Compare commits

..
18 changed files with 416 additions and 580 deletions

No files matched your search

+3
View File
@@ -7,6 +7,7 @@ import (
"testing"
"time"
"github.com/rcrowley/go-metrics"
"github.com/slackhq/nebula/cert"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/overlay/overlaytest"
@@ -21,6 +22,8 @@ func newTestLighthouse() *LightHouse {
l: test.NewLogger(),
addrMap: map[netip.Addr]*RemoteList{},
queryChan: make(chan netip.Addr, 10),
// Nothing drains queryChan here, so an 11th query is dropped.
queryDropped: metrics.NilCounter{},
}
lighthouses := []netip.Addr{}
staticList := map[netip.Addr]struct{}{}
+2 -2
View File
@@ -410,8 +410,8 @@ logging:
#try_interval: 100ms
#retries: 20
# query_buffer is the size of the buffer channel for querying lighthouses
#query_buffer: 64
# query_buffer is the size of the buffer channel for querying lighthouses, drops are recorded in the lighthouse.query.dropped metric.
#query_buffer: 1024
# trigger_buffer is the size of the buffer channel for quickly sending handshakes
# after receiving the response for lighthouse queries
+98 -111
View File
@@ -14,6 +14,7 @@ import (
"strconv"
"strings"
"sync"
"sync/atomic"
"time"
"github.com/gaissmai/bart"
@@ -28,16 +29,23 @@ type FirewallInterface interface {
AddRule(incoming bool, proto uint8, startPort int32, endPort int32, groups []string, host string, cidr, localCidr string, caName string, caSha string) error
}
// conn is a conntrack entry. Only expires changes after it is stored, a rules version change
// stores a replacement entry instead.
type conn struct {
Expires time.Time // Time when this conntrack entry will expire
expires atomic.Uint32 // conntrack clock second when this entry expires, see FirewallConntrack.now
// record why the original connection passed the firewall, so we can re-validate
// after ruleset changes. Note, rulesVersion is a uint16 so that these two
// fields pack for free after the uint32 above
// after ruleset changes
incoming bool
rulesVersion uint16
}
func newConn(expires uint32, incoming bool, rulesVersion uint16) *conn {
c := &conn{incoming: incoming, rulesVersion: rulesVersion}
c.expires.Store(expires)
return c
}
// TODO: need conntrack max tracked connections handling
type Firewall struct {
Conntrack *FirewallConntrack
@@ -79,11 +87,69 @@ type firewallMetrics struct {
droppedNoRule metrics.Counter
}
// FirewallConntrack is safe for concurrent use by every routine without a lock.
type FirewallConntrack struct {
sync.Mutex
conns sync.Map // firewall.Packet -> *conn
count atomic.Int64 // entries in conns, which sync.Map can't tell us
now atomic.Uint32 // the conntrack clock: whole seconds since epoch, kept current by Run
epoch time.Time
}
Conns map[firewall.Packet]*conn
TimerWheel *TimerWheel[firewall.Packet]
func newFirewallConntrack() *FirewallConntrack {
return &FirewallConntrack{epoch: time.Now()}
}
// Run advances the conntrack clock every second and sweeps out expired entries every minute,
// until ctx is done. Reading a shared clock is much cheaper than asking the OS on every packet.
func (ct *FirewallConntrack) Run(ctx context.Context) {
t := time.NewTicker(time.Second)
defer t.Stop()
var nextSweep uint32
for {
select {
case <-ctx.Done():
return
case <-t.C:
// Measured from epoch rather than counted, so a late tick can't slow the clock down
now := uint32(time.Since(ct.epoch) / time.Second)
ct.now.Store(now)
if now >= nextSweep {
ct.sweep(now)
nextSweep = now + 60
}
}
}
}
// sweep deletes entries that expired at or before now.
func (ct *FirewallConntrack) sweep(now uint32) {
ct.conns.Range(func(k, v any) bool {
if v.(*conn).expires.Load() <= now {
ct.delete(k.(firewall.Packet), v.(*conn))
}
return true
})
}
func (ct *FirewallConntrack) store(fp firewall.Packet, c *conn) {
if _, replaced := ct.conns.Swap(fp, c); !replaced {
ct.count.Add(1)
}
}
// delete removes fp's entry if it is still c, so a newer entry stored by another routine survives
func (ct *FirewallConntrack) delete(fp firewall.Packet, c *conn) {
if ct.conns.CompareAndDelete(fp, c) {
ct.count.Add(-1)
}
}
// clear deletes every entry
func (ct *FirewallConntrack) clear() {
ct.conns.Range(func(k, v any) bool {
ct.delete(k.(firewall.Packet), v.(*conn))
return true
})
}
// FirewallTable is the entry point for a rule, the evaluation order is:
@@ -132,26 +198,10 @@ type firewallLocalCIDR struct {
LocalCIDR *bart.Lite
}
// NewFirewall creates a new Firewall object. A TimerWheel is created for you from the provided timeouts.
// NewFirewall creates a new Firewall object.
// The certificate provided should be the highest version loaded in memory.
func NewFirewall(l *slog.Logger, tcpTimeout, UDPTimeout, defaultTimeout time.Duration, c cert.Certificate) *Firewall {
//TODO: error on 0 duration
var tmin, tmax time.Duration
if tcpTimeout < UDPTimeout {
tmin = tcpTimeout
tmax = UDPTimeout
} else {
tmin = UDPTimeout
tmax = tcpTimeout
}
if defaultTimeout < tmin {
tmin = defaultTimeout
} else if defaultTimeout > tmax {
tmax = defaultTimeout
}
routableNetworks := new(bart.Lite)
var assignedNetworks []netip.Prefix
for _, network := range c.Networks() {
@@ -166,10 +216,7 @@ func NewFirewall(l *slog.Logger, tcpTimeout, UDPTimeout, defaultTimeout time.Dur
}
return &Firewall{
Conntrack: &FirewallConntrack{
Conns: make(map[firewall.Packet]*conn),
TimerWheel: NewTimerWheel[firewall.Packet](tmin, tmax),
},
Conntrack: newFirewallConntrack(),
InRules: newFirewallTable(),
OutRules: newFirewallTable(),
TCPTimeout: tcpTimeout,
@@ -423,7 +470,7 @@ var ErrNoMatchingRule = errors.New("no matching rule in firewall table")
// Drop returns an error if the packet should be dropped, explaining why. It
// returns nil if the packet should not be dropped.
func (f *Firewall) Drop(fp firewall.Packet, incoming bool, h *HostInfo, caPool *cert.CAPool, localCache firewall.ConntrackCache) error {
func (f *Firewall) Drop(fp firewall.Packet, incoming bool, h *HostInfo, caPool *cert.CAPool) error {
// Make sure remote address matches nebula certificate, and determine how to treat it
if h.networks == nil {
// Simple case: Certificate has one address and no unsafe networks
@@ -458,7 +505,7 @@ func (f *Firewall) Drop(fp firewall.Packet, incoming bool, h *HostInfo, caPool *
}
// Check if we spoke to this tuple, if we did then allow this packet
if f.inConns(fp, h, caPool, localCache) {
if f.inConns(fp, h, caPool) {
return nil
}
@@ -494,36 +541,19 @@ func (f *Firewall) Destroy() {
}
func (f *Firewall) EmitStats() {
conntrack := f.Conntrack
conntrack.Lock()
conntrackCount := len(conntrack.Conns)
conntrack.Unlock()
metrics.GetOrRegisterGauge("firewall.conntrack.count", nil).Update(int64(conntrackCount))
metrics.GetOrRegisterGauge("firewall.conntrack.count", nil).Update(f.Conntrack.count.Load())
metrics.GetOrRegisterGauge("firewall.rules.version", nil).Update(int64(f.rulesVersion))
metrics.GetOrRegisterGauge("firewall.rules.hash", nil).Update(int64(f.GetRuleHashFNV()))
}
func (f *Firewall) inConns(fp firewall.Packet, h *HostInfo, caPool *cert.CAPool, localCache firewall.ConntrackCache) bool {
if localCache != nil {
if _, ok := localCache[fp]; ok {
return true
}
}
func (f *Firewall) inConns(fp firewall.Packet, h *HostInfo, caPool *cert.CAPool) bool {
conntrack := f.Conntrack
conntrack.Lock()
// Purge every time we test
ep, has := conntrack.TimerWheel.Purge()
if has {
f.evict(ep)
}
c, ok := conntrack.Conns[fp]
v, ok := conntrack.conns.Load(fp)
if !ok {
conntrack.Unlock()
return false
}
c := v.(*conn)
expires := conntrack.now.Load() + f.timeout(fp.Protocol)
if c.rulesVersion != f.rulesVersion {
// This conntrack entry was for an older rule set, validate
@@ -543,8 +573,7 @@ func (f *Firewall) inConns(fp firewall.Packet, h *HostInfo, caPool *cert.CAPool,
"oldRulesVersion", c.rulesVersion,
)
}
delete(conntrack.Conns, fp)
conntrack.Unlock()
conntrack.delete(fp, c)
return false
}
@@ -557,77 +586,35 @@ func (f *Firewall) inConns(fp firewall.Packet, h *HostInfo, caPool *cert.CAPool,
)
}
c.rulesVersion = f.rulesVersion
conntrack.store(fp, newConn(expires, c.incoming, f.rulesVersion))
return true
}
switch fp.Protocol {
case iputil.IPProtocolTCP:
c.Expires = time.Now().Add(f.TCPTimeout)
case iputil.IPProtocolUDP:
c.Expires = time.Now().Add(f.UDPTimeout)
default:
c.Expires = time.Now().Add(f.DefaultTimeout)
}
conntrack.Unlock()
if localCache != nil {
localCache[fp] = struct{}{}
// Most packets land in the same second as the one before, skip writing an unchanged expiry
if c.expires.Load() != expires {
c.expires.Store(expires)
}
return true
}
func (f *Firewall) addConn(fp firewall.Packet, incoming bool) {
var timeout time.Duration
c := &conn{}
switch fp.Protocol {
case iputil.IPProtocolTCP:
timeout = f.TCPTimeout
case iputil.IPProtocolUDP:
timeout = f.UDPTimeout
default:
timeout = f.DefaultTimeout
}
conntrack := f.Conntrack
conntrack.Lock()
if _, ok := conntrack.Conns[fp]; !ok {
conntrack.TimerWheel.Advance(time.Now())
conntrack.TimerWheel.Add(fp, timeout)
}
// Record which rulesVersion allowed this connection, so we can retest after
// firewall reload
c.incoming = incoming
c.rulesVersion = f.rulesVersion
c.Expires = time.Now().Add(timeout)
conntrack.Conns[fp] = c
conntrack.Unlock()
conntrack := f.Conntrack
conntrack.store(fp, newConn(conntrack.now.Load()+f.timeout(fp.Protocol), incoming, f.rulesVersion))
}
// Evict checks if a conntrack entry has expired, if so it is removed, if not it is re-added to the wheel
// Caller must own the connMutex lock!
func (f *Firewall) evict(p firewall.Packet) {
// Are we still tracking this conn?
conntrack := f.Conntrack
t, ok := conntrack.Conns[p]
if !ok {
return
// timeout returns how many seconds a conntrack entry for proto lives past its last packet
func (f *Firewall) timeout(proto uint8) uint32 {
switch proto {
case iputil.IPProtocolTCP:
return uint32(f.TCPTimeout / time.Second)
case iputil.IPProtocolUDP:
return uint32(f.UDPTimeout / time.Second)
default:
return uint32(f.DefaultTimeout / time.Second)
}
newT := t.Expires.Sub(time.Now())
// Timeout is in the future, re-add the timer
if newT > 0 {
conntrack.TimerWheel.Advance(time.Now())
conntrack.TimerWheel.Add(p, newT)
return
}
// This conn is done
delete(conntrack.Conns, p)
}
func (ft *FirewallTable) match(p firewall.Packet, incoming bool, c *cert.CachedCertificate, caPool *cert.CAPool) bool {
-69
View File
@@ -1,69 +0,0 @@
package firewall
import (
"context"
"log/slog"
"sync/atomic"
"time"
"github.com/slackhq/nebula/logging"
)
// ConntrackCache is used as a local routine cache to know if a given flow
// has been seen in the conntrack table.
type ConntrackCache map[Packet]struct{}
type ConntrackCacheTicker struct {
cacheV uint64
cacheTick atomic.Uint64
l *slog.Logger
cache ConntrackCache
}
func NewConntrackCacheTicker(ctx context.Context, l *slog.Logger, d time.Duration) *ConntrackCacheTicker {
if d == 0 {
return nil
}
c := &ConntrackCacheTicker{
l: l,
cache: ConntrackCache{},
}
go c.tick(ctx, d)
return c
}
func (c *ConntrackCacheTicker) tick(ctx context.Context, d time.Duration) {
t := time.NewTicker(d)
defer t.Stop()
for {
select {
case <-ctx.Done():
return
case <-t.C:
c.cacheTick.Add(1)
}
}
}
// Get checks if the cache ticker has moved to the next version before returning
// the map. If it has moved, we reset the map.
func (c *ConntrackCacheTicker) Get() ConntrackCache {
if c == nil {
return nil
}
if tick := c.cacheTick.Load(); tick != c.cacheV {
c.cacheV = tick
if ll := len(c.cache); ll > 0 {
if c.l.Enabled(context.Background(), logging.LevelTrace) {
c.l.Log(context.Background(), logging.LevelTrace, "resetting conntrack cache", "len", ll)
}
c.cache = make(ConntrackCache, ll)
}
}
return c.cache
}
-70
View File
@@ -1,70 +0,0 @@
package firewall
import (
"bytes"
"log/slog"
"strings"
"testing"
"github.com/slackhq/nebula/logging"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
)
// The tests below pin the log format produced by ConntrackCacheTicker.Get
// so changes cannot silently break what operators are grepping for. The
// ticker's internal state (cache + cacheTick) is poked directly to avoid
// racing a goroutine-driven tick in tests.
func newFixedTicker(t *testing.T, l *slog.Logger, cacheLen int) *ConntrackCacheTicker {
t.Helper()
c := &ConntrackCacheTicker{
l: l,
cache: make(ConntrackCache, cacheLen),
}
for i := range cacheLen {
c.cache[Packet{LocalPort: uint16(i) + 1}] = struct{}{}
}
c.cacheTick.Store(1) // cacheV starts at 0, so Get() takes the reset path
return c
}
func TestConntrackCacheTicker_Get_TextFormat(t *testing.T) {
buf := &bytes.Buffer{}
l := test.NewLoggerWithOutputAndLevel(buf, logging.LevelTrace)
c := newFixedTicker(t, l, 3)
c.Get()
assert.Equal(t, "level=DEBUG-4 msg=\"resetting conntrack cache\" len=3\n", buf.String())
}
func TestConntrackCacheTicker_Get_JSONFormat(t *testing.T) {
buf := &bytes.Buffer{}
l := test.NewJSONLoggerWithOutput(buf, logging.LevelTrace)
c := newFixedTicker(t, l, 2)
c.Get()
assert.JSONEq(t, `{"level":"DEBUG-4","msg":"resetting conntrack cache","len":2}`, strings.TrimSpace(buf.String()))
}
func TestConntrackCacheTicker_Get_QuietBelowTrace(t *testing.T) {
buf := &bytes.Buffer{}
l := test.NewLoggerWithOutputAndLevel(buf, slog.LevelDebug)
c := newFixedTicker(t, l, 5)
c.Get()
assert.Empty(t, buf.String())
}
func TestConntrackCacheTicker_Get_QuietWhenCacheEmpty(t *testing.T) {
buf := &bytes.Buffer{}
l := test.NewLoggerWithOutputAndLevel(buf, logging.LevelTrace)
c := newFixedTicker(t, l, 0)
c.Get()
assert.Empty(t, buf.String())
}
+4
View File
@@ -26,6 +26,10 @@ type Packet struct {
RemotePort uint16
Protocol uint8
Fragment bool
// pad fills what would otherwise be compiler padding. A Packet with no padding hashes as one
// block of memory, which makes it a much faster map key. Always zero.
pad [2]byte
}
func (fp *Packet) Copy() *Packet {
+128 -102
View File
@@ -2,6 +2,7 @@ package nebula
import (
"bytes"
"context"
"errors"
"log/slog"
"math"
@@ -23,39 +24,12 @@ func TestNewFirewall(t *testing.T) {
l := test.NewLogger()
c := &dummyCert{}
fw := NewFirewall(l, time.Second, time.Minute, time.Hour, c)
conntrack := fw.Conntrack
assert.NotNil(t, conntrack)
assert.NotNil(t, conntrack.Conns)
assert.NotNil(t, conntrack.TimerWheel)
assert.NotNil(t, fw.Conntrack)
assert.NotNil(t, fw.InRules)
assert.NotNil(t, fw.OutRules)
assert.Equal(t, time.Second, fw.TCPTimeout)
assert.Equal(t, time.Minute, fw.UDPTimeout)
assert.Equal(t, time.Hour, fw.DefaultTimeout)
assert.Equal(t, time.Hour, conntrack.TimerWheel.wheelDuration)
assert.Equal(t, time.Hour, conntrack.TimerWheel.wheelDuration)
assert.Equal(t, 3602, conntrack.TimerWheel.wheelLen)
fw = NewFirewall(l, time.Second, time.Hour, time.Minute, c)
assert.Equal(t, time.Hour, conntrack.TimerWheel.wheelDuration)
assert.Equal(t, 3602, conntrack.TimerWheel.wheelLen)
fw = NewFirewall(l, time.Hour, time.Second, time.Minute, c)
assert.Equal(t, time.Hour, conntrack.TimerWheel.wheelDuration)
assert.Equal(t, 3602, conntrack.TimerWheel.wheelLen)
fw = NewFirewall(l, time.Hour, time.Minute, time.Second, c)
assert.Equal(t, time.Hour, conntrack.TimerWheel.wheelDuration)
assert.Equal(t, 3602, conntrack.TimerWheel.wheelLen)
fw = NewFirewall(l, time.Minute, time.Hour, time.Second, c)
assert.Equal(t, time.Hour, conntrack.TimerWheel.wheelDuration)
assert.Equal(t, 3602, conntrack.TimerWheel.wheelLen)
fw = NewFirewall(l, time.Minute, time.Second, time.Hour, c)
assert.Equal(t, time.Hour, conntrack.TimerWheel.wheelDuration)
assert.Equal(t, 3602, conntrack.TimerWheel.wheelLen)
}
func TestFirewall_AddRule(t *testing.T) {
@@ -212,44 +186,44 @@ func TestFirewall_Drop(t *testing.T) {
cp := cert.NewCAPool()
// Drop outbound
assert.Equal(t, ErrNoMatchingRule, fw.Drop(p, false, &h, cp, nil))
assert.Equal(t, ErrNoMatchingRule, fw.Drop(p, false, &h, cp))
// Allow inbound
resetConntrack(fw)
require.NoError(t, fw.Drop(p, true, &h, cp, nil))
require.NoError(t, fw.Drop(p, true, &h, cp))
// Allow outbound because conntrack
require.NoError(t, fw.Drop(p, false, &h, cp, nil))
require.NoError(t, fw.Drop(p, false, &h, cp))
// test remote mismatch
oldRemote := p.RemoteAddr
p.RemoteAddr = netip.MustParseAddr("1.2.3.10")
assert.Equal(t, fw.Drop(p, false, &h, cp, nil), ErrInvalidRemoteIP)
assert.Equal(t, fw.Drop(p, false, &h, cp), ErrInvalidRemoteIP)
p.RemoteAddr = oldRemote
// ensure signer doesn't get in the way of group checks
fw = NewFirewall(l, time.Second, time.Minute, time.Hour, &c)
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"nope"}, "", "", "", "", "signer-shasum"))
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"default-group"}, "", "", "", "", "signer-shasum-bad"))
assert.Equal(t, fw.Drop(p, true, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(p, true, &h, cp), ErrNoMatchingRule)
// test caSha doesn't drop on match
fw = NewFirewall(l, time.Second, time.Minute, time.Hour, &c)
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"nope"}, "", "", "", "", "signer-shasum-bad"))
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"default-group"}, "", "", "", "", "signer-shasum"))
require.NoError(t, fw.Drop(p, true, &h, cp, nil))
require.NoError(t, fw.Drop(p, true, &h, cp))
// ensure ca name doesn't get in the way of group checks
cp.CAs["signer-shasum"] = &cert.CachedCertificate{Certificate: &dummyCert{name: "ca-good"}}
fw = NewFirewall(l, time.Second, time.Minute, time.Hour, &c)
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"nope"}, "", "", "", "ca-good", ""))
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"default-group"}, "", "", "", "ca-good-bad", ""))
assert.Equal(t, fw.Drop(p, true, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(p, true, &h, cp), ErrNoMatchingRule)
// test caName doesn't drop on match
cp.CAs["signer-shasum"] = &cert.CachedCertificate{Certificate: &dummyCert{name: "ca-good"}}
fw = NewFirewall(l, time.Second, time.Minute, time.Hour, &c)
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"nope"}, "", "", "", "ca-good-bad", ""))
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"default-group"}, "", "", "", "ca-good", ""))
require.NoError(t, fw.Drop(p, true, &h, cp, nil))
require.NoError(t, fw.Drop(p, true, &h, cp))
}
func TestFirewall_DropV6(t *testing.T) {
@@ -290,44 +264,44 @@ func TestFirewall_DropV6(t *testing.T) {
cp := cert.NewCAPool()
// Drop outbound
assert.Equal(t, ErrNoMatchingRule, fw.Drop(p, false, &h, cp, nil))
assert.Equal(t, ErrNoMatchingRule, fw.Drop(p, false, &h, cp))
// Allow inbound
resetConntrack(fw)
require.NoError(t, fw.Drop(p, true, &h, cp, nil))
require.NoError(t, fw.Drop(p, true, &h, cp))
// Allow outbound because conntrack
require.NoError(t, fw.Drop(p, false, &h, cp, nil))
require.NoError(t, fw.Drop(p, false, &h, cp))
// test remote mismatch
oldRemote := p.RemoteAddr
p.RemoteAddr = netip.MustParseAddr("fd12::56")
assert.Equal(t, fw.Drop(p, false, &h, cp, nil), ErrInvalidRemoteIP)
assert.Equal(t, fw.Drop(p, false, &h, cp), ErrInvalidRemoteIP)
p.RemoteAddr = oldRemote
// ensure signer doesn't get in the way of group checks
fw = NewFirewall(l, time.Second, time.Minute, time.Hour, &c)
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"nope"}, "", "", "", "", "signer-shasum"))
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"default-group"}, "", "", "", "", "signer-shasum-bad"))
assert.Equal(t, fw.Drop(p, true, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(p, true, &h, cp), ErrNoMatchingRule)
// test caSha doesn't drop on match
fw = NewFirewall(l, time.Second, time.Minute, time.Hour, &c)
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"nope"}, "", "", "", "", "signer-shasum-bad"))
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"default-group"}, "", "", "", "", "signer-shasum"))
require.NoError(t, fw.Drop(p, true, &h, cp, nil))
require.NoError(t, fw.Drop(p, true, &h, cp))
// ensure ca name doesn't get in the way of group checks
cp.CAs["signer-shasum"] = &cert.CachedCertificate{Certificate: &dummyCert{name: "ca-good"}}
fw = NewFirewall(l, time.Second, time.Minute, time.Hour, &c)
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"nope"}, "", "", "", "ca-good", ""))
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"default-group"}, "", "", "", "ca-good-bad", ""))
assert.Equal(t, fw.Drop(p, true, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(p, true, &h, cp), ErrNoMatchingRule)
// test caName doesn't drop on match
cp.CAs["signer-shasum"] = &cert.CachedCertificate{Certificate: &dummyCert{name: "ca-good"}}
fw = NewFirewall(l, time.Second, time.Minute, time.Hour, &c)
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"nope"}, "", "", "", "ca-good-bad", ""))
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"default-group"}, "", "", "", "ca-good", ""))
require.NoError(t, fw.Drop(p, true, &h, cp, nil))
require.NoError(t, fw.Drop(p, true, &h, cp))
}
func BenchmarkFirewallTable_match(b *testing.B) {
@@ -534,10 +508,10 @@ func TestFirewall_Drop2(t *testing.T) {
cp := cert.NewCAPool()
// h1/c1 lacks the proper groups
require.ErrorIs(t, fw.Drop(p, true, &h1, cp, nil), ErrNoMatchingRule)
require.ErrorIs(t, fw.Drop(p, true, &h1, cp), ErrNoMatchingRule)
// c has the proper groups
resetConntrack(fw)
require.NoError(t, fw.Drop(p, true, &h, cp, nil))
require.NoError(t, fw.Drop(p, true, &h, cp))
}
func TestFirewall_Drop3(t *testing.T) {
@@ -614,18 +588,18 @@ func TestFirewall_Drop3(t *testing.T) {
cp := cert.NewCAPool()
// c1 should pass because host match
require.NoError(t, fw.Drop(p, true, &h1, cp, nil))
require.NoError(t, fw.Drop(p, true, &h1, cp))
// c2 should pass because ca sha match
resetConntrack(fw)
require.NoError(t, fw.Drop(p, true, &h2, cp, nil))
require.NoError(t, fw.Drop(p, true, &h2, cp))
// c3 should fail because no match
resetConntrack(fw)
assert.Equal(t, fw.Drop(p, true, &h3, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(p, true, &h3, cp), ErrNoMatchingRule)
// Test a remote address match
fw = NewFirewall(l, time.Second, time.Minute, time.Hour, c.Certificate)
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 1, 1, []string{}, "", "1.2.3.4/24", "", "", ""))
require.NoError(t, fw.Drop(p, true, &h1, cp, nil))
require.NoError(t, fw.Drop(p, true, &h1, cp))
}
func TestFirewall_Drop3V6(t *testing.T) {
@@ -662,7 +636,7 @@ func TestFirewall_Drop3V6(t *testing.T) {
fw := NewFirewall(l, time.Second, time.Minute, time.Hour, c.Certificate)
cp := cert.NewCAPool()
require.NoError(t, fw.AddRule(true, firewall.ProtoAny, 1, 1, []string{}, "", "fd12::34/120", "", "", ""))
require.NoError(t, fw.Drop(p, true, &h, cp, nil))
require.NoError(t, fw.Drop(p, true, &h, cp))
}
func TestFirewall_DropConntrackReload(t *testing.T) {
@@ -703,12 +677,12 @@ func TestFirewall_DropConntrackReload(t *testing.T) {
cp := cert.NewCAPool()
// Drop outbound
assert.Equal(t, fw.Drop(p, false, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(p, false, &h, cp), ErrNoMatchingRule)
// Allow inbound
resetConntrack(fw)
require.NoError(t, fw.Drop(p, true, &h, cp, nil))
require.NoError(t, fw.Drop(p, true, &h, cp))
// Allow outbound because conntrack
require.NoError(t, fw.Drop(p, false, &h, cp, nil))
require.NoError(t, fw.Drop(p, false, &h, cp))
oldFw := fw
fw = NewFirewall(l, time.Second, time.Minute, time.Hour, c.Certificate)
@@ -717,7 +691,7 @@ func TestFirewall_DropConntrackReload(t *testing.T) {
fw.rulesVersion = oldFw.rulesVersion + 1
// Allow outbound because conntrack and new rules allow port 10
require.NoError(t, fw.Drop(p, false, &h, cp, nil))
require.NoError(t, fw.Drop(p, false, &h, cp))
oldFw = fw
fw = NewFirewall(l, time.Second, time.Minute, time.Hour, c.Certificate)
@@ -726,7 +700,7 @@ func TestFirewall_DropConntrackReload(t *testing.T) {
fw.rulesVersion = oldFw.rulesVersion + 1
// Drop outbound because conntrack doesn't match new ruleset
assert.Equal(t, fw.Drop(p, false, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(p, false, &h, cp), ErrNoMatchingRule)
}
func TestFirewall_ICMPPortBehavior(t *testing.T) {
@@ -771,12 +745,12 @@ func TestFirewall_ICMPPortBehavior(t *testing.T) {
p.LocalPort = 0
p.RemotePort = 0
// Drop outbound
assert.Equal(t, fw.Drop(*p, false, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(*p, false, &h, cp), ErrNoMatchingRule)
// Allow inbound
resetConntrack(fw)
require.NoError(t, fw.Drop(*p, true, &h, cp, nil))
require.NoError(t, fw.Drop(*p, true, &h, cp))
//now also allow outbound
require.NoError(t, fw.Drop(*p, false, &h, cp, nil))
require.NoError(t, fw.Drop(*p, false, &h, cp))
})
t.Run("nonzero ports", func(t *testing.T) {
@@ -784,12 +758,12 @@ func TestFirewall_ICMPPortBehavior(t *testing.T) {
p.LocalPort = 0xabcd
p.RemotePort = 0x1234
// Drop outbound
assert.Equal(t, fw.Drop(*p, false, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(*p, false, &h, cp), ErrNoMatchingRule)
// Allow inbound
resetConntrack(fw)
require.NoError(t, fw.Drop(*p, true, &h, cp, nil))
require.NoError(t, fw.Drop(*p, true, &h, cp))
//now also allow outbound
require.NoError(t, fw.Drop(*p, false, &h, cp, nil))
require.NoError(t, fw.Drop(*p, false, &h, cp))
})
})
@@ -801,12 +775,12 @@ func TestFirewall_ICMPPortBehavior(t *testing.T) {
p.LocalPort = 0
p.RemotePort = 0
// Drop outbound
assert.Equal(t, fw.Drop(*p, false, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(*p, false, &h, cp), ErrNoMatchingRule)
// Allow inbound
resetConntrack(fw)
assert.Equal(t, fw.Drop(*p, true, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(*p, true, &h, cp), ErrNoMatchingRule)
//now also allow outbound
assert.Equal(t, fw.Drop(*p, false, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(*p, false, &h, cp), ErrNoMatchingRule)
})
t.Run("nonzero ports, still blocked", func(t *testing.T) {
@@ -814,12 +788,12 @@ func TestFirewall_ICMPPortBehavior(t *testing.T) {
p.LocalPort = 0xabcd
p.RemotePort = 0x1234
// Drop outbound
assert.Equal(t, fw.Drop(*p, false, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(*p, false, &h, cp), ErrNoMatchingRule)
// Allow inbound
resetConntrack(fw)
assert.Equal(t, fw.Drop(*p, true, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(*p, true, &h, cp), ErrNoMatchingRule)
//now also allow outbound
assert.Equal(t, fw.Drop(*p, false, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(*p, false, &h, cp), ErrNoMatchingRule)
})
t.Run("nonzero, matching ports, still blocked", func(t *testing.T) {
@@ -827,12 +801,12 @@ func TestFirewall_ICMPPortBehavior(t *testing.T) {
p.LocalPort = 80
p.RemotePort = 80
// Drop outbound
assert.Equal(t, fw.Drop(*p, false, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(*p, false, &h, cp), ErrNoMatchingRule)
// Allow inbound
resetConntrack(fw)
assert.Equal(t, fw.Drop(*p, true, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(*p, true, &h, cp), ErrNoMatchingRule)
//now also allow outbound
assert.Equal(t, fw.Drop(*p, false, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(*p, false, &h, cp), ErrNoMatchingRule)
})
})
t.Run("Any proto, any port", func(t *testing.T) {
@@ -844,12 +818,12 @@ func TestFirewall_ICMPPortBehavior(t *testing.T) {
p.LocalPort = 0
p.RemotePort = 0
// Drop outbound
assert.Equal(t, fw.Drop(*p, false, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(*p, false, &h, cp), ErrNoMatchingRule)
// Allow inbound
resetConntrack(fw)
require.NoError(t, fw.Drop(*p, true, &h, cp, nil))
require.NoError(t, fw.Drop(*p, true, &h, cp))
//now also allow outbound
require.NoError(t, fw.Drop(*p, false, &h, cp, nil))
require.NoError(t, fw.Drop(*p, false, &h, cp))
})
t.Run("nonzero ports, allowed", func(t *testing.T) {
@@ -858,15 +832,15 @@ func TestFirewall_ICMPPortBehavior(t *testing.T) {
p.LocalPort = 0xabcd
p.RemotePort = 0x1234
// Drop outbound
assert.Equal(t, fw.Drop(*p, false, &h, cp, nil), ErrNoMatchingRule)
assert.Equal(t, fw.Drop(*p, false, &h, cp), ErrNoMatchingRule)
// Allow inbound
resetConntrack(fw)
require.NoError(t, fw.Drop(*p, true, &h, cp, nil))
require.NoError(t, fw.Drop(*p, true, &h, cp))
//now also allow outbound
require.NoError(t, fw.Drop(*p, false, &h, cp, nil))
require.NoError(t, fw.Drop(*p, false, &h, cp))
//different ID is blocked
p.RemotePort++
require.Equal(t, fw.Drop(*p, false, &h, cp, nil), ErrNoMatchingRule)
require.Equal(t, fw.Drop(*p, false, &h, cp), ErrNoMatchingRule)
})
})
@@ -914,7 +888,7 @@ func TestFirewall_DropIPSpoofing(t *testing.T) {
Protocol: iputil.IPProtocolUDP,
Fragment: false,
}
assert.Equal(t, fw.Drop(p, true, &h1, cp, nil), ErrInvalidRemoteIP)
assert.Equal(t, fw.Drop(p, true, &h1, cp), ErrInvalidRemoteIP)
}
func TestFirewall_ConntrackSourceSpoofingAcrossPeers(t *testing.T) {
@@ -965,20 +939,84 @@ func TestFirewall_ConntrackSourceSpoofingAcrossPeers(t *testing.T) {
Protocol: iputil.IPProtocolUDP,
}
require.NoError(t, fw.Drop(flow, true, &victimHI, cp, nil),
require.NoError(t, fw.Drop(flow, true, &victimHI, cp),
"victim's own traffic from its own overlay IP must be allowed")
unseen := flow
unseen.RemotePort = 55001
assert.Equal(t, ErrInvalidRemoteIP, fw.Drop(unseen, true, &attackerHI, cp, nil),
assert.Equal(t, ErrInvalidRemoteIP, fw.Drop(unseen, true, &attackerHI, cp),
"sanity: attacker forging victim's source IP must be rejected when no conntrack entry exists")
got := fw.Drop(flow, true, &attackerHI, cp, nil)
got := fw.Drop(flow, true, &attackerHI, cp)
t.Logf("attacker replaying victim's 4-tuple: Drop returned %v (nil == packet ALLOWED == spoof succeeded)", got)
assert.Equal(t, ErrInvalidRemoteIP, got,
"SECURITY: attacker spoofed victim's overlay source IP (192.0.2.2) by reusing an existing conntrack 4-tuple; Drop returned %v instead of rejecting", got)
}
func TestFirewallConntrack_sweep(t *testing.T) {
ct := newFirewallConntrack()
live := firewall.Packet{LocalPort: 1}
dead := firewall.Packet{LocalPort: 2}
ct.store(live, newConn(11, true, 0))
ct.store(dead, newConn(10, true, 0))
assert.Equal(t, int64(2), ct.count.Load())
ct.sweep(10)
_, ok := ct.conns.Load(live)
assert.True(t, ok)
_, ok = ct.conns.Load(dead)
assert.False(t, ok)
assert.Equal(t, int64(1), ct.count.Load())
}
func TestFirewallConntrack_storeAndDeleteCount(t *testing.T) {
ct := newFirewallConntrack()
fp := firewall.Packet{LocalPort: 1}
first := newConn(10, true, 0)
ct.store(fp, first)
// Replacing an entry doesn't add to the count
second := newConn(20, true, 1)
ct.store(fp, second)
assert.Equal(t, int64(1), ct.count.Load())
// Deleting a stale entry is a no-op, the newer one stays
ct.delete(fp, first)
v, ok := ct.conns.Load(fp)
assert.True(t, ok)
assert.Same(t, second, v)
assert.Equal(t, int64(1), ct.count.Load())
ct.delete(fp, second)
_, ok = ct.conns.Load(fp)
assert.False(t, ok)
assert.Equal(t, int64(0), ct.count.Load())
ct.store(fp, first)
ct.store(firewall.Packet{LocalPort: 2}, newConn(10, true, 0))
ct.clear()
assert.Equal(t, int64(0), ct.count.Load())
}
func TestFirewallConntrack_Run(t *testing.T) {
ct := newFirewallConntrack()
ct.epoch = time.Now().Add(-time.Hour)
ct.store(firewall.Packet{LocalPort: 1}, newConn(10, true, 0))
ctx, cancel := context.WithCancel(context.Background())
done := make(chan struct{})
go func() {
ct.Run(ctx)
close(done)
}()
// The first tick sets the clock to an hour in and sweeps the long expired entry
require.Eventually(t, func() bool { return ct.count.Load() == 0 }, 5*time.Second, 10*time.Millisecond)
assert.GreaterOrEqual(t, ct.now.Load(), uint32(3600))
cancel()
<-done
}
// BenchmarkFirewallDropConntrackHit measures Drop on an already-established flow
// (a conntrack hit). This is the fast path that the source-IP<->cert binding
// reordering adds work to, so it quantifies the cost of moving the address checks
@@ -987,8 +1025,6 @@ func TestFirewall_ConntrackSourceSpoofingAcrossPeers(t *testing.T) {
// so the remote-address check is a single netip.Addr compare.
// - complex: peer cert has unsafe networks (h.networks populated), so the
// remote-address check is a BART lookup.
// - noCache/localCache: whether a per-batch ConntrackCache is supplied, which in
// the original code let the fast path skip straight past the address checks.
func BenchmarkFirewallDropConntrackHit(b *testing.B) {
l := test.NewLoggerWithOutput(&bytes.Buffer{})
@@ -1036,14 +1072,11 @@ func BenchmarkFirewallDropConntrackHit(b *testing.B) {
}
cases := []struct {
name string
host *HostInfo
useCache bool
name string
host *HostInfo
}{
{"simple/noCache", simpleHost, false},
{"simple/localCache", simpleHost, true},
{"complex/noCache", complexHost, false},
{"complex/localCache", complexHost, true},
{"simple", simpleHost},
{"complex", complexHost},
}
for _, tc := range cases {
@@ -1052,17 +1085,12 @@ func BenchmarkFirewallDropConntrackHit(b *testing.B) {
require.NoError(b, fw.AddRule(true, firewall.ProtoAny, 0, 0, []string{"any"}, "", "", "", "", ""))
// Establish the conntrack entry so every benchmarked Drop is a hit.
require.NoError(b, fw.Drop(flow, true, tc.host, cp, nil))
var cache firewall.ConntrackCache
if tc.useCache {
cache = firewall.ConntrackCache{}
}
require.NoError(b, fw.Drop(flow, true, tc.host, cp))
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
if err := fw.Drop(flow, true, tc.host, cp, cache); err != nil {
if err := fw.Drop(flow, true, tc.host, cp); err != nil {
b.Fatal(err)
}
}
@@ -1550,7 +1578,7 @@ func (c *testcase) Test(t *testing.T, fw *Firewall) {
t.Helper()
cp := cert.NewCAPool()
resetConntrack(fw)
err := fw.Drop(c.p, true, c.h, cp, nil)
err := fw.Drop(c.p, true, c.h, cp)
if c.err == nil {
require.NoError(t, err, "failed to not drop remote address %s", c.p.RemoteAddr)
} else {
@@ -1741,7 +1769,5 @@ func (mf *mockFirewall) AddRule(incoming bool, proto uint8, startPort int32, end
}
func resetConntrack(fw *Firewall) {
fw.Conntrack.Lock()
fw.Conntrack.Conns = map[firewall.Packet]*conn{}
fw.Conntrack.Unlock()
fw.Conntrack.clear()
}
+3 -3
View File
@@ -16,7 +16,7 @@ import (
"github.com/slackhq/nebula/routing"
)
func (f *Interface) consumeInsidePacket(pkt tio.Packet, fwPacket *firewall.ParsedPacket, nb []byte, sendBatch *batch.SendBatch, rejectBuf []byte, q int, localCache firewall.ConntrackCache) {
func (f *Interface) consumeInsidePacket(pkt tio.Packet, fwPacket *firewall.ParsedPacket, nb []byte, sendBatch *batch.SendBatch, rejectBuf []byte, q int) {
// borrowed: pkt.Bytes is owned by the originating tio.Queue and is
// only valid until the next Read on that queue. Every consumer below
// (parse, self-forward, handshake cache, sendInsideMessage) reads it
@@ -109,7 +109,7 @@ func (f *Interface) consumeInsidePacket(pkt tio.Packet, fwPacket *firewall.Parse
return
}
dropReason := f.firewall.Drop(fwPacket.Packet, false, hostinfo, f.pki.GetCAPool(), localCache)
dropReason := f.firewall.Drop(fwPacket.Packet, false, hostinfo, f.pki.GetCAPool())
if dropReason == nil {
f.sendInsideMessage(hostinfo, pkt, nb, sendBatch)
} else {
@@ -380,7 +380,7 @@ func (f *Interface) sendMessageNow(t header.MessageType, st header.MessageSubTyp
}
// check if packet is in outbound fw rules
dropReason := f.firewall.Drop(fp.Packet, false, hostinfo, f.pki.GetCAPool(), nil)
dropReason := f.firewall.Drop(fp.Packet, false, hostinfo, f.pki.GetCAPool())
if dropReason != nil {
if f.l.Enabled(context.Background(), slog.LevelDebug) {
f.l.Debug("dropping cached packet",
+1 -1
View File
@@ -50,7 +50,7 @@ func newSelfForwardInterface(myAddrs ...netip.Addr) (*Interface, *capturingTun)
}
func consumeInside(f *Interface, packet []byte) {
f.consumeInsidePacket(tio.Packet{Bytes: packet}, &firewall.ParsedPacket{}, make([]byte, 12), nil, make([]byte, mtu), 0, nil)
f.consumeInsidePacket(tio.Packet{Bytes: packet}, &firewall.ParsedPacket{}, make([]byte, 12), nil, make([]byte, mtu), 0)
}
// l4Proto describes one upper-layer header for these tests: its IP next-header
+18 -17
View File
@@ -52,8 +52,6 @@ type InterfaceConfig struct {
reQueryEvery uint32
reQueryWait time.Duration
ConntrackCacheTimeout time.Duration
// CpuAffinity, when non-empty, names the CPUs each TUN reader goroutine
// should pin to. Queue i pins to CpuAffinity[i % len(CpuAffinity)] —
// shorter lists than `routines` cycle. Empty list keeps the default
@@ -111,8 +109,6 @@ type Interface struct {
rebindEpoch atomic.Uint32
version string
conntrackCacheTimeout time.Duration
ctx context.Context
writers []udp.Conn
queues []tio.Queue
@@ -227,7 +223,6 @@ func NewInterface(ctx context.Context, c *InterfaceConfig) (*Interface, error) {
myBroadcastAddrsTable: cs.myVpnBroadcastAddrsTable,
relayManager: c.relayManager,
connectionManager: c.connectionManager,
conntrackCacheTimeout: c.ConntrackCacheTimeout,
cpuAffinity: c.CpuAffinity,
pinThreads: c.PinThreads,
@@ -361,8 +356,19 @@ type rxContext struct {
h *header.H
fwPacket *firewall.ParsedPacket
hostmapCache map[uint32]*HostInfo
lhh *LightHouseHandler
ctCache *firewall.ConntrackCacheTicker
// lastAllowed is the last flow the inbound firewall let in during this batch. UDP GRO hands us segments
// in runs from the same flow, so the rest of a run can skip the firewall. Cleared by endBatch.
lastAllowed firewall.Packet
lastAllowedHost *HostInfo
lhh *LightHouseHandler
}
// endBatch forgets what was learned during a batch, so nothing outlives a hostmap or firewall change by more than one batch
func (rxc *rxContext) endBatch() {
clear(rxc.hostmapCache)
rxc.lastAllowed = firewall.Packet{}
rxc.lastAllowedHost = nil
}
func newRxContext(f *Interface, q int) *rxContext {
@@ -374,7 +380,6 @@ func newRxContext(f *Interface, q int) *rxContext {
fwPacket: &firewall.ParsedPacket{},
hostmapCache: map[uint32]*HostInfo{},
lhh: f.lightHouse.NewRequestHandler(),
ctCache: firewall.NewConntrackCacheTicker(f.ctx, f.l, f.conntrackCacheTimeout),
}
}
@@ -396,7 +401,7 @@ func (f *Interface) listenOut(i int) {
if err := f.batchers[i].Flush(); err != nil {
f.l.Error("Failed to flush tun coalescer", "error", err)
}
clear(rxc.hostmapCache)
rxc.endBatch()
}
err := li.ListenOut(listener, flusher)
@@ -444,8 +449,6 @@ func (f *Interface) listenIn(queue tio.Queue, i int) {
fwPacket := &firewall.ParsedPacket{}
nb := make([]byte, 12, 12)
conntrackCache := firewall.NewConntrackCacheTicker(f.ctx, f.l, f.conntrackCacheTimeout)
for {
pkts, err := queue.Read()
if err != nil {
@@ -458,7 +461,7 @@ func (f *Interface) listenIn(queue tio.Queue, i int) {
}
for _, pkt := range pkts {
f.consumeInsidePacket(pkt, fwPacket, nb, sb, rejectBuf, i, conntrackCache.Get())
f.consumeInsidePacket(pkt, fwPacket, nb, sb, rejectBuf, i)
// Flush incrementally once a full sendmmsg batch has
// accumulated so the first packets of a deep read drain
// hit the wire while the rest are still being encrypted.
@@ -531,9 +534,8 @@ func (f *Interface) reloadFirewall(c *config.C) {
}
oldFw := f.firewall
conntrack := oldFw.Conntrack
conntrack.Lock()
defer conntrack.Unlock()
// Conntrack lives as long as the interface, keep using the running one
fw.Conntrack = oldFw.Conntrack
fw.rulesVersion = oldFw.rulesVersion + 1
// If rulesVersion is back to zero, we have wrapped all the way around. Be
@@ -544,8 +546,7 @@ func (f *Interface) reloadFirewall(c *config.C) {
"oldFirewallHashes", oldFw.GetRuleHashes(),
"rulesVersion", fw.rulesVersion,
)
} else {
fw.Conntrack = conntrack
fw.Conntrack.clear()
}
f.firewall = fw
+1 -2
View File
@@ -10,7 +10,6 @@ import (
"github.com/rcrowley/go-metrics"
"github.com/slackhq/nebula/cert"
"github.com/slackhq/nebula/firewall"
"github.com/slackhq/nebula/overlay/overlaytest"
"github.com/slackhq/nebula/test"
"github.com/slackhq/nebula/udp"
@@ -43,7 +42,7 @@ func Test_emitStats_primesGauges(t *testing.T) {
hostMap: hostMap,
inside: &overlaytest.NoopTun{},
outside: &udp.NoopConn{},
firewall: &Firewall{Conntrack: &FirewallConntrack{Conns: map[firewall.Packet]*conn{}}},
firewall: &Firewall{Conntrack: newFirewallConntrack()},
lightHouse: lh,
pki: &PKI{},
handshakeManager: NewHandshakeManager(l, hostMap, lh, &udp.NoopConn{}, defaultHandshakeConfig),
+12 -3
View File
@@ -15,6 +15,7 @@ import (
"time"
"github.com/gaissmai/bart"
"github.com/rcrowley/go-metrics"
"github.com/slackhq/nebula/cert"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/header"
@@ -81,6 +82,8 @@ type LightHouse struct {
updateTrigger chan struct{}
queryChan chan netip.Addr
// queryDropped counts queries QueryServer dropped because queryChan was full.
queryDropped metrics.Counter
calculatedRemotes atomic.Pointer[bart.Table[[]*calculatedRemote]] // Maps VpnAddr to []*calculatedRemote
@@ -116,7 +119,8 @@ func NewLightHouseFromConfig(ctx context.Context, l *slog.Logger, c *config.C, c
nebulaPort: nebulaPort,
punchy: p,
updateTrigger: make(chan struct{}, 1),
queryChan: make(chan netip.Addr, c.GetUint32("handshakes.query_buffer", 64)),
queryChan: make(chan netip.Addr, c.GetUint32("handshakes.query_buffer", 1024)),
queryDropped: metrics.GetOrRegisterCounter("lighthouse.query.dropped", nil),
l: l,
}
h.localAddrsFn = func(al *LocalAllowList) []netip.Addr {
@@ -512,14 +516,19 @@ func (lh *LightHouse) Query(vpnAddr netip.Addr) *RemoteList {
return nil
}
// QueryServer is asynchronous so no reply should be expected
// QueryServer is asynchronous and non-blocking, no reply should be expected.
// If the query channel is full, the query is dropped.
func (lh *LightHouse) QueryServer(vpnAddr netip.Addr) {
// Don't put lighthouse addrs in the query channel because we can't query lighthouses about lighthouses
if lh.amLighthouse || lh.IsLighthouseAddr(vpnAddr) {
return
}
lh.queryChan <- vpnAddr
select {
case lh.queryChan <- vpnAddr:
default:
lh.queryDropped.Inc(1)
}
}
func (lh *LightHouse) QueryCache(vpnAddrs []netip.Addr) *RemoteList {
+54
View File
@@ -6,7 +6,9 @@ import (
"errors"
"fmt"
"net/netip"
"sync"
"testing"
"time"
"github.com/gaissmai/bart"
"github.com/slackhq/nebula/cert"
@@ -795,3 +797,55 @@ func TestLightHouse_logLocalAddrsErr(t *testing.T) {
lh.logLocalAddrsErr(errors.New("something else"))
assert.Contains(t, out.String(), "level=WARN")
}
// heldEncWriter holds the query worker in its first GetHostInfo until release closes.
type heldEncWriter struct {
mockEncWriter
once sync.Once
held chan struct{}
release chan struct{}
}
func (w *heldEncWriter) GetHostInfo(netip.Addr) *HostInfo {
w.once.Do(func() { close(w.held) })
<-w.release
return nil
}
// QueryServer never waits on the query worker, since the packet readers call it and nothing drains the channel at
// shutdown; a query that finds the channel full is dropped and counted. The worker is held on its first query so the
// channel fills.
func TestLighthouse_QueryServerDoesNotBlock(t *testing.T) {
l := test.NewLogger()
cs := testCertState(netip.MustParsePrefix("10.128.0.1/16"))
lh1 := "10.128.0.2"
c := config.NewC(l)
c.Settings["lighthouse"] = map[string]any{"hosts": []any{lh1}}
c.Settings["static_host_map"] = map[string]any{lh1: []any{"1.1.1.1:4242"}}
c.Settings["handshakes"] = map[string]any{"query_buffer": 1}
lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
require.NoError(t, err)
w := &heldEncWriter{held: make(chan struct{}), release: make(chan struct{})}
lh.ifce = w
t.Cleanup(func() { close(w.release) })
lh.QueryServer(netip.MustParseAddr("10.128.0.10"))
select {
case <-w.held:
case <-time.After(5 * time.Second):
t.Fatal("the query worker never took the first query")
}
dropped := lh.queryDropped.Count()
done := make(chan struct{})
go func() {
lh.QueryServer(netip.MustParseAddr("10.128.0.11"))
lh.QueryServer(netip.MustParseAddr("10.128.0.12"))
close(done)
}()
select {
case <-done:
case <-time.After(5 * time.Second):
t.Fatal("QueryServer blocked on a full query channel")
}
assert.EqualValues(t, 1, lh.queryDropped.Count()-dropped)
}
+23 -35
View File
@@ -113,18 +113,6 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
l.Info("Using multiple routines", "routines", routines)
}
// EXPERIMENTAL
// Intentionally not documented yet while we do more testing and determine
// a good default value.
conntrackCacheTimeout := c.GetDuration("firewall.conntrack.routine_cache_timeout", 0)
if routines > 1 && !c.IsSet("firewall.conntrack.routine_cache_timeout") {
// Use a different default if we are running with multiple routines
conntrackCacheTimeout = 1 * time.Second
}
if conntrackCacheTimeout > 0 {
l.Info("Using routine-local conntrack cache", "duration", conntrackCacheTimeout)
}
var tun overlay.Device
if !configTest {
c.CatchHUP(ctx)
@@ -274,29 +262,28 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
}
ifConfig := &InterfaceConfig{
HostMap: hostMap,
Inside: tun,
Outside: udpConns[0],
pki: pki,
Firewall: fw,
DnsServer: ds,
HandshakeManager: handshakeManager,
connectionManager: connManager,
lightHouse: lightHouse,
tryPromoteEvery: c.GetUint32("counters.try_promote", defaultPromoteEvery),
reQueryEvery: c.GetUint32("counters.requery_every_packets", defaultReQueryEvery),
reQueryWait: c.GetDuration("timers.requery_wait_duration", defaultReQueryWait),
DropLocalBroadcast: c.GetBool("tun.drop_local_broadcast", false),
DropMulticast: c.GetBool("tun.drop_multicast", false),
routines: routines,
MessageMetrics: messageMetrics,
version: buildVersion,
relayManager: NewRelayManager(ctx, l, hostMap, c),
punchy: punchy,
ConntrackCacheTimeout: conntrackCacheTimeout,
CpuAffinity: cpuAffinity,
PinThreads: pinThreads,
l: l,
HostMap: hostMap,
Inside: tun,
Outside: udpConns[0],
pki: pki,
Firewall: fw,
DnsServer: ds,
HandshakeManager: handshakeManager,
connectionManager: connManager,
lightHouse: lightHouse,
tryPromoteEvery: c.GetUint32("counters.try_promote", defaultPromoteEvery),
reQueryEvery: c.GetUint32("counters.requery_every_packets", defaultReQueryEvery),
reQueryWait: c.GetDuration("timers.requery_wait_duration", defaultReQueryWait),
DropLocalBroadcast: c.GetBool("tun.drop_local_broadcast", false),
DropMulticast: c.GetBool("tun.drop_multicast", false),
routines: routines,
MessageMetrics: messageMetrics,
version: buildVersion,
relayManager: NewRelayManager(ctx, l, hostMap, c),
punchy: punchy,
CpuAffinity: cpuAffinity,
PinThreads: pinThreads,
l: l,
}
var ifce *Interface
@@ -316,6 +303,7 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
handshakeManager.f = ifce
go handshakeManager.Run(ctx)
go ifce.firewall.Conntrack.Run(ctx)
punchy.Start(ctx, ifce, hostMap, lightHouse)
}
+18 -1
View File
@@ -477,7 +477,7 @@ func (f *Interface) handleOutsideMessagePacket(hostinfo *HostInfo, messageCounte
return
}
dropReason := f.firewall.Drop(rxc.fwPacket.Packet, true, hostinfo, f.pki.GetCAPool(), rxc.ctCache.Get())
dropReason := f.allowInbound(hostinfo, rxc)
if dropReason != nil {
f.rejectOutside(out, hostinfo.ConnectionState, hostinfo, rxc.nb, rxc.scratch, rxc.q)
if f.l.Enabled(context.Background(), slog.LevelDebug) {
@@ -492,6 +492,23 @@ func (f *Interface) handleOutsideMessagePacket(hostinfo *HostInfo, messageCounte
}
}
// allowInbound runs the inbound firewall check on rxc.fwPacket. It skips the check when the packet belongs to
// the same flow from the same host as the last one allowed in this batch.
func (f *Interface) allowInbound(hostinfo *HostInfo, rxc *rxContext) error {
fp := rxc.fwPacket.Packet
if hostinfo == rxc.lastAllowedHost && fp == rxc.lastAllowed {
return nil
}
if err := f.firewall.Drop(fp, true, hostinfo, f.pki.GetCAPool()); err != nil {
return err
}
rxc.lastAllowed = fp
rxc.lastAllowedHost = hostinfo
return nil
}
func (f *Interface) maybeSendRecvError(endpoint netip.AddrPort, index uint32) {
if f.sendRecvErrorConfig.ShouldRecvError(endpoint) {
f.sendRecvError(endpoint, index)
+50
View File
@@ -6,12 +6,16 @@ import (
"net"
"net/netip"
"testing"
"time"
"github.com/gaissmai/bart"
"github.com/google/gopacket"
"github.com/google/gopacket/layers"
"github.com/slackhq/nebula/cert"
"github.com/slackhq/nebula/iputil"
"github.com/slackhq/nebula/firewall"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"golang.org/x/net/ipv4"
@@ -841,3 +845,49 @@ func Test_newPacket_parsedFields(t *testing.T) {
assert.True(t, p.Fragment)
assert.True(t, p.FragAny)
}
func TestInterface_allowInbound(t *testing.T) {
l := test.NewLoggerWithOutput(&bytes.Buffer{})
myNetworks := new(bart.Lite)
myNetworks.Insert(netip.MustParsePrefix("192.0.2.1/24"))
me := &dummyCert{name: "me", networks: []netip.Prefix{netip.MustParsePrefix("192.0.2.1/24")}}
peer := &cert.CachedCertificate{Certificate: &dummyCert{name: "peer", networks: []netip.Prefix{netip.MustParsePrefix("192.0.2.2/24")}}}
h := &HostInfo{ConnectionState: &ConnectionState{peerCert: peer}, vpnAddrs: []netip.Addr{netip.MustParseAddr("192.0.2.2")}}
h.buildNetworks(myNetworks, peer.Certificate)
allowAll := NewFirewall(l, time.Minute, time.Minute, time.Minute, me)
require.NoError(t, allowAll.AddRule(true, firewall.ProtoAny, 0, 0, []string{"any"}, "", "", "", "", ""))
allowNone := NewFirewall(l, time.Minute, time.Minute, time.Minute, me)
f := &Interface{firewall: allowAll, pki: &PKI{}, l: l}
rxc := &rxContext{fwPacket: &firewall.ParsedPacket{}, hostmapCache: map[uint32]*HostInfo{}}
flow := firewall.Packet{
LocalAddr: netip.MustParseAddr("192.0.2.1"),
RemoteAddr: netip.MustParseAddr("192.0.2.2"),
LocalPort: 443,
RemotePort: 55000,
Protocol: iputil.IPProtocolUDP,
}
rxc.fwPacket.Packet = flow
require.NoError(t, f.allowInbound(h, rxc))
// With a firewall that allows nothing, the rest of the flow's run in this batch still passes
f.firewall = allowNone
require.NoError(t, f.allowInbound(h, rxc))
// A different flow is checked
other := flow
other.RemotePort++
rxc.fwPacket.Packet = other
require.ErrorIs(t, f.allowInbound(h, rxc), ErrNoMatchingRule)
// So is the same flow from a different host
rxc.fwPacket.Packet = flow
h2 := &HostInfo{ConnectionState: h.ConnectionState, vpnAddrs: h.vpnAddrs}
h2.buildNetworks(myNetworks, peer.Certificate)
require.ErrorIs(t, f.allowInbound(h2, rxc), ErrNoMatchingRule)
// And the same flow in the next batch
rxc.endBatch()
require.ErrorIs(t, f.allowInbound(h, rxc), ErrNoMatchingRule)
}
+1 -67
View File
@@ -607,72 +607,6 @@ func (t *tun) Read(to []byte) (int, error) {
return n - 4, nil
}
// tunReadBatch is the most packets one tunQueue.Read returns.
const tunReadBatch = 64
// tunReadArena is tunQueue's receive buffer. Draining stops once less than defaultBatchBufSize of it
// is left, so every readv has room for the largest packet utun can return at any device MTU.
const tunReadArena = 4 * defaultBatchBufSize
// tunQueue is the darwin tun's Queue. Read drains every packet already queued on the utun, up to
// tunReadBatch, so the caller encrypts and sends them as one batch rather than one per wakeup.
type tunQueue struct {
t *tun
buf []byte
pkts [tunReadBatch]tio.Packet
}
// Read waits for the utun to become readable, then reads packets until it would block. An error after
// at least one packet is dropped in favor of returning those packets; a persistent one recurs on the
// next Read.
func (q *tunQueue) Read() ([]tio.Packet, error) {
rc, err := q.t.f.SyscallConn()
if err != nil {
return nil, err
}
var head [4]byte
n, off := 0, 0
var callErr error
err = rc.Read(func(fd uintptr) bool {
for n < tunReadBatch && len(q.buf)-off >= defaultBatchBufSize {
iovecs := [2]unix.Iovec{
{Base: &head[0], Len: 4},
{Base: &q.buf[off], Len: uint64(len(q.buf) - off)},
}
l, e := tunReadv(int(fd), iovecs[:])
if e != nil {
if errno, ok := e.(syscall.Errno); ok && errno.Temporary() {
// Park on the poller only while there is nothing to hand back.
return n > 0
}
callErr = e
return true
}
if l < 4 {
// A datagram too short to carry the AF prefix, or end of file; stop rather than spin on it.
return true
}
end := off + l - 4
q.pkts[n] = tio.Packet{Bytes: q.buf[off:end:end]}
n++
off = end
}
return true
})
if n > 0 {
return q.pkts[:n], nil
}
if err != nil {
return nil, err
}
return nil, callErr
}
func (q *tunQueue) Write(p []byte) (int, error) { return q.t.Write(p) }
func (q *tunQueue) Close() error { return q.t.Close() }
// Write pushes one IP packet onto the utun device. Safe for concurrent use:
// the AF prefix and iovecs are per-call stack state, and the fd write itself
// serializes on the runtime's fd mutex (see the Queue contract in tio.go).
@@ -732,5 +666,5 @@ func (t *tun) Name() string {
}
func (t *tun) Queues(int) ([]tio.Queue, error) {
return []tio.Queue{&tunQueue{t: t, buf: make([]byte, tunReadArena)}}, nil
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
}
-97
View File
@@ -1,97 +0,0 @@
//go:build !ios && !e2e_testing
package overlay
import (
"os"
"syscall"
"testing"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"golang.org/x/sys/unix"
)
// newSocketpairTun returns a tun on one end of a connected AF_UNIX datagram socketpair, which keeps
// datagram boundaries the way a utun control socket does, and the other end's fd.
// sndbuf is the tun end's send buffer, which caps the largest datagram it accepts.
func newSocketpairTun(t *testing.T, sndbuf int) (*tun, int) {
t.Helper()
fds, err := unix.Socketpair(unix.AF_UNIX, unix.SOCK_DGRAM, 0)
require.NoError(t, err)
require.NoError(t, unix.SetsockoptInt(fds[0], unix.SOL_SOCKET, unix.SO_SNDBUF, sndbuf))
require.NoError(t, unix.SetsockoptInt(fds[1], unix.SOL_SOCKET, unix.SO_RCVBUF, 1<<20))
// A dropped datagram fails the read-back instead of hanging it.
require.NoError(t, unix.SetsockoptTimeval(fds[1], unix.SOL_SOCKET, unix.SO_RCVTIMEO, &unix.Timeval{Sec: 2}))
require.NoError(t, unix.SetNonblock(fds[0], true))
f := os.NewFile(uintptr(fds[0]), "socketpair")
t.Cleanup(func() {
_ = f.Close()
_ = unix.Close(fds[1])
})
return &tun{f: f, l: test.NewLogger()}, fds[1]
}
// testTunPkt returns packet i of size bytes, alternating IPv4 and IPv6, and the same packet as a utun
// datagram, behind its AF prefix.
func testTunPkt(i, size int) (pkt, wire []byte) {
pkt = make([]byte, size)
pkt[0] = 0x45
af := byte(syscall.AF_INET)
if i%2 == 1 {
pkt[0] = 0x60
af = syscall.AF_INET6
}
pkt[1] = byte(i)
pkt[2] = byte(i >> 8)
return pkt, append([]byte{0, 0, 0, af}, pkt...)
}
// TestTunQueueReadDrains pins that Read hands back every queued packet, AF prefix stripped and in
// order, capped at tunReadBatch per call, and doesn't wait for more once the queue is empty.
func TestTunQueueReadDrains(t *testing.T) {
tn, w := newSocketpairTun(t, 1<<20)
// An AF_UNIX datagram send is bounded by the receiver's buffer, here the tun's end.
rc, err := tn.f.SyscallConn()
require.NoError(t, err)
require.NoError(t, rc.Control(func(fd uintptr) {
require.NoError(t, unix.SetsockoptInt(int(fd), unix.SOL_SOCKET, unix.SO_RCVBUF, 1<<20))
}))
q := &tunQueue{t: tn, buf: make([]byte, tunReadArena)}
total := tunReadBatch + 3
var want [][]byte
for i := range total {
pkt, wire := testTunPkt(i, 60+i)
_, err := unix.Write(w, wire)
require.NoError(t, err)
want = append(want, pkt)
}
var got [][]byte
for _, size := range []int{tunReadBatch, 3} {
pkts, err := q.Read()
require.NoError(t, err)
require.Len(t, pkts, size)
for _, p := range pkts {
got = append(got, p.Clone().Bytes)
}
}
assert.Equal(t, want, got)
}
// TestTunQueueReadClipsPackets pins that each returned packet's capacity ends at its own bytes, so
// appending to one can't overwrite the next.
func TestTunQueueReadClipsPackets(t *testing.T) {
tn, w := newSocketpairTun(t, 1<<20)
q := &tunQueue{t: tn, buf: make([]byte, tunReadArena)}
for i := range 2 {
_, wire := testTunPkt(i, 100)
_, err := unix.Write(w, wire)
require.NoError(t, err)
}
pkts, err := q.Read()
require.NoError(t, err)
require.Len(t, pkts, 2)
assert.Equal(t, len(pkts[0].Bytes), cap(pkts[0].Bytes))
}