Advertise underlay addresses on Android (#1881)

This commit is contained in:
Jack Doan authored and GitHub committed 2026-09-21 14:59:56 -05:00
1 parent 019cc46a7f
commit 3a45c01656
11 files changed
+385 -65

No files matched your search

+3
View File
@@ -242,11 +242,14 @@ test-cov-html:
go test -coverprofile=coverage.out
go tool cover -html=coverage.out
# The package builds only compile. The final line links an android binary so a linker-only failure
# cannot pass CI.
build-test-mobile:
GOARCH=amd64 GOOS=ios go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
GOARCH=arm64 GOOS=ios go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
GOARCH=amd64 GOOS=android go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
GOARCH=arm64 GOOS=android go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
GOARCH=arm64 GOOS=android go build -o /dev/null ${NEBULA_CMD_PATH}
bench:
go test -bench=.
+1 -1
View File
@@ -5,6 +5,7 @@ go 1.26.0
require (
dario.cat/mergo v1.0.2
filippo.io/bigmod v0.1.0
github.com/DefinedNet/netlink v1.3.2-dn.1
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be
github.com/armon/go-radix v1.0.0
github.com/flynn/noise v1.1.0
@@ -20,7 +21,6 @@ require (
github.com/skip2/go-qrcode v0.0.0-20200617195104-da1b6568686e
github.com/stefanberger/go-pkcs11uri v0.0.0-20230803200340-78284954bff6
github.com/stretchr/testify v1.12.1
github.com/vishvananda/netlink v1.3.1
go.uber.org/goleak v1.3.0
go.yaml.in/yaml/v3 v3.0.5
golang.org/x/crypto v0.57.0
+2 -4
View File
@@ -3,6 +3,8 @@ dario.cat/mergo v1.0.2 h1:85+piFYR1tMbRrLcDwR18y4UKJ3aH1Tbzi24VRW1TK8=
dario.cat/mergo v1.0.2/go.mod h1:E/hbnu0NxMFBjpMIE34DRGLWqDy0g5FuKDhCb31ngxA=
filippo.io/bigmod v0.1.0 h1:UNzDk7y9ADKST+axd9skUpBQeW7fG2KrTZyOE4uGQy8=
filippo.io/bigmod v0.1.0/go.mod h1:OjOXDNlClLblvXdwgFFOQFJEocLhhtai8vGLy0JCZlI=
github.com/DefinedNet/netlink v1.3.2-dn.1 h1:Md2PsUE1Xuy1Zxs/Bm6356n1kt5bq2HspXlPJ6pEspg=
github.com/DefinedNet/netlink v1.3.2-dn.1/go.mod h1:o4YSn8Jw7zoDcYXDmV77TRd4eS5sSLuE+vu2zAN67C8=
github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
@@ -138,8 +140,6 @@ github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81P
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.12.1 h1:EuwCh5fleGS7H32xRwO3wRGT7DxrDhLAT6FF8MpWDWE=
github.com/stretchr/testify v1.12.1/go.mod h1:MDEgiDPPsNp5cuIrHPPCyornHKgEVbtFUmoNlxoYthg=
github.com/vishvananda/netlink v1.3.1 h1:3AEMt62VKqz90r0tmNhog0r/PpWKmrEShJU0wJW6bV0=
github.com/vishvananda/netlink v1.3.1/go.mod h1:ARtKouGSTGchR8aMwmkzC0qiNPrrWO5JS/XMVl45+b4=
github.com/vishvananda/netns v0.0.5 h1:DfiHV+j8bA32MFM7bfEunvT8IAqQ/NzSJHtcmW5zdEY=
github.com/vishvananda/netns v0.0.5/go.mod h1:SpkAiCQRtJ6TvvxPnOSyH3BMl6unz3xZlaprSwhNNJM=
github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
@@ -195,8 +195,6 @@ golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7w
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210603081109-ebe580a85c40/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.2.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.10.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.48.0 h1:bbX/i/6MgT9BVLM9RT1thmxL04yeTAhbEz4SyadbXoo=
golang.org/x/sys v0.48.0/go.mod h1:hNLxWAXmnKAxqDtdwIYC4bM9oQPEecfsnNMuSxOs3og=
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
-58
View File
@@ -6,7 +6,6 @@ import (
"errors"
"fmt"
"log/slog"
"net"
"net/netip"
"slices"
"sync"
@@ -18,7 +17,6 @@ import (
"github.com/slackhq/nebula/cert"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/header"
"github.com/slackhq/nebula/logging"
)
const defaultPromoteEvery = 1000 // Count of packets sent before we try moving a tunnel to a preferred underlay ip address
@@ -930,59 +928,3 @@ func (i *HostInfo) logger(l *slog.Logger) *slog.Logger {
return li
}
// Utility functions
func localAddrs(l *slog.Logger, allowList *LocalAllowList) []netip.Addr {
//FIXME: This function is pretty garbage
var finalAddrs []netip.Addr
ifaces, _ := net.Interfaces()
for _, i := range ifaces {
allow := allowList.AllowName(i.Name)
if l.Enabled(context.Background(), logging.LevelTrace) {
l.Log(context.Background(), logging.LevelTrace, "localAllowList.AllowName",
"interfaceName", i.Name,
"allow", allow,
)
}
if !allow {
continue
}
addrs, _ := i.Addrs()
for _, rawAddr := range addrs {
var addr netip.Addr
switch v := rawAddr.(type) {
case *net.IPNet:
//continue
addr, _ = netip.AddrFromSlice(v.IP)
case *net.IPAddr:
addr, _ = netip.AddrFromSlice(v.IP)
}
if !addr.IsValid() {
if l.Enabled(context.Background(), slog.LevelDebug) {
l.Debug("addr was invalid", "localAddr", rawAddr)
}
continue
}
addr = addr.Unmap()
if addr.IsLoopback() == false && addr.IsLinkLocalUnicast() == false {
isAllowed := allowList.Allow(addr)
if l.Enabled(context.Background(), logging.LevelTrace) {
l.Log(context.Background(), logging.LevelTrace, "localAllowList.Allow",
"localAddr", addr,
"allowed", isAllowed,
)
}
if !isAllowed {
continue
}
finalAddrs = append(finalAddrs, addr)
}
}
}
return finalAddrs
}
+28 -1
View File
@@ -19,6 +19,7 @@ import (
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/header"
"github.com/slackhq/nebula/logging"
"github.com/slackhq/nebula/nicfinder"
"github.com/slackhq/nebula/udp"
"github.com/slackhq/nebula/util"
)
@@ -42,6 +43,10 @@ type LightHouse struct {
// addresses rather than whatever this machine's NICs happen to be. Set it before Start.
localAddrsFn func(*LocalAllowList) []netip.Addr
// lastLocalAddrsErr is the previous localAddrsFn failure. Enumeration runs on every update, so an
// unchanged failure is demoted to Debug rather than warning every lighthouse.interval forever.
lastLocalAddrsErr atomic.Pointer[string]
// Local cache of answers from light houses
// map of vpn addr to answers
addrMap map[netip.Addr]*RemoteList
@@ -115,7 +120,9 @@ func NewLightHouseFromConfig(ctx context.Context, l *slog.Logger, c *config.C, c
l: l,
}
h.localAddrsFn = func(al *LocalAllowList) []netip.Addr {
return localAddrs(h.l, al)
addrs, err := nicfinder.Find(ctx, h.l, al)
h.logLocalAddrsErr(err)
return addrs
}
lighthouses := make([]netip.Addr, 0)
@@ -916,6 +923,26 @@ func (lh *LightHouse) TriggerUpdate() {
}
}
// logLocalAddrsErr reports a localAddrs failure at Warn the first time it is seen and at Debug while
// it persists unchanged, so a permanent failure does not warn on every update forever.
func (lh *LightHouse) logLocalAddrsErr(err error) {
if err == nil {
lh.lastLocalAddrsErr.Store(nil)
return
}
msg := err.Error()
prev := lh.lastLocalAddrsErr.Swap(&msg)
if prev != nil && *prev == msg {
if lh.l.Enabled(context.Background(), slog.LevelDebug) {
lh.l.Debug("Failed to collect local addresses to advertise", "error", err)
}
return
}
lh.l.Warn("Failed to collect local addresses to advertise", "error", err)
}
func (lh *LightHouse) SendUpdate() {
var v4 []*V4AddrPort
var v6 []*V6AddrPort
+31
View File
@@ -1,7 +1,9 @@
package nebula
import (
"bytes"
"encoding/binary"
"errors"
"fmt"
"net/netip"
"testing"
@@ -764,3 +766,32 @@ func TestLighthouse_DeletesWork(t *testing.T) {
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")
}
+39
View File
@@ -0,0 +1,39 @@
//go:build !android
package nicfinder
import (
"context"
"errors"
"fmt"
"log/slog"
"net"
"net/netip"
)
func localAddrs(ctx context.Context, l *slog.Logger, filter Filter) ([]netip.Addr, error) {
ifaces, err := net.Interfaces()
if err != nil {
return nil, fmt.Errorf("failed to enumerate local interfaces: %w", err)
}
var out []netip.Addr
var errs []error
for _, i := range ifaces {
if !allowName(ctx, l, filter, i.Name) {
continue
}
addrs, err := i.Addrs()
if err != nil {
errs = append(errs, fmt.Errorf("failed to get addresses for %s: %w", i.Name, err))
continue
}
for _, rawAddr := range addrs {
if addr, ok := allowedAddr(ctx, l, filter, rawAddr); ok {
out = append(out, addr)
}
}
}
return out, errors.Join(errs...)
}
+104
View File
@@ -0,0 +1,104 @@
//go:build android
package nicfinder
import (
"context"
"errors"
"fmt"
"log/slog"
"net/netip"
"os"
"github.com/DefinedNet/netlink"
"github.com/DefinedNet/netlink/nl"
"golang.org/x/sys/unix"
)
// Android denies bind() on netlink route sockets and RTM_GETLINK, so net.Interfaces fails with EACCES.
// Enumerate with an RTM_GETADDR dump on an unbound socket instead.
// localInterfaces returns every interface that has an address, with its addresses. It lists
// addresses over a netlink socket that is never bound and names each index with SIOCGIFNAME, the
// same operations Bionic's getifaddrs uses for app UIDs, which the sandbox permits.
func localAddrs(ctx context.Context, l *slog.Logger, filter Filter) ([]netip.Addr, error) {
var errs []error
addrs, err := netlinkAddrList()
if err != nil {
if !errors.Is(err, netlink.ErrDumpInterrupted) {
return nil, fmt.Errorf("failed to enumerate local interfaces: %w", err)
}
// The address table kept changing under the dump and netlink gave up retrying. What it
// returned is still worth advertising.
errs = append(errs, fmt.Errorf("local addresses may be incomplete: %w", err))
}
// Any socket will do for SIOCGIFNAME.
sfd, err := unix.Socket(unix.AF_INET, unix.SOCK_DGRAM|unix.SOCK_CLOEXEC, 0)
if err != nil {
return nil, os.NewSyscallError("socket", err)
}
defer unix.Close(sfd)
var out []netip.Addr
nameAllowed := make(map[int]bool) // by interface index, once named
for _, a := range addrs {
allow, named := nameAllowed[a.LinkIndex]
if (named && !allow) || a.IPNet == nil {
continue
}
addr, ok := allowedAddr(ctx, l, filter, a.IPNet)
if !ok {
continue
}
if !named {
name, err := interfaceNameByIndex(sfd, a.LinkIndex)
// ENODEV means the interface went away after the dump. Any other failure is reported
// and the interface skipped, so the rest are still returned.
if err != nil && !errors.Is(err, unix.ENODEV) {
errs = append(errs, fmt.Errorf("failed to resolve name of interface %d: %w", a.LinkIndex, err))
}
allow = err == nil && allowName(ctx, l, filter, name)
nameAllowed[a.LinkIndex] = allow
}
if allow {
out = append(out, addr)
}
}
return out, errors.Join(errs...)
}
// netlinkAddrList is netlink.AddrList over a socket that is never bound. The kernel autobinds it
// on the first send, which the sandbox permits.
func netlinkAddrList() ([]netlink.Addr, error) {
fd, err := unix.Socket(unix.AF_NETLINK, unix.SOCK_RAW|unix.SOCK_CLOEXEC, unix.NETLINK_ROUTE)
if err != nil {
return nil, os.NewSyscallError("socket", err)
}
s, err := nl.NewNetlinkSocketFromFd(fd)
if err != nil {
unix.Close(fd)
return nil, err
}
h := netlink.NewHandleFromSockets(
map[int]*nl.SocketHandle{unix.NETLINK_ROUTE: {Socket: s}},
netlink.HandleOptions{RetryInterrupted: true},
)
defer h.Close()
if err := h.SetSocketTimeout(netlink.GetSocketTimeout()); err != nil {
return nil, err
}
return h.AddrList(nil, netlink.FAMILY_ALL)
}
// interfaceNameByIndex resolves an interface index with SIOCGIFNAME.
func interfaceNameByIndex(fd int, index int) (string, error) {
var ifr unix.Ifreq
ifr.SetUint32(uint32(index)) // ifr_ifindex is in the ifr_ifru union
if err := unix.IoctlIfreq(fd, unix.SIOCGIFNAME, &ifr); err != nil {
return "", err
}
return ifr.Name(), nil
}
+59
View File
@@ -0,0 +1,59 @@
package nicfinder
import (
"context"
"log/slog"
"net"
"net/netip"
"github.com/slackhq/nebula/logging"
)
// Filter decides which interfaces, by name, and which of their addresses Find returns.
type Filter interface {
AllowName(string) bool
Allow(netip.Addr) bool
}
// Find returns the addresses of this host's network interfaces that allowList accepts, with
// loopback and link-local addresses left out. When only some interfaces could be read it returns
// their addresses alongside an error for the rest. allowList must not be nil; it is called as
// given, so a nil pointer of a type whose methods accept a nil receiver is fine.
func Find(ctx context.Context, l *slog.Logger, allowList Filter) ([]netip.Addr, error) {
return localAddrs(ctx, l, allowList)
}
// allowName asks filter about an interface name and traces the answer.
func allowName(ctx context.Context, l *slog.Logger, filter Filter, name string) bool {
allow := filter.AllowName(name)
if l.Enabled(ctx, logging.LevelTrace) {
l.Log(ctx, logging.LevelTrace, "localAllowList.AllowName", "interfaceName", name, "allow", allow)
}
return allow
}
// allowedAddr converts one address a platform reports and says whether to advertise it: it must
// be a *net.IPNet or *net.IPAddr carrying an IP, not be loopback or link-local, and be accepted by
// filter, whose answer is traced. IPv4 comes back unmapped.
func allowedAddr(ctx context.Context, l *slog.Logger, filter Filter, rawAddr net.Addr) (netip.Addr, bool) {
var ip net.IP
switch v := rawAddr.(type) {
case *net.IPNet:
ip = v.IP
case *net.IPAddr:
ip = v.IP
}
addr, ok := netip.AddrFromSlice(ip)
if !ok {
return netip.Addr{}, false
}
addr = addr.Unmap()
if addr.IsLoopback() || addr.IsLinkLocalUnicast() {
return netip.Addr{}, false
}
isAllowed := filter.Allow(addr)
if l.Enabled(ctx, logging.LevelTrace) {
l.Log(ctx, logging.LevelTrace, "localAllowList.Allow", "localAddr", addr, "allowed", isAllowed)
}
return addr, isAllowed
}
+117
View File
@@ -0,0 +1,117 @@
package nicfinder
import (
"context"
"net"
"net/netip"
"regexp"
"testing"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
)
type allowAll struct{}
func (allowAll) Allow(netip.Addr) bool { return true }
func (allowAll) AllowName(string) bool { return true }
type testAllowList struct {
bannedName *regexp.Regexp
bannedAddr netip.Addr
}
func (l *testAllowList) Allow(addr netip.Addr) bool {
return addr != l.bannedAddr
}
func (l *testAllowList) AllowName(n string) bool {
return !l.bannedName.MatchString(n)
}
func newTestAllowList(bannedName string) *testAllowList {
return &testAllowList{
bannedName: regexp.MustCompile(bannedName),
}
}
func TestAllowedAddr(t *testing.T) {
ctx, l := context.Background(), test.NewLogger()
allowed := func(filter Filter, addrs []net.Addr) []netip.Addr {
var out []netip.Addr
for _, rawAddr := range addrs {
if addr, ok := allowedAddr(ctx, l, filter, rawAddr); ok {
out = append(out, addr)
}
}
return out
}
addrs := []net.Addr{
&net.IPNet{IP: net.ParseIP("127.0.0.1"), Mask: net.CIDRMask(8, 32)},
&net.IPNet{IP: net.ParseIP("::1"), Mask: net.CIDRMask(128, 128)},
&net.IPNet{IP: net.ParseIP("10.0.0.5"), Mask: net.CIDRMask(24, 32)},
&net.IPNet{IP: net.ParseIP("169.254.10.10"), Mask: net.CIDRMask(16, 32)},
&net.IPNet{IP: net.ParseIP("fe80::1"), Mask: net.CIDRMask(64, 128)},
&net.IPAddr{IP: net.ParseIP("fd00::5")},
&net.IPNet{},
otherAddr{},
nil,
}
// Loopback, link local and anything without an IP are dropped, and IPv4 comes back unmapped
// even though net.ParseIP hands over a 16 byte slice.
assert.Equal(t, []netip.Addr{
netip.MustParseAddr("10.0.0.5"),
netip.MustParseAddr("fd00::5"),
}, allowed(allowAll{}, addrs))
// The filter sees the unmapped form and can drop a single address.
al := newTestAllowList("none")
al.bannedAddr = netip.MustParseAddr("10.0.0.5")
assert.Equal(t, []netip.Addr{netip.MustParseAddr("fd00::5")}, allowed(al, addrs))
}
// otherAddr is a net.Addr that is neither *net.IPNet nor *net.IPAddr. netlink.Addr is one such
// type: it satisfies net.Addr through an embedded *net.IPNet, and passing it directly once
// silently produced no addresses.
type otherAddr struct{}
func (otherAddr) Network() string { return "other" }
func (otherAddr) String() string { return "other" }
// hostFilter counts AllowName calls and can reject every name or every address.
type hostFilter struct {
rejectNames bool
rejectAddrs bool
asked map[string]int
}
func (f *hostFilter) Allow(netip.Addr) bool { return !f.rejectAddrs }
func (f *hostFilter) AllowName(name string) bool {
f.asked[name]++
return !f.rejectNames
}
// Runs this platform's localAddrs against the host and checks it honors the whole filter.
func TestLocalAddrsAppliesFilter(t *testing.T) {
ctx, l := context.Background(), test.NewLogger()
f := &hostFilter{asked: map[string]int{}}
all, err := localAddrs(ctx, l, f)
if len(f.asked) == 0 {
t.Skipf("no interfaces to enumerate here: %v", err)
}
for name, n := range f.asked {
assert.Equal(t, 1, n, "AllowName asked %d times for %s", n, name)
}
// Loopback and link-local never come back, whatever the filter says.
for _, addr := range all {
assert.False(t, addr.IsLoopback() || addr.IsLinkLocalUnicast(), "%s", addr)
}
none, _ := localAddrs(ctx, l, &hostFilter{rejectNames: true, asked: map[string]int{}})
assert.Empty(t, none, "addresses got past a filter that rejects every interface name")
none, _ = localAddrs(ctx, l, &hostFilter{rejectAddrs: true, asked: map[string]int{}})
assert.Empty(t, none, "addresses got past a filter that rejects every address")
}
+1 -1
View File
@@ -15,12 +15,12 @@ import (
"time"
"unsafe"
"github.com/DefinedNet/netlink"
"github.com/gaissmai/bart"
"github.com/slackhq/nebula/config"
"github.com/slackhq/nebula/overlay/tio"
"github.com/slackhq/nebula/routing"
"github.com/slackhq/nebula/util"
"github.com/vishvananda/netlink"
"golang.org/x/sys/unix"
)