mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-16 12:16:52 +01:00
Compare commits
14
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
f3b76703ae | ||
|
|
fc0dbfec4c | ||
|
|
ca69a0613b | ||
|
|
84a26846f4 | ||
|
|
317388e37d | ||
|
|
06fd191367 | ||
|
|
3f392883ca | ||
|
|
30cf2bbe6c | ||
|
|
11b04517f3 | ||
|
|
610ba57105 | ||
|
|
9e96894bd7 | ||
|
|
14f80450fb | ||
|
|
641d1fb703 | ||
|
|
11a4298c36 |
No files matched your search
+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())
|
|
||||||
}
|
|
||||||
+6
-1
@@ -449,7 +449,9 @@ firewall:
|
|||||||
#default_local_cidr_any: false
|
#default_local_cidr_any: false
|
||||||
|
|
||||||
conntrack:
|
conntrack:
|
||||||
|
# tcp_timeout also applies to sctp and dccp
|
||||||
tcp_timeout: 12m
|
tcp_timeout: 12m
|
||||||
|
# udp_timeout also applies to udplite
|
||||||
udp_timeout: 3m
|
udp_timeout: 3m
|
||||||
default_timeout: 10m
|
default_timeout: 10m
|
||||||
|
|
||||||
@@ -457,8 +459,11 @@ firewall:
|
|||||||
# Rules are comprised of a protocol, port, and one or more of host, group, or CIDR
|
# Rules are comprised of a protocol, port, and one or more of host, group, or CIDR
|
||||||
# Logical evaluation is roughly: port AND proto AND (ca_sha OR ca_name) AND (host OR group OR groups OR cidr) AND (local cidr)
|
# Logical evaluation is roughly: port AND proto AND (ca_sha OR ca_name) AND (host OR group OR groups OR cidr) AND (local cidr)
|
||||||
# - port: Takes `0` or `any` as any, a single number `80`, a range `200-901`, or `fragment` to match second and further fragments of fragmented packets (since there is no port available).
|
# - port: Takes `0` or `any` as any, a single number `80`, a range `200-901`, or `fragment` to match second and further fragments of fragmented packets (since there is no port available).
|
||||||
# proto: `any`, `tcp`, `udp`, or `icmp`
|
# proto: `any`, `tcp`, `udp`, `udplite`, `dccp`, `sctp`, `icmp`, or any other IP protocol number from 1 to 255, ie `47` for gre
|
||||||
# a port specification is ignored if proto is `icmp`
|
# a port specification is ignored if proto is `icmp`
|
||||||
|
# `icmp`, `1`, and `58` are the same, each matches both ICMP and ICMPv6
|
||||||
|
# Nebula only reads ports from tcp, udp, udplite, dccp, and sctp, so a proto `any` rule with a specific port or range only matches those protocols.
|
||||||
|
# Rules for other protocols (gre, esp, etc) need port `any`.
|
||||||
# host: `any` or a literal hostname, ie `test-host`
|
# host: `any` or a literal hostname, ie `test-host`
|
||||||
# group: `any` or a literal group name, ie `default-group`
|
# group: `any` or a literal group name, ie `default-group`
|
||||||
# groups: Same as group but accepts a list of values. Multiple values are AND'd together and a certificate would have to contain all groups to pass
|
# groups: Same as group but accepts a list of values. Multiple values are AND'd together and a certificate would have to contain all groups to pass
|
||||||
|
|||||||
+36
-755
@@ -2,17 +2,10 @@ package nebula
|
|||||||
|
|
||||||
import (
|
import (
|
||||||
"context"
|
"context"
|
||||||
"crypto/sha256"
|
|
||||||
"encoding/hex"
|
|
||||||
"errors"
|
"errors"
|
||||||
"fmt"
|
|
||||||
"hash/fnv"
|
|
||||||
"log/slog"
|
"log/slog"
|
||||||
"net/netip"
|
"net/netip"
|
||||||
"reflect"
|
|
||||||
"slices"
|
|
||||||
"strconv"
|
"strconv"
|
||||||
"strings"
|
|
||||||
"sync"
|
"sync"
|
||||||
"time"
|
"time"
|
||||||
|
|
||||||
@@ -24,10 +17,6 @@ import (
|
|||||||
"github.com/slackhq/nebula/iputil"
|
"github.com/slackhq/nebula/iputil"
|
||||||
)
|
)
|
||||||
|
|
||||||
type FirewallInterface interface {
|
|
||||||
AddRule(incoming bool, proto uint8, startPort int32, endPort int32, groups []string, host string, cidr, localCidr string, caName string, caSha string) error
|
|
||||||
}
|
|
||||||
|
|
||||||
type conn struct {
|
type conn struct {
|
||||||
Expires time.Time // Time when this conntrack entry will expire
|
Expires time.Time // Time when this conntrack entry will expire
|
||||||
|
|
||||||
@@ -42,8 +31,7 @@ type conn struct {
|
|||||||
type Firewall struct {
|
type Firewall struct {
|
||||||
Conntrack *FirewallConntrack
|
Conntrack *FirewallConntrack
|
||||||
|
|
||||||
InRules *FirewallTable
|
rules firewall.Rules
|
||||||
OutRules *FirewallTable
|
|
||||||
|
|
||||||
InboundSendReject bool
|
InboundSendReject bool
|
||||||
OutboundSendReject bool
|
OutboundSendReject bool
|
||||||
@@ -63,10 +51,8 @@ type Firewall struct {
|
|||||||
// unsafeNetworks is the list of unsafe networks issued to us in the certificate
|
// unsafeNetworks is the list of unsafe networks issued to us in the certificate
|
||||||
unsafeNetworks []netip.Prefix
|
unsafeNetworks []netip.Prefix
|
||||||
|
|
||||||
rules string
|
|
||||||
rulesVersion uint16
|
rulesVersion uint16
|
||||||
|
|
||||||
defaultLocalCIDRAny bool
|
|
||||||
incomingMetrics firewallMetrics
|
incomingMetrics firewallMetrics
|
||||||
outgoingMetrics firewallMetrics
|
outgoingMetrics firewallMetrics
|
||||||
|
|
||||||
@@ -86,52 +72,6 @@ type FirewallConntrack struct {
|
|||||||
TimerWheel *TimerWheel[firewall.Packet]
|
TimerWheel *TimerWheel[firewall.Packet]
|
||||||
}
|
}
|
||||||
|
|
||||||
// FirewallTable is the entry point for a rule, the evaluation order is:
|
|
||||||
// Proto AND port AND (CA SHA or CA name) AND local CIDR AND (group OR groups OR name OR remote CIDR)
|
|
||||||
type FirewallTable struct {
|
|
||||||
TCP firewallPort
|
|
||||||
UDP firewallPort
|
|
||||||
ICMP firewallPort
|
|
||||||
AnyProto firewallPort
|
|
||||||
}
|
|
||||||
|
|
||||||
func newFirewallTable() *FirewallTable {
|
|
||||||
return &FirewallTable{
|
|
||||||
TCP: firewallPort{},
|
|
||||||
UDP: firewallPort{},
|
|
||||||
ICMP: firewallPort{},
|
|
||||||
AnyProto: firewallPort{},
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
type FirewallCA struct {
|
|
||||||
Any *FirewallRule
|
|
||||||
CANames map[string]*FirewallRule
|
|
||||||
CAShas map[string]*FirewallRule
|
|
||||||
}
|
|
||||||
|
|
||||||
type FirewallRule struct {
|
|
||||||
// Any makes Hosts, Groups, and CIDR irrelevant
|
|
||||||
Any *firewallLocalCIDR
|
|
||||||
Hosts map[string]*firewallLocalCIDR
|
|
||||||
Groups []*firewallGroups
|
|
||||||
CIDR *bart.Table[*firewallLocalCIDR]
|
|
||||||
}
|
|
||||||
|
|
||||||
type firewallGroups struct {
|
|
||||||
Groups []string
|
|
||||||
LocalCIDR *firewallLocalCIDR
|
|
||||||
}
|
|
||||||
|
|
||||||
// Even though ports are uint16, int32 maps are faster for lookup
|
|
||||||
// Plus we can use `-1` for fragment rules
|
|
||||||
type firewallPort map[int32]*FirewallCA
|
|
||||||
|
|
||||||
type firewallLocalCIDR struct {
|
|
||||||
Any bool
|
|
||||||
LocalCIDR *bart.Lite
|
|
||||||
}
|
|
||||||
|
|
||||||
// NewFirewall creates a new Firewall object. A TimerWheel is created for you from the provided timeouts.
|
// NewFirewall creates a new Firewall object. A TimerWheel is created for you from the provided timeouts.
|
||||||
// The certificate provided should be the highest version loaded in memory.
|
// The certificate provided should be the highest version loaded in memory.
|
||||||
func NewFirewall(l *slog.Logger, tcpTimeout, UDPTimeout, defaultTimeout time.Duration, c cert.Certificate) *Firewall {
|
func NewFirewall(l *slog.Logger, tcpTimeout, UDPTimeout, defaultTimeout time.Duration, c cert.Certificate) *Firewall {
|
||||||
@@ -170,8 +110,8 @@ func NewFirewall(l *slog.Logger, tcpTimeout, UDPTimeout, defaultTimeout time.Dur
|
|||||||
Conns: make(map[firewall.Packet]*conn),
|
Conns: make(map[firewall.Packet]*conn),
|
||||||
TimerWheel: NewTimerWheel[firewall.Packet](tmin, tmax),
|
TimerWheel: NewTimerWheel[firewall.Packet](tmin, tmax),
|
||||||
},
|
},
|
||||||
InRules: newFirewallTable(),
|
// Nothing is allowed until there are rules
|
||||||
OutRules: newFirewallTable(),
|
rules: firewall.NewRulesBuilder(l).Build(assignedNetworks, unsafeNetworks),
|
||||||
TCPTimeout: tcpTimeout,
|
TCPTimeout: tcpTimeout,
|
||||||
UDPTimeout: UDPTimeout,
|
UDPTimeout: UDPTimeout,
|
||||||
DefaultTimeout: defaultTimeout,
|
DefaultTimeout: defaultTimeout,
|
||||||
@@ -212,8 +152,6 @@ func NewFirewallFromConfig(l *slog.Logger, cs *CertState, c *config.C) (*Firewal
|
|||||||
//TODO: max_connections
|
//TODO: max_connections
|
||||||
)
|
)
|
||||||
|
|
||||||
fw.defaultLocalCIDRAny = c.GetBool("firewall.default_local_cidr_any", false)
|
|
||||||
|
|
||||||
inboundAction := c.GetString("firewall.inbound_action", "drop")
|
inboundAction := c.GetString("firewall.inbound_action", "drop")
|
||||||
switch inboundAction {
|
switch inboundAction {
|
||||||
case "reject":
|
case "reject":
|
||||||
@@ -236,80 +174,23 @@ func NewFirewallFromConfig(l *slog.Logger, cs *CertState, c *config.C) (*Firewal
|
|||||||
fw.OutboundSendReject = false
|
fw.OutboundSendReject = false
|
||||||
}
|
}
|
||||||
|
|
||||||
err := AddFirewallRulesFromConfig(l, false, c, fw)
|
rules, err := firewall.RulesFromConfig(l, c, fw.assignedNetworks, fw.unsafeNetworks)
|
||||||
if err != nil {
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
|
|
||||||
err = AddFirewallRulesFromConfig(l, true, c, fw)
|
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
|
fw.rules = rules
|
||||||
|
|
||||||
return fw, nil
|
return fw, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
// AddRule properly creates the in memory rule structure for a firewall table.
|
|
||||||
func (f *Firewall) AddRule(incoming bool, proto uint8, startPort int32, endPort int32, groups []string, host string, cidr, localCidr, caName string, caSha string) error {
|
|
||||||
var (
|
|
||||||
ft *FirewallTable
|
|
||||||
fp firewallPort
|
|
||||||
)
|
|
||||||
|
|
||||||
if incoming {
|
|
||||||
ft = f.InRules
|
|
||||||
} else {
|
|
||||||
ft = f.OutRules
|
|
||||||
}
|
|
||||||
|
|
||||||
switch proto {
|
|
||||||
case iputil.IPProtocolTCP:
|
|
||||||
fp = ft.TCP
|
|
||||||
case iputil.IPProtocolUDP:
|
|
||||||
fp = ft.UDP
|
|
||||||
case iputil.IPProtocolICMP, iputil.IPProtocolICMPv6:
|
|
||||||
//ICMP traffic doesn't have ports, so we always coerce to "any", even if a value is provided
|
|
||||||
if startPort != firewall.PortAny {
|
|
||||||
f.l.Warn("ignoring port specification for ICMP firewall rule", "startPort", startPort)
|
|
||||||
}
|
|
||||||
startPort = firewall.PortAny
|
|
||||||
endPort = firewall.PortAny
|
|
||||||
fp = ft.ICMP
|
|
||||||
case firewall.ProtoAny:
|
|
||||||
fp = ft.AnyProto
|
|
||||||
default:
|
|
||||||
return fmt.Errorf("unknown protocol %v", proto)
|
|
||||||
}
|
|
||||||
|
|
||||||
// We need this rule string because we generate a hash. Removing this will break firewall reload.
|
|
||||||
ruleString := fmt.Sprintf(
|
|
||||||
"incoming: %v, proto: %v, startPort: %v, endPort: %v, groups: %v, host: %v, ip: %v, localIp: %v, caName: %v, caSha: %s",
|
|
||||||
incoming, proto, startPort, endPort, groups, host, cidr, localCidr, caName, caSha,
|
|
||||||
)
|
|
||||||
f.rules += ruleString + "\n"
|
|
||||||
|
|
||||||
direction := "incoming"
|
|
||||||
if !incoming {
|
|
||||||
direction = "outgoing"
|
|
||||||
}
|
|
||||||
f.l.Info("Firewall rule added",
|
|
||||||
"firewallRule", m{"direction": direction, "proto": proto, "startPort": startPort, "endPort": endPort, "groups": groups, "host": host, "cidr": cidr, "localCidr": localCidr, "caName": caName, "caSha": caSha},
|
|
||||||
)
|
|
||||||
|
|
||||||
return fp.addRule(f, startPort, endPort, groups, host, cidr, localCidr, caName, caSha)
|
|
||||||
}
|
|
||||||
|
|
||||||
// GetRuleHash returns a hash representation of all inbound and outbound rules
|
// GetRuleHash returns a hash representation of all inbound and outbound rules
|
||||||
func (f *Firewall) GetRuleHash() string {
|
func (f *Firewall) GetRuleHash() string {
|
||||||
sum := sha256.Sum256([]byte(f.rules))
|
return f.rules.Hash
|
||||||
return hex.EncodeToString(sum[:])
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// GetRuleHashFNV returns a uint32 FNV-1 hash representation the rules, for use as a metric value
|
// GetRuleHashFNV returns a uint32 FNV-1 hash representation the rules, for use as a metric value
|
||||||
func (f *Firewall) GetRuleHashFNV() uint32 {
|
func (f *Firewall) GetRuleHashFNV() uint32 {
|
||||||
h := fnv.New32a()
|
return f.rules.HashFNV
|
||||||
h.Write([]byte(f.rules))
|
|
||||||
return h.Sum32()
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// GetRuleHashes returns both the sha256 and FNV-1 hashes, suitable for logging
|
// GetRuleHashes returns both the sha256 and FNV-1 hashes, suitable for logging
|
||||||
@@ -317,104 +198,6 @@ func (f *Firewall) GetRuleHashes() string {
|
|||||||
return "SHA:" + f.GetRuleHash() + ",FNV:" + strconv.FormatUint(uint64(f.GetRuleHashFNV()), 10)
|
return "SHA:" + f.GetRuleHash() + ",FNV:" + strconv.FormatUint(uint64(f.GetRuleHashFNV()), 10)
|
||||||
}
|
}
|
||||||
|
|
||||||
func AddFirewallRulesFromConfig(l *slog.Logger, inbound bool, c *config.C, fw FirewallInterface) error {
|
|
||||||
var table string
|
|
||||||
if inbound {
|
|
||||||
table = "firewall.inbound"
|
|
||||||
} else {
|
|
||||||
table = "firewall.outbound"
|
|
||||||
}
|
|
||||||
|
|
||||||
r := c.Get(table)
|
|
||||||
if r == nil {
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
rs, ok := r.([]any)
|
|
||||||
if !ok {
|
|
||||||
return fmt.Errorf("%s failed to parse, should be an array of rules", table)
|
|
||||||
}
|
|
||||||
|
|
||||||
for i, t := range rs {
|
|
||||||
r, err := convertRule(l, t, table, i)
|
|
||||||
if err != nil {
|
|
||||||
return fmt.Errorf("%s rule #%v; %s", table, i, err)
|
|
||||||
}
|
|
||||||
|
|
||||||
if r.Code != "" && r.Port != "" {
|
|
||||||
return fmt.Errorf("%s rule #%v; only one of port or code should be provided", table, i)
|
|
||||||
}
|
|
||||||
|
|
||||||
if r.Host == "" && len(r.Groups) == 0 && r.Cidr == "" && r.LocalCidr == "" && r.CAName == "" && r.CASha == "" {
|
|
||||||
return fmt.Errorf("%s rule #%v; at least one of host, group, cidr, local_cidr, ca_name, or ca_sha must be provided", table, i)
|
|
||||||
}
|
|
||||||
|
|
||||||
var sPort, errPort string
|
|
||||||
if r.Code != "" {
|
|
||||||
errPort = "code"
|
|
||||||
sPort = r.Code
|
|
||||||
} else {
|
|
||||||
errPort = "port"
|
|
||||||
sPort = r.Port
|
|
||||||
}
|
|
||||||
|
|
||||||
var proto uint8
|
|
||||||
var startPort, endPort int32
|
|
||||||
switch r.Proto {
|
|
||||||
case "any":
|
|
||||||
proto = firewall.ProtoAny
|
|
||||||
startPort, endPort, err = parsePort(sPort)
|
|
||||||
case "tcp":
|
|
||||||
proto = iputil.IPProtocolTCP
|
|
||||||
startPort, endPort, err = parsePort(sPort)
|
|
||||||
case "udp":
|
|
||||||
proto = iputil.IPProtocolUDP
|
|
||||||
startPort, endPort, err = parsePort(sPort)
|
|
||||||
case "icmp":
|
|
||||||
proto = iputil.IPProtocolICMP
|
|
||||||
startPort = firewall.PortAny
|
|
||||||
endPort = firewall.PortAny
|
|
||||||
if sPort != "" {
|
|
||||||
l.Warn("ignoring port specification for ICMP firewall rule", "port", sPort)
|
|
||||||
}
|
|
||||||
default:
|
|
||||||
return fmt.Errorf("%s rule #%v; proto was not understood; `%s`", table, i, r.Proto)
|
|
||||||
}
|
|
||||||
if err != nil {
|
|
||||||
return fmt.Errorf("%s rule #%v; %s %s", table, i, errPort, err)
|
|
||||||
}
|
|
||||||
|
|
||||||
if r.Cidr != "" && r.Cidr != "any" {
|
|
||||||
_, err = netip.ParsePrefix(r.Cidr)
|
|
||||||
if err != nil {
|
|
||||||
return fmt.Errorf("%s rule #%v; cidr did not parse; %s", table, i, err)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if r.LocalCidr != "" && r.LocalCidr != "any" {
|
|
||||||
_, err = netip.ParsePrefix(r.LocalCidr)
|
|
||||||
if err != nil {
|
|
||||||
return fmt.Errorf("%s rule #%v; local_cidr did not parse; %s", table, i, err)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if warning := r.sanity(); warning != nil {
|
|
||||||
l.Warn("firewall rule sanity check",
|
|
||||||
"table", table,
|
|
||||||
"rule", i,
|
|
||||||
"warning", warning,
|
|
||||||
)
|
|
||||||
}
|
|
||||||
|
|
||||||
err = fw.AddRule(inbound, proto, startPort, endPort, r.Groups, r.Host, r.Cidr, r.LocalCidr, r.CAName, r.CASha)
|
|
||||||
if err != nil {
|
|
||||||
return fmt.Errorf("%s rule #%v; `%s`", table, i, err)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
var ErrUnknownNetworkType = errors.New("unknown network type")
|
var ErrUnknownNetworkType = errors.New("unknown network type")
|
||||||
var ErrPeerRejected = errors.New("remote address is not within a network that we handle")
|
var ErrPeerRejected = errors.New("remote address is not within a network that we handle")
|
||||||
var ErrInvalidRemoteIP = errors.New("remote address is not in remote certificate networks")
|
var ErrInvalidRemoteIP = errors.New("remote address is not in remote certificate networks")
|
||||||
@@ -458,23 +241,17 @@ func (f *Firewall) Drop(fp firewall.Packet, incoming bool, h *HostInfo, caPool *
|
|||||||
}
|
}
|
||||||
|
|
||||||
// Check if we spoke to this tuple, if we did then allow this packet
|
// Check if we spoke to this tuple, if we did then allow this packet
|
||||||
if f.inConns(fp, h, caPool, localCache) {
|
if f.inConns(&fp, h, caPool, localCache) {
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
table := f.OutRules
|
if !f.rules.Match(&fp, incoming, h.ConnectionState.peerCert, caPool) {
|
||||||
if incoming {
|
|
||||||
table = f.InRules
|
|
||||||
}
|
|
||||||
|
|
||||||
// We now know which firewall table to check against
|
|
||||||
if !table.match(fp, incoming, h.ConnectionState.peerCert, caPool) {
|
|
||||||
f.metrics(incoming).droppedNoRule.Inc(1)
|
f.metrics(incoming).droppedNoRule.Inc(1)
|
||||||
return ErrNoMatchingRule
|
return ErrNoMatchingRule
|
||||||
}
|
}
|
||||||
|
|
||||||
// We always want to conntrack since it is a faster operation
|
// We always want to conntrack since it is a faster operation
|
||||||
f.addConn(fp, incoming)
|
f.addConn(&fp, incoming)
|
||||||
|
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
@@ -503,9 +280,9 @@ func (f *Firewall) EmitStats() {
|
|||||||
metrics.GetOrRegisterGauge("firewall.rules.hash", nil).Update(int64(f.GetRuleHashFNV()))
|
metrics.GetOrRegisterGauge("firewall.rules.hash", nil).Update(int64(f.GetRuleHashFNV()))
|
||||||
}
|
}
|
||||||
|
|
||||||
func (f *Firewall) inConns(fp firewall.Packet, h *HostInfo, caPool *cert.CAPool, localCache firewall.ConntrackCache) bool {
|
func (f *Firewall) inConns(fp *firewall.Packet, h *HostInfo, caPool *cert.CAPool, localCache firewall.ConntrackCache) bool {
|
||||||
if localCache != nil {
|
if localCache != nil {
|
||||||
if _, ok := localCache[fp]; ok {
|
if _, ok := localCache[*fp]; ok {
|
||||||
return true
|
return true
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -518,7 +295,7 @@ func (f *Firewall) inConns(fp firewall.Packet, h *HostInfo, caPool *cert.CAPool,
|
|||||||
f.evict(ep)
|
f.evict(ep)
|
||||||
}
|
}
|
||||||
|
|
||||||
c, ok := conntrack.Conns[fp]
|
c, ok := conntrack.Conns[*fp]
|
||||||
|
|
||||||
if !ok {
|
if !ok {
|
||||||
conntrack.Unlock()
|
conntrack.Unlock()
|
||||||
@@ -528,29 +305,23 @@ func (f *Firewall) inConns(fp firewall.Packet, h *HostInfo, caPool *cert.CAPool,
|
|||||||
if c.rulesVersion != f.rulesVersion {
|
if c.rulesVersion != f.rulesVersion {
|
||||||
// This conntrack entry was for an older rule set, validate
|
// This conntrack entry was for an older rule set, validate
|
||||||
// it still passes with the current rule set
|
// it still passes with the current rule set
|
||||||
table := f.OutRules
|
if !f.rules.Match(fp, c.incoming, h.ConnectionState.peerCert, caPool) {
|
||||||
if c.incoming {
|
|
||||||
table = f.InRules
|
|
||||||
}
|
|
||||||
|
|
||||||
// We now know which firewall table to check against
|
|
||||||
if !table.match(fp, c.incoming, h.ConnectionState.peerCert, caPool) {
|
|
||||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||||
h.logger(f.l).Debug("dropping old conntrack entry, does not match new ruleset",
|
h.logger(f.l).Debug("dropping old conntrack entry, does not match new ruleset",
|
||||||
"fwPacket", fp,
|
"fwPacket", *fp,
|
||||||
"incoming", c.incoming,
|
"incoming", c.incoming,
|
||||||
"rulesVersion", f.rulesVersion,
|
"rulesVersion", f.rulesVersion,
|
||||||
"oldRulesVersion", c.rulesVersion,
|
"oldRulesVersion", c.rulesVersion,
|
||||||
)
|
)
|
||||||
}
|
}
|
||||||
delete(conntrack.Conns, fp)
|
delete(conntrack.Conns, *fp)
|
||||||
conntrack.Unlock()
|
conntrack.Unlock()
|
||||||
return false
|
return false
|
||||||
}
|
}
|
||||||
|
|
||||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||||
h.logger(f.l).Debug("keeping old conntrack entry, does match new ruleset",
|
h.logger(f.l).Debug("keeping old conntrack entry, does match new ruleset",
|
||||||
"fwPacket", fp,
|
"fwPacket", *fp,
|
||||||
"incoming", c.incoming,
|
"incoming", c.incoming,
|
||||||
"rulesVersion", f.rulesVersion,
|
"rulesVersion", f.rulesVersion,
|
||||||
"oldRulesVersion", c.rulesVersion,
|
"oldRulesVersion", c.rulesVersion,
|
||||||
@@ -560,42 +331,39 @@ func (f *Firewall) inConns(fp firewall.Packet, h *HostInfo, caPool *cert.CAPool,
|
|||||||
c.rulesVersion = f.rulesVersion
|
c.rulesVersion = f.rulesVersion
|
||||||
}
|
}
|
||||||
|
|
||||||
switch fp.Protocol {
|
c.Expires = time.Now().Add(f.conntrackTimeout(fp.Protocol))
|
||||||
case iputil.IPProtocolTCP:
|
|
||||||
c.Expires = time.Now().Add(f.TCPTimeout)
|
|
||||||
case iputil.IPProtocolUDP:
|
|
||||||
c.Expires = time.Now().Add(f.UDPTimeout)
|
|
||||||
default:
|
|
||||||
c.Expires = time.Now().Add(f.DefaultTimeout)
|
|
||||||
}
|
|
||||||
|
|
||||||
conntrack.Unlock()
|
conntrack.Unlock()
|
||||||
|
|
||||||
if localCache != nil {
|
if localCache != nil {
|
||||||
localCache[fp] = struct{}{}
|
localCache[*fp] = struct{}{}
|
||||||
}
|
}
|
||||||
|
|
||||||
return true
|
return true
|
||||||
}
|
}
|
||||||
|
|
||||||
func (f *Firewall) addConn(fp firewall.Packet, incoming bool) {
|
// conntrackTimeout returns how long a conntrack entry for proto lives without traffic.
|
||||||
var timeout time.Duration
|
// Connection oriented protocols share the tcp timeout, datagram protocols share the udp timeout.
|
||||||
c := &conn{}
|
func (f *Firewall) conntrackTimeout(proto uint8) time.Duration {
|
||||||
|
switch proto {
|
||||||
switch fp.Protocol {
|
case iputil.IPProtocolTCP, iputil.IPProtocolSCTP, iputil.IPProtocolDCCP:
|
||||||
case iputil.IPProtocolTCP:
|
return f.TCPTimeout
|
||||||
timeout = f.TCPTimeout
|
case iputil.IPProtocolUDP, iputil.IPProtocolUDPLite:
|
||||||
case iputil.IPProtocolUDP:
|
return f.UDPTimeout
|
||||||
timeout = f.UDPTimeout
|
|
||||||
default:
|
default:
|
||||||
timeout = f.DefaultTimeout
|
return f.DefaultTimeout
|
||||||
}
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func (f *Firewall) addConn(fp *firewall.Packet, incoming bool) {
|
||||||
|
timeout := f.conntrackTimeout(fp.Protocol)
|
||||||
|
c := &conn{}
|
||||||
|
|
||||||
conntrack := f.Conntrack
|
conntrack := f.Conntrack
|
||||||
conntrack.Lock()
|
conntrack.Lock()
|
||||||
if _, ok := conntrack.Conns[fp]; !ok {
|
if _, ok := conntrack.Conns[*fp]; !ok {
|
||||||
conntrack.TimerWheel.Advance(time.Now())
|
conntrack.TimerWheel.Advance(time.Now())
|
||||||
conntrack.TimerWheel.Add(fp, timeout)
|
conntrack.TimerWheel.Add(*fp, timeout)
|
||||||
}
|
}
|
||||||
|
|
||||||
// Record which rulesVersion allowed this connection, so we can retest after
|
// Record which rulesVersion allowed this connection, so we can retest after
|
||||||
@@ -603,7 +371,7 @@ func (f *Firewall) addConn(fp firewall.Packet, incoming bool) {
|
|||||||
c.incoming = incoming
|
c.incoming = incoming
|
||||||
c.rulesVersion = f.rulesVersion
|
c.rulesVersion = f.rulesVersion
|
||||||
c.Expires = time.Now().Add(timeout)
|
c.Expires = time.Now().Add(timeout)
|
||||||
conntrack.Conns[fp] = c
|
conntrack.Conns[*fp] = c
|
||||||
conntrack.Unlock()
|
conntrack.Unlock()
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -629,490 +397,3 @@ func (f *Firewall) evict(p firewall.Packet) {
|
|||||||
// This conn is done
|
// This conn is done
|
||||||
delete(conntrack.Conns, p)
|
delete(conntrack.Conns, p)
|
||||||
}
|
}
|
||||||
|
|
||||||
func (ft *FirewallTable) match(p firewall.Packet, incoming bool, c *cert.CachedCertificate, caPool *cert.CAPool) bool {
|
|
||||||
if ft.AnyProto.match(p, incoming, c, caPool) {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
|
|
||||||
switch p.Protocol {
|
|
||||||
case iputil.IPProtocolTCP:
|
|
||||||
if ft.TCP.match(p, incoming, c, caPool) {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
case iputil.IPProtocolUDP:
|
|
||||||
if ft.UDP.match(p, incoming, c, caPool) {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
case iputil.IPProtocolICMP, iputil.IPProtocolICMPv6:
|
|
||||||
if ft.ICMP.match(p, incoming, c, caPool) {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
|
|
||||||
func (fp firewallPort) addRule(f *Firewall, startPort int32, endPort int32, groups []string, host string, cidr, localCidr, caName string, caSha string) error {
|
|
||||||
if startPort > endPort {
|
|
||||||
return fmt.Errorf("start port was lower than end port")
|
|
||||||
}
|
|
||||||
|
|
||||||
for i := startPort; i <= endPort; i++ {
|
|
||||||
if _, ok := fp[i]; !ok {
|
|
||||||
fp[i] = &FirewallCA{
|
|
||||||
CANames: make(map[string]*FirewallRule),
|
|
||||||
CAShas: make(map[string]*FirewallRule),
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if err := fp[i].addRule(f, groups, host, cidr, localCidr, caName, caSha); err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
func (fp firewallPort) match(p firewall.Packet, incoming bool, c *cert.CachedCertificate, caPool *cert.CAPool) bool {
|
|
||||||
// We don't have any allowed ports, bail
|
|
||||||
if fp == nil {
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
|
|
||||||
// this branch is here to catch traffic from FirewallTable.Any.match and FirewallTable.ICMP.match
|
|
||||||
if p.Protocol == iputil.IPProtocolICMP || p.Protocol == iputil.IPProtocolICMPv6 {
|
|
||||||
// port numbers are re-used for connection tracking of ICMP,
|
|
||||||
// but we don't want to actually filter on them.
|
|
||||||
return fp[firewall.PortAny].match(p, c, caPool)
|
|
||||||
}
|
|
||||||
|
|
||||||
var port int32
|
|
||||||
|
|
||||||
if p.Fragment {
|
|
||||||
port = firewall.PortFragment
|
|
||||||
} else if incoming {
|
|
||||||
port = int32(p.LocalPort)
|
|
||||||
} else {
|
|
||||||
port = int32(p.RemotePort)
|
|
||||||
}
|
|
||||||
|
|
||||||
if fp[port].match(p, c, caPool) {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
|
|
||||||
return fp[firewall.PortAny].match(p, c, caPool)
|
|
||||||
}
|
|
||||||
|
|
||||||
func (fc *FirewallCA) addRule(f *Firewall, groups []string, host string, cidr, localCidr, caName, caSha string) error {
|
|
||||||
fr := func() *FirewallRule {
|
|
||||||
return &FirewallRule{
|
|
||||||
Hosts: make(map[string]*firewallLocalCIDR),
|
|
||||||
Groups: make([]*firewallGroups, 0),
|
|
||||||
CIDR: new(bart.Table[*firewallLocalCIDR]),
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if caSha == "" && caName == "" {
|
|
||||||
if fc.Any == nil {
|
|
||||||
fc.Any = fr()
|
|
||||||
}
|
|
||||||
|
|
||||||
return fc.Any.addRule(f, groups, host, cidr, localCidr)
|
|
||||||
}
|
|
||||||
|
|
||||||
if caSha != "" {
|
|
||||||
if _, ok := fc.CAShas[caSha]; !ok {
|
|
||||||
fc.CAShas[caSha] = fr()
|
|
||||||
}
|
|
||||||
err := fc.CAShas[caSha].addRule(f, groups, host, cidr, localCidr)
|
|
||||||
if err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if caName != "" {
|
|
||||||
if _, ok := fc.CANames[caName]; !ok {
|
|
||||||
fc.CANames[caName] = fr()
|
|
||||||
}
|
|
||||||
err := fc.CANames[caName].addRule(f, groups, host, cidr, localCidr)
|
|
||||||
if err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
func (fc *FirewallCA) match(p firewall.Packet, c *cert.CachedCertificate, caPool *cert.CAPool) bool {
|
|
||||||
if fc == nil {
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
|
|
||||||
if fc.Any.match(p, c) {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
|
|
||||||
if t, ok := fc.CAShas[c.Certificate.Issuer()]; ok {
|
|
||||||
if t.match(p, c) {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
s, err := caPool.GetCAForCert(c.Certificate)
|
|
||||||
if err != nil {
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
|
|
||||||
return fc.CANames[s.Certificate.Name()].match(p, c)
|
|
||||||
}
|
|
||||||
|
|
||||||
func (fr *FirewallRule) addRule(f *Firewall, groups []string, host, cidr, localCidr string) error {
|
|
||||||
flc := func() *firewallLocalCIDR {
|
|
||||||
return &firewallLocalCIDR{
|
|
||||||
LocalCIDR: new(bart.Lite),
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if fr.isAny(groups, host, cidr) {
|
|
||||||
if fr.Any == nil {
|
|
||||||
fr.Any = flc()
|
|
||||||
}
|
|
||||||
|
|
||||||
return fr.Any.addRule(f, localCidr)
|
|
||||||
}
|
|
||||||
|
|
||||||
if len(groups) > 0 {
|
|
||||||
nlc := flc()
|
|
||||||
err := nlc.addRule(f, localCidr)
|
|
||||||
if err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
|
|
||||||
fr.Groups = append(fr.Groups, &firewallGroups{
|
|
||||||
Groups: groups,
|
|
||||||
LocalCIDR: nlc,
|
|
||||||
})
|
|
||||||
}
|
|
||||||
|
|
||||||
if host != "" {
|
|
||||||
nlc := fr.Hosts[host]
|
|
||||||
if nlc == nil {
|
|
||||||
nlc = flc()
|
|
||||||
}
|
|
||||||
err := nlc.addRule(f, localCidr)
|
|
||||||
if err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
fr.Hosts[host] = nlc
|
|
||||||
}
|
|
||||||
|
|
||||||
if cidr != "" {
|
|
||||||
c, err := netip.ParsePrefix(cidr)
|
|
||||||
if err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
nlc, _ := fr.CIDR.Get(c)
|
|
||||||
if nlc == nil {
|
|
||||||
nlc = flc()
|
|
||||||
}
|
|
||||||
err = nlc.addRule(f, localCidr)
|
|
||||||
if err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
fr.CIDR.Insert(c, nlc)
|
|
||||||
}
|
|
||||||
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
func (fr *FirewallRule) isAny(groups []string, host string, cidr string) bool {
|
|
||||||
if len(groups) == 0 && host == "" && cidr == "" {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
|
|
||||||
if slices.Contains(groups, "any") {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
|
|
||||||
if host == "any" {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
|
|
||||||
if cidr == "any" {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
|
|
||||||
func (fr *FirewallRule) match(p firewall.Packet, c *cert.CachedCertificate) bool {
|
|
||||||
if fr == nil {
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
|
|
||||||
// Shortcut path for if groups, hosts, or cidr contained an `any`
|
|
||||||
if fr.Any.match(p, c) {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
|
|
||||||
// Need any of group, host, or cidr to match
|
|
||||||
for _, sg := range fr.Groups {
|
|
||||||
found := false
|
|
||||||
|
|
||||||
for _, g := range sg.Groups {
|
|
||||||
if _, ok := c.InvertedGroups[g]; !ok {
|
|
||||||
found = false
|
|
||||||
break
|
|
||||||
}
|
|
||||||
|
|
||||||
found = true
|
|
||||||
}
|
|
||||||
|
|
||||||
if found && sg.LocalCIDR.match(p, c) {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if fr.Hosts != nil {
|
|
||||||
if flc, ok := fr.Hosts[c.Certificate.Name()]; ok {
|
|
||||||
if flc.match(p, c) {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
for _, v := range fr.CIDR.Supernets(netip.PrefixFrom(p.RemoteAddr, p.RemoteAddr.BitLen())) {
|
|
||||||
if v.match(p, c) {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
|
|
||||||
func (flc *firewallLocalCIDR) addRule(f *Firewall, localCidr string) error {
|
|
||||||
if localCidr == "any" {
|
|
||||||
flc.Any = true
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
if localCidr == "" {
|
|
||||||
if len(f.unsafeNetworks) == 0 || f.defaultLocalCIDRAny {
|
|
||||||
flc.Any = true
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
for _, network := range f.assignedNetworks {
|
|
||||||
flc.LocalCIDR.Insert(network)
|
|
||||||
}
|
|
||||||
return nil
|
|
||||||
|
|
||||||
}
|
|
||||||
|
|
||||||
c, err := netip.ParsePrefix(localCidr)
|
|
||||||
if err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
flc.LocalCIDR.Insert(c)
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
func (flc *firewallLocalCIDR) match(p firewall.Packet, c *cert.CachedCertificate) bool {
|
|
||||||
if flc == nil {
|
|
||||||
return false
|
|
||||||
}
|
|
||||||
|
|
||||||
if flc.Any {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
|
|
||||||
return flc.LocalCIDR.Contains(p.LocalAddr)
|
|
||||||
}
|
|
||||||
|
|
||||||
type rule struct {
|
|
||||||
Port string
|
|
||||||
Code string
|
|
||||||
Proto string
|
|
||||||
Host string
|
|
||||||
Groups []string
|
|
||||||
Cidr string
|
|
||||||
LocalCidr string
|
|
||||||
CAName string
|
|
||||||
CASha string
|
|
||||||
}
|
|
||||||
|
|
||||||
func convertRule(l *slog.Logger, p any, table string, i int) (rule, error) {
|
|
||||||
r := rule{}
|
|
||||||
|
|
||||||
m, ok := p.(map[string]any)
|
|
||||||
if !ok {
|
|
||||||
return r, errors.New("could not parse rule")
|
|
||||||
}
|
|
||||||
|
|
||||||
toString := func(k string, m map[string]any) string {
|
|
||||||
v, ok := m[k]
|
|
||||||
if !ok {
|
|
||||||
return ""
|
|
||||||
}
|
|
||||||
return fmt.Sprintf("%v", v)
|
|
||||||
}
|
|
||||||
|
|
||||||
r.Port = toString("port", m)
|
|
||||||
r.Code = toString("code", m)
|
|
||||||
r.Proto = toString("proto", m)
|
|
||||||
r.Host = toString("host", m)
|
|
||||||
r.Cidr = toString("cidr", m)
|
|
||||||
r.LocalCidr = toString("local_cidr", m)
|
|
||||||
r.CAName = toString("ca_name", m)
|
|
||||||
r.CASha = toString("ca_sha", m)
|
|
||||||
|
|
||||||
// Make sure group isn't an array
|
|
||||||
if v, ok := m["group"].([]any); ok {
|
|
||||||
if len(v) > 1 {
|
|
||||||
return r, errors.New("group should contain a single value, an array with more than one entry was provided")
|
|
||||||
}
|
|
||||||
|
|
||||||
l.Warn("group was an array with a single value, converting to simple value",
|
|
||||||
"table", table,
|
|
||||||
"rule", i,
|
|
||||||
)
|
|
||||||
m["group"] = v[0]
|
|
||||||
}
|
|
||||||
|
|
||||||
singleGroup := toString("group", m)
|
|
||||||
|
|
||||||
if rg, ok := m["groups"]; ok {
|
|
||||||
switch reflect.TypeOf(rg).Kind() {
|
|
||||||
case reflect.Slice:
|
|
||||||
v := reflect.ValueOf(rg)
|
|
||||||
r.Groups = make([]string, v.Len())
|
|
||||||
for i := 0; i < v.Len(); i++ {
|
|
||||||
r.Groups[i] = v.Index(i).Interface().(string)
|
|
||||||
}
|
|
||||||
case reflect.String:
|
|
||||||
r.Groups = []string{rg.(string)}
|
|
||||||
default:
|
|
||||||
r.Groups = []string{fmt.Sprintf("%v", rg)}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
//flatten group vs groups
|
|
||||||
if singleGroup != "" {
|
|
||||||
// Check if we have both groups and group provided in the rule config
|
|
||||||
if len(r.Groups) > 0 {
|
|
||||||
return r, fmt.Errorf("only one of group or groups should be defined, both provided")
|
|
||||||
}
|
|
||||||
r.Groups = []string{singleGroup}
|
|
||||||
}
|
|
||||||
|
|
||||||
return r, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
// sanity returns an error if the rule would be evaluated in a way that would short-circuit a configured check on a wildcard value
|
|
||||||
// rules are evaluated as "port AND proto AND (ca_sha OR ca_name) AND (host OR group OR groups OR cidr) AND local_cidr"
|
|
||||||
func (r *rule) sanity() error {
|
|
||||||
//port, proto, local_cidr are AND, no need to check here
|
|
||||||
//ca_sha and ca_name don't have a wildcard value, no need to check here
|
|
||||||
groupsEmpty := len(r.Groups) == 0
|
|
||||||
hostEmpty := r.Host == ""
|
|
||||||
cidrEmpty := r.Cidr == ""
|
|
||||||
|
|
||||||
if (groupsEmpty && hostEmpty && cidrEmpty) == true {
|
|
||||||
return nil //no content!
|
|
||||||
}
|
|
||||||
|
|
||||||
groupsHasAny := slices.Contains(r.Groups, "any")
|
|
||||||
if groupsHasAny && len(r.Groups) > 1 {
|
|
||||||
return fmt.Errorf("groups spec [%s] contains the group '\"any\". This rule will ignore the other groups specified", r.Groups)
|
|
||||||
}
|
|
||||||
|
|
||||||
if r.Host == "any" {
|
|
||||||
if !groupsEmpty {
|
|
||||||
return fmt.Errorf("groups specified as %s, but host=any will match any host, regardless of groups", r.Groups)
|
|
||||||
}
|
|
||||||
|
|
||||||
if !cidrEmpty {
|
|
||||||
return fmt.Errorf("cidr specified as %s, but host=any will match any host, regardless of cidr", r.Cidr)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if groupsHasAny {
|
|
||||||
if !hostEmpty && r.Host != "any" {
|
|
||||||
return fmt.Errorf("groups spec [%s] contains the group '\"any\". This rule will ignore the specified host %s", r.Groups, r.Host)
|
|
||||||
}
|
|
||||||
if !cidrEmpty {
|
|
||||||
return fmt.Errorf("groups spec [%s] contains the group '\"any\". This rule will ignore the specified cidr %s", r.Groups, r.Cidr)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if r.Code != "" {
|
|
||||||
return fmt.Errorf("code specified as [%s]. Support for 'code' will be dropped in a future release, as it has never been functional", r.Code)
|
|
||||||
}
|
|
||||||
|
|
||||||
//todo alert on cidr-any
|
|
||||||
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
func parsePort(s string) (int32, int32, error) {
|
|
||||||
const notAPort int32 = -2
|
|
||||||
if s == "any" {
|
|
||||||
return firewall.PortAny, firewall.PortAny, nil
|
|
||||||
}
|
|
||||||
if s == "fragment" {
|
|
||||||
return firewall.PortFragment, firewall.PortFragment, nil
|
|
||||||
}
|
|
||||||
if !strings.Contains(s, `-`) {
|
|
||||||
rPort, err := parsePortValue("", s)
|
|
||||||
if err != nil {
|
|
||||||
return notAPort, notAPort, err
|
|
||||||
}
|
|
||||||
return rPort, rPort, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
sPorts := strings.SplitN(s, `-`, 2)
|
|
||||||
for i := range sPorts {
|
|
||||||
sPorts[i] = strings.Trim(sPorts[i], " ")
|
|
||||||
}
|
|
||||||
if len(sPorts) != 2 || sPorts[0] == "" || sPorts[1] == "" {
|
|
||||||
return notAPort, notAPort, fmt.Errorf("appears to be a range but could not be parsed; `%s`", s)
|
|
||||||
}
|
|
||||||
|
|
||||||
startPort, err := parsePortValue("beginning range ", sPorts[0])
|
|
||||||
if err != nil {
|
|
||||||
return notAPort, notAPort, err
|
|
||||||
}
|
|
||||||
|
|
||||||
endPort, err := parsePortValue("ending range ", sPorts[1])
|
|
||||||
if err != nil {
|
|
||||||
return notAPort, notAPort, err
|
|
||||||
}
|
|
||||||
|
|
||||||
if startPort == firewall.PortAny {
|
|
||||||
endPort = firewall.PortAny
|
|
||||||
}
|
|
||||||
|
|
||||||
return startPort, endPort, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
// parsePortValue accepts a base-10 decimal in [0, 65535] and returns it
|
|
||||||
// widened to int32. Using strconv.ParseUint with bitSize 16 rejects
|
|
||||||
// negative input, out-of-range input (>65535), and any non-decimal byte
|
|
||||||
// by construction, so the int32 widening that follows is provably safe
|
|
||||||
// and cannot collide with firewall.PortAny (0) or firewall.PortFragment
|
|
||||||
// (-1) via integer truncation.
|
|
||||||
//
|
|
||||||
// prefix is prepended to both error messages so callers can disambiguate
|
|
||||||
// the single-port path (prefix="") from the range bounds (prefix="beginning
|
|
||||||
// range " / "ending range "), preserving the historical error strings.
|
|
||||||
func parsePortValue(prefix, s string) (int32, error) {
|
|
||||||
n, err := strconv.ParseUint(s, 10, 16)
|
|
||||||
if err == nil {
|
|
||||||
return int32(n), nil
|
|
||||||
}
|
|
||||||
if errors.Is(err, strconv.ErrRange) {
|
|
||||||
return 0, fmt.Errorf("%sout of range [0,65535]; `%s`", prefix, s)
|
|
||||||
}
|
|
||||||
return 0, fmt.Errorf("%swas not a number; `%s`", prefix, s)
|
|
||||||
}
|
|
||||||
@@ -0,0 +1,319 @@
|
|||||||
|
package firewall
|
||||||
|
|
||||||
|
import (
|
||||||
|
"errors"
|
||||||
|
"fmt"
|
||||||
|
"log/slog"
|
||||||
|
"net/netip"
|
||||||
|
"reflect"
|
||||||
|
"slices"
|
||||||
|
"strconv"
|
||||||
|
"strings"
|
||||||
|
|
||||||
|
"github.com/slackhq/nebula/config"
|
||||||
|
"github.com/slackhq/nebula/iputil"
|
||||||
|
)
|
||||||
|
|
||||||
|
// ruleAdder takes firewall rules, it lets tests see what addRulesFromConfig adds
|
||||||
|
type ruleAdder interface {
|
||||||
|
AddRule(incoming bool, proto uint8, startPort int32, endPort int32, groups []string, host string, cidr, localCidr string, caName string, caSha string) error
|
||||||
|
}
|
||||||
|
|
||||||
|
// RulesFromConfig reads the inbound and outbound firewall rules from c and builds them, see RulesBuilder.Build
|
||||||
|
func RulesFromConfig(l *slog.Logger, c *config.C, vpnNetworks, unsafeNetworks []netip.Prefix) (Rules, error) {
|
||||||
|
b := NewRulesBuilder(l)
|
||||||
|
b.defaultLocalCIDRAny = c.GetBool("firewall.default_local_cidr_any", false)
|
||||||
|
|
||||||
|
if err := addRulesFromConfig(l, false, c, b); err != nil {
|
||||||
|
return Rules{}, err
|
||||||
|
}
|
||||||
|
if err := addRulesFromConfig(l, true, c, b); err != nil {
|
||||||
|
return Rules{}, err
|
||||||
|
}
|
||||||
|
|
||||||
|
return b.Build(vpnNetworks, unsafeNetworks), nil
|
||||||
|
}
|
||||||
|
|
||||||
|
func addRulesFromConfig(l *slog.Logger, inbound bool, c *config.C, ra ruleAdder) error {
|
||||||
|
var table string
|
||||||
|
if inbound {
|
||||||
|
table = "firewall.inbound"
|
||||||
|
} else {
|
||||||
|
table = "firewall.outbound"
|
||||||
|
}
|
||||||
|
|
||||||
|
r := c.Get(table)
|
||||||
|
if r == nil {
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
|
||||||
|
rs, ok := r.([]any)
|
||||||
|
if !ok {
|
||||||
|
return fmt.Errorf("%s failed to parse, should be an array of rules", table)
|
||||||
|
}
|
||||||
|
|
||||||
|
for i, t := range rs {
|
||||||
|
r, err := yamlToConfigRule(l, t, table, i)
|
||||||
|
if err != nil {
|
||||||
|
return fmt.Errorf("%s rule #%v; %s", table, i, err)
|
||||||
|
}
|
||||||
|
|
||||||
|
if r.Code != "" && r.Port != "" {
|
||||||
|
return fmt.Errorf("%s rule #%v; only one of port or code should be provided", table, i)
|
||||||
|
}
|
||||||
|
|
||||||
|
if r.Host == "" && len(r.Groups) == 0 && r.Cidr == "" && r.LocalCidr == "" && r.CAName == "" && r.CASha == "" {
|
||||||
|
return fmt.Errorf("%s rule #%v; at least one of host, group, cidr, local_cidr, ca_name, or ca_sha must be provided", table, i)
|
||||||
|
}
|
||||||
|
|
||||||
|
var sPort, errPort string
|
||||||
|
if r.Code != "" {
|
||||||
|
errPort = "code"
|
||||||
|
sPort = r.Code
|
||||||
|
} else {
|
||||||
|
errPort = "port"
|
||||||
|
sPort = r.Port
|
||||||
|
}
|
||||||
|
|
||||||
|
var proto uint8
|
||||||
|
switch r.Proto {
|
||||||
|
case "any":
|
||||||
|
proto = ProtoAny
|
||||||
|
case "tcp":
|
||||||
|
proto = iputil.IPProtocolTCP
|
||||||
|
case "udp":
|
||||||
|
proto = iputil.IPProtocolUDP
|
||||||
|
case "udplite":
|
||||||
|
proto = iputil.IPProtocolUDPLite
|
||||||
|
case "dccp":
|
||||||
|
proto = iputil.IPProtocolDCCP
|
||||||
|
case "sctp":
|
||||||
|
proto = iputil.IPProtocolSCTP
|
||||||
|
case "icmp":
|
||||||
|
proto = iputil.IPProtocolICMP
|
||||||
|
default:
|
||||||
|
// Any other protocol by number. 0 is reserved for `any`.
|
||||||
|
n, perr := strconv.ParseUint(r.Proto, 10, 8)
|
||||||
|
if perr != nil || n == 0 {
|
||||||
|
return fmt.Errorf("%s rule #%v; proto was not understood; `%s`", table, i, r.Proto)
|
||||||
|
}
|
||||||
|
proto = uint8(n)
|
||||||
|
}
|
||||||
|
|
||||||
|
var startPort, endPort int32
|
||||||
|
if proto == iputil.IPProtocolICMP || proto == iputil.IPProtocolICMPv6 {
|
||||||
|
startPort = PortAny
|
||||||
|
endPort = PortAny
|
||||||
|
if sPort != "" {
|
||||||
|
l.Warn("ignoring port specification for ICMP firewall rule", "port", sPort)
|
||||||
|
}
|
||||||
|
} else {
|
||||||
|
startPort, endPort, err = parsePort(sPort)
|
||||||
|
}
|
||||||
|
if err != nil {
|
||||||
|
return fmt.Errorf("%s rule #%v; %s %s", table, i, errPort, err)
|
||||||
|
}
|
||||||
|
|
||||||
|
if warning := r.sanity(); warning != nil {
|
||||||
|
l.Warn("firewall rule sanity check",
|
||||||
|
"table", table,
|
||||||
|
"rule", i,
|
||||||
|
"warning", warning,
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
err = ra.AddRule(inbound, proto, startPort, endPort, r.Groups, r.Host, r.Cidr, r.LocalCidr, r.CAName, r.CASha)
|
||||||
|
if err != nil {
|
||||||
|
return fmt.Errorf("%s rule #%v; %s", table, i, err)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
|
||||||
|
type configRule struct {
|
||||||
|
Port string
|
||||||
|
Code string
|
||||||
|
Proto string
|
||||||
|
Host string
|
||||||
|
Groups []string
|
||||||
|
Cidr string
|
||||||
|
LocalCidr string
|
||||||
|
CAName string
|
||||||
|
CASha string
|
||||||
|
}
|
||||||
|
|
||||||
|
func yamlToConfigRule(l *slog.Logger, p any, table string, i int) (configRule, error) {
|
||||||
|
r := configRule{}
|
||||||
|
|
||||||
|
m, ok := p.(map[string]any)
|
||||||
|
if !ok {
|
||||||
|
return r, errors.New("could not parse rule")
|
||||||
|
}
|
||||||
|
|
||||||
|
toString := func(k string, m map[string]any) string {
|
||||||
|
v, ok := m[k]
|
||||||
|
if !ok {
|
||||||
|
return ""
|
||||||
|
}
|
||||||
|
return fmt.Sprintf("%v", v)
|
||||||
|
}
|
||||||
|
|
||||||
|
r.Port = toString("port", m)
|
||||||
|
r.Code = toString("code", m)
|
||||||
|
r.Proto = toString("proto", m)
|
||||||
|
r.Host = toString("host", m)
|
||||||
|
r.Cidr = toString("cidr", m)
|
||||||
|
r.LocalCidr = toString("local_cidr", m)
|
||||||
|
r.CAName = toString("ca_name", m)
|
||||||
|
r.CASha = toString("ca_sha", m)
|
||||||
|
|
||||||
|
// Make sure group isn't an array
|
||||||
|
if v, ok := m["group"].([]any); ok {
|
||||||
|
if len(v) > 1 {
|
||||||
|
return r, errors.New("group should contain a single value, an array with more than one entry was provided")
|
||||||
|
}
|
||||||
|
|
||||||
|
l.Warn("group was an array with a single value, converting to simple value",
|
||||||
|
"table", table,
|
||||||
|
"rule", i,
|
||||||
|
)
|
||||||
|
m["group"] = v[0]
|
||||||
|
}
|
||||||
|
|
||||||
|
singleGroup := toString("group", m)
|
||||||
|
|
||||||
|
if rg, ok := m["groups"]; ok {
|
||||||
|
switch reflect.TypeOf(rg).Kind() {
|
||||||
|
case reflect.Slice:
|
||||||
|
v := reflect.ValueOf(rg)
|
||||||
|
r.Groups = make([]string, v.Len())
|
||||||
|
for i := 0; i < v.Len(); i++ {
|
||||||
|
r.Groups[i] = v.Index(i).Interface().(string)
|
||||||
|
}
|
||||||
|
case reflect.String:
|
||||||
|
r.Groups = []string{rg.(string)}
|
||||||
|
default:
|
||||||
|
r.Groups = []string{fmt.Sprintf("%v", rg)}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
//flatten group vs groups
|
||||||
|
if singleGroup != "" {
|
||||||
|
// Check if we have both groups and group provided in the rule config
|
||||||
|
if len(r.Groups) > 0 {
|
||||||
|
return r, fmt.Errorf("only one of group or groups should be defined, both provided")
|
||||||
|
}
|
||||||
|
r.Groups = []string{singleGroup}
|
||||||
|
}
|
||||||
|
|
||||||
|
return r, nil
|
||||||
|
}
|
||||||
|
|
||||||
|
// sanity returns an error if the rule would be evaluated in a way that would short-circuit a configured check on a wildcard value
|
||||||
|
// rules are evaluated as "port AND proto AND (ca_sha OR ca_name) AND (host OR group OR groups OR cidr) AND local_cidr"
|
||||||
|
func (r *configRule) sanity() error {
|
||||||
|
//port, proto, local_cidr are AND, no need to check here
|
||||||
|
//ca_sha and ca_name don't have a wildcard value, no need to check here
|
||||||
|
groupsEmpty := len(r.Groups) == 0
|
||||||
|
hostEmpty := r.Host == ""
|
||||||
|
cidrEmpty := r.Cidr == ""
|
||||||
|
|
||||||
|
if (groupsEmpty && hostEmpty && cidrEmpty) == true {
|
||||||
|
return nil //no content!
|
||||||
|
}
|
||||||
|
|
||||||
|
groupsHasAny := slices.Contains(r.Groups, "any")
|
||||||
|
if groupsHasAny && len(r.Groups) > 1 {
|
||||||
|
return fmt.Errorf("groups spec [%s] contains the group '\"any\". This rule will ignore the other groups specified", r.Groups)
|
||||||
|
}
|
||||||
|
|
||||||
|
if r.Host == "any" {
|
||||||
|
if !groupsEmpty {
|
||||||
|
return fmt.Errorf("groups specified as %s, but host=any will match any host, regardless of groups", r.Groups)
|
||||||
|
}
|
||||||
|
|
||||||
|
if !cidrEmpty {
|
||||||
|
return fmt.Errorf("cidr specified as %s, but host=any will match any host, regardless of cidr", r.Cidr)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
if groupsHasAny {
|
||||||
|
if !hostEmpty && r.Host != "any" {
|
||||||
|
return fmt.Errorf("groups spec [%s] contains the group '\"any\". This rule will ignore the specified host %s", r.Groups, r.Host)
|
||||||
|
}
|
||||||
|
if !cidrEmpty {
|
||||||
|
return fmt.Errorf("groups spec [%s] contains the group '\"any\". This rule will ignore the specified cidr %s", r.Groups, r.Cidr)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
if r.Code != "" {
|
||||||
|
return fmt.Errorf("code specified as [%s]. Support for 'code' will be dropped in a future release, as it has never been functional", r.Code)
|
||||||
|
}
|
||||||
|
|
||||||
|
//todo alert on cidr-any
|
||||||
|
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
|
||||||
|
func parsePort(s string) (int32, int32, error) {
|
||||||
|
const notAPort int32 = -2
|
||||||
|
if s == "any" {
|
||||||
|
return PortAny, PortAny, nil
|
||||||
|
}
|
||||||
|
if s == "fragment" {
|
||||||
|
return PortFragment, PortFragment, nil
|
||||||
|
}
|
||||||
|
if !strings.Contains(s, `-`) {
|
||||||
|
rPort, err := parsePortValue("", s)
|
||||||
|
if err != nil {
|
||||||
|
return notAPort, notAPort, err
|
||||||
|
}
|
||||||
|
return rPort, rPort, nil
|
||||||
|
}
|
||||||
|
|
||||||
|
sPorts := strings.SplitN(s, `-`, 2)
|
||||||
|
for i := range sPorts {
|
||||||
|
sPorts[i] = strings.Trim(sPorts[i], " ")
|
||||||
|
}
|
||||||
|
if len(sPorts) != 2 || sPorts[0] == "" || sPorts[1] == "" {
|
||||||
|
return notAPort, notAPort, fmt.Errorf("appears to be a range but could not be parsed; `%s`", s)
|
||||||
|
}
|
||||||
|
|
||||||
|
startPort, err := parsePortValue("beginning range ", sPorts[0])
|
||||||
|
if err != nil {
|
||||||
|
return notAPort, notAPort, err
|
||||||
|
}
|
||||||
|
|
||||||
|
endPort, err := parsePortValue("ending range ", sPorts[1])
|
||||||
|
if err != nil {
|
||||||
|
return notAPort, notAPort, err
|
||||||
|
}
|
||||||
|
|
||||||
|
if startPort == PortAny {
|
||||||
|
endPort = PortAny
|
||||||
|
}
|
||||||
|
|
||||||
|
return startPort, endPort, nil
|
||||||
|
}
|
||||||
|
|
||||||
|
// parsePortValue accepts a base-10 decimal in [0, 65535] and returns it
|
||||||
|
// widened to int32. Using strconv.ParseUint with bitSize 16 rejects
|
||||||
|
// negative input, out-of-range input (>65535), and any non-decimal byte
|
||||||
|
// by construction, so the int32 widening that follows is provably safe
|
||||||
|
// and cannot collide with PortAny (0) or PortFragment
|
||||||
|
// (-1) via integer truncation.
|
||||||
|
//
|
||||||
|
// prefix is prepended to both error messages so callers can disambiguate
|
||||||
|
// the single-port path (prefix="") from the range bounds (prefix="beginning
|
||||||
|
// range " / "ending range "), preserving the historical error strings.
|
||||||
|
func parsePortValue(prefix, s string) (int32, error) {
|
||||||
|
n, err := strconv.ParseUint(s, 10, 16)
|
||||||
|
if err == nil {
|
||||||
|
return int32(n), nil
|
||||||
|
}
|
||||||
|
if errors.Is(err, strconv.ErrRange) {
|
||||||
|
return 0, fmt.Errorf("%sout of range [0,65535]; `%s`", prefix, s)
|
||||||
|
}
|
||||||
|
return 0, fmt.Errorf("%swas not a number; `%s`", prefix, s)
|
||||||
|
}
|
||||||
@@ -0,0 +1,477 @@
|
|||||||
|
package firewall
|
||||||
|
|
||||||
|
import (
|
||||||
|
"bytes"
|
||||||
|
"errors"
|
||||||
|
"net/netip"
|
||||||
|
"testing"
|
||||||
|
|
||||||
|
"github.com/slackhq/nebula/config"
|
||||||
|
"github.com/slackhq/nebula/iputil"
|
||||||
|
"github.com/slackhq/nebula/test"
|
||||||
|
"github.com/stretchr/testify/assert"
|
||||||
|
"github.com/stretchr/testify/require"
|
||||||
|
)
|
||||||
|
|
||||||
|
func Test_parsePort(t *testing.T) {
|
||||||
|
_, _, err := parsePort("")
|
||||||
|
require.EqualError(t, err, "was not a number; ``")
|
||||||
|
|
||||||
|
_, _, err = parsePort(" ")
|
||||||
|
require.EqualError(t, err, "was not a number; ` `")
|
||||||
|
|
||||||
|
_, _, err = parsePort("-")
|
||||||
|
require.EqualError(t, err, "appears to be a range but could not be parsed; `-`")
|
||||||
|
|
||||||
|
_, _, err = parsePort(" - ")
|
||||||
|
require.EqualError(t, err, "appears to be a range but could not be parsed; ` - `")
|
||||||
|
|
||||||
|
_, _, err = parsePort("a-b")
|
||||||
|
require.EqualError(t, err, "beginning range was not a number; `a`")
|
||||||
|
|
||||||
|
_, _, err = parsePort("1-b")
|
||||||
|
require.EqualError(t, err, "ending range was not a number; `b`")
|
||||||
|
|
||||||
|
s, e, err := parsePort(" 1 - 2 ")
|
||||||
|
assert.Equal(t, int32(1), s)
|
||||||
|
assert.Equal(t, int32(2), e)
|
||||||
|
require.NoError(t, err)
|
||||||
|
|
||||||
|
s, e, err = parsePort("0-1")
|
||||||
|
assert.Equal(t, int32(0), s)
|
||||||
|
assert.Equal(t, int32(0), e)
|
||||||
|
require.NoError(t, err)
|
||||||
|
|
||||||
|
s, e, err = parsePort("9919")
|
||||||
|
assert.Equal(t, int32(9919), s)
|
||||||
|
assert.Equal(t, int32(9919), e)
|
||||||
|
require.NoError(t, err)
|
||||||
|
|
||||||
|
s, e, err = parsePort("any")
|
||||||
|
assert.Equal(t, int32(0), s)
|
||||||
|
assert.Equal(t, int32(0), e)
|
||||||
|
require.NoError(t, err)
|
||||||
|
}
|
||||||
|
|
||||||
|
// Test_parsePort_invalid covers inputs that must error. The named bug is
|
||||||
|
// that int32(strconv.Atoi("4294967296")) truncates to 0 == PortAny,
|
||||||
|
// silently turning a typo into a match-all-ports rule; the rest are
|
||||||
|
// representative syntax/range probes.
|
||||||
|
func Test_parsePort_invalid(t *testing.T) {
|
||||||
|
tests := []struct {
|
||||||
|
name string
|
||||||
|
input string
|
||||||
|
wantErrContains string
|
||||||
|
}{
|
||||||
|
// Numeric overflow (the named bug + boundary).
|
||||||
|
{"named bug: 2^32 truncates to PortAny", "4294967296", "out of range"},
|
||||||
|
{"just above max real port", "65536", "out of range"},
|
||||||
|
|
||||||
|
// Negatives route through the range branch and hit the empty-half
|
||||||
|
// guard; included as defense in depth so a future refactor cannot
|
||||||
|
// accidentally reach the int32 cast.
|
||||||
|
{"negative", "-1", "could not be parsed"},
|
||||||
|
|
||||||
|
// Syntax probes.
|
||||||
|
{"NUL between digits", "4\x002", "was not a number"},
|
||||||
|
{"hex notation", "0x10", "was not a number"},
|
||||||
|
{"scientific notation", "1e3", "was not a number"},
|
||||||
|
{"leading whitespace", " 42", "was not a number"},
|
||||||
|
{"fullwidth digits", "42", "was not a number"},
|
||||||
|
|
||||||
|
// Range branch.
|
||||||
|
{"range upper out of range", "1-65536", "ending range out of range"},
|
||||||
|
{"range lower out of range", "65536-65537", "beginning range out of range"},
|
||||||
|
{"range with negative upper", "1--1", "ending range was not a number"},
|
||||||
|
}
|
||||||
|
|
||||||
|
for _, tc := range tests {
|
||||||
|
t.Run(tc.name, func(t *testing.T) {
|
||||||
|
_, _, err := parsePort(tc.input)
|
||||||
|
require.Error(t, err, "input %q must error", tc.input)
|
||||||
|
require.ErrorContains(t, err, tc.wantErrContains)
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// Test_parsePort_valid_boundaries locks in success cases at 0, 1, and 65535
|
||||||
|
// so a future refactor cannot regress the boundaries.
|
||||||
|
func Test_parsePort_valid_boundaries(t *testing.T) {
|
||||||
|
tests := []struct {
|
||||||
|
name string
|
||||||
|
input string
|
||||||
|
wantStart int32
|
||||||
|
wantEnd int32
|
||||||
|
}{
|
||||||
|
{"zero is PortAny", "0", 0, 0},
|
||||||
|
{"min real port", "1", 1, 1},
|
||||||
|
{"max real port", "65535", 65535, 65535},
|
||||||
|
{"range zero to max forces end to zero", "0-65535", 0, 0},
|
||||||
|
{"range max to max", "65535-65535", 65535, 65535},
|
||||||
|
{"range one to max", "1-65535", 1, 65535},
|
||||||
|
{"range with whitespace inside", " 1 - 2 ", 1, 2},
|
||||||
|
}
|
||||||
|
|
||||||
|
for _, tc := range tests {
|
||||||
|
t.Run(tc.name, func(t *testing.T) {
|
||||||
|
s, e, err := parsePort(tc.input)
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, tc.wantStart, s, "start port")
|
||||||
|
assert.Equal(t, tc.wantEnd, e, "end port")
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestAddRulesFromConfig(t *testing.T) {
|
||||||
|
l := test.NewLogger()
|
||||||
|
// Test adding tcp rule
|
||||||
|
conf := config.NewC(test.NewLogger())
|
||||||
|
mf := &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"port": "1", "proto": "tcp", "host": "a"}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, false, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: false, proto: iputil.IPProtocolTCP, startPort: 1, endPort: 1, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test adding udp rule
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"port": "1", "proto": "udp", "host": "a"}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, false, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: false, proto: iputil.IPProtocolUDP, startPort: 1, endPort: 1, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test adding udplite, dccp, and sctp rules
|
||||||
|
for name, proto := range map[string]uint8{"udplite": iputil.IPProtocolUDPLite, "dccp": iputil.IPProtocolDCCP, "sctp": iputil.IPProtocolSCTP} {
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"port": "1-2", "proto": name, "host": "a"}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, false, conf, mf), name)
|
||||||
|
assert.Equal(t, addRuleCall{incoming: false, proto: proto, startPort: 1, endPort: 2, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall, name)
|
||||||
|
}
|
||||||
|
|
||||||
|
// Test adding icmp rule
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"port": "1", "proto": "icmp", "host": "a"}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, false, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: false, proto: iputil.IPProtocolICMP, startPort: PortAny, endPort: PortAny, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test adding icmp rule no port
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"proto": "icmp", "host": "a"}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, false, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: false, proto: iputil.IPProtocolICMP, startPort: PortAny, endPort: PortAny, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test adding rules by protocol number, as yaml would give a string or an int
|
||||||
|
for _, proto := range []any{"47", 47} {
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"port": "any", "proto": proto, "host": "a"}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, false, conf, mf), proto)
|
||||||
|
assert.Equal(t, addRuleCall{incoming: false, proto: 47, startPort: PortAny, endPort: PortAny, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall, proto)
|
||||||
|
}
|
||||||
|
|
||||||
|
// Test ICMP and ICMPv6 by number still ignore ports
|
||||||
|
for _, proto := range []uint8{iputil.IPProtocolICMP, iputil.IPProtocolICMPv6} {
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"port": "1", "proto": proto, "host": "a"}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, false, conf, mf), proto)
|
||||||
|
assert.Equal(t, addRuleCall{incoming: false, proto: proto, startPort: PortAny, endPort: PortAny, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall, proto)
|
||||||
|
}
|
||||||
|
|
||||||
|
// Test protocols that aren't a known name or a number from 1 to 255
|
||||||
|
for _, proto := range []string{"0", "256", "-1", "gre"} {
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"port": "any", "proto": proto, "host": "a"}}}
|
||||||
|
require.EqualError(t, addRulesFromConfig(l, false, conf, mf), "firewall.outbound rule #0; proto was not understood; `"+proto+"`")
|
||||||
|
}
|
||||||
|
|
||||||
|
// Test adding any rule
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "host": "a"}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test adding rule with cidr
|
||||||
|
cidr := netip.MustParsePrefix("10.0.0.0/8")
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "cidr": cidr.String()}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, ip: cidr.String(), localIp: ""}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test adding rule with local_cidr
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "local_cidr": cidr.String()}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, ip: "", localIp: cidr.String()}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test adding rule with cidr ipv6
|
||||||
|
cidr6 := netip.MustParsePrefix("fd00::/8")
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "cidr": cidr6.String()}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, ip: cidr6.String(), localIp: ""}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test adding rule with any cidr
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "cidr": "any"}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, ip: "any", localIp: ""}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test adding rule with junk cidr, which RulesBuilder rejects
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "cidr": "junk/junk"}}}
|
||||||
|
require.EqualError(t, addRulesFromConfig(l, true, conf, NewRulesBuilder(l)), "firewall.inbound rule #0; cidr did not parse; netip.ParsePrefix(\"junk/junk\"): ParseAddr(\"junk\"): unable to parse IP")
|
||||||
|
|
||||||
|
// Test adding rule with local_cidr ipv6
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "local_cidr": cidr6.String()}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, ip: "", localIp: cidr6.String()}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test adding rule with any local_cidr
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "local_cidr": "any"}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, localIp: "any"}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test adding rule with junk local_cidr, which RulesBuilder rejects
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "local_cidr": "junk/junk"}}}
|
||||||
|
require.EqualError(t, addRulesFromConfig(l, true, conf, NewRulesBuilder(l)), "firewall.inbound rule #0; local_cidr did not parse; netip.ParsePrefix(\"junk/junk\"): ParseAddr(\"junk\"): unable to parse IP")
|
||||||
|
|
||||||
|
// Test adding rule with ca_sha
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "ca_sha": "12312313123"}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, ip: "", localIp: "", caSha: "12312313123"}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test adding rule with ca_name
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "ca_name": "root01"}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, ip: "", localIp: "", caName: "root01"}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test single group
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "group": "a"}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: []string{"a"}, ip: "", localIp: ""}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test single groups
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "groups": "a"}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: []string{"a"}, ip: "", localIp: ""}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test multiple AND groups
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "groups": []string{"a", "b"}}}}
|
||||||
|
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||||
|
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: []string{"a", "b"}, ip: "", localIp: ""}, mf.lastCall)
|
||||||
|
|
||||||
|
// Test Add error
|
||||||
|
conf = config.NewC(test.NewLogger())
|
||||||
|
mf = &mockFirewall{}
|
||||||
|
mf.nextCallReturn = errors.New("test error")
|
||||||
|
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "host": "a"}}}
|
||||||
|
require.EqualError(t, addRulesFromConfig(l, true, conf, mf), "firewall.inbound rule #0; test error")
|
||||||
|
}
|
||||||
|
|
||||||
|
// TestRulesFromConfig_defaultLocalCIDR ensures rules without a local_cidr allow only the vpn networks when there are
|
||||||
|
// unsafe networks, unless default_local_cidr_any is set, and that a rule's own local_cidr is kept either way
|
||||||
|
func TestRulesFromConfig_defaultLocalCIDR(t *testing.T) {
|
||||||
|
vpnNetworks := []netip.Prefix{netip.MustParsePrefix("10.1.0.5/16")}
|
||||||
|
unsafeNetworks := []netip.Prefix{netip.MustParsePrefix("192.168.0.0/24")}
|
||||||
|
vpnAddr := netip.MustParseAddr("10.1.9.9")
|
||||||
|
unsafeAddr := netip.MustParseAddr("192.168.0.3")
|
||||||
|
|
||||||
|
allows := func(lr *localRules, addr netip.Addr) bool {
|
||||||
|
return lr.match(&Packet{LocalAddr: addr}, nil)
|
||||||
|
}
|
||||||
|
|
||||||
|
for _, tc := range []struct {
|
||||||
|
name string
|
||||||
|
unsafeNetworks []netip.Prefix
|
||||||
|
defaultLocalCIDRAny bool
|
||||||
|
wantUnsafe bool
|
||||||
|
}{
|
||||||
|
{"no unsafe networks", nil, false, true},
|
||||||
|
{"unsafe networks", unsafeNetworks, false, false},
|
||||||
|
{"unsafe networks and default_local_cidr_any", unsafeNetworks, true, true},
|
||||||
|
} {
|
||||||
|
t.Run(tc.name, func(t *testing.T) {
|
||||||
|
conf := config.NewC(test.NewLogger())
|
||||||
|
conf.Settings["firewall"] = map[string]any{
|
||||||
|
"default_local_cidr_any": tc.defaultLocalCIDRAny,
|
||||||
|
"inbound": []any{
|
||||||
|
map[string]any{"port": "any", "proto": "any", "host": "any"},
|
||||||
|
map[string]any{"port": "22", "proto": "tcp", "host": "any"},
|
||||||
|
map[string]any{"port": "80", "proto": "tcp", "host": "any", "local_cidr": "192.168.0.0/24"},
|
||||||
|
map[string]any{"port": "443", "proto": "tcp", "host": "any", "local_cidr": "any"},
|
||||||
|
},
|
||||||
|
}
|
||||||
|
rules, err := RulesFromConfig(test.NewLogger(), conf, vpnNetworks, tc.unsafeNetworks)
|
||||||
|
require.NoError(t, err)
|
||||||
|
|
||||||
|
// The proto `any` rule, copied into a protocol with rules of its own and shared by one without
|
||||||
|
for _, proto := range []uint8{iputil.IPProtocolTCP, 47} {
|
||||||
|
lr := rules.In.protos[proto][PortAny].Any.Any
|
||||||
|
assert.True(t, allows(lr, vpnAddr), "proto %d", proto)
|
||||||
|
assert.Equal(t, tc.wantUnsafe, allows(lr, unsafeAddr), "proto %d", proto)
|
||||||
|
}
|
||||||
|
|
||||||
|
tcp := rules.In.protos[iputil.IPProtocolTCP]
|
||||||
|
assert.True(t, allows(tcp[22].Any.Any, vpnAddr))
|
||||||
|
assert.Equal(t, tc.wantUnsafe, allows(tcp[22].Any.Any, unsafeAddr))
|
||||||
|
|
||||||
|
assert.False(t, allows(tcp[80].Any.Any, vpnAddr))
|
||||||
|
assert.True(t, allows(tcp[80].Any.Any, unsafeAddr))
|
||||||
|
|
||||||
|
assert.True(t, allows(tcp[443].Any.Any, vpnAddr))
|
||||||
|
assert.True(t, allows(tcp[443].Any.Any, unsafeAddr))
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func Test_convertRule(t *testing.T) {
|
||||||
|
ob := &bytes.Buffer{}
|
||||||
|
l := test.NewLoggerWithOutput(ob)
|
||||||
|
|
||||||
|
// Ensure group array of 1 is converted and a warning is printed
|
||||||
|
c := map[string]any{
|
||||||
|
"group": []any{"group1"},
|
||||||
|
}
|
||||||
|
|
||||||
|
r, err := yamlToConfigRule(l, c, "test", 1)
|
||||||
|
assert.Contains(t, ob.String(), "group was an array with a single value, converting to simple value")
|
||||||
|
assert.Contains(t, ob.String(), "table=test")
|
||||||
|
assert.Contains(t, ob.String(), "rule=1")
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, []string{"group1"}, r.Groups)
|
||||||
|
|
||||||
|
// Ensure group array of > 1 is errord
|
||||||
|
ob.Reset()
|
||||||
|
c = map[string]any{
|
||||||
|
"group": []any{"group1", "group2"},
|
||||||
|
}
|
||||||
|
|
||||||
|
r, err = yamlToConfigRule(l, c, "test", 1)
|
||||||
|
assert.Empty(t, ob.String())
|
||||||
|
require.Error(t, err, "group should contain a single value, an array with more than one entry was provided")
|
||||||
|
|
||||||
|
// Make sure a well formed group is alright
|
||||||
|
ob.Reset()
|
||||||
|
c = map[string]any{
|
||||||
|
"group": "group1",
|
||||||
|
}
|
||||||
|
|
||||||
|
r, err = yamlToConfigRule(l, c, "test", 1)
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, []string{"group1"}, r.Groups)
|
||||||
|
}
|
||||||
|
|
||||||
|
func Test_convertRuleSanity(t *testing.T) {
|
||||||
|
ob := &bytes.Buffer{}
|
||||||
|
l := test.NewLoggerWithOutput(ob)
|
||||||
|
|
||||||
|
noWarningPlease := []map[string]any{
|
||||||
|
{"group": "group1"},
|
||||||
|
{"groups": []any{"group2"}},
|
||||||
|
{"host": "bob"},
|
||||||
|
{"cidr": "1.1.1.1/1"},
|
||||||
|
{"groups": []any{"group2"}, "host": "bob"},
|
||||||
|
{"cidr": "1.1.1.1/1", "host": "bob"},
|
||||||
|
{"groups": []any{"group2"}, "cidr": "1.1.1.1/1"},
|
||||||
|
{"groups": []any{"group2"}, "cidr": "1.1.1.1/1", "host": "bob"},
|
||||||
|
}
|
||||||
|
for _, c := range noWarningPlease {
|
||||||
|
r, err := yamlToConfigRule(l, c, "test", 1)
|
||||||
|
require.NoError(t, err)
|
||||||
|
require.NoError(t, r.sanity(), "should not generate a sanity warning, %+v", c)
|
||||||
|
}
|
||||||
|
|
||||||
|
yesWarningPlease := []map[string]any{
|
||||||
|
{"group": "group1"},
|
||||||
|
{"groups": []any{"group2"}},
|
||||||
|
{"cidr": "1.1.1.1/1"},
|
||||||
|
{"groups": []any{"group2"}, "host": "bob"},
|
||||||
|
{"cidr": "1.1.1.1/1", "host": "bob"},
|
||||||
|
{"groups": []any{"group2"}, "cidr": "1.1.1.1/1"},
|
||||||
|
{"groups": []any{"group2"}, "cidr": "1.1.1.1/1", "host": "bob"},
|
||||||
|
}
|
||||||
|
for _, c := range yesWarningPlease {
|
||||||
|
c["host"] = "any"
|
||||||
|
r, err := yamlToConfigRule(l, c, "test", 1)
|
||||||
|
require.NoError(t, err)
|
||||||
|
err = r.sanity()
|
||||||
|
require.Error(t, err, "I wanted a warning: %+v", c)
|
||||||
|
}
|
||||||
|
//reset the list
|
||||||
|
yesWarningPlease = []map[string]any{
|
||||||
|
{"group": "group1"},
|
||||||
|
{"groups": []any{"group2"}},
|
||||||
|
{"cidr": "1.1.1.1/1"},
|
||||||
|
{"groups": []any{"group2"}, "host": "bob"},
|
||||||
|
{"cidr": "1.1.1.1/1", "host": "bob"},
|
||||||
|
{"groups": []any{"group2"}, "cidr": "1.1.1.1/1"},
|
||||||
|
{"groups": []any{"group2"}, "cidr": "1.1.1.1/1", "host": "bob"},
|
||||||
|
}
|
||||||
|
for _, c := range yesWarningPlease {
|
||||||
|
r, err := yamlToConfigRule(l, c, "test", 1)
|
||||||
|
require.NoError(t, err)
|
||||||
|
r.Groups = append(r.Groups, "any")
|
||||||
|
err = r.sanity()
|
||||||
|
require.Error(t, err, "I wanted a warning: %+v", c)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
type addRuleCall struct {
|
||||||
|
incoming bool
|
||||||
|
proto uint8
|
||||||
|
startPort int32
|
||||||
|
endPort int32
|
||||||
|
groups []string
|
||||||
|
host string
|
||||||
|
ip string
|
||||||
|
localIp string
|
||||||
|
caName string
|
||||||
|
caSha string
|
||||||
|
}
|
||||||
|
|
||||||
|
type mockFirewall struct {
|
||||||
|
lastCall addRuleCall
|
||||||
|
nextCallReturn error
|
||||||
|
}
|
||||||
|
|
||||||
|
func (mf *mockFirewall) AddRule(incoming bool, proto uint8, startPort int32, endPort int32, groups []string, host string, ip, localIp, caName string, caSha string) error {
|
||||||
|
mf.lastCall = addRuleCall{
|
||||||
|
incoming: incoming,
|
||||||
|
proto: proto,
|
||||||
|
startPort: startPort,
|
||||||
|
endPort: endPort,
|
||||||
|
groups: groups,
|
||||||
|
host: host,
|
||||||
|
ip: ip,
|
||||||
|
localIp: localIp,
|
||||||
|
caName: caName,
|
||||||
|
caSha: caSha,
|
||||||
|
}
|
||||||
|
|
||||||
|
err := mf.nextCallReturn
|
||||||
|
mf.nextCallReturn = nil
|
||||||
|
return err
|
||||||
|
}
|
||||||
@@ -50,6 +50,12 @@ func (fp Packet) MarshalJSON() ([]byte, error) {
|
|||||||
proto = "icmpv6"
|
proto = "icmpv6"
|
||||||
case iputil.IPProtocolUDP:
|
case iputil.IPProtocolUDP:
|
||||||
proto = "udp"
|
proto = "udp"
|
||||||
|
case iputil.IPProtocolUDPLite:
|
||||||
|
proto = "udplite"
|
||||||
|
case iputil.IPProtocolDCCP:
|
||||||
|
proto = "dccp"
|
||||||
|
case iputil.IPProtocolSCTP:
|
||||||
|
proto = "sctp"
|
||||||
default:
|
default:
|
||||||
proto = fmt.Sprintf("unknown %v", fp.Protocol)
|
proto = fmt.Sprintf("unknown %v", fp.Protocol)
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -0,0 +1,330 @@
|
|||||||
|
package firewall
|
||||||
|
|
||||||
|
import (
|
||||||
|
"crypto/sha256"
|
||||||
|
"encoding/hex"
|
||||||
|
"fmt"
|
||||||
|
"hash"
|
||||||
|
"hash/fnv"
|
||||||
|
"io"
|
||||||
|
"log/slog"
|
||||||
|
"net/netip"
|
||||||
|
"slices"
|
||||||
|
|
||||||
|
"github.com/gaissmai/bart"
|
||||||
|
"github.com/slackhq/nebula/iputil"
|
||||||
|
)
|
||||||
|
|
||||||
|
// RulesBuilder collects the inbound and outbound rules, Build turns them into a Table for each direction
|
||||||
|
type RulesBuilder struct {
|
||||||
|
in, out tableRules
|
||||||
|
|
||||||
|
// defaultLocalCIDRAny makes rules without a local cidr allow any local address, even with unsafe networks
|
||||||
|
defaultLocalCIDRAny bool
|
||||||
|
|
||||||
|
// ruleSHA and ruleFNV hash every rule as it's added, see Rules
|
||||||
|
ruleSHA hash.Hash
|
||||||
|
ruleFNV hash.Hash32
|
||||||
|
|
||||||
|
l *slog.Logger
|
||||||
|
}
|
||||||
|
|
||||||
|
// tableRules are one direction's rules, waiting to be built into a Table
|
||||||
|
type tableRules struct {
|
||||||
|
anyRules []rule
|
||||||
|
// protoRules holds the rules for each protocol besides proto `any`, ICMPv6 rules are kept with ICMP
|
||||||
|
protoRules [256][]rule
|
||||||
|
}
|
||||||
|
|
||||||
|
// rule is a parsed rule, so adding it to a Table can't fail
|
||||||
|
type rule struct {
|
||||||
|
startPort, endPort int32
|
||||||
|
groups []string
|
||||||
|
host string
|
||||||
|
caName, caSha string
|
||||||
|
|
||||||
|
// cidr is the remote cidr, not valid when the rule doesn't have one
|
||||||
|
cidr netip.Prefix
|
||||||
|
anyCIDR bool
|
||||||
|
|
||||||
|
// localCIDR is the local addresses the rule allows, anyLocalCIDR allows all of them.
|
||||||
|
// Neither is set for a rule without a local cidr until the Table is built and it gets the default.
|
||||||
|
// localCIDR is shared by every localRules the rule is added to, so it's never changed, see localRules.add
|
||||||
|
localCIDR *bart.Lite
|
||||||
|
anyLocalCIDR bool
|
||||||
|
}
|
||||||
|
|
||||||
|
func NewRulesBuilder(l *slog.Logger) *RulesBuilder {
|
||||||
|
return &RulesBuilder{
|
||||||
|
ruleSHA: sha256.New(),
|
||||||
|
ruleFNV: fnv.New32a(),
|
||||||
|
l: l,
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// AddRule adds a rule for incoming or outgoing traffic, on proto or on every protocol when proto is ProtoAny.
|
||||||
|
// The rule is parsed now, so a bad rule is reported when it's added rather than when the Tables are built.
|
||||||
|
func (b *RulesBuilder) AddRule(incoming bool, proto uint8, startPort int32, endPort int32, groups []string, host string, cidr, localCidr, caName string, caSha string) error {
|
||||||
|
if proto == iputil.IPProtocolICMP || proto == iputil.IPProtocolICMPv6 {
|
||||||
|
//ICMP traffic doesn't have ports, so we always coerce to "any", even if a value is provided
|
||||||
|
if startPort != PortAny {
|
||||||
|
b.l.Warn("ignoring port specification for ICMP firewall rule", "startPort", startPort)
|
||||||
|
}
|
||||||
|
startPort = PortAny
|
||||||
|
endPort = PortAny
|
||||||
|
}
|
||||||
|
|
||||||
|
r, err := parseRule(startPort, endPort, groups, host, cidr, localCidr, caName, caSha)
|
||||||
|
if err != nil {
|
||||||
|
return err
|
||||||
|
}
|
||||||
|
|
||||||
|
if incoming {
|
||||||
|
b.in.add(proto, r)
|
||||||
|
} else {
|
||||||
|
b.out.add(proto, r)
|
||||||
|
}
|
||||||
|
|
||||||
|
// The rule hashes are of these lines, changing them changes every hash
|
||||||
|
fmt.Fprintf(io.MultiWriter(b.ruleSHA, b.ruleFNV),
|
||||||
|
"incoming: %v, proto: %v, startPort: %v, endPort: %v, groups: %v, host: %v, ip: %v, localIp: %v, caName: %v, caSha: %s\n",
|
||||||
|
incoming, proto, startPort, endPort, groups, host, cidr, localCidr, caName, caSha,
|
||||||
|
)
|
||||||
|
|
||||||
|
direction := "incoming"
|
||||||
|
if !incoming {
|
||||||
|
direction = "outgoing"
|
||||||
|
}
|
||||||
|
b.l.Info("Firewall rule added",
|
||||||
|
"firewallRule", m{"direction": direction, "proto": proto, "startPort": startPort, "endPort": endPort, "groups": groups, "host": host, "cidr": cidr, "localCidr": localCidr, "caName": caName, "caSha": caSha},
|
||||||
|
)
|
||||||
|
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
|
||||||
|
// Build turns the rules into a Table for each direction, and hashes them. Rules without a local cidr allow
|
||||||
|
// vpnNetworks when there are unsafe networks, otherwise any local address.
|
||||||
|
func (b *RulesBuilder) Build(vpnNetworks, unsafeNetworks []netip.Prefix) Rules {
|
||||||
|
var defaultLocal *bart.Lite
|
||||||
|
if len(unsafeNetworks) > 0 && !b.defaultLocalCIDRAny {
|
||||||
|
defaultLocal = new(bart.Lite)
|
||||||
|
for _, network := range vpnNetworks {
|
||||||
|
defaultLocal.Insert(network)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
return Rules{
|
||||||
|
In: b.in.build(defaultLocal),
|
||||||
|
Out: b.out.build(defaultLocal),
|
||||||
|
Hash: hex.EncodeToString(b.ruleSHA.Sum(nil)),
|
||||||
|
HashFNV: b.ruleFNV.Sum32(),
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func parseRule(startPort, endPort int32, groups []string, host, cidr, localCidr, caName, caSha string) (rule, error) {
|
||||||
|
if startPort > endPort {
|
||||||
|
return rule{}, fmt.Errorf("start port was lower than end port")
|
||||||
|
}
|
||||||
|
|
||||||
|
r := rule{
|
||||||
|
startPort: startPort,
|
||||||
|
endPort: endPort,
|
||||||
|
groups: groups,
|
||||||
|
host: host,
|
||||||
|
caName: caName,
|
||||||
|
caSha: caSha,
|
||||||
|
}
|
||||||
|
|
||||||
|
var err error
|
||||||
|
r.cidr, r.anyCIDR, err = parseCIDR(cidr)
|
||||||
|
if err != nil {
|
||||||
|
return rule{}, fmt.Errorf("cidr did not parse; %w", err)
|
||||||
|
}
|
||||||
|
|
||||||
|
var localCIDR netip.Prefix
|
||||||
|
localCIDR, r.anyLocalCIDR, err = parseCIDR(localCidr)
|
||||||
|
if err != nil {
|
||||||
|
return rule{}, fmt.Errorf("local_cidr did not parse; %w", err)
|
||||||
|
}
|
||||||
|
if localCIDR.IsValid() {
|
||||||
|
r.localCIDR = new(bart.Lite)
|
||||||
|
r.localCIDR.Insert(localCIDR)
|
||||||
|
}
|
||||||
|
|
||||||
|
return r, nil
|
||||||
|
}
|
||||||
|
|
||||||
|
// add keeps r for proto, or for every protocol when proto is ProtoAny
|
||||||
|
func (tr *tableRules) add(proto uint8, r rule) {
|
||||||
|
switch proto {
|
||||||
|
case ProtoAny:
|
||||||
|
tr.anyRules = append(tr.anyRules, r)
|
||||||
|
case iputil.IPProtocolICMPv6:
|
||||||
|
tr.protoRules[iputil.IPProtocolICMP] = append(tr.protoRules[iputil.IPProtocolICMP], r)
|
||||||
|
default:
|
||||||
|
tr.protoRules[proto] = append(tr.protoRules[proto], r)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// build turns the rules into a Table. Rules without a local cidr allow defaultLocal,
|
||||||
|
// or any local address when defaultLocal is nil.
|
||||||
|
func (tr *tableRules) build(defaultLocal *bart.Lite) *Table {
|
||||||
|
t := &Table{}
|
||||||
|
|
||||||
|
// Every protocol starts out sharing the proto `any` rules, including protos[ProtoAny]
|
||||||
|
anyProto := newPortRules(defaultLocal, tr.anyRules)
|
||||||
|
for proto := range t.protos {
|
||||||
|
t.protos[proto] = anyProto
|
||||||
|
}
|
||||||
|
|
||||||
|
// Protocols with rules of their own get a copy of the proto `any` rules too, so a packet only checks one set
|
||||||
|
for proto, rules := range tr.protoRules {
|
||||||
|
if len(rules) > 0 {
|
||||||
|
t.protos[proto] = newPortRules(defaultLocal, tr.anyRules, rules)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// ICMP and ICMPv6 share one set of rules, add keeps them together under ICMP
|
||||||
|
t.protos[iputil.IPProtocolICMPv6] = t.protos[iputil.IPProtocolICMP]
|
||||||
|
|
||||||
|
return t
|
||||||
|
}
|
||||||
|
|
||||||
|
// newPortRules builds portRules from each set of rules, or returns nil when there are none
|
||||||
|
func newPortRules(defaultLocal *bart.Lite, ruleSets ...[]rule) portRules {
|
||||||
|
var pr portRules
|
||||||
|
for _, rules := range ruleSets {
|
||||||
|
for _, r := range rules {
|
||||||
|
if pr == nil {
|
||||||
|
pr = portRules{}
|
||||||
|
}
|
||||||
|
pr.add(r.withDefaultLocal(defaultLocal))
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return pr
|
||||||
|
}
|
||||||
|
|
||||||
|
// parseCIDR parses a rule's cidr, which is empty, `any`, or a prefix
|
||||||
|
func parseCIDR(s string) (prefix netip.Prefix, isAny bool, err error) {
|
||||||
|
switch s {
|
||||||
|
case "":
|
||||||
|
return netip.Prefix{}, false, nil
|
||||||
|
case "any":
|
||||||
|
return netip.Prefix{}, true, nil
|
||||||
|
}
|
||||||
|
|
||||||
|
prefix, err = netip.ParsePrefix(s)
|
||||||
|
return prefix, false, err
|
||||||
|
}
|
||||||
|
|
||||||
|
// isAny reports whether r matches any host, making its groups, host, and cidr irrelevant
|
||||||
|
func (r rule) isAny() bool {
|
||||||
|
if len(r.groups) == 0 && r.host == "" && !r.cidr.IsValid() {
|
||||||
|
return true
|
||||||
|
}
|
||||||
|
|
||||||
|
return slices.Contains(r.groups, "any") || r.host == "any" || r.anyCIDR
|
||||||
|
}
|
||||||
|
|
||||||
|
// withDefaultLocal returns r allowing defaultLocal, or any local address when defaultLocal is nil,
|
||||||
|
// unless r has a local cidr of its own
|
||||||
|
func (r rule) withDefaultLocal(defaultLocal *bart.Lite) rule {
|
||||||
|
if !r.anyLocalCIDR && r.localCIDR == nil {
|
||||||
|
r.anyLocalCIDR = defaultLocal == nil
|
||||||
|
r.localCIDR = defaultLocal
|
||||||
|
}
|
||||||
|
return r
|
||||||
|
}
|
||||||
|
|
||||||
|
func (pr portRules) add(r rule) {
|
||||||
|
for i := r.startPort; i <= r.endPort; i++ {
|
||||||
|
cr := pr[i]
|
||||||
|
if cr == nil {
|
||||||
|
cr = &caRules{}
|
||||||
|
pr[i] = cr
|
||||||
|
}
|
||||||
|
cr.add(r)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func (cr *caRules) add(r rule) {
|
||||||
|
if r.caSha == "" && r.caName == "" {
|
||||||
|
if cr.Any == nil {
|
||||||
|
cr.Any = &remoteRules{}
|
||||||
|
}
|
||||||
|
cr.Any.add(r)
|
||||||
|
return
|
||||||
|
}
|
||||||
|
|
||||||
|
if r.caSha != "" {
|
||||||
|
getOrNew(&cr.CAShas, r.caSha).add(r)
|
||||||
|
}
|
||||||
|
|
||||||
|
if r.caName != "" {
|
||||||
|
getOrNew(&cr.CANames, r.caName).add(r)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func (rr *remoteRules) add(r rule) {
|
||||||
|
if r.isAny() {
|
||||||
|
if rr.Any == nil {
|
||||||
|
rr.Any = &localRules{}
|
||||||
|
}
|
||||||
|
rr.Any.add(r)
|
||||||
|
return
|
||||||
|
}
|
||||||
|
|
||||||
|
if len(r.groups) > 0 {
|
||||||
|
lr := &localRules{}
|
||||||
|
lr.add(r)
|
||||||
|
rr.Groups = append(rr.Groups, &groupsRule{
|
||||||
|
Groups: r.groups,
|
||||||
|
LocalCIDR: lr,
|
||||||
|
})
|
||||||
|
}
|
||||||
|
|
||||||
|
if r.host != "" {
|
||||||
|
getOrNew(&rr.Hosts, r.host).add(r)
|
||||||
|
}
|
||||||
|
|
||||||
|
if r.cidr.IsValid() {
|
||||||
|
if rr.CIDR == nil {
|
||||||
|
rr.CIDR = new(bart.Table[*localRules])
|
||||||
|
}
|
||||||
|
lr, ok := rr.CIDR.Get(r.cidr)
|
||||||
|
if !ok {
|
||||||
|
lr = &localRules{}
|
||||||
|
rr.CIDR.Insert(r.cidr, lr)
|
||||||
|
}
|
||||||
|
lr.add(r)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func (lr *localRules) add(r rule) {
|
||||||
|
if r.anyLocalCIDR {
|
||||||
|
lr.Any = true
|
||||||
|
return
|
||||||
|
}
|
||||||
|
|
||||||
|
// Share the rule's local cidrs until another rule's need adding, then copy them instead of changing them
|
||||||
|
if lr.LocalCIDR == nil {
|
||||||
|
lr.LocalCIDR = r.localCIDR
|
||||||
|
return
|
||||||
|
}
|
||||||
|
for prefix := range r.localCIDR.All() {
|
||||||
|
lr.LocalCIDR = lr.LocalCIDR.InsertPersist(prefix)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// getOrNew returns m[k], adding a new value for k first when there isn't one. m is made if it's nil.
|
||||||
|
func getOrNew[M ~map[K]*V, K comparable, V any](m *M, k K) *V {
|
||||||
|
if *m == nil {
|
||||||
|
*m = make(M)
|
||||||
|
}
|
||||||
|
v := (*m)[k]
|
||||||
|
if v == nil {
|
||||||
|
v = new(V)
|
||||||
|
(*m)[k] = v
|
||||||
|
}
|
||||||
|
return v
|
||||||
|
}
|
||||||
@@ -0,0 +1,239 @@
|
|||||||
|
package firewall
|
||||||
|
|
||||||
|
import (
|
||||||
|
"math"
|
||||||
|
"net/netip"
|
||||||
|
"testing"
|
||||||
|
|
||||||
|
"github.com/slackhq/nebula/iputil"
|
||||||
|
"github.com/slackhq/nebula/test"
|
||||||
|
"github.com/stretchr/testify/assert"
|
||||||
|
"github.com/stretchr/testify/require"
|
||||||
|
)
|
||||||
|
|
||||||
|
func TestRulesBuilder_AddRule(t *testing.T) {
|
||||||
|
l := test.NewLogger()
|
||||||
|
|
||||||
|
ti, err := netip.ParsePrefix("1.2.3.4/32")
|
||||||
|
require.NoError(t, err)
|
||||||
|
|
||||||
|
ti6, err := netip.ParsePrefix("fd12::34/128")
|
||||||
|
require.NoError(t, err)
|
||||||
|
|
||||||
|
rb := NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 1, 1, []string{}, "", "", "", "", ""))
|
||||||
|
rules := rb.Build(nil, nil)
|
||||||
|
// An empty rule is any
|
||||||
|
assert.True(t, rules.In.protos[iputil.IPProtocolTCP][1].Any.Any.Any)
|
||||||
|
assert.Empty(t, rules.In.protos[iputil.IPProtocolTCP][1].Any.Groups)
|
||||||
|
assert.Empty(t, rules.In.protos[iputil.IPProtocolTCP][1].Any.Hosts)
|
||||||
|
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(true, iputil.IPProtocolUDP, 1, 1, []string{"g1"}, "", "", "", "", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.Nil(t, rules.In.protos[iputil.IPProtocolUDP][1].Any.Any)
|
||||||
|
assert.Contains(t, rules.In.protos[iputil.IPProtocolUDP][1].Any.Groups[0].Groups, "g1")
|
||||||
|
assert.Empty(t, rules.In.protos[iputil.IPProtocolUDP][1].Any.Hosts)
|
||||||
|
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(true, iputil.IPProtocolICMP, 1, 1, []string{}, "h1", "", "", "", ""))
|
||||||
|
require.NoError(t, rb.AddRule(true, iputil.IPProtocolICMPv6, 1, 1, []string{}, "h2", "", "", "", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
//no matter what port is given for icmp, it should end up as "any"
|
||||||
|
assert.Nil(t, rules.In.protos[iputil.IPProtocolICMP][PortAny].Any.Any)
|
||||||
|
assert.Empty(t, rules.In.protos[iputil.IPProtocolICMP][PortAny].Any.Groups)
|
||||||
|
assert.Contains(t, rules.In.protos[iputil.IPProtocolICMP][PortAny].Any.Hosts, "h1")
|
||||||
|
|
||||||
|
// ICMP and ICMPv6 share one set of rules
|
||||||
|
assert.Contains(t, rules.In.protos[iputil.IPProtocolICMP][PortAny].Any.Hosts, "h2")
|
||||||
|
assert.Contains(t, rules.In.protos[iputil.IPProtocolICMPv6][PortAny].Any.Hosts, "h1")
|
||||||
|
|
||||||
|
// Any other protocol number gets its own rules
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(true, 47, 0, 0, []string{"g1"}, "", "", "", "", "")) // GRE
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.Contains(t, rules.In.protos[47][PortAny].Any.Groups[0].Groups, "g1")
|
||||||
|
assert.Nil(t, rules.In.protos[iputil.IPProtocolTCP])
|
||||||
|
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(false, ProtoAny, 1, 1, []string{}, "", ti.String(), "", "", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.Nil(t, rules.Out.protos[ProtoAny][1].Any.Any)
|
||||||
|
_, ok := rules.Out.protos[ProtoAny][1].Any.CIDR.Get(ti)
|
||||||
|
assert.True(t, ok)
|
||||||
|
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(false, ProtoAny, 1, 1, []string{}, "", ti6.String(), "", "", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.Nil(t, rules.Out.protos[ProtoAny][1].Any.Any)
|
||||||
|
_, ok = rules.Out.protos[ProtoAny][1].Any.CIDR.Get(ti6)
|
||||||
|
assert.True(t, ok)
|
||||||
|
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(false, ProtoAny, 1, 1, []string{}, "", "", ti.String(), "", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.NotNil(t, rules.Out.protos[ProtoAny][1].Any.Any)
|
||||||
|
ok = rules.Out.protos[ProtoAny][1].Any.Any.LocalCIDR.Get(ti)
|
||||||
|
assert.True(t, ok)
|
||||||
|
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(false, ProtoAny, 1, 1, []string{}, "", "", ti6.String(), "", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.NotNil(t, rules.Out.protos[ProtoAny][1].Any.Any)
|
||||||
|
ok = rules.Out.protos[ProtoAny][1].Any.Any.LocalCIDR.Get(ti6)
|
||||||
|
assert.True(t, ok)
|
||||||
|
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(true, iputil.IPProtocolUDP, 1, 1, []string{"g1"}, "", "", "", "ca-name", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.Contains(t, rules.In.protos[iputil.IPProtocolUDP][1].CANames, "ca-name")
|
||||||
|
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(true, iputil.IPProtocolUDP, 1, 1, []string{"g1"}, "", "", "", "", "ca-sha"))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.Contains(t, rules.In.protos[iputil.IPProtocolUDP][1].CAShas, "ca-sha")
|
||||||
|
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "any", "", "", "", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.True(t, rules.Out.protos[ProtoAny][0].Any.Any.Any)
|
||||||
|
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
anyIp, err := netip.ParsePrefix("0.0.0.0/0")
|
||||||
|
require.NoError(t, err)
|
||||||
|
|
||||||
|
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", anyIp.String(), "", "", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.Nil(t, rules.Out.protos[ProtoAny][0].Any.Any)
|
||||||
|
table, ok := rules.Out.protos[ProtoAny][0].Any.CIDR.Lookup(netip.MustParseAddr("1.1.1.1"))
|
||||||
|
assert.True(t, table.Any)
|
||||||
|
table, ok = rules.Out.protos[ProtoAny][0].Any.CIDR.Lookup(netip.MustParseAddr("9::9"))
|
||||||
|
assert.False(t, ok)
|
||||||
|
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
anyIp6, err := netip.ParsePrefix("::/0")
|
||||||
|
require.NoError(t, err)
|
||||||
|
|
||||||
|
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", anyIp6.String(), "", "", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.Nil(t, rules.Out.protos[ProtoAny][0].Any.Any)
|
||||||
|
table, ok = rules.Out.protos[ProtoAny][0].Any.CIDR.Lookup(netip.MustParseAddr("9::9"))
|
||||||
|
assert.True(t, table.Any)
|
||||||
|
table, ok = rules.Out.protos[ProtoAny][0].Any.CIDR.Lookup(netip.MustParseAddr("1.1.1.1"))
|
||||||
|
assert.False(t, ok)
|
||||||
|
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", "any", "", "", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.True(t, rules.Out.protos[ProtoAny][0].Any.Any.Any)
|
||||||
|
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", "", anyIp.String(), "", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.False(t, rules.Out.protos[ProtoAny][0].Any.Any.Any)
|
||||||
|
assert.True(t, rules.Out.protos[ProtoAny][0].Any.Any.LocalCIDR.Lookup(netip.MustParseAddr("1.1.1.1")))
|
||||||
|
assert.False(t, rules.Out.protos[ProtoAny][0].Any.Any.LocalCIDR.Lookup(netip.MustParseAddr("9::9")))
|
||||||
|
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", "", anyIp6.String(), "", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.False(t, rules.Out.protos[ProtoAny][0].Any.Any.Any)
|
||||||
|
assert.True(t, rules.Out.protos[ProtoAny][0].Any.Any.LocalCIDR.Lookup(netip.MustParseAddr("9::9")))
|
||||||
|
assert.False(t, rules.Out.protos[ProtoAny][0].Any.Any.LocalCIDR.Lookup(netip.MustParseAddr("1.1.1.1")))
|
||||||
|
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", "", "any", "", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.True(t, rules.Out.protos[ProtoAny][0].Any.Any.Any)
|
||||||
|
|
||||||
|
// Every protocol number is accepted
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(true, math.MaxUint8, 0, 0, []string{}, "", "", "", "", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.True(t, rules.In.protos[math.MaxUint8][PortAny].Any.Any.Any)
|
||||||
|
|
||||||
|
// Test error conditions, a bad rule is reported when it's added
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.Error(t, rb.AddRule(true, ProtoAny, 10, 0, []string{}, "", "", "", "", ""))
|
||||||
|
require.Error(t, rb.AddRule(true, ProtoAny, 0, 0, []string{}, "", "junk", "", "", ""))
|
||||||
|
require.Error(t, rb.AddRule(true, ProtoAny, 0, 0, []string{}, "", "", "junk", "", ""))
|
||||||
|
|
||||||
|
// ICMP and ICMPv6 share one copy of each proto `any` rule
|
||||||
|
rb = NewRulesBuilder(l)
|
||||||
|
require.NoError(t, rb.AddRule(true, ProtoAny, PortAny, PortAny, []string{"default-group"}, "", "", "", "", ""))
|
||||||
|
require.NoError(t, rb.AddRule(true, iputil.IPProtocolICMPv6, PortAny, PortAny, []string{"nope"}, "", "", "", "", ""))
|
||||||
|
rules = rb.Build(nil, nil)
|
||||||
|
assert.Len(t, rules.In.protos[iputil.IPProtocolICMP][PortAny].Any.Groups, 2)
|
||||||
|
assert.Len(t, rules.In.protos[iputil.IPProtocolICMPv6][PortAny].Any.Groups, 2)
|
||||||
|
|
||||||
|
// No rules allow nothing
|
||||||
|
rules = NewRulesBuilder(l).Build(nil, nil)
|
||||||
|
for proto := range rules.In.protos {
|
||||||
|
assert.Nil(t, rules.In.protos[proto], "proto %d", proto)
|
||||||
|
assert.Nil(t, rules.Out.protos[proto], "proto %d", proto)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// TestRulesBuilder_sharedLocalCIDR ensures local cidrs shared between rules and ports are copied, not changed,
|
||||||
|
// when another rule's local cidrs are added to them. The prefixes share their first octet so the copy has to reach
|
||||||
|
// past the root of the shared table.
|
||||||
|
func TestRulesBuilder_sharedLocalCIDR(t *testing.T) {
|
||||||
|
vpnNetworks := []netip.Prefix{
|
||||||
|
netip.MustParsePrefix("10.1.0.5/16"),
|
||||||
|
netip.MustParsePrefix("10.2.0.5/16"),
|
||||||
|
netip.MustParsePrefix("fd00:1::5/64"),
|
||||||
|
}
|
||||||
|
unsafeNetworks := []netip.Prefix{netip.MustParsePrefix("192.168.0.0/24")}
|
||||||
|
vpn1 := netip.MustParseAddr("10.1.9.9")
|
||||||
|
vpn2 := netip.MustParseAddr("10.2.9.9")
|
||||||
|
vpn6 := netip.MustParseAddr("fd00:1::9")
|
||||||
|
h1Extra := netip.MustParseAddr("10.3.0.1")
|
||||||
|
h1Extra6 := netip.MustParseAddr("fd00:2::1")
|
||||||
|
h2Own := netip.MustParseAddr("10.4.0.1")
|
||||||
|
|
||||||
|
rb := NewRulesBuilder(test.NewLogger())
|
||||||
|
// h1 allows the vpn networks by default on ports 1 and 2, and 10.3.0.0/16 and fd00:2::/64 as well on port 1
|
||||||
|
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 1, 2, nil, "h1", "", "", "", ""))
|
||||||
|
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 1, 1, nil, "h1", "", "10.3.0.0/16", "", ""))
|
||||||
|
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 1, 1, nil, "h1", "", "fd00:2::/64", "", ""))
|
||||||
|
// h2 allows 10.4.0.0/16 on ports 1 and 2, and the vpn networks by default as well on port 1
|
||||||
|
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 1, 2, nil, "h2", "", "10.4.0.0/16", "", ""))
|
||||||
|
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 1, 1, nil, "h2", "", "", "", ""))
|
||||||
|
// h3 only has the default
|
||||||
|
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 3, 3, nil, "h3", "", "", "", ""))
|
||||||
|
rules := rb.Build(vpnNetworks, unsafeNetworks)
|
||||||
|
|
||||||
|
for _, tc := range []struct {
|
||||||
|
port int32
|
||||||
|
host string
|
||||||
|
addr netip.Addr
|
||||||
|
want bool
|
||||||
|
}{
|
||||||
|
{1, "h1", vpn1, true},
|
||||||
|
{1, "h1", vpn2, true},
|
||||||
|
{1, "h1", vpn6, true},
|
||||||
|
{1, "h1", h1Extra, true},
|
||||||
|
{1, "h1", h1Extra6, true},
|
||||||
|
{1, "h1", h2Own, false},
|
||||||
|
{2, "h1", vpn1, true},
|
||||||
|
{2, "h1", h1Extra, false},
|
||||||
|
{2, "h1", h1Extra6, false},
|
||||||
|
{1, "h2", h2Own, true},
|
||||||
|
{1, "h2", vpn1, true},
|
||||||
|
{1, "h2", vpn2, true},
|
||||||
|
{1, "h2", vpn6, true},
|
||||||
|
{1, "h2", h1Extra, false},
|
||||||
|
{2, "h2", h2Own, true},
|
||||||
|
{2, "h2", vpn1, false},
|
||||||
|
{2, "h2", vpn6, false},
|
||||||
|
{3, "h3", vpn1, true},
|
||||||
|
{3, "h3", vpn2, true},
|
||||||
|
{3, "h3", vpn6, true},
|
||||||
|
{3, "h3", h1Extra, false},
|
||||||
|
{3, "h3", h1Extra6, false},
|
||||||
|
{3, "h3", h2Own, false},
|
||||||
|
} {
|
||||||
|
lr := rules.In.protos[iputil.IPProtocolTCP][tc.port].Any.Hosts[tc.host]
|
||||||
|
assert.Equal(t, tc.want, lr.match(&Packet{LocalAddr: tc.addr}, nil), "port %d, %s, %s", tc.port, tc.host, tc.addr)
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,188 @@
|
|||||||
|
package firewall
|
||||||
|
|
||||||
|
import (
|
||||||
|
"net/netip"
|
||||||
|
|
||||||
|
"github.com/gaissmai/bart"
|
||||||
|
"github.com/slackhq/nebula/cert"
|
||||||
|
"github.com/slackhq/nebula/iputil"
|
||||||
|
)
|
||||||
|
|
||||||
|
// Rules are the Tables built for each direction, with hashes of the rules they were built from
|
||||||
|
type Rules struct {
|
||||||
|
In, Out *Table
|
||||||
|
|
||||||
|
// Hash is a sha256 of the rules, HashFNV is an FNV-1a of them for use as a metric value.
|
||||||
|
// Rule sets with the same rules have the same hashes.
|
||||||
|
Hash string
|
||||||
|
HashFNV uint32
|
||||||
|
}
|
||||||
|
|
||||||
|
// Table holds the rules for one direction, the evaluation order is:
|
||||||
|
// Proto AND port AND (CA SHA or CA name) AND local CIDR AND (group OR groups OR name OR remote CIDR)
|
||||||
|
// A Table doesn't change once built, see RulesBuilder.
|
||||||
|
type Table struct {
|
||||||
|
// protos holds the rules for each IP protocol number, so a packet is only checked against one set of rules.
|
||||||
|
// A protocol with rules of its own also holds a copy of every proto `any` rule, the rest share the proto `any`
|
||||||
|
// rules, which are at protos[ProtoAny]. nil when a protocol has no rules at all.
|
||||||
|
// ICMP and ICMPv6 share one set of rules.
|
||||||
|
protos [256]portRules
|
||||||
|
}
|
||||||
|
|
||||||
|
// Even though ports are uint16, int32 maps are faster for lookup
|
||||||
|
// Plus we can use `-1` for fragment rules
|
||||||
|
type portRules map[int32]*caRules
|
||||||
|
|
||||||
|
// caRules and the types below it only make their maps and tables once a rule needs them, a range of ports
|
||||||
|
// gets a copy for every port so empty ones add up
|
||||||
|
type caRules struct {
|
||||||
|
Any *remoteRules
|
||||||
|
CANames map[string]*remoteRules
|
||||||
|
CAShas map[string]*remoteRules
|
||||||
|
}
|
||||||
|
|
||||||
|
type remoteRules struct {
|
||||||
|
// Any makes Hosts, Groups, and CIDR irrelevant
|
||||||
|
Any *localRules
|
||||||
|
Hosts map[string]*localRules
|
||||||
|
Groups []*groupsRule
|
||||||
|
CIDR *bart.Table[*localRules]
|
||||||
|
}
|
||||||
|
|
||||||
|
type groupsRule struct {
|
||||||
|
Groups []string
|
||||||
|
LocalCIDR *localRules
|
||||||
|
}
|
||||||
|
|
||||||
|
type localRules struct {
|
||||||
|
Any bool
|
||||||
|
// LocalCIDR is always set when Any isn't. It's shared with other localRules, so it's never changed.
|
||||||
|
LocalCIDR *bart.Lite
|
||||||
|
}
|
||||||
|
|
||||||
|
// Match reports whether a rule for the direction p is going allows it
|
||||||
|
func (r *Rules) Match(p *Packet, incoming bool, c *cert.CachedCertificate, caPool *cert.CAPool) bool {
|
||||||
|
t := r.Out
|
||||||
|
if incoming {
|
||||||
|
t = r.In
|
||||||
|
}
|
||||||
|
return t.Match(p, incoming, c, caPool)
|
||||||
|
}
|
||||||
|
|
||||||
|
// Match reports whether a rule allows p
|
||||||
|
func (t *Table) Match(p *Packet, incoming bool, c *cert.CachedCertificate, caPool *cert.CAPool) bool {
|
||||||
|
return t.protos[p.Protocol].match(p, incoming, c, caPool)
|
||||||
|
}
|
||||||
|
|
||||||
|
func (pr portRules) match(p *Packet, incoming bool, c *cert.CachedCertificate, caPool *cert.CAPool) bool {
|
||||||
|
// We don't have any allowed ports, bail
|
||||||
|
if pr == nil {
|
||||||
|
return false
|
||||||
|
}
|
||||||
|
|
||||||
|
// ICMP has no ports, only the port `any` rules apply, including the ones copied in from proto `any` rules
|
||||||
|
if p.Protocol == iputil.IPProtocolICMP || p.Protocol == iputil.IPProtocolICMPv6 {
|
||||||
|
// port numbers are re-used for connection tracking of ICMP,
|
||||||
|
// but we don't want to actually filter on them.
|
||||||
|
return pr[PortAny].match(p, c, caPool)
|
||||||
|
}
|
||||||
|
|
||||||
|
var port int32
|
||||||
|
|
||||||
|
if p.Fragment {
|
||||||
|
port = PortFragment
|
||||||
|
} else if incoming {
|
||||||
|
port = int32(p.LocalPort)
|
||||||
|
} else {
|
||||||
|
port = int32(p.RemotePort)
|
||||||
|
}
|
||||||
|
|
||||||
|
// Packets without ports (gre, esp, etc) have port 0, which is PortAny, don't check those rules twice
|
||||||
|
if port != PortAny && pr[port].match(p, c, caPool) {
|
||||||
|
return true
|
||||||
|
}
|
||||||
|
|
||||||
|
return pr[PortAny].match(p, c, caPool)
|
||||||
|
}
|
||||||
|
|
||||||
|
func (cr *caRules) match(p *Packet, c *cert.CachedCertificate, caPool *cert.CAPool) bool {
|
||||||
|
if cr == nil {
|
||||||
|
return false
|
||||||
|
}
|
||||||
|
|
||||||
|
if cr.Any.match(p, c) {
|
||||||
|
return true
|
||||||
|
}
|
||||||
|
|
||||||
|
if t, ok := cr.CAShas[c.Certificate.Issuer()]; ok {
|
||||||
|
if t.match(p, c) {
|
||||||
|
return true
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
s, err := caPool.GetCAForCert(c.Certificate)
|
||||||
|
if err != nil {
|
||||||
|
return false
|
||||||
|
}
|
||||||
|
|
||||||
|
return cr.CANames[s.Certificate.Name()].match(p, c)
|
||||||
|
}
|
||||||
|
|
||||||
|
func (rr *remoteRules) match(p *Packet, c *cert.CachedCertificate) bool {
|
||||||
|
if rr == nil {
|
||||||
|
return false
|
||||||
|
}
|
||||||
|
|
||||||
|
// Shortcut path for if groups, hosts, or cidr contained an `any`
|
||||||
|
if rr.Any.match(p, c) {
|
||||||
|
return true
|
||||||
|
}
|
||||||
|
|
||||||
|
// Need any of group, host, or cidr to match
|
||||||
|
for _, sg := range rr.Groups {
|
||||||
|
found := false
|
||||||
|
|
||||||
|
for _, g := range sg.Groups {
|
||||||
|
if _, ok := c.InvertedGroups[g]; !ok {
|
||||||
|
found = false
|
||||||
|
break
|
||||||
|
}
|
||||||
|
|
||||||
|
found = true
|
||||||
|
}
|
||||||
|
|
||||||
|
if found && sg.LocalCIDR.match(p, c) {
|
||||||
|
return true
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
if rr.Hosts != nil {
|
||||||
|
if lr, ok := rr.Hosts[c.Certificate.Name()]; ok {
|
||||||
|
if lr.match(p, c) {
|
||||||
|
return true
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
if rr.CIDR != nil {
|
||||||
|
for _, v := range rr.CIDR.Supernets(netip.PrefixFrom(p.RemoteAddr, p.RemoteAddr.BitLen())) {
|
||||||
|
if v.match(p, c) {
|
||||||
|
return true
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
return false
|
||||||
|
}
|
||||||
|
|
||||||
|
func (lr *localRules) match(p *Packet, c *cert.CachedCertificate) bool {
|
||||||
|
if lr == nil {
|
||||||
|
return false
|
||||||
|
}
|
||||||
|
|
||||||
|
if lr.Any {
|
||||||
|
return true
|
||||||
|
}
|
||||||
|
|
||||||
|
return lr.LocalCIDR.Contains(p.LocalAddr)
|
||||||
|
}
|
||||||
+270
-549
File diff suppressed because it is too large.
Load diff
-16
@@ -69,8 +69,6 @@ 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.
|
|
||||||
established *establishedRemotes
|
|
||||||
l *slog.Logger
|
l *slog.Logger
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -278,11 +276,6 @@ 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 +516,6 @@ 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 +662,6 @@ 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 +842,6 @@ 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()
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -32,6 +32,9 @@ const (
|
|||||||
IPProtocolICMPv6 = 58
|
IPProtocolICMPv6 = 58
|
||||||
IPProtocolTCP = 6
|
IPProtocolTCP = 6
|
||||||
IPProtocolUDP = 17
|
IPProtocolUDP = 17
|
||||||
|
IPProtocolUDPLite = 136
|
||||||
|
IPProtocolDCCP = 33
|
||||||
|
IPProtocolSCTP = 132
|
||||||
ICMPv6TypeEchoRequest = 128
|
ICMPv6TypeEchoRequest = 128
|
||||||
ICMPv6TypeEchoReply = 129
|
ICMPv6TypeEchoReply = 129
|
||||||
)
|
)
|
||||||
|
|||||||
@@ -213,7 +213,6 @@ 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)
|
||||||
|
|||||||
+15
-3
@@ -385,7 +385,7 @@ func parseV6(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
|
|||||||
fp.RemotePort = 0
|
fp.RemotePort = 0
|
||||||
}
|
}
|
||||||
|
|
||||||
case iputil.IPProtocolTCP, iputil.IPProtocolUDP:
|
case iputil.IPProtocolTCP, iputil.IPProtocolUDP, iputil.IPProtocolDCCP, iputil.IPProtocolSCTP, iputil.IPProtocolUDPLite:
|
||||||
if dataLen < offset+4 {
|
if dataLen < offset+4 {
|
||||||
return ErrIPv6PacketTooShort
|
return ErrIPv6PacketTooShort
|
||||||
}
|
}
|
||||||
@@ -456,10 +456,16 @@ func parseV4(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
|
|||||||
if fp.Fragment {
|
if fp.Fragment {
|
||||||
fp.RemotePort = 0
|
fp.RemotePort = 0
|
||||||
fp.LocalPort = 0
|
fp.LocalPort = 0
|
||||||
} else if fp.Protocol == iputil.IPProtocolICMP { //note that orientation doesn't matter on ICMP
|
return nil
|
||||||
|
}
|
||||||
|
|
||||||
|
switch fp.Protocol {
|
||||||
|
case iputil.IPProtocolICMP: //note that orientation doesn't matter on ICMP
|
||||||
fp.RemotePort = binary.BigEndian.Uint16(data[ihl+4 : ihl+6]) //identifier
|
fp.RemotePort = binary.BigEndian.Uint16(data[ihl+4 : ihl+6]) //identifier
|
||||||
fp.LocalPort = 0 //code would be uint16(data[ihl+1])
|
fp.LocalPort = 0 //code would be uint16(data[ihl+1])
|
||||||
} else if incoming {
|
|
||||||
|
case iputil.IPProtocolTCP, iputil.IPProtocolUDP, iputil.IPProtocolDCCP, iputil.IPProtocolSCTP, iputil.IPProtocolUDPLite:
|
||||||
|
if incoming {
|
||||||
fp.RemotePort = binary.BigEndian.Uint16(data[ihl : ihl+2]) //src port
|
fp.RemotePort = binary.BigEndian.Uint16(data[ihl : ihl+2]) //src port
|
||||||
fp.LocalPort = binary.BigEndian.Uint16(data[ihl+2 : ihl+4]) //dst port
|
fp.LocalPort = binary.BigEndian.Uint16(data[ihl+2 : ihl+4]) //dst port
|
||||||
} else {
|
} else {
|
||||||
@@ -467,6 +473,12 @@ func parseV4(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
|
|||||||
fp.RemotePort = binary.BigEndian.Uint16(data[ihl+2 : ihl+4]) //dst port
|
fp.RemotePort = binary.BigEndian.Uint16(data[ihl+2 : ihl+4]) //dst port
|
||||||
}
|
}
|
||||||
|
|
||||||
|
default:
|
||||||
|
// don't set ports for protocols Nebula doesn't inspect, the first 4 bytes of GRE, IPIP, AH, etc. are not ports
|
||||||
|
fp.RemotePort = 0
|
||||||
|
fp.LocalPort = 0
|
||||||
|
}
|
||||||
|
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
+84
-19
@@ -77,7 +77,7 @@ func Test_newPacket(t *testing.T) {
|
|||||||
// account for variable ip header length - outgoing
|
// account for variable ip header length - outgoing
|
||||||
h = ipv4.Header{
|
h = ipv4.Header{
|
||||||
Version: 1,
|
Version: 1,
|
||||||
Protocol: 2,
|
Protocol: iputil.IPProtocolUDP,
|
||||||
Len: 100,
|
Len: 100,
|
||||||
Src: net.IPv4(10, 0, 0, 1),
|
Src: net.IPv4(10, 0, 0, 1),
|
||||||
Dst: net.IPv4(10, 0, 0, 2),
|
Dst: net.IPv4(10, 0, 0, 2),
|
||||||
@@ -89,7 +89,7 @@ func Test_newPacket(t *testing.T) {
|
|||||||
err = newPacket(b, false, p)
|
err = newPacket(b, false, p)
|
||||||
|
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
assert.Equal(t, uint8(2), p.Protocol)
|
assert.Equal(t, uint8(iputil.IPProtocolUDP), p.Protocol)
|
||||||
assert.Equal(t, netip.MustParseAddr("10.0.0.1"), p.LocalAddr)
|
assert.Equal(t, netip.MustParseAddr("10.0.0.1"), p.LocalAddr)
|
||||||
assert.Equal(t, netip.MustParseAddr("10.0.0.2"), p.RemoteAddr)
|
assert.Equal(t, netip.MustParseAddr("10.0.0.2"), p.RemoteAddr)
|
||||||
assert.Equal(t, uint16(6), p.RemotePort)
|
assert.Equal(t, uint16(6), p.RemotePort)
|
||||||
@@ -97,6 +97,71 @@ func Test_newPacket(t *testing.T) {
|
|||||||
assert.False(t, p.Fragment)
|
assert.False(t, p.Fragment)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Test_newPacket_v4NoPorts ensures only protocols that lead with src/dst ports report them. The first 4 bytes of other protocols are not ports,
|
||||||
|
// and are often chosen by the sender: a GRE header's protocol type, an IPIP inner total length, a 6in4 flow label.
|
||||||
|
// Reading them as ports would let a `proto: any` rule with a port match tunneled traffic.
|
||||||
|
func Test_newPacket_v4NoPorts(t *testing.T) {
|
||||||
|
p := &firewall.ParsedPacket{}
|
||||||
|
|
||||||
|
for _, proto := range []uint8{4, 41, 47, 50, 51} { // IPIP, 6in4, GRE, ESP, AH
|
||||||
|
h := ipv4.Header{
|
||||||
|
Version: 4,
|
||||||
|
Len: ipv4.HeaderLen,
|
||||||
|
Protocol: int(proto),
|
||||||
|
Src: net.IPv4(10, 0, 0, 1),
|
||||||
|
Dst: net.IPv4(10, 0, 0, 2),
|
||||||
|
}
|
||||||
|
b, err := h.Marshal()
|
||||||
|
require.NoError(t, err)
|
||||||
|
b = append(b, []byte{0x00, 0x00, 0x86, 0xdd}...) // a GRE header carrying IPv6 would read as port 34525
|
||||||
|
|
||||||
|
for _, incoming := range []bool{true, false} {
|
||||||
|
require.NoError(t, newPacket(b, incoming, p))
|
||||||
|
assert.Equal(t, proto, p.Protocol)
|
||||||
|
assert.Equal(t, uint16(0), p.RemotePort)
|
||||||
|
assert.Equal(t, uint16(0), p.LocalPort)
|
||||||
|
assert.False(t, p.Fragment)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// Test_newPacket_portedProtocols ensures UDP-Lite, DCCP, and SCTP report ports from the same leading
|
||||||
|
// src/dst port words as TCP and UDP, oriented the same way.
|
||||||
|
func Test_newPacket_portedProtocols(t *testing.T) {
|
||||||
|
p := &firewall.ParsedPacket{}
|
||||||
|
ports := []byte{0x13, 0x88, 0x00, 0x50} // src 5000, dst 80
|
||||||
|
|
||||||
|
for _, proto := range []uint8{iputil.IPProtocolUDPLite, iputil.IPProtocolDCCP, iputil.IPProtocolSCTP} {
|
||||||
|
h := ipv4.Header{
|
||||||
|
Version: 4,
|
||||||
|
Len: ipv4.HeaderLen,
|
||||||
|
Protocol: int(proto),
|
||||||
|
Src: net.IPv4(10, 0, 0, 1),
|
||||||
|
Dst: net.IPv4(10, 0, 0, 2),
|
||||||
|
}
|
||||||
|
v4, err := h.Marshal()
|
||||||
|
require.NoError(t, err)
|
||||||
|
v4 = append(v4, ports...)
|
||||||
|
|
||||||
|
v6 := make([]byte, 40, 44)
|
||||||
|
v6[0] = 0x60
|
||||||
|
v6[6] = proto
|
||||||
|
v6[7] = 64
|
||||||
|
v6 = append(v6, ports...)
|
||||||
|
|
||||||
|
for _, b := range [][]byte{v4, v6} {
|
||||||
|
require.NoError(t, newPacket(b, true, p))
|
||||||
|
assert.Equal(t, proto, p.Protocol)
|
||||||
|
assert.Equal(t, uint16(5000), p.RemotePort)
|
||||||
|
assert.Equal(t, uint16(80), p.LocalPort)
|
||||||
|
|
||||||
|
require.NoError(t, newPacket(b, false, p))
|
||||||
|
assert.Equal(t, uint16(5000), p.LocalPort)
|
||||||
|
assert.Equal(t, uint16(80), p.RemotePort)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
func Test_newPacket_v6(t *testing.T) {
|
func Test_newPacket_v6(t *testing.T) {
|
||||||
p := &firewall.ParsedPacket{}
|
p := &firewall.ParsedPacket{}
|
||||||
|
|
||||||
@@ -712,46 +777,46 @@ func Test_newPacket_v6ExtHeaderPastBuffer(t *testing.T) {
|
|||||||
|
|
||||||
// Test_newPacket_v6ExtHeaderConfusion is a regression test for parseV6 walking any unrecognized
|
// Test_newPacket_v6ExtHeaderConfusion is a regression test for parseV6 walking any unrecognized
|
||||||
// Next Header as if it were an ipv6 extension header. A real upper layer protocol Nebula doesn't
|
// Next Header as if it were an ipv6 extension header. A real upper layer protocol Nebula doesn't
|
||||||
// dissect (SCTP here) is not walkable, so applying the (len+1)*8 formula marched into the SCTP
|
// dissect (GRE here) is not walkable, so applying the (len+1)*8 formula marched into the GRE
|
||||||
// payload and landed on a byte that looked like UDP, forging a protocol/port pair the firewall
|
// payload and landed on a byte that looked like UDP, forging a protocol/port pair the firewall
|
||||||
// would trust while the host delivered the real SCTP datagram. The fix fails closed: the packet
|
// would trust while the host delivered the real GRE packet. The fix fails closed: the packet
|
||||||
// is classified as its true protocol with no ports, so it only matches an `any` rule.
|
// is classified as its true protocol with no ports, so it only matches an `any` rule.
|
||||||
func Test_newPacket_v6ExtHeaderConfusion(t *testing.T) {
|
func Test_newPacket_v6ExtHeaderConfusion(t *testing.T) {
|
||||||
p := &firewall.ParsedPacket{}
|
p := &firewall.ParsedPacket{}
|
||||||
|
|
||||||
pkt := make([]byte, 52)
|
pkt := make([]byte, 52)
|
||||||
pkt[0] = 0x60 // version 6
|
pkt[0] = 0x60 // version 6
|
||||||
pkt[6] = byte(layers.IPProtocolSCTP) // NextHeader = SCTP, a real protocol, not an extension header
|
pkt[6] = byte(layers.IPProtocolGRE) // NextHeader = GRE, a real protocol, not an extension header
|
||||||
pkt[7] = 64 // hop limit
|
pkt[7] = 64 // hop limit
|
||||||
|
|
||||||
// Real SCTP header at offset 40. Pre-fix parseV6 walked SCTP as an extension header: byte 41 (0x00, the
|
// Real GRE header at offset 40. Pre-fix parseV6 walked GRE as an extension header: byte 41 (0x00, the
|
||||||
// low byte of the src port below) was read as the header length, giving next=(0+1)*8=8, which landed the
|
// low byte of the flags/version word below) was read as the header length, giving next=(0+1)*8=8, which
|
||||||
// walk on byte 40 (0x11), misread as NextHeader=UDP, then bytes 48-51 as ports.
|
// landed the walk on byte 40 (0x11), misread as NextHeader=UDP, then bytes 48-51 as ports.
|
||||||
binary.BigEndian.PutUint16(pkt[40:42], 0x1100) // SCTP src port; byte 40=0x11, byte 41=0x00
|
binary.BigEndian.PutUint16(pkt[40:42], 0x1100) // GRE flags/version; byte 40=0x11, byte 41=0x00
|
||||||
binary.BigEndian.PutUint16(pkt[42:44], 445) // SCTP dst port, never read by parseV6
|
binary.BigEndian.PutUint16(pkt[42:44], 0x86dd) // GRE protocol type, never read by parseV6
|
||||||
binary.BigEndian.PutUint16(pkt[48:50], 53) // SCTP checksum bytes, pre-fix forged RemotePort
|
binary.BigEndian.PutUint16(pkt[48:50], 53) // GRE payload, pre-fix forged RemotePort
|
||||||
binary.BigEndian.PutUint16(pkt[50:52], 53) // pre-fix forged LocalPort
|
binary.BigEndian.PutUint16(pkt[50:52], 53) // pre-fix forged LocalPort
|
||||||
|
|
||||||
require.NoError(t, newPacket(pkt, true, p))
|
require.NoError(t, newPacket(pkt, true, p))
|
||||||
assert.Equal(t, uint8(layers.IPProtocolSCTP), p.Protocol, "must classify as the true protocol, not the forged UDP")
|
assert.Equal(t, uint8(layers.IPProtocolGRE), p.Protocol, "must classify as the true protocol, not the forged UDP")
|
||||||
assert.Equal(t, uint16(0), p.RemotePort)
|
assert.Equal(t, uint16(0), p.RemotePort)
|
||||||
assert.Equal(t, uint16(0), p.LocalPort)
|
assert.Equal(t, uint16(0), p.LocalPort)
|
||||||
assert.False(t, p.Fragment)
|
assert.False(t, p.Fragment)
|
||||||
|
|
||||||
// Same confusion, but the unknown protocol sits after a real extension header. The HopByHop is walked
|
// Same confusion, but the unknown protocol sits after a real extension header. The HopByHop is walked
|
||||||
// correctly, then SCTP must still fail closed instead of being walked into its own payload. Protocol is
|
// correctly, then GRE must still fail closed instead of being walked into its own payload. Protocol is
|
||||||
// the only assertion that discriminates the fix here, a regression that walked SCTP would misclassify it.
|
// the only assertion that discriminates the fix here, a regression that walked GRE would misclassify it.
|
||||||
chained := make([]byte, 60)
|
chained := make([]byte, 60)
|
||||||
chained[0] = 0x60 // version 6
|
chained[0] = 0x60 // version 6
|
||||||
chained[6] = byte(layers.IPProtocolIPv6HopByHop) // NextHeader = HopByHop extension
|
chained[6] = byte(layers.IPProtocolIPv6HopByHop) // NextHeader = HopByHop extension
|
||||||
chained[7] = 64 // hop limit
|
chained[7] = 64 // hop limit
|
||||||
chained[40] = byte(layers.IPProtocolSCTP) // HopByHop NextHeader = SCTP
|
chained[40] = byte(layers.IPProtocolGRE) // HopByHop NextHeader = GRE
|
||||||
chained[41] = 0 // HopByHop length 0 -> 8 bytes, SCTP begins at offset 48
|
chained[41] = 0 // HopByHop length 0 -> 8 bytes, GRE begins at offset 48
|
||||||
binary.BigEndian.PutUint16(chained[48:50], 0x1100) // SCTP src port, pre-fix forged NextHeader/length bait
|
binary.BigEndian.PutUint16(chained[48:50], 0x1100) // GRE flags/version, pre-fix forged NextHeader/length bait
|
||||||
binary.BigEndian.PutUint16(chained[50:52], 445) // SCTP dst port, never read by parseV6
|
binary.BigEndian.PutUint16(chained[50:52], 0x86dd) // GRE protocol type, never read by parseV6
|
||||||
|
|
||||||
require.NoError(t, newPacket(chained, true, p))
|
require.NoError(t, newPacket(chained, true, p))
|
||||||
assert.Equal(t, uint8(layers.IPProtocolSCTP), p.Protocol, "must fail closed on the unknown protocol after the extension header")
|
assert.Equal(t, uint8(layers.IPProtocolGRE), p.Protocol, "must fail closed on the unknown protocol after the extension header")
|
||||||
assert.Equal(t, uint16(0), p.RemotePort)
|
assert.Equal(t, uint16(0), p.RemotePort)
|
||||||
assert.Equal(t, uint16(0), p.LocalPort)
|
assert.Equal(t, uint16(0), p.LocalPort)
|
||||||
assert.False(t, p.Fragment)
|
assert.False(t, p.Fragment)
|
||||||
|
|||||||
@@ -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
|
|
||||||
+6
-103
@@ -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
|
||||||
|
|
||||||
@@ -176,14 +141,12 @@ 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()
|
|
||||||
if t == nil {
|
|
||||||
for i, b := range bufs {
|
for i, b := range bufs {
|
||||||
if err := u.writeTo(b, addrs[i]); err == nil {
|
if err := u.WriteTo(b, addrs[i]); err == nil {
|
||||||
written++
|
written++
|
||||||
} else {
|
} else {
|
||||||
u.l.Debug("failed to write packet in batch", "udpAddr", addrs[i], "error", err)
|
u.l.Debug("failed to write packet in batch", "udpAddr", addrs[i], "error", err)
|
||||||
@@ -191,36 +154,6 @@ func (u *StdConn) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error)
|
|||||||
}
|
}
|
||||||
return written, nil
|
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
|
|
||||||
}
|
|
||||||
|
|
||||||
func (u *StdConn) LocalAddr() (netip.AddrPort, error) {
|
func (u *StdConn) LocalAddr() (netip.AddrPort, error) {
|
||||||
a := u.UDPConn.LocalAddr()
|
a := u.UDPConn.LocalAddr()
|
||||||
@@ -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
|
|
||||||
}
|
|
||||||
|
|
||||||
// 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 err
|
||||||
}
|
}
|
||||||
return serr
|
|
||||||
}
|
|
||||||
Reference in new issue
Block a user