nebula/lighthouse_test.go

package nebula

import (
	"bytes"
	"encoding/binary"
	"errors"
	"fmt"
	"net/netip"
	"sync"
	"testing"
	"time"

	"github.com/gaissmai/bart"
	"github.com/slackhq/nebula/cert"
	"github.com/slackhq/nebula/config"
	"github.com/slackhq/nebula/header"
	"github.com/slackhq/nebula/test"
	"github.com/slackhq/nebula/udp"
	"github.com/stretchr/testify/assert"
	"github.com/stretchr/testify/require"
	"go.yaml.in/yaml/v3"
)

func TestOldIPv4Only(t *testing.T) {
	// This test ensures our new ipv6 enabled LH protobuf IpAndPorts works with the old style to enable backwards compatibility
	b := []byte{8, 129, 130, 132, 80, 16, 10}
	var m V4AddrPort
	err := m.Unmarshal(b)
	require.NoError(t, err)
	ip := netip.MustParseAddr("10.1.1.1")
	bp := ip.As4()
	assert.Equal(t, binary.BigEndian.Uint32(bp[:]), m.GetAddr())
}

func testCertState(networks ...netip.Prefix) *CertState {
	cs := &CertState{
		myVpnNetworks:      networks,
		myVpnNetworksTable: new(bart.Lite),
		myVpnAddrs:         make([]netip.Addr, 0, len(networks)),
		myVpnAddrsTable:    new(bart.Lite),
	}

	for _, n := range networks {
		cs.myVpnNetworksTable.Insert(n)
		cs.myVpnAddrs = append(cs.myVpnAddrs, n.Addr())
		cs.myVpnAddrsTable.Insert(netip.PrefixFrom(n.Addr(), n.Addr().BitLen()))
	}

	return cs
}

func Test_lhStaticMapping(t *testing.T) {
	l := test.NewLogger()
	myVpnNet := netip.MustParsePrefix("10.128.0.1/16")
	cs := testCertState(myVpnNet)
	lh1 := "10.128.0.2"

	c := config.NewC(l)
	c.Settings["lighthouse"] = map[string]any{"hosts": []any{lh1}}
	c.Settings["static_host_map"] = map[string]any{lh1: []any{"1.1.1.1:4242"}}
	_, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
	require.NoError(t, err)

	lh2 := "10.128.0.3"
	c = config.NewC(l)
	c.Settings["lighthouse"] = map[string]any{"hosts": []any{lh1, lh2}}
	c.Settings["static_host_map"] = map[string]any{lh1: []any{"100.1.1.1:4242"}}
	_, err = NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
	require.EqualError(t, err, "lighthouse 10.128.0.3 does not have a static_host_map entry")
}

func TestReloadLighthouseInterval(t *testing.T) {
	l := test.NewLogger()
	myVpnNet := netip.MustParsePrefix("10.128.0.1/16")
	cs := testCertState(myVpnNet)
	lh1 := "10.128.0.2"

	c := config.NewC(l)
	c.Settings["lighthouse"] = map[string]any{
		"hosts":    []any{lh1},
		"interval": "1s",
	}

	c.Settings["static_host_map"] = map[string]any{lh1: []any{"1.1.1.1:4242"}}
	lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
	require.NoError(t, err)
	lh.ifce = &mockEncWriter{}

	// The first one routine is kicked off by main.go currently, lets make sure that one dies
	require.NoError(t, c.ReloadConfigString("lighthouse:\n  interval: 5").Err)
	assert.Equal(t, int64(5), lh.interval.Load())

	// Subsequent calls are killed off by the LightHouse.Reload function
	require.NoError(t, c.ReloadConfigString("lighthouse:\n  interval: 10").Err)
	assert.Equal(t, int64(10), lh.interval.Load())

	// If this completes then nothing is stealing our reload routine
	require.NoError(t, c.ReloadConfigString("lighthouse:\n  interval: 11").Err)
	assert.Equal(t, int64(11), lh.interval.Load())
}

func BenchmarkLighthouseHandleRequest(b *testing.B) {
	l := test.NewLogger()
	myVpnNet := netip.MustParsePrefix("10.128.0.1/0")
	cs := testCertState(myVpnNet)

	c := config.NewC(l)
	lh, err := NewLightHouseFromConfig(b.Context(), l, c, cs, nil, nil)
	require.NoError(b, err)

	hAddr := netip.MustParseAddrPort("4.5.6.7:12345")
	hAddr2 := netip.MustParseAddrPort("4.5.6.7:12346")

	vpnIp3 := netip.MustParseAddr("0.0.0.3")
	lh.addrMap[vpnIp3] = NewRemoteList([]netip.Addr{vpnIp3}, nil)
	lh.addrMap[vpnIp3].unlockedSetV4(
		vpnIp3,
		vpnIp3,
		[]*V4AddrPort{
			netAddrToProtoV4AddrPort(hAddr.Addr(), hAddr.Port()),
			netAddrToProtoV4AddrPort(hAddr2.Addr(), hAddr2.Port()),
		},
		func(netip.Addr, *V4AddrPort) bool { return true },
	)

	rAddr := netip.MustParseAddrPort("1.2.2.3:12345")
	rAddr2 := netip.MustParseAddrPort("1.2.2.3:12346")
	vpnIp2 := netip.MustParseAddr("0.0.0.3")
	lh.addrMap[vpnIp2] = NewRemoteList([]netip.Addr{vpnIp2}, nil)
	lh.addrMap[vpnIp2].unlockedSetV4(
		vpnIp3,
		vpnIp3,
		[]*V4AddrPort{
			netAddrToProtoV4AddrPort(rAddr.Addr(), rAddr.Port()),
			netAddrToProtoV4AddrPort(rAddr2.Addr(), rAddr2.Port()),
		},
		func(netip.Addr, *V4AddrPort) bool { return true },
	)

	mw := &mockEncWriter{}

	hi := []netip.Addr{vpnIp2}
	b.Run("notfound", func(b *testing.B) {
		lhh := lh.NewRequestHandler()
		req := &NebulaMeta{
			Type: NebulaMeta_HostQuery,
			Details: &NebulaMetaDetails{
				OldVpnAddr:  4,
				V4AddrPorts: nil,
			},
		}
		p, err := req.Marshal()
		require.NoError(b, err)
		for n := 0; n < b.N; n++ {
			lhh.HandleRequest(rAddr, hi, p, mw)
		}
	})
	b.Run("found", func(b *testing.B) {
		lhh := lh.NewRequestHandler()
		req := &NebulaMeta{
			Type: NebulaMeta_HostQuery,
			Details: &NebulaMetaDetails{
				OldVpnAddr:  3,
				V4AddrPorts: nil,
			},
		}
		p, err := req.Marshal()
		require.NoError(b, err)

		for n := 0; n < b.N; n++ {
			lhh.HandleRequest(rAddr, hi, p, mw)
		}
	})
}

func TestLighthouse_Memory(t *testing.T) {
	l := test.NewLogger()

	myUdpAddr0 := netip.MustParseAddrPort("10.0.0.2:4242")
	myUdpAddr1 := netip.MustParseAddrPort("192.168.0.2:4242")
	myUdpAddr2 := netip.MustParseAddrPort("172.16.0.2:4242")
	myUdpAddr3 := netip.MustParseAddrPort("100.152.0.2:4242")
	myUdpAddr4 := netip.MustParseAddrPort("24.15.0.2:4242")
	myUdpAddr5 := netip.MustParseAddrPort("192.168.0.2:4243")
	myUdpAddr6 := netip.MustParseAddrPort("192.168.0.2:4244")
	myUdpAddr7 := netip.MustParseAddrPort("192.168.0.2:4245")
	myUdpAddr8 := netip.MustParseAddrPort("192.168.0.2:4246")
	myUdpAddr9 := netip.MustParseAddrPort("192.168.0.2:4247")
	myUdpAddr10 := netip.MustParseAddrPort("192.168.0.2:4248")
	myUdpAddr11 := netip.MustParseAddrPort("192.168.0.2:4249")
	myVpnIp := netip.MustParseAddr("10.128.0.2")

	theirUdpAddr0 := netip.MustParseAddrPort("10.0.0.3:4242")
	theirUdpAddr1 := netip.MustParseAddrPort("192.168.0.3:4242")
	theirUdpAddr2 := netip.MustParseAddrPort("172.16.0.3:4242")
	theirUdpAddr3 := netip.MustParseAddrPort("100.152.0.3:4242")
	theirUdpAddr4 := netip.MustParseAddrPort("24.15.0.3:4242")
	theirVpnIp := netip.MustParseAddr("10.128.0.3")

	c := config.NewC(l)
	c.Settings["lighthouse"] = map[string]any{"am_lighthouse": true}
	c.Settings["listen"] = map[string]any{"port": 4242}

	myVpnNet := netip.MustParsePrefix("10.128.0.1/24")
	cs := testCertState(myVpnNet)
	lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
	lh.ifce = &mockEncWriter{}
	require.NoError(t, err)
	lhh := lh.NewRequestHandler()

	// Test that my first update responds with just that
	newLHHostUpdate(myUdpAddr0, myVpnIp, []netip.AddrPort{myUdpAddr1, myUdpAddr2}, lhh)
	r := newLHHostRequest(myUdpAddr0, myVpnIp, myVpnIp, lhh)
	assertIp4InArray(t, r.msg.Details.V4AddrPorts, myUdpAddr1, myUdpAddr2)

	// Ensure we don't accumulate addresses
	newLHHostUpdate(myUdpAddr0, myVpnIp, []netip.AddrPort{myUdpAddr3}, lhh)
	r = newLHHostRequest(myUdpAddr0, myVpnIp, myVpnIp, lhh)
	assertIp4InArray(t, r.msg.Details.V4AddrPorts, myUdpAddr3)

	// Grow it back to 2
	newLHHostUpdate(myUdpAddr0, myVpnIp, []netip.AddrPort{myUdpAddr1, myUdpAddr4}, lhh)
	r = newLHHostRequest(myUdpAddr0, myVpnIp, myVpnIp, lhh)
	assertIp4InArray(t, r.msg.Details.V4AddrPorts, myUdpAddr1, myUdpAddr4)

	// Update a different host and ask about it
	newLHHostUpdate(theirUdpAddr0, theirVpnIp, []netip.AddrPort{theirUdpAddr1, theirUdpAddr2, theirUdpAddr3, theirUdpAddr4}, lhh)
	r = newLHHostRequest(theirUdpAddr0, theirVpnIp, theirVpnIp, lhh)
	assertIp4InArray(t, r.msg.Details.V4AddrPorts, theirUdpAddr1, theirUdpAddr2, theirUdpAddr3, theirUdpAddr4)

	// Have both hosts ask about the other
	r = newLHHostRequest(theirUdpAddr0, theirVpnIp, myVpnIp, lhh)
	assertIp4InArray(t, r.msg.Details.V4AddrPorts, myUdpAddr1, myUdpAddr4)

	r = newLHHostRequest(myUdpAddr0, myVpnIp, theirVpnIp, lhh)
	assertIp4InArray(t, r.msg.Details.V4AddrPorts, theirUdpAddr1, theirUdpAddr2, theirUdpAddr3, theirUdpAddr4)

	// Make sure we didn't get changed
	r = newLHHostRequest(myUdpAddr0, myVpnIp, myVpnIp, lhh)
	assertIp4InArray(t, r.msg.Details.V4AddrPorts, myUdpAddr1, myUdpAddr4)

	// Ensure proper ordering and limiting
	// Send 12 addrs, get 10 back, the last 2 removed, allowing the duplicate to remain (clients dedupe)
	newLHHostUpdate(
		myUdpAddr0,
		myVpnIp,
		[]netip.AddrPort{
			myUdpAddr1,
			myUdpAddr2,
			myUdpAddr3,
			myUdpAddr4,
			myUdpAddr5,
			myUdpAddr5, //Duplicated on purpose
			myUdpAddr6,
			myUdpAddr7,
			myUdpAddr8,
			myUdpAddr9,
			myUdpAddr10,
			myUdpAddr11, // This should get cut
		}, lhh)

	r = newLHHostRequest(myUdpAddr0, myVpnIp, myVpnIp, lhh)
	assertIp4InArray(
		t,
		r.msg.Details.V4AddrPorts,
		myUdpAddr1, myUdpAddr2, myUdpAddr3, myUdpAddr4, myUdpAddr5, myUdpAddr5, myUdpAddr6, myUdpAddr7, myUdpAddr8, myUdpAddr9,
	)

	// Make sure we won't add ips in our vpn network
	bad1 := netip.MustParseAddrPort("10.128.0.99:4242")
	bad2 := netip.MustParseAddrPort("10.128.0.100:4242")
	good := netip.MustParseAddrPort("1.128.0.99:4242")
	newLHHostUpdate(myUdpAddr0, myVpnIp, []netip.AddrPort{bad1, bad2, good}, lhh)
	r = newLHHostRequest(myUdpAddr0, myVpnIp, myVpnIp, lhh)
	assertIp4InArray(t, r.msg.Details.V4AddrPorts, good)
}

func TestLighthouse_reload(t *testing.T) {
	l := test.NewLogger()
	c := config.NewC(l)
	c.Settings["lighthouse"] = map[string]any{"am_lighthouse": true}
	c.Settings["listen"] = map[string]any{"port": 4242}

	myVpnNet := netip.MustParsePrefix("10.128.0.1/24")
	cs := testCertState(myVpnNet)

	lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
	require.NoError(t, err)

	nc := map[string]any{
		"static_host_map": map[string]any{
			"10.128.0.2": []any{"1.1.1.1:4242"},
		},
	}
	rc, err := yaml.Marshal(nc)
	require.NoError(t, err)
	c.ReloadConfigString(string(rc))

	err = lh.reload(c, false, nil)
	require.NoError(t, err)
}

// TestLighthouse_reloadStaticHostMap verifies that reloading static_host_map applies the new
// config rather than appending to it. See issue #718.
func TestLighthouse_reloadStaticHostMap(t *testing.T) {
	l := test.NewLogger()
	c := config.NewC(l)
	c.Settings["lighthouse"] = map[string]any{"am_lighthouse": true}
	c.Settings["listen"] = map[string]any{"port": 4242}
	c.Settings["static_host_map"] = map[string]any{
		"10.128.0.2": []any{"1.1.1.1:4242"},
	}

	myVpnNet := netip.MustParsePrefix("10.128.0.1/24")
	cs := testCertState(myVpnNet)

	lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
	require.NoError(t, err)

	staticHost := netip.MustParseAddr("10.128.0.2")
	otherHost := netip.MustParseAddr("10.128.0.3")

	// Capture the RemoteList pointer up front; an in-flight handshake would hold the same one
	// on hostinfo.remotes, so it must reflect every reload below.
	pinned := lh.Query(staticHost)
	require.NotNil(t, pinned)
	assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("1.1.1.1:4242")}, pinned.CopyAddrs([]netip.Prefix{}))

	// Replace the remote address. The new address should be the only entry.
	nc := map[string]any{
		"static_host_map": map[string]any{
			"10.128.0.2": []any{"2.2.2.2:4242"},
		},
	}
	rc, err := yaml.Marshal(nc)
	require.NoError(t, err)
	require.NoError(t, c.ReloadConfigString(string(rc)).Err)

	rl := lh.Query(staticHost)
	require.NotNil(t, rl)
	assert.Same(t, pinned, rl, "RemoteList pointer must stay stable so in-flight handshakes pick up the change")
	assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("2.2.2.2:4242")}, rl.CopyAddrs([]netip.Prefix{}))

	// Reload back to the original IP. Mirrors the round-trip in issue #718 step 6-8 where
	// the buggy reload produced [1.1.1.1, 2.2.2.2, 1.1.1.1] instead of [1.1.1.1].
	nc = map[string]any{
		"static_host_map": map[string]any{
			"10.128.0.2": []any{"1.1.1.1:4242"},
		},
	}
	rc, err = yaml.Marshal(nc)
	require.NoError(t, err)
	require.NoError(t, c.ReloadConfigString(string(rc)).Err)

	rl = lh.Query(staticHost)
	require.NotNil(t, rl)
	assert.Same(t, pinned, rl)
	assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("1.1.1.1:4242")}, rl.CopyAddrs([]netip.Prefix{}))

	// Reload with the same config. An unchanged entry must not duplicate.
	require.NoError(t, c.ReloadConfigString(string(rc)).Err)

	rl = lh.Query(staticHost)
	require.NotNil(t, rl)
	assert.Same(t, pinned, rl)
	assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("1.1.1.1:4242")}, rl.CopyAddrs([]netip.Prefix{}))

	// Switch back to 2.2.2.2 so the rest of the test continues against a known address.
	nc = map[string]any{
		"static_host_map": map[string]any{
			"10.128.0.2": []any{"2.2.2.2:4242"},
		},
	}
	rc, err = yaml.Marshal(nc)
	require.NoError(t, err)
	require.NoError(t, c.ReloadConfigString(string(rc)).Err)

	// Add a second host alongside the first. Both should be present, neither duplicated.
	nc = map[string]any{
		"static_host_map": map[string]any{
			"10.128.0.2": []any{"2.2.2.2:4242"},
			"10.128.0.3": []any{"3.3.3.3:4242"},
		},
	}
	rc, err = yaml.Marshal(nc)
	require.NoError(t, err)
	require.NoError(t, c.ReloadConfigString(string(rc)).Err)

	rl = lh.Query(staticHost)
	require.NotNil(t, rl)
	assert.Same(t, pinned, rl, "adding a sibling entry must not displace the existing RemoteList")
	assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("2.2.2.2:4242")}, rl.CopyAddrs([]netip.Prefix{}))

	rl = lh.Query(otherHost)
	require.NotNil(t, rl)
	assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("3.3.3.3:4242")}, rl.CopyAddrs([]netip.Prefix{}))

	// Drop the first host entirely. The vpnAddr is no longer marked static, our owner
	// contribution is cleared, but the addrMap entry stays in place so non-static cache
	// data (from lighthouse queries) on the same RemoteList isn't lost. In-flight handshakes
	// that already had the pointer see an empty address list rather than retrying stale ones.
	nc = map[string]any{
		"static_host_map": map[string]any{
			"10.128.0.3": []any{"3.3.3.3:4242"},
		},
	}
	rc, err = yaml.Marshal(nc)
	require.NoError(t, err)
	require.NoError(t, c.ReloadConfigString(string(rc)).Err)

	_, isStatic := lh.GetStaticHostList()[staticHost]
	assert.False(t, isStatic)

	rl = lh.Query(staticHost)
	require.NotNil(t, rl)
	assert.Same(t, pinned, rl)
	assert.Empty(t, rl.CopyAddrs([]netip.Prefix{}))

	rl = lh.Query(otherHost)
	require.NotNil(t, rl)
	assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("3.3.3.3:4242")}, rl.CopyAddrs([]netip.Prefix{}))
}

// sendLHHostRequest delivers a HostQuery to lhh and hands back the writer that
// captured what it emitted. Pass a nil filter to see every message.
func sendLHHostRequest(fromAddr netip.AddrPort, myVpnIp, queryVpnIp netip.Addr, lhh *LightHouseHandler, filter *NebulaMeta_MessageType) *testEncWriter {
	req := &NebulaMeta{
		Type:    NebulaMeta_HostQuery,
		Details: &NebulaMetaDetails{},
	}

	if queryVpnIp.Is4() {
		bip := queryVpnIp.As4()
		req.Details.OldVpnAddr = binary.BigEndian.Uint32(bip[:])
	} else {
		req.Details.VpnAddr = netAddrToProtoAddr(queryVpnIp)
	}

	b, err := req.Marshal()
	if err != nil {
		panic(err)
	}

	w := &testEncWriter{metaFilter: filter}
	lhh.HandleRequest(fromAddr, []netip.Addr{myVpnIp}, b, w)
	return w
}

func newLHHostRequest(fromAddr netip.AddrPort, myVpnIp, queryVpnIp netip.Addr, lhh *LightHouseHandler) testLhReply {
	filter := NebulaMeta_HostQueryReply
	return sendLHHostRequest(fromAddr, myVpnIp, queryVpnIp, lhh, &filter).lastReply
}

func TestLighthouse_IgnoresHostQueryForItself(t *testing.T) {
	// Validate that we don't answer host queries for our own address.
	l := test.NewLogger()

	myVpnNet := netip.MustParsePrefix("10.128.0.1/24")
	myVpnIp := myVpnNet.Addr()

	c := config.NewC(l)
	c.Settings["lighthouse"] = map[string]any{"am_lighthouse": true}
	c.Settings["listen"] = map[string]any{"port": 4242}
	// Add a static_host_map entry for ourselves, so our address
	// is in the addrMap.
	c.Settings["static_host_map"] = map[string]any{
		myVpnIp.String(): []any{"192.168.100.1:4242"},
	}

	lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(myVpnNet), nil, nil)
	require.NoError(t, err)
	lh.ifce = &mockEncWriter{}
	lhh := lh.NewRequestHandler()

	peerVpnIp := netip.MustParseAddr("10.128.0.2")
	peerUdpAddr := netip.MustParseAddrPort("10.0.0.2:4242")
	otherVpnIp := netip.MustParseAddr("10.128.0.3")
	otherUdpAddr := netip.MustParseAddrPort("10.0.0.3:4242")

	newLHHostUpdate(peerUdpAddr, peerVpnIp, []netip.AddrPort{peerUdpAddr}, lhh)
	newLHHostUpdate(otherUdpAddr, otherVpnIp, []netip.AddrPort{otherUdpAddr}, lhh)

	// Control: a query about a real peer is still answered, and still ends with
	// the punch notification aimed at the host that was asked about.
	w := sendLHHostRequest(peerUdpAddr, peerVpnIp, otherVpnIp, lhh, nil)
	require.NotNil(t, w.lastReply.msg)
	assert.Equal(t, NebulaMeta_HostPunchNotification, w.lastReply.msg.Type)
	assert.Equal(t, otherVpnIp, w.lastReply.vpnIp)

	// Now validate that we don't send to ourselves.
	found, _, err := lh.queryAndPrepMessage(myVpnIp, func(*cache) (int, error) { return 0, nil })
	require.NoError(t, err)
	require.True(t, found, "the lighthouse should hold a cache entry for its own address")

	w = sendLHHostRequest(peerUdpAddr, peerVpnIp, myVpnIp, lhh, nil)
	assert.Nil(t, w.lastReply.msg, "a query about our own address must produce no reply and no punch notification")
}

func newLHHostUpdate(fromAddr netip.AddrPort, vpnIp netip.Addr, addrs []netip.AddrPort, lhh *LightHouseHandler) {
	req := &NebulaMeta{
		Type:    NebulaMeta_HostUpdateNotification,
		Details: &NebulaMetaDetails{},
	}

	if vpnIp.Is4() {
		bip := vpnIp.As4()
		req.Details.OldVpnAddr = binary.BigEndian.Uint32(bip[:])
	} else {
		req.Details.VpnAddr = netAddrToProtoAddr(vpnIp)
	}

	for _, v := range addrs {
		if v.Addr().Is4() {
			req.Details.V4AddrPorts = append(req.Details.V4AddrPorts, netAddrToProtoV4AddrPort(v.Addr(), v.Port()))
		} else {
			req.Details.V6AddrPorts = append(req.Details.V6AddrPorts, netAddrToProtoV6AddrPort(v.Addr(), v.Port()))
		}
	}

	b, err := req.Marshal()
	if err != nil {
		panic(err)
	}

	w := &testEncWriter{}
	lhh.HandleRequest(fromAddr, []netip.Addr{vpnIp}, b, w)
}

type testLhReply struct {
	nebType    header.MessageType
	nebSubType header.MessageSubType
	vpnIp      netip.Addr
	msg        *NebulaMeta
}

type testEncWriter struct {
	lastReply       testLhReply
	metaFilter      *NebulaMeta_MessageType
	protocolVersion cert.Version
}

func (tw *testEncWriter) SendVia(via *HostInfo, relay *Relay, ad, nb, out []byte, nocopy bool, q int) {
}
func (tw *testEncWriter) Handshake(vpnIp netip.Addr) {
}

func (tw *testEncWriter) SendMessageToHostInfo(t header.MessageType, st header.MessageSubType, hostinfo *HostInfo, p, _, _ []byte) {
	msg := &NebulaMeta{}
	err := msg.Unmarshal(p)
	if tw.metaFilter == nil || msg.Type == *tw.metaFilter {
		tw.lastReply = testLhReply{
			nebType:    t,
			nebSubType: st,
			vpnIp:      hostinfo.vpnAddrs[0],
			msg:        msg,
		}
	}

	if err != nil {
		panic(err)
	}
}

func (tw *testEncWriter) SendMessageToVpnAddr(t header.MessageType, st header.MessageSubType, vpnIp netip.Addr, p, _, _ []byte) {
	msg := &NebulaMeta{}
	err := msg.Unmarshal(p)
	if tw.metaFilter == nil || msg.Type == *tw.metaFilter {
		tw.lastReply = testLhReply{
			nebType:    t,
			nebSubType: st,
			vpnIp:      vpnIp,
			msg:        msg,
		}
	}

	if err != nil {
		panic(err)
	}
}

func (tw *testEncWriter) GetHostInfo(vpnIp netip.Addr) *HostInfo {
	return nil
}

func (tw *testEncWriter) GetCertState() *CertState {
	return &CertState{initiatingVersion: tw.protocolVersion}
}

// assertIp4InArray asserts every address in want is at the same position in have and that the lengths match
func assertIp4InArray(t *testing.T, have []*V4AddrPort, want ...netip.AddrPort) {
	if !assert.Len(t, have, len(want)) {
		return
	}

	for k, w := range want {
		h := protoV4AddrPortToNetAddrPort(have[k])
		if !(h == w) {
			assert.Fail(t, fmt.Sprintf("Response did not contain: %v at %v, found %v", w, k, h))
		}
	}
}

func Test_findNetworkUnion(t *testing.T) {
	var out netip.Addr
	var ok bool

	tenDot := netip.MustParsePrefix("10.0.0.0/8")
	oneSevenTwo := netip.MustParsePrefix("172.16.0.0/16")
	fe80 := netip.MustParsePrefix("fe80::/8")
	fc00 := netip.MustParsePrefix("fc00::/7")

	a1 := netip.MustParseAddr("10.0.0.1")
	afe81 := netip.MustParseAddr("fe80::1")

	//simple
	out, ok = findNetworkUnion([]netip.Prefix{tenDot}, []netip.Addr{a1})
	assert.True(t, ok)
	assert.Equal(t, out, a1)

	//mixed lengths
	out, ok = findNetworkUnion([]netip.Prefix{tenDot}, []netip.Addr{a1, afe81})
	assert.True(t, ok)
	assert.Equal(t, out, a1)
	out, ok = findNetworkUnion([]netip.Prefix{tenDot, oneSevenTwo}, []netip.Addr{a1})
	assert.True(t, ok)
	assert.Equal(t, out, a1)

	//mixed family
	out, ok = findNetworkUnion([]netip.Prefix{tenDot, oneSevenTwo, fe80}, []netip.Addr{a1})
	assert.True(t, ok)
	assert.Equal(t, out, a1)
	out, ok = findNetworkUnion([]netip.Prefix{tenDot, oneSevenTwo, fe80}, []netip.Addr{a1, afe81})
	assert.True(t, ok)
	assert.Equal(t, out, a1)

	//ordering
	out, ok = findNetworkUnion([]netip.Prefix{tenDot, oneSevenTwo, fe80}, []netip.Addr{afe81, a1})
	assert.True(t, ok)
	assert.Equal(t, out, a1)
	out, ok = findNetworkUnion([]netip.Prefix{fe80, tenDot, oneSevenTwo}, []netip.Addr{afe81, a1})
	assert.True(t, ok)
	assert.Equal(t, out, afe81)

	//some mismatches
	out, ok = findNetworkUnion([]netip.Prefix{tenDot, oneSevenTwo, fe80}, []netip.Addr{afe81})
	assert.True(t, ok)
	assert.Equal(t, out, afe81)
	out, ok = findNetworkUnion([]netip.Prefix{oneSevenTwo, fe80}, []netip.Addr{a1, afe81})
	assert.True(t, ok)
	assert.Equal(t, out, afe81)

	//falsey cases
	out, ok = findNetworkUnion([]netip.Prefix{oneSevenTwo, fe80}, []netip.Addr{a1})
	assert.False(t, ok)
	out, ok = findNetworkUnion([]netip.Prefix{fc00, fe80}, []netip.Addr{a1})
	assert.False(t, ok)
	out, ok = findNetworkUnion([]netip.Prefix{oneSevenTwo, fc00}, []netip.Addr{a1, afe81})
	assert.False(t, ok)
	out, ok = findNetworkUnion([]netip.Prefix{fc00}, []netip.Addr{a1, afe81})
	assert.False(t, ok)
}

func TestLighthouse_Dont_Delete_Static_Hosts(t *testing.T) {
	l := test.NewLogger()

	myUdpAddr2 := netip.MustParseAddrPort("1.2.3.4:4242")

	testSameHostNotStatic := netip.MustParseAddr("10.128.0.41")
	testStaticHost := netip.MustParseAddr("10.128.0.42")
	//myVpnIp := netip.MustParseAddr("10.128.0.2")

	c := config.NewC(l)
	lh1 := "10.128.0.2"
	c.Settings["lighthouse"] = map[string]any{
		"hosts":    []any{lh1},
		"interval": "1s",
	}

	c.Settings["listen"] = map[string]any{"port": 4242}
	c.Settings["static_host_map"] = map[string]any{
		lh1:           []any{"1.1.1.1:4242"},
		"10.128.0.42": []any{"1.2.3.4:4242"},
	}

	myVpnNet := netip.MustParsePrefix("10.128.0.1/24")
	cs := testCertState(myVpnNet)
	lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
	require.NoError(t, err)
	lh.ifce = &mockEncWriter{}

	//test that we actually have the static entry:
	out := lh.Query(testStaticHost)
	assert.NotNil(t, out)
	assert.Equal(t, out.vpnAddrs[0], testStaticHost)
	out.Rebuild([]netip.Prefix{}) //why tho
	assert.Equal(t, out.addrs[0], myUdpAddr2)

	//bolt on a lower numbered primary IP
	am := lh.unlockedGetRemoteList([]netip.Addr{testStaticHost})
	am.vpnAddrs = []netip.Addr{testSameHostNotStatic, testStaticHost}
	lh.addrMap[testSameHostNotStatic] = am
	out.Rebuild([]netip.Prefix{}) //???

	//test that we actually have the static entry:
	out = lh.Query(testStaticHost)
	assert.NotNil(t, out)
	assert.Equal(t, out.vpnAddrs[0], testSameHostNotStatic)
	assert.Equal(t, out.vpnAddrs[1], testStaticHost)
	assert.Equal(t, out.addrs[0], myUdpAddr2)

	//test that we actually have the static entry for BOTH:
	out2 := lh.Query(testSameHostNotStatic)
	assert.Same(t, out2, out)

	//now do the delete
	lh.DeleteVpnAddrs([]netip.Addr{testSameHostNotStatic, testStaticHost})
	//verify
	out = lh.Query(testSameHostNotStatic)
	assert.NotNil(t, out)
	if out == nil {
		t.Fatal("expected non-nil query for the static host")
	}
	assert.Equal(t, out.vpnAddrs[0], testSameHostNotStatic)
	assert.Equal(t, out.vpnAddrs[1], testStaticHost)
	assert.Equal(t, out.addrs[0], myUdpAddr2)
}

func TestLighthouse_DeletesWork(t *testing.T) {
	l := test.NewLogger()

	myUdpAddr2 := netip.MustParseAddrPort("1.2.3.4:4242")
	testHost := netip.MustParseAddr("10.128.0.42")

	c := config.NewC(l)
	lh1 := "10.128.0.2"
	c.Settings["lighthouse"] = map[string]any{
		"hosts":    []any{lh1},
		"interval": "1s",
	}

	c.Settings["listen"] = map[string]any{"port": 4242}
	c.Settings["static_host_map"] = map[string]any{
		lh1: []any{"1.1.1.1:4242"},
	}

	myVpnNet := netip.MustParsePrefix("10.128.0.1/24")
	cs := testCertState(myVpnNet)
	lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
	require.NoError(t, err)
	lh.ifce = &mockEncWriter{}

	//insert the host
	am := lh.unlockedGetRemoteList([]netip.Addr{testHost})
	am.vpnAddrs = []netip.Addr{testHost}
	am.addrs = []netip.AddrPort{myUdpAddr2}
	lh.addrMap[testHost] = am
	am.Rebuild([]netip.Prefix{}) //???

	//test that we actually have the entry:
	out := lh.Query(testHost)
	assert.NotNil(t, out)
	assert.Equal(t, out.vpnAddrs[0], testHost)
	out.Rebuild([]netip.Prefix{}) //why tho
	assert.Equal(t, out.addrs[0], myUdpAddr2)

	//now do the delete
	lh.DeleteVpnAddrs([]netip.Addr{testHost})
	//verify
	out = lh.Query(testHost)
	assert.Nil(t, out)
}

func TestLightHouse_logLocalAddrsErr(t *testing.T) {
	out := &bytes.Buffer{}
	lh := &LightHouse{l: test.NewLoggerWithOutput(out)}

	// The first sighting of a failure warns.
	lh.logLocalAddrsErr(errors.New("permission denied"))
	assert.Contains(t, out.String(), "level=WARN")
	assert.Contains(t, out.String(), "permission denied")

	// Repeating unchanged does not warn again, which is what keeps a permanent failure from warning
	// on every lighthouse.interval for the life of the process.
	out.Reset()
	lh.logLocalAddrsErr(errors.New("permission denied"))
	assert.NotContains(t, out.String(), "level=WARN")

	// A different failure is a new event and warns.
	out.Reset()
	lh.logLocalAddrsErr(errors.New("something else"))
	assert.Contains(t, out.String(), "level=WARN")
	assert.Contains(t, out.String(), "something else")

	// Recovering resets, so the same failure returning later warns again.
	out.Reset()
	lh.logLocalAddrsErr(nil)
	assert.Empty(t, out.String())
	lh.logLocalAddrsErr(errors.New("something else"))
	assert.Contains(t, out.String(), "level=WARN")
}

// heldEncWriter holds the query worker in its first GetHostInfo until release closes.
type heldEncWriter struct {
	mockEncWriter
	once    sync.Once
	held    chan struct{}
	release chan struct{}
}

func (w *heldEncWriter) GetHostInfo(netip.Addr) *HostInfo {
	w.once.Do(func() { close(w.held) })
	<-w.release
	return nil
}

// QueryServer never waits on the query worker, since the packet readers call it and nothing drains the channel at
// shutdown; a query that finds the channel full is dropped and counted. The worker is held on its first query so the
// channel fills.
func TestLighthouse_QueryServerDoesNotBlock(t *testing.T) {
	l := test.NewLogger()
	cs := testCertState(netip.MustParsePrefix("10.128.0.1/16"))
	lh1 := "10.128.0.2"
	c := config.NewC(l)
	c.Settings["lighthouse"] = map[string]any{"hosts": []any{lh1}}
	c.Settings["static_host_map"] = map[string]any{lh1: []any{"1.1.1.1:4242"}}
	c.Settings["handshakes"] = map[string]any{"query_buffer": 1}
	lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
	require.NoError(t, err)
	w := &heldEncWriter{held: make(chan struct{}), release: make(chan struct{})}
	lh.ifce = w
	t.Cleanup(func() { close(w.release) })

	lh.QueryServer(netip.MustParseAddr("10.128.0.10"))
	select {
	case <-w.held:
	case <-time.After(5 * time.Second):
		t.Fatal("the query worker never took the first query")
	}
	dropped := lh.queryDropped.Count()
	done := make(chan struct{})
	go func() {
		lh.QueryServer(netip.MustParseAddr("10.128.0.11"))
		lh.QueryServer(netip.MustParseAddr("10.128.0.12"))
		close(done)
	}()
	select {
	case <-done:
	case <-time.After(5 * time.Second):
		t.Fatal("QueryServer blocked on a full query channel")
	}
	assert.EqualValues(t, 1, lh.queryDropped.Count()-dropped)
}

// hostmapEncWriter answers GetHostInfo from a real hostmap, the way Interface does.
type hostmapEncWriter struct {
	mockEncWriter
	hm *HostMap
}

func (w *hostmapEncWriter) GetHostInfo(a netip.Addr) *HostInfo { return w.hm.QueryVpnAddr(a) }
func (w *hostmapEncWriter) GetCertState() *CertState {
	return &CertState{initiatingVersion: cert.Version1}
}

// A lighthouse runs four paths that each hold one lock while waiting for the next: CheckAndComplete
// holds the hostmap and takes the handshake manager, StartHandshake holds the handshake manager and
// takes the lighthouse, a host update holds the lighthouse and takes the sender's RemoteList, and a
// punch notification holds the querier's RemoteList while it resolves the target. If that last step
// reaches the hostmap under the RemoteList lock, the four deadlock. Drive them all at once.
func TestLighthouse_PunchNotificationDoesNotCloseLockCycle(t *testing.T) {
	l := test.NewLogger()
	myVpnNet := netip.MustParsePrefix("10.128.0.1/24")

	c := config.NewC(l)
	c.Settings["lighthouse"] = map[string]any{"am_lighthouse": true}
	c.Settings["listen"] = map[string]any{"port": 4242}
	lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(myVpnNet), nil, nil)
	require.NoError(t, err)

	mainHM := newHostMap(l)
	pr := []netip.Prefix{}
	mainHM.preferredRanges.Store(&pr)
	lh.ifce = &hostmapEncWriter{hm: mainHM}

	hm := NewHandshakeManager(l, mainHM, lh, &udp.NoopConn{}, defaultHandshakeConfig)
	f := &Interface{hostMap: mainHM, lightHouse: lh, handshakeManager: hm, l: l}
	hm.f = f

	peer := netip.MustParseAddr("10.128.0.2")
	peerUdp := netip.MustParseAddrPort("10.0.0.2:4242")
	target := netip.MustParseAddr("10.128.0.3")
	targetUdp := netip.MustParseAddrPort("10.0.0.3:4242")
	outbound := netip.MustParseAddr("10.128.0.4")
	inbound := netip.MustParseAddr("10.128.0.5")

	seed := lh.NewRequestHandler()
	newLHHostUpdate(peerUdp, peer, []netip.AddrPort{peerUdp}, seed)
	newLHHostUpdate(targetUdp, target, []netip.AddrPort{targetUdp}, seed)

	stop := make(chan struct{})
	var wg sync.WaitGroup
	loop := func(body func()) {
		defer wg.Done()
		for {
			select {
			case <-stop:
				return
			default:
				body()
			}
		}
	}
	wg.Add(4)

	// Outbound handshakes keep starting and being dropped.
	go loop(func() {
		hm.DeleteHostInfo(hm.StartHandshake(outbound, nil))
	})

	// Inbound handshakes keep completing and being torn down.
	var idx uint32
	go loop(func() {
		idx++
		hi := &HostInfo{
			vpnAddrs:        []netip.Addr{inbound},
			localIndexId:    idx,
			remoteIndexId:   idx,
			remotes:         lh.QueryCache([]netip.Addr{inbound}),
			HandshakePacket: map[uint8][]byte{handshakePacketStage0: {byte(idx)}},
		}
		if _, err := hm.CheckAndComplete(hi, handshakePacketStage0, f); err == nil {
			mainHM.DeleteHostInfo(hi)
		}
	})

	// The peer keeps sending host updates.
	updates := lh.NewRequestHandler()
	go loop(func() {
		newLHHostUpdate(peerUdp, peer, []netip.AddrPort{peerUdp}, updates)
	})

	// The same peer keeps querying for the target, which ends in a punch notification.
	queries := lh.NewRequestHandler()
	go loop(func() {
		sendLHHostRequest(peerUdp, peer, target, queries, nil)
	})

	time.Sleep(time.Second)
	close(stop)
	done := make(chan struct{})
	go func() { wg.Wait(); close(done) }()
	select {
	case <-done:
	case <-time.After(5 * time.Second):
		t.Fatal("deadlock: the lighthouse paths never finished after stop was signalled")
	}
}

func TestLighthouse_reloadRelaysTriggersUpdate(t *testing.T) {
	l := test.NewLogger()
	c := config.NewC(l)
	base := "lighthouse:\n  am_lighthouse: true\nlisten:\n  port: 4242\n"
	require.NoError(t, c.LoadString(base+"relay:\n  relays: [10.128.0.5]\n"))

	lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
	require.NoError(t, err)
	assert.Empty(t, lh.updateTrigger)

	require.NoError(t, c.ReloadConfigString(base+"relay:\n  relays: [10.128.0.6]\n").Err)
	assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
	require.Len(t, lh.updateTrigger, 1)
	<-lh.updateTrigger

	// The config changed but what we advertise did not, a bad entry is skipped
	require.NoError(t, c.ReloadConfigString(base+"relay:\n  relays: [10.128.0.6, nope]\n").Err)
	assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
	assert.Empty(t, lh.updateTrigger)
}

func TestLighthouse_reloadAmRelayAlone(t *testing.T) {
	l := test.NewLogger()
	c := config.NewC(l)
	base := "lighthouse:\n  am_lighthouse: true\nlisten:\n  port: 4242\nrelay:\n  relays: [10.128.0.5]\n"
	require.NoError(t, c.LoadString(base+"  am_relay: false\n"))

	lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
	require.NoError(t, err)
	assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())

	// Relays aren't allowed to have relays, flipping am_relay alone must drop them and tell the lighthouses
	require.NoError(t, c.ReloadConfigString(base+"  am_relay: true\n").Err)
	assert.Empty(t, lh.GetRelaysForMe())
	require.Len(t, lh.updateTrigger, 1)
	<-lh.updateTrigger

	require.NoError(t, c.ReloadConfigString(base+"  am_relay: false\n").Err)
	assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
	require.Len(t, lh.updateTrigger, 1)
}

func TestLighthouse_reloadRestartRequired(t *testing.T) {
	l := test.NewLogger()
	c := config.NewC(l)
	base := "lighthouse:\n  am_lighthouse: true\n"
	require.NoError(t, c.LoadString(base+"listen:\n  port: 4242\n"))

	_, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
	require.NoError(t, err)

	res := c.ReloadConfigString(base + "listen:\n  port: 4242\n")
	require.NoError(t, res.Err)
	assert.False(t, res.RestartRequired)
	res = c.ReloadConfigString(base + "listen:\n  port: 4243\n")
	require.NoError(t, res.Err)
	assert.True(t, res.RestartRequired)
}

// A relay that doesn't parse is skipped and the rest are used, the reload says one was skipped
func TestLighthouse_reloadBadRelayFails(t *testing.T) {
	l := test.NewLogger()
	c := config.NewC(l)
	require.NoError(t, c.LoadString("listen:\n  port: 4242\n"))
	lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
	require.NoError(t, err)

	res := c.ReloadConfigString("listen:\n  port: 4242\nrelay:\n  relays: [10.128.0.2, nope]\n")
	require.NoError(t, res.Err)
	assert.True(t, res.Failed)
	assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.2")}, lh.GetRelaysForMe())
}

// An advertise_addrs entry inside our own network is skipped and the rest are used, the reload says one was skipped
func TestLighthouse_reloadAdvertiseAddrInNetworkFails(t *testing.T) {
	l := test.NewLogger()
	c := config.NewC(l)
	require.NoError(t, c.LoadString("listen:\n  port: 4242\n"))
	lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
	require.NoError(t, err)

	res := c.ReloadConfigString("listen:\n  port: 4242\nlighthouse:\n  advertise_addrs: [\"1.2.3.4:4242\", \"10.128.0.5:4242\"]\n")
	require.NoError(t, res.Err)
	assert.True(t, res.Failed)
	assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("1.2.3.4:4242")}, lh.GetAdvertiseAddrs())
}