Files
shater/dns/transport/quic/packetconn_leak_test.go
T
omarandClaude Opus 5 0a6689b29e fix(quic,v2ray): close the sockets quic-go was never going to close
DialEarly with a packet conn the caller made sets a flag that means quic-go does
not own it: closing the transport only stops reading from the socket. Neither DNS
transport closed it. On the QUIC one it was closed on a failed handshake and
never on success, so every redial — idle timeout, retry error, engine reload —
left a UDP socket for the life of the process. On the HTTP/3 one the library
drives its own reconnects, so the leak compounds without anything in our code
looking wrong.

That is the same shape as v2rayquic's, where offerNew overwrote the raw conn on
every reconnect without closing the previous one. Both are now owned by a watcher
tied to the connection's own context, so the socket lives exactly as long as the
connection does.

This matters more than it did last week: the shipped resolvers are DoH, and DNS
is intercepted by default now, so the whole network's query stream rides this
path on a router with 512 MB.

The same upstream commit fixes both halves. We had taken the v2ray half and not
the DNS one — the third time this session a paired fix arrived half-applied, and
the first of those cost a day of debugging. These two files are now byte-identical
to upstream so a rebase cannot reopen it.

Also from that family: websocket and httpupgrade leaked their conn on failed
handshakes, and a QUIC stream's Close did not release a blocked write.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-26 15:39:59 +03:00

352 lines
9.3 KiB
Go

package quic
import (
"context"
"crypto/tls"
"net"
"net/http"
"net/url"
"sync"
"testing"
"time"
"github.com/sagernet/quic-go"
"github.com/sagernet/quic-go/http3"
sbTLS "github.com/sagernet/sing-box/common/tls"
C "github.com/sagernet/sing-box/constant"
"github.com/sagernet/sing-box/dns"
"github.com/sagernet/sing-box/dns/transport"
"github.com/sagernet/sing-box/option"
"github.com/sagernet/sing/common"
"github.com/sagernet/sing/common/logger"
M "github.com/sagernet/sing/common/metadata"
N "github.com/sagernet/sing/common/network"
mDNS "github.com/miekg/dns"
)
var _ N.Dialer = (*trackingDialer)(nil)
// These tests pin down who owns the UDP socket handed to quic-go.
//
// quic-go's Dial/DialEarly take a net.PacketConn but do NOT take ownership of
// it: quic.setupTransport() builds a Transport with createdConn=false, and
// Transport.Close() then only calls conn.SetReadDeadline(time.Now()) instead of
// conn.Close(). So every QUIC connection torn down here — idle timeout, a
// retryable error, an engine reload calling Reset() — used to strand the UDP
// socket that carried it for the rest of the process's life. On a router that
// resolves through DoQ/DoH3 for months that is an unbounded fd leak.
//
// Both tests reconnect once and assert the socket from the FIRST connection is
// actually closed. Without the `<-conn.Context().Done() -> rawConn.Close()`
// watchdogs in quic.go / http3.go they fail on that assertion.
type trackedConn struct {
net.Conn
closeOnce sync.Once
closed chan struct{}
}
func (c *trackedConn) Close() error {
c.closeOnce.Do(func() { close(c.closed) })
return c.Conn.Close()
}
// trackingDialer hands out real UDP sockets and remembers every one of them.
type trackingDialer struct {
access sync.Mutex
conns []*trackedConn
}
func (d *trackingDialer) DialContext(ctx context.Context, network string, destination M.Socksaddr) (net.Conn, error) {
conn, err := (&net.Dialer{}).DialContext(ctx, network, destination.String())
if err != nil {
return nil, err
}
tracked := &trackedConn{Conn: conn, closed: make(chan struct{})}
d.access.Lock()
d.conns = append(d.conns, tracked)
d.access.Unlock()
return tracked, nil
}
func (d *trackingDialer) ListenPacket(ctx context.Context, destination M.Socksaddr) (net.PacketConn, error) {
return net.ListenUDP("udp", nil)
}
func (d *trackingDialer) count() int {
d.access.Lock()
defer d.access.Unlock()
return len(d.conns)
}
func (d *trackingDialer) at(index int) *trackedConn {
d.access.Lock()
defer d.access.Unlock()
return d.conns[index]
}
func (d *trackingDialer) closeAll() {
d.access.Lock()
defer d.access.Unlock()
for _, conn := range d.conns {
conn.Close()
}
}
func requireClosed(t *testing.T, conn *trackedConn, what string) {
t.Helper()
select {
case <-conn.closed:
case <-time.After(5 * time.Second):
t.Fatalf("%s: the UDP socket of the retired QUIC connection was never closed — quic-go does not own it, we must", what)
}
}
func requireDialed(t *testing.T, dialer *trackingDialer, want int) {
t.Helper()
deadline := time.Now().Add(5 * time.Second)
for time.Now().Before(deadline) {
if dialer.count() >= want {
return
}
time.Sleep(10 * time.Millisecond)
}
t.Fatalf("expected at least %d dial(s), got %d", want, dialer.count())
}
func testServerTLSConfig(t *testing.T, nextProtos []string) *tls.Config {
t.Helper()
certificate, err := sbTLS.GenerateKeyPair(nil, nil, nil, "localhost")
if err != nil {
t.Fatal(err)
}
return &tls.Config{
Certificates: []tls.Certificate{*certificate},
NextProtos: nextProtos,
MinVersion: tls.VersionTLS13,
}
}
func testClientTLSConfig(t *testing.T, nextProtos []string) sbTLS.Config {
t.Helper()
config, err := sbTLS.NewClient(context.Background(), logger.NOP(), "localhost", option.OutboundTLSOptions{
Enabled: true,
Insecure: true,
ServerName: "localhost",
})
if err != nil {
t.Fatal(err)
}
config.SetNextProtos(nextProtos)
return config
}
// startDoQServer serves a minimal DoQ responder and returns its address.
func startDoQServer(t *testing.T) M.Socksaddr {
t.Helper()
listener, err := quic.ListenAddr("127.0.0.1:0", testServerTLSConfig(t, []string{"doq"}), nil)
if err != nil {
t.Fatal(err)
}
ctx, cancel := context.WithCancel(context.Background())
t.Cleanup(func() {
cancel()
listener.Close()
})
go func() {
for {
conn, acceptErr := listener.Accept(ctx)
if acceptErr != nil {
return
}
go func(conn *quic.Conn) {
for {
stream, streamErr := conn.AcceptStream(ctx)
if streamErr != nil {
return
}
go func(stream *quic.Stream) {
defer stream.Close()
request, readErr := transport.ReadMessage(stream)
if readErr != nil {
return
}
response := new(mDNS.Msg)
response.SetReply(request)
transport.WriteMessage(stream, 0, response)
}(stream)
}
}(conn)
}
}()
return M.ParseSocksaddr(listener.Addr().String())
}
func testQuery() *mDNS.Msg {
message := new(mDNS.Msg)
message.SetQuestion("example.com.", mDNS.TypeA)
return message
}
func TestQUICTransportClosesPacketConnOnReconnect(t *testing.T) {
t.Parallel()
serverAddr := startDoQServer(t)
dialer := &trackingDialer{}
t.Cleanup(dialer.closeAll)
dnsTransport := &Transport{
TransportAdapter: dns.NewTransportAdapter(C.DNSTypeQUIC, "test-doq", nil),
dialer: dialer,
serverAddr: serverAddr,
tlsConfig: testClientTLSConfig(t, []string{"doq"}),
connection: transport.NewConnPool(transport.ConnPoolOptions[*quic.Conn]{
Mode: transport.ConnPoolSingle,
IsAlive: func(conn *quic.Conn) bool {
return conn != nil && !common.Done(conn.Context())
},
Close: func(conn *quic.Conn, _ error) {
conn.CloseWithError(0, "")
},
}),
}
t.Cleanup(func() { dnsTransport.Close() })
ctx, cancel := context.WithTimeout(context.Background(), 15*time.Second)
defer cancel()
if _, err := dnsTransport.Exchange(ctx, testQuery()); err != nil {
t.Fatal("first exchange: ", err)
}
requireDialed(t, dialer, 1)
first := dialer.at(0)
// Retire the connection the way a retryable error or an engine reload does.
dnsTransport.Reset()
requireClosed(t, first, "Reset()")
// The reconnect must still work, on a fresh socket.
if _, err := dnsTransport.Exchange(ctx, testQuery()); err != nil {
t.Fatal("second exchange: ", err)
}
requireDialed(t, dialer, 2)
second := dialer.at(1)
if second == first {
t.Fatal("expected a new UDP socket for the reconnect")
}
if err := dnsTransport.Close(); err != nil {
t.Fatal(err)
}
requireClosed(t, second, "Close()")
}
func TestHTTP3TransportClosesPacketConnOnReconnect(t *testing.T) {
t.Parallel()
mux := http.NewServeMux()
mux.HandleFunc("/dns-query", func(writer http.ResponseWriter, request *http.Request) {
message, err := readRequestMessage(request)
if err != nil {
writer.WriteHeader(http.StatusBadRequest)
return
}
response := new(mDNS.Msg)
response.SetReply(message)
rawResponse, err := response.Pack()
if err != nil {
writer.WriteHeader(http.StatusInternalServerError)
return
}
writer.Header().Set("Content-Type", transport.MimeType)
writer.Write(rawResponse)
})
listener, err := quic.ListenAddrEarly("127.0.0.1:0", testServerTLSConfig(t, []string{http3.NextProtoH3}), nil)
if err != nil {
t.Fatal(err)
}
server := &http3.Server{Handler: mux}
go server.ServeListener(listener)
t.Cleanup(func() {
server.Close()
listener.Close()
})
serverAddr := M.ParseSocksaddr(listener.Addr().String())
dialer := &trackingDialer{}
t.Cleanup(dialer.closeAll)
stdConfig := &tls.Config{
InsecureSkipVerify: true,
ServerName: "localhost",
NextProtos: []string{http3.NextProtoH3},
MinVersion: tls.VersionTLS13,
}
dnsTransport := &HTTP3Transport{
TransportAdapter: dns.NewTransportAdapter(C.DNSTypeHTTP3, "test-doh3", nil),
logger: logger.NOP(),
dialer: dialer,
destination: &url.URL{Scheme: "https", Host: "localhost", Path: "/dns-query"},
headers: http.Header{},
serverAddr: serverAddr,
tlsConfig: stdConfig,
}
dnsTransport.transport = dnsTransport.newTransport()
t.Cleanup(func() { dnsTransport.Close() })
ctx, cancel := context.WithTimeout(context.Background(), 15*time.Second)
defer cancel()
if _, err = dnsTransport.Exchange(ctx, testQuery()); err != nil {
t.Fatal("first exchange: ", err)
}
requireDialed(t, dialer, 1)
first := dialer.at(0)
dnsTransport.Reset()
requireClosed(t, first, "Reset()")
if _, err = dnsTransport.Exchange(ctx, testQuery()); err != nil {
t.Fatal("second exchange: ", err)
}
requireDialed(t, dialer, 2)
second := dialer.at(1)
if second == first {
t.Fatal("expected a new UDP socket for the reconnect")
}
if err = dnsTransport.Close(); err != nil {
t.Fatal(err)
}
requireClosed(t, second, "Close()")
}
func readRequestMessage(request *http.Request) (*mDNS.Msg, error) {
defer request.Body.Close()
rawMessage := make([]byte, 4096)
n, err := readFull(request.Body, rawMessage)
if err != nil {
return nil, err
}
var message mDNS.Msg
err = message.Unpack(rawMessage[:n])
if err != nil {
return nil, err
}
return &message, nil
}
func readFull(reader interface{ Read([]byte) (int, error) }, buffer []byte) (int, error) {
var total int
for total < len(buffer) {
n, err := reader.Read(buffer[total:])
total += n
if err != nil {
if total > 0 {
return total, nil
}
return total, err
}
}
return total, nil
}