mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-16 19:06:52 +01:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
16538f5e44 |
No files matched your search
@@ -263,20 +263,6 @@ try {
|
|||||||
}
|
}
|
||||||
Write-Host "OK: WSL peer -> windows lighthouse over v6"
|
Write-Host "OK: WSL peer -> windows lighthouse over v6"
|
||||||
|
|
||||||
# The NlMtu check above proves the value was written, not that windows honors it. A payload this size only
|
|
||||||
# crosses the tunnel as fragments cut at NlMtu on the way out of the adapter. Left at the adapter default it
|
|
||||||
# reaches nebula whole, overflows the udp.MTU (9001) write buffer and is dropped, so the ping never answers.
|
|
||||||
# Anything smaller would ride out as one oversized datagram and survive on IP fragmentation of the underlay.
|
|
||||||
$BigPayload = 9000
|
|
||||||
foreach ($target in @(@{ Family = 'v4'; Ip = $Ip2 }, @{ Family = 'v6'; Ip = $Ip6_2 })) {
|
|
||||||
Wait-Until -TimeoutSec 30 -What "$($target.Family) ping with a $BigPayload byte payload from windows lighthouse to WSL peer ($($target.Ip))" -Predicate {
|
|
||||||
if ($peerProc.HasExited) { throw "peer exited (code $($peerProc.ExitCode)) before the large $($target.Family) ping succeeded" }
|
|
||||||
$null = & ping.exe -n 1 -w 1000 -l $BigPayload $target.Ip
|
|
||||||
$LASTEXITCODE -eq 0
|
|
||||||
}
|
|
||||||
Write-Host "OK: windows lighthouse -> WSL peer, $BigPayload byte $($target.Family) payload"
|
|
||||||
}
|
|
||||||
|
|
||||||
Write-Host ''
|
Write-Host ''
|
||||||
Write-Host 'All smoke checks passed.'
|
Write-Host 'All smoke checks passed.'
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -242,14 +242,11 @@ test-cov-html:
|
|||||||
go test -coverprofile=coverage.out
|
go test -coverprofile=coverage.out
|
||||||
go tool cover -html=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:
|
build-test-mobile:
|
||||||
GOARCH=amd64 GOOS=ios go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
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=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=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 $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
||||||
GOARCH=arm64 GOOS=android go build -o /dev/null ${NEBULA_CMD_PATH}
|
|
||||||
|
|
||||||
bench:
|
bench:
|
||||||
go test -bench=.
|
go test -bench=.
|
||||||
|
|||||||
+1
-2
@@ -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
|
// 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;
|
// unlikely to help. Say so instead of silently carrying on as if we rebound.
|
||||||
// darwin's Rebind clears every listen routine's listener.
|
|
||||||
if err := c.f.outside.Rebind(); err != nil {
|
if err := c.f.outside.Rebind(); err != nil {
|
||||||
c.l.Error("Failed to rebind udp socket", "error", err)
|
c.l.Error("Failed to rebind udp socket", "error", err)
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -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
|
|
||||||
}
|
|
||||||
@@ -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())
|
|
||||||
}
|
|
||||||
@@ -5,7 +5,6 @@ go 1.26.0
|
|||||||
require (
|
require (
|
||||||
dario.cat/mergo v1.0.2
|
dario.cat/mergo v1.0.2
|
||||||
filippo.io/bigmod v0.1.0
|
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/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be
|
||||||
github.com/armon/go-radix v1.0.0
|
github.com/armon/go-radix v1.0.0
|
||||||
github.com/flynn/noise v1.1.0
|
github.com/flynn/noise v1.1.0
|
||||||
@@ -21,6 +20,7 @@ require (
|
|||||||
github.com/skip2/go-qrcode v0.0.0-20200617195104-da1b6568686e
|
github.com/skip2/go-qrcode v0.0.0-20200617195104-da1b6568686e
|
||||||
github.com/stefanberger/go-pkcs11uri v0.0.0-20230803200340-78284954bff6
|
github.com/stefanberger/go-pkcs11uri v0.0.0-20230803200340-78284954bff6
|
||||||
github.com/stretchr/testify v1.12.1
|
github.com/stretchr/testify v1.12.1
|
||||||
|
github.com/vishvananda/netlink v1.3.1
|
||||||
go.uber.org/goleak v1.3.0
|
go.uber.org/goleak v1.3.0
|
||||||
go.yaml.in/yaml/v3 v3.0.5
|
go.yaml.in/yaml/v3 v3.0.5
|
||||||
golang.org/x/crypto v0.57.0
|
golang.org/x/crypto v0.57.0
|
||||||
|
|||||||
@@ -3,8 +3,6 @@ dario.cat/mergo v1.0.2 h1:85+piFYR1tMbRrLcDwR18y4UKJ3aH1Tbzi24VRW1TK8=
|
|||||||
dario.cat/mergo v1.0.2/go.mod h1:E/hbnu0NxMFBjpMIE34DRGLWqDy0g5FuKDhCb31ngxA=
|
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 h1:UNzDk7y9ADKST+axd9skUpBQeW7fG2KrTZyOE4uGQy8=
|
||||||
filippo.io/bigmod v0.1.0/go.mod h1:OjOXDNlClLblvXdwgFFOQFJEocLhhtai8vGLy0JCZlI=
|
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 v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
|
||||||
github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/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=
|
github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
|
||||||
@@ -140,6 +138,8 @@ 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 v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
|
||||||
github.com/stretchr/testify v1.12.1 h1:EuwCh5fleGS7H32xRwO3wRGT7DxrDhLAT6FF8MpWDWE=
|
github.com/stretchr/testify v1.12.1 h1:EuwCh5fleGS7H32xRwO3wRGT7DxrDhLAT6FF8MpWDWE=
|
||||||
github.com/stretchr/testify v1.12.1/go.mod h1:MDEgiDPPsNp5cuIrHPPCyornHKgEVbtFUmoNlxoYthg=
|
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 h1:DfiHV+j8bA32MFM7bfEunvT8IAqQ/NzSJHtcmW5zdEY=
|
||||||
github.com/vishvananda/netns v0.0.5/go.mod h1:SpkAiCQRtJ6TvvxPnOSyH3BMl6unz3xZlaprSwhNNJM=
|
github.com/vishvananda/netns v0.0.5/go.mod h1:SpkAiCQRtJ6TvvxPnOSyH3BMl6unz3xZlaprSwhNNJM=
|
||||||
github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
|
github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
|
||||||
@@ -195,6 +195,8 @@ 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 v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
||||||
golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
||||||
golang.org/x/sys v0.0.0-20210603081109-ebe580a85c40/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
golang.org/x/sys v0.0.0-20210603081109-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 h1:bbX/i/6MgT9BVLM9RT1thmxL04yeTAhbEz4SyadbXoo=
|
||||||
golang.org/x/sys v0.48.0/go.mod h1:hNLxWAXmnKAxqDtdwIYC4bM9oQPEecfsnNMuSxOs3og=
|
golang.org/x/sys v0.48.0/go.mod h1:hNLxWAXmnKAxqDtdwIYC4bM9oQPEecfsnNMuSxOs3og=
|
||||||
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
|
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
|
||||||
|
|||||||
+59
-17
@@ -6,6 +6,7 @@ import (
|
|||||||
"errors"
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
"log/slog"
|
"log/slog"
|
||||||
|
"net"
|
||||||
"net/netip"
|
"net/netip"
|
||||||
"slices"
|
"slices"
|
||||||
"sync"
|
"sync"
|
||||||
@@ -17,6 +18,7 @@ import (
|
|||||||
"github.com/slackhq/nebula/cert"
|
"github.com/slackhq/nebula/cert"
|
||||||
"github.com/slackhq/nebula/config"
|
"github.com/slackhq/nebula/config"
|
||||||
"github.com/slackhq/nebula/header"
|
"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
|
const defaultPromoteEvery = 1000 // Count of packets sent before we try moving a tunnel to a preferred underlay ip address
|
||||||
@@ -69,9 +71,7 @@ type HostMap struct {
|
|||||||
Hosts map[netip.Addr]*HostInfo
|
Hosts map[netip.Addr]*HostInfo
|
||||||
moreHosts map[netip.Addr][]*HostInfo
|
moreHosts map[netip.Addr][]*HostInfo
|
||||||
preferredRanges atomic.Pointer[[]netip.Prefix]
|
preferredRanges atomic.Pointer[[]netip.Prefix]
|
||||||
// established hears about each hostinfo that joins or leaves the hostmap; nil when no conn wants to know.
|
l *slog.Logger
|
||||||
established *establishedRemotes
|
|
||||||
l *slog.Logger
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// For synchronization, treat the pointed-to Relay struct as immutable. To edit the Relay
|
// For synchronization, treat the pointed-to Relay struct as immutable. To edit the Relay
|
||||||
@@ -278,11 +278,6 @@ type HostInfo struct {
|
|||||||
// This value will be behind against actual tunnel utilization in the hot path.
|
// This value will be behind against actual tunnel utilization in the hot path.
|
||||||
// This should only be used by the ConnectionManagers ticker routine.
|
// This should only be used by the ConnectionManagers ticker routine.
|
||||||
lastUsed time.Time
|
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 {
|
type ViaSender struct {
|
||||||
@@ -523,7 +518,6 @@ func (hm *HostMap) unlockedDeleteHostInfo(hostinfo *HostInfo) bool {
|
|||||||
if len(hm.Indexes) == 0 {
|
if len(hm.Indexes) == 0 {
|
||||||
hm.Indexes = map[uint32]*HostInfo{}
|
hm.Indexes = map[uint32]*HostInfo{}
|
||||||
}
|
}
|
||||||
hm.established.remove(hostinfo)
|
|
||||||
|
|
||||||
if hm.l.Enabled(context.Background(), slog.LevelDebug) {
|
if hm.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||||
hm.l.Debug("Hostmap hostInfo deleted",
|
hm.l.Debug("Hostmap hostInfo deleted",
|
||||||
@@ -670,7 +664,6 @@ func (hm *HostMap) unlockedAddHostInfo(hostinfo *HostInfo, f *Interface) {
|
|||||||
|
|
||||||
hm.Indexes[hostinfo.localIndexId] = hostinfo
|
hm.Indexes[hostinfo.localIndexId] = hostinfo
|
||||||
hm.RemoteIndexes[hostinfo.remoteIndexId] = hostinfo
|
hm.RemoteIndexes[hostinfo.remoteIndexId] = hostinfo
|
||||||
hm.established.add(hostinfo)
|
|
||||||
|
|
||||||
hostinfo.markOut(f.rebindEpoch.Load())
|
hostinfo.markOut(f.rebindEpoch.Load())
|
||||||
if f.connectionManager != nil { // f.connectionManager is only nil in some unit tests
|
if f.connectionManager != nil { // f.connectionManager is only nil in some unit tests
|
||||||
@@ -851,13 +844,6 @@ func (i *HostInfo) SetRemote(remote netip.AddrPort) {
|
|||||||
if i.GetRemote() != remote {
|
if i.GetRemote() != remote {
|
||||||
i.remote.Store(&remote)
|
i.remote.Store(&remote)
|
||||||
i.remotes.LearnRemote(i.vpnAddrs[0], 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()
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -944,3 +930,59 @@ func (i *HostInfo) logger(l *slog.Logger) *slog.Logger {
|
|||||||
|
|
||||||
return li
|
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
|
||||||
|
}
|
||||||
+13
-3
@@ -45,7 +45,8 @@ func setTransportChecksum4(packet []byte) {
|
|||||||
if ihl < ipv4.HeaderLen || end < ihl || end > len(packet) {
|
if ihl < ipv4.HeaderLen || end < ihl || end > len(packet) {
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
// do not attempt to set checksums for fragments
|
// The checksum covers the whole datagram, which a fragment (MF set or a
|
||||||
|
// non-zero offset) does not carry.
|
||||||
if binary.BigEndian.Uint16(packet[6:8])&0x3fff != 0 {
|
if binary.BigEndian.Uint16(packet[6:8])&0x3fff != 0 {
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
@@ -67,7 +68,10 @@ func setTransportChecksum6(packet []byte) {
|
|||||||
return
|
return
|
||||||
}
|
}
|
||||||
|
|
||||||
// we must find the transport header in order to write a checksum
|
// The checksum covers the whole datagram, which a fragment does not carry.
|
||||||
|
// An unknown extension header hides where the transport header starts. A
|
||||||
|
// chain longer than the walk's budget ends it early, at an offset that was
|
||||||
|
// never checked against the packet.
|
||||||
proto, offset, _, anyFragment, err := IPv6FindUpperProtocol(packet[:end])
|
proto, offset, _, anyFragment, err := IPv6FindUpperProtocol(packet[:end])
|
||||||
if err != nil || anyFragment || offset >= end {
|
if err != nil || anyFragment || offset >= end {
|
||||||
return
|
return
|
||||||
@@ -105,7 +109,8 @@ func transportExtent(transport []byte, proto uint8) ([]byte, bool) {
|
|||||||
// writeTransportChecksum stores the checksum of transport, taken over the
|
// writeTransportChecksum stores the checksum of transport, taken over the
|
||||||
// pseudo-header sum csum, in the header's checksum field. A UDP checksum that
|
// pseudo-header sum csum, in the header's checksum field. A UDP checksum that
|
||||||
// computes to zero goes on the wire as 0xffff: zero means no checksum was
|
// computes to zero goes on the wire as 0xffff: zero means no checksum was
|
||||||
// computed (RFC 768), and over IPv6 the checksum is mandatory (RFC 8200 section 8.1).
|
// computed (RFC 768), and over IPv6 the checksum is mandatory (RFC 8200
|
||||||
|
// section 8.1).
|
||||||
func writeTransportChecksum(transport []byte, proto uint8, csum uint32) {
|
func writeTransportChecksum(transport []byte, proto uint8, csum uint32) {
|
||||||
var at, minLen int
|
var at, minLen int
|
||||||
switch proto {
|
switch proto {
|
||||||
@@ -128,6 +133,11 @@ func writeTransportChecksum(transport []byte, proto uint8, csum uint32) {
|
|||||||
binary.BigEndian.PutUint16(transport[at:], sum)
|
binary.BigEndian.PutUint16(transport[at:], sum)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// fold reduces a pseudo-header sum to the 16 bit seed Checksum takes. Carrying
|
||||||
|
// the high half back into the low half is what keeps the reduction lossless, so
|
||||||
|
// the seed sums exactly as the wider value would; 0xffff is its fixed point.
|
||||||
|
// Every term of that sum comes from a 16 bit field, so it stays far below the
|
||||||
|
// width at which the accumulator would wrap.
|
||||||
func fold(csum uint32) uint16 {
|
func fold(csum uint32) uint16 {
|
||||||
for csum > 0xffff {
|
for csum > 0xffff {
|
||||||
csum = (csum >> 16) + (csum & 0xffff)
|
csum = (csum >> 16) + (csum & 0xffff)
|
||||||
|
|||||||
+16
-13
@@ -345,11 +345,14 @@ func ipv6CreateRejectTCPPacket(packet []byte, out []byte, offset int) []byte {
|
|||||||
return out
|
return out
|
||||||
}
|
}
|
||||||
|
|
||||||
// IPv6FindUpperProtocol walks the ipv6 extension header chain and returns the upper layer protocol, the offset it begins at, and whether the packet is a non-first fragment.
|
// IPv6FindUpperProtocol walks the ipv6 extension header chain and returns the upper layer protocol, the
|
||||||
// Only the RFC 8200 and IANA extension headers below are walked.
|
// offset it begins at, and whether the packet is a non-first fragment. Only the RFC 8200 and IANA extension
|
||||||
// Everything else, including Mobility (135), HIP (139), Shim6 (140), experimental 253/254, and real upper layer protocols like SCTP or GRE, is terminal.
|
// headers below are walked. Everything else, including Mobility (135), HIP (139), Shim6 (140), experimental
|
||||||
// For a non-first fragment the returned protocol is the fragmented protocol and offset points at the fragment header, there is no transport header to locate.
|
// 253/254, and real upper layer protocols like SCTP or GRE, is terminal. Walking those as extension headers
|
||||||
// Returns ErrIPv6CouldNotFindPayload if packet is smaller than an ipv6 header, or the chain is truncated, or if more than 8 extension headers are present.
|
// is a firewall bypass, so they fail closed. For a non-first fragment the returned protocol is the fragmented
|
||||||
|
// protocol and offset points at the fragment header, there is no transport header to locate. Returns
|
||||||
|
// ErrIPv6CouldNotFindPayload if packet is smaller than an ipv6 header or the chain is truncated before a
|
||||||
|
// terminal protocol is reached.
|
||||||
func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragment bool, anyFragment bool, err error) {
|
func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragment bool, anyFragment bool, err error) {
|
||||||
const maxIPv6ExtHeaders = 8
|
const maxIPv6ExtHeaders = 8
|
||||||
if len(packet) < ipv6.HeaderLen {
|
if len(packet) < ipv6.HeaderLen {
|
||||||
@@ -362,14 +365,14 @@ func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragm
|
|||||||
switch nextHeader {
|
switch nextHeader {
|
||||||
case 0, 43, 60: // Hop-by-Hop, Routing, Destination
|
case 0, 43, 60: // Hop-by-Hop, Routing, Destination
|
||||||
if len(packet) < offset+2 {
|
if len(packet) < offset+2 {
|
||||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
return nextHeader, offset, isFragment, anyFragment, ErrIPv6CouldNotFindPayload
|
||||||
}
|
}
|
||||||
nextHeader = packet[offset]
|
nextHeader = packet[offset]
|
||||||
offset += (int(packet[offset+1]) + 1) << 3
|
offset += (int(packet[offset+1]) + 1) << 3
|
||||||
|
|
||||||
case 44: // Fragment
|
case 44: // Fragment
|
||||||
if len(packet) < offset+8 {
|
if len(packet) < offset+8 {
|
||||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
return nextHeader, offset, isFragment, anyFragment, ErrIPv6CouldNotFindPayload
|
||||||
}
|
}
|
||||||
anyFragment = true
|
anyFragment = true
|
||||||
// Non-first fragments carry no transport header, report the fragmented protocol and stop
|
// Non-first fragments carry no transport header, report the fragmented protocol and stop
|
||||||
@@ -381,21 +384,21 @@ func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragm
|
|||||||
|
|
||||||
case 51: // AH
|
case 51: // AH
|
||||||
if len(packet) < offset+2 {
|
if len(packet) < offset+2 {
|
||||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
return nextHeader, offset, isFragment, anyFragment, ErrIPv6CouldNotFindPayload
|
||||||
}
|
}
|
||||||
nextHeader = packet[offset]
|
nextHeader = packet[offset]
|
||||||
offset += (int(packet[offset+1]) + 2) << 2
|
offset += (int(packet[offset+1]) + 2) << 2
|
||||||
|
|
||||||
default:
|
default:
|
||||||
|
// A prior extension header can declare a length that advances offset past the packet. The terminal
|
||||||
|
// protocol's header isn't actually here, so treat the chain as truncated rather than classifying it.
|
||||||
if offset > len(packet) {
|
if offset > len(packet) {
|
||||||
// A prior extension header can declare a length that advances offset past the packet, reject this.
|
return nextHeader, offset, isFragment, anyFragment, ErrIPv6CouldNotFindPayload
|
||||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
|
||||||
}
|
}
|
||||||
return nextHeader, offset, isFragment, anyFragment, nil //success!
|
return nextHeader, offset, isFragment, anyFragment, nil
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
// Fail closed
|
return nextHeader, offset, isFragment, anyFragment, nil
|
||||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
|
||||||
}
|
}
|
||||||
|
|
||||||
func CreateICMPEchoResponse(packet, out []byte) []byte {
|
func CreateICMPEchoResponse(packet, out []byte) []byte {
|
||||||
|
|||||||
+5
-17
@@ -529,17 +529,6 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
|
|||||||
firstFragToUDP := []byte{17, 0, 0, 1, 0, 0, 0, 1} // frag offset 0, M=1, next = UDP
|
firstFragToUDP := []byte{17, 0, 0, 1, 0, 0, 0, 1} // frag offset 0, M=1, next = UDP
|
||||||
nonFirstFrag := []byte{17, 0, 0, 9, 0, 0, 0, 1} // frag offset non-zero, next = UDP
|
nonFirstFrag := []byte{17, 0, 0, 9, 0, 0, 0, 1} // frag offset non-zero, next = UDP
|
||||||
transport := []byte{0, 80, 1, 187, 0, 0, 0, 0} // stand-in bytes, IPv6FindUpperProtocol never reads ports
|
transport := []byte{0, 80, 1, 187, 0, 0, 0, 0} // stand-in bytes, IPv6FindUpperProtocol never reads ports
|
||||||
extToHbH := []byte{0, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = Hop-by-Hop
|
|
||||||
|
|
||||||
// 8 walked headers spend the budget before the 9th slot's terminal is ever classified. This is the
|
|
||||||
// report 4040546 shape: without failing closed the walk hands back offset 104, and a caller reads ports
|
|
||||||
// from the attacker's bytes there.
|
|
||||||
var budgetChain []byte
|
|
||||||
for range 7 {
|
|
||||||
budgetChain = append(budgetChain, extToHbH...)
|
|
||||||
}
|
|
||||||
budgetChain = append(budgetChain, extToTCP...)
|
|
||||||
budgetChain = append(budgetChain, transport...)
|
|
||||||
|
|
||||||
tests := []struct {
|
tests := []struct {
|
||||||
name string
|
name string
|
||||||
@@ -560,10 +549,9 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
|
|||||||
{"first fragment walks to transport", 44, append(firstFragToUDP, transport...), 17, ipv6.HeaderLen + 8, false, true, nil},
|
{"first fragment walks to transport", 44, append(firstFragToUDP, transport...), 17, ipv6.HeaderLen + 8, false, true, nil},
|
||||||
{"non-first fragment stops", 44, append(nonFirstFrag, transport...), 17, ipv6.HeaderLen, true, true, nil},
|
{"non-first fragment stops", 44, append(nonFirstFrag, transport...), 17, ipv6.HeaderLen, true, true, nil},
|
||||||
{"unknown protocol is terminal", 132, transport, 132, ipv6.HeaderLen, false, false, nil}, // SCTP
|
{"unknown protocol is terminal", 132, transport, 132, ipv6.HeaderLen, false, false, nil}, // SCTP
|
||||||
{"truncated extension header", 0, nil, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
|
{"truncated extension header", 0, nil, 0, ipv6.HeaderLen, false, false, ErrIPv6CouldNotFindPayload},
|
||||||
// Destination Options with a declared length (255+1)*8 = 2048 that runs past the 48 byte buffer, next = SCTP
|
// Destination Options with a declared length (255+1)*8 = 2048 that runs past the 48 byte buffer, next = SCTP
|
||||||
{"extension length past buffer", 0, []byte{132, 255, 0, 0, 0, 0, 0, 0}, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
|
{"extension length past buffer", 60, []byte{132, 255, 0, 0, 0, 0, 0, 0}, 132, ipv6.HeaderLen + 2048, false, false, ErrIPv6CouldNotFindPayload},
|
||||||
{"budget exhausted fails closed", 0, budgetChain, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
|
|
||||||
}
|
}
|
||||||
|
|
||||||
for _, tt := range tests {
|
for _, tt := range tests {
|
||||||
@@ -571,10 +559,10 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
|
|||||||
packet := makeIPv6Packet(src, dst, tt.nextHeader, tt.payload)
|
packet := makeIPv6Packet(src, dst, tt.nextHeader, tt.payload)
|
||||||
proto, offset, isFragment, anyFragment, err := IPv6FindUpperProtocol(packet)
|
proto, offset, isFragment, anyFragment, err := IPv6FindUpperProtocol(packet)
|
||||||
if tt.wantErr != nil {
|
if tt.wantErr != nil {
|
||||||
require.ErrorIs(t, err, tt.wantErr)
|
assert.ErrorIs(t, err, tt.wantErr)
|
||||||
} else {
|
return
|
||||||
require.NoError(t, err)
|
|
||||||
}
|
}
|
||||||
|
require.NoError(t, err)
|
||||||
assert.Equal(t, tt.wantProto, proto)
|
assert.Equal(t, tt.wantProto, proto)
|
||||||
assert.Equal(t, tt.wantOffset, offset)
|
assert.Equal(t, tt.wantOffset, offset)
|
||||||
assert.Equal(t, tt.wantFragment, isFragment)
|
assert.Equal(t, tt.wantFragment, isFragment)
|
||||||
|
|||||||
+1
-28
@@ -19,7 +19,6 @@ import (
|
|||||||
"github.com/slackhq/nebula/config"
|
"github.com/slackhq/nebula/config"
|
||||||
"github.com/slackhq/nebula/header"
|
"github.com/slackhq/nebula/header"
|
||||||
"github.com/slackhq/nebula/logging"
|
"github.com/slackhq/nebula/logging"
|
||||||
"github.com/slackhq/nebula/nicfinder"
|
|
||||||
"github.com/slackhq/nebula/udp"
|
"github.com/slackhq/nebula/udp"
|
||||||
"github.com/slackhq/nebula/util"
|
"github.com/slackhq/nebula/util"
|
||||||
)
|
)
|
||||||
@@ -43,10 +42,6 @@ type LightHouse struct {
|
|||||||
// addresses rather than whatever this machine's NICs happen to be. Set it before Start.
|
// addresses rather than whatever this machine's NICs happen to be. Set it before Start.
|
||||||
localAddrsFn func(*LocalAllowList) []netip.Addr
|
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
|
// Local cache of answers from light houses
|
||||||
// map of vpn addr to answers
|
// map of vpn addr to answers
|
||||||
addrMap map[netip.Addr]*RemoteList
|
addrMap map[netip.Addr]*RemoteList
|
||||||
@@ -120,9 +115,7 @@ func NewLightHouseFromConfig(ctx context.Context, l *slog.Logger, c *config.C, c
|
|||||||
l: l,
|
l: l,
|
||||||
}
|
}
|
||||||
h.localAddrsFn = func(al *LocalAllowList) []netip.Addr {
|
h.localAddrsFn = func(al *LocalAllowList) []netip.Addr {
|
||||||
addrs, err := nicfinder.Find(ctx, h.l, al)
|
return localAddrs(h.l, al)
|
||||||
h.logLocalAddrsErr(err)
|
|
||||||
return addrs
|
|
||||||
}
|
}
|
||||||
|
|
||||||
lighthouses := make([]netip.Addr, 0)
|
lighthouses := make([]netip.Addr, 0)
|
||||||
@@ -923,26 +916,6 @@ 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() {
|
func (lh *LightHouse) SendUpdate() {
|
||||||
var v4 []*V4AddrPort
|
var v4 []*V4AddrPort
|
||||||
var v6 []*V6AddrPort
|
var v6 []*V6AddrPort
|
||||||
|
|||||||
@@ -1,9 +1,7 @@
|
|||||||
package nebula
|
package nebula
|
||||||
|
|
||||||
import (
|
import (
|
||||||
"bytes"
|
|
||||||
"encoding/binary"
|
"encoding/binary"
|
||||||
"errors"
|
|
||||||
"fmt"
|
"fmt"
|
||||||
"net/netip"
|
"net/netip"
|
||||||
"testing"
|
"testing"
|
||||||
@@ -766,32 +764,3 @@ func TestLighthouse_DeletesWork(t *testing.T) {
|
|||||||
out = lh.Query(testHost)
|
out = lh.Query(testHost)
|
||||||
assert.Nil(t, out)
|
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")
|
|
||||||
}
|
|
||||||
@@ -32,12 +32,9 @@ const _ = noiseutil.RejectHeadroom - 4*maxRoutines
|
|||||||
|
|
||||||
func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, deviceFactory overlay.DeviceFactory) (retcon *Control, reterr error) {
|
func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, deviceFactory overlay.DeviceFactory) (retcon *Control, reterr error) {
|
||||||
ctx, cancel := context.WithCancel(context.Background())
|
ctx, cancel := context.WithCancel(context.Background())
|
||||||
// The goroutines started below stop only when this context does, and only a caller holding the
|
// Automatically cancel the context if Main returns an error, to signal all created goroutines to quit.
|
||||||
// Control can arrange that. Cancel whenever we are not handing one back, which covers an error
|
|
||||||
// and a config test alike: a config test used to leave the lighthouse query worker, and a
|
|
||||||
// hostname resolver per dns named static host, running for the life of the process.
|
|
||||||
defer func() {
|
defer func() {
|
||||||
if retcon == nil {
|
if reterr != nil {
|
||||||
cancel()
|
cancel()
|
||||||
}
|
}
|
||||||
}()
|
}()
|
||||||
@@ -213,7 +210,6 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
|||||||
}
|
}
|
||||||
|
|
||||||
hostMap := NewHostMapFromConfig(l, c)
|
hostMap := NewHostMapFromConfig(l, c)
|
||||||
hostMap.established = newEstablishedRemotes(udpConns)
|
|
||||||
punchy := NewPunchyFromConfig(l, c, udpConns[0])
|
punchy := NewPunchyFromConfig(l, c, udpConns[0])
|
||||||
connManager := newConnectionManagerFromConfig(l, c, hostMap, punchy)
|
connManager := newConnectionManagerFromConfig(l, c, hostMap, punchy)
|
||||||
lightHouse, err := NewLightHouseFromConfig(ctx, l, c, pki.getCertState(), udpConns[0], punchy)
|
lightHouse, err := NewLightHouseFromConfig(ctx, l, c, pki.getCertState(), udpConns[0], punchy)
|
||||||
|
|||||||
@@ -1,21 +1,12 @@
|
|||||||
package nebula
|
package nebula
|
||||||
|
|
||||||
import (
|
import (
|
||||||
"fmt"
|
|
||||||
"net/netip"
|
|
||||||
"os"
|
|
||||||
"path/filepath"
|
|
||||||
"testing"
|
"testing"
|
||||||
"time"
|
|
||||||
|
|
||||||
"github.com/slackhq/nebula/cert"
|
|
||||||
cert_test "github.com/slackhq/nebula/cert_test"
|
|
||||||
"github.com/slackhq/nebula/config"
|
"github.com/slackhq/nebula/config"
|
||||||
"github.com/slackhq/nebula/test"
|
"github.com/slackhq/nebula/test"
|
||||||
"github.com/slackhq/nebula/util"
|
"github.com/slackhq/nebula/util"
|
||||||
"github.com/stretchr/testify/assert"
|
"github.com/stretchr/testify/assert"
|
||||||
"github.com/stretchr/testify/require"
|
|
||||||
"go.uber.org/goleak"
|
|
||||||
)
|
)
|
||||||
|
|
||||||
func TestParseCpuAffinity(t *testing.T) {
|
func TestParseCpuAffinity(t *testing.T) {
|
||||||
@@ -58,68 +49,3 @@ func TestParseCpuAffinity(t *testing.T) {
|
|||||||
assert.Nil(t, parseCpuAffinity(newConfig([]any{1 << 20}), l, 1))
|
assert.Nil(t, parseCpuAffinity(newConfig([]any{1 << 20}), l, 1))
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// TestMain_ConfigTestReleasesItsGoroutines pins the rule that Main only leaves goroutines running
|
|
||||||
// when it hands back a Control to stop them with.
|
|
||||||
//
|
|
||||||
// A config test gets no Control, so anything it started had nothing to stop it: the lighthouse
|
|
||||||
// query worker, and a hostname resolver per dns named static host, ran for the life of the
|
|
||||||
// process. That matters to every embedder that validates a config in process rather than by
|
|
||||||
// exec'ing, dnclient and the apple clients included, because they do it on each config load and
|
|
||||||
// the leak accumulates.
|
|
||||||
func TestMain_ConfigTestReleasesItsGoroutines(t *testing.T) {
|
|
||||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
|
||||||
|
|
||||||
l := test.NewLogger()
|
|
||||||
dir := t.TempDir()
|
|
||||||
|
|
||||||
before := time.Now().Add(-time.Hour)
|
|
||||||
after := time.Now().Add(time.Hour)
|
|
||||||
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, before, after, nil, nil, nil)
|
|
||||||
networks := []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")}
|
|
||||||
_, _, keyPEM, certPEM := cert_test.NewTestCert(
|
|
||||||
cert.Version2, cert.Curve_CURVE25519, ca, caKey, "config-test", before, after, networks, nil, nil)
|
|
||||||
|
|
||||||
caPath := filepath.Join(dir, "ca.pem")
|
|
||||||
certPath := filepath.Join(dir, "cert.pem")
|
|
||||||
keyPath := filepath.Join(dir, "key.pem")
|
|
||||||
require.NoError(t, os.WriteFile(caPath, caPEM, 0o600))
|
|
||||||
require.NoError(t, os.WriteFile(certPath, certPEM, 0o600))
|
|
||||||
require.NoError(t, os.WriteFile(keyPath, keyPEM, 0o600))
|
|
||||||
|
|
||||||
// A static host by address, not by name: the query worker is the goroutine under test and a
|
|
||||||
// hostname would drag a real dns lookup into a unit test.
|
|
||||||
configBody := fmt.Sprintf(`
|
|
||||||
pki:
|
|
||||||
ca: %s
|
|
||||||
cert: %s
|
|
||||||
key: %s
|
|
||||||
static_host_map:
|
|
||||||
"10.0.0.2": ["192.0.2.1:4242"]
|
|
||||||
lighthouse:
|
|
||||||
hosts:
|
|
||||||
- "10.0.0.2"
|
|
||||||
listen:
|
|
||||||
host: 127.0.0.1
|
|
||||||
port: 0
|
|
||||||
tun:
|
|
||||||
disabled: true
|
|
||||||
firewall:
|
|
||||||
outbound:
|
|
||||||
- port: any
|
|
||||||
proto: any
|
|
||||||
host: any
|
|
||||||
inbound:
|
|
||||||
- port: any
|
|
||||||
proto: any
|
|
||||||
host: any
|
|
||||||
`, caPath, certPath, keyPath)
|
|
||||||
require.NoError(t, os.WriteFile(filepath.Join(dir, "config.yml"), []byte(configBody), 0o600))
|
|
||||||
|
|
||||||
c := config.NewC(l)
|
|
||||||
require.NoError(t, c.Load(dir))
|
|
||||||
|
|
||||||
ctrl, err := Main(c, true, "config-test", l, nil)
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.Nil(t, ctrl, "a config test hands back nothing to stop, so it must stop itself")
|
|
||||||
}
|
|
||||||
@@ -1,39 +0,0 @@
|
|||||||
//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...)
|
|
||||||
}
|
|
||||||
@@ -1,104 +0,0 @@
|
|||||||
//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
|
|
||||||
}
|
|
||||||
@@ -1,59 +0,0 @@
|
|||||||
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
|
|
||||||
}
|
|
||||||
@@ -1,117 +0,0 @@
|
|||||||
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")
|
|
||||||
}
|
|
||||||
+10
-73
@@ -2,14 +2,13 @@ package noiseutil
|
|||||||
|
|
||||||
import (
|
import (
|
||||||
"bytes"
|
"bytes"
|
||||||
|
"crypto/aes"
|
||||||
"crypto/cipher"
|
"crypto/cipher"
|
||||||
"crypto/fips140"
|
"crypto/fips140"
|
||||||
"encoding/binary"
|
"encoding/binary"
|
||||||
"errors"
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
"reflect"
|
|
||||||
"runtime"
|
"runtime"
|
||||||
"unsafe"
|
|
||||||
|
|
||||||
// unsafe needed for go:linkname
|
// unsafe needed for go:linkname
|
||||||
_ "crypto/tls"
|
_ "crypto/tls"
|
||||||
@@ -18,16 +17,6 @@ import (
|
|||||||
"github.com/flynn/noise"
|
"github.com/flynn/noise"
|
||||||
)
|
)
|
||||||
|
|
||||||
// TODO: Use NewGCMWithCounterNonce or NewGCMForQUIC once available:
|
|
||||||
// - https://github.com/golang/go/issues/73110
|
|
||||||
// - https://github.com/golang/go/issues/79219
|
|
||||||
// Using tls.aeadAESGCMTLS13 gives us the TLS 1.3 GCM, which also verifies
|
|
||||||
// that the nonce is strictly increasing. This works for both boringcrypto
|
|
||||||
// and fips140.
|
|
||||||
//
|
|
||||||
//go:linkname aeadAESGCMTLS13 crypto/tls.aeadAESGCMTLS13
|
|
||||||
func aeadAESGCMTLS13(key, noncePrefix []byte) cipher.AEAD
|
|
||||||
|
|
||||||
type cipherFn struct {
|
type cipherFn struct {
|
||||||
fn func([32]byte) noise.Cipher
|
fn func([32]byte) noise.Cipher
|
||||||
name string
|
name string
|
||||||
@@ -43,8 +32,14 @@ var CipherAESGCMFIPS140 noise.CipherFunc = cipherFn{cipherAESGCMFIPS140, "AESGCM
|
|||||||
var emptyNonce = []byte{0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}
|
var emptyNonce = []byte{0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}
|
||||||
|
|
||||||
func cipherAESGCMFIPS140(k [32]byte) noise.Cipher {
|
func cipherAESGCMFIPS140(k [32]byte) noise.Cipher {
|
||||||
gcm := aeadAESGCMTLS13(k[:], emptyNonce)
|
c, err := aes.NewCipher(k[:])
|
||||||
gcm = extractFIPSAEAD(gcm)
|
if err != nil {
|
||||||
|
panic(err)
|
||||||
|
}
|
||||||
|
gcm, err := cipher.NewGCMWithCounterNonce(c)
|
||||||
|
if err != nil {
|
||||||
|
panic(err)
|
||||||
|
}
|
||||||
return &aeadGCMFIPS140Cipher{
|
return &aeadGCMFIPS140Cipher{
|
||||||
AEAD: gcm,
|
AEAD: gcm,
|
||||||
}
|
}
|
||||||
@@ -52,57 +47,6 @@ func cipherAESGCMFIPS140(k [32]byte) noise.Cipher {
|
|||||||
|
|
||||||
type aeadGCMFIPS140Cipher struct {
|
type aeadGCMFIPS140Cipher struct {
|
||||||
cipher.AEAD
|
cipher.AEAD
|
||||||
ready bool
|
|
||||||
}
|
|
||||||
|
|
||||||
// Extract the internal FIPS GCM implementation from the tls wrapper. The TLS
|
|
||||||
// wrapper is not thread safe around Open, so instead of locking around it we
|
|
||||||
// can grab the internal implementation that is thread safe. This is the FIPS
|
|
||||||
// module implementation: `crypto/internal/fips140/aes/gcm.GCMWithXORCounterNonce`
|
|
||||||
//
|
|
||||||
// - https://github.com/golang/go/blob/go1.26.4/src/crypto/internal/fips140/aes/gcm/gcm_nonces.go#L212-L287
|
|
||||||
//
|
|
||||||
// The wrapper is struct `crypto/tls.xorNonceAEAD` , with field `aead`:
|
|
||||||
//
|
|
||||||
// - https://github.com/golang/go/blob/go1.26.4/src/crypto/tls/cipher_suites.go#L482-L487
|
|
||||||
//
|
|
||||||
// This can be cleaned up once these FIPS implementations are exposed directly:
|
|
||||||
//
|
|
||||||
// - https://github.com/golang/go/issues/73110
|
|
||||||
func extractFIPSAEAD(xorNonceAEAD cipher.AEAD) cipher.AEAD {
|
|
||||||
r := reflect.ValueOf(xorNonceAEAD)
|
|
||||||
v := r.Elem().FieldByName("aead")
|
|
||||||
if !v.IsValid() {
|
|
||||||
// The internal crypto/tls.xorNonceAEAD struct no longer has an `aead`
|
|
||||||
// field. This can only happen on a Go version this code was not built
|
|
||||||
// against; the package init() self-test guards against ever reaching
|
|
||||||
// this at runtime, so this is a defensive fail-fast.
|
|
||||||
panic(fmt.Sprintf("noiseutil: could not extract FIPS AEAD from %T on %s: no `aead` field (incompatible Go version)", xorNonceAEAD, runtime.Version()))
|
|
||||||
}
|
|
||||||
v2 := reflect.NewAt(v.Type(), unsafe.Pointer(v.UnsafeAddr())).Elem()
|
|
||||||
aead, ok := v2.Interface().(cipher.AEAD)
|
|
||||||
if !ok {
|
|
||||||
panic(fmt.Sprintf("noiseutil: extracted FIPS `aead` field is %s, not a cipher.AEAD, on %s (incompatible Go version)", v2.Type(), runtime.Version()))
|
|
||||||
}
|
|
||||||
return aead
|
|
||||||
}
|
|
||||||
|
|
||||||
func (c *aeadGCMFIPS140Cipher) init(nonce []byte) {
|
|
||||||
// GCMWithXORCounterNonce expects that the first call to Seal
|
|
||||||
// is with a counter of `0`, this is how it extracts the nonce mask.
|
|
||||||
// We can clean this up in the future when NewGCMWithCounterNonce or
|
|
||||||
// NewGCMForQUIC are available:
|
|
||||||
if !bytes.Equal(emptyNonce, nonce) {
|
|
||||||
c.AEAD.Seal([]byte{}, emptyNonce, []byte{}, []byte{})
|
|
||||||
}
|
|
||||||
c.ready = true
|
|
||||||
}
|
|
||||||
|
|
||||||
func (c *aeadGCMFIPS140Cipher) Seal(dst, nonce, plaintext, additionalData []byte) []byte {
|
|
||||||
if !c.ready {
|
|
||||||
c.init(nonce)
|
|
||||||
}
|
|
||||||
return c.AEAD.Seal(dst, nonce, plaintext, additionalData)
|
|
||||||
}
|
}
|
||||||
|
|
||||||
func (c *aeadGCMFIPS140Cipher) Encrypt(out []byte, n uint64, ad, plaintext []byte) []byte {
|
func (c *aeadGCMFIPS140Cipher) Encrypt(out []byte, n uint64, ad, plaintext []byte) []byte {
|
||||||
@@ -133,15 +77,8 @@ func (c *aeadGCMFIPS140Cipher) DecryptDanger(out, ad, ciphertext []byte, n uint6
|
|||||||
return c.Open(out, nb, ciphertext, ad)
|
return c.Open(out, nb, ciphertext, ad)
|
||||||
}
|
}
|
||||||
|
|
||||||
func (c *aeadGCMFIPS140Cipher) Overhead() int {
|
|
||||||
if c == nil {
|
|
||||||
return 0
|
|
||||||
}
|
|
||||||
return c.AEAD.Overhead()
|
|
||||||
}
|
|
||||||
|
|
||||||
func aeadGCMFIPS140CipherNonce(n uint64) []byte {
|
func aeadGCMFIPS140CipherNonce(n uint64) []byte {
|
||||||
// GCMWithXORCounterNonce uses a 4 byte static prefix and an 8 byte nonce
|
// GCMWithCounterNonce uses a 4 byte static prefix and an 8 byte nonce
|
||||||
var nonce [12]byte
|
var nonce [12]byte
|
||||||
binary.BigEndian.PutUint64(nonce[4:], n)
|
binary.BigEndian.PutUint64(nonce[4:], n)
|
||||||
return nonce[:]
|
return nonce[:]
|
||||||
|
|||||||
+1
-1
@@ -354,7 +354,7 @@ func parseV6(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
|
|||||||
// and cannot drift into misreading an unknown protocol (SCTP, GRE, etc.) as a forged transport.
|
// and cannot drift into misreading an unknown protocol (SCTP, GRE, etc.) as a forged transport.
|
||||||
proto, offset, isFragment, anyFragment, err := iputil.IPv6FindUpperProtocol(data)
|
proto, offset, isFragment, anyFragment, err := iputil.IPv6FindUpperProtocol(data)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return ErrIPv6PacketTooShort
|
||||||
}
|
}
|
||||||
|
|
||||||
fp.Protocol = proto
|
fp.Protocol = proto
|
||||||
|
|||||||
+7
-7
@@ -117,7 +117,7 @@ func Test_newPacket_v6(t *testing.T) {
|
|||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
|
|
||||||
err = newPacket(buffer.Bytes(), true, p)
|
err = newPacket(buffer.Bytes(), true, p)
|
||||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||||
|
|
||||||
// A v6 packet with a hop-by-hop extension
|
// A v6 packet with a hop-by-hop extension
|
||||||
// ICMPv6 Payload (Echo Request)
|
// ICMPv6 Payload (Echo Request)
|
||||||
@@ -151,12 +151,12 @@ func Test_newPacket_v6(t *testing.T) {
|
|||||||
// A full IPv6 header and 1 byte in the first extension, but missing
|
// A full IPv6 header and 1 byte in the first extension, but missing
|
||||||
// the length byte.
|
// the length byte.
|
||||||
err = newPacket(buffer.Bytes()[:41], true, p)
|
err = newPacket(buffer.Bytes()[:41], true, p)
|
||||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||||
|
|
||||||
// A full IPv6 header plus 1 full extension, but only 1 byte of the
|
// A full IPv6 header plus 1 full extension, but only 1 byte of the
|
||||||
// next layer, missing length byte
|
// next layer, missing length byte
|
||||||
err = newPacket(buffer.Bytes()[:49], true, p)
|
err = newPacket(buffer.Bytes()[:49], true, p)
|
||||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||||
err = nil
|
err = nil
|
||||||
|
|
||||||
// A good ICMP packet
|
// A good ICMP packet
|
||||||
@@ -354,12 +354,12 @@ func Test_newPacket_v6(t *testing.T) {
|
|||||||
|
|
||||||
// Ensure buffer bounds checking during processing, a truncated AH header can't reach the payload
|
// Ensure buffer bounds checking during processing, a truncated AH header can't reach the payload
|
||||||
err = newPacket(b[:41], true, p)
|
err = newPacket(b[:41], true, p)
|
||||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||||
|
|
||||||
// Invalid AH header
|
// Invalid AH header
|
||||||
b = buffer.Bytes()
|
b = buffer.Bytes()
|
||||||
err = newPacket(b, true, p)
|
err = newPacket(b, true, p)
|
||||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||||
}
|
}
|
||||||
|
|
||||||
func Test_newPacket_ipv6Fragment(t *testing.T) {
|
func Test_newPacket_ipv6Fragment(t *testing.T) {
|
||||||
@@ -466,7 +466,7 @@ func Test_newPacket_ipv6Fragment(t *testing.T) {
|
|||||||
|
|
||||||
// Too short of a fragment packet
|
// Too short of a fragment packet
|
||||||
err = newPacket(secondFrag[:len(secondFrag)-10], false, p)
|
err = newPacket(secondFrag[:len(secondFrag)-10], false, p)
|
||||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||||
}
|
}
|
||||||
|
|
||||||
func BenchmarkParseV6(b *testing.B) {
|
func BenchmarkParseV6(b *testing.B) {
|
||||||
@@ -707,7 +707,7 @@ func Test_newPacket_v6ExtHeaderPastBuffer(t *testing.T) {
|
|||||||
pkt[40] = byte(layers.IPProtocolSCTP) // Dest Options next header = SCTP
|
pkt[40] = byte(layers.IPProtocolSCTP) // Dest Options next header = SCTP
|
||||||
pkt[41] = 255 // declared length (255+1)*8 = 2048, past the 48 byte buffer
|
pkt[41] = 255 // declared length (255+1)*8 = 2048, past the 48 byte buffer
|
||||||
|
|
||||||
require.ErrorIs(t, newPacket(pkt, true, p), iputil.ErrIPv6CouldNotFindPayload)
|
require.ErrorIs(t, newPacket(pkt, true, p), ErrIPv6PacketTooShort)
|
||||||
}
|
}
|
||||||
|
|
||||||
// Test_newPacket_v6ExtHeaderConfusion is a regression test for parseV6 walking any unrecognized
|
// Test_newPacket_v6ExtHeaderConfusion is a regression test for parseV6 walking any unrecognized
|
||||||
|
|||||||
+3
-61
@@ -29,10 +29,7 @@ type tun struct {
|
|||||||
Routes atomic.Pointer[[]Route]
|
Routes atomic.Pointer[[]Route]
|
||||||
routeTree atomic.Pointer[bart.Table[routing.Gateways]]
|
routeTree atomic.Pointer[bart.Table[routing.Gateways]]
|
||||||
linkAddr *netroute.LinkAddr
|
linkAddr *netroute.LinkAddr
|
||||||
// hostOwned means the fd arrived from the OS, which has already configured addressing, mtu
|
l *slog.Logger
|
||||||
// and routes for it. NEPacketTunnelProvider on darwin does this.
|
|
||||||
hostOwned bool
|
|
||||||
l *slog.Logger
|
|
||||||
}
|
}
|
||||||
|
|
||||||
type ifReq struct {
|
type ifReq struct {
|
||||||
@@ -152,48 +149,8 @@ func (t *tun) deviceBytes() (o [16]byte) {
|
|||||||
return
|
return
|
||||||
}
|
}
|
||||||
|
|
||||||
// newTunFromFd adopts a utun the host already created and configured, which is how a darwin
|
func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
|
||||||
// network extension is handed its device. Everything about moving packets is shared with newTun,
|
return nil, fmt.Errorf("newTunFromFd not supported in Darwin")
|
||||||
// only the setup differs: the host owns addressing and routing here.
|
|
||||||
func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip.Prefix) (*tun, error) {
|
|
||||||
if err := unix.SetNonblock(deviceFd, true); err != nil {
|
|
||||||
// We own the fd from the moment it is handed to us
|
|
||||||
_ = unix.Close(deviceFd)
|
|
||||||
return nil, fmt.Errorf("failed to set the tun fd to non-blocking mode: %w", err)
|
|
||||||
}
|
|
||||||
|
|
||||||
file := os.NewFile(uintptr(deviceFd), "/dev/tun")
|
|
||||||
t := &tun{
|
|
||||||
f: file,
|
|
||||||
Device: utunNameFromFd(deviceFd),
|
|
||||||
vpnNetworks: vpnNetworks,
|
|
||||||
DefaultMTU: c.GetInt("tun.mtu", DefaultMTU),
|
|
||||||
hostOwned: true,
|
|
||||||
l: l,
|
|
||||||
}
|
|
||||||
|
|
||||||
if err := t.reload(c, true); err != nil {
|
|
||||||
_ = file.Close()
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
|
||||||
if err := t.reload(c, false); err != nil {
|
|
||||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
|
||||||
}
|
|
||||||
})
|
|
||||||
|
|
||||||
return t, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
// utunNameFromFd asks the socket what interface it is, for logs. A blank name is not worth
|
|
||||||
// failing a tunnel over, so an error just leaves it empty.
|
|
||||||
func utunNameFromFd(fd int) string {
|
|
||||||
name, err := unix.GetsockoptString(fd, unix.AF_SYS_CONTROL, _UTUN_OPT_IFNAME)
|
|
||||||
if err != nil {
|
|
||||||
return ""
|
|
||||||
}
|
|
||||||
return name
|
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) Close() error {
|
func (t *tun) Close() error {
|
||||||
@@ -204,12 +161,6 @@ func (t *tun) Close() error {
|
|||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) Activate() error {
|
func (t *tun) Activate() error {
|
||||||
// The host handed us a configured device. Its addresses, mtu and routes come from the network
|
|
||||||
// settings it applied, and a sandboxed extension cannot change them anyway.
|
|
||||||
if t.hostOwned {
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
devName := t.deviceBytes()
|
devName := t.deviceBytes()
|
||||||
|
|
||||||
s, err := unix.Socket(
|
s, err := unix.Socket(
|
||||||
@@ -423,11 +374,6 @@ func getLinkAddr(name string) (*netroute.LinkAddr, error) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) addRoutes(logErrors bool) error {
|
func (t *tun) addRoutes(logErrors bool) error {
|
||||||
// The route tree is still ours, the system routing table is not
|
|
||||||
if t.hostOwned {
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
routes := *t.Routes.Load()
|
routes := *t.Routes.Load()
|
||||||
|
|
||||||
for _, r := range routes {
|
for _, r := range routes {
|
||||||
@@ -457,10 +403,6 @@ func (t *tun) addRoutes(logErrors bool) error {
|
|||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) removeRoutes(routes []Route) error {
|
func (t *tun) removeRoutes(routes []Route) error {
|
||||||
if t.hostOwned {
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
for _, r := range routes {
|
for _, r := range routes {
|
||||||
if !r.Install {
|
if !r.Install {
|
||||||
continue
|
continue
|
||||||
|
|||||||
@@ -15,12 +15,12 @@ import (
|
|||||||
"time"
|
"time"
|
||||||
"unsafe"
|
"unsafe"
|
||||||
|
|
||||||
"github.com/DefinedNet/netlink"
|
|
||||||
"github.com/gaissmai/bart"
|
"github.com/gaissmai/bart"
|
||||||
"github.com/slackhq/nebula/config"
|
"github.com/slackhq/nebula/config"
|
||||||
"github.com/slackhq/nebula/overlay/tio"
|
"github.com/slackhq/nebula/overlay/tio"
|
||||||
"github.com/slackhq/nebula/routing"
|
"github.com/slackhq/nebula/routing"
|
||||||
"github.com/slackhq/nebula/util"
|
"github.com/slackhq/nebula/util"
|
||||||
|
"github.com/vishvananda/netlink"
|
||||||
"golang.org/x/sys/unix"
|
"golang.org/x/sys/unix"
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|||||||
@@ -48,14 +48,6 @@ type Conn interface {
|
|||||||
Close() error
|
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{}
|
type NoopConn struct{}
|
||||||
|
|
||||||
func (NoopConn) Rebind() error {
|
func (NoopConn) Rebind() error {
|
||||||
|
|||||||
@@ -1,115 +0,0 @@
|
|||||||
//go:build !e2e_testing
|
|
||||||
|
|
||||||
package udp
|
|
||||||
|
|
||||||
import (
|
|
||||||
"log/slog"
|
|
||||||
"net"
|
|
||||||
"net/netip"
|
|
||||||
"testing"
|
|
||||||
"time"
|
|
||||||
)
|
|
||||||
|
|
||||||
// benchConnSocks opens a wildcard listener with ListenOut running, with the connected socket knobs pinned to
|
|
||||||
// their defaults and then 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()
|
|
||||||
for k, v := range map[string]string{
|
|
||||||
"NEBULA_CONNSOCKS": "8",
|
|
||||||
"NEBULA_CONNSOCK_RUN": "64",
|
|
||||||
"NEBULA_CONNSOCK_WINDOW": "1s",
|
|
||||||
"NEBULA_CONNSOCK_IDLE": "30s",
|
|
||||||
"NEBULA_CONNSOCK_OPEN_EVERY": "1s",
|
|
||||||
} {
|
|
||||||
b.Setenv(k, v)
|
|
||||||
}
|
|
||||||
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.reader.Load() == nil {
|
|
||||||
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")
|
|
||||||
}
|
|
||||||
}
|
|
||||||
})
|
|
||||||
}
|
|
||||||
}
|
|
||||||
@@ -1,803 +0,0 @@
|
|||||||
//go:build !e2e_testing
|
|
||||||
|
|
||||||
package udp
|
|
||||||
|
|
||||||
import (
|
|
||||||
"context"
|
|
||||||
"errors"
|
|
||||||
"fmt"
|
|
||||||
"log/slog"
|
|
||||||
"maps"
|
|
||||||
"net"
|
|
||||||
"net/netip"
|
|
||||||
"os"
|
|
||||||
"slices"
|
|
||||||
"strconv"
|
|
||||||
"sync"
|
|
||||||
"sync/atomic"
|
|
||||||
"syscall"
|
|
||||||
"time"
|
|
||||||
|
|
||||||
"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 one datagram on the descriptor: writeFd, or a stand-in for the interface in tests.
|
|
||||||
sys func(fd int, b []byte) error
|
|
||||||
}
|
|
||||||
|
|
||||||
func writeFd(fd int, b []byte) error {
|
|
||||||
_, err := syscall.Write(fd, b)
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
|
|
||||||
// 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
|
|
||||||
b []byte
|
|
||||||
park bool
|
|
||||||
err error
|
|
||||||
fn func(fd uintptr) bool
|
|
||||||
}
|
|
||||||
|
|
||||||
var connSockWriters = sync.Pool{New: func() any {
|
|
||||||
w := &connSockWriter{}
|
|
||||||
w.fn = w.write
|
|
||||||
return w
|
|
||||||
}}
|
|
||||||
|
|
||||||
func (w *connSockWriter) write(fd uintptr) bool {
|
|
||||||
for {
|
|
||||||
w.err = w.s.sys(int(fd), w.b)
|
|
||||||
switch {
|
|
||||||
case w.err == syscall.EINTR:
|
|
||||||
case w.err == syscall.EAGAIN && w.park:
|
|
||||||
return false
|
|
||||||
default:
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// try writes b on s once and returns nil, 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(b []byte, park bool) error {
|
|
||||||
w := connSockWriters.Get().(*connSockWriter)
|
|
||||||
w.s, w.b, w.park = s, b, park
|
|
||||||
rerr := s.rc.Write(w.fn)
|
|
||||||
err := w.err
|
|
||||||
*w = connSockWriter{fn: w.fn}
|
|
||||||
connSockWriters.Put(w)
|
|
||||||
switch {
|
|
||||||
case rerr == nil:
|
|
||||||
return err
|
|
||||||
case errors.Is(rerr, os.ErrDeadlineExceeded):
|
|
||||||
return os.ErrDeadlineExceeded
|
|
||||||
default:
|
|
||||||
return net.ErrClosed
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// connSockConfig holds the knobs. connSockConfigFromEnv reads all but backoff and enobufsMax from the environment,
|
|
||||||
// so one binary can be tuned without a rebuild.
|
|
||||||
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 connSockConfigFromEnv() connSockConfig {
|
|
||||||
c := connSockConfig{
|
|
||||||
max: 8,
|
|
||||||
run: 64,
|
|
||||||
window: time.Second,
|
|
||||||
idle: 30 * time.Second,
|
|
||||||
backoff: 30 * time.Second,
|
|
||||||
openEvery: time.Second,
|
|
||||||
enobufsMax: 10 * time.Millisecond,
|
|
||||||
}
|
|
||||||
if v, err := strconv.Atoi(os.Getenv("NEBULA_CONNSOCKS")); err == nil {
|
|
||||||
c.max = v
|
|
||||||
}
|
|
||||||
if v, err := strconv.Atoi(os.Getenv("NEBULA_CONNSOCK_RUN")); err == nil && v > 0 {
|
|
||||||
c.run = v
|
|
||||||
}
|
|
||||||
if v, err := time.ParseDuration(os.Getenv("NEBULA_CONNSOCK_WINDOW")); err == nil && v > 0 {
|
|
||||||
c.window = v
|
|
||||||
}
|
|
||||||
if v, err := time.ParseDuration(os.Getenv("NEBULA_CONNSOCK_IDLE")); err == nil && v > 0 {
|
|
||||||
c.idle = v
|
|
||||||
}
|
|
||||||
if v, err := time.ParseDuration(os.Getenv("NEBULA_CONNSOCK_OPEN_EVERY")); err == nil && v > 0 {
|
|
||||||
c.openEvery = v
|
|
||||||
}
|
|
||||||
return c
|
|
||||||
}
|
|
||||||
|
|
||||||
// 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: connSockConfigFromEnv(), 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.reader.Load() == nil || 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: writeFd}
|
|
||||||
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, one datagram per write. 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())
|
|
||||||
}
|
|
||||||
}()
|
|
||||||
for sent < len(bufs) {
|
|
||||||
err := s.try(bufs[sent], false)
|
|
||||||
if err == syscall.EAGAIN || err == os.ErrDeadlineExceeded {
|
|
||||||
// os.ErrDeadlineExceeded here is another writer's parked deadline, passed but not yet cleared.
|
|
||||||
err = u.parkedWrite(s, bufs[sent])
|
|
||||||
}
|
|
||||||
switch err {
|
|
||||||
case nil:
|
|
||||||
sent++
|
|
||||||
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) error {
|
|
||||||
cs := u.socks
|
|
||||||
s.parkMu.Lock()
|
|
||||||
defer s.parkMu.Unlock()
|
|
||||||
left := cs.cfg.enobufsMax - s.stalledFor(cs.clock())
|
|
||||||
if left <= 0 {
|
|
||||||
return errStallSpent
|
|
||||||
}
|
|
||||||
if err := s.conn.SetWriteDeadline(time.Now().Add(left)); err != nil {
|
|
||||||
return net.ErrClosed
|
|
||||||
}
|
|
||||||
err := s.try(b, true)
|
|
||||||
_ = s.conn.SetWriteDeadline(time.Time{})
|
|
||||||
if err == os.ErrDeadlineExceeded {
|
|
||||||
return errStallSpent
|
|
||||||
}
|
|
||||||
return 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 delivers a connected socket's datagrams through the listener's reader, serialized with 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) {
|
|
||||||
rd := u.reader.Load()
|
|
||||||
buf := make([]byte, MTU)
|
|
||||||
for {
|
|
||||||
n, from, err := s.conn.ReadFromUDPAddrPort(buf)
|
|
||||||
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())
|
|
||||||
u.readMu.Lock()
|
|
||||||
rd.r(netip.AddrPortFrom(from.Addr().Unmap(), from.Port()), buf[:n:n])
|
|
||||||
rd.flush()
|
|
||||||
u.readMu.Unlock()
|
|
||||||
}
|
|
||||||
}
|
|
||||||
File diff suppressed because it is too large.
Load diff
@@ -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
|
|
||||||
@@ -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
|
|
||||||
+11
-108
@@ -10,8 +10,6 @@ import (
|
|||||||
"log/slog"
|
"log/slog"
|
||||||
"net"
|
"net"
|
||||||
"net/netip"
|
"net/netip"
|
||||||
"sync"
|
|
||||||
"sync/atomic"
|
|
||||||
"syscall"
|
"syscall"
|
||||||
"unsafe"
|
"unsafe"
|
||||||
|
|
||||||
@@ -24,26 +22,9 @@ type StdConn struct {
|
|||||||
isV4 bool
|
isV4 bool
|
||||||
sysFd uintptr
|
sysFd uintptr
|
||||||
l *slog.Logger
|
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
|
|
||||||
// reader is ListenOut's reader, which connected socket readers share; readMu serializes them, since an
|
|
||||||
// EncReader isn't safe for concurrent use.
|
|
||||||
reader atomic.Pointer[readerPair]
|
|
||||||
readMu sync.Mutex
|
|
||||||
}
|
|
||||||
|
|
||||||
type readerPair struct {
|
|
||||||
r EncReader
|
|
||||||
flush func()
|
|
||||||
}
|
}
|
||||||
|
|
||||||
var _ Conn = &StdConn{}
|
var _ Conn = &StdConn{}
|
||||||
var _ EstablishedPeerConn = &StdConn{}
|
|
||||||
|
|
||||||
func NewListener(l *slog.Logger, s Settings) (Conn, error) {
|
func NewListener(l *slog.Logger, s Settings) (Conn, error) {
|
||||||
lc := NewListenConfig(s.Multi)
|
lc := NewListenConfig(s.Multi)
|
||||||
@@ -53,13 +34,12 @@ func NewListener(l *slog.Logger, s Settings) (Conn, error) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
if uc, ok := pc.(*net.UDPConn); ok {
|
if uc, ok := pc.(*net.UDPConn); ok {
|
||||||
c := &StdConn{UDPConn: uc, l: l, listenHost: s.Listen.Addr()}
|
c := &StdConn{UDPConn: uc, l: l}
|
||||||
|
|
||||||
rc, err := uc.SyscallConn()
|
rc, err := uc.SyscallConn()
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, fmt.Errorf("failed to open udp socket: %w", err)
|
return nil, fmt.Errorf("failed to open udp socket: %w", err)
|
||||||
}
|
}
|
||||||
c.rc = rc
|
|
||||||
|
|
||||||
err = rc.Control(func(fd uintptr) {
|
err = rc.Control(func(fd uintptr) {
|
||||||
c.sysFd = fd
|
c.sysFd = fd
|
||||||
@@ -73,8 +53,6 @@ func NewListener(l *slog.Logger, s Settings) (Conn, error) {
|
|||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
c.isV4 = la.Addr().Is4()
|
c.isV4 = la.Addr().Is4()
|
||||||
c.port = la.Port()
|
|
||||||
c.socks = joinConnSocks(c, la, s)
|
|
||||||
|
|
||||||
return c, nil
|
return c, nil
|
||||||
}
|
}
|
||||||
@@ -111,19 +89,6 @@ func NewListenConfig(multi bool) net.ListenConfig {
|
|||||||
func sendto(s int, buf []byte, flags int, to unsafe.Pointer, addrlen int32) (err error)
|
func sendto(s int, buf []byte, flags int, to unsafe.Pointer, addrlen int32) (err error)
|
||||||
|
|
||||||
func (u *StdConn) WriteTo(b []byte, ap netip.AddrPort) 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 sa unsafe.Pointer
|
||||||
var addrLen int32
|
var addrLen int32
|
||||||
|
|
||||||
@@ -176,47 +141,15 @@ func (u *StdConn) writeTo(b []byte, ap netip.AddrPort) error {
|
|||||||
|
|
||||||
func (u *StdConn) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, 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.
|
// 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
|
// TODO: WriteTo maps EWOULDBLOCK to an error, so a full send buffer
|
||||||
// silently drops those packets (linux blocks instead). Poll for
|
// silently drops the rest of a burst (linux blocks instead). Poll for
|
||||||
// writability on EAGAIN before giving up on them.
|
// writability on EAGAIN before giving up on the remainder.
|
||||||
written := 0
|
written := 0
|
||||||
t := u.socks.table.Load()
|
for i, b := range bufs {
|
||||||
if t == nil {
|
if err := u.WriteTo(b, addrs[i]); err == nil {
|
||||||
for i, b := range bufs {
|
written++
|
||||||
if err := u.writeTo(b, addrs[i]); err == nil {
|
} else {
|
||||||
written++
|
u.l.Debug("failed to write packet in batch", "udpAddr", addrs[i], "error", err)
|
||||||
} 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)
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
return written, nil
|
return written, nil
|
||||||
@@ -249,8 +182,6 @@ func NewUDPStatsEmitter(udpConns []Conn) func() {
|
|||||||
|
|
||||||
func (u *StdConn) ListenOut(r EncReader, flush func()) error {
|
func (u *StdConn) ListenOut(r EncReader, flush func()) error {
|
||||||
buffer := make([]byte, MTU)
|
buffer := make([]byte, MTU)
|
||||||
u.reader.Store(&readerPair{r: r, flush: flush})
|
|
||||||
u.startConnSocks()
|
|
||||||
|
|
||||||
for {
|
for {
|
||||||
// Just read one packet at a time
|
// Just read one packet at a time
|
||||||
@@ -263,29 +194,18 @@ func (u *StdConn) ListenOut(r EncReader, flush func()) error {
|
|||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|
||||||
u.readMu.Lock()
|
|
||||||
r(netip.AddrPortFrom(rua.Addr().Unmap(), rua.Port()), buffer[:n:n])
|
r(netip.AddrPortFrom(rua.Addr().Unmap(), rua.Port()), buffer[:n:n])
|
||||||
flush()
|
flush()
|
||||||
u.readMu.Unlock()
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// 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 {
|
func (u *StdConn) SupportsMultipleReaders() bool {
|
||||||
return false
|
return false
|
||||||
}
|
}
|
||||||
|
|
||||||
// Rebind clears the interface the kernel scoped this socket to, so that sends are routed against the current
|
// 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
|
// 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
|
// this way on its own, which is what strands us after the underlying network changes.
|
||||||
// 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.
|
|
||||||
func (u *StdConn) Rebind() error {
|
func (u *StdConn) Rebind() error {
|
||||||
var err error
|
var err error
|
||||||
if u.isV4 {
|
if u.isV4 {
|
||||||
@@ -293,23 +213,6 @@ func (u *StdConn) Rebind() error {
|
|||||||
} else {
|
} else {
|
||||||
err = syscall.SetsockoptInt(int(u.sysFd), syscall.IPPROTO_IPV6, syscall.IPV6_BOUND_IF, 0)
|
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
|
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
|
|
||||||
}
|
|
||||||
Reference in new issue
Block a user