mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-16 21:36:52 +01:00
Compare commits
3
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
b4158b3855 | ||
|
|
905d01aee5 | ||
|
|
d5062dacf0 |
No files matched your search
@@ -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
@@ -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
@@ -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 {
|
||||
|
||||
@@ -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
|
||||
}
|
||||
@@ -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())
|
||||
}
|
||||
@@ -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
@@ -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()
|
||||
}
|
||||
@@ -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
@@ -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
@@ -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
|
||||
|
||||
@@ -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
@@ -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 {
|
||||
|
||||
@@ -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)
|
||||
}
|
||||
@@ -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
@@ -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)
|
||||
|
||||
@@ -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)
|
||||
}
|
||||
@@ -435,65 +435,3 @@ func testPP(pkt []byte) *firewall.ParsedPacket {
|
||||
}
|
||||
return pp
|
||||
}
|
||||
|
||||
// fakeTunBatchWriter records each WriteBatch call and each plain Write separately.
|
||||
type fakeTunBatchWriter struct {
|
||||
writes [][]byte
|
||||
batches [][][]byte
|
||||
}
|
||||
|
||||
func (w *fakeTunBatchWriter) Write(p []byte) (int, error) {
|
||||
w.writes = append(w.writes, bytes.Clone(p))
|
||||
return len(p), nil
|
||||
}
|
||||
|
||||
func (w *fakeTunBatchWriter) WriteBatch(pkts [][]byte) error {
|
||||
var b [][]byte
|
||||
for _, p := range pkts {
|
||||
b = append(b, bytes.Clone(p))
|
||||
}
|
||||
w.batches = append(w.batches, b)
|
||||
return nil
|
||||
}
|
||||
|
||||
// TestPassthroughUsesWriteBatch pins that a writer implementing tio.BatchWriter gets the whole
|
||||
// passthrough lane in one WriteBatch per Flush, in order, and no plain Writes; an empty Flush
|
||||
// makes no call.
|
||||
func TestPassthroughUsesWriteBatch(t *testing.T) {
|
||||
w := &fakeTunBatchWriter{}
|
||||
m := newTestMultiCoalescer(t, w)
|
||||
k := &keySeq{epoch: 1}
|
||||
|
||||
var want [][]byte
|
||||
for i := range 5 {
|
||||
icmp := make([]byte, 28)
|
||||
icmp[0] = 0x45
|
||||
icmp[3] = 28
|
||||
icmp[9] = 1
|
||||
icmp[20] = byte(i)
|
||||
want = append(want, icmp)
|
||||
if err := m.Commit(icmp, k.next(), testPP(icmp)); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
if err := m.Flush(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := m.Flush(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(w.writes) != 0 {
|
||||
t.Fatalf("got %d plain Writes, want 0", len(w.writes))
|
||||
}
|
||||
if len(w.batches) != 1 {
|
||||
t.Fatalf("got %d WriteBatch calls, want 1", len(w.batches))
|
||||
}
|
||||
for i, p := range w.batches[0] {
|
||||
if !bytes.Equal(p, want[i]) {
|
||||
t.Fatalf("packet %d: got % x, want % x", i, p, want[i])
|
||||
}
|
||||
}
|
||||
if len(w.batches[0]) != len(want) {
|
||||
t.Fatalf("got %d packets, want %d", len(w.batches[0]), len(want))
|
||||
}
|
||||
}
|
||||
@@ -2,23 +2,18 @@ package batch
|
||||
|
||||
import (
|
||||
"io"
|
||||
|
||||
"github.com/slackhq/nebula/overlay/tio"
|
||||
)
|
||||
|
||||
// Passthrough is MultiCoalescer's verbatim lane: no coalescing, packets are written at Flush in the
|
||||
// order enqueued, in one WriteBatch when out implements tio.BatchWriter.
|
||||
// Passthrough is MultiCoalescer's verbatim lane: no batching, packets are written at Flush in the
|
||||
// order enqueued.
|
||||
type Passthrough struct {
|
||||
out io.Writer
|
||||
bw tio.BatchWriter // nil: Flush writes one packet per Write
|
||||
slots [][]byte
|
||||
}
|
||||
|
||||
func NewPassthrough(w io.Writer) *Passthrough {
|
||||
bw, _ := w.(tio.BatchWriter)
|
||||
return &Passthrough{
|
||||
out: w,
|
||||
bw: bw,
|
||||
slots: make([][]byte, 0, 128),
|
||||
}
|
||||
}
|
||||
@@ -31,16 +26,10 @@ func (p *Passthrough) enqueue(pkt []byte) error {
|
||||
|
||||
func (p *Passthrough) Flush() error {
|
||||
var firstErr error
|
||||
if p.bw != nil {
|
||||
if len(p.slots) > 0 {
|
||||
firstErr = p.bw.WriteBatch(p.slots)
|
||||
}
|
||||
} else {
|
||||
for _, s := range p.slots {
|
||||
_, err := p.out.Write(s)
|
||||
if err != nil && firstErr == nil {
|
||||
firstErr = err
|
||||
}
|
||||
for _, s := range p.slots {
|
||||
_, err := p.out.Write(s)
|
||||
if err != nil && firstErr == nil {
|
||||
firstErr = err
|
||||
}
|
||||
}
|
||||
clear(p.slots)
|
||||
|
||||
+2
-17
@@ -15,13 +15,9 @@ type singleQueue struct {
|
||||
|
||||
// NewSingleQueue wraps a one-datagram-per-Read ReadWriteCloser (a legacy tun device) into a Queue.
|
||||
// bufSize is the per-queue read scratch size and must be at least the largest datagram the source can return.
|
||||
// Close closes rwc. The Queue implements BatchWriter when rwc does.
|
||||
// Close closes rwc.
|
||||
func NewSingleQueue(rwc io.ReadWriteCloser, bufSize int) Queue {
|
||||
q := &singleQueue{rw: rwc, closer: rwc, buf: make([]byte, bufSize)}
|
||||
if bw, ok := rwc.(BatchWriter); ok {
|
||||
return &batchSingleQueue{singleQueue: q, bw: bw}
|
||||
}
|
||||
return q
|
||||
return &singleQueue{rw: rwc, closer: rwc, buf: make([]byte, bufSize)}
|
||||
}
|
||||
|
||||
// NewSingleQueueNoClose is NewSingleQueue for a source owned by someone else,
|
||||
@@ -51,14 +47,3 @@ func (q *singleQueue) Close() error {
|
||||
}
|
||||
return q.closer.Close()
|
||||
}
|
||||
|
||||
// batchSingleQueue is a singleQueue whose source also implements BatchWriter.
|
||||
// It is a separate type so a plain singleQueue never advertises WriteBatch.
|
||||
type batchSingleQueue struct {
|
||||
*singleQueue
|
||||
bw BatchWriter
|
||||
}
|
||||
|
||||
func (q *batchSingleQueue) WriteBatch(pkts [][]byte) error {
|
||||
return q.bw.WriteBatch(pkts)
|
||||
}
|
||||
@@ -145,14 +145,3 @@ func SupportsGSO(w io.Writer, want GSOProto) (GSOWriter, bool) {
|
||||
return gw, false
|
||||
}
|
||||
}
|
||||
|
||||
// BatchWriter is implemented by Queues that can emit several already-segmented packets in one call.
|
||||
// Backends without a batched write do not implement it and callers loop over Write.
|
||||
//
|
||||
// pkts are borrowed: WriteBatch must not retain them past its return.
|
||||
// A returned error doesn't say which packets were delivered, so callers must not retry the batch.
|
||||
// Safe for concurrent use, like Write.
|
||||
type BatchWriter interface {
|
||||
io.Writer
|
||||
WriteBatch(pkts [][]byte) error
|
||||
}
|
||||
+9
-244
@@ -8,7 +8,6 @@ import (
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"os"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
"unsafe"
|
||||
@@ -34,35 +33,6 @@ type tun struct {
|
||||
// and routes for it. NEPacketTunnelProvider on darwin does this.
|
||||
hostOwned bool
|
||||
l *slog.Logger
|
||||
|
||||
// noSendmsgX is set once sendmsg_x is refused; WriteBatch then writes one packet at a time.
|
||||
noSendmsgX atomic.Bool
|
||||
batchMu sync.Mutex
|
||||
batch tunBatch
|
||||
}
|
||||
|
||||
// tunWriteBatch is how many packets one sendmsg_x call may carry.
|
||||
const tunWriteBatch = 64
|
||||
|
||||
// tunBatch is WriteBatch's scratch, guarded by tun.batchMu. The kernel reads every entry in place.
|
||||
type tunBatch struct {
|
||||
heads [tunWriteBatch][4]byte
|
||||
iovs [tunWriteBatch][2]unix.Iovec
|
||||
hdrs [tunWriteBatch]msghdrX
|
||||
pkts [tunWriteBatch][]byte
|
||||
}
|
||||
|
||||
// msghdrX mirrors xnu's struct msghdr_x (bsd/sys/socket_private.h).
|
||||
// Keep in sync with msghdrX in udp/udp_darwin.go.
|
||||
type msghdrX struct {
|
||||
Name *byte
|
||||
Namelen uint32
|
||||
Iov *unix.Iovec
|
||||
Iovlen int32
|
||||
Control *byte
|
||||
Controllen uint32
|
||||
Flags int32
|
||||
Datalen uint64
|
||||
}
|
||||
|
||||
type ifReq struct {
|
||||
@@ -637,74 +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) WriteBatch(pkts [][]byte) error { return q.t.WriteBatch(pkts) }
|
||||
|
||||
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).
|
||||
@@ -713,12 +615,16 @@ func (t *tun) Write(from []byte) (int, error) {
|
||||
return 0, syscall.EIO
|
||||
}
|
||||
|
||||
ipVer := from[0] >> 4
|
||||
var head [4]byte
|
||||
af, err := tunAF(from)
|
||||
if err != nil {
|
||||
return 0, err
|
||||
switch ipVer {
|
||||
case 4:
|
||||
head[3] = syscall.AF_INET
|
||||
case 6:
|
||||
head[3] = syscall.AF_INET6
|
||||
default:
|
||||
return 0, fmt.Errorf("unable to determine IP version from packet")
|
||||
}
|
||||
head[3] = af
|
||||
|
||||
// Grab rc as a local so the compiler can devirtualize the call and keep the closure on the stack.
|
||||
rc, err := t.f.SyscallConn()
|
||||
@@ -751,147 +657,6 @@ func (t *tun) Write(from []byte) (int, error) {
|
||||
return n - 4, nil
|
||||
}
|
||||
|
||||
// tunAF returns the utun address-family prefix byte for an IP packet.
|
||||
func tunAF(pkt []byte) (byte, error) {
|
||||
switch pkt[0] >> 4 {
|
||||
case 4:
|
||||
return syscall.AF_INET, nil
|
||||
case 6:
|
||||
return syscall.AF_INET6, nil
|
||||
default:
|
||||
return 0, fmt.Errorf("unable to determine IP version from packet")
|
||||
}
|
||||
}
|
||||
|
||||
// WriteBatch writes pkts to the utun device with sendmsg_x, xnu's private batched sendmsg, up to
|
||||
// tunWriteBatch packets per syscall. The kernel still hands each packet to utun on its own, so this
|
||||
// saves syscalls, not per-packet kernel work. Safe for concurrent use.
|
||||
//
|
||||
// An empty packet or one with no IP version is skipped and reported, as Write would. Any other
|
||||
// error from sendmsg_x means the kernel took an unknown prefix of that call and dropped the rest, so
|
||||
// it is reported rather than retried, which could deliver packets twice.
|
||||
//
|
||||
// Under mbuf exhaustion, sendmsg_x silently drops packets that writev would have delivered: the
|
||||
// kernel counts each packet as sent once it is copied in, and when a later allocation fails it
|
||||
// frees that prefix unsent and returns its length as a short count, which is indistinguishable
|
||||
// from a real one.
|
||||
func (t *tun) WriteBatch(pkts [][]byte) error {
|
||||
if t.noSendmsgX.Load() {
|
||||
return t.writeEach(pkts)
|
||||
}
|
||||
|
||||
t.batchMu.Lock()
|
||||
defer t.batchMu.Unlock()
|
||||
b := &t.batch
|
||||
var firstErr error
|
||||
for len(pkts) > 0 {
|
||||
n := 0
|
||||
for len(pkts) > 0 && n < tunWriteBatch {
|
||||
p := pkts[0]
|
||||
pkts = pkts[1:]
|
||||
var af byte
|
||||
err := error(syscall.EIO)
|
||||
if len(p) > 0 {
|
||||
af, err = tunAF(p)
|
||||
}
|
||||
if err != nil {
|
||||
if firstErr == nil {
|
||||
firstErr = err
|
||||
}
|
||||
continue
|
||||
}
|
||||
b.heads[n] = [4]byte{3: af}
|
||||
b.iovs[n] = [2]unix.Iovec{
|
||||
{Base: &b.heads[n][0], Len: 4},
|
||||
{Base: &p[0], Len: uint64(len(p))},
|
||||
}
|
||||
b.hdrs[n] = msghdrX{Iov: &b.iovs[n][0], Iovlen: 2}
|
||||
b.pkts[n] = p
|
||||
n++
|
||||
}
|
||||
if n == 0 {
|
||||
continue
|
||||
}
|
||||
|
||||
for off := 0; off < n; {
|
||||
sent, err := t.sendmsgX(off, n)
|
||||
switch {
|
||||
case err == nil && sent > 0:
|
||||
// The kernel stops early without an error on a packet larger than the socket's send
|
||||
// buffer, or when sending a later packet fails with ENOBUFS; resend the remainder.
|
||||
off += sent
|
||||
case err == nil:
|
||||
if werr := t.writeEach(b.pkts[off:n]); werr != nil && firstErr == nil {
|
||||
firstErr = werr
|
||||
}
|
||||
off = n
|
||||
case err == unix.EMSGSIZE:
|
||||
// Only the first packet being larger than the socket's send buffer fails the whole call,
|
||||
// before the kernel takes any; Write reports that one and the rest go out in the next call.
|
||||
if werr := t.writeEach(b.pkts[off : off+1]); werr != nil && firstErr == nil {
|
||||
firstErr = werr
|
||||
}
|
||||
off++
|
||||
case err == unix.ENOSYS || err == unix.EPERM || err == unix.EOPNOTSUPP:
|
||||
// sendmsg_x is private API: fall back to writev if a kernel or sandbox refuses it.
|
||||
if t.noSendmsgX.CompareAndSwap(false, true) {
|
||||
t.l.Warn("sendmsg_x unavailable on the tun device, writing one packet per syscall", "error", err)
|
||||
}
|
||||
if werr := t.writeEach(b.pkts[off:n]); werr != nil && firstErr == nil {
|
||||
firstErr = werr
|
||||
}
|
||||
clear(b.iovs[:n])
|
||||
clear(b.pkts[:n])
|
||||
if werr := t.writeEach(pkts); werr != nil && firstErr == nil {
|
||||
firstErr = werr
|
||||
}
|
||||
return firstErr
|
||||
default:
|
||||
if firstErr == nil {
|
||||
firstErr = err
|
||||
}
|
||||
off = n
|
||||
}
|
||||
}
|
||||
clear(b.iovs[:n])
|
||||
clear(b.pkts[:n])
|
||||
}
|
||||
return firstErr
|
||||
}
|
||||
|
||||
// sendmsgX hands entries off through n-1 of t.batch to sendmsg_x and returns how many the kernel took.
|
||||
func (t *tun) sendmsgX(off, n int) (int, error) {
|
||||
rc, err := t.f.SyscallConn()
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
var sent uintptr
|
||||
var errno syscall.Errno
|
||||
err = rc.Write(func(fd uintptr) bool {
|
||||
sent, _, errno = unix.Syscall6(unix.SYS_SENDMSG_X, fd, uintptr(unsafe.Pointer(&t.batch.hdrs[off])), uintptr(n-off), 0, 0, 0)
|
||||
// sendmsg_x reports EAGAIN only when it took nothing; a partial batch returns its count.
|
||||
return !errno.Temporary()
|
||||
})
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
if errno != 0 {
|
||||
return 0, errno
|
||||
}
|
||||
return int(sent), nil
|
||||
}
|
||||
|
||||
// writeEach writes pkts one at a time with Write.
|
||||
func (t *tun) writeEach(pkts [][]byte) error {
|
||||
var firstErr error
|
||||
for _, p := range pkts {
|
||||
if _, err := t.Write(p); err != nil && firstErr == nil {
|
||||
firstErr = err
|
||||
}
|
||||
}
|
||||
return firstErr
|
||||
}
|
||||
|
||||
func (t *tun) Networks() []netip.Prefix {
|
||||
return t.vpnNetworks
|
||||
}
|
||||
@@ -901,5 +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
|
||||
}
|
||||
@@ -1,201 +0,0 @@
|
||||
//go:build !ios && !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"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 writing to one end of a connected AF_UNIX datagram socketpair, which
|
||||
// takes sendmsg_x the way a utun control socket does, and the other end's fd for reading back.
|
||||
// sndbuf is the writer'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 datagram the utun
|
||||
// device should receive for it.
|
||||
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...)
|
||||
}
|
||||
|
||||
// readTunBack asserts r receives exactly want, in order.
|
||||
func readTunBack(t *testing.T, r int, want [][]byte) {
|
||||
t.Helper()
|
||||
buf := make([]byte, 4096)
|
||||
for i, w := range want {
|
||||
n, _, err := unix.Recvfrom(r, buf, 0)
|
||||
require.NoError(t, err, "datagram %d", i)
|
||||
if !bytes.Equal(w, buf[:n]) {
|
||||
t.Fatalf("datagram %d: got % x, want % x", i, buf[:n], w)
|
||||
}
|
||||
}
|
||||
_, _, err := unix.Recvfrom(r, buf, unix.MSG_DONTWAIT)
|
||||
assert.ErrorIs(t, err, unix.EAGAIN, "extra datagrams delivered")
|
||||
}
|
||||
|
||||
// forEachTunWritePath runs fn once over sendmsg_x and once over the per-packet writev fallback.
|
||||
func forEachTunWritePath(t *testing.T, fn func(t *testing.T, fallback bool)) {
|
||||
for _, fallback := range []bool{false, true} {
|
||||
name := "sendmsg_x"
|
||||
if fallback {
|
||||
name = "writev"
|
||||
}
|
||||
t.Run(name, func(t *testing.T) { fn(t, fallback) })
|
||||
}
|
||||
}
|
||||
|
||||
// TestTunWriteBatch pins that WriteBatch delivers every packet whole, in order and behind the right
|
||||
// utun AF prefix, across several sendmsg_x calls, and returns nil.
|
||||
func TestTunWriteBatch(t *testing.T) {
|
||||
forEachTunWritePath(t, func(t *testing.T, fallback bool) {
|
||||
tn, r := newSocketpairTun(t, 1<<20)
|
||||
tn.noSendmsgX.Store(fallback)
|
||||
|
||||
var pkts, want [][]byte
|
||||
for i := range 3*tunWriteBatch + 5 {
|
||||
p, w := testTunPkt(i, 60+i)
|
||||
pkts = append(pkts, p)
|
||||
want = append(want, w)
|
||||
}
|
||||
require.NoError(t, tn.WriteBatch(pkts))
|
||||
assert.Equal(t, fallback, tn.noSendmsgX.Load())
|
||||
readTunBack(t, r, want)
|
||||
})
|
||||
}
|
||||
|
||||
// TestTunWriteBatchSkipsInvalid pins that an empty packet or one with no IP version is skipped
|
||||
// without shifting the packets after it, and that the first such error is the one reported.
|
||||
func TestTunWriteBatchSkipsInvalid(t *testing.T) {
|
||||
forEachTunWritePath(t, func(t *testing.T, fallback bool) {
|
||||
tn, r := newSocketpairTun(t, 1<<20)
|
||||
tn.noSendmsgX.Store(fallback)
|
||||
|
||||
var pkts, want [][]byte
|
||||
for i := range 20 {
|
||||
p, w := testTunPkt(i, 60)
|
||||
pkts = append(pkts, p)
|
||||
want = append(want, w)
|
||||
}
|
||||
pkts = append(pkts[:10], append([][]byte{{0x10, 1, 2}, {}}, pkts[10:]...)...)
|
||||
|
||||
err := tn.WriteBatch(pkts)
|
||||
assert.ErrorContains(t, err, "IP version")
|
||||
readTunBack(t, r, want)
|
||||
})
|
||||
}
|
||||
|
||||
// TestTunWriteBatchOversize pins that a packet larger than the socket's send buffer drops only
|
||||
// itself and is reported, whether sendmsg_x reaches it mid-call (a short count) or first (EMSGSIZE
|
||||
// for the whole call). The send buffer is 1024 bytes and the oversize packet 2000.
|
||||
func TestTunWriteBatchOversize(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
at int
|
||||
}{
|
||||
{"mid-call", tunWriteBatch + 6},
|
||||
{"first-in-call", tunWriteBatch},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
forEachTunWritePath(t, func(t *testing.T, fallback bool) {
|
||||
tn, r := newSocketpairTun(t, 1024)
|
||||
tn.noSendmsgX.Store(fallback)
|
||||
|
||||
var pkts, want [][]byte
|
||||
for i := range 2*tunWriteBatch + 10 {
|
||||
size := 100
|
||||
if i == tc.at {
|
||||
size = 2000
|
||||
}
|
||||
p, w := testTunPkt(i, size)
|
||||
pkts = append(pkts, p)
|
||||
if i != tc.at {
|
||||
want = append(want, w)
|
||||
}
|
||||
}
|
||||
err := tn.WriteBatch(pkts)
|
||||
assert.ErrorIs(t, err, unix.EMSGSIZE)
|
||||
assert.Equal(t, fallback, tn.noSendmsgX.Load())
|
||||
readTunBack(t, r, want)
|
||||
})
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// 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))
|
||||
}
|
||||
+6
-276
@@ -10,7 +10,6 @@ import (
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
"unsafe"
|
||||
|
||||
@@ -23,9 +22,6 @@ type StdConn struct {
|
||||
isV4 bool
|
||||
sysFd uintptr
|
||||
l *slog.Logger
|
||||
|
||||
noSendmsgX atomic.Bool
|
||||
sb *sendScratch
|
||||
}
|
||||
|
||||
var _ Conn = &StdConn{}
|
||||
@@ -143,138 +139,11 @@ func (u *StdConn) WriteTo(b []byte, ap netip.AddrPort) error {
|
||||
}
|
||||
}
|
||||
|
||||
// sendBatch is how many datagrams one sendmsg_x call may carry.
|
||||
const sendBatch = 64
|
||||
|
||||
// sendScratch is WriteBatch's scratch. The kernel reads every entry in place.
|
||||
type sendScratch struct {
|
||||
names [sendBatch]unix.RawSockaddrInet6
|
||||
iovs [sendBatch]unix.Iovec
|
||||
hdrs [sendBatch]msghdrX
|
||||
// idx maps each entry back to its index in WriteBatch's bufs.
|
||||
idx [sendBatch]int
|
||||
}
|
||||
|
||||
// WriteBatch sends bufs with sendmsg_x, darwin's private batched sendmsg, so one syscall carries up to
|
||||
// sendBatch datagrams. On this unconnected socket xnu still runs each message through sendit, so the
|
||||
// saving is the syscall crossings, not the per-send policy checks.
|
||||
//
|
||||
// xnu's per-message loop stops at the first message that fails. For the errors in sentNothing it reports
|
||||
// how many went out; for any other it returns only the errno, with the messages before it already sent.
|
||||
// Each call therefore carries one run of datagrams to the same destination: a destination the kernel
|
||||
// refuses fails on its first datagram, so a failed call costs that run and nothing else, and no datagram
|
||||
// is ever resent after the kernel may have taken it.
|
||||
//
|
||||
// TODO: WriteTo maps EWOULDBLOCK to an error, so a full send buffer
|
||||
// silently drops the rest of a burst (linux blocks instead). Poll for
|
||||
// writability on EAGAIN before giving up on the remainder.
|
||||
func (u *StdConn) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error) {
|
||||
if u.noSendmsgX.Load() {
|
||||
return u.writeEach(bufs, addrs), nil
|
||||
}
|
||||
if u.sb == nil {
|
||||
u.sb = new(sendScratch)
|
||||
}
|
||||
b := u.sb
|
||||
written := 0
|
||||
for i := 0; i < len(bufs); {
|
||||
n := 0
|
||||
for ; i < len(bufs) && n < sendBatch; i++ {
|
||||
namelen, err := u.putSockaddr(&b.names[n], addrs[i])
|
||||
if err != nil {
|
||||
u.l.Debug("failed to write packet in batch", "udpAddr", addrs[i], "error", err)
|
||||
continue
|
||||
}
|
||||
b.iovs[n] = unix.Iovec{}
|
||||
if len(bufs[i]) > 0 {
|
||||
b.iovs[n].Base = &bufs[i][0]
|
||||
b.iovs[n].SetLen(len(bufs[i]))
|
||||
}
|
||||
b.hdrs[n] = msghdrX{Name: (*byte)(unsafe.Pointer(&b.names[n])), Namelen: namelen, Iov: &b.iovs[n], Iovlen: 1}
|
||||
b.idx[n] = i
|
||||
n++
|
||||
}
|
||||
|
||||
for off := 0; off < n; {
|
||||
dst := addrs[b.idx[off]]
|
||||
end := off + 1
|
||||
for end < n && addrs[b.idx[end]] == dst {
|
||||
end++
|
||||
}
|
||||
sent, errno := u.sendmsgX(off, end)
|
||||
switch {
|
||||
case errno == 0 && sent > 0:
|
||||
written += sent
|
||||
off += sent
|
||||
continue
|
||||
case sentNothing(errno):
|
||||
// The datagram at off failed on its own account. sendto delivers or reports it, as without
|
||||
// batching, and the rest of the run goes back to sendmsg_x.
|
||||
j := b.idx[off]
|
||||
written += u.writeEach(bufs[j:j+1], addrs[j:j+1])
|
||||
off++
|
||||
continue
|
||||
case errno == 0:
|
||||
case errno == unix.ENOSYS || errno == unix.EOPNOTSUPP:
|
||||
u.fallBack(errno)
|
||||
case errno == unix.EPERM || errno == unix.EINVAL:
|
||||
// Either can refuse one destination, but a datagram that sendto delivers was refused by
|
||||
// sendmsg_x itself, as a sandbox or an older kernel would.
|
||||
j := b.idx[off]
|
||||
if u.writeEach(bufs[j:j+1], addrs[j:j+1]) == 0 {
|
||||
off = end
|
||||
continue
|
||||
}
|
||||
written++
|
||||
off++
|
||||
u.fallBack(errno)
|
||||
default:
|
||||
u.l.Debug("failed to write packets in batch", "udpAddr", dst, "packets", end-off, "error", errno)
|
||||
off = end
|
||||
continue
|
||||
}
|
||||
// The kernel took nothing from this call, so the rest can go out one datagram at a time.
|
||||
for _, j := range b.idx[off:n] {
|
||||
written += u.writeEach(bufs[j:j+1], addrs[j:j+1])
|
||||
}
|
||||
off = n
|
||||
if u.noSendmsgX.Load() {
|
||||
clear(b.iovs[:n])
|
||||
return written + u.writeEach(bufs[i:], addrs[i:]), nil
|
||||
}
|
||||
}
|
||||
clear(b.iovs[:n])
|
||||
}
|
||||
return written, nil
|
||||
}
|
||||
|
||||
// sendmsgX hands entries off through end-1 of u.sb to sendmsg_x and returns how many the kernel took.
|
||||
// The socket is non-blocking, so a full send buffer returns EAGAIN rather than waiting.
|
||||
func (u *StdConn) sendmsgX(off, end int) (int, syscall.Errno) {
|
||||
for {
|
||||
r0, _, errno := unix.Syscall6(unix.SYS_SENDMSG_X, u.sysFd, uintptr(unsafe.Pointer(&u.sb.hdrs[off])), uintptr(end-off), 0, 0, 0)
|
||||
if errno == unix.EINTR {
|
||||
continue
|
||||
}
|
||||
return int(r0), errno
|
||||
}
|
||||
}
|
||||
|
||||
// sentNothing reports whether sendmsg_x failing with errno means no datagram went out: once any has, xnu
|
||||
// turns these errors into a short count instead.
|
||||
func sentNothing(errno syscall.Errno) bool {
|
||||
return errno == unix.EWOULDBLOCK || errno == unix.ENOBUFS || errno == unix.EMSGSIZE
|
||||
}
|
||||
|
||||
// fallBack switches WriteBatch to one sendto per datagram for the life of the socket.
|
||||
func (u *StdConn) fallBack(errno syscall.Errno) {
|
||||
if u.noSendmsgX.CompareAndSwap(false, true) {
|
||||
u.l.Warn("sendmsg_x unavailable, sending one datagram per syscall", "error", errno)
|
||||
}
|
||||
}
|
||||
|
||||
// writeEach sends bufs one at a time with WriteTo and returns how many were written.
|
||||
func (u *StdConn) writeEach(bufs [][]byte, addrs []netip.AddrPort) int {
|
||||
// An un-sendable destination costs its own packet, never the ones behind it in the batch.
|
||||
// TODO: WriteTo maps EWOULDBLOCK to an error, so a full send buffer
|
||||
// silently drops the rest of a burst (linux blocks instead). Poll for
|
||||
// writability on EAGAIN before giving up on the remainder.
|
||||
written := 0
|
||||
for i, b := range bufs {
|
||||
if err := u.WriteTo(b, addrs[i]); err == nil {
|
||||
@@ -283,23 +152,7 @@ func (u *StdConn) writeEach(bufs [][]byte, addrs []netip.AddrPort) int {
|
||||
u.l.Debug("failed to write packet in batch", "udpAddr", addrs[i], "error", err)
|
||||
}
|
||||
}
|
||||
return written
|
||||
}
|
||||
|
||||
// putSockaddr writes ap into sa in the socket's address family, as WriteTo would, and returns its length.
|
||||
func (u *StdConn) putSockaddr(sa *unix.RawSockaddrInet6, ap netip.AddrPort) (uint32, error) {
|
||||
if u.isV4 {
|
||||
if ap.Addr().Is6() {
|
||||
return 0, ErrInvalidIPv6RemoteForSocket
|
||||
}
|
||||
sa4 := (*unix.RawSockaddrInet4)(unsafe.Pointer(sa))
|
||||
*sa4 = unix.RawSockaddrInet4{Family: unix.AF_INET, Addr: ap.Addr().As4()}
|
||||
binary.BigEndian.PutUint16((*[2]byte)(unsafe.Pointer(&sa4.Port))[:], ap.Port())
|
||||
return unix.SizeofSockaddrInet4, nil
|
||||
}
|
||||
*sa = unix.RawSockaddrInet6{Family: unix.AF_INET6, Addr: ap.Addr().As16()}
|
||||
binary.BigEndian.PutUint16((*[2]byte)(unsafe.Pointer(&sa.Port))[:], ap.Port())
|
||||
return unix.SizeofSockaddrInet6, nil
|
||||
return written, nil
|
||||
}
|
||||
|
||||
func (u *StdConn) LocalAddr() (netip.AddrPort, error) {
|
||||
@@ -327,121 +180,11 @@ func NewUDPStatsEmitter(udpConns []Conn) func() {
|
||||
return func() {}
|
||||
}
|
||||
|
||||
// recvBatch is how many datagrams one recvmsg_x call may return.
|
||||
const recvBatch = 64
|
||||
|
||||
// msghdrX mirrors xnu's struct msghdr_x (bsd/sys/socket_private.h). recvmsg_x reports each
|
||||
// datagram's length in Datalen rather than in its return value.
|
||||
// Keep in sync with msghdrX in overlay/tun_darwin.go.
|
||||
type msghdrX struct {
|
||||
Name *byte
|
||||
Namelen uint32
|
||||
Iov *unix.Iovec
|
||||
Iovlen int32
|
||||
Control *byte
|
||||
Controllen uint32
|
||||
Flags int32
|
||||
Datalen uint64
|
||||
}
|
||||
|
||||
// ListenOut drains the socket with recvmsg_x, darwin's private batched recvmsg, so one syscall reads
|
||||
// up to recvBatch datagrams instead of one.
|
||||
func (u *StdConn) ListenOut(r EncReader, flush func()) error {
|
||||
rc, err := u.UDPConn.SyscallConn()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
bufs := make([][]byte, recvBatch)
|
||||
names := make([]unix.RawSockaddrInet6, recvBatch)
|
||||
iovs := make([]unix.Iovec, recvBatch)
|
||||
hdrs := make([]msghdrX, recvBatch)
|
||||
for i := range hdrs {
|
||||
bufs[i] = make([]byte, MTU)
|
||||
iovs[i].Base = &bufs[i][0]
|
||||
iovs[i].SetLen(MTU)
|
||||
hdrs[i].Iov = &iovs[i]
|
||||
hdrs[i].Iovlen = 1
|
||||
hdrs[i].Name = (*byte)(unsafe.Pointer(&names[i]))
|
||||
}
|
||||
|
||||
for {
|
||||
var n int
|
||||
var errno syscall.Errno
|
||||
err := rc.Read(func(fd uintptr) bool {
|
||||
for i := range hdrs {
|
||||
hdrs[i].Namelen = unix.SizeofSockaddrInet6
|
||||
hdrs[i].Flags = 0
|
||||
hdrs[i].Datalen = 0
|
||||
}
|
||||
r0, _, e := unix.Syscall6(unix.SYS_RECVMSG_X, fd, uintptr(unsafe.Pointer(&hdrs[0])), recvBatch, 0, 0, 0)
|
||||
if e == unix.EAGAIN {
|
||||
return false
|
||||
}
|
||||
n, errno = int(r0), e
|
||||
return true
|
||||
})
|
||||
if err != nil {
|
||||
if errors.Is(err, net.ErrClosed) {
|
||||
return err
|
||||
}
|
||||
u.l.Error("unexpected udp socket receive error", "error", err)
|
||||
continue
|
||||
}
|
||||
if errno == unix.ENOSYS || errno == unix.EPERM || errno == unix.EOPNOTSUPP {
|
||||
// recvmsg_x is private, so a kernel or sandbox (such as an iOS extension's) may refuse it.
|
||||
u.l.Warn("recvmsg_x unavailable, reading one datagram per syscall", "error", errno)
|
||||
return u.listenOutSingle(r, flush)
|
||||
}
|
||||
if errno != 0 {
|
||||
if errno != unix.EINTR {
|
||||
u.l.Error("unexpected udp socket receive error", "error", errno)
|
||||
}
|
||||
continue
|
||||
}
|
||||
if err := checkMsghdrX(hdrs, names, n); err != nil {
|
||||
// The batch was read through a layout the kernel no longer writes, so none of it is trustworthy.
|
||||
u.l.Warn("recvmsg_x returned an unexpected header, reading one datagram per syscall", "error", err)
|
||||
return u.listenOutSingle(r, flush)
|
||||
}
|
||||
|
||||
for i := 0; i < n; i++ {
|
||||
addr, ok := sockaddrToAddrPort(&names[i])
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
l := int(hdrs[i].Datalen)
|
||||
r(addr, bufs[i][:l:l])
|
||||
}
|
||||
flush()
|
||||
}
|
||||
}
|
||||
|
||||
// checkMsghdrX rejects a recvmsg_x result that intact msghdr_x entries can't produce, which is how a change
|
||||
// to xnu's private struct layout would show up.
|
||||
func checkMsghdrX(hdrs []msghdrX, names []unix.RawSockaddrInet6, n int) error {
|
||||
if n > len(hdrs) {
|
||||
return fmt.Errorf("returned %d datagrams for %d headers", n, len(hdrs))
|
||||
}
|
||||
for i := range n {
|
||||
if hdrs[i].Datalen > MTU {
|
||||
return fmt.Errorf("datagram %d is %d bytes, past the %d byte buffer", i, hdrs[i].Datalen, MTU)
|
||||
}
|
||||
switch {
|
||||
case names[i].Family == unix.AF_INET && hdrs[i].Namelen == unix.SizeofSockaddrInet4:
|
||||
case names[i].Family == unix.AF_INET6 && hdrs[i].Namelen == unix.SizeofSockaddrInet6:
|
||||
default:
|
||||
return fmt.Errorf("datagram %d has address family %d with length %d", i, names[i].Family, hdrs[i].Namelen)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// listenOutSingle reads one datagram per recvfrom and flushes after each, for when recvmsg_x is refused or misbehaves.
|
||||
func (u *StdConn) listenOutSingle(r EncReader, flush func()) error {
|
||||
buffer := make([]byte, MTU)
|
||||
|
||||
for {
|
||||
// Just read one packet at a time
|
||||
n, rua, err := u.ReadFromUDPAddrPort(buffer)
|
||||
if err != nil {
|
||||
if errors.Is(err, net.ErrClosed) {
|
||||
@@ -456,19 +199,6 @@ func (u *StdConn) listenOutSingle(r EncReader, flush func()) error {
|
||||
}
|
||||
}
|
||||
|
||||
func sockaddrToAddrPort(sa *unix.RawSockaddrInet6) (netip.AddrPort, bool) {
|
||||
switch sa.Family {
|
||||
case unix.AF_INET:
|
||||
sa4 := (*unix.RawSockaddrInet4)(unsafe.Pointer(sa))
|
||||
port := binary.BigEndian.Uint16((*[2]byte)(unsafe.Pointer(&sa4.Port))[:])
|
||||
return netip.AddrPortFrom(netip.AddrFrom4(sa4.Addr), port), true
|
||||
case unix.AF_INET6:
|
||||
port := binary.BigEndian.Uint16((*[2]byte)(unsafe.Pointer(&sa.Port))[:])
|
||||
return netip.AddrPortFrom(netip.AddrFrom16(sa.Addr).Unmap(), port), true
|
||||
}
|
||||
return netip.AddrPort{}, false
|
||||
}
|
||||
|
||||
func (u *StdConn) SupportsMultipleReaders() bool {
|
||||
return false
|
||||
}
|
||||
|
||||
@@ -1,85 +0,0 @@
|
||||
//go:build !e2e_testing
|
||||
|
||||
package udp
|
||||
|
||||
import (
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// BenchmarkListenOut measures the receive path on loopback: senders flood datagrams sized like a full tunnel
|
||||
// packet, and each op is one datagram delivered to the reader. There are enough senders that the reader, not the
|
||||
// senders, sets the pace. flushes/pkt is 1 when every receive is its own syscall and falls as receives batch. The
|
||||
// senders share the machine, so ns/op is only comparable between runs on the same host.
|
||||
func BenchmarkListenOut(b *testing.B) {
|
||||
for _, tc := range []struct{ name, listen string }{
|
||||
{"v4", "127.0.0.1"},
|
||||
{"v6", "::1"},
|
||||
} {
|
||||
b.Run(tc.name, func(b *testing.B) {
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.AddrPortFrom(netip.MustParseAddr(tc.listen), 0)})
|
||||
if err != nil {
|
||||
b.Fatal(err)
|
||||
}
|
||||
la, err := c.LocalAddr()
|
||||
if err != nil {
|
||||
b.Fatal(err)
|
||||
}
|
||||
const size, senders = 1300, 4
|
||||
txs := make([]net.Conn, senders)
|
||||
for i := range txs {
|
||||
if txs[i], err = net.Dial("udp", la.String()); err != nil {
|
||||
b.Fatal(err)
|
||||
}
|
||||
defer txs[i].Close()
|
||||
}
|
||||
|
||||
target := int64(b.N)
|
||||
var got, flushes atomic.Int64
|
||||
reached := make(chan struct{})
|
||||
done := make(chan struct{})
|
||||
go func() {
|
||||
_ = c.ListenOut(func(netip.AddrPort, []byte) {
|
||||
if got.Add(1) == target {
|
||||
close(reached)
|
||||
}
|
||||
}, func() { flushes.Add(1) })
|
||||
close(done)
|
||||
}()
|
||||
|
||||
// Writes fail with ENOBUFS while the send queue is full; the flood only has to keep the receiver busy.
|
||||
stop := make(chan struct{})
|
||||
var sent sync.WaitGroup
|
||||
for _, tx := range txs {
|
||||
sent.Go(func() {
|
||||
payload := make([]byte, size)
|
||||
for {
|
||||
select {
|
||||
case <-stop:
|
||||
return
|
||||
default:
|
||||
_, _ = tx.Write(payload)
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
b.SetBytes(size)
|
||||
b.ResetTimer()
|
||||
<-reached
|
||||
b.StopTimer()
|
||||
|
||||
close(stop)
|
||||
sent.Wait()
|
||||
if err := c.Close(); err != nil {
|
||||
b.Fatal(err)
|
||||
}
|
||||
<-done
|
||||
b.ReportMetric(float64(flushes.Load())/float64(got.Load()), "flushes/pkt")
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -1,302 +0,0 @@
|
||||
//go:build !e2e_testing
|
||||
|
||||
package udp
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
"sync"
|
||||
"syscall"
|
||||
"testing"
|
||||
"time"
|
||||
"unsafe"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// A burst larger than recvBatch arrives whole, with each datagram's own bytes and source address, and
|
||||
// flush runs once per recvmsg_x batch rather than once per datagram.
|
||||
func TestListenOutBatchesBurst(t *testing.T) {
|
||||
for _, tc := range []struct{ name, listen string }{
|
||||
{"v4", "127.0.0.1"},
|
||||
{"v6", "::1"},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.AddrPortFrom(netip.MustParseAddr(tc.listen), 0)})
|
||||
require.NoError(t, err)
|
||||
la, err := c.LocalAddr()
|
||||
require.NoError(t, err)
|
||||
|
||||
tx, err := net.Dial("udp", la.String())
|
||||
require.NoError(t, err)
|
||||
defer tx.Close()
|
||||
txAddr := netip.MustParseAddrPort(tx.LocalAddr().String())
|
||||
|
||||
const total = recvBatch*3 + 7
|
||||
var mu sync.Mutex
|
||||
var got []string
|
||||
var froms []netip.AddrPort
|
||||
flushes := 0
|
||||
// Queued before the reader starts, so recvmsg_x sees full batches.
|
||||
for i := 0; i < total; i++ {
|
||||
_, err := tx.Write([]byte(fmt.Sprintf("pkt-%03d", i)))
|
||||
require.NoError(t, err)
|
||||
}
|
||||
|
||||
done := make(chan struct{})
|
||||
go func() {
|
||||
_ = c.ListenOut(func(addr netip.AddrPort, payload []byte) {
|
||||
mu.Lock()
|
||||
got = append(got, string(payload))
|
||||
froms = append(froms, addr)
|
||||
mu.Unlock()
|
||||
}, func() {
|
||||
mu.Lock()
|
||||
flushes++
|
||||
mu.Unlock()
|
||||
})
|
||||
close(done)
|
||||
}()
|
||||
|
||||
require.Eventually(t, func() bool {
|
||||
mu.Lock()
|
||||
defer mu.Unlock()
|
||||
return len(got) == total
|
||||
}, 5*time.Second, 10*time.Millisecond)
|
||||
|
||||
require.NoError(t, c.Close())
|
||||
<-done
|
||||
|
||||
for i, p := range got {
|
||||
assert.Equal(t, fmt.Sprintf("pkt-%03d", i), p)
|
||||
assert.Equal(t, txAddr, froms[i])
|
||||
}
|
||||
assert.Equal(t, (total+recvBatch-1)/recvBatch, flushes)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// msghdrX round-trips through xnu's recvmsg_x on a loopback socket, v4 and v6. The kernel reads Name, Namelen,
|
||||
// Iov and Iovlen from each entry and writes Namelen, Flags and Datalen back, so a field at the wrong offset or a
|
||||
// wrong stride between entries shows up as a wrong length, sender, or payload.
|
||||
// TestListenOutSingleFallback pins the path ListenOut takes when the kernel refuses recvmsg_x.
|
||||
func TestListenOutSingleFallback(t *testing.T) {
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0")})
|
||||
require.NoError(t, err)
|
||||
la, err := c.LocalAddr()
|
||||
require.NoError(t, err)
|
||||
tx, err := net.Dial("udp", la.String())
|
||||
require.NoError(t, err)
|
||||
defer tx.Close()
|
||||
txAddr := netip.MustParseAddrPort(tx.LocalAddr().String())
|
||||
|
||||
const total = 5
|
||||
for i := 0; i < total; i++ {
|
||||
_, err := tx.Write([]byte(fmt.Sprintf("pkt-%03d", i)))
|
||||
require.NoError(t, err)
|
||||
}
|
||||
|
||||
var mu sync.Mutex
|
||||
var got []string
|
||||
flushes := 0
|
||||
done := make(chan struct{})
|
||||
go func() {
|
||||
_ = c.(*StdConn).listenOutSingle(func(addr netip.AddrPort, payload []byte) {
|
||||
assert.Equal(t, txAddr, addr)
|
||||
mu.Lock()
|
||||
got = append(got, string(payload))
|
||||
mu.Unlock()
|
||||
}, func() {
|
||||
mu.Lock()
|
||||
flushes++
|
||||
mu.Unlock()
|
||||
})
|
||||
close(done)
|
||||
}()
|
||||
|
||||
require.Eventually(t, func() bool {
|
||||
mu.Lock()
|
||||
defer mu.Unlock()
|
||||
return len(got) == total
|
||||
}, 5*time.Second, 10*time.Millisecond)
|
||||
require.NoError(t, c.Close())
|
||||
<-done
|
||||
|
||||
for i, p := range got {
|
||||
assert.Equal(t, fmt.Sprintf("pkt-%03d", i), p)
|
||||
}
|
||||
assert.Equal(t, total, flushes)
|
||||
}
|
||||
|
||||
func TestCheckMsghdrX(t *testing.T) {
|
||||
valid := func() ([]msghdrX, []unix.RawSockaddrInet6) {
|
||||
hdrs := make([]msghdrX, 2)
|
||||
names := make([]unix.RawSockaddrInet6, 2)
|
||||
hdrs[0].Namelen, hdrs[0].Datalen = unix.SizeofSockaddrInet4, 1
|
||||
names[0].Family = unix.AF_INET
|
||||
hdrs[1].Namelen, hdrs[1].Datalen = unix.SizeofSockaddrInet6, MTU
|
||||
names[1].Family = unix.AF_INET6
|
||||
return hdrs, names
|
||||
}
|
||||
|
||||
hdrs, names := valid()
|
||||
require.NoError(t, checkMsghdrX(hdrs, names, 2))
|
||||
require.NoError(t, checkMsghdrX(hdrs, names, 0))
|
||||
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
n int
|
||||
mutate func([]msghdrX, []unix.RawSockaddrInet6)
|
||||
}{
|
||||
{"count past headers", 3, func([]msghdrX, []unix.RawSockaddrInet6) {}},
|
||||
{"datalen past buffer", 2, func(h []msghdrX, _ []unix.RawSockaddrInet6) { h[1].Datalen = MTU + 1 }},
|
||||
{"unknown family", 2, func(_ []msghdrX, a []unix.RawSockaddrInet6) { a[0].Family = unix.AF_UNIX }},
|
||||
{"family and length disagree", 2, func(h []msghdrX, _ []unix.RawSockaddrInet6) { h[0].Namelen = unix.SizeofSockaddrInet6 }},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
hdrs, names := valid()
|
||||
tc.mutate(hdrs, names)
|
||||
assert.Error(t, checkMsghdrX(hdrs, names, tc.n))
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestMsghdrXKernelRoundTrip(t *testing.T) {
|
||||
for _, v6 := range []bool{false, true} {
|
||||
t.Run(fmt.Sprintf("v6=%v", v6), func(t *testing.T) {
|
||||
// Loopback delivery goes through the dlil input thread, so the settle gives all three time to
|
||||
// queue and come back from one call, which is what exercises the stride.
|
||||
got := recvmsgXRoundTrip(t, v6, []int{1, 300, 1400}, 4, 50*time.Millisecond)
|
||||
assert.Equal(t, 3, got, "largest batch from one recvmsg_x call")
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Any burst, of any datagram lengths up to the kernel's maxdgram, into any number of headers, comes back in order
|
||||
// with every entry's fields intact, and headers past the returned count untouched.
|
||||
func FuzzMsghdrXKernelRoundTrip(f *testing.F) {
|
||||
f.Add(false, uint8(3), []byte{0, 1, 1, 44, 5, 120})
|
||||
f.Add(true, uint8(0), []byte{0, 0, 0x23, 0x29}) // one empty datagram, then one at MTU
|
||||
f.Add(false, uint8(1), []byte{0x23, 0x2a, 0x24, 0x00, 0}) // past MTU: cut to MTU, no MSG_TRUNC
|
||||
f.Add(true, uint8(recvBatch-1), bytes.Repeat([]byte{0x05, 0xdc}, recvBatch))
|
||||
|
||||
f.Fuzz(func(t *testing.T, v6 bool, spare uint8, sizes []byte) {
|
||||
// Two bytes per datagram, big-endian, folded into [0, maxdgram].
|
||||
var lens []int
|
||||
for i := 0; i+1 < len(sizes) && len(lens) < recvBatch; i += 2 {
|
||||
lens = append(lens, (int(sizes[i])<<8|int(sizes[i+1]))%(maxDgram+1))
|
||||
}
|
||||
if len(lens) == 0 {
|
||||
return
|
||||
}
|
||||
recvmsgXRoundTrip(t, v6, lens, 1+int(spare)%recvBatch, time.Millisecond)
|
||||
})
|
||||
}
|
||||
|
||||
// maxDgram is darwin's default net.inet.udp.maxdgram, the largest datagram a loopback sender may write.
|
||||
const maxDgram = 9216
|
||||
|
||||
// recvmsgXRoundTrip sends one datagram per entry of lens to a fresh loopback socket, drains them with recvmsg_x
|
||||
// into nh headers, and checks every field the kernel writes. Neighboring datagrams differ in sender, length and
|
||||
// fill byte, so no field can pass by reading a neighbor's value. It returns the largest batch one call returned.
|
||||
func recvmsgXRoundTrip(t *testing.T, v6 bool, lens []int, nh int, settle time.Duration) int {
|
||||
t.Helper()
|
||||
network, lo := "udp4", netip.MustParseAddr("127.0.0.1")
|
||||
if v6 {
|
||||
network, lo = "udp6", netip.IPv6Loopback()
|
||||
}
|
||||
rx, err := net.ListenUDP(network, net.UDPAddrFromAddrPort(netip.AddrPortFrom(lo, 0)))
|
||||
require.NoError(t, err)
|
||||
defer rx.Close()
|
||||
|
||||
txs := make([]*net.UDPConn, 3)
|
||||
for i := range txs {
|
||||
txs[i], err = net.DialUDP(network, nil, rx.LocalAddr().(*net.UDPAddr))
|
||||
require.NoError(t, err)
|
||||
defer txs[i].Close()
|
||||
}
|
||||
senders := make([]netip.AddrPort, len(lens))
|
||||
for i, l := range lens {
|
||||
tx := txs[i%len(txs)]
|
||||
senders[i] = tx.LocalAddr().(*net.UDPAddr).AddrPort()
|
||||
_, err := tx.Write(bytes.Repeat([]byte{byte(i + 1)}, l))
|
||||
require.NoError(t, err)
|
||||
}
|
||||
time.Sleep(settle)
|
||||
|
||||
// Namelen goes in as the v6 size on both families, so the v4 size coming back proves the kernel wrote it.
|
||||
const sentinel = 0xa5a5a5a5a5a5a5a5
|
||||
wantNamelen := uint32(unix.SizeofSockaddrInet4)
|
||||
if v6 {
|
||||
wantNamelen = unix.SizeofSockaddrInet6
|
||||
}
|
||||
bufs := make([][]byte, nh)
|
||||
names := make([]unix.RawSockaddrInet6, nh)
|
||||
iovs := make([]unix.Iovec, nh)
|
||||
hdrs := make([]msghdrX, nh)
|
||||
for i := range hdrs {
|
||||
bufs[i] = make([]byte, MTU)
|
||||
iovs[i].Base = &bufs[i][0]
|
||||
iovs[i].SetLen(MTU)
|
||||
}
|
||||
|
||||
// A datagram dropped on loopback would otherwise block rc.Read forever.
|
||||
require.NoError(t, rx.SetReadDeadline(time.Now().Add(5*time.Second)))
|
||||
rc, err := rx.SyscallConn()
|
||||
require.NoError(t, err)
|
||||
largest := 0
|
||||
for next := 0; next < len(lens); {
|
||||
for i := range hdrs {
|
||||
clear(bufs[i])
|
||||
hdrs[i] = msghdrX{
|
||||
Name: (*byte)(unsafe.Pointer(&names[i])),
|
||||
Namelen: unix.SizeofSockaddrInet6,
|
||||
Iov: &iovs[i],
|
||||
Iovlen: 1,
|
||||
Flags: -1,
|
||||
Datalen: sentinel,
|
||||
}
|
||||
}
|
||||
var n int
|
||||
var errno syscall.Errno
|
||||
require.NoError(t, rc.Read(func(fd uintptr) bool {
|
||||
r0, _, e := unix.Syscall6(unix.SYS_RECVMSG_X, fd, uintptr(unsafe.Pointer(&hdrs[0])), uintptr(nh), 0, 0, 0)
|
||||
n, errno = int(r0), e
|
||||
return e != unix.EAGAIN
|
||||
}), "received %d of %d datagrams", next, len(lens))
|
||||
require.Zero(t, errno)
|
||||
require.Positive(t, n)
|
||||
require.LessOrEqual(t, n, min(nh, len(lens)-next))
|
||||
largest = max(largest, n)
|
||||
require.NoError(t, checkMsghdrX(hdrs[:nh], names[:nh], n), "ListenOut would fall back on this batch")
|
||||
|
||||
for i := range n {
|
||||
d := next + i
|
||||
h := &hdrs[i]
|
||||
want := min(lens[d], MTU)
|
||||
require.EqualValues(t, want, h.Datalen, "datagram %d Datalen", d)
|
||||
require.Equal(t, wantNamelen, h.Namelen, "datagram %d Namelen", d)
|
||||
from, ok := sockaddrToAddrPort(&names[i])
|
||||
require.True(t, ok, "datagram %d family %d", d, names[i].Family)
|
||||
require.Equal(t, senders[d], from, "datagram %d sender", d)
|
||||
// Flags goes in as -1 and must come back 0. xnu's list receive (soreceive_m_list) never sets
|
||||
// MSG_TRUNC, so a datagram past MTU arrives silently cut to MTU, as recvfrom through net.UDPConn does.
|
||||
require.Zero(t, h.Flags, "datagram %d Flags", d)
|
||||
require.Equal(t, bytes.Repeat([]byte{byte(d + 1)}, want), bufs[i][:want], "datagram %d payload", d)
|
||||
if want < MTU {
|
||||
require.Zero(t, bufs[i][want], "datagram %d wrote past Datalen", d)
|
||||
}
|
||||
}
|
||||
for i := n; i < nh; i++ {
|
||||
require.EqualValues(t, uint64(sentinel), hdrs[i].Datalen, "spare header %d Datalen", i)
|
||||
require.EqualValues(t, unix.SizeofSockaddrInet6, hdrs[i].Namelen, "spare header %d Namelen", i)
|
||||
}
|
||||
next += n
|
||||
}
|
||||
return largest
|
||||
}
|
||||
@@ -1,150 +0,0 @@
|
||||
//go:build !e2e_testing
|
||||
|
||||
package udp
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// recvAll reads n datagrams from pc, or fails the test after a second without one.
|
||||
func recvAll(t *testing.T, pc net.PacketConn, n int) []string {
|
||||
t.Helper()
|
||||
var got []string
|
||||
buf := make([]byte, 64)
|
||||
for len(got) < n {
|
||||
require.NoError(t, pc.SetReadDeadline(time.Now().Add(time.Second)))
|
||||
l, _, err := pc.ReadFrom(buf)
|
||||
require.NoError(t, err, "after %d of %d datagrams", len(got), n)
|
||||
got = append(got, string(buf[:l]))
|
||||
}
|
||||
return got
|
||||
}
|
||||
|
||||
// A batch longer than sendBatch reaches each peer whole and in order through sendmsg_x, without falling
|
||||
// back to sendto: a run to one peer that spans two calls, then datagrams alternating between peers.
|
||||
func TestWriteBatchSendsEachToItsPeer(t *testing.T) {
|
||||
for _, tc := range []struct{ name, listen string }{
|
||||
{"v4", "127.0.0.1"},
|
||||
{"v6", "::1"},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.AddrPortFrom(netip.MustParseAddr(tc.listen), 0)})
|
||||
require.NoError(t, err)
|
||||
defer c.Close()
|
||||
|
||||
var peers [2]net.PacketConn
|
||||
var dsts [2]netip.AddrPort
|
||||
for i := range peers {
|
||||
peers[i], err = net.ListenPacket("udp", net.JoinHostPort(tc.listen, "0"))
|
||||
require.NoError(t, err)
|
||||
defer peers[i].Close()
|
||||
dsts[i] = netip.MustParseAddrPort(peers[i].LocalAddr().String())
|
||||
}
|
||||
|
||||
const total = sendBatch*2 + 5
|
||||
bufs := make([][]byte, total)
|
||||
addrs := make([]netip.AddrPort, total)
|
||||
var want [2][]string
|
||||
for i := range bufs {
|
||||
bufs[i] = fmt.Appendf(nil, "pkt-%03d", i)
|
||||
p := i % 2
|
||||
if i < sendBatch+6 {
|
||||
p = 0
|
||||
}
|
||||
addrs[i] = dsts[p]
|
||||
want[p] = append(want[p], string(bufs[i]))
|
||||
}
|
||||
|
||||
n, err := c.WriteBatch(bufs, addrs)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, total, n)
|
||||
assert.False(t, c.(*StdConn).noSendmsgX.Load(), "fell back to sendto")
|
||||
for i := range peers {
|
||||
assert.Equal(t, want[i], recvAll(t, peers[i], len(want[i])))
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Destinations that can't be sent to cost only their own packets: an IPv6 peer on an IPv4 socket is
|
||||
// skipped before the call, and a broadcast address without SO_BROADCAST is refused by the kernel
|
||||
// mid-batch. Neither stops the packets around it, delivers any twice, or turns sendmsg_x off.
|
||||
func TestWriteBatchSkipsUnsendableDestinations(t *testing.T) {
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0")})
|
||||
require.NoError(t, err)
|
||||
defer c.Close()
|
||||
|
||||
peer, err := net.ListenPacket("udp", "127.0.0.1:0")
|
||||
require.NoError(t, err)
|
||||
defer peer.Close()
|
||||
good := netip.MustParseAddrPort(peer.LocalAddr().String())
|
||||
bcast := netip.AddrPortFrom(netip.MustParseAddr("255.255.255.255"), good.Port())
|
||||
v6 := netip.MustParseAddrPort("[::1]:4242")
|
||||
|
||||
addrs := []netip.AddrPort{good, bcast, bcast, good, v6, good, bcast}
|
||||
bufs := make([][]byte, len(addrs))
|
||||
for i := range bufs {
|
||||
bufs[i] = fmt.Appendf(nil, "pkt-%d", i)
|
||||
}
|
||||
|
||||
n, err := c.WriteBatch(bufs, addrs)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, 3, n)
|
||||
assert.False(t, c.(*StdConn).noSendmsgX.Load(), "fell back to sendto")
|
||||
assert.Equal(t, []string{"pkt-0", "pkt-3", "pkt-5"}, recvAll(t, peer, 3))
|
||||
require.NoError(t, peer.SetReadDeadline(time.Now().Add(100*time.Millisecond)))
|
||||
_, _, err = peer.ReadFrom(make([]byte, 64))
|
||||
assert.Error(t, err, "a datagram arrived twice")
|
||||
}
|
||||
|
||||
// A datagram the kernel refuses as its own fault (EMSGSIZE here, as ENOBUFS would be under a full
|
||||
// interface queue) costs only itself, whether it fails after others in the same call (a short count) or
|
||||
// first (the errno alone): the rest of its run still arrives, in order, and sendmsg_x stays on.
|
||||
func TestWriteBatchLosesOnlyTheFailedDatagram(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
big int
|
||||
}{
|
||||
{"mid-call", 2},
|
||||
{"first", 0},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0")})
|
||||
require.NoError(t, err)
|
||||
defer c.Close()
|
||||
|
||||
peer, err := net.ListenPacket("udp", "127.0.0.1:0")
|
||||
require.NoError(t, err)
|
||||
defer peer.Close()
|
||||
dst := netip.MustParseAddrPort(peer.LocalAddr().String())
|
||||
|
||||
bufs := make([][]byte, 5)
|
||||
addrs := make([]netip.AddrPort, len(bufs))
|
||||
var want []string
|
||||
for i := range bufs {
|
||||
addrs[i] = dst
|
||||
if i == tc.big {
|
||||
// Past the 65535-byte IP datagram limit, so the kernel can only refuse it.
|
||||
bufs[i] = make([]byte, 70000)
|
||||
continue
|
||||
}
|
||||
bufs[i] = fmt.Appendf(nil, "pkt-%d", i)
|
||||
want = append(want, string(bufs[i]))
|
||||
}
|
||||
|
||||
n, err := c.WriteBatch(bufs, addrs)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, len(want), n)
|
||||
assert.False(t, c.(*StdConn).noSendmsgX.Load(), "fell back to sendto")
|
||||
assert.Equal(t, want, recvAll(t, peer, len(want)))
|
||||
})
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user