ {
|
|
||||||
if m[r][col] != 0 {
|
|
||||||
pivot = r
|
|
||||||
break
|
|
||||||
}
|
|
||||||
}
|
|
||||||
if pivot < 0 {
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
m[col], m[pivot] = m[pivot], m[col]
|
|
||||||
inv[col], inv[pivot] = inv[pivot], inv[col]
|
|
||||||
|
|
||||||
scale := gfInv(m[col][col])
|
|
||||||
for c := range n {
|
|
||||||
m[col][c] = gfMul(m[col][c], scale)
|
|
||||||
inv[col][c] = gfMul(inv[col][c], scale)
|
|
||||||
}
|
|
||||||
|
|
||||||
for r := 0; r < n; r++ {
|
|
||||||
if r == col || m[r][col] == 0 {
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
f := m[r][col]
|
|
||||||
for c := range n {
|
|
||||||
m[r][c] ^= gfMul(f, m[col][c])
|
|
||||||
inv[r][c] ^= gfMul(f, inv[col][c])
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
copy(m, inv)
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
@@ -1,67 +0,0 @@
|
|||||||
package fragment
|
|
||||||
|
|
||||||
import (
|
|
||||||
"errors"
|
|
||||||
|
|
||||||
"github.com/slackhq/nebula/handshake/fec"
|
|
||||||
"github.com/slackhq/nebula/header"
|
|
||||||
)
|
|
||||||
|
|
||||||
// ErrMismatch is returned when a fragment disagrees with the message it claims to
|
|
||||||
// belong to. The caller should discard the whole assembly.
|
|
||||||
var ErrMismatch = errors.New("fragment does not match its message")
|
|
||||||
|
|
||||||
// Assembly collects the fragments of one incoming message. Its memory is bounded
|
|
||||||
// by the message length: at most K symbols are kept however many arrive.
|
|
||||||
//
|
|
||||||
// An Assembly is not safe for concurrent use.
|
|
||||||
type Assembly struct {
|
|
||||||
fragID uint32
|
|
||||||
msgLen uint16
|
|
||||||
dec *fec.Decoder
|
|
||||||
received int
|
|
||||||
}
|
|
||||||
|
|
||||||
// NewAssembly starts an assembly for the message described by h. The fragment
|
|
||||||
// itself still has to be passed to Add.
|
|
||||||
func NewAssembly(h Header) (*Assembly, error) {
|
|
||||||
dec, err := fec.NewDecoder(int(h.MsgLen), MaxSymbolSize)
|
|
||||||
if err != nil {
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
return &Assembly{fragID: h.FragID, msgLen: h.MsgLen, dec: dec}, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
// Add records a fragment parsed by Parse. It returns true once enough symbols
|
|
||||||
// are held to call Decode.
|
|
||||||
func (a *Assembly) Add(h Header, sym []byte) (bool, error) {
|
|
||||||
if h.FragID != a.fragID || h.MsgLen != a.msgLen {
|
|
||||||
return a.dec.Ready(), ErrMismatch
|
|
||||||
}
|
|
||||||
a.received += header.Len + HeaderLen + len(sym)
|
|
||||||
return a.dec.Add(int(h.Index), sym)
|
|
||||||
}
|
|
||||||
|
|
||||||
// wouldStore returns how many bytes Add would retain for this fragment.
|
|
||||||
func (a *Assembly) wouldStore(h Header, sym []byte) int {
|
|
||||||
if h.FragID != a.fragID || h.MsgLen != a.msgLen || a.dec.Ready() || a.dec.Has(int(h.Index)) {
|
|
||||||
return 0
|
|
||||||
}
|
|
||||||
return len(sym)
|
|
||||||
}
|
|
||||||
|
|
||||||
// Decode reconstructs the message. It requires Add to have reported ready.
|
|
||||||
func (a *Assembly) Decode() ([]byte, error) {
|
|
||||||
return a.dec.Decode()
|
|
||||||
}
|
|
||||||
|
|
||||||
// Stored returns the number of symbol bytes held.
|
|
||||||
func (a *Assembly) Stored() int {
|
|
||||||
return a.dec.Stored() * a.dec.Layout().SymbolSize
|
|
||||||
}
|
|
||||||
|
|
||||||
// Received returns the number of packet bytes received for this message,
|
|
||||||
// duplicates included. It is the basis for the amplification budget.
|
|
||||||
func (a *Assembly) Received() int {
|
|
||||||
return a.received
|
|
||||||
}
|
|
||||||
@@ -1,515 +0,0 @@
|
|||||||
package fragment
|
|
||||||
|
|
||||||
import (
|
|
||||||
"bytes"
|
|
||||||
"math/rand/v2"
|
|
||||||
"sync"
|
|
||||||
"testing"
|
|
||||||
"time"
|
|
||||||
|
|
||||||
"github.com/slackhq/nebula/header"
|
|
||||||
"github.com/stretchr/testify/assert"
|
|
||||||
"github.com/stretchr/testify/require"
|
|
||||||
)
|
|
||||||
|
|
||||||
const testSubtype = header.MessageSubType(9)
|
|
||||||
|
|
||||||
type testKey struct {
|
|
||||||
src string
|
|
||||||
fragID uint32
|
|
||||||
}
|
|
||||||
|
|
||||||
func randMsg(r *rand.Rand, n int) []byte {
|
|
||||||
b := make([]byte, n)
|
|
||||||
for i := range b {
|
|
||||||
b[i] = byte(r.Uint32())
|
|
||||||
}
|
|
||||||
return b
|
|
||||||
}
|
|
||||||
|
|
||||||
func testConfig() TableConfig {
|
|
||||||
return TableConfig{
|
|
||||||
MaxBytes: 1 << 20,
|
|
||||||
MaxEntries: 64,
|
|
||||||
MaxPerSource: 4,
|
|
||||||
MaxMsgLen: 16384,
|
|
||||||
TTL: 2 * time.Second,
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// checkInvariants verifies the table's bookkeeping against its contents.
|
|
||||||
func checkInvariants[K, S comparable](t *testing.T, tb *Table[K, S]) {
|
|
||||||
t.Helper()
|
|
||||||
tb.mu.Lock()
|
|
||||||
defer tb.mu.Unlock()
|
|
||||||
|
|
||||||
require.Len(t, tb.order, len(tb.entries))
|
|
||||||
require.LessOrEqual(t, len(tb.entries), tb.cfg.MaxEntries)
|
|
||||||
bytes := 0
|
|
||||||
perSource := map[S]int{}
|
|
||||||
for i, key := range tb.order {
|
|
||||||
e, ok := tb.entries[key]
|
|
||||||
require.True(t, ok)
|
|
||||||
require.Equal(t, i, e.pos)
|
|
||||||
bytes += e.a.Stored()
|
|
||||||
perSource[e.source]++
|
|
||||||
}
|
|
||||||
require.Equal(t, bytes, tb.bytes)
|
|
||||||
require.LessOrEqual(t, tb.bytes, tb.cfg.MaxBytes)
|
|
||||||
require.Equal(t, perSource, tb.perSource)
|
|
||||||
for _, n := range perSource {
|
|
||||||
require.LessOrEqual(t, n, tb.cfg.MaxPerSource)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
func parse(t *testing.T, p []byte) (header.H, Header, []byte) {
|
|
||||||
t.Helper()
|
|
||||||
var nh header.H
|
|
||||||
require.NoError(t, nh.Parse(p))
|
|
||||||
h, sym, err := Parse(p[header.Len:])
|
|
||||||
require.NoError(t, err)
|
|
||||||
return nh, h, sym
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestParse(t *testing.T) {
|
|
||||||
h := Header{FragID: 0xdeadbeef, MsgLen: 3000, Index: 7}
|
|
||||||
b := h.Encode(nil)
|
|
||||||
require.Len(t, b, HeaderLen)
|
|
||||||
b = append(b, make([]byte, 1000)...)
|
|
||||||
|
|
||||||
got, sym, err := Parse(b)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, h, got)
|
|
||||||
assert.Len(t, sym, 1000)
|
|
||||||
|
|
||||||
_, _, err = Parse(b[:HeaderLen-1])
|
|
||||||
require.ErrorIs(t, err, ErrShortFragment)
|
|
||||||
_, _, err = Parse(b[:len(b)-1])
|
|
||||||
require.ErrorIs(t, err, ErrSymbolSize)
|
|
||||||
_, _, err = Parse(append(b, 0))
|
|
||||||
require.ErrorIs(t, err, ErrSymbolSize)
|
|
||||||
|
|
||||||
bad := Header{FragID: 0, MsgLen: 3000}.Encode(nil)
|
|
||||||
_, _, err = Parse(append(bad, make([]byte, 1000)...))
|
|
||||||
require.ErrorIs(t, err, ErrFragID)
|
|
||||||
|
|
||||||
bad = Header{FragID: 1, MsgLen: 0}.Encode(nil)
|
|
||||||
_, _, err = Parse(bad)
|
|
||||||
require.ErrorIs(t, err, ErrMsgLen)
|
|
||||||
|
|
||||||
bad = Header{FragID: 1, MsgLen: 3000, Flags: 0x02}.Encode(nil)
|
|
||||||
_, _, err = Parse(append(bad, make([]byte, 1000)...))
|
|
||||||
require.ErrorIs(t, err, ErrFlags)
|
|
||||||
|
|
||||||
t.Run("cookie", func(t *testing.T) {
|
|
||||||
h := Header{FragID: 7, MsgLen: 3000, Index: 4, Flags: FlagCookie}
|
|
||||||
for i := range h.Cookie {
|
|
||||||
h.Cookie[i] = byte(i + 1)
|
|
||||||
}
|
|
||||||
b := h.Encode(nil)
|
|
||||||
require.Len(t, b, HeaderLen+CookieLen)
|
|
||||||
b = append(b, make([]byte, 1000)...)
|
|
||||||
|
|
||||||
got, sym, err := Parse(b)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, h, got)
|
|
||||||
assert.True(t, got.HasCookie())
|
|
||||||
assert.Len(t, sym, 1000)
|
|
||||||
|
|
||||||
_, _, err = Parse(b[:HeaderLen+CookieLen-1])
|
|
||||||
require.ErrorIs(t, err, ErrNoCookie)
|
|
||||||
})
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestDefaultRepair(t *testing.T) {
|
|
||||||
for k, want := range map[int]int{1: 2, 2: 2, 6: 2, 7: 3, 9: 3, 10: 4, 14: 5} {
|
|
||||||
assert.Equal(t, want, DefaultRepair(k), "k=%d", k)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestSender(t *testing.T) {
|
|
||||||
_, err := NewSender(nil, testSubtype, 0, 1, 1)
|
|
||||||
require.ErrorIs(t, err, ErrMsgLen)
|
|
||||||
_, err = NewSender(make([]byte, 65536), testSubtype, 0, 1, 1)
|
|
||||||
require.ErrorIs(t, err, ErrMsgLen)
|
|
||||||
_, err = NewSender(make([]byte, 10), testSubtype, 0, 1, 0)
|
|
||||||
require.ErrorIs(t, err, ErrFragID)
|
|
||||||
|
|
||||||
msg := randMsg(rand.New(rand.NewPCG(1, 1)), 9800)
|
|
||||||
s, err := NewSender(msg, testSubtype, 77, 2, 1234)
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.Equal(t, 9, s.Layout().K)
|
|
||||||
|
|
||||||
indexes := func(ps [][]byte) []int {
|
|
||||||
var out []int
|
|
||||||
for _, p := range ps {
|
|
||||||
require.LessOrEqual(t, len(p), MaxPacketLen)
|
|
||||||
nh, h, _ := parse(t, p)
|
|
||||||
assert.Equal(t, header.Handshake, nh.Type)
|
|
||||||
assert.Equal(t, testSubtype, nh.Subtype)
|
|
||||||
assert.Equal(t, uint32(77), nh.RemoteIndex)
|
|
||||||
assert.Equal(t, uint64(2), nh.MessageCounter)
|
|
||||||
assert.Equal(t, uint32(1234), h.FragID)
|
|
||||||
assert.Equal(t, uint16(9800), h.MsgLen)
|
|
||||||
out = append(out, int(h.Index))
|
|
||||||
}
|
|
||||||
return out
|
|
||||||
}
|
|
||||||
|
|
||||||
now, later, err := s.Attempt(3)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, []int{0, 1, 2, 3, 4, 5, 6, 7, 8}, indexes(now))
|
|
||||||
assert.Equal(t, []int{9, 10, 11}, indexes(later))
|
|
||||||
|
|
||||||
// A retry offers only indexes the receiver has not seen.
|
|
||||||
now, later, err = s.Attempt(3)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, []int{12, 13, 14, 15, 16, 17, 18, 19, 20}, indexes(now))
|
|
||||||
assert.Equal(t, []int{21, 22, 23}, indexes(later))
|
|
||||||
|
|
||||||
// A sender rebuilt from the same message resumes where it was told to.
|
|
||||||
s2, err := NewSender(msg, testSubtype, 77, 2, 1234)
|
|
||||||
require.NoError(t, err)
|
|
||||||
s2.SetNext(s.Next())
|
|
||||||
now2, _, err := s2.Attempt(0)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, []int{24, 25, 26, 27, 28, 29, 30, 31, 32}, indexes(now2))
|
|
||||||
s2.SetNext(-1)
|
|
||||||
assert.Equal(t, 255, s2.Next())
|
|
||||||
|
|
||||||
// A cookie rides on every later packet, which still fits MaxPacketLen even
|
|
||||||
// with a full size symbol.
|
|
||||||
full, err := NewSender(make([]byte, 2*MaxSymbolSize), testSubtype, 0, 1, 9)
|
|
||||||
require.NoError(t, err)
|
|
||||||
full.SetCookie(Cookie{1, 2, 3})
|
|
||||||
pkts, _, err := full.Attempt(1)
|
|
||||||
require.NoError(t, err)
|
|
||||||
for _, p := range pkts {
|
|
||||||
assert.Len(t, p, MaxPacketLen)
|
|
||||||
_, h, _ := parse(t, p)
|
|
||||||
assert.True(t, h.HasCookie())
|
|
||||||
assert.Equal(t, Cookie{1, 2, 3}, h.Cookie)
|
|
||||||
}
|
|
||||||
|
|
||||||
// Indexes wrap once the space is used up.
|
|
||||||
for range 19 {
|
|
||||||
_, _, err = s.Attempt(3)
|
|
||||||
require.NoError(t, err)
|
|
||||||
}
|
|
||||||
now, _, err = s.Attempt(3)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, []int{252, 253, 254, 255, 0, 1, 2, 3, 4}, indexes(now))
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestLossy runs whole messages through heavy loss, reordering and duplication,
|
|
||||||
// merging across attempts, and checks the table ends empty.
|
|
||||||
func TestLossy(t *testing.T) {
|
|
||||||
r := rand.New(rand.NewPCG(2, 2))
|
|
||||||
tb := NewTable[testKey, string](testConfig())
|
|
||||||
now := time.Unix(1000, 0)
|
|
||||||
|
|
||||||
for i := range 300 {
|
|
||||||
msg := randMsg(r, 1+r.IntN(16384))
|
|
||||||
fragID := uint32(i + 1)
|
|
||||||
s, err := NewSender(msg, testSubtype, 0, 1, fragID)
|
|
||||||
require.NoError(t, err)
|
|
||||||
|
|
||||||
var got *Result
|
|
||||||
for attempt := 0; got == nil; attempt++ {
|
|
||||||
require.Less(t, attempt, 20, "message never completed")
|
|
||||||
a, b, err := s.Attempt(DefaultRepair(s.Layout().K))
|
|
||||||
require.NoError(t, err)
|
|
||||||
var pkts [][]byte
|
|
||||||
for _, p := range append(a, b...) {
|
|
||||||
if r.Float64() < 0.3 {
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
pkts = append(pkts, p)
|
|
||||||
if r.Float64() < 0.2 {
|
|
||||||
pkts = append(pkts, p)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
r.Shuffle(len(pkts), func(i, j int) { pkts[i], pkts[j] = pkts[j], pkts[i] })
|
|
||||||
|
|
||||||
for _, p := range pkts {
|
|
||||||
_, h, sym := parse(t, p)
|
|
||||||
res, err := tb.Add(testKey{"a", h.FragID}, "a", now, h, sym)
|
|
||||||
require.NoError(t, err)
|
|
||||||
if res != nil {
|
|
||||||
// The table keeps no memory of completed messages, so a late
|
|
||||||
// duplicate can complete one again; the handshake layer
|
|
||||||
// recognises the repeat.
|
|
||||||
require.True(t, bytes.Equal(msg, res.Msg))
|
|
||||||
got = res
|
|
||||||
}
|
|
||||||
checkInvariants(t, tb)
|
|
||||||
}
|
|
||||||
now = now.Add(100 * time.Millisecond)
|
|
||||||
}
|
|
||||||
require.Positive(t, got.Received)
|
|
||||||
// Late fragments of a completed message start a fresh entry; drop it.
|
|
||||||
tb.Expire(now.Add(time.Hour))
|
|
||||||
}
|
|
||||||
assert.Zero(t, tb.Len())
|
|
||||||
assert.Zero(t, tb.Bytes())
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestConcurrent spreads each message's fragments across goroutines, as
|
|
||||||
// multiple UDP reader routines would.
|
|
||||||
func TestConcurrent(t *testing.T) {
|
|
||||||
tb := NewTable[testKey, string](testConfig())
|
|
||||||
now := time.Unix(1000, 0)
|
|
||||||
r := rand.New(rand.NewPCG(3, 3))
|
|
||||||
|
|
||||||
const msgs = 50
|
|
||||||
want := make(map[uint32][]byte, msgs)
|
|
||||||
var pkts [][]byte
|
|
||||||
for id := uint32(1); id <= msgs; id++ {
|
|
||||||
msg := randMsg(r, 1+r.IntN(16384))
|
|
||||||
want[id] = msg
|
|
||||||
s, err := NewSender(msg, testSubtype, 0, 1, id)
|
|
||||||
require.NoError(t, err)
|
|
||||||
a, b, err := s.Attempt(DefaultRepair(s.Layout().K))
|
|
||||||
require.NoError(t, err)
|
|
||||||
pkts = append(pkts, a...)
|
|
||||||
pkts = append(pkts, b...)
|
|
||||||
}
|
|
||||||
r.Shuffle(len(pkts), func(i, j int) { pkts[i], pkts[j] = pkts[j], pkts[i] })
|
|
||||||
|
|
||||||
var mu sync.Mutex
|
|
||||||
done := map[uint32]bool{}
|
|
||||||
var wg sync.WaitGroup
|
|
||||||
for w := range 8 {
|
|
||||||
wg.Go(func() {
|
|
||||||
for i := w; i < len(pkts); i += 8 {
|
|
||||||
h, sym, err := Parse(pkts[i][16:])
|
|
||||||
if err != nil {
|
|
||||||
t.Error(err)
|
|
||||||
return
|
|
||||||
}
|
|
||||||
src := string(rune('a' + h.FragID))
|
|
||||||
res, err := tb.Add(testKey{src, h.FragID}, src, now, h, sym)
|
|
||||||
if err != nil {
|
|
||||||
t.Error(err)
|
|
||||||
return
|
|
||||||
}
|
|
||||||
if res != nil {
|
|
||||||
if !bytes.Equal(want[h.FragID], res.Msg) {
|
|
||||||
t.Errorf("message %d decoded wrong", h.FragID)
|
|
||||||
}
|
|
||||||
mu.Lock()
|
|
||||||
done[h.FragID] = true
|
|
||||||
mu.Unlock()
|
|
||||||
}
|
|
||||||
}
|
|
||||||
})
|
|
||||||
}
|
|
||||||
wg.Wait()
|
|
||||||
assert.Len(t, done, msgs)
|
|
||||||
checkInvariants(t, tb)
|
|
||||||
}
|
|
||||||
|
|
||||||
func firstFragment(t *testing.T, msgLen int, fragID uint32) (Header, []byte) {
|
|
||||||
t.Helper()
|
|
||||||
s, err := NewSender(make([]byte, msgLen), testSubtype, 0, 1, fragID)
|
|
||||||
require.NoError(t, err)
|
|
||||||
now, _, err := s.Attempt(0)
|
|
||||||
require.NoError(t, err)
|
|
||||||
_, h, sym := parse(t, now[0])
|
|
||||||
return h, sym
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestTableLimits(t *testing.T) {
|
|
||||||
now := time.Unix(1000, 0)
|
|
||||||
|
|
||||||
t.Run("max message length", func(t *testing.T) {
|
|
||||||
tb := NewTable[testKey, string](testConfig())
|
|
||||||
h, sym := firstFragment(t, 16385, 1)
|
|
||||||
_, err := tb.Add(testKey{"a", 1}, "a", now, h, sym)
|
|
||||||
require.ErrorIs(t, err, ErrTooLarge)
|
|
||||||
assert.Zero(t, tb.Len())
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("per source quota", func(t *testing.T) {
|
|
||||||
cfg := testConfig()
|
|
||||||
cfg.MaxPerSource = 2
|
|
||||||
tb := NewTable[testKey, string](cfg)
|
|
||||||
for id := uint32(1); id <= 3; id++ {
|
|
||||||
h, sym := firstFragment(t, 5000, id)
|
|
||||||
_, err := tb.Add(testKey{"a", id}, "a", now, h, sym)
|
|
||||||
if id <= 2 {
|
|
||||||
require.NoError(t, err)
|
|
||||||
} else {
|
|
||||||
require.ErrorIs(t, err, ErrSourceQuota)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
h, sym := firstFragment(t, 5000, 4)
|
|
||||||
_, err := tb.Add(testKey{"b", 4}, "b", now, h, sym)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, 3, tb.Len())
|
|
||||||
checkInvariants(t, tb)
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("max entries evicts", func(t *testing.T) {
|
|
||||||
cfg := testConfig()
|
|
||||||
cfg.MaxEntries = 4
|
|
||||||
tb := NewTable[testKey, string](cfg)
|
|
||||||
for id := uint32(1); id <= 10; id++ {
|
|
||||||
h, sym := firstFragment(t, 5000, id)
|
|
||||||
src := string(rune('a' + id))
|
|
||||||
_, err := tb.Add(testKey{src, id}, src, now, h, sym)
|
|
||||||
require.NoError(t, err)
|
|
||||||
checkInvariants(t, tb)
|
|
||||||
}
|
|
||||||
assert.Equal(t, 4, tb.Len())
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("max bytes evicts others", func(t *testing.T) {
|
|
||||||
cfg := testConfig()
|
|
||||||
cfg.MaxBytes = 3 * 1000
|
|
||||||
tb := NewTable[testKey, string](cfg)
|
|
||||||
for id := uint32(1); id <= 10; id++ {
|
|
||||||
h, sym := firstFragment(t, 5000, id) // 5 symbols of 1000
|
|
||||||
src := string(rune('a' + id))
|
|
||||||
_, err := tb.Add(testKey{src, id}, src, now, h, sym)
|
|
||||||
require.NoError(t, err)
|
|
||||||
checkInvariants(t, tb)
|
|
||||||
}
|
|
||||||
assert.Equal(t, 3000, tb.Bytes())
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("no room removes new entry", func(t *testing.T) {
|
|
||||||
cfg := testConfig()
|
|
||||||
cfg.MaxBytes = 500
|
|
||||||
tb := NewTable[testKey, string](cfg)
|
|
||||||
h, sym := firstFragment(t, 5000, 1)
|
|
||||||
_, err := tb.Add(testKey{"a", 1}, "a", now, h, sym)
|
|
||||||
require.ErrorIs(t, err, ErrNoRoom)
|
|
||||||
assert.Zero(t, tb.Len())
|
|
||||||
checkInvariants(t, tb)
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("duplicates are not charged", func(t *testing.T) {
|
|
||||||
tb := NewTable[testKey, string](testConfig())
|
|
||||||
h, sym := firstFragment(t, 5000, 1)
|
|
||||||
for range 5 {
|
|
||||||
_, err := tb.Add(testKey{"a", 1}, "a", now, h, sym)
|
|
||||||
require.NoError(t, err)
|
|
||||||
}
|
|
||||||
assert.Equal(t, 1000, tb.Bytes())
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("mismatch drops the entry", func(t *testing.T) {
|
|
||||||
tb := NewTable[testKey, string](testConfig())
|
|
||||||
h, sym := firstFragment(t, 5000, 1)
|
|
||||||
_, err := tb.Add(testKey{"a", 1}, "a", now, h, sym)
|
|
||||||
require.NoError(t, err)
|
|
||||||
|
|
||||||
h2, sym2 := firstFragment(t, 6000, 1)
|
|
||||||
_, err = tb.Add(testKey{"a", 1}, "a", now, h2, sym2)
|
|
||||||
require.ErrorIs(t, err, ErrMismatch)
|
|
||||||
assert.Zero(t, tb.Len())
|
|
||||||
assert.Zero(t, tb.Bytes())
|
|
||||||
checkInvariants(t, tb)
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("load", func(t *testing.T) {
|
|
||||||
cfg := testConfig()
|
|
||||||
cfg.MaxEntries = 4
|
|
||||||
cfg.MaxBytes = 10000
|
|
||||||
tb := NewTable[testKey, string](cfg)
|
|
||||||
assert.Zero(t, tb.Load())
|
|
||||||
h, sym := firstFragment(t, 5000, 1)
|
|
||||||
_, err := tb.Add(testKey{"a", 1}, "a", now, h, sym)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.InDelta(t, 0.25, tb.Load(), 0.001, "one of four entries")
|
|
||||||
h, sym = firstFragment(t, 5000, 2)
|
|
||||||
_, err = tb.Add(testKey{"b", 2}, "b", now, h, sym)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.InDelta(t, 0.5, tb.Load(), 0.001)
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("ttl", func(t *testing.T) {
|
|
||||||
tb := NewTable[testKey, string](testConfig())
|
|
||||||
s, err := NewSender(make([]byte, 5000), testSubtype, 0, 1, 1)
|
|
||||||
require.NoError(t, err)
|
|
||||||
pkts, _, err := s.Attempt(0)
|
|
||||||
require.NoError(t, err)
|
|
||||||
|
|
||||||
_, h, sym := parse(t, pkts[0])
|
|
||||||
_, err = tb.Add(testKey{"a", 1}, "a", now, h, sym)
|
|
||||||
require.NoError(t, err)
|
|
||||||
|
|
||||||
// Activity within the TTL keeps the entry and slides its deadline.
|
|
||||||
_, h, sym = parse(t, pkts[1])
|
|
||||||
_, err = tb.Add(testKey{"a", 1}, "a", now.Add(1500*time.Millisecond), h, sym)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, 2000, tb.Bytes())
|
|
||||||
|
|
||||||
tb.Expire(now.Add(3 * time.Second))
|
|
||||||
assert.Equal(t, 1, tb.Len())
|
|
||||||
|
|
||||||
// A stale entry is restarted rather than merged.
|
|
||||||
_, h, sym = parse(t, pkts[2])
|
|
||||||
_, err = tb.Add(testKey{"a", 1}, "a", now.Add(10*time.Second), h, sym)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, 1000, tb.Bytes())
|
|
||||||
|
|
||||||
tb.Expire(now.Add(time.Minute))
|
|
||||||
assert.Zero(t, tb.Len())
|
|
||||||
checkInvariants(t, tb)
|
|
||||||
})
|
|
||||||
}
|
|
||||||
|
|
||||||
func FuzzParse(f *testing.F) {
|
|
||||||
f.Add(append(Header{FragID: 1, MsgLen: 3000}.Encode(nil), make([]byte, 1000)...))
|
|
||||||
f.Add([]byte{0, 0, 0, 1, 0, 1, 0, 0, 7})
|
|
||||||
f.Fuzz(func(t *testing.T, b []byte) {
|
|
||||||
h, sym, err := Parse(b)
|
|
||||||
if err != nil {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
require.Equal(t, b, append(h.Encode(nil), sym...))
|
|
||||||
l, err := h.Layout()
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.LessOrEqual(t, l.SymbolSize, MaxSymbolSize)
|
|
||||||
})
|
|
||||||
}
|
|
||||||
|
|
||||||
// FuzzTable drives a small table with arbitrary fragments and checks its
|
|
||||||
// bookkeeping after every step.
|
|
||||||
func FuzzTable(f *testing.F) {
|
|
||||||
f.Add([]byte{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12})
|
|
||||||
f.Fuzz(func(t *testing.T, ops []byte) {
|
|
||||||
tb := NewTable[testKey, string](TableConfig{
|
|
||||||
MaxBytes: 4000,
|
|
||||||
MaxEntries: 3,
|
|
||||||
MaxPerSource: 2,
|
|
||||||
MaxMsgLen: 6000,
|
|
||||||
TTL: time.Second,
|
|
||||||
})
|
|
||||||
now := time.Unix(0, 0)
|
|
||||||
for len(ops) >= 4 {
|
|
||||||
src := string(rune('a' + ops[0]%4))
|
|
||||||
fragID := uint32(ops[1]%5) + 1
|
|
||||||
msgLen := uint16(ops[2])*32 + 1
|
|
||||||
index := ops[3]
|
|
||||||
ops = ops[4:]
|
|
||||||
|
|
||||||
h := Header{FragID: fragID, MsgLen: msgLen, Index: index}
|
|
||||||
l, err := h.Layout()
|
|
||||||
require.NoError(t, err)
|
|
||||||
sym := make([]byte, l.SymbolSize)
|
|
||||||
if index%7 == 0 {
|
|
||||||
now = now.Add(600 * time.Millisecond)
|
|
||||||
tb.Expire(now)
|
|
||||||
}
|
|
||||||
res, err := tb.Add(testKey{src, fragID}, src, now, h, sym)
|
|
||||||
if res != nil {
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.Len(t, res.Msg, int(msgLen))
|
|
||||||
}
|
|
||||||
checkInvariants(t, tb)
|
|
||||||
}
|
|
||||||
})
|
|
||||||
}
|
|
||||||
@@ -1,118 +0,0 @@
|
|||||||
package fragment
|
|
||||||
|
|
||||||
import (
|
|
||||||
"errors"
|
|
||||||
"math"
|
|
||||||
|
|
||||||
"github.com/slackhq/nebula/handshake/fec"
|
|
||||||
"github.com/slackhq/nebula/header"
|
|
||||||
)
|
|
||||||
|
|
||||||
// DefaultRepair is the starting number of repair symbols per attempt for a
|
|
||||||
// message of k data symbols. Small messages get proportionally more repair.
|
|
||||||
func DefaultRepair(k int) int {
|
|
||||||
return max(2, (k+2)/3)
|
|
||||||
}
|
|
||||||
|
|
||||||
// Sender produces the fragment packets of one outgoing handshake message.
|
|
||||||
//
|
|
||||||
// The first attempt sends the K data symbols followed by repair symbols. Every
|
|
||||||
// later attempt sends symbols with indexes the receiver has not been offered yet,
|
|
||||||
// so whatever it already holds still counts toward K. Symbols are a deterministic
|
|
||||||
// function of the message, which keeps retransmits idempotent. Once all
|
|
||||||
// fec.MaxSymbols indexes are used the sequence wraps and repeats.
|
|
||||||
//
|
|
||||||
// A Sender is not safe for concurrent use.
|
|
||||||
type Sender struct {
|
|
||||||
enc *fec.Encoder
|
|
||||||
subtype header.MessageSubType
|
|
||||||
remoteIndex uint32
|
|
||||||
counter uint64
|
|
||||||
fragID uint32
|
|
||||||
next int
|
|
||||||
cookie *Cookie
|
|
||||||
}
|
|
||||||
|
|
||||||
// NewSender prepares msg for sending. subtype, remoteIndex and counter fill the
|
|
||||||
// Nebula header of every fragment; fragID is the sender's local index.
|
|
||||||
func NewSender(msg []byte, subtype header.MessageSubType, remoteIndex uint32, counter uint64, fragID uint32) (*Sender, error) {
|
|
||||||
if len(msg) == 0 || len(msg) > math.MaxUint16 {
|
|
||||||
return nil, ErrMsgLen
|
|
||||||
}
|
|
||||||
if fragID == 0 {
|
|
||||||
return nil, ErrFragID
|
|
||||||
}
|
|
||||||
enc, err := fec.NewEncoder(msg, MaxSymbolSize)
|
|
||||||
if err != nil {
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
return &Sender{
|
|
||||||
enc: enc,
|
|
||||||
subtype: subtype,
|
|
||||||
remoteIndex: remoteIndex,
|
|
||||||
counter: counter,
|
|
||||||
fragID: fragID,
|
|
||||||
}, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
func (s *Sender) Layout() fec.Layout {
|
|
||||||
return s.enc.Layout()
|
|
||||||
}
|
|
||||||
|
|
||||||
// SetNext sets the index the next attempt starts from, so a sender rebuilt from
|
|
||||||
// a cached message can carry on offering fresh symbols.
|
|
||||||
func (s *Sender) SetNext(index int) {
|
|
||||||
s.next = ((index % fec.MaxSymbols) + fec.MaxSymbols) % fec.MaxSymbols
|
|
||||||
}
|
|
||||||
|
|
||||||
// SetCookie attaches a cookie from a responder under load to every later packet.
|
|
||||||
func (s *Sender) SetCookie(c Cookie) {
|
|
||||||
s.cookie = &c
|
|
||||||
}
|
|
||||||
|
|
||||||
// Next returns the index the next attempt starts from.
|
|
||||||
func (s *Sender) Next() int {
|
|
||||||
return s.next
|
|
||||||
}
|
|
||||||
|
|
||||||
// Attempt returns the packets for one transmission attempt carrying K+repair
|
|
||||||
// symbols. now should be sent immediately and later after the repair delay, so
|
|
||||||
// a tail drop at the end of the first burst does not also take the repair.
|
|
||||||
func (s *Sender) Attempt(repair int) (now, later [][]byte, err error) {
|
|
||||||
if repair < 0 {
|
|
||||||
return nil, nil, errors.New("negative repair count")
|
|
||||||
}
|
|
||||||
k := s.enc.Layout().K
|
|
||||||
now = make([][]byte, 0, k)
|
|
||||||
later = make([][]byte, 0, repair)
|
|
||||||
for i := range k + repair {
|
|
||||||
p, err := s.packet(s.next)
|
|
||||||
if err != nil {
|
|
||||||
return nil, nil, err
|
|
||||||
}
|
|
||||||
s.next = (s.next + 1) % fec.MaxSymbols
|
|
||||||
if i < k {
|
|
||||||
now = append(now, p)
|
|
||||||
} else {
|
|
||||||
later = append(later, p)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return now, later, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
func (s *Sender) packet(index int) ([]byte, error) {
|
|
||||||
l := s.enc.Layout()
|
|
||||||
p := make([]byte, header.Len, header.Len+HeaderLen+CookieLen+l.SymbolSize)
|
|
||||||
header.Encode(p, header.Version, header.Handshake, s.subtype, s.remoteIndex, s.counter)
|
|
||||||
h := Header{
|
|
||||||
FragID: s.fragID,
|
|
||||||
MsgLen: uint16(l.MsgLen),
|
|
||||||
Index: uint8(index),
|
|
||||||
}
|
|
||||||
if s.cookie != nil {
|
|
||||||
h.Flags |= FlagCookie
|
|
||||||
h.Cookie = *s.cookie
|
|
||||||
}
|
|
||||||
p = h.Encode(p)
|
|
||||||
return s.enc.Symbol(p, index)
|
|
||||||
}
|
|
||||||
@@ -1,220 +0,0 @@
|
|||||||
package fragment
|
|
||||||
|
|
||||||
import (
|
|
||||||
"errors"
|
|
||||||
"math/rand/v2"
|
|
||||||
"sync"
|
|
||||||
"time"
|
|
||||||
)
|
|
||||||
|
|
||||||
var (
|
|
||||||
ErrTooLarge = errors.New("fragmented message exceeds the size limit")
|
|
||||||
ErrSourceQuota = errors.New("source has too many messages in progress")
|
|
||||||
ErrNoRoom = errors.New("no room for fragment")
|
|
||||||
)
|
|
||||||
|
|
||||||
// TableConfig bounds a Table.
|
|
||||||
type TableConfig struct {
|
|
||||||
MaxBytes int // symbol bytes held across all entries
|
|
||||||
MaxEntries int // messages in progress across all sources
|
|
||||||
MaxPerSource int // messages in progress per source
|
|
||||||
MaxMsgLen int // largest message accepted
|
|
||||||
TTL time.Duration // an entry idle this long is dropped
|
|
||||||
}
|
|
||||||
|
|
||||||
// Table reassembles messages from senders that have not authenticated yet, the
|
|
||||||
// responder's view of msg1. Every resource is capped. When a cap is hit a
|
|
||||||
// random entry is evicted; random eviction is harder to aim than LRU, which a
|
|
||||||
// flood can use to flush specific entries.
|
|
||||||
//
|
|
||||||
// K identifies one message, typically the source plus FragID. S identifies the
|
|
||||||
// source for quotas, typically the address masked to /32 or /64.
|
|
||||||
//
|
|
||||||
// A Table is safe for concurrent use.
|
|
||||||
type Table[K, S comparable] struct {
|
|
||||||
mu sync.Mutex
|
|
||||||
cfg TableConfig
|
|
||||||
entries map[K]*tableEntry[K, S]
|
|
||||||
order []K
|
|
||||||
perSource map[S]int
|
|
||||||
bytes int
|
|
||||||
}
|
|
||||||
|
|
||||||
type tableEntry[K, S comparable] struct {
|
|
||||||
a *Assembly
|
|
||||||
source S
|
|
||||||
lastSeen time.Time
|
|
||||||
pos int
|
|
||||||
}
|
|
||||||
|
|
||||||
func NewTable[K, S comparable](cfg TableConfig) *Table[K, S] {
|
|
||||||
return &Table[K, S]{
|
|
||||||
cfg: cfg,
|
|
||||||
entries: make(map[K]*tableEntry[K, S]),
|
|
||||||
perSource: make(map[S]int),
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// Result describes a completed message.
|
|
||||||
type Result struct {
|
|
||||||
Msg []byte // the decoded message
|
|
||||||
Received int // packet bytes received for it, for the amplification budget
|
|
||||||
}
|
|
||||||
|
|
||||||
// Add records a fragment parsed by Parse. When the message is complete its entry
|
|
||||||
// is removed and the result returned; otherwise the result is nil. A decode
|
|
||||||
// error means the message is lost and must be retransmitted.
|
|
||||||
func (t *Table[K, S]) Add(key K, source S, now time.Time, h Header, sym []byte) (*Result, error) {
|
|
||||||
if int(h.MsgLen) > t.cfg.MaxMsgLen {
|
|
||||||
return nil, ErrTooLarge
|
|
||||||
}
|
|
||||||
|
|
||||||
t.mu.Lock()
|
|
||||||
e, ok := t.entries[key]
|
|
||||||
if ok && now.Sub(e.lastSeen) > t.cfg.TTL {
|
|
||||||
t.remove(key, e)
|
|
||||||
ok = false
|
|
||||||
}
|
|
||||||
if !ok {
|
|
||||||
var err error
|
|
||||||
e, err = t.insert(key, source, h)
|
|
||||||
if err != nil {
|
|
||||||
t.mu.Unlock()
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
}
|
|
||||||
e.lastSeen = now
|
|
||||||
|
|
||||||
if !t.makeRoom(key, e.a.wouldStore(h, sym)) {
|
|
||||||
if e.a.Stored() == 0 {
|
|
||||||
t.remove(key, e)
|
|
||||||
}
|
|
||||||
t.mu.Unlock()
|
|
||||||
return nil, ErrNoRoom
|
|
||||||
}
|
|
||||||
|
|
||||||
before := e.a.Stored()
|
|
||||||
ready, err := e.a.Add(h, sym)
|
|
||||||
t.bytes += e.a.Stored() - before
|
|
||||||
if err != nil || !ready {
|
|
||||||
if errors.Is(err, ErrMismatch) || (err != nil && e.a.Stored() == 0) {
|
|
||||||
t.remove(key, e)
|
|
||||||
}
|
|
||||||
t.mu.Unlock()
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
|
|
||||||
t.remove(key, e)
|
|
||||||
t.mu.Unlock()
|
|
||||||
|
|
||||||
msg, err := e.a.Decode()
|
|
||||||
if err != nil {
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
return &Result{Msg: msg, Received: e.a.Received()}, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
// Expire drops every entry idle for longer than the TTL.
|
|
||||||
func (t *Table[K, S]) Expire(now time.Time) {
|
|
||||||
t.mu.Lock()
|
|
||||||
defer t.mu.Unlock()
|
|
||||||
for i := 0; i < len(t.order); {
|
|
||||||
key := t.order[i]
|
|
||||||
e := t.entries[key]
|
|
||||||
if now.Sub(e.lastSeen) > t.cfg.TTL {
|
|
||||||
// remove swaps the last entry into position i, so look at i again.
|
|
||||||
t.remove(key, e)
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
i++
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// Len returns the number of messages in progress.
|
|
||||||
func (t *Table[K, S]) Len() int {
|
|
||||||
t.mu.Lock()
|
|
||||||
defer t.mu.Unlock()
|
|
||||||
return len(t.entries)
|
|
||||||
}
|
|
||||||
|
|
||||||
// Load returns how full the table is, from 0 to 1, by whichever of its byte and
|
|
||||||
// entry limits is closer.
|
|
||||||
func (t *Table[K, S]) Load() float64 {
|
|
||||||
t.mu.Lock()
|
|
||||||
defer t.mu.Unlock()
|
|
||||||
return max(float64(t.bytes)/float64(t.cfg.MaxBytes), float64(len(t.entries))/float64(t.cfg.MaxEntries))
|
|
||||||
}
|
|
||||||
|
|
||||||
// Bytes returns the number of symbol bytes held.
|
|
||||||
func (t *Table[K, S]) Bytes() int {
|
|
||||||
t.mu.Lock()
|
|
||||||
defer t.mu.Unlock()
|
|
||||||
return t.bytes
|
|
||||||
}
|
|
||||||
|
|
||||||
func (t *Table[K, S]) insert(key K, source S, h Header) (*tableEntry[K, S], error) {
|
|
||||||
if t.perSource[source] >= t.cfg.MaxPerSource {
|
|
||||||
return nil, ErrSourceQuota
|
|
||||||
}
|
|
||||||
a, err := NewAssembly(h)
|
|
||||||
if err != nil {
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
for len(t.entries) >= t.cfg.MaxEntries {
|
|
||||||
if !t.evictRandom(nil) {
|
|
||||||
return nil, ErrNoRoom
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
e := &tableEntry[K, S]{a: a, source: source, pos: len(t.order)}
|
|
||||||
t.entries[key] = e
|
|
||||||
t.order = append(t.order, key)
|
|
||||||
t.perSource[source]++
|
|
||||||
return e, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
// makeRoom evicts random entries other than keep until n more bytes fit.
|
|
||||||
func (t *Table[K, S]) makeRoom(keep K, n int) bool {
|
|
||||||
for t.bytes+n > t.cfg.MaxBytes {
|
|
||||||
if !t.evictRandom(&keep) {
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
|
|
||||||
func (t *Table[K, S]) evictRandom(keep *K) bool {
|
|
||||||
candidates := len(t.order)
|
|
||||||
if keep != nil {
|
|
||||||
if _, ok := t.entries[*keep]; ok {
|
|
||||||
candidates--
|
|
||||||
}
|
|
||||||
}
|
|
||||||
if candidates <= 0 {
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
for {
|
|
||||||
key := t.order[rand.IntN(len(t.order))]
|
|
||||||
if keep != nil && key == *keep {
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
t.remove(key, t.entries[key])
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
func (t *Table[K, S]) remove(key K, e *tableEntry[K, S]) {
|
|
||||||
last := len(t.order) - 1
|
|
||||||
moved := t.order[last]
|
|
||||||
t.order[e.pos] = moved
|
|
||||||
t.entries[moved].pos = e.pos
|
|
||||||
t.order = t.order[:last]
|
|
||||||
delete(t.entries, key)
|
|
||||||
|
|
||||||
t.bytes -= e.a.Stored()
|
|
||||||
if t.perSource[e.source] <= 1 {
|
|
||||||
delete(t.perSource, e.source)
|
|
||||||
} else {
|
|
||||||
t.perSource[e.source]--
|
|
||||||
}
|
|
||||||
}
|
|
||||||
@@ -1,121 +0,0 @@
|
|||||||
// Package fragment carries handshake messages that do not fit in one UDP
|
|
||||||
// packet. A message is Reed-Solomon coded into equally sized symbols (see
|
|
||||||
// handshake/fec) and each symbol travels in its own packet:
|
|
||||||
//
|
|
||||||
// Nebula header (16) | Fragment header (8) | [cookie (16)] | symbol
|
|
||||||
//
|
|
||||||
// The fragment header is FragID u32 | MsgLen u16 | Index u8 | Flags u8, all big
|
|
||||||
// endian. Both ends derive the symbol layout from MsgLen, so any MsgLen-derived
|
|
||||||
// value never has to be sent. FlagCookie marks a cookie a responder under load
|
|
||||||
// asked for; room for it is always reserved, so a fragment never outgrows
|
|
||||||
// MaxPacketLen.
|
|
||||||
package fragment
|
|
||||||
|
|
||||||
import (
|
|
||||||
"encoding/binary"
|
|
||||||
"errors"
|
|
||||||
|
|
||||||
"github.com/slackhq/nebula/handshake/fec"
|
|
||||||
"github.com/slackhq/nebula/header"
|
|
||||||
)
|
|
||||||
|
|
||||||
const (
|
|
||||||
// HeaderLen is the size of the fragment header that follows the Nebula header.
|
|
||||||
HeaderLen = 8
|
|
||||||
|
|
||||||
// CookieLen is the size of the cookie a fragment carries when FlagCookie is set.
|
|
||||||
CookieLen = 16
|
|
||||||
|
|
||||||
// FlagCookie marks a fragment that carries a cookie after its header.
|
|
||||||
FlagCookie uint8 = 0x01
|
|
||||||
|
|
||||||
// MaxPacketLen bounds every fragment packet, Nebula header included. A relayed
|
|
||||||
// fragment gains a 16 byte header and a 16 byte tag, which lands exactly on
|
|
||||||
// the 1232 byte UDP payload available on an IPv6 minimum MTU path.
|
|
||||||
MaxPacketLen = 1200
|
|
||||||
|
|
||||||
// MaxSymbolSize is the largest symbol that fits in MaxPacketLen alongside a cookie.
|
|
||||||
MaxSymbolSize = MaxPacketLen - header.Len - HeaderLen - CookieLen
|
|
||||||
)
|
|
||||||
|
|
||||||
var (
|
|
||||||
ErrShortFragment = errors.New("fragment is too short")
|
|
||||||
ErrFragID = errors.New("fragment has a zero FragID")
|
|
||||||
ErrMsgLen = errors.New("fragment has a zero MsgLen")
|
|
||||||
ErrFlags = errors.New("fragment has reserved flags set")
|
|
||||||
ErrNoCookie = errors.New("fragment is too short for its cookie")
|
|
||||||
ErrSymbolSize = errors.New("fragment symbol size does not match its MsgLen")
|
|
||||||
)
|
|
||||||
|
|
||||||
// Cookie proves a sender received a responder's reply at its address.
|
|
||||||
type Cookie [CookieLen]byte
|
|
||||||
|
|
||||||
// Header is the fragment header.
|
|
||||||
type Header struct {
|
|
||||||
FragID uint32 // the sender's local index for this handshake, never zero
|
|
||||||
MsgLen uint16 // length of the whole message
|
|
||||||
Index uint8 // symbol index, data below K and repair from K
|
|
||||||
Flags uint8 // FlagCookie, other bits reserved and zero
|
|
||||||
Cookie Cookie // valid when Flags has FlagCookie
|
|
||||||
}
|
|
||||||
|
|
||||||
func (h Header) HasCookie() bool {
|
|
||||||
return h.Flags&FlagCookie != 0
|
|
||||||
}
|
|
||||||
|
|
||||||
// Encode appends the header, and its cookie if it has one, to b.
|
|
||||||
func (h Header) Encode(b []byte) []byte {
|
|
||||||
b = binary.BigEndian.AppendUint32(b, h.FragID)
|
|
||||||
b = binary.BigEndian.AppendUint16(b, h.MsgLen)
|
|
||||||
b = append(b, h.Index, h.Flags)
|
|
||||||
if h.HasCookie() {
|
|
||||||
b = append(b, h.Cookie[:]...)
|
|
||||||
}
|
|
||||||
return b
|
|
||||||
}
|
|
||||||
|
|
||||||
// Layout returns the symbol layout the header's MsgLen implies.
|
|
||||||
func (h Header) Layout() (fec.Layout, error) {
|
|
||||||
return fec.NewLayout(int(h.MsgLen), MaxSymbolSize)
|
|
||||||
}
|
|
||||||
|
|
||||||
// Parse validates the bytes following the Nebula header and splits them into
|
|
||||||
// the fragment header and the symbol. The symbol aliases b.
|
|
||||||
func Parse(b []byte) (Header, []byte, error) {
|
|
||||||
if len(b) < HeaderLen {
|
|
||||||
return Header{}, nil, ErrShortFragment
|
|
||||||
}
|
|
||||||
h := Header{
|
|
||||||
FragID: binary.BigEndian.Uint32(b[0:4]),
|
|
||||||
MsgLen: binary.BigEndian.Uint16(b[4:6]),
|
|
||||||
Index: b[6],
|
|
||||||
Flags: b[7],
|
|
||||||
}
|
|
||||||
if h.FragID == 0 {
|
|
||||||
return Header{}, nil, ErrFragID
|
|
||||||
}
|
|
||||||
if h.MsgLen == 0 {
|
|
||||||
return Header{}, nil, ErrMsgLen
|
|
||||||
}
|
|
||||||
if h.Flags&^FlagCookie != 0 {
|
|
||||||
return Header{}, nil, ErrFlags
|
|
||||||
}
|
|
||||||
b = b[HeaderLen:]
|
|
||||||
if h.HasCookie() {
|
|
||||||
if len(b) < CookieLen {
|
|
||||||
return Header{}, nil, ErrNoCookie
|
|
||||||
}
|
|
||||||
copy(h.Cookie[:], b)
|
|
||||||
b = b[CookieLen:]
|
|
||||||
}
|
|
||||||
|
|
||||||
l, err := h.Layout()
|
|
||||||
if err != nil {
|
|
||||||
return Header{}, nil, err
|
|
||||||
}
|
|
||||||
sym := b
|
|
||||||
if len(sym) != l.SymbolSize {
|
|
||||||
return Header{}, nil, ErrSymbolSize
|
|
||||||
}
|
|
||||||
return h, sym, nil
|
|
||||||
}
|
|
||||||
@@ -24,9 +24,6 @@ message NebulaHandshakeDetails {
|
|||||||
uint64 Cookie = 4 [deprecated = true];
|
uint64 Cookie = 4 [deprecated = true];
|
||||||
uint64 Time = 5;
|
uint64 Time = 5;
|
||||||
uint32 CertVersion = 8;
|
uint32 CertVersion = 8;
|
||||||
// KEMKey is the initiator's ephemeral ML-KEM-1024 encapsulation key. It is
|
|
||||||
// only present in msg1 of the ix_psk2_mlkem1024 subtype.
|
|
||||||
bytes KEMKey = 9;
|
|
||||||
// reserved for WIP multiport
|
// reserved for WIP multiport
|
||||||
reserved 6, 7;
|
reserved 6, 7;
|
||||||
}
|
}
|
||||||
@@ -1,68 +0,0 @@
|
|||||||
package handshake
|
|
||||||
|
|
||||||
import (
|
|
||||||
"crypto/hkdf"
|
|
||||||
"crypto/mlkem"
|
|
||||||
"crypto/sha256"
|
|
||||||
"errors"
|
|
||||||
"fmt"
|
|
||||||
)
|
|
||||||
|
|
||||||
// kemPSKSalt separates the psk derivation from any other use of the secret.
|
|
||||||
const kemPSKSalt = "nebula ix_psk2_mlkem1024 v1"
|
|
||||||
|
|
||||||
var ErrInvalidKEMKey = errors.New("peer sent an invalid ML-KEM encapsulation key")
|
|
||||||
|
|
||||||
// kemPSK derives the noise psk from an ML-KEM shared secret. The ciphertext is
|
|
||||||
// bound in because, unlike the encapsulation key, it travels outside the noise
|
|
||||||
// transcript.
|
|
||||||
func kemPSK(sharedKey, ciphertext []byte) ([]byte, error) {
|
|
||||||
secret := make([]byte, 0, len(sharedKey)+len(ciphertext))
|
|
||||||
secret = append(secret, sharedKey...)
|
|
||||||
secret = append(secret, ciphertext...)
|
|
||||||
return hkdf.Extract(sha256.New, secret, []byte(kemPSKSalt))
|
|
||||||
}
|
|
||||||
|
|
||||||
// kemEncapsulate is the responder half: encapsulate to the initiator's key,
|
|
||||||
// install the psk, and remember the ciphertext to prefix the response with.
|
|
||||||
func (m *Machine) kemEncapsulate(encapsulationKey []byte) error {
|
|
||||||
ek, err := mlkem.NewEncapsulationKey1024(encapsulationKey)
|
|
||||||
if err != nil {
|
|
||||||
return fmt.Errorf("%w: %w", ErrInvalidKEMKey, err)
|
|
||||||
}
|
|
||||||
sharedKey, ct := ek.Encapsulate()
|
|
||||||
psk, err := kemPSK(sharedKey, ct)
|
|
||||||
if err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
if err := m.hs.SetPresharedKey(psk); err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
m.kemCiphertext = ct
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
// kemDecapsulate is the initiator half: recover the shared secret from the
|
|
||||||
// ciphertext prefixing the response and install the psk. It returns the rest of
|
|
||||||
// the message, which is the noise message.
|
|
||||||
func (m *Machine) kemDecapsulate(msg []byte) ([]byte, error) {
|
|
||||||
if len(msg) < mlkem.CiphertextSize1024 {
|
|
||||||
return nil, ErrPacketTooShort
|
|
||||||
}
|
|
||||||
if m.kemKey == nil {
|
|
||||||
return nil, errors.New("no ML-KEM decapsulation key for this handshake")
|
|
||||||
}
|
|
||||||
ct := msg[:mlkem.CiphertextSize1024]
|
|
||||||
sharedKey, err := m.kemKey.Decapsulate(ct)
|
|
||||||
if err != nil {
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
psk, err := kemPSK(sharedKey, ct)
|
|
||||||
if err != nil {
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
if err := m.hs.SetPresharedKey(psk); err != nil {
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
return msg[mlkem.CiphertextSize1024:], nil
|
|
||||||
}
|
|
||||||
@@ -1,208 +0,0 @@
|
|||||||
package handshake
|
|
||||||
|
|
||||||
import (
|
|
||||||
"bytes"
|
|
||||||
"crypto/mlkem"
|
|
||||||
"net/netip"
|
|
||||||
"testing"
|
|
||||||
"time"
|
|
||||||
|
|
||||||
"github.com/flynn/noise"
|
|
||||||
"github.com/slackhq/nebula/cert"
|
|
||||||
ct "github.com/slackhq/nebula/cert_test"
|
|
||||||
"github.com/slackhq/nebula/header"
|
|
||||||
"github.com/stretchr/testify/assert"
|
|
||||||
"github.com/stretchr/testify/require"
|
|
||||||
)
|
|
||||||
|
|
||||||
func newKEMMachine(t *testing.T, cs *testCertState, v CertVerifier, initiator bool, index uint32) *Machine {
|
|
||||||
t.Helper()
|
|
||||||
m, err := NewMachine(
|
|
||||||
cs.version, cs.getCredential, v,
|
|
||||||
func() (uint32, error) { return index, nil },
|
|
||||||
initiator, header.HandshakeIXPSK2MLKEM1024,
|
|
||||||
)
|
|
||||||
require.NoError(t, err)
|
|
||||||
return m
|
|
||||||
}
|
|
||||||
|
|
||||||
type kemFixture struct {
|
|
||||||
initCS, respCS *testCertState
|
|
||||||
v CertVerifier
|
|
||||||
}
|
|
||||||
|
|
||||||
func newKEMFixture(t *testing.T, cipher noise.CipherFunc) kemFixture {
|
|
||||||
ca, _, caKey, _ := ct.NewTestCaCert(
|
|
||||||
cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil,
|
|
||||||
)
|
|
||||||
return kemFixture{
|
|
||||||
initCS: newTestCertStateWithCipher(t, ca, caKey, "initiator", []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")}, cipher),
|
|
||||||
respCS: newTestCertStateWithCipher(t, ca, caKey, "responder", []netip.Prefix{netip.MustParsePrefix("10.0.0.2/24")}, cipher),
|
|
||||||
v: testVerifier(ct.NewTestCAPool(ca)),
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
func requireKeysMatch(t *testing.T, a, b *Result) {
|
|
||||||
t.Helper()
|
|
||||||
c, err := a.EKey.Encrypt(nil, nil, []byte("hello"))
|
|
||||||
require.NoError(t, err)
|
|
||||||
p, err := b.DKey.Decrypt(nil, nil, c)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, []byte("hello"), p)
|
|
||||||
|
|
||||||
c, err = b.EKey.Encrypt(nil, nil, []byte("world"))
|
|
||||||
require.NoError(t, err)
|
|
||||||
p, err = a.DKey.Decrypt(nil, nil, c)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, []byte("world"), p)
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestKEMHandshake(t *testing.T) {
|
|
||||||
for _, cipher := range []noise.CipherFunc{noise.CipherChaChaPoly, noise.CipherAESGCM} {
|
|
||||||
t.Run(cipher.CipherName(), func(t *testing.T) {
|
|
||||||
f := newKEMFixture(t, cipher)
|
|
||||||
initM := newKEMMachine(t, f.initCS, f.v, true, 1000)
|
|
||||||
respM := newKEMMachine(t, f.respCS, f.v, false, 2000)
|
|
||||||
|
|
||||||
msg1, err := initM.Initiate(nil)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, header.HandshakeIXPSK2MLKEM1024, header.MessageSubType(msg1[1]))
|
|
||||||
assert.Greater(t, len(msg1), header.Len+mlkem.EncapsulationKeySize1024)
|
|
||||||
|
|
||||||
msg2, respR, err := respM.ProcessPacket(nil, msg1)
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.NotNil(t, respR)
|
|
||||||
assert.Greater(t, len(msg2), header.Len+mlkem.CiphertextSize1024)
|
|
||||||
|
|
||||||
_, initR, err := initM.ProcessPacket(nil, msg2)
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.NotNil(t, initR)
|
|
||||||
|
|
||||||
assert.Equal(t, "responder", initR.RemoteCert.Certificate.Name())
|
|
||||||
assert.Equal(t, "initiator", respR.RemoteCert.Certificate.Name())
|
|
||||||
assert.Equal(t, uint32(2000), initR.RemoteIndex)
|
|
||||||
assert.Equal(t, uint32(1000), respR.RemoteIndex)
|
|
||||||
requireKeysMatch(t, initR, respR)
|
|
||||||
})
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestKEMSecretMatters checks the ML-KEM secret really reaches the transport
|
|
||||||
// keys: an initiator holding a different decapsulation key cannot complete even
|
|
||||||
// though every DH input is genuine.
|
|
||||||
func TestKEMSecretMatters(t *testing.T) {
|
|
||||||
f := newKEMFixture(t, noise.CipherChaChaPoly)
|
|
||||||
initM := newKEMMachine(t, f.initCS, f.v, true, 1000)
|
|
||||||
respM := newKEMMachine(t, f.respCS, f.v, false, 2000)
|
|
||||||
|
|
||||||
msg1, err := initM.Initiate(nil)
|
|
||||||
require.NoError(t, err)
|
|
||||||
msg2, _, err := respM.ProcessPacket(nil, msg1)
|
|
||||||
require.NoError(t, err)
|
|
||||||
|
|
||||||
other, err := mlkem.GenerateKey1024()
|
|
||||||
require.NoError(t, err)
|
|
||||||
initM.kemKey = other
|
|
||||||
|
|
||||||
_, res, err := initM.ProcessPacket(nil, msg2)
|
|
||||||
require.Error(t, err)
|
|
||||||
assert.Nil(t, res)
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestKEMTamperedCiphertext(t *testing.T) {
|
|
||||||
f := newKEMFixture(t, noise.CipherChaChaPoly)
|
|
||||||
initM := newKEMMachine(t, f.initCS, f.v, true, 1000)
|
|
||||||
respM := newKEMMachine(t, f.respCS, f.v, false, 2000)
|
|
||||||
|
|
||||||
msg1, err := initM.Initiate(nil)
|
|
||||||
require.NoError(t, err)
|
|
||||||
msg2, respR, err := respM.ProcessPacket(nil, msg1)
|
|
||||||
require.NoError(t, err)
|
|
||||||
|
|
||||||
t.Run("truncated", func(t *testing.T) {
|
|
||||||
_, res, err := initM.ProcessPacket(nil, msg2[:header.Len+mlkem.CiphertextSize1024-1])
|
|
||||||
require.ErrorIs(t, err, ErrPacketTooShort)
|
|
||||||
assert.Nil(t, res)
|
|
||||||
assert.False(t, initM.Failed())
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("flipped ciphertext bit", func(t *testing.T) {
|
|
||||||
bad := bytes.Clone(msg2)
|
|
||||||
bad[header.Len+10] ^= 1
|
|
||||||
_, res, err := initM.ProcessPacket(nil, bad)
|
|
||||||
require.Error(t, err)
|
|
||||||
assert.Nil(t, res)
|
|
||||||
assert.False(t, initM.Failed(), "a forged ciphertext must not kill the handshake")
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("genuine response still completes", func(t *testing.T) {
|
|
||||||
_, initR, err := initM.ProcessPacket(nil, msg2)
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.NotNil(t, initR)
|
|
||||||
requireKeysMatch(t, initR, respR)
|
|
||||||
})
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestKEMBadMsg1 drives processPayload by hand. With the psk modifier msg1's
|
|
||||||
// payload is encrypted under a key derived from the public ephemeral, so a
|
|
||||||
// forged payload would need re-encrypting; the parsing rules are what matter.
|
|
||||||
func TestKEMBadMsg1(t *testing.T) {
|
|
||||||
f := newKEMFixture(t, noise.CipherChaChaPoly)
|
|
||||||
msg1Flags := subtypeInfos[header.HandshakeIXPSK2MLKEM1024].msgs[0]
|
|
||||||
cert := f.initCS.creds[cert.Version2]
|
|
||||||
payload := func(kemKey []byte) []byte {
|
|
||||||
return MarshalPayload(nil, Payload{
|
|
||||||
Cert: cert.Bytes,
|
|
||||||
CertVersion: uint32(cert.Cert.Version()),
|
|
||||||
InitiatorIndex: 1000,
|
|
||||||
Time: 1,
|
|
||||||
KEMKey: kemKey,
|
|
||||||
})
|
|
||||||
}
|
|
||||||
dk, err := mlkem.GenerateKey1024()
|
|
||||||
require.NoError(t, err)
|
|
||||||
|
|
||||||
t.Run("missing KEM key", func(t *testing.T) {
|
|
||||||
m := newKEMMachine(t, f.respCS, f.v, false, 2000)
|
|
||||||
err := m.processPayload(payload(nil), msg1Flags)
|
|
||||||
require.ErrorIs(t, err, ErrUnexpectedContent)
|
|
||||||
assert.True(t, m.Failed())
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("invalid KEM key", func(t *testing.T) {
|
|
||||||
m := newKEMMachine(t, f.respCS, f.v, false, 2000)
|
|
||||||
// Coefficients of 0xfff exceed the modulus, which ML-KEM must reject.
|
|
||||||
bad := bytes.Repeat([]byte{0xff}, mlkem.EncapsulationKeySize1024)
|
|
||||||
err := m.kemEncapsulate(bad)
|
|
||||||
require.ErrorIs(t, err, ErrInvalidKEMKey)
|
|
||||||
err = m.kemEncapsulate(bad[:100])
|
|
||||||
require.ErrorIs(t, err, ErrInvalidKEMKey)
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("valid KEM key", func(t *testing.T) {
|
|
||||||
m := newKEMMachine(t, f.respCS, f.v, false, 2000)
|
|
||||||
require.NoError(t, m.kemEncapsulate(dk.EncapsulationKey().Bytes()))
|
|
||||||
assert.Len(t, m.kemCiphertext, mlkem.CiphertextSize1024)
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("KEM key on the classical subtype", func(t *testing.T) {
|
|
||||||
m := newTestMachine(t, f.respCS, f.v, false, 2000)
|
|
||||||
classical := subtypeInfos[header.HandshakeIXPSK0].msgs[0]
|
|
||||||
err := m.processPayload(payload(dk.EncapsulationKey().Bytes()), classical)
|
|
||||||
require.ErrorIs(t, err, ErrUnexpectedContent)
|
|
||||||
assert.True(t, m.Failed())
|
|
||||||
})
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestKEMDistinctFromClassical makes sure the two subtypes cannot be mixed: a
|
|
||||||
// classical responder cannot answer a KEM initiator.
|
|
||||||
func TestKEMDistinctFromClassical(t *testing.T) {
|
|
||||||
f := newKEMFixture(t, noise.CipherChaChaPoly)
|
|
||||||
initM := newKEMMachine(t, f.initCS, f.v, true, 1000)
|
|
||||||
respM := newTestMachine(t, f.respCS, f.v, false, 2000)
|
|
||||||
|
|
||||||
msg1, err := initM.Initiate(nil)
|
|
||||||
require.NoError(t, err)
|
|
||||||
_, _, err = respM.ProcessPacket(nil, msg1)
|
|
||||||
require.ErrorIs(t, err, ErrSubtypeMismatch)
|
|
||||||
}
|
|
||||||
+5
-54
@@ -2,8 +2,6 @@ package handshake
|
|||||||
|
|
||||||
import (
|
import (
|
||||||
"bytes"
|
"bytes"
|
||||||
"crypto/mlkem"
|
|
||||||
"errors"
|
|
||||||
"fmt"
|
"fmt"
|
||||||
"slices"
|
"slices"
|
||||||
"time"
|
"time"
|
||||||
@@ -69,9 +67,6 @@ type Machine struct {
|
|||||||
remoteCertSet bool
|
remoteCertSet bool
|
||||||
payloadSet bool
|
payloadSet bool
|
||||||
failed bool
|
failed bool
|
||||||
|
|
||||||
kemKey *mlkem.DecapsulationKey1024 // initiator's ephemeral ML-KEM key, until completion
|
|
||||||
kemCiphertext []byte // responder's ciphertext to prefix its response with
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// NewMachine creates a handshake state machine. The subtype determines both
|
// NewMachine creates a handshake state machine. The subtype determines both
|
||||||
@@ -96,7 +91,7 @@ func NewMachine(
|
|||||||
return nil, fmt.Errorf("%w: %v", ErrNoCredential, version)
|
return nil, fmt.Errorf("%w: %v", ErrNoCredential, version)
|
||||||
}
|
}
|
||||||
|
|
||||||
hs, err := cred.buildHandshakeState(initiator, info.pattern, info.pskPlacement)
|
hs, err := cred.buildHandshakeState(initiator, info.pattern)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, fmt.Errorf("build noise state: %w", err)
|
return nil, fmt.Errorf("build noise state: %w", err)
|
||||||
}
|
}
|
||||||
@@ -142,8 +137,7 @@ func (m *Machine) requireComplete() error {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
// myMsgFlags returns the flags for the current outgoing message, which are
|
// myMsgFlags returns the flags for the current outgoing message.
|
||||||
// also the flags of the next incoming message before it is read.
|
|
||||||
func (m *Machine) myMsgFlags() msgFlags {
|
func (m *Machine) myMsgFlags() msgFlags {
|
||||||
idx := m.hs.MessageIndex()
|
idx := m.hs.MessageIndex()
|
||||||
if idx < len(m.msgs) {
|
if idx < len(m.msgs) {
|
||||||
@@ -231,18 +225,7 @@ func (m *Machine) ProcessPacket(out, packet []byte) ([]byte, *Result, error) {
|
|||||||
// noise returns (cs1, cs2) where cs1 is the initiator->responder cipher.
|
// noise returns (cs1, cs2) where cs1 is the initiator->responder cipher.
|
||||||
// For 3-message patterns where a responder finishes by reading the final
|
// For 3-message patterns where a responder finishes by reading the final
|
||||||
// message, this ordering would be wrong; revisit when XX/pqIX lands.
|
// message, this ordering would be wrong; revisit when XX/pqIX lands.
|
||||||
noiseMsg := packet[header.Len:]
|
msg, eKey, dKey, err := m.hs.ReadMessage(nil, packet[header.Len:])
|
||||||
if m.myMsgFlags().kemCiphertext {
|
|
||||||
var err error
|
|
||||||
// Installing a psk derived from a forged ciphertext is harmless: ReadMessage
|
|
||||||
// then fails without advancing, and the next packet installs its own.
|
|
||||||
noiseMsg, err = m.kemDecapsulate(noiseMsg)
|
|
||||||
if err != nil {
|
|
||||||
return nil, nil, err
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
msg, eKey, dKey, err := m.hs.ReadMessage(nil, noiseMsg)
|
|
||||||
if err != nil {
|
if err != nil {
|
||||||
// Noise ReadMessage failed. The noise library checkpoints and rolls back
|
// Noise ReadMessage failed. The noise library checkpoints and rolls back
|
||||||
// on failure, so the Machine is still alive. The caller can retry with
|
// on failure, so the Machine is still alive. The caller can retry with
|
||||||
@@ -293,8 +276,6 @@ func (m *Machine) ProcessPacket(out, packet []byte) ([]byte, *Result, error) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
func (m *Machine) completed(eKey, dKey *noise.CipherState) *Result {
|
func (m *Machine) completed(eKey, dKey *noise.CipherState) *Result {
|
||||||
m.kemKey = nil
|
|
||||||
m.kemCiphertext = nil
|
|
||||||
m.result.EKey = eKey
|
m.result.EKey = eKey
|
||||||
m.result.DKey = dKey
|
m.result.DKey = dKey
|
||||||
m.result.MessageIndex = uint64(m.hs.MessageIndex())
|
m.result.MessageIndex = uint64(m.hs.MessageIndex())
|
||||||
@@ -303,7 +284,7 @@ func (m *Machine) completed(eKey, dKey *noise.CipherState) *Result {
|
|||||||
|
|
||||||
func (m *Machine) processPayload(msg []byte, flags msgFlags) error {
|
func (m *Machine) processPayload(msg []byte, flags msgFlags) error {
|
||||||
if len(msg) == 0 {
|
if len(msg) == 0 {
|
||||||
if flags.expectsPayload || flags.expectsCert || flags.kemKey {
|
if flags.expectsPayload || flags.expectsCert {
|
||||||
m.failed = true
|
m.failed = true
|
||||||
return ErrMissingContent
|
return ErrMissingContent
|
||||||
}
|
}
|
||||||
@@ -329,12 +310,6 @@ func (m *Machine) processPayload(msg []byte, flags msgFlags) error {
|
|||||||
return ErrUnexpectedContent
|
return ErrUnexpectedContent
|
||||||
}
|
}
|
||||||
|
|
||||||
hasKEMKey := len(payload.KEMKey) > 0
|
|
||||||
if hasKEMKey != flags.kemKey {
|
|
||||||
m.failed = true
|
|
||||||
return ErrUnexpectedContent
|
|
||||||
}
|
|
||||||
|
|
||||||
// Process payload
|
// Process payload
|
||||||
if flags.expectsPayload {
|
if flags.expectsPayload {
|
||||||
var remoteIndex uint32
|
var remoteIndex uint32
|
||||||
@@ -361,13 +336,6 @@ func (m *Machine) processPayload(msg []byte, flags msgFlags) error {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
if flags.kemKey {
|
|
||||||
if err := m.kemEncapsulate(payload.KEMKey); err != nil {
|
|
||||||
m.failed = true
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -412,21 +380,11 @@ func (m *Machine) validateCert(payload Payload) error {
|
|||||||
}
|
}
|
||||||
|
|
||||||
func (m *Machine) marshalOutgoing(flags msgFlags) ([]byte, error) {
|
func (m *Machine) marshalOutgoing(flags msgFlags) ([]byte, error) {
|
||||||
if !flags.expectsPayload && !flags.expectsCert && !flags.kemKey {
|
if !flags.expectsPayload && !flags.expectsCert {
|
||||||
return nil, nil
|
return nil, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
var p Payload
|
var p Payload
|
||||||
if flags.kemKey {
|
|
||||||
if m.kemKey == nil {
|
|
||||||
dk, err := mlkem.GenerateKey1024()
|
|
||||||
if err != nil {
|
|
||||||
return nil, fmt.Errorf("generate ML-KEM key: %w", err)
|
|
||||||
}
|
|
||||||
m.kemKey = dk
|
|
||||||
}
|
|
||||||
p.KEMKey = m.kemKey.EncapsulationKey().Bytes()
|
|
||||||
}
|
|
||||||
if flags.expectsPayload {
|
if flags.expectsPayload {
|
||||||
if !m.indexAllocated {
|
if !m.indexAllocated {
|
||||||
index, err := m.allocIndex()
|
index, err := m.allocIndex()
|
||||||
@@ -478,13 +436,6 @@ func (m *Machine) buildResponse(out []byte) ([]byte, *noise.CipherState, *noise.
|
|||||||
uint64(m.hs.MessageIndex()+1),
|
uint64(m.hs.MessageIndex()+1),
|
||||||
)
|
)
|
||||||
|
|
||||||
if flags.kemCiphertext {
|
|
||||||
if m.kemCiphertext == nil {
|
|
||||||
return nil, nil, nil, errors.New("no ML-KEM ciphertext to send")
|
|
||||||
}
|
|
||||||
out = append(out, m.kemCiphertext...)
|
|
||||||
}
|
|
||||||
|
|
||||||
// noise.WriteMessage appends the encrypted handshake message to out,
|
// noise.WriteMessage appends the encrypted handshake message to out,
|
||||||
// reusing capacity when present.
|
// reusing capacity when present.
|
||||||
//
|
//
|
||||||
|
|||||||
@@ -11,15 +11,12 @@ import (
|
|||||||
type msgFlags struct {
|
type msgFlags struct {
|
||||||
expectsPayload bool // message carries indexes and time
|
expectsPayload bool // message carries indexes and time
|
||||||
expectsCert bool // message carries the certificate
|
expectsCert bool // message carries the certificate
|
||||||
kemKey bool // payload carries an ML-KEM encapsulation key
|
|
||||||
kemCiphertext bool // message is prefixed with the ML-KEM ciphertext for the peer's key
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// subtypeInfo bundles the noise pattern with the per-message flags for a
|
// subtypeInfo bundles the noise pattern with the per-message flags for a
|
||||||
// given handshake subtype.
|
// given handshake subtype.
|
||||||
type subtypeInfo struct {
|
type subtypeInfo struct {
|
||||||
pattern noise.HandshakePattern
|
pattern noise.HandshakePattern
|
||||||
pskPlacement int // noise psk modifier position, 0 means no psk token
|
|
||||||
msgs []msgFlags
|
msgs []msgFlags
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -35,22 +32,6 @@ var subtypeInfos = map[header.MessageSubType]subtypeInfo{
|
|||||||
},
|
},
|
||||||
},
|
},
|
||||||
|
|
||||||
// IX with an ephemeral ML-KEM-1024 exchange:
|
|
||||||
// msg1 (I->R): payload + cert + encapsulation key
|
|
||||||
// msg2 (R->I): ciphertext || noise(payload + cert)
|
|
||||||
// The responder encapsulates after reading msg1 and mixes the shared secret in
|
|
||||||
// through the psk2 token at the end of msg2. The ciphertext travels outside the
|
|
||||||
// noise message because the initiator needs the secret before it can process
|
|
||||||
// that token.
|
|
||||||
header.HandshakeIXPSK2MLKEM1024: {
|
|
||||||
pattern: noise.HandshakeIX,
|
|
||||||
pskPlacement: 2,
|
|
||||||
msgs: []msgFlags{
|
|
||||||
{expectsPayload: true, expectsCert: true, kemKey: true},
|
|
||||||
{expectsPayload: true, expectsCert: true, kemCiphertext: true},
|
|
||||||
},
|
|
||||||
},
|
|
||||||
|
|
||||||
// XX: 3 messages
|
// XX: 3 messages
|
||||||
// msg1 (I->R): payload only
|
// msg1 (I->R): payload only
|
||||||
// msg2 (R->I): payload + cert
|
// msg2 (R->I): payload + cert
|
||||||
|
|||||||
@@ -20,7 +20,6 @@ type Payload struct {
|
|||||||
ResponderIndex uint32
|
ResponderIndex uint32
|
||||||
Time uint64
|
Time uint64
|
||||||
CertVersion uint32
|
CertVersion uint32
|
||||||
KEMKey []byte // ML-KEM encapsulation key, only in subtypes that carry one
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// Proto field numbers for NebulaHandshakeDetails
|
// Proto field numbers for NebulaHandshakeDetails
|
||||||
@@ -30,7 +29,6 @@ const (
|
|||||||
fieldResponderIndex = 3 // uint32
|
fieldResponderIndex = 3 // uint32
|
||||||
fieldTime = 5 // uint64
|
fieldTime = 5 // uint64
|
||||||
fieldCertVersion = 8 // uint32
|
fieldCertVersion = 8 // uint32
|
||||||
fieldKEMKey = 9 // bytes
|
|
||||||
)
|
)
|
||||||
|
|
||||||
// MarshalPayload encodes a handshake payload in protobuf wire format compatible
|
// MarshalPayload encodes a handshake payload in protobuf wire format compatible
|
||||||
@@ -59,10 +57,6 @@ func MarshalPayload(out []byte, p Payload) []byte {
|
|||||||
details = protowire.AppendTag(details, fieldCertVersion, protowire.VarintType)
|
details = protowire.AppendTag(details, fieldCertVersion, protowire.VarintType)
|
||||||
details = protowire.AppendVarint(details, uint64(p.CertVersion))
|
details = protowire.AppendVarint(details, uint64(p.CertVersion))
|
||||||
}
|
}
|
||||||
if len(p.KEMKey) > 0 {
|
|
||||||
details = protowire.AppendTag(details, fieldKEMKey, protowire.BytesType)
|
|
||||||
details = protowire.AppendBytes(details, p.KEMKey)
|
|
||||||
}
|
|
||||||
|
|
||||||
out = protowire.AppendTag(out, 1, protowire.BytesType)
|
out = protowire.AppendTag(out, 1, protowire.BytesType)
|
||||||
out = protowire.AppendBytes(out, details)
|
out = protowire.AppendBytes(out, details)
|
||||||
@@ -167,16 +161,6 @@ func unmarshalPayloadDetails(p *Payload, b []byte) error {
|
|||||||
}
|
}
|
||||||
p.CertVersion = uint32(v)
|
p.CertVersion = uint32(v)
|
||||||
b = b[n:]
|
b = b[n:]
|
||||||
case fieldKEMKey:
|
|
||||||
if typ != protowire.BytesType {
|
|
||||||
return errInvalidHandshakeDetails
|
|
||||||
}
|
|
||||||
v, n := protowire.ConsumeBytes(b)
|
|
||||||
if n < 0 {
|
|
||||||
return errInvalidHandshakeDetails
|
|
||||||
}
|
|
||||||
p.KEMKey = append([]byte(nil), v...)
|
|
||||||
b = b[n:]
|
|
||||||
default:
|
default:
|
||||||
n := protowire.ConsumeFieldValue(num, typ, b)
|
n := protowire.ConsumeFieldValue(num, typ, b)
|
||||||
if n < 0 {
|
if n < 0 {
|
||||||
|
|||||||
+37
-142
@@ -10,15 +10,12 @@ import (
|
|||||||
"net/netip"
|
"net/netip"
|
||||||
"slices"
|
"slices"
|
||||||
"sync"
|
"sync"
|
||||||
"sync/atomic"
|
|
||||||
"time"
|
"time"
|
||||||
|
|
||||||
"github.com/rcrowley/go-metrics"
|
"github.com/rcrowley/go-metrics"
|
||||||
"github.com/slackhq/nebula/cert"
|
"github.com/slackhq/nebula/cert"
|
||||||
"github.com/slackhq/nebula/handshake"
|
"github.com/slackhq/nebula/handshake"
|
||||||
"github.com/slackhq/nebula/handshake/fragment"
|
|
||||||
"github.com/slackhq/nebula/header"
|
"github.com/slackhq/nebula/header"
|
||||||
"github.com/slackhq/nebula/ratelimit"
|
|
||||||
"github.com/slackhq/nebula/udp"
|
"github.com/slackhq/nebula/udp"
|
||||||
)
|
)
|
||||||
|
|
||||||
@@ -52,7 +49,6 @@ type HandshakeConfig struct {
|
|||||||
tryInterval time.Duration
|
tryInterval time.Duration
|
||||||
retries int64
|
retries int64
|
||||||
triggerBuffer int
|
triggerBuffer int
|
||||||
pq pqHandshakeConfig
|
|
||||||
|
|
||||||
messageMetrics *MessageMetrics
|
messageMetrics *MessageMetrics
|
||||||
}
|
}
|
||||||
@@ -78,18 +74,6 @@ type HandshakeManager struct {
|
|||||||
|
|
||||||
// can be used to trigger outbound handshake for the given vpnIp
|
// can be used to trigger outbound handshake for the given vpnIp
|
||||||
trigger chan netip.Addr
|
trigger chan netip.Addr
|
||||||
|
|
||||||
// pq holds the post-quantum settings, which change on reload.
|
|
||||||
pq atomic.Pointer[pqHandshakeConfig]
|
|
||||||
// pqTable reassembles post-quantum msg1s from senders that have not authenticated yet.
|
|
||||||
pqTable *fragment.Table[pqFragKey, pqFragSource]
|
|
||||||
// pqPeers holds vpn addresses that completed a post-quantum handshake, for sticky mode.
|
|
||||||
pqPeers sync.Map
|
|
||||||
// pqAnswered recognises repeats of post-quantum msg1s already answered.
|
|
||||||
pqAnswered *pqAnswered
|
|
||||||
// pqCookies and pqCookieLimiter serve cookies while pqTable is under load.
|
|
||||||
pqCookies *pqCookies
|
|
||||||
pqCookieLimiter *ratelimit.Limiter
|
|
||||||
}
|
}
|
||||||
|
|
||||||
type HandshakeHostInfo struct {
|
type HandshakeHostInfo struct {
|
||||||
@@ -105,8 +89,6 @@ type HandshakeHostInfo struct {
|
|||||||
|
|
||||||
hostinfo *HostInfo
|
hostinfo *HostInfo
|
||||||
machine *handshake.Machine // The handshake state machine, set during stage 0 (initiator) or beginHandshake (responder multi-message)
|
machine *handshake.Machine // The handshake state machine, set during stage 0 (initiator) or beginHandshake (responder multi-message)
|
||||||
pq *pqAttempt // The initiator's post-quantum attempt, pending alongside the classical one
|
|
||||||
lastPQ bool // Whether the latest attempt was post-quantum
|
|
||||||
}
|
}
|
||||||
|
|
||||||
func (hh *HandshakeHostInfo) cachePacket(l *slog.Logger, t header.MessageType, st header.MessageSubType, packet []byte, f packetCallback, m *cachedPacketMetrics) {
|
func (hh *HandshakeHostInfo) cachePacket(l *slog.Logger, t header.MessageType, st header.MessageSubType, packet []byte, f packetCallback, m *cachedPacketMetrics) {
|
||||||
@@ -135,7 +117,7 @@ func (hh *HandshakeHostInfo) cachePacket(l *slog.Logger, t header.MessageType, s
|
|||||||
}
|
}
|
||||||
|
|
||||||
func NewHandshakeManager(l *slog.Logger, mainHostMap *HostMap, lightHouse *LightHouse, outside udp.Conn, config HandshakeConfig) *HandshakeManager {
|
func NewHandshakeManager(l *slog.Logger, mainHostMap *HostMap, lightHouse *LightHouse, outside udp.Conn, config HandshakeConfig) *HandshakeManager {
|
||||||
hm := &HandshakeManager{
|
return &HandshakeManager{
|
||||||
vpnIps: map[netip.Addr]*HandshakeHostInfo{},
|
vpnIps: map[netip.Addr]*HandshakeHostInfo{},
|
||||||
indexes: map[uint32]*HandshakeHostInfo{},
|
indexes: map[uint32]*HandshakeHostInfo{},
|
||||||
mainHostMap: mainHostMap,
|
mainHostMap: mainHostMap,
|
||||||
@@ -148,16 +130,7 @@ func NewHandshakeManager(l *slog.Logger, mainHostMap *HostMap, lightHouse *Light
|
|||||||
metricInitiated: metrics.GetOrRegisterCounter("handshake_manager.initiated", nil),
|
metricInitiated: metrics.GetOrRegisterCounter("handshake_manager.initiated", nil),
|
||||||
metricTimedOut: metrics.GetOrRegisterCounter("handshake_manager.timed_out", nil),
|
metricTimedOut: metrics.GetOrRegisterCounter("handshake_manager.timed_out", nil),
|
||||||
l: l,
|
l: l,
|
||||||
pqTable: fragment.NewTable[pqFragKey, pqFragSource](pqTableConfig),
|
|
||||||
pqAnswered: newPQAnswered(hsTimeout(config.retries, config.tryInterval)),
|
|
||||||
}
|
}
|
||||||
pq := config.pq
|
|
||||||
hm.pq.Store(&pq)
|
|
||||||
hm.pqCookies = newPQCookies(time.Now())
|
|
||||||
// Cookie replies are tiny, but a flood of spoofed fragments must not turn
|
|
||||||
// into a flood of replies.
|
|
||||||
hm.pqCookieLimiter, _ = ratelimit.New(256, time.Millisecond)
|
|
||||||
return hm
|
|
||||||
}
|
}
|
||||||
|
|
||||||
func (hm *HandshakeManager) Run(ctx context.Context) {
|
func (hm *HandshakeManager) Run(ctx context.Context) {
|
||||||
@@ -172,8 +145,6 @@ func (hm *HandshakeManager) Run(ctx context.Context) {
|
|||||||
hm.handleOutbound(vpnIP, true)
|
hm.handleOutbound(vpnIP, true)
|
||||||
case now := <-clockSource.C:
|
case now := <-clockSource.C:
|
||||||
hm.NextOutboundHandshakeTimerTick(now)
|
hm.NextOutboundHandshakeTimerTick(now)
|
||||||
hm.pqTable.Expire(now)
|
|
||||||
hm.pqAnswered.expire(now)
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -183,7 +154,7 @@ func (hm *HandshakeManager) HandleIncoming(via ViaSender, packet []byte, h *head
|
|||||||
// don't yet support) are dropped here rather than silently routed through
|
// don't yet support) are dropped here rather than silently routed through
|
||||||
// the IX path. Add a case when introducing a new pattern.
|
// the IX path. Add a case when introducing a new pattern.
|
||||||
switch h.Subtype {
|
switch h.Subtype {
|
||||||
case header.HandshakeIXPSK0, pqSubtype:
|
case header.HandshakeIXPSK0:
|
||||||
// supported
|
// supported
|
||||||
default:
|
default:
|
||||||
hm.l.Debug("dropping handshake with unsupported subtype",
|
hm.l.Debug("dropping handshake with unsupported subtype",
|
||||||
@@ -199,11 +170,6 @@ func (hm *HandshakeManager) HandleIncoming(via ViaSender, packet []byte, h *head
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
if header.IsFragmented(h.Subtype) {
|
|
||||||
hm.handleFragment(via, packet, h)
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
// First message of a new handshake. The wire format requires RemoteIndex
|
// First message of a new handshake. The wire format requires RemoteIndex
|
||||||
// to be zero here (the initiator has no responder index to fill in yet),
|
// to be zero here (the initiator has no responder index to fill in yet),
|
||||||
// and generateIndex never allocates 0, so any non-zero RemoteIndex on a
|
// and generateIndex never allocates 0, so any non-zero RemoteIndex on a
|
||||||
@@ -215,11 +181,7 @@ func (hm *HandshakeManager) HandleIncoming(via ViaSender, packet []byte, h *head
|
|||||||
"from", via, "remoteIndex", h.RemoteIndex)
|
"from", via, "remoteIndex", h.RemoteIndex)
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
if hm.pqConfig().require {
|
hm.beginHandshake(via, packet, h)
|
||||||
hm.l.Debug("dropping classical handshake, post-quantum handshakes are required", "from", via)
|
|
||||||
return
|
|
||||||
}
|
|
||||||
hm.beginHandshake(via, packet, h, 0)
|
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -268,9 +230,6 @@ func (hm *HandshakeManager) handleOutbound(vpnIp netip.Addr, lighthouseTriggered
|
|||||||
"style": header.SubTypeName(header.Handshake, hh.machine.Subtype()),
|
"style": header.SubTypeName(header.Handshake, hh.machine.Subtype()),
|
||||||
})
|
})
|
||||||
}
|
}
|
||||||
if hh.pq != nil {
|
|
||||||
fields = append(fields, "pqInitiatorIndex", hh.pq.index)
|
|
||||||
}
|
|
||||||
hh.hostinfo.logger(hm.l).Info("Handshake timed out", fields...)
|
hh.hostinfo.logger(hm.l).Info("Handshake timed out", fields...)
|
||||||
hm.metricTimedOut.Inc(1)
|
hm.metricTimedOut.Inc(1)
|
||||||
hm.DeleteHostInfo(hostinfo)
|
hm.DeleteHostInfo(hostinfo)
|
||||||
@@ -280,32 +239,14 @@ func (hm *HandshakeManager) handleOutbound(vpnIp netip.Addr, lighthouseTriggered
|
|||||||
// Increment the counter to increase our delay, linear backoff
|
// Increment the counter to increase our delay, linear backoff
|
||||||
hh.counter++
|
hh.counter++
|
||||||
|
|
||||||
// Pick this attempt's style and make sure its first message exists. A PQ
|
// Check if we have a handshake packet to transmit yet
|
||||||
// attempt sends msg1 as fragments: now goes out immediately, later after the
|
|
||||||
// repair delay, and every attempt offers fresh repair symbols.
|
|
||||||
var now, later [][]byte
|
|
||||||
var machine *handshake.Machine
|
|
||||||
hh.lastPQ = hm.usePQ(hh, vpnIp, lighthouseTriggered)
|
|
||||||
if hh.lastPQ {
|
|
||||||
if hh.pq == nil && !hm.buildPQAttempt(hh) {
|
|
||||||
hm.OutboundHandshakeTimer.Add(vpnIp, hm.config.tryInterval*time.Duration(hh.counter))
|
|
||||||
return
|
|
||||||
}
|
|
||||||
var err error
|
|
||||||
now, later, err = hh.pq.sender.Attempt(fragment.DefaultRepair(hh.pq.sender.Layout().K))
|
|
||||||
if err != nil {
|
|
||||||
hostinfo.logger(hm.l).Error("Failed to fragment handshake", "error", err)
|
|
||||||
hm.OutboundHandshakeTimer.Add(vpnIp, hm.config.tryInterval*time.Duration(hh.counter))
|
|
||||||
return
|
|
||||||
}
|
|
||||||
machine = hh.pq.machine
|
|
||||||
} else {
|
|
||||||
if !hh.ready {
|
if !hh.ready {
|
||||||
if !hm.buildStage0Packet(hh) {
|
if !hm.buildStage0Packet(hh) {
|
||||||
hm.OutboundHandshakeTimer.Add(vpnIp, hm.config.tryInterval*time.Duration(hh.counter))
|
hm.OutboundHandshakeTimer.Add(vpnIp, hm.config.tryInterval*time.Duration(hh.counter))
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// TODO: this hardcodes "always retransmit stage 0", which is correct for
|
// TODO: this hardcodes "always retransmit stage 0", which is correct for
|
||||||
// IX (the initiator only ever sends one packet, msg1) but wrong the
|
// IX (the initiator only ever sends one packet, msg1) but wrong the
|
||||||
// moment a 3+ message pattern lands. The retry loop should resend the
|
// moment a 3+ message pattern lands. The retry loop should resend the
|
||||||
@@ -313,12 +254,10 @@ func (hm *HandshakeManager) handleOutbound(vpnIp netip.Addr, lighthouseTriggered
|
|||||||
// HandshakeHostInfo tracking a single "currentOutbound" packet (bytes +
|
// HandshakeHostInfo tracking a single "currentOutbound" packet (bytes +
|
||||||
// header metadata) that gets replaced as the handshake progresses,
|
// header metadata) that gets replaced as the handshake progresses,
|
||||||
// instead of indexing into HandshakePacket.
|
// instead of indexing into HandshakePacket.
|
||||||
now = [][]byte{hostinfo.HandshakePacket[handshakePacketStage0]}
|
stage0 := hostinfo.HandshakePacket[handshakePacketStage0]
|
||||||
machine = hh.machine
|
|
||||||
}
|
|
||||||
hsFields := m{
|
hsFields := m{
|
||||||
"stage": uint64(machine.MessageIndex()),
|
"stage": uint64(hh.machine.MessageIndex()),
|
||||||
"style": header.SubTypeName(header.Handshake, machine.Subtype()),
|
"style": header.SubTypeName(header.Handshake, hh.machine.Subtype()),
|
||||||
}
|
}
|
||||||
|
|
||||||
remotes := hostinfo.remotes.CopyAddrs(hm.mainHostMap.GetPreferredRanges())
|
remotes := hostinfo.remotes.CopyAddrs(hm.mainHostMap.GetPreferredRanges())
|
||||||
@@ -346,10 +285,8 @@ func (hm *HandshakeManager) handleOutbound(vpnIp netip.Addr, lighthouseTriggered
|
|||||||
// Send the handshake to all known ips, stage 2 takes care of assigning the hostinfo.remote based on the first to reply
|
// Send the handshake to all known ips, stage 2 takes care of assigning the hostinfo.remote based on the first to reply
|
||||||
var sentTo []netip.AddrPort
|
var sentTo []netip.AddrPort
|
||||||
hostinfo.remotes.ForEach(hm.mainHostMap.GetPreferredRanges(), func(addr netip.AddrPort, _ bool) {
|
hostinfo.remotes.ForEach(hm.mainHostMap.GetPreferredRanges(), func(addr netip.AddrPort, _ bool) {
|
||||||
hm.messageMetrics.Tx(header.Handshake, machine.Subtype(), int64(len(now)+len(later)))
|
hm.messageMetrics.Tx(header.Handshake, hh.machine.Subtype(), 1)
|
||||||
err := hm.sendFragmented(now, later, func(p []byte) error {
|
err := hm.outside.WriteTo(stage0, addr)
|
||||||
return hm.outside.WriteTo(p, addr)
|
|
||||||
})
|
|
||||||
if err != nil {
|
if err != nil {
|
||||||
// These repeat every attempt, so match the success log below and only shout when the remotes changed
|
// These repeat every attempt, so match the success log below and only shout when the remotes changed
|
||||||
level := slog.LevelDebug
|
level := slog.LevelDebug
|
||||||
@@ -385,7 +322,7 @@ func (hm *HandshakeManager) handleOutbound(vpnIp netip.Addr, lighthouseTriggered
|
|||||||
)
|
)
|
||||||
}
|
}
|
||||||
|
|
||||||
hm.f.relayManager.StartRelays(hm.f, vpnIp, hh, now, later)
|
hm.f.relayManager.StartRelays(hm.f, vpnIp, hh, stage0)
|
||||||
|
|
||||||
// If a lighthouse triggered this attempt then we are still in the timer wheel and do not need to re-add
|
// If a lighthouse triggered this attempt then we are still in the timer wheel and do not need to re-add
|
||||||
if !lighthouseTriggered {
|
if !lighthouseTriggered {
|
||||||
@@ -595,10 +532,6 @@ func (hm *HandshakeManager) DeleteHostInfo(hostinfo *HostInfo) {
|
|||||||
func (hm *HandshakeManager) unlockedDeleteHostInfo(hostinfo *HostInfo) {
|
func (hm *HandshakeManager) unlockedDeleteHostInfo(hostinfo *HostInfo) {
|
||||||
for _, addr := range hostinfo.vpnAddrs {
|
for _, addr := range hostinfo.vpnAddrs {
|
||||||
if cur, ok := hm.vpnIps[addr]; ok && cur.hostinfo == hostinfo {
|
if cur, ok := hm.vpnIps[addr]; ok && cur.hostinfo == hostinfo {
|
||||||
// A PQ attempt holds its own index alongside the hostinfo's.
|
|
||||||
if idx := cur.pqIndex(); idx != 0 && hm.indexes[idx] == cur {
|
|
||||||
delete(hm.indexes, idx)
|
|
||||||
}
|
|
||||||
delete(hm.vpnIps, addr)
|
delete(hm.vpnIps, addr)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -709,8 +642,9 @@ func hsTimeout(tries int64, interval time.Duration) time.Duration {
|
|||||||
return time.Duration(tries / 2 * ((2 * int64(interval)) + (tries-1)*int64(interval)))
|
return time.Duration(tries / 2 * ((2 * int64(interval)) + (tries-1)*int64(interval)))
|
||||||
}
|
}
|
||||||
|
|
||||||
// initiatingVersion picks the certificate version to initiate a handshake with.
|
// buildStage0Packet creates the initial handshake packet for the initiator.
|
||||||
func (hm *HandshakeManager) initiatingVersion(hh *HandshakeHostInfo, cs *CertState) cert.Version {
|
func (hm *HandshakeManager) buildStage0Packet(hh *HandshakeHostInfo) bool {
|
||||||
|
cs := hm.f.pki.getCertState()
|
||||||
v := cs.DefaultVersion()
|
v := cs.DefaultVersion()
|
||||||
if hh.initiatingVersionOverride != cert.VersionPre1 {
|
if hh.initiatingVersionOverride != cert.VersionPre1 {
|
||||||
v = hh.initiatingVersionOverride
|
v = hh.initiatingVersionOverride
|
||||||
@@ -722,13 +656,6 @@ func (hm *HandshakeManager) initiatingVersion(hh *HandshakeHostInfo, cs *CertSta
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
return v
|
|
||||||
}
|
|
||||||
|
|
||||||
// buildStage0Packet creates the initial handshake packet for the initiator.
|
|
||||||
func (hm *HandshakeManager) buildStage0Packet(hh *HandshakeHostInfo) bool {
|
|
||||||
cs := hm.f.pki.getCertState()
|
|
||||||
v := hm.initiatingVersion(hh, cs)
|
|
||||||
|
|
||||||
cred := cs.GetCredential(v)
|
cred := cs.GetCredential(v)
|
||||||
if cred == nil {
|
if cred == nil {
|
||||||
@@ -767,10 +694,7 @@ func (hm *HandshakeManager) buildStage0Packet(hh *HandshakeHostInfo) bool {
|
|||||||
// beginHandshake handles an incoming handshake packet that doesn't match any
|
// beginHandshake handles an incoming handshake packet that doesn't match any
|
||||||
// existing pending handshake. It creates a new responder Machine and processes
|
// existing pending handshake. It creates a new responder Machine and processes
|
||||||
// the first message.
|
// the first message.
|
||||||
//
|
func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *header.H) {
|
||||||
// received is the number of bytes a fragmented msg1 arrived in, which bounds the
|
|
||||||
// response sent back before the address is validated; 0 for unfragmented ones.
|
|
||||||
func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *header.H, received int) {
|
|
||||||
f := hm.f
|
f := hm.f
|
||||||
cs := f.pki.getCertState()
|
cs := f.pki.getCertState()
|
||||||
|
|
||||||
@@ -784,7 +708,7 @@ func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *head
|
|||||||
machine, err := handshake.NewMachine(
|
machine, err := handshake.NewMachine(
|
||||||
v, cs.GetCredential,
|
v, cs.GetCredential,
|
||||||
hm.certVerifier(), func() (uint32, error) { return generateIndex(f.l) },
|
hm.certVerifier(), func() (uint32, error) { return generateIndex(f.l) },
|
||||||
false, h.Subtype,
|
false, header.HandshakeIXPSK0,
|
||||||
)
|
)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
f.l.Error("Failed to create handshake machine", "from", via, "error", err)
|
f.l.Error("Failed to create handshake machine", "from", via, "error", err)
|
||||||
@@ -874,15 +798,11 @@ func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *head
|
|||||||
|
|
||||||
existing, err := hm.CheckAndComplete(hostinfo, handshakePacketStage0, f)
|
existing, err := hm.CheckAndComplete(hostinfo, handshakePacketStage0, f)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
hm.handleCheckAndCompleteError(err, existing, hostinfo, via, machine.Subtype(), received)
|
hm.handleCheckAndCompleteError(err, existing, hostinfo, via)
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
|
|
||||||
hm.sendHandshakeResponse(via, response, hostinfo, false, received)
|
hm.sendHandshakeResponse(via, response, hostinfo, false)
|
||||||
if header.IsFragmented(machine.Subtype()) {
|
|
||||||
hm.pqAnswered.add(packet[header.Len:], hostinfo, time.Now())
|
|
||||||
}
|
|
||||||
hm.notePQPeer(machine.Subtype(), vpnAddrs)
|
|
||||||
hostinfo.remotes.RefreshFromHandshake(vpnAddrs)
|
hostinfo.remotes.RefreshFromHandshake(vpnAddrs)
|
||||||
|
|
||||||
// Don't wait for UpdateWorker
|
// Don't wait for UpdateWorker
|
||||||
@@ -893,32 +813,23 @@ func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *head
|
|||||||
|
|
||||||
// continueHandshake feeds an incoming packet to an existing pending handshake Machine.
|
// continueHandshake feeds an incoming packet to an existing pending handshake Machine.
|
||||||
func (hm *HandshakeManager) continueHandshake(via ViaSender, hh *HandshakeHostInfo, packet []byte) {
|
func (hm *HandshakeManager) continueHandshake(via ViaSender, hh *HandshakeHostInfo, packet []byte) {
|
||||||
|
f := hm.f
|
||||||
|
|
||||||
hh.Lock()
|
hh.Lock()
|
||||||
defer hh.Unlock()
|
defer hh.Unlock()
|
||||||
|
|
||||||
if !hm.stillPending(hh, hh.hostinfo.localIndexId) {
|
// Re-verify hh is still tracked. Between queryIndex returning and us taking
|
||||||
|
// hh.Lock, handleOutbound may have timed out and deleted it. Once we hold
|
||||||
|
// hh.Lock no other deleter can race our index: handleOutbound also takes
|
||||||
|
// hh.Lock first, and handleRecvError targets a main-hostmap entry with a
|
||||||
|
// different localIndexId.
|
||||||
|
hm.RLock()
|
||||||
|
cur, ok := hm.indexes[hh.hostinfo.localIndexId]
|
||||||
|
hm.RUnlock()
|
||||||
|
if !ok || cur != hh {
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
hm.processResponse(via, hh, hh.machine, packet)
|
|
||||||
}
|
|
||||||
|
|
||||||
// stillPending re-verifies hh is still tracked under index. Between queryIndex
|
|
||||||
// returning and the caller taking hh.Lock, handleOutbound may have timed out and
|
|
||||||
// deleted it. Once hh.Lock is held no other deleter can race the index:
|
|
||||||
// handleOutbound also takes hh.Lock first, and handleRecvError targets a
|
|
||||||
// main-hostmap entry with a different localIndexId. The caller must hold hh.Lock.
|
|
||||||
func (hm *HandshakeManager) stillPending(hh *HandshakeHostInfo, index uint32) bool {
|
|
||||||
hm.RLock()
|
|
||||||
defer hm.RUnlock()
|
|
||||||
cur, ok := hm.indexes[index]
|
|
||||||
return ok && cur == hh
|
|
||||||
}
|
|
||||||
|
|
||||||
// processResponse runs a responder's message through one of the initiator's
|
|
||||||
// pending attempts and completes the tunnel when the handshake finishes. The
|
|
||||||
// caller must hold hh.Lock.
|
|
||||||
func (hm *HandshakeManager) processResponse(via ViaSender, hh *HandshakeHostInfo, machine *handshake.Machine, packet []byte) {
|
|
||||||
f := hm.f
|
|
||||||
hostinfo := hh.hostinfo
|
hostinfo := hh.hostinfo
|
||||||
if !via.IsRelayed {
|
if !via.IsRelayed {
|
||||||
if !f.lightHouse.GetRemoteAllowList().AllowAll(hostinfo.vpnAddrs, via.UdpAddr.Addr()) {
|
if !f.lightHouse.GetRemoteAllowList().AllowAll(hostinfo.vpnAddrs, via.UdpAddr.Addr()) {
|
||||||
@@ -928,6 +839,7 @@ func (hm *HandshakeManager) processResponse(via ViaSender, hh *HandshakeHostInfo
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
machine := hh.machine
|
||||||
if machine == nil {
|
if machine == nil {
|
||||||
f.l.Error("No handshake machine available for continuation",
|
f.l.Error("No handshake machine available for continuation",
|
||||||
"vpnAddrs", hostinfo.vpnAddrs, "from", via)
|
"vpnAddrs", hostinfo.vpnAddrs, "from", via)
|
||||||
@@ -950,7 +862,7 @@ func (hm *HandshakeManager) processResponse(via ViaSender, hh *HandshakeHostInfo
|
|||||||
}
|
}
|
||||||
|
|
||||||
if response != nil {
|
if response != nil {
|
||||||
hm.sendHandshakeResponse(via, response, hostinfo, false, 0)
|
hm.sendHandshakeResponse(via, response, hostinfo, false)
|
||||||
}
|
}
|
||||||
|
|
||||||
if result == nil {
|
if result == nil {
|
||||||
@@ -1063,10 +975,7 @@ func (hm *HandshakeManager) processResponse(via ViaSender, hh *HandshakeHostInfo
|
|||||||
hostinfo.vpnAddrs = vpnAddrs
|
hostinfo.vpnAddrs = vpnAddrs
|
||||||
hostinfo.buildNetworks(f.myVpnNetworksTable, remoteCert.Certificate)
|
hostinfo.buildNetworks(f.myVpnNetworksTable, remoteCert.Certificate)
|
||||||
|
|
||||||
// The classical and PQ attempts each hold an index; keep the one that won.
|
|
||||||
hm.settleIndex(hh, result.LocalIndex)
|
|
||||||
hm.Complete(hostinfo, f)
|
hm.Complete(hostinfo, f)
|
||||||
hm.notePQPeer(machine.Subtype(), vpnAddrs)
|
|
||||||
|
|
||||||
if len(hh.packetStore) > 0 {
|
if len(hh.packetStore) > 0 {
|
||||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||||
@@ -1145,23 +1054,20 @@ func (hm *HandshakeManager) validatePeerCert(via ViaSender, remoteCert *cert.Cac
|
|||||||
// cached is true when msg is a stored response being retransmitted because
|
// cached is true when msg is a stored response being retransmitted because
|
||||||
// the peer's stage-1 retransmit landed (the ErrAlreadySeen path); false on a
|
// the peer's stage-1 retransmit landed (the ErrAlreadySeen path); false on a
|
||||||
// fresh response.
|
// fresh response.
|
||||||
//
|
func (hm *HandshakeManager) sendHandshakeResponse(via ViaSender, msg []byte, hostinfo *HostInfo, cached bool) {
|
||||||
// received is the number of bytes a fragmented msg1 arrived in; it bounds what a
|
|
||||||
// fragmented response may send back. It is ignored for unfragmented subtypes.
|
|
||||||
func (hm *HandshakeManager) sendHandshakeResponse(via ViaSender, msg []byte, hostinfo *HostInfo, cached bool, received int) {
|
|
||||||
if msg == nil {
|
if msg == nil {
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
|
|
||||||
f := hm.f
|
f := hm.f
|
||||||
subtype := header.MessageSubType(msg[1])
|
f.messageMetrics.Tx(header.Handshake, header.MessageSubType(msg[1]), 1)
|
||||||
|
|
||||||
// Common log fields. peerCert may be nil during intermediate
|
// Common log fields. peerCert may be nil during intermediate
|
||||||
// multi-message flows (handshake hasn't completed yet); skip the cert
|
// multi-message flows (handshake hasn't completed yet); skip the cert
|
||||||
// block if so.
|
// block if so.
|
||||||
logFields := []any{
|
logFields := []any{
|
||||||
"vpnAddrs", hostinfo.vpnAddrs,
|
"vpnAddrs", hostinfo.vpnAddrs,
|
||||||
"handshake", m{"stage": uint64(2), "style": header.SubTypeName(header.Handshake, subtype)},
|
"handshake", m{"stage": uint64(2), "style": header.SubTypeName(header.Handshake, header.HandshakeIXPSK0)},
|
||||||
"cached", cached,
|
"cached", cached,
|
||||||
"initiatorIndex", hostinfo.remoteIndexId,
|
"initiatorIndex", hostinfo.remoteIndexId,
|
||||||
"responderIndex", hostinfo.localIndexId,
|
"responderIndex", hostinfo.localIndexId,
|
||||||
@@ -1175,17 +1081,6 @@ func (hm *HandshakeManager) sendHandshakeResponse(via ViaSender, msg []byte, hos
|
|||||||
)
|
)
|
||||||
}
|
}
|
||||||
|
|
||||||
if header.IsFragmented(subtype) {
|
|
||||||
fields := append(logFields, "from", via)
|
|
||||||
if err := hm.sendFragmentedResponse(via, msg, hostinfo, cached, received); err != nil {
|
|
||||||
f.l.Debug("Did not send handshake message", append(fields, "error", err)...)
|
|
||||||
} else {
|
|
||||||
f.l.Info("Handshake message sent", fields...)
|
|
||||||
}
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
f.messageMetrics.Tx(header.Handshake, subtype, 1)
|
|
||||||
if !via.IsRelayed {
|
if !via.IsRelayed {
|
||||||
fields := append(logFields, "from", via)
|
fields := append(logFields, "from", via)
|
||||||
err := f.outside.WriteTo(msg, via.UdpAddr)
|
err := f.outside.WriteTo(msg, via.UdpAddr)
|
||||||
@@ -1212,10 +1107,10 @@ func (hm *HandshakeManager) sendHandshakeResponse(via ViaSender, msg []byte, hos
|
|||||||
// This only fires from the responder-side beginHandshake path, after the
|
// This only fires from the responder-side beginHandshake path, after the
|
||||||
// peer cert has been validated and ConnectionState populated, so peerCert
|
// peer cert has been validated and ConnectionState populated, so peerCert
|
||||||
// is always non-nil for the cases that log it.
|
// is always non-nil for the cases that log it.
|
||||||
func (hm *HandshakeManager) handleCheckAndCompleteError(err error, existing, hostinfo *HostInfo, via ViaSender, subtype header.MessageSubType, received int) {
|
func (hm *HandshakeManager) handleCheckAndCompleteError(err error, existing, hostinfo *HostInfo, via ViaSender) {
|
||||||
f := hm.f
|
f := hm.f
|
||||||
peerCert := hostinfo.ConnectionState.peerCert
|
peerCert := hostinfo.ConnectionState.peerCert
|
||||||
hsFields := m{"stage": uint64(1), "style": header.SubTypeName(header.Handshake, subtype)}
|
hsFields := m{"stage": uint64(1), "style": header.SubTypeName(header.Handshake, header.HandshakeIXPSK0)}
|
||||||
|
|
||||||
switch err {
|
switch err {
|
||||||
case ErrAlreadySeen:
|
case ErrAlreadySeen:
|
||||||
@@ -1226,7 +1121,7 @@ func (hm *HandshakeManager) handleCheckAndCompleteError(err error, existing, hos
|
|||||||
// ephemeral keys; a freshly-built one would have different keys and break
|
// ephemeral keys; a freshly-built one would have different keys and break
|
||||||
// the tunnel even though both sides "completed" the handshake.
|
// the tunnel even though both sides "completed" the handshake.
|
||||||
if msg := existing.HandshakePacket[handshakePacketStage2]; msg != nil {
|
if msg := existing.HandshakePacket[handshakePacketStage2]; msg != nil {
|
||||||
hm.sendHandshakeResponse(via, msg, existing, true, received)
|
hm.sendHandshakeResponse(via, msg, existing, true)
|
||||||
}
|
}
|
||||||
|
|
||||||
case ErrExistingHostInfo:
|
case ErrExistingHostInfo:
|
||||||
|
|||||||
@@ -1,699 +0,0 @@
|
|||||||
package nebula
|
|
||||||
|
|
||||||
import (
|
|
||||||
"context"
|
|
||||||
"crypto/hmac"
|
|
||||||
"crypto/rand"
|
|
||||||
"crypto/sha256"
|
|
||||||
"encoding/binary"
|
|
||||||
"errors"
|
|
||||||
"log/slog"
|
|
||||||
"net/netip"
|
|
||||||
"sync"
|
|
||||||
"time"
|
|
||||||
|
|
||||||
"github.com/slackhq/nebula/config"
|
|
||||||
"github.com/slackhq/nebula/handshake"
|
|
||||||
"github.com/slackhq/nebula/handshake/fragment"
|
|
||||||
"github.com/slackhq/nebula/header"
|
|
||||||
)
|
|
||||||
|
|
||||||
const (
|
|
||||||
// pqSubtype is the post-quantum handshake this node speaks.
|
|
||||||
pqSubtype = header.HandshakeIXPSK2MLKEM1024
|
|
||||||
|
|
||||||
// DefaultPQRepairDelay is how long repair fragments trail the data fragments.
|
|
||||||
DefaultPQRepairDelay = 10 * time.Millisecond
|
|
||||||
|
|
||||||
// pqAmplification bounds what a responder sends in reply to an unvalidated
|
|
||||||
// address, as a multiple of what it received from it.
|
|
||||||
pqAmplification = 3
|
|
||||||
)
|
|
||||||
|
|
||||||
// pqTableConfig bounds the responder's reassembly of msg1 fragments from senders
|
|
||||||
// that have not authenticated yet.
|
|
||||||
var pqTableConfig = fragment.TableConfig{
|
|
||||||
MaxBytes: 4 << 20,
|
|
||||||
MaxEntries: 1024,
|
|
||||||
MaxPerSource: 4,
|
|
||||||
MaxMsgLen: 16384,
|
|
||||||
TTL: 3 * time.Second,
|
|
||||||
}
|
|
||||||
|
|
||||||
type pqHandshakeConfig struct {
|
|
||||||
initiate bool // start PQ handshakes
|
|
||||||
accept bool // answer PQ handshakes
|
|
||||||
require bool // only PQ handshakes, in either direction
|
|
||||||
sticky bool // never fall back to classical for a peer that completed PQ
|
|
||||||
repairDelay time.Duration // delay between data and repair fragments
|
|
||||||
}
|
|
||||||
|
|
||||||
func pqHandshakeConfigFrom(c *config.C) pqHandshakeConfig {
|
|
||||||
cfg := pqHandshakeConfig{
|
|
||||||
initiate: c.GetBool("handshakes.pq.initiate", false),
|
|
||||||
accept: c.GetBool("handshakes.pq.accept", false),
|
|
||||||
require: c.GetBool("handshakes.pq.require", false),
|
|
||||||
sticky: c.GetBool("handshakes.pq.sticky", false),
|
|
||||||
repairDelay: c.GetDuration("handshakes.pq.repair_delay", DefaultPQRepairDelay),
|
|
||||||
}
|
|
||||||
if cfg.require {
|
|
||||||
cfg.initiate = true
|
|
||||||
cfg.accept = true
|
|
||||||
}
|
|
||||||
return cfg
|
|
||||||
}
|
|
||||||
|
|
||||||
// pqConfig returns the post-quantum settings in effect.
|
|
||||||
func (hm *HandshakeManager) pqConfig() *pqHandshakeConfig {
|
|
||||||
return hm.pq.Load()
|
|
||||||
}
|
|
||||||
|
|
||||||
// reloadPQ applies changed post-quantum settings. Handshakes already in flight
|
|
||||||
// keep going; the new settings apply to the next attempt and packet.
|
|
||||||
func (hm *HandshakeManager) reloadPQ(c *config.C) {
|
|
||||||
if !c.HasChanged("handshakes.pq") {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
old := hm.pqConfig()
|
|
||||||
cfg := pqHandshakeConfigFrom(c)
|
|
||||||
hm.pq.Store(&cfg)
|
|
||||||
hm.l.Info("Post-quantum handshake settings changed",
|
|
||||||
"initiate", cfg.initiate, "oldInitiate", old.initiate,
|
|
||||||
"accept", cfg.accept, "oldAccept", old.accept,
|
|
||||||
"require", cfg.require, "oldRequire", old.require,
|
|
||||||
"sticky", cfg.sticky, "oldSticky", old.sticky,
|
|
||||||
"repairDelay", cfg.repairDelay, "oldRepairDelay", old.repairDelay,
|
|
||||||
)
|
|
||||||
}
|
|
||||||
|
|
||||||
// pqAttempt is the initiator's post-quantum attempt for a pending handshake. It
|
|
||||||
// lives alongside the classical attempt in HandshakeHostInfo and has its own
|
|
||||||
// local index, so whichever answer arrives first wins.
|
|
||||||
type pqAttempt struct {
|
|
||||||
machine *handshake.Machine
|
|
||||||
index uint32
|
|
||||||
sender *fragment.Sender
|
|
||||||
msg2 *fragment.Assembly
|
|
||||||
cookieResendAt time.Time // last resend prompted by a cookie reply
|
|
||||||
heard bool // a msg2 fragment or cookie reply arrived, so the peer speaks PQ
|
|
||||||
}
|
|
||||||
|
|
||||||
// pqFragKey identifies one msg1 being reassembled.
|
|
||||||
type pqFragKey struct {
|
|
||||||
addr netip.AddrPort
|
|
||||||
relay uint32
|
|
||||||
fragID uint32
|
|
||||||
}
|
|
||||||
|
|
||||||
// pqFragSource groups msg1 reassemblies for the per-source quota: an IPv4 /32,
|
|
||||||
// an IPv6 /64, or one relay channel.
|
|
||||||
type pqFragSource struct {
|
|
||||||
prefix netip.Prefix
|
|
||||||
relay uint32
|
|
||||||
}
|
|
||||||
|
|
||||||
func pqFragKeyFor(via ViaSender, fragID uint32) (pqFragKey, pqFragSource) {
|
|
||||||
if via.IsRelayed {
|
|
||||||
return pqFragKey{relay: via.relay.LocalIndex, fragID: fragID},
|
|
||||||
pqFragSource{relay: via.relay.LocalIndex}
|
|
||||||
}
|
|
||||||
addr := via.UdpAddr.Addr().Unmap()
|
|
||||||
bits := 64
|
|
||||||
if addr.Is4() {
|
|
||||||
bits = 32
|
|
||||||
}
|
|
||||||
prefix, _ := addr.Prefix(bits)
|
|
||||||
return pqFragKey{addr: via.UdpAddr, fragID: fragID}, pqFragSource{prefix: prefix}
|
|
||||||
}
|
|
||||||
|
|
||||||
// reassembled rebuilds the packet the handshake Machine expects from the header
|
|
||||||
// of a fragment and the decoded message.
|
|
||||||
func reassembled(h *header.H, msg []byte) []byte {
|
|
||||||
p := make([]byte, header.Len, header.Len+len(msg))
|
|
||||||
header.Encode(p, header.Version, header.Handshake, h.Subtype, h.RemoteIndex, h.MessageCounter)
|
|
||||||
return append(p, msg...)
|
|
||||||
}
|
|
||||||
|
|
||||||
// usePQ decides whether this outbound attempt is post-quantum. A peer that does
|
|
||||||
// not speak PQ silently drops it, so timer retries alternate between PQ and
|
|
||||||
// classical, starting with PQ. An attempt triggered early by a lighthouse reply
|
|
||||||
// is sending to addresses nothing has been sent to yet, and a new path gets the
|
|
||||||
// PQ attempt first. With require, or for a peer that completed a PQ handshake
|
|
||||||
// when sticky is on, every attempt is PQ. Once anything has come back for the PQ
|
|
||||||
// attempt the peer evidently speaks PQ, and a classical attempt would only race
|
|
||||||
// it, so classical stops getting turns.
|
|
||||||
func (hm *HandshakeManager) usePQ(hh *HandshakeHostInfo, vpnIp netip.Addr, triggered bool) bool {
|
|
||||||
cfg := hm.pqConfig()
|
|
||||||
switch {
|
|
||||||
case !cfg.initiate:
|
|
||||||
return false
|
|
||||||
case cfg.require:
|
|
||||||
return true
|
|
||||||
case hh.pq != nil && hh.pq.heard:
|
|
||||||
return true
|
|
||||||
case cfg.sticky:
|
|
||||||
if _, ok := hm.pqPeers.Load(vpnIp); ok {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return hh.counter <= 1 || triggered || !hh.lastPQ
|
|
||||||
}
|
|
||||||
|
|
||||||
// relayEstablished pushes the pending handshake with target through a relay that
|
|
||||||
// just came up, rather than leaving it for the next retry. Nothing has gone over
|
|
||||||
// the relay yet, so like any new path it gets the PQ attempt first, which then
|
|
||||||
// counts as the PQ turn: the next retry is classical, as if it had been sent on
|
|
||||||
// schedule. Without this, relays coming up while the first attempt is in flight
|
|
||||||
// handed every relayed handshake to the classical retry.
|
|
||||||
func (hm *HandshakeManager) relayEstablished(target netip.Addr, relayHI *HostInfo, relay *Relay) {
|
|
||||||
hh := hm.queryVpnIp(target)
|
|
||||||
if hh == nil {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
hh.Lock()
|
|
||||||
defer hh.Unlock()
|
|
||||||
if hm.queryVpnIp(target) != hh {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
var now, later [][]byte
|
|
||||||
switch {
|
|
||||||
case hh.pq != nil:
|
|
||||||
var err error
|
|
||||||
now, later, err = hh.pq.sender.Attempt(fragment.DefaultRepair(hh.pq.sender.Layout().K))
|
|
||||||
if err != nil {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
hh.lastPQ = true
|
|
||||||
case hh.ready:
|
|
||||||
now = [][]byte{hh.hostinfo.HandshakePacket[handshakePacketStage0]}
|
|
||||||
default:
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
f := hm.f
|
|
||||||
hh.hostinfo.logger(hm.l).Info("Send handshake via new relay", "relay", relayHI.vpnAddrs[0])
|
|
||||||
_ = hm.sendFragmented(now, later, func(p []byte) error {
|
|
||||||
f.SendVia(relayHI, relay, p, make([]byte, 12), make([]byte, mtu), false, 0)
|
|
||||||
return nil
|
|
||||||
})
|
|
||||||
}
|
|
||||||
|
|
||||||
// buildPQAttempt creates the initiator's PQ Machine and msg1 sender.
|
|
||||||
func (hm *HandshakeManager) buildPQAttempt(hh *HandshakeHostInfo) bool {
|
|
||||||
cs := hm.f.pki.getCertState()
|
|
||||||
v := hm.initiatingVersion(hh, cs)
|
|
||||||
if cs.GetCredential(v) == nil {
|
|
||||||
hm.f.l.Error("Unable to handshake with host because no certificate is available",
|
|
||||||
"vpnAddrs", hh.hostinfo.vpnAddrs, "certVersion", v)
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
|
|
||||||
pq := &pqAttempt{}
|
|
||||||
machine, err := handshake.NewMachine(
|
|
||||||
v, cs.GetCredential,
|
|
||||||
hm.certVerifier(), func() (uint32, error) { return hm.allocatePQIndex(hh, pq) },
|
|
||||||
true, pqSubtype,
|
|
||||||
)
|
|
||||||
if err != nil {
|
|
||||||
hm.f.l.Error("Failed to create handshake machine",
|
|
||||||
"vpnAddrs", hh.hostinfo.vpnAddrs, "error", err)
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
|
|
||||||
msg, err := machine.Initiate(nil)
|
|
||||||
if err != nil {
|
|
||||||
hm.f.l.Error("Failed to initiate handshake",
|
|
||||||
"vpnAddrs", hh.hostinfo.vpnAddrs, "error", err)
|
|
||||||
hm.releasePQIndex(hh, pq)
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
|
|
||||||
sender, err := fragment.NewSender(msg[header.Len:], pqSubtype, 0, 1, pq.index)
|
|
||||||
if err != nil {
|
|
||||||
hm.f.l.Error("Failed to fragment handshake",
|
|
||||||
"vpnAddrs", hh.hostinfo.vpnAddrs, "error", err)
|
|
||||||
hm.releasePQIndex(hh, pq)
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
|
|
||||||
pq.machine = machine
|
|
||||||
pq.sender = sender
|
|
||||||
hh.pq = pq
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
|
|
||||||
// allocatePQIndex registers a local index for the PQ attempt. Unlike
|
|
||||||
// allocateIndex it leaves hostinfo.localIndexId alone; that is settled when one
|
|
||||||
// of the attempts completes.
|
|
||||||
func (hm *HandshakeManager) allocatePQIndex(hh *HandshakeHostInfo, pq *pqAttempt) (uint32, error) {
|
|
||||||
hm.mainHostMap.RLock()
|
|
||||||
defer hm.mainHostMap.RUnlock()
|
|
||||||
hm.Lock()
|
|
||||||
defer hm.Unlock()
|
|
||||||
|
|
||||||
for range 32 {
|
|
||||||
index, err := generateIndex(hm.l)
|
|
||||||
if err != nil {
|
|
||||||
return 0, err
|
|
||||||
}
|
|
||||||
|
|
||||||
_, inPending := hm.indexes[index]
|
|
||||||
_, inMain := hm.mainHostMap.Indexes[index]
|
|
||||||
|
|
||||||
if !inMain && !inPending {
|
|
||||||
pq.index = index
|
|
||||||
hm.indexes[index] = hh
|
|
||||||
return index, nil
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
return 0, errors.New("failed to generate unique localIndexId")
|
|
||||||
}
|
|
||||||
|
|
||||||
func (hm *HandshakeManager) releasePQIndex(hh *HandshakeHostInfo, pq *pqAttempt) {
|
|
||||||
hm.Lock()
|
|
||||||
defer hm.Unlock()
|
|
||||||
if pq.index != 0 && hm.indexes[pq.index] == hh {
|
|
||||||
delete(hm.indexes, pq.index)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// settleIndex makes winner the hostinfo's local index and releases the index of
|
|
||||||
// the attempt that lost.
|
|
||||||
func (hm *HandshakeManager) settleIndex(hh *HandshakeHostInfo, winner uint32) {
|
|
||||||
hm.Lock()
|
|
||||||
defer hm.Unlock()
|
|
||||||
for _, idx := range []uint32{hh.hostinfo.localIndexId, hh.pqIndex()} {
|
|
||||||
if idx != 0 && idx != winner && hm.indexes[idx] == hh {
|
|
||||||
delete(hm.indexes, idx)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
hh.hostinfo.localIndexId = winner
|
|
||||||
}
|
|
||||||
|
|
||||||
func (hh *HandshakeHostInfo) pqIndex() uint32 {
|
|
||||||
if hh.pq == nil {
|
|
||||||
return 0
|
|
||||||
}
|
|
||||||
return hh.pq.index
|
|
||||||
}
|
|
||||||
|
|
||||||
// handleFragment routes one fragment of a PQ handshake message.
|
|
||||||
func (hm *HandshakeManager) handleFragment(via ViaSender, packet []byte, h *header.H) {
|
|
||||||
if h.MessageCounter == pqCookieCounter {
|
|
||||||
hm.handleCookie(via, packet, h)
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
fh, sym, err := fragment.Parse(packet[header.Len:])
|
|
||||||
if err != nil {
|
|
||||||
hm.l.Debug("dropping malformed handshake fragment", "from", via, "error", err)
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
switch h.MessageCounter {
|
|
||||||
case 1:
|
|
||||||
if !hm.pqConfig().accept {
|
|
||||||
hm.l.Debug("dropping post-quantum handshake, not accepting them", "from", via)
|
|
||||||
return
|
|
||||||
}
|
|
||||||
if h.RemoteIndex != 0 {
|
|
||||||
hm.l.Debug("dropping stage-1 handshake with non-zero RemoteIndex",
|
|
||||||
"from", via, "remoteIndex", h.RemoteIndex)
|
|
||||||
return
|
|
||||||
}
|
|
||||||
now := time.Now()
|
|
||||||
key, src := pqFragKeyFor(via, fh.FragID)
|
|
||||||
if hm.pqTable.Load() >= pqCookieLoad && !(fh.HasCookie() && hm.pqCookies.valid(key, fh.Cookie, now)) {
|
|
||||||
hm.sendCookie(via, fh, key, len(packet), now)
|
|
||||||
return
|
|
||||||
}
|
|
||||||
res, err := hm.pqTable.Add(key, src, now, fh, sym)
|
|
||||||
if err != nil {
|
|
||||||
hm.l.Debug("dropping handshake fragment", "from", via, "error", err)
|
|
||||||
return
|
|
||||||
}
|
|
||||||
if res == nil {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
if existing := hm.pqAnswered.lookup(res.Msg, time.Now()); existing != nil {
|
|
||||||
// Already answered: resend, rate limited, with fresh symbols.
|
|
||||||
if msg := existing.HandshakePacket[handshakePacketStage2]; msg != nil {
|
|
||||||
hm.sendHandshakeResponse(via, msg, existing, true, res.Received)
|
|
||||||
}
|
|
||||||
return
|
|
||||||
}
|
|
||||||
hm.beginHandshake(via, reassembled(h, res.Msg), h, res.Received)
|
|
||||||
|
|
||||||
case 2:
|
|
||||||
if hh := hm.queryIndex(h.RemoteIndex); hh != nil {
|
|
||||||
hm.continuePQ(via, hh, h, fh, sym)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// continuePQ collects msg2 fragments for the initiator's PQ attempt.
|
|
||||||
func (hm *HandshakeManager) continuePQ(via ViaSender, hh *HandshakeHostInfo, h *header.H, fh fragment.Header, sym []byte) {
|
|
||||||
hh.Lock()
|
|
||||||
defer hh.Unlock()
|
|
||||||
|
|
||||||
pq := hh.pq
|
|
||||||
if pq == nil || pq.index != h.RemoteIndex || !hm.stillPending(hh, pq.index) {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
pq.heard = true
|
|
||||||
|
|
||||||
if pq.msg2 == nil {
|
|
||||||
a, err := fragment.NewAssembly(fh)
|
|
||||||
if err != nil {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
pq.msg2 = a
|
|
||||||
}
|
|
||||||
ready, err := pq.msg2.Add(fh, sym)
|
|
||||||
if errors.Is(err, fragment.ErrMismatch) {
|
|
||||||
// The responder's FragID and MsgLen never change, so this is a stray or a
|
|
||||||
// forgery. Start over from this fragment rather than wedge.
|
|
||||||
pq.msg2 = nil
|
|
||||||
return
|
|
||||||
}
|
|
||||||
if err != nil || !ready {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
msg, err := pq.msg2.Decode()
|
|
||||||
pq.msg2 = nil
|
|
||||||
if err != nil {
|
|
||||||
hm.l.Debug("failed to decode handshake fragments", "from", via, "error", err)
|
|
||||||
return
|
|
||||||
}
|
|
||||||
hm.processResponse(via, hh, pq.machine, reassembled(h, msg))
|
|
||||||
}
|
|
||||||
|
|
||||||
// sendFragmented sends packets to a peer: now immediately and later after the
|
|
||||||
// repair delay. It returns the first error from the immediate sends; errors from
|
|
||||||
// delayed sends are only logged.
|
|
||||||
func (hm *HandshakeManager) sendFragmented(now, later [][]byte, send func([]byte) error) error {
|
|
||||||
var first error
|
|
||||||
for _, p := range now {
|
|
||||||
if err := send(p); err != nil && first == nil {
|
|
||||||
first = err
|
|
||||||
}
|
|
||||||
}
|
|
||||||
sendLater := func() {
|
|
||||||
for _, p := range later {
|
|
||||||
if err := send(p); err != nil {
|
|
||||||
hm.l.Debug("Failed to send handshake repair fragment", "error", err)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
delay := hm.pqConfig().repairDelay
|
|
||||||
switch {
|
|
||||||
case len(later) == 0:
|
|
||||||
case delay <= 0:
|
|
||||||
sendLater()
|
|
||||||
default:
|
|
||||||
time.AfterFunc(delay, sendLater)
|
|
||||||
}
|
|
||||||
return first
|
|
||||||
}
|
|
||||||
|
|
||||||
// sendFragmentedResponse sends the responder's msg2 as fragments. A resend of a
|
|
||||||
// cached response (cached) offers fresh symbols and is rate limited to one per
|
|
||||||
// retry interval. received is how many bytes the triggering msg1 took, which
|
|
||||||
// bounds what may be sent back before the address is validated.
|
|
||||||
func (hm *HandshakeManager) sendFragmentedResponse(via ViaSender, msg []byte, hostinfo *HostInfo, cached bool, received int) error {
|
|
||||||
now := time.Now()
|
|
||||||
if cached {
|
|
||||||
last := hostinfo.handshakeResendAt.Load()
|
|
||||||
if now.UnixNano()-last < int64(hm.config.tryInterval) ||
|
|
||||||
!hostinfo.handshakeResendAt.CompareAndSwap(last, now.UnixNano()) {
|
|
||||||
return errors.New("handshake response resend rate limited")
|
|
||||||
}
|
|
||||||
} else {
|
|
||||||
hostinfo.handshakeResendAt.Store(now.UnixNano())
|
|
||||||
}
|
|
||||||
|
|
||||||
var h header.H
|
|
||||||
if err := h.Parse(msg); err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
s, err := fragment.NewSender(msg[header.Len:], h.Subtype, h.RemoteIndex, h.MessageCounter, hostinfo.localIndexId)
|
|
||||||
if err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
|
|
||||||
l := s.Layout()
|
|
||||||
repair := fragment.DefaultRepair(l.K)
|
|
||||||
if received > 0 {
|
|
||||||
pktLen := header.Len + fragment.HeaderLen + l.SymbolSize
|
|
||||||
budget := pqAmplification * received / pktLen
|
|
||||||
if budget < l.K {
|
|
||||||
return errors.New("handshake response exceeds the amplification budget")
|
|
||||||
}
|
|
||||||
repair = min(repair, budget-l.K)
|
|
||||||
}
|
|
||||||
|
|
||||||
n := uint32(l.K + repair)
|
|
||||||
s.SetNext(int(hostinfo.handshakeNextSymbol.Add(n) - n))
|
|
||||||
pkts, later, err := s.Attempt(repair)
|
|
||||||
if err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
|
|
||||||
if via.IsRelayed {
|
|
||||||
if via.relay == nil {
|
|
||||||
return errors.New("both addr and via.relay are nil")
|
|
||||||
}
|
|
||||||
// We received a valid handshake on this relay, so make sure the relay
|
|
||||||
// state reflects that, in case it had been marked Disestablished.
|
|
||||||
hostinfo.relayState.InsertRelayTo(via.relayHI.vpnAddrs[0])
|
|
||||||
via.relayHI.relayState.UpdateRelayForByIdxState(via.relay.LocalIndex, Established)
|
|
||||||
}
|
|
||||||
hm.f.messageMetrics.Tx(header.Handshake, h.Subtype, int64(len(pkts)+len(later)))
|
|
||||||
return hm.sendFragmented(pkts, later, hm.sendTo(via))
|
|
||||||
}
|
|
||||||
|
|
||||||
// notePQPeer remembers peers that completed a PQ handshake, for sticky mode.
|
|
||||||
func (hm *HandshakeManager) notePQPeer(subtype header.MessageSubType, vpnAddrs []netip.Addr) {
|
|
||||||
if !hm.pqConfig().sticky || subtype != pqSubtype {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
for _, a := range vpnAddrs {
|
|
||||||
hm.pqPeers.Store(a, struct{}{})
|
|
||||||
}
|
|
||||||
if hm.l.Enabled(context.Background(), slog.LevelDebug) {
|
|
||||||
hm.l.Debug("Remembering post-quantum peer", "vpnAddrs", vpnAddrs)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// pqAnswered remembers the msg1s a responder recently answered, keyed by hash,
|
|
||||||
// so a repeat is recognised before any noise, KEM or certificate work. Repeats
|
|
||||||
// are routine: the trailing repair fragments of an attempt rebuild a msg1 that
|
|
||||||
// its data fragments already completed, and a retrying initiator offers fresh
|
|
||||||
// symbols for the same msg1. Entries only exist for completed handshakes, which
|
|
||||||
// need a valid certificate, and live as long as an initiator keeps retrying.
|
|
||||||
type pqAnswered struct {
|
|
||||||
sync.Mutex
|
|
||||||
ttl time.Duration
|
|
||||||
entries map[[sha256.Size]byte]pqAnsweredEntry
|
|
||||||
}
|
|
||||||
|
|
||||||
type pqAnsweredEntry struct {
|
|
||||||
hostinfo *HostInfo
|
|
||||||
at time.Time
|
|
||||||
}
|
|
||||||
|
|
||||||
const pqAnsweredMax = 4096
|
|
||||||
|
|
||||||
func newPQAnswered(ttl time.Duration) *pqAnswered {
|
|
||||||
return &pqAnswered{ttl: ttl, entries: map[[sha256.Size]byte]pqAnsweredEntry{}}
|
|
||||||
}
|
|
||||||
|
|
||||||
func (a *pqAnswered) add(msg1 []byte, hostinfo *HostInfo, now time.Time) {
|
|
||||||
a.Lock()
|
|
||||||
defer a.Unlock()
|
|
||||||
if len(a.entries) >= pqAnsweredMax {
|
|
||||||
for k := range a.entries {
|
|
||||||
delete(a.entries, k)
|
|
||||||
break
|
|
||||||
}
|
|
||||||
}
|
|
||||||
a.entries[sha256.Sum256(msg1)] = pqAnsweredEntry{hostinfo: hostinfo, at: now}
|
|
||||||
}
|
|
||||||
|
|
||||||
func (a *pqAnswered) lookup(msg1 []byte, now time.Time) *HostInfo {
|
|
||||||
a.Lock()
|
|
||||||
defer a.Unlock()
|
|
||||||
e, ok := a.entries[sha256.Sum256(msg1)]
|
|
||||||
if !ok || now.Sub(e.at) > a.ttl {
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
return e.hostinfo
|
|
||||||
}
|
|
||||||
|
|
||||||
func (a *pqAnswered) expire(now time.Time) {
|
|
||||||
a.Lock()
|
|
||||||
defer a.Unlock()
|
|
||||||
for k, e := range a.entries {
|
|
||||||
if now.Sub(e.at) > a.ttl {
|
|
||||||
delete(a.entries, k)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// A responder whose msg1 table is under load stops keeping state for senders
|
|
||||||
// that have not shown they receive at their address. It answers a fragment
|
|
||||||
// without a valid cookie with a cookie reply and keeps nothing; the initiator
|
|
||||||
// resends with the cookie attached. This is WireGuard's under-load cookie, QUIC's
|
|
||||||
// Retry and SCTP's state cookie: one extra round trip, only while under attack.
|
|
||||||
const (
|
|
||||||
// pqCookieLoad is the table load above which msg1 fragments need a cookie.
|
|
||||||
pqCookieLoad = 0.5
|
|
||||||
|
|
||||||
// pqCookieCounter marks a cookie reply in the header's message counter.
|
|
||||||
// Handshake messages count from 1.
|
|
||||||
pqCookieCounter = 0
|
|
||||||
|
|
||||||
// pqCookieRotate is how often the cookie secret changes. A cookie stays
|
|
||||||
// valid for between one and two rotations.
|
|
||||||
pqCookieRotate = 2 * time.Minute
|
|
||||||
|
|
||||||
pqCookieReplyLen = header.Len + fragment.CookieLen
|
|
||||||
)
|
|
||||||
|
|
||||||
// pqCookies mints and checks cookies: an HMAC over the sender's address (or relay
|
|
||||||
// channel) and FragID under a rotating secret, with the previous secret still
|
|
||||||
// accepted.
|
|
||||||
type pqCookies struct {
|
|
||||||
sync.Mutex
|
|
||||||
secrets [2][32]byte
|
|
||||||
rotatedAt time.Time
|
|
||||||
}
|
|
||||||
|
|
||||||
func newPQCookies(now time.Time) *pqCookies {
|
|
||||||
c := &pqCookies{rotatedAt: now}
|
|
||||||
_, _ = rand.Read(c.secrets[0][:])
|
|
||||||
_, _ = rand.Read(c.secrets[1][:])
|
|
||||||
return c
|
|
||||||
}
|
|
||||||
|
|
||||||
func (c *pqCookies) rotate(now time.Time) {
|
|
||||||
if now.Sub(c.rotatedAt) < pqCookieRotate {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
c.secrets[1] = c.secrets[0]
|
|
||||||
_, _ = rand.Read(c.secrets[0][:])
|
|
||||||
c.rotatedAt = now
|
|
||||||
}
|
|
||||||
|
|
||||||
func cookieMAC(secret []byte, key pqFragKey) fragment.Cookie {
|
|
||||||
mac := hmac.New(sha256.New, secret)
|
|
||||||
addr := key.addr.Addr().As16()
|
|
||||||
mac.Write(addr[:])
|
|
||||||
var b [10]byte
|
|
||||||
binary.BigEndian.PutUint16(b[0:], key.addr.Port())
|
|
||||||
binary.BigEndian.PutUint32(b[2:], key.relay)
|
|
||||||
binary.BigEndian.PutUint32(b[6:], key.fragID)
|
|
||||||
mac.Write(b[:])
|
|
||||||
var c fragment.Cookie
|
|
||||||
copy(c[:], mac.Sum(nil))
|
|
||||||
return c
|
|
||||||
}
|
|
||||||
|
|
||||||
func (c *pqCookies) make(key pqFragKey, now time.Time) fragment.Cookie {
|
|
||||||
c.Lock()
|
|
||||||
defer c.Unlock()
|
|
||||||
c.rotate(now)
|
|
||||||
return cookieMAC(c.secrets[0][:], key)
|
|
||||||
}
|
|
||||||
|
|
||||||
func (c *pqCookies) valid(key pqFragKey, cookie fragment.Cookie, now time.Time) bool {
|
|
||||||
c.Lock()
|
|
||||||
defer c.Unlock()
|
|
||||||
c.rotate(now)
|
|
||||||
for _, s := range c.secrets {
|
|
||||||
want := cookieMAC(s[:], key)
|
|
||||||
if hmac.Equal(want[:], cookie[:]) {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
|
|
||||||
// sendCookie answers a msg1 fragment that arrived without a valid cookie while
|
|
||||||
// under load. The reply is never larger than what triggered it, and replies are
|
|
||||||
// rate limited as a whole.
|
|
||||||
func (hm *HandshakeManager) sendCookie(via ViaSender, fh fragment.Header, key pqFragKey, received int, now time.Time) {
|
|
||||||
if received < pqCookieReplyLen {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
if _, ok := hm.pqCookieLimiter.Allow(); !ok {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
c := hm.pqCookies.make(key, now)
|
|
||||||
reply := make([]byte, header.Len, pqCookieReplyLen)
|
|
||||||
header.Encode(reply, header.Version, header.Handshake, pqSubtype, fh.FragID, pqCookieCounter)
|
|
||||||
reply = append(reply, c[:]...)
|
|
||||||
hm.f.messageMetrics.Tx(header.Handshake, pqSubtype, 1)
|
|
||||||
if err := hm.sendTo(via)(reply); err != nil {
|
|
||||||
hm.l.Debug("Failed to send handshake cookie", "to", via, "error", err)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// handleCookie attaches a responder's cookie to the PQ attempt it names and
|
|
||||||
// resends right away, at most once per retry interval, rather than waiting for
|
|
||||||
// the next attempt.
|
|
||||||
func (hm *HandshakeManager) handleCookie(via ViaSender, packet []byte, h *header.H) {
|
|
||||||
if len(packet) != pqCookieReplyLen {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
hh := hm.queryIndex(h.RemoteIndex)
|
|
||||||
if hh == nil {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
hh.Lock()
|
|
||||||
defer hh.Unlock()
|
|
||||||
|
|
||||||
pq := hh.pq
|
|
||||||
if pq == nil || pq.index != h.RemoteIndex || !hm.stillPending(hh, pq.index) {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
var c fragment.Cookie
|
|
||||||
copy(c[:], packet[header.Len:])
|
|
||||||
pq.sender.SetCookie(c)
|
|
||||||
pq.heard = true
|
|
||||||
|
|
||||||
now := time.Now()
|
|
||||||
if now.Sub(pq.cookieResendAt) < hm.config.tryInterval {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
pq.cookieResendAt = now
|
|
||||||
pkts, later, err := pq.sender.Attempt(fragment.DefaultRepair(pq.sender.Layout().K))
|
|
||||||
if err != nil {
|
|
||||||
return
|
|
||||||
}
|
|
||||||
hm.messageMetrics.Tx(header.Handshake, pqSubtype, int64(len(pkts)+len(later)))
|
|
||||||
if err := hm.sendFragmented(pkts, later, hm.sendTo(via)); err != nil {
|
|
||||||
hm.l.Debug("Failed to resend handshake with cookie", "to", via, "error", err)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// sendTo returns a function sending a packet back the way via came: directly, or
|
|
||||||
// through the relay it arrived on.
|
|
||||||
func (hm *HandshakeManager) sendTo(via ViaSender) func([]byte) error {
|
|
||||||
f := hm.f
|
|
||||||
if !via.IsRelayed {
|
|
||||||
return func(p []byte) error {
|
|
||||||
return f.outside.WriteTo(p, via.UdpAddr)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return func(p []byte) error {
|
|
||||||
if via.relay == nil {
|
|
||||||
return errors.New("both addr and via.relay are nil")
|
|
||||||
}
|
|
||||||
f.SendVia(via.relayHI, via.relay, p, make([]byte, 12), make([]byte, mtu), false, 0)
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
}
|
|
||||||
@@ -1,398 +0,0 @@
|
|||||||
package nebula
|
|
||||||
|
|
||||||
import (
|
|
||||||
"math/rand/v2"
|
|
||||||
"net/netip"
|
|
||||||
"sync"
|
|
||||||
"testing"
|
|
||||||
"time"
|
|
||||||
|
|
||||||
"github.com/slackhq/nebula/config"
|
|
||||||
"github.com/slackhq/nebula/handshake/fragment"
|
|
||||||
"github.com/slackhq/nebula/header"
|
|
||||||
"github.com/slackhq/nebula/test"
|
|
||||||
"github.com/slackhq/nebula/udp"
|
|
||||||
"github.com/stretchr/testify/assert"
|
|
||||||
"github.com/stretchr/testify/require"
|
|
||||||
)
|
|
||||||
|
|
||||||
// recordingConn captures what is written to it.
|
|
||||||
type recordingConn struct {
|
|
||||||
udp.NoopConn
|
|
||||||
sync.Mutex
|
|
||||||
sent [][]byte
|
|
||||||
}
|
|
||||||
|
|
||||||
func (c *recordingConn) WriteTo(b []byte, _ netip.AddrPort) error {
|
|
||||||
c.Lock()
|
|
||||||
defer c.Unlock()
|
|
||||||
c.sent = append(c.sent, append([]byte(nil), b...))
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
func (c *recordingConn) take() [][]byte {
|
|
||||||
c.Lock()
|
|
||||||
defer c.Unlock()
|
|
||||||
s := c.sent
|
|
||||||
c.sent = nil
|
|
||||||
return s
|
|
||||||
}
|
|
||||||
|
|
||||||
func newPQTestManager(t *testing.T) (*HandshakeManager, *recordingConn) {
|
|
||||||
l := test.NewLogger()
|
|
||||||
conn := &recordingConn{}
|
|
||||||
cfg := defaultHandshakeConfig
|
|
||||||
cfg.pq = pqHandshakeConfig{initiate: true, accept: true}
|
|
||||||
hm := NewHandshakeManager(l, newHostMap(l), newTestLighthouse(), conn, cfg)
|
|
||||||
hm.f = &Interface{
|
|
||||||
handshakeManager: hm,
|
|
||||||
outside: conn,
|
|
||||||
messageMetrics: newMessageMetricsOnlyRecvError(),
|
|
||||||
l: l,
|
|
||||||
}
|
|
||||||
return hm, conn
|
|
||||||
}
|
|
||||||
|
|
||||||
// fragmentIndexes checks every packet is a fragment of the expected response and
|
|
||||||
// returns their symbol indexes.
|
|
||||||
func fragmentIndexes(t *testing.T, pkts [][]byte, fragID, remoteIndex uint32) []int {
|
|
||||||
t.Helper()
|
|
||||||
var out []int
|
|
||||||
for _, p := range pkts {
|
|
||||||
require.LessOrEqual(t, len(p), fragment.MaxPacketLen)
|
|
||||||
var h header.H
|
|
||||||
require.NoError(t, h.Parse(p))
|
|
||||||
assert.Equal(t, pqSubtype, h.Subtype)
|
|
||||||
assert.Equal(t, remoteIndex, h.RemoteIndex)
|
|
||||||
assert.Equal(t, uint64(2), h.MessageCounter)
|
|
||||||
fh, _, err := fragment.Parse(p[header.Len:])
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, fragID, fh.FragID)
|
|
||||||
out = append(out, int(fh.Index))
|
|
||||||
}
|
|
||||||
return out
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestSendFragmentedResponse(t *testing.T) {
|
|
||||||
hm, conn := newPQTestManager(t)
|
|
||||||
via := ViaSender{UdpAddr: netip.MustParseAddrPort("192.0.2.1:4242")}
|
|
||||||
hostinfo := &HostInfo{localIndexId: 77}
|
|
||||||
|
|
||||||
// A 2000 byte message is 2 symbols of 1000, so packets of 1024 bytes.
|
|
||||||
msg := make([]byte, header.Len, header.Len+2000)
|
|
||||||
header.Encode(msg, header.Version, header.Handshake, pqSubtype, 5, 2)
|
|
||||||
r := rand.New(rand.NewPCG(1, 1))
|
|
||||||
for range 2000 {
|
|
||||||
msg = append(msg, byte(r.Uint32()))
|
|
||||||
}
|
|
||||||
const pktLen = header.Len + fragment.HeaderLen + 1000
|
|
||||||
|
|
||||||
t.Run("first send", func(t *testing.T) {
|
|
||||||
require.NoError(t, hm.sendFragmentedResponse(via, msg, hostinfo, false, 0))
|
|
||||||
assert.Equal(t, []int{0, 1, 2, 3}, fragmentIndexes(t, conn.take(), 77, 5))
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("resends are rate limited", func(t *testing.T) {
|
|
||||||
require.Error(t, hm.sendFragmentedResponse(via, msg, hostinfo, true, 10*pktLen))
|
|
||||||
assert.Empty(t, conn.take())
|
|
||||||
})
|
|
||||||
|
|
||||||
allowResend := func() {
|
|
||||||
hostinfo.handshakeResendAt.Store(time.Now().Add(-time.Second).UnixNano())
|
|
||||||
}
|
|
||||||
|
|
||||||
t.Run("resend offers fresh symbols", func(t *testing.T) {
|
|
||||||
allowResend()
|
|
||||||
require.NoError(t, hm.sendFragmentedResponse(via, msg, hostinfo, true, 10*pktLen))
|
|
||||||
assert.Equal(t, []int{4, 5, 6, 7}, fragmentIndexes(t, conn.take(), 77, 5))
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("amplification budget trims repair", func(t *testing.T) {
|
|
||||||
allowResend()
|
|
||||||
// 3x of a little over one packet allows 3 packets: both data and 1 repair.
|
|
||||||
require.NoError(t, hm.sendFragmentedResponse(via, msg, hostinfo, true, pktLen+10))
|
|
||||||
assert.Equal(t, []int{8, 9, 10}, fragmentIndexes(t, conn.take(), 77, 5))
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("amplification budget below the data refuses", func(t *testing.T) {
|
|
||||||
allowResend()
|
|
||||||
require.Error(t, hm.sendFragmentedResponse(via, msg, hostinfo, true, pktLen/2))
|
|
||||||
assert.Empty(t, conn.take())
|
|
||||||
})
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestPQAnswered(t *testing.T) {
|
|
||||||
now := time.Unix(1000, 0)
|
|
||||||
a := newPQAnswered(5 * time.Second)
|
|
||||||
hi := &HostInfo{}
|
|
||||||
|
|
||||||
assert.Nil(t, a.lookup([]byte("msg1"), now))
|
|
||||||
a.add([]byte("msg1"), hi, now)
|
|
||||||
assert.Same(t, hi, a.lookup([]byte("msg1"), now.Add(time.Second)))
|
|
||||||
assert.Nil(t, a.lookup([]byte("other"), now))
|
|
||||||
assert.Nil(t, a.lookup([]byte("msg1"), now.Add(6*time.Second)), "stale entries are not answered")
|
|
||||||
|
|
||||||
a.expire(now.Add(6 * time.Second))
|
|
||||||
assert.Empty(t, a.entries)
|
|
||||||
|
|
||||||
for i := range pqAnsweredMax + 10 {
|
|
||||||
a.add([]byte{byte(i), byte(i >> 8)}, hi, now)
|
|
||||||
}
|
|
||||||
assert.Len(t, a.entries, pqAnsweredMax)
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestPQFragKeyFor(t *testing.T) {
|
|
||||||
k1, s1 := pqFragKeyFor(ViaSender{UdpAddr: netip.MustParseAddrPort("192.0.2.1:4242")}, 9)
|
|
||||||
k2, s2 := pqFragKeyFor(ViaSender{UdpAddr: netip.MustParseAddrPort("192.0.2.1:4243")}, 9)
|
|
||||||
assert.NotEqual(t, k1, k2, "different ports are different messages")
|
|
||||||
assert.Equal(t, s1, s2, "but share an IPv4 /32 quota")
|
|
||||||
|
|
||||||
_, s3 := pqFragKeyFor(ViaSender{UdpAddr: netip.MustParseAddrPort("[2001:db8::1]:1")}, 9)
|
|
||||||
_, s4 := pqFragKeyFor(ViaSender{UdpAddr: netip.MustParseAddrPort("[2001:db8::ffff]:1")}, 9)
|
|
||||||
assert.Equal(t, s3, s4, "an IPv6 /64 shares a quota")
|
|
||||||
|
|
||||||
_, s5 := pqFragKeyFor(ViaSender{UdpAddr: netip.MustParseAddrPort("[::ffff:192.0.2.1]:1")}, 9)
|
|
||||||
assert.Equal(t, s1, s5, "v4-mapped addresses count as IPv4")
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestPQCookies(t *testing.T) {
|
|
||||||
now := time.Unix(1000, 0)
|
|
||||||
c := newPQCookies(now)
|
|
||||||
key := pqFragKey{addr: netip.MustParseAddrPort("192.0.2.1:4242"), fragID: 9}
|
|
||||||
|
|
||||||
cookie := c.make(key, now)
|
|
||||||
assert.True(t, c.valid(key, cookie, now))
|
|
||||||
|
|
||||||
for _, other := range []pqFragKey{
|
|
||||||
{addr: netip.MustParseAddrPort("192.0.2.2:4242"), fragID: 9},
|
|
||||||
{addr: netip.MustParseAddrPort("192.0.2.1:4243"), fragID: 9},
|
|
||||||
{addr: netip.MustParseAddrPort("192.0.2.1:4242"), fragID: 10},
|
|
||||||
{addr: netip.MustParseAddrPort("192.0.2.1:4242"), relay: 1, fragID: 9},
|
|
||||||
} {
|
|
||||||
assert.False(t, c.valid(other, cookie, now), "%+v", other)
|
|
||||||
}
|
|
||||||
|
|
||||||
now = now.Add(pqCookieRotate)
|
|
||||||
assert.True(t, c.valid(key, cookie, now), "the previous secret is still accepted")
|
|
||||||
assert.NotEqual(t, cookie, c.make(key, now), "new cookies come from the new secret")
|
|
||||||
|
|
||||||
now = now.Add(pqCookieRotate)
|
|
||||||
assert.False(t, c.valid(key, cookie, now), "two rotations retire a cookie")
|
|
||||||
}
|
|
||||||
|
|
||||||
// pqMsg1Fragment builds the first fragment of a msg1, optionally with a cookie.
|
|
||||||
func pqMsg1Fragment(t *testing.T, fragID uint32, cookie *fragment.Cookie) ([]byte, *header.H) {
|
|
||||||
t.Helper()
|
|
||||||
s, err := fragment.NewSender(make([]byte, 2000), pqSubtype, 0, 1, fragID)
|
|
||||||
require.NoError(t, err)
|
|
||||||
if cookie != nil {
|
|
||||||
s.SetCookie(*cookie)
|
|
||||||
}
|
|
||||||
pkts, _, err := s.Attempt(0)
|
|
||||||
require.NoError(t, err)
|
|
||||||
var h header.H
|
|
||||||
require.NoError(t, h.Parse(pkts[0]))
|
|
||||||
return pkts[0], &h
|
|
||||||
}
|
|
||||||
|
|
||||||
// fillPQTable puts the responder's msg1 table at the cookie threshold.
|
|
||||||
func fillPQTable(t *testing.T, hm *HandshakeManager) {
|
|
||||||
t.Helper()
|
|
||||||
now := time.Now()
|
|
||||||
for i := 0; hm.pqTable.Load() < pqCookieLoad; i++ {
|
|
||||||
p, _ := pqMsg1Fragment(t, uint32(i+1), nil)
|
|
||||||
fh, sym, err := fragment.Parse(p[header.Len:])
|
|
||||||
require.NoError(t, err)
|
|
||||||
addr := netip.AddrPortFrom(netip.AddrFrom4([4]byte{198, 18, byte(i >> 8), byte(i)}), 4242)
|
|
||||||
key, src := pqFragKeyFor(ViaSender{UdpAddr: addr}, fh.FragID)
|
|
||||||
_, err = hm.pqTable.Add(key, src, now, fh, sym)
|
|
||||||
require.NoError(t, err)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestPQCookieUnderLoad(t *testing.T) {
|
|
||||||
hm, conn := newPQTestManager(t)
|
|
||||||
via := ViaSender{UdpAddr: netip.MustParseAddrPort("192.0.2.1:4242")}
|
|
||||||
|
|
||||||
t.Run("no cookie needed below the threshold", func(t *testing.T) {
|
|
||||||
p, h := pqMsg1Fragment(t, 5000, nil)
|
|
||||||
before := hm.pqTable.Len()
|
|
||||||
hm.handleFragment(via, p, h)
|
|
||||||
assert.Empty(t, conn.take())
|
|
||||||
assert.Equal(t, before+1, hm.pqTable.Len())
|
|
||||||
})
|
|
||||||
|
|
||||||
fillPQTable(t, hm)
|
|
||||||
|
|
||||||
var cookie fragment.Cookie
|
|
||||||
t.Run("a fragment without a cookie gets one and leaves no state", func(t *testing.T) {
|
|
||||||
p, h := pqMsg1Fragment(t, 7, nil)
|
|
||||||
before := hm.pqTable.Len()
|
|
||||||
hm.handleFragment(via, p, h)
|
|
||||||
assert.Equal(t, before, hm.pqTable.Len())
|
|
||||||
|
|
||||||
sent := conn.take()
|
|
||||||
require.Len(t, sent, 1)
|
|
||||||
reply := sent[0]
|
|
||||||
require.Len(t, reply, pqCookieReplyLen)
|
|
||||||
var rh header.H
|
|
||||||
require.NoError(t, rh.Parse(reply))
|
|
||||||
assert.Equal(t, header.Handshake, rh.Type)
|
|
||||||
assert.Equal(t, pqSubtype, rh.Subtype)
|
|
||||||
assert.Equal(t, uint32(7), rh.RemoteIndex, "the reply names the initiator's FragID")
|
|
||||||
assert.Equal(t, uint64(pqCookieCounter), rh.MessageCounter)
|
|
||||||
copy(cookie[:], reply[header.Len:])
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("a forged cookie gets a fresh one", func(t *testing.T) {
|
|
||||||
bad := cookie
|
|
||||||
bad[0] ^= 1
|
|
||||||
p, h := pqMsg1Fragment(t, 7, &bad)
|
|
||||||
before := hm.pqTable.Len()
|
|
||||||
hm.handleFragment(via, p, h)
|
|
||||||
assert.Equal(t, before, hm.pqTable.Len())
|
|
||||||
assert.Len(t, conn.take(), 1)
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("the cookie gets the fragment in", func(t *testing.T) {
|
|
||||||
p, h := pqMsg1Fragment(t, 7, &cookie)
|
|
||||||
before := hm.pqTable.Len()
|
|
||||||
hm.handleFragment(via, p, h)
|
|
||||||
assert.Equal(t, before+1, hm.pqTable.Len())
|
|
||||||
assert.Empty(t, conn.take())
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("a cookie is bound to its address", func(t *testing.T) {
|
|
||||||
p, h := pqMsg1Fragment(t, 7, &cookie)
|
|
||||||
hm.handleFragment(ViaSender{UdpAddr: netip.MustParseAddrPort("192.0.2.99:4242")}, p, h)
|
|
||||||
assert.Len(t, conn.take(), 1, "another address gets its own cookie instead")
|
|
||||||
})
|
|
||||||
|
|
||||||
t.Run("a reply never outgrows what prompted it", func(t *testing.T) {
|
|
||||||
p, h := pqMsg1Fragment(t, 8, nil)
|
|
||||||
hm.sendCookie(via, fragment.Header{FragID: 8}, pqFragKey{}, pqCookieReplyLen-1, time.Now())
|
|
||||||
assert.Empty(t, conn.take())
|
|
||||||
hm.handleFragment(via, p, h)
|
|
||||||
assert.Len(t, conn.take(), 1)
|
|
||||||
})
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestPQHandleCookie(t *testing.T) {
|
|
||||||
hm, conn := newPQTestManager(t)
|
|
||||||
via := ViaSender{UdpAddr: netip.MustParseAddrPort("192.0.2.1:4242")}
|
|
||||||
|
|
||||||
s, err := fragment.NewSender(make([]byte, 2000), pqSubtype, 0, 1, 99)
|
|
||||||
require.NoError(t, err)
|
|
||||||
_, _, err = s.Attempt(2)
|
|
||||||
require.NoError(t, err)
|
|
||||||
hh := &HandshakeHostInfo{hostinfo: &HostInfo{}, pq: &pqAttempt{index: 99, sender: s}}
|
|
||||||
hm.indexes[99] = hh
|
|
||||||
|
|
||||||
reply := make([]byte, header.Len, pqCookieReplyLen)
|
|
||||||
header.Encode(reply, header.Version, header.Handshake, pqSubtype, 99, pqCookieCounter)
|
|
||||||
reply = append(reply, bytes16(0xab)...)
|
|
||||||
var h header.H
|
|
||||||
require.NoError(t, h.Parse(reply))
|
|
||||||
|
|
||||||
hm.handleFragment(via, reply, &h)
|
|
||||||
assert.True(t, hh.pq.heard, "a cookie reply shows the peer speaks PQ")
|
|
||||||
sent := conn.take()
|
|
||||||
require.Len(t, sent, 4, "an immediate resend of fresh symbols")
|
|
||||||
for i, p := range sent {
|
|
||||||
fh, _, err := fragment.Parse(p[header.Len:])
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.True(t, fh.HasCookie())
|
|
||||||
assert.Equal(t, fragment.Cookie(bytes16(0xab)), fh.Cookie)
|
|
||||||
assert.Equal(t, uint8(4+i), fh.Index)
|
|
||||||
}
|
|
||||||
|
|
||||||
hm.handleFragment(via, reply, &h)
|
|
||||||
assert.Empty(t, conn.take(), "immediate resends are rate limited")
|
|
||||||
|
|
||||||
t.Run("replies for other indexes are ignored", func(t *testing.T) {
|
|
||||||
other := append([]byte(nil), reply...)
|
|
||||||
header.Encode(other, header.Version, header.Handshake, pqSubtype, 98, pqCookieCounter)
|
|
||||||
var oh header.H
|
|
||||||
require.NoError(t, oh.Parse(other))
|
|
||||||
hh.pq.cookieResendAt = time.Time{}
|
|
||||||
hm.handleFragment(via, other, &oh)
|
|
||||||
assert.Empty(t, conn.take())
|
|
||||||
})
|
|
||||||
}
|
|
||||||
|
|
||||||
func bytes16(b byte) []byte {
|
|
||||||
out := make([]byte, 16)
|
|
||||||
for i := range out {
|
|
||||||
out[i] = b
|
|
||||||
}
|
|
||||||
return out
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestReloadPQ(t *testing.T) {
|
|
||||||
l := test.NewLogger()
|
|
||||||
c := config.NewC(l)
|
|
||||||
require.NoError(t, c.LoadString(`handshakes: {pq: {initiate: false}}`))
|
|
||||||
cfg := defaultHandshakeConfig
|
|
||||||
cfg.pq = pqHandshakeConfigFrom(c)
|
|
||||||
hm := NewHandshakeManager(l, newHostMap(l), newTestLighthouse(), &udp.NoopConn{}, cfg)
|
|
||||||
c.RegisterReloadCallback(hm.reloadPQ)
|
|
||||||
|
|
||||||
assert.Equal(t, pqHandshakeConfig{repairDelay: DefaultPQRepairDelay}, *hm.pqConfig())
|
|
||||||
|
|
||||||
require.NoError(t, c.ReloadConfigString(`handshakes: {pq: {initiate: true, accept: true, sticky: true, repair_delay: 25ms}}`))
|
|
||||||
assert.Equal(t, pqHandshakeConfig{initiate: true, accept: true, sticky: true, repairDelay: 25 * time.Millisecond}, *hm.pqConfig())
|
|
||||||
|
|
||||||
before := hm.pqConfig()
|
|
||||||
require.NoError(t, c.ReloadConfigString(`handshakes: {try_interval: 1s, pq: {initiate: true, accept: true, sticky: true, repair_delay: 25ms}}`))
|
|
||||||
assert.Same(t, before, hm.pqConfig(), "an unrelated change leaves the settings alone")
|
|
||||||
|
|
||||||
require.NoError(t, c.ReloadConfigString(`handshakes: {}`))
|
|
||||||
assert.Equal(t, pqHandshakeConfig{repairDelay: DefaultPQRepairDelay}, *hm.pqConfig(), "removing the section restores the defaults")
|
|
||||||
|
|
||||||
require.NoError(t, c.ReloadConfigString(`handshakes: {pq: {require: true}}`))
|
|
||||||
assert.Equal(t, pqHandshakeConfig{initiate: true, accept: true, require: true, repairDelay: DefaultPQRepairDelay}, *hm.pqConfig(), "require implies initiate and accept")
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestUsePQ(t *testing.T) {
|
|
||||||
hm, _ := newPQTestManager(t)
|
|
||||||
peer := netip.MustParseAddr("10.1.0.1")
|
|
||||||
set := func(cfg pqHandshakeConfig) { hm.pq.Store(&cfg) }
|
|
||||||
|
|
||||||
// attempts plays a run of attempts, given whether each was triggered early,
|
|
||||||
// and returns which were PQ.
|
|
||||||
attempts := func(triggered ...bool) []bool {
|
|
||||||
hh := &HandshakeHostInfo{}
|
|
||||||
var out []bool
|
|
||||||
for _, tr := range triggered {
|
|
||||||
hh.counter++
|
|
||||||
hh.lastPQ = hm.usePQ(hh, peer, tr)
|
|
||||||
out = append(out, hh.lastPQ)
|
|
||||||
}
|
|
||||||
return out
|
|
||||||
}
|
|
||||||
|
|
||||||
set(pqHandshakeConfig{})
|
|
||||||
assert.Equal(t, []bool{false, false, false}, attempts(false, false, false), "off")
|
|
||||||
|
|
||||||
set(pqHandshakeConfig{initiate: true})
|
|
||||||
assert.Equal(t, []bool{true, false, true, false}, attempts(false, false, false, false), "timer retries alternate, PQ first")
|
|
||||||
assert.Equal(t, []bool{true, true, false, true, false}, attempts(false, true, false, true, false), "an early trigger is a new path, which gets PQ first")
|
|
||||||
assert.Equal(t, []bool{true, true, false}, attempts(true, true, false), "a triggered first attempt is PQ")
|
|
||||||
|
|
||||||
t.Run("hearing back stops the classical turns", func(t *testing.T) {
|
|
||||||
hh := &HandshakeHostInfo{pq: &pqAttempt{}}
|
|
||||||
hh.counter, hh.lastPQ = 1, true
|
|
||||||
hh.counter++
|
|
||||||
assert.False(t, hm.usePQ(hh, peer, false), "unheard, the classical attempt gets its turn")
|
|
||||||
hh.pq.heard = true
|
|
||||||
assert.True(t, hm.usePQ(hh, peer, false))
|
|
||||||
})
|
|
||||||
|
|
||||||
set(pqHandshakeConfig{initiate: true, accept: true, require: true})
|
|
||||||
assert.Equal(t, []bool{true, true, true, true}, attempts(false, false, true, false), "require never offers classical")
|
|
||||||
|
|
||||||
set(pqHandshakeConfig{initiate: true, sticky: true})
|
|
||||||
assert.Equal(t, []bool{true, false}, attempts(false, false), "sticky alternates until the peer has done PQ")
|
|
||||||
hm.notePQPeer(pqSubtype, []netip.Addr{peer})
|
|
||||||
assert.Equal(t, []bool{true, true, true}, attempts(false, false, false), "then only PQ")
|
|
||||||
}
|
|
||||||
+1
-13
@@ -67,19 +67,8 @@ const (
|
|||||||
const (
|
const (
|
||||||
HandshakeIXPSK0 MessageSubType = 0
|
HandshakeIXPSK0 MessageSubType = 0
|
||||||
HandshakeXXPSK0 MessageSubType = 1
|
HandshakeXXPSK0 MessageSubType = 1
|
||||||
|
|
||||||
// HandshakeIXPSK2MLKEM1024 is IX with an ephemeral ML-KEM-1024 exchange mixed
|
|
||||||
// in through the psk2 slot. Its messages exceed the MTU and travel as
|
|
||||||
// fragments (see handshake/fragment).
|
|
||||||
HandshakeIXPSK2MLKEM1024 MessageSubType = 2
|
|
||||||
)
|
)
|
||||||
|
|
||||||
// IsFragmented reports whether handshake messages of this subtype travel as
|
|
||||||
// fragments.
|
|
||||||
func IsFragmented(st MessageSubType) bool {
|
|
||||||
return st == HandshakeIXPSK2MLKEM1024
|
|
||||||
}
|
|
||||||
|
|
||||||
var ErrHeaderTooShort = errors.New("header is too short")
|
var ErrHeaderTooShort = errors.New("header is too short")
|
||||||
|
|
||||||
var subTypeTestMap = map[MessageSubType]string{
|
var subTypeTestMap = map[MessageSubType]string{
|
||||||
@@ -100,7 +89,6 @@ var subTypeMap = map[MessageType]*map[MessageSubType]string{
|
|||||||
CloseTunnel: &subTypeNoneMap,
|
CloseTunnel: &subTypeNoneMap,
|
||||||
Handshake: {
|
Handshake: {
|
||||||
HandshakeIXPSK0: "ix_psk0",
|
HandshakeIXPSK0: "ix_psk0",
|
||||||
HandshakeIXPSK2MLKEM1024: "ix_psk2_mlkem1024",
|
|
||||||
},
|
},
|
||||||
Control: &subTypeNoneMap,
|
Control: &subTypeNoneMap,
|
||||||
}
|
}
|
||||||
@@ -211,7 +199,7 @@ func IsValidSubType(t MessageType, s MessageSubType) bool {
|
|||||||
case Message:
|
case Message:
|
||||||
return s == MessageNone || s == MessageRelay
|
return s == MessageNone || s == MessageRelay
|
||||||
case Handshake:
|
case Handshake:
|
||||||
return s == HandshakeIXPSK0 || s == HandshakeIXPSK2MLKEM1024
|
return s == HandshakeIXPSK0
|
||||||
case Test:
|
case Test:
|
||||||
return s == TestReply || s == TestRequest
|
return s == TestReply || s == TestRequest
|
||||||
case Control, CloseTunnel, RecvError, LightHouse:
|
case Control, CloseTunnel, RecvError, LightHouse:
|
||||||
|
|||||||
@@ -97,7 +97,6 @@ func TestTypeMap(t *testing.T) {
|
|||||||
CloseTunnel: &subTypeNoneMap,
|
CloseTunnel: &subTypeNoneMap,
|
||||||
Handshake: {
|
Handshake: {
|
||||||
HandshakeIXPSK0: "ix_psk0",
|
HandshakeIXPSK0: "ix_psk0",
|
||||||
HandshakeIXPSK2MLKEM1024: "ix_psk2_mlkem1024",
|
|
||||||
},
|
},
|
||||||
Control: &subTypeNoneMap,
|
Control: &subTypeNoneMap,
|
||||||
}, subTypeMap)
|
}, subTypeMap)
|
||||||
@@ -123,7 +122,6 @@ func TestIsValidSubType(t *testing.T) {
|
|||||||
assert.False(t, IsValidSubType(Message, 2))
|
assert.False(t, IsValidSubType(Message, 2))
|
||||||
|
|
||||||
assert.True(t, IsValidSubType(Handshake, HandshakeIXPSK0))
|
assert.True(t, IsValidSubType(Handshake, HandshakeIXPSK0))
|
||||||
assert.True(t, IsValidSubType(Handshake, HandshakeIXPSK2MLKEM1024))
|
|
||||||
// HandshakeXXPSK0 is defined but not a wire-valid subtype.
|
// HandshakeXXPSK0 is defined but not a wire-valid subtype.
|
||||||
assert.False(t, IsValidSubType(Handshake, HandshakeXXPSK0))
|
assert.False(t, IsValidSubType(Handshake, HandshakeXXPSK0))
|
||||||
|
|
||||||
|
|||||||
+7
-10
@@ -260,11 +260,6 @@ type HostInfo struct {
|
|||||||
// We need these to avoid replayed handshake packets creating new hostinfos which causes churn
|
// We need these to avoid replayed handshake packets creating new hostinfos which causes churn
|
||||||
HandshakePacket map[uint8][]byte
|
HandshakePacket map[uint8][]byte
|
||||||
|
|
||||||
// A responder resending a fragmented handshake response offers symbols it has
|
|
||||||
// not sent before, at most once per retry interval.
|
|
||||||
handshakeResendAt atomic.Int64 // unix nanos of the last send
|
|
||||||
handshakeNextSymbol atomic.Uint32 // next fragment symbol index to offer
|
|
||||||
|
|
||||||
// nextLHQuery is the earliest we can ask the lighthouse for new information.
|
// nextLHQuery is the earliest we can ask the lighthouse for new information.
|
||||||
// This is used to limit lighthouse re-queries in chatty clients
|
// This is used to limit lighthouse re-queries in chatty clients
|
||||||
nextLHQuery atomic.Int64
|
nextLHQuery atomic.Int64
|
||||||
@@ -321,9 +316,9 @@ type cachedPacketMetrics struct {
|
|||||||
func NewHostMapFromConfig(l *slog.Logger, c *config.C) *HostMap {
|
func NewHostMapFromConfig(l *slog.Logger, c *config.C) *HostMap {
|
||||||
hm := newHostMap(l)
|
hm := newHostMap(l)
|
||||||
|
|
||||||
hm.reload(c, true)
|
hm.reload(c, true, nil)
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
hm.reload(c, false)
|
hm.reload(c, false, r)
|
||||||
})
|
})
|
||||||
|
|
||||||
l.Info("Main HostMap created", "preferredRanges", hm.GetPreferredRanges())
|
l.Info("Main HostMap created", "preferredRanges", hm.GetPreferredRanges())
|
||||||
@@ -342,7 +337,8 @@ func newHostMap(l *slog.Logger) *HostMap {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
func (hm *HostMap) reload(c *config.C, initial bool) {
|
// r is nil on the initial load
|
||||||
|
func (hm *HostMap) reload(c *config.C, initial bool, r *config.Reload) {
|
||||||
if initial || c.HasChanged("preferred_ranges") {
|
if initial || c.HasChanged("preferred_ranges") {
|
||||||
var preferredRanges []netip.Prefix
|
var preferredRanges []netip.Prefix
|
||||||
rawPreferredRanges := c.GetStringSlice("preferred_ranges", []string{})
|
rawPreferredRanges := c.GetStringSlice("preferred_ranges", []string{})
|
||||||
@@ -353,8 +349,9 @@ func (hm *HostMap) reload(c *config.C, initial bool) {
|
|||||||
if err != nil {
|
if err != nil {
|
||||||
hm.l.Warn("Failed to parse preferred ranges, ignoring",
|
hm.l.Warn("Failed to parse preferred ranges, ignoring",
|
||||||
"error", err,
|
"error", err,
|
||||||
"range", rawPreferredRanges,
|
"range", rawPreferredRange,
|
||||||
)
|
)
|
||||||
|
r.Failed()
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -447,3 +447,16 @@ func TestHostInfo_markOutOnly(t *testing.T) {
|
|||||||
assert.True(t, h.markOut(6), "a relayed send must not consume the epoch edge")
|
assert.True(t, h.markOut(6), "a relayed send must not consume the epoch edge")
|
||||||
assert.False(t, h.markOut(6))
|
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())
|
||||||
|
}
|
||||||
+10
-5
@@ -384,6 +384,8 @@ type rxContext struct {
|
|||||||
hostmapCache map[uint32]*HostInfo
|
hostmapCache map[uint32]*HostInfo
|
||||||
lhh *LightHouseHandler
|
lhh *LightHouseHandler
|
||||||
ctCache *firewall.ConntrackCacheTicker
|
ctCache *firewall.ConntrackCacheTicker
|
||||||
|
relayBatch *batch.SendBatch
|
||||||
|
relayRemote netip.AddrPort
|
||||||
}
|
}
|
||||||
|
|
||||||
func newRxContext(f *Interface, q int) *rxContext {
|
func newRxContext(f *Interface, q int) *rxContext {
|
||||||
@@ -414,6 +416,7 @@ func (f *Interface) listenOut(i int) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
flusher := func() {
|
flusher := func() {
|
||||||
|
f.flushRelayBatch(rxc)
|
||||||
if err := f.batchers[i].Flush(); err != nil {
|
if err := f.batchers[i].Flush(); err != nil {
|
||||||
f.l.Error("Failed to flush tun coalescer", "error", err)
|
f.l.Error("Failed to flush tun coalescer", "error", err)
|
||||||
}
|
}
|
||||||
@@ -509,10 +512,11 @@ func (f *Interface) flushSendBatch(sb *batch.SendBatch, q int) {
|
|||||||
|
|
||||||
func (f *Interface) RegisterConfigChangeCallbacks(c *config.C) {
|
func (f *Interface) RegisterConfigChangeCallbacks(c *config.C) {
|
||||||
c.RegisterReloadCallback(f.reloadFirewall)
|
c.RegisterReloadCallback(f.reloadFirewall)
|
||||||
c.RegisterReloadCallback(f.reloadSendRecvError)
|
for _, reload := range []func(*config.C){
|
||||||
c.RegisterReloadCallback(f.reloadAcceptRecvError)
|
f.reloadSendRecvError, f.reloadAcceptRecvError, f.reloadDisconnectInvalid, f.reloadMisc,
|
||||||
c.RegisterReloadCallback(f.reloadDisconnectInvalid)
|
} {
|
||||||
c.RegisterReloadCallback(f.reloadMisc)
|
c.RegisterReloadCallback(func(c *config.C, _ *config.Reload) { reload(c) })
|
||||||
|
}
|
||||||
|
|
||||||
for _, udpConn := range f.writers {
|
for _, udpConn := range f.writers {
|
||||||
c.RegisterReloadCallback(udpConn.ReloadConfig)
|
c.RegisterReloadCallback(udpConn.ReloadConfig)
|
||||||
@@ -529,7 +533,7 @@ func (f *Interface) reloadDisconnectInvalid(c *config.C) {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
func (f *Interface) reloadFirewall(c *config.C) {
|
func (f *Interface) reloadFirewall(c *config.C, r *config.Reload) {
|
||||||
cs := f.pki.getCertState()
|
cs := f.pki.getCertState()
|
||||||
curCert := cs.getCertificate(cert.Version2)
|
curCert := cs.getCertificate(cert.Version2)
|
||||||
if curCert == nil {
|
if curCert == nil {
|
||||||
@@ -548,6 +552,7 @@ func (f *Interface) reloadFirewall(c *config.C) {
|
|||||||
fw, err := NewFirewallFromConfig(f.l, cs, c)
|
fw, err := NewFirewallFromConfig(f.l, cs, c)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
f.l.Error("Error while creating firewall during reload", "error", err)
|
f.l.Error("Error while creating firewall during reload", "error", err)
|
||||||
|
r.Failed()
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
+26
-4
@@ -65,10 +65,10 @@ func TestReloadFirewall_CertUnsafeNetworksChanged(t *testing.T) {
|
|||||||
pki.cs.Store(&CertState{v2Cert: c2, initiatingVersion: cert.Version2})
|
pki.cs.Store(&CertState{v2Cert: c2, initiatingVersion: cert.Version2})
|
||||||
|
|
||||||
// Reload with the same YAML so HasChanged("firewall") reports false.
|
// Reload with the same YAML so HasChanged("firewall") reports false.
|
||||||
require.NoError(t, cfg.ReloadConfigString(rawYAML))
|
require.NoError(t, cfg.ReloadConfigString(rawYAML).Err)
|
||||||
require.False(t, cfg.HasChanged("firewall"))
|
require.False(t, cfg.HasChanged("firewall"))
|
||||||
|
|
||||||
f.reloadFirewall(cfg)
|
f.reloadFirewall(cfg, nil)
|
||||||
|
|
||||||
assert.NotSame(t, fw, f.firewall, "firewall pointer should have been replaced")
|
assert.NotSame(t, fw, f.firewall, "firewall pointer should have been replaced")
|
||||||
assert.Equal(t, newUnsafe, f.firewall.unsafeNetworks)
|
assert.Equal(t, newUnsafe, f.firewall.unsafeNetworks)
|
||||||
@@ -113,8 +113,30 @@ func TestReloadFirewall_NoChange(t *testing.T) {
|
|||||||
l: l,
|
l: l,
|
||||||
}
|
}
|
||||||
|
|
||||||
require.NoError(t, cfg.ReloadConfigString(rawYAML))
|
require.NoError(t, cfg.ReloadConfigString(rawYAML).Err)
|
||||||
f.reloadFirewall(cfg)
|
f.reloadFirewall(cfg, nil)
|
||||||
|
|
||||||
assert.Same(t, fw, f.firewall, "firewall should not have been replaced")
|
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)
|
||||||
|
}
|
||||||
+10
-4
@@ -138,18 +138,21 @@ func NewLightHouseFromConfig(ctx context.Context, l *slog.Logger, c *config.C, c
|
|||||||
h.metrics = newLighthouseMetrics()
|
h.metrics = newLighthouseMetrics()
|
||||||
}
|
}
|
||||||
|
|
||||||
err := h.reload(c, true)
|
err := h.reload(c, true, nil)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
err := h.reload(c, false)
|
r.RestartRequiredIfChanged("lighthouse.am_lighthouse", "listen.port", "handshakes.query_buffer", "stats.lighthouse_metrics")
|
||||||
|
err := h.reload(c, false, r)
|
||||||
switch v := err.(type) {
|
switch v := err.(type) {
|
||||||
case *util.ContextualError:
|
case *util.ContextualError:
|
||||||
v.Log(l)
|
v.Log(l)
|
||||||
|
r.Failed()
|
||||||
case error:
|
case error:
|
||||||
l.Error("failed to reload lighthouse", "error", err)
|
l.Error("failed to reload lighthouse", "error", err)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
|
||||||
@@ -190,7 +193,8 @@ func (lh *LightHouse) GetUpdateInterval() int64 {
|
|||||||
return lh.interval.Load()
|
return lh.interval.Load()
|
||||||
}
|
}
|
||||||
|
|
||||||
func (lh *LightHouse) reload(c *config.C, initial bool) error {
|
// r is nil on the initial load
|
||||||
|
func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||||
if initial || c.HasChanged("lighthouse.advertise_addrs") {
|
if initial || c.HasChanged("lighthouse.advertise_addrs") {
|
||||||
rawAdvAddrs := c.GetStringSlice("lighthouse.advertise_addrs", []string{})
|
rawAdvAddrs := c.GetStringSlice("lighthouse.advertise_addrs", []string{})
|
||||||
advAddrs := make([]netip.AddrPort, 0)
|
advAddrs := make([]netip.AddrPort, 0)
|
||||||
@@ -225,6 +229,7 @@ func (lh *LightHouse) reload(c *config.C, initial bool) error {
|
|||||||
"addr", rawAddr,
|
"addr", rawAddr,
|
||||||
"entry", i+1,
|
"entry", i+1,
|
||||||
)
|
)
|
||||||
|
r.Failed()
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -383,6 +388,7 @@ func (lh *LightHouse) reload(c *config.C, initial bool) error {
|
|||||||
"relay", v,
|
"relay", v,
|
||||||
"error", err,
|
"error", err,
|
||||||
)
|
)
|
||||||
|
r.Failed()
|
||||||
} else {
|
} else {
|
||||||
lh.l.Info("Read relay from config", "relay", v)
|
lh.l.Info("Read relay from config", "relay", v)
|
||||||
relaysForMe = append(relaysForMe, configRIP)
|
relaysForMe = append(relaysForMe, configRIP)
|
||||||
|
|||||||
+59
-14
@@ -87,15 +87,15 @@ func TestReloadLighthouseInterval(t *testing.T) {
|
|||||||
lh.ifce = &mockEncWriter{}
|
lh.ifce = &mockEncWriter{}
|
||||||
|
|
||||||
// The first one routine is kicked off by main.go currently, lets make sure that one dies
|
// 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"))
|
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 5").Err)
|
||||||
assert.Equal(t, int64(5), lh.interval.Load())
|
assert.Equal(t, int64(5), lh.interval.Load())
|
||||||
|
|
||||||
// Subsequent calls are killed off by the LightHouse.Reload function
|
// Subsequent calls are killed off by the LightHouse.Reload function
|
||||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 10"))
|
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 10").Err)
|
||||||
assert.Equal(t, int64(10), lh.interval.Load())
|
assert.Equal(t, int64(10), lh.interval.Load())
|
||||||
|
|
||||||
// If this completes then nothing is stealing our reload routine
|
// If this completes then nothing is stealing our reload routine
|
||||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 11"))
|
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 11").Err)
|
||||||
assert.Equal(t, int64(11), lh.interval.Load())
|
assert.Equal(t, int64(11), lh.interval.Load())
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -296,7 +296,7 @@ func TestLighthouse_reload(t *testing.T) {
|
|||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
c.ReloadConfigString(string(rc))
|
c.ReloadConfigString(string(rc))
|
||||||
|
|
||||||
err = lh.reload(c, false)
|
err = lh.reload(c, false, nil)
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -334,7 +334,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
|||||||
}
|
}
|
||||||
rc, err := yaml.Marshal(nc)
|
rc, err := yaml.Marshal(nc)
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||||
|
|
||||||
rl := lh.Query(staticHost)
|
rl := lh.Query(staticHost)
|
||||||
require.NotNil(t, rl)
|
require.NotNil(t, rl)
|
||||||
@@ -350,7 +350,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
|||||||
}
|
}
|
||||||
rc, err = yaml.Marshal(nc)
|
rc, err = yaml.Marshal(nc)
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||||
|
|
||||||
rl = lh.Query(staticHost)
|
rl = lh.Query(staticHost)
|
||||||
require.NotNil(t, rl)
|
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{}))
|
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.
|
// Reload with the same config. An unchanged entry must not duplicate.
|
||||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||||
|
|
||||||
rl = lh.Query(staticHost)
|
rl = lh.Query(staticHost)
|
||||||
require.NotNil(t, rl)
|
require.NotNil(t, rl)
|
||||||
@@ -373,7 +373,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
|||||||
}
|
}
|
||||||
rc, err = yaml.Marshal(nc)
|
rc, err = yaml.Marshal(nc)
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||||
|
|
||||||
// Add a second host alongside the first. Both should be present, neither duplicated.
|
// Add a second host alongside the first. Both should be present, neither duplicated.
|
||||||
nc = map[string]any{
|
nc = map[string]any{
|
||||||
@@ -384,7 +384,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
|||||||
}
|
}
|
||||||
rc, err = yaml.Marshal(nc)
|
rc, err = yaml.Marshal(nc)
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||||
|
|
||||||
rl = lh.Query(staticHost)
|
rl = lh.Query(staticHost)
|
||||||
require.NotNil(t, rl)
|
require.NotNil(t, rl)
|
||||||
@@ -406,7 +406,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
|||||||
}
|
}
|
||||||
rc, err = yaml.Marshal(nc)
|
rc, err = yaml.Marshal(nc)
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||||
|
|
||||||
_, isStatic := lh.GetStaticHostList()[staticHost]
|
_, isStatic := lh.GetStaticHostList()[staticHost]
|
||||||
assert.False(t, isStatic)
|
assert.False(t, isStatic)
|
||||||
@@ -966,13 +966,13 @@ func TestLighthouse_reloadRelaysTriggersUpdate(t *testing.T) {
|
|||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
assert.Empty(t, lh.updateTrigger)
|
assert.Empty(t, lh.updateTrigger)
|
||||||
|
|
||||||
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6]\n"))
|
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6]\n").Err)
|
||||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
|
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
|
||||||
require.Len(t, lh.updateTrigger, 1)
|
require.Len(t, lh.updateTrigger, 1)
|
||||||
<-lh.updateTrigger
|
<-lh.updateTrigger
|
||||||
|
|
||||||
// The config changed but what we advertise did not, a bad entry is skipped
|
// 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"))
|
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6, nope]\n").Err)
|
||||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
|
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
|
||||||
assert.Empty(t, lh.updateTrigger)
|
assert.Empty(t, lh.updateTrigger)
|
||||||
}
|
}
|
||||||
@@ -988,12 +988,57 @@ func TestLighthouse_reloadAmRelayAlone(t *testing.T) {
|
|||||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
|
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
|
// 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"))
|
require.NoError(t, c.ReloadConfigString(base+" am_relay: true\n").Err)
|
||||||
assert.Empty(t, lh.GetRelaysForMe())
|
assert.Empty(t, lh.GetRelaysForMe())
|
||||||
require.Len(t, lh.updateTrigger, 1)
|
require.Len(t, lh.updateTrigger, 1)
|
||||||
<-lh.updateTrigger
|
<-lh.updateTrigger
|
||||||
|
|
||||||
require.NoError(t, c.ReloadConfigString(base+" am_relay: false\n"))
|
require.NoError(t, c.ReloadConfigString(base+" am_relay: false\n").Err)
|
||||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
|
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
|
||||||
require.Len(t, lh.updateTrigger, 1)
|
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)
|
wireSSHReload(l, ssh, c)
|
||||||
var sshStart func()
|
var sshStart func()
|
||||||
if c.GetBool("sshd.enabled", false) {
|
if c.GetBool("sshd.enabled", false) {
|
||||||
sshStart, err = configSSH(l, ssh, c)
|
sshStart, err = configSSH(l, ssh, c, nil)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
l.Warn("Failed to configure sshd, ssh debugging will not be available", "error", err)
|
l.Warn("Failed to configure sshd, ssh debugging will not be available", "error", err)
|
||||||
sshStart = nil
|
sshStart = nil
|
||||||
@@ -197,7 +197,7 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
|||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, util.NewContextualError("Failed to open udp listener", m{"queue": i}, err)
|
return nil, util.NewContextualError("Failed to open udp listener", m{"queue": i}, err)
|
||||||
}
|
}
|
||||||
udpServer.ReloadConfig(c)
|
udpServer.ReloadConfig(c, nil)
|
||||||
udpConns[i] = udpServer
|
udpConns[i] = udpServer
|
||||||
|
|
||||||
// If port is dynamic, discover it before the next pass through the for loop
|
// If port is dynamic, discover it before the next pass through the for loop
|
||||||
@@ -232,11 +232,9 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
|||||||
retries: int64(c.GetInt("handshakes.retries", DefaultHandshakeRetries)),
|
retries: int64(c.GetInt("handshakes.retries", DefaultHandshakeRetries)),
|
||||||
triggerBuffer: c.GetInt("handshakes.trigger_buffer", DefaultHandshakeTriggerBuffer),
|
triggerBuffer: c.GetInt("handshakes.trigger_buffer", DefaultHandshakeTriggerBuffer),
|
||||||
messageMetrics: messageMetrics,
|
messageMetrics: messageMetrics,
|
||||||
pq: pqHandshakeConfigFrom(c),
|
|
||||||
}
|
}
|
||||||
|
|
||||||
handshakeManager := NewHandshakeManager(l, hostMap, lightHouse, udpConns[0], handshakeConfig)
|
handshakeManager := NewHandshakeManager(l, hostMap, lightHouse, udpConns[0], handshakeConfig)
|
||||||
c.RegisterReloadCallback(handshakeManager.reloadPQ)
|
|
||||||
lightHouse.handshakeTrigger = handshakeManager.trigger
|
lightHouse.handshakeTrigger = handshakeManager.trigger
|
||||||
|
|
||||||
ds, err := newDnsServerFromConfig(ctx, l, pki, hostMap, c)
|
ds, err := newDnsServerFromConfig(ctx, l, pki, hostMap, c)
|
||||||
@@ -313,6 +311,16 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
|||||||
lightHouse.ifce = ifce
|
lightHouse.ifce = ifce
|
||||||
|
|
||||||
ifce.RegisterConfigChangeCallbacks(c)
|
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.reloadDisconnectInvalid(c)
|
||||||
ifce.reloadSendRecvError(c)
|
ifce.reloadSendRecvError(c)
|
||||||
ifce.reloadAcceptRecvError(c)
|
ifce.reloadAcceptRecvError(c)
|
||||||
|
|||||||
@@ -0,0 +1,6 @@
|
|||||||
|
//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"}
|
||||||
@@ -0,0 +1,6 @@
|
|||||||
|
//go:build !linux || android || e2e_testing
|
||||||
|
|
||||||
|
package nebula
|
||||||
|
|
||||||
|
// osStartupOnlyKeys is empty, none of the OS specific startup keys matter here
|
||||||
|
var osStartupOnlyKeys []string
|
||||||
+37
-7
@@ -25,7 +25,7 @@ var ErrOutOfWindow = errors.New("out of window packet")
|
|||||||
|
|
||||||
// readOutsidePackets processes one received underlay packet.
|
// readOutsidePackets processes one received underlay packet.
|
||||||
// Message payloads are decrypted IN PLACE, so packet must stay untouched
|
// Message payloads are decrypted IN PLACE, so packet must stay untouched
|
||||||
// by the caller until the batcher for queue q has been flushed
|
// by the caller until the TUN and relay batches for queue q have been flushed.
|
||||||
func (f *Interface) readOutsidePackets(via ViaSender, packet []byte, rxc *rxContext) {
|
func (f *Interface) readOutsidePackets(via ViaSender, packet []byte, rxc *rxContext) {
|
||||||
h := rxc.h
|
h := rxc.h
|
||||||
err := h.Parse(packet)
|
err := h.Parse(packet)
|
||||||
@@ -77,6 +77,12 @@ func (f *Interface) readOutsidePackets(via ViaSender, packet []byte, rxc *rxCont
|
|||||||
f.messageMetrics.Rx(h.Type, h.Subtype, 1)
|
f.messageMetrics.Rx(h.Type, h.Subtype, 1)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Earlier forwards must leave before this packet can generate a response.
|
||||||
|
isMessageRelay := h.Type == header.Message && h.Subtype == header.MessageRelay
|
||||||
|
if !isMessageRelay {
|
||||||
|
f.flushRelayBatch(rxc)
|
||||||
|
}
|
||||||
|
|
||||||
// Unencrypted packets
|
// Unencrypted packets
|
||||||
switch h.Type {
|
switch h.Type {
|
||||||
case header.Handshake:
|
case header.Handshake:
|
||||||
@@ -88,9 +94,6 @@ func (f *Interface) readOutsidePackets(via ViaSender, packet []byte, rxc *rxCont
|
|||||||
return
|
return
|
||||||
}
|
}
|
||||||
|
|
||||||
// Relay packets are special
|
|
||||||
isMessageRelay := (h.Type == header.Message && h.Subtype == header.MessageRelay)
|
|
||||||
|
|
||||||
var hostinfo *HostInfo
|
var hostinfo *HostInfo
|
||||||
if isMessageRelay {
|
if isMessageRelay {
|
||||||
hostinfo = f.hostMap.QueryRelayIndex(h.RemoteIndex)
|
hostinfo = f.hostMap.QueryRelayIndex(h.RemoteIndex)
|
||||||
@@ -102,6 +105,8 @@ func (f *Interface) readOutsidePackets(via ViaSender, packet []byte, rxc *rxCont
|
|||||||
// recvError if necessary
|
// recvError if necessary
|
||||||
if hostinfo == nil || hostinfo.ConnectionState == nil {
|
if hostinfo == nil || hostinfo.ConnectionState == nil {
|
||||||
if !via.IsRelayed {
|
if !via.IsRelayed {
|
||||||
|
// An unknown relay index can also produce a response.
|
||||||
|
f.flushRelayBatch(rxc)
|
||||||
f.maybeSendRecvError(via.UdpAddr, h.RemoteIndex)
|
f.maybeSendRecvError(via.UdpAddr, h.RemoteIndex)
|
||||||
}
|
}
|
||||||
return
|
return
|
||||||
@@ -233,8 +238,10 @@ func (f *Interface) handleOutsideRelayPacket(hostinfo *HostInfo, via ViaSender,
|
|||||||
// Forward this packet through the relay tunnel, rebuilding it in place.
|
// 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
|
// Encode overwrites the old outer header, and the new AEAD tag lands where the old one was
|
||||||
fwdBuf := packet[:0]
|
fwdBuf := packet[:0]
|
||||||
//todo it would potentially be nice to batch these
|
out, err := f.prepareSendVia(targetHI, targetRelay, signedPayload, rxc.nb, fwdBuf, true)
|
||||||
f.SendVia(targetHI, targetRelay, signedPayload, rxc.nb, fwdBuf, true, rxc.q)
|
if err == nil {
|
||||||
|
f.queueRelayPacket(out, targetHI.GetRemote(), rxc)
|
||||||
|
}
|
||||||
case TerminalType:
|
case TerminalType:
|
||||||
hostinfo.logger(f.l).Error("Unexpected Relay Type of Terminal")
|
hostinfo.logger(f.l).Error("Unexpected Relay Type of Terminal")
|
||||||
return
|
return
|
||||||
@@ -259,6 +266,27 @@ func (f *Interface) handleOutsideRelayPacket(hostinfo *HostInfo, via ViaSender,
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// queueRelayPacket borrows a receive buffer until the batch is flushed. Destination changes and the send batch
|
||||||
|
// limit end a run, preserving arrival order while allowing WriteBatch to use UDP segmentation offload.
|
||||||
|
func (f *Interface) queueRelayPacket(packet []byte, remote netip.AddrPort, rxc *rxContext) {
|
||||||
|
if rxc.relayBatch == nil {
|
||||||
|
rxc.relayBatch = batch.NewSendBatch(f.writers[rxc.q], batch.SendBatchCap, 0)
|
||||||
|
} else if rxc.relayRemote != remote {
|
||||||
|
f.flushRelayBatch(rxc)
|
||||||
|
}
|
||||||
|
rxc.relayRemote = remote
|
||||||
|
rxc.relayBatch.Commit(packet, remote)
|
||||||
|
if rxc.relayBatch.Len() >= batch.SendBatchCap {
|
||||||
|
f.flushRelayBatch(rxc)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func (f *Interface) flushRelayBatch(rxc *rxContext) {
|
||||||
|
if rxc.relayBatch != nil {
|
||||||
|
f.flushSendBatch(rxc.relayBatch, rxc.q)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
// closeTunnel closes a tunnel locally, it does not send a closeTunnel packet to the remote
|
// closeTunnel closes a tunnel locally, it does not send a closeTunnel packet to the remote
|
||||||
func (f *Interface) closeTunnel(hostInfo *HostInfo) {
|
func (f *Interface) closeTunnel(hostInfo *HostInfo) {
|
||||||
// Hold the hostmap lock across both the delete and the lighthouse eviction,
|
// Hold the hostmap lock across both the delete and the lighthouse eviction,
|
||||||
@@ -476,7 +504,9 @@ func parseV4(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
|
|||||||
func (f *Interface) handleOutsideMessagePacket(hostinfo *HostInfo, messageCounter uint64, out []byte, rxc *rxContext) {
|
func (f *Interface) handleOutsideMessagePacket(hostinfo *HostInfo, messageCounter uint64, out []byte, rxc *rxContext) {
|
||||||
err := newPacket(out, true, rxc.fwPacket)
|
err := newPacket(out, true, rxc.fwPacket)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
hostinfo.logger(f.l).Warn("Error while validating inbound packet", "error", err, "packet", out)
|
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||||
|
hostinfo.logger(f.l).Debug("Error while validating inbound packet", "error", err, "packet", out)
|
||||||
|
}
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -0,0 +1,291 @@
|
|||||||
|
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 TestRelayBatchDestinationChange(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, 3)
|
||||||
|
for i, wantRemotes := range [][]netip.AddrPort{{first, first}, {second, second}, {first}} {
|
||||||
|
require.Equal(t, wantRemotes, p.conn.writes[i].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 TestRelayBatchBeforeResponse(t *testing.T) {
|
||||||
|
for _, unknownRelay := range []bool{false, true} {
|
||||||
|
name := "test request"
|
||||||
|
if unknownRelay {
|
||||||
|
name = "unknown relay"
|
||||||
|
}
|
||||||
|
t.Run(name, func(t *testing.T) {
|
||||||
|
p := newRelayBatchPath(t, noise.CipherChaChaPoly)
|
||||||
|
first, last := p.wrap(t, []byte("first")), p.wrap(t, []byte("last"))
|
||||||
|
p.counter++
|
||||||
|
request := header.Encode(make([]byte, header.Len), header.Version, header.Test, header.TestRequest, 100, p.counter)
|
||||||
|
request, err := p.sourceKey.EncryptDanger(request, request, []byte("ping"), p.counter, make([]byte, 12))
|
||||||
|
require.NoError(t, err)
|
||||||
|
if unknownRelay {
|
||||||
|
request = header.Encode(make([]byte, header.Len), header.Version, header.Message, header.MessageRelay, 999, p.counter)
|
||||||
|
}
|
||||||
|
p.conn.read = func(r udp.EncReader, flush func()) {
|
||||||
|
r(p.source.GetRemote(), first)
|
||||||
|
require.Empty(t, p.conn.writes)
|
||||||
|
r(p.source.GetRemote(), request)
|
||||||
|
require.Len(t, p.conn.writes, 2)
|
||||||
|
r(p.source.GetRemote(), last)
|
||||||
|
flush()
|
||||||
|
}
|
||||||
|
p.f.listenOut(0)
|
||||||
|
require.Len(t, p.conn.writes, 3)
|
||||||
|
require.True(t, p.conn.writes[0].batched)
|
||||||
|
require.False(t, p.conn.writes[1].batched)
|
||||||
|
require.True(t, p.conn.writes[2].batched)
|
||||||
|
require.Equal(t, p.source.GetRemote(), p.conn.writes[1].remotes[0])
|
||||||
|
h := &header.H{}
|
||||||
|
require.NoError(t, h.Parse(p.conn.writes[1].packets[0]))
|
||||||
|
if unknownRelay {
|
||||||
|
require.Equal(t, header.RecvError, h.Type)
|
||||||
|
require.EqualValues(t, 999, h.RemoteIndex)
|
||||||
|
} else {
|
||||||
|
require.Equal(t, header.Test, h.Type)
|
||||||
|
require.Equal(t, header.TestReply, h.Subtype)
|
||||||
|
reply := p.conn.writes[1].packets[0]
|
||||||
|
out, err := p.sourceKey.DecryptDanger(nil, reply[:header.Len], reply[header.Len:], h.MessageCounter, make([]byte, 12))
|
||||||
|
require.NoError(t, err)
|
||||||
|
require.Equal(t, []byte("ping"), out)
|
||||||
|
}
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
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.
|
// SendBatch accumulates encrypted UDP packets and flushes them via WriteBatch.
|
||||||
// One SendBatch is owned by each listenIn goroutine; no locking is needed.
|
// Each reader goroutine owns its own SendBatch; no locking is needed.
|
||||||
// Slots are backed by an Arena (see its docs)
|
// Slots can borrow receive buffers or be backed by an Arena (see its docs).
|
||||||
type SendBatch struct {
|
type SendBatch struct {
|
||||||
out batchWriter
|
out batchWriter
|
||||||
bufs [][]byte
|
bufs [][]byte
|
||||||
|
|||||||
@@ -41,9 +41,16 @@ func (e *NameError) Error() string {
|
|||||||
type DeviceFactory func(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, routines int) (Device, error)
|
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) {
|
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 {
|
switch {
|
||||||
case c.GetBool("tun.disabled", false):
|
case c.GetBool("tun.disabled", false):
|
||||||
tun := newDisabledTun(vpnNetworks, c.GetInt("tun.tx_queue", 5000), c.GetBool("stats.message_metrics", false), l)
|
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
|
return tun, nil
|
||||||
|
|
||||||
default:
|
default:
|
||||||
|
|||||||
@@ -38,16 +38,17 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
|
|||||||
l: l,
|
l: l,
|
||||||
}
|
}
|
||||||
|
|
||||||
err := t.reload(c, true)
|
err := t.reload(c, true, nil)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
_ = file.Close()
|
_ = file.Close()
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
err := t.reload(c, false)
|
err := t.reload(c, false, r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
|
||||||
@@ -67,7 +68,7 @@ func (t *tun) Activate() error {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) reload(c *config.C, initial bool) error {
|
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return err
|
||||||
|
|||||||
@@ -0,0 +1,45 @@
|
|||||||
|
//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)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,80 @@
|
|||||||
|
//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)
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -10,6 +10,9 @@ import (
|
|||||||
"github.com/slackhq/nebula/wfp"
|
"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
|
// installInterfaceBypass installs a WFP PERMIT filter scoped to the wintun interface LUID so inbound traffic on the
|
||||||
// nebula adapter bypasses Windows Defender Firewall.
|
// nebula adapter bypasses Windows Defender Firewall.
|
||||||
func installInterfaceBypass(l *slog.Logger, luid uint64) closer {
|
func installInterfaceBypass(l *slog.Logger, luid uint64) closer {
|
||||||
|
|||||||
@@ -4,6 +4,9 @@ package overlay
|
|||||||
|
|
||||||
import "log/slog"
|
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.
|
// installInterfaceBypass is a no-op on windows-386 because we don't currently build for it.
|
||||||
func installInterfaceBypass(_ *slog.Logger, _ uint64) closer {
|
func installInterfaceBypass(_ *slog.Logger, _ uint64) closer {
|
||||||
return nil
|
return nil
|
||||||
|
|||||||
+146
-35
@@ -6,8 +6,10 @@ import (
|
|||||||
"errors"
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
"log/slog"
|
"log/slog"
|
||||||
|
"math/bits"
|
||||||
"net/netip"
|
"net/netip"
|
||||||
"os"
|
"os"
|
||||||
|
"sync"
|
||||||
"sync/atomic"
|
"sync/atomic"
|
||||||
"syscall"
|
"syscall"
|
||||||
"unsafe"
|
"unsafe"
|
||||||
@@ -28,7 +30,7 @@ type tun struct {
|
|||||||
DefaultMTU int
|
DefaultMTU int
|
||||||
Routes atomic.Pointer[[]Route]
|
Routes atomic.Pointer[[]Route]
|
||||||
routeTree atomic.Pointer[bart.Table[routing.Gateways]]
|
routeTree atomic.Pointer[bart.Table[routing.Gateways]]
|
||||||
linkAddr *netroute.LinkAddr
|
linkAddr atomic.Pointer[netroute.LinkAddr]
|
||||||
// hostOwned means the fd arrived from the OS, which has already configured addressing, mtu
|
// hostOwned means the fd arrived from the OS, which has already configured addressing, mtu
|
||||||
// and routes for it. NEPacketTunnelProvider on darwin does this.
|
// and routes for it. NEPacketTunnelProvider on darwin does this.
|
||||||
hostOwned bool
|
hostOwned bool
|
||||||
@@ -78,17 +80,31 @@ type ifreqAlias6 struct {
|
|||||||
Lifetime addrLifetime
|
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) {
|
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
|
||||||
name := c.GetString("tun.dev", "")
|
ifIndex, ok := utunIndex(c.GetString("tun.dev", ""))
|
||||||
ifIndex := -1
|
if !ok {
|
||||||
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
|
// NOTE: we don't make this error so we don't break existing
|
||||||
// configs that set a name before it was used.
|
// configs that set a name before it was used.
|
||||||
l.Warn("interface name must be utun[0-9]+ on Darwin, ignoring")
|
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)
|
fd, err := unix.Socket(unix.AF_SYSTEM, unix.SOCK_DGRAM, unix.AF_SYS_CONTROL)
|
||||||
@@ -112,7 +128,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
|||||||
return nil, fmt.Errorf("SYS_CONNECT: %v", err)
|
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 {
|
if err != nil {
|
||||||
return nil, fmt.Errorf("failed to retrieve tun name: %w", err)
|
return nil, fmt.Errorf("failed to retrieve tun name: %w", err)
|
||||||
}
|
}
|
||||||
@@ -130,15 +146,20 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
|||||||
l: l,
|
l: l,
|
||||||
}
|
}
|
||||||
|
|
||||||
err = t.reload(c, true)
|
err = t.reload(c, true, nil)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
err := t.reload(c, false)
|
r.RestartRequiredIfChanged("tun.mtu")
|
||||||
|
if tunDevNeedsRestart(c.GetString("tun.dev", ""), t.Device) {
|
||||||
|
r.RestartRequiredIfChanged("tun.dev")
|
||||||
|
}
|
||||||
|
err := t.reload(c, false, r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
|
||||||
@@ -172,14 +193,15 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
|
|||||||
l: l,
|
l: l,
|
||||||
}
|
}
|
||||||
|
|
||||||
if err := t.reload(c, true); err != nil {
|
if err := t.reload(c, true, nil); err != nil {
|
||||||
_ = file.Close()
|
_ = file.Close()
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
if err := t.reload(c, false); err != nil {
|
if err := t.reload(c, false, r); err != nil {
|
||||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
|
||||||
@@ -243,7 +265,7 @@ func (t *tun) Activate() error {
|
|||||||
if linkAddr == nil {
|
if linkAddr == nil {
|
||||||
return fmt.Errorf("unable to discover link_addr for tun interface")
|
return fmt.Errorf("unable to discover link_addr for tun interface")
|
||||||
}
|
}
|
||||||
t.linkAddr = linkAddr
|
t.linkAddr.Store(linkAddr)
|
||||||
|
|
||||||
for _, network := range t.vpnNetworks {
|
for _, network := range t.vpnNetworks {
|
||||||
if network.Addr().Is4() {
|
if network.Addr().Is4() {
|
||||||
@@ -266,9 +288,10 @@ func (t *tun) Activate() error {
|
|||||||
}
|
}
|
||||||
|
|
||||||
// Unsafe path routes
|
// Unsafe path routes
|
||||||
return t.addRoutes(false)
|
return t.addRoutes(false, nil)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// activate4 assigns our vpn address as a /32 and routes the vpn network to the tun explicitly.
|
||||||
func (t *tun) activate4(network netip.Prefix) error {
|
func (t *tun) activate4(network netip.Prefix) error {
|
||||||
s, err := unix.Socket(
|
s, err := unix.Socket(
|
||||||
unix.AF_INET,
|
unix.AF_INET,
|
||||||
@@ -295,22 +318,32 @@ func (t *tun) activate4(network netip.Prefix) error {
|
|||||||
MaskAddr: unix.RawSockaddrInet4{
|
MaskAddr: unix.RawSockaddrInet4{
|
||||||
Len: unix.SizeofSockaddrInet4,
|
Len: unix.SizeofSockaddrInet4,
|
||||||
Family: unix.AF_INET,
|
Family: unix.AF_INET,
|
||||||
Addr: prefixToMask(network).As4(),
|
Addr: [4]byte{255, 255, 255, 255}, //always make the address a /32
|
||||||
},
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// On Darwin, VPNs don't edit the routing table directly.
|
||||||
|
// A network extension hands its routes to the system, and configd installs them.
|
||||||
|
// configd replaces any route already holding the same prefix, including ours.
|
||||||
|
// As an example, Tailscale with an exit node treats any interface prefix wider than one address as a LAN.
|
||||||
|
// With LAN access off, it routes each LAN into Tailscale's utun.
|
||||||
|
// With LAN access on, it excludes each LAN from its tunnel.
|
||||||
|
// configd routes an excluded prefix like its own routes would, ignoring ours, so it goes out the default route.
|
||||||
|
// Either way our route is replaced, and traffic for the vpn network no longer reaches nebula.
|
||||||
|
// A single address isn't a LAN to Tailscale, so our route is left alone.
|
||||||
|
// We route the vpn network to the tun explicitly instead.
|
||||||
|
|
||||||
if err := ioctl(uintptr(s), unix.SIOCAIFADDR, uintptr(unsafe.Pointer(&ifr))); err != nil {
|
if err := ioctl(uintptr(s), unix.SIOCAIFADDR, uintptr(unsafe.Pointer(&ifr))); err != nil {
|
||||||
return fmt.Errorf("failed to set tun v4 address: %s", err)
|
return fmt.Errorf("failed to set tun v4 address: %s", err)
|
||||||
}
|
}
|
||||||
|
|
||||||
err = addRoute(network, t.linkAddr)
|
if err := addRoute(network, t.linkAddr.Load()); err != nil {
|
||||||
if err != nil {
|
return fmt.Errorf("failed to add route for %v: %w", network.Masked(), err)
|
||||||
return err
|
|
||||||
}
|
}
|
||||||
|
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// activate6 is activate4 for IPv6
|
||||||
func (t *tun) activate6(network netip.Prefix) error {
|
func (t *tun) activate6(network netip.Prefix) error {
|
||||||
s, err := unix.Socket(
|
s, err := unix.Socket(
|
||||||
unix.AF_INET6,
|
unix.AF_INET6,
|
||||||
@@ -332,24 +365,28 @@ func (t *tun) activate6(network netip.Prefix) error {
|
|||||||
PrefixMask: unix.RawSockaddrInet6{
|
PrefixMask: unix.RawSockaddrInet6{
|
||||||
Len: unix.SizeofSockaddrInet6,
|
Len: unix.SizeofSockaddrInet6,
|
||||||
Family: unix.AF_INET6,
|
Family: unix.AF_INET6,
|
||||||
Addr: prefixToMask(network).As16(),
|
// Always set the netmask to be a /128. See activate4 for why we do this.
|
||||||
|
Addr: [16]byte{255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255},
|
||||||
},
|
},
|
||||||
Lifetime: addrLifetime{
|
Lifetime: addrLifetime{
|
||||||
// never expires
|
// never expires
|
||||||
Vltime: 0xffffffff,
|
Vltime: 0xffffffff,
|
||||||
Pltime: 0xffffffff,
|
Pltime: 0xffffffff,
|
||||||
},
|
},
|
||||||
Flags: _IN6_IFF_NODAD,
|
Flags: _IN6_IFF_NODAD, // No DAD, a utun has no neighbors.
|
||||||
}
|
}
|
||||||
|
|
||||||
if err := ioctl(uintptr(s), _SIOCAIFADDR_IN6, uintptr(unsafe.Pointer(&ifr))); err != nil {
|
if err := ioctl(uintptr(s), _SIOCAIFADDR_IN6, uintptr(unsafe.Pointer(&ifr))); err != nil {
|
||||||
return fmt.Errorf("failed to set tun address: %s", err)
|
return fmt.Errorf("failed to set tun address: %s", err)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
if err := addRoute(network, t.linkAddr.Load()); err != nil {
|
||||||
|
return fmt.Errorf("failed to add route for %v: %w", network.Masked(), err)
|
||||||
|
}
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) reload(c *config.C, initial bool) error {
|
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return err
|
||||||
@@ -370,16 +407,18 @@ func (t *tun) reload(c *config.C, initial bool) error {
|
|||||||
|
|
||||||
if !initial {
|
if !initial {
|
||||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
|
|
||||||
// Ensure any routes we actually want are installed
|
// Ensure any routes we actually want are installed
|
||||||
err = t.addRoutes(true)
|
err = t.addRoutes(true, r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
// Catch any stray logs
|
// Catch any stray logs
|
||||||
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -394,6 +433,56 @@ func (t *tun) RoutesFor(ip netip.Addr) routing.Gateways {
|
|||||||
return routing.Gateways{}
|
return routing.Gateways{}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func fetchRoutes() ([]netroute.Message, error) {
|
||||||
|
rib, err := netroute.FetchRIB(unix.AF_UNSPEC, unix.NET_RT_DUMP, 0)
|
||||||
|
if err != nil {
|
||||||
|
return nil, err
|
||||||
|
}
|
||||||
|
return netroute.ParseRIB(unix.NET_RT_DUMP, rib)
|
||||||
|
}
|
||||||
|
|
||||||
|
// routeInterfaceIn returns the index of the interface prefix is routed through, or 0 if msgs has no route for exactly
|
||||||
|
// that prefix. Routes scoped to an interface are skipped, they don't stop us adding ours.
|
||||||
|
func routeInterfaceIn(msgs []netroute.Message, prefix netip.Prefix) int {
|
||||||
|
for _, msg := range msgs {
|
||||||
|
m, ok := msg.(*netroute.RouteMessage)
|
||||||
|
if !ok || len(m.Addrs) <= unix.RTAX_NETMASK || m.Flags&unix.RTF_IFSCOPE != 0 {
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
if p, ok := routePrefix(m.Addrs[unix.RTAX_DST], m.Addrs[unix.RTAX_NETMASK]); ok && p == prefix.Masked() {
|
||||||
|
return m.Index
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return 0
|
||||||
|
}
|
||||||
|
|
||||||
|
// routePrefix returns the prefix a route covers. Host routes have no netmask.
|
||||||
|
func routePrefix(dst, mask netroute.Addr) (netip.Prefix, bool) {
|
||||||
|
switch d := dst.(type) {
|
||||||
|
case *netroute.Inet4Addr:
|
||||||
|
bits := 32
|
||||||
|
if m, ok := mask.(*netroute.Inet4Addr); ok {
|
||||||
|
bits = maskBits(m.IP[:])
|
||||||
|
}
|
||||||
|
return netip.PrefixFrom(netip.AddrFrom4(d.IP), bits), true
|
||||||
|
case *netroute.Inet6Addr:
|
||||||
|
bits := 128
|
||||||
|
if m, ok := mask.(*netroute.Inet6Addr); ok {
|
||||||
|
bits = maskBits(m.IP[:])
|
||||||
|
}
|
||||||
|
return netip.PrefixFrom(netip.AddrFrom16(d.IP), bits), true
|
||||||
|
}
|
||||||
|
return netip.Prefix{}, false
|
||||||
|
}
|
||||||
|
|
||||||
|
func maskBits(mask []byte) int {
|
||||||
|
n := 0
|
||||||
|
for _, b := range mask {
|
||||||
|
n += bits.OnesCount8(b)
|
||||||
|
}
|
||||||
|
return n
|
||||||
|
}
|
||||||
|
|
||||||
// Get the LinkAddr for the interface of the given name
|
// Get the LinkAddr for the interface of the given name
|
||||||
// Is there an easier way to fetch this when we create the interface?
|
// Is there an easier way to fetch this when we create the interface?
|
||||||
// Maybe SIOCGIFINDEX? but this doesn't appear to exist in the darwin headers.
|
// Maybe SIOCGIFINDEX? but this doesn't appear to exist in the darwin headers.
|
||||||
@@ -422,13 +511,20 @@ func getLinkAddr(name string) (*netroute.LinkAddr, error) {
|
|||||||
return nil, nil
|
return nil, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) addRoutes(logErrors bool) error {
|
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||||
// The route tree is still ours, the system routing table is not
|
// The route tree is still ours, the system routing table is not
|
||||||
if t.hostOwned {
|
if t.hostOwned {
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Activate hasn't run yet, it will install the routes
|
||||||
|
linkAddr := t.linkAddr.Load()
|
||||||
|
if linkAddr == nil {
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
|
||||||
routes := *t.Routes.Load()
|
routes := *t.Routes.Load()
|
||||||
|
systemRoutes := sync.OnceValues(fetchRoutes)
|
||||||
|
|
||||||
for _, r := range routes {
|
for _, r := range routes {
|
||||||
if len(r.Via) == 0 || !r.Install {
|
if len(r.Via) == 0 || !r.Install {
|
||||||
@@ -436,39 +532,54 @@ func (t *tun) addRoutes(logErrors bool) error {
|
|||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|
||||||
err := addRoute(r.Cidr, t.linkAddr)
|
err := addRoute(r.Cidr, linkAddr)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
if errors.Is(err, unix.EEXIST) {
|
if errors.Is(err, unix.EEXIST) {
|
||||||
t.l.Warn("unable to add unsafe_route, identical route already exists", "route", r.Cidr)
|
// Every route we added already exists on a reload, only warn about someone else's
|
||||||
|
msgs, err := systemRoutes()
|
||||||
|
if err != nil {
|
||||||
|
t.l.Warn("unable to add unsafe_route, a route already exists but its interface could not be determined", "route", r.Cidr, "error", err)
|
||||||
|
} else if routeInterfaceIn(msgs, r.Cidr) != linkAddr.Index {
|
||||||
|
t.l.Warn("unable to add unsafe_route, the destination is already routed through another interface", "route", r.Cidr)
|
||||||
|
}
|
||||||
} else {
|
} else {
|
||||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||||
if logErrors {
|
if logErrors {
|
||||||
retErr.Log(t.l)
|
retErr.Log(t.l)
|
||||||
|
rl.Failed()
|
||||||
} else {
|
} else {
|
||||||
return retErr
|
return retErr
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
} else {
|
} else {
|
||||||
t.l.Info("Added route", "route", r)
|
t.l.Info("Added route", "route", r)
|
||||||
|
// A cidr listed twice would otherwise find our own route missing from an older fetch
|
||||||
|
systemRoutes = sync.OnceValues(fetchRoutes)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) removeRoutes(routes []Route) error {
|
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||||
if t.hostOwned {
|
linkAddr := t.linkAddr.Load()
|
||||||
|
if t.hostOwned || linkAddr == nil {
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
for _, r := range routes {
|
for _, r := range routes {
|
||||||
if !r.Install {
|
if len(r.Via) == 0 || !r.Install {
|
||||||
|
// addRoutes never installs these
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|
||||||
err := delRoute(r.Cidr, t.linkAddr)
|
err := delRoute(r.Cidr, linkAddr)
|
||||||
if err != nil {
|
if errors.Is(err, unix.ESRCH) {
|
||||||
|
// Already gone, which is what we wanted
|
||||||
|
t.l.Info("Route was already removed", "route", r)
|
||||||
|
} else if err != nil {
|
||||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||||
|
rl.Failed()
|
||||||
} else {
|
} else {
|
||||||
t.l.Info("Removed route", "route", r)
|
t.l.Info("Removed route", "route", r)
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -0,0 +1,118 @@
|
|||||||
|
//go:build darwin && !ios && !e2e_testing
|
||||||
|
|
||||||
|
package overlay
|
||||||
|
|
||||||
|
import (
|
||||||
|
"net"
|
||||||
|
"net/netip"
|
||||||
|
"os"
|
||||||
|
"os/exec"
|
||||||
|
"strings"
|
||||||
|
"testing"
|
||||||
|
|
||||||
|
"github.com/slackhq/nebula/config"
|
||||||
|
"github.com/slackhq/nebula/routing"
|
||||||
|
"github.com/slackhq/nebula/test"
|
||||||
|
"github.com/stretchr/testify/assert"
|
||||||
|
"github.com/stretchr/testify/require"
|
||||||
|
netroute "golang.org/x/net/route"
|
||||||
|
"golang.org/x/sys/unix"
|
||||||
|
)
|
||||||
|
|
||||||
|
// Every mac routes loopback through lo0
|
||||||
|
func TestRouteInterfaceIn(t *testing.T) {
|
||||||
|
msgs, err := fetchRoutes()
|
||||||
|
require.NoError(t, err)
|
||||||
|
routeInterface := func(s string) int { return routeInterfaceIn(msgs, netip.MustParsePrefix(s)) }
|
||||||
|
|
||||||
|
lo0, err := net.InterfaceByName("lo0")
|
||||||
|
require.NoError(t, err)
|
||||||
|
|
||||||
|
assert.Equal(t, lo0.Index, routeInterface("127.0.0.0/8"))
|
||||||
|
assert.Equal(t, lo0.Index, routeInterface("127.0.0.1/32"), "a host route has no netmask")
|
||||||
|
assert.Equal(t, lo0.Index, routeInterface("::1/128"))
|
||||||
|
assert.Equal(t, 0, routeInterface("127.0.0.0/16"), "only an exact prefix counts")
|
||||||
|
|
||||||
|
// Most macs also list the default route scoped to their other interfaces
|
||||||
|
out, err := exec.Command("route", "-n", "get", "default").Output()
|
||||||
|
require.NoError(t, err)
|
||||||
|
var name string
|
||||||
|
for _, line := range strings.Split(string(out), "\n") {
|
||||||
|
if v, ok := strings.CutPrefix(strings.TrimSpace(line), "interface: "); ok {
|
||||||
|
name = v
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if name == "" {
|
||||||
|
t.Skip("no default route")
|
||||||
|
}
|
||||||
|
def, err := net.InterfaceByName(name)
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, def.Index, routeInterface("0.0.0.0/0"))
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestRouteInterfaceIn_SkipsScopedCopies(t *testing.T) {
|
||||||
|
route := func(index, flags int) netroute.Message {
|
||||||
|
addrs := make([]netroute.Addr, unix.RTAX_MAX)
|
||||||
|
addrs[unix.RTAX_DST] = &netroute.Inet4Addr{IP: [4]byte{192, 168, 1, 0}}
|
||||||
|
addrs[unix.RTAX_NETMASK] = &netroute.Inet4Addr{IP: [4]byte{255, 255, 255, 0}}
|
||||||
|
return &netroute.RouteMessage{Index: index, Flags: flags, Addrs: addrs}
|
||||||
|
}
|
||||||
|
p := netip.MustParsePrefix("192.168.1.0/24")
|
||||||
|
assert.Equal(t, 7, routeInterfaceIn([]netroute.Message{route(4, unix.RTF_UP|unix.RTF_IFSCOPE), route(7, unix.RTF_UP)}, p))
|
||||||
|
assert.Equal(t, 0, routeInterfaceIn([]netroute.Message{route(4, unix.RTF_UP|unix.RTF_IFSCOPE)}, p))
|
||||||
|
}
|
||||||
|
|
||||||
|
// A reload can happen before Activate
|
||||||
|
func TestTunRoutesBeforeActivate(t *testing.T) {
|
||||||
|
tn := &tun{l: test.NewLogger()}
|
||||||
|
routes := []Route{{
|
||||||
|
Cidr: netip.MustParsePrefix("10.253.1.0/24"),
|
||||||
|
Via: routing.Gateways{routing.NewGateway(netip.MustParseAddr("10.250.0.2"), 1)},
|
||||||
|
Install: true,
|
||||||
|
}}
|
||||||
|
tn.Routes.Store(&routes)
|
||||||
|
|
||||||
|
assert.NoError(t, tn.addRoutes(true, nil))
|
||||||
|
assert.NoError(t, tn.removeRoutes(routes, nil))
|
||||||
|
}
|
||||||
|
|
||||||
|
// A tun.routes entry with no via is never installed, so removing it must not delete a route for the same cidr that
|
||||||
|
// belongs to someone else
|
||||||
|
func TestTunReloadLeavesRoutesItNeverInstalled(t *testing.T) {
|
||||||
|
if os.Geteuid() != 0 {
|
||||||
|
t.Skip("creating a utun and adding routes needs root")
|
||||||
|
}
|
||||||
|
lo0, err := net.InterfaceByName("lo0")
|
||||||
|
require.NoError(t, err)
|
||||||
|
cidr := "10.250.0.128/25"
|
||||||
|
require.NoError(t, exec.Command("route", "-q", "-n", "add", "-net", cidr, "-interface", "lo0").Run())
|
||||||
|
t.Cleanup(func() { _ = exec.Command("route", "-q", "-n", "delete", "-net", cidr).Run() })
|
||||||
|
|
||||||
|
l := test.NewLogger()
|
||||||
|
c := config.NewC(l)
|
||||||
|
require.NoError(t, c.LoadString("tun:\n routes:\n - route: "+cidr+"\n mtu: 1300\n"))
|
||||||
|
tn, err := newTun(c, l, []netip.Prefix{netip.MustParsePrefix("10.250.0.1/24")}, false)
|
||||||
|
require.NoError(t, err)
|
||||||
|
t.Cleanup(func() { _ = tn.Close() })
|
||||||
|
require.NoError(t, tn.Activate())
|
||||||
|
|
||||||
|
res := c.ReloadConfigString("tun: {}\n")
|
||||||
|
require.NoError(t, res.Err)
|
||||||
|
assert.False(t, res.Failed, "removing a route we never installed failed the reload")
|
||||||
|
msgs, err := fetchRoutes()
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, lo0.Index, routeInterfaceIn(msgs, netip.MustParsePrefix(cidr)))
|
||||||
|
}
|
||||||
|
|
||||||
|
// Only naming a different utun asks for a restart. Empty, plain utun and names that aren't utunN take whichever is free
|
||||||
|
func TestTunDevNeedsRestart(t *testing.T) {
|
||||||
|
for name, want := range map[string]bool{
|
||||||
|
"": false,
|
||||||
|
"utun": false,
|
||||||
|
"nope": false,
|
||||||
|
"utun7": false,
|
||||||
|
"utun3": true,
|
||||||
|
} {
|
||||||
|
assert.Equal(t, want, tunDevNeedsRestart(name, "utun7"), name)
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,121 @@
|
|||||||
|
//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)
|
||||||
|
}
|
||||||
+21
-11
@@ -385,16 +385,18 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
|||||||
},
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
err = t.reload(c, true)
|
err = t.reload(c, true, nil)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
closeOnErr = false
|
closeOnErr = false
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
err := t.reload(c, false)
|
r.RestartRequiredIfChanged("tun.dev", "tun.mtu")
|
||||||
|
err := t.reload(c, false, r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
|
||||||
@@ -493,7 +495,7 @@ func (t *tun) Activate() error {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
return t.addRoutes(false)
|
return t.addRoutes(false, nil)
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) setMTU() error {
|
func (t *tun) setMTU() error {
|
||||||
@@ -509,7 +511,7 @@ func (t *tun) setMTU() error {
|
|||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) reload(c *config.C, initial bool) error {
|
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return err
|
||||||
@@ -530,16 +532,18 @@ func (t *tun) reload(c *config.C, initial bool) error {
|
|||||||
|
|
||||||
if !initial {
|
if !initial {
|
||||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
|
|
||||||
// Ensure any routes we actually want are installed
|
// Ensure any routes we actually want are installed
|
||||||
err = t.addRoutes(true)
|
err = t.addRoutes(true, r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
// Catch any stray logs
|
// Catch any stray logs
|
||||||
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -563,7 +567,7 @@ func (t *tun) Queues(int) ([]tio.Queue, error) {
|
|||||||
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) addRoutes(logErrors bool) error {
|
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||||
routes := *t.Routes.Load()
|
routes := *t.Routes.Load()
|
||||||
for _, r := range routes {
|
for _, r := range routes {
|
||||||
if len(r.Via) == 0 || !r.Install {
|
if len(r.Via) == 0 || !r.Install {
|
||||||
@@ -576,6 +580,7 @@ func (t *tun) addRoutes(logErrors bool) error {
|
|||||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||||
if logErrors {
|
if logErrors {
|
||||||
retErr.Log(t.l)
|
retErr.Log(t.l)
|
||||||
|
rl.Failed()
|
||||||
} else {
|
} else {
|
||||||
return retErr
|
return retErr
|
||||||
}
|
}
|
||||||
@@ -587,15 +592,20 @@ func (t *tun) addRoutes(logErrors bool) error {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) removeRoutes(routes []Route) error {
|
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||||
for _, r := range routes {
|
for _, r := range routes {
|
||||||
if !r.Install {
|
if len(r.Via) == 0 || !r.Install {
|
||||||
|
// addRoutes never installs these
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|
||||||
err := delRoute(r.Cidr, t.linkAddr)
|
err := delRoute(r.Cidr, t.linkAddr)
|
||||||
if err != nil {
|
if errors.Is(err, unix.ESRCH) {
|
||||||
|
// Already gone, which is what we wanted
|
||||||
|
t.l.Info("Route was already removed", "route", r)
|
||||||
|
} else if err != nil {
|
||||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||||
|
rl.Failed()
|
||||||
} else {
|
} else {
|
||||||
t.l.Info("Removed route", "route", r)
|
t.l.Info("Removed route", "route", r)
|
||||||
}
|
}
|
||||||
|
|||||||
+5
-4
@@ -47,16 +47,17 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
|
|||||||
l: l,
|
l: l,
|
||||||
}
|
}
|
||||||
|
|
||||||
err := t.reload(c, true)
|
err := t.reload(c, true, nil)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
_ = file.Close()
|
_ = file.Close()
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
err := t.reload(c, false)
|
err := t.reload(c, false, r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
|
||||||
@@ -67,7 +68,7 @@ func (t *tun) Activate() error {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) reload(c *config.C, initial bool) error {
|
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return err
|
||||||
|
|||||||
+28
-14
@@ -185,6 +185,10 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, multiqueue
|
|||||||
}
|
}
|
||||||
|
|
||||||
t.Device = name
|
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
|
return t, nil
|
||||||
}
|
}
|
||||||
@@ -228,22 +232,24 @@ func newTunGeneric(c *config.C, l *slog.Logger, fd int, vnetHdr bool, offloadFla
|
|||||||
l: l,
|
l: l,
|
||||||
}
|
}
|
||||||
|
|
||||||
if err = t.reload(c, true); err != nil {
|
if err = t.reload(c, true, nil); err != nil {
|
||||||
_ = t.Close()
|
_ = t.Close()
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
err := t.reload(c, false)
|
r.RestartRequiredIfChanged("tun.tx_queue", "tun.use_system_route_table", "tun.use_system_route_table_buffer_size")
|
||||||
|
err := t.reload(c, false, r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
|
||||||
return t, nil
|
return t, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) reload(c *config.C, initial bool) error {
|
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||||
routeChange, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
routeChange, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return err
|
||||||
@@ -297,7 +303,7 @@ func (t *tun) reload(c *config.C, initial bool) error {
|
|||||||
|
|
||||||
if !initial {
|
if !initial {
|
||||||
if oldMaxMTU != newMaxMTU {
|
if oldMaxMTU != newMaxMTU {
|
||||||
t.setMTU()
|
t.setMTU(r)
|
||||||
t.l.Info("Set max MTU", "mtu", t.MaxMTU, "oldMTU", oldMaxMTU)
|
t.l.Info("Set max MTU", "mtu", t.MaxMTU, "oldMTU", oldMaxMTU)
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -305,7 +311,8 @@ func (t *tun) reload(c *config.C, initial bool) error {
|
|||||||
for i := range t.vpnNetworks {
|
for i := range t.vpnNetworks {
|
||||||
err := t.setDefaultRoute(t.vpnNetworks[i])
|
err := t.setDefaultRoute(t.vpnNetworks[i])
|
||||||
if err != nil {
|
if err != nil {
|
||||||
t.l.Warn(err.Error())
|
t.l.Error(err.Error())
|
||||||
|
r.Failed()
|
||||||
} else {
|
} else {
|
||||||
t.l.Info("Set default MTU", "mtu", t.DefaultMTU, "oldMTU", oldDefaultMTU)
|
t.l.Info("Set default MTU", "mtu", t.DefaultMTU, "oldMTU", oldDefaultMTU)
|
||||||
}
|
}
|
||||||
@@ -313,13 +320,14 @@ func (t *tun) reload(c *config.C, initial bool) error {
|
|||||||
}
|
}
|
||||||
|
|
||||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||||
t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
|
||||||
|
|
||||||
// Ensure any routes we actually want are installed
|
// Ensure any routes we actually want are installed
|
||||||
err = t.addRoutes(true)
|
err = t.addRoutes(true, r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
// This should never be called since addRoutes should log its own errors in a reload condition
|
// 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)
|
util.LogWithContextIfNeeded("Failed to refresh routes", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -474,7 +482,7 @@ func (t *tun) Activate() error {
|
|||||||
t.deviceIndex = link.Attrs().Index
|
t.deviceIndex = link.Attrs().Index
|
||||||
|
|
||||||
// Setup our default MTU
|
// Setup our default MTU
|
||||||
t.setMTU()
|
t.setMTU(nil)
|
||||||
|
|
||||||
// Set the transmit queue length
|
// Set the transmit queue length
|
||||||
ifrq := ifreqQLEN{Name: devName, Value: int32(t.TXQueueLen)}
|
ifrq := ifreqQLEN{Name: devName, Value: int32(t.TXQueueLen)}
|
||||||
@@ -506,7 +514,7 @@ func (t *tun) Activate() error {
|
|||||||
}
|
}
|
||||||
|
|
||||||
// Set the routes
|
// Set the routes
|
||||||
if err = t.addRoutes(false); err != nil {
|
if err = t.addRoutes(false, nil); err != nil {
|
||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -519,12 +527,13 @@ func (t *tun) Activate() error {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) setMTU() {
|
func (t *tun) setMTU(r *config.Reload) {
|
||||||
// Set the MTU on the device
|
// Set the MTU on the device
|
||||||
ifm := ifreqMTU{Name: t.deviceBytes(), MTU: int32(t.MaxMTU)}
|
ifm := ifreqMTU{Name: t.deviceBytes(), MTU: int32(t.MaxMTU)}
|
||||||
if err := ioctl(t.ioctlFd, unix.SIOCSIFMTU, uintptr(unsafe.Pointer(&ifm))); err != nil {
|
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
|
// 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)
|
t.l.Error("Failed to set tun mtu", "error", err)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -577,7 +586,7 @@ func (t *tun) setDefaultRoute(cidr netip.Prefix) error {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) addRoutes(logErrors bool) error {
|
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||||
// Path routes
|
// Path routes
|
||||||
routes := *t.Routes.Load()
|
routes := *t.Routes.Load()
|
||||||
for _, r := range routes {
|
for _, r := range routes {
|
||||||
@@ -607,6 +616,7 @@ func (t *tun) addRoutes(logErrors bool) error {
|
|||||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||||
if logErrors {
|
if logErrors {
|
||||||
retErr.Log(t.l)
|
retErr.Log(t.l)
|
||||||
|
rl.Failed()
|
||||||
} else {
|
} else {
|
||||||
return retErr
|
return retErr
|
||||||
}
|
}
|
||||||
@@ -618,7 +628,7 @@ func (t *tun) addRoutes(logErrors bool) error {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) removeRoutes(routes []Route) {
|
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) {
|
||||||
for _, r := range routes {
|
for _, r := range routes {
|
||||||
if !r.Install {
|
if !r.Install {
|
||||||
continue
|
continue
|
||||||
@@ -642,8 +652,12 @@ func (t *tun) removeRoutes(routes []Route) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
err := netlink.RouteDel(&nr)
|
err := netlink.RouteDel(&nr)
|
||||||
if err != nil {
|
if errors.Is(err, unix.ESRCH) {
|
||||||
|
// Already gone, which is what we wanted
|
||||||
|
t.l.Info("Route was already removed", "route", r)
|
||||||
|
} else if err != nil {
|
||||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||||
|
rl.Failed()
|
||||||
} else {
|
} else {
|
||||||
t.l.Info("Removed route", "route", r)
|
t.l.Info("Removed route", "route", r)
|
||||||
}
|
}
|
||||||
|
|||||||
+25
-25
@@ -8,7 +8,6 @@ import (
|
|||||||
"log/slog"
|
"log/slog"
|
||||||
"net/netip"
|
"net/netip"
|
||||||
"os"
|
"os"
|
||||||
"regexp"
|
|
||||||
"sync/atomic"
|
"sync/atomic"
|
||||||
"syscall"
|
"syscall"
|
||||||
"unsafe"
|
"unsafe"
|
||||||
@@ -67,24 +66,12 @@ type tun struct {
|
|||||||
fd int
|
fd int
|
||||||
}
|
}
|
||||||
|
|
||||||
var deviceNameRE = regexp.MustCompile(`^tun[0-9]+$`)
|
|
||||||
|
|
||||||
func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
|
func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
|
||||||
return nil, fmt.Errorf("newTunFromFd not supported in NetBSD")
|
return nil, fmt.Errorf("newTunFromFd not supported in NetBSD")
|
||||||
}
|
}
|
||||||
|
|
||||||
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
|
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
|
||||||
// Try to open tun device
|
fd, deviceName, err := openTun(l, c.GetString("tun.dev", ""))
|
||||||
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 {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
@@ -103,15 +90,20 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
|||||||
l: l,
|
l: l,
|
||||||
}
|
}
|
||||||
|
|
||||||
err = t.reload(c, true)
|
err = t.reload(c, true, nil)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
err := t.reload(c, false)
|
r.RestartRequiredIfChanged("tun.mtu")
|
||||||
|
if tunDevNeedsRestart(c.GetString("tun.dev", ""), t.Device) {
|
||||||
|
r.RestartRequiredIfChanged("tun.dev")
|
||||||
|
}
|
||||||
|
err := t.reload(c, false, r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
|
||||||
@@ -324,7 +316,7 @@ func (t *tun) Activate() error {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
return t.addRoutes(false)
|
return t.addRoutes(false, nil)
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
||||||
@@ -339,7 +331,7 @@ func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
|||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) reload(c *config.C, initial bool) error {
|
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return err
|
||||||
@@ -360,16 +352,18 @@ func (t *tun) reload(c *config.C, initial bool) error {
|
|||||||
|
|
||||||
if !initial {
|
if !initial {
|
||||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
|
|
||||||
// Ensure any routes we actually want are installed
|
// Ensure any routes we actually want are installed
|
||||||
err = t.addRoutes(true)
|
err = t.addRoutes(true, r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
// Catch any stray logs
|
// Catch any stray logs
|
||||||
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -393,7 +387,7 @@ func (t *tun) Queues(int) ([]tio.Queue, error) {
|
|||||||
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) addRoutes(logErrors bool) error {
|
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||||
routes := *t.Routes.Load()
|
routes := *t.Routes.Load()
|
||||||
|
|
||||||
for _, r := range routes {
|
for _, r := range routes {
|
||||||
@@ -407,6 +401,7 @@ func (t *tun) addRoutes(logErrors bool) error {
|
|||||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||||
if logErrors {
|
if logErrors {
|
||||||
retErr.Log(t.l)
|
retErr.Log(t.l)
|
||||||
|
rl.Failed()
|
||||||
} else {
|
} else {
|
||||||
return retErr
|
return retErr
|
||||||
}
|
}
|
||||||
@@ -418,15 +413,20 @@ func (t *tun) addRoutes(logErrors bool) error {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) removeRoutes(routes []Route) error {
|
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||||
for _, r := range routes {
|
for _, r := range routes {
|
||||||
if !r.Install {
|
if len(r.Via) == 0 || !r.Install {
|
||||||
|
// addRoutes never installs these
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|
||||||
err := delRoute(r.Cidr, t.vpnNetworks)
|
err := delRoute(r.Cidr, t.vpnNetworks)
|
||||||
if err != nil {
|
if errors.Is(err, unix.ESRCH) {
|
||||||
|
// Already gone, which is what we wanted
|
||||||
|
t.l.Info("Route was already removed", "route", r)
|
||||||
|
} else if err != nil {
|
||||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||||
|
rl.Failed()
|
||||||
} else {
|
} else {
|
||||||
t.l.Info("Removed route", "route", r)
|
t.l.Info("Removed route", "route", r)
|
||||||
}
|
}
|
||||||
|
|||||||
+25
-25
@@ -8,7 +8,6 @@ import (
|
|||||||
"log/slog"
|
"log/slog"
|
||||||
"net/netip"
|
"net/netip"
|
||||||
"os"
|
"os"
|
||||||
"regexp"
|
|
||||||
"sync/atomic"
|
"sync/atomic"
|
||||||
"syscall"
|
"syscall"
|
||||||
"unsafe"
|
"unsafe"
|
||||||
@@ -58,24 +57,12 @@ type tun struct {
|
|||||||
fd int
|
fd int
|
||||||
}
|
}
|
||||||
|
|
||||||
var deviceNameRE = regexp.MustCompile(`^tun[0-9]+$`)
|
|
||||||
|
|
||||||
func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
|
func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
|
||||||
return nil, fmt.Errorf("newTunFromFd not supported in openbsd")
|
return nil, fmt.Errorf("newTunFromFd not supported in openbsd")
|
||||||
}
|
}
|
||||||
|
|
||||||
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
|
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
|
||||||
// Try to open tun device
|
fd, deviceName, err := openTun(l, c.GetString("tun.dev", ""))
|
||||||
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 {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
@@ -94,15 +81,20 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
|||||||
l: l,
|
l: l,
|
||||||
}
|
}
|
||||||
|
|
||||||
err = t.reload(c, true)
|
err = t.reload(c, true, nil)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
err := t.reload(c, false)
|
r.RestartRequiredIfChanged("tun.mtu")
|
||||||
|
if tunDevNeedsRestart(c.GetString("tun.dev", ""), t.Device) {
|
||||||
|
r.RestartRequiredIfChanged("tun.dev")
|
||||||
|
}
|
||||||
|
err := t.reload(c, false, r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
|
||||||
@@ -303,7 +295,7 @@ func (t *tun) Activate() error {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
return t.addRoutes(false)
|
return t.addRoutes(false, nil)
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
||||||
@@ -318,7 +310,7 @@ func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
|||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) reload(c *config.C, initial bool) error {
|
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return err
|
||||||
@@ -339,16 +331,18 @@ func (t *tun) reload(c *config.C, initial bool) error {
|
|||||||
|
|
||||||
if !initial {
|
if !initial {
|
||||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
|
|
||||||
// Ensure any routes we actually want are installed
|
// Ensure any routes we actually want are installed
|
||||||
err = t.addRoutes(true)
|
err = t.addRoutes(true, r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
// Catch any stray logs
|
// Catch any stray logs
|
||||||
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -372,7 +366,7 @@ func (t *tun) Queues(int) ([]tio.Queue, error) {
|
|||||||
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) addRoutes(logErrors bool) error {
|
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||||
routes := *t.Routes.Load()
|
routes := *t.Routes.Load()
|
||||||
|
|
||||||
for _, r := range routes {
|
for _, r := range routes {
|
||||||
@@ -386,6 +380,7 @@ func (t *tun) addRoutes(logErrors bool) error {
|
|||||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||||
if logErrors {
|
if logErrors {
|
||||||
retErr.Log(t.l)
|
retErr.Log(t.l)
|
||||||
|
rl.Failed()
|
||||||
} else {
|
} else {
|
||||||
return retErr
|
return retErr
|
||||||
}
|
}
|
||||||
@@ -397,15 +392,20 @@ func (t *tun) addRoutes(logErrors bool) error {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) removeRoutes(routes []Route) error {
|
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||||
for _, r := range routes {
|
for _, r := range routes {
|
||||||
if !r.Install {
|
if len(r.Via) == 0 || !r.Install {
|
||||||
|
// addRoutes never installs these
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|
||||||
err := delRoute(r.Cidr, t.vpnNetworks)
|
err := delRoute(r.Cidr, t.vpnNetworks)
|
||||||
if err != nil {
|
if errors.Is(err, unix.ESRCH) {
|
||||||
|
// Already gone, which is what we wanted
|
||||||
|
t.l.Info("Route was already removed", "route", r)
|
||||||
|
} else if err != nil {
|
||||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||||
|
rl.Failed()
|
||||||
} else {
|
} else {
|
||||||
t.l.Info("Removed route", "route", r)
|
t.l.Info("Removed route", "route", r)
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -4,6 +4,7 @@ package overlay
|
|||||||
|
|
||||||
import (
|
import (
|
||||||
"net/netip"
|
"net/netip"
|
||||||
|
"os"
|
||||||
"testing"
|
"testing"
|
||||||
|
|
||||||
"github.com/slackhq/nebula/config"
|
"github.com/slackhq/nebula/config"
|
||||||
@@ -25,10 +26,10 @@ func TestReloadMTUOnlyKeepsRoutes(t *testing.T) {
|
|||||||
ioctlFd: ^uintptr(0),
|
ioctlFd: ^uintptr(0),
|
||||||
routesFromSystem: map[netip.Prefix]routing.Gateways{},
|
routesFromSystem: map[netip.Prefix]routing.Gateways{},
|
||||||
}
|
}
|
||||||
require.NoError(t, tn.reload(c, true))
|
require.NoError(t, tn.reload(c, true, nil))
|
||||||
|
|
||||||
require.NoError(t, c.ReloadConfigString("tun:\n mtu: 1400\n"+routes))
|
require.NoError(t, c.ReloadConfigString("tun:\n mtu: 1400\n"+routes).Err)
|
||||||
_ = tn.reload(c, false)
|
_ = tn.reload(c, false, nil)
|
||||||
|
|
||||||
got := *tn.Routes.Load()
|
got := *tn.Routes.Load()
|
||||||
require.Len(t, got, 1)
|
require.Len(t, got, 1)
|
||||||
@@ -50,7 +51,57 @@ func TestReloadMaxMTUIsTheLargestRoute(t *testing.T) {
|
|||||||
ioctlFd: ^uintptr(0),
|
ioctlFd: ^uintptr(0),
|
||||||
routesFromSystem: map[netip.Prefix]routing.Gateways{},
|
routesFromSystem: map[netip.Prefix]routing.Gateways{},
|
||||||
}
|
}
|
||||||
require.NoError(t, tn.reload(c, true))
|
require.NoError(t, tn.reload(c, true, nil))
|
||||||
assert.Equal(t, 1500, tn.MaxMTU)
|
assert.Equal(t, 1500, tn.MaxMTU)
|
||||||
assert.Equal(t, 1300, tn.DefaultMTU)
|
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)
|
||||||
|
}
|
||||||
@@ -0,0 +1,24 @@
|
|||||||
|
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)
|
||||||
|
}
|
||||||
+28
-10
@@ -84,7 +84,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*w
|
|||||||
l: l,
|
l: l,
|
||||||
}
|
}
|
||||||
|
|
||||||
err = t.reload(c, true)
|
err = t.reload(c, true, nil)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
@@ -108,17 +108,28 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*w
|
|||||||
// Disable registration before Activate assigns addresses and triggers it.
|
// Disable registration before Activate assigns addresses and triggers it.
|
||||||
disableDNSRegistration(l, *guid)
|
disableDNSRegistration(l, *guid)
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
err := t.reload(c, false)
|
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)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
|
||||||
return t, nil
|
return t, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *winTun) reload(c *config.C, initial bool) error {
|
func (t *winTun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return err
|
||||||
@@ -139,16 +150,18 @@ func (t *winTun) reload(c *config.C, initial bool) error {
|
|||||||
|
|
||||||
if !initial {
|
if !initial {
|
||||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||||
err := t.removeRoutes(findRemovedSystemRoutes(routes, *oldRoutes))
|
err := t.removeRoutes(findRemovedSystemRoutes(routes, *oldRoutes), r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
|
|
||||||
// Ensure any routes we actually want are installed
|
// Ensure any routes we actually want are installed
|
||||||
err = t.addRoutes(true)
|
err = t.addRoutes(true, r)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
// Catch any stray logs
|
// Catch any stray logs
|
||||||
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -163,7 +176,7 @@ func (t *winTun) Activate() error {
|
|||||||
return fmt.Errorf("failed to set address: %w", err)
|
return fmt.Errorf("failed to set address: %w", err)
|
||||||
}
|
}
|
||||||
|
|
||||||
err = t.addRoutes(false)
|
err = t.addRoutes(false, nil)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
@@ -182,7 +195,7 @@ func (t *winTun) Activate() error {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *winTun) addRoutes(logErrors bool) error {
|
func (t *winTun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||||
luid := winipcfg.LUID(t.tun.LUID())
|
luid := winipcfg.LUID(t.tun.LUID())
|
||||||
routes := *t.Routes.Load()
|
routes := *t.Routes.Load()
|
||||||
foundDefault4 := false
|
foundDefault4 := false
|
||||||
@@ -213,6 +226,7 @@ func (t *winTun) addRoutes(logErrors bool) error {
|
|||||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||||
if logErrors {
|
if logErrors {
|
||||||
retErr.Log(t.l)
|
retErr.Log(t.l)
|
||||||
|
rl.Failed()
|
||||||
continue
|
continue
|
||||||
} else {
|
} else {
|
||||||
return retErr
|
return retErr
|
||||||
@@ -274,7 +288,7 @@ func (t *winTun) setMTU(luid winipcfg.LUID, foundDefault4, carriesV6 bool) error
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *winTun) removeRoutes(routes []Route) error {
|
func (t *winTun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||||
luid := winipcfg.LUID(t.tun.LUID())
|
luid := winipcfg.LUID(t.tun.LUID())
|
||||||
|
|
||||||
for _, r := range routes {
|
for _, r := range routes {
|
||||||
@@ -284,8 +298,12 @@ func (t *winTun) removeRoutes(routes []Route) error {
|
|||||||
|
|
||||||
// See comment on luid.AddRoute
|
// See comment on luid.AddRoute
|
||||||
err := luid.DeleteRoute(r.Cidr, unspecifiedNextHop(r.Cidr))
|
err := luid.DeleteRoute(r.Cidr, unspecifiedNextHop(r.Cidr))
|
||||||
if err != nil {
|
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 {
|
||||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||||
|
rl.Failed()
|
||||||
} else {
|
} else {
|
||||||
t.l.Info("Removed route", "route", r)
|
t.l.Info("Removed route", "route", r)
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -53,6 +53,14 @@ func (rt *routeTest) metric(t *testing.T, cidr string) uint32 {
|
|||||||
return row.Metric
|
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 {
|
func unsafeRoutes(routes ...string) string {
|
||||||
var b strings.Builder
|
var b strings.Builder
|
||||||
b.WriteString("tun:\n dev: nebroutetest\n unsafe_routes:\n")
|
b.WriteString("tun:\n dev: nebroutetest\n unsafe_routes:\n")
|
||||||
@@ -77,7 +85,7 @@ func TestWinTun_ReloadKeepsInstalledRoutes(t *testing.T) {
|
|||||||
rt := newRouteTest(t, unsafeRoutes(a))
|
rt := newRouteTest(t, unsafeRoutes(a))
|
||||||
require.NoError(t, rt.tun.Activate())
|
require.NoError(t, rt.tun.Activate())
|
||||||
|
|
||||||
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a, b)))
|
rt.reload(t, unsafeRoutes(a, b))
|
||||||
assert.NotContains(t, rt.log.String(), "Failed to add route")
|
assert.NotContains(t, rt.log.String(), "Failed to add route")
|
||||||
rt.metric(t, a)
|
rt.metric(t, a)
|
||||||
rt.metric(t, b)
|
rt.metric(t, b)
|
||||||
@@ -92,7 +100,7 @@ func TestWinTun_ReloadMetricChangeApplies(t *testing.T) {
|
|||||||
require.NoError(t, rt.tun.Activate())
|
require.NoError(t, rt.tun.Activate())
|
||||||
require.Equal(t, uint32(100), rt.metric(t, a))
|
require.Equal(t, uint32(100), rt.metric(t, a))
|
||||||
|
|
||||||
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a+"@200")))
|
rt.reload(t, unsafeRoutes(a+"@200"))
|
||||||
assert.NotContains(t, rt.log.String(), "Failed to add route")
|
assert.NotContains(t, rt.log.String(), "Failed to add route")
|
||||||
assert.NotContains(t, rt.log.String(), "Removed route")
|
assert.NotContains(t, rt.log.String(), "Removed route")
|
||||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||||
@@ -120,7 +128,7 @@ func TestWinTun_DuplicateCidrInstallsTheLastEntry(t *testing.T) {
|
|||||||
require.NoError(t, rt.tun.Activate())
|
require.NoError(t, rt.tun.Activate())
|
||||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||||
|
|
||||||
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a+"@100", a+"@200", b)))
|
rt.reload(t, unsafeRoutes(a+"@100", a+"@200", b))
|
||||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||||
assert.NotContains(t, rt.log.String(), "Updated route metric")
|
assert.NotContains(t, rt.log.String(), "Updated route metric")
|
||||||
assert.NotContains(t, rt.log.String(), "Failed to add route")
|
assert.NotContains(t, rt.log.String(), "Failed to add route")
|
||||||
@@ -134,7 +142,7 @@ func TestWinTun_DroppingAnUninstalledDuplicateKeepsTheRoute(t *testing.T) {
|
|||||||
rt := newRouteTest(t, unsafeRoutes(a+"@100", a+"@200"))
|
rt := newRouteTest(t, unsafeRoutes(a+"@100", a+"@200"))
|
||||||
require.NoError(t, rt.tun.Activate())
|
require.NoError(t, rt.tun.Activate())
|
||||||
|
|
||||||
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a+"@200")))
|
rt.reload(t, unsafeRoutes(a+"@200"))
|
||||||
assert.NotContains(t, rt.log.String(), "Removed route")
|
assert.NotContains(t, rt.log.String(), "Removed route")
|
||||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||||
})
|
})
|
||||||
@@ -155,12 +163,45 @@ func TestWinTun_ReloadMatchesAFreshStart(t *testing.T) {
|
|||||||
|
|
||||||
rt := newRouteTest(t, unsafeRoutes(a+"@100"))
|
rt := newRouteTest(t, unsafeRoutes(a+"@100"))
|
||||||
require.NoError(t, rt.tun.Activate())
|
require.NoError(t, rt.tun.Activate())
|
||||||
require.NoError(t, rt.c.ReloadConfigString(routes))
|
rt.reload(t, routes)
|
||||||
_, err = rt.luid.Route(cidr, unspecifiedNextHop(cidr))
|
_, err = rt.luid.Route(cidr, unspecifiedNextHop(cidr))
|
||||||
assert.Error(t, err, "the reload left it installed")
|
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
|
// 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)) {
|
func forFamilies(t *testing.T, f func(t *testing.T, a, b string)) {
|
||||||
t.Run("ipv4", func(t *testing.T) { f(t, "10.251.1.0/24", "10.251.2.0/24") })
|
t.Run("ipv4", func(t *testing.T) { f(t, "10.251.1.0/24", "10.251.2.0/24") })
|
||||||
|
|||||||
@@ -2,7 +2,9 @@ package nebula
|
|||||||
|
|
||||||
import (
|
import (
|
||||||
"crypto/fips140"
|
"crypto/fips140"
|
||||||
|
"crypto/sha256"
|
||||||
"encoding/binary"
|
"encoding/binary"
|
||||||
|
"encoding/hex"
|
||||||
"encoding/json"
|
"encoding/json"
|
||||||
"errors"
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
@@ -50,15 +52,30 @@ type CertState struct {
|
|||||||
myVpnBroadcastAddrsTable *bart.Lite
|
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) {
|
func NewPKIFromConfig(l *slog.Logger, c *config.C) (*PKI, error) {
|
||||||
pki := &PKI{l: l}
|
pki := &PKI{l: l}
|
||||||
err := pki.reload(c, true)
|
err := pki.reload(c, true, nil)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
rErr := pki.reload(c, false)
|
// 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)
|
||||||
if rErr != nil {
|
if rErr != nil {
|
||||||
util.LogWithContextIfNeeded("Failed to reload PKI from config", rErr, l)
|
util.LogWithContextIfNeeded("Failed to reload PKI from config", rErr, l)
|
||||||
}
|
}
|
||||||
@@ -75,13 +92,29 @@ func (p *PKI) getCertState() *CertState {
|
|||||||
return p.cs.Load()
|
return p.cs.Load()
|
||||||
}
|
}
|
||||||
|
|
||||||
func (p *PKI) reload(c *config.C, initial bool) error {
|
// r is nil on the initial load
|
||||||
|
func (p *PKI) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||||
|
before := p.cs.Load()
|
||||||
err := p.reloadCerts(c, initial)
|
err := p.reloadCerts(c, initial)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
if initial {
|
if initial {
|
||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
err.Log(p.l)
|
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)
|
err = p.reloadCAPool(c)
|
||||||
@@ -90,21 +123,27 @@ func (p *PKI) reload(c *config.C, initial bool) error {
|
|||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
err.Log(p.l)
|
err.Log(p.l)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
|
|
||||||
return nil
|
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 {
|
func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
||||||
var cipher string
|
var cipher string
|
||||||
var currentState *CertState
|
var currentState *CertState
|
||||||
if initial {
|
if initial {
|
||||||
cipher = c.GetString("cipher", "aes")
|
cipher = c.GetString("cipher", "aes")
|
||||||
switch cipher {
|
if !validCipher(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(
|
return util.NewContextualError(
|
||||||
"unknown cipher",
|
"unknown cipher",
|
||||||
m{"cipher": cipher},
|
m{"cipher": cipher},
|
||||||
@@ -132,7 +171,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
|||||||
return util.NewContextualError(
|
return util.NewContextualError(
|
||||||
"Networks in new cert was different from old",
|
"Networks in new cert was different from old",
|
||||||
m{"new_networks": newState.v1Cert.Networks(), "old_networks": currentState.v1Cert.Networks(), "cert_version": cert.Version1},
|
m{"new_networks": newState.v1Cert.Networks(), "old_networks": currentState.v1Cert.Networks(), "cert_version": cert.Version1},
|
||||||
nil,
|
errCertNeedsRestart,
|
||||||
)
|
)
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -140,7 +179,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
|||||||
return util.NewContextualError(
|
return util.NewContextualError(
|
||||||
"Curve in new v1 cert was different from old",
|
"Curve in new v1 cert was different from old",
|
||||||
m{"new_curve": newState.v1Cert.Curve(), "old_curve": currentState.v1Cert.Curve(), "cert_version": cert.Version1},
|
m{"new_curve": newState.v1Cert.Curve(), "old_curve": currentState.v1Cert.Curve(), "cert_version": cert.Version1},
|
||||||
nil,
|
errCertNeedsRestart,
|
||||||
)
|
)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -155,7 +194,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
|||||||
return util.NewContextualError(
|
return util.NewContextualError(
|
||||||
"Networks in new cert was different from old",
|
"Networks in new cert was different from old",
|
||||||
m{"new_networks": newState.v2Cert.Networks(), "old_networks": currentState.v2Cert.Networks(), "cert_version": cert.Version2},
|
m{"new_networks": newState.v2Cert.Networks(), "old_networks": currentState.v2Cert.Networks(), "cert_version": cert.Version2},
|
||||||
nil,
|
errCertNeedsRestart,
|
||||||
)
|
)
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -163,7 +202,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
|||||||
return util.NewContextualError(
|
return util.NewContextualError(
|
||||||
"Curve in new cert was different from old",
|
"Curve in new cert was different from old",
|
||||||
m{"new_curve": newState.v2Cert.Curve(), "old_curve": currentState.v2Cert.Curve(), "cert_version": cert.Version2},
|
m{"new_curve": newState.v2Cert.Curve(), "old_curve": currentState.v2Cert.Curve(), "cert_version": cert.Version2},
|
||||||
nil,
|
errCertNeedsRestart,
|
||||||
)
|
)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -178,7 +217,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
|||||||
return util.NewContextualError(
|
return util.NewContextualError(
|
||||||
"Removing a V2 cert is not permitted unless it has identical networks to the new V1 cert",
|
"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()},
|
m{"new_v1_networks": newState.v1Cert.Networks(), "old_v2_networks": currentState.v2Cert.Networks()},
|
||||||
nil,
|
errCertNeedsRestart,
|
||||||
)
|
)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -196,12 +235,14 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
|||||||
|
|
||||||
func (p *PKI) reloadCAPool(c *config.C) *util.ContextualError {
|
func (p *PKI) reloadCAPool(c *config.C) *util.ContextualError {
|
||||||
caPool, err := loadCAPoolFromConfig(p.l, c)
|
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 {
|
if err != nil {
|
||||||
return util.NewContextualError("Failed to load ca from config", nil, err)
|
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
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -576,11 +617,22 @@ func loadCAPoolFromConfig(l *slog.Logger, c *config.C) (*cert.CAPool, error) {
|
|||||||
|
|
||||||
bl := c.GetStringSlice("pki.blocklist", []string{})
|
bl := c.GetStringSlice("pki.blocklist", []string{})
|
||||||
if len(bl) > 0 {
|
if len(bl) > 0 {
|
||||||
for _, fp := range bl {
|
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
|
||||||
|
}
|
||||||
caPool.BlocklistFingerprint(fp)
|
caPool.BlocklistFingerprint(fp)
|
||||||
}
|
}
|
||||||
|
|
||||||
l.Info("Blocklisted certificates", "fingerprintCount", len(bl))
|
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, ", "))
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
return caPool, nil
|
return caPool, nil
|
||||||
|
|||||||
+168
@@ -1,10 +1,17 @@
|
|||||||
package nebula
|
package nebula
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
"crypto/fips140"
|
||||||
|
"fmt"
|
||||||
|
"net/netip"
|
||||||
"strings"
|
"strings"
|
||||||
"testing"
|
"testing"
|
||||||
|
"time"
|
||||||
|
|
||||||
"github.com/slackhq/nebula/cert"
|
"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/assert"
|
||||||
"github.com/stretchr/testify/require"
|
"github.com/stretchr/testify/require"
|
||||||
)
|
)
|
||||||
@@ -92,3 +99,164 @@ func TestNewCipherSuiteUnsupportedCurve(t *testing.T) {
|
|||||||
assert.True(t, strings.HasPrefix(err.Error(), "unsupported curve:"), "got: %v", err)
|
assert.True(t, strings.HasPrefix(err.Error(), "unsupported curve:"), "got: %v", err)
|
||||||
assert.Nil(t, cs)
|
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))
|
||||||
|
}
|
||||||
@@ -67,7 +67,8 @@ func NewPunchyFromConfig(l *slog.Logger, c *config.C, punchConn udp.Conn) *Punch
|
|||||||
}
|
}
|
||||||
|
|
||||||
p.reload(c, true)
|
p.reload(c, true)
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
|
r.RestartRequiredIfChanged("stats.lighthouse_metrics")
|
||||||
p.reload(c, false)
|
p.reload(c, false)
|
||||||
})
|
})
|
||||||
|
|
||||||
|
|||||||
+16
-6
@@ -76,7 +76,7 @@ punchy:
|
|||||||
punch: true
|
punch: true
|
||||||
delay: 10m
|
delay: 10m
|
||||||
respond: true
|
respond: true
|
||||||
`))
|
`).Err)
|
||||||
p.reload(c, false)
|
p.reload(c, false)
|
||||||
assert.True(t, p.punch.Load())
|
assert.True(t, p.punch.Load())
|
||||||
assert.Equal(t, newDelay, time.Duration(p.delay.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)
|
NewPunchyFromConfig(l, c, nil)
|
||||||
hook.entries = nil
|
hook.entries = nil
|
||||||
|
|
||||||
require.NoError(t, c.ReloadConfigString(`punchy: {punch: true}`))
|
require.NoError(t, c.ReloadConfigString(`punchy: {punch: true}`).Err)
|
||||||
|
|
||||||
entry := findEntry(t, hook.entries, "punchy.punch changed")
|
entry := findEntry(t, hook.entries, "punchy.punch changed")
|
||||||
assert.Equal(t, slog.LevelInfo, entry.Level)
|
assert.Equal(t, slog.LevelInfo, entry.Level)
|
||||||
@@ -184,7 +184,7 @@ func TestPunchy_LogFormat_ReloadRespond(t *testing.T) {
|
|||||||
NewPunchyFromConfig(l, c, nil)
|
NewPunchyFromConfig(l, c, nil)
|
||||||
hook.entries = nil
|
hook.entries = nil
|
||||||
|
|
||||||
require.NoError(t, c.ReloadConfigString(`punchy: {respond: true}`))
|
require.NoError(t, c.ReloadConfigString(`punchy: {respond: true}`).Err)
|
||||||
|
|
||||||
entry := findEntry(t, hook.entries, "punchy.respond changed")
|
entry := findEntry(t, hook.entries, "punchy.respond changed")
|
||||||
assert.Equal(t, slog.LevelInfo, entry.Level)
|
assert.Equal(t, slog.LevelInfo, entry.Level)
|
||||||
@@ -198,7 +198,7 @@ func TestPunchy_LogFormat_ReloadDelay(t *testing.T) {
|
|||||||
NewPunchyFromConfig(l, c, nil)
|
NewPunchyFromConfig(l, c, nil)
|
||||||
hook.entries = nil
|
hook.entries = nil
|
||||||
|
|
||||||
require.NoError(t, c.ReloadConfigString(`punchy: {delay: 10s}`))
|
require.NoError(t, c.ReloadConfigString(`punchy: {delay: 10s}`).Err)
|
||||||
|
|
||||||
entry := findEntry(t, hook.entries, "punchy.delay changed")
|
entry := findEntry(t, hook.entries, "punchy.delay changed")
|
||||||
assert.Equal(t, slog.LevelInfo, entry.Level)
|
assert.Equal(t, slog.LevelInfo, entry.Level)
|
||||||
@@ -212,7 +212,7 @@ func TestPunchy_LogFormat_ReloadTargetAllRemotes(t *testing.T) {
|
|||||||
NewPunchyFromConfig(l, c, nil)
|
NewPunchyFromConfig(l, c, nil)
|
||||||
hook.entries = nil
|
hook.entries = nil
|
||||||
|
|
||||||
require.NoError(t, c.ReloadConfigString(`punchy: {target_all_remotes: true}`))
|
require.NoError(t, c.ReloadConfigString(`punchy: {target_all_remotes: true}`).Err)
|
||||||
|
|
||||||
entry := findEntry(t, hook.entries, "punchy.target_all_remotes changed")
|
entry := findEntry(t, hook.entries, "punchy.target_all_remotes changed")
|
||||||
assert.Equal(t, slog.LevelInfo, entry.Level)
|
assert.Equal(t, slog.LevelInfo, entry.Level)
|
||||||
@@ -226,9 +226,19 @@ func TestPunchy_LogFormat_ReloadRespondDelay(t *testing.T) {
|
|||||||
NewPunchyFromConfig(l, c, nil)
|
NewPunchyFromConfig(l, c, nil)
|
||||||
hook.entries = nil
|
hook.entries = nil
|
||||||
|
|
||||||
require.NoError(t, c.ReloadConfigString(`punchy: {respond_delay: 15s}`))
|
require.NoError(t, c.ReloadConfigString(`punchy: {respond_delay: 15s}`).Err)
|
||||||
|
|
||||||
entry := findEntry(t, hook.entries, "punchy.respond_delay changed")
|
entry := findEntry(t, hook.entries, "punchy.respond_delay changed")
|
||||||
assert.Equal(t, slog.LevelInfo, entry.Level)
|
assert.Equal(t, slog.LevelInfo, entry.Level)
|
||||||
assert.Equal(t, map[string]any{"respond_delay": 15 * time.Second}, entry.Attrs)
|
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)
|
||||||
|
}
|
||||||
+5
-10
@@ -28,10 +28,11 @@ func NewRelayManager(ctx context.Context, l *slog.Logger, hostmap *HostMap, c *c
|
|||||||
hostmap: hostmap,
|
hostmap: hostmap,
|
||||||
}
|
}
|
||||||
rm.reload(c, true)
|
rm.reload(c, true)
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
err := rm.reload(c, false)
|
err := rm.reload(c, false)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
rm.l.Error("Failed to reload relay_manager", "error", err)
|
rm.l.Error("Failed to reload relay_manager", "error", err)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
return rm
|
return rm
|
||||||
@@ -57,9 +58,8 @@ func (rm *relayManager) GetUseRelays() bool {
|
|||||||
// StartRelays drives the relay-establishment side of an outbound handshake attempt.
|
// StartRelays drives the relay-establishment side of an outbound handshake attempt.
|
||||||
// For each candidate relay it either kicks off a handshake to the relay, sends a CreateRelayRequest, retransmits
|
// For each candidate relay it either kicks off a handshake to the relay, sends a CreateRelayRequest, retransmits
|
||||||
// one that may have been lost, or, once the relay is Established, forwards the in-progress
|
// one that may have been lost, or, once the relay is Established, forwards the in-progress
|
||||||
// stage 0 handshake packets for vpnIp through it: now immediately and later after the
|
// stage 0 handshake packet for vpnIp through it.
|
||||||
// handshake repair delay.
|
func (rm *relayManager) StartRelays(f *Interface, vpnIp netip.Addr, hh *HandshakeHostInfo, stage0 []byte) {
|
||||||
func (rm *relayManager) StartRelays(f *Interface, vpnIp netip.Addr, hh *HandshakeHostInfo, now, later [][]byte) {
|
|
||||||
hostinfo := hh.hostinfo
|
hostinfo := hh.hostinfo
|
||||||
if !rm.GetUseRelays() || len(hostinfo.remotes.relays) == 0 {
|
if !rm.GetUseRelays() || len(hostinfo.remotes.relays) == 0 {
|
||||||
hh.lastRelays = nil
|
hh.lastRelays = nil
|
||||||
@@ -162,10 +162,7 @@ func (rm *relayManager) StartRelays(f *Interface, vpnIp netip.Addr, hh *Handshak
|
|||||||
switch existingRelay.State {
|
switch existingRelay.State {
|
||||||
case Established:
|
case Established:
|
||||||
hl.Log(context.Background(), level, "Send handshake via relay", "relay", relay.String())
|
hl.Log(context.Background(), level, "Send handshake via relay", "relay", relay.String())
|
||||||
_ = f.handshakeManager.sendFragmented(now, later, func(p []byte) error {
|
f.SendVia(relayHostInfo, existingRelay, stage0, make([]byte, 12), make([]byte, mtu), false, 0)
|
||||||
f.SendVia(relayHostInfo, existingRelay, p, make([]byte, 12), make([]byte, mtu), false, 0)
|
|
||||||
return nil
|
|
||||||
})
|
|
||||||
case Disestablished:
|
case Disestablished:
|
||||||
// Mark this relay as 'requested'
|
// Mark this relay as 'requested'
|
||||||
relayHostInfo.relayState.UpdateRelayForByIpState(vpnIp, Requested)
|
relayHostInfo.relayState.UpdateRelayForByIpState(vpnIp, Requested)
|
||||||
@@ -364,8 +361,6 @@ func (rm *relayManager) handleCreateRelayResponse(v cert.Version, h *HostInfo, f
|
|||||||
}
|
}
|
||||||
// Do I need to complete the relays now?
|
// Do I need to complete the relays now?
|
||||||
if relay.Type == TerminalType {
|
if relay.Type == TerminalType {
|
||||||
// The relay I asked for is up; a handshake waiting on it can go now.
|
|
||||||
f.handshakeManager.relayEstablished(relay.PeerAddr, h, relay)
|
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
// I'm the middle man. Let the initiator know that the I've established the relay they requested.
|
// I'm the middle man. Let the initiator know that the I've established the relay they requested.
|
||||||
|
|||||||
@@ -50,7 +50,7 @@ func TestStartRelaysLogDedupe(t *testing.T) {
|
|||||||
var buf bytes.Buffer
|
var buf bytes.Buffer
|
||||||
rm := newRM(&buf)
|
rm := newRM(&buf)
|
||||||
hh := newHH()
|
hh := newHH()
|
||||||
rm.StartRelays(f, vpnIp, hh, nil, nil)
|
rm.StartRelays(f, vpnIp, hh, nil)
|
||||||
assert.Equal(t, []netip.Addr{vpnIp}, hh.lastRelays, "lastRelays should record the relay set we just attempted")
|
assert.Equal(t, []netip.Addr{vpnIp}, hh.lastRelays, "lastRelays should record the relay set we just attempted")
|
||||||
assert.Contains(t, buf.String(), "level=INFO "+msg, "expected Info level on first attempt")
|
assert.Contains(t, buf.String(), "level=INFO "+msg, "expected Info level on first attempt")
|
||||||
})
|
})
|
||||||
@@ -59,10 +59,10 @@ func TestStartRelaysLogDedupe(t *testing.T) {
|
|||||||
var buf bytes.Buffer
|
var buf bytes.Buffer
|
||||||
rm := newRM(&buf)
|
rm := newRM(&buf)
|
||||||
hh := newHH()
|
hh := newHH()
|
||||||
rm.StartRelays(f, vpnIp, hh, nil, nil)
|
rm.StartRelays(f, vpnIp, hh, nil)
|
||||||
first := append([]netip.Addr(nil), hh.lastRelays...)
|
first := append([]netip.Addr(nil), hh.lastRelays...)
|
||||||
buf.Reset()
|
buf.Reset()
|
||||||
rm.StartRelays(f, vpnIp, hh, nil, nil)
|
rm.StartRelays(f, vpnIp, hh, nil)
|
||||||
assert.Equal(t, first, hh.lastRelays)
|
assert.Equal(t, first, hh.lastRelays)
|
||||||
assert.Contains(t, buf.String(), "level=DEBUG "+msg, "expected Debug level on identical retry")
|
assert.Contains(t, buf.String(), "level=DEBUG "+msg, "expected Debug level on identical retry")
|
||||||
assert.NotContains(t, buf.String(), "level=INFO "+msg, "Info should not fire on identical retry")
|
assert.NotContains(t, buf.String(), "level=INFO "+msg, "Info should not fire on identical retry")
|
||||||
@@ -72,13 +72,13 @@ func TestStartRelaysLogDedupe(t *testing.T) {
|
|||||||
var buf bytes.Buffer
|
var buf bytes.Buffer
|
||||||
rm := newRM(&buf)
|
rm := newRM(&buf)
|
||||||
hh := newHH()
|
hh := newHH()
|
||||||
rm.StartRelays(f, vpnIp, hh, nil, nil)
|
rm.StartRelays(f, vpnIp, hh, nil)
|
||||||
buf.Reset()
|
buf.Reset()
|
||||||
|
|
||||||
// The lighthouse handed us a new set this round.
|
// The lighthouse handed us a new set this round.
|
||||||
hh.hostinfo.remotes.relays = []netip.Addr{vpnIp, otherRelay}
|
hh.hostinfo.remotes.relays = []netip.Addr{vpnIp, otherRelay}
|
||||||
|
|
||||||
rm.StartRelays(f, vpnIp, hh, nil, nil)
|
rm.StartRelays(f, vpnIp, hh, nil)
|
||||||
assert.Equal(t, []netip.Addr{vpnIp, otherRelay}, hh.lastRelays)
|
assert.Equal(t, []netip.Addr{vpnIp, otherRelay}, hh.lastRelays)
|
||||||
assert.Contains(t, buf.String(), "level=INFO "+msg, "expected Info when the relay list changes")
|
assert.Contains(t, buf.String(), "level=INFO "+msg, "expected Info when the relay list changes")
|
||||||
})
|
})
|
||||||
@@ -90,7 +90,7 @@ func TestStartRelaysLogDedupe(t *testing.T) {
|
|||||||
hh := newHH()
|
hh := newHH()
|
||||||
hh.lastRelays = []netip.Addr{vpnIp}
|
hh.lastRelays = []netip.Addr{vpnIp}
|
||||||
|
|
||||||
rm.StartRelays(f, vpnIp, hh, nil, nil)
|
rm.StartRelays(f, vpnIp, hh, nil)
|
||||||
assert.Nil(t, hh.lastRelays, "with relays disabled lastRelays should be cleared")
|
assert.Nil(t, hh.lastRelays, "with relays disabled lastRelays should be cleared")
|
||||||
assert.NotContains(t, buf.String(), msg, "should not log when we shortcut out")
|
assert.NotContains(t, buf.String(), msg, "should not log when we shortcut out")
|
||||||
})
|
})
|
||||||
|
|||||||
+26
-9
@@ -1,8 +1,8 @@
|
|||||||
package service
|
package service
|
||||||
|
|
||||||
import (
|
import (
|
||||||
"io"
|
|
||||||
"net"
|
"net"
|
||||||
|
"sync"
|
||||||
)
|
)
|
||||||
|
|
||||||
type tcpListener struct {
|
type tcpListener struct {
|
||||||
@@ -10,23 +10,40 @@ type tcpListener struct {
|
|||||||
s *Service
|
s *Service
|
||||||
addr *net.TCPAddr
|
addr *net.TCPAddr
|
||||||
accept chan net.Conn
|
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) {
|
func (l *tcpListener) Accept() (net.Conn, error) {
|
||||||
conn, ok := <-l.accept
|
// select picks randomly among ready cases, so without this a handler still
|
||||||
if !ok {
|
// waiting to hand off could win over closed after Close has returned.
|
||||||
return nil, io.EOF
|
select {
|
||||||
|
case <-l.closed:
|
||||||
|
return nil, net.ErrClosed
|
||||||
|
default:
|
||||||
}
|
}
|
||||||
|
|
||||||
|
select {
|
||||||
|
case conn := <-l.accept:
|
||||||
return conn, nil
|
return conn, nil
|
||||||
|
case <-l.closed:
|
||||||
|
return nil, net.ErrClosed
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
func (l *tcpListener) Close() error {
|
func (l *tcpListener) Close() error {
|
||||||
|
l.closeOnce.Do(func() {
|
||||||
|
// Close before leaving the map so a concurrent closeListeners that
|
||||||
|
// no longer sees this listener knows Accept is already released.
|
||||||
|
close(l.closed)
|
||||||
|
|
||||||
l.s.mu.Lock()
|
l.s.mu.Lock()
|
||||||
defer l.s.mu.Unlock()
|
delete(l.s.mu.listeners, l.port)
|
||||||
delete(l.s.mu.listeners, uint16(l.addr.Port))
|
l.s.mu.Unlock()
|
||||||
|
})
|
||||||
close(l.accept)
|
|
||||||
|
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
+79
-10
@@ -32,13 +32,18 @@ import (
|
|||||||
const nicID = 1
|
const nicID = 1
|
||||||
|
|
||||||
type Service struct {
|
type Service struct {
|
||||||
eg *errgroup.Group
|
|
||||||
control *nebula.Control
|
control *nebula.Control
|
||||||
ipstack *stack.Stack
|
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 {
|
mu struct {
|
||||||
sync.Mutex
|
sync.Mutex
|
||||||
|
|
||||||
|
closed bool
|
||||||
listeners map[uint16]*tcpListener
|
listeners map[uint16]*tcpListener
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -65,7 +70,6 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
|||||||
ctx := control.Context()
|
ctx := control.Context()
|
||||||
eg, ctx := errgroup.WithContext(ctx)
|
eg, ctx := errgroup.WithContext(ctx)
|
||||||
s := Service{
|
s := Service{
|
||||||
eg: eg,
|
|
||||||
control: control,
|
control: control,
|
||||||
}
|
}
|
||||||
s.mu.listeners = map[uint16]*tcpListener{}
|
s.mu.listeners = map[uint16]*tcpListener{}
|
||||||
@@ -74,6 +78,12 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
|||||||
NetworkProtocols: []stack.NetworkProtocolFactory{ipv4.NewProtocol, ipv6.NewProtocol},
|
NetworkProtocols: []stack.NetworkProtocolFactory{ipv4.NewProtocol, ipv6.NewProtocol},
|
||||||
TransportProtocols: []stack.TransportProtocolFactory{tcp.NewProtocol, udp.NewProtocol, icmp.NewProtocol4, icmp.NewProtocol6},
|
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
|
sackEnabledOpt := tcpip.TCPSACKEnabled(true) // TCP SACK is disabled by default
|
||||||
tcpipErr := s.ipstack.SetTransportProtocolOption(tcp.ProtocolNumber, &sackEnabledOpt)
|
tcpipErr := s.ipstack.SetTransportProtocolOption(tcp.ProtocolNumber, &sackEnabledOpt)
|
||||||
if tcpipErr != nil {
|
if tcpipErr != nil {
|
||||||
@@ -123,6 +133,12 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
|||||||
// this will read exactly one packet
|
// this will read exactly one packet
|
||||||
n, err := reader.Read(buf)
|
n, err := reader.Read(buf)
|
||||||
if err != nil {
|
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
|
return err
|
||||||
}
|
}
|
||||||
packetBuf := stack.NewPacketBuffer(stack.PacketBufferOptions{
|
packetBuf := stack.NewPacketBuffer(stack.PacketBufferOptions{
|
||||||
@@ -130,8 +146,8 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
|||||||
})
|
})
|
||||||
linkEP.InjectInbound(header.IPv4ProtocolNumber, packetBuf)
|
linkEP.InjectInbound(header.IPv4ProtocolNumber, packetBuf)
|
||||||
|
|
||||||
if err := ctx.Err(); err != nil {
|
if ctx.Err() != nil {
|
||||||
return err
|
return nil
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
@@ -139,13 +155,18 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
|||||||
for {
|
for {
|
||||||
packet := linkEP.ReadContext(ctx)
|
packet := linkEP.ReadContext(ctx)
|
||||||
if packet == nil {
|
if packet == nil {
|
||||||
if err := ctx.Err(); err != nil {
|
if ctx.Err() != nil {
|
||||||
return err
|
return nil
|
||||||
}
|
}
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
bufView := packet.ToView()
|
bufView := packet.ToView()
|
||||||
if _, err := bufView.WriteTo(writer); err != nil {
|
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
|
return err
|
||||||
}
|
}
|
||||||
bufView.Release()
|
bufView.Release()
|
||||||
@@ -158,6 +179,22 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
|||||||
return control.Wait()
|
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
|
return &s, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -231,11 +268,15 @@ func (s *Service) Listen(network, address string) (net.Listener, error) {
|
|||||||
s: s,
|
s: s,
|
||||||
addr: addr,
|
addr: addr,
|
||||||
accept: make(chan net.Conn),
|
accept: make(chan net.Conn),
|
||||||
|
closed: make(chan struct{}),
|
||||||
}
|
}
|
||||||
|
|
||||||
s.mu.Lock()
|
s.mu.Lock()
|
||||||
defer s.mu.Unlock()
|
defer s.mu.Unlock()
|
||||||
|
|
||||||
|
if s.mu.closed {
|
||||||
|
return nil, net.ErrClosed
|
||||||
|
}
|
||||||
if _, ok := s.mu.listeners[port]; ok {
|
if _, ok := s.mu.listeners[port]; ok {
|
||||||
return nil, fmt.Errorf("already listening on port %d", port)
|
return nil, fmt.Errorf("already listening on port %d", port)
|
||||||
}
|
}
|
||||||
@@ -244,22 +285,44 @@ func (s *Service) Listen(network, address string) (net.Listener, error) {
|
|||||||
return l, nil
|
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 {
|
func (s *Service) Wait() error {
|
||||||
return s.eg.Wait()
|
<-s.done
|
||||||
|
return s.err
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Close closes all listeners and stops nebula. Use Wait to block until
|
||||||
|
// shutdown has completed.
|
||||||
func (s *Service) Close() error {
|
func (s *Service) Close() error {
|
||||||
|
s.closeListeners()
|
||||||
s.control.Stop()
|
s.control.Stop()
|
||||||
return nil
|
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) {
|
func (s *Service) tcpHandler(r *tcp.ForwarderRequest) {
|
||||||
endpointID := r.ID()
|
endpointID := r.ID()
|
||||||
|
|
||||||
s.mu.Lock()
|
s.mu.Lock()
|
||||||
defer s.mu.Unlock()
|
|
||||||
|
|
||||||
l, ok := s.mu.listeners[endpointID.LocalPort]
|
l, ok := s.mu.listeners[endpointID.LocalPort]
|
||||||
|
s.mu.Unlock()
|
||||||
if !ok {
|
if !ok {
|
||||||
r.Complete(true)
|
r.Complete(true)
|
||||||
return
|
return
|
||||||
@@ -275,6 +338,12 @@ func (s *Service) tcpHandler(r *tcp.ForwarderRequest) {
|
|||||||
r.Complete(false)
|
r.Complete(false)
|
||||||
ep.SocketOptions().SetKeepAlive(true)
|
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)
|
conn := gonet.NewTCPConn(&wq, ep)
|
||||||
l.accept <- conn
|
select {
|
||||||
|
case l.accept <- conn:
|
||||||
|
case <-l.closed:
|
||||||
|
_ = conn.Close()
|
||||||
|
}
|
||||||
}
|
}
|
||||||
@@ -188,3 +188,301 @@ func TestService(t *testing.T) {
|
|||||||
t.Fatal(err)
|
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")
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -11,11 +11,8 @@ import (
|
|||||||
"net"
|
"net"
|
||||||
"net/netip"
|
"net/netip"
|
||||||
"os"
|
"os"
|
||||||
"path/filepath"
|
"slices"
|
||||||
"runtime"
|
|
||||||
"runtime/pprof"
|
|
||||||
"sort"
|
"sort"
|
||||||
"strconv"
|
|
||||||
"strings"
|
"strings"
|
||||||
|
|
||||||
"github.com/slackhq/nebula/config"
|
"github.com/slackhq/nebula/config"
|
||||||
@@ -58,12 +55,28 @@ type sshDeviceInfoFlags struct {
|
|||||||
}
|
}
|
||||||
|
|
||||||
func wireSSHReload(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) {
|
func wireSSHReload(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) {
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
if c.GetBool("sshd.enabled", false) {
|
if c.GetBool("sshd.enabled", false) {
|
||||||
sshRun, err := configSSH(l, ssh, c)
|
// 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) {
|
||||||
|
key, err := loadSSHHostKey(c)
|
||||||
|
if err == nil {
|
||||||
|
err = ssh.SetHostKey(key)
|
||||||
|
}
|
||||||
if err != nil {
|
if err != nil {
|
||||||
l.Error("Failed to reconfigure the sshd", "error", err)
|
l.Error("Failed to reconfigure the sshd", "error", err)
|
||||||
ssh.Stop()
|
ssh.Stop()
|
||||||
|
r.Failed()
|
||||||
|
}
|
||||||
|
return
|
||||||
|
}
|
||||||
|
sshRun, err := configSSH(l, ssh, c, r)
|
||||||
|
if err != nil {
|
||||||
|
l.Error("Failed to reconfigure the sshd", "error", err)
|
||||||
|
ssh.Stop()
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
if sshRun != nil {
|
if sshRun != nil {
|
||||||
go sshRun()
|
go sshRun()
|
||||||
@@ -74,11 +87,31 @@ 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", "")
|
||||||
|
if hostKeyPathOrKey == "" {
|
||||||
|
return nil, fmt.Errorf("sshd.host_key must be provided")
|
||||||
|
}
|
||||||
|
if strings.Contains(hostKeyPathOrKey, "-----BEGIN") {
|
||||||
|
return []byte(hostKeyPathOrKey), nil
|
||||||
|
}
|
||||||
|
b, err := os.ReadFile(hostKeyPathOrKey)
|
||||||
|
if err != nil {
|
||||||
|
return nil, fmt.Errorf("error while loading sshd.host_key file: %s", err)
|
||||||
|
}
|
||||||
|
return b, nil
|
||||||
|
}
|
||||||
|
|
||||||
// configSSH reads the ssh info out of the passed-in Config and
|
// configSSH reads the ssh info out of the passed-in Config and
|
||||||
// updates the passed-in SSHServer. On success, it returns a function
|
// updates the passed-in SSHServer. On success, it returns a function
|
||||||
// that callers may invoke to run the configured ssh server. On
|
// that callers may invoke to run the configured ssh server. On
|
||||||
// failure, it returns nil, error.
|
// failure, it returns nil, error.
|
||||||
func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) (func(), 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) {
|
||||||
listen := c.GetString("sshd.listen", "")
|
listen := c.GetString("sshd.listen", "")
|
||||||
if listen == "" {
|
if listen == "" {
|
||||||
return nil, fmt.Errorf("sshd.listen must be provided")
|
return nil, fmt.Errorf("sshd.listen must be provided")
|
||||||
@@ -92,19 +125,9 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) (func(), error)
|
|||||||
return nil, fmt.Errorf("sshd.listen can not use port 22")
|
return nil, fmt.Errorf("sshd.listen can not use port 22")
|
||||||
}
|
}
|
||||||
|
|
||||||
hostKeyPathOrKey := c.GetString("sshd.host_key", "")
|
hostKeyBytes, err := loadSSHHostKey(c)
|
||||||
if hostKeyPathOrKey == "" {
|
|
||||||
return nil, fmt.Errorf("sshd.host_key must be provided")
|
|
||||||
}
|
|
||||||
|
|
||||||
var hostKeyBytes []byte
|
|
||||||
if strings.Contains(hostKeyPathOrKey, "-----BEGIN") {
|
|
||||||
hostKeyBytes = []byte(hostKeyPathOrKey)
|
|
||||||
} else {
|
|
||||||
hostKeyBytes, err = os.ReadFile(hostKeyPathOrKey)
|
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, fmt.Errorf("error while loading sshd.host_key file: %s", err)
|
return nil, err
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
err = ssh.SetHostKey(hostKeyBytes)
|
err = ssh.SetHostKey(hostKeyBytes)
|
||||||
@@ -121,6 +144,7 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) (func(), error)
|
|||||||
err := ssh.AddTrustedCA(caAuthorizedKey)
|
err := ssh.AddTrustedCA(caAuthorizedKey)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
l.Warn("SSH CA had an error, ignoring", "error", err, "sshCA", caAuthorizedKey)
|
l.Warn("SSH CA had an error, ignoring", "error", err, "sshCA", caAuthorizedKey)
|
||||||
|
r.Failed()
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -132,12 +156,14 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) (func(), error)
|
|||||||
kDef, ok := rk.(map[string]any)
|
kDef, ok := rk.(map[string]any)
|
||||||
if !ok {
|
if !ok {
|
||||||
l.Warn("Authorized user had an error, ignoring", "sshKeyConfig", rk)
|
l.Warn("Authorized user had an error, ignoring", "sshKeyConfig", rk)
|
||||||
|
r.Failed()
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|
||||||
user, ok := kDef["user"].(string)
|
user, ok := kDef["user"].(string)
|
||||||
if !ok {
|
if !ok {
|
||||||
l.Warn("Authorized user is missing the user field", "sshKeyConfig", rk)
|
l.Warn("Authorized user is missing the user field", "sshKeyConfig", rk)
|
||||||
|
r.Failed()
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -151,6 +177,7 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) (func(), error)
|
|||||||
"sshKeyConfig", rk,
|
"sshKeyConfig", rk,
|
||||||
"sshKey", v,
|
"sshKey", v,
|
||||||
)
|
)
|
||||||
|
r.Failed()
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -162,6 +189,7 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) (func(), error)
|
|||||||
"sshKeyConfig", rk,
|
"sshKeyConfig", rk,
|
||||||
"sshKey", subK,
|
"sshKey", subK,
|
||||||
)
|
)
|
||||||
|
r.Failed()
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -171,12 +199,14 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) (func(), error)
|
|||||||
"error", err,
|
"error", err,
|
||||||
"sshKeyConfig", sk,
|
"sshKeyConfig", sk,
|
||||||
)
|
)
|
||||||
|
r.Failed()
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
default:
|
default:
|
||||||
l.Warn("Authorized user is missing the keys field or was not understood", "sshKeyConfig", rk)
|
l.Warn("Authorized user is missing the keys field or was not understood", "sshKeyConfig", rk)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
} else {
|
} else {
|
||||||
@@ -199,12 +229,6 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) (func(), error)
|
|||||||
}
|
}
|
||||||
|
|
||||||
func attachCommands(l *slog.Logger, c *config.C, ssh *sshd.SSHServer, f *Interface) {
|
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{
|
ssh.RegisterCommand(&sshd.Command{
|
||||||
Name: "list-hostmap",
|
Name: "list-hostmap",
|
||||||
ShortDescription: "List all known previously connected hosts",
|
ShortDescription: "List all known previously connected hosts",
|
||||||
@@ -256,46 +280,7 @@ func attachCommands(l *slog.Logger, c *config.C, ssh *sshd.SSHServer, f *Interfa
|
|||||||
Name: "reload",
|
Name: "reload",
|
||||||
ShortDescription: "Reloads configuration from disk, same as sending HUP to the process",
|
ShortDescription: "Reloads configuration from disk, same as sending HUP to the process",
|
||||||
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
Callback: func(fs any, a []string, w sshd.StringWriter) error {
|
||||||
return sshReload(c, w)
|
return sshReload(l, 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)
|
|
||||||
},
|
},
|
||||||
})
|
})
|
||||||
|
|
||||||
@@ -529,58 +514,6 @@ func sshListLighthouseMap(lightHouse *LightHouse, a any, w sshd.StringWriter) er
|
|||||||
return nil
|
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 {
|
func sshVersion(ifce *Interface, fs any, a []string, w sshd.StringWriter) error {
|
||||||
return w.WriteLine(fmt.Sprintf("%s", ifce.version))
|
return w.WriteLine(fmt.Sprintf("%s", ifce.version))
|
||||||
}
|
}
|
||||||
@@ -733,76 +666,6 @@ func sshChangeRemote(ifce *Interface, fs any, a []string, w sshd.StringWriter) e
|
|||||||
return w.WriteLine("Changed")
|
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 {
|
func sshLogLevel(l *slog.Logger, fs any, a []string, w sshd.StringWriter) error {
|
||||||
ctrl, ok := l.Handler().(interface {
|
ctrl, ok := l.Handler().(interface {
|
||||||
GetLevel() slog.Level
|
GetLevel() slog.Level
|
||||||
@@ -1055,8 +918,13 @@ func sshDeviceInfo(ifce *Interface, fs any, w sshd.StringWriter) error {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
func sshReload(c *config.C, w sshd.StringWriter) error {
|
// sshReload reloads the config and writes the result to the client. It reloads even if the client has gone away
|
||||||
err := w.WriteLine("Reloading config")
|
func sshReload(l *slog.Logger, c *config.C, w sshd.StringWriter) error {
|
||||||
c.ReloadConfig()
|
writeErr := w.WriteLine("Reloading config")
|
||||||
return err
|
res := c.ReloadConfig()
|
||||||
|
res.Log(l)
|
||||||
|
if err := w.WriteLine(res.String()); writeErr == nil {
|
||||||
|
writeErr = err
|
||||||
|
}
|
||||||
|
return writeErr
|
||||||
}
|
}
|
||||||
@@ -0,0 +1,83 @@
|
|||||||
|
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)
|
||||||
|
}
|
||||||
+47
-12
@@ -8,13 +8,17 @@ import (
|
|||||||
"log/slog"
|
"log/slog"
|
||||||
"net"
|
"net"
|
||||||
"sync"
|
"sync"
|
||||||
|
"sync/atomic"
|
||||||
|
|
||||||
"github.com/armon/go-radix"
|
"github.com/armon/go-radix"
|
||||||
"golang.org/x/crypto/ssh"
|
"golang.org/x/crypto/ssh"
|
||||||
)
|
)
|
||||||
|
|
||||||
type SSHServer struct {
|
type SSHServer struct {
|
||||||
config *ssh.ServerConfig
|
// config is replaced whole when the host key changes, ssh.ServerConfig.AddHostKey only replaces a key of the same
|
||||||
|
// algorithm and appends any other
|
||||||
|
config atomic.Pointer[ssh.ServerConfig]
|
||||||
|
authenticate func(ssh.ConnMetadata, ssh.PublicKey) (*ssh.Permissions, error)
|
||||||
l *slog.Logger
|
l *slog.Logger
|
||||||
|
|
||||||
certChecker *ssh.CertChecker
|
certChecker *ssh.CertChecker
|
||||||
@@ -28,7 +32,12 @@ type SSHServer struct {
|
|||||||
// List of available commands
|
// List of available commands
|
||||||
helpCommand *Command
|
helpCommand *Command
|
||||||
commands *radix.Tree
|
commands *radix.Tree
|
||||||
listener net.Listener
|
listener atomic.Pointer[net.Listener]
|
||||||
|
|
||||||
|
// runs counts the Runs that are listening. A reload's Run can start before the one it replaced has returned
|
||||||
|
runs atomic.Int32
|
||||||
|
// addr is where the newest Run listens, nil when none is
|
||||||
|
addr atomic.Pointer[net.Addr]
|
||||||
|
|
||||||
// ctx parents per-Run contexts. Cancelling it (e.g. via Control.Stop) tears the server down even
|
// ctx parents per-Run contexts. Cancelling it (e.g. via Control.Stop) tears the server down even
|
||||||
// across reloads, since each Run derives a fresh child rather than reusing this one directly.
|
// across reloads, since each Run derives a fresh child rather than reusing this one directly.
|
||||||
@@ -85,10 +94,8 @@ func NewSSHServer(ctx context.Context, l *slog.Logger) (*SSHServer, error) {
|
|||||||
},
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
s.config = &ssh.ServerConfig{
|
s.authenticate = cc.Authenticate
|
||||||
PublicKeyCallback: cc.Authenticate,
|
s.config.Store(s.newConfig())
|
||||||
ServerVersion: fmt.Sprintf("SSH-2.0-Nebula???"),
|
|
||||||
}
|
|
||||||
|
|
||||||
s.RegisterCommand(&Command{
|
s.RegisterCommand(&Command{
|
||||||
Name: "help",
|
Name: "help",
|
||||||
@@ -107,10 +114,32 @@ func (s *SSHServer) SetHostKey(hostPrivateKey []byte) error {
|
|||||||
return fmt.Errorf("failed to parse private key: %s", err)
|
return fmt.Errorf("failed to parse private key: %s", err)
|
||||||
}
|
}
|
||||||
|
|
||||||
s.config.AddHostKey(private)
|
config := s.newConfig()
|
||||||
|
config.AddHostKey(private)
|
||||||
|
s.config.Store(config)
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func (s *SSHServer) newConfig() *ssh.ServerConfig {
|
||||||
|
return &ssh.ServerConfig{
|
||||||
|
PublicKeyCallback: s.authenticate,
|
||||||
|
ServerVersion: fmt.Sprintf("SSH-2.0-Nebula???"),
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// Addr is the address the newest Run listens on, nil when none is.
|
||||||
|
func (s *SSHServer) Addr() net.Addr {
|
||||||
|
if a := s.addr.Load(); a != nil {
|
||||||
|
return *a
|
||||||
|
}
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
|
||||||
|
// Running is true while a Run is listening.
|
||||||
|
func (s *SSHServer) Running() bool {
|
||||||
|
return s.runs.Load() > 0
|
||||||
|
}
|
||||||
|
|
||||||
func (s *SSHServer) ClearTrustedCAs() {
|
func (s *SSHServer) ClearTrustedCAs() {
|
||||||
s.authLock.Lock()
|
s.authLock.Lock()
|
||||||
s.trustedCAs = []ssh.PublicKey{}
|
s.trustedCAs = []ssh.PublicKey{}
|
||||||
@@ -181,10 +210,16 @@ func (s *SSHServer) Run(addr string) error {
|
|||||||
// this run owns. They start equal but a fast reload may overwrite s.listener with the next run's
|
// this run owns. They start equal but a fast reload may overwrite s.listener with the next run's
|
||||||
// listener before this run's watcher fires, so each run must close its own listener via the local
|
// listener before this run's watcher fires, so each run must close its own listener via the local
|
||||||
// reference.
|
// reference.
|
||||||
s.listener = listener
|
s.listener.Store(&listener)
|
||||||
|
s.runs.Add(1)
|
||||||
|
bound := listener.Addr()
|
||||||
|
s.addr.Store(&bound)
|
||||||
|
|
||||||
runCtx, cancel := context.WithCancel(s.ctx)
|
runCtx, cancel := context.WithCancel(s.ctx)
|
||||||
defer cancel()
|
defer cancel()
|
||||||
|
// Deferred after cancel so they run first, a run on its way out no longer counts as listening
|
||||||
|
defer s.runs.Add(-1)
|
||||||
|
defer s.addr.CompareAndSwap(&bound, nil)
|
||||||
|
|
||||||
// Close the listener when this run's context is cancelled. That can come from the parent
|
// Close the listener when this run's context is cancelled. That can come from the parent
|
||||||
// (Control.Stop), from Run returning normally (defer cancel above), or transitively when a sibling
|
// (Control.Stop), from Run returning normally (defer cancel above), or transitively when a sibling
|
||||||
@@ -197,7 +232,7 @@ func (s *SSHServer) Run(addr string) error {
|
|||||||
}
|
}
|
||||||
}()
|
}()
|
||||||
|
|
||||||
s.l.Info("SSH server is listening", "sshListener", addr)
|
s.l.Info("SSH server is listening", "sshListener", bound)
|
||||||
|
|
||||||
// Run loops until there is an error
|
// Run loops until there is an error
|
||||||
s.run(runCtx, listener)
|
s.run(runCtx, listener)
|
||||||
@@ -226,7 +261,7 @@ func (s *SSHServer) run(ctx context.Context, listener net.Listener) {
|
|||||||
<-sessionContext.Done()
|
<-sessionContext.Done()
|
||||||
c.Close()
|
c.Close()
|
||||||
}()
|
}()
|
||||||
conn, chans, reqs, err := ssh.NewServerConn(c, s.config)
|
conn, chans, reqs, err := ssh.NewServerConn(c, s.config.Load())
|
||||||
fp := ""
|
fp := ""
|
||||||
if conn != nil {
|
if conn != nil {
|
||||||
fp = conn.Permissions.Extensions["fp"]
|
fp = conn.Permissions.Extensions["fp"]
|
||||||
@@ -264,8 +299,8 @@ func (s *SSHServer) run(ctx context.Context, listener net.Listener) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
func (s *SSHServer) Stop() {
|
func (s *SSHServer) Stop() {
|
||||||
if s.listener != nil {
|
if l := s.listener.Load(); l != nil {
|
||||||
if err := s.listener.Close(); err != nil {
|
if err := (*l).Close(); err != nil && !errors.Is(err, net.ErrClosed) {
|
||||||
s.l.Warn("Failed to close the sshd listener", "error", err)
|
s.l.Warn("Failed to close the sshd listener", "error", err)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -0,0 +1,240 @@
|
|||||||
|
package nebula
|
||||||
|
|
||||||
|
import (
|
||||||
|
"crypto"
|
||||||
|
"crypto/ed25519"
|
||||||
|
"crypto/rand"
|
||||||
|
"crypto/rsa"
|
||||||
|
"encoding/pem"
|
||||||
|
"fmt"
|
||||||
|
"net"
|
||||||
|
"os"
|
||||||
|
"path/filepath"
|
||||||
|
"testing"
|
||||||
|
"time"
|
||||||
|
|
||||||
|
"github.com/slackhq/nebula/config"
|
||||||
|
"github.com/slackhq/nebula/sshd"
|
||||||
|
"github.com/slackhq/nebula/test"
|
||||||
|
"github.com/stretchr/testify/assert"
|
||||||
|
"github.com/stretchr/testify/require"
|
||||||
|
"golang.org/x/crypto/ssh"
|
||||||
|
)
|
||||||
|
|
||||||
|
type sshdReloadHarness struct {
|
||||||
|
c *config.C
|
||||||
|
server *sshd.SSHServer
|
||||||
|
keyFile string
|
||||||
|
signer ssh.Signer
|
||||||
|
listen string
|
||||||
|
users []string
|
||||||
|
extra string
|
||||||
|
}
|
||||||
|
|
||||||
|
func newSSHDReloadHarness(t *testing.T) *sshdReloadHarness {
|
||||||
|
t.Helper()
|
||||||
|
l := test.NewLogger()
|
||||||
|
h := &sshdReloadHarness{keyFile: filepath.Join(t.TempDir(), "host_key"), listen: "127.0.0.1:0", users: []string{"test"}}
|
||||||
|
h.writeHostKey(t, newEd25519Key(t))
|
||||||
|
|
||||||
|
_, userKey, err := ed25519.GenerateKey(rand.Reader)
|
||||||
|
require.NoError(t, err)
|
||||||
|
h.signer, err = ssh.NewSignerFromKey(userKey)
|
||||||
|
require.NoError(t, err)
|
||||||
|
|
||||||
|
h.c = config.NewC(l)
|
||||||
|
require.NoError(t, h.c.LoadString(h.config()))
|
||||||
|
h.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)
|
||||||
|
require.NoError(t, err)
|
||||||
|
go run()
|
||||||
|
t.Cleanup(h.server.Stop)
|
||||||
|
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
|
||||||
|
return h
|
||||||
|
}
|
||||||
|
|
||||||
|
func newEd25519Key(t *testing.T) crypto.Signer {
|
||||||
|
_, key, err := ed25519.GenerateKey(rand.Reader)
|
||||||
|
require.NoError(t, err)
|
||||||
|
return key
|
||||||
|
}
|
||||||
|
|
||||||
|
// writeHostKey replaces the host key file and returns the public key a client should now see
|
||||||
|
func (h *sshdReloadHarness) writeHostKey(t *testing.T, key crypto.Signer) ssh.PublicKey {
|
||||||
|
t.Helper()
|
||||||
|
block, err := ssh.MarshalPrivateKey(key, "")
|
||||||
|
require.NoError(t, err)
|
||||||
|
require.NoError(t, os.WriteFile(h.keyFile, pem.EncodeToMemory(block), 0o600))
|
||||||
|
pub, err := ssh.NewPublicKey(key.Public())
|
||||||
|
require.NoError(t, err)
|
||||||
|
return pub
|
||||||
|
}
|
||||||
|
|
||||||
|
func (h *sshdReloadHarness) config() string {
|
||||||
|
users := ""
|
||||||
|
for _, u := range h.users {
|
||||||
|
users += fmt.Sprintf(" - user: %s\n keys: [%q]\n", u, string(ssh.MarshalAuthorizedKey(h.signer.PublicKey())))
|
||||||
|
}
|
||||||
|
return fmt.Sprintf("sshd:\n enabled: true\n listen: %s\n host_key: %s\n authorized_users:\n%s%s",
|
||||||
|
h.listen, h.keyFile, users, h.extra)
|
||||||
|
}
|
||||||
|
|
||||||
|
// dial connects to wherever the server listens now, a restart on :0 moves it. hostKeyAlgorithms limits which host keys
|
||||||
|
// the client accepts, none means any
|
||||||
|
func (h *sshdReloadHarness) dial(hostKeyAlgorithms ...string) (*ssh.Client, ssh.PublicKey, error) {
|
||||||
|
addr := h.server.Addr()
|
||||||
|
if addr == nil {
|
||||||
|
return nil, nil, fmt.Errorf("not listening")
|
||||||
|
}
|
||||||
|
var hostKey ssh.PublicKey
|
||||||
|
c, err := ssh.Dial("tcp", addr.String(), &ssh.ClientConfig{
|
||||||
|
User: "test",
|
||||||
|
Auth: []ssh.AuthMethod{ssh.PublicKeys(h.signer)},
|
||||||
|
HostKeyCallback: func(_ string, _ net.Addr, key ssh.PublicKey) error {
|
||||||
|
hostKey = key
|
||||||
|
return nil
|
||||||
|
},
|
||||||
|
HostKeyAlgorithms: hostKeyAlgorithms,
|
||||||
|
Timeout: time.Second,
|
||||||
|
})
|
||||||
|
return c, hostKey, err
|
||||||
|
}
|
||||||
|
|
||||||
|
func (h *sshdReloadHarness) connect(t *testing.T) (*ssh.Client, ssh.PublicKey) {
|
||||||
|
t.Helper()
|
||||||
|
var client *ssh.Client
|
||||||
|
var hostKey ssh.PublicKey
|
||||||
|
require.Eventually(t, func() bool {
|
||||||
|
var err error
|
||||||
|
client, hostKey, err = h.dial()
|
||||||
|
return err == nil
|
||||||
|
}, 5*time.Second, 20*time.Millisecond)
|
||||||
|
t.Cleanup(func() { _ = client.Close() })
|
||||||
|
return client, hostKey
|
||||||
|
}
|
||||||
|
|
||||||
|
// dropped is true when the server closed the client's connection within wait
|
||||||
|
func dropped(client *ssh.Client, wait time.Duration) bool {
|
||||||
|
done := make(chan struct{})
|
||||||
|
go func() {
|
||||||
|
_ = client.Wait()
|
||||||
|
close(done)
|
||||||
|
}()
|
||||||
|
select {
|
||||||
|
case <-done:
|
||||||
|
return true
|
||||||
|
case <-time.After(wait):
|
||||||
|
return false
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// Restarting sshd drops every open session, the one that asked for the reload included. A reload that touches nothing
|
||||||
|
// sshd reads leaves it alone
|
||||||
|
func TestSSHDReload_UnchangedKeepsSessions(t *testing.T) {
|
||||||
|
h := newSSHDReloadHarness(t)
|
||||||
|
client, _ := h.connect(t)
|
||||||
|
|
||||||
|
require.NoError(t, h.c.ReloadConfigString(h.config()+"punchy:\n punch: true\n").Err)
|
||||||
|
assert.False(t, dropped(client, 500*time.Millisecond), "an unchanged sshd was restarted")
|
||||||
|
}
|
||||||
|
|
||||||
|
// Every key the server reads restarts it when it changes
|
||||||
|
func TestSSHDReload_ChangedConfigRestarts(t *testing.T) {
|
||||||
|
cases := map[string]func(t *testing.T, h *sshdReloadHarness){
|
||||||
|
"listen": func(t *testing.T, h *sshdReloadHarness) { h.listen = "localhost:0" },
|
||||||
|
"authorized_users": func(t *testing.T, h *sshdReloadHarness) { h.users = append(h.users, "other") },
|
||||||
|
"trusted_cas": func(t *testing.T, h *sshdReloadHarness) { h.extra = " trusted_cas: []\n" },
|
||||||
|
"host_key": func(t *testing.T, h *sshdReloadHarness) {
|
||||||
|
h.keyFile = filepath.Join(t.TempDir(), "other_host_key")
|
||||||
|
h.writeHostKey(t, newEd25519Key(t))
|
||||||
|
},
|
||||||
|
}
|
||||||
|
for name, change := range cases {
|
||||||
|
t.Run(name, func(t *testing.T) {
|
||||||
|
h := newSSHDReloadHarness(t)
|
||||||
|
client, _ := h.connect(t)
|
||||||
|
|
||||||
|
change(t, h)
|
||||||
|
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
|
||||||
|
assert.True(t, dropped(client, 5*time.Second), "a changed sshd config was not applied")
|
||||||
|
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
|
||||||
|
h.connect(t)
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// The config can stay the same while the host key file it names changes. New connections get the new key, open
|
||||||
|
// sessions are left alone
|
||||||
|
func TestSSHDReload_ChangedHostKeyFile(t *testing.T) {
|
||||||
|
h := newSSHDReloadHarness(t)
|
||||||
|
client, _ := h.connect(t)
|
||||||
|
|
||||||
|
want := h.writeHostKey(t, newEd25519Key(t))
|
||||||
|
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
|
||||||
|
_, got := h.connect(t)
|
||||||
|
assert.Equal(t, want.Marshal(), got.Marshal(), "a new host key was not applied")
|
||||||
|
assert.False(t, dropped(client, 500*time.Millisecond), "a new host key restarted sshd")
|
||||||
|
}
|
||||||
|
|
||||||
|
// A host key of another algorithm replaces the old one rather than being offered next to it
|
||||||
|
func TestSSHDReload_HostKeyAlgorithmChange(t *testing.T) {
|
||||||
|
h := newSSHDReloadHarness(t)
|
||||||
|
h.connect(t)
|
||||||
|
|
||||||
|
rsaKey, err := rsa.GenerateKey(rand.Reader, 2048)
|
||||||
|
require.NoError(t, err)
|
||||||
|
want := h.writeHostKey(t, rsaKey)
|
||||||
|
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
|
||||||
|
|
||||||
|
_, got := h.connect(t)
|
||||||
|
assert.Equal(t, want.Marshal(), got.Marshal())
|
||||||
|
_, _, err = h.dial(ssh.KeyAlgoED25519)
|
||||||
|
assert.Error(t, err, "the old ed25519 host key is still offered")
|
||||||
|
}
|
||||||
|
|
||||||
|
// A server that isn't running, say its port was busy, is tried again on every reload as before
|
||||||
|
func TestSSHDReload_NotRunningRestarts(t *testing.T) {
|
||||||
|
h := newSSHDReloadHarness(t)
|
||||||
|
h.server.Stop()
|
||||||
|
require.Eventually(t, func() bool { return !h.server.Running() }, 5*time.Second, 10*time.Millisecond)
|
||||||
|
|
||||||
|
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
|
||||||
|
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
|
||||||
|
h.connect(t)
|
||||||
|
}
|
||||||
|
|
||||||
|
// A host key that no longer loads stops sshd, the same as a config that doesn't
|
||||||
|
func TestSSHDReload_BadHostKeyFileStops(t *testing.T) {
|
||||||
|
h := newSSHDReloadHarness(t)
|
||||||
|
h.connect(t)
|
||||||
|
|
||||||
|
require.NoError(t, os.WriteFile(h.keyFile, []byte("not a key"), 0o600))
|
||||||
|
assert.True(t, h.c.ReloadConfigString(h.config()).Failed)
|
||||||
|
require.Eventually(t, func() bool { return !h.server.Running() }, 5*time.Second, 10*time.Millisecond)
|
||||||
|
}
|
||||||
|
|
||||||
|
// A trusted CA or authorized user that is skipped with a warning fails the reload, the valid ones are still used
|
||||||
|
func TestSSHDReload_SkippedEntriesFail(t *testing.T) {
|
||||||
|
cases := map[string]string{
|
||||||
|
"bad trusted ca": " trusted_cas: [nope]\n",
|
||||||
|
"user entry not a map": " - nope\n",
|
||||||
|
"user missing": " - keys: [nope]\n",
|
||||||
|
"bad key": " - user: other\n keys: nope\n",
|
||||||
|
"key in a list not a string": " - user: other\n keys: [5]\n",
|
||||||
|
"bad key in a list": " - user: other\n keys: [nope]\n",
|
||||||
|
"keys missing": " - user: other\n",
|
||||||
|
}
|
||||||
|
for name, extra := range cases {
|
||||||
|
t.Run(name, func(t *testing.T) {
|
||||||
|
h := newSSHDReloadHarness(t)
|
||||||
|
h.extra = extra
|
||||||
|
res := h.c.ReloadConfigString(h.config())
|
||||||
|
require.NoError(t, res.Err)
|
||||||
|
assert.True(t, res.Failed)
|
||||||
|
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
|
||||||
|
h.connect(t)
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -99,9 +99,10 @@ func newStatsServerFromConfig(ctx context.Context, l *slog.Logger, c *config.C,
|
|||||||
emitStats: emitStats,
|
emitStats: emitStats,
|
||||||
}
|
}
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||||
if err := s.reload(c, false); err != nil {
|
if err := s.reload(c, false); err != nil {
|
||||||
s.l.Error("Failed to reload stats from config", "error", err)
|
s.l.Error("Failed to reload stats from config", "error", err)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
|
||||||
|
|||||||
+4
-3
@@ -41,9 +41,10 @@ type Conn interface {
|
|||||||
//
|
//
|
||||||
// Returns the number of packets successfully written. A destination the kernel rejects costs only
|
// 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.
|
// its own packet, so a short count means some peers were undeliverable, not that the batch failed.
|
||||||
// Not safe for concurrent use on the same Conn.
|
// Safe for concurrent use on the same Conn.
|
||||||
WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error)
|
WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error)
|
||||||
ReloadConfig(c *config.C)
|
// ReloadConfig applies the listen settings that can change, r is nil at startup
|
||||||
|
ReloadConfig(c *config.C, r *config.Reload)
|
||||||
SupportsMultipleReaders() bool
|
SupportsMultipleReaders() bool
|
||||||
Close() error
|
Close() error
|
||||||
}
|
}
|
||||||
@@ -68,7 +69,7 @@ func (NoopConn) WriteTo(_ []byte, _ netip.AddrPort) error {
|
|||||||
func (NoopConn) WriteBatch(bufs [][]byte, _ []netip.AddrPort) (int, error) {
|
func (NoopConn) WriteBatch(bufs [][]byte, _ []netip.AddrPort) (int, error) {
|
||||||
return len(bufs), nil
|
return len(bufs), nil
|
||||||
}
|
}
|
||||||
func (NoopConn) ReloadConfig(_ *config.C) {
|
func (NoopConn) ReloadConfig(_ *config.C, _ *config.Reload) {
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
func (NoopConn) Close() error {
|
func (NoopConn) Close() error {
|
||||||
|
|||||||
@@ -24,6 +24,12 @@ type NetworkChangeMonitor struct {
|
|||||||
// NewNetworkChangeMonitor builds a monitor for local network changes. The returned monitor is always usable: Start
|
// 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.
|
// 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 {
|
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{
|
return &NetworkChangeMonitor{
|
||||||
l: l,
|
l: l,
|
||||||
ctx: ctx,
|
ctx: ctx,
|
||||||
|
|||||||
@@ -13,6 +13,9 @@ import (
|
|||||||
"golang.org/x/sys/unix"
|
"golang.org/x/sys/unix"
|
||||||
)
|
)
|
||||||
|
|
||||||
|
// watchesNetworkChanges is true where Start does anything
|
||||||
|
const watchesNetworkChanges = true
|
||||||
|
|
||||||
const (
|
const (
|
||||||
// netChangeSettleWindow is how long we keep swallowing routing messages after the first interesting one. A
|
// 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
|
// single network change is never a single message, it is a burst: the link drops, addresses go away, new ones
|
||||||
|
|||||||
@@ -7,6 +7,9 @@ import (
|
|||||||
"log/slog"
|
"log/slog"
|
||||||
)
|
)
|
||||||
|
|
||||||
|
// watchesNetworkChanges is true where Start does anything
|
||||||
|
const watchesNetworkChanges = false
|
||||||
|
|
||||||
// watchNetworkChanges is a no-op outside of darwin.
|
// 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
|
// Darwin is the platform that scopes a udp socket to the interface it came up on, so it is the platform whose socket
|
||||||
|
|||||||
@@ -37,3 +37,19 @@ func TestNetworkChangeMonitorNilRebindIsANoOp(t *testing.T) {
|
|||||||
m := newMonitor(t, context.Background(), "listen:\n rebind_on_network_change: true\n")
|
m := newMonitor(t, context.Background(), "listen:\n rebind_on_network_change: true\n")
|
||||||
m.Start(nil)
|
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")
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -26,7 +26,9 @@ type bypassConn struct {
|
|||||||
session *wfp.Session
|
session *wfp.Session
|
||||||
}
|
}
|
||||||
|
|
||||||
func (b *bypassConn) ReloadConfig(c *config.C) {
|
func (b *bypassConn) ReloadConfig(c *config.C, r *config.Reload) {
|
||||||
|
// Only read on the first call, at startup
|
||||||
|
r.RestartRequiredIfChanged("listen.windows_bypass_wdf")
|
||||||
b.installOnce.Do(func() {
|
b.installOnce.Do(func() {
|
||||||
if !c.GetBool("listen.windows_bypass_wdf", true) {
|
if !c.GetBool("listen.windows_bypass_wdf", true) {
|
||||||
return
|
return
|
||||||
@@ -45,7 +47,7 @@ func (b *bypassConn) ReloadConfig(c *config.C) {
|
|||||||
"port", addr.Port())
|
"port", addr.Port())
|
||||||
b.session = s
|
b.session = s
|
||||||
})
|
})
|
||||||
b.Conn.ReloadConfig(c)
|
b.Conn.ReloadConfig(c, r)
|
||||||
}
|
}
|
||||||
|
|
||||||
func (b *bypassConn) Close() error {
|
func (b *bypassConn) Close() error {
|
||||||
|
|||||||
+1
-1
@@ -171,7 +171,7 @@ func (u *StdConn) LocalAddr() (netip.AddrPort, error) {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
func (u *StdConn) ReloadConfig(c *config.C) {
|
func (u *StdConn) ReloadConfig(c *config.C, r *config.Reload) {
|
||||||
// TODO
|
// TODO
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
+1
-1
@@ -73,7 +73,7 @@ func (u *GenericConn) LocalAddr() (netip.AddrPort, error) {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
func (u *GenericConn) ReloadConfig(c *config.C) {
|
func (u *GenericConn) ReloadConfig(c *config.C, r *config.Reload) {
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
+4
-1
@@ -392,7 +392,7 @@ func writeSockaddr(buf []byte, addr netip.AddrPort, isV4 bool) (int, error) {
|
|||||||
return unix.SizeofSockaddrInet6, nil
|
return unix.SizeofSockaddrInet6, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func (u *StdConn) ReloadConfig(c *config.C) {
|
func (u *StdConn) ReloadConfig(c *config.C, r *config.Reload) {
|
||||||
b := c.GetInt("listen.read_buffer", 0)
|
b := c.GetInt("listen.read_buffer", 0)
|
||||||
if b > 0 {
|
if b > 0 {
|
||||||
if err := u.SetRecvBuffer(b); err == nil {
|
if err := u.SetRecvBuffer(b); err == nil {
|
||||||
@@ -403,6 +403,7 @@ func (u *StdConn) ReloadConfig(c *config.C) {
|
|||||||
}
|
}
|
||||||
} else {
|
} else {
|
||||||
u.l.Error("Failed to set listen.read_buffer", "error", err)
|
u.l.Error("Failed to set listen.read_buffer", "error", err)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -416,6 +417,7 @@ func (u *StdConn) ReloadConfig(c *config.C) {
|
|||||||
}
|
}
|
||||||
} else {
|
} else {
|
||||||
u.l.Error("Failed to set listen.write_buffer", "error", err)
|
u.l.Error("Failed to set listen.write_buffer", "error", err)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -430,6 +432,7 @@ func (u *StdConn) ReloadConfig(c *config.C) {
|
|||||||
}
|
}
|
||||||
} else {
|
} else {
|
||||||
u.l.Error("Failed to set listen.so_mark", "error", err)
|
u.l.Error("Failed to set listen.so_mark", "error", err)
|
||||||
|
r.Failed()
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -0,0 +1,31 @@
|
|||||||
|
//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)
|
||||||
|
}
|
||||||
@@ -12,6 +12,7 @@ import (
|
|||||||
"net/netip"
|
"net/netip"
|
||||||
"strconv"
|
"strconv"
|
||||||
"strings"
|
"strings"
|
||||||
|
"sync"
|
||||||
"unsafe"
|
"unsafe"
|
||||||
|
|
||||||
"golang.org/x/sys/unix"
|
"golang.org/x/sys/unix"
|
||||||
@@ -20,7 +21,7 @@ import (
|
|||||||
// batchWriter owns the sendmmsg(2)/UDP-GSO transmit path for a StdConn: the
|
// batchWriter owns the sendmmsg(2)/UDP-GSO transmit path for a StdConn: the
|
||||||
// scratch WriteBatch packs mmsghdr entries into, plus the GSO capability
|
// scratch WriteBatch packs mmsghdr entries into, plus the GSO capability
|
||||||
// state probed at socket creation. Each queue has its own StdConn and
|
// state probed at socket creation. Each queue has its own StdConn and
|
||||||
// batchWriter, so no locking is needed.
|
// batchWriter; mu serializes batches from the TUN reader and relay forwarding.
|
||||||
//
|
//
|
||||||
// Terminology, smallest to largest:
|
// Terminology, smallest to largest:
|
||||||
//
|
//
|
||||||
@@ -39,6 +40,7 @@ import (
|
|||||||
// chunk the entries packed for one sendmmsg call, at most MaxWriteBatch.
|
// 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.
|
// batch the caller's whole bufs/addrs pair, processed as one or more chunks.
|
||||||
type batchWriter struct {
|
type batchWriter struct {
|
||||||
|
mu sync.Mutex
|
||||||
fd int
|
fd int
|
||||||
isV4 bool
|
isV4 bool
|
||||||
|
|
||||||
@@ -192,6 +194,9 @@ func parseRelease(r string) (major, minor int) {
|
|||||||
// Returns the number of packets sent. An error means the call itself failed.
|
// Returns the number of packets sent. An error means the call itself failed.
|
||||||
// A short count means some destinations were undeliverable.
|
// A short count means some destinations were undeliverable.
|
||||||
func (w *batchWriter) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error) {
|
func (w *batchWriter) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error) {
|
||||||
|
w.mu.Lock()
|
||||||
|
defer w.mu.Unlock()
|
||||||
|
|
||||||
if len(bufs) != len(addrs) {
|
if len(bufs) != len(addrs) {
|
||||||
return 0, fmt.Errorf("WriteBatch: len(bufs)=%d != len(addrs)=%d", len(bufs), len(addrs))
|
return 0, fmt.Errorf("WriteBatch: len(bufs)=%d != len(addrs)=%d", len(bufs), len(addrs))
|
||||||
}
|
}
|
||||||
|
|||||||
Loaded 100 of 103 files, more files were not shown because too many files have changed in this diff.
Show more
Reference in new issue
Block a user