mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-16 13:36:57 +01:00
Compare commits
2
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
10e1924489 | ||
|
|
4d191f805f |
No files matched your search
+69
-1
@@ -637,6 +637,74 @@ func (t *tun) Read(to []byte) (int, error) {
|
||||
return n - 4, nil
|
||||
}
|
||||
|
||||
// tunReadBatch is the most packets one tunQueue.Read returns.
|
||||
const tunReadBatch = 64
|
||||
|
||||
// tunReadArena is tunQueue's receive buffer. Draining stops once less than defaultBatchBufSize of it
|
||||
// is left, so every readv has room for the largest packet utun can return at any device MTU.
|
||||
const tunReadArena = 4 * defaultBatchBufSize
|
||||
|
||||
// tunQueue is the darwin tun's Queue. Read drains every packet already queued on the utun, up to
|
||||
// tunReadBatch, so the caller encrypts and sends them as one batch rather than one per wakeup.
|
||||
type tunQueue struct {
|
||||
t *tun
|
||||
buf []byte
|
||||
pkts [tunReadBatch]tio.Packet
|
||||
}
|
||||
|
||||
// Read waits for the utun to become readable, then reads packets until it would block. An error after
|
||||
// at least one packet is dropped in favor of returning those packets; a persistent one recurs on the
|
||||
// next Read.
|
||||
func (q *tunQueue) Read() ([]tio.Packet, error) {
|
||||
rc, err := q.t.f.SyscallConn()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
var head [4]byte
|
||||
n, off := 0, 0
|
||||
var callErr error
|
||||
err = rc.Read(func(fd uintptr) bool {
|
||||
for n < tunReadBatch && len(q.buf)-off >= defaultBatchBufSize {
|
||||
iovecs := [2]unix.Iovec{
|
||||
{Base: &head[0], Len: 4},
|
||||
{Base: &q.buf[off], Len: uint64(len(q.buf) - off)},
|
||||
}
|
||||
l, e := tunReadv(int(fd), iovecs[:])
|
||||
if e != nil {
|
||||
if errno, ok := e.(syscall.Errno); ok && errno.Temporary() {
|
||||
// Park on the poller only while there is nothing to hand back.
|
||||
return n > 0
|
||||
}
|
||||
callErr = e
|
||||
return true
|
||||
}
|
||||
if l < 4 {
|
||||
// A datagram too short to carry the AF prefix, or end of file; stop rather than spin on it.
|
||||
return true
|
||||
}
|
||||
end := off + l - 4
|
||||
q.pkts[n] = tio.Packet{Bytes: q.buf[off:end:end]}
|
||||
n++
|
||||
off = end
|
||||
}
|
||||
return true
|
||||
})
|
||||
if n > 0 {
|
||||
return q.pkts[:n], nil
|
||||
}
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return nil, callErr
|
||||
}
|
||||
|
||||
func (q *tunQueue) Write(p []byte) (int, error) { return q.t.Write(p) }
|
||||
|
||||
func (q *tunQueue) WriteBatch(pkts [][]byte) error { return q.t.WriteBatch(pkts) }
|
||||
|
||||
func (q *tunQueue) Close() error { return q.t.Close() }
|
||||
|
||||
// Write pushes one IP packet onto the utun device. Safe for concurrent use:
|
||||
// the AF prefix and iovecs are per-call stack state, and the fd write itself
|
||||
// serializes on the runtime's fd mutex (see the Queue contract in tio.go).
|
||||
@@ -833,5 +901,5 @@ func (t *tun) Name() string {
|
||||
}
|
||||
|
||||
func (t *tun) Queues(int) ([]tio.Queue, error) {
|
||||
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
||||
return []tio.Queue{&tunQueue{t: t, buf: make([]byte, tunReadArena)}}, nil
|
||||
}
|
||||
@@ -151,3 +151,51 @@ func TestTunWriteBatchOversize(t *testing.T) {
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestTunQueueReadDrains pins that Read hands back every queued packet, AF prefix stripped and in
|
||||
// order, capped at tunReadBatch per call, and doesn't wait for more once the queue is empty.
|
||||
func TestTunQueueReadDrains(t *testing.T) {
|
||||
tn, w := newSocketpairTun(t, 1<<20)
|
||||
// An AF_UNIX datagram send is bounded by the receiver's buffer, here the tun's end.
|
||||
rc, err := tn.f.SyscallConn()
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, rc.Control(func(fd uintptr) {
|
||||
require.NoError(t, unix.SetsockoptInt(int(fd), unix.SOL_SOCKET, unix.SO_RCVBUF, 1<<20))
|
||||
}))
|
||||
q := &tunQueue{t: tn, buf: make([]byte, tunReadArena)}
|
||||
total := tunReadBatch + 3
|
||||
var want [][]byte
|
||||
for i := range total {
|
||||
pkt, wire := testTunPkt(i, 60+i)
|
||||
_, err := unix.Write(w, wire)
|
||||
require.NoError(t, err)
|
||||
want = append(want, pkt)
|
||||
}
|
||||
|
||||
var got [][]byte
|
||||
for _, size := range []int{tunReadBatch, 3} {
|
||||
pkts, err := q.Read()
|
||||
require.NoError(t, err)
|
||||
require.Len(t, pkts, size)
|
||||
for _, p := range pkts {
|
||||
got = append(got, p.Clone().Bytes)
|
||||
}
|
||||
}
|
||||
assert.Equal(t, want, got)
|
||||
}
|
||||
|
||||
// TestTunQueueReadClipsPackets pins that each returned packet's capacity ends at its own bytes, so
|
||||
// appending to one can't overwrite the next.
|
||||
func TestTunQueueReadClipsPackets(t *testing.T) {
|
||||
tn, w := newSocketpairTun(t, 1<<20)
|
||||
q := &tunQueue{t: tn, buf: make([]byte, tunReadArena)}
|
||||
for i := range 2 {
|
||||
_, wire := testTunPkt(i, 100)
|
||||
_, err := unix.Write(w, wire)
|
||||
require.NoError(t, err)
|
||||
}
|
||||
pkts, err := q.Read()
|
||||
require.NoError(t, err)
|
||||
require.Len(t, pkts, 2)
|
||||
assert.Equal(t, len(pkts[0].Bytes), cap(pkts[0].Bytes))
|
||||
}
|
||||
+153
-7
@@ -10,6 +10,7 @@ import (
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
"unsafe"
|
||||
|
||||
@@ -22,6 +23,9 @@ type StdConn struct {
|
||||
isV4 bool
|
||||
sysFd uintptr
|
||||
l *slog.Logger
|
||||
|
||||
noSendmsgX atomic.Bool
|
||||
sb *sendScratch
|
||||
}
|
||||
|
||||
var _ Conn = &StdConn{}
|
||||
@@ -139,11 +143,138 @@ func (u *StdConn) WriteTo(b []byte, ap netip.AddrPort) error {
|
||||
}
|
||||
}
|
||||
|
||||
// sendBatch is how many datagrams one sendmsg_x call may carry.
|
||||
const sendBatch = 64
|
||||
|
||||
// sendScratch is WriteBatch's scratch. The kernel reads every entry in place.
|
||||
type sendScratch struct {
|
||||
names [sendBatch]unix.RawSockaddrInet6
|
||||
iovs [sendBatch]unix.Iovec
|
||||
hdrs [sendBatch]msghdrX
|
||||
// idx maps each entry back to its index in WriteBatch's bufs.
|
||||
idx [sendBatch]int
|
||||
}
|
||||
|
||||
// WriteBatch sends bufs with sendmsg_x, darwin's private batched sendmsg, so one syscall carries up to
|
||||
// sendBatch datagrams. On this unconnected socket xnu still runs each message through sendit, so the
|
||||
// saving is the syscall crossings, not the per-send policy checks.
|
||||
//
|
||||
// xnu's per-message loop stops at the first message that fails. For the errors in sentNothing it reports
|
||||
// how many went out; for any other it returns only the errno, with the messages before it already sent.
|
||||
// Each call therefore carries one run of datagrams to the same destination: a destination the kernel
|
||||
// refuses fails on its first datagram, so a failed call costs that run and nothing else, and no datagram
|
||||
// is ever resent after the kernel may have taken it.
|
||||
//
|
||||
// TODO: WriteTo maps EWOULDBLOCK to an error, so a full send buffer
|
||||
// silently drops the rest of a burst (linux blocks instead). Poll for
|
||||
// writability on EAGAIN before giving up on the remainder.
|
||||
func (u *StdConn) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error) {
|
||||
// An un-sendable destination costs its own packet, never the ones behind it in the batch.
|
||||
// TODO: WriteTo maps EWOULDBLOCK to an error, so a full send buffer
|
||||
// silently drops the rest of a burst (linux blocks instead). Poll for
|
||||
// writability on EAGAIN before giving up on the remainder.
|
||||
if u.noSendmsgX.Load() {
|
||||
return u.writeEach(bufs, addrs), nil
|
||||
}
|
||||
if u.sb == nil {
|
||||
u.sb = new(sendScratch)
|
||||
}
|
||||
b := u.sb
|
||||
written := 0
|
||||
for i := 0; i < len(bufs); {
|
||||
n := 0
|
||||
for ; i < len(bufs) && n < sendBatch; i++ {
|
||||
namelen, err := u.putSockaddr(&b.names[n], addrs[i])
|
||||
if err != nil {
|
||||
u.l.Debug("failed to write packet in batch", "udpAddr", addrs[i], "error", err)
|
||||
continue
|
||||
}
|
||||
b.iovs[n] = unix.Iovec{}
|
||||
if len(bufs[i]) > 0 {
|
||||
b.iovs[n].Base = &bufs[i][0]
|
||||
b.iovs[n].SetLen(len(bufs[i]))
|
||||
}
|
||||
b.hdrs[n] = msghdrX{Name: (*byte)(unsafe.Pointer(&b.names[n])), Namelen: namelen, Iov: &b.iovs[n], Iovlen: 1}
|
||||
b.idx[n] = i
|
||||
n++
|
||||
}
|
||||
|
||||
for off := 0; off < n; {
|
||||
dst := addrs[b.idx[off]]
|
||||
end := off + 1
|
||||
for end < n && addrs[b.idx[end]] == dst {
|
||||
end++
|
||||
}
|
||||
sent, errno := u.sendmsgX(off, end)
|
||||
switch {
|
||||
case errno == 0 && sent > 0:
|
||||
written += sent
|
||||
off += sent
|
||||
continue
|
||||
case sentNothing(errno):
|
||||
// The datagram at off failed on its own account. sendto delivers or reports it, as without
|
||||
// batching, and the rest of the run goes back to sendmsg_x.
|
||||
j := b.idx[off]
|
||||
written += u.writeEach(bufs[j:j+1], addrs[j:j+1])
|
||||
off++
|
||||
continue
|
||||
case errno == 0:
|
||||
case errno == unix.ENOSYS || errno == unix.EOPNOTSUPP:
|
||||
u.fallBack(errno)
|
||||
case errno == unix.EPERM || errno == unix.EINVAL:
|
||||
// Either can refuse one destination, but a datagram that sendto delivers was refused by
|
||||
// sendmsg_x itself, as a sandbox or an older kernel would.
|
||||
j := b.idx[off]
|
||||
if u.writeEach(bufs[j:j+1], addrs[j:j+1]) == 0 {
|
||||
off = end
|
||||
continue
|
||||
}
|
||||
written++
|
||||
off++
|
||||
u.fallBack(errno)
|
||||
default:
|
||||
u.l.Debug("failed to write packets in batch", "udpAddr", dst, "packets", end-off, "error", errno)
|
||||
off = end
|
||||
continue
|
||||
}
|
||||
// The kernel took nothing from this call, so the rest can go out one datagram at a time.
|
||||
for _, j := range b.idx[off:n] {
|
||||
written += u.writeEach(bufs[j:j+1], addrs[j:j+1])
|
||||
}
|
||||
off = n
|
||||
if u.noSendmsgX.Load() {
|
||||
clear(b.iovs[:n])
|
||||
return written + u.writeEach(bufs[i:], addrs[i:]), nil
|
||||
}
|
||||
}
|
||||
clear(b.iovs[:n])
|
||||
}
|
||||
return written, nil
|
||||
}
|
||||
|
||||
// sendmsgX hands entries off through end-1 of u.sb to sendmsg_x and returns how many the kernel took.
|
||||
// The socket is non-blocking, so a full send buffer returns EAGAIN rather than waiting.
|
||||
func (u *StdConn) sendmsgX(off, end int) (int, syscall.Errno) {
|
||||
for {
|
||||
r0, _, errno := unix.Syscall6(unix.SYS_SENDMSG_X, u.sysFd, uintptr(unsafe.Pointer(&u.sb.hdrs[off])), uintptr(end-off), 0, 0, 0)
|
||||
if errno == unix.EINTR {
|
||||
continue
|
||||
}
|
||||
return int(r0), errno
|
||||
}
|
||||
}
|
||||
|
||||
// sentNothing reports whether sendmsg_x failing with errno means no datagram went out: once any has, xnu
|
||||
// turns these errors into a short count instead.
|
||||
func sentNothing(errno syscall.Errno) bool {
|
||||
return errno == unix.EWOULDBLOCK || errno == unix.ENOBUFS || errno == unix.EMSGSIZE
|
||||
}
|
||||
|
||||
// fallBack switches WriteBatch to one sendto per datagram for the life of the socket.
|
||||
func (u *StdConn) fallBack(errno syscall.Errno) {
|
||||
if u.noSendmsgX.CompareAndSwap(false, true) {
|
||||
u.l.Warn("sendmsg_x unavailable, sending one datagram per syscall", "error", errno)
|
||||
}
|
||||
}
|
||||
|
||||
// writeEach sends bufs one at a time with WriteTo and returns how many were written.
|
||||
func (u *StdConn) writeEach(bufs [][]byte, addrs []netip.AddrPort) int {
|
||||
written := 0
|
||||
for i, b := range bufs {
|
||||
if err := u.WriteTo(b, addrs[i]); err == nil {
|
||||
@@ -152,7 +283,23 @@ func (u *StdConn) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error)
|
||||
u.l.Debug("failed to write packet in batch", "udpAddr", addrs[i], "error", err)
|
||||
}
|
||||
}
|
||||
return written, nil
|
||||
return written
|
||||
}
|
||||
|
||||
// putSockaddr writes ap into sa in the socket's address family, as WriteTo would, and returns its length.
|
||||
func (u *StdConn) putSockaddr(sa *unix.RawSockaddrInet6, ap netip.AddrPort) (uint32, error) {
|
||||
if u.isV4 {
|
||||
if ap.Addr().Is6() {
|
||||
return 0, ErrInvalidIPv6RemoteForSocket
|
||||
}
|
||||
sa4 := (*unix.RawSockaddrInet4)(unsafe.Pointer(sa))
|
||||
*sa4 = unix.RawSockaddrInet4{Family: unix.AF_INET, Addr: ap.Addr().As4()}
|
||||
binary.BigEndian.PutUint16((*[2]byte)(unsafe.Pointer(&sa4.Port))[:], ap.Port())
|
||||
return unix.SizeofSockaddrInet4, nil
|
||||
}
|
||||
*sa = unix.RawSockaddrInet6{Family: unix.AF_INET6, Addr: ap.Addr().As16()}
|
||||
binary.BigEndian.PutUint16((*[2]byte)(unsafe.Pointer(&sa.Port))[:], ap.Port())
|
||||
return unix.SizeofSockaddrInet6, nil
|
||||
}
|
||||
|
||||
func (u *StdConn) LocalAddr() (netip.AddrPort, error) {
|
||||
@@ -198,8 +345,7 @@ type msghdrX struct {
|
||||
}
|
||||
|
||||
// ListenOut drains the socket with recvmsg_x, darwin's private batched recvmsg, so one syscall reads
|
||||
// up to recvBatch datagrams instead of one. Sends stay on sendto: xnu batches sendmsg_x through
|
||||
// the stack only on connected sockets, and on this unconnected one it loops sendit per message.
|
||||
// up to recvBatch datagrams instead of one.
|
||||
func (u *StdConn) ListenOut(r EncReader, flush func()) error {
|
||||
rc, err := u.UDPConn.SyscallConn()
|
||||
if err != nil {
|
||||
|
||||
@@ -0,0 +1,150 @@
|
||||
//go:build !e2e_testing
|
||||
|
||||
package udp
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// recvAll reads n datagrams from pc, or fails the test after a second without one.
|
||||
func recvAll(t *testing.T, pc net.PacketConn, n int) []string {
|
||||
t.Helper()
|
||||
var got []string
|
||||
buf := make([]byte, 64)
|
||||
for len(got) < n {
|
||||
require.NoError(t, pc.SetReadDeadline(time.Now().Add(time.Second)))
|
||||
l, _, err := pc.ReadFrom(buf)
|
||||
require.NoError(t, err, "after %d of %d datagrams", len(got), n)
|
||||
got = append(got, string(buf[:l]))
|
||||
}
|
||||
return got
|
||||
}
|
||||
|
||||
// A batch longer than sendBatch reaches each peer whole and in order through sendmsg_x, without falling
|
||||
// back to sendto: a run to one peer that spans two calls, then datagrams alternating between peers.
|
||||
func TestWriteBatchSendsEachToItsPeer(t *testing.T) {
|
||||
for _, tc := range []struct{ name, listen string }{
|
||||
{"v4", "127.0.0.1"},
|
||||
{"v6", "::1"},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.AddrPortFrom(netip.MustParseAddr(tc.listen), 0)})
|
||||
require.NoError(t, err)
|
||||
defer c.Close()
|
||||
|
||||
var peers [2]net.PacketConn
|
||||
var dsts [2]netip.AddrPort
|
||||
for i := range peers {
|
||||
peers[i], err = net.ListenPacket("udp", net.JoinHostPort(tc.listen, "0"))
|
||||
require.NoError(t, err)
|
||||
defer peers[i].Close()
|
||||
dsts[i] = netip.MustParseAddrPort(peers[i].LocalAddr().String())
|
||||
}
|
||||
|
||||
const total = sendBatch*2 + 5
|
||||
bufs := make([][]byte, total)
|
||||
addrs := make([]netip.AddrPort, total)
|
||||
var want [2][]string
|
||||
for i := range bufs {
|
||||
bufs[i] = fmt.Appendf(nil, "pkt-%03d", i)
|
||||
p := i % 2
|
||||
if i < sendBatch+6 {
|
||||
p = 0
|
||||
}
|
||||
addrs[i] = dsts[p]
|
||||
want[p] = append(want[p], string(bufs[i]))
|
||||
}
|
||||
|
||||
n, err := c.WriteBatch(bufs, addrs)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, total, n)
|
||||
assert.False(t, c.(*StdConn).noSendmsgX.Load(), "fell back to sendto")
|
||||
for i := range peers {
|
||||
assert.Equal(t, want[i], recvAll(t, peers[i], len(want[i])))
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Destinations that can't be sent to cost only their own packets: an IPv6 peer on an IPv4 socket is
|
||||
// skipped before the call, and a broadcast address without SO_BROADCAST is refused by the kernel
|
||||
// mid-batch. Neither stops the packets around it, delivers any twice, or turns sendmsg_x off.
|
||||
func TestWriteBatchSkipsUnsendableDestinations(t *testing.T) {
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0")})
|
||||
require.NoError(t, err)
|
||||
defer c.Close()
|
||||
|
||||
peer, err := net.ListenPacket("udp", "127.0.0.1:0")
|
||||
require.NoError(t, err)
|
||||
defer peer.Close()
|
||||
good := netip.MustParseAddrPort(peer.LocalAddr().String())
|
||||
bcast := netip.AddrPortFrom(netip.MustParseAddr("255.255.255.255"), good.Port())
|
||||
v6 := netip.MustParseAddrPort("[::1]:4242")
|
||||
|
||||
addrs := []netip.AddrPort{good, bcast, bcast, good, v6, good, bcast}
|
||||
bufs := make([][]byte, len(addrs))
|
||||
for i := range bufs {
|
||||
bufs[i] = fmt.Appendf(nil, "pkt-%d", i)
|
||||
}
|
||||
|
||||
n, err := c.WriteBatch(bufs, addrs)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, 3, n)
|
||||
assert.False(t, c.(*StdConn).noSendmsgX.Load(), "fell back to sendto")
|
||||
assert.Equal(t, []string{"pkt-0", "pkt-3", "pkt-5"}, recvAll(t, peer, 3))
|
||||
require.NoError(t, peer.SetReadDeadline(time.Now().Add(100*time.Millisecond)))
|
||||
_, _, err = peer.ReadFrom(make([]byte, 64))
|
||||
assert.Error(t, err, "a datagram arrived twice")
|
||||
}
|
||||
|
||||
// A datagram the kernel refuses as its own fault (EMSGSIZE here, as ENOBUFS would be under a full
|
||||
// interface queue) costs only itself, whether it fails after others in the same call (a short count) or
|
||||
// first (the errno alone): the rest of its run still arrives, in order, and sendmsg_x stays on.
|
||||
func TestWriteBatchLosesOnlyTheFailedDatagram(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
big int
|
||||
}{
|
||||
{"mid-call", 2},
|
||||
{"first", 0},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0")})
|
||||
require.NoError(t, err)
|
||||
defer c.Close()
|
||||
|
||||
peer, err := net.ListenPacket("udp", "127.0.0.1:0")
|
||||
require.NoError(t, err)
|
||||
defer peer.Close()
|
||||
dst := netip.MustParseAddrPort(peer.LocalAddr().String())
|
||||
|
||||
bufs := make([][]byte, 5)
|
||||
addrs := make([]netip.AddrPort, len(bufs))
|
||||
var want []string
|
||||
for i := range bufs {
|
||||
addrs[i] = dst
|
||||
if i == tc.big {
|
||||
// Past the 65535-byte IP datagram limit, so the kernel can only refuse it.
|
||||
bufs[i] = make([]byte, 70000)
|
||||
continue
|
||||
}
|
||||
bufs[i] = fmt.Appendf(nil, "pkt-%d", i)
|
||||
want = append(want, string(bufs[i]))
|
||||
}
|
||||
|
||||
n, err := c.WriteBatch(bufs, addrs)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, len(want), n)
|
||||
assert.False(t, c.(*StdConn).noSendmsgX.Load(), "fell back to sendto")
|
||||
assert.Equal(t, want, recvAll(t, peer, len(want)))
|
||||
})
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user