mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-16 16:16:52 +01:00
Compare commits
4
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
10e1924489 | ||
|
|
4d191f805f | ||
|
|
61947ff1c2 | ||
|
|
a33a6356c6 |
No files matched your search
+1
-2
@@ -203,8 +203,7 @@ func (c *Control) RebindUDPServer() {
|
||||
}
|
||||
|
||||
// A failure here means we are likely still pinned to the interface we came up on, so the rest of this is
|
||||
// unlikely to help. Say so instead of silently carrying on as if we rebound. Only the first writer is rebound;
|
||||
// darwin's Rebind clears every listen routine's listener.
|
||||
// unlikely to help. Say so instead of silently carrying on as if we rebound.
|
||||
if err := c.f.outside.Rebind(); err != nil {
|
||||
c.l.Error("Failed to rebind udp socket", "error", err)
|
||||
}
|
||||
|
||||
@@ -1,90 +0,0 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"sync"
|
||||
|
||||
"github.com/slackhq/nebula/udp"
|
||||
)
|
||||
|
||||
// establishedRemotes tells the udp conns that implement udp.EstablishedPeerConn which addresses are the current
|
||||
// direct remote of at least one established tunnel. A hostinfo holds a reference on its remote while it is in the
|
||||
// main hostmap, and SetRemote moves the reference; a relayed tunnel has no direct remote and holds none.
|
||||
type establishedRemotes struct {
|
||||
mu sync.Mutex
|
||||
conns []udp.EstablishedPeerConn
|
||||
refs map[netip.AddrPort]int
|
||||
}
|
||||
|
||||
// newEstablishedRemotes returns nil when no conn wants to know, which every method accepts.
|
||||
func newEstablishedRemotes(conns []udp.Conn) *establishedRemotes {
|
||||
var pc []udp.EstablishedPeerConn
|
||||
for _, c := range conns {
|
||||
if p, ok := c.(udp.EstablishedPeerConn); ok {
|
||||
pc = append(pc, p)
|
||||
}
|
||||
}
|
||||
if len(pc) == 0 {
|
||||
return nil
|
||||
}
|
||||
return &establishedRemotes{conns: pc, refs: map[netip.AddrPort]int{}}
|
||||
}
|
||||
|
||||
// add makes hostinfo hold a reference on its remote, as it joins the main hostmap. A hostinfo holds references in
|
||||
// one establishedRemotes at a time, so an add while it is in another is ignored.
|
||||
func (e *establishedRemotes) add(hostinfo *HostInfo) {
|
||||
if e == nil {
|
||||
return
|
||||
}
|
||||
e.mu.Lock()
|
||||
defer e.mu.Unlock()
|
||||
if !hostinfo.establishedIn.CompareAndSwap(nil, e) && hostinfo.establishedIn.Load() != e {
|
||||
return
|
||||
}
|
||||
e.syncLocked(hostinfo)
|
||||
}
|
||||
|
||||
// remove drops hostinfo's reference, as it leaves the main hostmap.
|
||||
func (e *establishedRemotes) remove(hostinfo *HostInfo) {
|
||||
if e == nil {
|
||||
return
|
||||
}
|
||||
e.mu.Lock()
|
||||
defer e.mu.Unlock()
|
||||
if hostinfo.establishedIn.CompareAndSwap(e, nil) {
|
||||
e.syncLocked(hostinfo)
|
||||
}
|
||||
}
|
||||
|
||||
// syncLocked moves hostinfo's reference to the remote it should hold now: its current remote while it is
|
||||
// established, none otherwise. Reading both under mu makes the last call win however add, remove and SetRemote
|
||||
// interleave. Only the establishedRemotes that hostinfo is in, or has just left, may call it, since
|
||||
// hostinfo.establishedRemote is a reference in that one's refs.
|
||||
func (e *establishedRemotes) syncLocked(hostinfo *HostInfo) {
|
||||
var want netip.AddrPort
|
||||
if hostinfo.establishedIn.Load() == e {
|
||||
want = hostinfo.GetRemote()
|
||||
}
|
||||
held := hostinfo.establishedRemote
|
||||
if want == held {
|
||||
return
|
||||
}
|
||||
if held.IsValid() {
|
||||
e.refs[held]--
|
||||
if e.refs[held] == 0 {
|
||||
delete(e.refs, held)
|
||||
for _, c := range e.conns {
|
||||
c.SetEstablishedPeer(held, false)
|
||||
}
|
||||
}
|
||||
}
|
||||
if want.IsValid() {
|
||||
e.refs[want]++
|
||||
if e.refs[want] == 1 {
|
||||
for _, c := range e.conns {
|
||||
c.SetEstablishedPeer(want, true)
|
||||
}
|
||||
}
|
||||
}
|
||||
hostinfo.establishedRemote = want
|
||||
}
|
||||
@@ -1,173 +0,0 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"sync"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// establishedPeerConn records which destinations the hostmap has told it are established peers, and fails the test
|
||||
// on a call that doesn't change anything, which would mean a reference count went wrong.
|
||||
type establishedPeerConn struct {
|
||||
udp.NoopConn
|
||||
t *testing.T
|
||||
mu sync.Mutex
|
||||
peers map[netip.AddrPort]bool
|
||||
}
|
||||
|
||||
func (c *establishedPeerConn) SetEstablishedPeer(dst netip.AddrPort, established bool) {
|
||||
c.mu.Lock()
|
||||
defer c.mu.Unlock()
|
||||
assert.NotEqual(c.t, established, c.peers[dst], "SetEstablishedPeer(%v, %v) repeated", dst, established)
|
||||
if established {
|
||||
c.peers[dst] = true
|
||||
} else {
|
||||
delete(c.peers, dst)
|
||||
}
|
||||
}
|
||||
|
||||
func (c *establishedPeerConn) established() []netip.AddrPort {
|
||||
c.mu.Lock()
|
||||
defer c.mu.Unlock()
|
||||
var out []netip.AddrPort
|
||||
for dst := range c.peers {
|
||||
out = append(out, dst)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// newEstablishedTestHostMap returns a hostmap whose conns are a recording conn and one that doesn't track peers.
|
||||
func newEstablishedTestHostMap(t *testing.T) (*HostMap, *establishedPeerConn) {
|
||||
hm := newHostMap(test.NewLogger())
|
||||
hm.preferredRanges.Store(&[]netip.Prefix{netip.MustParsePrefix("192.168.0.0/16")})
|
||||
c := &establishedPeerConn{t: t, peers: map[netip.AddrPort]bool{}}
|
||||
hm.established = newEstablishedRemotes([]udp.Conn{c, udp.NoopConn{}})
|
||||
require.NotNil(t, hm.established)
|
||||
return hm, c
|
||||
}
|
||||
|
||||
func newEstablishedTestHostInfo(vpnAddr netip.Addr, index uint32) *HostInfo {
|
||||
return &HostInfo{
|
||||
vpnAddrs: []netip.Addr{vpnAddr},
|
||||
localIndexId: index,
|
||||
remotes: NewRemoteList([]netip.Addr{vpnAddr}, nil),
|
||||
}
|
||||
}
|
||||
|
||||
func TestNewEstablishedRemotesWithoutTrackingConns(t *testing.T) {
|
||||
assert.Nil(t, newEstablishedRemotes([]udp.Conn{udp.NoopConn{}}))
|
||||
}
|
||||
|
||||
// A conn hears about a remote while at least one hostinfo in the main hostmap has it as its direct remote: from
|
||||
// the add, through roaming and SetRemoteIfPreferred, until the last such hostinfo is deleted or retired by
|
||||
// MaxHostInfosPerVpnIp. Pending and relayed hostinfos never count.
|
||||
func TestHostMap_EstablishedRemotes(t *testing.T) {
|
||||
hm, c := newEstablishedTestHostMap(t)
|
||||
f := &Interface{}
|
||||
a := netip.MustParseAddr("10.0.0.1")
|
||||
r1 := netip.MustParseAddrPort("203.0.113.1:4242")
|
||||
r2 := netip.MustParseAddrPort("203.0.113.2:4242")
|
||||
r3 := netip.MustParseAddrPort("192.168.1.3:4242")
|
||||
|
||||
// A pending hostinfo, as a handshake sets its remote, isn't established.
|
||||
h1 := newEstablishedTestHostInfo(a, 1)
|
||||
h1.SetRemote(r1)
|
||||
assert.Empty(t, c.established())
|
||||
|
||||
// Handshake completion adds it to the main hostmap.
|
||||
hm.unlockedAddHostInfo(h1, f)
|
||||
assert.ElementsMatch(t, []netip.AddrPort{r1}, c.established())
|
||||
|
||||
// A relayed tunnel has no direct remote.
|
||||
relayed := newEstablishedTestHostInfo(netip.MustParseAddr("10.0.0.2"), 2)
|
||||
hm.unlockedAddHostInfo(relayed, f)
|
||||
assert.ElementsMatch(t, []netip.AddrPort{r1}, c.established())
|
||||
|
||||
// A rehandshake's new hostinfo shares the remote, which stays established until both are gone.
|
||||
h3 := newEstablishedTestHostInfo(a, 3)
|
||||
h3.SetRemote(r1)
|
||||
hm.unlockedAddHostInfo(h3, f)
|
||||
hm.DeleteHostInfo(h1)
|
||||
assert.ElementsMatch(t, []netip.AddrPort{r1}, c.established())
|
||||
|
||||
// Roaming moves the reference.
|
||||
h3.SetRemote(r2)
|
||||
assert.ElementsMatch(t, []netip.AddrPort{r2}, c.established())
|
||||
require.True(t, h3.SetRemoteIfPreferred(hm, ViaSender{UdpAddr: r3}))
|
||||
assert.ElementsMatch(t, []netip.AddrPort{r3}, c.established())
|
||||
|
||||
// A relayed tunnel that hears from its peer directly roams onto a direct remote.
|
||||
relayed.SetRemote(r1)
|
||||
assert.ElementsMatch(t, []netip.AddrPort{r1, r3}, c.established())
|
||||
hm.DeleteHostInfo(relayed)
|
||||
|
||||
// A deleted hostinfo lets go, and a SetRemote after that changes nothing.
|
||||
hm.DeleteHostInfo(h3)
|
||||
assert.Empty(t, c.established())
|
||||
h3.SetRemote(r2)
|
||||
assert.Empty(t, c.established())
|
||||
hm.DeleteHostInfo(h3)
|
||||
|
||||
// Adding past MaxHostInfosPerVpnIp retires the oldest hostinfo and its remote.
|
||||
var hs []*HostInfo
|
||||
for i := range MaxHostInfosPerVpnIp + 1 {
|
||||
h := newEstablishedTestHostInfo(a, uint32(10+i))
|
||||
h.SetRemote(netip.AddrPortFrom(netip.MustParseAddr("198.51.100.1"), uint16(1000+i)))
|
||||
hm.unlockedAddHostInfo(h, f)
|
||||
hs = append(hs, h)
|
||||
}
|
||||
assert.Len(t, c.established(), MaxHostInfosPerVpnIp)
|
||||
assert.NotContains(t, c.established(), hs[0].GetRemote())
|
||||
}
|
||||
|
||||
// Roaming on the receive path races tunnel teardown on the connection manager; whatever the order, a deleted
|
||||
// hostinfo holds no reference.
|
||||
func TestHostMap_EstablishedRemotesRoamRacesDelete(t *testing.T) {
|
||||
hm, c := newEstablishedTestHostMap(t)
|
||||
f := &Interface{}
|
||||
a := netip.MustParseAddr("10.0.0.1")
|
||||
for i := range 200 {
|
||||
h := newEstablishedTestHostInfo(a, uint32(i+1))
|
||||
h.SetRemote(netip.MustParseAddrPort("203.0.113.1:4242"))
|
||||
hm.Lock()
|
||||
hm.unlockedAddHostInfo(h, f)
|
||||
hm.Unlock()
|
||||
var wg sync.WaitGroup
|
||||
wg.Go(func() { h.SetRemote(netip.AddrPortFrom(netip.MustParseAddr("203.0.113.2"), uint16(i+1))) })
|
||||
wg.Go(func() { hm.DeleteHostInfo(h) })
|
||||
wg.Wait()
|
||||
require.Empty(t, c.established(), "round %d", i)
|
||||
}
|
||||
}
|
||||
|
||||
// A hostinfo holds its reference in the first tracking hostmap it joins; another's add and delete of it change
|
||||
// nothing, so neither hostmap's counts go wrong.
|
||||
func TestHostMap_EstablishedRemotesSingleOwner(t *testing.T) {
|
||||
hm1, c1 := newEstablishedTestHostMap(t)
|
||||
hm2, c2 := newEstablishedTestHostMap(t)
|
||||
f := &Interface{}
|
||||
r := netip.MustParseAddrPort("203.0.113.1:4242")
|
||||
h := newEstablishedTestHostInfo(netip.MustParseAddr("10.0.0.1"), 1)
|
||||
h.SetRemote(r)
|
||||
|
||||
hm1.unlockedAddHostInfo(h, f)
|
||||
hm2.unlockedAddHostInfo(h, f)
|
||||
assert.ElementsMatch(t, []netip.AddrPort{r}, c1.established())
|
||||
assert.Empty(t, c2.established())
|
||||
|
||||
hm2.DeleteHostInfo(h)
|
||||
assert.Equal(t, map[netip.AddrPort]int{r: 1}, hm1.established.refs)
|
||||
assert.Empty(t, hm2.established.refs)
|
||||
assert.ElementsMatch(t, []netip.AddrPort{r}, c1.established())
|
||||
|
||||
hm1.DeleteHostInfo(h)
|
||||
assert.Empty(t, hm1.established.refs)
|
||||
assert.Empty(t, hm2.established.refs)
|
||||
assert.Empty(t, c1.established())
|
||||
assert.Empty(t, c2.established())
|
||||
}
|
||||
+1
-17
@@ -69,9 +69,7 @@ type HostMap struct {
|
||||
Hosts map[netip.Addr]*HostInfo
|
||||
moreHosts map[netip.Addr][]*HostInfo
|
||||
preferredRanges atomic.Pointer[[]netip.Prefix]
|
||||
// established hears about each hostinfo that joins or leaves the hostmap; nil when no conn wants to know.
|
||||
established *establishedRemotes
|
||||
l *slog.Logger
|
||||
l *slog.Logger
|
||||
}
|
||||
|
||||
// For synchronization, treat the pointed-to Relay struct as immutable. To edit the Relay
|
||||
@@ -278,11 +276,6 @@ type HostInfo struct {
|
||||
// This value will be behind against actual tunnel utilization in the hot path.
|
||||
// This should only be used by the ConnectionManagers ticker routine.
|
||||
lastUsed time.Time
|
||||
|
||||
// establishedIn is set while the hostinfo is in a main hostmap whose conns track established remotes, and
|
||||
// establishedRemote is the remote it holds a reference on there, guarded by establishedIn's mu.
|
||||
establishedIn atomic.Pointer[establishedRemotes]
|
||||
establishedRemote netip.AddrPort
|
||||
}
|
||||
|
||||
type ViaSender struct {
|
||||
@@ -523,7 +516,6 @@ func (hm *HostMap) unlockedDeleteHostInfo(hostinfo *HostInfo) bool {
|
||||
if len(hm.Indexes) == 0 {
|
||||
hm.Indexes = map[uint32]*HostInfo{}
|
||||
}
|
||||
hm.established.remove(hostinfo)
|
||||
|
||||
if hm.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
hm.l.Debug("Hostmap hostInfo deleted",
|
||||
@@ -670,7 +662,6 @@ func (hm *HostMap) unlockedAddHostInfo(hostinfo *HostInfo, f *Interface) {
|
||||
|
||||
hm.Indexes[hostinfo.localIndexId] = hostinfo
|
||||
hm.RemoteIndexes[hostinfo.remoteIndexId] = hostinfo
|
||||
hm.established.add(hostinfo)
|
||||
|
||||
hostinfo.markOut(f.rebindEpoch.Load())
|
||||
if f.connectionManager != nil { // f.connectionManager is only nil in some unit tests
|
||||
@@ -851,13 +842,6 @@ func (i *HostInfo) SetRemote(remote netip.AddrPort) {
|
||||
if i.GetRemote() != remote {
|
||||
i.remote.Store(&remote)
|
||||
i.remotes.LearnRemote(i.vpnAddrs[0], remote)
|
||||
if e := i.establishedIn.Load(); e != nil {
|
||||
e.mu.Lock()
|
||||
if i.establishedIn.Load() == e {
|
||||
e.syncLocked(i)
|
||||
}
|
||||
e.mu.Unlock()
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -213,7 +213,6 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
}
|
||||
|
||||
hostMap := NewHostMapFromConfig(l, c)
|
||||
hostMap.established = newEstablishedRemotes(udpConns)
|
||||
punchy := NewPunchyFromConfig(l, c, udpConns[0])
|
||||
connManager := newConnectionManagerFromConfig(l, c, hostMap, punchy)
|
||||
lightHouse, err := NewLightHouseFromConfig(ctx, l, c, pki.getCertState(), udpConns[0], punchy)
|
||||
|
||||
@@ -435,3 +435,65 @@ 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))
|
||||
}
|
||||
}
|
||||
@@ -2,18 +2,23 @@ package batch
|
||||
|
||||
import (
|
||||
"io"
|
||||
|
||||
"github.com/slackhq/nebula/overlay/tio"
|
||||
)
|
||||
|
||||
// Passthrough is MultiCoalescer's verbatim lane: no batching, packets are written at Flush in the
|
||||
// order enqueued.
|
||||
// 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.
|
||||
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),
|
||||
}
|
||||
}
|
||||
@@ -26,10 +31,16 @@ func (p *Passthrough) enqueue(pkt []byte) error {
|
||||
|
||||
func (p *Passthrough) Flush() error {
|
||||
var firstErr error
|
||||
for _, s := range p.slots {
|
||||
_, err := p.out.Write(s)
|
||||
if err != nil && firstErr == nil {
|
||||
firstErr = err
|
||||
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
|
||||
}
|
||||
}
|
||||
}
|
||||
clear(p.slots)
|
||||
|
||||
+17
-2
@@ -15,9 +15,13 @@ 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.
|
||||
// Close closes rwc. The Queue implements BatchWriter when rwc does.
|
||||
func NewSingleQueue(rwc io.ReadWriteCloser, bufSize int) Queue {
|
||||
return &singleQueue{rw: rwc, closer: rwc, buf: make([]byte, bufSize)}
|
||||
q := &singleQueue{rw: rwc, closer: rwc, buf: make([]byte, bufSize)}
|
||||
if bw, ok := rwc.(BatchWriter); ok {
|
||||
return &batchSingleQueue{singleQueue: q, bw: bw}
|
||||
}
|
||||
return q
|
||||
}
|
||||
|
||||
// NewSingleQueueNoClose is NewSingleQueue for a source owned by someone else,
|
||||
@@ -47,3 +51,14 @@ 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)
|
||||
}
|
||||
@@ -145,3 +145,14 @@ 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
|
||||
}
|
||||
+244
-9
@@ -8,6 +8,7 @@ import (
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"os"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
"unsafe"
|
||||
@@ -33,6 +34,35 @@ 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 {
|
||||
@@ -607,6 +637,74 @@ 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).
|
||||
@@ -615,16 +713,12 @@ func (t *tun) Write(from []byte) (int, error) {
|
||||
return 0, syscall.EIO
|
||||
}
|
||||
|
||||
ipVer := from[0] >> 4
|
||||
var head [4]byte
|
||||
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")
|
||||
af, err := tunAF(from)
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
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()
|
||||
@@ -657,6 +751,147 @@ 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
|
||||
}
|
||||
@@ -666,5 +901,5 @@ func (t *tun) Name() string {
|
||||
}
|
||||
|
||||
func (t *tun) Queues(int) ([]tio.Queue, error) {
|
||||
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
||||
return []tio.Queue{&tunQueue{t: t, buf: make([]byte, tunReadArena)}}, nil
|
||||
}
|
||||
@@ -0,0 +1,201 @@
|
||||
//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))
|
||||
}
|
||||
@@ -48,14 +48,6 @@ type Conn interface {
|
||||
Close() error
|
||||
}
|
||||
|
||||
// EstablishedPeerConn is a Conn that treats the remotes of established tunnels differently from other
|
||||
// destinations, as darwin's gives busy ones connected sockets.
|
||||
type EstablishedPeerConn interface {
|
||||
// SetEstablishedPeer reports whether dst is the current remote of at least one established tunnel. Calls for
|
||||
// one dst must not race each other.
|
||||
SetEstablishedPeer(dst netip.AddrPort, established bool)
|
||||
}
|
||||
|
||||
type NoopConn struct{}
|
||||
|
||||
func (NoopConn) Rebind() error {
|
||||
|
||||
@@ -1,115 +0,0 @@
|
||||
//go:build !e2e_testing
|
||||
|
||||
package udp
|
||||
|
||||
import (
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
// benchConnSocks opens a wildcard listener with ListenOut running, with the connected socket knobs pinned to
|
||||
// their defaults and then cfg applied, and a loopback peer that never reads, so its sends cost only the sender.
|
||||
func benchConnSocks(b *testing.B, s Settings, cfg func(*connSockConfig)) (*StdConn, netip.AddrPort) {
|
||||
b.Helper()
|
||||
for k, v := range map[string]string{
|
||||
"NEBULA_CONNSOCKS": "8",
|
||||
"NEBULA_CONNSOCK_RUN": "64",
|
||||
"NEBULA_CONNSOCK_WINDOW": "1s",
|
||||
"NEBULA_CONNSOCK_IDLE": "30s",
|
||||
"NEBULA_CONNSOCK_OPEN_EVERY": "1s",
|
||||
} {
|
||||
b.Setenv(k, v)
|
||||
}
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), s)
|
||||
if err != nil {
|
||||
b.Fatal(err)
|
||||
}
|
||||
b.Cleanup(func() { _ = c.Close() })
|
||||
u := c.(*StdConn)
|
||||
if cfg != nil {
|
||||
cfg(&u.socks.cfg)
|
||||
}
|
||||
go func() { _ = u.ListenOut(func(netip.AddrPort, []byte) {}, func() {}) }()
|
||||
for u.reader.Load() == nil {
|
||||
time.Sleep(time.Millisecond)
|
||||
}
|
||||
pc, err := net.ListenPacket("udp4", "127.0.0.1:0")
|
||||
if err != nil {
|
||||
b.Fatal(err)
|
||||
}
|
||||
b.Cleanup(func() { _ = pc.Close() })
|
||||
return u, pc.LocalAddr().(*net.UDPAddr).AddrPort()
|
||||
}
|
||||
|
||||
// BenchmarkConnSockWriteTo measures one WriteTo of a full-size datagram down each path: the listener with
|
||||
// connected sockets off, to a destination that is no tunnel's remote while another is, to an established peer
|
||||
// that never gets busy, and on a connected socket.
|
||||
func BenchmarkConnSockWriteTo(b *testing.B) {
|
||||
pkt := make([]byte, 1400)
|
||||
cases := []struct {
|
||||
name string
|
||||
cfg func(*connSockConfig)
|
||||
setup func(b *testing.B, u *StdConn, dst netip.AddrPort)
|
||||
}{
|
||||
{name: "listener/off", cfg: func(c *connSockConfig) { c.max = 0 }},
|
||||
{name: "listener/ineligible", setup: func(b *testing.B, u *StdConn, dst netip.AddrPort) {
|
||||
u.SetEstablishedPeer(netip.AddrPortFrom(dst.Addr(), dst.Port()+1), true)
|
||||
}},
|
||||
{name: "listener/eligible-not-busy", cfg: func(c *connSockConfig) { c.run = 1 << 30 },
|
||||
setup: func(b *testing.B, u *StdConn, dst netip.AddrPort) { u.SetEstablishedPeer(dst, true) }},
|
||||
{name: "connected", setup: func(b *testing.B, u *StdConn, dst netip.AddrPort) {
|
||||
u.SetEstablishedPeer(dst, true)
|
||||
for range u.socks.cfg.run {
|
||||
_ = u.WriteTo(pkt, dst)
|
||||
}
|
||||
if u.connSockFor(dst) == nil {
|
||||
b.Fatal("no connected socket")
|
||||
}
|
||||
}},
|
||||
}
|
||||
for _, c := range cases {
|
||||
b.Run(c.name, func(b *testing.B) {
|
||||
u, dst := benchConnSocks(b, Settings{Listen: netip.MustParseAddrPort("0.0.0.0:0")}, c.cfg)
|
||||
if c.setup != nil {
|
||||
c.setup(b, u, dst)
|
||||
}
|
||||
b.ReportAllocs()
|
||||
b.ResetTimer()
|
||||
for range b.N {
|
||||
_ = u.WriteTo(pkt, dst)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// BenchmarkConnSockDispatch measures what WriteTo adds before the listener's sendto, without the syscall: a v4
|
||||
// listener refuses a v6 destination before sending, with connected sockets off or with another peer established.
|
||||
func BenchmarkConnSockDispatch(b *testing.B) {
|
||||
pkt := make([]byte, 1400)
|
||||
dst := netip.MustParseAddrPort("[::1]:4242")
|
||||
for _, c := range []struct {
|
||||
name string
|
||||
cfg func(*connSockConfig)
|
||||
establish bool
|
||||
}{
|
||||
{name: "off", cfg: func(c *connSockConfig) { c.max = 0 }},
|
||||
{name: "ineligible", establish: true},
|
||||
} {
|
||||
b.Run(c.name, func(b *testing.B) {
|
||||
u, peer := benchConnSocks(b, Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0"), Multi: true}, c.cfg)
|
||||
if c.establish {
|
||||
u.SetEstablishedPeer(peer, true)
|
||||
}
|
||||
b.ReportAllocs()
|
||||
b.ResetTimer()
|
||||
for range b.N {
|
||||
if u.WriteTo(pkt, dst) == nil {
|
||||
b.Fatal("sent a v6 datagram on a v4 listener")
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -1,803 +0,0 @@
|
||||
//go:build !e2e_testing
|
||||
|
||||
package udp
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"maps"
|
||||
"net"
|
||||
"net/netip"
|
||||
"os"
|
||||
"slices"
|
||||
"strconv"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
"time"
|
||||
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// A connected socket is a UDP socket connected to one busy peer, on the listener's port and bound to the source
|
||||
// address the listener's route to that peer picks, so the peer sees the same address and port from either. A send
|
||||
// on a connected socket skips the per-datagram address and MAC policy checks, and the EndpointSecurity send check
|
||||
// that xprotectd can hold every unconnected sendto on, and it is the only UDP send that reports the interface
|
||||
// queue's flow control, as ENOBUFS. A connected socket wins xnu's lookup for its peer's datagrams; it never sees
|
||||
// anyone else's.
|
||||
//
|
||||
// A connected socket sets SO_REUSEPORT and binds a specific address beside a wildcard listener, which sets
|
||||
// SO_REUSEPORT only for listen routines. xnu refuses a wildcard SO_REUSEPORT bind beside a holder without the
|
||||
// option, and refuses another uid's bind to an address a socket holds specifically, so no other user can join the
|
||||
// port while connected sockets open and close: uid nobody got EADDRINUSE on every bind against a root listener
|
||||
// with connected sockets in the 09-25 probes. A connected socket is closed, never disconnected, because xnu widens
|
||||
// a disconnected socket's local address to the wildcard.
|
||||
//
|
||||
// Only the current remote of an established tunnel may get one: Nebula names those with SetEstablishedPeer, so an
|
||||
// unauthenticated sender can't earn a connected socket by drawing replies such as recv_error or handshake
|
||||
// responses.
|
||||
type connSock struct {
|
||||
dst netip.AddrPort
|
||||
peer *connSockPeer
|
||||
conn *net.UDPConn
|
||||
rc syscall.RawConn
|
||||
// used is the monotonic time in nanoseconds of the connected socket's last send or receive.
|
||||
used atomic.Int64
|
||||
// stallAt is the monotonic time of the first ENOBUFS or EAGAIN since a send last went through, or 0, and
|
||||
// dropping is set once that stall has dropped a datagram, so each stall logs its drops once.
|
||||
stallAt atomic.Int64
|
||||
dropping atomic.Bool
|
||||
// parkMu serializes the writes that wait for a full send buffer, since the write deadline bounding each wait
|
||||
// is the descriptor's, not the writer's.
|
||||
parkMu sync.Mutex
|
||||
// sys writes one datagram on the descriptor: writeFd, or a stand-in for the interface in tests.
|
||||
sys func(fd int, b []byte) error
|
||||
}
|
||||
|
||||
func writeFd(fd int, b []byte) error {
|
||||
_, err := syscall.Write(fd, b)
|
||||
return err
|
||||
}
|
||||
|
||||
// errStallSpent is a write that found the connected socket's stall budget spent, so its datagram is dropped.
|
||||
var errStallSpent = errors.New("connected socket stall budget spent")
|
||||
|
||||
// connSockWriter carries one write through RawConn.Write. They are pooled with fn bound once, since a closure
|
||||
// passed through the RawConn interface escapes and would allocate on every send.
|
||||
type connSockWriter struct {
|
||||
s *connSock
|
||||
b []byte
|
||||
park bool
|
||||
err error
|
||||
fn func(fd uintptr) bool
|
||||
}
|
||||
|
||||
var connSockWriters = sync.Pool{New: func() any {
|
||||
w := &connSockWriter{}
|
||||
w.fn = w.write
|
||||
return w
|
||||
}}
|
||||
|
||||
func (w *connSockWriter) write(fd uintptr) bool {
|
||||
for {
|
||||
w.err = w.s.sys(int(fd), w.b)
|
||||
switch {
|
||||
case w.err == syscall.EINTR:
|
||||
case w.err == syscall.EAGAIN && w.park:
|
||||
return false
|
||||
default:
|
||||
return true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// try writes b on s once and returns nil, the write's errno, os.ErrDeadlineExceeded, or net.ErrClosed. With park
|
||||
// set, EAGAIN waits in the netpoller until the socket is writable or the write deadline passes; without it, EAGAIN
|
||||
// is returned.
|
||||
func (s *connSock) try(b []byte, park bool) error {
|
||||
w := connSockWriters.Get().(*connSockWriter)
|
||||
w.s, w.b, w.park = s, b, park
|
||||
rerr := s.rc.Write(w.fn)
|
||||
err := w.err
|
||||
*w = connSockWriter{fn: w.fn}
|
||||
connSockWriters.Put(w)
|
||||
switch {
|
||||
case rerr == nil:
|
||||
return err
|
||||
case errors.Is(rerr, os.ErrDeadlineExceeded):
|
||||
return os.ErrDeadlineExceeded
|
||||
default:
|
||||
return net.ErrClosed
|
||||
}
|
||||
}
|
||||
|
||||
// connSockConfig holds the knobs. connSockConfigFromEnv reads all but backoff and enobufsMax from the environment,
|
||||
// so one binary can be tuned without a rebuild.
|
||||
type connSockConfig struct {
|
||||
// max is how many connected sockets the listen routines may have open at once; 0 turns connected sockets off.
|
||||
max int
|
||||
// run is how many datagrams to one destination within one window earn it a connected socket. darwin's tun
|
||||
// hands over one packet per read, so a peer's sends arrive one WriteTo or one-datagram batch at a time and
|
||||
// busyness has to be counted across calls.
|
||||
run int
|
||||
window time.Duration
|
||||
// idle closes a connected socket after it has neither sent nor received for this long.
|
||||
idle time.Duration
|
||||
// backoff keeps a destination whose connected socket failed on the listener for this long.
|
||||
backoff time.Duration
|
||||
// openEvery is how often the open bucket earns back an open once max are spent, which bounds connected socket
|
||||
// churn however fast senders earn connected sockets and errors close them.
|
||||
openEvery time.Duration
|
||||
// enobufsMax is how long a connected socket's sends may wait out ENOBUFS without one going through before they
|
||||
// drop instead, so a suspended interface costs one write per datagram rather than stalling the tun reader.
|
||||
enobufsMax time.Duration
|
||||
}
|
||||
|
||||
func connSockConfigFromEnv() connSockConfig {
|
||||
c := connSockConfig{
|
||||
max: 8,
|
||||
run: 64,
|
||||
window: time.Second,
|
||||
idle: 30 * time.Second,
|
||||
backoff: 30 * time.Second,
|
||||
openEvery: time.Second,
|
||||
enobufsMax: 10 * time.Millisecond,
|
||||
}
|
||||
if v, err := strconv.Atoi(os.Getenv("NEBULA_CONNSOCKS")); err == nil {
|
||||
c.max = v
|
||||
}
|
||||
if v, err := strconv.Atoi(os.Getenv("NEBULA_CONNSOCK_RUN")); err == nil && v > 0 {
|
||||
c.run = v
|
||||
}
|
||||
if v, err := time.ParseDuration(os.Getenv("NEBULA_CONNSOCK_WINDOW")); err == nil && v > 0 {
|
||||
c.window = v
|
||||
}
|
||||
if v, err := time.ParseDuration(os.Getenv("NEBULA_CONNSOCK_IDLE")); err == nil && v > 0 {
|
||||
c.idle = v
|
||||
}
|
||||
if v, err := time.ParseDuration(os.Getenv("NEBULA_CONNSOCK_OPEN_EVERY")); err == nil && v > 0 {
|
||||
c.openEvery = v
|
||||
}
|
||||
return c
|
||||
}
|
||||
|
||||
// connSockGroups holds the connSocks that the listen routines bound to one address share, so the limits, the
|
||||
// connected sockets and Rebind cover every routine, and a peer has at most one connected socket.
|
||||
var connSockGroups = struct {
|
||||
sync.Mutex
|
||||
m map[netip.AddrPort]*connSocks
|
||||
}{m: map[netip.AddrPort]*connSocks{}}
|
||||
|
||||
// joinConnSocks returns the connSocks u shares with the other listen routines bound to la, and makes it for the
|
||||
// first.
|
||||
func joinConnSocks(u *StdConn, la netip.AddrPort, s Settings) *connSocks {
|
||||
g := &connSockGroups
|
||||
g.Lock()
|
||||
defer g.Unlock()
|
||||
if cs := g.m[la]; s.Multi && cs != nil {
|
||||
cs.mu.Lock()
|
||||
cs.members = append(cs.members, u)
|
||||
cs.mu.Unlock()
|
||||
return cs
|
||||
}
|
||||
cs := &connSocks{cfg: connSockConfigFromEnv(), key: la, members: []*StdConn{u}, clock: monoNow, sleep: time.Sleep}
|
||||
if cs.cfg.max > 0 && !u.listenHost.IsUnspecified() && !s.Multi {
|
||||
// A connected socket on a specific listen.host binds the listener's own address, which xnu allows only when
|
||||
// both sockets set SO_REUSEPORT, and a listener with it lets another uid bind a dual-stack wildcard on the
|
||||
// port.
|
||||
cs.off.Store(true)
|
||||
u.l.Debug("connected sockets: off for a specific listen.host", "addr", s.Listen)
|
||||
}
|
||||
if s.Multi {
|
||||
g.m[la] = cs
|
||||
}
|
||||
return cs
|
||||
}
|
||||
|
||||
type connSocks struct {
|
||||
cfg connSockConfig
|
||||
// key is the listeners' bound address, which connSockGroups files this under.
|
||||
key netip.AddrPort
|
||||
// off keeps connected sockets from opening, when the listener's address can't be shared with them.
|
||||
off atomic.Bool
|
||||
// table maps each destination that is the remote of an established tunnel, and that a connected socket could
|
||||
// reach, to its peer; it is nil when there are none, so a send with nothing to consider costs one load. Every
|
||||
// send reads it without a lock, and mu guards copying it. An open that holds mu and still finds its peer here
|
||||
// can't outlive the tunnel.
|
||||
table atomic.Pointer[map[netip.AddrPort]*connSockPeer]
|
||||
// reserved counts the connected sockets that are open, opening or closing, against cfg.max; mu guards changing it.
|
||||
reserved atomic.Int32
|
||||
mu sync.Mutex
|
||||
closed bool
|
||||
// members are the listen routines' listeners that share these connected sockets.
|
||||
members []*StdConn
|
||||
// pending holds each destination whose connected socket is opening or closing, and not on its peer. xnu
|
||||
// refuses to connect a 4-tuple that is still bound, so a destination in pending can't open another.
|
||||
pending map[netip.AddrPort]struct{}
|
||||
// rebinds counts Rebinds, so an open that copied the listener's interface before one is discarded.
|
||||
rebinds uint64
|
||||
// closers tracks the goroutines that close detached connected sockets.
|
||||
closers sync.WaitGroup
|
||||
// done stops the reaper; it is made when ListenOut starts the connected sockets.
|
||||
done chan struct{}
|
||||
// opens bounds connected socket opens to cfg.max at once and one per cfg.openEvery after.
|
||||
opens gcra
|
||||
// logs bounds connected socket log lines at info or warn; see connSockLogBurst.
|
||||
logs gcra
|
||||
// clock returns monotonic nanoseconds and sleep waits out ENOBUFS: monoNow and time.Sleep, or stand-ins in
|
||||
// tests.
|
||||
clock func() int64
|
||||
sleep func(time.Duration)
|
||||
// dialHook and closeHook, when set, run just before an open's dials and a close's Close, outside mu; tests
|
||||
// use them to hold an open or close in flight.
|
||||
dialHook, closeHook func(dst netip.AddrPort)
|
||||
}
|
||||
|
||||
// connSockPeer is what connSocks keeps about an established tunnel's remote: its connected socket, how busy it is,
|
||||
// and how long a failed connected socket keeps it on the listener.
|
||||
type connSockPeer struct {
|
||||
sock atomic.Pointer[connSock]
|
||||
// windowMu guards start, the monotonic time the current window began, and n, the datagrams sent in it, so a
|
||||
// window's reset and its counts can't interleave with another sender's.
|
||||
windowMu sync.Mutex
|
||||
start int64
|
||||
n int
|
||||
// retryAt is the monotonic time before which a peer whose connected socket failed stays on the listener;
|
||||
// connSocks.mu guards it.
|
||||
retryAt int64
|
||||
}
|
||||
|
||||
// busy counts n more datagrams to p and reports whether it has now sent cfg.run within one window. A busy peer's
|
||||
// count starts over, so a peer that can't get a connected socket retries at most once per cfg.run sends.
|
||||
func (p *connSockPeer) busy(now int64, n int, cfg *connSockConfig) bool {
|
||||
p.windowMu.Lock()
|
||||
defer p.windowMu.Unlock()
|
||||
if time.Duration(now-p.start) > cfg.window {
|
||||
p.start, p.n = now, 0
|
||||
}
|
||||
p.n += n
|
||||
if p.n < cfg.run {
|
||||
return false
|
||||
}
|
||||
p.n = 0
|
||||
return true
|
||||
}
|
||||
|
||||
// connSockLogBurst and connSockLogEvery size the bucket that lets connected socket opens, closes and failures log
|
||||
// at info or warn; past it they log at debug, so churn can't flood the log.
|
||||
const (
|
||||
connSockLogBurst = 32
|
||||
connSockLogEvery = 10 * time.Second
|
||||
)
|
||||
|
||||
var monoStart = time.Now()
|
||||
|
||||
func monoNow() int64 { return int64(time.Since(monoStart)) }
|
||||
|
||||
// gcra is a token bucket kept as the monotonic time it is next full (the generic cell rate algorithm), so it needs
|
||||
// no refill tick.
|
||||
type gcra struct{ tat int64 }
|
||||
|
||||
// take spends a token from a bucket of burst that earns one back per every, and reports whether there was one to
|
||||
// spend.
|
||||
func (g *gcra) take(now int64, burst int, every time.Duration) bool {
|
||||
e := int64(every)
|
||||
tat := max(g.tat, now)
|
||||
if tat-now > int64(burst-1)*e {
|
||||
return false
|
||||
}
|
||||
g.tat = tat + e
|
||||
return true
|
||||
}
|
||||
|
||||
// logLevelLocked returns level while the log bucket has a token, and debug once it is spent.
|
||||
func (cs *connSocks) logLevelLocked(level slog.Level) slog.Level {
|
||||
if cs.logs.take(cs.clock(), connSockLogBurst, connSockLogEvery) {
|
||||
return level
|
||||
}
|
||||
return slog.LevelDebug
|
||||
}
|
||||
|
||||
// startConnSocks starts the idle reaper.
|
||||
func (u *StdConn) startConnSocks() {
|
||||
cs := u.socks
|
||||
cs.mu.Lock()
|
||||
defer cs.mu.Unlock()
|
||||
if cs.closed || cs.done != nil || cs.cfg.max <= 0 || cs.off.Load() {
|
||||
return
|
||||
}
|
||||
cs.done = make(chan struct{})
|
||||
go u.reapConnSocks(cs.done)
|
||||
}
|
||||
|
||||
// stopConnSocks closes every connected socket and keeps new ones from opening, once any listen routine's listener
|
||||
// closes, as they do together at shutdown. It returns once their descriptors are closed.
|
||||
func (u *StdConn) stopConnSocks() {
|
||||
cs := u.socks
|
||||
cs.mu.Lock()
|
||||
cs.members = slices.DeleteFunc(cs.members, func(m *StdConn) bool { return m == u })
|
||||
if !cs.closed {
|
||||
cs.closed = true
|
||||
if cs.done != nil {
|
||||
close(cs.done)
|
||||
}
|
||||
u.detachAllLocked("close")
|
||||
}
|
||||
cs.mu.Unlock()
|
||||
connSockGroups.Lock()
|
||||
if connSockGroups.m[cs.key] == cs {
|
||||
delete(connSockGroups.m, cs.key)
|
||||
}
|
||||
connSockGroups.Unlock()
|
||||
cs.closers.Wait()
|
||||
}
|
||||
|
||||
// siblings returns the other listen routines' listeners.
|
||||
func (cs *connSocks) siblings(u *StdConn) []*StdConn {
|
||||
cs.mu.Lock()
|
||||
defer cs.mu.Unlock()
|
||||
return slices.DeleteFunc(slices.Clone(cs.members), func(m *StdConn) bool { return m == u })
|
||||
}
|
||||
|
||||
// connSockFor returns dst's connected socket, or nil.
|
||||
func (u *StdConn) connSockFor(dst netip.AddrPort) *connSock {
|
||||
if p := u.socks.peer(dst); p != nil {
|
||||
return p.sock.Load()
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func (cs *connSocks) peer(dst netip.AddrPort) *connSockPeer {
|
||||
if t := cs.table.Load(); t != nil {
|
||||
return (*t)[dst]
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// SetEstablishedPeer makes dst eligible for a connected socket while it is the remote of an established tunnel,
|
||||
// and closes the one it has once it no longer is. Nebula calls it for every listen routine under the hostmap's
|
||||
// write lock, so repeats are no-ops and it makes no syscalls: the descriptor is closed by another goroutine.
|
||||
func (u *StdConn) SetEstablishedPeer(dst netip.AddrPort, established bool) {
|
||||
cs := u.socks
|
||||
if cs.cfg.max <= 0 || cs.off.Load() || !u.connSockable(dst) {
|
||||
return
|
||||
}
|
||||
cs.mu.Lock()
|
||||
defer cs.mu.Unlock()
|
||||
t := cs.table.Load()
|
||||
p := cs.peer(dst)
|
||||
if cs.closed || (p != nil) == established {
|
||||
return
|
||||
}
|
||||
next := map[netip.AddrPort]*connSockPeer{}
|
||||
if t != nil {
|
||||
next = maps.Clone(*t)
|
||||
}
|
||||
if established {
|
||||
p = &connSockPeer{start: cs.clock()}
|
||||
next[dst] = p
|
||||
} else {
|
||||
delete(next, dst)
|
||||
if s := p.sock.Load(); s != nil {
|
||||
u.detachLocked(s, "tunnel gone", false)
|
||||
}
|
||||
}
|
||||
cs.storeTableLocked(next)
|
||||
}
|
||||
|
||||
// storeTableLocked publishes t, or nil for an empty one.
|
||||
func (cs *connSocks) storeTableLocked(t map[netip.AddrPort]*connSockPeer) {
|
||||
if len(t) == 0 {
|
||||
cs.table.Store(nil)
|
||||
return
|
||||
}
|
||||
cs.table.Store(&t)
|
||||
}
|
||||
|
||||
// connSockable reports whether a connected socket to dst could send what the listener would. A v4 listener can't
|
||||
// reach a v6 destination at all, and a connected socket bound to a specific listen.host must share its family.
|
||||
func (u *StdConn) connSockable(dst netip.AddrPort) bool {
|
||||
if !dst.IsValid() || dst.Port() == 0 {
|
||||
return false
|
||||
}
|
||||
if u.isV4 {
|
||||
return dst.Addr().Is4()
|
||||
}
|
||||
return u.listenHost.IsUnspecified() || u.listenHost.Unmap().Is4() == dst.Addr().Unmap().Is4()
|
||||
}
|
||||
|
||||
// connSockRun sends bufs, all to p's destination, on p's connected socket, opening one if they make p busy. It
|
||||
// returns how many went out; when that is short of len(bufs), err is the failure of bufs[sent], or nil to leave
|
||||
// bufs[sent:] to the listener.
|
||||
func (u *StdConn) connSockRun(p *connSockPeer, dst netip.AddrPort, bufs [][]byte) (sent int, err error) {
|
||||
s := p.sock.Load()
|
||||
if s == nil {
|
||||
if s = u.maybeOpenConnSock(p, dst, len(bufs)); s == nil {
|
||||
return 0, nil
|
||||
}
|
||||
}
|
||||
sent, errno, closed := u.connSockWrite(s, bufs)
|
||||
switch {
|
||||
case sent == len(bufs):
|
||||
case connSockDead(errno):
|
||||
u.closeConnSock(s, errno.Error(), true)
|
||||
case !closed:
|
||||
return sent, &net.OpError{Op: "write", Err: errno}
|
||||
}
|
||||
return sent, nil
|
||||
}
|
||||
|
||||
// maybeOpenConnSock counts n datagrams to p, and opens a connected socket to it once it is busy and nothing rules
|
||||
// one out.
|
||||
func (u *StdConn) maybeOpenConnSock(p *connSockPeer, dst netip.AddrPort, n int) *connSock {
|
||||
cs := u.socks
|
||||
if n <= 0 || u.reader.Load() == nil || int(cs.reserved.Load()) >= cs.cfg.max || !p.busy(cs.clock(), n, &cs.cfg) {
|
||||
return nil
|
||||
}
|
||||
cs.mu.Lock()
|
||||
if cs.closed || cs.peer(dst) != p {
|
||||
cs.mu.Unlock()
|
||||
return nil
|
||||
}
|
||||
if s := p.sock.Load(); s != nil {
|
||||
cs.mu.Unlock()
|
||||
return s
|
||||
}
|
||||
now := cs.clock()
|
||||
if _, ok := cs.pending[dst]; ok || int(cs.reserved.Load()) >= cs.cfg.max || now < p.retryAt ||
|
||||
!cs.opens.take(now, cs.cfg.max, cs.cfg.openEvery) {
|
||||
cs.mu.Unlock()
|
||||
return nil
|
||||
}
|
||||
if cs.pending == nil {
|
||||
cs.pending = map[netip.AddrPort]struct{}{}
|
||||
}
|
||||
cs.pending[dst] = struct{}{}
|
||||
cs.reserved.Add(1)
|
||||
rebinds := cs.rebinds
|
||||
cs.mu.Unlock()
|
||||
|
||||
if cs.dialHook != nil {
|
||||
cs.dialHook(dst)
|
||||
}
|
||||
s, err := u.dialConnSock(p, dst)
|
||||
|
||||
cs.mu.Lock()
|
||||
if err != nil {
|
||||
delete(cs.pending, dst)
|
||||
cs.reserved.Add(-1)
|
||||
p.retryAt = cs.clock() + int64(cs.cfg.backoff)
|
||||
level := cs.logLevelLocked(slog.LevelWarn)
|
||||
cs.mu.Unlock()
|
||||
u.l.Log(context.Background(), level, "connected socket: open failed, staying on the listener", "udpAddr", dst, "error", err)
|
||||
return nil
|
||||
}
|
||||
if cs.closed || cs.rebinds != rebinds || cs.peer(dst) != p {
|
||||
// The tunnel went away, or a Rebind or shutdown ran, while the socket was opening; it stays in pending until
|
||||
// it is closed.
|
||||
cs.mu.Unlock()
|
||||
u.finishClose(s)
|
||||
u.l.Debug("connected socket: discarded, its tunnel or route changed while it opened", "udpAddr", dst)
|
||||
return nil
|
||||
}
|
||||
delete(cs.pending, dst)
|
||||
p.sock.Store(s)
|
||||
go u.readConnSock(s)
|
||||
level := cs.logLevelLocked(slog.LevelInfo)
|
||||
cs.mu.Unlock()
|
||||
u.l.Log(context.Background(), level, "connected socket: opened", "udpAddr", dst, "local", s.conn.LocalAddr(), "open", cs.reserved.Load())
|
||||
return s
|
||||
}
|
||||
|
||||
// dialConnSock opens a socket on the listener's port with SO_REUSEPORT, bound to the configured listen.host or,
|
||||
// for a wildcard listener, to the source address the route to dst picks, and connected to dst. It carries the
|
||||
// listener's IP_BOUND_IF, so both route the same way.
|
||||
func (u *StdConn) dialConnSock(p *connSockPeer, dst netip.AddrPort) (*connSock, error) {
|
||||
raddr := net.UDPAddrFromAddrPort(netip.AddrPortFrom(dst.Addr().Unmap(), dst.Port()))
|
||||
network := "udp6"
|
||||
if raddr.IP.To4() != nil {
|
||||
network = "udp4"
|
||||
}
|
||||
ifindex, err := u.boundIf()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
local := &net.UDPAddr{IP: u.listenHost.AsSlice(), Zone: u.listenHost.Zone()}
|
||||
if u.listenHost.IsUnspecified() {
|
||||
// A connected socket gets the source address xnu would pick for an unconnected send to dst.
|
||||
d := net.Dialer{Control: connSockControl(false, ifindex)}
|
||||
probe, err := d.Dial(network, raddr.String())
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
local = probe.LocalAddr().(*net.UDPAddr)
|
||||
_ = probe.Close()
|
||||
}
|
||||
local.Port = int(u.port)
|
||||
d := net.Dialer{LocalAddr: local, Control: connSockControl(true, ifindex)}
|
||||
c, err := d.Dial(network, raddr.String())
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
uc := c.(*net.UDPConn)
|
||||
rc, err := uc.SyscallConn()
|
||||
if err != nil {
|
||||
_ = uc.Close()
|
||||
return nil, err
|
||||
}
|
||||
s := &connSock{dst: dst, peer: p, conn: uc, rc: rc, sys: writeFd}
|
||||
s.used.Store(u.socks.clock())
|
||||
return s, nil
|
||||
}
|
||||
|
||||
// connSockControl sets SO_REUSEPORT when reuse is set, and IP_BOUND_IF or IPV6_BOUND_IF when ifindex isn't 0,
|
||||
// before the socket binds.
|
||||
func connSockControl(reuse bool, ifindex int) func(network, address string, c syscall.RawConn) error {
|
||||
return func(network, _ string, c syscall.RawConn) error {
|
||||
var serr error
|
||||
err := c.Control(func(fd uintptr) {
|
||||
if reuse {
|
||||
serr = unix.SetsockoptInt(int(fd), unix.SOL_SOCKET, unix.SO_REUSEPORT, 1)
|
||||
}
|
||||
if serr == nil && ifindex != 0 {
|
||||
if network == "udp4" {
|
||||
serr = unix.SetsockoptInt(int(fd), unix.IPPROTO_IP, unix.IP_BOUND_IF, ifindex)
|
||||
} else {
|
||||
serr = unix.SetsockoptInt(int(fd), unix.IPPROTO_IPV6, unix.IPV6_BOUND_IF, ifindex)
|
||||
}
|
||||
}
|
||||
})
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
return serr
|
||||
}
|
||||
}
|
||||
|
||||
// boundIf returns the interface index the listener is scoped to, or 0. An error keeps the peer on the listener,
|
||||
// since a connected socket opened without the listener's scope could route out an interface the listener can't.
|
||||
func (u *StdConn) boundIf() (int, error) {
|
||||
level, opt := unix.IPPROTO_IPV6, unix.IPV6_BOUND_IF
|
||||
if u.isV4 {
|
||||
level, opt = unix.IPPROTO_IP, unix.IP_BOUND_IF
|
||||
}
|
||||
v, err := unix.GetsockoptInt(int(u.sysFd), level, opt)
|
||||
if err != nil {
|
||||
return 0, fmt.Errorf("reading the listener's bound interface: %w", err)
|
||||
}
|
||||
return v, nil
|
||||
}
|
||||
|
||||
// closeConnSock closes s if it is still open. With backoff set, the peer stays on the listener until the backoff
|
||||
// runs out.
|
||||
func (u *StdConn) closeConnSock(s *connSock, why string, backoff bool) {
|
||||
u.socks.mu.Lock()
|
||||
u.detachLocked(s, why, backoff)
|
||||
u.socks.mu.Unlock()
|
||||
}
|
||||
|
||||
// detachLocked takes s off its peer, if it is still there, and closes it on another goroutine, since callers such
|
||||
// as SetEstablishedPeer hold locks that no socket syscall should run under. s.dst stays in pending until the close
|
||||
// completes.
|
||||
func (u *StdConn) detachLocked(s *connSock, why string, backoff bool) {
|
||||
cs := u.socks
|
||||
if !s.peer.sock.CompareAndSwap(s, nil) {
|
||||
return
|
||||
}
|
||||
if backoff {
|
||||
s.peer.retryAt = cs.clock() + int64(cs.cfg.backoff)
|
||||
}
|
||||
if cs.pending == nil {
|
||||
cs.pending = map[netip.AddrPort]struct{}{}
|
||||
}
|
||||
cs.pending[s.dst] = struct{}{}
|
||||
level := cs.logLevelLocked(slog.LevelInfo)
|
||||
cs.closers.Add(1)
|
||||
go func() {
|
||||
defer cs.closers.Done()
|
||||
open := u.finishClose(s)
|
||||
u.l.Log(context.Background(), level, "connected socket: closed", "udpAddr", s.dst, "reason", why, "open", open)
|
||||
}()
|
||||
}
|
||||
|
||||
// finishClose closes s, whose destination is in pending, then lets the destination open again, and returns how
|
||||
// many connected sockets are left. Closing waits only for a write already in a syscall: a write parked on a full
|
||||
// buffer is woken, and one waiting out ENOBUFS holds no reference on the descriptor.
|
||||
func (u *StdConn) finishClose(s *connSock) int32 {
|
||||
cs := u.socks
|
||||
if cs.closeHook != nil {
|
||||
cs.closeHook(s.dst)
|
||||
}
|
||||
_ = s.conn.Close()
|
||||
cs.mu.Lock()
|
||||
defer cs.mu.Unlock()
|
||||
delete(cs.pending, s.dst)
|
||||
return cs.reserved.Add(-1)
|
||||
}
|
||||
|
||||
// detachAllLocked detaches every connected socket, for a network change or shutdown.
|
||||
func (u *StdConn) detachAllLocked(why string) {
|
||||
if t := u.socks.table.Load(); t != nil {
|
||||
for _, p := range *t {
|
||||
if s := p.sock.Load(); s != nil {
|
||||
u.detachLocked(s, why, false)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// closeConnSocks detaches every connected socket and discards the ones still opening, for a network change.
|
||||
func (u *StdConn) closeConnSocks(why string) {
|
||||
u.socks.mu.Lock()
|
||||
u.socks.rebinds++
|
||||
u.detachAllLocked(why)
|
||||
u.socks.mu.Unlock()
|
||||
}
|
||||
|
||||
func (u *StdConn) reapConnSocks(done <-chan struct{}) {
|
||||
cs := u.socks
|
||||
idle := cs.cfg.idle
|
||||
tick := time.NewTicker(max(min(idle/4, 5*time.Second), time.Millisecond))
|
||||
defer tick.Stop()
|
||||
for {
|
||||
select {
|
||||
case <-done:
|
||||
return
|
||||
case <-tick.C:
|
||||
}
|
||||
t := cs.table.Load()
|
||||
if t == nil {
|
||||
continue
|
||||
}
|
||||
now := cs.clock()
|
||||
for _, p := range *t {
|
||||
if s := p.sock.Load(); s != nil && time.Duration(now-s.used.Load()) > idle {
|
||||
u.closeConnSock(s, "idle", false)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// connSockDead reports whether a connected socket send or receive error means the connected path to the peer is
|
||||
// gone, so its traffic belongs back on the listener. A connected UDP socket reports a peer's ICMP unreachable as
|
||||
// ECONNREFUSED on its next call, which the unconnected listener never sees.
|
||||
func connSockDead(errno syscall.Errno) bool {
|
||||
switch errno {
|
||||
case unix.ECONNREFUSED, unix.EHOSTUNREACH, unix.EHOSTDOWN, unix.ENETUNREACH, unix.ENETDOWN,
|
||||
unix.EADDRNOTAVAIL, unix.EPIPE, unix.ENOTCONN, unix.EDESTADDRREQ:
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// enobufsWait is how long a connected socket send sleeps when the interface queue is flow controlled. The kernel
|
||||
// posts no wakeup when the advisory lifts, so this polls; 50us kept a gigabit link full without spinning a core in
|
||||
// the 09-25 probes.
|
||||
const enobufsWait = 50 * time.Microsecond
|
||||
|
||||
// connSockWrite writes bufs on s, one datagram per write. A full socket buffer parks the caller in the netpoller
|
||||
// until the socket is writable, and a flow-controlled interface makes it wait out ENOBUFS, so a busy link slows
|
||||
// the tun reader instead of dropping. Once the connected socket has waited cfg.enobufsMax without a send going
|
||||
// through, either one drops the datagram instead, and a dropped datagram counts as sent, as the listener's
|
||||
// unreported interface drops do; it never falls back to the listener, which would reorder it. closed reports that
|
||||
// the connected socket was closed before bufs[sent] went out; any other error stops the run and is returned with
|
||||
// how many went out.
|
||||
func (u *StdConn) connSockWrite(s *connSock, bufs [][]byte) (sent int, errno syscall.Errno, closed bool) {
|
||||
cs := u.socks
|
||||
defer func() {
|
||||
if sent > 0 {
|
||||
s.used.Store(cs.clock())
|
||||
}
|
||||
}()
|
||||
for sent < len(bufs) {
|
||||
err := s.try(bufs[sent], false)
|
||||
if err == syscall.EAGAIN || err == os.ErrDeadlineExceeded {
|
||||
// os.ErrDeadlineExceeded here is another writer's parked deadline, passed but not yet cleared.
|
||||
err = u.parkedWrite(s, bufs[sent])
|
||||
}
|
||||
switch err {
|
||||
case nil:
|
||||
sent++
|
||||
if s.stallAt.Load() != 0 {
|
||||
s.stallAt.Store(0)
|
||||
s.dropping.Store(false)
|
||||
}
|
||||
continue
|
||||
case errStallSpent:
|
||||
u.dropStalled(s)
|
||||
sent++
|
||||
continue
|
||||
}
|
||||
errno, ok := err.(syscall.Errno)
|
||||
if !ok {
|
||||
return sent, 0, true
|
||||
}
|
||||
if errno != syscall.ENOBUFS {
|
||||
return sent, errno, false
|
||||
}
|
||||
// The wait holds no reference on the descriptor, so a close doesn't wait for it.
|
||||
if s.stalledFor(cs.clock()) < cs.cfg.enobufsMax {
|
||||
cs.sleep(enobufsWait)
|
||||
} else {
|
||||
u.dropStalled(s)
|
||||
sent++
|
||||
}
|
||||
}
|
||||
return sent, 0, false
|
||||
}
|
||||
|
||||
// parkedWrite writes b after EAGAIN, parked in the netpoller for what is left of s's stall budget, and returns
|
||||
// errStallSpent once none is. golang/go#73919: a darwin UDP write parked on EAGAIN can wait forever for a
|
||||
// writability event that never comes, so the wait always has a deadline.
|
||||
func (u *StdConn) parkedWrite(s *connSock, b []byte) error {
|
||||
cs := u.socks
|
||||
s.parkMu.Lock()
|
||||
defer s.parkMu.Unlock()
|
||||
left := cs.cfg.enobufsMax - s.stalledFor(cs.clock())
|
||||
if left <= 0 {
|
||||
return errStallSpent
|
||||
}
|
||||
if err := s.conn.SetWriteDeadline(time.Now().Add(left)); err != nil {
|
||||
return net.ErrClosed
|
||||
}
|
||||
err := s.try(b, true)
|
||||
_ = s.conn.SetWriteDeadline(time.Time{})
|
||||
if err == os.ErrDeadlineExceeded {
|
||||
return errStallSpent
|
||||
}
|
||||
return err
|
||||
}
|
||||
|
||||
// dropStalled logs the first datagram a stall drops.
|
||||
func (u *StdConn) dropStalled(s *connSock) {
|
||||
if !s.dropping.Swap(true) {
|
||||
u.l.Debug("connected socket: sends stalled, dropping datagrams until one goes through", "udpAddr", s.dst)
|
||||
}
|
||||
}
|
||||
|
||||
// stalledFor records an ENOBUFS or EAGAIN on s at now and returns how long its sends have stalled: since the first
|
||||
// ENOBUFS or EAGAIN after a send last went through. Every writer measures from that one time, so concurrent writers
|
||||
// spend the budget no faster than one, and a send going through ends the stall for every writer, including one
|
||||
// asleep in it.
|
||||
func (s *connSock) stalledFor(now int64) time.Duration {
|
||||
if s.stallAt.CompareAndSwap(0, now) {
|
||||
return 0
|
||||
}
|
||||
at := s.stallAt.Load()
|
||||
if at == 0 {
|
||||
return 0
|
||||
}
|
||||
return time.Duration(now - at)
|
||||
}
|
||||
|
||||
// readConnSock delivers a connected socket's datagrams through the listener's reader, serialized with ListenOut,
|
||||
// until the connected socket is closed. Any receive error closes it: a connected socket reports its peer's
|
||||
// unreachables here, and retrying an unexpected error could spin.
|
||||
func (u *StdConn) readConnSock(s *connSock) {
|
||||
rd := u.reader.Load()
|
||||
buf := make([]byte, MTU)
|
||||
for {
|
||||
n, from, err := s.conn.ReadFromUDPAddrPort(buf)
|
||||
if err != nil {
|
||||
if errors.Is(err, net.ErrClosed) {
|
||||
return
|
||||
}
|
||||
why := err.Error()
|
||||
var errno syscall.Errno
|
||||
if errors.As(err, &errno) && connSockDead(errno) {
|
||||
why = errno.Error()
|
||||
} else {
|
||||
u.l.Warn("connected socket: unexpected receive error", "udpAddr", s.dst, "error", err)
|
||||
}
|
||||
u.closeConnSock(s, why, true)
|
||||
return
|
||||
}
|
||||
s.used.Store(u.socks.clock())
|
||||
u.readMu.Lock()
|
||||
rd.r(netip.AddrPortFrom(from.Addr().Unmap(), from.Port()), buf[:n:n])
|
||||
rd.flush()
|
||||
u.readMu.Unlock()
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large.
Load diff
@@ -1,6 +0,0 @@
|
||||
//go:build !race && !e2e_testing
|
||||
|
||||
package udp
|
||||
|
||||
// raceEnabled reports a -race build, whose sync.Pool drops a random share of what is put back.
|
||||
const raceEnabled = false
|
||||
@@ -1,6 +0,0 @@
|
||||
//go:build race && !e2e_testing
|
||||
|
||||
package udp
|
||||
|
||||
// raceEnabled reports a -race build, whose sync.Pool drops a random share of what is put back.
|
||||
const raceEnabled = true
|
||||
+273
-100
@@ -10,7 +10,6 @@ import (
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
"unsafe"
|
||||
@@ -25,25 +24,11 @@ type StdConn struct {
|
||||
sysFd uintptr
|
||||
l *slog.Logger
|
||||
|
||||
// listenHost and port are the configured address and the bound port, which a connected socket shares.
|
||||
listenHost netip.Addr
|
||||
port uint16
|
||||
// rc reaches the listener's descriptor for another listen routine's Rebind.
|
||||
rc syscall.RawConn
|
||||
socks *connSocks
|
||||
// reader is ListenOut's reader, which connected socket readers share; readMu serializes them, since an
|
||||
// EncReader isn't safe for concurrent use.
|
||||
reader atomic.Pointer[readerPair]
|
||||
readMu sync.Mutex
|
||||
}
|
||||
|
||||
type readerPair struct {
|
||||
r EncReader
|
||||
flush func()
|
||||
noSendmsgX atomic.Bool
|
||||
sb *sendScratch
|
||||
}
|
||||
|
||||
var _ Conn = &StdConn{}
|
||||
var _ EstablishedPeerConn = &StdConn{}
|
||||
|
||||
func NewListener(l *slog.Logger, s Settings) (Conn, error) {
|
||||
lc := NewListenConfig(s.Multi)
|
||||
@@ -53,13 +38,12 @@ func NewListener(l *slog.Logger, s Settings) (Conn, error) {
|
||||
}
|
||||
|
||||
if uc, ok := pc.(*net.UDPConn); ok {
|
||||
c := &StdConn{UDPConn: uc, l: l, listenHost: s.Listen.Addr()}
|
||||
c := &StdConn{UDPConn: uc, l: l}
|
||||
|
||||
rc, err := uc.SyscallConn()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to open udp socket: %w", err)
|
||||
}
|
||||
c.rc = rc
|
||||
|
||||
err = rc.Control(func(fd uintptr) {
|
||||
c.sysFd = fd
|
||||
@@ -73,8 +57,6 @@ func NewListener(l *slog.Logger, s Settings) (Conn, error) {
|
||||
return nil, err
|
||||
}
|
||||
c.isV4 = la.Addr().Is4()
|
||||
c.port = la.Port()
|
||||
c.socks = joinConnSocks(c, la, s)
|
||||
|
||||
return c, nil
|
||||
}
|
||||
@@ -111,19 +93,6 @@ func NewListenConfig(multi bool) net.ListenConfig {
|
||||
func sendto(s int, buf []byte, flags int, to unsafe.Pointer, addrlen int32) (err error)
|
||||
|
||||
func (u *StdConn) WriteTo(b []byte, ap netip.AddrPort) error {
|
||||
if t := u.socks.table.Load(); t != nil {
|
||||
if p := (*t)[ap]; p != nil {
|
||||
bufs := [1][]byte{b}
|
||||
if sent, err := u.connSockRun(p, ap, bufs[:]); sent == 1 || err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
}
|
||||
return u.writeTo(b, ap)
|
||||
}
|
||||
|
||||
// writeTo sends b through the listener.
|
||||
func (u *StdConn) writeTo(b []byte, ap netip.AddrPort) error {
|
||||
var sa unsafe.Pointer
|
||||
var addrLen int32
|
||||
|
||||
@@ -174,54 +143,165 @@ 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) {
|
||||
// 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 listener send buffer
|
||||
// silently drops those packets (linux blocks instead). Poll for
|
||||
// writability on EAGAIN before giving up on them.
|
||||
written := 0
|
||||
t := u.socks.table.Load()
|
||||
if t == nil {
|
||||
for i, b := range bufs {
|
||||
if err := u.writeTo(b, addrs[i]); err == nil {
|
||||
written++
|
||||
} else {
|
||||
u.l.Debug("failed to write packet in batch", "udpAddr", addrs[i], "error", err)
|
||||
}
|
||||
}
|
||||
return written, nil
|
||||
if u.noSendmsgX.Load() {
|
||||
return u.writeEach(bufs, addrs), nil
|
||||
}
|
||||
for off := 0; off < len(bufs); {
|
||||
// A run of datagrams to one peer goes out together, on its connected socket if it has or earns one.
|
||||
dst := addrs[off]
|
||||
end := off + 1
|
||||
for end < len(bufs) && addrs[end] == dst {
|
||||
end++
|
||||
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++
|
||||
}
|
||||
if p := (*t)[dst]; p != nil {
|
||||
for off < end {
|
||||
sent, err := u.connSockRun(p, dst, bufs[off:end])
|
||||
|
||||
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
|
||||
if err == nil {
|
||||
break
|
||||
}
|
||||
u.l.Debug("failed to write packet in batch", "udpAddr", dst, "error", err)
|
||||
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++
|
||||
}
|
||||
}
|
||||
// The listener sends what no connected socket took.
|
||||
for ; off < end; off++ {
|
||||
if err := u.writeTo(bufs[off], dst); err == nil {
|
||||
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++
|
||||
} else {
|
||||
u.l.Debug("failed to write packet in batch", "udpAddr", dst, "error", err)
|
||||
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 {
|
||||
written := 0
|
||||
for i, b := range bufs {
|
||||
if err := u.WriteTo(b, addrs[i]); err == nil {
|
||||
written++
|
||||
} else {
|
||||
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
|
||||
}
|
||||
|
||||
func (u *StdConn) LocalAddr() (netip.AddrPort, error) {
|
||||
a := u.UDPConn.LocalAddr()
|
||||
|
||||
@@ -247,13 +327,121 @@ 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)
|
||||
u.reader.Store(&readerPair{r: r, flush: flush})
|
||||
u.startConnSocks()
|
||||
|
||||
for {
|
||||
// Just read one packet at a time
|
||||
n, rua, err := u.ReadFromUDPAddrPort(buffer)
|
||||
if err != nil {
|
||||
if errors.Is(err, net.ErrClosed) {
|
||||
@@ -263,17 +451,22 @@ func (u *StdConn) ListenOut(r EncReader, flush func()) error {
|
||||
continue
|
||||
}
|
||||
|
||||
u.readMu.Lock()
|
||||
r(netip.AddrPortFrom(rua.Addr().Unmap(), rua.Port()), buffer[:n:n])
|
||||
flush()
|
||||
u.readMu.Unlock()
|
||||
}
|
||||
}
|
||||
|
||||
// Close closes the connected sockets of every listen routine, then the listener.
|
||||
func (u *StdConn) Close() error {
|
||||
u.stopConnSocks()
|
||||
return u.UDPConn.Close()
|
||||
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 {
|
||||
@@ -282,10 +475,7 @@ func (u *StdConn) SupportsMultipleReaders() bool {
|
||||
|
||||
// Rebind clears the interface the kernel scoped this socket to, so that sends are routed against the current
|
||||
// routing table instead of the interface we happened to be on when the socket was created. Darwin pins sockets
|
||||
// this way on its own, which is what strands us after the underlying network changes. Control.RebindUDPServer
|
||||
// rebinds only the first writer, so this clears the other listen routines' listeners too. Connected sockets are
|
||||
// closed after the listeners are cleared, and later ones copy the cleared scope and pick their source addresses
|
||||
// afresh.
|
||||
// this way on its own, which is what strands us after the underlying network changes.
|
||||
func (u *StdConn) Rebind() error {
|
||||
var err error
|
||||
if u.isV4 {
|
||||
@@ -293,23 +483,6 @@ func (u *StdConn) Rebind() error {
|
||||
} else {
|
||||
err = syscall.SetsockoptInt(int(u.sysFd), syscall.IPPROTO_IPV6, syscall.IPV6_BOUND_IF, 0)
|
||||
}
|
||||
for _, m := range u.socks.siblings(u) {
|
||||
err = errors.Join(err, m.clearBoundIf())
|
||||
}
|
||||
u.closeConnSocks("rebind")
|
||||
|
||||
return err
|
||||
}
|
||||
|
||||
// clearBoundIf clears the interface the listener is scoped to through its RawConn, which fails on a listener that
|
||||
// closed concurrently instead of reaching whatever reused its descriptor number.
|
||||
func (u *StdConn) clearBoundIf() error {
|
||||
level, opt := syscall.IPPROTO_IPV6, syscall.IPV6_BOUND_IF
|
||||
if u.isV4 {
|
||||
level, opt = syscall.IPPROTO_IP, syscall.IP_BOUND_IF
|
||||
}
|
||||
var serr error
|
||||
if err := u.rc.Control(func(fd uintptr) { serr = syscall.SetsockoptInt(int(fd), level, opt, 0) }); err != nil {
|
||||
return err
|
||||
}
|
||||
return serr
|
||||
}
|
||||
@@ -0,0 +1,85 @@
|
||||
//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")
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,302 @@
|
||||
//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
|
||||
}
|
||||
@@ -0,0 +1,150 @@
|
||||
//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