Compare commits

..
Author SHA1 Message Date
JackDoan 641d1fb703 Clarify which traffic port rules match 2026-09-29 13:17:21 -05:00
JackDoan 11a4298c36 Only read IPv4 ports from TCP and UDP 2026-09-29 13:02:30 -05:00
29 changed files with 85 additions and 4904 deletions

No files matched your search

+1 -2
View File
@@ -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)
}
-90
View File
@@ -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
}
-173
View File
@@ -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())
}
+2
View File
@@ -459,6 +459,8 @@ firewall:
# - port: Takes `0` or `any` as any, a single number `80`, a range `200-901`, or `fragment` to match second and further fragments of fragmented packets (since there is no port available).
# proto: `any`, `tcp`, `udp`, or `icmp`
# a port specification is ignored if proto is `icmp`
# Nebula only reads ports from tcp and udp, so a proto `any` rule with a specific port or range only matches tcp and udp traffic.
# Other protocols (gre, esp, sctp, etc) need port `any`.
# host: `any` or a literal hostname, ie `test-host`
# group: `any` or a literal group name, ie `default-group`
# groups: Same as group but accepts a list of values. Multiple values are AND'd together and a certificate would have to contain all groups to pass
+1 -17
View File
@@ -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()
}
}
}
-10
View File
@@ -432,11 +432,6 @@ func (f *Interface) pinThisThread(i int) {
}
func (f *Interface) listenIn(queue tio.Queue, i int) {
if sendPipelinePlatform {
listenInPipelined(f, queue, i)
return
}
// Pinning this thread (and goroutine) to a single CPU keeps every sendmmsg from this goroutine going through the
// same TX ring on the nic, so the wire sees per-flow order. Skip entirely when tun.pin_threads is false.
if f.pinThreads {
@@ -483,11 +478,6 @@ func (f *Interface) listenIn(queue tio.Queue, i int) {
func (f *Interface) flushSendBatch(sb *batch.SendBatch, q int) {
queued := sb.Len()
written, err := sb.Flush()
f.accountSendBatch(queued, written, err, q)
}
// accountSendBatch is flushSendBatch's accounting, also for the writes a send pipeline makes.
func (f *Interface) accountSendBatch(queued, written int, err error, q int) {
if err != nil {
f.l.Error("Failed to write outgoing batch", "error", err, "writer", q)
}
-58
View File
@@ -1,58 +0,0 @@
//go:build darwin || send_pipeline
package nebula
import (
"github.com/slackhq/nebula/firewall"
"github.com/slackhq/nebula/overlay/batch"
"github.com/slackhq/nebula/overlay/tio"
"github.com/slackhq/nebula/udp"
)
// sendPipelinePlatform lets listenIn take the pipelined send path. It is on for darwin, and for any platform built
// with -tags send_pipeline so the pipeline's tests (and the e2e suite through it) run on linux too.
const sendPipelinePlatform = true
// listenInPipelined is f.listenIn with the underlay writes moved to a sender goroutine (batch.SendPipeline). This
// goroutine still reads the tun, runs the firewall and encrypts, straight into the pipeline's batch. The sender
// writes whatever has built up each time its previous write returns, so under load the packets read while one
// write is in the kernel leave together in the next one, and the next tun read overlaps the write.
func listenInPipelined(f *Interface, queue tio.Queue, i int) {
if f.pinThreads {
f.pinThisThread(i)
}
rejectBuf := make([]byte, mtu)
arenaSize := batch.SendBatchCap * (udp.MTU + 32)
onWrite := func(queued, written int, err error) {
f.accountSendBatch(queued, written, err, i)
}
p := batch.NewSendPipeline(f.writers[i], batch.SendBatchCap, arenaSize, udp.MaxWriteBatch, onWrite)
defer p.Close()
fwPacket := &firewall.ParsedPacket{}
nb := make([]byte, 12, 12)
conntrackCache := firewall.NewConntrackCacheTicker(f.ctx, f.l, f.conntrackCacheTimeout)
for {
pkts, err := queue.Read()
if err != nil {
// Same shutdown noise handling as listenOut
if !f.closed.Load() && f.ctx.Err() == nil {
f.l.Error("Error while reading outbound packet, closing", "error", err, "reader", i)
f.onFatal(err)
}
break
}
for j, pkt := range pkts {
// One Begin/End per packet holds the batch only briefly, so a sender that finishes a write mid-read
// takes what is ready then. An idle sender is woken once, at the end of the read, to take it whole.
sb := p.Begin()
f.consumeInsidePacket(pkt, fwPacket, nb, sb, rejectBuf, i, conntrackCache.Get())
p.End(j == len(pkts)-1)
}
}
f.l.Debug("overlay reader is done", "reader", i)
}
-89
View File
@@ -1,89 +0,0 @@
//go:build darwin || send_pipeline
package nebula
import (
"context"
"errors"
"net/netip"
"sync"
"testing"
"time"
"github.com/slackhq/nebula/overlay/tio"
"github.com/slackhq/nebula/test"
"github.com/slackhq/nebula/udp"
"github.com/stretchr/testify/assert"
"go.uber.org/goleak"
)
// scriptedQueue hands out reads from a script, then fails every Read with err.
type scriptedQueue struct {
reads [][]tio.Packet
err error
}
func (q *scriptedQueue) Read() ([]tio.Packet, error) {
if len(q.reads) == 0 {
return nil, q.err
}
r := q.reads[0]
q.reads = q.reads[1:]
return r, nil
}
func (q *scriptedQueue) Write(b []byte) (int, error) { return len(b), nil }
func (q *scriptedQueue) Close() error { return nil }
type countingConn struct {
udp.NoopConn
mu sync.Mutex
batches int
}
func (c *countingConn) WriteBatch(bufs [][]byte, _ []netip.AddrPort) (int, error) {
c.mu.Lock()
c.batches++
c.mu.Unlock()
return len(bufs), nil
}
// TestListenInPipelinedStops pins that the pipelined reader returns when its queue fails, stopping its sender, and
// reports the error as fatal only when the interface isn't shutting down.
func TestListenInPipelinedStops(t *testing.T) {
for _, closing := range []bool{false, true} {
t.Run(map[bool]string{false: "fatal", true: "shutdown"}[closing], func(t *testing.T) {
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
readErr := errors.New("tun gone")
conn := &countingConn{}
// Packets too short to parse are dropped before the firewall, so this reads without a hostmap.
junk := tio.Packet{Bytes: []byte{0x45, 0}}
q := &scriptedQueue{reads: [][]tio.Packet{{junk}, {junk, junk, junk}, {}}, err: readErr}
shutdown := make(chan struct{})
f := &Interface{
ctx: context.Background(),
l: test.NewLogger(),
writers: []udp.Conn{conn},
triggerShutdown: func() { close(shutdown) },
}
f.closed.Store(closing)
done := make(chan struct{})
go func() {
f.listenIn(q, 0)
close(done)
}()
select {
case <-done:
case <-time.After(5 * time.Second):
t.Fatal("listenIn did not return after its queue failed")
}
if closing {
assert.Nil(t, f.fatalErr.Load())
} else {
<-shutdown
assert.Equal(t, readErr, *f.fatalErr.Load())
}
assert.Zero(t, conn.batches, "dropped packets must not be written")
})
}
}
-58
View File
@@ -1,58 +0,0 @@
// Package msgx calls xnu's private batched socket calls, sendmsg_x and recvmsg_x, which move many datagrams per
// syscall. They are not public API, so a kernel or sandbox may refuse them; callers fall back to one datagram per
// syscall when Unsupported reports that.
package msgx
import (
"syscall"
"unsafe"
"golang.org/x/sys/unix"
)
// Batch is the most messages the callers hand one sendmsg_x or recvmsg_x call.
const Batch = 64
// Hdr mirrors xnu's struct msghdr_x (bsd/sys/socket_private.h), which the SDK doesn't ship. recvmsg_x reports each
// message's length in Datalen rather than in its return value.
type Hdr struct {
Name *byte
Namelen uint32
Iov *unix.Iovec
Iovlen int32
Control *byte
Controllen uint32
Flags int32
Datalen uint64
}
// Send passes hdrs to sendmsg_x on fd and returns how many messages the kernel took. EINTR is retried.
func Send(fd uintptr, hdrs []Hdr) (int, syscall.Errno) {
return call(unix.SYS_SENDMSG_X, fd, hdrs)
}
// Recv passes hdrs to recvmsg_x on fd and returns how many messages it filled. EINTR is retried.
func Recv(fd uintptr, hdrs []Hdr) (int, syscall.Errno) {
return call(unix.SYS_RECVMSG_X, fd, hdrs)
}
func call(trap, fd uintptr, hdrs []Hdr) (int, syscall.Errno) {
if len(hdrs) == 0 {
return 0, syscall.EINVAL
}
for {
r, _, errno := unix.Syscall6(trap, fd, uintptr(unsafe.Pointer(&hdrs[0])), uintptr(len(hdrs)), 0, 0, 0)
switch errno {
case 0:
return int(r), 0
case syscall.EINTR:
default:
return 0, errno
}
}
}
// Unsupported reports whether errno means the kernel or a sandbox refuses the private calls.
func Unsupported(errno syscall.Errno) bool {
return errno == syscall.ENOSYS || errno == syscall.EPERM || errno == syscall.EOPNOTSUPP
}
-79
View File
@@ -1,79 +0,0 @@
package msgx
import (
"bytes"
"syscall"
"testing"
"unsafe"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"golang.org/x/sys/unix"
)
// TestHdrLayout pins Hdr to struct msghdr_x's LP64 layout: 56 bytes, Datalen last at 48.
func TestHdrLayout(t *testing.T) {
var h Hdr
assert.EqualValues(t, 56, unsafe.Sizeof(h))
assert.EqualValues(t, 48, unsafe.Offsetof(h.Datalen))
}
// TestSendRecvRoundTrip sends a batch through sendmsg_x in one call and reads it back through recvmsg_x in one
// call, each message whole, in order, with Datalen set.
func TestSendRecvRoundTrip(t *testing.T) {
fds, err := unix.Socketpair(unix.AF_UNIX, unix.SOCK_DGRAM, 0)
require.NoError(t, err)
t.Cleanup(func() {
_ = unix.Close(fds[0])
_ = unix.Close(fds[1])
})
// A dropped datagram fails the receive instead of hanging it.
require.NoError(t, unix.SetsockoptTimeval(fds[1], unix.SOL_SOCKET, unix.SO_RCVTIMEO, &unix.Timeval{Sec: 2}))
const n = 5
var want [n][]byte
var iovs [n]unix.Iovec
hdrs := make([]Hdr, n)
for i := range n {
want[i] = bytes.Repeat([]byte{byte(i + 1)}, 10+i)
iovs[i] = unix.Iovec{Base: &want[i][0]}
iovs[i].SetLen(len(want[i]))
hdrs[i] = Hdr{Iov: &iovs[i], Iovlen: 1}
}
sent, errno := Send(uintptr(fds[0]), hdrs)
require.Zero(t, errno)
require.Equal(t, n, sent)
var bufs [n + 1][64]byte
var riovs [n + 1]unix.Iovec
rhdrs := make([]Hdr, n+1)
for i := range rhdrs {
riovs[i] = unix.Iovec{Base: &bufs[i][0]}
riovs[i].SetLen(len(bufs[i]))
rhdrs[i] = Hdr{Iov: &riovs[i], Iovlen: 1}
}
got, errno := Recv(uintptr(fds[1]), rhdrs)
require.Zero(t, errno)
require.Equal(t, n, got)
for i := range n {
l := int(rhdrs[i].Datalen)
assert.Equal(t, want[i], bufs[i][:l], "message %d", i)
}
}
// TestEmptyBatch pins that an empty batch is refused before it reaches the kernel.
func TestEmptyBatch(t *testing.T) {
_, errno := Send(0, nil)
assert.Equal(t, syscall.EINVAL, errno)
_, errno = Recv(0, nil)
assert.Equal(t, syscall.EINVAL, errno)
}
func TestUnsupported(t *testing.T) {
for _, e := range []syscall.Errno{syscall.ENOSYS, syscall.EPERM, syscall.EOPNOTSUPP} {
assert.True(t, Unsupported(e), "%v", e)
}
for _, e := range []syscall.Errno{0, syscall.EAGAIN, syscall.ENOBUFS, syscall.EINVAL} {
assert.False(t, Unsupported(e), "%v", e)
}
}
-1
View File
@@ -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)
+19 -7
View File
@@ -456,15 +456,27 @@ func parseV4(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
if fp.Fragment {
fp.RemotePort = 0
fp.LocalPort = 0
} else if fp.Protocol == iputil.IPProtocolICMP { //note that orientation doesn't matter on ICMP
return nil
}
switch fp.Protocol {
case iputil.IPProtocolICMP: //note that orientation doesn't matter on ICMP
fp.RemotePort = binary.BigEndian.Uint16(data[ihl+4 : ihl+6]) //identifier
fp.LocalPort = 0 //code would be uint16(data[ihl+1])
} else if incoming {
fp.RemotePort = binary.BigEndian.Uint16(data[ihl : ihl+2]) //src port
fp.LocalPort = binary.BigEndian.Uint16(data[ihl+2 : ihl+4]) //dst port
} else {
fp.LocalPort = binary.BigEndian.Uint16(data[ihl : ihl+2]) //src port
fp.RemotePort = binary.BigEndian.Uint16(data[ihl+2 : ihl+4]) //dst port
case iputil.IPProtocolTCP, iputil.IPProtocolUDP:
if incoming {
fp.RemotePort = binary.BigEndian.Uint16(data[ihl : ihl+2]) //src port
fp.LocalPort = binary.BigEndian.Uint16(data[ihl+2 : ihl+4]) //dst port
} else {
fp.LocalPort = binary.BigEndian.Uint16(data[ihl : ihl+2]) //src port
fp.RemotePort = binary.BigEndian.Uint16(data[ihl+2 : ihl+4]) //dst port
}
default:
// don't set ports for protocols Nebula doesn't inspect, the first 4 bytes of GRE, IPIP, AH, etc. are not ports
fp.RemotePort = 0
fp.LocalPort = 0
}
return nil
+30 -2
View File
@@ -77,7 +77,7 @@ func Test_newPacket(t *testing.T) {
// account for variable ip header length - outgoing
h = ipv4.Header{
Version: 1,
Protocol: 2,
Protocol: iputil.IPProtocolUDP,
Len: 100,
Src: net.IPv4(10, 0, 0, 1),
Dst: net.IPv4(10, 0, 0, 2),
@@ -89,7 +89,7 @@ func Test_newPacket(t *testing.T) {
err = newPacket(b, false, p)
require.NoError(t, err)
assert.Equal(t, uint8(2), p.Protocol)
assert.Equal(t, uint8(iputil.IPProtocolUDP), p.Protocol)
assert.Equal(t, netip.MustParseAddr("10.0.0.1"), p.LocalAddr)
assert.Equal(t, netip.MustParseAddr("10.0.0.2"), p.RemoteAddr)
assert.Equal(t, uint16(6), p.RemotePort)
@@ -97,6 +97,34 @@ func Test_newPacket(t *testing.T) {
assert.False(t, p.Fragment)
}
// Test_newPacket_v4NoPorts ensures only TCP and UDP report ports. The first 4 bytes of other protocols are not ports,
// and are often chosen by the sender: a GRE header's protocol type, an IPIP inner total length, a 6in4 flow label.
// Reading them as ports would let a `proto: any` rule with a port match tunneled traffic.
func Test_newPacket_v4NoPorts(t *testing.T) {
p := &firewall.ParsedPacket{}
for _, proto := range []uint8{4, 41, 47, 50, 51, 132} { // IPIP, 6in4, GRE, ESP, AH, SCTP
h := ipv4.Header{
Version: 4,
Len: ipv4.HeaderLen,
Protocol: int(proto),
Src: net.IPv4(10, 0, 0, 1),
Dst: net.IPv4(10, 0, 0, 2),
}
b, err := h.Marshal()
require.NoError(t, err)
b = append(b, []byte{0x00, 0x00, 0x86, 0xdd}...) // a GRE header carrying IPv6 would read as port 34525
for _, incoming := range []bool{true, false} {
require.NoError(t, newPacket(b, incoming, p))
assert.Equal(t, proto, p.Protocol)
assert.Equal(t, uint16(0), p.RemotePort)
assert.Equal(t, uint16(0), p.LocalPort)
assert.False(t, p.Fragment)
}
}
}
func Test_newPacket_v6(t *testing.T) {
p := &firewall.ParsedPacket{}
-62
View File
@@ -435,65 +435,3 @@ func testPP(pkt []byte) *firewall.ParsedPacket {
}
return pp
}
// fakeTunBatchWriter records each WriteBatch call and each plain Write separately.
type fakeTunBatchWriter struct {
writes [][]byte
batches [][][]byte
}
func (w *fakeTunBatchWriter) Write(p []byte) (int, error) {
w.writes = append(w.writes, bytes.Clone(p))
return len(p), nil
}
func (w *fakeTunBatchWriter) WriteBatch(pkts [][]byte) error {
var b [][]byte
for _, p := range pkts {
b = append(b, bytes.Clone(p))
}
w.batches = append(w.batches, b)
return nil
}
// TestPassthroughUsesWriteBatch pins that a writer implementing tio.BatchWriter gets the whole
// passthrough lane in one WriteBatch per Flush, in order, and no plain Writes; an empty Flush
// makes no call.
func TestPassthroughUsesWriteBatch(t *testing.T) {
w := &fakeTunBatchWriter{}
m := newTestMultiCoalescer(t, w)
k := &keySeq{epoch: 1}
var want [][]byte
for i := range 5 {
icmp := make([]byte, 28)
icmp[0] = 0x45
icmp[3] = 28
icmp[9] = 1
icmp[20] = byte(i)
want = append(want, icmp)
if err := m.Commit(icmp, k.next(), testPP(icmp)); err != nil {
t.Fatal(err)
}
}
if err := m.Flush(); err != nil {
t.Fatal(err)
}
if err := m.Flush(); err != nil {
t.Fatal(err)
}
if len(w.writes) != 0 {
t.Fatalf("got %d plain Writes, want 0", len(w.writes))
}
if len(w.batches) != 1 {
t.Fatalf("got %d WriteBatch calls, want 1", len(w.batches))
}
for i, p := range w.batches[0] {
if !bytes.Equal(p, want[i]) {
t.Fatalf("packet %d: got % x, want % x", i, p, want[i])
}
}
if len(w.batches[0]) != len(want) {
t.Fatalf("got %d packets, want %d", len(w.batches[0]), len(want))
}
}
+6 -17
View File
@@ -2,23 +2,18 @@ package batch
import (
"io"
"github.com/slackhq/nebula/overlay/tio"
)
// Passthrough is MultiCoalescer's verbatim lane: no coalescing, packets are written at Flush in the
// order enqueued, in one WriteBatch when out implements tio.BatchWriter.
// Passthrough is MultiCoalescer's verbatim lane: no batching, packets are written at Flush in the
// order enqueued.
type Passthrough struct {
out io.Writer
bw tio.BatchWriter // nil: Flush writes one packet per Write
slots [][]byte
}
func NewPassthrough(w io.Writer) *Passthrough {
bw, _ := w.(tio.BatchWriter)
return &Passthrough{
out: w,
bw: bw,
slots: make([][]byte, 0, 128),
}
}
@@ -31,16 +26,10 @@ func (p *Passthrough) enqueue(pkt []byte) error {
func (p *Passthrough) Flush() error {
var firstErr error
if p.bw != nil {
if len(p.slots) > 0 {
firstErr = p.bw.WriteBatch(p.slots)
}
} else {
for _, s := range p.slots {
_, err := p.out.Write(s)
if err != nil && firstErr == nil {
firstErr = err
}
for _, s := range p.slots {
_, err := p.out.Write(s)
if err != nil && firstErr == nil {
firstErr = err
}
}
clear(p.slots)
-156
View File
@@ -1,156 +0,0 @@
//go:build darwin || send_pipeline
package batch
import (
"sync"
)
// SendPipeline splits encrypt from send. The producer (a tun reader) encrypts packets into one SendBatch while a
// sender goroutine writes the other, and they swap whenever the sender is free. The sender takes everything the
// producer committed since its last take, so packets that arrive during a write leave together in the next
// WriteBatch, and the reader returns to the tun while the kernel is still sending.
//
// The producer holds the batch for one packet at a time (Begin, reserve and commit, End) so the sender can take the
// batch between any two packets, never while a reserved slot is still being written.
//
// Ownership: the producer touches its batch only between Begin and End, and the sender swaps batches only under
// the same lock, so a slot the producer reserved is never sent half written. A batch goes back to the producer
// only after its WriteBatch returned and it was emptied, so no slot is reused before its send completes.
//
// Memory is bounded at two batches. When the producer fills its batch while the sender is still writing the other,
// Begin waits for the swap. That slows the tun reader instead of dropping, as the unpipelined path does.
//
// Order: a single sender writes batches in the order they were filled, each in commit order, so every peer's
// packets leave in the order their message counters were taken.
type SendPipeline struct {
out batchWriter
cap int
maxWrite int
onWrite func(queued, written int, err error)
mu sync.Mutex
cond sync.Cond
cur *SendBatch // the producer's batch, guarded by mu
gen uint64 // swaps so far, guarded by mu
ready chan struct{} // cap 1: cur may have packets for the sender
stop chan struct{}
done chan struct{}
once sync.Once
}
// NewSendPipeline starts a pipeline over two batches of batchCap slots and arenaSize arena bytes each. It writes
// to out at most maxWrite packets per WriteBatch. If onWrite is not nil, it is called on the sender goroutine
// after every WriteBatch with how many packets that call was given, how many went out, and its error. Close stops
// the pipeline.
func NewSendPipeline(out batchWriter, batchCap, arenaSize, maxWrite int, onWrite func(queued, written int, err error)) *SendPipeline {
batchCap = max(batchCap, 1)
p := &SendPipeline{
out: out,
cap: batchCap,
maxWrite: max(maxWrite, 1),
onWrite: onWrite,
cur: NewSendBatch(out, batchCap, arenaSize),
ready: make(chan struct{}, 1),
stop: make(chan struct{}),
done: make(chan struct{}),
}
p.cond.L = &p.mu
go p.run(NewSendBatch(out, batchCap, arenaSize))
return p
}
// Begin returns a batch with room for at least one more packet. The batch stays the producer's until End. If the
// batch is full, Begin first waits for the sender to swap it out. Producer only.
func (p *SendPipeline) Begin() *SendBatch {
p.mu.Lock()
if p.cur.Len() >= p.cap {
g := p.gen
p.wake()
for p.gen == g {
p.cond.Wait()
}
}
return p.cur
}
// End gives up the batch Begin returned. With wake set it also tells the sender the batch has packets for it, which
// the producer does once a run of packets is in (the end of a tun read) rather than per packet, so the sender takes
// the run whole when it is idle. A sender still writing takes the batch when it finishes, woken or not.
func (p *SendPipeline) End(wake bool) {
n := p.cur.Len()
p.mu.Unlock()
if wake && n > 0 {
p.wake()
}
}
func (p *SendPipeline) wake() {
select {
case p.ready <- struct{}{}:
default:
}
}
// Close writes whatever the producer left in its batch, stops the sender, and waits for it. The producer calls it,
// outside Begin/End, once it is done. Safe to call more than once.
func (p *SendPipeline) Close() {
p.once.Do(func() { close(p.stop) })
<-p.done
}
func (p *SendPipeline) run(mine *SendBatch) {
defer close(p.done)
for {
stopping := false
select {
case <-p.ready:
case <-p.stop:
stopping = true
}
// Keep taking whatever the producer committed during the last write, without waiting to be woken, so a
// busy sender goes straight from one write to the next and each write carries everything that built up.
// Once stopping, the producer is done and this writes what it left.
for p.take(&mine) {
p.write(mine)
}
if stopping {
return
}
}
}
// take swaps the producer's batch for the empty *mine if the producer's has packets, and reports whether it did.
func (p *SendPipeline) take(mine **SendBatch) bool {
p.mu.Lock()
defer p.mu.Unlock()
if p.cur.Len() == 0 {
return false
}
*mine, p.cur = p.cur, *mine
p.gen++
p.cond.Broadcast()
return true
}
// write sends b's packets, maxWrite at a time, then empties b.
func (p *SendPipeline) write(b *SendBatch) {
for off := 0; off < len(b.bufs); {
n := min(p.maxWrite, len(b.bufs)-off)
written, err := p.out.WriteBatch(b.bufs[off:off+n], b.dsts[off:off+n])
if p.onWrite != nil {
p.onWrite(n, written, err)
}
off += n
}
b.recycle()
}
// recycle empties b without writing it. SendPipeline uses it because it writes a batch's packets itself.
func (b *SendBatch) recycle() {
clear(b.bufs)
b.bufs = b.bufs[:0]
b.dsts = b.dsts[:0]
b.arena.Reset()
}
-400
View File
@@ -1,400 +0,0 @@
//go:build darwin || send_pipeline
package batch
import (
"encoding/binary"
"errors"
"net/netip"
"sync"
"testing"
"time"
"unsafe"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"go.uber.org/goleak"
)
// pipeWriter records every WriteBatch a SendPipeline makes. It checks each packet's bytes against the sequence
// number they carry while the call is in progress, and can hold a call until the test releases it.
type pipeWriter struct {
t *testing.T
mu sync.Mutex
seqs []uint32
dsts []netip.AddrPort
calls []int
inCall [][]byte // the bufs of the call in progress, for overlap checks
gate chan struct{} // if not nil, each call waits for a receive from it
entered chan int // if not nil, each call sends its size here on entry
short int // each call reports this many fewer written
err error
}
func (w *pipeWriter) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error) {
w.mu.Lock()
w.inCall = bufs
w.mu.Unlock()
if w.entered != nil {
w.entered <- len(bufs)
}
if w.gate != nil {
<-w.gate
}
w.mu.Lock()
defer w.mu.Unlock()
for i, b := range bufs {
seq := binary.BigEndian.Uint32(b)
if !checkPkt(b, seq) {
w.t.Errorf("packet %d changed while being sent", seq)
}
w.seqs = append(w.seqs, seq)
w.dsts = append(w.dsts, addrs[i])
}
w.calls = append(w.calls, len(bufs))
w.inCall = nil
return max(len(bufs)-w.short, 0), w.err
}
func (w *pipeWriter) sent() ([]uint32, []netip.AddrPort, []int) {
w.mu.Lock()
defer w.mu.Unlock()
return append([]uint32(nil), w.seqs...), append([]netip.AddrPort(nil), w.dsts...), append([]int(nil), w.calls...)
}
// fillPkt writes seq and a pattern derived from it into b, as the encrypt step writes a slot.
func fillPkt(b []byte, seq uint32) {
binary.BigEndian.PutUint32(b, seq)
for i := 4; i < len(b); i++ {
b[i] = byte(seq) ^ byte(i)
}
}
func checkPkt(b []byte, seq uint32) bool {
if len(b) < 4 || binary.BigEndian.Uint32(b) != seq {
return false
}
for i := 4; i < len(b); i++ {
if b[i] != byte(seq)^byte(i) {
return false
}
}
return true
}
func pktSize(seq uint32) int { return 16 + int(seq%97) }
var testDsts = []netip.AddrPort{
netip.MustParseAddrPort("10.0.0.1:4242"),
netip.MustParseAddrPort("10.0.0.2:4242"),
netip.MustParseAddrPort("[fd00::3]:4242"),
}
// commit adds packet seq to p the way listenIn does: Begin, reserve, encrypt, commit, End.
func commit(p *SendPipeline, seq uint32, last bool) {
sb := p.Begin()
slot := sb.Reserve(pktSize(seq))
fillPkt(slot, seq)
sb.Commit(slot, testDsts[seq%uint32(len(testDsts))])
p.End(last)
}
func TestSendPipelineOrder(t *testing.T) {
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
w := &pipeWriter{t: t}
// A small arena makes the batches grow theirs, and a small maxWrite splits takes across several writes.
p := NewSendPipeline(w, 16, 64, 5, nil)
const n = 20000
seq := uint32(0)
for seq < n {
// Reads of 1 to 40 packets, with an occasional pause so the sender goes idle and is woken.
read := 1 + int(seq*7%40)
for j := 0; j < read && seq < n; j++ {
commit(p, seq, j == read-1 || seq == n-1)
seq++
}
if seq%1000 < 40 {
time.Sleep(50 * time.Microsecond)
}
}
p.Close()
seqs, dsts, calls := w.sent()
require.Len(t, seqs, n)
for i, s := range seqs {
require.Equal(t, uint32(i), s, "packet %d out of order", i)
require.Equal(t, testDsts[s%uint32(len(testDsts))], dsts[i])
}
for _, c := range calls {
assert.LessOrEqual(t, c, 5, "WriteBatch got more than maxWrite")
assert.Positive(t, c)
}
}
func TestSendPipelineConcurrentPeersKeepOrder(t *testing.T) {
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
// A slow writer makes the sender take many packets per write, interleaving the three peers in each batch.
w := &pipeWriter{t: t}
slow := &slowWriter{pipeWriter: w, d: 20 * time.Microsecond}
p := NewSendPipeline(slow, 128, 128*64, 128, nil)
const n = 5000
for i := uint32(0); i < n; i++ {
commit(p, i, i%8 == 7 || i == n-1)
}
p.Close()
seqs, dsts, _ := w.sent()
require.Len(t, seqs, n)
last := map[netip.AddrPort]int64{}
for i, s := range seqs {
prev, ok := last[dsts[i]]
if ok {
require.Greater(t, int64(s), prev, "peer %v went backwards", dsts[i])
}
last[dsts[i]] = int64(s)
}
}
type slowWriter struct {
*pipeWriter
d time.Duration
}
func (s *slowWriter) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error) {
time.Sleep(s.d)
return s.pipeWriter.WriteBatch(bufs, addrs)
}
// TestSendPipelineBackpressureAndReuse holds the sender inside a write and checks that the producer can fill
// exactly one more batch, that none of its slots overlap the packets being written, and that the next Begin waits
// until the write returns.
func TestSendPipelineBackpressureAndReuse(t *testing.T) {
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
const batchCap = 8
w := &pipeWriter{t: t, gate: make(chan struct{}), entered: make(chan int, 16)}
p := NewSendPipeline(w, batchCap, 64, 128, nil)
seq := uint32(0)
for ; seq < batchCap; seq++ {
commit(p, seq, seq == batchCap-1)
}
require.Equal(t, batchCap, <-w.entered, "sender should take the first batch whole")
w.mu.Lock()
inFlight := append([][]byte(nil), w.inCall...)
w.mu.Unlock()
// The second batch fills while the first is being written, in slots that don't touch the first's bytes.
for ; seq < 2*batchCap; seq++ {
sb := p.Begin()
slot := sb.Reserve(pktSize(seq))
for _, b := range inFlight {
assert.False(t, overlaps(slot, b), "slot for packet %d overlaps packet %d, still being sent", seq, binary.BigEndian.Uint32(b))
}
fillPkt(slot, seq)
sb.Commit(slot, testDsts[0])
p.End(true)
}
// Both batches are now spoken for, so the next Begin must wait for the write to return.
begun := make(chan struct{})
go func() {
commit(p, seq, true)
close(begun)
}()
select {
case <-begun:
t.Fatal("Begin returned with both batches in use: the pipeline is not bounded")
case <-time.After(50 * time.Millisecond):
}
for i, b := range inFlight {
assert.True(t, checkPkt(b, uint32(i)), "packet %d was overwritten before its send completed", i)
}
w.gate <- struct{}{} // first write returns; the sender swaps and starts on the second batch
assert.Equal(t, batchCap, <-w.entered)
select {
case <-begun:
case <-time.After(5 * time.Second):
t.Fatal("Begin did not return after the sender freed a batch")
}
w.gate <- struct{}{}
go func() {
for range w.entered {
w.gate <- struct{}{}
}
}()
p.Close()
close(w.entered)
seqs, _, calls := w.sent()
require.Len(t, seqs, 2*batchCap+1)
for i, s := range seqs {
assert.Equal(t, uint32(i), s)
}
assert.Equal(t, []int{batchCap, batchCap, 1}, calls)
}
func overlaps(a, b []byte) bool {
if len(a) == 0 || len(b) == 0 {
return false
}
a0, b0 := uintptr(unsafe.Pointer(&a[0])), uintptr(unsafe.Pointer(&b[0]))
return a0 < b0+uintptr(len(b)) && b0 < a0+uintptr(len(a))
}
// TestSendPipelineBatchesBuildUp checks the point of the pipeline: while one write is in the kernel, everything the
// producer commits leaves together in the next write.
func TestSendPipelineBatchesBuildUp(t *testing.T) {
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
w := &pipeWriter{t: t, gate: make(chan struct{}), entered: make(chan int, 16)}
p := NewSendPipeline(w, 128, 128*64, 128, nil)
commit(p, 0, true)
require.Equal(t, 1, <-w.entered)
// Ten one-packet reads while the first write is held.
for i := uint32(1); i <= 10; i++ {
commit(p, i, true)
}
w.gate <- struct{}{}
require.Equal(t, 10, <-w.entered, "packets queued during a write should go out in one WriteBatch")
w.gate <- struct{}{}
p.Close()
_, _, calls := w.sent()
assert.Equal(t, []int{1, 10}, calls)
}
func TestSendPipelineCloseFlushes(t *testing.T) {
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
w := &pipeWriter{t: t}
p := NewSendPipeline(w, 32, 32*64, 128, nil)
// End(false) never wakes the sender, so only Close's final take sends these.
for i := uint32(0); i < 5; i++ {
commit(p, i, false)
}
p.Close()
p.Close() // idempotent
seqs, _, _ := w.sent()
assert.Equal(t, []uint32{0, 1, 2, 3, 4}, seqs)
}
func TestSendPipelineCloseEmpty(t *testing.T) {
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
w := &pipeWriter{t: t}
p := NewSendPipeline(w, 4, 64, 128, nil)
sb := p.Begin()
p.End(true) // nothing committed: no write
assert.Zero(t, sb.Len())
p.Close()
_, _, calls := w.sent()
assert.Empty(t, calls)
}
// TestSendPipelineCloseWaitsForWrite checks that Close returns only after a write in progress has returned, so the
// caller can't free anything the sender still uses.
func TestSendPipelineCloseWaitsForWrite(t *testing.T) {
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
w := &pipeWriter{t: t, gate: make(chan struct{}), entered: make(chan int, 4)}
p := NewSendPipeline(w, 4, 64, 128, nil)
commit(p, 0, true)
<-w.entered
commit(p, 1, false)
closed := make(chan struct{})
go func() {
p.Close()
close(closed)
}()
select {
case <-closed:
t.Fatal("Close returned during a write")
case <-time.After(50 * time.Millisecond):
}
w.gate <- struct{}{}
<-w.entered // Close's final take writes packet 1
w.gate <- struct{}{}
select {
case <-closed:
case <-time.After(5 * time.Second):
t.Fatal("Close did not return")
}
seqs, _, _ := w.sent()
assert.Equal(t, []uint32{0, 1}, seqs)
}
func TestSendPipelineOnWriteAndDrops(t *testing.T) {
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
werr := errors.New("boom")
w := &pipeWriter{t: t, short: 1, err: werr}
type call struct {
queued, written int
err error
}
var got []call
p := NewSendPipeline(w, 16, 16*64, 4, func(q, n int, err error) {
got = append(got, call{q, n, err}) // sender goroutine only
})
for i := uint32(0); i < 10; i++ {
commit(p, i, false)
}
p.Close()
assert.Equal(t, []call{{4, 3, werr}, {4, 3, werr}, {2, 1, werr}}, got)
}
// TestSendPipelineStressRace runs a producer against a sender whose writes take varying time, for the race
// detector, and checks nothing is lost, reordered or overwritten.
func TestSendPipelineStressRace(t *testing.T) {
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
w := &pipeWriter{t: t}
jitter := &jitterWriter{pipeWriter: w}
p := NewSendPipeline(jitter, 32, 256, 16, nil)
const n = 50000
for i := uint32(0); i < n; i++ {
commit(p, i, i%3 == 0)
}
p.Close()
seqs, _, _ := w.sent()
require.Len(t, seqs, n)
for i, s := range seqs {
if uint32(i) != s {
t.Fatalf("packet %d arrived at %d", s, i)
}
}
}
type jitterWriter struct {
*pipeWriter
i int
}
func (j *jitterWriter) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error) {
j.i++
if j.i%7 == 0 {
time.Sleep(time.Duration(j.i%5) * 10 * time.Microsecond)
}
return j.pipeWriter.WriteBatch(bufs, addrs)
}
type discardWriter struct{}
func (discardWriter) WriteBatch(bufs [][]byte, _ []netip.AddrPort) (int, error) {
return len(bufs), nil
}
// BenchmarkSendPipeline measures a packet through Begin, reserve, commit and End with a writer that costs nothing;
// its allocs/op is the pipeline's steady-state heap cost per packet.
func BenchmarkSendPipeline(b *testing.B) {
p := NewSendPipeline(discardWriter{}, SendBatchCap, SendBatchCap*1500, 128, nil)
defer p.Close()
b.ReportAllocs()
for i := range b.N {
sb := p.Begin()
sb.Commit(sb.Reserve(1400), testDsts[0])
p.End(i%8 == 7)
}
}
-11
View File
@@ -145,14 +145,3 @@ func SupportsGSO(w io.Writer, want GSOProto) (GSOWriter, bool) {
return gw, false
}
}
// BatchWriter is implemented by Queues that can emit several already-segmented packets in one call.
// Backends without a batched write do not implement it and callers loop over Write.
//
// pkts are borrowed: WriteBatch must not retain them past its return.
// A returned error doesn't say which packets were delivered, so callers must not retry the batch.
// Safe for concurrent use, like Write.
type BatchWriter interface {
io.Writer
WriteBatch(pkts [][]byte) error
}
+9 -404
View File
@@ -8,14 +8,12 @@ import (
"log/slog"
"net/netip"
"os"
"sync"
"sync/atomic"
"syscall"
"unsafe"
"github.com/gaissmai/bart"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/internal/msgx"
"github.com/slackhq/nebula/overlay/tio"
"github.com/slackhq/nebula/routing"
"github.com/slackhq/nebula/util"
@@ -35,23 +33,8 @@ type tun struct {
// and routes for it. NEPacketTunnelProvider on darwin does this.
hostOwned bool
l *slog.Logger
// batchMu guards batch, WriteBatch's sendmsg_x scratch.
batchMu sync.Mutex
batch tunBatch
}
// tunBatch is WriteBatch's scratch. The kernel reads every entry in place.
type tunBatch struct {
heads [msgx.Batch][4]byte
iovs [msgx.Batch][2]unix.Iovec
hdrs [msgx.Batch]msgx.Hdr
pkts [msgx.Batch][]byte
}
// noTunSendX is set once sendmsg_x is refused on the tun; WriteBatch then writes one packet at a time.
var noTunSendX atomic.Bool
type ifReq struct {
Name [unix.IFNAMSIZ]byte
Flags uint16
@@ -632,12 +615,16 @@ func (t *tun) Write(from []byte) (int, error) {
return 0, syscall.EIO
}
ipVer := from[0] >> 4
var head [4]byte
af, err := tunAF(from)
if err != nil {
return 0, err
switch ipVer {
case 4:
head[3] = syscall.AF_INET
case 6:
head[3] = syscall.AF_INET6
default:
return 0, fmt.Errorf("unable to determine IP version from packet")
}
head[3] = af
// Grab rc as a local so the compiler can devirtualize the call and keep the closure on the stack.
rc, err := t.f.SyscallConn()
@@ -670,129 +657,6 @@ func (t *tun) Write(from []byte) (int, error) {
return n - 4, nil
}
// tunAF returns the utun address-family prefix byte for an IP packet.
func tunAF(pkt []byte) (byte, error) {
switch pkt[0] >> 4 {
case 4:
return syscall.AF_INET, nil
case 6:
return syscall.AF_INET6, nil
default:
return 0, fmt.Errorf("unable to determine IP version from packet")
}
}
// WriteBatch writes pkts to the utun device with sendmsg_x, up to msgx.Batch packets per syscall. utun is a
// connected datagram socket, so xnu takes the batched send path, though it still hands utun each packet on its own:
// 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. A short count goes on with the
// rest; EMSGSIZE, which sendmsg_x returns only when the first packet is past the send buffer, sends that one through
// Write, which reports it. Any other error means the kernel took an unknown prefix and dropped the rest, so it is
// reported rather than retried, which could deliver packets twice. Under mbuf exhaustion sendmsg_x reports packets it
// freed unsent as a short count, so they are lost where writev would have delivered them.
func (t *tun) WriteBatch(pkts [][]byte) error {
if noTunSendX.Load() {
return t.writeEach(pkts)
}
t.batchMu.Lock()
defer t.batchMu.Unlock()
b := &t.batch
var firstErr error
keep := func(err error) {
if err != nil && firstErr == nil {
firstErr = err
}
}
for len(pkts) > 0 {
n := 0
for len(pkts) > 0 && n < msgx.Batch {
p := pkts[0]
pkts = pkts[1:]
if len(p) == 0 {
keep(syscall.EIO)
continue
}
af, err := tunAF(p)
if err != nil {
keep(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] = msgx.Hdr{Iov: &b.iovs[n][0], Iovlen: 2}
b.pkts[n] = p
n++
}
for off := 0; off < n; {
sent, err := t.sendmsgX(b.hdrs[off:n])
switch {
case err == nil && sent > 0:
off += sent
case err == nil:
keep(t.writeEach(b.pkts[off:n]))
off = n
case err == unix.EMSGSIZE:
keep(t.writeEach(b.pkts[off : off+1]))
off++
case isUnsupported(err):
if noTunSendX.CompareAndSwap(false, true) {
t.l.Warn("sendmsg_x unavailable on the tun device, writing one packet per syscall", "error", err)
}
keep(t.writeEach(b.pkts[off:n]))
keep(t.writeEach(pkts))
pkts, off = nil, n
default:
keep(err)
off = n
}
}
clear(b.iovs[:n])
clear(b.pkts[:n])
}
return firstErr
}
// sendmsgX hands hdrs to sendmsg_x, waiting while the socket is full, and returns how many the kernel took.
func (t *tun) sendmsgX(hdrs []msgx.Hdr) (int, error) {
rc, err := t.f.SyscallConn()
if err != nil {
return 0, err
}
var sent int
var errno syscall.Errno
err = rc.Write(func(fd uintptr) bool {
sent, errno = msgx.Send(fd, hdrs)
// sendmsg_x reports EAGAIN only when it took nothing; a partial batch returns its count.
return errno != syscall.EAGAIN
})
if err != nil {
return 0, err
}
if errno != 0 {
return 0, errno
}
return sent, nil
}
func isUnsupported(err error) bool {
errno, ok := err.(syscall.Errno)
return ok && msgx.Unsupported(errno)
}
// 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
}
@@ -802,264 +666,5 @@ func (t *tun) Name() string {
}
func (t *tun) Queues(int) ([]tio.Queue, error) {
return []tio.Queue{newTunQueue(t)}, nil
}
// tunReadBatch is the most packets one tunQueue.Read returns.
const tunReadBatch = msgx.Batch
// tunRecvXSlot is each recvmsg_x entry's packet buffer. recvmsg_x lays its buffers out before it knows the packet
// sizes, so each gets room for the largest IP packet; the kernel only touches what it writes.
const tunRecvXSlot = defaultBatchBufSize
// tunRecvXStride is how far apart the slots start: 64 byte aligned, and one cache line more than 64KiB so the packet
// starts don't all land in the same cache sets.
const tunRecvXStride = 65536 + 64
// tunQueue is the darwin tun's Queue. Read hands back 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. It reads them with one recvmsg_x when
// it can and one readv per packet otherwise.
type tunQueue struct {
t *tun
// buf holds the packets Read returns: recvmsg_x's slots, or, for readv, one arena. readv stops once less than
// defaultBatchBufSize of it is left, so every readv has room for the largest packet utun can return.
buf []byte
pkts [tunReadBatch]tio.Packet
// x is the recvmsg_x scratch, nil once recvmsg_x is off for good.
x *tunRecvX
}
// tunRecvX is the recvmsg_x scratch. Entry i scatters its AF prefix into heads[i] and its packet into slot i of the
// queue's buf; the kernel reads and writes every entry in place.
type tunRecvX struct {
heads [tunReadBatch][4]byte
iovs [tunReadBatch][2]unix.Iovec
hdrs [tunReadBatch]msgx.Hdr
}
// newTunQueue returns t's Queue, raising t's pending packet limit first so a read can find more than one.
func newTunQueue(t *tun) *tunQueue {
t.raisePendingPackets()
q := &tunQueue{t: t, buf: make([]byte, tunReadBatch*tunRecvXStride), x: &tunRecvX{}}
x := q.x
for i := range x.hdrs {
x.iovs[i] = [2]unix.Iovec{
{Base: &x.heads[i][0], Len: 4},
{Base: &q.buf[i*tunRecvXStride], Len: tunRecvXSlot},
}
x.hdrs[i] = msgx.Hdr{Iov: &x.iovs[i][0], Iovlen: 2}
}
return q
}
// Read waits for the utun to become readable, then returns the packets queued on it.
func (q *tunQueue) Read() ([]tio.Packet, error) {
if q.x != nil {
if pkts, err, ok := q.readX(); ok {
return pkts, err
}
}
return q.readv()
}
// tunRecvmsgX is msgx.Recv; tests swap it to inject results.
var tunRecvmsgX = msgx.Recv
// readX reads up to tunReadBatch packets with one recvmsg_x. ok is false when the caller should read with readv
// instead: recvmsg_x failed this time, or has been turned off for good. A batch that fails tunRecvXCheck is dropped:
// its packets are off the socket, but their lengths can't be trusted.
func (q *tunQueue) readX() (pkts []tio.Packet, err error, ok bool) {
rc, err := q.t.f.SyscallConn()
if err != nil {
return nil, err, true
}
x := q.x
var n int
var errno syscall.Errno
err = rc.Read(func(fd uintptr) bool {
for i := range x.hdrs {
x.hdrs[i].Flags = 0
x.hdrs[i].Datalen = 0
}
n, errno = tunRecvmsgX(fd, x.hdrs[:])
return errno != unix.EAGAIN
})
if err != nil {
return nil, err, true
}
if tunRecvXRefused(errno) {
q.disableX("unavailable", errno)
return nil, nil, false
}
if errno != 0 {
// recvmsg_x can fail where readv wouldn't (a kernel allocation, say), so let readv read this wakeup and
// report the error if it is real.
return nil, nil, false
}
if cerr := tunRecvXCheck(n, x.hdrs[:], x.heads[:], tunRecvXSlot); cerr != nil {
q.disableX("returned an unexpected batch", cerr)
return nil, nil, false
}
for i := range n {
off := i * tunRecvXStride
end := off + int(x.hdrs[i].Datalen) - 4
q.pkts[i] = tio.Packet{Bytes: q.buf[off:end:end]}
}
// n is 0 at end of file, as readv's short read is.
return q.pkts[:n], nil, true
}
// tunRecvXRefused reports whether a recvmsg_x errno means it will never work here: msgx.Unsupported's refusals, and
// EINVAL and EMSGSIZE, which with the headers newTunQueue builds come only from xnu rejecting their layout.
func tunRecvXRefused(errno syscall.Errno) bool {
return msgx.Unsupported(errno) || errno == unix.EINVAL || errno == unix.EMSGSIZE
}
// disableX turns recvmsg_x off for q for good. readv keeps reading into buf.
func (q *tunQueue) disableX(why string, err error) {
q.x = nil
q.t.l.Warn("recvmsg_x "+why+" on the tun device, reading one packet per syscall", "error", err)
}
// tunRecvXCheck rejects a recvmsg_x batch of n entries that intact msghdr_x entries can't produce, which would mean
// the private layout changed under us: more entries than headers, one past its 4 byte head plus slot byte buffer or
// too short to hold the head, or an AF prefix utun never writes. A slot holds the largest IP packet, so nothing is
// ever truncated; xnu's default recvmsg_x path doesn't report MSG_TRUNC per entry anyway, only its SO_DONTTRUNC path
// does, and that is checked too.
func tunRecvXCheck(n int, hdrs []msgx.Hdr, heads [][4]byte, slot int) error {
if n < 0 || n > len(hdrs) || n > len(heads) {
return fmt.Errorf("returned %d packets for %d headers", n, len(hdrs))
}
for i := range n {
h := &hdrs[i]
if h.Flags&unix.MSG_TRUNC != 0 {
return fmt.Errorf("packet %d came back truncated, flags %#x", i, h.Flags)
}
if h.Datalen < 4 || h.Datalen > uint64(4+slot) {
return fmt.Errorf("packet %d is %d bytes, outside the 4 to %d the buffers allow", i, h.Datalen, 4+slot)
}
switch heads[i] {
case [4]byte{3: syscall.AF_INET}, [4]byte{3: syscall.AF_INET6}:
default:
return fmt.Errorf("packet %d has AF prefix % x", i, heads[i])
}
}
return nil
}
// readv reads packets one readv at a time until the utun 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) readv() ([]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() }
// xnu lets one packet wait on a utun control socket by default (if_utun.c utun_ctl_bind): utun_start stops moving
// packets from the interface's send queue to the socket once one is waiting, and resumes only when a read wakes the
// interface's starter thread. So every read finds one packet. tunPendingPackets lets a whole read batch wait
// instead (_UTUN_OPT_MAX_PENDING_PACKETS, bsd/net/if_utun.h, set at SYSPROTO_CONTROL level).
const (
tunPendingPackets = tunReadBatch
_UTUN_OPT_MAX_PENDING_PACKETS = 16
_SYSPROTO_CONTROL = 2
)
// tunSetsockoptInt and tunGetsockoptInt are setsockopt and getsockopt; tests swap them.
var (
tunSetsockoptInt = unix.SetsockoptInt
tunGetsockoptInt = unix.GetsockoptInt
)
// raisePendingPackets lets up to tunPendingPackets packets wait on the utun control socket, first growing its
// receive buffer to hold that many packets and their 4 byte AF prefix: utun drops a packet the buffer has no room
// for, while one over the limit waits in the interface's queue. It sizes for the larger of tun.mtu and the device's
// current MTU. Failures are logged and leave xnu's default; the tun works either way.
func (t *tun) raisePendingPackets() {
if t.f == nil {
return
}
rc, err := t.f.SyscallConn()
if err != nil {
return
}
mtu := max(t.DefaultMTU, t.currentMTU())
_ = rc.Control(func(fd uintptr) {
pending := tunPendingPackets
need := pending * (mtu + 4)
if have, err := tunGetsockoptInt(int(fd), unix.SOL_SOCKET, unix.SO_RCVBUF); err == nil && have < need {
if err := tunSetsockoptInt(int(fd), unix.SOL_SOCKET, unix.SO_RCVBUF, need); err != nil {
pending = max(have/(mtu+4), 1)
t.l.Warn("could not grow the tun control socket's receive buffer, capping pending packets",
"error", err, "rcvbuf", have, "wanted", need, "pending", pending)
}
}
if err := tunSetsockoptInt(int(fd), _SYSPROTO_CONTROL, _UTUN_OPT_MAX_PENDING_PACKETS, pending); err != nil {
t.l.Warn("could not raise the tun's pending packet limit, reads will return one packet each",
"error", err, "pending", pending)
}
})
}
// currentMTU is the utun's MTU as the kernel has it now, or 0 if that can't be read. A host-owned device's MTU
// comes from the host, not tun.mtu.
func (t *tun) currentMTU() int {
if t.Device == "" {
return 0
}
s, err := unix.Socket(unix.AF_INET, unix.SOCK_DGRAM, unix.IPPROTO_IP)
if err != nil {
return 0
}
defer unix.Close(s)
ifr, err := unix.IoctlGetIfreqMTU(s, t.Device)
if err != nil {
return 0
}
return int(ifr.MTU)
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
}
-637
View File
@@ -1,637 +0,0 @@
//go:build !ios && !e2e_testing
package overlay
import (
"bytes"
"os"
"sync/atomic"
"syscall"
"testing"
"time"
"github.com/slackhq/nebula/internal/msgx"
"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) {
noTunSendX.Store(fallback)
t.Cleanup(func() { noTunSendX.Store(false) })
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)
var pkts, want [][]byte
for i := range 3*msgx.Batch + 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, noTunSendX.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)
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", msgx.Batch + 6},
{"first-in-call", msgx.Batch},
} {
t.Run(tc.name, func(t *testing.T) {
forEachTunWritePath(t, func(t *testing.T, fallback bool) {
tn, r := newSocketpairTun(t, 1024)
var pkts, want [][]byte
for i := range 2*msgx.Batch + 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, noTunSendX.Load())
readTunBack(t, r, want)
})
})
}
}
// forEachTunReadPath runs fn once over recvmsg_x and once over the per-packet readv drain.
func forEachTunReadPath(t *testing.T, fn func(t *testing.T, newQ func(*tun) *tunQueue)) {
for _, recvX := range []bool{true, false} {
name := "recvmsg_x"
if !recvX {
name = "readv"
}
t.Run(name, func(t *testing.T) {
fn(t, func(tn *tun) *tunQueue {
q := newTunQueue(tn)
if !recvX {
q.x = nil
}
return q
})
})
}
}
// writeTunPkts writes n test packets of size bytes to the peer end w and returns the packets the tun should hand back
// for them.
func writeTunPkts(t *testing.T, w, n, size int) [][]byte {
t.Helper()
var want [][]byte
for i := range n {
pkt, wire := testTunPkt(i, size+i)
_, err := unix.Write(w, wire)
require.NoError(t, err)
want = append(want, pkt)
}
return want
}
// newReadTun is newSocketpairTun with the tun's receive buffer big enough for every test burst, since an AF_UNIX
// datagram send is bounded by the receiver's buffer, and the writer's send buffer big enough for the largest IP packet.
func newReadTun(t *testing.T) (*tun, int) {
t.Helper()
tn, w := newSocketpairTun(t, 1<<20)
require.NoError(t, unix.SetsockoptInt(w, unix.SOL_SOCKET, unix.SO_SNDBUF, 1<<18))
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))
}))
return tn, w
}
// readTunPkts calls q.Read once per entry of sizes, requires each to return that many packets, and returns copies of
// them all.
func readTunPkts(t *testing.T, q *tunQueue, sizes ...int) [][]byte {
t.Helper()
var got [][]byte
for _, size := range sizes {
pkts, err := q.Read()
require.NoError(t, err)
require.Len(t, pkts, size)
for _, p := range pkts {
got = append(got, p.Clone().Bytes)
}
}
return got
}
// stubTunRecvmsgX swaps tunRecvmsgX for fn until the test ends and counts its calls. fn gets the real msgx.Recv to
// delegate to.
func stubTunRecvmsgX(t *testing.T, fn func(sys func(uintptr, []msgx.Hdr) (int, syscall.Errno), fd uintptr, hdrs []msgx.Hdr) (int, syscall.Errno)) *atomic.Int64 {
t.Helper()
sys := tunRecvmsgX
var calls atomic.Int64
tunRecvmsgX = func(fd uintptr, hdrs []msgx.Hdr) (int, syscall.Errno) {
calls.Add(1)
return fn(sys, fd, hdrs)
}
t.Cleanup(func() { tunRecvmsgX = sys })
return &calls
}
// 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) {
forEachTunReadPath(t, func(t *testing.T, newQ func(*tun) *tunQueue) {
tn, w := newReadTun(t)
q := newQ(tn)
want := writeTunPkts(t, w, tunReadBatch+3, 60)
assert.Equal(t, want, readTunPkts(t, q, tunReadBatch, 3))
})
}
// TestTunQueueReadUsesRecvX pins that a burst is read with one recvmsg_x, not one call per packet.
func TestTunQueueReadUsesRecvX(t *testing.T) {
calls := stubTunRecvmsgX(t, func(sys func(uintptr, []msgx.Hdr) (int, syscall.Errno), fd uintptr, hdrs []msgx.Hdr) (int, syscall.Errno) {
return sys(fd, hdrs)
})
tn, w := newReadTun(t)
q := newTunQueue(tn)
want := writeTunPkts(t, w, 10, 60)
assert.Equal(t, want, readTunPkts(t, q, 10))
assert.EqualValues(t, 1, calls.Load())
assert.NotNil(t, q.x)
}
// TestTunQueueReadLargePackets pins that packets up to the largest IP packet come back whole, which on the recvmsg_x
// path means each lands in its own slot and none spills into the next.
func TestTunQueueReadLargePackets(t *testing.T) {
forEachTunReadPath(t, func(t *testing.T, newQ func(*tun) *tunQueue) {
tn, w := newReadTun(t)
q := newQ(tn)
var want [][]byte
for i, size := range []int{65535, 1, 9001, 65535} {
pkt, wire := testTunPkt(i, max(size, 3))
pkt, wire = pkt[:size], wire[:4+size]
_, err := unix.Write(w, wire)
require.NoError(t, err)
want = append(want, pkt)
}
assert.Equal(t, want, readTunPkts(t, q, 4))
})
}
// 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) {
forEachTunReadPath(t, func(t *testing.T, newQ func(*tun) *tunQueue) {
tn, w := newSocketpairTun(t, 1<<20)
q := newQ(tn)
writeTunPkts(t, w, 2, 100)
pkts, err := q.Read()
require.NoError(t, err)
require.Len(t, pkts, 2)
assert.Equal(t, len(pkts[0].Bytes), cap(pkts[0].Bytes))
assert.Equal(t, len(pkts[1].Bytes), cap(pkts[1].Bytes))
})
}
// TestTunQueueReadDoesNotAllocate pins both read paths to zero allocations per Read once the queue exists.
func TestTunQueueReadDoesNotAllocate(t *testing.T) {
forEachTunReadPath(t, func(t *testing.T, newQ func(*tun) *tunQueue) {
tn, w := newReadTun(t)
q := newQ(tn)
_, wire := testTunPkt(0, 1300)
allocs := testing.AllocsPerRun(1000, func() {
if _, err := unix.Write(w, wire); err != nil {
t.Fatal(err)
}
if pkts, err := q.Read(); err != nil || len(pkts) != 1 {
t.Fatalf("read %d packets: %v", len(pkts), err)
}
})
assert.Zero(t, allocs)
})
}
// TestTunQueueReadXRefused pins that recvmsg_x being refused turns it off for good, and that the same Read still
// hands back the queued packets through readv.
func TestTunQueueReadXRefused(t *testing.T) {
for _, errno := range []syscall.Errno{unix.ENOSYS, unix.EPERM, unix.EOPNOTSUPP, unix.EINVAL} {
t.Run(errno.Error(), func(t *testing.T) {
calls := stubTunRecvmsgX(t, func(func(uintptr, []msgx.Hdr) (int, syscall.Errno), uintptr, []msgx.Hdr) (int, syscall.Errno) {
return 0, errno
})
tn, w := newReadTun(t)
q := newTunQueue(tn)
want := writeTunPkts(t, w, 5, 60)
assert.Equal(t, want, readTunPkts(t, q, 5))
assert.Nil(t, q.x)
assert.EqualValues(t, 1, calls.Load())
want = writeTunPkts(t, w, 2, 60)
assert.Equal(t, want, readTunPkts(t, q, 2))
assert.EqualValues(t, 1, calls.Load(), "recvmsg_x was tried again after it was refused")
})
}
}
// TestTunQueueReadXTransientError pins that an error from recvmsg_x that doesn't mean it is refused leaves this Read
// to readv but keeps recvmsg_x on for the next.
func TestTunQueueReadXTransientError(t *testing.T) {
var failed atomic.Bool
calls := stubTunRecvmsgX(t, func(sys func(uintptr, []msgx.Hdr) (int, syscall.Errno), fd uintptr, hdrs []msgx.Hdr) (int, syscall.Errno) {
if !failed.Swap(true) {
return 0, unix.ENOBUFS
}
return sys(fd, hdrs)
})
tn, w := newReadTun(t)
q := newTunQueue(tn)
want := writeTunPkts(t, w, 3, 60)
assert.Equal(t, want, readTunPkts(t, q, 3))
assert.NotNil(t, q.x)
assert.EqualValues(t, 1, calls.Load())
want = writeTunPkts(t, w, 2, 60)
assert.Equal(t, want, readTunPkts(t, q, 2))
assert.EqualValues(t, 2, calls.Load(), "recvmsg_x wasn't tried again after a transient error")
}
// TestTunQueueReadXParks pins that EAGAIN from recvmsg_x parks the Read until the utun is readable, rather than
// falling back or returning an empty batch.
func TestTunQueueReadXParks(t *testing.T) {
var failed atomic.Bool
calls := stubTunRecvmsgX(t, func(sys func(uintptr, []msgx.Hdr) (int, syscall.Errno), fd uintptr, hdrs []msgx.Hdr) (int, syscall.Errno) {
if !failed.Swap(true) {
return 0, unix.EAGAIN
}
return sys(fd, hdrs)
})
tn, w := newReadTun(t)
q := newTunQueue(tn)
// A real EAGAIN means nothing is queued, so the packet arrives only once Read has parked. One packet, so the
// wakeup can't split it across Reads.
done := make(chan struct{})
go func() {
defer close(done)
time.Sleep(50 * time.Millisecond)
_, wire := testTunPkt(0, 60)
_, _ = unix.Write(w, wire)
}()
t.Cleanup(func() { <-done })
pkt, _ := testTunPkt(0, 60)
assert.Equal(t, [][]byte{pkt}, readTunPkts(t, q, 1))
assert.NotNil(t, q.x)
// A spurious wakeup costs another EAGAIN, so only a floor.
assert.GreaterOrEqual(t, calls.Load(), int64(2))
}
// TestTunQueueReadXBadBatch pins that a recvmsg_x batch no intact header could produce turns recvmsg_x off for good
// and hands the Read to readv. The stub reports a bad batch without taking any packets, so readv then reads them all.
func TestTunQueueReadXBadBatch(t *testing.T) {
v4 := [4]byte{3: syscall.AF_INET}
for _, tc := range []struct {
name string
mess func(x *tunRecvX) int
}{
{"too many", func(x *tunRecvX) int {
for i := range x.hdrs {
x.hdrs[i].Datalen, x.heads[i] = 64, v4
}
return len(x.hdrs) + 1
}},
{"past the buffer", func(x *tunRecvX) int {
x.hdrs[0].Datalen, x.heads[0] = 4+tunRecvXSlot+1, v4
return 1
}},
{"bad AF prefix", func(x *tunRecvX) int {
x.hdrs[0].Datalen, x.heads[0] = 64, [4]byte{syscall.AF_INET}
return 1
}},
} {
t.Run(tc.name, func(t *testing.T) {
var q *tunQueue
stubTunRecvmsgX(t, func(func(uintptr, []msgx.Hdr) (int, syscall.Errno), uintptr, []msgx.Hdr) (int, syscall.Errno) {
return tc.mess(q.x), 0
})
tn, w := newReadTun(t)
q = newTunQueue(tn)
want := writeTunPkts(t, w, 4, 60)
assert.Equal(t, want, readTunPkts(t, q, 4))
assert.Nil(t, q.x)
})
}
}
// TestTunRecvXCheck pins which recvmsg_x batches tunRecvXCheck accepts.
func TestTunRecvXCheck(t *testing.T) {
const slot = 1000
v4, v6 := [4]byte{3: syscall.AF_INET}, [4]byte{3: syscall.AF_INET6}
good := func() ([]msgx.Hdr, [][4]byte) {
hdrs := make([]msgx.Hdr, 4)
heads := make([][4]byte, 4)
for i := range hdrs {
hdrs[i].Datalen = uint64(4 + 20 + i)
heads[i] = v4
if i%2 == 1 {
heads[i] = v6
}
}
return hdrs, heads
}
for _, tc := range []struct {
name string
n int
mess func(hdrs []msgx.Hdr, heads [][4]byte)
ok bool
}{
{"all", 4, nil, true},
{"none", 0, nil, true},
{"prefix", 2, nil, true},
{"garbage past n is ignored", 2, func(h []msgx.Hdr, hd [][4]byte) { h[3].Datalen, hd[3] = 1<<40, [4]byte{9} }, true},
{"just the AF prefix", 1, func(h []msgx.Hdr, _ [][4]byte) { h[0].Datalen = 4 }, true},
{"fills the slot", 1, func(h []msgx.Hdr, _ [][4]byte) { h[0].Datalen = 4 + slot }, true},
{"more than headers", 5, nil, false},
{"negative", -1, nil, false},
{"past the slot", 2, func(h []msgx.Hdr, _ [][4]byte) { h[1].Datalen = 4 + slot + 1 }, false},
{"shorter than the AF prefix", 1, func(h []msgx.Hdr, _ [][4]byte) { h[0].Datalen = 3 }, false},
{"truncated", 3, func(h []msgx.Hdr, _ [][4]byte) { h[2].Flags = unix.MSG_TRUNC }, false},
{"zero AF prefix", 1, func(_ []msgx.Hdr, hd [][4]byte) { hd[0] = [4]byte{} }, false},
{"host order AF prefix", 1, func(_ []msgx.Hdr, hd [][4]byte) { hd[0] = [4]byte{syscall.AF_INET} }, false},
{"other AF", 2, func(_ []msgx.Hdr, hd [][4]byte) { hd[1] = [4]byte{3: syscall.AF_UNIX} }, false},
} {
t.Run(tc.name, func(t *testing.T) {
hdrs, heads := good()
if tc.mess != nil {
tc.mess(hdrs, heads)
}
err := tunRecvXCheck(tc.n, hdrs, heads, slot)
if tc.ok {
assert.NoError(t, err)
} else {
assert.Error(t, err)
}
})
}
}
// TestTunRecvXRefused pins which recvmsg_x errnos turn it off for good.
func TestTunRecvXRefused(t *testing.T) {
for _, errno := range []syscall.Errno{unix.ENOSYS, unix.EPERM, unix.EOPNOTSUPP, unix.EINVAL, unix.EMSGSIZE} {
assert.True(t, tunRecvXRefused(errno), "%v", errno)
}
for _, errno := range []syscall.Errno{0, unix.EAGAIN, unix.EINTR, unix.ENOBUFS, unix.ENOMEM, unix.EBADF, unix.ENOTCONN} {
assert.False(t, tunRecvXRefused(errno), "%v", errno)
}
}
// TestTunRaisePendingPackets pins that the pending limit is set at SYSPROTO_CONTROL level after the receive buffer is
// grown to hold that many packets of the tun's MTU, and capped to what the buffer holds when it can't grow.
func TestTunRaisePendingPackets(t *testing.T) {
type call struct{ level, opt, value int }
stub := func(t *testing.T, rcvbuf int, failLevel, failOpt int) *[]call {
set, get := tunSetsockoptInt, tunGetsockoptInt
var calls []call
tunSetsockoptInt = func(fd, level, opt, value int) error {
calls = append(calls, call{level, opt, value})
if level == failLevel && opt == failOpt {
return unix.ENOBUFS
}
return nil
}
tunGetsockoptInt = func(fd, level, opt int) (int, error) { return rcvbuf, nil }
t.Cleanup(func() { tunSetsockoptInt, tunGetsockoptInt = set, get })
return &calls
}
for _, tc := range []struct {
name string
rcvbuf int
mtu int
failLevel int
failOpt int
want []call
}{
{"grows rcvbuf first", 1 << 16, 9000, -1, -1, []call{
{unix.SOL_SOCKET, unix.SO_RCVBUF, 64 * 9004},
{2, 16, 64},
}},
{"rcvbuf already big enough", 1 << 20, 1300, -1, -1, []call{{2, 16, 64}}},
{"rcvbuf refused caps pending", 10 * 1304, 1300, unix.SOL_SOCKET, unix.SO_RCVBUF, []call{
{unix.SOL_SOCKET, unix.SO_RCVBUF, 64 * 1304},
{2, 16, 10},
}},
} {
t.Run(tc.name, func(t *testing.T) {
calls := stub(t, tc.rcvbuf, tc.failLevel, tc.failOpt)
tn, _ := newSocketpairTun(t, 1<<20)
tn.DefaultMTU = tc.mtu
_, err := tn.Queues(1)
require.NoError(t, err)
assert.Equal(t, tc.want, *calls)
})
}
}
func TestTun_WriteFraming(t *testing.T) {
r, w, err := os.Pipe()
require.NoError(t, err)
defer r.Close()
defer w.Close()
tn := &tun{f: w}
for _, tc := range []struct {
name string
pkt []byte
af byte
}{
// Literal families rather than syscall.AF_*, so a wrong constant in Write can't also fix the expectation.
{"ipv4", []byte{0x45, 1, 2, 3, 4, 5}, 2},
{"ipv6", []byte{0x60, 1, 2, 3, 4, 5}, 30},
} {
t.Run(tc.name, func(t *testing.T) {
n, err := tn.Write(tc.pkt)
require.NoError(t, err)
require.Equal(t, len(tc.pkt), n)
got := make([]byte, 64)
n, err = r.Read(got)
require.NoError(t, err)
require.Equal(t, append([]byte{0, 0, 0, tc.af}, tc.pkt...), got[:n])
})
}
_, err = tn.Write([]byte{0x10, 1, 2, 3})
require.Error(t, err)
_, err = tn.Write([]byte{})
require.ErrorIs(t, err, syscall.EIO)
// The rejected writes must not have put anything on the fd, so the next read sees only this packet.
pkt := []byte{0x45, 9, 9}
_, err = tn.Write(pkt)
require.NoError(t, err)
got := make([]byte, 64)
n, err := r.Read(got)
require.NoError(t, err)
require.Equal(t, append([]byte{0, 0, 0, 2}, pkt...), got[:n])
}
func TestTun_ReadStripsHeader(t *testing.T) {
r, w, err := os.Pipe()
require.NoError(t, err)
defer r.Close()
defer w.Close()
tn := &tun{f: r}
pkt := []byte{0x45, 1, 2, 3, 4, 5}
_, err = w.Write(append([]byte{0, 0, 0, syscall.AF_INET}, pkt...))
require.NoError(t, err)
got := make([]byte, 64)
n, err := tn.Read(got)
require.NoError(t, err)
require.Equal(t, pkt, got[:n])
}
func TestTun_ReadShort(t *testing.T) {
r, w, err := os.Pipe()
require.NoError(t, err)
defer r.Close()
defer w.Close()
tn := &tun{f: r}
// Fewer bytes than the protocol header is not a packet.
_, err = w.Write([]byte{0, 0})
require.NoError(t, err)
n, err := tn.Read(make([]byte, 64))
require.NoError(t, err)
require.Zero(t, n)
// The next packet reads cleanly only if the short read consumed exactly what was written.
pkt := []byte{0x45, 1, 2, 3}
_, err = w.Write(append([]byte{0, 0, 0, syscall.AF_INET}, pkt...))
require.NoError(t, err)
got := make([]byte, 64)
n, err = tn.Read(got)
require.NoError(t, err)
require.Equal(t, pkt, got[:n])
}
// A heap allocation per packet rarely shows in a short throughput run, only across GC pauses, so
// this pins Read and Write to zero allocations directly.
func TestTun_ReadWriteDoNotAllocate(t *testing.T) {
r, w, err := os.Pipe()
require.NoError(t, err)
defer r.Close()
defer w.Close()
tw := &tun{f: w}
tr := &tun{f: r}
pkts := [][]byte{bytes.Repeat([]byte{0x45}, 1300), bytes.Repeat([]byte{0x60}, 1300)}
buf := make([]byte, 1500)
i := 0
allocs := testing.AllocsPerRun(1000, func() {
i++
if _, err := tw.Write(pkts[i%len(pkts)]); err != nil {
t.Fatal(err)
}
if _, err := tr.Read(buf); err != nil {
t.Fatal(err)
}
})
require.Zero(t, allocs)
}
-13
View File
@@ -1,13 +0,0 @@
//go:build !darwin && !send_pipeline
package nebula
import "github.com/slackhq/nebula/overlay/tio"
// sendPipelinePlatform is false off darwin: the pipelined send path (interface_pipeline.go) is darwin only for now,
// and listenIn writes its own batches everywhere else. Being a constant, it removes the branch at compile time.
// Build with -tags send_pipeline to run the pipeline, and its tests, on another platform.
const sendPipelinePlatform = false
// listenInPipelined is a plain function rather than a method so this unreachable stub leaves no trace in the binary.
func listenInPipelined(*Interface, tio.Queue, int) {}
-8
View File
@@ -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 {
-106
View File
@@ -1,106 +0,0 @@
//go:build !e2e_testing
package udp
import (
"log/slog"
"net"
"net/netip"
"testing"
"time"
)
// benchConnSocks opens a wildcard listener with ListenOut running and 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()
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.listening.Load() {
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")
}
}
})
}
}
-839
View File
@@ -1,839 +0,0 @@
//go:build !e2e_testing
package udp
import (
"context"
"errors"
"fmt"
"log/slog"
"maps"
"net"
"net/netip"
"os"
"slices"
"sync"
"sync/atomic"
"syscall"
"time"
"unsafe"
"github.com/slackhq/nebula/internal/msgx"
"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 bufs on the descriptor and returns how many went out: sendFd, or a stand-in for the interface in
// tests.
sys func(fd int, bufs [][]byte, x *sendScratch) (int, error)
}
// sendScratch is the msghdr_x array one sendmsg_x reads.
type sendScratch struct {
hdrs [msgx.Batch]msgx.Hdr
iovs [msgx.Batch]unix.Iovec
}
// noSendX is set once sendmsg_x is refused; connected sockets then write one datagram per syscall.
var noSendX atomic.Bool
// sendFd writes bufs on fd, a lone datagram with write and more with one sendmsg_x, which xnu runs through the stack
// as a batch on a connected socket. It returns how many went out, or none and the errno. sendmsg_x reports EAGAIN,
// ENOBUFS and EMSGSIZE only when it took nothing, and any other error without the count it took, which a connected
// socket gets only on its first datagram, as its peer's unreachable.
func sendFd(fd int, bufs [][]byte, x *sendScratch) (int, error) {
if len(bufs) == 1 {
if _, err := syscall.Write(fd, bufs[0]); err != nil {
return 0, err
}
return 1, nil
}
n := min(len(bufs), msgx.Batch)
for i, b := range bufs[:n] {
x.iovs[i] = unix.Iovec{Base: unsafe.SliceData(b)}
x.iovs[i].SetLen(len(b))
x.hdrs[i] = msgx.Hdr{Iov: &x.iovs[i], Iovlen: 1}
}
sent, errno := msgx.Send(uintptr(fd), x.hdrs[:n])
clear(x.iovs[:n])
if errno != 0 {
return 0, errno
}
if sent == 0 {
return 0, syscall.EAGAIN
}
return sent, nil
}
// 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
// bufs holds a copy of the datagrams' slice headers rather than the caller's slice, which would escape
// through the pool and cost WriteTo's one-datagram array an allocation per send.
bufs [msgx.Batch][]byte
nbufs int
park bool
n int
err error
fn func(fd uintptr) bool
x sendScratch
}
var connSockWriters = sync.Pool{New: func() any {
w := &connSockWriter{}
w.fn = w.write
return w
}}
func (w *connSockWriter) write(fd uintptr) bool {
for {
w.n, w.err = w.s.sys(int(fd), w.bufs[:w.nbufs], &w.x)
switch {
case w.err == syscall.EINTR:
case w.err == syscall.EAGAIN && w.park:
return false
default:
return true
}
}
}
// try writes bufs on s once and returns how many went out, or none and 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(bufs [][]byte, park bool) (int, error) {
w := connSockWriters.Get().(*connSockWriter)
w.s, w.nbufs, w.park = s, copy(w.bufs[:], bufs), park
rerr := s.rc.Write(w.fn)
n, err := w.n, w.err
clear(w.bufs[:w.nbufs])
w.s, w.nbufs, w.n, w.err = nil, 0, 0, nil
connSockWriters.Put(w)
switch {
case rerr == nil:
return n, err
case errors.Is(rerr, os.ErrDeadlineExceeded):
return 0, os.ErrDeadlineExceeded
default:
return 0, net.ErrClosed
}
}
// connSockConfig holds the knobs, which tests change.
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 defaultConnSockConfig() connSockConfig {
return connSockConfig{
max: 8,
run: 64,
window: time.Second,
idle: 30 * time.Second,
backoff: 30 * time.Second,
openEvery: time.Second,
enobufsMax: 10 * time.Millisecond,
}
}
// 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: defaultConnSockConfig(), 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.listening.Load() || 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: sendFd}
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, up to msgx.Batch datagrams per sendmsg_x. 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())
}
}()
probe := false
for sent < len(bufs) {
n := 1
if !noSendX.Load() && !probe {
n = len(bufs) - sent
}
k, err := s.try(bufs[sent:sent+n], false)
if errno, ok := err.(syscall.Errno); ok && n > 1 && msgx.Unsupported(errno) {
// EPERM may be the datagram's own fault, so sendmsg_x is off for good only once a plain write of the same
// datagram goes through.
probe = true
continue
}
if probe && err == nil && noSendX.CompareAndSwap(false, true) {
u.l.Warn("sendmsg_x unavailable, writing one datagram per syscall")
}
probe = false
if err == syscall.EAGAIN || err == os.ErrDeadlineExceeded {
// os.ErrDeadlineExceeded here is another writer's parked deadline, passed but not yet cleared.
k, err = u.parkedWrite(s, bufs[sent:sent+1])
}
switch err {
case nil:
sent += k
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) (int, error) {
cs := u.socks
s.parkMu.Lock()
defer s.parkMu.Unlock()
left := cs.cfg.enobufsMax - s.stalledFor(cs.clock())
if left <= 0 {
return 0, errStallSpent
}
if err := s.conn.SetWriteDeadline(time.Now().Add(left)); err != nil {
return 0, net.ErrClosed
}
n, err := s.try(b, true)
_ = s.conn.SetWriteDeadline(time.Time{})
if err == os.ErrDeadlineExceeded {
return 0, errStallSpent
}
return n, 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 hands a connected socket's batches to 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) {
r := u.newBatchReader(s.conn, s.rc)
for {
b, err := u.read(r)
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())
if !u.deliver(b) {
return
}
}
}
File diff suppressed because it is too large. Load diff
-6
View File
@@ -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
-6
View File
@@ -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
+17 -284
View File
@@ -10,12 +10,10 @@ import (
"log/slog"
"net"
"net/netip"
"sync/atomic"
"syscall"
"unsafe"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/internal/msgx"
"golang.org/x/sys/unix"
)
@@ -24,24 +22,9 @@ type StdConn struct {
isV4 bool
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
// listening is set once ListenOut runs. The listener's and every connected socket's readers hand their batches
// to it on rx, so the EncReader runs on ListenOut's goroutine alone; done closes when ListenOut returns.
listening atomic.Bool
rx chan *rxBatch
done chan struct{}
// free holds the batches ListenOut has delivered, for the readers to fill again.
free chan *rxBatch
}
var _ Conn = &StdConn{}
var _ EstablishedPeerConn = &StdConn{}
func NewListener(l *slog.Logger, s Settings) (Conn, error) {
lc := NewListenConfig(s.Multi)
@@ -51,14 +34,12 @@ 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(), rx: make(chan *rxBatch, 1), done: make(chan struct{}),
free: make(chan *rxBatch, rxBatchesKept)}
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
@@ -72,8 +53,6 @@ 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
}
@@ -110,19 +89,6 @@ 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
@@ -175,47 +141,15 @@ func (u *StdConn) writeTo(b []byte, ap netip.AddrPort) error {
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.
// TODO: WriteTo maps EWOULDBLOCK to an error, so a full send buffer
// silently drops the rest of a burst (linux blocks instead). Poll for
// writability on EAGAIN before giving up on the remainder.
written := 0
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
}
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 p := (*t)[dst]; p != nil {
for off < end {
sent, err := u.connSockRun(p, dst, bufs[off:end])
written += sent
off += sent
if err == nil {
break
}
u.l.Debug("failed to write packet in batch", "udpAddr", dst, "error", err)
off++
}
}
// The listener sends what no connected socket took.
for ; off < end; off++ {
if err := u.writeTo(bufs[off], dst); err == nil {
written++
} else {
u.l.Debug("failed to write packet in batch", "udpAddr", dst, "error", err)
}
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
@@ -246,176 +180,12 @@ func NewUDPStatsEmitter(udpConns []Conn) func() {
return func() {}
}
// ListenOut delivers the batches that the listener's reader and the connected sockets' readers hand it.
func (u *StdConn) ListenOut(r EncReader, flush func()) error {
defer close(u.done)
u.listening.Store(true)
u.startConnSocks()
errc := make(chan error, 1)
go func() { errc <- u.readListener() }()
buffer := make([]byte, MTU)
for {
select {
case b := <-u.rx:
for i := range b.n {
r(b.addrs[i], b.pkts[i])
}
flush()
u.putBatch(b)
case err := <-errc:
return err
}
}
}
// rxBatch is one recvmsg_x batch: n datagrams in pkts, from addrs. A reader takes one only while its socket is
// readable, so an idle connected socket holds none.
type rxBatch struct {
n int
pkts [msgx.Batch][]byte
addrs [msgx.Batch]netip.AddrPort
buf []byte
names [msgx.Batch]unix.RawSockaddrInet6
iovs [msgx.Batch]unix.Iovec
hdrs [msgx.Batch]msgx.Hdr
}
// rxBatchesKept is how many batches a listener keeps for reuse: one being delivered and one queued, plus one for
// each socket reading at once, the listener and up to 8 connected sockets. Each is msgx.Batch*MTU, about 576KB.
const rxBatchesKept = 11
func (u *StdConn) getBatch() *rxBatch {
select {
case b := <-u.free:
return b
default:
}
b := &rxBatch{buf: make([]byte, msgx.Batch*MTU)}
for i := range b.hdrs {
b.iovs[i].Base = &b.buf[i*MTU]
b.iovs[i].SetLen(MTU)
b.hdrs[i] = msgx.Hdr{Name: (*byte)(unsafe.Pointer(&b.names[i])), Iov: &b.iovs[i], Iovlen: 1}
}
return b
}
func (u *StdConn) putBatch(b *rxBatch) {
select {
case u.free <- b:
default:
}
}
// noRecvX is set once recvmsg_x is refused or misbehaves; every reader then reads one datagram per syscall.
var noRecvX atomic.Bool
// parse checks the n entries recvmsg_x filled and sets pkts and addrs from them. It rejects a batch that intact
// msghdr_x entries can't produce, which is how a change to xnu's private struct layout would show up.
func (b *rxBatch) parse(n int) error {
if n > len(b.hdrs) {
return fmt.Errorf("returned %d datagrams for %d headers", n, len(b.hdrs))
}
for i := range n {
h := &b.hdrs[i]
if h.Datalen > MTU {
return fmt.Errorf("datagram %d is %d bytes, past the %d byte buffer", i, h.Datalen, MTU)
}
sa := &b.names[i]
switch {
case sa.Family == unix.AF_INET && h.Namelen == unix.SizeofSockaddrInet4:
sa4 := (*unix.RawSockaddrInet4)(unsafe.Pointer(sa))
b.addrs[i] = netip.AddrPortFrom(netip.AddrFrom4(sa4.Addr), binary.BigEndian.Uint16((*[2]byte)(unsafe.Pointer(&sa4.Port))[:]))
case sa.Family == unix.AF_INET6 && h.Namelen == unix.SizeofSockaddrInet6:
b.addrs[i] = netip.AddrPortFrom(netip.AddrFrom16(sa.Addr).Unmap(), binary.BigEndian.Uint16((*[2]byte)(unsafe.Pointer(&sa.Port))[:]))
default:
return fmt.Errorf("datagram %d has address family %d with length %d", i, sa.Family, h.Namelen)
}
b.pkts[i] = b.buf[i*MTU : i*MTU+int(h.Datalen) : i*MTU+int(h.Datalen)]
}
b.n = n
return nil
}
// batchReader reads one socket in batches. Its fn is bound once, since a closure passed through the RawConn
// interface escapes and would allocate on every read.
type batchReader struct {
u *StdConn
conn *net.UDPConn
rc syscall.RawConn
b *rxBatch
errno syscall.Errno
fn func(fd uintptr) bool
}
func (u *StdConn) newBatchReader(conn *net.UDPConn, rc syscall.RawConn) *batchReader {
r := &batchReader{u: u, conn: conn, rc: rc}
r.fn = r.recv
return r
}
func (r *batchReader) recv(fd uintptr) bool {
b := r.u.getBatch()
for i := range b.hdrs {
b.hdrs[i].Namelen = unix.SizeofSockaddrInet6
b.hdrs[i].Flags = 0
b.hdrs[i].Datalen = 0
}
n, errno := msgx.Recv(fd, b.hdrs[:])
if errno == unix.EAGAIN {
r.u.putBatch(b)
return false
}
b.n, r.b, r.errno = n, b, errno
return true
}
// read returns the next batch: up to msgx.Batch datagrams from one recvmsg_x, or one datagram once recvmsg_x is off.
func (u *StdConn) read(r *batchReader) (*rxBatch, error) {
if !noRecvX.Load() {
r.b = nil
err := r.rc.Read(r.fn)
b := r.b
switch {
case err != nil:
if b != nil {
u.putBatch(b)
}
return nil, err
case r.errno == 0:
perr := b.parse(b.n)
if perr == nil {
return b, nil
}
// The batch was read through a layout the kernel no longer writes, so none of it is trustworthy.
u.disableRecvX("returned an unexpected header", perr)
case msgx.Unsupported(r.errno):
u.disableRecvX("unavailable", r.errno)
default:
u.putBatch(b)
return nil, r.errno
}
u.putBatch(b)
}
b := u.getBatch()
n, from, err := r.conn.ReadFromUDPAddrPort(b.buf[:MTU])
if err != nil {
u.putBatch(b)
return nil, err
}
b.n, b.pkts[0], b.addrs[0] = 1, b.buf[:n:n], netip.AddrPortFrom(from.Addr().Unmap(), from.Port())
return b, nil
}
func (u *StdConn) disableRecvX(why string, err error) {
if noRecvX.CompareAndSwap(false, true) {
u.l.Warn("recvmsg_x "+why+", reading one datagram per syscall", "error", err)
}
}
// readListener hands the listener's batches to ListenOut until the listener closes.
func (u *StdConn) readListener() error {
r := u.newBatchReader(u.UDPConn, u.rc)
for {
b, err := u.read(r)
// Just read one packet at a time
n, rua, err := u.ReadFromUDPAddrPort(buffer)
if err != nil {
if errors.Is(err, net.ErrClosed) {
return err
@@ -423,39 +193,19 @@ func (u *StdConn) readListener() error {
u.l.Error("unexpected udp socket receive error", "error", err)
continue
}
if !u.deliver(b) {
return net.ErrClosed
}
}
}
// deliver hands b to ListenOut, and reports false once ListenOut has returned.
func (u *StdConn) deliver(b *rxBatch) bool {
select {
case u.rx <- b:
return true
case <-u.done:
u.putBatch(b)
return false
r(netip.AddrPortFrom(rua.Addr().Unmap(), rua.Port()), buffer[:n:n])
flush()
}
}
// Close closes the connected sockets of every listen routine, then the listener.
func (u *StdConn) Close() error {
u.stopConnSocks()
return u.UDPConn.Close()
}
func (u *StdConn) SupportsMultipleReaders() bool {
return false
}
// 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 {
@@ -463,23 +213,6 @@ 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
}
-344
View File
@@ -1,344 +0,0 @@
//go:build !e2e_testing
package udp
import (
"bytes"
"fmt"
"log/slog"
"net"
"net/netip"
"sync"
"syscall"
"testing"
"time"
"unsafe"
"github.com/slackhq/nebula/internal/msgx"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"golang.org/x/sys/unix"
)
// A burst larger than msgx.Batch 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 = msgx.Batch*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+msgx.Batch-1)/msgx.Batch, flushes)
})
}
}
// Once recvmsg_x is off, every datagram still arrives, one per batch.
func TestListenOutSingleFallback(t *testing.T) {
noRecvX.Store(true)
t.Cleanup(func() { noRecvX.Store(false) })
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.ListenOut(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 TestRxBatchParse(t *testing.T) {
valid := func() *rxBatch {
b := (&StdConn{}).getBatch()
b.hdrs[0].Namelen, b.hdrs[0].Datalen = unix.SizeofSockaddrInet4, 1
b.names[0].Family = unix.AF_INET
sa4 := (*unix.RawSockaddrInet4)(unsafe.Pointer(&b.names[0]))
sa4.Addr = [4]byte{10, 0, 0, 1}
sa4.Port = 0x0110 // 4097 in network order
b.hdrs[1].Namelen, b.hdrs[1].Datalen = unix.SizeofSockaddrInet6, MTU
b.names[1].Family = unix.AF_INET6
b.names[1].Addr = netip.MustParseAddr("::ffff:10.0.0.2").As16()
b.names[1].Port = 0x0210
return b
}
b := valid()
require.NoError(t, b.parse(2))
assert.Equal(t, 2, b.n)
assert.Equal(t, netip.MustParseAddrPort("10.0.0.1:4097"), b.addrs[0])
assert.Equal(t, netip.MustParseAddrPort("10.0.0.2:4098"), b.addrs[1], "v4-mapped sources arrive unmapped")
assert.Len(t, b.pkts[0], 1)
assert.Equal(t, 1, cap(b.pkts[0]))
assert.Len(t, b.pkts[1], MTU)
require.NoError(t, valid().parse(0))
for _, tc := range []struct {
name string
n int
mutate func(*rxBatch)
}{
{"count past headers", msgx.Batch + 1, func(*rxBatch) {}},
{"datalen past buffer", 2, func(b *rxBatch) { b.hdrs[1].Datalen = MTU + 1 }},
{"unknown family", 2, func(b *rxBatch) { b.names[0].Family = unix.AF_UNIX }},
{"family and length disagree", 2, func(b *rxBatch) { b.hdrs[0].Namelen = unix.SizeofSockaddrInet6 }},
} {
t.Run(tc.name, func(t *testing.T) {
b := valid()
tc.mutate(b)
assert.Error(t, b.parse(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(msgx.Batch-1), bytes.Repeat([]byte{0x05, 0xdc}, msgx.Batch))
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) < msgx.Batch; 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)%msgx.Batch, 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([]msgx.Hdr, 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] = msgx.Hdr{
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 {
n, errno = msgx.Recv(fd, hdrs)
return errno != 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)
b := &rxBatch{buf: make([]byte, n*MTU)}
copy(b.hdrs[:], hdrs[:n])
copy(b.names[:], names[:n])
require.NoError(t, b.parse(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)
require.Equal(t, senders[d], b.addrs[i], "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
}
// Once a listener has batches to reuse, reading one allocates nothing, on recvmsg_x or on the fallback.
func TestReadDoesNotAllocate(t *testing.T) {
for _, single := range []bool{false, true} {
t.Run(fmt.Sprintf("single=%v", single), func(t *testing.T) {
noRecvX.Store(single)
t.Cleanup(func() { noRecvX.Store(false) })
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0")})
require.NoError(t, err)
t.Cleanup(func() { _ = c.Close() })
u := c.(*StdConn)
la, err := c.LocalAddr()
require.NoError(t, err)
tx, err := net.DialUDP("udp4", nil, net.UDPAddrFromAddrPort(la))
require.NoError(t, err)
t.Cleanup(func() { _ = tx.Close() })
r := u.newBatchReader(u.UDPConn, u.rc)
pkt := []byte("steady")
allocs := testing.AllocsPerRun(100, func() {
if _, err := tx.Write(pkt); err != nil {
t.Fatal(err)
}
b, err := u.read(r)
if err != nil || b.n != 1 {
t.Fatalf("read %v: %v", b, err)
}
u.putBatch(b)
})
assert.Zero(t, allocs)
})
}
}