Compare commits

..
Author SHA1 Message Date
Ryan Huber 73d26dd87d tun: Allow excluding CPUs from process threads at startup
Set tun.avoid_cpus to a list of logical CPUs to remove from the affinity of
every thread of the process on Linux, before services start and reader CPUs
are chosen. Later threads inherit the restricted mask; enumeration repeats so
threads created meanwhile are covered. Inherited taskset and cgroup
restrictions are kept. Keeping Nebula off the underlay NIC's receive IRQ CPUs
and their SMT siblings is what this is for; the example configuration shows
how to find them.

Invalid IDs, a list that would leave a thread no CPU, and syscall failures
fail startup. Configuration tests only validate. Other platforms log and
ignore the setting. The exclusion is process-wide, including embedded use, and
not reloadable. It is independent of thread pinning.

New API: util.AvoidCPUs, next to the existing PinThreadToCPU and AllowedCPUs.

Tests run in a child process and check existing and new threads, preserved
inherited masks, validation without changes, and the unix.CPUSet bounds on
32- and 64-bit platforms. No isolated performance claim is made.
2026-10-15 14:40:45 +00:00
79 changed files with 753 additions and 1695 deletions

No files matched your search

+3 -3
View File
@@ -14,7 +14,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: Build
@@ -40,7 +40,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: Build
@@ -83,7 +83,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
# GitHub holds ARNs, not credentials, and ARNs outlive a rotation
+3 -3
View File
@@ -34,7 +34,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: add hashicorp source
@@ -66,7 +66,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: add hashicorp source
@@ -92,7 +92,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
# WSL2 + Ubuntu so the smoke can run a real linux peer with its own
+2 -2
View File
@@ -22,7 +22,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: Smoke Docker
@@ -51,7 +51,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: build
+4 -4
View File
@@ -22,7 +22,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: Install goimports
@@ -42,7 +42,7 @@ jobs:
- name: golangci-lint
uses: golangci/golangci-lint-action@v9
with:
version: v2.14
version: v2.12
test:
name: Test ${{ matrix.name }}
@@ -87,7 +87,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: Build
@@ -132,7 +132,7 @@ jobs:
- uses: actions/setup-go@v7
with:
go-version: '1.27'
go-version: '1.26'
check-latest: true
- name: Build ${{ matrix.name }}
-5
View File
@@ -7,11 +7,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
### Removed
- The SSH debug server's `start-cpu-profile`, `stop-cpu-profile`, `save-heap-profile`, `save-mutex-profile`, and
`mutex-profile-fraction` commands, and `sshd.sandbox_dir`, which is now ignored if set.
### Fixed
- `create-tunnel -address <ip:port>` panicked on a nil RemoteList and, over the ssh debug server, took nebula
+1 -2
View File
@@ -85,10 +85,9 @@ func main() {
fmt.Printf("failed to apply logging config: %s", err)
os.Exit(1)
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
c.RegisterReloadCallback(func(c *config.C) {
if err := logging.ApplyConfig(l, c); err != nil {
l.Error("Failed to reconfigure logger on reload", "error", err)
r.Failed()
}
})
+1 -2
View File
@@ -34,10 +34,9 @@ func (p *program) Start(s service.Service) error {
if err := logging.ApplyConfig(l, c); err != nil {
return fmt.Errorf("failed to apply logging config: %s", err)
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
c.RegisterReloadCallback(func(c *config.C) {
if err := logging.ApplyConfig(l, c); err != nil {
l.Error("Failed to reconfigure logger on reload", "error", err)
r.Failed()
}
})
+1 -2
View File
@@ -71,10 +71,9 @@ func main() {
fmt.Printf("failed to apply logging config: %s", err)
os.Exit(1)
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
c.RegisterReloadCallback(func(c *config.C) {
if err := logging.ApplyConfig(l, c); err != nil {
l.Error("Failed to reconfigure logger on reload", "error", err)
r.Failed()
}
})
+31 -40
View File
@@ -26,12 +26,9 @@ type C struct {
files []string
Settings map[string]any
oldSettings map[string]any
callbacks []func(*C, *Reload)
callbacks []func(*C)
l *slog.Logger
reloadLock sync.Mutex
// Set by the first reload that needs a restart and never cleared. Guarded by reloadLock
needsRestart bool
}
func NewC(l *slog.Logger) *C {
@@ -75,9 +72,8 @@ func (c *C) LoadString(raw string) error {
// RegisterReloadCallback stores a function to be called when a config reload is triggered. The functions registered
// here should decide if they need to make a change to the current process before making the change. HasChanged can be
// used to help decide if a change is necessary.
// These functions should return quickly or spawn their own go routine if they will take a while.
// Use r to report anything that failed or needs a restart to apply.
func (c *C) RegisterReloadCallback(f func(c *C, r *Reload)) {
// These functions should return quickly or spawn their own go routine if they will take a while
func (c *C) RegisterReloadCallback(f func(*C)) {
c.callbacks = append(c.callbacks, f)
}
@@ -148,55 +144,50 @@ func (c *C) CatchHUP(ctx context.Context) {
return
case <-ch:
c.l.Info("Caught HUP, reloading config")
c.ReloadConfig().Log(c.l)
c.ReloadConfig()
}
}
}()
}
// ReloadConfig reloads the config from the path provided to Load and runs every registered callback. A config that
// fails to load is logged here, like any other failure, and the result carries the error for the summary.
func (c *C) ReloadConfig() ReloadResult {
func (c *C) ReloadConfig() {
c.reloadLock.Lock()
defer c.reloadLock.Unlock()
c.oldSettings = make(map[string]any)
maps.Copy(c.oldSettings, c.Settings)
if err := c.Load(c.path); err != nil {
c.l.Error("Error occurred while reloading config", "config_path", c.path, "error", err)
return ReloadResult{Err: err, RestartRequired: c.needsRestart}
err := c.Load(c.path)
if err != nil {
c.l.Error("Error occurred while reloading config",
"config_path", c.path,
"error", err,
)
return
}
return c.runCallbacks()
}
// ReloadConfigString is ReloadConfig for a config held in memory rather than on disk.
func (c *C) ReloadConfigString(raw string) ReloadResult {
c.reloadLock.Lock()
defer c.reloadLock.Unlock()
c.oldSettings = make(map[string]any)
maps.Copy(c.oldSettings, c.Settings)
if err := c.LoadString(raw); err != nil {
c.l.Error("Error occurred while reloading config", "error", err)
return ReloadResult{Err: err, RestartRequired: c.needsRestart}
}
return c.runCallbacks()
}
func (c *C) runCallbacks() ReloadResult {
r := &Reload{c: c}
for _, v := range c.callbacks {
v(c, r)
v(c)
}
}
func (c *C) ReloadConfigString(raw string) error {
c.reloadLock.Lock()
defer c.reloadLock.Unlock()
c.oldSettings = make(map[string]any)
maps.Copy(c.oldSettings, c.Settings)
err := c.LoadString(raw)
if err != nil {
return err
}
if r.restart {
c.needsRestart = true
for _, v := range c.callbacks {
v(c)
}
return ReloadResult{Failed: r.failed, RestartRequired: c.needsRestart, RestartKeys: r.keys}
return nil
}
// GetString will get the string for k or return the default d if not found or invalid
@@ -400,7 +391,7 @@ func (c *C) parse() error {
var nm map[string]any
err = yaml.Unmarshal(b, &nm)
if err != nil {
return fmt.Errorf("%s: %w", path, err)
return err
}
// We need to use WithAppendSlice so that firewall rules in separate
+2 -2
View File
@@ -19,7 +19,7 @@ func TestConfig_Load(t *testing.T) {
// invalid yaml
c := NewC(l)
os.WriteFile(filepath.Join(dir, "01.yaml"), []byte(" invalid yaml"), 0644)
require.EqualError(t, c.Load(dir), filepath.Join(dir, "01.yaml")+": yaml: unmarshal errors:\n line 1: cannot unmarshal !!str `invalid...` into map[string]interface {}")
require.EqualError(t, c.Load(dir), "yaml: unmarshal errors:\n line 1: cannot unmarshal !!str `invalid...` into map[string]interface {}")
// simple multi config merge
c = NewC(l)
@@ -129,7 +129,7 @@ func TestConfig_ReloadConfig(t *testing.T) {
os.WriteFile(filepath.Join(dir, "01.yaml"), []byte("outer:\n inner: ho"), 0644)
c.RegisterReloadCallback(func(c *C, _ *Reload) {
c.RegisterReloadCallback(func(c *C) {
done <- true
})
-98
View File
@@ -1,98 +0,0 @@
package config
import (
"context"
"fmt"
"log/slog"
"slices"
)
// ReloadResult describes how a reload went. Problems are logged where they happen, Log writes a one line summary.
type ReloadResult struct {
// Err is set when the new config could not be read or parsed, no callbacks ran
Err error
// Failed is true when a callback could not apply part of the new config
Failed bool
// RestartRequired is true once any reload has needed a restart, and stays true until the process restarts
RestartRequired bool
// RestartKeys are the keys this reload changed that only apply on a restart
RestartKeys []string
}
// Summary returns a one line summary of the reload and the level to log it at.
func (r ReloadResult) Summary() (slog.Level, string) {
switch {
case r.Err != nil && r.RestartRequired:
return slog.LevelError, "Config reload failed, the new config did not load and a restart is still required"
case r.Err != nil:
return slog.LevelError, "Config reload failed, the new config did not load"
case r.Failed && r.RestartRequired:
return slog.LevelError, "Config reload completed with errors and requires a restart to fully apply, review the logs"
case r.Failed:
return slog.LevelError, "Config reload completed with errors, review the logs"
case r.RestartRequired:
return slog.LevelWarn, "Config reload was completed but requires a restart to fully apply"
default:
return slog.LevelInfo, "Config reload complete"
}
}
// String is the summary with Err and RestartKeys included, for output other than the log.
func (r ReloadResult) String() string {
_, msg := r.Summary()
if r.Err != nil {
msg = fmt.Sprintf("%s: %v", msg, r.Err)
}
if len(r.RestartKeys) > 0 {
msg = fmt.Sprintf("%s, keys %v", msg, r.RestartKeys)
}
return msg
}
// Log writes Summary to l.
func (r ReloadResult) Log(l *slog.Logger) {
level, msg := r.Summary()
if len(r.RestartKeys) > 0 {
l.Log(context.Background(), level, msg, "keys", r.RestartKeys)
return
}
l.Log(context.Background(), level, msg)
}
// Reload is passed to each reload callback to report how applying the new config went.
type Reload struct {
c *C
failed bool
restart bool
// Changed keys that only apply on a restart, from every callback
keys []string
}
// Failed marks the reload as failed, the caller logs why. Safe to call on a nil Reload, which is what the initial load
// passes.
func (r *Reload) Failed() {
if r != nil {
r.failed = true
}
}
// RestartRequired marks the reload as needing a restart, the caller logs why. Safe to call on a nil Reload.
func (r *Reload) RestartRequired() {
if r != nil {
r.restart = true
}
}
// RestartRequiredIfChanged marks the reload as needing a restart if any of keys changed, and adds them to RestartKeys.
// Use it for keys that are only read at startup. Safe to call on a nil Reload.
func (r *Reload) RestartRequiredIfChanged(keys ...string) {
if r == nil {
return
}
for _, k := range keys {
if r.c.HasChanged(k) && !slices.Contains(r.keys, k) {
r.keys = append(r.keys, k)
r.restart = true
}
}
}
-108
View File
@@ -1,108 +0,0 @@
package config
import (
"errors"
"log/slog"
"testing"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestReloadConfigString(t *testing.T) {
c := NewC(test.NewLogger())
require.NoError(t, c.LoadString("a: 1"))
fail := false
ran := 0
c.RegisterReloadCallback(func(c *C, r *Reload) {
ran++
if fail {
r.Failed()
}
})
assert.Equal(t, ReloadResult{}, c.ReloadConfigString("a: 2"))
fail = true
assert.Equal(t, ReloadResult{Failed: true}, c.ReloadConfigString("a: 3"))
assert.Equal(t, 2, ran)
// A config that fails to load runs no callbacks and returns the error
res := c.ReloadConfigString("a: [")
require.Error(t, res.Err)
assert.False(t, res.Failed)
assert.Equal(t, 2, ran)
assert.Equal(t, 3, c.GetInt("a", 0))
}
func TestReloadRestartRequiredLatches(t *testing.T) {
c := NewC(test.NewLogger())
require.NoError(t, c.LoadString("a: 1\nb: 1"))
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequiredIfChanged("a", "b") })
// Nothing that needs a restart changed
assert.Equal(t, ReloadResult{}, c.ReloadConfigString("a: 1\nb: 1\nc: 1"))
assert.Equal(t, ReloadResult{RestartRequired: true, RestartKeys: []string{"a"}}, c.ReloadConfigString("a: 2\nb: 1\nc: 1"))
// The restart sticks through a reload with no changes, reverting the key and a config that fails to load. Only the
// reload that changed the key lists it
assert.Equal(t, ReloadResult{RestartRequired: true}, c.ReloadConfigString("a: 2\nb: 1\nc: 1"))
assert.Equal(t, ReloadResult{RestartRequired: true, RestartKeys: []string{"a"}}, c.ReloadConfigString("a: 1\nb: 1\nc: 1"))
res := c.ReloadConfigString("a: [")
require.Error(t, res.Err)
assert.True(t, res.RestartRequired)
}
// A key reported by more than one callback is listed once
func TestReloadRestartKeysDeduped(t *testing.T) {
c := NewC(test.NewLogger())
require.NoError(t, c.LoadString("a: 1\nb: 1"))
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequiredIfChanged("a") })
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequiredIfChanged("a", "b") })
assert.Equal(t, []string{"a", "b"}, c.ReloadConfigString("a: 2\nb: 2").RestartKeys)
}
// A callback can require a restart without a key changing, a file the config points at may have
func TestReloadRestartRequiredWithoutAChange(t *testing.T) {
c := NewC(test.NewLogger())
require.NoError(t, c.LoadString("a: 1"))
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequired() })
assert.Equal(t, ReloadResult{RestartRequired: true}, c.ReloadConfigString("a: 1"))
}
func TestReloadResultSummary(t *testing.T) {
cases := []struct {
res ReloadResult
level slog.Level
msg string
}{
{ReloadResult{}, slog.LevelInfo, "Config reload complete"},
{ReloadResult{RestartRequired: true}, slog.LevelWarn, "Config reload was completed but requires a restart to fully apply"},
{ReloadResult{Failed: true}, slog.LevelError, "Config reload completed with errors, review the logs"},
{ReloadResult{Failed: true, RestartRequired: true}, slog.LevelError, "Config reload completed with errors and requires a restart to fully apply, review the logs"},
{ReloadResult{Err: errors.New("bad yaml")}, slog.LevelError, "Config reload failed, the new config did not load"},
{ReloadResult{Err: errors.New("bad yaml"), RestartRequired: true}, slog.LevelError, "Config reload failed, the new config did not load and a restart is still required"},
}
for _, tc := range cases {
level, msg := tc.res.Summary()
assert.Equal(t, tc.level, level, tc.msg)
assert.Equal(t, tc.msg, msg)
}
res := ReloadResult{RestartRequired: true, RestartKeys: []string{"a", "b"}}
assert.Equal(t, "Config reload was completed but requires a restart to fully apply, keys [a b]", res.String())
// String includes the error
assert.Equal(t, "Config reload failed, the new config did not load: bad yaml", ReloadResult{Err: errors.New("bad yaml")}.String())
}
// The initial load passes a nil Reload
func TestReloadNilIsSafe(t *testing.T) {
var r *Reload
r.Failed()
r.RestartRequired()
r.RestartRequiredIfChanged("a")
}
+1 -2
View File
@@ -57,8 +57,7 @@ func newConnectionManagerFromConfig(l *slog.Logger, c *config.C, hm *HostMap, p
}
cm.reload(c, true)
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("timers.connection_alive_interval", "timers.pending_deletion_interval")
c.RegisterReloadCallback(func(c *config.C) {
cm.reload(c, false)
})
+3 -3
View File
@@ -151,9 +151,9 @@ func (c *fakeConn) WriteTo(_ []byte, _ netip.AddrPort) error { return nil }
func (c *fakeConn) WriteBatch(bufs [][]byte, _ []netip.AddrPort) (int, error) {
return len(bufs), nil
}
func (c *fakeConn) ReloadConfig(_ *config.C, _ *config.Reload) {}
func (c *fakeConn) SupportsMultipleReaders() bool { return true }
func (c *fakeConn) Close() error { c.closed = true; return nil }
func (c *fakeConn) ReloadConfig(_ *config.C) {}
func (c *fakeConn) SupportsMultipleReaders() bool { return true }
func (c *fakeConn) Close() error { c.closed = true; return nil }
type multiqueueDevice struct {
*fakeDevice
+1 -2
View File
@@ -69,10 +69,9 @@ func newDnsServerFromConfig(ctx context.Context, l *slog.Logger, pki *PKI, hostM
ds.mux = dns.NewServeMux()
ds.mux.HandleFunc(".", ds.handleDnsRequest)
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
c.RegisterReloadCallback(func(c *config.C) {
if err := ds.reload(c, false); err != nil {
ds.l.Error("Failed to reload DNS responder from config", "error", err)
r.Failed()
}
})
+1 -1
View File
@@ -1513,7 +1513,7 @@ func TestLighthouseUpdateOnReload(t *testing.T) {
// Reload the config. The lighthouse.hosts change triggers TriggerUpdate,
// which wakes the update worker. It calls SendUpdate, initiating a
// handshake to the new lighthouse and caching the HostUpdateNotification.
require.NoError(t, myConfig.ReloadConfigString(string(newCfg)).Err)
require.NoError(t, myConfig.ReloadConfigString(string(newCfg)))
// Route until the lighthouse receives the HostUpdateNotification.
// This covers: handshake stage 1, stage 2, then the cached update.
+2 -2
View File
@@ -129,7 +129,7 @@ func TestCertUpgrade(t *testing.T) {
}
r.Logf("reload new v2-only config")
err = myC.ReloadConfigString(string(cb)).Err
err = myC.ReloadConfigString(string(cb))
assert.NoError(t, err)
r.Log("yay, spin until their sees it")
waitStart := time.Now()
@@ -222,7 +222,7 @@ func TestCertDowngrade(t *testing.T) {
}
r.Logf("reload new v1-only config")
err = myC.ReloadConfigString(string(cb)).Err
err = myC.ReloadConfigString(string(cb))
assert.NoError(t, err)
r.Log("yay, spin until their sees it")
waitStart := time.Now()
+22 -20
View File
@@ -8,7 +8,6 @@ pki:
cert: /etc/nebula/host.crt
key: /etc/nebula/host.key
# blocklist is a list of certificate fingerprints that we will refuse to talk to
# Entries are the hex fingerprints shown by `nebula-cert print`, an invalid entry fails startup and reload.
#blocklist:
# - c99d4e650533b92061b09918e838a5a0a6aaee21eed1d12fd937682865936c72
# disconnect_invalid is a toggle to force a client to be disconnected if the certificate is expired or invalid.
@@ -44,7 +43,7 @@ static_host_map:
lighthouse:
# am_lighthouse is used to enable lighthouse functionality for a node. This should ONLY be true on nodes
# you have configured to be lighthouses in your network. Not reloadable.
# you have configured to be lighthouses in your network
am_lighthouse: false
# serve_dns optionally starts a dns listener that responds to various queries and can even be
# delegated to for resolution
@@ -127,9 +126,8 @@ lighthouse:
# Port Nebula will be listening on. The default here is 4242. For a lighthouse node, the port should be defined,
# however using port 0 will dynamically assign a port and is recommended for roaming nodes.
listen:
# To listen on only ipv4, use "0.0.0.0". Not reloadable.
# To listen on only ipv4, use "0.0.0.0"
host: "::"
# Not reloadable.
port: 4242
# Sets the max number of packets to pull from the kernel for each syscall (under systems that support recvmmsg)
# default is 64, does not support reload
@@ -137,8 +135,7 @@ listen:
# superpacket, so the receive scratch is batch * 64KiB per listening socket (~4MiB per routine at the
# default of 64). Lower this to trade peak per-syscall throughput for memory on constrained hosts.
#batch: 64
# Linux only. Reloadable, but removing a value leaves the socket at the old size until Nebula restarts.
# Configure socket buffers for the udp side (outside), leave unset to use the system defaults. Values will be doubled by the kernel
# Linux only. Configure socket buffers for the udp side (outside), leave unset to use the system defaults. Values will be doubled by the kernel
# Default is net.core.rmem_default and net.core.wmem_default (/proc/sys/net/core/rmem_default and /proc/sys/net/core/rmem_default)
# Maximum is limited by memory in the system, SO_RCVBUFFORCE and SO_SNDBUFFORCE is used to avoid having to raise the system wide
# max, net.core.rmem_max and net.core.wmem_max
@@ -182,7 +179,7 @@ listen:
# Currently, this defaults to 1 which means we have 1 tun queue reader and 1
# UDP queue reader. Setting this above one will set IFF_MULTI_QUEUE on the tun
# device and SO_REUSEPORT on the UDP socket to allow multiple queues.
# This option is only supported on Linux. Not reloadable.
# This option is only supported on Linux.
#routines: 1
punchy:
@@ -206,7 +203,6 @@ punchy:
# Cipher allows you to choose between the available ciphers for your network. Options are chachapoly or aes
# IMPORTANT: this value must be identical on ALL NODES/LIGHTHOUSES. We do not/will not support use of different ciphers simultaneously!
# Not reloadable.
#cipher: aes
# Preferred ranges is used to define a hint about the local network ranges, which speeds up discovering the fastest
@@ -233,6 +229,12 @@ punchy:
# Trusted SSH CA public keys. These are the public keys of the CAs that are allowed to sign SSH keys for access.
#trusted_cas:
#- "ssh public key string"
# sandbox_dir restricts file paths for profiling commands (start-cpu-profile, save-heap-profile,
# save-mutex-profile) to the specified directory. Relative paths will be resolved within this directory,
# and absolute paths outside of it will be rejected. Default is $TMP/nebula-debug.
# The directory is NOT automatically created.
# Overriding this to "" is the same as "/" and will allow overwriting any path on the host.
#sandbox_dir: /var/tmp/nebula-debug
# EXPERIMENTAL: relay support for networks that can't establish direct connections.
relay:
@@ -251,25 +253,19 @@ relay:
# Configure the private interface. Note: addr is baked into the nebula certificate
tun:
# When tun is disabled, a lighthouse can be started without a local tun interface (and therefore without root)
# Not reloadable.
disabled: false
# Name of the device. If not set, a default will be chosen by the OS.
# For macOS: if set, must be in the form `utun[0-9]+`.
# For OpenBSD and NetBSD: if set, must be in the form `tun[0-9]+`, otherwise the first free one is used.
# Not reloadable.
# For NetBSD: Required to be set, must be in the form `tun[0-9]+`
dev: nebula1
# Toggles forwarding of local broadcast packets, the address of which depends on the ip/mask encoded in pki.cert
# Not reloadable.
drop_local_broadcast: false
# Toggles forwarding of multicast packets. Not reloadable.
# Toggles forwarding of multicast packets
drop_multicast: false
# Sets the transmit queue length, if you notice lots of transmit drops on the tun it may help to raise this number. Default is 5000
# Not reloadable.
tx_queue: 5000
# Default MTU for every packet, safe setting is (and the default) 1300 for internet based traffic
# Anything above 8937, here or on a route below, is capped to 8937 with a warning
# Reloadable on Linux only. Where the tun is handed to nebula by a host app (iOS, Android, macOS network extensions)
# the host app owns the MTU.
mtu: 1300
# the use_offloads setting controls if Nebula will attempt to enable GSO and GRO for the tun device. Linux only, not reloadable.
@@ -299,6 +295,14 @@ tun:
# - 2
# - 4
# Linux only. avoid_cpus removes these CPU IDs from the affinity of every thread of the process at startup,
# embedding applications included; later threads inherit the remaining set. Applied before cpu_affinity and the
# default pin selection, independent of pin_threads. Invalid IDs, or IDs that would leave no CPU, fail
# startup. Not reloadable; ignored on other platforms. To keep Nebula off the underlay NIC's receive IRQ CPUs, find
# them in /proc/interrupts and /proc/irq/<IRQ>/effective_affinity_list, add their SMT siblings from
# /sys/devices/system/cpu/cpu<N>/topology/thread_siblings_list, and revisit the list when IRQ placement changes.
#avoid_cpus: []
# Route based MTU overrides, you have known vpn ip paths that can support larger MTUs you can increase/decrease them here
routes:
#- mtu: 8800
@@ -362,7 +366,7 @@ tun:
#use_system_route_table: false
# Buffer size for reading routes updates. 0 means default system buffer size. (/proc/sys/net/core/rmem_default).
# If using massive routes updates, for example BGP, you may need to increase this value to avoid packet loss.
# SO_RCVBUFFORCE is used to avoid having to raise the system wide max. Not reloadable.
# SO_RCVBUFFORCE is used to avoid having to raise the system wide max
#use_system_route_table_buffer_size: 0
# Configure logging level
@@ -412,16 +416,14 @@ logging:
# Handshakes are sent to all known addresses at each interval with a linear backoff,
# Wait try_interval after the 1st attempt, 2 * try_interval after the 2nd, etc, until the handshake is older than timeout
# A 100ms interval with the default 10 retries will give a handshake 5.5 seconds to resolve before timing out
# Not reloadable.
#try_interval: 100ms
#retries: 20
# query_buffer is the size of the buffer channel for querying lighthouses, drops are recorded in the lighthouse.query.dropped metric.
# Not reloadable.
#query_buffer: 1024
# trigger_buffer is the size of the buffer channel for quickly sending handshakes
# after receiving the response for lighthouse queries. Not reloadable.
# after receiving the response for lighthouse queries
#trigger_buffer: 64
# Tunnel manager settings
+3 -4
View File
@@ -1,6 +1,6 @@
module github.com/slackhq/nebula
go 1.27.2
go 1.26.0
require (
dario.cat/mergo v1.0.2
@@ -33,7 +33,7 @@ require (
golang.zx2c4.com/wireguard/windows v1.0.1
google.golang.org/protobuf v1.36.12
gopkg.in/yaml.v3 v3.0.1
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe
)
require (
@@ -45,6 +45,5 @@ require (
github.com/prometheus/common v0.70.1 // indirect
github.com/prometheus/procfs v0.21.1 // indirect
github.com/vishvananda/netns v0.0.5 // indirect
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc // indirect
golang.org/x/time v0.15.0 // indirect
golang.org/x/time v0.5.0 // indirect
)
+4 -6
View File
@@ -157,8 +157,6 @@ golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPh
golang.org/x/crypto v0.0.0-20210322153248-0c34fe9e7dc2/go.mod h1:T9bdIzuCu7OtxOm1hfPfRQxPLYneinmdGuTeoZ9dtd4=
golang.org/x/crypto v0.57.0 h1:3ZVCjf8Ggz7zneR/EHRVx68Ctf+2pmIMP2UFhh9cC6M=
golang.org/x/crypto v0.57.0/go.mod h1:Fdz0i5U6CoizGwLda9DttjSk6qlZo25zYNtR+ycvuZA=
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc h1:TS73t7x3KarrNd5qAipmspBDS1rkMcgVG/fS1aRb4Rc=
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc/go.mod h1:A+z0yzpGtvnG90cToK5n2tu8UJVP2XUATh+r+sfOOOc=
golang.org/x/lint v0.0.0-20200302205851-738671d3881b/go.mod h1:3xt1FjdF8hUf6vQPIChWIBhFzV8gjjsPE/fR3IyQdNY=
golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
@@ -205,8 +203,8 @@ golang.org/x/term v0.46.0/go.mod h1:+K02xbkittuwc0Am4abfA3Fc+XRGXkvBXNO88NCXPoc=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
golang.org/x/time v0.5.0 h1:o7cqy6amK/52YcAKIPlM3a+Fpj35zvRj2TP+e1xFSfk=
golang.org/x/time v0.5.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/tools v0.0.0-20200130002326-2f3ba24bd6e7/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
@@ -245,5 +243,5 @@ gopkg.in/yaml.v2 v2.3.0/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980 h1:ribyrTYQ/QYeUIs8x8bVLYwGyepa7RnHLqJzegT5YYk=
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980/go.mod h1:pK/dapF5Bf3KGW7/kd5CI5IC4lYh9FMFY1qETAIGLXk=
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe h1:fre4i6mv4iBuz5lCMOzHD1rH1ljqHWSICFmZRbbgp3g=
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe/go.mod h1:sxc3Uvk/vHcd3tj7/DHVBoR5wvWT/MmRq2pj7HRJnwU=
+17 -22
View File
@@ -65,7 +65,7 @@ type HandshakeManager struct {
lightHouse *LightHouse
outside udp.Conn
config HandshakeConfig
OutboundHandshakeTimer *LockingTimerWheel[*HandshakeHostInfo]
OutboundHandshakeTimer *LockingTimerWheel[netip.Addr]
messageMetrics *MessageMetrics
metricInitiated metrics.Counter
metricTimedOut metrics.Counter
@@ -81,7 +81,6 @@ type HandshakeHostInfo struct {
startTime time.Time // Time that we first started trying with this handshake
ready bool // Is the handshake ready
deleted bool // Has the handshake been removed from the pending maps, deleters hold the lock
initiatingVersionOverride cert.Version // Should we use a non-default cert version for this handshake?
counter int64 // How many attempts have we made so far
lastRemotes []netip.AddrPort // Remotes that we sent to during the previous attempt
@@ -126,7 +125,7 @@ func NewHandshakeManager(l *slog.Logger, mainHostMap *HostMap, lightHouse *Light
outside: outside,
config: config,
trigger: make(chan netip.Addr, config.triggerBuffer),
OutboundHandshakeTimer: NewLockingTimerWheel[*HandshakeHostInfo](config.tryInterval, hsTimeout(config.retries, config.tryInterval)),
OutboundHandshakeTimer: NewLockingTimerWheel[netip.Addr](config.tryInterval, hsTimeout(config.retries, config.tryInterval)),
messageMetrics: config.messageMetrics,
metricInitiated: metrics.GetOrRegisterCounter("handshake_manager.initiated", nil),
metricTimedOut: metrics.GetOrRegisterCounter("handshake_manager.timed_out", nil),
@@ -143,9 +142,7 @@ func (hm *HandshakeManager) Run(ctx context.Context) {
case <-ctx.Done():
return
case vpnIP := <-hm.trigger:
if hh := hm.queryVpnIp(vpnIP); hh != nil {
hm.handleOutbound(hh, true)
}
hm.handleOutbound(vpnIP, true)
case now := <-clockSource.C:
hm.NextOutboundHandshakeTimerTick(now)
}
@@ -200,25 +197,23 @@ func (hm *HandshakeManager) HandleIncoming(via ViaSender, packet []byte, h *head
func (hm *HandshakeManager) NextOutboundHandshakeTimerTick(now time.Time) {
hm.OutboundHandshakeTimer.Advance(now)
for {
hh, has := hm.OutboundHandshakeTimer.Purge()
vpnIp, has := hm.OutboundHandshakeTimer.Purge()
if !has {
break
}
hm.handleOutbound(hh, false)
hm.handleOutbound(vpnIp, false)
}
}
func (hm *HandshakeManager) handleOutbound(hh *HandshakeHostInfo, lighthouseTriggered bool) {
func (hm *HandshakeManager) handleOutbound(vpnIp netip.Addr, lighthouseTriggered bool) {
hh := hm.queryVpnIp(vpnIp)
if hh == nil {
return
}
hh.Lock()
defer hh.Unlock()
// Timer entries outlive their handshake. A new handshake for the same vpn addr runs its own timer chain.
if hh.deleted {
return
}
hostinfo := hh.hostinfo
vpnIp := hostinfo.vpnAddrs[0]
// If we are out of time, clean up
if hh.counter >= hm.config.retries {
fields := []any{
@@ -244,14 +239,10 @@ func (hm *HandshakeManager) handleOutbound(hh *HandshakeHostInfo, lighthouseTrig
// Increment the counter to increase our delay, linear backoff
hh.counter++
// A lighthouse triggered attempt is still in the timer wheel, adding it again would start a second retry chain
if !lighthouseTriggered {
defer hm.OutboundHandshakeTimer.Add(hh, hm.config.tryInterval*time.Duration(hh.counter))
}
// Check if we have a handshake packet to transmit yet
if !hh.ready {
if !hm.buildStage0Packet(hh) {
hm.OutboundHandshakeTimer.Add(vpnIp, hm.config.tryInterval*time.Duration(hh.counter))
return
}
}
@@ -332,6 +323,11 @@ func (hm *HandshakeManager) handleOutbound(hh *HandshakeHostInfo, lighthouseTrig
}
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 !lighthouseTriggered {
hm.OutboundHandshakeTimer.Add(vpnIp, hm.config.tryInterval*time.Duration(hh.counter))
}
}
// GetOrHandshake will try to find a hostinfo with a fully formed tunnel or start a new handshake if one is not present
@@ -384,7 +380,7 @@ func (hm *HandshakeManager) StartHandshake(vpnAddr netip.Addr, cacheCb func(*Han
}
hm.vpnIps[vpnAddr] = hh
hm.metricInitiated.Inc(1)
hm.OutboundHandshakeTimer.Add(hh, hm.config.tryInterval)
hm.OutboundHandshakeTimer.Add(vpnAddr, hm.config.tryInterval)
if cacheCb != nil {
cacheCb(hh)
@@ -536,7 +532,6 @@ func (hm *HandshakeManager) DeleteHostInfo(hostinfo *HostInfo) {
func (hm *HandshakeManager) unlockedDeleteHostInfo(hostinfo *HostInfo) {
for _, addr := range hostinfo.vpnAddrs {
if cur, ok := hm.vpnIps[addr]; ok && cur.hostinfo == hostinfo {
cur.deleted = true
delete(hm.vpnIps, addr)
}
}
+1 -63
View File
@@ -65,69 +65,7 @@ func Test_NewHandshakeManagerVpnIp(t *testing.T) {
assert.NotContains(t, blah.vpnIps, ip)
}
// newTestHandshakeManager returns a manager whose handshakes never build a stage 0 packet (the cert has no key), so
// every attempt just bumps the counter and schedules the next one. tick advances its timer wheel by one tryInterval.
func newTestHandshakeManager() (hm *HandshakeManager, tick func()) {
l := test.NewLogger()
mainHM := newHostMap(l)
mainHM.preferredRanges.Store(&[]netip.Prefix{})
hm = NewHandshakeManager(l, mainHM, newTestLighthouse(), &udp.NoopConn{}, defaultHandshakeConfig)
hm.f = &Interface{handshakeManager: hm, pki: &PKI{}, l: l}
hm.f.pki.cs.Store(&CertState{
initiatingVersion: cert.Version1,
privateKey: []byte{},
v1Cert: &dummyCert{version: cert.Version1},
})
now := time.Now()
hm.NextOutboundHandshakeTimerTick(now)
return hm, func() {
now = now.Add(DefaultHandshakeTryInterval)
hm.NextOutboundHandshakeTimerTick(now)
}
}
func Test_HandshakeManager_RestartDropsOldTimer(t *testing.T) {
ip := netip.MustParseAddr("172.1.1.2")
hm, tick := newTestHandshakeManager()
hm.StartHandshake(ip, nil)
old := hm.queryVpnIp(ip)
tick()
tick()
require.Equal(t, int64(1), old.counter)
// Restart the handshake while the old one still has a retry queued
hm.DeleteHostInfo(old.hostinfo)
hm.StartHandshake(ip, nil)
hh := hm.queryVpnIp(ip)
require.NotSame(t, old, hh)
// An entry for timeout d fires d/tryInterval+1 ticks after it is added, so linear backoff lands attempts on ticks
// 2, 4 and 7
var counters []int64
for range 7 {
tick()
counters = append(counters, hh.counter)
}
assert.Equal(t, []int64{0, 1, 1, 2, 2, 2, 3}, counters)
// The old handshake's queued retry ended its chain instead of retrying a deleted handshake
assert.Equal(t, int64(1), old.counter)
assert.Equal(t, 1, testCountTimerWheelEntries(hm.OutboundHandshakeTimer))
}
func Test_HandshakeManager_LighthouseTriggerKeepsOneTimer(t *testing.T) {
ip := netip.MustParseAddr("172.1.1.2")
hm, _ := newTestHandshakeManager()
hm.StartHandshake(ip, nil)
hm.handleOutbound(hm.queryVpnIp(ip), true)
assert.Equal(t, 1, testCountTimerWheelEntries(hm.OutboundHandshakeTimer))
}
func testCountTimerWheelEntries(tw *LockingTimerWheel[*HandshakeHostInfo]) (c int) {
func testCountTimerWheelEntries(tw *LockingTimerWheel[netip.Addr]) (c int) {
for _, i := range tw.t.wheel {
n := i.Head
for n != nil {
+5 -7
View File
@@ -316,9 +316,9 @@ type cachedPacketMetrics struct {
func NewHostMapFromConfig(l *slog.Logger, c *config.C) *HostMap {
hm := newHostMap(l)
hm.reload(c, true, nil)
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
hm.reload(c, false, r)
hm.reload(c, true)
c.RegisterReloadCallback(func(c *config.C) {
hm.reload(c, false)
})
l.Info("Main HostMap created", "preferredRanges", hm.GetPreferredRanges())
@@ -337,8 +337,7 @@ func newHostMap(l *slog.Logger) *HostMap {
}
}
// r is nil on the initial load
func (hm *HostMap) reload(c *config.C, initial bool, r *config.Reload) {
func (hm *HostMap) reload(c *config.C, initial bool) {
if initial || c.HasChanged("preferred_ranges") {
var preferredRanges []netip.Prefix
rawPreferredRanges := c.GetStringSlice("preferred_ranges", []string{})
@@ -349,9 +348,8 @@ func (hm *HostMap) reload(c *config.C, initial bool, r *config.Reload) {
if err != nil {
hm.l.Warn("Failed to parse preferred ranges, ignoring",
"error", err,
"range", rawPreferredRange,
"range", rawPreferredRanges,
)
r.Failed()
continue
}
-13
View File
@@ -447,16 +447,3 @@ func TestHostInfo_markOutOnly(t *testing.T) {
assert.True(t, h.markOut(6), "a relayed send must not consume the epoch edge")
assert.False(t, h.markOut(6))
}
// A preferred range that doesn't parse is skipped and the rest are used, the reload says one was skipped
func TestHostMap_reloadBadPreferredRangeFails(t *testing.T) {
l := test.NewLogger()
c := config.NewC(l)
require.NoError(t, c.LoadString("preferred_ranges: [10.0.0.0/8]\n"))
hm := NewHostMapFromConfig(l, c)
res := c.ReloadConfigString("preferred_ranges: [10.0.0.0/8, nope]\n")
require.NoError(t, res.Err)
assert.True(t, res.Failed)
assert.Equal(t, []netip.Prefix{netip.MustParsePrefix("10.0.0.0/8")}, hm.GetPreferredRanges())
}
+5 -7
View File
@@ -509,11 +509,10 @@ func (f *Interface) flushSendBatch(sb *batch.SendBatch, q int) {
func (f *Interface) RegisterConfigChangeCallbacks(c *config.C) {
c.RegisterReloadCallback(f.reloadFirewall)
for _, reload := range []func(*config.C){
f.reloadSendRecvError, f.reloadAcceptRecvError, f.reloadDisconnectInvalid, f.reloadMisc,
} {
c.RegisterReloadCallback(func(c *config.C, _ *config.Reload) { reload(c) })
}
c.RegisterReloadCallback(f.reloadSendRecvError)
c.RegisterReloadCallback(f.reloadAcceptRecvError)
c.RegisterReloadCallback(f.reloadDisconnectInvalid)
c.RegisterReloadCallback(f.reloadMisc)
for _, udpConn := range f.writers {
c.RegisterReloadCallback(udpConn.ReloadConfig)
@@ -530,7 +529,7 @@ func (f *Interface) reloadDisconnectInvalid(c *config.C) {
}
}
func (f *Interface) reloadFirewall(c *config.C, r *config.Reload) {
func (f *Interface) reloadFirewall(c *config.C) {
cs := f.pki.getCertState()
curCert := cs.getCertificate(cert.Version2)
if curCert == nil {
@@ -549,7 +548,6 @@ func (f *Interface) reloadFirewall(c *config.C, r *config.Reload) {
fw, err := NewFirewallFromConfig(f.l, cs, c)
if err != nil {
f.l.Error("Error while creating firewall during reload", "error", err)
r.Failed()
return
}
+4 -26
View File
@@ -65,10 +65,10 @@ func TestReloadFirewall_CertUnsafeNetworksChanged(t *testing.T) {
pki.cs.Store(&CertState{v2Cert: c2, initiatingVersion: cert.Version2})
// Reload with the same YAML so HasChanged("firewall") reports false.
require.NoError(t, cfg.ReloadConfigString(rawYAML).Err)
require.NoError(t, cfg.ReloadConfigString(rawYAML))
require.False(t, cfg.HasChanged("firewall"))
f.reloadFirewall(cfg, nil)
f.reloadFirewall(cfg)
assert.NotSame(t, fw, f.firewall, "firewall pointer should have been replaced")
assert.Equal(t, newUnsafe, f.firewall.unsafeNetworks)
@@ -113,30 +113,8 @@ func TestReloadFirewall_NoChange(t *testing.T) {
l: l,
}
require.NoError(t, cfg.ReloadConfigString(rawYAML).Err)
f.reloadFirewall(cfg, nil)
require.NoError(t, cfg.ReloadConfigString(rawYAML))
f.reloadFirewall(cfg)
assert.Same(t, fw, f.firewall, "firewall should not have been replaced")
}
// Rules that don't parse keep the old firewall, and the reload says it could not apply them
func TestReloadFirewall_BadRulesFailTheReload(t *testing.T) {
l := test.NewLogger()
pki := &PKI{}
pki.cs.Store(&CertState{v2Cert: &dummyCert{version: cert.Version2, networks: []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")}}, initiatingVersion: cert.Version2})
rules := func(proto string) string {
return "firewall:\n outbound:\n - port: any\n proto: any\n host: any\n inbound:\n - port: any\n proto: " + proto + "\n host: any\n"
}
cfg := config.NewC(l)
require.NoError(t, cfg.LoadString(rules("any")))
fw, err := NewFirewallFromConfig(l, pki.getCertState(), cfg)
require.NoError(t, err)
f := &Interface{pki: pki, firewall: fw, l: l}
cfg.RegisterReloadCallback(f.reloadFirewall)
res := cfg.ReloadConfigString(rules("nope"))
require.NoError(t, res.Err)
assert.True(t, res.Failed)
assert.Same(t, fw, f.firewall)
}
+4 -10
View File
@@ -138,21 +138,18 @@ func NewLightHouseFromConfig(ctx context.Context, l *slog.Logger, c *config.C, c
h.metrics = newLighthouseMetrics()
}
err := h.reload(c, true, nil)
err := h.reload(c, true)
if err != nil {
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("lighthouse.am_lighthouse", "listen.port", "handshakes.query_buffer", "stats.lighthouse_metrics")
err := h.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := h.reload(c, false)
switch v := err.(type) {
case *util.ContextualError:
v.Log(l)
r.Failed()
case error:
l.Error("failed to reload lighthouse", "error", err)
r.Failed()
}
})
@@ -193,8 +190,7 @@ func (lh *LightHouse) GetUpdateInterval() int64 {
return lh.interval.Load()
}
// r is nil on the initial load
func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error {
func (lh *LightHouse) reload(c *config.C, initial bool) error {
if initial || c.HasChanged("lighthouse.advertise_addrs") {
rawAdvAddrs := c.GetStringSlice("lighthouse.advertise_addrs", []string{})
advAddrs := make([]netip.AddrPort, 0)
@@ -229,7 +225,6 @@ func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error
"addr", rawAddr,
"entry", i+1,
)
r.Failed()
continue
}
@@ -388,7 +383,6 @@ func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error
"relay", v,
"error", err,
)
r.Failed()
} else {
lh.l.Info("Read relay from config", "relay", v)
relaysForMe = append(relaysForMe, configRIP)
+14 -59
View File
@@ -87,15 +87,15 @@ func TestReloadLighthouseInterval(t *testing.T) {
lh.ifce = &mockEncWriter{}
// The first one routine is kicked off by main.go currently, lets make sure that one dies
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 5").Err)
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 5"))
assert.Equal(t, int64(5), lh.interval.Load())
// Subsequent calls are killed off by the LightHouse.Reload function
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 10").Err)
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 10"))
assert.Equal(t, int64(10), lh.interval.Load())
// If this completes then nothing is stealing our reload routine
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 11").Err)
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 11"))
assert.Equal(t, int64(11), lh.interval.Load())
}
@@ -296,7 +296,7 @@ func TestLighthouse_reload(t *testing.T) {
require.NoError(t, err)
c.ReloadConfigString(string(rc))
err = lh.reload(c, false, nil)
err = lh.reload(c, false)
require.NoError(t, err)
}
@@ -334,7 +334,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
}
rc, err := yaml.Marshal(nc)
require.NoError(t, err)
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
require.NoError(t, c.ReloadConfigString(string(rc)))
rl := lh.Query(staticHost)
require.NotNil(t, rl)
@@ -350,7 +350,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
}
rc, err = yaml.Marshal(nc)
require.NoError(t, err)
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
require.NoError(t, c.ReloadConfigString(string(rc)))
rl = lh.Query(staticHost)
require.NotNil(t, rl)
@@ -358,7 +358,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("1.1.1.1:4242")}, rl.CopyAddrs([]netip.Prefix{}))
// Reload with the same config. An unchanged entry must not duplicate.
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
require.NoError(t, c.ReloadConfigString(string(rc)))
rl = lh.Query(staticHost)
require.NotNil(t, rl)
@@ -373,7 +373,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
}
rc, err = yaml.Marshal(nc)
require.NoError(t, err)
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
require.NoError(t, c.ReloadConfigString(string(rc)))
// Add a second host alongside the first. Both should be present, neither duplicated.
nc = map[string]any{
@@ -384,7 +384,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
}
rc, err = yaml.Marshal(nc)
require.NoError(t, err)
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
require.NoError(t, c.ReloadConfigString(string(rc)))
rl = lh.Query(staticHost)
require.NotNil(t, rl)
@@ -406,7 +406,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
}
rc, err = yaml.Marshal(nc)
require.NoError(t, err)
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
require.NoError(t, c.ReloadConfigString(string(rc)))
_, isStatic := lh.GetStaticHostList()[staticHost]
assert.False(t, isStatic)
@@ -966,13 +966,13 @@ func TestLighthouse_reloadRelaysTriggersUpdate(t *testing.T) {
require.NoError(t, err)
assert.Empty(t, lh.updateTrigger)
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6]\n").Err)
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6]\n"))
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
require.Len(t, lh.updateTrigger, 1)
<-lh.updateTrigger
// The config changed but what we advertise did not, a bad entry is skipped
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6, nope]\n").Err)
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6, nope]\n"))
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
assert.Empty(t, lh.updateTrigger)
}
@@ -988,57 +988,12 @@ func TestLighthouse_reloadAmRelayAlone(t *testing.T) {
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
// Relays aren't allowed to have relays, flipping am_relay alone must drop them and tell the lighthouses
require.NoError(t, c.ReloadConfigString(base+" am_relay: true\n").Err)
require.NoError(t, c.ReloadConfigString(base+" am_relay: true\n"))
assert.Empty(t, lh.GetRelaysForMe())
require.Len(t, lh.updateTrigger, 1)
<-lh.updateTrigger
require.NoError(t, c.ReloadConfigString(base+" am_relay: false\n").Err)
require.NoError(t, c.ReloadConfigString(base+" am_relay: false\n"))
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
require.Len(t, lh.updateTrigger, 1)
}
func TestLighthouse_reloadRestartRequired(t *testing.T) {
l := test.NewLogger()
c := config.NewC(l)
base := "lighthouse:\n am_lighthouse: true\n"
require.NoError(t, c.LoadString(base+"listen:\n port: 4242\n"))
_, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
require.NoError(t, err)
res := c.ReloadConfigString(base + "listen:\n port: 4242\n")
require.NoError(t, res.Err)
assert.False(t, res.RestartRequired)
res = c.ReloadConfigString(base + "listen:\n port: 4243\n")
require.NoError(t, res.Err)
assert.True(t, res.RestartRequired)
}
// A relay that doesn't parse is skipped and the rest are used, the reload says one was skipped
func TestLighthouse_reloadBadRelayFails(t *testing.T) {
l := test.NewLogger()
c := config.NewC(l)
require.NoError(t, c.LoadString("listen:\n port: 4242\n"))
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
require.NoError(t, err)
res := c.ReloadConfigString("listen:\n port: 4242\nrelay:\n relays: [10.128.0.2, nope]\n")
require.NoError(t, res.Err)
assert.True(t, res.Failed)
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.2")}, lh.GetRelaysForMe())
}
// An advertise_addrs entry inside our own network is skipped and the rest are used, the reload says one was skipped
func TestLighthouse_reloadAdvertiseAddrInNetworkFails(t *testing.T) {
l := test.NewLogger()
c := config.NewC(l)
require.NoError(t, c.LoadString("listen:\n port: 4242\n"))
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
require.NoError(t, err)
res := c.ReloadConfigString("listen:\n port: 4242\nlighthouse:\n advertise_addrs: [\"1.2.3.4:4242\", \"10.128.0.5:4242\"]\n")
require.NoError(t, res.Err)
assert.True(t, res.Failed)
assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("1.2.3.4:4242")}, lh.GetAdvertiseAddrs())
}
+42 -12
View File
@@ -2,6 +2,7 @@ package nebula
import (
"context"
"errors"
"fmt"
"log/slog"
"net"
@@ -31,6 +32,10 @@ const maxRoutines = 1 << 16
const _ = noiseutil.RejectHeadroom - 4*maxRoutines
func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, deviceFactory overlay.DeviceFactory) (retcon *Control, reterr error) {
// Apply before starting services or selecting per-reader pin CPUs.
if err := configureAvoidCPUs(c, l, configTest); err != nil {
return nil, err
}
ctx, cancel := context.WithCancel(context.Background())
// The goroutines started below stop only when this context does, and only a caller holding the
// Control can arrange that. Cancel whenever we are not handing one back, which covers an error
@@ -78,7 +83,7 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
wireSSHReload(l, ssh, c)
var sshStart func()
if c.GetBool("sshd.enabled", false) {
sshStart, err = configSSH(l, ssh, c, nil)
sshStart, err = configSSH(l, ssh, c)
if err != nil {
l.Warn("Failed to configure sshd, ssh debugging will not be available", "error", err)
sshStart = nil
@@ -197,7 +202,7 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
if err != nil {
return nil, util.NewContextualError("Failed to open udp listener", m{"queue": i}, err)
}
udpServer.ReloadConfig(c, nil)
udpServer.ReloadConfig(c)
udpConns[i] = udpServer
// If port is dynamic, discover it before the next pass through the for loop
@@ -311,16 +316,6 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
lightHouse.ifce = ifce
ifce.RegisterConfigChangeCallbacks(c)
// These are only read at startup
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged(
"routines", "tun.routines", "listen.routines", "firewall.conntrack.routine_cache_timeout",
"listen.port", "listen.host", "stats.message_metrics",
"handshakes.try_interval", "handshakes.retries", "handshakes.trigger_buffer",
"tun.drop_local_broadcast", "tun.drop_multicast",
)
r.RestartRequiredIfChanged(osStartupOnlyKeys...)
})
ifce.reloadDisconnectInvalid(c)
ifce.reloadSendRecvError(c)
ifce.reloadAcceptRecvError(c)
@@ -426,6 +421,41 @@ func parseCpuAffinity(c *config.C, l *slog.Logger, routines int) []int {
return cpus
}
// configureAvoidCPUs applies tun.avoid_cpus, a list of CPU IDs to keep every thread of the process off. Unlike
// tun.cpu_affinity, a bad entry fails startup rather than being ignored. Configuration tests only validate it.
func configureAvoidCPUs(c *config.C, l *slog.Logger, configTest bool) error {
raw := c.Get("tun.avoid_cpus")
if raw == nil {
return nil
}
values, ok := raw.([]any)
if !ok {
return fmt.Errorf("tun.avoid_cpus must be a list of non-negative integers")
}
cpus := make([]int, 0, len(values))
for _, value := range values {
cpu, ok := value.(int)
if !ok || cpu < 0 {
return fmt.Errorf("tun.avoid_cpus must contain non-negative integers, got %v", value)
}
cpus = append(cpus, cpu)
}
if len(cpus) == 0 {
return nil
}
if err := util.AvoidCPUs(cpus, !configTest); err != nil {
if errors.Is(err, errors.ErrUnsupported) {
l.Warn("tun.avoid_cpus is only supported on Linux; ignoring")
return nil
}
return fmt.Errorf("tun.avoid_cpus: %w", err)
}
if !configTest {
l.Info("Excluded CPUs from process threads", "cpus", cpus)
}
return nil
}
func moduleVersion() string {
info, ok := debug.ReadBuildInfo()
if !ok {
-6
View File
@@ -1,6 +0,0 @@
//go:build linux && !android && !e2e_testing
package nebula
// osStartupOnlyKeys are startup only keys that only matter on linux: udp batch size, udp offloads and thread pinning
var osStartupOnlyKeys = []string{"listen.batch", "listen.udp_offloads", "tun.pin_threads", "tun.pin_threads_key", "tun.cpu_affinity"}
-6
View File
@@ -1,6 +0,0 @@
//go:build !linux || android || e2e_testing
package nebula
// osStartupOnlyKeys is empty, none of the OS specific startup keys matter here
var osStartupOnlyKeys []string
+21
View File
@@ -59,6 +59,27 @@ func TestParseCpuAffinity(t *testing.T) {
}
}
func TestConfigureAvoidCPUs(t *testing.T) {
l := test.NewLogger()
for _, tc := range []struct {
value any
valid bool
}{
{nil, true}, {[]any{}, true}, {"auto", false}, {"1,2", false}, {[]any{-1}, false}, {[]any{1.5}, false},
{[]any{"2"}, false},
} {
c := config.NewC(l)
if tc.value != nil {
c.Settings["tun"] = map[string]any{"avoid_cpus": tc.value}
}
if err := configureAvoidCPUs(c, l, true); tc.valid {
require.NoError(t, err)
} else {
require.Error(t, err, "%v", tc.value)
}
}
}
// TestMain_ConfigTestReleasesItsGoroutines pins the rule that Main only leaves goroutines running
// when it hands back a Control to stop them with.
//
+2 -4
View File
@@ -476,10 +476,8 @@ func parseV4(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
func (f *Interface) handleOutsideMessagePacket(hostinfo *HostInfo, messageCounter uint64, out []byte, rxc *rxContext) {
err := newPacket(out, true, rxc.fwPacket)
if err != nil {
if f.l.Enabled(context.Background(), slog.LevelDebug) {
hostinfo.logger(f.l).Debug("Error while validating inbound packet", "error", err, "packet", out)
return
}
hostinfo.logger(f.l).Warn("Error while validating inbound packet", "error", err, "packet", out)
return
}
dropReason := f.firewall.Drop(rxc.fwPacket.Packet, true, hostinfo, f.pki.GetCAPool(), rxc.ctCache.Get())
-7
View File
@@ -41,16 +41,9 @@ func (e *NameError) Error() string {
type DeviceFactory func(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, routines int) (Device, error)
func NewDeviceFromConfig(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, routines int) (Device, error) {
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.disabled")
})
switch {
case c.GetBool("tun.disabled", false):
tun := newDisabledTun(vpnNetworks, c.GetInt("tun.tx_queue", 5000), c.GetBool("stats.message_metrics", false), l)
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.tx_queue", "stats.message_metrics")
})
return tun, nil
default:
+4 -5
View File
@@ -38,17 +38,16 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
l: l,
}
err := t.reload(c, true, nil)
err := t.reload(c, true)
if err != nil {
_ = file.Close()
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
@@ -68,7 +67,7 @@ func (t *tun) Activate() error {
return nil
}
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
func (t *tun) reload(c *config.C, initial bool) error {
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
if err != nil {
return err
-45
View File
@@ -1,45 +0,0 @@
//go:build (openbsd || netbsd) && !e2e_testing
package overlay
import (
"errors"
"fmt"
"log/slog"
"os"
"regexp"
"runtime"
"golang.org/x/sys/unix"
)
var deviceNameRE = regexp.MustCompile(`^tun[0-9]+$`)
// tunDevNeedsRestart is true when tun.dev asks for a particular tun that isn't the running one. Anything else takes the
// first free one, and the one we have will do
func tunDevNeedsRestart(name, running string) bool {
return deviceNameRE.MatchString(name) && name != running
}
// openTun opens /dev/name, or the first /dev/tunN nothing else has open when name is empty or not tunN
func openTun(l *slog.Logger, name string) (int, string, error) {
if name != "" && !deviceNameRE.MatchString(name) {
// The name doesn't mean anything here, so like darwin a bad one isn't worth refusing to start over
l.Warn("interface name must be tun[0-9]+ on "+runtime.GOOS+", ignoring", "name", name)
name = ""
}
if name != "" {
fd, err := unix.Open("/dev/"+name, os.O_RDWR, 0)
return fd, name, err
}
for i := 0; ; i++ {
name = fmt.Sprintf("tun%d", i)
fd, err := unix.Open("/dev/"+name, os.O_RDWR, 0)
if err == nil {
return fd, name, nil
}
if !errors.Is(err, unix.EBUSY) {
return -1, "", fmt.Errorf("no free tun device, %s: %w", name, err)
}
}
}
-80
View File
@@ -1,80 +0,0 @@
//go:build (openbsd || netbsd) && !e2e_testing
package overlay
import (
"net/netip"
"testing"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// A tun.dev that isn't tunN is ignored like darwin does, and the first free tun is used. Only naming a different tun
// asks for a restart
func TestTunReloadDevRestart(t *testing.T) {
newWithDev := func(dev string) (*config.C, *tun, error) {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString("tun:\n dev: "+dev+"\n"))
tn, err := newTun(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, false)
if err == nil {
t.Cleanup(func() { _ = tn.Close() })
}
return c, tn, err
}
if _, _, err := newWithDev(""); err != nil {
t.Skipf("can't create a tun device here: %v", err)
}
c, tn, err := newWithDev("nope")
require.NoError(t, err, "a bad name should fall back to a free tun")
require.Regexp(t, `^tun[0-9]+$`, tn.Device)
for _, dev := range []string{"nope", "", tn.Device, "nope"} {
res := c.ReloadConfigString("tun:\n dev: " + dev + "\n")
require.NoError(t, res.Err)
assert.False(t, res.Failed, dev)
assert.False(t, res.RestartRequired, dev)
}
other := "tun0"
if tn.Device == other {
other = "tun1"
}
res := c.ReloadConfigString("tun:\n dev: " + other + "\n")
require.NoError(t, res.Err)
assert.Equal(t, []string{"tun.dev"}, res.RestartKeys)
}
// An empty tun.dev takes the first tun nothing else has open. Reloading it empty, or naming the one we have, needs
// no restart
func TestTunEmptyDevPicksAFreeOne(t *testing.T) {
newEmpty := func() (*config.C, *tun, error) {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString("tun: {}\n"))
tn, err := newTun(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, false)
if err == nil {
t.Cleanup(func() { _ = tn.Close() })
}
return c, tn, err
}
c, first, err := newEmpty()
if err != nil {
t.Skipf("can't create a tun device here: %v", err)
}
_, second, err := newEmpty()
require.NoError(t, err, "the second tun should skip the one the first has open")
assert.NotEqual(t, first.Device, second.Device)
for _, cfg := range []string{
"tun: {}\npunchy:\n punch: true\n",
"tun:\n dev: " + first.Device + "\n",
"tun: {}\n",
} {
res := c.ReloadConfigString(cfg)
require.NoError(t, res.Err)
assert.False(t, res.Failed)
assert.False(t, res.RestartRequired, cfg)
}
}
-3
View File
@@ -10,9 +10,6 @@ import (
"github.com/slackhq/nebula/wfp"
)
// interfaceBypassKeys are only read when the interface bypass is installed
var interfaceBypassKeys = []string{"tun.windows_bypass_wdf"}
// installInterfaceBypass installs a WFP PERMIT filter scoped to the wintun interface LUID so inbound traffic on the
// nebula adapter bypasses Windows Defender Firewall.
func installInterfaceBypass(l *slog.Logger, luid uint64) closer {
-3
View File
@@ -4,9 +4,6 @@ package overlay
import "log/slog"
// interfaceBypassKeys is empty, windows-386 has no bypass
var interfaceBypassKeys []string
// installInterfaceBypass is a no-op on windows-386 because we don't currently build for it.
func installInterfaceBypass(_ *slog.Logger, _ uint64) closer {
return nil
+24 -51
View File
@@ -80,31 +80,17 @@ type ifreqAlias6 struct {
Lifetime addrLifetime
}
// utunIndex is the utun tun.dev asks for, or -1 for whichever is free. ok is false for a name that isn't utunN, which
// also gets whichever is free
func utunIndex(name string) (index int, ok bool) {
if name == "" || name == "utun" {
return -1, true
}
if _, err := fmt.Sscanf(name, "utun%d", &index); err != nil || index < 0 {
return -1, false
}
return index, true
}
// tunDevNeedsRestart is true when tun.dev asks for a particular utun that isn't the running one. Anything else takes
// whichever is free, and the one we have will do
func tunDevNeedsRestart(name, running string) bool {
index, _ := utunIndex(name)
return index >= 0 && fmt.Sprintf("utun%d", index) != running
}
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
ifIndex, ok := utunIndex(c.GetString("tun.dev", ""))
if !ok {
// NOTE: we don't make this error so we don't break existing
// configs that set a name before it was used.
l.Warn("interface name must be utun[0-9]+ on Darwin, ignoring")
name := c.GetString("tun.dev", "")
ifIndex := -1
if name != "" && name != "utun" {
_, err := fmt.Sscanf(name, "utun%d", &ifIndex)
if err != nil || ifIndex < 0 {
// NOTE: we don't make this error so we don't break existing
// configs that set a name before it was used.
l.Warn("interface name must be utun[0-9]+ on Darwin, ignoring")
ifIndex = -1
}
}
fd, err := unix.Socket(unix.AF_SYSTEM, unix.SOCK_DGRAM, unix.AF_SYS_CONTROL)
@@ -128,7 +114,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
return nil, fmt.Errorf("SYS_CONNECT: %v", err)
}
name, err := unix.GetsockoptString(fd, unix.AF_SYS_CONTROL, _UTUN_OPT_IFNAME)
name, err = unix.GetsockoptString(fd, unix.AF_SYS_CONTROL, _UTUN_OPT_IFNAME)
if err != nil {
return nil, fmt.Errorf("failed to retrieve tun name: %w", err)
}
@@ -146,20 +132,15 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
l: l,
}
err = t.reload(c, true, nil)
err = t.reload(c, true)
if err != nil {
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.mtu")
if tunDevNeedsRestart(c.GetString("tun.dev", ""), t.Device) {
r.RestartRequiredIfChanged("tun.dev")
}
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
@@ -193,15 +174,14 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
l: l,
}
if err := t.reload(c, true, nil); err != nil {
if err := t.reload(c, true); err != nil {
_ = file.Close()
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
if err := t.reload(c, false, r); err != nil {
c.RegisterReloadCallback(func(c *config.C) {
if err := t.reload(c, false); err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
@@ -288,7 +268,7 @@ func (t *tun) Activate() error {
}
// Unsafe path routes
return t.addRoutes(false, nil)
return t.addRoutes(false)
}
// activate4 assigns our vpn address as a /32 and routes the vpn network to the tun explicitly.
@@ -386,7 +366,7 @@ func (t *tun) activate6(network netip.Prefix) error {
return nil
}
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
func (t *tun) reload(c *config.C, initial bool) error {
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
if err != nil {
return err
@@ -407,18 +387,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
if !initial {
// Remove first, if the system removes a wanted route hopefully it will be re-added next
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
if err != nil {
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
r.Failed()
}
// Ensure any routes we actually want are installed
err = t.addRoutes(true, r)
err = t.addRoutes(true)
if err != nil {
// Catch any stray logs
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
r.Failed()
}
}
@@ -511,7 +489,7 @@ func getLinkAddr(name string) (*netroute.LinkAddr, error) {
return nil, nil
}
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
func (t *tun) addRoutes(logErrors bool) error {
// The route tree is still ours, the system routing table is not
if t.hostOwned {
return nil
@@ -546,7 +524,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
if logErrors {
retErr.Log(t.l)
rl.Failed()
} else {
return retErr
}
@@ -561,7 +538,7 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
return nil
}
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
func (t *tun) removeRoutes(routes []Route) error {
linkAddr := t.linkAddr.Load()
if t.hostOwned || linkAddr == nil {
return nil
@@ -574,12 +551,8 @@ func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
}
err := delRoute(r.Cidr, linkAddr)
if errors.Is(err, unix.ESRCH) {
// Already gone, which is what we wanted
t.l.Info("Route was already removed", "route", r)
} else if err != nil {
if err != nil {
t.l.Error("Failed to remove route", "error", err, "route", r)
rl.Failed()
} else {
t.l.Info("Removed route", "route", r)
}
+3 -18
View File
@@ -72,8 +72,8 @@ func TestTunRoutesBeforeActivate(t *testing.T) {
}}
tn.Routes.Store(&routes)
assert.NoError(t, tn.addRoutes(true, nil))
assert.NoError(t, tn.removeRoutes(routes, nil))
assert.NoError(t, tn.addRoutes(true))
assert.NoError(t, tn.removeRoutes(routes))
}
// A tun.routes entry with no via is never installed, so removing it must not delete a route for the same cidr that
@@ -96,23 +96,8 @@ func TestTunReloadLeavesRoutesItNeverInstalled(t *testing.T) {
t.Cleanup(func() { _ = tn.Close() })
require.NoError(t, tn.Activate())
res := c.ReloadConfigString("tun: {}\n")
require.NoError(t, res.Err)
assert.False(t, res.Failed, "removing a route we never installed failed the reload")
require.NoError(t, c.ReloadConfigString("tun: {}\n"))
msgs, err := fetchRoutes()
require.NoError(t, err)
assert.Equal(t, lo0.Index, routeInterfaceIn(msgs, netip.MustParsePrefix(cidr)))
}
// Only naming a different utun asks for a restart. Empty, plain utun and names that aren't utunN take whichever is free
func TestTunDevNeedsRestart(t *testing.T) {
for name, want := range map[string]bool{
"": false,
"utun": false,
"nope": false,
"utun7": false,
"utun3": true,
} {
assert.Equal(t, want, tunDevNeedsRestart(name, "utun7"), name)
}
}
+10 -19
View File
@@ -385,18 +385,16 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
},
}
err = t.reload(c, true, nil)
err = t.reload(c, true)
if err != nil {
return nil, err
}
closeOnErr = false
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.dev", "tun.mtu")
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
@@ -495,7 +493,7 @@ func (t *tun) Activate() error {
}
}
return t.addRoutes(false, nil)
return t.addRoutes(false)
}
func (t *tun) setMTU() error {
@@ -511,7 +509,7 @@ func (t *tun) setMTU() error {
return err
}
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
func (t *tun) reload(c *config.C, initial bool) error {
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
if err != nil {
return err
@@ -532,18 +530,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
if !initial {
// Remove first, if the system removes a wanted route hopefully it will be re-added next
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
if err != nil {
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
r.Failed()
}
// Ensure any routes we actually want are installed
err = t.addRoutes(true, r)
err = t.addRoutes(true)
if err != nil {
// Catch any stray logs
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
r.Failed()
}
}
@@ -567,7 +563,7 @@ func (t *tun) Queues(int) ([]tio.Queue, error) {
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
}
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
func (t *tun) addRoutes(logErrors bool) error {
routes := *t.Routes.Load()
for _, r := range routes {
if len(r.Via) == 0 || !r.Install {
@@ -580,7 +576,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
if logErrors {
retErr.Log(t.l)
rl.Failed()
} else {
return retErr
}
@@ -592,7 +587,7 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
return nil
}
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
func (t *tun) removeRoutes(routes []Route) error {
for _, r := range routes {
if len(r.Via) == 0 || !r.Install {
// addRoutes never installs these
@@ -600,12 +595,8 @@ func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
}
err := delRoute(r.Cidr, t.linkAddr)
if errors.Is(err, unix.ESRCH) {
// Already gone, which is what we wanted
t.l.Info("Route was already removed", "route", r)
} else if err != nil {
if err != nil {
t.l.Error("Failed to remove route", "error", err, "route", r)
rl.Failed()
} else {
t.l.Info("Removed route", "route", r)
}
+4 -5
View File
@@ -47,17 +47,16 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
l: l,
}
err := t.reload(c, true, nil)
err := t.reload(c, true)
if err != nil {
_ = file.Close()
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
@@ -68,7 +67,7 @@ func (t *tun) Activate() error {
return nil
}
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
func (t *tun) reload(c *config.C, initial bool) error {
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
if err != nil {
return err
+14 -28
View File
@@ -185,10 +185,6 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, multiqueue
}
t.Device = name
// Only read when we create the device, an fd handed to us already has its name and offloads
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.dev", "tun.use_offloads")
})
return t, nil
}
@@ -232,24 +228,22 @@ func newTunGeneric(c *config.C, l *slog.Logger, fd int, vnetHdr bool, offloadFla
l: l,
}
if err = t.reload(c, true, nil); err != nil {
if err = t.reload(c, true); err != nil {
_ = t.Close()
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.tx_queue", "tun.use_system_route_table", "tun.use_system_route_table_buffer_size")
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
return t, nil
}
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
func (t *tun) reload(c *config.C, initial bool) error {
routeChange, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
if err != nil {
return err
@@ -303,7 +297,7 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
if !initial {
if oldMaxMTU != newMaxMTU {
t.setMTU(r)
t.setMTU()
t.l.Info("Set max MTU", "mtu", t.MaxMTU, "oldMTU", oldMaxMTU)
}
@@ -311,8 +305,7 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
for i := range t.vpnNetworks {
err := t.setDefaultRoute(t.vpnNetworks[i])
if err != nil {
t.l.Error(err.Error())
r.Failed()
t.l.Warn(err.Error())
} else {
t.l.Info("Set default MTU", "mtu", t.DefaultMTU, "oldMTU", oldDefaultMTU)
}
@@ -320,14 +313,13 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
}
// Remove first, if the system removes a wanted route hopefully it will be re-added next
t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
// Ensure any routes we actually want are installed
err = t.addRoutes(true, r)
err = t.addRoutes(true)
if err != nil {
// This should never be called since addRoutes should log its own errors in a reload condition
util.LogWithContextIfNeeded("Failed to refresh routes", err, t.l)
r.Failed()
}
}
@@ -482,7 +474,7 @@ func (t *tun) Activate() error {
t.deviceIndex = link.Attrs().Index
// Setup our default MTU
t.setMTU(nil)
t.setMTU()
// Set the transmit queue length
ifrq := ifreqQLEN{Name: devName, Value: int32(t.TXQueueLen)}
@@ -514,7 +506,7 @@ func (t *tun) Activate() error {
}
// Set the routes
if err = t.addRoutes(false, nil); err != nil {
if err = t.addRoutes(false); err != nil {
return err
}
@@ -527,13 +519,12 @@ func (t *tun) Activate() error {
return nil
}
func (t *tun) setMTU(r *config.Reload) {
func (t *tun) setMTU() {
// Set the MTU on the device
ifm := ifreqMTU{Name: t.deviceBytes(), MTU: int32(t.MaxMTU)}
if err := ioctl(t.ioctlFd, unix.SIOCSIFMTU, uintptr(unsafe.Pointer(&ifm))); err != nil {
// This is currently a non fatal condition because the route table must have the MTU set appropriately as well
t.l.Error("Failed to set tun mtu", "error", err)
r.Failed()
}
}
@@ -586,7 +577,7 @@ func (t *tun) setDefaultRoute(cidr netip.Prefix) error {
return nil
}
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
func (t *tun) addRoutes(logErrors bool) error {
// Path routes
routes := *t.Routes.Load()
for _, r := range routes {
@@ -616,7 +607,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
if logErrors {
retErr.Log(t.l)
rl.Failed()
} else {
return retErr
}
@@ -628,7 +618,7 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
return nil
}
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) {
func (t *tun) removeRoutes(routes []Route) {
for _, r := range routes {
if !r.Install {
continue
@@ -652,12 +642,8 @@ func (t *tun) removeRoutes(routes []Route, rl *config.Reload) {
}
err := netlink.RouteDel(&nr)
if errors.Is(err, unix.ESRCH) {
// Already gone, which is what we wanted
t.l.Info("Route was already removed", "route", r)
} else if err != nil {
if err != nil {
t.l.Error("Failed to remove route", "error", err, "route", r)
rl.Failed()
} else {
t.l.Info("Removed route", "route", r)
}
+24 -23
View File
@@ -8,6 +8,7 @@ import (
"log/slog"
"net/netip"
"os"
"regexp"
"sync/atomic"
"syscall"
"unsafe"
@@ -66,12 +67,24 @@ type tun struct {
fd int
}
var deviceNameRE = regexp.MustCompile(`^tun[0-9]+$`)
func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
return nil, fmt.Errorf("newTunFromFd not supported in NetBSD")
}
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
fd, deviceName, err := openTun(l, c.GetString("tun.dev", ""))
// Try to open tun device
var err error
deviceName := c.GetString("tun.dev", "")
if deviceName == "" {
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
}
if !deviceNameRE.MatchString(deviceName) {
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
}
fd, err := unix.Open("/dev/"+deviceName, os.O_RDWR, 0)
if err != nil {
return nil, err
}
@@ -90,20 +103,15 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
l: l,
}
err = t.reload(c, true, nil)
err = t.reload(c, true)
if err != nil {
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.mtu")
if tunDevNeedsRestart(c.GetString("tun.dev", ""), t.Device) {
r.RestartRequiredIfChanged("tun.dev")
}
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
@@ -316,7 +324,7 @@ func (t *tun) Activate() error {
}
}
return t.addRoutes(false, nil)
return t.addRoutes(false)
}
func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
@@ -331,7 +339,7 @@ func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
return err
}
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
func (t *tun) reload(c *config.C, initial bool) error {
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
if err != nil {
return err
@@ -352,18 +360,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
if !initial {
// Remove first, if the system removes a wanted route hopefully it will be re-added next
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
if err != nil {
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
r.Failed()
}
// Ensure any routes we actually want are installed
err = t.addRoutes(true, r)
err = t.addRoutes(true)
if err != nil {
// Catch any stray logs
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
r.Failed()
}
}
@@ -387,7 +393,7 @@ func (t *tun) Queues(int) ([]tio.Queue, error) {
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
}
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
func (t *tun) addRoutes(logErrors bool) error {
routes := *t.Routes.Load()
for _, r := range routes {
@@ -401,7 +407,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
if logErrors {
retErr.Log(t.l)
rl.Failed()
} else {
return retErr
}
@@ -413,7 +418,7 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
return nil
}
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
func (t *tun) removeRoutes(routes []Route) error {
for _, r := range routes {
if len(r.Via) == 0 || !r.Install {
// addRoutes never installs these
@@ -421,12 +426,8 @@ func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
}
err := delRoute(r.Cidr, t.vpnNetworks)
if errors.Is(err, unix.ESRCH) {
// Already gone, which is what we wanted
t.l.Info("Route was already removed", "route", r)
} else if err != nil {
if err != nil {
t.l.Error("Failed to remove route", "error", err, "route", r)
rl.Failed()
} else {
t.l.Info("Removed route", "route", r)
}
+24 -23
View File
@@ -8,6 +8,7 @@ import (
"log/slog"
"net/netip"
"os"
"regexp"
"sync/atomic"
"syscall"
"unsafe"
@@ -57,12 +58,24 @@ type tun struct {
fd int
}
var deviceNameRE = regexp.MustCompile(`^tun[0-9]+$`)
func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
return nil, fmt.Errorf("newTunFromFd not supported in openbsd")
}
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
fd, deviceName, err := openTun(l, c.GetString("tun.dev", ""))
// Try to open tun device
var err error
deviceName := c.GetString("tun.dev", "")
if deviceName == "" {
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
}
if !deviceNameRE.MatchString(deviceName) {
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
}
fd, err := unix.Open("/dev/"+deviceName, os.O_RDWR, 0)
if err != nil {
return nil, err
}
@@ -81,20 +94,15 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
l: l,
}
err = t.reload(c, true, nil)
err = t.reload(c, true)
if err != nil {
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.mtu")
if tunDevNeedsRestart(c.GetString("tun.dev", ""), t.Device) {
r.RestartRequiredIfChanged("tun.dev")
}
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
@@ -295,7 +303,7 @@ func (t *tun) Activate() error {
}
}
return t.addRoutes(false, nil)
return t.addRoutes(false)
}
func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
@@ -310,7 +318,7 @@ func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
return err
}
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
func (t *tun) reload(c *config.C, initial bool) error {
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
if err != nil {
return err
@@ -331,18 +339,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
if !initial {
// Remove first, if the system removes a wanted route hopefully it will be re-added next
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
if err != nil {
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
r.Failed()
}
// Ensure any routes we actually want are installed
err = t.addRoutes(true, r)
err = t.addRoutes(true)
if err != nil {
// Catch any stray logs
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
r.Failed()
}
}
@@ -366,7 +372,7 @@ func (t *tun) Queues(int) ([]tio.Queue, error) {
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
}
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
func (t *tun) addRoutes(logErrors bool) error {
routes := *t.Routes.Load()
for _, r := range routes {
@@ -380,7 +386,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
if logErrors {
retErr.Log(t.l)
rl.Failed()
} else {
return retErr
}
@@ -392,7 +397,7 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
return nil
}
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
func (t *tun) removeRoutes(routes []Route) error {
for _, r := range routes {
if len(r.Via) == 0 || !r.Install {
// addRoutes never installs these
@@ -400,12 +405,8 @@ func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
}
err := delRoute(r.Cidr, t.vpnNetworks)
if errors.Is(err, unix.ESRCH) {
// Already gone, which is what we wanted
t.l.Info("Route was already removed", "route", r)
} else if err != nil {
if err != nil {
t.l.Error("Failed to remove route", "error", err, "route", r)
rl.Failed()
} else {
t.l.Info("Removed route", "route", r)
}
+4 -55
View File
@@ -4,7 +4,6 @@ package overlay
import (
"net/netip"
"os"
"testing"
"github.com/slackhq/nebula/config"
@@ -26,10 +25,10 @@ func TestReloadMTUOnlyKeepsRoutes(t *testing.T) {
ioctlFd: ^uintptr(0),
routesFromSystem: map[netip.Prefix]routing.Gateways{},
}
require.NoError(t, tn.reload(c, true, nil))
require.NoError(t, tn.reload(c, true))
require.NoError(t, c.ReloadConfigString("tun:\n mtu: 1400\n"+routes).Err)
_ = tn.reload(c, false, nil)
require.NoError(t, c.ReloadConfigString("tun:\n mtu: 1400\n"+routes))
_ = tn.reload(c, false)
got := *tn.Routes.Load()
require.Len(t, got, 1)
@@ -51,57 +50,7 @@ func TestReloadMaxMTUIsTheLargestRoute(t *testing.T) {
ioctlFd: ^uintptr(0),
routesFromSystem: map[netip.Prefix]routing.Gateways{},
}
require.NoError(t, tn.reload(c, true, nil))
require.NoError(t, tn.reload(c, true))
assert.Equal(t, 1500, tn.MaxMTU)
assert.Equal(t, 1300, tn.DefaultMTU)
}
// There is no device behind this tun, so adding a route always fails. Removing one is refused without root, as root the
// kernel answers that the route isn't there, which is what we wanted
func TestReloadRouteFailures(t *testing.T) {
route := "tun:\n mtu: 1300\n unsafe_routes:\n - route: 192.168.100.0/24\n via: 10.1.0.1\n"
cases := []struct {
name string
from, to string
wantFails bool
}{
{"added", "tun:\n mtu: 1300\n", route, true},
{"removed", route, "tun:\n mtu: 1300\n", os.Geteuid() != 0},
{"unchanged", route, route + "punchy:\n punch: true\n", false},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString(tc.from))
tn := &tun{
l: test.NewLogger(),
vpnNetworks: []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")},
ioctlFd: ^uintptr(0),
routesFromSystem: map[netip.Prefix]routing.Gateways{},
}
require.NoError(t, tn.reload(c, true, nil))
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
require.NoError(t, tn.reload(c, false, r))
})
res := c.ReloadConfigString(tc.to)
require.NoError(t, res.Err)
assert.Equal(t, tc.wantFails, res.Failed)
})
}
}
// Keys only read when the device is created need a restart to apply
func TestTunReloadRestartKeys(t *testing.T) {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString("tun:\n dev: nebrk0\n"))
tn, err := NewDeviceFromConfig(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, 1)
if err != nil {
t.Skipf("can't create a tun device here: %v", err)
}
t.Cleanup(func() { _ = tn.Close() })
res := c.ReloadConfigString("tun:\n disabled: true\n dev: nebrk1\n tx_queue: 100\n")
require.NoError(t, res.Err)
assert.ElementsMatch(t, []string{"tun.disabled", "tun.dev", "tun.tx_queue"}, res.RestartKeys)
}
-24
View File
@@ -1,24 +0,0 @@
package overlay
import (
"net/netip"
"testing"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// tun.disabled and the disabled tun's settings are only read when the device is made
func TestDisabledTunRestartKeys(t *testing.T) {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString("tun:\n disabled: true\n"))
d, err := NewDeviceFromConfig(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, 1)
require.NoError(t, err)
t.Cleanup(func() { _ = d.Close() })
res := c.ReloadConfigString("tun:\n disabled: false\n tx_queue: 100\n")
require.NoError(t, res.Err)
assert.ElementsMatch(t, []string{"tun.disabled", "tun.tx_queue"}, res.RestartKeys)
}
+10 -28
View File
@@ -84,7 +84,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*w
l: l,
}
err = t.reload(c, true, nil)
err = t.reload(c, true)
if err != nil {
return nil, err
}
@@ -108,28 +108,17 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*w
// Disable registration before Activate assigns addresses and triggers it.
disableDNSRegistration(l, *guid)
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("tun.dev", "tun.mtu")
// Compare with the running category, not the last config. A restart with one we can't parse would fail, so say
// that now rather than ask for one, and going back to the running one after a bad reload needs no restart
if cat, setCat, err := parseNetworkCategory(c.GetString("tun.network_category", "private")); err != nil {
t.l.Error("Invalid tun.network_category, a restart with it would fail", "error", err)
r.Failed()
} else if cat != t.networkCategory || setCat != t.setCategory {
r.RestartRequiredIfChanged("tun.network_category")
}
r.RestartRequiredIfChanged(interfaceBypassKeys...)
err := t.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
err := t.reload(c, false)
if err != nil {
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
r.Failed()
}
})
return t, nil
}
func (t *winTun) reload(c *config.C, initial bool, r *config.Reload) error {
func (t *winTun) reload(c *config.C, initial bool) error {
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
if err != nil {
return err
@@ -150,18 +139,16 @@ func (t *winTun) reload(c *config.C, initial bool, r *config.Reload) error {
if !initial {
// Remove first, if the system removes a wanted route hopefully it will be re-added next
err := t.removeRoutes(findRemovedSystemRoutes(routes, *oldRoutes), r)
err := t.removeRoutes(findRemovedSystemRoutes(routes, *oldRoutes))
if err != nil {
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
r.Failed()
}
// Ensure any routes we actually want are installed
err = t.addRoutes(true, r)
err = t.addRoutes(true)
if err != nil {
// Catch any stray logs
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
r.Failed()
}
}
@@ -176,7 +163,7 @@ func (t *winTun) Activate() error {
return fmt.Errorf("failed to set address: %w", err)
}
err = t.addRoutes(false, nil)
err = t.addRoutes(false)
if err != nil {
return err
}
@@ -195,7 +182,7 @@ func (t *winTun) Activate() error {
return nil
}
func (t *winTun) addRoutes(logErrors bool, rl *config.Reload) error {
func (t *winTun) addRoutes(logErrors bool) error {
luid := winipcfg.LUID(t.tun.LUID())
routes := *t.Routes.Load()
foundDefault4 := false
@@ -226,7 +213,6 @@ func (t *winTun) addRoutes(logErrors bool, rl *config.Reload) error {
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
if logErrors {
retErr.Log(t.l)
rl.Failed()
continue
} else {
return retErr
@@ -288,7 +274,7 @@ func (t *winTun) setMTU(luid winipcfg.LUID, foundDefault4, carriesV6 bool) error
return nil
}
func (t *winTun) removeRoutes(routes []Route, rl *config.Reload) error {
func (t *winTun) removeRoutes(routes []Route) error {
luid := winipcfg.LUID(t.tun.LUID())
for _, r := range routes {
@@ -298,12 +284,8 @@ func (t *winTun) removeRoutes(routes []Route, rl *config.Reload) error {
// See comment on luid.AddRoute
err := luid.DeleteRoute(r.Cidr, unspecifiedNextHop(r.Cidr))
if errors.Is(err, windows.ERROR_NOT_FOUND) {
// Already gone, which is what we wanted
t.l.Info("Route was already removed", "route", r)
} else if err != nil {
if err != nil {
t.l.Error("Failed to remove route", "error", err, "route", r)
rl.Failed()
} else {
t.l.Info("Removed route", "route", r)
}
+5 -46
View File
@@ -53,14 +53,6 @@ func (rt *routeTest) metric(t *testing.T, cidr string) uint32 {
return row.Metric
}
// reload applies cfg and expects nothing in it to fail
func (rt *routeTest) reload(t *testing.T, cfg string) {
t.Helper()
res := rt.c.ReloadConfigString(cfg)
require.NoError(t, res.Err)
assert.False(t, res.Failed, "the reload reported a failure")
}
func unsafeRoutes(routes ...string) string {
var b strings.Builder
b.WriteString("tun:\n dev: nebroutetest\n unsafe_routes:\n")
@@ -85,7 +77,7 @@ func TestWinTun_ReloadKeepsInstalledRoutes(t *testing.T) {
rt := newRouteTest(t, unsafeRoutes(a))
require.NoError(t, rt.tun.Activate())
rt.reload(t, unsafeRoutes(a, b))
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a, b)))
assert.NotContains(t, rt.log.String(), "Failed to add route")
rt.metric(t, a)
rt.metric(t, b)
@@ -100,7 +92,7 @@ func TestWinTun_ReloadMetricChangeApplies(t *testing.T) {
require.NoError(t, rt.tun.Activate())
require.Equal(t, uint32(100), rt.metric(t, a))
rt.reload(t, unsafeRoutes(a+"@200"))
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a+"@200")))
assert.NotContains(t, rt.log.String(), "Failed to add route")
assert.NotContains(t, rt.log.String(), "Removed route")
assert.Equal(t, uint32(200), rt.metric(t, a))
@@ -128,7 +120,7 @@ func TestWinTun_DuplicateCidrInstallsTheLastEntry(t *testing.T) {
require.NoError(t, rt.tun.Activate())
assert.Equal(t, uint32(200), rt.metric(t, a))
rt.reload(t, unsafeRoutes(a+"@100", a+"@200", b))
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a+"@100", a+"@200", b)))
assert.Equal(t, uint32(200), rt.metric(t, a))
assert.NotContains(t, rt.log.String(), "Updated route metric")
assert.NotContains(t, rt.log.String(), "Failed to add route")
@@ -142,7 +134,7 @@ func TestWinTun_DroppingAnUninstalledDuplicateKeepsTheRoute(t *testing.T) {
rt := newRouteTest(t, unsafeRoutes(a+"@100", a+"@200"))
require.NoError(t, rt.tun.Activate())
rt.reload(t, unsafeRoutes(a+"@200"))
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a+"@200")))
assert.NotContains(t, rt.log.String(), "Removed route")
assert.Equal(t, uint32(200), rt.metric(t, a))
})
@@ -163,45 +155,12 @@ func TestWinTun_ReloadMatchesAFreshStart(t *testing.T) {
rt := newRouteTest(t, unsafeRoutes(a+"@100"))
require.NoError(t, rt.tun.Activate())
rt.reload(t, routes)
require.NoError(t, rt.c.ReloadConfigString(routes))
_, err = rt.luid.Route(cidr, unspecifiedNextHop(cidr))
assert.Error(t, err, "the reload left it installed")
})
}
// Removing a route that is already gone is what we wanted, not a failure
func TestWinTun_ReloadRouteAlreadyGone(t *testing.T) {
forFamilies(t, func(t *testing.T, a, b string) {
rt := newRouteTest(t, unsafeRoutes(a, b))
require.NoError(t, rt.tun.Activate())
p := netip.MustParsePrefix(b)
require.NoError(t, rt.luid.DeleteRoute(p, unspecifiedNextHop(p)))
rt.reload(t, unsafeRoutes(a))
})
}
// A network category we can't parse would fail the restart, so it fails the reload instead of asking for one
func TestWinTun_ReloadInvalidNetworkCategoryFails(t *testing.T) {
rt := newRouteTest(t, unsafeRoutes())
for range 2 {
res := rt.c.ReloadConfigString(unsafeRoutes() + " network_category: nope\n")
require.NoError(t, res.Err)
assert.True(t, res.Failed, "a bad category that didn't change since the last reload is still bad")
assert.False(t, res.RestartRequired)
}
// Fixing it back to the running category needs nothing
res := rt.c.ReloadConfigString(unsafeRoutes() + " network_category: private\n")
require.NoError(t, res.Err)
assert.False(t, res.Failed)
assert.False(t, res.RestartRequired)
res = rt.c.ReloadConfigString(unsafeRoutes() + " network_category: public\n")
require.NoError(t, res.Err)
assert.Equal(t, []string{"tun.network_category"}, res.RestartKeys)
}
// forFamilies runs f with two unsafe_routes CIDRs of each address family, the tun's own network stays IPv4
func forFamilies(t *testing.T, f func(t *testing.T, a, b string)) {
t.Run("ipv4", func(t *testing.T) { f(t, "10.251.1.0/24", "10.251.2.0/24") })
+18 -70
View File
@@ -2,9 +2,7 @@ package nebula
import (
"crypto/fips140"
"crypto/sha256"
"encoding/binary"
"encoding/hex"
"encoding/json"
"errors"
"fmt"
@@ -52,30 +50,15 @@ type CertState struct {
myVpnBroadcastAddrsTable *bart.Lite
}
// errCertNeedsRestart marks a new cert that is refused on reload because only a restart can apply it
var errCertNeedsRestart = errors.New("a restart is required to use the new cert")
func NewPKIFromConfig(l *slog.Logger, c *config.C) (*PKI, error) {
pki := &PKI{l: l}
err := pki.reload(c, true, nil)
err := pki.reload(c, true)
if err != nil {
return nil, err
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
// Compare with the running cipher, not the last config. A restart with one we can't run would fail, so say that
// now rather than ask for one, and going back to the running one after a bad reload needs no restart
if cipher := c.GetString("cipher", "aes"); !validCipher(cipher) {
l.Error("Unknown cipher, a restart with it would fail", "cipher", cipher)
r.Failed()
} else if cipher == "chachapoly" && fipsOnly() {
// newCipherSuite refuses it at startup
l.Error("ChaChaPoly is not allowed in FIPS 140-only mode, a restart with it would fail", "cipher", cipher)
r.Failed()
} else if cipher != pki.getCertState().cipher {
r.RestartRequiredIfChanged("cipher")
}
rErr := pki.reload(c, false, r)
c.RegisterReloadCallback(func(c *config.C) {
rErr := pki.reload(c, false)
if rErr != nil {
util.LogWithContextIfNeeded("Failed to reload PKI from config", rErr, l)
}
@@ -92,29 +75,13 @@ func (p *PKI) getCertState() *CertState {
return p.cs.Load()
}
// r is nil on the initial load
func (p *PKI) reload(c *config.C, initial bool, r *config.Reload) error {
before := p.cs.Load()
func (p *PKI) reload(c *config.C, initial bool) error {
err := p.reloadCerts(c, initial)
if err != nil {
if initial {
return err
}
err.Log(p.l)
if errors.Is(err, errCertNeedsRestart) {
r.RestartRequired()
} else {
r.Failed()
}
} else if !initial {
// A cert for a version we weren't running is accepted without comparing its networks to ours. The tun and the
// lighthouse keep the networks they started with
after := p.cs.Load()
if !slices.Equal(before.myVpnNetworks, after.myVpnNetworks) {
p.l.Warn("The new cert changes our networks, a restart is required to use them",
"old_networks", before.myVpnNetworks, "new_networks", after.myVpnNetworks)
r.RestartRequired()
}
}
err = p.reloadCAPool(c)
@@ -123,27 +90,21 @@ func (p *PKI) reload(c *config.C, initial bool, r *config.Reload) error {
return err
}
err.Log(p.l)
r.Failed()
}
return nil
}
// fipsOnly is fips140.Enforced, a variable so a test can run the FIPS 140-only reload check without GODEBUG
var fipsOnly = fips140.Enforced
// validCipher is true for the ciphers nebula can run. Each post-handshake CipherState in noiseutil hardcodes its own
// nonce endianness, so there's nothing to set up for either.
func validCipher(cipher string) bool {
return cipher == "aes" || cipher == "chachapoly"
}
func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
var cipher string
var currentState *CertState
if initial {
cipher = c.GetString("cipher", "aes")
if !validCipher(cipher) {
switch cipher {
case "aes", "chachapoly":
// Each post-handshake CipherState in noiseutil hardcodes its own
// nonce endianness now, so there's nothing to set up here.
default:
return util.NewContextualError(
"unknown cipher",
m{"cipher": cipher},
@@ -171,7 +132,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
return util.NewContextualError(
"Networks in new cert was different from old",
m{"new_networks": newState.v1Cert.Networks(), "old_networks": currentState.v1Cert.Networks(), "cert_version": cert.Version1},
errCertNeedsRestart,
nil,
)
}
@@ -179,7 +140,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
return util.NewContextualError(
"Curve in new v1 cert was different from old",
m{"new_curve": newState.v1Cert.Curve(), "old_curve": currentState.v1Cert.Curve(), "cert_version": cert.Version1},
errCertNeedsRestart,
nil,
)
}
}
@@ -194,7 +155,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
return util.NewContextualError(
"Networks in new cert was different from old",
m{"new_networks": newState.v2Cert.Networks(), "old_networks": currentState.v2Cert.Networks(), "cert_version": cert.Version2},
errCertNeedsRestart,
nil,
)
}
@@ -202,7 +163,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
return util.NewContextualError(
"Curve in new cert was different from old",
m{"new_curve": newState.v2Cert.Curve(), "old_curve": currentState.v2Cert.Curve(), "cert_version": cert.Version2},
errCertNeedsRestart,
nil,
)
}
}
@@ -217,7 +178,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
return util.NewContextualError(
"Removing a V2 cert is not permitted unless it has identical networks to the new V1 cert",
m{"new_v1_networks": newState.v1Cert.Networks(), "old_v2_networks": currentState.v2Cert.Networks()},
errCertNeedsRestart,
nil,
)
}
}
@@ -235,14 +196,12 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
func (p *PKI) reloadCAPool(c *config.C) *util.ContextualError {
caPool, err := loadCAPoolFromConfig(p.l, c)
if caPool != nil {
p.caPool.Store(caPool)
p.l.Debug("Trusted CA fingerprints", "fingerprints", caPool.GetFingerprints())
}
if err != nil {
return util.NewContextualError("Failed to load ca from config", nil, err)
}
p.caPool.Store(caPool)
p.l.Debug("Trusted CA fingerprints", "fingerprints", caPool.GetFingerprints())
return nil
}
@@ -617,22 +576,11 @@ func loadCAPoolFromConfig(l *slog.Logger, c *config.C) (*cert.CAPool, error) {
bl := c.GetStringSlice("pki.blocklist", []string{})
if len(bl) > 0 {
var bad []string
for i, raw := range bl {
// Fingerprints are compared as lowercase hex strings, a malformed entry would silently block nothing
fp := strings.ToLower(strings.TrimSpace(raw))
if b, err := hex.DecodeString(fp); err != nil || len(b) != sha256.Size {
bad = append(bad, fmt.Sprintf("entry %d %q", i+1, raw))
continue
}
for _, fp := range bl {
caPool.BlocklistFingerprint(fp)
}
l.Info("Blocklisted certificates", "fingerprintCount", len(bl)-len(bad))
if len(bad) > 0 {
// The valid entries are still returned so a failed reload blocks them, startup refuses the error
return caPool, fmt.Errorf("pki.blocklist entries are not hex certificate fingerprints: %s", strings.Join(bad, ", "))
}
l.Info("Blocklisted certificates", "fingerprintCount", len(bl))
}
return caPool, nil
-168
View File
@@ -1,17 +1,10 @@
package nebula
import (
"crypto/fips140"
"fmt"
"net/netip"
"strings"
"testing"
"time"
"github.com/slackhq/nebula/cert"
"github.com/slackhq/nebula/cert_test"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
@@ -99,164 +92,3 @@ func TestNewCipherSuiteUnsupportedCurve(t *testing.T) {
assert.True(t, strings.HasPrefix(err.Error(), "unsupported curve:"), "got: %v", err)
assert.Nil(t, cs)
}
func TestPKIReloadRestartRequired(t *testing.T) {
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
pkiConfig := func(cipher, network string) string {
_, _, keyPEM, certPEM := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix(network)}, nil, nil)
return fmt.Sprintf("cipher: %s\npki:\n ca: %q\n cert: %q\n key: %q\n", cipher, caPEM, certPEM, keyPEM)
}
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString(pkiConfig("aes", "10.1.0.2/24")))
p, err := NewPKIFromConfig(test.NewLogger(), c)
require.NoError(t, err)
// A cert that changes our networks is refused and needs a restart, it is not a failure
res := c.ReloadConfigString(pkiConfig("aes", "10.1.0.3/24"))
require.NoError(t, res.Err)
assert.True(t, res.RestartRequired)
assert.False(t, res.Failed)
assert.Equal(t, []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, p.getCertState().myVpnNetworks)
// The cipher only applies at startup
c2 := config.NewC(test.NewLogger())
require.NoError(t, c2.LoadString(pkiConfig("aes", "10.1.0.2/24")))
p, err = NewPKIFromConfig(test.NewLogger(), c2)
require.NoError(t, err)
res = c2.ReloadConfigString(pkiConfig("chachapoly", "10.1.0.2/24"))
require.NoError(t, res.Err)
assert.True(t, res.RestartRequired)
assert.Equal(t, "aes", p.getCertState().cipher)
// A cipher we can't run would fail the restart, so it fails the reload instead of asking for one
c4 := config.NewC(test.NewLogger())
require.NoError(t, c4.LoadString(pkiConfig("aes", "10.1.0.2/24")))
_, err = NewPKIFromConfig(test.NewLogger(), c4)
require.NoError(t, err)
for range 2 {
res = c4.ReloadConfigString(pkiConfig("nope", "10.1.0.2/24"))
require.NoError(t, res.Err)
assert.True(t, res.Failed, "a bad cipher that didn't change since the last reload is still bad")
assert.False(t, res.RestartRequired)
}
// Fixing it back to the running cipher needs nothing
res = c4.ReloadConfigString(pkiConfig("aes", "10.1.0.2/24"))
require.NoError(t, res.Err)
assert.False(t, res.Failed)
assert.False(t, res.RestartRequired)
// A cert that keeps our networks applies without a restart
c3 := config.NewC(test.NewLogger())
require.NoError(t, c3.LoadString(pkiConfig("aes", "10.1.0.2/24")))
_, err = NewPKIFromConfig(test.NewLogger(), c3)
require.NoError(t, err)
res = c3.ReloadConfigString(pkiConfig("aes", "10.1.0.2/24"))
require.NoError(t, res.Err)
assert.False(t, res.RestartRequired)
// A cert that can't be read is a failure, and a restart wouldn't help
res = c3.ReloadConfigString(strings.Replace(pkiConfig("aes", "10.1.0.2/24"), "cert: \"", "cert: \"garbage", 1))
require.NoError(t, res.Err)
assert.True(t, res.Failed)
assert.False(t, res.RestartRequired)
}
// A cert for a version we weren't running is accepted without comparing networks, so switching to one with different
// networks needs a restart. One with the same networks doesn't
func TestPKIReloadNewVersionWithOtherNetworks(t *testing.T) {
ca1, _, ca1Key, ca1PEM := cert_test.NewTestCaCert(cert.Version1, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
ca2, _, ca2Key, ca2PEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
caPEM := string(ca1PEM) + string(ca2PEM)
pkiConfig := func(v cert.Version, network string) string {
ca, caKey := ca1, ca1Key
if v == cert.Version2 {
ca, caKey = ca2, ca2Key
}
_, _, keyPEM, certPEM := cert_test.NewTestCert(v, cert.Curve_CURVE25519, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix(network)}, nil, nil)
return fmt.Sprintf("pki:\n ca: %q\n cert: %q\n key: %q\n", caPEM, certPEM, keyPEM)
}
for _, tc := range []struct {
network string
restart bool
}{
{"10.9.0.7/24", true},
{"10.1.0.2/24", false},
} {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString(pkiConfig(cert.Version1, "10.1.0.2/24")))
p, err := NewPKIFromConfig(test.NewLogger(), c)
require.NoError(t, err)
res := c.ReloadConfigString(pkiConfig(cert.Version2, tc.network))
require.NoError(t, res.Err)
assert.False(t, res.Failed, tc.network)
assert.Equal(t, tc.restart, res.RestartRequired, tc.network)
assert.Equal(t, []netip.Prefix{netip.MustParsePrefix(tc.network)}, p.getCertState().myVpnNetworks, "accepted either way, as before")
}
}
// FIPS 140-only mode refuses chachapoly at startup, so reloading to it fails rather than asks for a restart
func TestPKIReloadChachapolyInFIPSOnlyFails(t *testing.T) {
fipsOnly = func() bool { return true }
t.Cleanup(func() { fipsOnly = fips140.Enforced })
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_P256, time.Time{}, time.Time{}, nil, nil, nil)
_, _, keyPEM, certPEM := cert_test.NewTestCert(cert.Version2, cert.Curve_P256, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, nil, nil)
pkiConfig := func(cipher string) string {
return fmt.Sprintf("cipher: %s\npki:\n ca: %q\n cert: %q\n key: %q\n", cipher, caPEM, certPEM, keyPEM)
}
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString(pkiConfig("aes")))
_, err := NewPKIFromConfig(test.NewLogger(), c)
require.NoError(t, err)
res := c.ReloadConfigString(pkiConfig("chachapoly"))
require.NoError(t, res.Err)
assert.True(t, res.Failed)
assert.False(t, res.RestartRequired)
}
func TestLoadCAPoolBlocklist(t *testing.T) {
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
crt, _, _, _ := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, nil, nil)
fp, err := crt.Fingerprint()
require.NoError(t, err)
load := func(entry string) (*cert.CAPool, error) {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString(fmt.Sprintf("pki:\n ca: %q\n blocklist:\n - %q\n", caPEM, entry)))
return loadCAPoolFromConfig(test.NewLogger(), c)
}
for _, entry := range []string{fp, strings.ToUpper(fp), " " + fp + "\t"} {
pool, err := load(entry)
require.NoError(t, err, entry)
assert.True(t, pool.IsBlocklisted(fp), entry)
}
for _, entry := range []string{fp[1:], fp + "00", "sha256:" + fp, "zz" + fp[2:], ""} {
_, err := load(entry)
require.Error(t, err, entry)
}
// A bad entry on reload fails it, the valid entries are still blocked
_, _, keyPEM, certPEM := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "me", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.1/24")}, nil, nil)
pkiConfig := func(entry string) string {
return fmt.Sprintf("pki:\n ca: %q\n cert: %q\n key: %q\n blocklist:\n - %q\n", caPEM, certPEM, keyPEM, entry)
}
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString(pkiConfig(fp)))
p, err := NewPKIFromConfig(test.NewLogger(), c)
require.NoError(t, err)
other, _, _, _ := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "other", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.3/24")}, nil, nil)
otherFp, err := other.Fingerprint()
require.NoError(t, err)
res := c.ReloadConfigString(pkiConfig(fp) + fmt.Sprintf(" - %q\n - %q\n", otherFp, fp[1:]))
assert.True(t, res.Failed)
assert.True(t, p.GetCAPool().IsBlocklisted(fp))
assert.True(t, p.GetCAPool().IsBlocklisted(otherFp))
}
+1 -2
View File
@@ -67,8 +67,7 @@ func NewPunchyFromConfig(l *slog.Logger, c *config.C, punchConn udp.Conn) *Punch
}
p.reload(c, true)
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("stats.lighthouse_metrics")
c.RegisterReloadCallback(func(c *config.C) {
p.reload(c, false)
})
+6 -16
View File
@@ -76,7 +76,7 @@ punchy:
punch: true
delay: 10m
respond: true
`).Err)
`))
p.reload(c, false)
assert.True(t, p.punch.Load())
assert.Equal(t, newDelay, time.Duration(p.delay.Load()))
@@ -170,7 +170,7 @@ func TestPunchy_LogFormat_ReloadPunch(t *testing.T) {
NewPunchyFromConfig(l, c, nil)
hook.entries = nil
require.NoError(t, c.ReloadConfigString(`punchy: {punch: true}`).Err)
require.NoError(t, c.ReloadConfigString(`punchy: {punch: true}`))
entry := findEntry(t, hook.entries, "punchy.punch changed")
assert.Equal(t, slog.LevelInfo, entry.Level)
@@ -184,7 +184,7 @@ func TestPunchy_LogFormat_ReloadRespond(t *testing.T) {
NewPunchyFromConfig(l, c, nil)
hook.entries = nil
require.NoError(t, c.ReloadConfigString(`punchy: {respond: true}`).Err)
require.NoError(t, c.ReloadConfigString(`punchy: {respond: true}`))
entry := findEntry(t, hook.entries, "punchy.respond changed")
assert.Equal(t, slog.LevelInfo, entry.Level)
@@ -198,7 +198,7 @@ func TestPunchy_LogFormat_ReloadDelay(t *testing.T) {
NewPunchyFromConfig(l, c, nil)
hook.entries = nil
require.NoError(t, c.ReloadConfigString(`punchy: {delay: 10s}`).Err)
require.NoError(t, c.ReloadConfigString(`punchy: {delay: 10s}`))
entry := findEntry(t, hook.entries, "punchy.delay changed")
assert.Equal(t, slog.LevelInfo, entry.Level)
@@ -212,7 +212,7 @@ func TestPunchy_LogFormat_ReloadTargetAllRemotes(t *testing.T) {
NewPunchyFromConfig(l, c, nil)
hook.entries = nil
require.NoError(t, c.ReloadConfigString(`punchy: {target_all_remotes: true}`).Err)
require.NoError(t, c.ReloadConfigString(`punchy: {target_all_remotes: true}`))
entry := findEntry(t, hook.entries, "punchy.target_all_remotes changed")
assert.Equal(t, slog.LevelInfo, entry.Level)
@@ -226,19 +226,9 @@ func TestPunchy_LogFormat_ReloadRespondDelay(t *testing.T) {
NewPunchyFromConfig(l, c, nil)
hook.entries = nil
require.NoError(t, c.ReloadConfigString(`punchy: {respond_delay: 15s}`).Err)
require.NoError(t, c.ReloadConfigString(`punchy: {respond_delay: 15s}`))
entry := findEntry(t, hook.entries, "punchy.respond_delay changed")
assert.Equal(t, slog.LevelInfo, entry.Level)
assert.Equal(t, map[string]any{"respond_delay": 15 * time.Second}, entry.Attrs)
}
func TestPunchyReloadRestartRequired(t *testing.T) {
c := config.NewC(test.NewLogger())
require.NoError(t, c.LoadString("stats:\n lighthouse_metrics: false\n"))
NewPunchyFromConfig(test.NewLogger(), c, nil)
res := c.ReloadConfigString("stats:\n lighthouse_metrics: true\n")
require.NoError(t, res.Err)
assert.True(t, res.RestartRequired)
}
+1 -2
View File
@@ -28,11 +28,10 @@ func NewRelayManager(ctx context.Context, l *slog.Logger, hostmap *HostMap, c *c
hostmap: hostmap,
}
rm.reload(c, true)
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
c.RegisterReloadCallback(func(c *config.C) {
err := rm.reload(c, false)
if err != nil {
rm.l.Error("Failed to reload relay_manager", "error", err)
r.Failed()
}
})
return rm
+10 -25
View File
@@ -1,8 +1,8 @@
package service
import (
"io"
"net"
"sync"
)
type tcpListener struct {
@@ -10,38 +10,23 @@ type tcpListener struct {
s *Service
addr *net.TCPAddr
accept chan net.Conn
// closed is closed instead of accept so a handler blocked handing off a
// connection can't send on a closed channel.
closed chan struct{}
closeOnce sync.Once
}
func (l *tcpListener) Accept() (net.Conn, error) {
// select picks randomly among ready cases, so without this a handler still
// waiting to hand off could win over closed after Close has returned.
select {
case <-l.closed:
return nil, net.ErrClosed
default:
}
select {
case conn := <-l.accept:
return conn, nil
case <-l.closed:
return nil, net.ErrClosed
conn, ok := <-l.accept
if !ok {
return nil, io.EOF
}
return conn, nil
}
func (l *tcpListener) Close() error {
l.closeOnce.Do(func() {
l.s.mu.Lock()
delete(l.s.mu.listeners, l.port)
l.s.mu.Unlock()
l.s.mu.Lock()
defer l.s.mu.Unlock()
delete(l.s.mu.listeners, uint16(l.addr.Port))
close(l.accept)
close(l.closed)
})
return nil
}
+3 -9
View File
@@ -231,7 +231,6 @@ func (s *Service) Listen(network, address string) (net.Listener, error) {
s: s,
addr: addr,
accept: make(chan net.Conn),
closed: make(chan struct{}),
}
s.mu.Lock()
@@ -258,8 +257,9 @@ func (s *Service) tcpHandler(r *tcp.ForwarderRequest) {
endpointID := r.ID()
s.mu.Lock()
defer s.mu.Unlock()
l, ok := s.mu.listeners[endpointID.LocalPort]
s.mu.Unlock()
if !ok {
r.Complete(true)
return
@@ -275,12 +275,6 @@ func (s *Service) tcpHandler(r *tcp.ForwarderRequest) {
r.Complete(false)
ep.SocketOptions().SetKeepAlive(true)
// The handoff blocks until Accept is called, so it must not hold s.mu or a
// listener nobody accepts from stalls every other port.
conn := gonet.NewTCPConn(&wq, ep)
select {
case l.accept <- conn:
case <-l.closed:
_ = conn.Close()
}
l.accept <- conn
}
-139
View File
@@ -188,142 +188,3 @@ func TestService(t *testing.T) {
t.Fatal(err)
}
}
// A listener that is never accepted from must not stall connections to other
// ports, and closing it must not block.
func TestServiceUnacceptedListener(t *testing.T) {
lighthousePort := ephemeralUDPPort(t)
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
a := newSimpleService(ca, caKey, "a", netip.MustParseAddr("10.0.0.1"), m{
"static_host_map": m{},
"lighthouse": m{
"am_lighthouse": true,
},
"listen": m{
"host": "0.0.0.0",
"port": lighthousePort,
},
})
t.Cleanup(func() { _ = a.Close() })
b := newSimpleService(ca, caKey, "b", netip.MustParseAddr("10.0.0.2"), m{
"static_host_map": m{
"10.0.0.1": []string{fmt.Sprintf("127.0.0.1:%d", lighthousePort)},
},
"lighthouse": m{
"hosts": []string{"10.0.0.1"},
"interval": 1,
},
})
t.Cleanup(func() { _ = b.Close() })
idle, err := a.Listen("tcp", ":1234")
if err != nil {
t.Fatal(err)
}
active, err := a.Listen("tcp", ":1235")
if err != nil {
t.Fatal(err)
}
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
defer cancel()
idleConn, err := b.DialContext(ctx, "tcp", "10.0.0.1:1234")
if err != nil {
t.Fatal(err)
}
defer idleConn.Close()
accepted := make(chan error, 1)
go func() {
conn, err := active.Accept()
if err == nil {
err = conn.Close()
}
accepted <- err
}()
ctx, cancel = context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
activeConn, err := b.DialContext(ctx, "tcp", "10.0.0.1:1235")
if err != nil {
t.Fatalf("dial to accepted port stalled behind idle listener: %v", err)
}
defer activeConn.Close()
select {
case err := <-accepted:
if err != nil {
t.Fatal(err)
}
case <-time.After(5 * time.Second):
t.Fatal("accept stalled behind idle listener")
}
closed := make(chan error, 1)
go func() { closed <- idle.Close() }()
select {
case err := <-closed:
if err != nil {
t.Fatal(err)
}
case <-time.After(5 * time.Second):
t.Fatal("closing idle listener blocked")
}
if _, err := idle.Accept(); !errors.Is(err, net.ErrClosed) {
t.Fatalf("expected net.ErrClosed from closed listener, got %v", err)
}
if err := idle.Close(); err != nil {
t.Fatalf("second close: %v", err)
}
}
// Accept must report net.ErrClosed after Close even while a handler is still
// trying to hand off a connection.
func TestListenerAcceptAfterClose(t *testing.T) {
s := &Service{}
s.mu.listeners = map[uint16]*tcpListener{}
l := &tcpListener{
port: 1234,
s: s,
accept: make(chan net.Conn),
closed: make(chan struct{}),
}
s.mu.listeners[l.port] = l
if err := l.Close(); err != nil {
t.Fatal(err)
}
// Keep a send pending so every Accept has a connection ready alongside closed.
stop := make(chan struct{})
done := make(chan struct{})
go func() {
defer close(done)
for {
server, client := net.Pipe()
_ = client.Close()
select {
case l.accept <- server:
case <-stop:
_ = server.Close()
return
}
}
}()
defer func() {
close(stop)
<-done
}()
for range 100 {
time.Sleep(time.Millisecond)
conn, err := l.Accept()
if conn != nil {
_ = conn.Close()
}
if !errors.Is(err, net.ErrClosed) {
t.Fatalf("Accept after Close: got err %v, want net.ErrClosed", err)
}
}
}
+180 -28
View File
@@ -11,8 +11,11 @@ import (
"net"
"net/netip"
"os"
"slices"
"path/filepath"
"runtime"
"runtime/pprof"
"sort"
"strconv"
"strings"
"github.com/slackhq/nebula/config"
@@ -55,12 +58,12 @@ type sshDeviceInfoFlags struct {
}
func wireSSHReload(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) {
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
c.RegisterReloadCallback(func(c *config.C) {
if c.GetBool("sshd.enabled", false) {
// Restarting the server drops every open session, the one that asked for this reload included. Only restart
// when it isn't running or its config changed. The host key file can change under the same config, new
// handshakes use the new key without a restart
if ssh.Running() && !slices.ContainsFunc(sshdServerKeys, c.HasChanged) {
if ssh.Running() && !c.HasChanged("sshd") {
key, err := loadSSHHostKey(c)
if err == nil {
err = ssh.SetHostKey(key)
@@ -68,15 +71,13 @@ func wireSSHReload(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) {
if err != nil {
l.Error("Failed to reconfigure the sshd", "error", err)
ssh.Stop()
r.Failed()
}
return
}
sshRun, err := configSSH(l, ssh, c, r)
sshRun, err := configSSH(l, ssh, c)
if err != nil {
l.Error("Failed to reconfigure the sshd", "error", err)
ssh.Stop()
r.Failed()
}
if sshRun != nil {
go sshRun()
@@ -87,9 +88,6 @@ func wireSSHReload(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) {
})
}
// sshdServerKeys are what configSSH reads
var sshdServerKeys = []string{"sshd.enabled", "sshd.listen", "sshd.host_key", "sshd.trusted_cas", "sshd.authorized_users"}
// loadSSHHostKey returns sshd.host_key, read from its file when it names one.
func loadSSHHostKey(c *config.C) ([]byte, error) {
hostKeyPathOrKey := c.GetString("sshd.host_key", "")
@@ -110,8 +108,7 @@ func loadSSHHostKey(c *config.C) ([]byte, error) {
// updates the passed-in SSHServer. On success, it returns a function
// that callers may invoke to run the configured ssh server. On
// failure, it returns nil, error.
// r is nil at startup, entries that are skipped with a warning fail it on a reload
func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C, r *config.Reload) (func(), error) {
func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C) (func(), error) {
listen := c.GetString("sshd.listen", "")
if listen == "" {
return nil, fmt.Errorf("sshd.listen must be provided")
@@ -144,7 +141,6 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C, r *config.Reloa
err := ssh.AddTrustedCA(caAuthorizedKey)
if err != nil {
l.Warn("SSH CA had an error, ignoring", "error", err, "sshCA", caAuthorizedKey)
r.Failed()
continue
}
}
@@ -156,14 +152,12 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C, r *config.Reloa
kDef, ok := rk.(map[string]any)
if !ok {
l.Warn("Authorized user had an error, ignoring", "sshKeyConfig", rk)
r.Failed()
continue
}
user, ok := kDef["user"].(string)
if !ok {
l.Warn("Authorized user is missing the user field", "sshKeyConfig", rk)
r.Failed()
continue
}
@@ -177,7 +171,6 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C, r *config.Reloa
"sshKeyConfig", rk,
"sshKey", v,
)
r.Failed()
continue
}
@@ -189,7 +182,6 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C, r *config.Reloa
"sshKeyConfig", rk,
"sshKey", subK,
)
r.Failed()
continue
}
@@ -199,14 +191,12 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C, r *config.Reloa
"error", err,
"sshKeyConfig", sk,
)
r.Failed()
continue
}
}
default:
l.Warn("Authorized user is missing the keys field or was not understood", "sshKeyConfig", rk)
r.Failed()
}
}
} else {
@@ -229,6 +219,12 @@ func configSSH(l *slog.Logger, ssh *sshd.SSHServer, c *config.C, r *config.Reloa
}
func attachCommands(l *slog.Logger, c *config.C, ssh *sshd.SSHServer, f *Interface) {
// sandboxDir defaults to a dir in temp. The intention is that end user will
// create this dir as needed. Overriding this config value to "" allows
// writing to anywhere in the system.
defaultDir := filepath.Join(os.TempDir(), "nebula-debug")
sandboxDir := c.GetString("sshd.sandbox_dir", defaultDir)
ssh.RegisterCommand(&sshd.Command{
Name: "list-hostmap",
ShortDescription: "List all known previously connected hosts",
@@ -280,7 +276,46 @@ func attachCommands(l *slog.Logger, c *config.C, ssh *sshd.SSHServer, f *Interfa
Name: "reload",
ShortDescription: "Reloads configuration from disk, same as sending HUP to the process",
Callback: func(fs any, a []string, w sshd.StringWriter) error {
return sshReload(l, c, w)
return sshReload(c, w)
},
})
ssh.RegisterCommand(&sshd.Command{
Name: "start-cpu-profile",
ShortDescription: "Starts a cpu profile and write output to the provided file, ex: `cpu-profile.pb.gz`",
Callback: func(fs any, a []string, w sshd.StringWriter) error {
return sshStartCpuProfile(sandboxDir, fs, a, w)
},
})
ssh.RegisterCommand(&sshd.Command{
Name: "stop-cpu-profile",
ShortDescription: "Stops a cpu profile and writes output to the previously provided file",
Callback: func(fs any, a []string, w sshd.StringWriter) error {
pprof.StopCPUProfile()
return w.WriteLine("If a CPU profile was running it is now stopped")
},
})
ssh.RegisterCommand(&sshd.Command{
Name: "save-heap-profile",
ShortDescription: "Saves a heap profile to the provided path, ex: `heap-profile.pb.gz`",
Callback: func(fs any, a []string, w sshd.StringWriter) error {
return sshGetHeapProfile(sandboxDir, fs, a, w)
},
})
ssh.RegisterCommand(&sshd.Command{
Name: "mutex-profile-fraction",
ShortDescription: "Gets or sets runtime.SetMutexProfileFraction",
Callback: sshMutexProfileFraction,
})
ssh.RegisterCommand(&sshd.Command{
Name: "save-mutex-profile",
ShortDescription: "Saves a mutex profile to the provided path, ex: `mutex-profile.pb.gz`",
Callback: func(fs any, a []string, w sshd.StringWriter) error {
return sshGetMutexProfile(sandboxDir, fs, a, w)
},
})
@@ -514,6 +549,58 @@ func sshListLighthouseMap(lightHouse *LightHouse, a any, w sshd.StringWriter) er
return nil
}
// sshSanitizeFilePath validates that the given file path is within the sandbox directory.
// If sandboxDir is empty, the path is returned as-is for backwards compatibility.
func sshSanitizeFilePath(sandboxDir, filePath string) (string, error) {
if sandboxDir == "" {
return filePath, nil
}
// Clean and resolve the path relative to the sandbox directory
if !filepath.IsAbs(filePath) {
filePath = filepath.Join(sandboxDir, filePath)
}
cleaned := filepath.Clean(filePath)
// Ensure the resolved path is within the sandbox directory
cleanedSandbox := filepath.Clean(sandboxDir)
if cleaned == cleanedSandbox {
return "", fmt.Errorf("path %q resolves to the sandbox directory itself %q", filePath, sandboxDir)
}
if !strings.HasPrefix(cleaned, cleanedSandbox+string(filepath.Separator)) {
return "", fmt.Errorf("path %q is outside the sandbox directory %q", filePath, sandboxDir)
}
return cleaned, nil
}
func sshStartCpuProfile(sandboxDir string, fs any, a []string, w sshd.StringWriter) error {
if len(a) == 0 {
err := w.WriteLine("No path to write profile provided")
return err
}
filePath, err := sshSanitizeFilePath(sandboxDir, a[0])
if err != nil {
return w.WriteLine(err.Error())
}
file, err := os.Create(filePath)
if err != nil {
err = w.WriteLine(fmt.Sprintf("Unable to create profile file: %s", err))
return err
}
err = pprof.StartCPUProfile(file)
if err != nil {
err = w.WriteLine(fmt.Sprintf("Unable to start cpu profile: %s", err))
return err
}
err = w.WriteLine(fmt.Sprintf("Started cpu profile, issue stop-cpu-profile to write the output to %s", a))
return err
}
func sshVersion(ifce *Interface, fs any, a []string, w sshd.StringWriter) error {
return w.WriteLine(fmt.Sprintf("%s", ifce.version))
}
@@ -666,6 +753,76 @@ func sshChangeRemote(ifce *Interface, fs any, a []string, w sshd.StringWriter) e
return w.WriteLine("Changed")
}
func sshGetHeapProfile(sandboxDir string, fs any, a []string, w sshd.StringWriter) error {
if len(a) == 0 {
return w.WriteLine("No path to write profile provided")
}
filePath, err := sshSanitizeFilePath(sandboxDir, a[0])
if err != nil {
return w.WriteLine(err.Error())
}
file, err := os.Create(filePath)
if err != nil {
err = w.WriteLine(fmt.Sprintf("Unable to create profile file: %s", err))
return err
}
err = pprof.WriteHeapProfile(file)
if err != nil {
err = w.WriteLine(fmt.Sprintf("Unable to write profile: %s", err))
return err
}
err = w.WriteLine(fmt.Sprintf("Mem profile created at %s", a))
return err
}
func sshMutexProfileFraction(fs any, a []string, w sshd.StringWriter) error {
if len(a) == 0 {
rate := runtime.SetMutexProfileFraction(-1)
return w.WriteLine(fmt.Sprintf("Current value: %d", rate))
}
newRate, err := strconv.Atoi(a[0])
if err != nil {
return w.WriteLine(fmt.Sprintf("Invalid argument: %s", a[0]))
}
oldRate := runtime.SetMutexProfileFraction(newRate)
return w.WriteLine(fmt.Sprintf("New value: %d. Old value: %d", newRate, oldRate))
}
func sshGetMutexProfile(sandboxDir string, fs any, a []string, w sshd.StringWriter) error {
if len(a) == 0 {
return w.WriteLine("No path to write profile provided")
}
filePath, err := sshSanitizeFilePath(sandboxDir, a[0])
if err != nil {
return w.WriteLine(err.Error())
}
file, err := os.Create(filePath)
if err != nil {
return w.WriteLine(fmt.Sprintf("Unable to create profile file: %s", err))
}
defer file.Close()
mutexProfile := pprof.Lookup("mutex")
if mutexProfile == nil {
return w.WriteLine("Unable to get pprof.Lookup(\"mutex\")")
}
err = mutexProfile.WriteTo(file, 0)
if err != nil {
return w.WriteLine(fmt.Sprintf("Unable to write profile: %s", err))
}
return w.WriteLine(fmt.Sprintf("Mutex profile created at %s", a))
}
func sshLogLevel(l *slog.Logger, fs any, a []string, w sshd.StringWriter) error {
ctrl, ok := l.Handler().(interface {
GetLevel() slog.Level
@@ -918,13 +1075,8 @@ func sshDeviceInfo(ifce *Interface, fs any, w sshd.StringWriter) error {
}
}
// sshReload reloads the config and writes the result to the client. It reloads even if the client has gone away
func sshReload(l *slog.Logger, c *config.C, w sshd.StringWriter) error {
writeErr := w.WriteLine("Reloading config")
res := c.ReloadConfig()
res.Log(l)
if err := w.WriteLine(res.String()); writeErr == nil {
writeErr = err
}
return writeErr
func sshReload(c *config.C, w sshd.StringWriter) error {
err := w.WriteLine("Reloading config")
c.ReloadConfig()
return err
}
-83
View File
@@ -1,83 +0,0 @@
package nebula
import (
"errors"
"io"
"os"
"path/filepath"
"testing"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
type lineWriter struct {
lines []string
err error
}
func (w *lineWriter) WriteLine(s string) error {
w.lines = append(w.lines, s)
return w.err
}
func (w *lineWriter) Write(s string) error { return w.WriteLine(s) }
func (w *lineWriter) WriteBytes(b []byte) error { return w.WriteLine(string(b)) }
func (w *lineWriter) GetWriter() io.Writer { return io.Discard }
func TestSSHReloadReportsTheResult(t *testing.T) {
dir := t.TempDir()
write := func(body string) {
require.NoError(t, os.WriteFile(filepath.Join(dir, "config.yml"), []byte(body), 0o600))
}
write("a: 1\nb: 1")
l := test.NewLogger()
c := config.NewC(l)
require.NoError(t, c.Load(dir))
fail := false
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("b")
if fail {
r.Failed()
}
})
reload := func() []string {
w := &lineWriter{}
require.NoError(t, sshReload(l, c, w))
return w.lines
}
write("a: 2\nb: 1")
assert.Equal(t, []string{"Reloading config", "Config reload complete"}, reload())
fail = true
write("a: 3\nb: 1")
assert.Equal(t, []string{"Reloading config", "Config reload completed with errors, review the logs"}, reload())
fail = false
write("a: 3\nb: 2")
assert.Equal(t, []string{"Reloading config", "Config reload was completed but requires a restart to fully apply, keys [b]"}, reload())
write("a: [")
lines := reload()
require.Len(t, lines, 2)
assert.Contains(t, lines[1], "Config reload failed, the new config did not load")
assert.Contains(t, lines[1], dir, "names the config that did not load")
}
// A client that went away still gets the reload it asked for
func TestSSHReloadReloadsWhenTheClientIsGone(t *testing.T) {
dir := t.TempDir()
require.NoError(t, os.WriteFile(filepath.Join(dir, "config.yml"), []byte("a: 1"), 0o600))
l := test.NewLogger()
c := config.NewC(l)
require.NoError(t, c.Load(dir))
reloaded := false
c.RegisterReloadCallback(func(*config.C, *config.Reload) { reloaded = true })
gone := errors.New("client is gone")
require.ErrorIs(t, sshReload(l, c, &lineWriter{err: gone}), gone)
assert.True(t, reloaded)
}
+16 -60
View File
@@ -26,15 +26,13 @@ type sshdReloadHarness struct {
server *sshd.SSHServer
keyFile string
signer ssh.Signer
listen string
users []string
extra string
}
func newSSHDReloadHarness(t *testing.T) *sshdReloadHarness {
t.Helper()
l := test.NewLogger()
h := &sshdReloadHarness{keyFile: filepath.Join(t.TempDir(), "host_key"), listen: "127.0.0.1:0", users: []string{"test"}}
h := &sshdReloadHarness{keyFile: filepath.Join(t.TempDir(), "host_key")}
h.writeHostKey(t, newEd25519Key(t))
_, userKey, err := ed25519.GenerateKey(rand.Reader)
@@ -47,7 +45,7 @@ func newSSHDReloadHarness(t *testing.T) *sshdReloadHarness {
h.server, err = sshd.NewSSHServer(t.Context(), l)
require.NoError(t, err)
wireSSHReload(l, h.server, h.c)
run, err := configSSH(l, h.server, h.c, nil)
run, err := configSSH(l, h.server, h.c)
require.NoError(t, err)
go run()
t.Cleanup(h.server.Stop)
@@ -73,12 +71,8 @@ func (h *sshdReloadHarness) writeHostKey(t *testing.T, key crypto.Signer) ssh.Pu
}
func (h *sshdReloadHarness) config() string {
users := ""
for _, u := range h.users {
users += fmt.Sprintf(" - user: %s\n keys: [%q]\n", u, string(ssh.MarshalAuthorizedKey(h.signer.PublicKey())))
}
return fmt.Sprintf("sshd:\n enabled: true\n listen: %s\n host_key: %s\n authorized_users:\n%s%s",
h.listen, h.keyFile, users, h.extra)
return fmt.Sprintf("sshd:\n enabled: true\n listen: 127.0.0.1:0\n host_key: %s\n authorized_users:\n - user: test\n keys: [%q]\n%s",
h.keyFile, string(ssh.MarshalAuthorizedKey(h.signer.PublicKey())), h.extra)
}
// dial connects to wherever the server listens now, a restart on :0 moves it. hostKeyAlgorithms limits which host keys
@@ -136,33 +130,19 @@ func TestSSHDReload_UnchangedKeepsSessions(t *testing.T) {
h := newSSHDReloadHarness(t)
client, _ := h.connect(t)
require.NoError(t, h.c.ReloadConfigString(h.config()+"punchy:\n punch: true\n").Err)
require.NoError(t, h.c.ReloadConfigString(h.config()+"punchy:\n punch: true\n"))
assert.False(t, dropped(client, 500*time.Millisecond), "an unchanged sshd was restarted")
}
// Every key the server reads restarts it when it changes
func TestSSHDReload_ChangedConfigRestarts(t *testing.T) {
cases := map[string]func(t *testing.T, h *sshdReloadHarness){
"listen": func(t *testing.T, h *sshdReloadHarness) { h.listen = "localhost:0" },
"authorized_users": func(t *testing.T, h *sshdReloadHarness) { h.users = append(h.users, "other") },
"trusted_cas": func(t *testing.T, h *sshdReloadHarness) { h.extra = " trusted_cas: []\n" },
"host_key": func(t *testing.T, h *sshdReloadHarness) {
h.keyFile = filepath.Join(t.TempDir(), "other_host_key")
h.writeHostKey(t, newEd25519Key(t))
},
}
for name, change := range cases {
t.Run(name, func(t *testing.T) {
h := newSSHDReloadHarness(t)
client, _ := h.connect(t)
h := newSSHDReloadHarness(t)
client, _ := h.connect(t)
change(t, h)
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
assert.True(t, dropped(client, 5*time.Second), "a changed sshd config was not applied")
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
h.connect(t)
})
}
h.extra = " trusted_cas: []\n"
require.NoError(t, h.c.ReloadConfigString(h.config()))
assert.True(t, dropped(client, 5*time.Second), "a changed sshd config was not applied")
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
h.connect(t)
}
// The config can stay the same while the host key file it names changes. New connections get the new key, open
@@ -172,7 +152,7 @@ func TestSSHDReload_ChangedHostKeyFile(t *testing.T) {
client, _ := h.connect(t)
want := h.writeHostKey(t, newEd25519Key(t))
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
require.NoError(t, h.c.ReloadConfigString(h.config()))
_, got := h.connect(t)
assert.Equal(t, want.Marshal(), got.Marshal(), "a new host key was not applied")
assert.False(t, dropped(client, 500*time.Millisecond), "a new host key restarted sshd")
@@ -186,7 +166,7 @@ func TestSSHDReload_HostKeyAlgorithmChange(t *testing.T) {
rsaKey, err := rsa.GenerateKey(rand.Reader, 2048)
require.NoError(t, err)
want := h.writeHostKey(t, rsaKey)
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
require.NoError(t, h.c.ReloadConfigString(h.config()))
_, got := h.connect(t)
assert.Equal(t, want.Marshal(), got.Marshal())
@@ -200,7 +180,7 @@ func TestSSHDReload_NotRunningRestarts(t *testing.T) {
h.server.Stop()
require.Eventually(t, func() bool { return !h.server.Running() }, 5*time.Second, 10*time.Millisecond)
require.NoError(t, h.c.ReloadConfigString(h.config()).Err)
require.NoError(t, h.c.ReloadConfigString(h.config()))
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
h.connect(t)
}
@@ -211,30 +191,6 @@ func TestSSHDReload_BadHostKeyFileStops(t *testing.T) {
h.connect(t)
require.NoError(t, os.WriteFile(h.keyFile, []byte("not a key"), 0o600))
assert.True(t, h.c.ReloadConfigString(h.config()).Failed)
require.NoError(t, h.c.ReloadConfigString(h.config()))
require.Eventually(t, func() bool { return !h.server.Running() }, 5*time.Second, 10*time.Millisecond)
}
// A trusted CA or authorized user that is skipped with a warning fails the reload, the valid ones are still used
func TestSSHDReload_SkippedEntriesFail(t *testing.T) {
cases := map[string]string{
"bad trusted ca": " trusted_cas: [nope]\n",
"user entry not a map": " - nope\n",
"user missing": " - keys: [nope]\n",
"bad key": " - user: other\n keys: nope\n",
"key in a list not a string": " - user: other\n keys: [5]\n",
"bad key in a list": " - user: other\n keys: [nope]\n",
"keys missing": " - user: other\n",
}
for name, extra := range cases {
t.Run(name, func(t *testing.T) {
h := newSSHDReloadHarness(t)
h.extra = extra
res := h.c.ReloadConfigString(h.config())
require.NoError(t, res.Err)
assert.True(t, res.Failed)
require.Eventually(t, h.server.Running, 5*time.Second, 10*time.Millisecond)
h.connect(t)
})
}
}
+1 -2
View File
@@ -99,10 +99,9 @@ func newStatsServerFromConfig(ctx context.Context, l *slog.Logger, c *config.C,
emitStats: emitStats,
}
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
c.RegisterReloadCallback(func(c *config.C) {
if err := s.reload(c, false); err != nil {
s.l.Error("Failed to reload stats from config", "error", err)
r.Failed()
}
})
+2 -5
View File
@@ -147,10 +147,7 @@ func (tw *TimerWheel[T]) Purge() (T, bool) {
tw.expired.Tail = nil
}
// Clear out the items references, a cached item must not keep its value alive
v := ti.Item
var zero T
ti.Item = zero
// Clear out the items references
ti.Next = nil
// Maybe cache it for later
@@ -160,7 +157,7 @@ func (tw *TimerWheel[T]) Purge() (T, bool) {
tw.itemsCached++
}
return v, true
return ti.Item, true
}
// findWheel find the next position in the wheel for the provided timeout given the current tick
+1 -3
View File
@@ -7,7 +7,6 @@ import (
"github.com/slackhq/nebula/firewall"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestNewTimerWheel(t *testing.T) {
@@ -151,8 +150,7 @@ func TestTimerWheel_Purge(t *testing.T) {
assert.Equal(t, 4, tw.itemsCached)
ci := tw.itemCache
for range 4 {
require.NotNil(t, ci)
assert.Zero(t, ci.Item)
assert.NotNil(t, ci)
ci = ci.Next
}
assert.Nil(t, ci)
+2 -3
View File
@@ -43,8 +43,7 @@ type Conn interface {
// 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.
WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error)
// ReloadConfig applies the listen settings that can change, r is nil at startup
ReloadConfig(c *config.C, r *config.Reload)
ReloadConfig(c *config.C)
SupportsMultipleReaders() bool
Close() error
}
@@ -69,7 +68,7 @@ func (NoopConn) WriteTo(_ []byte, _ netip.AddrPort) error {
func (NoopConn) WriteBatch(bufs [][]byte, _ []netip.AddrPort) (int, error) {
return len(bufs), nil
}
func (NoopConn) ReloadConfig(_ *config.C, _ *config.Reload) {
func (NoopConn) ReloadConfig(_ *config.C) {
return
}
func (NoopConn) Close() error {
-6
View File
@@ -24,12 +24,6 @@ type NetworkChangeMonitor struct {
// NewNetworkChangeMonitor builds a monitor for local network changes. The returned monitor is always usable: Start
// is safe to call unconditionally, it no-ops when disabled or on a platform that does not need it.
func NewNetworkChangeMonitor(ctx context.Context, l *slog.Logger, c *config.C) *NetworkChangeMonitor {
if watchesNetworkChanges {
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
r.RestartRequiredIfChanged("listen.rebind_on_network_change")
})
}
return &NetworkChangeMonitor{
l: l,
ctx: ctx,
-3
View File
@@ -13,9 +13,6 @@ import (
"golang.org/x/sys/unix"
)
// watchesNetworkChanges is true where Start does anything
const watchesNetworkChanges = true
const (
// netChangeSettleWindow is how long we keep swallowing routing messages after the first interesting one. A
// single network change is never a single message, it is a burst: the link drops, addresses go away, new ones
-3
View File
@@ -7,9 +7,6 @@ import (
"log/slog"
)
// watchesNetworkChanges is true where Start does anything
const watchesNetworkChanges = false
// watchNetworkChanges is a no-op outside of darwin.
//
// Darwin is the platform that scopes a udp socket to the interface it came up on, so it is the platform whose socket
-16
View File
@@ -37,19 +37,3 @@ func TestNetworkChangeMonitorNilRebindIsANoOp(t *testing.T) {
m := newMonitor(t, context.Background(), "listen:\n rebind_on_network_change: true\n")
m.Start(nil)
}
// The monitor only reads listen.rebind_on_network_change when it is made
func TestNetworkChangeMonitorRestartKey(t *testing.T) {
l := test.NewLogger()
c := config.NewC(l)
require.NoError(t, c.LoadString("listen:\n rebind_on_network_change: true\n"))
NewNetworkChangeMonitor(context.Background(), l, c)
res := c.ReloadConfigString("listen:\n rebind_on_network_change: false\n")
require.NoError(t, res.Err)
if watchesNetworkChanges {
assert.Equal(t, []string{"listen.rebind_on_network_change"}, res.RestartKeys)
} else {
assert.Empty(t, res.RestartKeys, "the setting does nothing here")
}
}
+2 -4
View File
@@ -26,9 +26,7 @@ type bypassConn struct {
session *wfp.Session
}
func (b *bypassConn) ReloadConfig(c *config.C, r *config.Reload) {
// Only read on the first call, at startup
r.RestartRequiredIfChanged("listen.windows_bypass_wdf")
func (b *bypassConn) ReloadConfig(c *config.C) {
b.installOnce.Do(func() {
if !c.GetBool("listen.windows_bypass_wdf", true) {
return
@@ -47,7 +45,7 @@ func (b *bypassConn) ReloadConfig(c *config.C, r *config.Reload) {
"port", addr.Port())
b.session = s
})
b.Conn.ReloadConfig(c, r)
b.Conn.ReloadConfig(c)
}
func (b *bypassConn) Close() error {
+1 -1
View File
@@ -171,7 +171,7 @@ func (u *StdConn) LocalAddr() (netip.AddrPort, error) {
}
}
func (u *StdConn) ReloadConfig(c *config.C, r *config.Reload) {
func (u *StdConn) ReloadConfig(c *config.C) {
// TODO
}
+1 -1
View File
@@ -73,7 +73,7 @@ func (u *GenericConn) LocalAddr() (netip.AddrPort, error) {
}
}
func (u *GenericConn) ReloadConfig(c *config.C, r *config.Reload) {
func (u *GenericConn) ReloadConfig(c *config.C) {
}
+1 -4
View File
@@ -392,7 +392,7 @@ func writeSockaddr(buf []byte, addr netip.AddrPort, isV4 bool) (int, error) {
return unix.SizeofSockaddrInet6, nil
}
func (u *StdConn) ReloadConfig(c *config.C, r *config.Reload) {
func (u *StdConn) ReloadConfig(c *config.C) {
b := c.GetInt("listen.read_buffer", 0)
if b > 0 {
if err := u.SetRecvBuffer(b); err == nil {
@@ -403,7 +403,6 @@ func (u *StdConn) ReloadConfig(c *config.C, r *config.Reload) {
}
} else {
u.l.Error("Failed to set listen.read_buffer", "error", err)
r.Failed()
}
}
@@ -417,7 +416,6 @@ func (u *StdConn) ReloadConfig(c *config.C, r *config.Reload) {
}
} else {
u.l.Error("Failed to set listen.write_buffer", "error", err)
r.Failed()
}
}
@@ -432,7 +430,6 @@ func (u *StdConn) ReloadConfig(c *config.C, r *config.Reload) {
}
} else {
u.l.Error("Failed to set listen.so_mark", "error", err)
r.Failed()
}
}
}
-31
View File
@@ -1,31 +0,0 @@
//go:build linux && !android && !e2e_testing
package udp
import (
"net/netip"
"os"
"testing"
"github.com/slackhq/nebula/config"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// A setting the kernel refuses fails the reload
func TestReloadConfig_RefusedSettingFailsTheReload(t *testing.T) {
if os.Geteuid() == 0 {
t.Skip("root may set listen.so_mark, run as an unprivileged user")
}
conn, err := NewListener(testLogger(), Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0"), Batch: 1})
require.NoError(t, err)
t.Cleanup(func() { _ = conn.Close() })
c := config.NewC(testLogger())
require.NoError(t, c.LoadString("listen:\n port: 0\n"))
c.RegisterReloadCallback(conn.ReloadConfig)
res := c.ReloadConfigString("listen:\n port: 0\n so_mark: 42\n")
require.NoError(t, res.Err)
assert.True(t, res.Failed)
}
+1 -1
View File
@@ -351,7 +351,7 @@ func (u *RIOConn) Rebind() error {
return nil
}
func (u *RIOConn) ReloadConfig(*config.C, *config.Reload) {}
func (u *RIOConn) ReloadConfig(*config.C) {}
func (u *RIOConn) Close() error {
if !u.isOpen.CompareAndSwap(true, false) {
+1 -1
View File
@@ -197,7 +197,7 @@ func (u *TesterConn) ListenOut(r EncReader, flush func()) error {
}
}
func (u *TesterConn) ReloadConfig(*config.C, *config.Reload) {}
func (u *TesterConn) ReloadConfig(*config.C) {}
func NewUDPStatsEmitter(_ []Conn) func() {
// No UDP stats for non-linux
+74
View File
@@ -0,0 +1,74 @@
//go:build linux && !android && !e2e_testing
package util
import (
"errors"
"fmt"
"os"
"strconv"
"unsafe"
"golang.org/x/sys/unix"
)
// AvoidCPUs removes cpus from the affinity of every thread of the process, for use at startup. New threads inherit
// their parent's mask, so it repeats until a pass finds nothing left to change; a thread that exits meanwhile is
// skipped. Every mask is checked before any is changed. With apply false it only validates, for configuration tests.
// This affects the entire process, including other users of an embedded Nebula.
func AvoidCPUs(cpus []int, apply bool) error {
const capacity = int(unsafe.Sizeof(unix.CPUSet{})) * 8
for _, cpu := range cpus {
if cpu < 0 || cpu >= capacity {
return fmt.Errorf("CPU %d is out of range", cpu)
}
}
if len(cpus) == 0 {
return nil
}
for {
masks, err := avoidingMasks(cpus)
if err != nil || !apply || len(masks) == 0 {
return err
}
for tid, mask := range masks {
if err := unix.SchedSetaffinity(tid, &mask); err != nil && !errors.Is(err, unix.ESRCH) {
return fmt.Errorf("set thread %d affinity: %w", tid, err)
}
}
}
}
// avoidingMasks returns the mask without cpus of every thread whose mask has any of them.
func avoidingMasks(cpus []int) (map[int]unix.CPUSet, error) {
entries, err := os.ReadDir("/proc/self/task")
if err != nil {
return nil, err
}
masks := make(map[int]unix.CPUSet, len(entries))
for _, entry := range entries {
tid, err := strconv.Atoi(entry.Name())
if err != nil {
return nil, err
}
var mask unix.CPUSet
err = unix.SchedGetaffinity(tid, &mask)
if errors.Is(err, unix.ESRCH) {
continue
}
if err != nil {
return nil, fmt.Errorf("read thread %d affinity: %w", tid, err)
}
next := mask
for _, cpu := range cpus {
next.Clear(cpu)
}
if next.Count() == 0 {
return nil, fmt.Errorf("avoid_cpus leaves thread %d with no allowed CPU", tid)
}
if next != mask {
masks[tid] = next
}
}
return masks, nil
}
+97
View File
@@ -0,0 +1,97 @@
//go:build linux && !android && !e2e_testing
package util
import (
"fmt"
"os"
"os/exec"
"runtime"
"strconv"
"sync"
"testing"
"unsafe"
"github.com/stretchr/testify/require"
"golang.org/x/sys/unix"
)
// TestAvoidCPUs changes the affinity of the whole process, so it runs in a child, leaving the test runner untouched.
func TestAvoidCPUs(t *testing.T) {
if os.Getenv("NEBULA_AVOID_CPU_TEST") != "1" {
exe, err := os.Executable()
require.NoError(t, err)
cmd := exec.Command(exe, "-test.run=^TestAvoidCPUs$", "-test.v")
cmd.Env = append(os.Environ(), "NEBULA_AVOID_CPU_TEST=1")
out, err := cmd.CombinedOutput()
require.NoError(t, err, "%s", out)
return
}
allowed, err := AllowedCPUs()
require.NoError(t, err)
if len(allowed) < 2 {
t.Skip("requires at least two allowed CPUs")
}
cpu := allowed[0]
release := make(chan struct{})
var wg sync.WaitGroup
// lockThreads occupies 8 OS threads until release, so the runtime has to start more
lockThreads := func() {
var ready sync.WaitGroup
for range 8 {
ready.Add(1)
wg.Go(func() {
runtime.LockOSThread()
ready.Done()
<-release
})
}
ready.Wait()
}
lockThreads()
require.NoError(t, AvoidCPUs([]int{cpu}, false))
after, err := AllowedCPUs()
require.NoError(t, err)
require.Equal(t, allowed, after, "configuration check must not mutate affinity")
require.Error(t, AvoidCPUs(allowed, true), "must reject an empty mask before applying")
require.NoError(t, AvoidCPUs([]int{cpu, cpu}, true))
requireAvoided(t, cpu, allowed)
// Existing threads stay locked while new ones inherit the restriction
lockThreads()
requireAvoided(t, cpu, allowed)
close(release)
wg.Wait()
}
// requireAvoided checks no thread may run on cpu, and every thread still may on some CPU of allowed only.
func requireAvoided(t *testing.T, cpu int, allowed []int) {
t.Helper()
entries, err := os.ReadDir("/proc/self/task")
require.NoError(t, err)
for _, entry := range entries {
tid, err := strconv.Atoi(entry.Name())
require.NoError(t, err)
var mask unix.CPUSet
err = unix.SchedGetaffinity(tid, &mask)
if err == unix.ESRCH {
continue
}
require.NoError(t, err)
require.False(t, mask.IsSet(cpu), "thread %d", tid)
require.Positive(t, mask.Count())
for id := range len(mask) * 64 {
if mask.IsSet(id) {
require.Contains(t, allowed, id, "must not widen the inherited mask")
}
}
}
}
// TestAvoidCPUsRange checks the bounds of unix.CPUSet, whose words are 32 bits wide on 32-bit platforms.
func TestAvoidCPUsRange(t *testing.T) {
capacity := int(unsafe.Sizeof(unix.CPUSet{})) * 8
require.NoError(t, AvoidCPUs([]int{capacity - 1}, false))
require.EqualError(t, AvoidCPUs([]int{capacity}, false), fmt.Sprintf("CPU %d is out of range", capacity))
require.EqualError(t, AvoidCPUs([]int{-1}, false), "CPU -1 is out of range")
}
+8
View File
@@ -0,0 +1,8 @@
//go:build !linux || android || e2e_testing
package util
import "errors"
// AvoidCPUs is unsupported outside Linux: there is no thread affinity API to restrict.
func AvoidCPUs(_ []int, _ bool) error { return errors.ErrUnsupported }