mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-16 22:26:57 +01:00
Compare commits
23
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
04e80f0dcf | ||
|
|
ed8ae57fee | ||
|
|
e99e48cca7 | ||
|
|
027c728702 | ||
|
|
1cfed59214 | ||
|
|
c4b9df20ac | ||
|
|
92bad7460b | ||
|
|
cac7586c0b | ||
|
|
9aab46c1ad | ||
|
|
f3b76703ae | ||
|
|
fc0dbfec4c | ||
|
|
ca69a0613b | ||
|
|
84a26846f4 | ||
|
|
317388e37d | ||
|
|
06fd191367 | ||
|
|
3f392883ca | ||
|
|
30cf2bbe6c | ||
|
|
11b04517f3 | ||
|
|
610ba57105 | ||
|
|
9e96894bd7 | ||
|
|
14f80450fb | ||
|
|
641d1fb703 | ||
|
|
11a4298c36 |
No files matched your search
@@ -7,6 +7,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
### Changed
|
||||
|
||||
- Firewall rules are held as a flat list with a bitset of rule ids per port, instead of a tree of maps copied
|
||||
into every port of a range. A rule like `port: 1024-65535` now costs kilobytes rather than tens of megabytes,
|
||||
and matching is faster on every path.
|
||||
- A firewall rule's `proto` can be `udplite`, `dccp`, `sctp`, `icmpv6`, or any IP protocol number. A rule with
|
||||
a port or port range on a protocol that has no ports, such as `proto: 47`, is rejected rather than silently
|
||||
never matching. `port: any` and `port: fragment` apply to every protocol.
|
||||
- An ICMP non-first fragment is matched against `port: fragment` rules like a fragment of any other protocol.
|
||||
It was only matched against `port: any` rules before.
|
||||
|
||||
### Fixed
|
||||
|
||||
- A firewall rule with `group: []`, `groups:` with no value, or a `groups` entry that isn't a string, such as
|
||||
`groups: [1, 2]`, no longer crashes Nebula on startup or reload. An empty `group` array is rejected, a null
|
||||
`groups` means no groups, and non-string entries are read as strings.
|
||||
|
||||
## [1.11.1] - 2026-08-21
|
||||
|
||||
See the [v1.11.1](https://github.com/slackhq/nebula/milestone/30?closed=1) milestone for a complete list of changes.
|
||||
|
||||
+6
-1
@@ -449,7 +449,9 @@ firewall:
|
||||
#default_local_cidr_any: false
|
||||
|
||||
conntrack:
|
||||
# tcp_timeout also applies to sctp and dccp
|
||||
tcp_timeout: 12m
|
||||
# udp_timeout also applies to udplite
|
||||
udp_timeout: 3m
|
||||
default_timeout: 10m
|
||||
|
||||
@@ -457,8 +459,11 @@ firewall:
|
||||
# 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)
|
||||
# - 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`
|
||||
# `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`
|
||||
# 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
|
||||
|
||||
+38
-757
@@ -2,17 +2,10 @@ package nebula
|
||||
|
||||
import (
|
||||
"context"
|
||||
"crypto/sha256"
|
||||
"encoding/hex"
|
||||
"errors"
|
||||
"fmt"
|
||||
"hash/fnv"
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"reflect"
|
||||
"slices"
|
||||
"strconv"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
@@ -24,10 +17,6 @@ import (
|
||||
"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 {
|
||||
Expires time.Time // Time when this conntrack entry will expire
|
||||
|
||||
@@ -42,8 +31,7 @@ type conn struct {
|
||||
type Firewall struct {
|
||||
Conntrack *FirewallConntrack
|
||||
|
||||
InRules *FirewallTable
|
||||
OutRules *FirewallTable
|
||||
rules firewall.Rules
|
||||
|
||||
InboundSendReject bool
|
||||
OutboundSendReject bool
|
||||
@@ -63,12 +51,10 @@ type Firewall struct {
|
||||
// unsafeNetworks is the list of unsafe networks issued to us in the certificate
|
||||
unsafeNetworks []netip.Prefix
|
||||
|
||||
rules string
|
||||
rulesVersion uint16
|
||||
|
||||
defaultLocalCIDRAny bool
|
||||
incomingMetrics firewallMetrics
|
||||
outgoingMetrics firewallMetrics
|
||||
incomingMetrics firewallMetrics
|
||||
outgoingMetrics firewallMetrics
|
||||
|
||||
l *slog.Logger
|
||||
}
|
||||
@@ -86,52 +72,6 @@ type FirewallConntrack struct {
|
||||
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.
|
||||
// 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 {
|
||||
@@ -170,8 +110,8 @@ func NewFirewall(l *slog.Logger, tcpTimeout, UDPTimeout, defaultTimeout time.Dur
|
||||
Conns: make(map[firewall.Packet]*conn),
|
||||
TimerWheel: NewTimerWheel[firewall.Packet](tmin, tmax),
|
||||
},
|
||||
InRules: newFirewallTable(),
|
||||
OutRules: newFirewallTable(),
|
||||
// Nothing is allowed until there are rules
|
||||
rules: firewall.NewRulesBuilder(l).Build(assignedNetworks, unsafeNetworks),
|
||||
TCPTimeout: tcpTimeout,
|
||||
UDPTimeout: UDPTimeout,
|
||||
DefaultTimeout: defaultTimeout,
|
||||
@@ -212,8 +152,6 @@ func NewFirewallFromConfig(l *slog.Logger, cs *CertState, c *config.C) (*Firewal
|
||||
//TODO: max_connections
|
||||
)
|
||||
|
||||
fw.defaultLocalCIDRAny = c.GetBool("firewall.default_local_cidr_any", false)
|
||||
|
||||
inboundAction := c.GetString("firewall.inbound_action", "drop")
|
||||
switch inboundAction {
|
||||
case "reject":
|
||||
@@ -236,80 +174,23 @@ func NewFirewallFromConfig(l *slog.Logger, cs *CertState, c *config.C) (*Firewal
|
||||
fw.OutboundSendReject = false
|
||||
}
|
||||
|
||||
err := AddFirewallRulesFromConfig(l, false, c, fw)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
err = AddFirewallRulesFromConfig(l, true, c, fw)
|
||||
rules, err := firewall.RulesFromConfig(l, c, fw.assignedNetworks, fw.unsafeNetworks)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
fw.rules = rules
|
||||
|
||||
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
|
||||
func (f *Firewall) GetRuleHash() string {
|
||||
sum := sha256.Sum256([]byte(f.rules))
|
||||
return hex.EncodeToString(sum[:])
|
||||
return f.rules.Hash
|
||||
}
|
||||
|
||||
// GetRuleHashFNV returns a uint32 FNV-1 hash representation the rules, for use as a metric value
|
||||
func (f *Firewall) GetRuleHashFNV() uint32 {
|
||||
h := fnv.New32a()
|
||||
h.Write([]byte(f.rules))
|
||||
return h.Sum32()
|
||||
return f.rules.HashFNV
|
||||
}
|
||||
|
||||
// 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)
|
||||
}
|
||||
|
||||
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 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")
|
||||
@@ -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
|
||||
if f.inConns(fp, h, caPool, localCache) {
|
||||
if f.inConns(&fp, h, caPool, localCache) {
|
||||
return nil
|
||||
}
|
||||
|
||||
table := f.OutRules
|
||||
if incoming {
|
||||
table = f.InRules
|
||||
}
|
||||
|
||||
// We now know which firewall table to check against
|
||||
if !table.match(fp, incoming, h.ConnectionState.peerCert, caPool) {
|
||||
if !f.rules.Match(&fp, incoming, h.ConnectionState.peerCert, caPool) {
|
||||
f.metrics(incoming).droppedNoRule.Inc(1)
|
||||
return ErrNoMatchingRule
|
||||
}
|
||||
|
||||
// We always want to conntrack since it is a faster operation
|
||||
f.addConn(fp, incoming)
|
||||
f.addConn(&fp, incoming)
|
||||
|
||||
return nil
|
||||
}
|
||||
@@ -503,9 +280,9 @@ func (f *Firewall) EmitStats() {
|
||||
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 _, ok := localCache[fp]; ok {
|
||||
if _, ok := localCache[*fp]; ok {
|
||||
return true
|
||||
}
|
||||
}
|
||||
@@ -518,7 +295,7 @@ func (f *Firewall) inConns(fp firewall.Packet, h *HostInfo, caPool *cert.CAPool,
|
||||
f.evict(ep)
|
||||
}
|
||||
|
||||
c, ok := conntrack.Conns[fp]
|
||||
c, ok := conntrack.Conns[*fp]
|
||||
|
||||
if !ok {
|
||||
conntrack.Unlock()
|
||||
@@ -528,29 +305,23 @@ func (f *Firewall) inConns(fp firewall.Packet, h *HostInfo, caPool *cert.CAPool,
|
||||
if c.rulesVersion != f.rulesVersion {
|
||||
// This conntrack entry was for an older rule set, validate
|
||||
// it still passes with the current rule set
|
||||
table := f.OutRules
|
||||
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.rules.Match(fp, c.incoming, h.ConnectionState.peerCert, caPool) {
|
||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
h.logger(f.l).Debug("dropping old conntrack entry, does not match new ruleset",
|
||||
"fwPacket", fp,
|
||||
"fwPacket", *fp,
|
||||
"incoming", c.incoming,
|
||||
"rulesVersion", f.rulesVersion,
|
||||
"oldRulesVersion", c.rulesVersion,
|
||||
)
|
||||
}
|
||||
delete(conntrack.Conns, fp)
|
||||
delete(conntrack.Conns, *fp)
|
||||
conntrack.Unlock()
|
||||
return false
|
||||
}
|
||||
|
||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
h.logger(f.l).Debug("keeping old conntrack entry, does match new ruleset",
|
||||
"fwPacket", fp,
|
||||
"fwPacket", *fp,
|
||||
"incoming", c.incoming,
|
||||
"rulesVersion", f.rulesVersion,
|
||||
"oldRulesVersion", c.rulesVersion,
|
||||
@@ -560,42 +331,39 @@ func (f *Firewall) inConns(fp firewall.Packet, h *HostInfo, caPool *cert.CAPool,
|
||||
c.rulesVersion = f.rulesVersion
|
||||
}
|
||||
|
||||
switch 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)
|
||||
}
|
||||
c.Expires = time.Now().Add(f.conntrackTimeout(fp.Protocol))
|
||||
|
||||
conntrack.Unlock()
|
||||
|
||||
if localCache != nil {
|
||||
localCache[fp] = struct{}{}
|
||||
localCache[*fp] = struct{}{}
|
||||
}
|
||||
|
||||
return true
|
||||
}
|
||||
|
||||
func (f *Firewall) addConn(fp firewall.Packet, incoming bool) {
|
||||
var timeout time.Duration
|
||||
c := &conn{}
|
||||
|
||||
switch fp.Protocol {
|
||||
case iputil.IPProtocolTCP:
|
||||
timeout = f.TCPTimeout
|
||||
case iputil.IPProtocolUDP:
|
||||
timeout = f.UDPTimeout
|
||||
// conntrackTimeout returns how long a conntrack entry for proto lives without traffic.
|
||||
// Connection oriented protocols share the tcp timeout, datagram protocols share the udp timeout.
|
||||
func (f *Firewall) conntrackTimeout(proto uint8) time.Duration {
|
||||
switch proto {
|
||||
case iputil.IPProtocolTCP, iputil.IPProtocolSCTP, iputil.IPProtocolDCCP:
|
||||
return f.TCPTimeout
|
||||
case iputil.IPProtocolUDP, iputil.IPProtocolUDPLite:
|
||||
return f.UDPTimeout
|
||||
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.Lock()
|
||||
if _, ok := conntrack.Conns[fp]; !ok {
|
||||
if _, ok := conntrack.Conns[*fp]; !ok {
|
||||
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
|
||||
@@ -603,7 +371,7 @@ func (f *Firewall) addConn(fp firewall.Packet, incoming bool) {
|
||||
c.incoming = incoming
|
||||
c.rulesVersion = f.rulesVersion
|
||||
c.Expires = time.Now().Add(timeout)
|
||||
conntrack.Conns[fp] = c
|
||||
conntrack.Conns[*fp] = c
|
||||
conntrack.Unlock()
|
||||
}
|
||||
|
||||
@@ -629,490 +397,3 @@ func (f *Firewall) evict(p firewall.Packet) {
|
||||
// This conn is done
|
||||
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 +1,310 @@
|
||||
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
|
||||
}
|
||||
|
||||
proto, ok := protoByName(r.Proto)
|
||||
if !ok {
|
||||
// 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 {
|
||||
// RulesBuilder.AddRule coerces ICMP ports to `any` as well. This copy stays so that an ICMP rule's
|
||||
// port is warned about rather than parsed, whatever it holds.
|
||||
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")
|
||||
}
|
||||
if len(v) == 0 {
|
||||
return r, errors.New("group should contain a single value, an empty array 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)
|
||||
|
||||
// A null value, `groups:` with nothing after it, is the same as no groups
|
||||
if rg, ok := m["groups"]; ok && rg != nil {
|
||||
switch reflect.TypeOf(rg).Kind() {
|
||||
case reflect.Slice:
|
||||
// Every entry is read as a string, as the other fields are, so `groups: [1, 2]` is the groups "1" and "2"
|
||||
v := reflect.ValueOf(rg)
|
||||
r.Groups = make([]string, v.Len())
|
||||
for i := 0; i < v.Len(); i++ {
|
||||
r.Groups[i] = fmt.Sprintf("%v", v.Index(i).Interface())
|
||||
}
|
||||
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 +1,516 @@
|
||||
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 name and by number, still ignore ports
|
||||
for _, tc := range []struct {
|
||||
given any
|
||||
want uint8
|
||||
}{
|
||||
{"icmp", iputil.IPProtocolICMP},
|
||||
{"icmpv6", iputil.IPProtocolICMPv6},
|
||||
{iputil.IPProtocolICMP, iputil.IPProtocolICMP},
|
||||
{iputil.IPProtocolICMPv6, iputil.IPProtocolICMPv6},
|
||||
} {
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"port": "1", "proto": tc.given, "host": "a"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, false, conf, mf), tc.given)
|
||||
assert.Equal(t, addRuleCall{incoming: false, proto: tc.want, startPort: PortAny, endPort: PortAny, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall, tc.given)
|
||||
}
|
||||
|
||||
// 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 group and groups values that used to crash: an empty group array is rejected, groups entries that
|
||||
// aren't strings are read as strings, and a null groups is no groups
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "group": []any{}}}}
|
||||
require.EqualError(t, addRulesFromConfig(l, true, conf, mf), "firewall.inbound rule #0; group should contain a single value, an empty array was provided")
|
||||
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "groups": []any{1, 2}}}}
|
||||
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, []string{"1", "2"}, mf.lastCall.groups)
|
||||
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "groups": nil, "host": "a"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||
assert.Empty(t, mf.lastCall.groups)
|
||||
assert.Equal(t, "a", mf.lastCall.host)
|
||||
|
||||
// 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")
|
||||
|
||||
// ruleOnPort returns the rule on proto whose port clause is exactly port, chosen from the rules that a packet
|
||||
// on port is checked against.
|
||||
ruleOnPort := func(t *testing.T, table *Table, proto uint8, port int32) *rule {
|
||||
t.Helper()
|
||||
for _, r := range table.rulesAt(proto, port) {
|
||||
if r.startPort == port {
|
||||
return r
|
||||
}
|
||||
}
|
||||
require.Failf(t, "no rule found", "proto %d port %d", proto, port)
|
||||
return 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, as indexed by a protocol with rules of its own and as shared by one without.
|
||||
for _, proto := range []uint8{iputil.IPProtocolTCP, 47} {
|
||||
r := ruleOnPort(t, rules.In, proto, PortAny)
|
||||
assert.True(t, r.matchLocal(vpnAddr), "proto %d", proto)
|
||||
assert.Equal(t, tc.wantUnsafe, r.matchLocal(unsafeAddr), "proto %d", proto)
|
||||
}
|
||||
|
||||
r := ruleOnPort(t, rules.In, iputil.IPProtocolTCP, 22)
|
||||
assert.True(t, r.matchLocal(vpnAddr))
|
||||
assert.Equal(t, tc.wantUnsafe, r.matchLocal(unsafeAddr))
|
||||
|
||||
r = ruleOnPort(t, rules.In, iputil.IPProtocolTCP, 80)
|
||||
assert.False(t, r.matchLocal(vpnAddr))
|
||||
assert.True(t, r.matchLocal(unsafeAddr))
|
||||
|
||||
r = ruleOnPort(t, rules.In, iputil.IPProtocolTCP, 443)
|
||||
assert.True(t, r.matchLocal(vpnAddr))
|
||||
assert.True(t, r.matchLocal(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
|
||||
}
|
||||
+40
-14
@@ -40,29 +40,55 @@ func (fp *Packet) Copy() *Packet {
|
||||
}
|
||||
|
||||
func (fp Packet) MarshalJSON() ([]byte, error) {
|
||||
var proto string
|
||||
switch fp.Protocol {
|
||||
case iputil.IPProtocolTCP:
|
||||
proto = "tcp"
|
||||
case iputil.IPProtocolICMP:
|
||||
proto = "icmp"
|
||||
case iputil.IPProtocolICMPv6:
|
||||
proto = "icmpv6"
|
||||
case iputil.IPProtocolUDP:
|
||||
proto = "udp"
|
||||
default:
|
||||
proto = fmt.Sprintf("unknown %v", fp.Protocol)
|
||||
}
|
||||
return json.Marshal(m{
|
||||
"LocalAddr": fp.LocalAddr.String(),
|
||||
"RemoteAddr": fp.RemoteAddr.String(),
|
||||
"LocalPort": fp.LocalPort,
|
||||
"RemotePort": fp.RemotePort,
|
||||
"Protocol": proto,
|
||||
"Protocol": protoName(fp.Protocol),
|
||||
"Fragment": fp.Fragment,
|
||||
})
|
||||
}
|
||||
|
||||
// protoNames are the protocol names that rules accept and packets report, and their numbers. Any other protocol
|
||||
// is given by number.
|
||||
var protoNames = []struct {
|
||||
name string
|
||||
proto uint8
|
||||
}{
|
||||
{"any", ProtoAny},
|
||||
{"tcp", iputil.IPProtocolTCP},
|
||||
{"udp", iputil.IPProtocolUDP},
|
||||
{"udplite", iputil.IPProtocolUDPLite},
|
||||
{"dccp", iputil.IPProtocolDCCP},
|
||||
{"sctp", iputil.IPProtocolSCTP},
|
||||
{"icmp", iputil.IPProtocolICMP},
|
||||
{"icmpv6", iputil.IPProtocolICMPv6},
|
||||
}
|
||||
|
||||
// protoByName returns the number of a protocol named in protoNames.
|
||||
func protoByName(name string) (uint8, bool) {
|
||||
for _, p := range protoNames {
|
||||
if p.name == name {
|
||||
return p.proto, true
|
||||
}
|
||||
}
|
||||
return 0, false
|
||||
}
|
||||
|
||||
// protoName returns the name in protoNames of a packet's protocol, or "unknown" and its number. `any` is only
|
||||
// a rule's protocol, so a packet's protocol 0 is unknown.
|
||||
func protoName(proto uint8) string {
|
||||
if proto != ProtoAny {
|
||||
for _, p := range protoNames {
|
||||
if p.proto == proto {
|
||||
return p.name
|
||||
}
|
||||
}
|
||||
}
|
||||
return fmt.Sprintf("unknown %v", proto)
|
||||
}
|
||||
|
||||
// ParsedPacket is a Packet plus the parse byproducts the RX path reuses
|
||||
type ParsedPacket struct {
|
||||
Packet
|
||||
|
||||
@@ -0,0 +1,258 @@
|
||||
package firewall
|
||||
|
||||
import (
|
||||
"crypto/sha256"
|
||||
"encoding/hex"
|
||||
"fmt"
|
||||
"hash/fnv"
|
||||
"log/slog"
|
||||
"math"
|
||||
"net/netip"
|
||||
"slices"
|
||||
"strings"
|
||||
|
||||
"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 and out are each direction's rules in the order they were added
|
||||
in, out []rule
|
||||
|
||||
// defaultLocalCIDRAny makes rules without a local cidr allow any local address, even with unsafe networks
|
||||
defaultLocalCIDRAny bool
|
||||
|
||||
// ruleText describes every rule as it is added, one line each. Build hashes it; see Rules.
|
||||
ruleText strings.Builder
|
||||
|
||||
l *slog.Logger
|
||||
}
|
||||
|
||||
func NewRulesBuilder(l *slog.Logger) *RulesBuilder {
|
||||
return &RulesBuilder{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 {
|
||||
// ICMPv6 rules are ICMP rules, and a packet of either protocol is checked against both
|
||||
if proto == iputil.IPProtocolICMPv6 {
|
||||
proto = iputil.IPProtocolICMP
|
||||
}
|
||||
|
||||
if proto == iputil.IPProtocolICMP {
|
||||
//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(proto, startPort, endPort, groups, host, cidr, localCidr, caName, caSha)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
if incoming {
|
||||
b.in = append(b.in, r)
|
||||
} else {
|
||||
b.out = append(b.out, r)
|
||||
}
|
||||
|
||||
// The rule hashes are of these lines, changing them changes every hash
|
||||
fmt.Fprintf(&b.ruleText,
|
||||
"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 []netip.Prefix
|
||||
if len(unsafeNetworks) > 0 && !b.defaultLocalCIDRAny {
|
||||
// Never nil, even when there are no vpn networks, so that the rules allow nothing rather than everything.
|
||||
defaultLocal = append([]netip.Prefix{}, vpnNetworks...)
|
||||
}
|
||||
|
||||
text := []byte(b.ruleText.String())
|
||||
sha := sha256.Sum256(text)
|
||||
h := fnv.New32a()
|
||||
h.Write(text)
|
||||
|
||||
return Rules{
|
||||
In: buildTable(b.in, defaultLocal),
|
||||
Out: buildTable(b.out, defaultLocal),
|
||||
Hash: hex.EncodeToString(sha[:]),
|
||||
HashFNV: h.Sum32(),
|
||||
}
|
||||
}
|
||||
|
||||
func parseRule(proto uint8, 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")
|
||||
}
|
||||
if startPort < PortFragment || endPort > math.MaxUint16 {
|
||||
return rule{}, fmt.Errorf("port range %d-%d is outside of %d-%d", startPort, endPort, PortFragment, math.MaxUint16)
|
||||
}
|
||||
// A range that includes port 0 is port `any`.
|
||||
if startPort <= PortAny && PortAny <= endPort {
|
||||
startPort, endPort = PortAny, PortAny
|
||||
}
|
||||
// A port rule on a protocol without ports could never match. ICMP rules were coerced to `any` by AddRule,
|
||||
// and a proto `any` rule with a port applies to the protocols that have them.
|
||||
if startPort > PortAny && proto != ProtoAny && !iputil.HasPorts(proto) {
|
||||
return rule{}, fmt.Errorf("protocol %d has no ports, port must be any or fragment", proto)
|
||||
}
|
||||
|
||||
r := rule{
|
||||
proto: proto,
|
||||
startPort: startPort,
|
||||
endPort: endPort,
|
||||
groups: groups,
|
||||
host: host,
|
||||
caName: caName,
|
||||
caSha: caSha,
|
||||
}
|
||||
|
||||
var anyCIDR bool
|
||||
var err error
|
||||
r.cidr, anyCIDR, err = parseCIDR(cidr)
|
||||
if err != nil {
|
||||
return rule{}, fmt.Errorf("cidr did not parse; %w", err)
|
||||
}
|
||||
|
||||
// A rule with no group, host, or cidr allows any host, as does a rule with `any` for one of them.
|
||||
r.remoteAny = anyCIDR || host == "any" || slices.Contains(groups, "any") ||
|
||||
(len(groups) == 0 && host == "" && !r.cidr.IsValid())
|
||||
|
||||
var localCIDR netip.Prefix
|
||||
localCIDR, r.localAny, err = parseCIDR(localCidr)
|
||||
if err != nil {
|
||||
return rule{}, fmt.Errorf("local_cidr did not parse; %w", err)
|
||||
}
|
||||
if localCIDR.IsValid() {
|
||||
r.local = []netip.Prefix{localCIDR}
|
||||
}
|
||||
|
||||
return r, nil
|
||||
}
|
||||
|
||||
// buildTable turns one direction's rules into a Table. Rules without a local cidr allow defaultLocal,
|
||||
// or any local address when defaultLocal is nil.
|
||||
func buildTable(rules []rule, defaultLocal []netip.Prefix) *Table {
|
||||
t := &Table{rules: make([]rule, len(rules))}
|
||||
var hasOwn [256]bool
|
||||
for id, r := range rules {
|
||||
t.rules[id] = r.withDefaultLocal(defaultLocal)
|
||||
if r.proto != ProtoAny {
|
||||
hasOwn[r.proto] = true
|
||||
}
|
||||
}
|
||||
|
||||
// A protocol with rules of its own gets an index of those rules plus the proto `any` rules, so a packet
|
||||
// checks a single index. The other protocols share an index of the proto `any` rules, one for protocols with
|
||||
// ports and one for protocols without.
|
||||
anyPorts := newProtoIndex(true, t.rules, ProtoAny)
|
||||
anyNoPorts := newProtoIndex(false, t.rules, ProtoAny)
|
||||
for proto := range t.protos {
|
||||
switch {
|
||||
case hasOwn[proto]:
|
||||
t.protos[proto] = newProtoIndex(iputil.HasPorts(uint8(proto)), t.rules, uint8(proto))
|
||||
case iputil.HasPorts(uint8(proto)):
|
||||
t.protos[proto] = anyPorts
|
||||
default:
|
||||
t.protos[proto] = anyNoPorts
|
||||
}
|
||||
}
|
||||
|
||||
// ICMPv6 rules are ICMP rules, see AddRule, so ICMPv6 packets are checked against the ICMP index
|
||||
t.protos[iputil.IPProtocolICMPv6] = t.protos[iputil.IPProtocolICMP]
|
||||
|
||||
return t
|
||||
}
|
||||
|
||||
// newProtoIndex builds an index of the proto `any` rules and proto's own rules, for a protocol with or without
|
||||
// ports, or returns nil when there are none. With ProtoAny, it indexes only the proto `any` rules.
|
||||
func newProtoIndex(hasPorts bool, rules []rule, proto uint8) *protoIndex {
|
||||
var pi *protoIndex
|
||||
for id := range rules {
|
||||
r := &rules[id]
|
||||
if r.proto != ProtoAny && r.proto != proto {
|
||||
continue
|
||||
}
|
||||
|
||||
if pi == nil {
|
||||
pi = &protoIndex{hasPorts: hasPorts, fragment: newRuleSet(len(rules))}
|
||||
if hasPorts {
|
||||
pi.byPort = newRuleSets(math.MaxUint16+1, len(rules))
|
||||
} else {
|
||||
pi.packet = newRuleSet(len(rules))
|
||||
}
|
||||
}
|
||||
pi.add(r, id)
|
||||
}
|
||||
return pi
|
||||
}
|
||||
|
||||
// add puts id in every set that r's port clause covers.
|
||||
func (pi *protoIndex) add(r *rule, id int) {
|
||||
switch r.startPort {
|
||||
case PortAny:
|
||||
pi.fragment.add(id)
|
||||
if pi.hasPorts {
|
||||
pi.addPorts(0, math.MaxUint16, id)
|
||||
} else {
|
||||
pi.packet.add(id)
|
||||
}
|
||||
case PortFragment:
|
||||
pi.fragment.add(id)
|
||||
default:
|
||||
// A proto `any` rule with a port is indexed for the protocols that have ports, parseRule rejects a port on
|
||||
// a protocol without them.
|
||||
if pi.hasPorts {
|
||||
pi.addPorts(int(r.startPort), int(r.endPort), id)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// addPorts puts id in the set of every port from lo through hi.
|
||||
func (pi *protoIndex) addPorts(lo, hi, id int) {
|
||||
for port := lo; port <= hi; port++ {
|
||||
pi.byPort.at(port).add(id)
|
||||
}
|
||||
}
|
||||
|
||||
// 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
|
||||
}
|
||||
|
||||
// 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 []netip.Prefix) rule {
|
||||
if !r.localAny && r.local == nil {
|
||||
r.localAny = defaultLocal == nil
|
||||
r.local = defaultLocal
|
||||
}
|
||||
return r
|
||||
}
|
||||
@@ -0,0 +1,367 @@
|
||||
package firewall
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"math"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/iputil"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// rulesAt returns the rules that a packet on proto with the given port is checked against, in id order.
|
||||
// port may also be PortAny or PortFragment.
|
||||
func (t *Table) rulesAt(proto uint8, port int32) []*rule {
|
||||
pi := t.protos[proto]
|
||||
if pi == nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
p := &Packet{Protocol: proto, Fragment: port == PortFragment}
|
||||
if port > 0 {
|
||||
p.LocalPort = uint16(port)
|
||||
}
|
||||
|
||||
var rules []*rule
|
||||
for id := range pi.whichMatch(p, true).all() {
|
||||
rules = append(rules, &t.rules[id])
|
||||
}
|
||||
return rules
|
||||
}
|
||||
|
||||
// oneRuleAt returns the single rule that rulesAt finds, and fails the test when there is not exactly one.
|
||||
func oneRuleAt(t *testing.T, table *Table, proto uint8, key int32) *rule {
|
||||
t.Helper()
|
||||
rules := table.rulesAt(proto, key)
|
||||
require.Len(t, rules, 1)
|
||||
return rules[0]
|
||||
}
|
||||
|
||||
func TestRulesBuilder_AddRule(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
|
||||
ti := netip.MustParsePrefix("1.2.3.4/32")
|
||||
ti6 := netip.MustParsePrefix("fd12::34/128")
|
||||
|
||||
rb := NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 1, 1, []string{}, "", "", "", "", ""))
|
||||
rules := rb.Build(nil, nil)
|
||||
// An empty rule is any
|
||||
r := oneRuleAt(t, rules.In, iputil.IPProtocolTCP, 1)
|
||||
assert.True(t, r.remoteAny)
|
||||
assert.Empty(t, r.groups)
|
||||
assert.Empty(t, r.host)
|
||||
// It applies only to its own port.
|
||||
assert.Empty(t, rules.In.rulesAt(iputil.IPProtocolTCP, 2))
|
||||
assert.Empty(t, rules.In.rulesAt(iputil.IPProtocolTCP, PortAny))
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolUDP, 1, 1, []string{"g1"}, "", "", "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
r = oneRuleAt(t, rules.In, iputil.IPProtocolUDP, 1)
|
||||
assert.False(t, r.remoteAny)
|
||||
assert.Equal(t, []string{"g1"}, r.groups)
|
||||
assert.Empty(t, r.host)
|
||||
|
||||
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)
|
||||
// An ICMP rule is port `any` regardless of the port given, and ICMP and ICMPv6 share one set of rules.
|
||||
for _, proto := range []uint8{iputil.IPProtocolICMP, iputil.IPProtocolICMPv6} {
|
||||
rs := rules.In.rulesAt(proto, PortAny)
|
||||
require.Len(t, rs, 2, "proto %d", proto)
|
||||
assert.False(t, rs[0].remoteAny)
|
||||
assert.Equal(t, "h1", rs[0].host)
|
||||
assert.Equal(t, "h2", rs[1].host)
|
||||
}
|
||||
assert.Same(t, rules.In.protos[iputil.IPProtocolICMP], rules.In.protos[iputil.IPProtocolICMPv6])
|
||||
|
||||
// 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.Equal(t, []string{"g1"}, oneRuleAt(t, rules.In, 47, PortAny).groups)
|
||||
assert.Nil(t, rules.In.protos[iputil.IPProtocolTCP])
|
||||
|
||||
// A proto `any` rule with a port applies to every protocol with ports, and ProtoAny itself has none.
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 1, 1, []string{}, "", ti.String(), "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.Empty(t, rules.Out.rulesAt(ProtoAny, 1))
|
||||
r = oneRuleAt(t, rules.Out, iputil.IPProtocolTCP, 1)
|
||||
assert.False(t, r.remoteAny)
|
||||
assert.Equal(t, ti, r.cidr)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 1, 1, []string{}, "", ti6.String(), "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
r = oneRuleAt(t, rules.Out, iputil.IPProtocolTCP, 1)
|
||||
assert.False(t, r.remoteAny)
|
||||
assert.Equal(t, ti6, r.cidr)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 1, 1, []string{}, "", "", ti.String(), "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
r = oneRuleAt(t, rules.Out, iputil.IPProtocolTCP, 1)
|
||||
assert.True(t, r.remoteAny)
|
||||
assert.False(t, r.localAny)
|
||||
assert.Equal(t, []netip.Prefix{ti}, r.local)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 1, 1, []string{}, "", "", ti6.String(), "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
r = oneRuleAt(t, rules.Out, iputil.IPProtocolTCP, 1)
|
||||
assert.True(t, r.remoteAny)
|
||||
assert.False(t, r.localAny)
|
||||
assert.Equal(t, []netip.Prefix{ti6}, r.local)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolUDP, 1, 1, []string{"g1"}, "", "", "", "ca-name", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.Equal(t, "ca-name", oneRuleAt(t, rules.In, iputil.IPProtocolUDP, 1).caName)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolUDP, 1, 1, []string{"g1"}, "", "", "", "", "ca-sha"))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.Equal(t, "ca-sha", oneRuleAt(t, rules.In, iputil.IPProtocolUDP, 1).caSha)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "any", "", "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.True(t, oneRuleAt(t, rules.Out, ProtoAny, 0).remoteAny)
|
||||
|
||||
// 0.0.0.0/0 allows any IPv4 address, but no IPv6 address.
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", "0.0.0.0/0", "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
r = oneRuleAt(t, rules.Out, ProtoAny, 0)
|
||||
assert.False(t, r.remoteAny)
|
||||
assert.True(t, r.matchRemote(netip.MustParseAddr("1.1.1.1"), nil))
|
||||
assert.False(t, r.matchRemote(netip.MustParseAddr("9::9"), nil))
|
||||
|
||||
// ::/0 allows any IPv6 address, but no IPv4 address.
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", "::/0", "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
r = oneRuleAt(t, rules.Out, ProtoAny, 0)
|
||||
assert.False(t, r.remoteAny)
|
||||
assert.True(t, r.matchRemote(netip.MustParseAddr("9::9"), nil))
|
||||
assert.False(t, r.matchRemote(netip.MustParseAddr("1.1.1.1"), nil))
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", "any", "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.True(t, oneRuleAt(t, rules.Out, ProtoAny, 0).remoteAny)
|
||||
|
||||
// A local cidr is likewise limited to its own address family.
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", "", "0.0.0.0/0", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
r = oneRuleAt(t, rules.Out, ProtoAny, 0)
|
||||
assert.False(t, r.localAny)
|
||||
assert.True(t, r.matchLocal(netip.MustParseAddr("1.1.1.1")))
|
||||
assert.False(t, r.matchLocal(netip.MustParseAddr("9::9")))
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", "", "::/0", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
r = oneRuleAt(t, rules.Out, ProtoAny, 0)
|
||||
assert.False(t, r.localAny)
|
||||
assert.True(t, r.matchLocal(netip.MustParseAddr("9::9")))
|
||||
assert.False(t, r.matchLocal(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, oneRuleAt(t, rules.Out, ProtoAny, 0).localAny)
|
||||
|
||||
// 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, oneRuleAt(t, rules.In, math.MaxUint8, PortAny).remoteAny)
|
||||
|
||||
// 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, PortFragment-1, 0, []string{}, "", "", "", "", ""))
|
||||
require.Error(t, rb.AddRule(true, ProtoAny, 1, math.MaxUint16+1, []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.rules, 2)
|
||||
assert.Len(t, rules.In.rulesAt(iputil.IPProtocolICMP, PortAny), 2)
|
||||
assert.Len(t, rules.In.rulesAt(iputil.IPProtocolICMPv6, PortAny), 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_protoIndex checks which packets each kind of port clause covers, and which protocols
|
||||
// share an index.
|
||||
func TestRulesBuilder_protoIndex(t *testing.T) {
|
||||
rb := NewRulesBuilder(test.NewLogger())
|
||||
require.NoError(t, rb.AddRule(true, ProtoAny, PortAny, PortAny, nil, "any", "", "", "", ""))
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 22, 22, nil, "port", "", "", "", ""))
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 1024, math.MaxUint16, nil, "range", "", "", "", ""))
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, PortFragment, PortFragment, nil, "fragment", "", "", "", ""))
|
||||
// A range that includes port 0 is port `any`.
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolUDP, 0, 100, nil, "zero", "", "", "", ""))
|
||||
// GRE has no ports, so a port rule on it is rejected rather than never applying, and `any` and `fragment` apply
|
||||
require.Error(t, rb.AddRule(true, 47, 22, 22, nil, "gre", "", "", "", ""))
|
||||
require.NoError(t, rb.AddRule(true, 47, PortFragment, PortFragment, nil, "gre", "", "", "", ""))
|
||||
rules := rb.Build(nil, nil)
|
||||
|
||||
hosts := func(proto uint8, key int32) []string {
|
||||
var hosts []string
|
||||
for _, r := range rules.In.rulesAt(proto, key) {
|
||||
hosts = append(hosts, r.host)
|
||||
}
|
||||
return hosts
|
||||
}
|
||||
|
||||
assert.Equal(t, []string{"any", "fragment"}, hosts(iputil.IPProtocolTCP, PortFragment))
|
||||
assert.Equal(t, []string{"any"}, hosts(iputil.IPProtocolTCP, PortAny))
|
||||
assert.Equal(t, []string{"any"}, hosts(iputil.IPProtocolTCP, 21))
|
||||
assert.Equal(t, []string{"any", "port"}, hosts(iputil.IPProtocolTCP, 22))
|
||||
assert.Equal(t, []string{"any"}, hosts(iputil.IPProtocolTCP, 23))
|
||||
assert.Equal(t, []string{"any"}, hosts(iputil.IPProtocolTCP, 1023))
|
||||
assert.Equal(t, []string{"any", "range"}, hosts(iputil.IPProtocolTCP, 1024))
|
||||
assert.Equal(t, []string{"any", "range"}, hosts(iputil.IPProtocolTCP, math.MaxUint16))
|
||||
|
||||
assert.Equal(t, []string{"any", "zero"}, hosts(iputil.IPProtocolUDP, PortFragment))
|
||||
assert.Equal(t, []string{"any", "zero"}, hosts(iputil.IPProtocolUDP, PortAny))
|
||||
assert.Equal(t, []string{"any", "zero"}, hosts(iputil.IPProtocolUDP, math.MaxUint16))
|
||||
|
||||
// A protocol without ports sees only the port `any` rules, and the port `fragment` rules for a fragment.
|
||||
assert.False(t, rules.In.protos[47].hasPorts)
|
||||
assert.Equal(t, []string{"any"}, hosts(47, PortAny))
|
||||
assert.Equal(t, []string{"any"}, hosts(47, 22))
|
||||
assert.Equal(t, []string{"any", "gre"}, hosts(47, PortFragment))
|
||||
assert.Equal(t, []string{"any"}, hosts(iputil.IPProtocolICMP, PortFragment))
|
||||
|
||||
// Protocols without rules of their own share an index of the proto `any` rules: one for protocols with
|
||||
// ports and one for protocols without.
|
||||
assert.True(t, rules.In.protos[iputil.IPProtocolSCTP].hasPorts)
|
||||
assert.Equal(t, []string{"any"}, hosts(iputil.IPProtocolSCTP, 5000))
|
||||
assert.Same(t, rules.In.protos[iputil.IPProtocolSCTP], rules.In.protos[iputil.IPProtocolDCCP])
|
||||
assert.NotSame(t, rules.In.protos[iputil.IPProtocolSCTP], rules.In.protos[iputil.IPProtocolTCP])
|
||||
assert.Equal(t, []string{"any"}, hosts(50, PortAny))
|
||||
assert.Same(t, rules.In.protos[ProtoAny], rules.In.protos[50])
|
||||
assert.Same(t, rules.In.protos[ProtoAny], rules.In.protos[iputil.IPProtocolICMP])
|
||||
assert.NotSame(t, rules.In.protos[ProtoAny], rules.In.protos[iputil.IPProtocolSCTP])
|
||||
assert.Nil(t, rules.Out.protos[iputil.IPProtocolTCP])
|
||||
}
|
||||
|
||||
// TestRulesBuilder_manyRules checks that rule ids beyond the first byte of a rule set are indexed correctly.
|
||||
func TestRulesBuilder_manyRules(t *testing.T) {
|
||||
rb := NewRulesBuilder(test.NewLogger())
|
||||
const n = 130
|
||||
for i := range n {
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, int32(i+1), int32(i+1), nil, fmt.Sprintf("h%d", i), "", "", "", ""))
|
||||
}
|
||||
require.NoError(t, rb.AddRule(true, ProtoAny, PortAny, PortAny, nil, "any", "", "", "", ""))
|
||||
rules := rb.Build(nil, nil)
|
||||
|
||||
assert.Equal(t, ruleSetLen(n+1), rules.In.protos[iputil.IPProtocolTCP].byPort.setLen)
|
||||
// Ids are the order the rules were added in, so the proto `any` rule comes last
|
||||
for i := range n {
|
||||
rs := rules.In.rulesAt(iputil.IPProtocolTCP, int32(i+1))
|
||||
require.Len(t, rs, 2, "port %d", i+1)
|
||||
assert.Equal(t, fmt.Sprintf("h%d", i), rs[0].host)
|
||||
assert.Equal(t, "any", rs[1].host)
|
||||
}
|
||||
assert.Len(t, rules.In.rulesAt(iputil.IPProtocolTCP, n+1), 1)
|
||||
}
|
||||
|
||||
// TestRulesBuilder_defaultLocalCIDR checks which local addresses rules allow when there are unsafe networks.
|
||||
// A rule without a local cidr allows only the vpn networks, and a rule with one allows only that cidr.
|
||||
func TestRulesBuilder_defaultLocalCIDR(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)
|
||||
|
||||
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
|
||||
caPool := cert.NewCAPool()
|
||||
require.NoError(t, caPool.AddCA(ca))
|
||||
certs := map[string]*cert.CachedCertificate{}
|
||||
for _, name := range []string{"h1", "h2", "h3"} {
|
||||
crt, _, _, _ := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, name, time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.9/16")}, nil, nil)
|
||||
c, err := caPool.VerifyCertificate(time.Now(), crt)
|
||||
require.NoError(t, err)
|
||||
certs[name] = c
|
||||
}
|
||||
|
||||
for _, tc := range []struct {
|
||||
port uint16
|
||||
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},
|
||||
// Only h3 is allowed on port 3.
|
||||
{3, "h1", vpn1, false},
|
||||
} {
|
||||
p := &Packet{Protocol: iputil.IPProtocolTCP, LocalPort: tc.port, LocalAddr: tc.addr, RemoteAddr: netip.MustParseAddr("10.1.0.9")}
|
||||
assert.Equal(t, tc.want, rules.In.Match(p, true, certs[tc.host], caPool), "port %d, %s, %s", tc.port, tc.host, tc.addr)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,60 @@
|
||||
package firewall
|
||||
|
||||
import (
|
||||
"iter"
|
||||
"math/bits"
|
||||
)
|
||||
|
||||
// ruleSet is a set of rule ids, stored as a bitset. s[i] holds ids i*8 through i*8+7, one per bit.
|
||||
// Bytes rather than words keep a set to the size the rule count needs, which matters when there is a set for
|
||||
// every port number.
|
||||
type ruleSet []uint8
|
||||
|
||||
// ruleSetLen returns the length of a ruleSet that can hold ids below n.
|
||||
func ruleSetLen(n int) int {
|
||||
return (n + 7) / 8
|
||||
}
|
||||
|
||||
// newRuleSet returns an empty set that can hold ids below idLimit.
|
||||
func newRuleSet(idLimit int) ruleSet {
|
||||
return make(ruleSet, ruleSetLen(idLimit))
|
||||
}
|
||||
|
||||
// add puts id in s.
|
||||
func (s ruleSet) add(id int) {
|
||||
s[id/8] |= 1 << (id % 8)
|
||||
}
|
||||
|
||||
// ruleSets holds several ruleSet objects of the same length in a single allocation.
|
||||
type ruleSets struct {
|
||||
// setLen is the number of bytes needed to represent one set
|
||||
setLen int
|
||||
// bits holds the sets in order. Set i starts at i*setLen.
|
||||
bits []uint8
|
||||
}
|
||||
|
||||
// newRuleSets returns n empty sets, each of which can hold ids below idLimit.
|
||||
func newRuleSets(n, idLimit int) ruleSets {
|
||||
setLen := ruleSetLen(idLimit)
|
||||
return ruleSets{setLen: setLen, bits: make([]uint8, n*setLen)}
|
||||
}
|
||||
|
||||
// at returns set i.
|
||||
func (s ruleSets) at(i int) ruleSet {
|
||||
return s.bits[i*s.setLen : (i+1)*s.setLen]
|
||||
}
|
||||
|
||||
// all returns an iterator over the ids in s, in ascending order.
|
||||
func (s ruleSet) all() iter.Seq[int] {
|
||||
return func(yield func(int) bool) {
|
||||
for i, ids := range s {
|
||||
for ids != 0 {
|
||||
id := i*8 + bits.TrailingZeros8(ids)
|
||||
ids &= ids - 1 // Clear the lowest set bit, which is id's.
|
||||
if !yield(id) {
|
||||
return
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,189 @@
|
||||
package firewall
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
|
||||
"github.com/slackhq/nebula/cert"
|
||||
)
|
||||
|
||||
// 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. A packet is allowed when every clause of a single rule allows it:
|
||||
// proto AND port AND (CA SHA or CA name) AND local CIDR AND (group OR groups OR name OR remote CIDR).
|
||||
// A Table does not change once built; see RulesBuilder.
|
||||
type Table struct {
|
||||
// rules holds every rule for the direction, in the order they were added. A rule's index in this slice is
|
||||
// its id in the ruleSets.
|
||||
rules []rule
|
||||
|
||||
// protos holds the index for each IP protocol number, so a packet is checked against a single index.
|
||||
// A protocol with rules of its own has an index that also includes every proto `any` rule. The remaining
|
||||
// protocols share an index of only the proto `any` rules: one for protocols with ports and one for
|
||||
// protocols without; see hasPorts. An entry is nil when the protocol has no rules at all.
|
||||
// ICMP and ICMPv6 share one index.
|
||||
protos [256]*protoIndex
|
||||
}
|
||||
|
||||
// protoIndex holds the rules that can apply to one protocol, in a set for each kind of packet. Rule ids are
|
||||
// indexes into the direction's rules, so every set is sized by the direction's rule count, not the protocol's:
|
||||
// byPort costs 64 KB per 8 rules in the direction.
|
||||
type protoIndex struct {
|
||||
// hasPorts reports whether the protocol has ports; see iputil.HasPorts.
|
||||
hasPorts bool
|
||||
// byPort has a set for every port number of a protocol with ports. Port 0 is covered only by port `any`
|
||||
// rules, since a range starts at 1.
|
||||
byPort ruleSets
|
||||
// packet holds the rules for a packet of a protocol without ports: the port `any` rules.
|
||||
packet ruleSet
|
||||
// fragment holds the rules for a fragment of any protocol: the port `any` and port `fragment` rules.
|
||||
fragment ruleSet
|
||||
}
|
||||
|
||||
// whichMatch returns the set of rules whose proto and port clauses allow p.
|
||||
func (pi *protoIndex) whichMatch(p *Packet, incoming bool) ruleSet {
|
||||
switch {
|
||||
case p.Fragment:
|
||||
// The ports of a fragmented packet are in its first fragment, and this is a later one.
|
||||
return pi.fragment
|
||||
case !pi.hasPorts:
|
||||
// The port fields are zero, or for ICMP the identifier, which is only for connection tracking.
|
||||
return pi.packet
|
||||
case incoming:
|
||||
return pi.byPort.at(int(p.LocalPort))
|
||||
default:
|
||||
return pi.byPort.at(int(p.RemotePort))
|
||||
}
|
||||
}
|
||||
|
||||
// rule is a parsed rule. A packet is allowed by the rule when its port, certificate, and address clauses all pass.
|
||||
type rule struct {
|
||||
// proto is the IP protocol number the rule applies to, or ProtoAny for every protocol. ICMPv6 rules are kept
|
||||
// as ICMP. The protoIndex checks it, so match does not.
|
||||
proto uint8
|
||||
|
||||
// startPort and endPort are the port clause. A startPort of PortAny covers every port, every packet of a
|
||||
// protocol without ports, and every fragment. PortFragment covers only fragments. A range covers the ports
|
||||
// in it, so it never applies to a protocol without ports.
|
||||
startPort, endPort int32
|
||||
|
||||
// caSha and caName pass a certificate issued by either CA. When neither is set, any CA passes.
|
||||
caSha, caName string
|
||||
|
||||
// remoteAny makes host, groups, and cidr irrelevant. Otherwise, the peer passes when any one of them matches.
|
||||
remoteAny bool
|
||||
host string
|
||||
groups []string
|
||||
cidr netip.Prefix // Invalid when the rule has no cidr.
|
||||
|
||||
// localAny allows any local address. Otherwise, local must contain the address. Neither is set for a rule
|
||||
// without a local cidr until the Table is built and the rule gets the default; see withDefaultLocal.
|
||||
localAny bool
|
||||
local []netip.Prefix
|
||||
}
|
||||
|
||||
// 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 {
|
||||
proto := t.protos[p.Protocol]
|
||||
if proto == nil {
|
||||
// The protocol has no rules of its own, and there are no proto `any` rules.
|
||||
return false
|
||||
}
|
||||
|
||||
// The index yields every rule whose proto and port clauses allow p.
|
||||
// The packet is allowed when the remaining clauses of any of those rules allow it as well.
|
||||
for id := range proto.whichMatch(p, incoming).all() {
|
||||
if t.rules[id].match(p, c, caPool) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
// match reports whether r allows p from the peer with certificate c. The port clause is not checked here; the
|
||||
// protoIndex has already done so.
|
||||
func (r *rule) match(p *Packet, c *cert.CachedCertificate, caPool *cert.CAPool) bool {
|
||||
return r.matchLocal(p.LocalAddr) && r.matchRemote(p.RemoteAddr, c) && r.matchCA(c, caPool)
|
||||
}
|
||||
|
||||
// matchLocal reports whether r allows the local address addr.
|
||||
func (r *rule) matchLocal(addr netip.Addr) bool {
|
||||
if r.localAny {
|
||||
return true
|
||||
}
|
||||
|
||||
for _, prefix := range r.local {
|
||||
if prefix.Contains(addr) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
// matchRemote reports whether r allows the peer with certificate c, sending from addr. The cidr is checked with
|
||||
// Prefix.Contains, so 0.0.0.0/0 allows any IPv4 address and ::/0 allows any IPv6 address; neither allows the
|
||||
// other family.
|
||||
func (r *rule) matchRemote(addr netip.Addr, c *cert.CachedCertificate) bool {
|
||||
if r.remoteAny {
|
||||
return true
|
||||
}
|
||||
|
||||
if r.cidr.IsValid() && r.cidr.Contains(addr) {
|
||||
return true
|
||||
}
|
||||
|
||||
if r.host != "" && r.host == c.Certificate.Name() {
|
||||
return true
|
||||
}
|
||||
|
||||
// Every group must be present.
|
||||
if len(r.groups) == 0 {
|
||||
return false
|
||||
}
|
||||
for _, g := range r.groups {
|
||||
if _, ok := c.InvertedGroups[g]; !ok {
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
return true
|
||||
}
|
||||
|
||||
// matchCA reports whether c was issued by a CA that r allows.
|
||||
func (r *rule) matchCA(c *cert.CachedCertificate, caPool *cert.CAPool) bool {
|
||||
if r.caSha == "" && r.caName == "" {
|
||||
return true
|
||||
}
|
||||
|
||||
if r.caSha != "" && r.caSha == c.Certificate.Issuer() {
|
||||
return true
|
||||
}
|
||||
|
||||
if r.caName != "" {
|
||||
s, err := caPool.GetCAForCert(c.Certificate)
|
||||
if err != nil {
|
||||
return false
|
||||
}
|
||||
return r.caName == s.Certificate.Name()
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
+333
-549
File diff suppressed because it is too large.
Load diff
@@ -1,5 +0,0 @@
|
||||
// Package msgx calls xnu's private batched socket calls, sendmsg_x and recvmsg_x, through libSystem.
|
||||
//
|
||||
// The calls are not public API, so the package never links them: it looks them up with dlsym on first use.
|
||||
// The package is darwin-only, and on iOS Available is always false, so App Store builds keep to public API.
|
||||
package msgx
|
||||
@@ -1,16 +0,0 @@
|
||||
package msgx
|
||||
|
||||
import "golang.org/x/sys/unix"
|
||||
|
||||
// Hdr mirrors xnu's struct msghdr_x (bsd/sys/socket_private.h), which the SDK doesn't ship.
|
||||
// recvmsg_x reports each message's length in Datalen rather than in its return value.
|
||||
type Hdr struct {
|
||||
Name *byte
|
||||
Namelen uint32
|
||||
Iov *unix.Iovec
|
||||
Iovlen int32
|
||||
Control *byte
|
||||
Controllen uint32
|
||||
Flags int32
|
||||
Datalen uint64
|
||||
}
|
||||
@@ -1,77 +0,0 @@
|
||||
//go:build !ios
|
||||
|
||||
package msgx
|
||||
|
||||
import (
|
||||
"sync"
|
||||
"syscall"
|
||||
"unsafe"
|
||||
)
|
||||
|
||||
// dlsym is public libSystem API, imported the way x/sys/unix imports its libSystem stubs. The local name is
|
||||
// distinct from runtime/race's dlsym import.
|
||||
//
|
||||
//go:cgo_import_dynamic msgx_dlsym dlsym "/usr/lib/libSystem.B.dylib"
|
||||
|
||||
// dlsymTrampolineAddr is the address of msgx_darwin.s's jump to dlsym.
|
||||
var dlsymTrampolineAddr uintptr
|
||||
|
||||
// syscall6X calls the C function at fn on the system stack and returns errno when it returns a 64-bit -1.
|
||||
// It is how x/sys/unix calls libSystem, and the runtime keeps it linkable for that.
|
||||
//
|
||||
//go:linkname syscall6X syscall.syscall6X
|
||||
func syscall6X(fn, a1, a2, a3, a4, a5, a6 uintptr) (r1, r2 uintptr, err syscall.Errno)
|
||||
|
||||
// rtldDefault is dlfcn.h's RTLD_DEFAULT, ((void *)-2): search every image loaded in the process.
|
||||
const rtldDefault = ^uintptr(1)
|
||||
|
||||
var (
|
||||
sendmsgXName = []byte("sendmsg_x\x00")
|
||||
recvmsgXName = []byte("recvmsg_x\x00")
|
||||
)
|
||||
|
||||
type funcs struct {
|
||||
sendmsgX uintptr
|
||||
recvmsgX uintptr
|
||||
}
|
||||
|
||||
var resolve = sync.OnceValue(func() funcs {
|
||||
return funcs{sendmsgX: lookup(sendmsgXName), recvmsgX: lookup(recvmsgXName)}
|
||||
})
|
||||
|
||||
// lookup returns the address of the NUL-terminated C symbol name, or 0 when no loaded image exports it.
|
||||
func lookup(name []byte) uintptr {
|
||||
p, _, _ := syscall6X(dlsymTrampolineAddr, rtldDefault, uintptr(unsafe.Pointer(&name[0])), 0, 0, 0, 0)
|
||||
return p
|
||||
}
|
||||
|
||||
// Available reports whether libSystem exports both sendmsg_x and recvmsg_x. When it is false, Send and Recv
|
||||
// return ENOSYS.
|
||||
func Available() bool {
|
||||
f := resolve()
|
||||
return f.sendmsgX != 0 && f.recvmsgX != 0
|
||||
}
|
||||
|
||||
// Send passes hdrs to sendmsg_x on fd and returns how many messages the kernel took.
|
||||
func Send(fd uintptr, hdrs []Hdr, flags int) (int, syscall.Errno) {
|
||||
return call(resolve().sendmsgX, fd, hdrs, flags)
|
||||
}
|
||||
|
||||
// Recv passes hdrs to recvmsg_x on fd and returns how many messages it filled.
|
||||
func Recv(fd uintptr, hdrs []Hdr, flags int) (int, syscall.Errno) {
|
||||
return call(resolve().recvmsgX, fd, hdrs, flags)
|
||||
}
|
||||
|
||||
func call(fn, fd uintptr, hdrs []Hdr, flags int) (int, syscall.Errno) {
|
||||
if fn == 0 {
|
||||
return 0, syscall.ENOSYS
|
||||
}
|
||||
if len(hdrs) == 0 {
|
||||
return 0, syscall.EINVAL
|
||||
}
|
||||
r, _, errno := syscall6X(fn, fd, uintptr(unsafe.Pointer(&hdrs[0])), uintptr(len(hdrs)), uintptr(flags), 0, 0)
|
||||
if errno != 0 {
|
||||
return 0, errno
|
||||
}
|
||||
return int(r), 0
|
||||
}
|
||||
@@ -1,9 +0,0 @@
|
||||
//go:build !ios
|
||||
|
||||
#include "textflag.h"
|
||||
|
||||
// The same trampoline shape x/sys/unix uses for its libSystem stubs; it assembles for amd64 and arm64 alike.
|
||||
TEXT msgx_dlsym_trampoline<>(SB),NOSPLIT,$0-0
|
||||
JMP msgx_dlsym(SB)
|
||||
GLOBL ·dlsymTrampolineAddr(SB), RODATA, $8
|
||||
DATA ·dlsymTrampolineAddr(SB)/8, $msgx_dlsym_trampoline<>(SB)
|
||||
@@ -1,69 +0,0 @@
|
||||
//go:build !ios
|
||||
|
||||
package msgx
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"syscall"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// TestAvailable pins that dlsym finds both calls in this macOS's libSystem, so the batched paths are live.
|
||||
func TestAvailable(t *testing.T) {
|
||||
assert.True(t, Available())
|
||||
}
|
||||
|
||||
// TestSendRecvRoundTrip pins the libSystem calling path end to end: a batch goes out through sendmsg_x in one
|
||||
// call and comes back through recvmsg_x in one call, each message whole, in order, with Datalen set.
|
||||
func TestSendRecvRoundTrip(t *testing.T) {
|
||||
fds, err := unix.Socketpair(unix.AF_UNIX, unix.SOCK_DGRAM, 0)
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() {
|
||||
_ = unix.Close(fds[0])
|
||||
_ = unix.Close(fds[1])
|
||||
})
|
||||
// A dropped datagram fails the receive instead of hanging it.
|
||||
require.NoError(t, unix.SetsockoptTimeval(fds[1], unix.SOL_SOCKET, unix.SO_RCVTIMEO, &unix.Timeval{Sec: 2}))
|
||||
|
||||
const n = 5
|
||||
var want [n][]byte
|
||||
var iovs [n]unix.Iovec
|
||||
hdrs := make([]Hdr, n)
|
||||
for i := range n {
|
||||
want[i] = bytes.Repeat([]byte{byte(i + 1)}, 10+i)
|
||||
iovs[i] = unix.Iovec{Base: &want[i][0]}
|
||||
iovs[i].SetLen(len(want[i]))
|
||||
hdrs[i] = Hdr{Iov: &iovs[i], Iovlen: 1}
|
||||
}
|
||||
sent, errno := Send(uintptr(fds[0]), hdrs, 0)
|
||||
require.Zero(t, errno)
|
||||
require.Equal(t, n, sent)
|
||||
|
||||
var bufs [n + 1][64]byte
|
||||
var riovs [n + 1]unix.Iovec
|
||||
rhdrs := make([]Hdr, n+1)
|
||||
for i := range rhdrs {
|
||||
riovs[i] = unix.Iovec{Base: &bufs[i][0]}
|
||||
riovs[i].SetLen(len(bufs[i]))
|
||||
rhdrs[i] = Hdr{Iov: &riovs[i], Iovlen: 1}
|
||||
}
|
||||
got, errno := Recv(uintptr(fds[1]), rhdrs, 0)
|
||||
require.Zero(t, errno)
|
||||
require.Equal(t, n, got)
|
||||
for i := range n {
|
||||
l := int(rhdrs[i].Datalen)
|
||||
assert.Equal(t, want[i], bufs[i][:l], "message %d", i)
|
||||
}
|
||||
}
|
||||
|
||||
// TestEmptyBatch pins that an empty batch is refused before it reaches the kernel.
|
||||
func TestEmptyBatch(t *testing.T) {
|
||||
_, errno := Send(0, nil, 0)
|
||||
assert.Equal(t, syscall.EINVAL, errno)
|
||||
_, errno = Recv(0, nil, 0)
|
||||
assert.Equal(t, syscall.EINVAL, errno)
|
||||
}
|
||||
@@ -1,12 +0,0 @@
|
||||
package msgx
|
||||
|
||||
import "syscall"
|
||||
|
||||
// Available is always false on iOS, so App Store builds never look up private symbols.
|
||||
func Available() bool { return false }
|
||||
|
||||
// Send always returns ENOSYS on iOS.
|
||||
func Send(uintptr, []Hdr, int) (int, syscall.Errno) { return 0, syscall.ENOSYS }
|
||||
|
||||
// Recv always returns ENOSYS on iOS.
|
||||
func Recv(uintptr, []Hdr, int) (int, syscall.Errno) { return 0, syscall.ENOSYS }
|
||||
@@ -32,10 +32,23 @@ const (
|
||||
IPProtocolICMPv6 = 58
|
||||
IPProtocolTCP = 6
|
||||
IPProtocolUDP = 17
|
||||
IPProtocolUDPLite = 136
|
||||
IPProtocolDCCP = 33
|
||||
IPProtocolSCTP = 132
|
||||
ICMPv6TypeEchoRequest = 128
|
||||
ICMPv6TypeEchoReply = 129
|
||||
)
|
||||
|
||||
// HasPorts reports whether packets of proto carry port numbers that the packet parsers read: TCP, UDP, UDPLite,
|
||||
// DCCP, and SCTP. Firewall rules with a port or a port range only apply to these protocols.
|
||||
func HasPorts(proto uint8) bool {
|
||||
switch proto {
|
||||
case IPProtocolTCP, IPProtocolUDP, IPProtocolUDPLite, IPProtocolDCCP, IPProtocolSCTP:
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
func CreateRejectPacket(packet []byte, out []byte) []byte {
|
||||
if len(packet) < 1 {
|
||||
return nil
|
||||
|
||||
+25
-25
@@ -361,31 +361,29 @@ func parseV6(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
|
||||
fp.Fragment = isFragment
|
||||
fp.FragAny = anyFragment
|
||||
fp.IPHdrLen = offset
|
||||
// fp is reused, so the ports are cleared for the packets that have none: fragments, protocols Nebula
|
||||
// doesn't inspect, and ICMPv6 other than echo. Only the cases below set them.
|
||||
fp.RemotePort, fp.LocalPort = 0, 0
|
||||
if isFragment {
|
||||
// Non-first fragments carry no transport header, so we have no ports to read
|
||||
fp.RemotePort = 0
|
||||
fp.LocalPort = 0
|
||||
return nil
|
||||
}
|
||||
|
||||
switch proto {
|
||||
case iputil.IPProtocolICMPv6:
|
||||
switch {
|
||||
case proto == iputil.IPProtocolICMPv6:
|
||||
// An ICMPv6 message is at least type, code and checksum, 4 bytes. Only echo carries more than we read.
|
||||
if dataLen < offset+4 {
|
||||
return ErrIPv6PacketTooShort
|
||||
}
|
||||
fp.LocalPort = 0 //incoming vs outgoing doesn't matter for icmpv6
|
||||
switch data[offset] { //icmp type
|
||||
case iputil.ICMPv6TypeEchoRequest, iputil.ICMPv6TypeEchoReply:
|
||||
if dataLen < offset+6 {
|
||||
return ErrIPv6PacketTooShort
|
||||
}
|
||||
fp.RemotePort = binary.BigEndian.Uint16(data[offset+4 : offset+6]) //identifier
|
||||
default:
|
||||
fp.RemotePort = 0
|
||||
fp.RemotePort = binary.BigEndian.Uint16(data[offset+4 : offset+6]) //identifier, orientation doesn't matter
|
||||
}
|
||||
|
||||
case iputil.IPProtocolTCP, iputil.IPProtocolUDP:
|
||||
case iputil.HasPorts(proto):
|
||||
if dataLen < offset+4 {
|
||||
return ErrIPv6PacketTooShort
|
||||
}
|
||||
@@ -396,11 +394,6 @@ func parseV6(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
|
||||
fp.LocalPort = binary.BigEndian.Uint16(data[offset : offset+2])
|
||||
fp.RemotePort = binary.BigEndian.Uint16(data[offset+2 : offset+4])
|
||||
}
|
||||
|
||||
default:
|
||||
// don't set ports for protocols Nebula doesn't inspect
|
||||
fp.RemotePort = 0
|
||||
fp.LocalPort = 0
|
||||
}
|
||||
|
||||
return nil
|
||||
@@ -453,18 +446,25 @@ func parseV4(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
|
||||
fp.RemoteAddr, _ = netip.AddrFromSlice(data[16:20])
|
||||
}
|
||||
|
||||
// fp is reused, so the ports are cleared for the packets that have none: fragments, and protocols Nebula
|
||||
// doesn't inspect, whose first 4 bytes (GRE, IPIP, AH, etc.) are not ports. Only the cases below set them.
|
||||
fp.RemotePort, fp.LocalPort = 0, 0
|
||||
if fp.Fragment {
|
||||
fp.RemotePort = 0
|
||||
fp.LocalPort = 0
|
||||
} else if fp.Protocol == iputil.IPProtocolICMP { //note that orientation doesn't matter on ICMP
|
||||
fp.RemotePort = binary.BigEndian.Uint16(data[ihl+4 : ihl+6]) //identifier
|
||||
fp.LocalPort = 0 //code would be uint16(data[ihl+1])
|
||||
} else if incoming {
|
||||
fp.RemotePort = binary.BigEndian.Uint16(data[ihl : ihl+2]) //src port
|
||||
fp.LocalPort = binary.BigEndian.Uint16(data[ihl+2 : ihl+4]) //dst port
|
||||
} else {
|
||||
fp.LocalPort = binary.BigEndian.Uint16(data[ihl : ihl+2]) //src port
|
||||
fp.RemotePort = binary.BigEndian.Uint16(data[ihl+2 : ihl+4]) //dst port
|
||||
return nil
|
||||
}
|
||||
|
||||
switch {
|
||||
case fp.Protocol == iputil.IPProtocolICMP: //note that orientation doesn't matter on ICMP
|
||||
fp.RemotePort = binary.BigEndian.Uint16(data[ihl+4 : ihl+6]) //identifier, LocalPort stays 0 but could be the code, data[ihl+1]
|
||||
|
||||
case iputil.HasPorts(fp.Protocol):
|
||||
if incoming {
|
||||
fp.RemotePort = binary.BigEndian.Uint16(data[ihl : ihl+2]) //src port
|
||||
fp.LocalPort = binary.BigEndian.Uint16(data[ihl+2 : ihl+4]) //dst port
|
||||
} else {
|
||||
fp.LocalPort = binary.BigEndian.Uint16(data[ihl : ihl+2]) //src port
|
||||
fp.RemotePort = binary.BigEndian.Uint16(data[ihl+2 : ihl+4]) //dst port
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
|
||||
+86
-21
@@ -77,7 +77,7 @@ func Test_newPacket(t *testing.T) {
|
||||
// account for variable ip header length - outgoing
|
||||
h = ipv4.Header{
|
||||
Version: 1,
|
||||
Protocol: 2,
|
||||
Protocol: iputil.IPProtocolUDP,
|
||||
Len: 100,
|
||||
Src: net.IPv4(10, 0, 0, 1),
|
||||
Dst: net.IPv4(10, 0, 0, 2),
|
||||
@@ -89,7 +89,7 @@ func Test_newPacket(t *testing.T) {
|
||||
err = newPacket(b, false, p)
|
||||
|
||||
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("10.0.0.2"), p.RemoteAddr)
|
||||
assert.Equal(t, uint16(6), p.RemotePort)
|
||||
@@ -97,6 +97,71 @@ func Test_newPacket(t *testing.T) {
|
||||
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) {
|
||||
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
|
||||
// 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
|
||||
// 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.
|
||||
func Test_newPacket_v6ExtHeaderConfusion(t *testing.T) {
|
||||
p := &firewall.ParsedPacket{}
|
||||
|
||||
pkt := make([]byte, 52)
|
||||
pkt[0] = 0x60 // version 6
|
||||
pkt[6] = byte(layers.IPProtocolSCTP) // NextHeader = SCTP, a real protocol, not an extension header
|
||||
pkt[7] = 64 // hop limit
|
||||
pkt[0] = 0x60 // version 6
|
||||
pkt[6] = byte(layers.IPProtocolGRE) // NextHeader = GRE, a real protocol, not an extension header
|
||||
pkt[7] = 64 // hop limit
|
||||
|
||||
// Real SCTP header at offset 40. Pre-fix parseV6 walked SCTP 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
|
||||
// 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[42:44], 445) // SCTP dst port, never read by parseV6
|
||||
binary.BigEndian.PutUint16(pkt[48:50], 53) // SCTP checksum bytes, pre-fix forged RemotePort
|
||||
// Real GRE header at offset 40. Pre-fix parseV6 walked GRE as an extension header: byte 41 (0x00, the
|
||||
// low byte of the flags/version word below) was read as the header length, giving next=(0+1)*8=8, which
|
||||
// landed the walk on byte 40 (0x11), misread as NextHeader=UDP, then bytes 48-51 as ports.
|
||||
binary.BigEndian.PutUint16(pkt[40:42], 0x1100) // GRE flags/version; byte 40=0x11, byte 41=0x00
|
||||
binary.BigEndian.PutUint16(pkt[42:44], 0x86dd) // GRE protocol type, never read by parseV6
|
||||
binary.BigEndian.PutUint16(pkt[48:50], 53) // GRE payload, pre-fix forged RemotePort
|
||||
binary.BigEndian.PutUint16(pkt[50:52], 53) // pre-fix forged LocalPort
|
||||
|
||||
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.LocalPort)
|
||||
assert.False(t, p.Fragment)
|
||||
|
||||
// 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
|
||||
// the only assertion that discriminates the fix here, a regression that walked SCTP would misclassify it.
|
||||
// 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 GRE would misclassify it.
|
||||
chained := make([]byte, 60)
|
||||
chained[0] = 0x60 // version 6
|
||||
chained[6] = byte(layers.IPProtocolIPv6HopByHop) // NextHeader = HopByHop extension
|
||||
chained[7] = 64 // hop limit
|
||||
chained[40] = byte(layers.IPProtocolSCTP) // HopByHop NextHeader = SCTP
|
||||
chained[41] = 0 // HopByHop length 0 -> 8 bytes, SCTP begins at offset 48
|
||||
binary.BigEndian.PutUint16(chained[48:50], 0x1100) // SCTP src port, pre-fix forged NextHeader/length bait
|
||||
binary.BigEndian.PutUint16(chained[50:52], 445) // SCTP dst port, never read by parseV6
|
||||
chained[40] = byte(layers.IPProtocolGRE) // HopByHop NextHeader = GRE
|
||||
chained[41] = 0 // HopByHop length 0 -> 8 bytes, GRE begins at offset 48
|
||||
binary.BigEndian.PutUint16(chained[48:50], 0x1100) // GRE flags/version, pre-fix forged NextHeader/length bait
|
||||
binary.BigEndian.PutUint16(chained[50:52], 0x86dd) // GRE protocol type, never read by parseV6
|
||||
|
||||
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.LocalPort)
|
||||
assert.False(t, p.Fragment)
|
||||
|
||||
@@ -435,65 +435,3 @@ func testPP(pkt []byte) *firewall.ParsedPacket {
|
||||
}
|
||||
return pp
|
||||
}
|
||||
|
||||
// fakeTunBatchWriter records each WriteBatch call and each plain Write separately.
|
||||
type fakeTunBatchWriter struct {
|
||||
writes [][]byte
|
||||
batches [][][]byte
|
||||
}
|
||||
|
||||
func (w *fakeTunBatchWriter) Write(p []byte) (int, error) {
|
||||
w.writes = append(w.writes, bytes.Clone(p))
|
||||
return len(p), nil
|
||||
}
|
||||
|
||||
func (w *fakeTunBatchWriter) WriteBatch(pkts [][]byte) error {
|
||||
var b [][]byte
|
||||
for _, p := range pkts {
|
||||
b = append(b, bytes.Clone(p))
|
||||
}
|
||||
w.batches = append(w.batches, b)
|
||||
return nil
|
||||
}
|
||||
|
||||
// TestPassthroughUsesWriteBatch pins that a writer implementing tio.BatchWriter gets the whole
|
||||
// passthrough lane in one WriteBatch per Flush, in order, and no plain Writes; an empty Flush
|
||||
// makes no call.
|
||||
func TestPassthroughUsesWriteBatch(t *testing.T) {
|
||||
w := &fakeTunBatchWriter{}
|
||||
m := newTestMultiCoalescer(t, w)
|
||||
k := &keySeq{epoch: 1}
|
||||
|
||||
var want [][]byte
|
||||
for i := range 5 {
|
||||
icmp := make([]byte, 28)
|
||||
icmp[0] = 0x45
|
||||
icmp[3] = 28
|
||||
icmp[9] = 1
|
||||
icmp[20] = byte(i)
|
||||
want = append(want, icmp)
|
||||
if err := m.Commit(icmp, k.next(), testPP(icmp)); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
if err := m.Flush(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := m.Flush(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(w.writes) != 0 {
|
||||
t.Fatalf("got %d plain Writes, want 0", len(w.writes))
|
||||
}
|
||||
if len(w.batches) != 1 {
|
||||
t.Fatalf("got %d WriteBatch calls, want 1", len(w.batches))
|
||||
}
|
||||
for i, p := range w.batches[0] {
|
||||
if !bytes.Equal(p, want[i]) {
|
||||
t.Fatalf("packet %d: got % x, want % x", i, p, want[i])
|
||||
}
|
||||
}
|
||||
if len(w.batches[0]) != len(want) {
|
||||
t.Fatalf("got %d packets, want %d", len(w.batches[0]), len(want))
|
||||
}
|
||||
}
|
||||
@@ -2,23 +2,18 @@ package batch
|
||||
|
||||
import (
|
||||
"io"
|
||||
|
||||
"github.com/slackhq/nebula/overlay/tio"
|
||||
)
|
||||
|
||||
// Passthrough is MultiCoalescer's verbatim lane: no coalescing, packets are written at Flush in the
|
||||
// order enqueued, in one WriteBatch when out implements tio.BatchWriter.
|
||||
// Passthrough is MultiCoalescer's verbatim lane: no batching, packets are written at Flush in the
|
||||
// order enqueued.
|
||||
type Passthrough struct {
|
||||
out io.Writer
|
||||
bw tio.BatchWriter // nil: Flush writes one packet per Write
|
||||
slots [][]byte
|
||||
}
|
||||
|
||||
func NewPassthrough(w io.Writer) *Passthrough {
|
||||
bw, _ := w.(tio.BatchWriter)
|
||||
return &Passthrough{
|
||||
out: w,
|
||||
bw: bw,
|
||||
slots: make([][]byte, 0, 128),
|
||||
}
|
||||
}
|
||||
@@ -31,16 +26,10 @@ func (p *Passthrough) enqueue(pkt []byte) error {
|
||||
|
||||
func (p *Passthrough) Flush() error {
|
||||
var firstErr error
|
||||
if p.bw != nil {
|
||||
if len(p.slots) > 0 {
|
||||
firstErr = p.bw.WriteBatch(p.slots)
|
||||
}
|
||||
} else {
|
||||
for _, s := range p.slots {
|
||||
_, err := p.out.Write(s)
|
||||
if err != nil && firstErr == nil {
|
||||
firstErr = err
|
||||
}
|
||||
for _, s := range p.slots {
|
||||
_, err := p.out.Write(s)
|
||||
if err != nil && firstErr == nil {
|
||||
firstErr = err
|
||||
}
|
||||
}
|
||||
clear(p.slots)
|
||||
|
||||
@@ -145,14 +145,3 @@ func SupportsGSO(w io.Writer, want GSOProto) (GSOWriter, bool) {
|
||||
return gw, false
|
||||
}
|
||||
}
|
||||
|
||||
// BatchWriter is implemented by Queues that can emit several already-segmented packets in one call.
|
||||
// Backends without a batched write do not implement it and callers loop over Write.
|
||||
//
|
||||
// pkts are borrowed: WriteBatch must not retain them past its return.
|
||||
// A returned error doesn't say which packets were delivered, so callers must not retry the batch.
|
||||
// Safe for concurrent use, like Write.
|
||||
type BatchWriter interface {
|
||||
io.Writer
|
||||
WriteBatch(pkts [][]byte) error
|
||||
}
|
||||
@@ -1,328 +0,0 @@
|
||||
//go:build darwin && !ios
|
||||
|
||||
package tio
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"os"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
_ "unsafe" // for go:linkname
|
||||
|
||||
"github.com/slackhq/nebula/internal/msgx"
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// tunMaxPacket is the largest packet utun can return at any device MTU.
|
||||
const tunMaxPacket = 65535
|
||||
|
||||
// tunReadBatch is the most packets one Utun.Read returns.
|
||||
const tunReadBatch = 64
|
||||
|
||||
// tunReadArena is Utun's receive buffer. Draining stops once less than tunMaxPacket of it is left,
|
||||
// so every readv has room for the largest packet utun can return.
|
||||
const tunReadArena = 4 * tunMaxPacket
|
||||
|
||||
// tunWriteBatch is how many packets one sendmsg_x call may carry.
|
||||
const tunWriteBatch = 64
|
||||
|
||||
// Utun is a darwin utun control socket as a Queue. Every packet crosses the socket behind a 4 byte
|
||||
// address family prefix, which Read strips and the writes add.
|
||||
//
|
||||
// The fd lives in the runtime poller, so Close wakes a Read parked on it; darwin needs no QueueSet
|
||||
// shutdown fd.
|
||||
type Utun struct {
|
||||
f *os.File
|
||||
l *slog.Logger
|
||||
|
||||
// readBuf and readRet are Read's scratch, owned by the single reader.
|
||||
readBuf []byte
|
||||
readRet [tunReadBatch]Packet
|
||||
|
||||
// noSendmsgX is set when libSystem lacks sendmsg_x or the kernel refuses it; WriteBatch then writes one packet at a time.
|
||||
noSendmsgX atomic.Bool
|
||||
batchMu sync.Mutex
|
||||
batch tunBatch
|
||||
}
|
||||
|
||||
// tunBatch is WriteBatch's scratch, guarded by Utun.batchMu. The kernel reads every entry in place.
|
||||
type tunBatch struct {
|
||||
heads [tunWriteBatch][4]byte
|
||||
iovs [tunWriteBatch][2]unix.Iovec
|
||||
hdrs [tunWriteBatch]msgx.Hdr
|
||||
pkts [tunWriteBatch][]byte
|
||||
}
|
||||
|
||||
// NewUtun wraps a utun control socket fd and makes it non-blocking.
|
||||
// On failure it does NOT close fd: the caller owns fd until NewUtun succeeds, after which Close closes it.
|
||||
func NewUtun(fd int, l *slog.Logger) (*Utun, error) {
|
||||
// Before os.NewFile, which only hands a non-blocking fd to the runtime poller.
|
||||
if err := unix.SetNonblock(fd, true); err != nil {
|
||||
return nil, fmt.Errorf("failed to set the tun fd to non-blocking mode: %w", err)
|
||||
}
|
||||
u := &Utun{
|
||||
f: os.NewFile(uintptr(fd), "utun"),
|
||||
l: l,
|
||||
readBuf: make([]byte, tunReadArena),
|
||||
}
|
||||
u.noSendmsgX.Store(!msgx.Available())
|
||||
return u, nil
|
||||
}
|
||||
|
||||
// tunWritev and tunReadv are linkname'd to x/sys/unix's libc-routed writev/readv stubs so the
|
||||
// calls go through libSystem's pinned trampoline. A raw syscall.Syscall(SYS_WRITEV/SYS_READV, ...)
|
||||
// on darwin/arm64 emits an SVC #0x80 trap (see $GOROOT/src/syscall/asm_darwin_arm64.s), the path
|
||||
// Apple keeps warning they will eventually disallow. We pull the low-level stubs instead of calling
|
||||
// unix.Writev/unix.Readv because those take [][]byte and rebuild the []Iovec every call, which
|
||||
// heap-allocates the header; linkname'ing the stubs lets us hand them our own stack-allocated
|
||||
// iovecs. See golang/go#78049.
|
||||
|
||||
//go:linkname tunWritev golang.org/x/sys/unix.writev
|
||||
//go:noescape
|
||||
func tunWritev(fd int, iovecs []unix.Iovec) (n int, err error)
|
||||
|
||||
//go:linkname tunReadv golang.org/x/sys/unix.readv
|
||||
//go:noescape
|
||||
func tunReadv(fd int, iovecs []unix.Iovec) (n int, err error)
|
||||
|
||||
// Read waits for the utun to become readable, then reads packets until it would block, up to
|
||||
// tunReadBatch, so the caller encrypts and sends them as one batch rather than one per wakeup. Each
|
||||
// packet is read with its AF prefix scattered away, so the payload lands directly in readBuf.
|
||||
// An error after at least one packet is dropped in favor of returning those packets; a persistent
|
||||
// one recurs on the next Read.
|
||||
func (u *Utun) Read() ([]Packet, error) {
|
||||
rc, err := u.f.SyscallConn()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
var head [4]byte
|
||||
n, off := 0, 0
|
||||
var callErr error
|
||||
err = rc.Read(func(fd uintptr) bool {
|
||||
for n < tunReadBatch && len(u.readBuf)-off >= tunMaxPacket {
|
||||
iovecs := [2]unix.Iovec{
|
||||
{Base: &head[0], Len: 4},
|
||||
{Base: &u.readBuf[off], Len: uint64(len(u.readBuf) - off)},
|
||||
}
|
||||
l, e := tunReadv(int(fd), iovecs[:])
|
||||
if e != nil {
|
||||
if errno, ok := e.(syscall.Errno); ok && errno.Temporary() {
|
||||
// Park on the poller only while there is nothing to hand back.
|
||||
return n > 0
|
||||
}
|
||||
callErr = e
|
||||
return true
|
||||
}
|
||||
if l < 4 {
|
||||
// A datagram too short to carry the AF prefix, or end of file; stop rather than spin on it.
|
||||
return true
|
||||
}
|
||||
end := off + l - 4
|
||||
u.readRet[n] = Packet{Bytes: u.readBuf[off:end:end]}
|
||||
n++
|
||||
off = end
|
||||
}
|
||||
return true
|
||||
})
|
||||
if n > 0 {
|
||||
return u.readRet[:n], nil
|
||||
}
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return nil, callErr
|
||||
}
|
||||
|
||||
// Write pushes one IP packet onto the utun device. Safe for concurrent use:
|
||||
// the AF prefix and iovecs are per-call stack state, and the fd write itself
|
||||
// serializes on the runtime's fd mutex (see the Queue contract in tio.go).
|
||||
func (u *Utun) Write(from []byte) (int, error) {
|
||||
if len(from) == 0 {
|
||||
return 0, syscall.EIO
|
||||
}
|
||||
|
||||
var head [4]byte
|
||||
af, err := tunAF(from)
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
head[3] = af
|
||||
|
||||
// Grab rc as a local so the compiler can devirtualize the call and keep the closure on the stack.
|
||||
rc, err := u.f.SyscallConn()
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
|
||||
var n int
|
||||
var callErr error
|
||||
err = rc.Write(func(fd uintptr) bool {
|
||||
iovecs := []unix.Iovec{
|
||||
{Base: &head[0], Len: 4},
|
||||
{Base: &from[0], Len: uint64(len(from))},
|
||||
}
|
||||
n, callErr = tunWritev(int(fd), iovecs)
|
||||
// Type-assert to syscall.Errno so the EAGAIN/EWOULDBLOCK/EINTR check doesn't box the errno
|
||||
// constants into error interfaces on every call.
|
||||
if errno, ok := callErr.(syscall.Errno); ok && errno.Temporary() {
|
||||
return false
|
||||
}
|
||||
return true
|
||||
})
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
if callErr != nil {
|
||||
return 0, callErr
|
||||
}
|
||||
|
||||
return n - 4, nil
|
||||
}
|
||||
|
||||
// tunAF returns the utun address-family prefix byte for an IP packet.
|
||||
func tunAF(pkt []byte) (byte, error) {
|
||||
switch pkt[0] >> 4 {
|
||||
case 4:
|
||||
return syscall.AF_INET, nil
|
||||
case 6:
|
||||
return syscall.AF_INET6, nil
|
||||
default:
|
||||
return 0, fmt.Errorf("unable to determine IP version from packet")
|
||||
}
|
||||
}
|
||||
|
||||
// WriteBatch writes pkts to the utun device with sendmsg_x, xnu's private batched sendmsg, up to
|
||||
// tunWriteBatch packets per syscall. The kernel still hands each packet to utun on its own, so this
|
||||
// saves syscalls, not per-packet kernel work. Safe for concurrent use.
|
||||
//
|
||||
// An empty packet or one with no IP version is skipped and reported, as Write would. Any other
|
||||
// error from sendmsg_x means the kernel took an unknown prefix of that call and dropped the rest, so
|
||||
// it is reported rather than retried, which could deliver packets twice.
|
||||
//
|
||||
// Under mbuf exhaustion, sendmsg_x silently drops packets that writev would have delivered: the
|
||||
// kernel counts each packet as sent once it is copied in, and when a later allocation fails it
|
||||
// frees that prefix unsent and returns its length as a short count, which is indistinguishable
|
||||
// from a real one.
|
||||
func (u *Utun) WriteBatch(pkts [][]byte) error {
|
||||
if u.noSendmsgX.Load() {
|
||||
return u.writeEach(pkts)
|
||||
}
|
||||
|
||||
u.batchMu.Lock()
|
||||
defer u.batchMu.Unlock()
|
||||
b := &u.batch
|
||||
var firstErr error
|
||||
for len(pkts) > 0 {
|
||||
n := 0
|
||||
for len(pkts) > 0 && n < tunWriteBatch {
|
||||
p := pkts[0]
|
||||
pkts = pkts[1:]
|
||||
var af byte
|
||||
err := error(syscall.EIO)
|
||||
if len(p) > 0 {
|
||||
af, err = tunAF(p)
|
||||
}
|
||||
if err != nil {
|
||||
if firstErr == nil {
|
||||
firstErr = err
|
||||
}
|
||||
continue
|
||||
}
|
||||
b.heads[n] = [4]byte{3: af}
|
||||
b.iovs[n] = [2]unix.Iovec{
|
||||
{Base: &b.heads[n][0], Len: 4},
|
||||
{Base: &p[0], Len: uint64(len(p))},
|
||||
}
|
||||
b.hdrs[n] = msgx.Hdr{Iov: &b.iovs[n][0], Iovlen: 2}
|
||||
b.pkts[n] = p
|
||||
n++
|
||||
}
|
||||
if n == 0 {
|
||||
continue
|
||||
}
|
||||
|
||||
for off := 0; off < n; {
|
||||
sent, err := u.sendmsgX(off, n)
|
||||
switch {
|
||||
case err == nil && sent > 0:
|
||||
// The kernel stops early without an error on a packet larger than the socket's send
|
||||
// buffer, or when sending a later packet fails with ENOBUFS; resend the remainder.
|
||||
off += sent
|
||||
case err == nil:
|
||||
if werr := u.writeEach(b.pkts[off:n]); werr != nil && firstErr == nil {
|
||||
firstErr = werr
|
||||
}
|
||||
off = n
|
||||
case err == unix.EMSGSIZE:
|
||||
// Only the first packet being larger than the socket's send buffer fails the whole call,
|
||||
// before the kernel takes any; Write reports that one and the rest go out in the next call.
|
||||
if werr := u.writeEach(b.pkts[off : off+1]); werr != nil && firstErr == nil {
|
||||
firstErr = werr
|
||||
}
|
||||
off++
|
||||
case err == unix.ENOSYS || err == unix.EPERM || err == unix.EOPNOTSUPP:
|
||||
// sendmsg_x is private API: fall back to writev if a kernel or sandbox refuses it.
|
||||
if u.noSendmsgX.CompareAndSwap(false, true) {
|
||||
u.l.Warn("sendmsg_x unavailable on the tun device, writing one packet per syscall", "error", err)
|
||||
}
|
||||
if werr := u.writeEach(b.pkts[off:n]); werr != nil && firstErr == nil {
|
||||
firstErr = werr
|
||||
}
|
||||
clear(b.iovs[:n])
|
||||
clear(b.pkts[:n])
|
||||
if werr := u.writeEach(pkts); werr != nil && firstErr == nil {
|
||||
firstErr = werr
|
||||
}
|
||||
return firstErr
|
||||
default:
|
||||
if firstErr == nil {
|
||||
firstErr = err
|
||||
}
|
||||
off = n
|
||||
}
|
||||
}
|
||||
clear(b.iovs[:n])
|
||||
clear(b.pkts[:n])
|
||||
}
|
||||
return firstErr
|
||||
}
|
||||
|
||||
// sendmsgX hands entries off through n-1 of u.batch to sendmsg_x and returns how many the kernel took.
|
||||
func (u *Utun) sendmsgX(off, n int) (int, error) {
|
||||
rc, err := u.f.SyscallConn()
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
var sent int
|
||||
var errno syscall.Errno
|
||||
err = rc.Write(func(fd uintptr) bool {
|
||||
sent, errno = msgx.Send(fd, u.batch.hdrs[off:n], 0)
|
||||
// sendmsg_x reports EAGAIN only when it took nothing; a partial batch returns its count.
|
||||
return !errno.Temporary()
|
||||
})
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
if errno != 0 {
|
||||
return 0, errno
|
||||
}
|
||||
return sent, nil
|
||||
}
|
||||
|
||||
// writeEach writes pkts one at a time with Write.
|
||||
func (u *Utun) writeEach(pkts [][]byte) error {
|
||||
var firstErr error
|
||||
for _, p := range pkts {
|
||||
if _, err := u.Write(p); err != nil && firstErr == nil {
|
||||
firstErr = err
|
||||
}
|
||||
}
|
||||
return firstErr
|
||||
}
|
||||
|
||||
func (u *Utun) Close() error {
|
||||
return u.f.Close()
|
||||
}
|
||||
@@ -1,198 +0,0 @@
|
||||
//go:build darwin && !ios
|
||||
|
||||
package tio
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"log/slog"
|
||||
"syscall"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// newSocketpairUtun returns a Utun over one end of a connected AF_UNIX datagram socketpair, which
|
||||
// takes sendmsg_x the way a utun control socket does, and the other end's fd for the test to use.
|
||||
// sndbuf is the Utun's send buffer, which caps the largest datagram it accepts.
|
||||
func newSocketpairUtun(t *testing.T, sndbuf int) (*Utun, int) {
|
||||
t.Helper()
|
||||
fds, err := unix.Socketpair(unix.AF_UNIX, unix.SOCK_DGRAM, 0)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, unix.SetsockoptInt(fds[0], unix.SOL_SOCKET, unix.SO_SNDBUF, sndbuf))
|
||||
// An AF_UNIX datagram send is bounded by the receiver's buffer, so size both ends' for the tests.
|
||||
require.NoError(t, unix.SetsockoptInt(fds[0], unix.SOL_SOCKET, unix.SO_RCVBUF, 1<<20))
|
||||
require.NoError(t, unix.SetsockoptInt(fds[1], unix.SOL_SOCKET, unix.SO_RCVBUF, 1<<20))
|
||||
// A dropped datagram fails the read-back instead of hanging it.
|
||||
require.NoError(t, unix.SetsockoptTimeval(fds[1], unix.SOL_SOCKET, unix.SO_RCVTIMEO, &unix.Timeval{Sec: 2}))
|
||||
u, err := NewUtun(fds[0], slog.New(slog.DiscardHandler))
|
||||
if err != nil {
|
||||
_ = unix.Close(fds[0])
|
||||
_ = unix.Close(fds[1])
|
||||
t.Fatal(err)
|
||||
}
|
||||
t.Cleanup(func() {
|
||||
_ = u.Close()
|
||||
_ = unix.Close(fds[1])
|
||||
})
|
||||
return u, fds[1]
|
||||
}
|
||||
|
||||
// testTunPkt returns packet i of size bytes, alternating IPv4 and IPv6, and the datagram the utun
|
||||
// device should receive for it.
|
||||
func testTunPkt(i, size int) (pkt, wire []byte) {
|
||||
pkt = make([]byte, size)
|
||||
pkt[0] = 0x45
|
||||
af := byte(syscall.AF_INET)
|
||||
if i%2 == 1 {
|
||||
pkt[0] = 0x60
|
||||
af = syscall.AF_INET6
|
||||
}
|
||||
pkt[1] = byte(i)
|
||||
pkt[2] = byte(i >> 8)
|
||||
return pkt, append([]byte{0, 0, 0, af}, pkt...)
|
||||
}
|
||||
|
||||
// readTunBack asserts r receives exactly want, in order.
|
||||
func readTunBack(t *testing.T, r int, want [][]byte) {
|
||||
t.Helper()
|
||||
buf := make([]byte, 4096)
|
||||
for i, w := range want {
|
||||
n, _, err := unix.Recvfrom(r, buf, 0)
|
||||
require.NoError(t, err, "datagram %d", i)
|
||||
if !bytes.Equal(w, buf[:n]) {
|
||||
t.Fatalf("datagram %d: got % x, want % x", i, buf[:n], w)
|
||||
}
|
||||
}
|
||||
_, _, err := unix.Recvfrom(r, buf, unix.MSG_DONTWAIT)
|
||||
assert.ErrorIs(t, err, unix.EAGAIN, "extra datagrams delivered")
|
||||
}
|
||||
|
||||
// forEachTunWritePath runs fn once over sendmsg_x and once over the per-packet writev fallback.
|
||||
func forEachTunWritePath(t *testing.T, fn func(t *testing.T, fallback bool)) {
|
||||
for _, fallback := range []bool{false, true} {
|
||||
name := "sendmsg_x"
|
||||
if fallback {
|
||||
name = "writev"
|
||||
}
|
||||
t.Run(name, func(t *testing.T) { fn(t, fallback) })
|
||||
}
|
||||
}
|
||||
|
||||
// TestUtunWriteBatch pins that WriteBatch delivers every packet whole, in order and behind the right
|
||||
// utun AF prefix, across several sendmsg_x calls, and returns nil.
|
||||
func TestUtunWriteBatch(t *testing.T) {
|
||||
forEachTunWritePath(t, func(t *testing.T, fallback bool) {
|
||||
u, r := newSocketpairUtun(t, 1<<20)
|
||||
u.noSendmsgX.Store(fallback)
|
||||
|
||||
var pkts, want [][]byte
|
||||
for i := range 3*tunWriteBatch + 5 {
|
||||
p, w := testTunPkt(i, 60+i)
|
||||
pkts = append(pkts, p)
|
||||
want = append(want, w)
|
||||
}
|
||||
require.NoError(t, u.WriteBatch(pkts))
|
||||
assert.Equal(t, fallback, u.noSendmsgX.Load())
|
||||
readTunBack(t, r, want)
|
||||
})
|
||||
}
|
||||
|
||||
// TestUtunWriteBatchSkipsInvalid pins that an empty packet or one with no IP version is skipped
|
||||
// without shifting the packets after it, and that the first such error is the one reported.
|
||||
func TestUtunWriteBatchSkipsInvalid(t *testing.T) {
|
||||
forEachTunWritePath(t, func(t *testing.T, fallback bool) {
|
||||
u, r := newSocketpairUtun(t, 1<<20)
|
||||
u.noSendmsgX.Store(fallback)
|
||||
|
||||
var pkts, want [][]byte
|
||||
for i := range 20 {
|
||||
p, w := testTunPkt(i, 60)
|
||||
pkts = append(pkts, p)
|
||||
want = append(want, w)
|
||||
}
|
||||
pkts = append(pkts[:10], append([][]byte{{0x10, 1, 2}, {}}, pkts[10:]...)...)
|
||||
|
||||
err := u.WriteBatch(pkts)
|
||||
assert.ErrorContains(t, err, "IP version")
|
||||
readTunBack(t, r, want)
|
||||
})
|
||||
}
|
||||
|
||||
// TestUtunWriteBatchOversize pins that a packet larger than the socket's send buffer drops only
|
||||
// itself and is reported, whether sendmsg_x reaches it mid-call (a short count) or first (EMSGSIZE
|
||||
// for the whole call). The send buffer is 1024 bytes and the oversize packet 2000.
|
||||
func TestUtunWriteBatchOversize(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
at int
|
||||
}{
|
||||
{"mid-call", tunWriteBatch + 6},
|
||||
{"first-in-call", tunWriteBatch},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
forEachTunWritePath(t, func(t *testing.T, fallback bool) {
|
||||
u, r := newSocketpairUtun(t, 1024)
|
||||
u.noSendmsgX.Store(fallback)
|
||||
|
||||
var pkts, want [][]byte
|
||||
for i := range 2*tunWriteBatch + 10 {
|
||||
size := 100
|
||||
if i == tc.at {
|
||||
size = 2000
|
||||
}
|
||||
p, w := testTunPkt(i, size)
|
||||
pkts = append(pkts, p)
|
||||
if i != tc.at {
|
||||
want = append(want, w)
|
||||
}
|
||||
}
|
||||
err := u.WriteBatch(pkts)
|
||||
assert.ErrorIs(t, err, unix.EMSGSIZE)
|
||||
assert.Equal(t, fallback, u.noSendmsgX.Load())
|
||||
readTunBack(t, r, want)
|
||||
})
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestUtunReadDrains pins that Read hands back every queued packet, AF prefix stripped and in
|
||||
// order, capped at tunReadBatch per call, and doesn't wait for more once the queue is empty.
|
||||
func TestUtunReadDrains(t *testing.T) {
|
||||
u, w := newSocketpairUtun(t, 1<<20)
|
||||
total := tunReadBatch + 3
|
||||
var want [][]byte
|
||||
for i := range total {
|
||||
pkt, wire := testTunPkt(i, 60+i)
|
||||
_, err := unix.Write(w, wire)
|
||||
require.NoError(t, err)
|
||||
want = append(want, pkt)
|
||||
}
|
||||
|
||||
var got [][]byte
|
||||
for _, size := range []int{tunReadBatch, 3} {
|
||||
pkts, err := u.Read()
|
||||
require.NoError(t, err)
|
||||
require.Len(t, pkts, size)
|
||||
for _, p := range pkts {
|
||||
got = append(got, p.Clone().Bytes)
|
||||
}
|
||||
}
|
||||
assert.Equal(t, want, got)
|
||||
}
|
||||
|
||||
// TestUtunReadClipsPackets pins that each returned packet's capacity ends at its own bytes, so
|
||||
// appending to one can't overwrite the next.
|
||||
func TestUtunReadClipsPackets(t *testing.T) {
|
||||
u, w := newSocketpairUtun(t, 1<<20)
|
||||
for i := range 2 {
|
||||
_, wire := testTunPkt(i, 100)
|
||||
_, err := unix.Write(w, wire)
|
||||
require.NoError(t, err)
|
||||
}
|
||||
pkts, err := u.Read()
|
||||
require.NoError(t, err)
|
||||
require.Len(t, pkts, 2)
|
||||
assert.Equal(t, len(pkts[0].Bytes), cap(pkts[0].Bytes))
|
||||
}
|
||||
+115
-12
@@ -7,7 +7,9 @@ import (
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"os"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
"unsafe"
|
||||
|
||||
"github.com/gaissmai/bart"
|
||||
@@ -20,7 +22,7 @@ import (
|
||||
)
|
||||
|
||||
type tun struct {
|
||||
queue *tio.Utun
|
||||
f *os.File
|
||||
Device string
|
||||
vpnNetworks []netip.Prefix
|
||||
DefaultMTU int
|
||||
@@ -115,13 +117,13 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
return nil, fmt.Errorf("failed to retrieve tun name: %w", err)
|
||||
}
|
||||
|
||||
queue, err := tio.NewUtun(fd, l)
|
||||
err = unix.SetNonblock(fd, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
return nil, fmt.Errorf("SetNonblock: %v", err)
|
||||
}
|
||||
|
||||
t := &tun{
|
||||
queue: queue,
|
||||
f: os.NewFile(uintptr(fd), ""),
|
||||
Device: name,
|
||||
vpnNetworks: vpnNetworks,
|
||||
DefaultMTU: c.GetInt("tun.mtu", DefaultMTU),
|
||||
@@ -154,15 +156,15 @@ func (t *tun) deviceBytes() (o [16]byte) {
|
||||
// network extension is handed its device. Everything about moving packets is shared with newTun,
|
||||
// only the setup differs: the host owns addressing and routing here.
|
||||
func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip.Prefix) (*tun, error) {
|
||||
queue, err := tio.NewUtun(deviceFd, l)
|
||||
if err != nil {
|
||||
if err := unix.SetNonblock(deviceFd, true); err != nil {
|
||||
// We own the fd from the moment it is handed to us
|
||||
_ = unix.Close(deviceFd)
|
||||
return nil, err
|
||||
return nil, fmt.Errorf("failed to set the tun fd to non-blocking mode: %w", err)
|
||||
}
|
||||
|
||||
file := os.NewFile(uintptr(deviceFd), "/dev/tun")
|
||||
t := &tun{
|
||||
queue: queue,
|
||||
f: file,
|
||||
Device: utunNameFromFd(deviceFd),
|
||||
vpnNetworks: vpnNetworks,
|
||||
DefaultMTU: c.GetInt("tun.mtu", DefaultMTU),
|
||||
@@ -171,7 +173,7 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
|
||||
}
|
||||
|
||||
if err := t.reload(c, true); err != nil {
|
||||
_ = queue.Close()
|
||||
_ = file.Close()
|
||||
return nil, err
|
||||
}
|
||||
|
||||
@@ -195,8 +197,8 @@ func utunNameFromFd(fd int) string {
|
||||
}
|
||||
|
||||
func (t *tun) Close() error {
|
||||
if t.queue != nil {
|
||||
return t.queue.Close()
|
||||
if t.f != nil {
|
||||
return t.f.Close()
|
||||
}
|
||||
return nil
|
||||
}
|
||||
@@ -554,6 +556,107 @@ func delRoute(prefix netip.Prefix, gateway netroute.Addr) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// tunWritev and tunReadv are linkname'd to x/sys/unix's libc-routed writev/readv stubs so the
|
||||
// calls go through libSystem's pinned trampoline. A raw syscall.Syscall(SYS_WRITEV/SYS_READV, ...)
|
||||
// on darwin/arm64 emits an SVC #0x80 trap (see $GOROOT/src/syscall/asm_darwin_arm64.s), the path
|
||||
// Apple keeps warning they will eventually disallow. We pull the low-level stubs instead of calling
|
||||
// unix.Writev/unix.Readv because those take [][]byte and rebuild the []Iovec every call, which
|
||||
// heap-allocates the header; linkname'ing the stubs lets us hand them our own stack-allocated
|
||||
// iovecs. See golang/go#78049.
|
||||
|
||||
//go:linkname tunWritev golang.org/x/sys/unix.writev
|
||||
//go:noescape
|
||||
func tunWritev(fd int, iovecs []unix.Iovec) (n int, err error)
|
||||
|
||||
//go:linkname tunReadv golang.org/x/sys/unix.readv
|
||||
//go:noescape
|
||||
func tunReadv(fd int, iovecs []unix.Iovec) (n int, err error)
|
||||
|
||||
// Read pulls one IP packet off the utun device, scattering the 4 byte protocol header away from
|
||||
// the packet so the payload lands directly in to.
|
||||
func (t *tun) Read(to []byte) (int, error) {
|
||||
var head [4]byte
|
||||
|
||||
rc, err := t.f.SyscallConn()
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
|
||||
var n int
|
||||
var callErr error
|
||||
err = rc.Read(func(fd uintptr) bool {
|
||||
iovecs := []unix.Iovec{
|
||||
{Base: &head[0], Len: 4},
|
||||
{Base: &to[0], Len: uint64(len(to))},
|
||||
}
|
||||
n, callErr = tunReadv(int(fd), iovecs)
|
||||
if errno, ok := callErr.(syscall.Errno); ok && errno.Temporary() {
|
||||
return false
|
||||
}
|
||||
return true
|
||||
})
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
if callErr != nil {
|
||||
return 0, callErr
|
||||
}
|
||||
if n < 4 {
|
||||
return 0, nil
|
||||
}
|
||||
return n - 4, nil
|
||||
}
|
||||
|
||||
// Write pushes one IP packet onto the utun device. Safe for concurrent use:
|
||||
// the AF prefix and iovecs are per-call stack state, and the fd write itself
|
||||
// serializes on the runtime's fd mutex (see the Queue contract in tio.go).
|
||||
func (t *tun) Write(from []byte) (int, error) {
|
||||
if len(from) == 0 {
|
||||
return 0, syscall.EIO
|
||||
}
|
||||
|
||||
ipVer := from[0] >> 4
|
||||
var head [4]byte
|
||||
switch ipVer {
|
||||
case 4:
|
||||
head[3] = syscall.AF_INET
|
||||
case 6:
|
||||
head[3] = syscall.AF_INET6
|
||||
default:
|
||||
return 0, fmt.Errorf("unable to determine IP version from packet")
|
||||
}
|
||||
|
||||
// Grab rc as a local so the compiler can devirtualize the call and keep the closure on the stack.
|
||||
rc, err := t.f.SyscallConn()
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
|
||||
var n int
|
||||
var callErr error
|
||||
err = rc.Write(func(fd uintptr) bool {
|
||||
iovecs := []unix.Iovec{
|
||||
{Base: &head[0], Len: 4},
|
||||
{Base: &from[0], Len: uint64(len(from))},
|
||||
}
|
||||
n, callErr = tunWritev(int(fd), iovecs)
|
||||
// Type-assert to syscall.Errno so the EAGAIN/EWOULDBLOCK/EINTR check doesn't box the errno
|
||||
// constants into error interfaces on every call.
|
||||
if errno, ok := callErr.(syscall.Errno); ok && errno.Temporary() {
|
||||
return false
|
||||
}
|
||||
return true
|
||||
})
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
if callErr != nil {
|
||||
return 0, callErr
|
||||
}
|
||||
|
||||
return n - 4, nil
|
||||
}
|
||||
|
||||
func (t *tun) Networks() []netip.Prefix {
|
||||
return t.vpnNetworks
|
||||
}
|
||||
@@ -563,5 +666,5 @@ func (t *tun) Name() string {
|
||||
}
|
||||
|
||||
func (t *tun) Queues(int) ([]tio.Queue, error) {
|
||||
return []tio.Queue{t.queue}, nil
|
||||
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
||||
}
|
||||
+6
-263
@@ -10,12 +10,10 @@ import (
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
"unsafe"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/internal/msgx"
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
@@ -24,9 +22,6 @@ type StdConn struct {
|
||||
isV4 bool
|
||||
sysFd uintptr
|
||||
l *slog.Logger
|
||||
|
||||
noSendmsgX atomic.Bool
|
||||
sb *sendScratch
|
||||
}
|
||||
|
||||
var _ Conn = &StdConn{}
|
||||
@@ -40,7 +35,6 @@ func NewListener(l *slog.Logger, s Settings) (Conn, error) {
|
||||
|
||||
if uc, ok := pc.(*net.UDPConn); ok {
|
||||
c := &StdConn{UDPConn: uc, l: l}
|
||||
c.noSendmsgX.Store(!msgx.Available())
|
||||
|
||||
rc, err := uc.SyscallConn()
|
||||
if err != nil {
|
||||
@@ -145,138 +139,11 @@ func (u *StdConn) WriteTo(b []byte, ap netip.AddrPort) error {
|
||||
}
|
||||
}
|
||||
|
||||
// sendBatch is how many datagrams one sendmsg_x call may carry.
|
||||
const sendBatch = 64
|
||||
|
||||
// sendScratch is WriteBatch's scratch. The kernel reads every entry in place.
|
||||
type sendScratch struct {
|
||||
names [sendBatch]unix.RawSockaddrInet6
|
||||
iovs [sendBatch]unix.Iovec
|
||||
hdrs [sendBatch]msgx.Hdr
|
||||
// idx maps each entry back to its index in WriteBatch's bufs.
|
||||
idx [sendBatch]int
|
||||
}
|
||||
|
||||
// WriteBatch sends bufs with sendmsg_x, darwin's private batched sendmsg, so one syscall carries up to
|
||||
// sendBatch datagrams. On this unconnected socket xnu still runs each message through sendit, so the
|
||||
// saving is the syscall crossings, not the per-send policy checks.
|
||||
//
|
||||
// xnu's per-message loop stops at the first message that fails. For the errors in sentNothing it reports
|
||||
// how many went out; for any other it returns only the errno, with the messages before it already sent.
|
||||
// Each call therefore carries one run of datagrams to the same destination: a destination the kernel
|
||||
// refuses fails on its first datagram, so a failed call costs that run and nothing else, and no datagram
|
||||
// is ever resent after the kernel may have taken it.
|
||||
//
|
||||
// TODO: WriteTo maps EWOULDBLOCK to an error, so a full send buffer
|
||||
// silently drops the rest of a burst (linux blocks instead). Poll for
|
||||
// writability on EAGAIN before giving up on the remainder.
|
||||
func (u *StdConn) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error) {
|
||||
if u.noSendmsgX.Load() {
|
||||
return u.writeEach(bufs, addrs), nil
|
||||
}
|
||||
if u.sb == nil {
|
||||
u.sb = new(sendScratch)
|
||||
}
|
||||
b := u.sb
|
||||
written := 0
|
||||
for i := 0; i < len(bufs); {
|
||||
n := 0
|
||||
for ; i < len(bufs) && n < sendBatch; i++ {
|
||||
namelen, err := u.putSockaddr(&b.names[n], addrs[i])
|
||||
if err != nil {
|
||||
u.l.Debug("failed to write packet in batch", "udpAddr", addrs[i], "error", err)
|
||||
continue
|
||||
}
|
||||
b.iovs[n] = unix.Iovec{}
|
||||
if len(bufs[i]) > 0 {
|
||||
b.iovs[n].Base = &bufs[i][0]
|
||||
b.iovs[n].SetLen(len(bufs[i]))
|
||||
}
|
||||
b.hdrs[n] = msgx.Hdr{Name: (*byte)(unsafe.Pointer(&b.names[n])), Namelen: namelen, Iov: &b.iovs[n], Iovlen: 1}
|
||||
b.idx[n] = i
|
||||
n++
|
||||
}
|
||||
|
||||
for off := 0; off < n; {
|
||||
dst := addrs[b.idx[off]]
|
||||
end := off + 1
|
||||
for end < n && addrs[b.idx[end]] == dst {
|
||||
end++
|
||||
}
|
||||
sent, errno := u.sendmsgX(off, end)
|
||||
switch {
|
||||
case errno == 0 && sent > 0:
|
||||
written += sent
|
||||
off += sent
|
||||
continue
|
||||
case sentNothing(errno):
|
||||
// The datagram at off failed on its own account. sendto delivers or reports it, as without
|
||||
// batching, and the rest of the run goes back to sendmsg_x.
|
||||
j := b.idx[off]
|
||||
written += u.writeEach(bufs[j:j+1], addrs[j:j+1])
|
||||
off++
|
||||
continue
|
||||
case errno == 0:
|
||||
case errno == unix.ENOSYS || errno == unix.EOPNOTSUPP:
|
||||
u.fallBack(errno)
|
||||
case errno == unix.EPERM || errno == unix.EINVAL:
|
||||
// Either can refuse one destination, but a datagram that sendto delivers was refused by
|
||||
// sendmsg_x itself, as a sandbox or an older kernel would.
|
||||
j := b.idx[off]
|
||||
if u.writeEach(bufs[j:j+1], addrs[j:j+1]) == 0 {
|
||||
off = end
|
||||
continue
|
||||
}
|
||||
written++
|
||||
off++
|
||||
u.fallBack(errno)
|
||||
default:
|
||||
u.l.Debug("failed to write packets in batch", "udpAddr", dst, "packets", end-off, "error", errno)
|
||||
off = end
|
||||
continue
|
||||
}
|
||||
// The kernel took nothing from this call, so the rest can go out one datagram at a time.
|
||||
for _, j := range b.idx[off:n] {
|
||||
written += u.writeEach(bufs[j:j+1], addrs[j:j+1])
|
||||
}
|
||||
off = n
|
||||
if u.noSendmsgX.Load() {
|
||||
clear(b.iovs[:n])
|
||||
return written + u.writeEach(bufs[i:], addrs[i:]), nil
|
||||
}
|
||||
}
|
||||
clear(b.iovs[:n])
|
||||
}
|
||||
return written, nil
|
||||
}
|
||||
|
||||
// sendmsgX hands entries off through end-1 of u.sb to sendmsg_x and returns how many the kernel took.
|
||||
// The socket is non-blocking, so a full send buffer returns EAGAIN rather than waiting.
|
||||
func (u *StdConn) sendmsgX(off, end int) (int, syscall.Errno) {
|
||||
for {
|
||||
sent, errno := msgx.Send(u.sysFd, u.sb.hdrs[off:end], 0)
|
||||
if errno == unix.EINTR {
|
||||
continue
|
||||
}
|
||||
return sent, errno
|
||||
}
|
||||
}
|
||||
|
||||
// sentNothing reports whether sendmsg_x failing with errno means no datagram went out: once any has, xnu
|
||||
// turns these errors into a short count instead.
|
||||
func sentNothing(errno syscall.Errno) bool {
|
||||
return errno == unix.EWOULDBLOCK || errno == unix.ENOBUFS || errno == unix.EMSGSIZE
|
||||
}
|
||||
|
||||
// fallBack switches WriteBatch to one sendto per datagram for the life of the socket.
|
||||
func (u *StdConn) fallBack(errno syscall.Errno) {
|
||||
if u.noSendmsgX.CompareAndSwap(false, true) {
|
||||
u.l.Warn("sendmsg_x unavailable, sending one datagram per syscall", "error", errno)
|
||||
}
|
||||
}
|
||||
|
||||
// writeEach sends bufs one at a time with WriteTo and returns how many were written.
|
||||
func (u *StdConn) writeEach(bufs [][]byte, addrs []netip.AddrPort) int {
|
||||
// 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 send buffer
|
||||
// silently drops the rest of a burst (linux blocks instead). Poll for
|
||||
// writability on EAGAIN before giving up on the remainder.
|
||||
written := 0
|
||||
for i, b := range bufs {
|
||||
if err := u.WriteTo(b, addrs[i]); err == nil {
|
||||
@@ -285,23 +152,7 @@ func (u *StdConn) writeEach(bufs [][]byte, addrs []netip.AddrPort) int {
|
||||
u.l.Debug("failed to write packet in batch", "udpAddr", addrs[i], "error", err)
|
||||
}
|
||||
}
|
||||
return written
|
||||
}
|
||||
|
||||
// putSockaddr writes ap into sa in the socket's address family, as WriteTo would, and returns its length.
|
||||
func (u *StdConn) putSockaddr(sa *unix.RawSockaddrInet6, ap netip.AddrPort) (uint32, error) {
|
||||
if u.isV4 {
|
||||
if ap.Addr().Is6() {
|
||||
return 0, ErrInvalidIPv6RemoteForSocket
|
||||
}
|
||||
sa4 := (*unix.RawSockaddrInet4)(unsafe.Pointer(sa))
|
||||
*sa4 = unix.RawSockaddrInet4{Family: unix.AF_INET, Addr: ap.Addr().As4()}
|
||||
binary.BigEndian.PutUint16((*[2]byte)(unsafe.Pointer(&sa4.Port))[:], ap.Port())
|
||||
return unix.SizeofSockaddrInet4, nil
|
||||
}
|
||||
*sa = unix.RawSockaddrInet6{Family: unix.AF_INET6, Addr: ap.Addr().As16()}
|
||||
binary.BigEndian.PutUint16((*[2]byte)(unsafe.Pointer(&sa.Port))[:], ap.Port())
|
||||
return unix.SizeofSockaddrInet6, nil
|
||||
return written, nil
|
||||
}
|
||||
|
||||
func (u *StdConn) LocalAddr() (netip.AddrPort, error) {
|
||||
@@ -329,106 +180,11 @@ func NewUDPStatsEmitter(udpConns []Conn) func() {
|
||||
return func() {}
|
||||
}
|
||||
|
||||
// recvBatch is how many datagrams one recvmsg_x call may return.
|
||||
const recvBatch = 64
|
||||
|
||||
// ListenOut drains the socket with recvmsg_x, darwin's private batched recvmsg, so one syscall reads
|
||||
// up to recvBatch datagrams instead of one.
|
||||
func (u *StdConn) ListenOut(r EncReader, flush func()) error {
|
||||
if !msgx.Available() {
|
||||
return u.listenOutSingle(r, flush)
|
||||
}
|
||||
rc, err := u.UDPConn.SyscallConn()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
bufs := make([][]byte, recvBatch)
|
||||
names := make([]unix.RawSockaddrInet6, recvBatch)
|
||||
iovs := make([]unix.Iovec, recvBatch)
|
||||
hdrs := make([]msgx.Hdr, recvBatch)
|
||||
for i := range hdrs {
|
||||
bufs[i] = make([]byte, MTU)
|
||||
iovs[i].Base = &bufs[i][0]
|
||||
iovs[i].SetLen(MTU)
|
||||
hdrs[i].Iov = &iovs[i]
|
||||
hdrs[i].Iovlen = 1
|
||||
hdrs[i].Name = (*byte)(unsafe.Pointer(&names[i]))
|
||||
}
|
||||
|
||||
for {
|
||||
var n int
|
||||
var errno syscall.Errno
|
||||
err := rc.Read(func(fd uintptr) bool {
|
||||
for i := range hdrs {
|
||||
hdrs[i].Namelen = unix.SizeofSockaddrInet6
|
||||
hdrs[i].Flags = 0
|
||||
hdrs[i].Datalen = 0
|
||||
}
|
||||
n, errno = msgx.Recv(fd, hdrs, 0)
|
||||
return errno != unix.EAGAIN
|
||||
})
|
||||
if err != nil {
|
||||
if errors.Is(err, net.ErrClosed) {
|
||||
return err
|
||||
}
|
||||
u.l.Error("unexpected udp socket receive error", "error", err)
|
||||
continue
|
||||
}
|
||||
if errno == unix.ENOSYS || errno == unix.EPERM || errno == unix.EOPNOTSUPP {
|
||||
// recvmsg_x is private, so a kernel or sandbox may refuse it.
|
||||
u.l.Warn("recvmsg_x unavailable, reading one datagram per syscall", "error", errno)
|
||||
return u.listenOutSingle(r, flush)
|
||||
}
|
||||
if errno != 0 {
|
||||
if errno != unix.EINTR {
|
||||
u.l.Error("unexpected udp socket receive error", "error", errno)
|
||||
}
|
||||
continue
|
||||
}
|
||||
if err := checkMsghdrX(hdrs, names, n); err != nil {
|
||||
// The batch was read through a layout the kernel no longer writes, so none of it is trustworthy.
|
||||
u.l.Warn("recvmsg_x returned an unexpected header, reading one datagram per syscall", "error", err)
|
||||
return u.listenOutSingle(r, flush)
|
||||
}
|
||||
|
||||
for i := 0; i < n; i++ {
|
||||
addr, ok := sockaddrToAddrPort(&names[i])
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
l := int(hdrs[i].Datalen)
|
||||
r(addr, bufs[i][:l:l])
|
||||
}
|
||||
flush()
|
||||
}
|
||||
}
|
||||
|
||||
// checkMsghdrX rejects a recvmsg_x result that intact msghdr_x entries can't produce, which is how a change
|
||||
// to xnu's private struct layout would show up.
|
||||
func checkMsghdrX(hdrs []msgx.Hdr, names []unix.RawSockaddrInet6, n int) error {
|
||||
if n > len(hdrs) {
|
||||
return fmt.Errorf("returned %d datagrams for %d headers", n, len(hdrs))
|
||||
}
|
||||
for i := range n {
|
||||
if hdrs[i].Datalen > MTU {
|
||||
return fmt.Errorf("datagram %d is %d bytes, past the %d byte buffer", i, hdrs[i].Datalen, MTU)
|
||||
}
|
||||
switch {
|
||||
case names[i].Family == unix.AF_INET && hdrs[i].Namelen == unix.SizeofSockaddrInet4:
|
||||
case names[i].Family == unix.AF_INET6 && hdrs[i].Namelen == unix.SizeofSockaddrInet6:
|
||||
default:
|
||||
return fmt.Errorf("datagram %d has address family %d with length %d", i, names[i].Family, hdrs[i].Namelen)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// listenOutSingle reads one datagram per recvfrom and flushes after each, for when recvmsg_x is refused or misbehaves.
|
||||
func (u *StdConn) listenOutSingle(r EncReader, flush func()) error {
|
||||
buffer := make([]byte, MTU)
|
||||
|
||||
for {
|
||||
// Just read one packet at a time
|
||||
n, rua, err := u.ReadFromUDPAddrPort(buffer)
|
||||
if err != nil {
|
||||
if errors.Is(err, net.ErrClosed) {
|
||||
@@ -443,19 +199,6 @@ func (u *StdConn) listenOutSingle(r EncReader, flush func()) error {
|
||||
}
|
||||
}
|
||||
|
||||
func sockaddrToAddrPort(sa *unix.RawSockaddrInet6) (netip.AddrPort, bool) {
|
||||
switch sa.Family {
|
||||
case unix.AF_INET:
|
||||
sa4 := (*unix.RawSockaddrInet4)(unsafe.Pointer(sa))
|
||||
port := binary.BigEndian.Uint16((*[2]byte)(unsafe.Pointer(&sa4.Port))[:])
|
||||
return netip.AddrPortFrom(netip.AddrFrom4(sa4.Addr), port), true
|
||||
case unix.AF_INET6:
|
||||
port := binary.BigEndian.Uint16((*[2]byte)(unsafe.Pointer(&sa.Port))[:])
|
||||
return netip.AddrPortFrom(netip.AddrFrom16(sa.Addr).Unmap(), port), true
|
||||
}
|
||||
return netip.AddrPort{}, false
|
||||
}
|
||||
|
||||
func (u *StdConn) SupportsMultipleReaders() bool {
|
||||
return false
|
||||
}
|
||||
|
||||
@@ -1,85 +0,0 @@
|
||||
//go:build !e2e_testing
|
||||
|
||||
package udp
|
||||
|
||||
import (
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// BenchmarkListenOut measures the receive path on loopback: senders flood datagrams sized like a full tunnel
|
||||
// packet, and each op is one datagram delivered to the reader. There are enough senders that the reader, not the
|
||||
// senders, sets the pace. flushes/pkt is 1 when every receive is its own syscall and falls as receives batch. The
|
||||
// senders share the machine, so ns/op is only comparable between runs on the same host.
|
||||
func BenchmarkListenOut(b *testing.B) {
|
||||
for _, tc := range []struct{ name, listen string }{
|
||||
{"v4", "127.0.0.1"},
|
||||
{"v6", "::1"},
|
||||
} {
|
||||
b.Run(tc.name, func(b *testing.B) {
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.AddrPortFrom(netip.MustParseAddr(tc.listen), 0)})
|
||||
if err != nil {
|
||||
b.Fatal(err)
|
||||
}
|
||||
la, err := c.LocalAddr()
|
||||
if err != nil {
|
||||
b.Fatal(err)
|
||||
}
|
||||
const size, senders = 1300, 4
|
||||
txs := make([]net.Conn, senders)
|
||||
for i := range txs {
|
||||
if txs[i], err = net.Dial("udp", la.String()); err != nil {
|
||||
b.Fatal(err)
|
||||
}
|
||||
defer txs[i].Close()
|
||||
}
|
||||
|
||||
target := int64(b.N)
|
||||
var got, flushes atomic.Int64
|
||||
reached := make(chan struct{})
|
||||
done := make(chan struct{})
|
||||
go func() {
|
||||
_ = c.ListenOut(func(netip.AddrPort, []byte) {
|
||||
if got.Add(1) == target {
|
||||
close(reached)
|
||||
}
|
||||
}, func() { flushes.Add(1) })
|
||||
close(done)
|
||||
}()
|
||||
|
||||
// Writes fail with ENOBUFS while the send queue is full; the flood only has to keep the receiver busy.
|
||||
stop := make(chan struct{})
|
||||
var sent sync.WaitGroup
|
||||
for _, tx := range txs {
|
||||
sent.Go(func() {
|
||||
payload := make([]byte, size)
|
||||
for {
|
||||
select {
|
||||
case <-stop:
|
||||
return
|
||||
default:
|
||||
_, _ = tx.Write(payload)
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
b.SetBytes(size)
|
||||
b.ResetTimer()
|
||||
<-reached
|
||||
b.StopTimer()
|
||||
|
||||
close(stop)
|
||||
sent.Wait()
|
||||
if err := c.Close(); err != nil {
|
||||
b.Fatal(err)
|
||||
}
|
||||
<-done
|
||||
b.ReportMetric(float64(flushes.Load())/float64(got.Load()), "flushes/pkt")
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -1,302 +0,0 @@
|
||||
//go:build !e2e_testing
|
||||
|
||||
package udp
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
"sync"
|
||||
"syscall"
|
||||
"testing"
|
||||
"time"
|
||||
"unsafe"
|
||||
|
||||
"github.com/slackhq/nebula/internal/msgx"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// A burst larger than recvBatch arrives whole, with each datagram's own bytes and source address, and
|
||||
// flush runs once per recvmsg_x batch rather than once per datagram.
|
||||
func TestListenOutBatchesBurst(t *testing.T) {
|
||||
for _, tc := range []struct{ name, listen string }{
|
||||
{"v4", "127.0.0.1"},
|
||||
{"v6", "::1"},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.AddrPortFrom(netip.MustParseAddr(tc.listen), 0)})
|
||||
require.NoError(t, err)
|
||||
la, err := c.LocalAddr()
|
||||
require.NoError(t, err)
|
||||
|
||||
tx, err := net.Dial("udp", la.String())
|
||||
require.NoError(t, err)
|
||||
defer tx.Close()
|
||||
txAddr := netip.MustParseAddrPort(tx.LocalAddr().String())
|
||||
|
||||
const total = recvBatch*3 + 7
|
||||
var mu sync.Mutex
|
||||
var got []string
|
||||
var froms []netip.AddrPort
|
||||
flushes := 0
|
||||
// Queued before the reader starts, so recvmsg_x sees full batches.
|
||||
for i := 0; i < total; i++ {
|
||||
_, err := tx.Write([]byte(fmt.Sprintf("pkt-%03d", i)))
|
||||
require.NoError(t, err)
|
||||
}
|
||||
|
||||
done := make(chan struct{})
|
||||
go func() {
|
||||
_ = c.ListenOut(func(addr netip.AddrPort, payload []byte) {
|
||||
mu.Lock()
|
||||
got = append(got, string(payload))
|
||||
froms = append(froms, addr)
|
||||
mu.Unlock()
|
||||
}, func() {
|
||||
mu.Lock()
|
||||
flushes++
|
||||
mu.Unlock()
|
||||
})
|
||||
close(done)
|
||||
}()
|
||||
|
||||
require.Eventually(t, func() bool {
|
||||
mu.Lock()
|
||||
defer mu.Unlock()
|
||||
return len(got) == total
|
||||
}, 5*time.Second, 10*time.Millisecond)
|
||||
|
||||
require.NoError(t, c.Close())
|
||||
<-done
|
||||
|
||||
for i, p := range got {
|
||||
assert.Equal(t, fmt.Sprintf("pkt-%03d", i), p)
|
||||
assert.Equal(t, txAddr, froms[i])
|
||||
}
|
||||
assert.Equal(t, (total+recvBatch-1)/recvBatch, flushes)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// msgx.Hdr round-trips through xnu's recvmsg_x on a loopback socket, v4 and v6. The kernel reads Name, Namelen,
|
||||
// Iov and Iovlen from each entry and writes Namelen, Flags and Datalen back, so a field at the wrong offset or a
|
||||
// wrong stride between entries shows up as a wrong length, sender, or payload.
|
||||
// TestListenOutSingleFallback pins the path ListenOut takes when the kernel refuses recvmsg_x.
|
||||
func TestListenOutSingleFallback(t *testing.T) {
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0")})
|
||||
require.NoError(t, err)
|
||||
la, err := c.LocalAddr()
|
||||
require.NoError(t, err)
|
||||
tx, err := net.Dial("udp", la.String())
|
||||
require.NoError(t, err)
|
||||
defer tx.Close()
|
||||
txAddr := netip.MustParseAddrPort(tx.LocalAddr().String())
|
||||
|
||||
const total = 5
|
||||
for i := 0; i < total; i++ {
|
||||
_, err := tx.Write([]byte(fmt.Sprintf("pkt-%03d", i)))
|
||||
require.NoError(t, err)
|
||||
}
|
||||
|
||||
var mu sync.Mutex
|
||||
var got []string
|
||||
flushes := 0
|
||||
done := make(chan struct{})
|
||||
go func() {
|
||||
_ = c.(*StdConn).listenOutSingle(func(addr netip.AddrPort, payload []byte) {
|
||||
assert.Equal(t, txAddr, addr)
|
||||
mu.Lock()
|
||||
got = append(got, string(payload))
|
||||
mu.Unlock()
|
||||
}, func() {
|
||||
mu.Lock()
|
||||
flushes++
|
||||
mu.Unlock()
|
||||
})
|
||||
close(done)
|
||||
}()
|
||||
|
||||
require.Eventually(t, func() bool {
|
||||
mu.Lock()
|
||||
defer mu.Unlock()
|
||||
return len(got) == total
|
||||
}, 5*time.Second, 10*time.Millisecond)
|
||||
require.NoError(t, c.Close())
|
||||
<-done
|
||||
|
||||
for i, p := range got {
|
||||
assert.Equal(t, fmt.Sprintf("pkt-%03d", i), p)
|
||||
}
|
||||
assert.Equal(t, total, flushes)
|
||||
}
|
||||
|
||||
func TestCheckMsghdrX(t *testing.T) {
|
||||
valid := func() ([]msgx.Hdr, []unix.RawSockaddrInet6) {
|
||||
hdrs := make([]msgx.Hdr, 2)
|
||||
names := make([]unix.RawSockaddrInet6, 2)
|
||||
hdrs[0].Namelen, hdrs[0].Datalen = unix.SizeofSockaddrInet4, 1
|
||||
names[0].Family = unix.AF_INET
|
||||
hdrs[1].Namelen, hdrs[1].Datalen = unix.SizeofSockaddrInet6, MTU
|
||||
names[1].Family = unix.AF_INET6
|
||||
return hdrs, names
|
||||
}
|
||||
|
||||
hdrs, names := valid()
|
||||
require.NoError(t, checkMsghdrX(hdrs, names, 2))
|
||||
require.NoError(t, checkMsghdrX(hdrs, names, 0))
|
||||
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
n int
|
||||
mutate func([]msgx.Hdr, []unix.RawSockaddrInet6)
|
||||
}{
|
||||
{"count past headers", 3, func([]msgx.Hdr, []unix.RawSockaddrInet6) {}},
|
||||
{"datalen past buffer", 2, func(h []msgx.Hdr, _ []unix.RawSockaddrInet6) { h[1].Datalen = MTU + 1 }},
|
||||
{"unknown family", 2, func(_ []msgx.Hdr, a []unix.RawSockaddrInet6) { a[0].Family = unix.AF_UNIX }},
|
||||
{"family and length disagree", 2, func(h []msgx.Hdr, _ []unix.RawSockaddrInet6) { h[0].Namelen = unix.SizeofSockaddrInet6 }},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
hdrs, names := valid()
|
||||
tc.mutate(hdrs, names)
|
||||
assert.Error(t, checkMsghdrX(hdrs, names, tc.n))
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestMsghdrXKernelRoundTrip(t *testing.T) {
|
||||
for _, v6 := range []bool{false, true} {
|
||||
t.Run(fmt.Sprintf("v6=%v", v6), func(t *testing.T) {
|
||||
// Loopback delivery goes through the dlil input thread, so the settle gives all three time to
|
||||
// queue and come back from one call, which is what exercises the stride.
|
||||
got := recvmsgXRoundTrip(t, v6, []int{1, 300, 1400}, 4, 50*time.Millisecond)
|
||||
assert.Equal(t, 3, got, "largest batch from one recvmsg_x call")
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Any burst, of any datagram lengths up to the kernel's maxdgram, into any number of headers, comes back in order
|
||||
// with every entry's fields intact, and headers past the returned count untouched.
|
||||
func FuzzMsghdrXKernelRoundTrip(f *testing.F) {
|
||||
f.Add(false, uint8(3), []byte{0, 1, 1, 44, 5, 120})
|
||||
f.Add(true, uint8(0), []byte{0, 0, 0x23, 0x29}) // one empty datagram, then one at MTU
|
||||
f.Add(false, uint8(1), []byte{0x23, 0x2a, 0x24, 0x00, 0}) // past MTU: cut to MTU, no MSG_TRUNC
|
||||
f.Add(true, uint8(recvBatch-1), bytes.Repeat([]byte{0x05, 0xdc}, recvBatch))
|
||||
|
||||
f.Fuzz(func(t *testing.T, v6 bool, spare uint8, sizes []byte) {
|
||||
// Two bytes per datagram, big-endian, folded into [0, maxdgram].
|
||||
var lens []int
|
||||
for i := 0; i+1 < len(sizes) && len(lens) < recvBatch; i += 2 {
|
||||
lens = append(lens, (int(sizes[i])<<8|int(sizes[i+1]))%(maxDgram+1))
|
||||
}
|
||||
if len(lens) == 0 {
|
||||
return
|
||||
}
|
||||
recvmsgXRoundTrip(t, v6, lens, 1+int(spare)%recvBatch, time.Millisecond)
|
||||
})
|
||||
}
|
||||
|
||||
// maxDgram is darwin's default net.inet.udp.maxdgram, the largest datagram a loopback sender may write.
|
||||
const maxDgram = 9216
|
||||
|
||||
// recvmsgXRoundTrip sends one datagram per entry of lens to a fresh loopback socket, drains them with recvmsg_x
|
||||
// into nh headers, and checks every field the kernel writes. Neighboring datagrams differ in sender, length and
|
||||
// fill byte, so no field can pass by reading a neighbor's value. It returns the largest batch one call returned.
|
||||
func recvmsgXRoundTrip(t *testing.T, v6 bool, lens []int, nh int, settle time.Duration) int {
|
||||
t.Helper()
|
||||
network, lo := "udp4", netip.MustParseAddr("127.0.0.1")
|
||||
if v6 {
|
||||
network, lo = "udp6", netip.IPv6Loopback()
|
||||
}
|
||||
rx, err := net.ListenUDP(network, net.UDPAddrFromAddrPort(netip.AddrPortFrom(lo, 0)))
|
||||
require.NoError(t, err)
|
||||
defer rx.Close()
|
||||
|
||||
txs := make([]*net.UDPConn, 3)
|
||||
for i := range txs {
|
||||
txs[i], err = net.DialUDP(network, nil, rx.LocalAddr().(*net.UDPAddr))
|
||||
require.NoError(t, err)
|
||||
defer txs[i].Close()
|
||||
}
|
||||
senders := make([]netip.AddrPort, len(lens))
|
||||
for i, l := range lens {
|
||||
tx := txs[i%len(txs)]
|
||||
senders[i] = tx.LocalAddr().(*net.UDPAddr).AddrPort()
|
||||
_, err := tx.Write(bytes.Repeat([]byte{byte(i + 1)}, l))
|
||||
require.NoError(t, err)
|
||||
}
|
||||
time.Sleep(settle)
|
||||
|
||||
// Namelen goes in as the v6 size on both families, so the v4 size coming back proves the kernel wrote it.
|
||||
const sentinel = 0xa5a5a5a5a5a5a5a5
|
||||
wantNamelen := uint32(unix.SizeofSockaddrInet4)
|
||||
if v6 {
|
||||
wantNamelen = unix.SizeofSockaddrInet6
|
||||
}
|
||||
bufs := make([][]byte, nh)
|
||||
names := make([]unix.RawSockaddrInet6, nh)
|
||||
iovs := make([]unix.Iovec, nh)
|
||||
hdrs := make([]msgx.Hdr, nh)
|
||||
for i := range hdrs {
|
||||
bufs[i] = make([]byte, MTU)
|
||||
iovs[i].Base = &bufs[i][0]
|
||||
iovs[i].SetLen(MTU)
|
||||
}
|
||||
|
||||
// A datagram dropped on loopback would otherwise block rc.Read forever.
|
||||
require.NoError(t, rx.SetReadDeadline(time.Now().Add(5*time.Second)))
|
||||
rc, err := rx.SyscallConn()
|
||||
require.NoError(t, err)
|
||||
largest := 0
|
||||
for next := 0; next < len(lens); {
|
||||
for i := range hdrs {
|
||||
clear(bufs[i])
|
||||
hdrs[i] = msgx.Hdr{
|
||||
Name: (*byte)(unsafe.Pointer(&names[i])),
|
||||
Namelen: unix.SizeofSockaddrInet6,
|
||||
Iov: &iovs[i],
|
||||
Iovlen: 1,
|
||||
Flags: -1,
|
||||
Datalen: sentinel,
|
||||
}
|
||||
}
|
||||
var n int
|
||||
var errno syscall.Errno
|
||||
require.NoError(t, rc.Read(func(fd uintptr) bool {
|
||||
n, errno = msgx.Recv(fd, hdrs[:nh], 0)
|
||||
return errno != unix.EAGAIN
|
||||
}), "received %d of %d datagrams", next, len(lens))
|
||||
require.Zero(t, errno)
|
||||
require.Positive(t, n)
|
||||
require.LessOrEqual(t, n, min(nh, len(lens)-next))
|
||||
largest = max(largest, n)
|
||||
require.NoError(t, checkMsghdrX(hdrs[:nh], names[:nh], n), "ListenOut would fall back on this batch")
|
||||
|
||||
for i := range n {
|
||||
d := next + i
|
||||
h := &hdrs[i]
|
||||
want := min(lens[d], MTU)
|
||||
require.EqualValues(t, want, h.Datalen, "datagram %d Datalen", d)
|
||||
require.Equal(t, wantNamelen, h.Namelen, "datagram %d Namelen", d)
|
||||
from, ok := sockaddrToAddrPort(&names[i])
|
||||
require.True(t, ok, "datagram %d family %d", d, names[i].Family)
|
||||
require.Equal(t, senders[d], from, "datagram %d sender", d)
|
||||
// Flags goes in as -1 and must come back 0. xnu's list receive (soreceive_m_list) never sets
|
||||
// MSG_TRUNC, so a datagram past MTU arrives silently cut to MTU, as recvfrom through net.UDPConn does.
|
||||
require.Zero(t, h.Flags, "datagram %d Flags", d)
|
||||
require.Equal(t, bytes.Repeat([]byte{byte(d + 1)}, want), bufs[i][:want], "datagram %d payload", d)
|
||||
if want < MTU {
|
||||
require.Zero(t, bufs[i][want], "datagram %d wrote past Datalen", d)
|
||||
}
|
||||
}
|
||||
for i := n; i < nh; i++ {
|
||||
require.EqualValues(t, uint64(sentinel), hdrs[i].Datalen, "spare header %d Datalen", i)
|
||||
require.EqualValues(t, unix.SizeofSockaddrInet6, hdrs[i].Namelen, "spare header %d Namelen", i)
|
||||
}
|
||||
next += n
|
||||
}
|
||||
return largest
|
||||
}
|
||||
@@ -1,150 +0,0 @@
|
||||
//go:build !e2e_testing
|
||||
|
||||
package udp
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// recvAll reads n datagrams from pc, or fails the test after a second without one.
|
||||
func recvAll(t *testing.T, pc net.PacketConn, n int) []string {
|
||||
t.Helper()
|
||||
var got []string
|
||||
buf := make([]byte, 64)
|
||||
for len(got) < n {
|
||||
require.NoError(t, pc.SetReadDeadline(time.Now().Add(time.Second)))
|
||||
l, _, err := pc.ReadFrom(buf)
|
||||
require.NoError(t, err, "after %d of %d datagrams", len(got), n)
|
||||
got = append(got, string(buf[:l]))
|
||||
}
|
||||
return got
|
||||
}
|
||||
|
||||
// A batch longer than sendBatch reaches each peer whole and in order through sendmsg_x, without falling
|
||||
// back to sendto: a run to one peer that spans two calls, then datagrams alternating between peers.
|
||||
func TestWriteBatchSendsEachToItsPeer(t *testing.T) {
|
||||
for _, tc := range []struct{ name, listen string }{
|
||||
{"v4", "127.0.0.1"},
|
||||
{"v6", "::1"},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.AddrPortFrom(netip.MustParseAddr(tc.listen), 0)})
|
||||
require.NoError(t, err)
|
||||
defer c.Close()
|
||||
|
||||
var peers [2]net.PacketConn
|
||||
var dsts [2]netip.AddrPort
|
||||
for i := range peers {
|
||||
peers[i], err = net.ListenPacket("udp", net.JoinHostPort(tc.listen, "0"))
|
||||
require.NoError(t, err)
|
||||
defer peers[i].Close()
|
||||
dsts[i] = netip.MustParseAddrPort(peers[i].LocalAddr().String())
|
||||
}
|
||||
|
||||
const total = sendBatch*2 + 5
|
||||
bufs := make([][]byte, total)
|
||||
addrs := make([]netip.AddrPort, total)
|
||||
var want [2][]string
|
||||
for i := range bufs {
|
||||
bufs[i] = fmt.Appendf(nil, "pkt-%03d", i)
|
||||
p := i % 2
|
||||
if i < sendBatch+6 {
|
||||
p = 0
|
||||
}
|
||||
addrs[i] = dsts[p]
|
||||
want[p] = append(want[p], string(bufs[i]))
|
||||
}
|
||||
|
||||
n, err := c.WriteBatch(bufs, addrs)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, total, n)
|
||||
assert.False(t, c.(*StdConn).noSendmsgX.Load(), "fell back to sendto")
|
||||
for i := range peers {
|
||||
assert.Equal(t, want[i], recvAll(t, peers[i], len(want[i])))
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Destinations that can't be sent to cost only their own packets: an IPv6 peer on an IPv4 socket is
|
||||
// skipped before the call, and a broadcast address without SO_BROADCAST is refused by the kernel
|
||||
// mid-batch. Neither stops the packets around it, delivers any twice, or turns sendmsg_x off.
|
||||
func TestWriteBatchSkipsUnsendableDestinations(t *testing.T) {
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0")})
|
||||
require.NoError(t, err)
|
||||
defer c.Close()
|
||||
|
||||
peer, err := net.ListenPacket("udp", "127.0.0.1:0")
|
||||
require.NoError(t, err)
|
||||
defer peer.Close()
|
||||
good := netip.MustParseAddrPort(peer.LocalAddr().String())
|
||||
bcast := netip.AddrPortFrom(netip.MustParseAddr("255.255.255.255"), good.Port())
|
||||
v6 := netip.MustParseAddrPort("[::1]:4242")
|
||||
|
||||
addrs := []netip.AddrPort{good, bcast, bcast, good, v6, good, bcast}
|
||||
bufs := make([][]byte, len(addrs))
|
||||
for i := range bufs {
|
||||
bufs[i] = fmt.Appendf(nil, "pkt-%d", i)
|
||||
}
|
||||
|
||||
n, err := c.WriteBatch(bufs, addrs)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, 3, n)
|
||||
assert.False(t, c.(*StdConn).noSendmsgX.Load(), "fell back to sendto")
|
||||
assert.Equal(t, []string{"pkt-0", "pkt-3", "pkt-5"}, recvAll(t, peer, 3))
|
||||
require.NoError(t, peer.SetReadDeadline(time.Now().Add(100*time.Millisecond)))
|
||||
_, _, err = peer.ReadFrom(make([]byte, 64))
|
||||
assert.Error(t, err, "a datagram arrived twice")
|
||||
}
|
||||
|
||||
// A datagram the kernel refuses as its own fault (EMSGSIZE here, as ENOBUFS would be under a full
|
||||
// interface queue) costs only itself, whether it fails after others in the same call (a short count) or
|
||||
// first (the errno alone): the rest of its run still arrives, in order, and sendmsg_x stays on.
|
||||
func TestWriteBatchLosesOnlyTheFailedDatagram(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
big int
|
||||
}{
|
||||
{"mid-call", 2},
|
||||
{"first", 0},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0")})
|
||||
require.NoError(t, err)
|
||||
defer c.Close()
|
||||
|
||||
peer, err := net.ListenPacket("udp", "127.0.0.1:0")
|
||||
require.NoError(t, err)
|
||||
defer peer.Close()
|
||||
dst := netip.MustParseAddrPort(peer.LocalAddr().String())
|
||||
|
||||
bufs := make([][]byte, 5)
|
||||
addrs := make([]netip.AddrPort, len(bufs))
|
||||
var want []string
|
||||
for i := range bufs {
|
||||
addrs[i] = dst
|
||||
if i == tc.big {
|
||||
// Past the 65535-byte IP datagram limit, so the kernel can only refuse it.
|
||||
bufs[i] = make([]byte, 70000)
|
||||
continue
|
||||
}
|
||||
bufs[i] = fmt.Appendf(nil, "pkt-%d", i)
|
||||
want = append(want, string(bufs[i]))
|
||||
}
|
||||
|
||||
n, err := c.WriteBatch(bufs, addrs)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, len(want), n)
|
||||
assert.False(t, c.(*StdConn).noSendmsgX.Load(), "fell back to sendto")
|
||||
assert.Equal(t, want, recvAll(t, peer, len(want)))
|
||||
})
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user