mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-16 07:36:52 +01:00
Compare commits
14
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
f3b76703ae | ||
|
|
fc0dbfec4c | ||
|
|
ca69a0613b | ||
|
|
84a26846f4 | ||
|
|
317388e37d | ||
|
|
06fd191367 | ||
|
|
3f392883ca | ||
|
|
30cf2bbe6c | ||
|
|
11b04517f3 | ||
|
|
610ba57105 | ||
|
|
9e96894bd7 | ||
|
|
14f80450fb | ||
|
|
641d1fb703 | ||
|
|
11a4298c36 |
No files matched your search
@@ -1,2 +0,0 @@
|
||||
# Goldens are compared byte for byte, so they must come out of git the way they went in.
|
||||
*.golden -text
|
||||
@@ -14,7 +14,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: Build
|
||||
@@ -40,7 +40,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: Build
|
||||
@@ -83,7 +83,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
# GitHub holds ARNs, not credentials, and ARNs outlive a rotation
|
||||
|
||||
@@ -34,7 +34,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: add hashicorp source
|
||||
@@ -66,7 +66,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: add hashicorp source
|
||||
@@ -92,7 +92,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
# WSL2 + Ubuntu so the smoke can run a real linux peer with its own
|
||||
|
||||
@@ -22,7 +22,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: Smoke Docker
|
||||
@@ -51,7 +51,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: build
|
||||
|
||||
@@ -22,7 +22,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: Install goimports
|
||||
@@ -42,7 +42,7 @@ jobs:
|
||||
- name: golangci-lint
|
||||
uses: golangci/golangci-lint-action@v9
|
||||
with:
|
||||
version: v2.14
|
||||
version: v2.12
|
||||
|
||||
test:
|
||||
name: Test ${{ matrix.name }}
|
||||
@@ -87,7 +87,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: Build
|
||||
@@ -132,7 +132,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.27'
|
||||
go-version: '1.26'
|
||||
check-latest: true
|
||||
|
||||
- name: Build ${{ matrix.name }}
|
||||
|
||||
@@ -7,31 +7,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
### Changed
|
||||
|
||||
- A tunnel whose remote becomes unreachable, such as an IPv6 remote after moving to a network without IPv6, now
|
||||
moves to another of the peer's addresses within a round trip or two instead of waiting 20-35s to be torn down
|
||||
and rehandshaked. When a send fails because there is no route to the remote, the tunnel sends a test packet to
|
||||
every other address it knows for the peer and asks the lighthouse to have the peer punch its new address.
|
||||
Whichever path answers carries the tunnel. With `punchy.punch` enabled, idle tunnels notice on their next
|
||||
keepalive punch. An idle tunnel whose remote is unreachable and none of whose other addresses answer is now
|
||||
torn down by the connection manager rather than left in place. Not yet effective for relayed traffic or on
|
||||
Windows with the default RIO backend.
|
||||
|
||||
### Removed
|
||||
|
||||
- The SSH debug server's `start-cpu-profile`, `stop-cpu-profile`, `save-heap-profile`, `save-mutex-profile`, and
|
||||
`mutex-profile-fraction` commands, and `sshd.sandbox_dir`, which is now ignored if set.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Signing a v2 certificate with an empty name, a name longer than 253 bytes, or an empty group now fails.
|
||||
These certificates were signed successfully but could not be loaded.
|
||||
- `create-tunnel -address <ip:port>` panicked on a nil RemoteList and, over the ssh debug server, took nebula
|
||||
down with it. A hostinfo returned by StartHandshake had no RemoteList until the handshake loop's first
|
||||
pass attached one, and `create-tunnel -address` set the remote before that. The list is now attached when
|
||||
the handshake starts, so a pending hostinfo never exists without one.
|
||||
|
||||
## [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.
|
||||
|
||||
+1
-10
@@ -389,16 +389,7 @@ func (c *certificateV2) fromTBSCertificate(t *TBSCertificate) error {
|
||||
}
|
||||
|
||||
func (c *certificateV2) validate() error {
|
||||
// Mirror the name and group rules in unmarshalDetails so signing fails instead of producing an unparseable certificate
|
||||
if c.details.name == "" || len(c.details.name) > MaxNameLength {
|
||||
return NewErrInvalidCertificateProperties("name must be between 1 and %d bytes", MaxNameLength)
|
||||
}
|
||||
|
||||
for _, group := range c.details.groups {
|
||||
if group == "" {
|
||||
return NewErrInvalidCertificateProperties("groups may not be empty")
|
||||
}
|
||||
}
|
||||
// Empty names are allowed
|
||||
|
||||
if len(c.publicKey) == 0 {
|
||||
return ErrInvalidPublicKey
|
||||
|
||||
@@ -6,7 +6,6 @@ import (
|
||||
"crypto/elliptic"
|
||||
"crypto/rand"
|
||||
"net/netip"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
@@ -136,47 +135,3 @@ func TestCertificate_SignP256_AlwaysNormalized(t *testing.T) {
|
||||
assert.True(t, normie)
|
||||
}
|
||||
}
|
||||
|
||||
func TestCertificateV2_SignRejectsUnparseable(t *testing.T) {
|
||||
_, priv, err := ed25519.GenerateKey(rand.Reader)
|
||||
require.NoError(t, err)
|
||||
var invalid *ErrInvalidCertificateProperties
|
||||
|
||||
newTBS := func() TBSCertificate {
|
||||
return TBSCertificate{
|
||||
Version: Version2,
|
||||
Name: "testing",
|
||||
Networks: []netip.Prefix{mustParsePrefixUnmapped("10.1.1.1/24")},
|
||||
Groups: []string{"test-group1"},
|
||||
NotBefore: time.Now().Add(-time.Minute),
|
||||
NotAfter: time.Now().Add(time.Minute),
|
||||
PublicKey: []byte("1234567890abcedfghij1234567890ab"),
|
||||
Curve: Curve_CURVE25519,
|
||||
IsCA: true,
|
||||
}
|
||||
}
|
||||
|
||||
tbs := newTBS()
|
||||
tbs.Name = strings.Repeat("a", MaxNameLength)
|
||||
c, err := tbs.Sign(nil, Curve_CURVE25519, priv)
|
||||
require.NoError(t, err)
|
||||
b, err := c.Marshal()
|
||||
require.NoError(t, err)
|
||||
_, err = unmarshalCertificateV2(b, nil, Curve_CURVE25519)
|
||||
require.NoError(t, err)
|
||||
|
||||
tbs = newTBS()
|
||||
tbs.Name = strings.Repeat("a", MaxNameLength+1)
|
||||
_, err = tbs.Sign(nil, Curve_CURVE25519, priv)
|
||||
require.ErrorAs(t, err, &invalid)
|
||||
|
||||
tbs = newTBS()
|
||||
tbs.Name = ""
|
||||
_, err = tbs.Sign(nil, Curve_CURVE25519, priv)
|
||||
require.ErrorAs(t, err, &invalid)
|
||||
|
||||
tbs = newTBS()
|
||||
tbs.Groups = []string{"test-group1", ""}
|
||||
_, err = tbs.Sign(nil, Curve_CURVE25519, priv)
|
||||
require.ErrorAs(t, err, &invalid)
|
||||
}
|
||||
@@ -85,10 +85,9 @@ func main() {
|
||||
fmt.Printf("failed to apply logging config: %s", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
if err := logging.ApplyConfig(l, c); err != nil {
|
||||
l.Error("Failed to reconfigure logger on reload", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
|
||||
@@ -34,10 +34,9 @@ func (p *program) Start(s service.Service) error {
|
||||
if err := logging.ApplyConfig(l, c); err != nil {
|
||||
return fmt.Errorf("failed to apply logging config: %s", err)
|
||||
}
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
if err := logging.ApplyConfig(l, c); err != nil {
|
||||
l.Error("Failed to reconfigure logger on reload", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
|
||||
+1
-2
@@ -71,10 +71,9 @@ func main() {
|
||||
fmt.Printf("failed to apply logging config: %s", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
if err := logging.ApplyConfig(l, c); err != nil {
|
||||
l.Error("Failed to reconfigure logger on reload", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
|
||||
-710
@@ -1,710 +0,0 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/json"
|
||||
"flag"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"maps"
|
||||
"net/netip"
|
||||
"sort"
|
||||
"strings"
|
||||
|
||||
"github.com/slackhq/nebula/commands"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/logging"
|
||||
)
|
||||
|
||||
// The commands nebula serves. attachCommands builds the one registry every surface
|
||||
// reads. See the commands package for what a Command is.
|
||||
|
||||
type listHostMapFlags struct {
|
||||
Json bool
|
||||
Pretty bool
|
||||
ByIndex bool
|
||||
}
|
||||
|
||||
// listHostMapFlagSet is the flag set list-hostmap and list-pending-hostmap share.
|
||||
func listHostMapFlagSet() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := listHostMapFlags{}
|
||||
fl.BoolVar(&s.Json, "json", false, "outputs as json with more information")
|
||||
fl.BoolVar(&s.Pretty, "pretty", false, "pretty prints json, assumes -json")
|
||||
fl.BoolVar(&s.ByIndex, "by-index", false, "gets all hosts in the hostmap from the index table")
|
||||
return fl, &s
|
||||
}
|
||||
|
||||
type printCertFlags struct {
|
||||
Json bool
|
||||
Pretty bool
|
||||
Raw bool
|
||||
}
|
||||
|
||||
type printTunnelFlags struct {
|
||||
Pretty bool
|
||||
}
|
||||
|
||||
type changeRemoteFlags struct {
|
||||
Address string
|
||||
}
|
||||
|
||||
type closeTunnelFlags struct {
|
||||
LocalOnly bool
|
||||
}
|
||||
|
||||
type createTunnelFlags struct {
|
||||
Address string
|
||||
}
|
||||
|
||||
type deviceInfoFlags struct {
|
||||
Json bool
|
||||
Pretty bool
|
||||
}
|
||||
|
||||
func attachCommands(l *slog.Logger, c *config.C, reg *commands.Registry, f *Interface) {
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.ListHostmap,
|
||||
ShortDescription: "List all known previously connected hosts",
|
||||
Flags: listHostMapFlagSet,
|
||||
Callback: func(fs any, a []string, w commands.StringWriter) error {
|
||||
return listHostMapCommand(f.hostMap, fs, w)
|
||||
},
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.ListPendingHostmap,
|
||||
ShortDescription: "List all handshaking hosts",
|
||||
Flags: listHostMapFlagSet,
|
||||
Callback: func(fs any, a []string, w commands.StringWriter) error {
|
||||
return listHostMapCommand(f.handshakeManager, fs, w)
|
||||
},
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.ListLighthouseAddrmap,
|
||||
ShortDescription: "List all lighthouse map entries",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := listHostMapFlags{}
|
||||
fl.BoolVar(&s.Json, "json", false, "outputs as json with more information")
|
||||
fl.BoolVar(&s.Pretty, "pretty", false, "pretty prints json, assumes -json")
|
||||
return fl, &s
|
||||
},
|
||||
Callback: func(fs any, a []string, w commands.StringWriter) error {
|
||||
return listLighthouseAddrmapCommand(f.lightHouse, fs, w)
|
||||
},
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.Reload,
|
||||
ShortDescription: "Reloads configuration from disk, same as sending HUP to the process",
|
||||
Callback: func(fs any, a []string, w commands.StringWriter) error {
|
||||
return reloadCommand(l, c, w)
|
||||
},
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.LogLevel,
|
||||
ShortDescription: "Gets or sets the current log level",
|
||||
Callback: func(fs any, a []string, w commands.StringWriter) error {
|
||||
return logLevelCommand(l, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.LogFormat,
|
||||
ShortDescription: "Gets or sets the current log format",
|
||||
Callback: func(fs any, a []string, w commands.StringWriter) error {
|
||||
return logFormatCommand(l, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.Version,
|
||||
ShortDescription: "Prints the currently running version of nebula",
|
||||
Callback: func(fs any, a []string, w commands.StringWriter) error {
|
||||
return versionCommand(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.DeviceInfo,
|
||||
ShortDescription: "Prints information about the network device.",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := deviceInfoFlags{}
|
||||
fl.BoolVar(&s.Json, "json", false, "outputs as json with more information")
|
||||
fl.BoolVar(&s.Pretty, "pretty", false, "pretty prints json, assumes -json")
|
||||
return fl, &s
|
||||
},
|
||||
Callback: func(fs any, a []string, w commands.StringWriter) error {
|
||||
return deviceInfoCommand(f, fs, w)
|
||||
},
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.PrintCert,
|
||||
ShortDescription: "Prints the current certificate being used or the certificate for the provided vpn addr",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := printCertFlags{}
|
||||
fl.BoolVar(&s.Json, "json", false, "outputs as json")
|
||||
fl.BoolVar(&s.Pretty, "pretty", false, "pretty prints json, assumes -json")
|
||||
fl.BoolVar(&s.Raw, "raw", false, "raw prints the PEM encoded certificate, not compatible with -json or -pretty")
|
||||
return fl, &s
|
||||
},
|
||||
Callback: func(fs any, a []string, w commands.StringWriter) error {
|
||||
return printCertCommand(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.PrintTunnel,
|
||||
ShortDescription: "Prints json details about a tunnel for the provided vpn addr",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := printTunnelFlags{}
|
||||
fl.BoolVar(&s.Pretty, "pretty", false, "pretty prints json")
|
||||
return fl, &s
|
||||
},
|
||||
Callback: func(fs any, a []string, w commands.StringWriter) error {
|
||||
return printTunnelCommand(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.PrintRelays,
|
||||
ShortDescription: "Prints json details about all relay info",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := printTunnelFlags{}
|
||||
fl.BoolVar(&s.Pretty, "pretty", false, "pretty prints json")
|
||||
return fl, &s
|
||||
},
|
||||
Callback: func(fs any, a []string, w commands.StringWriter) error {
|
||||
return printRelaysCommand(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.ChangeRemote,
|
||||
ShortDescription: "Changes the remote address used in the tunnel for the provided vpn addr",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := changeRemoteFlags{}
|
||||
fl.StringVar(&s.Address, "address", "", "The new remote address, ip:port")
|
||||
return fl, &s
|
||||
},
|
||||
Callback: func(fs any, a []string, w commands.StringWriter) error {
|
||||
return changeRemoteCommand(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.CloseTunnel,
|
||||
ShortDescription: "Closes a tunnel for the provided vpn addr",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := closeTunnelFlags{}
|
||||
fl.BoolVar(&s.LocalOnly, "local-only", false, "Disables notifying the remote that the tunnel is shutting down")
|
||||
return fl, &s
|
||||
},
|
||||
Callback: func(fs any, a []string, w commands.StringWriter) error {
|
||||
return closeTunnelCommand(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.CreateTunnel,
|
||||
ShortDescription: "Creates a tunnel for the provided vpn address",
|
||||
Help: "The lighthouses will be queried for real addresses but you can provide one as well.",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := createTunnelFlags{}
|
||||
fl.StringVar(&s.Address, "address", "", "Optionally provide a real remote address, ip:port ")
|
||||
return fl, &s
|
||||
},
|
||||
Callback: func(fs any, a []string, w commands.StringWriter) error {
|
||||
return createTunnelCommand(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.QueryLighthouse,
|
||||
ShortDescription: "Query the lighthouses for the provided vpn address",
|
||||
Help: "This command is asynchronous. Only currently known udp addresses will be printed.",
|
||||
Callback: func(fs any, a []string, w commands.StringWriter) error {
|
||||
return queryLighthouseCommand(f, fs, a, w)
|
||||
},
|
||||
})
|
||||
}
|
||||
|
||||
func listHostMapCommand(hl controlHostLister, a any, w commands.StringWriter) error {
|
||||
fs, ok := a.(*listHostMapFlags)
|
||||
if !ok {
|
||||
return fmt.Errorf("internal error: expected *listHostMapFlags but was %T", a)
|
||||
}
|
||||
|
||||
var hm []ControlHostInfo
|
||||
if fs.ByIndex {
|
||||
hm = listHostMapIndexes(hl)
|
||||
} else {
|
||||
hm = listHostMapHosts(hl)
|
||||
}
|
||||
|
||||
sort.Slice(hm, func(i, j int) bool {
|
||||
return hm[i].VpnAddrs[0].Compare(hm[j].VpnAddrs[0]) < 0
|
||||
})
|
||||
|
||||
if fs.Json || fs.Pretty {
|
||||
js := json.NewEncoder(w.GetWriter())
|
||||
if fs.Pretty {
|
||||
js.SetIndent("", " ")
|
||||
}
|
||||
|
||||
if err := js.Encode(hm); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
} else {
|
||||
for _, v := range hm {
|
||||
err := w.WriteLine(fmt.Sprintf("%s: %s", v.VpnAddrs, v.RemoteAddrs))
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
func listLighthouseAddrmapCommand(lightHouse *LightHouse, a any, w commands.StringWriter) error {
|
||||
fs, ok := a.(*listHostMapFlags)
|
||||
if !ok {
|
||||
return fmt.Errorf("internal error: expected *listHostMapFlags but was %T", a)
|
||||
}
|
||||
|
||||
type lighthouseInfo struct {
|
||||
VpnAddr string `json:"vpnAddr"`
|
||||
Addrs *CacheMap `json:"addrs"`
|
||||
}
|
||||
|
||||
lightHouse.RLock()
|
||||
addrMap := make([]lighthouseInfo, len(lightHouse.addrMap))
|
||||
x := 0
|
||||
for k, v := range lightHouse.addrMap {
|
||||
addrMap[x] = lighthouseInfo{
|
||||
VpnAddr: k.String(),
|
||||
Addrs: v.CopyCache(),
|
||||
}
|
||||
x++
|
||||
}
|
||||
lightHouse.RUnlock()
|
||||
|
||||
sort.Slice(addrMap, func(i, j int) bool {
|
||||
return strings.Compare(addrMap[i].VpnAddr, addrMap[j].VpnAddr) < 0
|
||||
})
|
||||
|
||||
if fs.Json || fs.Pretty {
|
||||
js := json.NewEncoder(w.GetWriter())
|
||||
if fs.Pretty {
|
||||
js.SetIndent("", " ")
|
||||
}
|
||||
|
||||
if err := js.Encode(addrMap); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
} else {
|
||||
for _, v := range addrMap {
|
||||
b, err := json.Marshal(v.Addrs)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
err = w.WriteLine(fmt.Sprintf("%s: %s", v.VpnAddr, string(b)))
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// parseVpnAddr parses the vpn address a command takes as its first operand, failing to w
|
||||
// when there is none or it does not parse. noun is how the command's messages name it,
|
||||
// "vpn address" or "vpn addr", which the output golden pins per command.
|
||||
func parseVpnAddr(a []string, noun string, w commands.StringWriter) (netip.Addr, error) {
|
||||
if len(a) == 0 {
|
||||
return netip.Addr{}, commands.Fail(w, "No vpn address was provided")
|
||||
}
|
||||
|
||||
vpnAddr, err := netip.ParseAddr(a[0])
|
||||
if err != nil {
|
||||
return netip.Addr{}, commands.Fail(w, fmt.Sprintf("The provided %s could not be parsed: %s", noun, a[0]))
|
||||
}
|
||||
|
||||
return vpnAddr, nil
|
||||
}
|
||||
|
||||
func versionCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
|
||||
return w.WriteLine(ifce.version)
|
||||
}
|
||||
|
||||
func queryLighthouseCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
|
||||
vpnAddr, err := parseVpnAddr(a, "vpn address", w)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
var cm *CacheMap
|
||||
rl := ifce.lightHouse.Query(vpnAddr)
|
||||
if rl != nil {
|
||||
cm = rl.CopyCache()
|
||||
}
|
||||
return json.NewEncoder(w.GetWriter()).Encode(cm)
|
||||
}
|
||||
|
||||
func closeTunnelCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
|
||||
flags, ok := fs.(*closeTunnelFlags)
|
||||
if !ok {
|
||||
return fmt.Errorf("internal error: expected *closeTunnelFlags but was %T", fs)
|
||||
}
|
||||
|
||||
vpnAddr, err := parseVpnAddr(a, "vpn address", w)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
|
||||
if hostInfo == nil {
|
||||
return commands.Fail(w, fmt.Sprintf("Could not find tunnel for vpn address: %v", a[0]))
|
||||
}
|
||||
|
||||
if !flags.LocalOnly {
|
||||
ifce.sendCloseTunnel(hostInfo)
|
||||
}
|
||||
|
||||
ifce.closeTunnel(hostInfo)
|
||||
return w.WriteLine("Closed")
|
||||
}
|
||||
|
||||
func createTunnelCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
|
||||
flags, ok := fs.(*createTunnelFlags)
|
||||
if !ok {
|
||||
return fmt.Errorf("internal error: expected *createTunnelFlags but was %T", fs)
|
||||
}
|
||||
|
||||
vpnAddr, err := parseVpnAddr(a, "vpn address", w)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
|
||||
if hostInfo != nil {
|
||||
return commands.Fail(w, "Tunnel already exists")
|
||||
}
|
||||
|
||||
hostInfo = ifce.handshakeManager.QueryVpnAddr(vpnAddr)
|
||||
if hostInfo != nil {
|
||||
return commands.Fail(w, "Tunnel already handshaking")
|
||||
}
|
||||
|
||||
var addr netip.AddrPort
|
||||
if flags.Address != "" {
|
||||
addr, err = netip.ParseAddrPort(flags.Address)
|
||||
if err != nil {
|
||||
return commands.Fail(w, "Address could not be parsed")
|
||||
}
|
||||
}
|
||||
|
||||
// Set the remote from the callback, which StartHandshake runs under the handshake manager lock
|
||||
// before the hostinfo reaches the handshake loop or the static-host trigger, so the address is
|
||||
// in the RemoteList before the first handshake is sent.
|
||||
ifce.handshakeManager.StartHandshake(vpnAddr, func(hh *HandshakeHostInfo) {
|
||||
if addr.IsValid() {
|
||||
hh.hostinfo.SetRemote(addr)
|
||||
}
|
||||
})
|
||||
|
||||
return w.WriteLine("Created")
|
||||
}
|
||||
|
||||
func changeRemoteCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
|
||||
flags, ok := fs.(*changeRemoteFlags)
|
||||
if !ok {
|
||||
return fmt.Errorf("internal error: expected *changeRemoteFlags but was %T", fs)
|
||||
}
|
||||
|
||||
vpnAddr, err := parseVpnAddr(a, "vpn address", w)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
if flags.Address == "" {
|
||||
return commands.Fail(w, "No address was provided")
|
||||
}
|
||||
|
||||
addr, err := netip.ParseAddrPort(flags.Address)
|
||||
if err != nil {
|
||||
return commands.Fail(w, "Address could not be parsed")
|
||||
}
|
||||
|
||||
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
|
||||
if hostInfo == nil {
|
||||
return commands.Fail(w, fmt.Sprintf("Could not find tunnel for vpn address: %v", a[0]))
|
||||
}
|
||||
|
||||
hostInfo.SetRemote(addr)
|
||||
return w.WriteLine("Changed")
|
||||
}
|
||||
|
||||
func logLevelCommand(l *slog.Logger, fs any, a []string, w commands.StringWriter) error {
|
||||
ctrl, ok := l.Handler().(interface {
|
||||
GetLevel() slog.Level
|
||||
SetLevel(slog.Level)
|
||||
})
|
||||
if !ok {
|
||||
return commands.Fail(w, "Log level is not reconfigurable on this logger")
|
||||
}
|
||||
|
||||
if len(a) == 0 {
|
||||
return w.WriteLine(fmt.Sprintf("Log level is: %s", logging.LevelName(ctrl.GetLevel())))
|
||||
}
|
||||
|
||||
level, err := logging.ParseLevel(strings.ToLower(a[0]))
|
||||
if err != nil {
|
||||
return commands.Fail(w, fmt.Sprintf("Unknown log level %s. Possible log levels: trace, debug, info, warn, error", a))
|
||||
}
|
||||
|
||||
ctrl.SetLevel(level)
|
||||
return w.WriteLine(fmt.Sprintf("Log level is: %s", logging.LevelName(ctrl.GetLevel())))
|
||||
}
|
||||
|
||||
func logFormatCommand(l *slog.Logger, fs any, a []string, w commands.StringWriter) error {
|
||||
ctrl, ok := l.Handler().(interface {
|
||||
GetFormat() string
|
||||
SetFormat(string) error
|
||||
})
|
||||
if !ok {
|
||||
return commands.Fail(w, "Log format is not reconfigurable on this logger")
|
||||
}
|
||||
|
||||
if len(a) == 0 {
|
||||
return w.WriteLine(fmt.Sprintf("Log format is: %s", ctrl.GetFormat()))
|
||||
}
|
||||
|
||||
if err := ctrl.SetFormat(strings.ToLower(a[0])); err != nil {
|
||||
return commands.Fail(w, fmt.Sprintf("Unable to set log format: %s", err))
|
||||
}
|
||||
return w.WriteLine(fmt.Sprintf("Log format is: %s", ctrl.GetFormat()))
|
||||
}
|
||||
|
||||
func printCertCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
|
||||
args, ok := fs.(*printCertFlags)
|
||||
if !ok {
|
||||
return fmt.Errorf("internal error: expected *printCertFlags but was %T", fs)
|
||||
}
|
||||
|
||||
cert := ifce.pki.getCertState().GetDefaultCertificate()
|
||||
if len(a) > 0 {
|
||||
vpnAddr, err := parseVpnAddr(a, "vpn addr", w)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
|
||||
if hostInfo == nil {
|
||||
return commands.Fail(w, fmt.Sprintf("Could not find tunnel for vpn addr: %v", a[0]))
|
||||
}
|
||||
|
||||
cert = hostInfo.GetCert().Certificate
|
||||
}
|
||||
|
||||
if args.Json || args.Pretty {
|
||||
b, err := cert.MarshalJSON()
|
||||
if err != nil {
|
||||
return commands.Fail(w, fmt.Sprintf("Unable to marshal the certificate: %s", err))
|
||||
}
|
||||
|
||||
if args.Pretty {
|
||||
buf := new(bytes.Buffer)
|
||||
if err := json.Indent(buf, b, "", " "); err != nil {
|
||||
return commands.Fail(w, fmt.Sprintf("Unable to marshal the certificate: %s", err))
|
||||
}
|
||||
b = buf.Bytes()
|
||||
}
|
||||
|
||||
return w.WriteBytes(b)
|
||||
}
|
||||
|
||||
if args.Raw {
|
||||
b, err := cert.MarshalPEM()
|
||||
if err != nil {
|
||||
return commands.Fail(w, fmt.Sprintf("Unable to marshal the certificate: %s", err))
|
||||
}
|
||||
|
||||
return w.WriteBytes(b)
|
||||
}
|
||||
|
||||
return w.WriteLine(cert.String())
|
||||
}
|
||||
|
||||
func printRelaysCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
|
||||
args, ok := fs.(*printTunnelFlags)
|
||||
if !ok {
|
||||
return fmt.Errorf("internal error: expected *printTunnelFlags but was %T", fs)
|
||||
}
|
||||
|
||||
ifce.hostMap.RLock()
|
||||
relays := maps.Clone(ifce.hostMap.Relays)
|
||||
ifce.hostMap.RUnlock()
|
||||
|
||||
type RelayFor struct {
|
||||
Error string `json:",omitempty"`
|
||||
Type string
|
||||
State string
|
||||
PeerAddr netip.Addr
|
||||
LocalIndex uint32
|
||||
RemoteIndex uint32
|
||||
RelayedThrough []netip.Addr
|
||||
}
|
||||
|
||||
type RelayOutput struct {
|
||||
NebulaAddr netip.Addr
|
||||
RelayForAddrs []RelayFor
|
||||
}
|
||||
|
||||
type CmdOutput struct {
|
||||
Relays []*RelayOutput
|
||||
}
|
||||
|
||||
co := CmdOutput{}
|
||||
|
||||
enc := json.NewEncoder(w.GetWriter())
|
||||
|
||||
if args.Pretty {
|
||||
enc.SetIndent("", " ")
|
||||
}
|
||||
|
||||
for k, v := range relays {
|
||||
ro := RelayOutput{NebulaAddr: v.vpnAddrs[0]}
|
||||
co.Relays = append(co.Relays, &ro)
|
||||
relayHI := ifce.hostMap.QueryVpnAddr(v.vpnAddrs[0])
|
||||
if relayHI == nil {
|
||||
ro.RelayForAddrs = append(ro.RelayForAddrs, RelayFor{Error: "could not find hostinfo"})
|
||||
continue
|
||||
}
|
||||
for _, vpnAddr := range relayHI.relayState.CopyRelayForIps() {
|
||||
rf := RelayFor{}
|
||||
r, ok := relayHI.relayState.GetRelayForByAddr(vpnAddr)
|
||||
if ok {
|
||||
t := ""
|
||||
switch r.Type {
|
||||
case ForwardingType:
|
||||
t = "forwarding"
|
||||
case TerminalType:
|
||||
t = "terminal"
|
||||
default:
|
||||
t = "unknown"
|
||||
}
|
||||
|
||||
s := ""
|
||||
switch r.State {
|
||||
case Requested:
|
||||
s = "requested"
|
||||
case Established:
|
||||
s = "established"
|
||||
default:
|
||||
s = "unknown"
|
||||
}
|
||||
|
||||
rf.LocalIndex = r.LocalIndex
|
||||
rf.RemoteIndex = r.RemoteIndex
|
||||
rf.PeerAddr = r.PeerAddr
|
||||
rf.Type = t
|
||||
rf.State = s
|
||||
if rf.LocalIndex != k {
|
||||
rf.Error = fmt.Sprintf("hostmap LocalIndex '%v' does not match RelayState LocalIndex", k)
|
||||
}
|
||||
}
|
||||
relayedHI := ifce.hostMap.QueryVpnAddr(vpnAddr)
|
||||
if relayedHI != nil {
|
||||
rf.RelayedThrough = append(rf.RelayedThrough, relayedHI.relayState.CopyRelayIps()...)
|
||||
}
|
||||
|
||||
ro.RelayForAddrs = append(ro.RelayForAddrs, rf)
|
||||
}
|
||||
}
|
||||
return enc.Encode(co)
|
||||
}
|
||||
|
||||
func printTunnelCommand(ifce *Interface, fs any, a []string, w commands.StringWriter) error {
|
||||
args, ok := fs.(*printTunnelFlags)
|
||||
if !ok {
|
||||
return fmt.Errorf("internal error: expected *printTunnelFlags but was %T", fs)
|
||||
}
|
||||
|
||||
vpnAddr, err := parseVpnAddr(a, "vpn addr", w)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
|
||||
if hostInfo == nil {
|
||||
return commands.Fail(w, fmt.Sprintf("Could not find tunnel for vpn addr: %v", a[0]))
|
||||
}
|
||||
|
||||
enc := json.NewEncoder(w.GetWriter())
|
||||
if args.Pretty {
|
||||
enc.SetIndent("", " ")
|
||||
}
|
||||
|
||||
return enc.Encode(copyHostInfo(hostInfo, ifce.hostMap.GetPreferredRanges()))
|
||||
}
|
||||
|
||||
func deviceInfoCommand(ifce *Interface, fs any, w commands.StringWriter) error {
|
||||
flags, ok := fs.(*deviceInfoFlags)
|
||||
if !ok {
|
||||
return fmt.Errorf("internal error: expected flags to be deviceInfoFlags but was %+v", fs)
|
||||
}
|
||||
|
||||
data := struct {
|
||||
Name string `json:"name"`
|
||||
Cidr []netip.Prefix `json:"cidr"`
|
||||
}{
|
||||
Name: ifce.inside.Name(),
|
||||
Cidr: make([]netip.Prefix, len(ifce.inside.Networks())),
|
||||
}
|
||||
|
||||
copy(data.Cidr, ifce.inside.Networks())
|
||||
|
||||
if flags.Json || flags.Pretty {
|
||||
js := json.NewEncoder(w.GetWriter())
|
||||
if flags.Pretty {
|
||||
js.SetIndent("", " ")
|
||||
}
|
||||
|
||||
return js.Encode(data)
|
||||
} else {
|
||||
return w.WriteLine(fmt.Sprintf("name=%v cidr=%v", data.Name, data.Cidr))
|
||||
}
|
||||
}
|
||||
|
||||
// reloadCommand reloads the config and writes the result to the client. It reloads even if the client has gone away
|
||||
func reloadCommand(l *slog.Logger, c *config.C, w commands.StringWriter) error {
|
||||
writeErr := w.WriteLine("Reloading config")
|
||||
res := c.ReloadConfig()
|
||||
res.Log(l)
|
||||
if err := w.WriteLine(res.String()); writeErr == nil {
|
||||
writeErr = err
|
||||
}
|
||||
if writeErr != nil {
|
||||
return writeErr
|
||||
}
|
||||
if res.Err != nil || res.Failed {
|
||||
return &commands.Failure{Msg: res.String()}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
@@ -1,83 +0,0 @@
|
||||
package commands
|
||||
|
||||
import (
|
||||
"flag"
|
||||
)
|
||||
|
||||
// CommandFlags is called before help or command execution to parse command line flags.
|
||||
// It should return a flag.FlagSet instance and a pointer to the struct that will contain parsed flags
|
||||
type CommandFlags func() (*flag.FlagSet, any)
|
||||
|
||||
// CommandCallback is called when your command should execute.
|
||||
// fs will be a pointer to the struct provided by Command.Flags callback, if there was one. -h and -help are reserved
|
||||
// and handled automatically for you.
|
||||
// a will be any unconsumed arguments, if no Command.Flags was available this will be all the flags passed in.
|
||||
// w is the writer to use when sending messages back to the client.
|
||||
// An error returned by the callback is handed back to whoever dispatched the command, which reports a failure: exit
|
||||
// status 1 over ssh. The error is not shown to the user. For a failure the user caused or can act on, write the
|
||||
// message and return it as a *Failure, which Fail does in one step; the surface then reports the failure without
|
||||
// logging what the user was already told. Any other error is logged by the surface as well.
|
||||
type CommandCallback func(fs any, a []string, w StringWriter) error
|
||||
|
||||
type Command struct {
|
||||
Name Name
|
||||
ShortDescription string
|
||||
Help string
|
||||
|
||||
Flags CommandFlags
|
||||
Callback CommandCallback
|
||||
}
|
||||
|
||||
// Failure is the error a command returns for a failure it has already explained to the user:
|
||||
// the message it wrote is the whole story. A surface reports it as a failure and does not
|
||||
// log it.
|
||||
type Failure struct {
|
||||
Msg string
|
||||
}
|
||||
|
||||
func (f *Failure) Error() string {
|
||||
return f.Msg
|
||||
}
|
||||
|
||||
// Fail writes msg to w and returns it as a *Failure, so a command reports a failure to the
|
||||
// user and to its surface in one line. If the write itself fails, that error is returned
|
||||
// instead: the user was not told anything.
|
||||
func Fail(w StringWriter, msg string) error {
|
||||
if err := w.WriteLine(msg); err != nil {
|
||||
return err
|
||||
}
|
||||
return &Failure{Msg: msg}
|
||||
}
|
||||
|
||||
func execCommand(c *Command, args []string, w StringWriter) error {
|
||||
var (
|
||||
fl *flag.FlagSet
|
||||
fs any
|
||||
)
|
||||
|
||||
if c.Flags != nil {
|
||||
fl, fs = c.Flags()
|
||||
if fl != nil {
|
||||
// SetOutput() here in case fl.Parse dumps usage.
|
||||
fl.SetOutput(w.GetWriter())
|
||||
err := fl.Parse(args)
|
||||
if err != nil {
|
||||
// fl.Parse has dumped error information to the user via the w writer.
|
||||
return err
|
||||
}
|
||||
args = fl.Args()
|
||||
}
|
||||
}
|
||||
|
||||
return c.Callback(fs, args, w)
|
||||
}
|
||||
|
||||
func checkHelpArgs(args []string) bool {
|
||||
for _, a := range args {
|
||||
if a == "-h" || a == "-help" {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
@@ -1,28 +0,0 @@
|
||||
package commands
|
||||
|
||||
// Name identifies a command. Every command nebula serves is a constant here, so a
|
||||
// surface, a client and a test spell it the same way and are told at compile time when
|
||||
// they do not. It is a string rather than an integer so a test can register a throwaway
|
||||
// command without adding it here, and so the wire carries the name as the string it has
|
||||
// always been.
|
||||
type Name string
|
||||
|
||||
const (
|
||||
ChangeRemote Name = "change-remote"
|
||||
CloseTunnel Name = "close-tunnel"
|
||||
CreateTunnel Name = "create-tunnel"
|
||||
DeviceInfo Name = "device-info"
|
||||
Help Name = "help"
|
||||
ListHostmap Name = "list-hostmap"
|
||||
ListLighthouseAddrmap Name = "list-lighthouse-addrmap"
|
||||
ListPendingHostmap Name = "list-pending-hostmap"
|
||||
LogFormat Name = "log-format"
|
||||
LogLevel Name = "log-level"
|
||||
Logout Name = "logout"
|
||||
PrintCert Name = "print-cert"
|
||||
PrintRelays Name = "print-relays"
|
||||
PrintTunnel Name = "print-tunnel"
|
||||
QueryLighthouse Name = "query-lighthouse"
|
||||
Reload Name = "reload"
|
||||
Version Name = "version"
|
||||
)
|
||||
@@ -1,181 +0,0 @@
|
||||
package commands
|
||||
|
||||
import (
|
||||
"cmp"
|
||||
"fmt"
|
||||
"maps"
|
||||
"slices"
|
||||
"strings"
|
||||
"sync"
|
||||
|
||||
"github.com/anmitsu/go-shlex"
|
||||
)
|
||||
|
||||
// Registry holds a set of commands. New is the only way to make one.
|
||||
//
|
||||
// It is safe for concurrent use. Commands may be registered while a surface is serving
|
||||
// from the registry: the ssh server clones it per session, and a clone may overlap a
|
||||
// Register.
|
||||
type Registry struct {
|
||||
mu sync.RWMutex
|
||||
commands map[Name]*Command
|
||||
}
|
||||
|
||||
// New returns an empty Registry with only `help` available.
|
||||
func New() *Registry {
|
||||
r := &Registry{commands: map[Name]*Command{}}
|
||||
r.registerHelp()
|
||||
return r
|
||||
}
|
||||
|
||||
func (r *Registry) registerHelp() {
|
||||
r.Register(&Command{
|
||||
Name: Help,
|
||||
ShortDescription: "prints available commands or help <command> for specific usage info",
|
||||
Callback: func(a any, args []string, w StringWriter) error {
|
||||
return r.help(args, w)
|
||||
},
|
||||
})
|
||||
}
|
||||
|
||||
// Register adds a command that can be run by a user. A command registered under a name
|
||||
// already held replaces it; see Clone for what that means for Help.
|
||||
func (r *Registry) Register(c *Command) {
|
||||
r.mu.Lock()
|
||||
defer r.mu.Unlock()
|
||||
r.commands[c.Name] = c
|
||||
}
|
||||
|
||||
// Get returns the command registered under name, or nil if there is no such command.
|
||||
func (r *Registry) Get(name Name) *Command {
|
||||
r.mu.RLock()
|
||||
defer r.mu.RUnlock()
|
||||
return r.commands[name]
|
||||
}
|
||||
|
||||
// Match returns the names of every command starting with prefix, sorted, as strings for
|
||||
// a prompt to complete and print.
|
||||
func (r *Registry) Match(prefix string) []string {
|
||||
cmds := make([]string, 0)
|
||||
r.mu.RLock()
|
||||
for n := range r.commands {
|
||||
if strings.HasPrefix(string(n), prefix) {
|
||||
cmds = append(cmds, string(n))
|
||||
}
|
||||
}
|
||||
r.mu.RUnlock()
|
||||
slices.Sort(cmds)
|
||||
return cmds
|
||||
}
|
||||
|
||||
// All returns every registered command sorted by name, which is the order help lists them.
|
||||
func (r *Registry) All() []*Command {
|
||||
r.mu.RLock()
|
||||
defer r.mu.RUnlock()
|
||||
|
||||
cmds := slices.Collect(maps.Values(r.commands))
|
||||
slices.SortFunc(cmds, func(a, b *Command) int { return cmp.Compare(a.Name, b.Name) })
|
||||
return cmds
|
||||
}
|
||||
|
||||
// Clone returns a copy holding the same commands, with help bound to the copy: a
|
||||
// command registered on the clone alone is listed and described there, and one the
|
||||
// clone withholds is not. That rebinding replaces whatever was registered under Help on
|
||||
// the source, built-in or not.
|
||||
func (r *Registry) Clone() *Registry {
|
||||
r.mu.RLock()
|
||||
c := &Registry{commands: maps.Clone(r.commands)}
|
||||
r.mu.RUnlock()
|
||||
c.registerHelp()
|
||||
return c
|
||||
}
|
||||
|
||||
// Dispatch parses a command line and runs it, reporting problems to w. The error is for
|
||||
// the caller to log, not to show; see CommandCallback.
|
||||
func (r *Registry) Dispatch(line string, w StringWriter) error {
|
||||
// A line shlex cannot split, an unbalanced quote.
|
||||
args, err := shlex.Split(line, true)
|
||||
if err != nil {
|
||||
return Fail(w, "could not parse the command line: "+err.Error())
|
||||
}
|
||||
|
||||
return r.DispatchArgs(args, w)
|
||||
}
|
||||
|
||||
// DispatchArgs runs an already tokenized command line. The error is as for Dispatch.
|
||||
func (r *Registry) DispatchArgs(args []string, w StringWriter) error {
|
||||
if len(args) == 0 {
|
||||
r.dumpCommands(w)
|
||||
return nil
|
||||
}
|
||||
|
||||
c := r.Get(Name(args[0]))
|
||||
if c == nil {
|
||||
// Only the first word was looked up, so only it is named.
|
||||
msg := fmt.Sprintf("did not understand: %s", args[0])
|
||||
if err := w.WriteLine(msg); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
r.dumpCommands(w)
|
||||
return &Failure{Msg: msg}
|
||||
}
|
||||
|
||||
if checkHelpArgs(args) {
|
||||
// Through the registered help command, so -h and `help <name>` are one path.
|
||||
return execCommand(r.Get(Help), []string{string(c.Name)}, w)
|
||||
}
|
||||
|
||||
return execCommand(c, args[1:], w)
|
||||
}
|
||||
|
||||
// dumpCommands writes the list of available commands to w.
|
||||
func (r *Registry) dumpCommands(w StringWriter) {
|
||||
err := w.WriteLine("Available commands:")
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
|
||||
// In the order All gives, which is the display order.
|
||||
cmds := make([]string, 0)
|
||||
for _, l := range r.All() {
|
||||
cmds = append(cmds, fmt.Sprintf("%s - %s", l.Name, l.ShortDescription))
|
||||
}
|
||||
|
||||
_ = w.Write(strings.Join(cmds, "\n") + "\n\n")
|
||||
}
|
||||
|
||||
// help writes the command list, or usage for the single command named in a.
|
||||
func (r *Registry) help(a []string, w StringWriter) error {
|
||||
// Just typed help
|
||||
if len(a) == 0 {
|
||||
r.dumpCommands(w)
|
||||
return nil
|
||||
}
|
||||
|
||||
// We are printing a specific commands help text
|
||||
cmd := r.Get(Name(a[0]))
|
||||
if cmd == nil {
|
||||
return Fail(w, "Command not available "+a[0])
|
||||
}
|
||||
|
||||
if err := w.WriteLine(fmt.Sprintf("%s - %s", cmd.Name, cmd.ShortDescription)); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
if cmd.Help != "" {
|
||||
if err := w.WriteLine(fmt.Sprintf(" %s", cmd.Help)); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
if cmd.Flags != nil {
|
||||
fs, _ := cmd.Flags()
|
||||
if fs != nil {
|
||||
fs.SetOutput(w.GetWriter())
|
||||
fs.PrintDefaults()
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
@@ -1,176 +0,0 @@
|
||||
package commands
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"errors"
|
||||
"flag"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
func testRegistry() *Registry {
|
||||
r := New()
|
||||
r.Register(&Command{
|
||||
Name: "served",
|
||||
ShortDescription: "a command this surface serves",
|
||||
Callback: func(fs any, a []string, w StringWriter) error {
|
||||
return w.WriteLine("read " + strings.Join(a, ","))
|
||||
},
|
||||
})
|
||||
r.Register(&Command{
|
||||
Name: "withheld",
|
||||
ShortDescription: "a command this surface withholds",
|
||||
Callback: func(fs any, a []string, w StringWriter) error {
|
||||
return w.WriteLine("wrote")
|
||||
},
|
||||
})
|
||||
return r
|
||||
}
|
||||
|
||||
// TestFlagUsageGoesToTheWriter pins that a parse failure's usage lands on the command's
|
||||
// writer.
|
||||
func TestFlagUsageGoesToTheWriter(t *testing.T) {
|
||||
r := New()
|
||||
r.Register(&Command{
|
||||
Name: "emit",
|
||||
ShortDescription: "emits",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
fl.Bool("json", false, "emit json")
|
||||
return fl, nil
|
||||
},
|
||||
Callback: func(fs any, a []string, w StringWriter) error { return nil },
|
||||
})
|
||||
|
||||
merged := &bytes.Buffer{}
|
||||
require.Error(t, r.DispatchArgs([]string{"emit", "-nope"}, NewStringWriter(merged)))
|
||||
assert.Contains(t, merged.String(), "flag provided but not defined")
|
||||
}
|
||||
|
||||
// TestDispatchReportsUnparseableLine: a line shlex rejects, an unbalanced quote, is a
|
||||
// failure the user is told about.
|
||||
func TestDispatchReportsUnparseableLine(t *testing.T) {
|
||||
out := &bytes.Buffer{}
|
||||
err := testRegistry().Dispatch(`served "unterminated`, NewStringWriter(out))
|
||||
|
||||
var f *Failure
|
||||
require.ErrorAs(t, err, &f)
|
||||
assert.Equal(t, f.Msg+"\n", out.String())
|
||||
assert.Contains(t, out.String(), "could not parse the command line: ")
|
||||
}
|
||||
|
||||
// TestFailTellsTheUserAndTheSurface: Fail writes the message and returns it as a Failure;
|
||||
// when the write fails, the user heard nothing, so the write error is what comes back.
|
||||
func TestFailTellsTheUserAndTheSurface(t *testing.T) {
|
||||
out := &bytes.Buffer{}
|
||||
err := Fail(NewStringWriter(out), "no such tunnel")
|
||||
var f *Failure
|
||||
require.ErrorAs(t, err, &f)
|
||||
assert.Equal(t, "no such tunnel", f.Msg)
|
||||
assert.Equal(t, "no such tunnel\n", out.String())
|
||||
|
||||
err = Fail(NewStringWriter(failingWriter{}), "no such tunnel")
|
||||
require.EqualError(t, err, "gone")
|
||||
assert.NotErrorAs(t, err, &f)
|
||||
}
|
||||
|
||||
type failingWriter struct{}
|
||||
|
||||
func (failingWriter) Write([]byte) (int, error) { return 0, errors.New("gone") }
|
||||
|
||||
// TestAllSortsByName: registration order does not matter.
|
||||
func TestAllSortsByName(t *testing.T) {
|
||||
r := New()
|
||||
for _, n := range []Name{"zz", Version, "aa", ChangeRemote} {
|
||||
r.Register(&Command{Name: n})
|
||||
}
|
||||
|
||||
var got []Name
|
||||
for _, c := range r.All() {
|
||||
got = append(got, c.Name)
|
||||
}
|
||||
assert.Equal(t, []Name{"aa", ChangeRemote, Help, Version, "zz"}, got)
|
||||
}
|
||||
|
||||
// TestHelpFlagAgreesWithHelpCommand pins that -h answers through the registered help
|
||||
// command, and that help on a clone describes the clone: a command registered only there
|
||||
// is known to both -h and `help <name>`, and one withheld from it is known to neither.
|
||||
func TestHelpFlagAgreesWithHelpCommand(t *testing.T) {
|
||||
r := testRegistry()
|
||||
c := r.Clone()
|
||||
c.Register(&Command{
|
||||
Name: Logout,
|
||||
ShortDescription: "ends the session",
|
||||
Callback: func(fs any, a []string, w StringWriter) error { return nil },
|
||||
})
|
||||
|
||||
flag := &bytes.Buffer{}
|
||||
c.Dispatch("logout -h", NewStringWriter(flag))
|
||||
cmd := &bytes.Buffer{}
|
||||
c.Dispatch("help logout", NewStringWriter(cmd))
|
||||
assert.Equal(t, cmd.String(), flag.String())
|
||||
assert.Equal(t, "logout - ends the session\n", flag.String())
|
||||
|
||||
// The source never learns of it.
|
||||
src := &bytes.Buffer{}
|
||||
r.Dispatch("help logout", NewStringWriter(src))
|
||||
assert.Equal(t, "Command not available logout\n", src.String())
|
||||
|
||||
// And a command both hold is described either way.
|
||||
flag.Reset()
|
||||
c.Dispatch("served -h", NewStringWriter(flag))
|
||||
assert.Equal(t, "served - a command this surface serves\n", flag.String())
|
||||
}
|
||||
|
||||
// TestCloneHelpListsTheClone: the command list help prints is the clone's, so a clone
|
||||
// that withholds a command does not name it, and the source still does.
|
||||
func TestCloneHelpListsTheClone(t *testing.T) {
|
||||
r := testRegistry()
|
||||
c := New()
|
||||
c.Register(r.Get("served"))
|
||||
c = c.Clone()
|
||||
|
||||
out := &bytes.Buffer{}
|
||||
c.Dispatch("help", NewStringWriter(out))
|
||||
assert.Equal(t, "Available commands:\n"+
|
||||
"help - prints available commands or help <command> for specific usage info\n"+
|
||||
"served - a command this surface serves\n\n", out.String())
|
||||
|
||||
out.Reset()
|
||||
c.Dispatch("help withheld", NewStringWriter(out))
|
||||
assert.Equal(t, "Command not available withheld\n", out.String())
|
||||
|
||||
out.Reset()
|
||||
r.Dispatch("help withheld", NewStringWriter(out))
|
||||
assert.Equal(t, "withheld - a command this surface withholds\n", out.String())
|
||||
}
|
||||
|
||||
// TestDispatchReturnsTheCommandsError: what the callback returns reaches the caller, so
|
||||
// a surface can log it.
|
||||
func TestDispatchReturnsTheCommandsError(t *testing.T) {
|
||||
r := New()
|
||||
r.Register(&Command{
|
||||
Name: "fails",
|
||||
Callback: func(fs any, a []string, w StringWriter) error {
|
||||
return errors.New("boom")
|
||||
},
|
||||
})
|
||||
|
||||
out := &bytes.Buffer{}
|
||||
require.EqualError(t, r.Dispatch("fails", NewStringWriter(out)), "boom")
|
||||
assert.Empty(t, out.String(), "a command's own error is not shown; the command speaks for itself")
|
||||
}
|
||||
|
||||
// TestUnknownCommandNamesTheWord: only the first word is looked up, so only it is
|
||||
// reported, followed by the command list, and the line is a failure to the surface.
|
||||
func TestUnknownCommandNamesTheWord(t *testing.T) {
|
||||
out := &bytes.Buffer{}
|
||||
err := testRegistry().Dispatch(`nope "with args"`, NewStringWriter(out))
|
||||
var f *Failure
|
||||
require.ErrorAs(t, err, &f)
|
||||
assert.Equal(t, "did not understand: nope", f.Msg)
|
||||
assert.True(t, strings.HasPrefix(out.String(), "did not understand: nope\nAvailable commands:\n"), out.String())
|
||||
}
|
||||
@@ -1,67 +0,0 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"io"
|
||||
"net/netip"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/commands"
|
||||
"github.com/slackhq/nebula/logging"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// TestLogFormatRefusalIsShown: a format the logger does not know is reported to the user
|
||||
// as a failure, rather than returned bare, which over ssh was silence.
|
||||
func TestLogFormatRefusalIsShown(t *testing.T) {
|
||||
l := logging.NewLogger(io.Discard)
|
||||
out := &bytes.Buffer{}
|
||||
w := commands.NewStringWriter(out)
|
||||
|
||||
var f *commands.Failure
|
||||
require.ErrorAs(t, logFormatCommand(l, nil, []string{"bogus"}, w), &f)
|
||||
assert.Equal(t, "Unable to set log format: unknown log format `bogus`. possible formats: [text json]\n", out.String())
|
||||
|
||||
out.Reset()
|
||||
require.NoError(t, logFormatCommand(l, nil, []string{"JSON"}, w))
|
||||
assert.Equal(t, "Log format is: json\n", out.String())
|
||||
}
|
||||
|
||||
// TestPrintRelaysReportsErrorsAsText: the Error field was an error value, which encodes
|
||||
// as {} and lost the message. It is the message now, and absent when there is none.
|
||||
func TestPrintRelaysReportsErrorsAsText(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
hm := newHostMap(l)
|
||||
relay := netip.MustParseAddr("10.0.0.1")
|
||||
peer := netip.MustParseAddr("10.0.0.2")
|
||||
|
||||
// A relay host that is in Relays but not in Hosts, so its hostinfo cannot be found.
|
||||
hm.Relays[1] = &HostInfo{vpnAddrs: []netip.Addr{relay}}
|
||||
ifce := &Interface{hostMap: hm}
|
||||
|
||||
out := &bytes.Buffer{}
|
||||
require.NoError(t, printRelaysCommand(ifce, &printTunnelFlags{}, nil, commands.NewStringWriter(out)))
|
||||
assert.JSONEq(t, `{"Relays":[{"NebulaAddr":"10.0.0.1","RelayForAddrs":[{"Error":"could not find hostinfo","Type":"","State":"","PeerAddr":"","LocalIndex":0,"RemoteIndex":0,"RelayedThrough":null}]}]}`, out.String())
|
||||
|
||||
// The same relay host, found, relaying for a peer whose index matches: no Error key.
|
||||
hi := hm.Relays[1]
|
||||
r := &Relay{Type: ForwardingType, State: Established, PeerAddr: peer, LocalIndex: 1, RemoteIndex: 2}
|
||||
hi.relayState = RelayState{
|
||||
relayForByAddr: map[netip.Addr]*Relay{peer: r},
|
||||
relayForByIdx: map[uint32]*Relay{r.LocalIndex: r},
|
||||
}
|
||||
hm.Hosts[relay] = hi
|
||||
|
||||
out.Reset()
|
||||
require.NoError(t, printRelaysCommand(ifce, &printTunnelFlags{}, nil, commands.NewStringWriter(out)))
|
||||
assert.JSONEq(t, `{"Relays":[{"NebulaAddr":"10.0.0.1","RelayForAddrs":[{"Type":"forwarding","State":"established","PeerAddr":"10.0.0.2","LocalIndex":1,"RemoteIndex":2,"RelayedThrough":null}]}]}`, out.String())
|
||||
|
||||
// And an index mismatch names it.
|
||||
hm.Relays[7] = hi
|
||||
delete(hm.Relays, 1)
|
||||
out.Reset()
|
||||
require.NoError(t, printRelaysCommand(ifce, &printTunnelFlags{}, nil, commands.NewStringWriter(out)))
|
||||
assert.Contains(t, out.String(), `"Error":"hostmap LocalIndex '7' does not match RelayState LocalIndex"`)
|
||||
}
|
||||
+31
-55
@@ -26,12 +26,9 @@ type C struct {
|
||||
files []string
|
||||
Settings map[string]any
|
||||
oldSettings map[string]any
|
||||
callbacks []func(*C, *Reload)
|
||||
callbacks []func(*C)
|
||||
l *slog.Logger
|
||||
reloadLock sync.Mutex
|
||||
|
||||
// Set by the first reload that needs a restart and never cleared. Guarded by reloadLock
|
||||
needsRestart bool
|
||||
}
|
||||
|
||||
func NewC(l *slog.Logger) *C {
|
||||
@@ -75,9 +72,8 @@ func (c *C) LoadString(raw string) error {
|
||||
// RegisterReloadCallback stores a function to be called when a config reload is triggered. The functions registered
|
||||
// here should decide if they need to make a change to the current process before making the change. HasChanged can be
|
||||
// used to help decide if a change is necessary.
|
||||
// These functions should return quickly or spawn their own go routine if they will take a while.
|
||||
// Use r to report anything that failed or needs a restart to apply.
|
||||
func (c *C) RegisterReloadCallback(f func(c *C, r *Reload)) {
|
||||
// These functions should return quickly or spawn their own go routine if they will take a while
|
||||
func (c *C) RegisterReloadCallback(f func(*C)) {
|
||||
c.callbacks = append(c.callbacks, f)
|
||||
}
|
||||
|
||||
@@ -86,21 +82,6 @@ func (c *C) InitialLoad() bool {
|
||||
return c.oldSettings == nil
|
||||
}
|
||||
|
||||
// Render returns keys and their values as yaml, for a subsystem to remember what it applied. Empty means they couldn't
|
||||
// be rendered and should never match.
|
||||
func (c *C) Render(keys ...string) string {
|
||||
m := make(map[string]any, len(keys))
|
||||
for _, k := range keys {
|
||||
m[k] = c.Get(k)
|
||||
}
|
||||
b, err := yaml.Marshal(m)
|
||||
if err != nil {
|
||||
c.l.Debug("Failed to render config", "keys", keys, "error", err)
|
||||
return ""
|
||||
}
|
||||
return string(b)
|
||||
}
|
||||
|
||||
// HasChanged checks if the underlying structure of the provided key has changed after a config reload. The value of
|
||||
// k in both the old and new settings will be serialized, the result of the string comparison is returned.
|
||||
// If k is an empty string the entire config is tested.
|
||||
@@ -163,55 +144,50 @@ func (c *C) CatchHUP(ctx context.Context) {
|
||||
return
|
||||
case <-ch:
|
||||
c.l.Info("Caught HUP, reloading config")
|
||||
c.ReloadConfig().Log(c.l)
|
||||
c.ReloadConfig()
|
||||
}
|
||||
}
|
||||
}()
|
||||
}
|
||||
|
||||
// ReloadConfig reloads the config from the path provided to Load and runs every registered callback. A config that
|
||||
// fails to load is logged here, like any other failure, and the result carries the error for the summary.
|
||||
func (c *C) ReloadConfig() ReloadResult {
|
||||
func (c *C) ReloadConfig() {
|
||||
c.reloadLock.Lock()
|
||||
defer c.reloadLock.Unlock()
|
||||
|
||||
c.oldSettings = make(map[string]any)
|
||||
maps.Copy(c.oldSettings, c.Settings)
|
||||
|
||||
if err := c.Load(c.path); err != nil {
|
||||
c.l.Error("Error occurred while reloading config", "config_path", c.path, "error", err)
|
||||
return ReloadResult{Err: err, RestartRequired: c.needsRestart}
|
||||
err := c.Load(c.path)
|
||||
if err != nil {
|
||||
c.l.Error("Error occurred while reloading config",
|
||||
"config_path", c.path,
|
||||
"error", err,
|
||||
)
|
||||
return
|
||||
}
|
||||
|
||||
return c.runCallbacks()
|
||||
}
|
||||
|
||||
// ReloadConfigString is ReloadConfig for a config held in memory rather than on disk.
|
||||
func (c *C) ReloadConfigString(raw string) ReloadResult {
|
||||
c.reloadLock.Lock()
|
||||
defer c.reloadLock.Unlock()
|
||||
|
||||
c.oldSettings = make(map[string]any)
|
||||
maps.Copy(c.oldSettings, c.Settings)
|
||||
|
||||
if err := c.LoadString(raw); err != nil {
|
||||
c.l.Error("Error occurred while reloading config", "error", err)
|
||||
return ReloadResult{Err: err, RestartRequired: c.needsRestart}
|
||||
}
|
||||
|
||||
return c.runCallbacks()
|
||||
}
|
||||
|
||||
func (c *C) runCallbacks() ReloadResult {
|
||||
r := &Reload{c: c}
|
||||
for _, v := range c.callbacks {
|
||||
v(c, r)
|
||||
v(c)
|
||||
}
|
||||
}
|
||||
|
||||
func (c *C) ReloadConfigString(raw string) error {
|
||||
c.reloadLock.Lock()
|
||||
defer c.reloadLock.Unlock()
|
||||
|
||||
c.oldSettings = make(map[string]any)
|
||||
maps.Copy(c.oldSettings, c.Settings)
|
||||
|
||||
err := c.LoadString(raw)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
if r.restart {
|
||||
c.needsRestart = true
|
||||
for _, v := range c.callbacks {
|
||||
v(c)
|
||||
}
|
||||
return ReloadResult{Failed: r.failed, RestartRequired: c.needsRestart, RestartKeys: r.keys}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// GetString will get the string for k or return the default d if not found or invalid
|
||||
@@ -415,7 +391,7 @@ func (c *C) parse() error {
|
||||
var nm map[string]any
|
||||
err = yaml.Unmarshal(b, &nm)
|
||||
if err != nil {
|
||||
return fmt.Errorf("%s: %w", path, err)
|
||||
return err
|
||||
}
|
||||
|
||||
// We need to use WithAppendSlice so that firewall rules in separate
|
||||
|
||||
@@ -19,7 +19,7 @@ func TestConfig_Load(t *testing.T) {
|
||||
// invalid yaml
|
||||
c := NewC(l)
|
||||
os.WriteFile(filepath.Join(dir, "01.yaml"), []byte(" invalid yaml"), 0644)
|
||||
require.EqualError(t, c.Load(dir), filepath.Join(dir, "01.yaml")+": yaml: unmarshal errors:\n line 1: cannot unmarshal !!str `invalid...` into map[string]interface {}")
|
||||
require.EqualError(t, c.Load(dir), "yaml: unmarshal errors:\n line 1: cannot unmarshal !!str `invalid...` into map[string]interface {}")
|
||||
|
||||
// simple multi config merge
|
||||
c = NewC(l)
|
||||
@@ -129,7 +129,7 @@ func TestConfig_ReloadConfig(t *testing.T) {
|
||||
|
||||
os.WriteFile(filepath.Join(dir, "01.yaml"), []byte("outer:\n inner: ho"), 0644)
|
||||
|
||||
c.RegisterReloadCallback(func(c *C, _ *Reload) {
|
||||
c.RegisterReloadCallback(func(c *C) {
|
||||
done <- true
|
||||
})
|
||||
|
||||
|
||||
@@ -1,98 +0,0 @@
|
||||
package config
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"slices"
|
||||
)
|
||||
|
||||
// ReloadResult describes how a reload went. Problems are logged where they happen, Log writes a one line summary.
|
||||
type ReloadResult struct {
|
||||
// Err is set when the new config could not be read or parsed, no callbacks ran
|
||||
Err error
|
||||
// Failed is true when a callback could not apply part of the new config
|
||||
Failed bool
|
||||
// RestartRequired is true once any reload has needed a restart, and stays true until the process restarts
|
||||
RestartRequired bool
|
||||
// RestartKeys are the keys this reload changed that only apply on a restart
|
||||
RestartKeys []string
|
||||
}
|
||||
|
||||
// Summary returns a one line summary of the reload and the level to log it at.
|
||||
func (r ReloadResult) Summary() (slog.Level, string) {
|
||||
switch {
|
||||
case r.Err != nil && r.RestartRequired:
|
||||
return slog.LevelError, "Config reload failed, the new config did not load and a restart is still required"
|
||||
case r.Err != nil:
|
||||
return slog.LevelError, "Config reload failed, the new config did not load"
|
||||
case r.Failed && r.RestartRequired:
|
||||
return slog.LevelError, "Config reload completed with errors and requires a restart to fully apply, review the logs"
|
||||
case r.Failed:
|
||||
return slog.LevelError, "Config reload completed with errors, review the logs"
|
||||
case r.RestartRequired:
|
||||
return slog.LevelWarn, "Config reload was completed but requires a restart to fully apply"
|
||||
default:
|
||||
return slog.LevelInfo, "Config reload complete"
|
||||
}
|
||||
}
|
||||
|
||||
// String is the summary with Err and RestartKeys included, for output other than the log.
|
||||
func (r ReloadResult) String() string {
|
||||
_, msg := r.Summary()
|
||||
if r.Err != nil {
|
||||
msg = fmt.Sprintf("%s: %v", msg, r.Err)
|
||||
}
|
||||
if len(r.RestartKeys) > 0 {
|
||||
msg = fmt.Sprintf("%s, keys %v", msg, r.RestartKeys)
|
||||
}
|
||||
return msg
|
||||
}
|
||||
|
||||
// Log writes Summary to l.
|
||||
func (r ReloadResult) Log(l *slog.Logger) {
|
||||
level, msg := r.Summary()
|
||||
if len(r.RestartKeys) > 0 {
|
||||
l.Log(context.Background(), level, msg, "keys", r.RestartKeys)
|
||||
return
|
||||
}
|
||||
l.Log(context.Background(), level, msg)
|
||||
}
|
||||
|
||||
// Reload is passed to each reload callback to report how applying the new config went.
|
||||
type Reload struct {
|
||||
c *C
|
||||
failed bool
|
||||
restart bool
|
||||
// Changed keys that only apply on a restart, from every callback
|
||||
keys []string
|
||||
}
|
||||
|
||||
// Failed marks the reload as failed, the caller logs why. Safe to call on a nil Reload, which is what the initial load
|
||||
// passes.
|
||||
func (r *Reload) Failed() {
|
||||
if r != nil {
|
||||
r.failed = true
|
||||
}
|
||||
}
|
||||
|
||||
// RestartRequired marks the reload as needing a restart, the caller logs why. Safe to call on a nil Reload.
|
||||
func (r *Reload) RestartRequired() {
|
||||
if r != nil {
|
||||
r.restart = true
|
||||
}
|
||||
}
|
||||
|
||||
// RestartRequiredIfChanged marks the reload as needing a restart if any of keys changed, and adds them to RestartKeys.
|
||||
// Use it for keys that are only read at startup. Safe to call on a nil Reload.
|
||||
func (r *Reload) RestartRequiredIfChanged(keys ...string) {
|
||||
if r == nil {
|
||||
return
|
||||
}
|
||||
for _, k := range keys {
|
||||
if r.c.HasChanged(k) && !slices.Contains(r.keys, k) {
|
||||
r.keys = append(r.keys, k)
|
||||
r.restart = true
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,108 +0,0 @@
|
||||
package config
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"log/slog"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
func TestReloadConfigString(t *testing.T) {
|
||||
c := NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("a: 1"))
|
||||
fail := false
|
||||
ran := 0
|
||||
c.RegisterReloadCallback(func(c *C, r *Reload) {
|
||||
ran++
|
||||
if fail {
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
assert.Equal(t, ReloadResult{}, c.ReloadConfigString("a: 2"))
|
||||
fail = true
|
||||
assert.Equal(t, ReloadResult{Failed: true}, c.ReloadConfigString("a: 3"))
|
||||
assert.Equal(t, 2, ran)
|
||||
|
||||
// A config that fails to load runs no callbacks and returns the error
|
||||
res := c.ReloadConfigString("a: [")
|
||||
require.Error(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.Equal(t, 2, ran)
|
||||
assert.Equal(t, 3, c.GetInt("a", 0))
|
||||
}
|
||||
|
||||
func TestReloadRestartRequiredLatches(t *testing.T) {
|
||||
c := NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("a: 1\nb: 1"))
|
||||
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequiredIfChanged("a", "b") })
|
||||
|
||||
// Nothing that needs a restart changed
|
||||
assert.Equal(t, ReloadResult{}, c.ReloadConfigString("a: 1\nb: 1\nc: 1"))
|
||||
assert.Equal(t, ReloadResult{RestartRequired: true, RestartKeys: []string{"a"}}, c.ReloadConfigString("a: 2\nb: 1\nc: 1"))
|
||||
|
||||
// The restart sticks through a reload with no changes, reverting the key and a config that fails to load. Only the
|
||||
// reload that changed the key lists it
|
||||
assert.Equal(t, ReloadResult{RestartRequired: true}, c.ReloadConfigString("a: 2\nb: 1\nc: 1"))
|
||||
assert.Equal(t, ReloadResult{RestartRequired: true, RestartKeys: []string{"a"}}, c.ReloadConfigString("a: 1\nb: 1\nc: 1"))
|
||||
|
||||
res := c.ReloadConfigString("a: [")
|
||||
require.Error(t, res.Err)
|
||||
assert.True(t, res.RestartRequired)
|
||||
}
|
||||
|
||||
// A key reported by more than one callback is listed once
|
||||
func TestReloadRestartKeysDeduped(t *testing.T) {
|
||||
c := NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("a: 1\nb: 1"))
|
||||
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequiredIfChanged("a") })
|
||||
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequiredIfChanged("a", "b") })
|
||||
|
||||
assert.Equal(t, []string{"a", "b"}, c.ReloadConfigString("a: 2\nb: 2").RestartKeys)
|
||||
}
|
||||
|
||||
// A callback can require a restart without a key changing, a file the config points at may have
|
||||
func TestReloadRestartRequiredWithoutAChange(t *testing.T) {
|
||||
c := NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("a: 1"))
|
||||
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequired() })
|
||||
|
||||
assert.Equal(t, ReloadResult{RestartRequired: true}, c.ReloadConfigString("a: 1"))
|
||||
}
|
||||
|
||||
func TestReloadResultSummary(t *testing.T) {
|
||||
cases := []struct {
|
||||
res ReloadResult
|
||||
level slog.Level
|
||||
msg string
|
||||
}{
|
||||
{ReloadResult{}, slog.LevelInfo, "Config reload complete"},
|
||||
{ReloadResult{RestartRequired: true}, slog.LevelWarn, "Config reload was completed but requires a restart to fully apply"},
|
||||
{ReloadResult{Failed: true}, slog.LevelError, "Config reload completed with errors, review the logs"},
|
||||
{ReloadResult{Failed: true, RestartRequired: true}, slog.LevelError, "Config reload completed with errors and requires a restart to fully apply, review the logs"},
|
||||
{ReloadResult{Err: errors.New("bad yaml")}, slog.LevelError, "Config reload failed, the new config did not load"},
|
||||
{ReloadResult{Err: errors.New("bad yaml"), RestartRequired: true}, slog.LevelError, "Config reload failed, the new config did not load and a restart is still required"},
|
||||
}
|
||||
for _, tc := range cases {
|
||||
level, msg := tc.res.Summary()
|
||||
assert.Equal(t, tc.level, level, tc.msg)
|
||||
assert.Equal(t, tc.msg, msg)
|
||||
}
|
||||
|
||||
res := ReloadResult{RestartRequired: true, RestartKeys: []string{"a", "b"}}
|
||||
assert.Equal(t, "Config reload was completed but requires a restart to fully apply, keys [a b]", res.String())
|
||||
|
||||
// String includes the error
|
||||
assert.Equal(t, "Config reload failed, the new config did not load: bad yaml", ReloadResult{Err: errors.New("bad yaml")}.String())
|
||||
}
|
||||
|
||||
// The initial load passes a nil Reload
|
||||
func TestReloadNilIsSafe(t *testing.T) {
|
||||
var r *Reload
|
||||
r.Failed()
|
||||
r.RestartRequired()
|
||||
r.RestartRequiredIfChanged("a")
|
||||
}
|
||||
+17
-32
@@ -14,7 +14,6 @@ import (
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
)
|
||||
|
||||
type trafficDecision int
|
||||
@@ -58,8 +57,7 @@ func newConnectionManagerFromConfig(l *slog.Logger, c *config.C, hm *HostMap, p
|
||||
}
|
||||
|
||||
cm.reload(c, true)
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("timers.connection_alive_interval", "timers.pending_deletion_interval")
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
cm.reload(c, false)
|
||||
})
|
||||
|
||||
@@ -172,12 +170,14 @@ func (cm *connectionManager) Start(ctx context.Context) {
|
||||
}
|
||||
|
||||
func (cm *connectionManager) doTrafficCheck(localIndex uint32, p, nb, out []byte, now time.Time) {
|
||||
decision, hostinfo, primary, punch := cm.makeTrafficDecision(localIndex, now)
|
||||
decision, hostinfo, primary := cm.makeTrafficDecision(localIndex, now)
|
||||
|
||||
switch decision {
|
||||
case deleteTunnel:
|
||||
// Local delete only, clearing the lighthouse cache if this was the last hostinfo for the vpn addr
|
||||
cm.intf.closeTunnel(hostinfo)
|
||||
if cm.hostMap.DeleteHostInfo(hostinfo) {
|
||||
// Only clearing the lighthouse cache if this is the last hostinfo for this vpn ip in the hostmap
|
||||
cm.intf.lightHouse.DeleteVpnAddrs(hostinfo.vpnAddrs)
|
||||
}
|
||||
|
||||
case closeTunnel:
|
||||
cm.intf.sendCloseTunnel(hostinfo)
|
||||
@@ -197,20 +197,6 @@ func (cm *connectionManager) doTrafficCheck(localIndex uint32, p, nb, out []byte
|
||||
}
|
||||
|
||||
cm.resetRelayTrafficCheck(hostinfo)
|
||||
|
||||
if punch != nil {
|
||||
cm.sendPunch(punch)
|
||||
}
|
||||
}
|
||||
|
||||
// sendPunch keeps a tunnel's NAT state alive when we are not sending on it. When we have no route to its remote any
|
||||
// more, typically after moving to a network without that address family, the tunnel probes its other remotes so the
|
||||
// peer roams over to us. Nothing else would notice, a tunnel we are not sending on has nothing else that could fail.
|
||||
func (cm *connectionManager) sendPunch(hostinfo *HostInfo) {
|
||||
remote, err := cm.punchy.SendPunch(hostinfo)
|
||||
if udp.IsUnreachable(err) {
|
||||
hostinfo.remoteUnreachable(cm.intf, remote)
|
||||
}
|
||||
}
|
||||
|
||||
func (cm *connectionManager) resetRelayTrafficCheck(hostinfo *HostInfo) {
|
||||
@@ -328,9 +314,7 @@ func (cm *connectionManager) migrateRelayUsed(oldhostinfo, newhostinfo *HostInfo
|
||||
}
|
||||
}
|
||||
|
||||
// makeTrafficDecision decides what to do with a tunnel under the hostmap lock. It also returns the tunnel to punch when
|
||||
// we are not sending on it, for the caller to send once the lock is released.
|
||||
func (cm *connectionManager) makeTrafficDecision(localIndex uint32, now time.Time) (trafficDecision, *HostInfo, *HostInfo, *HostInfo) {
|
||||
func (cm *connectionManager) makeTrafficDecision(localIndex uint32, now time.Time) (trafficDecision, *HostInfo, *HostInfo) {
|
||||
// Read lock the main hostmap to order decisions based on tunnels being the primary tunnel
|
||||
cm.hostMap.RLock()
|
||||
defer cm.hostMap.RUnlock()
|
||||
@@ -338,17 +322,17 @@ func (cm *connectionManager) makeTrafficDecision(localIndex uint32, now time.Tim
|
||||
hostinfo := cm.hostMap.Indexes[localIndex]
|
||||
if hostinfo == nil {
|
||||
cm.l.Debug("Not found in hostmap", "localIndex", localIndex)
|
||||
return doNothing, nil, nil, nil
|
||||
return doNothing, nil, nil
|
||||
}
|
||||
|
||||
if cm.isInvalidCertificate(now, hostinfo) {
|
||||
return closeTunnel, hostinfo, nil, nil
|
||||
return closeTunnel, hostinfo, nil
|
||||
}
|
||||
|
||||
if hostinfo.ConnectionState != nil && hostinfo.ConnectionState.messageCounter.Load() >= RejectAfterMessages {
|
||||
// Send path can't encrypt a CloseTunnel notify, so just delete locally; the peer recovers via recv_error.
|
||||
hostinfo.logger(cm.l).Error("Dropping tunnel, message counter is exhausted")
|
||||
return deleteTunnel, hostinfo, nil, nil
|
||||
return deleteTunnel, hostinfo, nil
|
||||
}
|
||||
|
||||
primary := cm.hostMap.Hosts[hostinfo.vpnAddrs[0]]
|
||||
@@ -385,10 +369,10 @@ func (cm *connectionManager) makeTrafficDecision(localIndex uint32, now time.Tim
|
||||
|
||||
if !outTraffic {
|
||||
// Send a punch packet to keep the NAT state alive
|
||||
return decision, hostinfo, primary, hostinfo
|
||||
cm.punchy.SendPunch(hostinfo)
|
||||
}
|
||||
|
||||
return decision, hostinfo, primary, nil
|
||||
return decision, hostinfo, primary
|
||||
}
|
||||
|
||||
if hostinfo.isPendingDeletion() {
|
||||
@@ -397,7 +381,7 @@ func (cm *connectionManager) makeTrafficDecision(localIndex uint32, now time.Tim
|
||||
"tunnelCheck", m{"state": "dead", "method": "active"},
|
||||
)
|
||||
|
||||
return deleteTunnel, hostinfo, nil, nil
|
||||
return deleteTunnel, hostinfo, nil
|
||||
}
|
||||
|
||||
decision := doNothing
|
||||
@@ -411,13 +395,14 @@ func (cm *connectionManager) makeTrafficDecision(localIndex uint32, now time.Tim
|
||||
"primary", mainHostInfo,
|
||||
)
|
||||
|
||||
return closeTunnel, hostinfo, primary, nil
|
||||
return closeTunnel, hostinfo, primary
|
||||
}
|
||||
|
||||
// If we aren't sending or receiving traffic then its an unused tunnel and we don't to test the tunnel.
|
||||
// Just maintain NAT state if configured to do so.
|
||||
cm.punchy.SendPunch(hostinfo)
|
||||
cm.trafficTimer.Add(hostinfo.localIndexId, cm.checkInterval)
|
||||
return doNothing, nil, nil, hostinfo
|
||||
return doNothing, nil, nil
|
||||
}
|
||||
|
||||
// We aren't receiving traffic but we are sending it. The outbound
|
||||
@@ -443,7 +428,7 @@ func (cm *connectionManager) makeTrafficDecision(localIndex uint32, now time.Tim
|
||||
|
||||
hostinfo.setPendingDeletion(true)
|
||||
cm.trafficTimer.Add(hostinfo.localIndexId, cm.pendingDeletionInterval)
|
||||
return decision, hostinfo, nil, nil
|
||||
return decision, hostinfo, nil
|
||||
}
|
||||
|
||||
func (cm *connectionManager) isInactive(hostinfo *HostInfo, now time.Time) (time.Duration, bool) {
|
||||
|
||||
+6
-250
@@ -3,18 +3,12 @@ package nebula
|
||||
import (
|
||||
"crypto/ed25519"
|
||||
"crypto/rand"
|
||||
"io"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/flynn/noise"
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/noiseutil"
|
||||
"github.com/slackhq/nebula/overlay/batch"
|
||||
"github.com/slackhq/nebula/overlay/overlaytest"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
@@ -27,8 +21,6 @@ func newTestLighthouse() *LightHouse {
|
||||
l: test.NewLogger(),
|
||||
addrMap: map[netip.Addr]*RemoteList{},
|
||||
queryChan: make(chan netip.Addr, 10),
|
||||
// Nothing drains queryChan here, so an 11th query is dropped.
|
||||
queryDropped: metrics.NilCounter{},
|
||||
}
|
||||
lighthouses := []netip.Addr{}
|
||||
staticList := map[netip.Addr]struct{}{}
|
||||
@@ -271,12 +263,12 @@ func Test_NewConnectionManager_CounterLimits(t *testing.T) {
|
||||
|
||||
// Still below the reject limit, the tunnel stays up
|
||||
nc.In(hostinfo)
|
||||
decision, _, _, _ := nc.makeTrafficDecision(hostinfo.localIndexId, time.Now())
|
||||
decision, _, _ := nc.makeTrafficDecision(hostinfo.localIndexId, time.Now())
|
||||
assert.Equal(t, tryRehandshake, decision)
|
||||
|
||||
// At the reject limit, the tunnel is deleted locally without a doomed CloseTunnel notify
|
||||
hostinfo.ConnectionState.messageCounter.Store(RejectAfterMessages)
|
||||
decision, _, _, _ = nc.makeTrafficDecision(hostinfo.localIndexId, time.Now())
|
||||
decision, _, _ = nc.makeTrafficDecision(hostinfo.localIndexId, time.Now())
|
||||
assert.Equal(t, deleteTunnel, decision)
|
||||
}
|
||||
|
||||
@@ -338,14 +330,14 @@ func Test_NewConnectionManager_DisconnectInactive(t *testing.T) {
|
||||
assert.True(t, (hostinfo.state.Load()&stateIn != 0))
|
||||
|
||||
now := time.Now()
|
||||
decision, _, _, _ := nc.makeTrafficDecision(hostinfo.localIndexId, now)
|
||||
decision, _, _ := nc.makeTrafficDecision(hostinfo.localIndexId, now)
|
||||
assert.Equal(t, tryRehandshake, decision)
|
||||
assert.Equal(t, now, hostinfo.lastUsed)
|
||||
assert.False(t, hostinfo.isPendingDeletion())
|
||||
assert.False(t, hostinfo.sentSinceCheck())
|
||||
assert.False(t, (hostinfo.state.Load()&stateIn != 0))
|
||||
|
||||
decision, _, _, _ = nc.makeTrafficDecision(hostinfo.localIndexId, now.Add(time.Second*5))
|
||||
decision, _, _ = nc.makeTrafficDecision(hostinfo.localIndexId, now.Add(time.Second*5))
|
||||
assert.Equal(t, doNothing, decision)
|
||||
assert.Equal(t, now, hostinfo.lastUsed)
|
||||
assert.False(t, hostinfo.isPendingDeletion())
|
||||
@@ -353,7 +345,7 @@ func Test_NewConnectionManager_DisconnectInactive(t *testing.T) {
|
||||
assert.False(t, (hostinfo.state.Load()&stateIn != 0))
|
||||
|
||||
// Do another traffic check tick, should still not be pending deletion
|
||||
decision, _, _, _ = nc.makeTrafficDecision(hostinfo.localIndexId, now.Add(time.Second*10))
|
||||
decision, _, _ = nc.makeTrafficDecision(hostinfo.localIndexId, now.Add(time.Second*10))
|
||||
assert.Equal(t, doNothing, decision)
|
||||
assert.Equal(t, now, hostinfo.lastUsed)
|
||||
assert.False(t, hostinfo.isPendingDeletion())
|
||||
@@ -363,7 +355,7 @@ func Test_NewConnectionManager_DisconnectInactive(t *testing.T) {
|
||||
assert.Contains(t, nc.hostMap.Hosts, hostinfo.vpnAddrs[0])
|
||||
|
||||
// Finally advance beyond the inactivity timeout
|
||||
decision, _, _, _ = nc.makeTrafficDecision(hostinfo.localIndexId, now.Add(time.Minute*10))
|
||||
decision, _, _ = nc.makeTrafficDecision(hostinfo.localIndexId, now.Add(time.Minute*10))
|
||||
assert.Equal(t, closeTunnel, decision)
|
||||
assert.Equal(t, now, hostinfo.lastUsed)
|
||||
assert.False(t, hostinfo.isPendingDeletion())
|
||||
@@ -583,239 +575,3 @@ func (d *dummyCert) MarshalJSON() ([]byte, error) {
|
||||
func (d *dummyCert) Copy() cert.Certificate {
|
||||
return d
|
||||
}
|
||||
|
||||
// newPunchTestConnectionManager is a connection manager punching through conn, holding the tunnel from newPunchTarget
|
||||
func newPunchTestConnectionManager(t *testing.T, conn udp.Conn) (*connectionManager, *HostInfo) {
|
||||
l := test.NewLogger()
|
||||
hostMap := newHostMap(l)
|
||||
hostMap.preferredRanges.Store(&[]netip.Prefix{})
|
||||
|
||||
lh := newTestLighthouse()
|
||||
ifce := &Interface{
|
||||
hostMap: hostMap,
|
||||
inside: &overlaytest.NoopTun{},
|
||||
outside: &udp.NoopConn{},
|
||||
firewall: &Firewall{},
|
||||
lightHouse: lh,
|
||||
pki: &PKI{},
|
||||
handshakeManager: NewHandshakeManager(l, hostMap, lh, &udp.NoopConn{}, defaultHandshakeConfig),
|
||||
l: l,
|
||||
}
|
||||
ifce.pki.cs.Store(&CertState{
|
||||
initiatingVersion: cert.Version1,
|
||||
privateKey: []byte{},
|
||||
v1Cert: &dummyCert{version: cert.Version1},
|
||||
})
|
||||
|
||||
punchy := newPunchyForTest(t, map[string]any{"punch": true}, conn)
|
||||
nc := newConnectionManagerFromConfig(l, config.NewC(l), hostMap, punchy)
|
||||
nc.intf = ifce
|
||||
ifce.connectionManager = nc
|
||||
// Tunnel sends go through conn too, though without a key from withTestKey they never get as far as writing
|
||||
ifce.writers = []udp.Conn{conn}
|
||||
ifce.metricTxDropped = metrics.NilCounter{}
|
||||
|
||||
hostinfo := newPunchTarget()
|
||||
hostinfo.localIndexId = 1099
|
||||
hostinfo.remoteIndexId = 9901
|
||||
hostinfo.ConnectionState = &ConnectionState{myCert: &dummyCert{version: cert.Version1}}
|
||||
nc.hostMap.unlockedAddHostInfo(hostinfo, ifce)
|
||||
return nc, hostinfo
|
||||
}
|
||||
|
||||
// A tunnel we are not sending on gets punched whether or not it is receiving, the punch is the only thing that
|
||||
// would notice its remote has become unreachable.
|
||||
func Test_makeTrafficDecision_punchesWhenNotSending(t *testing.T) {
|
||||
nc, hostinfo := newPunchTestConnectionManager(t, &recordingConn{})
|
||||
now := time.Now()
|
||||
|
||||
// Receiving but not sending
|
||||
hostinfo.takeTraffic()
|
||||
nc.In(hostinfo)
|
||||
decision, _, _, punch := nc.makeTrafficDecision(hostinfo.localIndexId, now)
|
||||
assert.Equal(t, tryRehandshake, decision)
|
||||
assert.Same(t, hostinfo, punch)
|
||||
|
||||
// Sending and receiving, our own traffic keeps the NAT state alive
|
||||
nc.Out(hostinfo)
|
||||
nc.In(hostinfo)
|
||||
decision, _, _, punch = nc.makeTrafficDecision(hostinfo.localIndexId, now)
|
||||
assert.Equal(t, tryRehandshake, decision)
|
||||
assert.Nil(t, punch)
|
||||
|
||||
// Unused
|
||||
decision, decided, _, punch := nc.makeTrafficDecision(hostinfo.localIndexId, now)
|
||||
assert.Equal(t, doNothing, decision)
|
||||
assert.Nil(t, decided, "an unused tunnel has no relay usage to reset")
|
||||
assert.Same(t, hostinfo, punch)
|
||||
|
||||
// Sending but not receiving gets a test packet instead, which finds an unreachable remote on its own
|
||||
nc.Out(hostinfo)
|
||||
decision, _, _, punch = nc.makeTrafficDecision(hostinfo.localIndexId, now)
|
||||
assert.Equal(t, sendTestPacket, decision)
|
||||
assert.Nil(t, punch)
|
||||
}
|
||||
|
||||
func Test_sendPunch_probesWhenRemoteUnreachable(t *testing.T) {
|
||||
t.Run("unreachable", func(t *testing.T) {
|
||||
conn := &recordingConn{fail: map[netip.AddrPort]error{punchTargetV6: errNoRoute}}
|
||||
nc, hostinfo := newPunchTestConnectionManager(t, conn)
|
||||
|
||||
nc.sendPunch(hostinfo)
|
||||
assert.Equal(t, []netip.AddrPort{punchTargetV6}, conn.wrote)
|
||||
assert.NotZero(t, hostinfo.nextUnreachableProbe.Load(), "the tunnel should have probed its other remotes")
|
||||
assert.Equal(t, []netip.Addr{hostinfo.vpnAddrs[0]}, drainQueries(nc.intf.lightHouse),
|
||||
"the probe should ask the lighthouse to have the peer punch us")
|
||||
|
||||
// Within the probe interval nothing more goes out, however many sends fail
|
||||
nc.sendPunch(hostinfo)
|
||||
nc.sendPunch(hostinfo)
|
||||
assert.Empty(t, drainQueries(nc.intf.lightHouse))
|
||||
})
|
||||
|
||||
t.Run("delivered", func(t *testing.T) {
|
||||
conn := &recordingConn{}
|
||||
nc, hostinfo := newPunchTestConnectionManager(t, conn)
|
||||
|
||||
nc.sendPunch(hostinfo)
|
||||
assert.Equal(t, []netip.AddrPort{punchTargetV6}, conn.wrote)
|
||||
assert.Zero(t, hostinfo.nextUnreachableProbe.Load())
|
||||
assert.Empty(t, drainQueries(nc.intf.lightHouse))
|
||||
})
|
||||
|
||||
t.Run("other failure", func(t *testing.T) {
|
||||
conn := &recordingConn{fail: map[netip.AddrPort]error{punchTargetV6: io.ErrShortWrite}}
|
||||
nc, hostinfo := newPunchTestConnectionManager(t, conn)
|
||||
|
||||
nc.sendPunch(hostinfo)
|
||||
assert.Zero(t, hostinfo.nextUnreachableProbe.Load(), "only a missing route says to look elsewhere")
|
||||
assert.Empty(t, drainQueries(nc.intf.lightHouse))
|
||||
})
|
||||
}
|
||||
|
||||
// A packet the data path had no route for names its tunnel in its header, the peer's index for it
|
||||
func Test_sendUnreachable_findsTunnelFromHeader(t *testing.T) {
|
||||
head := func(st header.MessageSubType, remoteIndex uint32) []byte {
|
||||
return header.Encode(make([]byte, header.Len), header.Version, header.Message, st, remoteIndex, 1)
|
||||
}
|
||||
|
||||
t.Run("direct", func(t *testing.T) {
|
||||
nc, hostinfo := newPunchTestConnectionManager(t, &recordingConn{})
|
||||
nc.intf.sendUnreachable(head(header.MessageNone, hostinfo.remoteIndexId), punchTargetV6)
|
||||
assert.NotZero(t, hostinfo.nextUnreachableProbe.Load(), "the tunnel should have probed its other remotes")
|
||||
assert.Equal(t, []netip.Addr{hostinfo.vpnAddrs[0]}, drainQueries(nc.intf.lightHouse))
|
||||
})
|
||||
|
||||
t.Run("not its remote", func(t *testing.T) {
|
||||
nc, hostinfo := newPunchTestConnectionManager(t, &recordingConn{})
|
||||
nc.intf.sendUnreachable(head(header.MessageNone, hostinfo.remoteIndexId), punchTargetV4)
|
||||
assert.Zero(t, hostinfo.nextUnreachableProbe.Load(), "a failure on a remote the tunnel is not using is stale")
|
||||
})
|
||||
|
||||
t.Run("relayed", func(t *testing.T) {
|
||||
nc, hostinfo := newPunchTestConnectionManager(t, &recordingConn{})
|
||||
// A relay header's index is the relay session's, it must not be taken for a tunnel's even when they collide
|
||||
nc.intf.sendUnreachable(head(header.MessageRelay, hostinfo.remoteIndexId), punchTargetV6)
|
||||
assert.Zero(t, hostinfo.nextUnreachableProbe.Load())
|
||||
assert.Empty(t, drainQueries(nc.intf.lightHouse))
|
||||
})
|
||||
|
||||
t.Run("unknown tunnel", func(t *testing.T) {
|
||||
nc, hostinfo := newPunchTestConnectionManager(t, &recordingConn{})
|
||||
nc.intf.sendUnreachable(head(header.MessageNone, hostinfo.remoteIndexId+1), punchTargetV6)
|
||||
assert.Zero(t, hostinfo.nextUnreachableProbe.Load())
|
||||
})
|
||||
}
|
||||
|
||||
// withTestKey gives a tunnel a real key so its sends get encrypted and written instead of returning early
|
||||
func withTestKey(hostinfo *HostInfo) {
|
||||
cs := noise.NewCipherSuite(noise.DH25519, noise.CipherAESGCM, noise.HashSHA256)
|
||||
hostinfo.ConnectionState.eKey = noiseutil.NewCipherState(noise.UnsafeNewCipherState(cs, [32]byte{}, 0), noise.CipherAESGCM)
|
||||
}
|
||||
|
||||
// The probe itself, end to end from a failed send: a test packet to every remote but the one we cannot reach, and a
|
||||
// lighthouse query, through both places a send can fail.
|
||||
func Test_remoteUnreachable_probesOtherRemotes(t *testing.T) {
|
||||
t.Run("control send", func(t *testing.T) {
|
||||
conn := &recordingConn{fail: map[netip.AddrPort]error{punchTargetV6: errNoRoute}}
|
||||
nc, hostinfo := newPunchTestConnectionManager(t, conn)
|
||||
withTestKey(hostinfo)
|
||||
|
||||
nc.intf.SendMessageToHostInfo(header.Test, header.TestRequest, hostinfo, []byte{}, make([]byte, 12), make([]byte, mtu))
|
||||
assert.Equal(t, []netip.AddrPort{punchTargetV6, punchTargetV4}, conn.wrote, "the failed send, then the probe")
|
||||
assert.Equal(t, []header.MessageType{header.Test, header.Test}, conn.types)
|
||||
assert.Equal(t, []netip.Addr{hostinfo.vpnAddrs[0]}, drainQueries(nc.intf.lightHouse))
|
||||
})
|
||||
|
||||
t.Run("data path batch", func(t *testing.T) {
|
||||
conn := &recordingConn{fail: map[netip.AddrPort]error{punchTargetV6: errNoRoute}}
|
||||
nc, hostinfo := newPunchTestConnectionManager(t, conn)
|
||||
withTestKey(hostinfo)
|
||||
|
||||
// Two of the tunnel's packets fail in one batch, they probe once
|
||||
sb := batch.NewSendBatch(conn, 4, 4096)
|
||||
for c := uint64(1); c <= 2; c++ {
|
||||
pkt := header.Encode(sb.Reserve(64), header.Version, header.Message, header.MessageNone, hostinfo.remoteIndexId, c)
|
||||
sb.Commit(append(pkt, make([]byte, 32)...), punchTargetV6)
|
||||
}
|
||||
nc.intf.flushSendBatch(sb, 0)
|
||||
|
||||
assert.Equal(t, []netip.AddrPort{punchTargetV6, punchTargetV6, punchTargetV4}, conn.wrote,
|
||||
"the failed packets, then one probe")
|
||||
assert.Equal(t, header.Test, conn.types[2])
|
||||
assert.Equal(t, []netip.Addr{hostinfo.vpnAddrs[0]}, drainQueries(nc.intf.lightHouse))
|
||||
})
|
||||
|
||||
t.Run("closing", func(t *testing.T) {
|
||||
conn := &recordingConn{fail: map[netip.AddrPort]error{punchTargetV6: errNoRoute}}
|
||||
nc, hostinfo := newPunchTestConnectionManager(t, conn)
|
||||
withTestKey(hostinfo)
|
||||
|
||||
nc.intf.SendMessageToHostInfo(header.CloseTunnel, 0, hostinfo, []byte{}, make([]byte, 12), make([]byte, mtu))
|
||||
assert.Equal(t, []netip.AddrPort{punchTargetV6}, conn.wrote, "a tunnel being torn down does not probe")
|
||||
assert.Empty(t, drainQueries(nc.intf.lightHouse))
|
||||
})
|
||||
|
||||
t.Run("lighthouse", func(t *testing.T) {
|
||||
conn := &recordingConn{fail: map[netip.AddrPort]error{punchTargetV6: errNoRoute}}
|
||||
nc, hostinfo := newPunchTestConnectionManager(t, conn)
|
||||
withTestKey(hostinfo)
|
||||
nc.intf.lightHouse.amLighthouse = true
|
||||
|
||||
nc.intf.SendMessageToHostInfo(header.Test, header.TestRequest, hostinfo, []byte{}, make([]byte, 12), make([]byte, mtu))
|
||||
assert.Equal(t, []netip.AddrPort{punchTargetV6}, conn.wrote, "a lighthouse does not roam its clients")
|
||||
})
|
||||
|
||||
t.Run("nothing else to probe", func(t *testing.T) {
|
||||
conn := &recordingConn{fail: map[netip.AddrPort]error{punchTargetV6: errNoRoute}}
|
||||
nc, hostinfo := newPunchTestConnectionManager(t, conn)
|
||||
withTestKey(hostinfo)
|
||||
nc.intf.reQueryWait.Store(int64(time.Minute))
|
||||
// Forget the IPv4 remote, all the tunnel knows is the one it cannot reach
|
||||
hostinfo.remotes = NewRemoteList(hostinfo.vpnAddrs, nil)
|
||||
hostinfo.remotes.LearnRemote(hostinfo.vpnAddrs[0], punchTargetV6)
|
||||
|
||||
nc.intf.SendMessageToHostInfo(header.Test, header.TestRequest, hostinfo, []byte{}, make([]byte, 12), make([]byte, mtu))
|
||||
assert.Equal(t, []netip.Addr{hostinfo.vpnAddrs[0]}, drainQueries(nc.intf.lightHouse),
|
||||
"the lighthouse is the only way to learn of another remote")
|
||||
|
||||
// Past the probe interval, but the lighthouse is only asked again on the requery schedule
|
||||
hostinfo.nextUnreachableProbe.Store(0)
|
||||
nc.intf.SendMessageToHostInfo(header.Test, header.TestRequest, hostinfo, []byte{}, make([]byte, 12), make([]byte, mtu))
|
||||
assert.Empty(t, drainQueries(nc.intf.lightHouse))
|
||||
assert.Equal(t, []netip.AddrPort{punchTargetV6, punchTargetV6}, conn.wrote)
|
||||
})
|
||||
}
|
||||
|
||||
// drainQueries returns every lighthouse query waiting to go out
|
||||
func drainQueries(lh *LightHouse) []netip.Addr {
|
||||
var queries []netip.Addr
|
||||
for {
|
||||
select {
|
||||
case addr := <-lh.queryChan:
|
||||
queries = append(queries, addr)
|
||||
default:
|
||||
return queries
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -2,8 +2,6 @@ package nebula
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"strconv"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
@@ -13,7 +11,6 @@ import (
|
||||
ct "github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/handshake"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/overlay"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/assert"
|
||||
@@ -150,122 +147,6 @@ func TestSendNoMetricsCloseTunnelKeepsRebindEpoch(t *testing.T) {
|
||||
assert.True(t, hostinfo.markOut(1), "a CloseTunnel send must not consume the rebind epoch")
|
||||
}
|
||||
|
||||
// capturingConn is a udp.Conn that records every WriteTo.
|
||||
type capturingConn struct {
|
||||
udp.NoopConn
|
||||
writes [][]byte
|
||||
addrs []netip.AddrPort
|
||||
}
|
||||
|
||||
func (c *capturingConn) WriteTo(b []byte, addr netip.AddrPort) error {
|
||||
c.writes = append(c.writes, append([]byte(nil), b...))
|
||||
c.addrs = append(c.addrs, addr)
|
||||
return nil
|
||||
}
|
||||
|
||||
// TestSendNoMetricsViaRelay sends through a relay from the mtu sized buffer the cached packet flush uses. Payloads up
|
||||
// to overlay.MaxMTU go out intact, anything bigger is dropped rather than outgrowing the buffer, which once panicked.
|
||||
func TestSendNoMetricsViaRelay(t *testing.T) {
|
||||
tests := []struct {
|
||||
n int
|
||||
sent bool
|
||||
}{
|
||||
{0, true},
|
||||
{1300, true},
|
||||
{overlay.MaxMTU, true},
|
||||
{overlay.MaxMTU + 1, false}, // too big for the relay's tag
|
||||
{mtu - 47, false}, // too big for the inner tag, this panicked
|
||||
{9000, false}, // a full packet at tun.mtu 9000
|
||||
}
|
||||
for _, tt := range tests {
|
||||
t.Run(strconv.Itoa(tt.n), func(t *testing.T) {
|
||||
// One tunnel to the target, carried end to end, and one to the relay that wraps it
|
||||
targetInit, targetResp := runTestHandshake(t)
|
||||
relayInit, relayResp := runTestHandshake(t)
|
||||
ci, err := newConnectionStateFromResult(targetInit)
|
||||
require.NoError(t, err)
|
||||
relayCI, err := newConnectionStateFromResult(relayInit)
|
||||
require.NoError(t, err)
|
||||
|
||||
targetAddr := netip.MustParseAddr("10.0.0.2")
|
||||
relayAddr := netip.MustParseAddr("10.0.0.3")
|
||||
relayRemote := netip.MustParseAddrPort("192.0.2.1:4242")
|
||||
|
||||
relay := &Relay{Type: TerminalType, State: Established, LocalIndex: 5, RemoteIndex: 6, PeerAddr: targetAddr}
|
||||
relayHI := &HostInfo{
|
||||
vpnAddrs: []netip.Addr{relayAddr},
|
||||
ConnectionState: relayCI,
|
||||
relayState: RelayState{
|
||||
relayForByAddr: map[netip.Addr]*Relay{targetAddr: relay},
|
||||
relayForByIdx: map[uint32]*Relay{relay.LocalIndex: relay},
|
||||
},
|
||||
}
|
||||
relayHI.remote.Store(&relayRemote)
|
||||
|
||||
// No remote of its own, so the send has to go via the relay
|
||||
hostinfo := &HostInfo{
|
||||
vpnAddrs: []netip.Addr{targetAddr},
|
||||
ConnectionState: ci,
|
||||
remoteIndexId: 7,
|
||||
relayState: RelayState{
|
||||
relays: []netip.Addr{relayAddr},
|
||||
relayForByAddr: map[netip.Addr]*Relay{},
|
||||
relayForByIdx: map[uint32]*Relay{},
|
||||
},
|
||||
}
|
||||
|
||||
l := test.NewLogger()
|
||||
hm := newHostMap(l)
|
||||
hm.Hosts[relayAddr] = relayHI
|
||||
conn := &capturingConn{}
|
||||
f := &Interface{
|
||||
l: l,
|
||||
hostMap: hm,
|
||||
messageMetrics: &MessageMetrics{txExhausted: metrics.NewCounter()},
|
||||
writers: []udp.Conn{conn},
|
||||
}
|
||||
f.connectionManager = &connectionManager{intf: f, relayUsed: map[uint32]struct{}{}, relayUsedLock: &sync.RWMutex{}}
|
||||
|
||||
payload := make([]byte, tt.n)
|
||||
for i := range payload {
|
||||
payload[i] = byte(i)
|
||||
}
|
||||
counter := ci.messageCounter.Load()
|
||||
f.sendNoMetrics(header.Message, 0, ci, hostinfo, netip.AddrPort{}, payload, make([]byte, 12), make([]byte, mtu), 0)
|
||||
|
||||
if !tt.sent {
|
||||
assert.Empty(t, conn.writes)
|
||||
assert.Equal(t, counter, ci.messageCounter.Load(), "a dropped packet must not spend a counter")
|
||||
return
|
||||
}
|
||||
require.Len(t, conn.writes, 1)
|
||||
assert.Equal(t, relayRemote, conn.addrs[0])
|
||||
pkt := conn.writes[0]
|
||||
|
||||
// The relay authenticates the whole packet under its own header
|
||||
outer := &header.H{}
|
||||
require.NoError(t, outer.Parse(pkt))
|
||||
assert.Equal(t, header.MessageRelay, outer.Subtype)
|
||||
assert.Equal(t, relay.RemoteIndex, outer.RemoteIndex)
|
||||
relayPeer, err := newConnectionStateFromResult(relayResp)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, relayPeer.VerifyRelay(l, outer.MessageCounter, pkt, make([]byte, 12)))
|
||||
|
||||
// Inside it, the target decrypts the end to end packet back to the payload
|
||||
inner := pkt[header.Len : len(pkt)-relayPeer.dKey.Overhead()]
|
||||
h := &header.H{}
|
||||
require.NoError(t, h.Parse(inner))
|
||||
assert.Equal(t, header.Message, h.Type)
|
||||
assert.Equal(t, hostinfo.remoteIndexId, h.RemoteIndex)
|
||||
targetPeer, err := newConnectionStateFromResult(targetResp)
|
||||
require.NoError(t, err)
|
||||
got, err := targetPeer.Decrypt(l, h.MessageCounter, inner, make([]byte, 12))
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, payload, got)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestNewConnectionStateFromResult(t *testing.T) {
|
||||
initR, respR := runTestHandshake(t)
|
||||
|
||||
|
||||
@@ -11,7 +11,6 @@ import (
|
||||
"syscall"
|
||||
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/commands"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/overlay"
|
||||
)
|
||||
@@ -48,7 +47,6 @@ type Control struct {
|
||||
|
||||
f *Interface
|
||||
l *slog.Logger
|
||||
commands *commands.Registry
|
||||
ctx context.Context
|
||||
cancel context.CancelFunc
|
||||
sshStart func()
|
||||
@@ -374,13 +372,6 @@ func (c *Control) CloseAllTunnels(excludeLighthouses bool) (closed int) {
|
||||
return
|
||||
}
|
||||
|
||||
// Commands returns the registry the daemon's surfaces serve from. It is the live
|
||||
// registry, not a copy: a command registered on it is served to every ssh session that
|
||||
// starts afterwards. Clone it to run commands without that reach.
|
||||
func (c *Control) Commands() *commands.Registry {
|
||||
return c.commands
|
||||
}
|
||||
|
||||
func (c *Control) Device() overlay.Device {
|
||||
return c.f.inside
|
||||
}
|
||||
|
||||
@@ -148,12 +148,12 @@ func (c *fakeConn) Rebind() error { c.rebinds++; ret
|
||||
func (c *fakeConn) LocalAddr() (netip.AddrPort, error) { return netip.AddrPort{}, nil }
|
||||
func (c *fakeConn) ListenOut(_ udp.EncReader, _ func()) error { return nil }
|
||||
func (c *fakeConn) WriteTo(_ []byte, _ netip.AddrPort) error { return nil }
|
||||
func (c *fakeConn) WriteBatch(bufs [][]byte, _ []netip.AddrPort, _ func(int, error)) (int, error) {
|
||||
func (c *fakeConn) WriteBatch(bufs [][]byte, _ []netip.AddrPort) (int, error) {
|
||||
return len(bufs), nil
|
||||
}
|
||||
func (c *fakeConn) ReloadConfig(_ *config.C, _ *config.Reload) {}
|
||||
func (c *fakeConn) SupportsMultipleReaders() bool { return true }
|
||||
func (c *fakeConn) Close() error { c.closed = true; return nil }
|
||||
func (c *fakeConn) ReloadConfig(_ *config.C) {}
|
||||
func (c *fakeConn) SupportsMultipleReaders() bool { return true }
|
||||
func (c *fakeConn) Close() error { c.closed = true; return nil }
|
||||
|
||||
type multiqueueDevice struct {
|
||||
*fakeDevice
|
||||
|
||||
@@ -117,18 +117,6 @@ func (c *Control) SetUDPAddr(addr netip.AddrPort) {
|
||||
c.f.outside.(*udp.TesterConn).SetAddr(addr)
|
||||
}
|
||||
|
||||
// GetUDPAddrFor returns the underlay address this node sends to dst from, which differs by family for a dual stack node
|
||||
func (c *Control) GetUDPAddrFor(dst netip.AddrPort) netip.AddrPort {
|
||||
return c.f.outside.(*udp.TesterConn).GetAddrFor(dst)
|
||||
}
|
||||
|
||||
// SetDualStackUDPAddrs gives this node one underlay address per family, sending from whichever matches the
|
||||
// destination. An invalid AddrPort leaves the node without that family, sends to it fail with ENETUNREACH. Register
|
||||
// any address the node did not start on with the router as well or nothing will route back.
|
||||
func (c *Control) SetDualStackUDPAddrs(v4, v6 netip.AddrPort) {
|
||||
c.f.outside.(*udp.TesterConn).SetDualStackAddrs(v4, v6)
|
||||
}
|
||||
|
||||
// SetLocalAddrsFn replaces underlay address discovery so a test can advertise its simulated address instead of
|
||||
// whatever this machine's NICs happen to be. Call it before Start, SendUpdate reads it from the update worker.
|
||||
func (c *Control) SetLocalAddrsFn(fn func(*LocalAllowList) []netip.Addr) {
|
||||
|
||||
+1
-2
@@ -69,10 +69,9 @@ func newDnsServerFromConfig(ctx context.Context, l *slog.Logger, pki *PKI, hostM
|
||||
ds.mux = dns.NewServeMux()
|
||||
ds.mux.HandleFunc(".", ds.handleDnsRequest)
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
if err := ds.reload(c, false); err != nil {
|
||||
ds.l.Error("Failed to reload DNS responder from config", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
|
||||
@@ -1,164 +0,0 @@
|
||||
//go:build e2e_testing
|
||||
|
||||
package e2e
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"path/filepath"
|
||||
"regexp"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/commands"
|
||||
"github.com/slackhq/nebula/sshd"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// volatile lists everything in command output that legitimately differs between runs.
|
||||
// Each run mints fresh certificates and indexes, so these are replaced with a marker
|
||||
// before comparison. Keep the list short: anything added here is something the golden
|
||||
// stops guarding.
|
||||
var volatile = []struct {
|
||||
re *regexp.Regexp
|
||||
with string
|
||||
}{
|
||||
{regexp.MustCompile(`[0-9a-f]{40,}`), "<hex>"}, // fingerprints, keys, signatures
|
||||
{regexp.MustCompile(`\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(?:\.\d+)?(?:Z|[+-]\d{2}:\d{2})`), "<time>"}, // RFC 3339
|
||||
{regexp.MustCompile(`\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}(?:\.\d+)? [+-]\d{4} \w+`), "<time>"}, // time.Time.String()
|
||||
{regexp.MustCompile(`(?s)(-----BEGIN [A-Z ]+-----\n).*?(\n-----END [A-Z ]+-----)`), "${1}<pem>${2}"}, // print-cert -raw
|
||||
{regexp.MustCompile(`(-----BEGIN [A-Z ]+-----\\n).*?(\\n-----END [A-Z ]+-----)`), "${1}<pem>${2}"}, // the same, inside a JSON string
|
||||
{regexp.MustCompile(`"(localIndex|remoteIndex|messageCounter)":\d+`), `"$1":<n>`},
|
||||
{regexp.MustCompile(`(?m)^(\s*"?(?:LocalIndex|RemoteIndex|localIndex|remoteIndex|messageCounter)"?:?\s*)\d+`), "${1}<n>"}, // and the -pretty form
|
||||
}
|
||||
|
||||
func normalise(s string) string {
|
||||
for _, v := range volatile {
|
||||
s = v.re.ReplaceAllString(s, v.with)
|
||||
}
|
||||
return s
|
||||
}
|
||||
|
||||
// outputCase is one command line to run through the ssh dispatch path.
|
||||
type outputCase struct {
|
||||
name string
|
||||
args []string
|
||||
}
|
||||
|
||||
// TestCommandOutput pins the bytes every command produces, in every format, through the
|
||||
// ssh dispatch path. It is the safety net for moving rendering out of the commands: a
|
||||
// change here is a change someone at an ssh prompt would see. Regenerate with:
|
||||
//
|
||||
// go test -tags e2e_testing ./e2e -run TestCommandOutput -update
|
||||
func TestCommandOutput(t *testing.T) {
|
||||
ca, _, caKey, _ := cert_test.NewTestCaCert(
|
||||
cert.Version1, cert.Curve_CURVE25519,
|
||||
time.Now(), time.Now().Add(10*time.Minute),
|
||||
nil, nil, []string{},
|
||||
)
|
||||
|
||||
control, _, _, _ := newSimpleServer(cert.Version1, ca, caKey, "output-golden", "10.222.0.1/24", nil)
|
||||
control.Start()
|
||||
t.Cleanup(func() { control.Stop() })
|
||||
|
||||
// As an ssh session does: a clone of the daemon's registry with logout added, which
|
||||
// help on the clone lists and describes. There is no session to end here.
|
||||
reg := control.Commands().Clone()
|
||||
reg.Register(sshd.LogoutCommand(func() {}))
|
||||
|
||||
// run dispatches as the ssh exec path does and returns the output and the error, which
|
||||
// over ssh is exit status 1.
|
||||
run := func(args ...string) (string, error) {
|
||||
buf := &bytes.Buffer{}
|
||||
err := reg.DispatchArgs(args, commands.NewStringWriter(buf))
|
||||
return buf.String(), err
|
||||
}
|
||||
|
||||
// Seed a pending tunnel so the listing and per-address commands have something to show.
|
||||
seed, err := run("create-tunnel", "10.222.0.9")
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, "Created\n", seed, "seeding a tunnel should succeed before anything else is recorded")
|
||||
|
||||
cases := []outputCase{
|
||||
{"version", nil},
|
||||
{"device-info", nil},
|
||||
{"list-hostmap", nil},
|
||||
{"list-hostmap", []string{"-by-index"}},
|
||||
{"list-pending-hostmap", nil},
|
||||
{"list-pending-hostmap", []string{"-by-index"}},
|
||||
{"list-lighthouse-addrmap", nil},
|
||||
{"print-cert", nil},
|
||||
{"print-cert", []string{"-raw"}},
|
||||
{"print-cert", []string{"10.222.0.9"}},
|
||||
{"print-cert", []string{"10.222.0.250"}},
|
||||
{"print-cert", []string{"not-an-address"}},
|
||||
{"print-tunnel", nil},
|
||||
{"print-tunnel", []string{"10.222.0.9"}},
|
||||
{"print-tunnel", []string{"10.222.0.250"}},
|
||||
{"print-relays", nil},
|
||||
{"query-lighthouse", nil},
|
||||
{"query-lighthouse", []string{"10.222.0.9"}},
|
||||
{"query-lighthouse", []string{"not-an-address"}},
|
||||
// The test logger cannot change level or format, so these cases record the
|
||||
// refusal each command prints on it, not a successful change.
|
||||
{"log-level", nil},
|
||||
{"log-level", []string{"debug"}},
|
||||
{"log-level", []string{"bogus"}},
|
||||
{"log-level", []string{"info"}},
|
||||
{"log-format", nil},
|
||||
{"log-format", []string{"json"}},
|
||||
{"log-format", []string{"text"}},
|
||||
{"change-remote", nil},
|
||||
{"change-remote", []string{"10.222.0.9"}},
|
||||
{"change-remote", []string{"-address", "10.94.0.10:4242", "10.222.0.9"}},
|
||||
{"change-remote", []string{"-address", "10.94.0.10:4242", "10.222.0.250"}},
|
||||
{"create-tunnel", nil},
|
||||
{"create-tunnel", []string{"10.222.0.9"}},
|
||||
// A fresh address, so this exercises the handshake start with a remote attached
|
||||
// rather than the "already handshaking" path above.
|
||||
{"create-tunnel", []string{"-address", "10.94.0.10:4242", "10.222.0.10"}},
|
||||
{"create-tunnel", []string{"not-an-address"}},
|
||||
{"close-tunnel", nil},
|
||||
{"close-tunnel", []string{"10.222.0.250"}},
|
||||
{"close-tunnel", []string{"not-an-address"}},
|
||||
{"help", nil},
|
||||
{"help", []string{"print-cert"}},
|
||||
{"help", []string{"logout"}},
|
||||
{"logout", []string{"-h"}},
|
||||
{"not-a-command", []string{"10.222.0.9"}},
|
||||
// reload is last so that whatever a reload does to the daemon cannot leak into an
|
||||
// earlier case. In this harness it fails: the config was loaded from a string and
|
||||
// has no path to re-read, which is what the recorded result says.
|
||||
{"reload", nil},
|
||||
}
|
||||
|
||||
got := &strings.Builder{}
|
||||
for _, c := range cases {
|
||||
for _, fmtFlags := range [][]string{nil, {"-json"}, {"-pretty"}} {
|
||||
args := append([]string{c.name}, fmtFlags...)
|
||||
args = append(args, c.args...)
|
||||
|
||||
fmt.Fprintf(got, "$ %s\n", strings.Join(args, " "))
|
||||
out, err := run(args...)
|
||||
out = normalise(out)
|
||||
got.WriteString(out)
|
||||
// Output that does not end in a newline is recorded as such, the way diff marks
|
||||
// it, so the golden sees that byte too and the next prompt still starts a line.
|
||||
if out != "" && !strings.HasSuffix(out, "\n") {
|
||||
got.WriteString("\\ No newline at end of output\n")
|
||||
}
|
||||
// A failed command is recorded as the exit status an ssh caller sees, so the
|
||||
// golden pins which outcomes count as failures.
|
||||
if err != nil {
|
||||
got.WriteString("exit status 1\n")
|
||||
}
|
||||
got.WriteString("\n")
|
||||
}
|
||||
}
|
||||
|
||||
test.Golden(t, filepath.Join("testdata", "commands_output.golden"), got.String())
|
||||
}
|
||||
@@ -1,305 +0,0 @@
|
||||
//go:build e2e_testing
|
||||
|
||||
package e2e
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"sync/atomic"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/e2e/router"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
)
|
||||
|
||||
// TestDualStackRoamToV4Only measures how long a laptop's tunnels take to come back after it moves from a dual stack
|
||||
// network, where its tunnels formed over IPv6, to one with no IPv6 service at all: the office to hotel wifi. Every
|
||||
// peer still has an IPv4 address the laptop can reach, so nothing about the move should strand a tunnel.
|
||||
//
|
||||
// It is a measurement, not a pass/fail assertion, and it runs on the production connection manager timers.
|
||||
//
|
||||
// go test -tags e2e_testing -v -run TestDualStackRoamToV4Only ./e2e/
|
||||
func TestDualStackRoamToV4Only(t *testing.T) {
|
||||
for _, tc := range []dualStackRoamCase{
|
||||
{name: "both send", meSends: true, themSends: true},
|
||||
{name: "both send, rebind", meSends: true, themSends: true, rebind: true},
|
||||
{name: "both send, two tunnels", meSends: true, themSends: true, simultaneous: true},
|
||||
{name: "laptop sends", meSends: true},
|
||||
{name: "peer sends", themSends: true},
|
||||
{name: "peer sends, rebind", themSends: true, rebind: true},
|
||||
{name: "peer sends, lh over v4", themSends: true, lhOverV4: true},
|
||||
{name: "peer sends, punchy", themSends: true, punchy: true},
|
||||
{name: "peer sends, punchy all", themSends: true, punchy: true, punchAll: true},
|
||||
{name: "laptop sends, peer NAT", meSends: true, peerNAT: true},
|
||||
{name: "laptop sends, peer NAT, lh v4", meSends: true, peerNAT: true, lhOverV4: true},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
t.Parallel()
|
||||
fwd, rev := measureDualStackRoam(t, tc)
|
||||
t.Logf("RESULT %-24s laptop->peer %-9v peer->laptop %-9v", tc.name, fmtRecovery(fwd), fmtRecovery(rev))
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestDualStackRoamRecovers holds the line TestDualStackRoamToV4Only measures: a tunnel whose remote became unreachable
|
||||
// moves to the peer's other address instead of waiting out the connection manager to rehandshake, which takes 20s.
|
||||
func TestDualStackRoamRecovers(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
dualStackRoamCase
|
||||
// within bounds recovery in each direction that has traffic
|
||||
within time.Duration
|
||||
}{
|
||||
// Measures 0.4s. Under the 5s connection manager check, so it fails if the data path stops probing.
|
||||
{dualStackRoamCase{name: "both send", meSends: true, themSends: true}, 2 * time.Second},
|
||||
// Measures 2.6s or 3.8s, depending on whether a probe beats the peer's punch. Half the 20s it used to take.
|
||||
{dualStackRoamCase{name: "laptop sends, peer NAT", meSends: true, peerNAT: true}, 10 * time.Second},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
t.Parallel()
|
||||
fwd, rev := measureDualStackRoam(t, tc.dualStackRoamCase)
|
||||
if fwd == 0 || fwd > tc.within {
|
||||
t.Errorf("laptop->peer recovered in %v, want within %v", fmtRecovery(fwd), tc.within)
|
||||
}
|
||||
if tc.themSends && (rev == 0 || rev > tc.within) {
|
||||
t.Errorf("peer->laptop recovered in %v, want within %v", fmtRecovery(rev), tc.within)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
type dualStackRoamCase struct {
|
||||
name string
|
||||
// meSends and themSends say who keeps traffic flowing after the move
|
||||
meSends, themSends bool
|
||||
// rebind fires RebindUDPServer on the move, as the darwin network change monitor would
|
||||
rebind bool
|
||||
// lhOverV4 forms the lighthouse tunnel over IPv4 at the office, so the move does not break it
|
||||
lhOverV4 bool
|
||||
// simultaneous has both sides initiate at once at the office, which can leave each side a different primary
|
||||
// tunnel for the other
|
||||
simultaneous bool
|
||||
// punchy turns on punchy.punch everywhere, punchAll adds punchy.target_all_remotes
|
||||
punchy, punchAll bool
|
||||
// peerNAT puts the peer behind a NAT that, after the move, only lets in traffic from addresses the peer has sent to
|
||||
peerNAT bool
|
||||
}
|
||||
|
||||
func fmtRecovery(d time.Duration) string {
|
||||
if d == 0 {
|
||||
return "never"
|
||||
}
|
||||
return d.Round(time.Millisecond).String()
|
||||
}
|
||||
|
||||
type dualStackNode struct {
|
||||
c *nebula.Control
|
||||
vpnAddr netip.Addr
|
||||
v4, v6 netip.AddrPort
|
||||
adv atomic.Pointer[[]netip.Addr]
|
||||
}
|
||||
|
||||
// move puts the node on a new network, advertising only what it can be reached on there
|
||||
func (n *dualStackNode) move(v4, v6 netip.AddrPort) {
|
||||
n.v4, n.v6 = v4, v6
|
||||
n.c.SetDualStackUDPAddrs(v4, v6)
|
||||
var adv []netip.Addr
|
||||
for _, a := range []netip.AddrPort{v4, v6} {
|
||||
if a.IsValid() {
|
||||
adv = append(adv, a.Addr())
|
||||
}
|
||||
}
|
||||
n.adv.Store(&adv)
|
||||
}
|
||||
|
||||
func newDualStackNode(ca cert.Certificate, caKey []byte, name, vpnNet string, v4, v6 netip.AddrPort, overrides m) *dualStackNode {
|
||||
c, vpnNets, _, _ := newSimpleServerWithUdp(cert.Version2, ca, caKey, name, vpnNet, v4, overrides)
|
||||
n := &dualStackNode{c: c, vpnAddr: vpnNets[0].Addr()}
|
||||
n.move(v4, v6)
|
||||
c.SetLocalAddrsFn(func(*nebula.LocalAllowList) []netip.Addr {
|
||||
return *n.adv.Load()
|
||||
})
|
||||
return n
|
||||
}
|
||||
|
||||
// measureDualStackRoam returns how long after the move the first packet made it laptop->peer and peer->laptop, zero
|
||||
// for a direction that never recovered.
|
||||
func measureDualStackRoam(t *testing.T, tc dualStackRoamCase) (time.Duration, time.Duration) {
|
||||
t.Helper()
|
||||
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
|
||||
|
||||
ap := netip.MustParseAddrPort
|
||||
lhV4, lhV6 := ap("10.0.0.1:4242"), ap("[fd00::1]:4242")
|
||||
lh := newDualStackNode(ca, caKey, "lh", "10.128.0.1/24", lhV4, lhV6, m{
|
||||
"lighthouse": m{"am_lighthouse": true},
|
||||
})
|
||||
|
||||
// Production timers rather than the 2s the harness defaults to, this is about how long a real laptop waits
|
||||
peerCfg := m{
|
||||
"lighthouse": m{
|
||||
"hosts": []any{lh.vpnAddr.String()},
|
||||
"interval": 10,
|
||||
},
|
||||
"static_host_map": m{
|
||||
lh.vpnAddr.String(): []any{lhV4.String(), lhV6.String()},
|
||||
},
|
||||
"timers": m{
|
||||
"connection_alive_interval": 5,
|
||||
"pending_deletion_interval": 10,
|
||||
},
|
||||
"punchy": m{
|
||||
"punch": tc.punchy,
|
||||
"target_all_remotes": tc.punchAll,
|
||||
},
|
||||
}
|
||||
|
||||
me := newDualStackNode(ca, caKey, "me", "10.128.0.2/24", ap("10.0.0.2:4242"), ap("[fd00::2]:4242"), peerCfg)
|
||||
them := newDualStackNode(ca, caKey, "them", "10.128.0.3/24", ap("10.0.0.3:4242"), ap("[fd00::3]:4242"), peerCfg)
|
||||
|
||||
r := router.NewR(t, lh.c, me.c, them.c)
|
||||
r.CancelFlowLogs()
|
||||
for _, n := range []*dualStackNode{lh, me, them} {
|
||||
r.AddRoute(n.v6.Addr(), n.v6.Port(), n.c)
|
||||
}
|
||||
defer func() {
|
||||
lh.c.Stop()
|
||||
me.c.Stop()
|
||||
them.c.Stop()
|
||||
}()
|
||||
|
||||
lh.c.Start()
|
||||
me.c.Start()
|
||||
them.c.Start()
|
||||
|
||||
// At the office IPv6 wins every race, so everything forms over it. The lighthouse tunnel optionally does not,
|
||||
// for a static_host_map that only lists the lighthouse's IPv4 address.
|
||||
officeV6 := func(p *udp.Packet, _ *nebula.Control) router.ExitType {
|
||||
lhTraffic := p.To == lhV4 || p.To == lhV6 || p.From == lhV4 || p.From == lhV6
|
||||
if p.To.Addr().Is4() == (tc.lhOverV4 && lhTraffic) {
|
||||
return router.KeepRouting
|
||||
}
|
||||
return router.Drop
|
||||
}
|
||||
r.RouteForAllExitFuncOrTimeout(time.Second, officeV6)
|
||||
|
||||
// One side at a time, so both sides hold the same single tunnel, unless the case wants them racing
|
||||
me.c.InjectTunPacket(BuildTunUDPPacket(them.vpnAddr, 80, me.vpnAddr, 80, []byte("establish")))
|
||||
if !tc.simultaneous {
|
||||
r.RouteForAllExitFuncOrTimeout(time.Second, officeV6)
|
||||
}
|
||||
them.c.InjectTunPacket(BuildTunUDPPacket(me.vpnAddr, 80, them.vpnAddr, 80, []byte("establish")))
|
||||
r.RouteForAllExitFuncOrTimeout(time.Second, officeV6)
|
||||
if tc.simultaneous && me.c.GetHostmapIndexCount() < 3 {
|
||||
// A tunnel to the lighthouse and two to the peer, or the race did not happen
|
||||
t.Logf("simultaneous handshakes settled on a single tunnel this run")
|
||||
}
|
||||
drainTun(me.c)
|
||||
drainTun(them.c)
|
||||
|
||||
for _, want := range []struct {
|
||||
name string
|
||||
c *nebula.Control
|
||||
vpnAddr netip.Addr
|
||||
v6 bool
|
||||
}{
|
||||
{"laptop->peer", me.c, them.vpnAddr, true},
|
||||
{"peer->laptop", them.c, me.vpnAddr, true},
|
||||
{"laptop->lh", me.c, lh.vpnAddr, !tc.lhOverV4},
|
||||
} {
|
||||
hi := want.c.GetHostInfoByVpnAddr(want.vpnAddr, false)
|
||||
if hi == nil {
|
||||
t.Fatalf("%s: no tunnel at the office", want.name)
|
||||
}
|
||||
if hi.CurrentRemote.Addr().Is6() != want.v6 {
|
||||
t.Fatalf("%s: tunnel formed over %v, the scenario wants v6=%v", want.name, hi.CurrentRemote, want.v6)
|
||||
}
|
||||
}
|
||||
|
||||
// Hotel wifi: a new NAT'd IPv4 address and no IPv6 at all. The office addresses are gone, nothing reaches them.
|
||||
officeV4, officeV6Addr := me.v4, me.v6
|
||||
hotel := ap("10.0.0.99:4242")
|
||||
me.move(hotel, netip.AddrPort{})
|
||||
r.AddRoute(hotel.Addr(), hotel.Port(), me.c)
|
||||
|
||||
start := time.Now()
|
||||
if tc.rebind {
|
||||
me.c.RebindUDPServer()
|
||||
}
|
||||
|
||||
var fwd, rev atomic.Int64
|
||||
stop := make(chan struct{})
|
||||
defer close(stop)
|
||||
watchTun(them.c, stop, start, &fwd)
|
||||
watchTun(me.c, stop, start, &rev)
|
||||
|
||||
go func() {
|
||||
tick := time.NewTicker(time.Millisecond * 200)
|
||||
defer tick.Stop()
|
||||
for {
|
||||
select {
|
||||
case <-stop:
|
||||
return
|
||||
case <-tick.C:
|
||||
if tc.meSends {
|
||||
me.c.InjectTunPacket(BuildTunUDPPacket(them.vpnAddr, 80, me.vpnAddr, 80, []byte("retry")))
|
||||
}
|
||||
if tc.themSends {
|
||||
them.c.InjectTunPacket(BuildTunUDPPacket(me.vpnAddr, 80, them.vpnAddr, 80, []byte("retry")))
|
||||
}
|
||||
}
|
||||
}
|
||||
}()
|
||||
|
||||
// When only one side has traffic, the other direction recovering is a bonus we still report but do not wait for
|
||||
done := func() bool {
|
||||
return (!tc.meSends || fwd.Load() != 0) && (!tc.themSends || rev.Load() != 0)
|
||||
}
|
||||
// The peer's NAT has state for the lighthouse, which its own updates keep fresh, and for wherever it sends from here
|
||||
natOpen := map[netip.AddrPort]bool{lhV4: true, lhV6: true}
|
||||
isPeer := func(a netip.AddrPort) bool { return a == them.v4 || a == them.v6 }
|
||||
|
||||
r.RouteForAllExitFuncOrTimeout(time.Second*90, func(p *udp.Packet, _ *nebula.Control) router.ExitType {
|
||||
if p.To == officeV4 || p.To == officeV6Addr {
|
||||
return router.Drop
|
||||
}
|
||||
if tc.peerNAT {
|
||||
if isPeer(p.From) {
|
||||
natOpen[p.To] = true
|
||||
} else if isPeer(p.To) && !natOpen[p.From] {
|
||||
return router.Drop
|
||||
}
|
||||
}
|
||||
if done() {
|
||||
return router.ExitNow
|
||||
}
|
||||
return router.KeepRouting
|
||||
})
|
||||
|
||||
return time.Duration(fwd.Load()), time.Duration(rev.Load())
|
||||
}
|
||||
|
||||
func drainTun(c *nebula.Control) {
|
||||
for {
|
||||
select {
|
||||
case <-c.GetTunTxChan():
|
||||
default:
|
||||
return
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// watchTun records how long after start the first packet came out of c's tun, and keeps the tun drained after
|
||||
func watchTun(c *nebula.Control, stop chan struct{}, start time.Time, first *atomic.Int64) {
|
||||
go func() {
|
||||
for {
|
||||
select {
|
||||
case <-stop:
|
||||
return
|
||||
case <-c.GetTunTxChan():
|
||||
first.CompareAndSwap(0, int64(time.Since(start)))
|
||||
}
|
||||
}
|
||||
}()
|
||||
}
|
||||
@@ -1513,7 +1513,7 @@ func TestLighthouseUpdateOnReload(t *testing.T) {
|
||||
// Reload the config. The lighthouse.hosts change triggers TriggerUpdate,
|
||||
// which wakes the update worker. It calls SendUpdate, initiating a
|
||||
// handshake to the new lighthouse and caching the HostUpdateNotification.
|
||||
require.NoError(t, myConfig.ReloadConfigString(string(newCfg)).Err)
|
||||
require.NoError(t, myConfig.ReloadConfigString(string(newCfg)))
|
||||
|
||||
// Route until the lighthouse receives the HostUpdateNotification.
|
||||
// This covers: handshake stage 1, stage 2, then the cached update.
|
||||
|
||||
+13
-14
@@ -497,10 +497,11 @@ func (r *R) RouteUntilTxTun(sender *nebula.Control, receiver *nebula.Control) []
|
||||
// Nope, lets push the sender along
|
||||
case p := <-udpTx:
|
||||
r.Lock()
|
||||
c := r.getControl(p)
|
||||
a := sender.GetUDPAddr()
|
||||
c := r.getControl(a, p.To, p)
|
||||
if c == nil {
|
||||
r.Unlock()
|
||||
panic("No control for udp tx " + p.To.String())
|
||||
panic("No control for udp tx " + a.String())
|
||||
}
|
||||
fp := r.unlockedInjectFlow(sender, c, p, false)
|
||||
c.InjectUDPPacket(p) // copies internally; original is ours to release
|
||||
@@ -621,7 +622,8 @@ func (r *R) stopFanInWorkers() {
|
||||
func (r *R) routeUDP(from *nebula.Control, p *udp.Packet) {
|
||||
r.Lock()
|
||||
defer r.Unlock()
|
||||
c := r.getControl(p)
|
||||
a := from.GetUDPAddr()
|
||||
c := r.getControl(a, p.To, p)
|
||||
if c == nil {
|
||||
panic(fmt.Sprintf("No control for udp tx %s", p.To))
|
||||
}
|
||||
@@ -669,7 +671,7 @@ func (r *R) RouteExitFunc(sender *nebula.Control, whatDo ExitFunc) {
|
||||
panic(err)
|
||||
}
|
||||
|
||||
receiver := r.getControl(p)
|
||||
receiver := r.getControl(sender.GetUDPAddr(), p.To, p)
|
||||
if receiver == nil {
|
||||
r.Unlock()
|
||||
panic("Can't RouteExitFunc for host: " + p.To.String())
|
||||
@@ -765,7 +767,7 @@ func (r *R) RouteForAllExitFuncOrTimeout(timeout time.Duration, whatDo ExitFunc)
|
||||
|
||||
r.Lock()
|
||||
p := rx.Interface().(*udp.Packet)
|
||||
receiver := r.getControl(p)
|
||||
receiver := r.getControl(cm[x].GetUDPAddr(), p.To, p)
|
||||
if receiver == nil {
|
||||
r.Unlock()
|
||||
panic("Can't RouteForAllExitFuncOrTimeout for host: " + p.To.String())
|
||||
@@ -874,7 +876,7 @@ func (r *R) RouteForAllExitFunc(whatDo ExitFunc) {
|
||||
r.Lock()
|
||||
|
||||
p := rx.Interface().(*udp.Packet)
|
||||
receiver := r.getControl(p)
|
||||
receiver := r.getControl(cm[x].GetUDPAddr(), p.To, p)
|
||||
if receiver == nil {
|
||||
r.Unlock()
|
||||
panic("Can't RouteForAllExitFunc for host: " + p.To.String())
|
||||
@@ -937,7 +939,7 @@ func (r *R) FlushAll() {
|
||||
})
|
||||
|
||||
for {
|
||||
_, rx, ok := reflect.Select(sc)
|
||||
x, rx, ok := reflect.Select(sc)
|
||||
if !ok {
|
||||
return
|
||||
}
|
||||
@@ -945,7 +947,7 @@ func (r *R) FlushAll() {
|
||||
|
||||
p := rx.Interface().(*udp.Packet)
|
||||
|
||||
receiver := r.getControl(p)
|
||||
receiver := r.getControl(cm[x].GetUDPAddr(), p.To, p)
|
||||
if receiver == nil {
|
||||
r.Unlock()
|
||||
panic("Can't FlushAll for host: " + p.To.String())
|
||||
@@ -956,19 +958,16 @@ func (r *R) FlushAll() {
|
||||
}
|
||||
}
|
||||
|
||||
// getControl performs or seeds NAT translation and returns the control for p.To, p from fields may change
|
||||
// getControl performs or seeds NAT translation and returns the control for toAddr, p from fields may change
|
||||
// This is an internal router function, the caller must hold the lock
|
||||
func (r *R) getControl(p *udp.Packet) *nebula.Control {
|
||||
// Key on the address the packet actually left from, a dual stack sender has one per family
|
||||
fromAddr, toAddr := p.From, p.To
|
||||
func (r *R) getControl(fromAddr, toAddr netip.AddrPort, p *udp.Packet) *nebula.Control {
|
||||
if newAddr, ok := r.outNat[outNatKey{from: fromAddr, to: toAddr}]; ok {
|
||||
p.From = newAddr
|
||||
}
|
||||
|
||||
c, ok := r.inNat[toAddr]
|
||||
if ok {
|
||||
// Key the return path on the address the receiver will answer from, which is per family for a dual stack node
|
||||
r.outNat[outNatKey{from: c.GetUDPAddrFor(fromAddr), to: fromAddr}] = toAddr
|
||||
r.outNat[outNatKey{from: c.GetUDPAddr(), to: fromAddr}] = toAddr
|
||||
return c
|
||||
}
|
||||
|
||||
|
||||
Vendored
-720
@@ -1,720 +0,0 @@
|
||||
$ version
|
||||
e2e-test
|
||||
|
||||
$ version -json
|
||||
e2e-test
|
||||
|
||||
$ version -pretty
|
||||
e2e-test
|
||||
|
||||
$ device-info
|
||||
name= cidr=[10.222.0.1/24]
|
||||
|
||||
$ device-info -json
|
||||
{"name":"","cidr":["10.222.0.1/24"]}
|
||||
|
||||
$ device-info -pretty
|
||||
{
|
||||
"name": "",
|
||||
"cidr": [
|
||||
"10.222.0.1/24"
|
||||
]
|
||||
}
|
||||
|
||||
$ list-hostmap
|
||||
|
||||
$ list-hostmap -json
|
||||
[]
|
||||
|
||||
$ list-hostmap -pretty
|
||||
[]
|
||||
|
||||
$ list-hostmap -by-index
|
||||
|
||||
$ list-hostmap -json -by-index
|
||||
[]
|
||||
|
||||
$ list-hostmap -pretty -by-index
|
||||
[]
|
||||
|
||||
$ list-pending-hostmap
|
||||
[10.222.0.9]: []
|
||||
|
||||
$ list-pending-hostmap -json
|
||||
[{"vpnAddrs":["10.222.0.9"],"localIndex":<n>,"remoteIndex":<n>,"remoteAddrs":[],"cert":null,"messageCounter":<n>,"currentRemote":"","currentRelaysToMe":[],"currentRelaysThroughMe":[]}]
|
||||
|
||||
$ list-pending-hostmap -pretty
|
||||
[
|
||||
{
|
||||
"vpnAddrs": [
|
||||
"10.222.0.9"
|
||||
],
|
||||
"localIndex": <n>,
|
||||
"remoteIndex": <n>,
|
||||
"remoteAddrs": [],
|
||||
"cert": null,
|
||||
"messageCounter": <n>,
|
||||
"currentRemote": "",
|
||||
"currentRelaysToMe": [],
|
||||
"currentRelaysThroughMe": []
|
||||
}
|
||||
]
|
||||
|
||||
$ list-pending-hostmap -by-index
|
||||
|
||||
$ list-pending-hostmap -json -by-index
|
||||
[]
|
||||
|
||||
$ list-pending-hostmap -pretty -by-index
|
||||
[]
|
||||
|
||||
$ list-lighthouse-addrmap
|
||||
10.222.0.9: {}
|
||||
|
||||
$ list-lighthouse-addrmap -json
|
||||
[{"vpnAddr":"10.222.0.9","addrs":{}}]
|
||||
|
||||
$ list-lighthouse-addrmap -pretty
|
||||
[
|
||||
{
|
||||
"vpnAddr": "10.222.0.9",
|
||||
"addrs": {}
|
||||
}
|
||||
]
|
||||
|
||||
$ print-cert
|
||||
{
|
||||
"details": {
|
||||
"curve": "CURVE25519",
|
||||
"groups": [],
|
||||
"isCa": false,
|
||||
"issuer": "<hex>",
|
||||
"name": "output-golden",
|
||||
"networks": [
|
||||
"10.222.0.1/24"
|
||||
],
|
||||
"notAfter": "<time>",
|
||||
"notBefore": "<time>",
|
||||
"publicKey": "<hex>",
|
||||
"unsafeNetworks": []
|
||||
},
|
||||
"fingerprint": "<hex>",
|
||||
"signature": "<hex>",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
$ print-cert -json
|
||||
{"details":{"curve":"CURVE25519","groups":[],"isCa":false,"issuer":"<hex>","name":"output-golden","networks":["10.222.0.1/24"],"notAfter":"<time>","notBefore":"<time>","publicKey":"<hex>","unsafeNetworks":[]},"fingerprint":"<hex>","signature":"<hex>","version":1}\ No newline at end of output
|
||||
|
||||
$ print-cert -pretty
|
||||
{
|
||||
"details": {
|
||||
"curve": "CURVE25519",
|
||||
"groups": [],
|
||||
"isCa": false,
|
||||
"issuer": "<hex>",
|
||||
"name": "output-golden",
|
||||
"networks": [
|
||||
"10.222.0.1/24"
|
||||
],
|
||||
"notAfter": "<time>",
|
||||
"notBefore": "<time>",
|
||||
"publicKey": "<hex>",
|
||||
"unsafeNetworks": []
|
||||
},
|
||||
"fingerprint": "<hex>",
|
||||
"signature": "<hex>",
|
||||
"version": 1
|
||||
}\ No newline at end of output
|
||||
|
||||
$ print-cert -raw
|
||||
-----BEGIN NEBULA CERTIFICATE-----
|
||||
<pem>
|
||||
-----END NEBULA CERTIFICATE-----
|
||||
|
||||
$ print-cert -json -raw
|
||||
{"details":{"curve":"CURVE25519","groups":[],"isCa":false,"issuer":"<hex>","name":"output-golden","networks":["10.222.0.1/24"],"notAfter":"<time>","notBefore":"<time>","publicKey":"<hex>","unsafeNetworks":[]},"fingerprint":"<hex>","signature":"<hex>","version":1}\ No newline at end of output
|
||||
|
||||
$ print-cert -pretty -raw
|
||||
{
|
||||
"details": {
|
||||
"curve": "CURVE25519",
|
||||
"groups": [],
|
||||
"isCa": false,
|
||||
"issuer": "<hex>",
|
||||
"name": "output-golden",
|
||||
"networks": [
|
||||
"10.222.0.1/24"
|
||||
],
|
||||
"notAfter": "<time>",
|
||||
"notBefore": "<time>",
|
||||
"publicKey": "<hex>",
|
||||
"unsafeNetworks": []
|
||||
},
|
||||
"fingerprint": "<hex>",
|
||||
"signature": "<hex>",
|
||||
"version": 1
|
||||
}\ No newline at end of output
|
||||
|
||||
$ print-cert 10.222.0.9
|
||||
Could not find tunnel for vpn addr: 10.222.0.9
|
||||
exit status 1
|
||||
|
||||
$ print-cert -json 10.222.0.9
|
||||
Could not find tunnel for vpn addr: 10.222.0.9
|
||||
exit status 1
|
||||
|
||||
$ print-cert -pretty 10.222.0.9
|
||||
Could not find tunnel for vpn addr: 10.222.0.9
|
||||
exit status 1
|
||||
|
||||
$ print-cert 10.222.0.250
|
||||
Could not find tunnel for vpn addr: 10.222.0.250
|
||||
exit status 1
|
||||
|
||||
$ print-cert -json 10.222.0.250
|
||||
Could not find tunnel for vpn addr: 10.222.0.250
|
||||
exit status 1
|
||||
|
||||
$ print-cert -pretty 10.222.0.250
|
||||
Could not find tunnel for vpn addr: 10.222.0.250
|
||||
exit status 1
|
||||
|
||||
$ print-cert not-an-address
|
||||
The provided vpn addr could not be parsed: not-an-address
|
||||
exit status 1
|
||||
|
||||
$ print-cert -json not-an-address
|
||||
The provided vpn addr could not be parsed: not-an-address
|
||||
exit status 1
|
||||
|
||||
$ print-cert -pretty not-an-address
|
||||
The provided vpn addr could not be parsed: not-an-address
|
||||
exit status 1
|
||||
|
||||
$ print-tunnel
|
||||
No vpn address was provided
|
||||
exit status 1
|
||||
|
||||
$ print-tunnel -json
|
||||
flag provided but not defined: -json
|
||||
Usage:
|
||||
-pretty
|
||||
pretty prints json
|
||||
exit status 1
|
||||
|
||||
$ print-tunnel -pretty
|
||||
No vpn address was provided
|
||||
exit status 1
|
||||
|
||||
$ print-tunnel 10.222.0.9
|
||||
Could not find tunnel for vpn addr: 10.222.0.9
|
||||
exit status 1
|
||||
|
||||
$ print-tunnel -json 10.222.0.9
|
||||
flag provided but not defined: -json
|
||||
Usage:
|
||||
-pretty
|
||||
pretty prints json
|
||||
exit status 1
|
||||
|
||||
$ print-tunnel -pretty 10.222.0.9
|
||||
Could not find tunnel for vpn addr: 10.222.0.9
|
||||
exit status 1
|
||||
|
||||
$ print-tunnel 10.222.0.250
|
||||
Could not find tunnel for vpn addr: 10.222.0.250
|
||||
exit status 1
|
||||
|
||||
$ print-tunnel -json 10.222.0.250
|
||||
flag provided but not defined: -json
|
||||
Usage:
|
||||
-pretty
|
||||
pretty prints json
|
||||
exit status 1
|
||||
|
||||
$ print-tunnel -pretty 10.222.0.250
|
||||
Could not find tunnel for vpn addr: 10.222.0.250
|
||||
exit status 1
|
||||
|
||||
$ print-relays
|
||||
{"Relays":null}
|
||||
|
||||
$ print-relays -json
|
||||
flag provided but not defined: -json
|
||||
Usage:
|
||||
-pretty
|
||||
pretty prints json
|
||||
exit status 1
|
||||
|
||||
$ print-relays -pretty
|
||||
{
|
||||
"Relays": null
|
||||
}
|
||||
|
||||
$ query-lighthouse
|
||||
No vpn address was provided
|
||||
exit status 1
|
||||
|
||||
$ query-lighthouse -json
|
||||
The provided vpn address could not be parsed: -json
|
||||
exit status 1
|
||||
|
||||
$ query-lighthouse -pretty
|
||||
The provided vpn address could not be parsed: -pretty
|
||||
exit status 1
|
||||
|
||||
$ query-lighthouse 10.222.0.9
|
||||
{}
|
||||
|
||||
$ query-lighthouse -json 10.222.0.9
|
||||
The provided vpn address could not be parsed: -json
|
||||
exit status 1
|
||||
|
||||
$ query-lighthouse -pretty 10.222.0.9
|
||||
The provided vpn address could not be parsed: -pretty
|
||||
exit status 1
|
||||
|
||||
$ query-lighthouse not-an-address
|
||||
The provided vpn address could not be parsed: not-an-address
|
||||
exit status 1
|
||||
|
||||
$ query-lighthouse -json not-an-address
|
||||
The provided vpn address could not be parsed: -json
|
||||
exit status 1
|
||||
|
||||
$ query-lighthouse -pretty not-an-address
|
||||
The provided vpn address could not be parsed: -pretty
|
||||
exit status 1
|
||||
|
||||
$ log-level
|
||||
Log level is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-level -json
|
||||
Log level is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-level -pretty
|
||||
Log level is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-level debug
|
||||
Log level is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-level -json debug
|
||||
Log level is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-level -pretty debug
|
||||
Log level is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-level bogus
|
||||
Log level is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-level -json bogus
|
||||
Log level is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-level -pretty bogus
|
||||
Log level is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-level info
|
||||
Log level is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-level -json info
|
||||
Log level is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-level -pretty info
|
||||
Log level is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-format
|
||||
Log format is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-format -json
|
||||
Log format is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-format -pretty
|
||||
Log format is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-format json
|
||||
Log format is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-format -json json
|
||||
Log format is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-format -pretty json
|
||||
Log format is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-format text
|
||||
Log format is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-format -json text
|
||||
Log format is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ log-format -pretty text
|
||||
Log format is not reconfigurable on this logger
|
||||
exit status 1
|
||||
|
||||
$ change-remote
|
||||
No vpn address was provided
|
||||
exit status 1
|
||||
|
||||
$ change-remote -json
|
||||
flag provided but not defined: -json
|
||||
Usage:
|
||||
-address string
|
||||
The new remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ change-remote -pretty
|
||||
flag provided but not defined: -pretty
|
||||
Usage:
|
||||
-address string
|
||||
The new remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ change-remote 10.222.0.9
|
||||
No address was provided
|
||||
exit status 1
|
||||
|
||||
$ change-remote -json 10.222.0.9
|
||||
flag provided but not defined: -json
|
||||
Usage:
|
||||
-address string
|
||||
The new remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ change-remote -pretty 10.222.0.9
|
||||
flag provided but not defined: -pretty
|
||||
Usage:
|
||||
-address string
|
||||
The new remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ change-remote -address 10.94.0.10:4242 10.222.0.9
|
||||
Could not find tunnel for vpn address: 10.222.0.9
|
||||
exit status 1
|
||||
|
||||
$ change-remote -json -address 10.94.0.10:4242 10.222.0.9
|
||||
flag provided but not defined: -json
|
||||
Usage:
|
||||
-address string
|
||||
The new remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ change-remote -pretty -address 10.94.0.10:4242 10.222.0.9
|
||||
flag provided but not defined: -pretty
|
||||
Usage:
|
||||
-address string
|
||||
The new remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ change-remote -address 10.94.0.10:4242 10.222.0.250
|
||||
Could not find tunnel for vpn address: 10.222.0.250
|
||||
exit status 1
|
||||
|
||||
$ change-remote -json -address 10.94.0.10:4242 10.222.0.250
|
||||
flag provided but not defined: -json
|
||||
Usage:
|
||||
-address string
|
||||
The new remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ change-remote -pretty -address 10.94.0.10:4242 10.222.0.250
|
||||
flag provided but not defined: -pretty
|
||||
Usage:
|
||||
-address string
|
||||
The new remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ create-tunnel
|
||||
No vpn address was provided
|
||||
exit status 1
|
||||
|
||||
$ create-tunnel -json
|
||||
flag provided but not defined: -json
|
||||
Usage:
|
||||
-address string
|
||||
Optionally provide a real remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ create-tunnel -pretty
|
||||
flag provided but not defined: -pretty
|
||||
Usage:
|
||||
-address string
|
||||
Optionally provide a real remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ create-tunnel 10.222.0.9
|
||||
Tunnel already handshaking
|
||||
exit status 1
|
||||
|
||||
$ create-tunnel -json 10.222.0.9
|
||||
flag provided but not defined: -json
|
||||
Usage:
|
||||
-address string
|
||||
Optionally provide a real remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ create-tunnel -pretty 10.222.0.9
|
||||
flag provided but not defined: -pretty
|
||||
Usage:
|
||||
-address string
|
||||
Optionally provide a real remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ create-tunnel -address 10.94.0.10:4242 10.222.0.10
|
||||
Created
|
||||
|
||||
$ create-tunnel -json -address 10.94.0.10:4242 10.222.0.10
|
||||
flag provided but not defined: -json
|
||||
Usage:
|
||||
-address string
|
||||
Optionally provide a real remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ create-tunnel -pretty -address 10.94.0.10:4242 10.222.0.10
|
||||
flag provided but not defined: -pretty
|
||||
Usage:
|
||||
-address string
|
||||
Optionally provide a real remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ create-tunnel not-an-address
|
||||
The provided vpn address could not be parsed: not-an-address
|
||||
exit status 1
|
||||
|
||||
$ create-tunnel -json not-an-address
|
||||
flag provided but not defined: -json
|
||||
Usage:
|
||||
-address string
|
||||
Optionally provide a real remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ create-tunnel -pretty not-an-address
|
||||
flag provided but not defined: -pretty
|
||||
Usage:
|
||||
-address string
|
||||
Optionally provide a real remote address, ip:port
|
||||
exit status 1
|
||||
|
||||
$ close-tunnel
|
||||
No vpn address was provided
|
||||
exit status 1
|
||||
|
||||
$ close-tunnel -json
|
||||
flag provided but not defined: -json
|
||||
Usage:
|
||||
-local-only
|
||||
Disables notifying the remote that the tunnel is shutting down
|
||||
exit status 1
|
||||
|
||||
$ close-tunnel -pretty
|
||||
flag provided but not defined: -pretty
|
||||
Usage:
|
||||
-local-only
|
||||
Disables notifying the remote that the tunnel is shutting down
|
||||
exit status 1
|
||||
|
||||
$ close-tunnel 10.222.0.250
|
||||
Could not find tunnel for vpn address: 10.222.0.250
|
||||
exit status 1
|
||||
|
||||
$ close-tunnel -json 10.222.0.250
|
||||
flag provided but not defined: -json
|
||||
Usage:
|
||||
-local-only
|
||||
Disables notifying the remote that the tunnel is shutting down
|
||||
exit status 1
|
||||
|
||||
$ close-tunnel -pretty 10.222.0.250
|
||||
flag provided but not defined: -pretty
|
||||
Usage:
|
||||
-local-only
|
||||
Disables notifying the remote that the tunnel is shutting down
|
||||
exit status 1
|
||||
|
||||
$ close-tunnel not-an-address
|
||||
The provided vpn address could not be parsed: not-an-address
|
||||
exit status 1
|
||||
|
||||
$ close-tunnel -json not-an-address
|
||||
flag provided but not defined: -json
|
||||
Usage:
|
||||
-local-only
|
||||
Disables notifying the remote that the tunnel is shutting down
|
||||
exit status 1
|
||||
|
||||
$ close-tunnel -pretty not-an-address
|
||||
flag provided but not defined: -pretty
|
||||
Usage:
|
||||
-local-only
|
||||
Disables notifying the remote that the tunnel is shutting down
|
||||
exit status 1
|
||||
|
||||
$ help
|
||||
Available commands:
|
||||
change-remote - Changes the remote address used in the tunnel for the provided vpn addr
|
||||
close-tunnel - Closes a tunnel for the provided vpn addr
|
||||
create-tunnel - Creates a tunnel for the provided vpn address
|
||||
device-info - Prints information about the network device.
|
||||
help - prints available commands or help <command> for specific usage info
|
||||
list-hostmap - List all known previously connected hosts
|
||||
list-lighthouse-addrmap - List all lighthouse map entries
|
||||
list-pending-hostmap - List all handshaking hosts
|
||||
log-format - Gets or sets the current log format
|
||||
log-level - Gets or sets the current log level
|
||||
logout - Ends the current session
|
||||
print-cert - Prints the current certificate being used or the certificate for the provided vpn addr
|
||||
print-relays - Prints json details about all relay info
|
||||
print-tunnel - Prints json details about a tunnel for the provided vpn addr
|
||||
query-lighthouse - Query the lighthouses for the provided vpn address
|
||||
reload - Reloads configuration from disk, same as sending HUP to the process
|
||||
version - Prints the currently running version of nebula
|
||||
|
||||
|
||||
$ help -json
|
||||
Command not available -json
|
||||
exit status 1
|
||||
|
||||
$ help -pretty
|
||||
Command not available -pretty
|
||||
exit status 1
|
||||
|
||||
$ help print-cert
|
||||
print-cert - Prints the current certificate being used or the certificate for the provided vpn addr
|
||||
-json
|
||||
outputs as json
|
||||
-pretty
|
||||
pretty prints json, assumes -json
|
||||
-raw
|
||||
raw prints the PEM encoded certificate, not compatible with -json or -pretty
|
||||
|
||||
$ help -json print-cert
|
||||
Command not available -json
|
||||
exit status 1
|
||||
|
||||
$ help -pretty print-cert
|
||||
Command not available -pretty
|
||||
exit status 1
|
||||
|
||||
$ help logout
|
||||
logout - Ends the current session
|
||||
|
||||
$ help -json logout
|
||||
Command not available -json
|
||||
exit status 1
|
||||
|
||||
$ help -pretty logout
|
||||
Command not available -pretty
|
||||
exit status 1
|
||||
|
||||
$ logout -h
|
||||
logout - Ends the current session
|
||||
|
||||
$ logout -json -h
|
||||
logout - Ends the current session
|
||||
|
||||
$ logout -pretty -h
|
||||
logout - Ends the current session
|
||||
|
||||
$ not-a-command 10.222.0.9
|
||||
did not understand: not-a-command
|
||||
Available commands:
|
||||
change-remote - Changes the remote address used in the tunnel for the provided vpn addr
|
||||
close-tunnel - Closes a tunnel for the provided vpn addr
|
||||
create-tunnel - Creates a tunnel for the provided vpn address
|
||||
device-info - Prints information about the network device.
|
||||
help - prints available commands or help <command> for specific usage info
|
||||
list-hostmap - List all known previously connected hosts
|
||||
list-lighthouse-addrmap - List all lighthouse map entries
|
||||
list-pending-hostmap - List all handshaking hosts
|
||||
log-format - Gets or sets the current log format
|
||||
log-level - Gets or sets the current log level
|
||||
logout - Ends the current session
|
||||
print-cert - Prints the current certificate being used or the certificate for the provided vpn addr
|
||||
print-relays - Prints json details about all relay info
|
||||
print-tunnel - Prints json details about a tunnel for the provided vpn addr
|
||||
query-lighthouse - Query the lighthouses for the provided vpn address
|
||||
reload - Reloads configuration from disk, same as sending HUP to the process
|
||||
version - Prints the currently running version of nebula
|
||||
|
||||
exit status 1
|
||||
|
||||
$ not-a-command -json 10.222.0.9
|
||||
did not understand: not-a-command
|
||||
Available commands:
|
||||
change-remote - Changes the remote address used in the tunnel for the provided vpn addr
|
||||
close-tunnel - Closes a tunnel for the provided vpn addr
|
||||
create-tunnel - Creates a tunnel for the provided vpn address
|
||||
device-info - Prints information about the network device.
|
||||
help - prints available commands or help <command> for specific usage info
|
||||
list-hostmap - List all known previously connected hosts
|
||||
list-lighthouse-addrmap - List all lighthouse map entries
|
||||
list-pending-hostmap - List all handshaking hosts
|
||||
log-format - Gets or sets the current log format
|
||||
log-level - Gets or sets the current log level
|
||||
logout - Ends the current session
|
||||
print-cert - Prints the current certificate being used or the certificate for the provided vpn addr
|
||||
print-relays - Prints json details about all relay info
|
||||
print-tunnel - Prints json details about a tunnel for the provided vpn addr
|
||||
query-lighthouse - Query the lighthouses for the provided vpn address
|
||||
reload - Reloads configuration from disk, same as sending HUP to the process
|
||||
version - Prints the currently running version of nebula
|
||||
|
||||
exit status 1
|
||||
|
||||
$ not-a-command -pretty 10.222.0.9
|
||||
did not understand: not-a-command
|
||||
Available commands:
|
||||
change-remote - Changes the remote address used in the tunnel for the provided vpn addr
|
||||
close-tunnel - Closes a tunnel for the provided vpn addr
|
||||
create-tunnel - Creates a tunnel for the provided vpn address
|
||||
device-info - Prints information about the network device.
|
||||
help - prints available commands or help <command> for specific usage info
|
||||
list-hostmap - List all known previously connected hosts
|
||||
list-lighthouse-addrmap - List all lighthouse map entries
|
||||
list-pending-hostmap - List all handshaking hosts
|
||||
log-format - Gets or sets the current log format
|
||||
log-level - Gets or sets the current log level
|
||||
logout - Ends the current session
|
||||
print-cert - Prints the current certificate being used or the certificate for the provided vpn addr
|
||||
print-relays - Prints json details about all relay info
|
||||
print-tunnel - Prints json details about a tunnel for the provided vpn addr
|
||||
query-lighthouse - Query the lighthouses for the provided vpn address
|
||||
reload - Reloads configuration from disk, same as sending HUP to the process
|
||||
version - Prints the currently running version of nebula
|
||||
|
||||
exit status 1
|
||||
|
||||
$ reload
|
||||
Reloading config
|
||||
Config reload failed, the new config did not load: no config files found at
|
||||
exit status 1
|
||||
|
||||
$ reload -json
|
||||
Reloading config
|
||||
Config reload failed, the new config did not load: no config files found at
|
||||
exit status 1
|
||||
|
||||
$ reload -pretty
|
||||
Reloading config
|
||||
Config reload failed, the new config did not load: no config files found at
|
||||
exit status 1
|
||||
|
||||
+2
-2
@@ -129,7 +129,7 @@ func TestCertUpgrade(t *testing.T) {
|
||||
}
|
||||
|
||||
r.Logf("reload new v2-only config")
|
||||
err = myC.ReloadConfigString(string(cb)).Err
|
||||
err = myC.ReloadConfigString(string(cb))
|
||||
assert.NoError(t, err)
|
||||
r.Log("yay, spin until their sees it")
|
||||
waitStart := time.Now()
|
||||
@@ -222,7 +222,7 @@ func TestCertDowngrade(t *testing.T) {
|
||||
}
|
||||
|
||||
r.Logf("reload new v1-only config")
|
||||
err = myC.ReloadConfigString(string(cb)).Err
|
||||
err = myC.ReloadConfigString(string(cb))
|
||||
assert.NoError(t, err)
|
||||
r.Log("yay, spin until their sees it")
|
||||
waitStart := time.Now()
|
||||
|
||||
+25
-30
@@ -8,7 +8,6 @@ pki:
|
||||
cert: /etc/nebula/host.crt
|
||||
key: /etc/nebula/host.key
|
||||
# blocklist is a list of certificate fingerprints that we will refuse to talk to
|
||||
# Entries are the hex fingerprints shown by `nebula-cert print`, an invalid entry fails startup and reload.
|
||||
#blocklist:
|
||||
# - c99d4e650533b92061b09918e838a5a0a6aaee21eed1d12fd937682865936c72
|
||||
# disconnect_invalid is a toggle to force a client to be disconnected if the certificate is expired or invalid.
|
||||
@@ -44,7 +43,7 @@ static_host_map:
|
||||
|
||||
lighthouse:
|
||||
# am_lighthouse is used to enable lighthouse functionality for a node. This should ONLY be true on nodes
|
||||
# you have configured to be lighthouses in your network. Not reloadable.
|
||||
# you have configured to be lighthouses in your network
|
||||
am_lighthouse: false
|
||||
# serve_dns optionally starts a dns listener that responds to various queries and can even be
|
||||
# delegated to for resolution
|
||||
@@ -127,9 +126,8 @@ lighthouse:
|
||||
# Port Nebula will be listening on. The default here is 4242. For a lighthouse node, the port should be defined,
|
||||
# however using port 0 will dynamically assign a port and is recommended for roaming nodes.
|
||||
listen:
|
||||
# To listen on only ipv4, use "0.0.0.0". Not reloadable.
|
||||
# To listen on only ipv4, use "0.0.0.0"
|
||||
host: "::"
|
||||
# Not reloadable.
|
||||
port: 4242
|
||||
# Sets the max number of packets to pull from the kernel for each syscall (under systems that support recvmmsg)
|
||||
# default is 64, does not support reload
|
||||
@@ -137,13 +135,12 @@ listen:
|
||||
# superpacket, so the receive scratch is batch * 64KiB per listening socket (~4MiB per routine at the
|
||||
# default of 64). Lower this to trade peak per-syscall throughput for memory on constrained hosts.
|
||||
#batch: 64
|
||||
# Linux only. Reloadable, but removing a value leaves the socket at the old size until Nebula restarts.
|
||||
# Configure socket buffers for the udp side (outside), leave unset to use the system defaults. Values will be doubled by the kernel
|
||||
# Default is net.core.rmem_default and net.core.wmem_default (/proc/sys/net/core/rmem_default and /proc/sys/net/core/rmem_default)
|
||||
# Maximum is limited by memory in the system, SO_RCVBUFFORCE and SO_SNDBUFFORCE is used to avoid having to raise the system wide
|
||||
# max, net.core.rmem_max and net.core.wmem_max
|
||||
read_buffer: 3412512
|
||||
write_buffer: 3412512
|
||||
#read_buffer: 10485760
|
||||
#write_buffer: 10485760
|
||||
|
||||
# On Windows only
|
||||
# When true, Nebula installs a WFP (Windows Filtering Platform) PERMIT filter scoped to UDP at the listener port.
|
||||
@@ -182,7 +179,7 @@ listen:
|
||||
# Currently, this defaults to 1 which means we have 1 tun queue reader and 1
|
||||
# UDP queue reader. Setting this above one will set IFF_MULTI_QUEUE on the tun
|
||||
# device and SO_REUSEPORT on the UDP socket to allow multiple queues.
|
||||
# This option is only supported on Linux. Not reloadable.
|
||||
# This option is only supported on Linux.
|
||||
#routines: 1
|
||||
|
||||
punchy:
|
||||
@@ -206,7 +203,6 @@ punchy:
|
||||
|
||||
# Cipher allows you to choose between the available ciphers for your network. Options are chachapoly or aes
|
||||
# IMPORTANT: this value must be identical on ALL NODES/LIGHTHOUSES. We do not/will not support use of different ciphers simultaneously!
|
||||
# Not reloadable.
|
||||
#cipher: aes
|
||||
|
||||
# Preferred ranges is used to define a hint about the local network ranges, which speeds up discovering the fastest
|
||||
@@ -233,6 +229,12 @@ punchy:
|
||||
# Trusted SSH CA public keys. These are the public keys of the CAs that are allowed to sign SSH keys for access.
|
||||
#trusted_cas:
|
||||
#- "ssh public key string"
|
||||
# sandbox_dir restricts file paths for profiling commands (start-cpu-profile, save-heap-profile,
|
||||
# save-mutex-profile) to the specified directory. Relative paths will be resolved within this directory,
|
||||
# and absolute paths outside of it will be rejected. Default is $TMP/nebula-debug.
|
||||
# The directory is NOT automatically created.
|
||||
# Overriding this to "" is the same as "/" and will allow overwriting any path on the host.
|
||||
#sandbox_dir: /var/tmp/nebula-debug
|
||||
|
||||
# EXPERIMENTAL: relay support for networks that can't establish direct connections.
|
||||
relay:
|
||||
@@ -251,25 +253,18 @@ relay:
|
||||
# Configure the private interface. Note: addr is baked into the nebula certificate
|
||||
tun:
|
||||
# When tun is disabled, a lighthouse can be started without a local tun interface (and therefore without root)
|
||||
# Not reloadable.
|
||||
disabled: false
|
||||
# Name of the device. If not set, a default will be chosen by the OS.
|
||||
# For macOS: if set, must be in the form `utun[0-9]+`.
|
||||
# For OpenBSD and NetBSD: if set, must be in the form `tun[0-9]+`, otherwise the first free one is used.
|
||||
# Not reloadable.
|
||||
# For NetBSD: Required to be set, must be in the form `tun[0-9]+`
|
||||
dev: nebula1
|
||||
# Toggles forwarding of local broadcast packets, the address of which depends on the ip/mask encoded in pki.cert
|
||||
# Not reloadable.
|
||||
drop_local_broadcast: false
|
||||
# Toggles forwarding of multicast packets. Not reloadable.
|
||||
# Toggles forwarding of multicast packets
|
||||
drop_multicast: false
|
||||
# Sets the transmit queue length, if you notice lots of transmit drops on the tun it may help to raise this number. Default is 5000
|
||||
# Not reloadable.
|
||||
tx_queue: 5000
|
||||
# Sets the transmit queue length, if you notice lots of transmit drops on the tun it may help to raise this number. Default is 500
|
||||
tx_queue: 500
|
||||
# Default MTU for every packet, safe setting is (and the default) 1300 for internet based traffic
|
||||
# Anything above 8937, here or on a route below, is capped to 8937 with a warning
|
||||
# Reloadable on Linux only. Where the tun is handed to nebula by a host app (iOS, Android, macOS network extensions)
|
||||
# the host app owns the MTU.
|
||||
mtu: 1300
|
||||
|
||||
# the use_offloads setting controls if Nebula will attempt to enable GSO and GRO for the tun device. Linux only, not reloadable.
|
||||
@@ -331,9 +326,6 @@ tun:
|
||||
# `mtu`: will default to tun mtu if this option is not specified
|
||||
# `metric`: will default to 0 if this option is not specified
|
||||
# `install`: will default to true, controls whether this route is installed in the systems routing table.
|
||||
# On macOS, a route whose destination another interface already routes, like the local network, is installed once
|
||||
# that route is removed. One deleted by hand stays deleted until nebula reloads or restarts, or until another
|
||||
# interface routes its destination and lets it go.
|
||||
# This setting is reloadable.
|
||||
unsafe_routes:
|
||||
#- route: 172.16.1.0/24
|
||||
@@ -365,7 +357,7 @@ tun:
|
||||
#use_system_route_table: false
|
||||
# Buffer size for reading routes updates. 0 means default system buffer size. (/proc/sys/net/core/rmem_default).
|
||||
# If using massive routes updates, for example BGP, you may need to increase this value to avoid packet loss.
|
||||
# SO_RCVBUFFORCE is used to avoid having to raise the system wide max. Not reloadable.
|
||||
# SO_RCVBUFFORCE is used to avoid having to raise the system wide max
|
||||
#use_system_route_table_buffer_size: 0
|
||||
|
||||
# Configure logging level
|
||||
@@ -415,16 +407,14 @@ logging:
|
||||
# Handshakes are sent to all known addresses at each interval with a linear backoff,
|
||||
# Wait try_interval after the 1st attempt, 2 * try_interval after the 2nd, etc, until the handshake is older than timeout
|
||||
# A 100ms interval with the default 10 retries will give a handshake 5.5 seconds to resolve before timing out
|
||||
# Not reloadable.
|
||||
#try_interval: 100ms
|
||||
#retries: 20
|
||||
|
||||
# query_buffer is the size of the buffer channel for querying lighthouses, drops are recorded in the lighthouse.query.dropped metric.
|
||||
# Not reloadable.
|
||||
#query_buffer: 1024
|
||||
# query_buffer is the size of the buffer channel for querying lighthouses
|
||||
#query_buffer: 64
|
||||
|
||||
# trigger_buffer is the size of the buffer channel for quickly sending handshakes
|
||||
# after receiving the response for lighthouse queries. Not reloadable.
|
||||
# after receiving the response for lighthouse queries
|
||||
#trigger_buffer: 64
|
||||
|
||||
# Tunnel manager settings
|
||||
@@ -459,7 +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
|
||||
|
||||
@@ -467,8 +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
-761
@@ -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
|
||||
@@ -63,15 +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
|
||||
|
||||
// source is the rendered firewall config this firewall was built from, the cert networks are kept above
|
||||
source string
|
||||
|
||||
defaultLocalCIDRAny bool
|
||||
incomingMetrics firewallMetrics
|
||||
outgoingMetrics firewallMetrics
|
||||
incomingMetrics firewallMetrics
|
||||
outgoingMetrics firewallMetrics
|
||||
|
||||
l *slog.Logger
|
||||
}
|
||||
@@ -89,52 +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 {
|
||||
@@ -173,8 +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,
|
||||
@@ -215,8 +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":
|
||||
@@ -239,81 +174,23 @@ func NewFirewallFromConfig(l *slog.Logger, cs *CertState, c *config.C) (*Firewal
|
||||
fw.OutboundSendReject = false
|
||||
}
|
||||
|
||||
err := AddFirewallRulesFromConfig(l, false, c, fw)
|
||||
rules, err := firewall.RulesFromConfig(l, c, fw.assignedNetworks, fw.unsafeNetworks)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
fw.rules = rules
|
||||
|
||||
err = AddFirewallRulesFromConfig(l, true, c, fw)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
fw.source = c.Render("firewall")
|
||||
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
|
||||
@@ -321,104 +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")
|
||||
@@ -462,23 +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
|
||||
}
|
||||
@@ -507,9 +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
|
||||
}
|
||||
}
|
||||
@@ -522,7 +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()
|
||||
@@ -532,29 +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,
|
||||
@@ -564,42 +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
|
||||
@@ -607,7 +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()
|
||||
}
|
||||
|
||||
@@ -633,490 +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 +1,319 @@
|
||||
package firewall
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"reflect"
|
||||
"slices"
|
||||
"strconv"
|
||||
"strings"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/iputil"
|
||||
)
|
||||
|
||||
// ruleAdder takes firewall rules, it lets tests see what addRulesFromConfig adds
|
||||
type ruleAdder interface {
|
||||
AddRule(incoming bool, proto uint8, startPort int32, endPort int32, groups []string, host string, cidr, localCidr string, caName string, caSha string) error
|
||||
}
|
||||
|
||||
// RulesFromConfig reads the inbound and outbound firewall rules from c and builds them, see RulesBuilder.Build
|
||||
func RulesFromConfig(l *slog.Logger, c *config.C, vpnNetworks, unsafeNetworks []netip.Prefix) (Rules, error) {
|
||||
b := NewRulesBuilder(l)
|
||||
b.defaultLocalCIDRAny = c.GetBool("firewall.default_local_cidr_any", false)
|
||||
|
||||
if err := addRulesFromConfig(l, false, c, b); err != nil {
|
||||
return Rules{}, err
|
||||
}
|
||||
if err := addRulesFromConfig(l, true, c, b); err != nil {
|
||||
return Rules{}, err
|
||||
}
|
||||
|
||||
return b.Build(vpnNetworks, unsafeNetworks), nil
|
||||
}
|
||||
|
||||
func addRulesFromConfig(l *slog.Logger, inbound bool, c *config.C, ra ruleAdder) error {
|
||||
var table string
|
||||
if inbound {
|
||||
table = "firewall.inbound"
|
||||
} else {
|
||||
table = "firewall.outbound"
|
||||
}
|
||||
|
||||
r := c.Get(table)
|
||||
if r == nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
rs, ok := r.([]any)
|
||||
if !ok {
|
||||
return fmt.Errorf("%s failed to parse, should be an array of rules", table)
|
||||
}
|
||||
|
||||
for i, t := range rs {
|
||||
r, err := yamlToConfigRule(l, t, table, i)
|
||||
if err != nil {
|
||||
return fmt.Errorf("%s rule #%v; %s", table, i, err)
|
||||
}
|
||||
|
||||
if r.Code != "" && r.Port != "" {
|
||||
return fmt.Errorf("%s rule #%v; only one of port or code should be provided", table, i)
|
||||
}
|
||||
|
||||
if r.Host == "" && len(r.Groups) == 0 && r.Cidr == "" && r.LocalCidr == "" && r.CAName == "" && r.CASha == "" {
|
||||
return fmt.Errorf("%s rule #%v; at least one of host, group, cidr, local_cidr, ca_name, or ca_sha must be provided", table, i)
|
||||
}
|
||||
|
||||
var sPort, errPort string
|
||||
if r.Code != "" {
|
||||
errPort = "code"
|
||||
sPort = r.Code
|
||||
} else {
|
||||
errPort = "port"
|
||||
sPort = r.Port
|
||||
}
|
||||
|
||||
var proto uint8
|
||||
switch r.Proto {
|
||||
case "any":
|
||||
proto = ProtoAny
|
||||
case "tcp":
|
||||
proto = iputil.IPProtocolTCP
|
||||
case "udp":
|
||||
proto = iputil.IPProtocolUDP
|
||||
case "udplite":
|
||||
proto = iputil.IPProtocolUDPLite
|
||||
case "dccp":
|
||||
proto = iputil.IPProtocolDCCP
|
||||
case "sctp":
|
||||
proto = iputil.IPProtocolSCTP
|
||||
case "icmp":
|
||||
proto = iputil.IPProtocolICMP
|
||||
default:
|
||||
// Any other protocol by number. 0 is reserved for `any`.
|
||||
n, perr := strconv.ParseUint(r.Proto, 10, 8)
|
||||
if perr != nil || n == 0 {
|
||||
return fmt.Errorf("%s rule #%v; proto was not understood; `%s`", table, i, r.Proto)
|
||||
}
|
||||
proto = uint8(n)
|
||||
}
|
||||
|
||||
var startPort, endPort int32
|
||||
if proto == iputil.IPProtocolICMP || proto == iputil.IPProtocolICMPv6 {
|
||||
startPort = PortAny
|
||||
endPort = PortAny
|
||||
if sPort != "" {
|
||||
l.Warn("ignoring port specification for ICMP firewall rule", "port", sPort)
|
||||
}
|
||||
} else {
|
||||
startPort, endPort, err = parsePort(sPort)
|
||||
}
|
||||
if err != nil {
|
||||
return fmt.Errorf("%s rule #%v; %s %s", table, i, errPort, err)
|
||||
}
|
||||
|
||||
if warning := r.sanity(); warning != nil {
|
||||
l.Warn("firewall rule sanity check",
|
||||
"table", table,
|
||||
"rule", i,
|
||||
"warning", warning,
|
||||
)
|
||||
}
|
||||
|
||||
err = ra.AddRule(inbound, proto, startPort, endPort, r.Groups, r.Host, r.Cidr, r.LocalCidr, r.CAName, r.CASha)
|
||||
if err != nil {
|
||||
return fmt.Errorf("%s rule #%v; %s", table, i, err)
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
type configRule struct {
|
||||
Port string
|
||||
Code string
|
||||
Proto string
|
||||
Host string
|
||||
Groups []string
|
||||
Cidr string
|
||||
LocalCidr string
|
||||
CAName string
|
||||
CASha string
|
||||
}
|
||||
|
||||
func yamlToConfigRule(l *slog.Logger, p any, table string, i int) (configRule, error) {
|
||||
r := configRule{}
|
||||
|
||||
m, ok := p.(map[string]any)
|
||||
if !ok {
|
||||
return r, errors.New("could not parse rule")
|
||||
}
|
||||
|
||||
toString := func(k string, m map[string]any) string {
|
||||
v, ok := m[k]
|
||||
if !ok {
|
||||
return ""
|
||||
}
|
||||
return fmt.Sprintf("%v", v)
|
||||
}
|
||||
|
||||
r.Port = toString("port", m)
|
||||
r.Code = toString("code", m)
|
||||
r.Proto = toString("proto", m)
|
||||
r.Host = toString("host", m)
|
||||
r.Cidr = toString("cidr", m)
|
||||
r.LocalCidr = toString("local_cidr", m)
|
||||
r.CAName = toString("ca_name", m)
|
||||
r.CASha = toString("ca_sha", m)
|
||||
|
||||
// Make sure group isn't an array
|
||||
if v, ok := m["group"].([]any); ok {
|
||||
if len(v) > 1 {
|
||||
return r, errors.New("group should contain a single value, an array with more than one entry was provided")
|
||||
}
|
||||
|
||||
l.Warn("group was an array with a single value, converting to simple value",
|
||||
"table", table,
|
||||
"rule", i,
|
||||
)
|
||||
m["group"] = v[0]
|
||||
}
|
||||
|
||||
singleGroup := toString("group", m)
|
||||
|
||||
if rg, ok := m["groups"]; ok {
|
||||
switch reflect.TypeOf(rg).Kind() {
|
||||
case reflect.Slice:
|
||||
v := reflect.ValueOf(rg)
|
||||
r.Groups = make([]string, v.Len())
|
||||
for i := 0; i < v.Len(); i++ {
|
||||
r.Groups[i] = v.Index(i).Interface().(string)
|
||||
}
|
||||
case reflect.String:
|
||||
r.Groups = []string{rg.(string)}
|
||||
default:
|
||||
r.Groups = []string{fmt.Sprintf("%v", rg)}
|
||||
}
|
||||
}
|
||||
|
||||
//flatten group vs groups
|
||||
if singleGroup != "" {
|
||||
// Check if we have both groups and group provided in the rule config
|
||||
if len(r.Groups) > 0 {
|
||||
return r, fmt.Errorf("only one of group or groups should be defined, both provided")
|
||||
}
|
||||
r.Groups = []string{singleGroup}
|
||||
}
|
||||
|
||||
return r, nil
|
||||
}
|
||||
|
||||
// sanity returns an error if the rule would be evaluated in a way that would short-circuit a configured check on a wildcard value
|
||||
// rules are evaluated as "port AND proto AND (ca_sha OR ca_name) AND (host OR group OR groups OR cidr) AND local_cidr"
|
||||
func (r *configRule) sanity() error {
|
||||
//port, proto, local_cidr are AND, no need to check here
|
||||
//ca_sha and ca_name don't have a wildcard value, no need to check here
|
||||
groupsEmpty := len(r.Groups) == 0
|
||||
hostEmpty := r.Host == ""
|
||||
cidrEmpty := r.Cidr == ""
|
||||
|
||||
if (groupsEmpty && hostEmpty && cidrEmpty) == true {
|
||||
return nil //no content!
|
||||
}
|
||||
|
||||
groupsHasAny := slices.Contains(r.Groups, "any")
|
||||
if groupsHasAny && len(r.Groups) > 1 {
|
||||
return fmt.Errorf("groups spec [%s] contains the group '\"any\". This rule will ignore the other groups specified", r.Groups)
|
||||
}
|
||||
|
||||
if r.Host == "any" {
|
||||
if !groupsEmpty {
|
||||
return fmt.Errorf("groups specified as %s, but host=any will match any host, regardless of groups", r.Groups)
|
||||
}
|
||||
|
||||
if !cidrEmpty {
|
||||
return fmt.Errorf("cidr specified as %s, but host=any will match any host, regardless of cidr", r.Cidr)
|
||||
}
|
||||
}
|
||||
|
||||
if groupsHasAny {
|
||||
if !hostEmpty && r.Host != "any" {
|
||||
return fmt.Errorf("groups spec [%s] contains the group '\"any\". This rule will ignore the specified host %s", r.Groups, r.Host)
|
||||
}
|
||||
if !cidrEmpty {
|
||||
return fmt.Errorf("groups spec [%s] contains the group '\"any\". This rule will ignore the specified cidr %s", r.Groups, r.Cidr)
|
||||
}
|
||||
}
|
||||
|
||||
if r.Code != "" {
|
||||
return fmt.Errorf("code specified as [%s]. Support for 'code' will be dropped in a future release, as it has never been functional", r.Code)
|
||||
}
|
||||
|
||||
//todo alert on cidr-any
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
func parsePort(s string) (int32, int32, error) {
|
||||
const notAPort int32 = -2
|
||||
if s == "any" {
|
||||
return PortAny, PortAny, nil
|
||||
}
|
||||
if s == "fragment" {
|
||||
return PortFragment, PortFragment, nil
|
||||
}
|
||||
if !strings.Contains(s, `-`) {
|
||||
rPort, err := parsePortValue("", s)
|
||||
if err != nil {
|
||||
return notAPort, notAPort, err
|
||||
}
|
||||
return rPort, rPort, nil
|
||||
}
|
||||
|
||||
sPorts := strings.SplitN(s, `-`, 2)
|
||||
for i := range sPorts {
|
||||
sPorts[i] = strings.Trim(sPorts[i], " ")
|
||||
}
|
||||
if len(sPorts) != 2 || sPorts[0] == "" || sPorts[1] == "" {
|
||||
return notAPort, notAPort, fmt.Errorf("appears to be a range but could not be parsed; `%s`", s)
|
||||
}
|
||||
|
||||
startPort, err := parsePortValue("beginning range ", sPorts[0])
|
||||
if err != nil {
|
||||
return notAPort, notAPort, err
|
||||
}
|
||||
|
||||
endPort, err := parsePortValue("ending range ", sPorts[1])
|
||||
if err != nil {
|
||||
return notAPort, notAPort, err
|
||||
}
|
||||
|
||||
if startPort == PortAny {
|
||||
endPort = PortAny
|
||||
}
|
||||
|
||||
return startPort, endPort, nil
|
||||
}
|
||||
|
||||
// parsePortValue accepts a base-10 decimal in [0, 65535] and returns it
|
||||
// widened to int32. Using strconv.ParseUint with bitSize 16 rejects
|
||||
// negative input, out-of-range input (>65535), and any non-decimal byte
|
||||
// by construction, so the int32 widening that follows is provably safe
|
||||
// and cannot collide with PortAny (0) or PortFragment
|
||||
// (-1) via integer truncation.
|
||||
//
|
||||
// prefix is prepended to both error messages so callers can disambiguate
|
||||
// the single-port path (prefix="") from the range bounds (prefix="beginning
|
||||
// range " / "ending range "), preserving the historical error strings.
|
||||
func parsePortValue(prefix, s string) (int32, error) {
|
||||
n, err := strconv.ParseUint(s, 10, 16)
|
||||
if err == nil {
|
||||
return int32(n), nil
|
||||
}
|
||||
if errors.Is(err, strconv.ErrRange) {
|
||||
return 0, fmt.Errorf("%sout of range [0,65535]; `%s`", prefix, s)
|
||||
}
|
||||
return 0, fmt.Errorf("%swas not a number; `%s`", prefix, s)
|
||||
}
|
||||
@@ -0,0 +1,477 @@
|
||||
package firewall
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"errors"
|
||||
"net/netip"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/iputil"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
func Test_parsePort(t *testing.T) {
|
||||
_, _, err := parsePort("")
|
||||
require.EqualError(t, err, "was not a number; ``")
|
||||
|
||||
_, _, err = parsePort(" ")
|
||||
require.EqualError(t, err, "was not a number; ` `")
|
||||
|
||||
_, _, err = parsePort("-")
|
||||
require.EqualError(t, err, "appears to be a range but could not be parsed; `-`")
|
||||
|
||||
_, _, err = parsePort(" - ")
|
||||
require.EqualError(t, err, "appears to be a range but could not be parsed; ` - `")
|
||||
|
||||
_, _, err = parsePort("a-b")
|
||||
require.EqualError(t, err, "beginning range was not a number; `a`")
|
||||
|
||||
_, _, err = parsePort("1-b")
|
||||
require.EqualError(t, err, "ending range was not a number; `b`")
|
||||
|
||||
s, e, err := parsePort(" 1 - 2 ")
|
||||
assert.Equal(t, int32(1), s)
|
||||
assert.Equal(t, int32(2), e)
|
||||
require.NoError(t, err)
|
||||
|
||||
s, e, err = parsePort("0-1")
|
||||
assert.Equal(t, int32(0), s)
|
||||
assert.Equal(t, int32(0), e)
|
||||
require.NoError(t, err)
|
||||
|
||||
s, e, err = parsePort("9919")
|
||||
assert.Equal(t, int32(9919), s)
|
||||
assert.Equal(t, int32(9919), e)
|
||||
require.NoError(t, err)
|
||||
|
||||
s, e, err = parsePort("any")
|
||||
assert.Equal(t, int32(0), s)
|
||||
assert.Equal(t, int32(0), e)
|
||||
require.NoError(t, err)
|
||||
}
|
||||
|
||||
// Test_parsePort_invalid covers inputs that must error. The named bug is
|
||||
// that int32(strconv.Atoi("4294967296")) truncates to 0 == PortAny,
|
||||
// silently turning a typo into a match-all-ports rule; the rest are
|
||||
// representative syntax/range probes.
|
||||
func Test_parsePort_invalid(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
input string
|
||||
wantErrContains string
|
||||
}{
|
||||
// Numeric overflow (the named bug + boundary).
|
||||
{"named bug: 2^32 truncates to PortAny", "4294967296", "out of range"},
|
||||
{"just above max real port", "65536", "out of range"},
|
||||
|
||||
// Negatives route through the range branch and hit the empty-half
|
||||
// guard; included as defense in depth so a future refactor cannot
|
||||
// accidentally reach the int32 cast.
|
||||
{"negative", "-1", "could not be parsed"},
|
||||
|
||||
// Syntax probes.
|
||||
{"NUL between digits", "4\x002", "was not a number"},
|
||||
{"hex notation", "0x10", "was not a number"},
|
||||
{"scientific notation", "1e3", "was not a number"},
|
||||
{"leading whitespace", " 42", "was not a number"},
|
||||
{"fullwidth digits", "42", "was not a number"},
|
||||
|
||||
// Range branch.
|
||||
{"range upper out of range", "1-65536", "ending range out of range"},
|
||||
{"range lower out of range", "65536-65537", "beginning range out of range"},
|
||||
{"range with negative upper", "1--1", "ending range was not a number"},
|
||||
}
|
||||
|
||||
for _, tc := range tests {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
_, _, err := parsePort(tc.input)
|
||||
require.Error(t, err, "input %q must error", tc.input)
|
||||
require.ErrorContains(t, err, tc.wantErrContains)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Test_parsePort_valid_boundaries locks in success cases at 0, 1, and 65535
|
||||
// so a future refactor cannot regress the boundaries.
|
||||
func Test_parsePort_valid_boundaries(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
input string
|
||||
wantStart int32
|
||||
wantEnd int32
|
||||
}{
|
||||
{"zero is PortAny", "0", 0, 0},
|
||||
{"min real port", "1", 1, 1},
|
||||
{"max real port", "65535", 65535, 65535},
|
||||
{"range zero to max forces end to zero", "0-65535", 0, 0},
|
||||
{"range max to max", "65535-65535", 65535, 65535},
|
||||
{"range one to max", "1-65535", 1, 65535},
|
||||
{"range with whitespace inside", " 1 - 2 ", 1, 2},
|
||||
}
|
||||
|
||||
for _, tc := range tests {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
s, e, err := parsePort(tc.input)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, tc.wantStart, s, "start port")
|
||||
assert.Equal(t, tc.wantEnd, e, "end port")
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestAddRulesFromConfig(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
// Test adding tcp rule
|
||||
conf := config.NewC(test.NewLogger())
|
||||
mf := &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"port": "1", "proto": "tcp", "host": "a"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, false, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: false, proto: iputil.IPProtocolTCP, startPort: 1, endPort: 1, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall)
|
||||
|
||||
// Test adding udp rule
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"port": "1", "proto": "udp", "host": "a"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, false, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: false, proto: iputil.IPProtocolUDP, startPort: 1, endPort: 1, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall)
|
||||
|
||||
// Test adding udplite, dccp, and sctp rules
|
||||
for name, proto := range map[string]uint8{"udplite": iputil.IPProtocolUDPLite, "dccp": iputil.IPProtocolDCCP, "sctp": iputil.IPProtocolSCTP} {
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"port": "1-2", "proto": name, "host": "a"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, false, conf, mf), name)
|
||||
assert.Equal(t, addRuleCall{incoming: false, proto: proto, startPort: 1, endPort: 2, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall, name)
|
||||
}
|
||||
|
||||
// Test adding icmp rule
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"port": "1", "proto": "icmp", "host": "a"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, false, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: false, proto: iputil.IPProtocolICMP, startPort: PortAny, endPort: PortAny, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall)
|
||||
|
||||
// Test adding icmp rule no port
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"proto": "icmp", "host": "a"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, false, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: false, proto: iputil.IPProtocolICMP, startPort: PortAny, endPort: PortAny, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall)
|
||||
|
||||
// Test adding rules by protocol number, as yaml would give a string or an int
|
||||
for _, proto := range []any{"47", 47} {
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"port": "any", "proto": proto, "host": "a"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, false, conf, mf), proto)
|
||||
assert.Equal(t, addRuleCall{incoming: false, proto: 47, startPort: PortAny, endPort: PortAny, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall, proto)
|
||||
}
|
||||
|
||||
// Test ICMP and ICMPv6 by number still ignore ports
|
||||
for _, proto := range []uint8{iputil.IPProtocolICMP, iputil.IPProtocolICMPv6} {
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"port": "1", "proto": proto, "host": "a"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, false, conf, mf), proto)
|
||||
assert.Equal(t, addRuleCall{incoming: false, proto: proto, startPort: PortAny, endPort: PortAny, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall, proto)
|
||||
}
|
||||
|
||||
// Test protocols that aren't a known name or a number from 1 to 255
|
||||
for _, proto := range []string{"0", "256", "-1", "gre"} {
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"outbound": []any{map[string]any{"port": "any", "proto": proto, "host": "a"}}}
|
||||
require.EqualError(t, addRulesFromConfig(l, false, conf, mf), "firewall.outbound rule #0; proto was not understood; `"+proto+"`")
|
||||
}
|
||||
|
||||
// Test adding any rule
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "host": "a"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, host: "a", ip: "", localIp: ""}, mf.lastCall)
|
||||
|
||||
// Test adding rule with cidr
|
||||
cidr := netip.MustParsePrefix("10.0.0.0/8")
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "cidr": cidr.String()}}}
|
||||
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, ip: cidr.String(), localIp: ""}, mf.lastCall)
|
||||
|
||||
// Test adding rule with local_cidr
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "local_cidr": cidr.String()}}}
|
||||
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, ip: "", localIp: cidr.String()}, mf.lastCall)
|
||||
|
||||
// Test adding rule with cidr ipv6
|
||||
cidr6 := netip.MustParsePrefix("fd00::/8")
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "cidr": cidr6.String()}}}
|
||||
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, ip: cidr6.String(), localIp: ""}, mf.lastCall)
|
||||
|
||||
// Test adding rule with any cidr
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "cidr": "any"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, ip: "any", localIp: ""}, mf.lastCall)
|
||||
|
||||
// Test adding rule with junk cidr, which RulesBuilder rejects
|
||||
conf = config.NewC(test.NewLogger())
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "cidr": "junk/junk"}}}
|
||||
require.EqualError(t, addRulesFromConfig(l, true, conf, NewRulesBuilder(l)), "firewall.inbound rule #0; cidr did not parse; netip.ParsePrefix(\"junk/junk\"): ParseAddr(\"junk\"): unable to parse IP")
|
||||
|
||||
// Test adding rule with local_cidr ipv6
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "local_cidr": cidr6.String()}}}
|
||||
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, ip: "", localIp: cidr6.String()}, mf.lastCall)
|
||||
|
||||
// Test adding rule with any local_cidr
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "local_cidr": "any"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, localIp: "any"}, mf.lastCall)
|
||||
|
||||
// Test adding rule with junk local_cidr, which RulesBuilder rejects
|
||||
conf = config.NewC(test.NewLogger())
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "local_cidr": "junk/junk"}}}
|
||||
require.EqualError(t, addRulesFromConfig(l, true, conf, NewRulesBuilder(l)), "firewall.inbound rule #0; local_cidr did not parse; netip.ParsePrefix(\"junk/junk\"): ParseAddr(\"junk\"): unable to parse IP")
|
||||
|
||||
// Test adding rule with ca_sha
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "ca_sha": "12312313123"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, ip: "", localIp: "", caSha: "12312313123"}, mf.lastCall)
|
||||
|
||||
// Test adding rule with ca_name
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "ca_name": "root01"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: nil, ip: "", localIp: "", caName: "root01"}, mf.lastCall)
|
||||
|
||||
// Test single group
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "group": "a"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: []string{"a"}, ip: "", localIp: ""}, mf.lastCall)
|
||||
|
||||
// Test single groups
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "groups": "a"}}}
|
||||
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: []string{"a"}, ip: "", localIp: ""}, mf.lastCall)
|
||||
|
||||
// Test multiple AND groups
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "groups": []string{"a", "b"}}}}
|
||||
require.NoError(t, addRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: true, proto: ProtoAny, startPort: 1, endPort: 1, groups: []string{"a", "b"}, ip: "", localIp: ""}, mf.lastCall)
|
||||
|
||||
// Test Add error
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
mf.nextCallReturn = errors.New("test error")
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "host": "a"}}}
|
||||
require.EqualError(t, addRulesFromConfig(l, true, conf, mf), "firewall.inbound rule #0; test error")
|
||||
}
|
||||
|
||||
// TestRulesFromConfig_defaultLocalCIDR ensures rules without a local_cidr allow only the vpn networks when there are
|
||||
// unsafe networks, unless default_local_cidr_any is set, and that a rule's own local_cidr is kept either way
|
||||
func TestRulesFromConfig_defaultLocalCIDR(t *testing.T) {
|
||||
vpnNetworks := []netip.Prefix{netip.MustParsePrefix("10.1.0.5/16")}
|
||||
unsafeNetworks := []netip.Prefix{netip.MustParsePrefix("192.168.0.0/24")}
|
||||
vpnAddr := netip.MustParseAddr("10.1.9.9")
|
||||
unsafeAddr := netip.MustParseAddr("192.168.0.3")
|
||||
|
||||
allows := func(lr *localRules, addr netip.Addr) bool {
|
||||
return lr.match(&Packet{LocalAddr: addr}, nil)
|
||||
}
|
||||
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
unsafeNetworks []netip.Prefix
|
||||
defaultLocalCIDRAny bool
|
||||
wantUnsafe bool
|
||||
}{
|
||||
{"no unsafe networks", nil, false, true},
|
||||
{"unsafe networks", unsafeNetworks, false, false},
|
||||
{"unsafe networks and default_local_cidr_any", unsafeNetworks, true, true},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
conf := config.NewC(test.NewLogger())
|
||||
conf.Settings["firewall"] = map[string]any{
|
||||
"default_local_cidr_any": tc.defaultLocalCIDRAny,
|
||||
"inbound": []any{
|
||||
map[string]any{"port": "any", "proto": "any", "host": "any"},
|
||||
map[string]any{"port": "22", "proto": "tcp", "host": "any"},
|
||||
map[string]any{"port": "80", "proto": "tcp", "host": "any", "local_cidr": "192.168.0.0/24"},
|
||||
map[string]any{"port": "443", "proto": "tcp", "host": "any", "local_cidr": "any"},
|
||||
},
|
||||
}
|
||||
rules, err := RulesFromConfig(test.NewLogger(), conf, vpnNetworks, tc.unsafeNetworks)
|
||||
require.NoError(t, err)
|
||||
|
||||
// The proto `any` rule, copied into a protocol with rules of its own and shared by one without
|
||||
for _, proto := range []uint8{iputil.IPProtocolTCP, 47} {
|
||||
lr := rules.In.protos[proto][PortAny].Any.Any
|
||||
assert.True(t, allows(lr, vpnAddr), "proto %d", proto)
|
||||
assert.Equal(t, tc.wantUnsafe, allows(lr, unsafeAddr), "proto %d", proto)
|
||||
}
|
||||
|
||||
tcp := rules.In.protos[iputil.IPProtocolTCP]
|
||||
assert.True(t, allows(tcp[22].Any.Any, vpnAddr))
|
||||
assert.Equal(t, tc.wantUnsafe, allows(tcp[22].Any.Any, unsafeAddr))
|
||||
|
||||
assert.False(t, allows(tcp[80].Any.Any, vpnAddr))
|
||||
assert.True(t, allows(tcp[80].Any.Any, unsafeAddr))
|
||||
|
||||
assert.True(t, allows(tcp[443].Any.Any, vpnAddr))
|
||||
assert.True(t, allows(tcp[443].Any.Any, unsafeAddr))
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func Test_convertRule(t *testing.T) {
|
||||
ob := &bytes.Buffer{}
|
||||
l := test.NewLoggerWithOutput(ob)
|
||||
|
||||
// Ensure group array of 1 is converted and a warning is printed
|
||||
c := map[string]any{
|
||||
"group": []any{"group1"},
|
||||
}
|
||||
|
||||
r, err := yamlToConfigRule(l, c, "test", 1)
|
||||
assert.Contains(t, ob.String(), "group was an array with a single value, converting to simple value")
|
||||
assert.Contains(t, ob.String(), "table=test")
|
||||
assert.Contains(t, ob.String(), "rule=1")
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, []string{"group1"}, r.Groups)
|
||||
|
||||
// Ensure group array of > 1 is errord
|
||||
ob.Reset()
|
||||
c = map[string]any{
|
||||
"group": []any{"group1", "group2"},
|
||||
}
|
||||
|
||||
r, err = yamlToConfigRule(l, c, "test", 1)
|
||||
assert.Empty(t, ob.String())
|
||||
require.Error(t, err, "group should contain a single value, an array with more than one entry was provided")
|
||||
|
||||
// Make sure a well formed group is alright
|
||||
ob.Reset()
|
||||
c = map[string]any{
|
||||
"group": "group1",
|
||||
}
|
||||
|
||||
r, err = yamlToConfigRule(l, c, "test", 1)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, []string{"group1"}, r.Groups)
|
||||
}
|
||||
|
||||
func Test_convertRuleSanity(t *testing.T) {
|
||||
ob := &bytes.Buffer{}
|
||||
l := test.NewLoggerWithOutput(ob)
|
||||
|
||||
noWarningPlease := []map[string]any{
|
||||
{"group": "group1"},
|
||||
{"groups": []any{"group2"}},
|
||||
{"host": "bob"},
|
||||
{"cidr": "1.1.1.1/1"},
|
||||
{"groups": []any{"group2"}, "host": "bob"},
|
||||
{"cidr": "1.1.1.1/1", "host": "bob"},
|
||||
{"groups": []any{"group2"}, "cidr": "1.1.1.1/1"},
|
||||
{"groups": []any{"group2"}, "cidr": "1.1.1.1/1", "host": "bob"},
|
||||
}
|
||||
for _, c := range noWarningPlease {
|
||||
r, err := yamlToConfigRule(l, c, "test", 1)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, r.sanity(), "should not generate a sanity warning, %+v", c)
|
||||
}
|
||||
|
||||
yesWarningPlease := []map[string]any{
|
||||
{"group": "group1"},
|
||||
{"groups": []any{"group2"}},
|
||||
{"cidr": "1.1.1.1/1"},
|
||||
{"groups": []any{"group2"}, "host": "bob"},
|
||||
{"cidr": "1.1.1.1/1", "host": "bob"},
|
||||
{"groups": []any{"group2"}, "cidr": "1.1.1.1/1"},
|
||||
{"groups": []any{"group2"}, "cidr": "1.1.1.1/1", "host": "bob"},
|
||||
}
|
||||
for _, c := range yesWarningPlease {
|
||||
c["host"] = "any"
|
||||
r, err := yamlToConfigRule(l, c, "test", 1)
|
||||
require.NoError(t, err)
|
||||
err = r.sanity()
|
||||
require.Error(t, err, "I wanted a warning: %+v", c)
|
||||
}
|
||||
//reset the list
|
||||
yesWarningPlease = []map[string]any{
|
||||
{"group": "group1"},
|
||||
{"groups": []any{"group2"}},
|
||||
{"cidr": "1.1.1.1/1"},
|
||||
{"groups": []any{"group2"}, "host": "bob"},
|
||||
{"cidr": "1.1.1.1/1", "host": "bob"},
|
||||
{"groups": []any{"group2"}, "cidr": "1.1.1.1/1"},
|
||||
{"groups": []any{"group2"}, "cidr": "1.1.1.1/1", "host": "bob"},
|
||||
}
|
||||
for _, c := range yesWarningPlease {
|
||||
r, err := yamlToConfigRule(l, c, "test", 1)
|
||||
require.NoError(t, err)
|
||||
r.Groups = append(r.Groups, "any")
|
||||
err = r.sanity()
|
||||
require.Error(t, err, "I wanted a warning: %+v", c)
|
||||
}
|
||||
}
|
||||
|
||||
type addRuleCall struct {
|
||||
incoming bool
|
||||
proto uint8
|
||||
startPort int32
|
||||
endPort int32
|
||||
groups []string
|
||||
host string
|
||||
ip string
|
||||
localIp string
|
||||
caName string
|
||||
caSha string
|
||||
}
|
||||
|
||||
type mockFirewall struct {
|
||||
lastCall addRuleCall
|
||||
nextCallReturn error
|
||||
}
|
||||
|
||||
func (mf *mockFirewall) AddRule(incoming bool, proto uint8, startPort int32, endPort int32, groups []string, host string, ip, localIp, caName string, caSha string) error {
|
||||
mf.lastCall = addRuleCall{
|
||||
incoming: incoming,
|
||||
proto: proto,
|
||||
startPort: startPort,
|
||||
endPort: endPort,
|
||||
groups: groups,
|
||||
host: host,
|
||||
ip: ip,
|
||||
localIp: localIp,
|
||||
caName: caName,
|
||||
caSha: caSha,
|
||||
}
|
||||
|
||||
err := mf.nextCallReturn
|
||||
mf.nextCallReturn = nil
|
||||
return err
|
||||
}
|
||||
@@ -50,6 +50,12 @@ func (fp Packet) MarshalJSON() ([]byte, error) {
|
||||
proto = "icmpv6"
|
||||
case iputil.IPProtocolUDP:
|
||||
proto = "udp"
|
||||
case iputil.IPProtocolUDPLite:
|
||||
proto = "udplite"
|
||||
case iputil.IPProtocolDCCP:
|
||||
proto = "dccp"
|
||||
case iputil.IPProtocolSCTP:
|
||||
proto = "sctp"
|
||||
default:
|
||||
proto = fmt.Sprintf("unknown %v", fp.Protocol)
|
||||
}
|
||||
|
||||
@@ -0,0 +1,330 @@
|
||||
package firewall
|
||||
|
||||
import (
|
||||
"crypto/sha256"
|
||||
"encoding/hex"
|
||||
"fmt"
|
||||
"hash"
|
||||
"hash/fnv"
|
||||
"io"
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"slices"
|
||||
|
||||
"github.com/gaissmai/bart"
|
||||
"github.com/slackhq/nebula/iputil"
|
||||
)
|
||||
|
||||
// RulesBuilder collects the inbound and outbound rules, Build turns them into a Table for each direction
|
||||
type RulesBuilder struct {
|
||||
in, out tableRules
|
||||
|
||||
// defaultLocalCIDRAny makes rules without a local cidr allow any local address, even with unsafe networks
|
||||
defaultLocalCIDRAny bool
|
||||
|
||||
// ruleSHA and ruleFNV hash every rule as it's added, see Rules
|
||||
ruleSHA hash.Hash
|
||||
ruleFNV hash.Hash32
|
||||
|
||||
l *slog.Logger
|
||||
}
|
||||
|
||||
// tableRules are one direction's rules, waiting to be built into a Table
|
||||
type tableRules struct {
|
||||
anyRules []rule
|
||||
// protoRules holds the rules for each protocol besides proto `any`, ICMPv6 rules are kept with ICMP
|
||||
protoRules [256][]rule
|
||||
}
|
||||
|
||||
// rule is a parsed rule, so adding it to a Table can't fail
|
||||
type rule struct {
|
||||
startPort, endPort int32
|
||||
groups []string
|
||||
host string
|
||||
caName, caSha string
|
||||
|
||||
// cidr is the remote cidr, not valid when the rule doesn't have one
|
||||
cidr netip.Prefix
|
||||
anyCIDR bool
|
||||
|
||||
// localCIDR is the local addresses the rule allows, anyLocalCIDR allows all of them.
|
||||
// Neither is set for a rule without a local cidr until the Table is built and it gets the default.
|
||||
// localCIDR is shared by every localRules the rule is added to, so it's never changed, see localRules.add
|
||||
localCIDR *bart.Lite
|
||||
anyLocalCIDR bool
|
||||
}
|
||||
|
||||
func NewRulesBuilder(l *slog.Logger) *RulesBuilder {
|
||||
return &RulesBuilder{
|
||||
ruleSHA: sha256.New(),
|
||||
ruleFNV: fnv.New32a(),
|
||||
l: l,
|
||||
}
|
||||
}
|
||||
|
||||
// AddRule adds a rule for incoming or outgoing traffic, on proto or on every protocol when proto is ProtoAny.
|
||||
// The rule is parsed now, so a bad rule is reported when it's added rather than when the Tables are built.
|
||||
func (b *RulesBuilder) AddRule(incoming bool, proto uint8, startPort int32, endPort int32, groups []string, host string, cidr, localCidr, caName string, caSha string) error {
|
||||
if proto == iputil.IPProtocolICMP || proto == iputil.IPProtocolICMPv6 {
|
||||
//ICMP traffic doesn't have ports, so we always coerce to "any", even if a value is provided
|
||||
if startPort != PortAny {
|
||||
b.l.Warn("ignoring port specification for ICMP firewall rule", "startPort", startPort)
|
||||
}
|
||||
startPort = PortAny
|
||||
endPort = PortAny
|
||||
}
|
||||
|
||||
r, err := parseRule(startPort, endPort, groups, host, cidr, localCidr, caName, caSha)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
if incoming {
|
||||
b.in.add(proto, r)
|
||||
} else {
|
||||
b.out.add(proto, r)
|
||||
}
|
||||
|
||||
// The rule hashes are of these lines, changing them changes every hash
|
||||
fmt.Fprintf(io.MultiWriter(b.ruleSHA, b.ruleFNV),
|
||||
"incoming: %v, proto: %v, startPort: %v, endPort: %v, groups: %v, host: %v, ip: %v, localIp: %v, caName: %v, caSha: %s\n",
|
||||
incoming, proto, startPort, endPort, groups, host, cidr, localCidr, caName, caSha,
|
||||
)
|
||||
|
||||
direction := "incoming"
|
||||
if !incoming {
|
||||
direction = "outgoing"
|
||||
}
|
||||
b.l.Info("Firewall rule added",
|
||||
"firewallRule", m{"direction": direction, "proto": proto, "startPort": startPort, "endPort": endPort, "groups": groups, "host": host, "cidr": cidr, "localCidr": localCidr, "caName": caName, "caSha": caSha},
|
||||
)
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// Build turns the rules into a Table for each direction, and hashes them. Rules without a local cidr allow
|
||||
// vpnNetworks when there are unsafe networks, otherwise any local address.
|
||||
func (b *RulesBuilder) Build(vpnNetworks, unsafeNetworks []netip.Prefix) Rules {
|
||||
var defaultLocal *bart.Lite
|
||||
if len(unsafeNetworks) > 0 && !b.defaultLocalCIDRAny {
|
||||
defaultLocal = new(bart.Lite)
|
||||
for _, network := range vpnNetworks {
|
||||
defaultLocal.Insert(network)
|
||||
}
|
||||
}
|
||||
|
||||
return Rules{
|
||||
In: b.in.build(defaultLocal),
|
||||
Out: b.out.build(defaultLocal),
|
||||
Hash: hex.EncodeToString(b.ruleSHA.Sum(nil)),
|
||||
HashFNV: b.ruleFNV.Sum32(),
|
||||
}
|
||||
}
|
||||
|
||||
func parseRule(startPort, endPort int32, groups []string, host, cidr, localCidr, caName, caSha string) (rule, error) {
|
||||
if startPort > endPort {
|
||||
return rule{}, fmt.Errorf("start port was lower than end port")
|
||||
}
|
||||
|
||||
r := rule{
|
||||
startPort: startPort,
|
||||
endPort: endPort,
|
||||
groups: groups,
|
||||
host: host,
|
||||
caName: caName,
|
||||
caSha: caSha,
|
||||
}
|
||||
|
||||
var err error
|
||||
r.cidr, r.anyCIDR, err = parseCIDR(cidr)
|
||||
if err != nil {
|
||||
return rule{}, fmt.Errorf("cidr did not parse; %w", err)
|
||||
}
|
||||
|
||||
var localCIDR netip.Prefix
|
||||
localCIDR, r.anyLocalCIDR, err = parseCIDR(localCidr)
|
||||
if err != nil {
|
||||
return rule{}, fmt.Errorf("local_cidr did not parse; %w", err)
|
||||
}
|
||||
if localCIDR.IsValid() {
|
||||
r.localCIDR = new(bart.Lite)
|
||||
r.localCIDR.Insert(localCIDR)
|
||||
}
|
||||
|
||||
return r, nil
|
||||
}
|
||||
|
||||
// add keeps r for proto, or for every protocol when proto is ProtoAny
|
||||
func (tr *tableRules) add(proto uint8, r rule) {
|
||||
switch proto {
|
||||
case ProtoAny:
|
||||
tr.anyRules = append(tr.anyRules, r)
|
||||
case iputil.IPProtocolICMPv6:
|
||||
tr.protoRules[iputil.IPProtocolICMP] = append(tr.protoRules[iputil.IPProtocolICMP], r)
|
||||
default:
|
||||
tr.protoRules[proto] = append(tr.protoRules[proto], r)
|
||||
}
|
||||
}
|
||||
|
||||
// build turns the rules into a Table. Rules without a local cidr allow defaultLocal,
|
||||
// or any local address when defaultLocal is nil.
|
||||
func (tr *tableRules) build(defaultLocal *bart.Lite) *Table {
|
||||
t := &Table{}
|
||||
|
||||
// Every protocol starts out sharing the proto `any` rules, including protos[ProtoAny]
|
||||
anyProto := newPortRules(defaultLocal, tr.anyRules)
|
||||
for proto := range t.protos {
|
||||
t.protos[proto] = anyProto
|
||||
}
|
||||
|
||||
// Protocols with rules of their own get a copy of the proto `any` rules too, so a packet only checks one set
|
||||
for proto, rules := range tr.protoRules {
|
||||
if len(rules) > 0 {
|
||||
t.protos[proto] = newPortRules(defaultLocal, tr.anyRules, rules)
|
||||
}
|
||||
}
|
||||
|
||||
// ICMP and ICMPv6 share one set of rules, add keeps them together under ICMP
|
||||
t.protos[iputil.IPProtocolICMPv6] = t.protos[iputil.IPProtocolICMP]
|
||||
|
||||
return t
|
||||
}
|
||||
|
||||
// newPortRules builds portRules from each set of rules, or returns nil when there are none
|
||||
func newPortRules(defaultLocal *bart.Lite, ruleSets ...[]rule) portRules {
|
||||
var pr portRules
|
||||
for _, rules := range ruleSets {
|
||||
for _, r := range rules {
|
||||
if pr == nil {
|
||||
pr = portRules{}
|
||||
}
|
||||
pr.add(r.withDefaultLocal(defaultLocal))
|
||||
}
|
||||
}
|
||||
return pr
|
||||
}
|
||||
|
||||
// parseCIDR parses a rule's cidr, which is empty, `any`, or a prefix
|
||||
func parseCIDR(s string) (prefix netip.Prefix, isAny bool, err error) {
|
||||
switch s {
|
||||
case "":
|
||||
return netip.Prefix{}, false, nil
|
||||
case "any":
|
||||
return netip.Prefix{}, true, nil
|
||||
}
|
||||
|
||||
prefix, err = netip.ParsePrefix(s)
|
||||
return prefix, false, err
|
||||
}
|
||||
|
||||
// isAny reports whether r matches any host, making its groups, host, and cidr irrelevant
|
||||
func (r rule) isAny() bool {
|
||||
if len(r.groups) == 0 && r.host == "" && !r.cidr.IsValid() {
|
||||
return true
|
||||
}
|
||||
|
||||
return slices.Contains(r.groups, "any") || r.host == "any" || r.anyCIDR
|
||||
}
|
||||
|
||||
// withDefaultLocal returns r allowing defaultLocal, or any local address when defaultLocal is nil,
|
||||
// unless r has a local cidr of its own
|
||||
func (r rule) withDefaultLocal(defaultLocal *bart.Lite) rule {
|
||||
if !r.anyLocalCIDR && r.localCIDR == nil {
|
||||
r.anyLocalCIDR = defaultLocal == nil
|
||||
r.localCIDR = defaultLocal
|
||||
}
|
||||
return r
|
||||
}
|
||||
|
||||
func (pr portRules) add(r rule) {
|
||||
for i := r.startPort; i <= r.endPort; i++ {
|
||||
cr := pr[i]
|
||||
if cr == nil {
|
||||
cr = &caRules{}
|
||||
pr[i] = cr
|
||||
}
|
||||
cr.add(r)
|
||||
}
|
||||
}
|
||||
|
||||
func (cr *caRules) add(r rule) {
|
||||
if r.caSha == "" && r.caName == "" {
|
||||
if cr.Any == nil {
|
||||
cr.Any = &remoteRules{}
|
||||
}
|
||||
cr.Any.add(r)
|
||||
return
|
||||
}
|
||||
|
||||
if r.caSha != "" {
|
||||
getOrNew(&cr.CAShas, r.caSha).add(r)
|
||||
}
|
||||
|
||||
if r.caName != "" {
|
||||
getOrNew(&cr.CANames, r.caName).add(r)
|
||||
}
|
||||
}
|
||||
|
||||
func (rr *remoteRules) add(r rule) {
|
||||
if r.isAny() {
|
||||
if rr.Any == nil {
|
||||
rr.Any = &localRules{}
|
||||
}
|
||||
rr.Any.add(r)
|
||||
return
|
||||
}
|
||||
|
||||
if len(r.groups) > 0 {
|
||||
lr := &localRules{}
|
||||
lr.add(r)
|
||||
rr.Groups = append(rr.Groups, &groupsRule{
|
||||
Groups: r.groups,
|
||||
LocalCIDR: lr,
|
||||
})
|
||||
}
|
||||
|
||||
if r.host != "" {
|
||||
getOrNew(&rr.Hosts, r.host).add(r)
|
||||
}
|
||||
|
||||
if r.cidr.IsValid() {
|
||||
if rr.CIDR == nil {
|
||||
rr.CIDR = new(bart.Table[*localRules])
|
||||
}
|
||||
lr, ok := rr.CIDR.Get(r.cidr)
|
||||
if !ok {
|
||||
lr = &localRules{}
|
||||
rr.CIDR.Insert(r.cidr, lr)
|
||||
}
|
||||
lr.add(r)
|
||||
}
|
||||
}
|
||||
|
||||
func (lr *localRules) add(r rule) {
|
||||
if r.anyLocalCIDR {
|
||||
lr.Any = true
|
||||
return
|
||||
}
|
||||
|
||||
// Share the rule's local cidrs until another rule's need adding, then copy them instead of changing them
|
||||
if lr.LocalCIDR == nil {
|
||||
lr.LocalCIDR = r.localCIDR
|
||||
return
|
||||
}
|
||||
for prefix := range r.localCIDR.All() {
|
||||
lr.LocalCIDR = lr.LocalCIDR.InsertPersist(prefix)
|
||||
}
|
||||
}
|
||||
|
||||
// getOrNew returns m[k], adding a new value for k first when there isn't one. m is made if it's nil.
|
||||
func getOrNew[M ~map[K]*V, K comparable, V any](m *M, k K) *V {
|
||||
if *m == nil {
|
||||
*m = make(M)
|
||||
}
|
||||
v := (*m)[k]
|
||||
if v == nil {
|
||||
v = new(V)
|
||||
(*m)[k] = v
|
||||
}
|
||||
return v
|
||||
}
|
||||
@@ -0,0 +1,239 @@
|
||||
package firewall
|
||||
|
||||
import (
|
||||
"math"
|
||||
"net/netip"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/iputil"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
func TestRulesBuilder_AddRule(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
|
||||
ti, err := netip.ParsePrefix("1.2.3.4/32")
|
||||
require.NoError(t, err)
|
||||
|
||||
ti6, err := netip.ParsePrefix("fd12::34/128")
|
||||
require.NoError(t, err)
|
||||
|
||||
rb := NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 1, 1, []string{}, "", "", "", "", ""))
|
||||
rules := rb.Build(nil, nil)
|
||||
// An empty rule is any
|
||||
assert.True(t, rules.In.protos[iputil.IPProtocolTCP][1].Any.Any.Any)
|
||||
assert.Empty(t, rules.In.protos[iputil.IPProtocolTCP][1].Any.Groups)
|
||||
assert.Empty(t, rules.In.protos[iputil.IPProtocolTCP][1].Any.Hosts)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolUDP, 1, 1, []string{"g1"}, "", "", "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.Nil(t, rules.In.protos[iputil.IPProtocolUDP][1].Any.Any)
|
||||
assert.Contains(t, rules.In.protos[iputil.IPProtocolUDP][1].Any.Groups[0].Groups, "g1")
|
||||
assert.Empty(t, rules.In.protos[iputil.IPProtocolUDP][1].Any.Hosts)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolICMP, 1, 1, []string{}, "h1", "", "", "", ""))
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolICMPv6, 1, 1, []string{}, "h2", "", "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
//no matter what port is given for icmp, it should end up as "any"
|
||||
assert.Nil(t, rules.In.protos[iputil.IPProtocolICMP][PortAny].Any.Any)
|
||||
assert.Empty(t, rules.In.protos[iputil.IPProtocolICMP][PortAny].Any.Groups)
|
||||
assert.Contains(t, rules.In.protos[iputil.IPProtocolICMP][PortAny].Any.Hosts, "h1")
|
||||
|
||||
// ICMP and ICMPv6 share one set of rules
|
||||
assert.Contains(t, rules.In.protos[iputil.IPProtocolICMP][PortAny].Any.Hosts, "h2")
|
||||
assert.Contains(t, rules.In.protos[iputil.IPProtocolICMPv6][PortAny].Any.Hosts, "h1")
|
||||
|
||||
// Any other protocol number gets its own rules
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(true, 47, 0, 0, []string{"g1"}, "", "", "", "", "")) // GRE
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.Contains(t, rules.In.protos[47][PortAny].Any.Groups[0].Groups, "g1")
|
||||
assert.Nil(t, rules.In.protos[iputil.IPProtocolTCP])
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 1, 1, []string{}, "", ti.String(), "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.Nil(t, rules.Out.protos[ProtoAny][1].Any.Any)
|
||||
_, ok := rules.Out.protos[ProtoAny][1].Any.CIDR.Get(ti)
|
||||
assert.True(t, ok)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 1, 1, []string{}, "", ti6.String(), "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.Nil(t, rules.Out.protos[ProtoAny][1].Any.Any)
|
||||
_, ok = rules.Out.protos[ProtoAny][1].Any.CIDR.Get(ti6)
|
||||
assert.True(t, ok)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 1, 1, []string{}, "", "", ti.String(), "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.NotNil(t, rules.Out.protos[ProtoAny][1].Any.Any)
|
||||
ok = rules.Out.protos[ProtoAny][1].Any.Any.LocalCIDR.Get(ti)
|
||||
assert.True(t, ok)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 1, 1, []string{}, "", "", ti6.String(), "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.NotNil(t, rules.Out.protos[ProtoAny][1].Any.Any)
|
||||
ok = rules.Out.protos[ProtoAny][1].Any.Any.LocalCIDR.Get(ti6)
|
||||
assert.True(t, ok)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolUDP, 1, 1, []string{"g1"}, "", "", "", "ca-name", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.Contains(t, rules.In.protos[iputil.IPProtocolUDP][1].CANames, "ca-name")
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolUDP, 1, 1, []string{"g1"}, "", "", "", "", "ca-sha"))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.Contains(t, rules.In.protos[iputil.IPProtocolUDP][1].CAShas, "ca-sha")
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "any", "", "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.True(t, rules.Out.protos[ProtoAny][0].Any.Any.Any)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
anyIp, err := netip.ParsePrefix("0.0.0.0/0")
|
||||
require.NoError(t, err)
|
||||
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", anyIp.String(), "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.Nil(t, rules.Out.protos[ProtoAny][0].Any.Any)
|
||||
table, ok := rules.Out.protos[ProtoAny][0].Any.CIDR.Lookup(netip.MustParseAddr("1.1.1.1"))
|
||||
assert.True(t, table.Any)
|
||||
table, ok = rules.Out.protos[ProtoAny][0].Any.CIDR.Lookup(netip.MustParseAddr("9::9"))
|
||||
assert.False(t, ok)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
anyIp6, err := netip.ParsePrefix("::/0")
|
||||
require.NoError(t, err)
|
||||
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", anyIp6.String(), "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.Nil(t, rules.Out.protos[ProtoAny][0].Any.Any)
|
||||
table, ok = rules.Out.protos[ProtoAny][0].Any.CIDR.Lookup(netip.MustParseAddr("9::9"))
|
||||
assert.True(t, table.Any)
|
||||
table, ok = rules.Out.protos[ProtoAny][0].Any.CIDR.Lookup(netip.MustParseAddr("1.1.1.1"))
|
||||
assert.False(t, ok)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", "any", "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.True(t, rules.Out.protos[ProtoAny][0].Any.Any.Any)
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", "", anyIp.String(), "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.False(t, rules.Out.protos[ProtoAny][0].Any.Any.Any)
|
||||
assert.True(t, rules.Out.protos[ProtoAny][0].Any.Any.LocalCIDR.Lookup(netip.MustParseAddr("1.1.1.1")))
|
||||
assert.False(t, rules.Out.protos[ProtoAny][0].Any.Any.LocalCIDR.Lookup(netip.MustParseAddr("9::9")))
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", "", anyIp6.String(), "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.False(t, rules.Out.protos[ProtoAny][0].Any.Any.Any)
|
||||
assert.True(t, rules.Out.protos[ProtoAny][0].Any.Any.LocalCIDR.Lookup(netip.MustParseAddr("9::9")))
|
||||
assert.False(t, rules.Out.protos[ProtoAny][0].Any.Any.LocalCIDR.Lookup(netip.MustParseAddr("1.1.1.1")))
|
||||
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(false, ProtoAny, 0, 0, []string{}, "", "", "any", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.True(t, rules.Out.protos[ProtoAny][0].Any.Any.Any)
|
||||
|
||||
// Every protocol number is accepted
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(true, math.MaxUint8, 0, 0, []string{}, "", "", "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.True(t, rules.In.protos[math.MaxUint8][PortAny].Any.Any.Any)
|
||||
|
||||
// Test error conditions, a bad rule is reported when it's added
|
||||
rb = NewRulesBuilder(l)
|
||||
require.Error(t, rb.AddRule(true, ProtoAny, 10, 0, []string{}, "", "", "", "", ""))
|
||||
require.Error(t, rb.AddRule(true, ProtoAny, 0, 0, []string{}, "", "junk", "", "", ""))
|
||||
require.Error(t, rb.AddRule(true, ProtoAny, 0, 0, []string{}, "", "", "junk", "", ""))
|
||||
|
||||
// ICMP and ICMPv6 share one copy of each proto `any` rule
|
||||
rb = NewRulesBuilder(l)
|
||||
require.NoError(t, rb.AddRule(true, ProtoAny, PortAny, PortAny, []string{"default-group"}, "", "", "", "", ""))
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolICMPv6, PortAny, PortAny, []string{"nope"}, "", "", "", "", ""))
|
||||
rules = rb.Build(nil, nil)
|
||||
assert.Len(t, rules.In.protos[iputil.IPProtocolICMP][PortAny].Any.Groups, 2)
|
||||
assert.Len(t, rules.In.protos[iputil.IPProtocolICMPv6][PortAny].Any.Groups, 2)
|
||||
|
||||
// No rules allow nothing
|
||||
rules = NewRulesBuilder(l).Build(nil, nil)
|
||||
for proto := range rules.In.protos {
|
||||
assert.Nil(t, rules.In.protos[proto], "proto %d", proto)
|
||||
assert.Nil(t, rules.Out.protos[proto], "proto %d", proto)
|
||||
}
|
||||
}
|
||||
|
||||
// TestRulesBuilder_sharedLocalCIDR ensures local cidrs shared between rules and ports are copied, not changed,
|
||||
// when another rule's local cidrs are added to them. The prefixes share their first octet so the copy has to reach
|
||||
// past the root of the shared table.
|
||||
func TestRulesBuilder_sharedLocalCIDR(t *testing.T) {
|
||||
vpnNetworks := []netip.Prefix{
|
||||
netip.MustParsePrefix("10.1.0.5/16"),
|
||||
netip.MustParsePrefix("10.2.0.5/16"),
|
||||
netip.MustParsePrefix("fd00:1::5/64"),
|
||||
}
|
||||
unsafeNetworks := []netip.Prefix{netip.MustParsePrefix("192.168.0.0/24")}
|
||||
vpn1 := netip.MustParseAddr("10.1.9.9")
|
||||
vpn2 := netip.MustParseAddr("10.2.9.9")
|
||||
vpn6 := netip.MustParseAddr("fd00:1::9")
|
||||
h1Extra := netip.MustParseAddr("10.3.0.1")
|
||||
h1Extra6 := netip.MustParseAddr("fd00:2::1")
|
||||
h2Own := netip.MustParseAddr("10.4.0.1")
|
||||
|
||||
rb := NewRulesBuilder(test.NewLogger())
|
||||
// h1 allows the vpn networks by default on ports 1 and 2, and 10.3.0.0/16 and fd00:2::/64 as well on port 1
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 1, 2, nil, "h1", "", "", "", ""))
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 1, 1, nil, "h1", "", "10.3.0.0/16", "", ""))
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 1, 1, nil, "h1", "", "fd00:2::/64", "", ""))
|
||||
// h2 allows 10.4.0.0/16 on ports 1 and 2, and the vpn networks by default as well on port 1
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 1, 2, nil, "h2", "", "10.4.0.0/16", "", ""))
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 1, 1, nil, "h2", "", "", "", ""))
|
||||
// h3 only has the default
|
||||
require.NoError(t, rb.AddRule(true, iputil.IPProtocolTCP, 3, 3, nil, "h3", "", "", "", ""))
|
||||
rules := rb.Build(vpnNetworks, unsafeNetworks)
|
||||
|
||||
for _, tc := range []struct {
|
||||
port int32
|
||||
host string
|
||||
addr netip.Addr
|
||||
want bool
|
||||
}{
|
||||
{1, "h1", vpn1, true},
|
||||
{1, "h1", vpn2, true},
|
||||
{1, "h1", vpn6, true},
|
||||
{1, "h1", h1Extra, true},
|
||||
{1, "h1", h1Extra6, true},
|
||||
{1, "h1", h2Own, false},
|
||||
{2, "h1", vpn1, true},
|
||||
{2, "h1", h1Extra, false},
|
||||
{2, "h1", h1Extra6, false},
|
||||
{1, "h2", h2Own, true},
|
||||
{1, "h2", vpn1, true},
|
||||
{1, "h2", vpn2, true},
|
||||
{1, "h2", vpn6, true},
|
||||
{1, "h2", h1Extra, false},
|
||||
{2, "h2", h2Own, true},
|
||||
{2, "h2", vpn1, false},
|
||||
{2, "h2", vpn6, false},
|
||||
{3, "h3", vpn1, true},
|
||||
{3, "h3", vpn2, true},
|
||||
{3, "h3", vpn6, true},
|
||||
{3, "h3", h1Extra, false},
|
||||
{3, "h3", h1Extra6, false},
|
||||
{3, "h3", h2Own, false},
|
||||
} {
|
||||
lr := rules.In.protos[iputil.IPProtocolTCP][tc.port].Any.Hosts[tc.host]
|
||||
assert.Equal(t, tc.want, lr.match(&Packet{LocalAddr: tc.addr}, nil), "port %d, %s, %s", tc.port, tc.host, tc.addr)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,188 @@
|
||||
package firewall
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
|
||||
"github.com/gaissmai/bart"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/iputil"
|
||||
)
|
||||
|
||||
// Rules are the Tables built for each direction, with hashes of the rules they were built from
|
||||
type Rules struct {
|
||||
In, Out *Table
|
||||
|
||||
// Hash is a sha256 of the rules, HashFNV is an FNV-1a of them for use as a metric value.
|
||||
// Rule sets with the same rules have the same hashes.
|
||||
Hash string
|
||||
HashFNV uint32
|
||||
}
|
||||
|
||||
// Table holds the rules for one direction, the evaluation order is:
|
||||
// Proto AND port AND (CA SHA or CA name) AND local CIDR AND (group OR groups OR name OR remote CIDR)
|
||||
// A Table doesn't change once built, see RulesBuilder.
|
||||
type Table struct {
|
||||
// protos holds the rules for each IP protocol number, so a packet is only checked against one set of rules.
|
||||
// A protocol with rules of its own also holds a copy of every proto `any` rule, the rest share the proto `any`
|
||||
// rules, which are at protos[ProtoAny]. nil when a protocol has no rules at all.
|
||||
// ICMP and ICMPv6 share one set of rules.
|
||||
protos [256]portRules
|
||||
}
|
||||
|
||||
// Even though ports are uint16, int32 maps are faster for lookup
|
||||
// Plus we can use `-1` for fragment rules
|
||||
type portRules map[int32]*caRules
|
||||
|
||||
// caRules and the types below it only make their maps and tables once a rule needs them, a range of ports
|
||||
// gets a copy for every port so empty ones add up
|
||||
type caRules struct {
|
||||
Any *remoteRules
|
||||
CANames map[string]*remoteRules
|
||||
CAShas map[string]*remoteRules
|
||||
}
|
||||
|
||||
type remoteRules struct {
|
||||
// Any makes Hosts, Groups, and CIDR irrelevant
|
||||
Any *localRules
|
||||
Hosts map[string]*localRules
|
||||
Groups []*groupsRule
|
||||
CIDR *bart.Table[*localRules]
|
||||
}
|
||||
|
||||
type groupsRule struct {
|
||||
Groups []string
|
||||
LocalCIDR *localRules
|
||||
}
|
||||
|
||||
type localRules struct {
|
||||
Any bool
|
||||
// LocalCIDR is always set when Any isn't. It's shared with other localRules, so it's never changed.
|
||||
LocalCIDR *bart.Lite
|
||||
}
|
||||
|
||||
// Match reports whether a rule for the direction p is going allows it
|
||||
func (r *Rules) Match(p *Packet, incoming bool, c *cert.CachedCertificate, caPool *cert.CAPool) bool {
|
||||
t := r.Out
|
||||
if incoming {
|
||||
t = r.In
|
||||
}
|
||||
return t.Match(p, incoming, c, caPool)
|
||||
}
|
||||
|
||||
// Match reports whether a rule allows p
|
||||
func (t *Table) Match(p *Packet, incoming bool, c *cert.CachedCertificate, caPool *cert.CAPool) bool {
|
||||
return t.protos[p.Protocol].match(p, incoming, c, caPool)
|
||||
}
|
||||
|
||||
func (pr portRules) match(p *Packet, incoming bool, c *cert.CachedCertificate, caPool *cert.CAPool) bool {
|
||||
// We don't have any allowed ports, bail
|
||||
if pr == nil {
|
||||
return false
|
||||
}
|
||||
|
||||
// ICMP has no ports, only the port `any` rules apply, including the ones copied in from proto `any` rules
|
||||
if p.Protocol == iputil.IPProtocolICMP || p.Protocol == iputil.IPProtocolICMPv6 {
|
||||
// port numbers are re-used for connection tracking of ICMP,
|
||||
// but we don't want to actually filter on them.
|
||||
return pr[PortAny].match(p, c, caPool)
|
||||
}
|
||||
|
||||
var port int32
|
||||
|
||||
if p.Fragment {
|
||||
port = PortFragment
|
||||
} else if incoming {
|
||||
port = int32(p.LocalPort)
|
||||
} else {
|
||||
port = int32(p.RemotePort)
|
||||
}
|
||||
|
||||
// Packets without ports (gre, esp, etc) have port 0, which is PortAny, don't check those rules twice
|
||||
if port != PortAny && pr[port].match(p, c, caPool) {
|
||||
return true
|
||||
}
|
||||
|
||||
return pr[PortAny].match(p, c, caPool)
|
||||
}
|
||||
|
||||
func (cr *caRules) match(p *Packet, c *cert.CachedCertificate, caPool *cert.CAPool) bool {
|
||||
if cr == nil {
|
||||
return false
|
||||
}
|
||||
|
||||
if cr.Any.match(p, c) {
|
||||
return true
|
||||
}
|
||||
|
||||
if t, ok := cr.CAShas[c.Certificate.Issuer()]; ok {
|
||||
if t.match(p, c) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
s, err := caPool.GetCAForCert(c.Certificate)
|
||||
if err != nil {
|
||||
return false
|
||||
}
|
||||
|
||||
return cr.CANames[s.Certificate.Name()].match(p, c)
|
||||
}
|
||||
|
||||
func (rr *remoteRules) match(p *Packet, c *cert.CachedCertificate) bool {
|
||||
if rr == nil {
|
||||
return false
|
||||
}
|
||||
|
||||
// Shortcut path for if groups, hosts, or cidr contained an `any`
|
||||
if rr.Any.match(p, c) {
|
||||
return true
|
||||
}
|
||||
|
||||
// Need any of group, host, or cidr to match
|
||||
for _, sg := range rr.Groups {
|
||||
found := false
|
||||
|
||||
for _, g := range sg.Groups {
|
||||
if _, ok := c.InvertedGroups[g]; !ok {
|
||||
found = false
|
||||
break
|
||||
}
|
||||
|
||||
found = true
|
||||
}
|
||||
|
||||
if found && sg.LocalCIDR.match(p, c) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
if rr.Hosts != nil {
|
||||
if lr, ok := rr.Hosts[c.Certificate.Name()]; ok {
|
||||
if lr.match(p, c) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if rr.CIDR != nil {
|
||||
for _, v := range rr.CIDR.Supernets(netip.PrefixFrom(p.RemoteAddr, p.RemoteAddr.BitLen())) {
|
||||
if v.match(p, c) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
func (lr *localRules) match(p *Packet, c *cert.CachedCertificate) bool {
|
||||
if lr == nil {
|
||||
return false
|
||||
}
|
||||
|
||||
if lr.Any {
|
||||
return true
|
||||
}
|
||||
|
||||
return lr.LocalCIDR.Contains(p.LocalAddr)
|
||||
}
|
||||
+270
-549
File diff suppressed because it is too large.
Load diff
@@ -1,12 +1,13 @@
|
||||
module github.com/slackhq/nebula
|
||||
|
||||
go 1.27.2
|
||||
go 1.26.0
|
||||
|
||||
require (
|
||||
dario.cat/mergo v1.0.2
|
||||
filippo.io/bigmod v0.1.0
|
||||
github.com/DefinedNet/netlink v1.3.2-dn.1
|
||||
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be
|
||||
github.com/armon/go-radix v1.0.0
|
||||
github.com/flynn/noise v1.1.0
|
||||
github.com/gaissmai/bart v0.29.0
|
||||
github.com/gogo/protobuf v1.3.2
|
||||
@@ -32,7 +33,7 @@ require (
|
||||
golang.zx2c4.com/wireguard/windows v1.0.1
|
||||
google.golang.org/protobuf v1.36.12
|
||||
gopkg.in/yaml.v3 v3.0.1
|
||||
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980
|
||||
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe
|
||||
)
|
||||
|
||||
require (
|
||||
@@ -44,6 +45,5 @@ require (
|
||||
github.com/prometheus/common v0.70.1 // indirect
|
||||
github.com/prometheus/procfs v0.21.1 // indirect
|
||||
github.com/vishvananda/netns v0.0.5 // indirect
|
||||
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc // indirect
|
||||
golang.org/x/time v0.15.0 // indirect
|
||||
golang.org/x/time v0.5.0 // indirect
|
||||
)
|
||||
@@ -12,6 +12,8 @@ github.com/alecthomas/units v0.0.0-20190717042225-c3de453c63f4/go.mod h1:ybxpYRF
|
||||
github.com/alecthomas/units v0.0.0-20190924025748-f65c72e2690d/go.mod h1:rBZYJk541a8SKzHPHnH3zbiI+7dagKZ0cgpgrD7Fyho=
|
||||
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be h1:9AeTilPcZAjCFIImctFaOjnTIavg87rW78vTPkQqLI8=
|
||||
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be/go.mod h1:ySMOLuWl6zY27l47sB3qLNK6tF2fkHG55UZxx8oIVo4=
|
||||
github.com/armon/go-radix v1.0.0 h1:F4z6KzEeeQIMeLFa97iZU6vupzoecKdU5TX24SNppXI=
|
||||
github.com/armon/go-radix v1.0.0/go.mod h1:ufUuZ+zHj4x4TnLV4JWEpy2hxWSpsRywHrMgIH9cCH8=
|
||||
github.com/beorn7/perks v0.0.0-20180321164747-3a771d992973/go.mod h1:Dwedo/Wpr24TaqPxmxbtue+5NUziq4I4S80YR8gNf3Q=
|
||||
github.com/beorn7/perks v1.0.0/go.mod h1:KWe93zE9D1o94FZ5RNwFwVgaQK1VOXiVxmqh+CedLV8=
|
||||
github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
|
||||
@@ -155,8 +157,6 @@ golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPh
|
||||
golang.org/x/crypto v0.0.0-20210322153248-0c34fe9e7dc2/go.mod h1:T9bdIzuCu7OtxOm1hfPfRQxPLYneinmdGuTeoZ9dtd4=
|
||||
golang.org/x/crypto v0.57.0 h1:3ZVCjf8Ggz7zneR/EHRVx68Ctf+2pmIMP2UFhh9cC6M=
|
||||
golang.org/x/crypto v0.57.0/go.mod h1:Fdz0i5U6CoizGwLda9DttjSk6qlZo25zYNtR+ycvuZA=
|
||||
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc h1:TS73t7x3KarrNd5qAipmspBDS1rkMcgVG/fS1aRb4Rc=
|
||||
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc/go.mod h1:A+z0yzpGtvnG90cToK5n2tu8UJVP2XUATh+r+sfOOOc=
|
||||
golang.org/x/lint v0.0.0-20200302205851-738671d3881b/go.mod h1:3xt1FjdF8hUf6vQPIChWIBhFzV8gjjsPE/fR3IyQdNY=
|
||||
golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
|
||||
golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
|
||||
@@ -203,8 +203,8 @@ golang.org/x/term v0.46.0/go.mod h1:+K02xbkittuwc0Am4abfA3Fc+XRGXkvBXNO88NCXPoc=
|
||||
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
|
||||
golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
|
||||
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
|
||||
golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
|
||||
golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
|
||||
golang.org/x/time v0.5.0 h1:o7cqy6amK/52YcAKIPlM3a+Fpj35zvRj2TP+e1xFSfk=
|
||||
golang.org/x/time v0.5.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
|
||||
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
|
||||
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
|
||||
golang.org/x/tools v0.0.0-20200130002326-2f3ba24bd6e7/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
|
||||
@@ -243,5 +243,5 @@ gopkg.in/yaml.v2 v2.3.0/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
|
||||
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
|
||||
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
|
||||
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
|
||||
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980 h1:ribyrTYQ/QYeUIs8x8bVLYwGyepa7RnHLqJzegT5YYk=
|
||||
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980/go.mod h1:pK/dapF5Bf3KGW7/kd5CI5IC4lYh9FMFY1qETAIGLXk=
|
||||
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe h1:fre4i6mv4iBuz5lCMOzHD1rH1ljqHWSICFmZRbbgp3g=
|
||||
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe/go.mod h1:sxc3Uvk/vHcd3tj7/DHVBoR5wvWT/MmRq2pj7HRJnwU=
|
||||
+5
-18
@@ -31,7 +31,6 @@ package nebula
|
||||
|
||||
import (
|
||||
"bufio"
|
||||
"context"
|
||||
"fmt"
|
||||
"net"
|
||||
"strconv"
|
||||
@@ -52,29 +51,17 @@ type graphiteConfigExport struct {
|
||||
Percentiles []float64 // Percentiles to export from timers and histograms
|
||||
}
|
||||
|
||||
// graphiteTimeout bounds one submission, the connect and the write together. An export is a few KB, a host that can't
|
||||
// take that in this long isn't going to.
|
||||
const graphiteTimeout = 30 * time.Second
|
||||
|
||||
// graphiteOnce performs a single submission to Graphite, returning a non-nil
|
||||
// error if it could not connect or write all of it within timeout. It gives up
|
||||
// as soon as ctx is done.
|
||||
func graphiteOnce(ctx context.Context, c graphiteConfigExport, timeout time.Duration) error {
|
||||
// error on failed connections.
|
||||
func graphiteOnce(c graphiteConfigExport) error {
|
||||
now := time.Now().Unix()
|
||||
du := float64(c.DurationUnit)
|
||||
flushSeconds := float64(c.FlushInterval) / float64(time.Second)
|
||||
deadline := time.Now().Add(timeout)
|
||||
d := net.Dialer{Deadline: deadline}
|
||||
conn, err := d.DialContext(ctx, "tcp", c.Addr.String())
|
||||
conn, err := net.DialTCP("tcp", nil, c.Addr)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer conn.Close()
|
||||
if err := conn.SetDeadline(deadline); err != nil {
|
||||
return err
|
||||
}
|
||||
stop := context.AfterFunc(ctx, func() { _ = conn.Close() })
|
||||
defer stop()
|
||||
w := bufio.NewWriter(conn)
|
||||
c.Registry.Each(func(name string, i any) {
|
||||
switch metric := i.(type) {
|
||||
@@ -124,7 +111,7 @@ func graphiteOnce(ctx context.Context, c graphiteConfigExport, timeout time.Dura
|
||||
fmt.Fprintf(w, "%s.%s.fifteen-minute %.2f %d\n", c.Prefix, name, t.Rate15(), now)
|
||||
fmt.Fprintf(w, "%s.%s.mean-rate %.2f %d\n", c.Prefix, name, t.RateMean(), now)
|
||||
}
|
||||
w.Flush()
|
||||
})
|
||||
// A failed write sticks, so this reports the first one
|
||||
return w.Flush()
|
||||
return nil
|
||||
}
|
||||
@@ -1,315 +0,0 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"net"
|
||||
"strings"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// graphiteHost accepts connections and hands each one to the test
|
||||
type graphiteHost struct {
|
||||
ln net.Listener
|
||||
conns chan net.Conn
|
||||
|
||||
mu sync.Mutex
|
||||
closed bool
|
||||
open []net.Conn
|
||||
}
|
||||
|
||||
// newGraphiteHost accepts connections for the test. A non-zero window shrinks each connection's receive buffer, so a
|
||||
// sender that is not read from blocks after a little whatever the host's TCP tuning. Only for tests that need a stall,
|
||||
// a small window makes reading very slow on Linux.
|
||||
func newGraphiteHost(t *testing.T, window int) *graphiteHost {
|
||||
t.Helper()
|
||||
ln, err := net.Listen("tcp", "127.0.0.1:0")
|
||||
require.NoError(t, err)
|
||||
h := &graphiteHost{ln: ln, conns: make(chan net.Conn, 8)}
|
||||
done := make(chan struct{})
|
||||
t.Cleanup(func() {
|
||||
_ = ln.Close()
|
||||
h.mu.Lock()
|
||||
h.closed = true
|
||||
for _, c := range h.open {
|
||||
_ = c.Close()
|
||||
}
|
||||
h.mu.Unlock()
|
||||
close(done)
|
||||
})
|
||||
go func() {
|
||||
for {
|
||||
c, err := ln.Accept()
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
h.mu.Lock()
|
||||
if h.closed {
|
||||
h.mu.Unlock()
|
||||
_ = c.Close()
|
||||
return
|
||||
}
|
||||
h.open = append(h.open, c)
|
||||
h.mu.Unlock()
|
||||
if tc, ok := c.(*net.TCPConn); ok && window > 0 {
|
||||
_ = tc.SetReadBuffer(window)
|
||||
}
|
||||
select {
|
||||
case h.conns <- c:
|
||||
case <-done:
|
||||
return
|
||||
}
|
||||
}
|
||||
}()
|
||||
return h
|
||||
}
|
||||
|
||||
func (h *graphiteHost) addr(t *testing.T) *net.TCPAddr {
|
||||
a, err := net.ResolveTCPAddr("tcp", h.ln.Addr().String())
|
||||
require.NoError(t, err)
|
||||
return a
|
||||
}
|
||||
|
||||
// readExport reads what one send wrote, bounded so a send that never finishes fails the test rather than hanging it
|
||||
func readExport(t *testing.T, c net.Conn) []byte {
|
||||
t.Helper()
|
||||
require.NoError(t, c.SetReadDeadline(time.Now().Add(10*time.Second)))
|
||||
b, err := io.ReadAll(c)
|
||||
require.NoError(t, err)
|
||||
return b
|
||||
}
|
||||
|
||||
func (h *graphiteHost) next(t *testing.T, wait time.Duration) net.Conn {
|
||||
t.Helper()
|
||||
select {
|
||||
case c := <-h.conns:
|
||||
return c
|
||||
case <-time.After(wait):
|
||||
t.Fatal("no connection")
|
||||
return nil
|
||||
}
|
||||
}
|
||||
|
||||
// lockedBuffer is a log destination a test can read while the code under test writes to it from another goroutine
|
||||
type lockedBuffer struct {
|
||||
mu sync.Mutex
|
||||
buf bytes.Buffer
|
||||
}
|
||||
|
||||
func (b *lockedBuffer) Write(p []byte) (int, error) {
|
||||
b.mu.Lock()
|
||||
defer b.mu.Unlock()
|
||||
return b.buf.Write(p)
|
||||
}
|
||||
|
||||
func (b *lockedBuffer) String() string {
|
||||
b.mu.Lock()
|
||||
defer b.mu.Unlock()
|
||||
return b.buf.String()
|
||||
}
|
||||
|
||||
func testGraphiteConfig(addr *net.TCPAddr, r metrics.Registry) graphiteConfigExport {
|
||||
return graphiteConfigExport{Addr: addr, Registry: r, FlushInterval: time.Second, DurationUnit: time.Nanosecond, Prefix: "nebula"}
|
||||
}
|
||||
|
||||
// Enough metrics that one export overflows the socket buffers on any platform, so a send to a host that stops
|
||||
// reading blocks
|
||||
func bigGraphiteRegistry(r metrics.Registry, t *testing.T) {
|
||||
for i := range 200000 {
|
||||
name := fmt.Sprintf("big.gauge.%d", i)
|
||||
metrics.GetOrRegisterGauge(name, r).Update(int64(i))
|
||||
t.Cleanup(func() { r.Unregister(name) })
|
||||
}
|
||||
}
|
||||
|
||||
func TestGraphiteOnce_sends(t *testing.T) {
|
||||
r := metrics.NewRegistry()
|
||||
metrics.GetOrRegisterGauge("g", r).Update(7)
|
||||
metrics.GetOrRegisterCounter("c", r).Inc(3)
|
||||
h := newGraphiteHost(t, 0)
|
||||
|
||||
require.NoError(t, graphiteOnce(t.Context(), testGraphiteConfig(h.addr(t), r), time.Minute))
|
||||
b := readExport(t, h.next(t, 5*time.Second))
|
||||
assert.Contains(t, string(b), "nebula.g.value 7 ")
|
||||
assert.Contains(t, string(b), "nebula.c.count 3 ")
|
||||
assert.Contains(t, string(b), "nebula.c.count_ps 3.00 ")
|
||||
}
|
||||
|
||||
// A host that accepts and never reads is given up on, and the failed write is reported
|
||||
func TestGraphiteOnce_stalledHostTimesOut(t *testing.T) {
|
||||
r := metrics.NewRegistry()
|
||||
bigGraphiteRegistry(r, t)
|
||||
h := newGraphiteHost(t, 4096)
|
||||
done := make(chan error, 1)
|
||||
cfg := testGraphiteConfig(h.addr(t), r)
|
||||
go func() { done <- graphiteOnce(t.Context(), cfg, 300*time.Millisecond) }()
|
||||
h.next(t, 5*time.Second) // accepted, never read
|
||||
|
||||
select {
|
||||
case err := <-done:
|
||||
require.Error(t, err)
|
||||
case <-time.After(10 * time.Second):
|
||||
t.Fatal("the send did not give up on a host that stopped reading")
|
||||
}
|
||||
}
|
||||
|
||||
// The timeout covers the whole send, a host that keeps reading but too slowly is still given up on
|
||||
func TestGraphiteOnce_timeoutCoversTheWholeSend(t *testing.T) {
|
||||
r := metrics.NewRegistry()
|
||||
bigGraphiteRegistry(r, t)
|
||||
h := newGraphiteHost(t, 0)
|
||||
done := make(chan error, 1)
|
||||
start := time.Now()
|
||||
cfg := testGraphiteConfig(h.addr(t), r)
|
||||
go func() { done <- graphiteOnce(t.Context(), cfg, 500*time.Millisecond) }()
|
||||
c := h.next(t, 5*time.Second)
|
||||
stopReading := make(chan struct{})
|
||||
defer close(stopReading)
|
||||
// 32KB every 10ms keeps every write well inside the timeout, the whole export takes seconds
|
||||
go func() {
|
||||
buf := make([]byte, 32<<10)
|
||||
for {
|
||||
select {
|
||||
case <-stopReading:
|
||||
return
|
||||
case <-time.After(10 * time.Millisecond):
|
||||
}
|
||||
if _, err := c.Read(buf); err != nil {
|
||||
return
|
||||
}
|
||||
}
|
||||
}()
|
||||
|
||||
select {
|
||||
case err := <-done:
|
||||
require.Error(t, err)
|
||||
assert.Less(t, time.Since(start), 5*time.Second)
|
||||
case <-time.After(10 * time.Second):
|
||||
t.Fatal("a host that kept reading slowly held the send past its timeout")
|
||||
}
|
||||
}
|
||||
|
||||
func TestGraphiteOnce_cancelledCtxDoesNotConnect(t *testing.T) {
|
||||
h := newGraphiteHost(t, 0)
|
||||
ctx, cancel := context.WithCancel(t.Context())
|
||||
cancel()
|
||||
require.Error(t, graphiteOnce(ctx, testGraphiteConfig(h.addr(t), metrics.NewRegistry()), time.Minute))
|
||||
select {
|
||||
case <-h.conns:
|
||||
t.Fatal("connected on a cancelled ctx")
|
||||
case <-time.After(200 * time.Millisecond):
|
||||
}
|
||||
}
|
||||
|
||||
// A stop or reload abandons a stuck send rather than waiting out its timeout
|
||||
func TestGraphiteOnce_cancelAbandonsSend(t *testing.T) {
|
||||
r := metrics.NewRegistry()
|
||||
bigGraphiteRegistry(r, t)
|
||||
h := newGraphiteHost(t, 4096)
|
||||
ctx, cancel := context.WithCancel(t.Context())
|
||||
done := make(chan error, 1)
|
||||
cfg := testGraphiteConfig(h.addr(t), r)
|
||||
go func() { done <- graphiteOnce(ctx, cfg, time.Minute) }()
|
||||
h.next(t, 5*time.Second)
|
||||
select {
|
||||
case err := <-done:
|
||||
t.Fatalf("the send should be stuck on a host that is not reading, it ended with %v", err)
|
||||
case <-time.After(200 * time.Millisecond):
|
||||
}
|
||||
|
||||
cancel()
|
||||
select {
|
||||
case err := <-done:
|
||||
require.Error(t, err)
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("the send is still stuck after its ctx was cancelled")
|
||||
}
|
||||
}
|
||||
|
||||
// buildRuntime hands graphite the configured prefix and interval
|
||||
func TestStatsServer_graphiteExportUsesConfig(t *testing.T) {
|
||||
const name = "graphite.wiring.test"
|
||||
metrics.GetOrRegisterCounter(name, nil).Inc(8)
|
||||
t.Cleanup(func() { metrics.DefaultRegistry.Unregister(name) })
|
||||
h := newGraphiteHost(t, 0)
|
||||
s, c := newTestStatsServer(t)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "4s", "prefix": "pfx", "host": h.ln.Addr().String()})
|
||||
cfg, err := loadStatsConfig(c)
|
||||
require.NoError(t, err)
|
||||
|
||||
s.runMu.Lock()
|
||||
fns, _ := s.buildRuntime(t.Context(), cfg)
|
||||
s.runMu.Unlock()
|
||||
for _, fn := range fns {
|
||||
fn()
|
||||
}
|
||||
b := readExport(t, h.next(t, 5*time.Second))
|
||||
assert.Contains(t, string(b), "pfx."+name+".count 8 ")
|
||||
assert.Contains(t, string(b), "pfx."+name+".count_ps 2.00 ")
|
||||
}
|
||||
|
||||
func TestStatsServer_graphiteFailureIsLogged(t *testing.T) {
|
||||
logs := &lockedBuffer{}
|
||||
s, c := newTestStatsServer(t)
|
||||
s.l = test.NewLoggerWithOutput(logs)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": "127.0.0.1:" + freeTCPPort(t)})
|
||||
cfg, err := loadStatsConfig(c)
|
||||
require.NoError(t, err)
|
||||
|
||||
s.runMu.Lock()
|
||||
fns, _ := s.buildRuntime(t.Context(), cfg)
|
||||
s.runMu.Unlock()
|
||||
for _, fn := range fns {
|
||||
fn()
|
||||
}
|
||||
assert.Contains(t, logs.String(), "Graphite export failed")
|
||||
}
|
||||
|
||||
// Stop abandons the running export, so it goes through Start rather than handing buildRuntime a ctx, and a stop is
|
||||
// not logged as a failure
|
||||
func TestStatsServer_stopAbandonsGraphiteSend(t *testing.T) {
|
||||
bigGraphiteRegistry(metrics.DefaultRegistry, t)
|
||||
h := newGraphiteHost(t, 4096)
|
||||
logs := &lockedBuffer{}
|
||||
s, c := newTestStatsServer(t)
|
||||
s.l = test.NewLoggerWithOutput(logs)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "50ms", "host": h.ln.Addr().String()})
|
||||
require.NoError(t, s.reload(c, true))
|
||||
|
||||
started := make(chan struct{})
|
||||
go func() {
|
||||
s.Start()
|
||||
close(started)
|
||||
}()
|
||||
stuck := h.next(t, 30*time.Second)
|
||||
s.Stop()
|
||||
select {
|
||||
case <-started:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("Start did not return after Stop")
|
||||
}
|
||||
|
||||
// A closed sender resets the connection once it sees this, one still sending just buffers it. Either way the
|
||||
// read below doesn't have to drain the export through the small window to find out
|
||||
_, err := stuck.Write([]byte("x"))
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, stuck.SetReadDeadline(time.Now().Add(10*time.Second)))
|
||||
n, err := io.Copy(io.Discard, stuck)
|
||||
var ne net.Error
|
||||
if errors.As(err, &ne) && ne.Timeout() {
|
||||
t.Fatalf("the send kept the connection after Stop, read %d bytes", n)
|
||||
}
|
||||
assert.Less(t, n, int64(1<<20), "the send kept going after Stop")
|
||||
// The capture loop logs on its own goroutine after Start has returned, give it the chance
|
||||
assert.Never(t, func() bool { return strings.Contains(logs.String(), "Graphite export failed") }, 500*time.Millisecond, 10*time.Millisecond, "a stop is not a failure")
|
||||
}
|
||||
+35
-42
@@ -54,24 +54,22 @@ type HandshakeConfig struct {
|
||||
}
|
||||
|
||||
type HandshakeManager struct {
|
||||
// Mutex for interacting with the vpnIps and indexes maps.
|
||||
// Lock order is hostmap, then this lock, then the lighthouse, then a RemoteList.
|
||||
// Mutex for interacting with the vpnIps and indexes maps
|
||||
sync.RWMutex
|
||||
|
||||
vpnIps map[netip.Addr]*HandshakeHostInfo
|
||||
indexes map[uint32]*HandshakeHostInfo
|
||||
|
||||
mainHostMap *HostMap
|
||||
lightHouse *LightHouse
|
||||
outside udp.Conn
|
||||
config HandshakeConfig
|
||||
OutboundHandshakeTimer *LockingTimerWheel[netip.Addr]
|
||||
messageMetrics *MessageMetrics
|
||||
metricInitiated metrics.Counter
|
||||
metricTimedOut metrics.Counter
|
||||
metricRejectedBlocklisted metrics.Counter
|
||||
f *Interface
|
||||
l *slog.Logger
|
||||
mainHostMap *HostMap
|
||||
lightHouse *LightHouse
|
||||
outside udp.Conn
|
||||
config HandshakeConfig
|
||||
OutboundHandshakeTimer *LockingTimerWheel[netip.Addr]
|
||||
messageMetrics *MessageMetrics
|
||||
metricInitiated metrics.Counter
|
||||
metricTimedOut metrics.Counter
|
||||
f *Interface
|
||||
l *slog.Logger
|
||||
|
||||
// can be used to trigger outbound handshake for the given vpnIp
|
||||
trigger chan netip.Addr
|
||||
@@ -119,19 +117,18 @@ func (hh *HandshakeHostInfo) cachePacket(l *slog.Logger, t header.MessageType, s
|
||||
|
||||
func NewHandshakeManager(l *slog.Logger, mainHostMap *HostMap, lightHouse *LightHouse, outside udp.Conn, config HandshakeConfig) *HandshakeManager {
|
||||
return &HandshakeManager{
|
||||
vpnIps: map[netip.Addr]*HandshakeHostInfo{},
|
||||
indexes: map[uint32]*HandshakeHostInfo{},
|
||||
mainHostMap: mainHostMap,
|
||||
lightHouse: lightHouse,
|
||||
outside: outside,
|
||||
config: config,
|
||||
trigger: make(chan netip.Addr, config.triggerBuffer),
|
||||
OutboundHandshakeTimer: NewLockingTimerWheel[netip.Addr](config.tryInterval, hsTimeout(config.retries, config.tryInterval)),
|
||||
messageMetrics: config.messageMetrics,
|
||||
metricInitiated: metrics.GetOrRegisterCounter("handshake_manager.initiated", nil),
|
||||
metricTimedOut: metrics.GetOrRegisterCounter("handshake_manager.timed_out", nil),
|
||||
metricRejectedBlocklisted: metrics.GetOrRegisterCounter("handshake_manager.rejected.blocklisted", nil),
|
||||
l: l,
|
||||
vpnIps: map[netip.Addr]*HandshakeHostInfo{},
|
||||
indexes: map[uint32]*HandshakeHostInfo{},
|
||||
mainHostMap: mainHostMap,
|
||||
lightHouse: lightHouse,
|
||||
outside: outside,
|
||||
config: config,
|
||||
trigger: make(chan netip.Addr, config.triggerBuffer),
|
||||
OutboundHandshakeTimer: NewLockingTimerWheel[netip.Addr](config.tryInterval, hsTimeout(config.retries, config.tryInterval)),
|
||||
messageMetrics: config.messageMetrics,
|
||||
metricInitiated: metrics.GetOrRegisterCounter("handshake_manager.initiated", nil),
|
||||
metricTimedOut: metrics.GetOrRegisterCounter("handshake_manager.timed_out", nil),
|
||||
l: l,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -262,6 +259,14 @@ func (hm *HandshakeManager) handleOutbound(vpnIp netip.Addr, lighthouseTriggered
|
||||
"style": header.SubTypeName(header.Handshake, hh.machine.Subtype()),
|
||||
}
|
||||
|
||||
// Get a remotes object if we don't already have one.
|
||||
// This is mainly to protect us as this should never be the case
|
||||
// NB ^ This comment doesn't jive. It's how the thing gets initialized.
|
||||
// It's the common path. Should it update every time, in case a future LH query/queries give us more info?
|
||||
if hostinfo.remotes == nil {
|
||||
hostinfo.remotes = hm.lightHouse.QueryCache([]netip.Addr{vpnIp})
|
||||
}
|
||||
|
||||
remotes := hostinfo.remotes.CopyAddrs(hm.mainHostMap.GetPreferredRanges())
|
||||
remotesHaveChanged := !slices.Equal(remotes, hh.lastRemotes)
|
||||
|
||||
@@ -366,9 +371,6 @@ func (hm *HandshakeManager) StartHandshake(vpnAddr netip.Addr, cacheCb func(*Han
|
||||
hostinfo := &HostInfo{
|
||||
vpnAddrs: []netip.Addr{vpnAddr},
|
||||
HandshakePacket: make(map[uint8][]byte, 0),
|
||||
// Attached here so a pending hostinfo never exists without one: SetRemote dereferences
|
||||
// it, and create-tunnel -address can reach SetRemote before the handshake loop runs.
|
||||
remotes: hm.lightHouse.QueryCache([]netip.Addr{vpnAddr}),
|
||||
relayState: RelayState{
|
||||
relays: nil,
|
||||
relayForByAddr: map[netip.Addr]*Relay{},
|
||||
@@ -719,12 +721,7 @@ func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *head
|
||||
|
||||
response, result, err := machine.ProcessPacket(nil, packet)
|
||||
if err != nil {
|
||||
level := slog.LevelError
|
||||
if errors.Is(err, cert.ErrBlockListed) {
|
||||
level = slog.LevelDebug
|
||||
hm.metricRejectedBlocklisted.Inc(1)
|
||||
}
|
||||
f.l.Log(context.Background(), level, "Failed to process handshake packet", "from", via, "error", err)
|
||||
f.l.Error("Failed to process handshake packet", "from", via, "error", err)
|
||||
return
|
||||
}
|
||||
|
||||
@@ -856,9 +853,6 @@ func (hm *HandshakeManager) continueHandshake(via ViaSender, hh *HandshakeHostIn
|
||||
|
||||
response, result, err := machine.ProcessPacket(nil, packet)
|
||||
if err != nil {
|
||||
if errors.Is(err, cert.ErrBlockListed) {
|
||||
hm.metricRejectedBlocklisted.Inc(1)
|
||||
}
|
||||
// Recoverable errors are routine noise, log at Debug. Fatal errors get a Warn.
|
||||
if machine.Failed() {
|
||||
f.l.Warn("Failed to process handshake packet, abandoning",
|
||||
@@ -952,14 +946,13 @@ func (hm *HandshakeManager) continueHandshake(via ViaSender, hh *HandshakeHostIn
|
||||
|
||||
hm.DeleteHostInfo(hostinfo)
|
||||
hm.StartHandshake(hostinfo.vpnAddrs[0], func(newHH *HandshakeHostInfo) {
|
||||
newHH.hostinfo.remotes = hostinfo.remotes
|
||||
newHH.hostinfo.remotes.BlockRemote(via)
|
||||
newHH.packetStore = hh.packetStore
|
||||
hh.packetStore = []*cachedPacket{}
|
||||
hostinfo.vpnAddrs = vpnAddrs
|
||||
f.sendCloseTunnel(hostinfo)
|
||||
})
|
||||
// sendCloseTunnel may take the hostmap lock, so it must not run under the handshake
|
||||
// manager lock that StartHandshake holds around the callback.
|
||||
hostinfo.vpnAddrs = vpnAddrs
|
||||
f.sendCloseTunnel(hostinfo)
|
||||
return
|
||||
}
|
||||
|
||||
|
||||
+2
-156
@@ -1,22 +1,16 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/flynn/noise"
|
||||
"github.com/gaissmai/bart"
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
ct "github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/handshake"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
func Test_NewHandshakeManagerVpnIp(t *testing.T) {
|
||||
@@ -48,6 +42,8 @@ func Test_NewHandshakeManagerVpnIp(t *testing.T) {
|
||||
i2 := blah.StartHandshake(ip, nil)
|
||||
assert.Same(t, i, i2)
|
||||
|
||||
i.remotes = NewRemoteList([]netip.Addr{}, nil)
|
||||
|
||||
// Adding something to pending should not affect the main hostmap
|
||||
assert.Empty(t, mainHM.Hosts)
|
||||
|
||||
@@ -239,153 +235,3 @@ func TestHandleIncomingDispatch(t *testing.T) {
|
||||
assert.Empty(t, hm.indexes, "orphan stage-2 must not create state")
|
||||
})
|
||||
}
|
||||
|
||||
func TestBlocklistedHandshakeLogLevelAndCounter(t *testing.T) {
|
||||
ca, _, caKey, _ := ct.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
|
||||
pool := ct.NewTestCAPool(ca)
|
||||
|
||||
newCredential := func(name, network string) (cert.Certificate, *handshake.Credential) {
|
||||
c, _, rawKey, _ := ct.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey,
|
||||
name, ca.NotBefore(), ca.NotAfter(), []netip.Prefix{netip.MustParsePrefix(network)}, nil, nil)
|
||||
privateKey, _, _, err := cert.UnmarshalPrivateKeyFromPEM(rawKey)
|
||||
require.NoError(t, err)
|
||||
certBytes, err := c.MarshalForHandshakes()
|
||||
require.NoError(t, err)
|
||||
cipherSuite := noise.NewCipherSuite(noise.DH25519, noise.CipherChaChaPoly, noise.HashSHA256)
|
||||
return c, handshake.NewCredential(c, certBytes, privateKey, cipherSuite)
|
||||
}
|
||||
|
||||
initiatorCert, initiatorCredential := newCredential("initiator", "10.0.0.1/24")
|
||||
responderCert, responderCredential := newCredential("responder", "10.0.0.2/24")
|
||||
fingerprint, err := initiatorCert.Fingerprint()
|
||||
require.NoError(t, err)
|
||||
pool.BlocklistFingerprint(fingerprint)
|
||||
|
||||
initiator, err := handshake.NewMachine(cert.Version2,
|
||||
func(cert.Version) *handshake.Credential { return initiatorCredential },
|
||||
func(c cert.Certificate) (*cert.CachedCertificate, error) {
|
||||
return pool.VerifyCertificate(time.Now(), c)
|
||||
},
|
||||
func() (uint32, error) { return 1, nil }, true, header.HandshakeIXPSK0)
|
||||
require.NoError(t, err)
|
||||
packet, err := initiator.Initiate(nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
handler := &capturingHandler{}
|
||||
logger := slog.New(handler)
|
||||
pki := &PKI{}
|
||||
pki.cs.Store(&CertState{initiatingVersion: cert.Version2, v2Credential: responderCredential})
|
||||
pki.caPool.Store(pool)
|
||||
hm := NewHandshakeManager(logger, nil, nil, nil, defaultHandshakeConfig)
|
||||
hm.metricRejectedBlocklisted = metrics.NewCounter()
|
||||
hm.f = &Interface{pki: pki, l: logger}
|
||||
via := ViaSender{UdpAddr: netip.MustParseAddrPort("198.51.100.7:4242")}
|
||||
|
||||
hm.beginHandshake(via, packet, nil)
|
||||
entry := findEntry(t, handler.entries, "Failed to process handshake packet")
|
||||
assert.Equal(t, slog.LevelDebug, entry.Level)
|
||||
require.ErrorIs(t, entry.Attrs["error"].(error), cert.ErrBlockListed)
|
||||
assert.Equal(t, int64(1), hm.metricRejectedBlocklisted.Count())
|
||||
|
||||
handler.entries = nil
|
||||
hm.beginHandshake(via, nil, nil)
|
||||
entry = findEntry(t, handler.entries, "Failed to process handshake packet")
|
||||
assert.Equal(t, slog.LevelError, entry.Level)
|
||||
assert.Equal(t, int64(1), hm.metricRejectedBlocklisted.Count())
|
||||
|
||||
// The initiator sees the same rejection in continueHandshake, after a
|
||||
// responder has accepted its first packet and sent a valid reply.
|
||||
cleanPool := ct.NewTestCAPool(ca)
|
||||
responder, err := handshake.NewMachine(cert.Version2,
|
||||
func(cert.Version) *handshake.Credential { return responderCredential },
|
||||
func(c cert.Certificate) (*cert.CachedCertificate, error) {
|
||||
return cleanPool.VerifyCertificate(time.Now(), c)
|
||||
},
|
||||
func() (uint32, error) { return 2, nil }, false, header.HandshakeIXPSK0)
|
||||
require.NoError(t, err)
|
||||
response, _, err := responder.ProcessPacket(nil, packet)
|
||||
require.NoError(t, err)
|
||||
|
||||
responderFingerprint, err := responderCert.Fingerprint()
|
||||
require.NoError(t, err)
|
||||
pool.BlocklistFingerprint(responderFingerprint)
|
||||
|
||||
initiatingHM := NewHandshakeManager(logger, nil, nil, nil, defaultHandshakeConfig)
|
||||
initiatingHM.metricRejectedBlocklisted = metrics.NewCounter()
|
||||
initiatingHM.f = &Interface{l: logger}
|
||||
hh := &HandshakeHostInfo{
|
||||
machine: initiator,
|
||||
hostinfo: &HostInfo{localIndexId: 1, vpnAddrs: []netip.Addr{netip.MustParseAddr("10.0.0.2")}},
|
||||
}
|
||||
initiatingHM.indexes[1] = hh
|
||||
via.IsRelayed = true // skip the remote allow list before certificate validation
|
||||
initiatingHM.continueHandshake(via, hh, response)
|
||||
assert.Equal(t, int64(1), initiatingHM.metricRejectedBlocklisted.Count())
|
||||
}
|
||||
|
||||
// Test_PendingHandshakeHasRemotes covers create-tunnel -address: a pending hostinfo must already
|
||||
// carry its RemoteList when StartHandshake runs its callback, so SetRemote there, before the
|
||||
// handshake loop has run, is safe and the address becomes one the handshake is sent to.
|
||||
func Test_PendingHandshakeHasRemotes(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
mainHM := newHostMap(l)
|
||||
preferredRanges := []netip.Prefix{}
|
||||
mainHM.preferredRanges.Store(&preferredRanges)
|
||||
|
||||
hm := NewHandshakeManager(l, mainHM, newTestLighthouse(), &udp.NoopConn{}, defaultHandshakeConfig)
|
||||
|
||||
vpnIp := netip.MustParseAddr("172.1.1.2")
|
||||
remote := netip.MustParseAddrPort("192.168.1.9:4242")
|
||||
|
||||
hi := hm.StartHandshake(vpnIp, func(hh *HandshakeHostInfo) {
|
||||
require.NotNil(t, hh.hostinfo.remotes, "a pending handshake must never be without its RemoteList")
|
||||
hh.hostinfo.SetRemote(remote)
|
||||
})
|
||||
assert.Contains(t, hi.remotes.CopyAddrs(preferredRanges), remote, "the handshake must be sent to the supplied remote")
|
||||
assert.Equal(t, remote, hi.GetRemote())
|
||||
|
||||
// A RemoteList keeps one learned address per host, so a second remote replaces the
|
||||
// first — the same behaviour change-remote has on an established tunnel.
|
||||
other := netip.MustParseAddrPort("192.168.1.10:4242")
|
||||
hi.SetRemote(other)
|
||||
assert.Equal(t, []netip.AddrPort{other}, hi.remotes.CopyAddrs(preferredRanges))
|
||||
assert.Equal(t, other, hi.GetRemote())
|
||||
}
|
||||
|
||||
// newRemotesRaceFixture builds a handshake manager with an established tunnel to vpnAddr whose
|
||||
// RemoteList is the lighthouse's cached list, the state every teardown-during-handshake race starts from.
|
||||
func newRemotesRaceFixture(t *testing.T, vpnAddr netip.Addr) (*HandshakeManager, *Interface, *HostInfo) {
|
||||
t.Helper()
|
||||
l := test.NewLogger()
|
||||
mainHM := newHostMap(l)
|
||||
preferredRanges := []netip.Prefix{}
|
||||
mainHM.preferredRanges.Store(&preferredRanges)
|
||||
|
||||
lh := newTestLighthouse()
|
||||
hm := NewHandshakeManager(l, mainHM, lh, &udp.NoopConn{}, defaultHandshakeConfig)
|
||||
f := &Interface{hostMap: mainHM, lightHouse: lh, handshakeManager: hm, l: l}
|
||||
hm.f = f
|
||||
|
||||
established := &HostInfo{
|
||||
vpnAddrs: []netip.Addr{vpnAddr},
|
||||
localIndexId: 1,
|
||||
remoteIndexId: 101,
|
||||
remotes: lh.QueryCache([]netip.Addr{vpnAddr}),
|
||||
HandshakePacket: map[uint8][]byte{},
|
||||
}
|
||||
mainHM.Lock()
|
||||
mainHM.unlockedAddHostInfo(established, f)
|
||||
mainHM.Unlock()
|
||||
|
||||
return hm, f, established
|
||||
}
|
||||
|
||||
// With no handshake pending, tearing down the last tunnel still evicts the list.
|
||||
func Test_CloseTunnelEvictsWithoutPendingHandshake(t *testing.T) {
|
||||
vpnAddr := netip.MustParseAddr("172.1.1.2")
|
||||
_, f, established := newRemotesRaceFixture(t, vpnAddr)
|
||||
|
||||
f.closeTunnel(established)
|
||||
assert.NotContains(t, f.hostMap.Hosts, vpnAddr)
|
||||
assert.NotContains(t, f.lightHouse.addrMap, vpnAddr)
|
||||
}
|
||||
@@ -24,11 +24,6 @@ type m = map[string]any
|
||||
const (
|
||||
Version uint8 = 1
|
||||
Len = 16
|
||||
|
||||
// MaxOverhead is the most a payload grows on its way to the underlay.
|
||||
// A relayed packet has two headers and two AEAD tags, one for the inner tunnel and another for the relay tunnel.
|
||||
// Every supported cipher (today) has a 16 byte tag.
|
||||
MaxOverhead = 2 * (Len + 16)
|
||||
)
|
||||
|
||||
type MessageType uint8
|
||||
|
||||
+5
-69
@@ -264,9 +264,6 @@ type HostInfo struct {
|
||||
// This is used to limit lighthouse re-queries in chatty clients
|
||||
nextLHQuery atomic.Int64
|
||||
|
||||
// nextUnreachableProbe is the earliest we will probe our other remotes again after failing to reach the current one
|
||||
nextUnreachableProbe atomic.Int64
|
||||
|
||||
// lastHandshakeTime records the time the remote side told us about at the stage when the handshake was completed locally
|
||||
// Stage 1 packet will contain it if I am a responder, stage 2 packet if I am an initiator
|
||||
// This is used to avoid an attack where a handshake packet is replayed after some time
|
||||
@@ -319,9 +316,9 @@ type cachedPacketMetrics struct {
|
||||
func NewHostMapFromConfig(l *slog.Logger, c *config.C) *HostMap {
|
||||
hm := newHostMap(l)
|
||||
|
||||
hm.reload(c, true, nil)
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
hm.reload(c, false, r)
|
||||
hm.reload(c, true)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
hm.reload(c, false)
|
||||
})
|
||||
|
||||
l.Info("Main HostMap created", "preferredRanges", hm.GetPreferredRanges())
|
||||
@@ -340,8 +337,7 @@ func newHostMap(l *slog.Logger) *HostMap {
|
||||
}
|
||||
}
|
||||
|
||||
// r is nil on the initial load
|
||||
func (hm *HostMap) reload(c *config.C, initial bool, r *config.Reload) {
|
||||
func (hm *HostMap) reload(c *config.C, initial bool) {
|
||||
if initial || c.HasChanged("preferred_ranges") {
|
||||
var preferredRanges []netip.Prefix
|
||||
rawPreferredRanges := c.GetStringSlice("preferred_ranges", []string{})
|
||||
@@ -352,9 +348,8 @@ func (hm *HostMap) reload(c *config.C, initial bool, r *config.Reload) {
|
||||
if err != nil {
|
||||
hm.l.Warn("Failed to parse preferred ranges, ignoring",
|
||||
"error", err,
|
||||
"range", rawPreferredRange,
|
||||
"range", rawPreferredRanges,
|
||||
)
|
||||
r.Failed()
|
||||
continue
|
||||
}
|
||||
|
||||
@@ -769,65 +764,6 @@ func (i *HostInfo) TryPromoteBest(preferredRanges []netip.Prefix, ifce *Interfac
|
||||
}
|
||||
}
|
||||
|
||||
// unreachableProbeInterval bounds how often a tunnel whose remote we cannot reach probes its other remotes
|
||||
const unreachableProbeInterval = time.Second
|
||||
|
||||
// remoteUnreachable is called when a send to our current remote failed because we have no route to it, typically
|
||||
// after moving to a network without that address family. Sends a test packet to every other remote we know for this
|
||||
// host: the first one that arrives roams the peer over to wherever we are now, and its reply roams us onto that path.
|
||||
//
|
||||
// A peer behind a NAT drops a test from an address it has never sent to, so every probe also asks the lighthouse
|
||||
// about the peer. The lighthouse tells the peer where we are now, the peer punches us, and the next probe gets in.
|
||||
func (i *HostInfo) remoteUnreachable(ifce *Interface, dead netip.AddrPort) {
|
||||
if i.remotes == nil || i.ConnectionState == nil || i.GetRemote() != dead {
|
||||
// Nothing to probe with, or we already moved on from the remote that failed
|
||||
return
|
||||
}
|
||||
if ifce.lightHouse == nil || ifce.lightHouse.amLighthouse {
|
||||
// A lighthouse hands out the address it reaches a client on, it must not go roaming its clients itself
|
||||
return
|
||||
}
|
||||
|
||||
now := time.Now().UnixNano()
|
||||
next := i.nextUnreachableProbe.Load()
|
||||
if now < next || !i.nextUnreachableProbe.CompareAndSwap(next, now+int64(unreachableProbeInterval)) {
|
||||
return
|
||||
}
|
||||
|
||||
nb := make([]byte, 12)
|
||||
out := make([]byte, mtu)
|
||||
probed := 0
|
||||
i.remotes.ForEach(ifce.hostMap.GetPreferredRanges(), func(addr netip.AddrPort, _ bool) {
|
||||
if addr == dead {
|
||||
return
|
||||
}
|
||||
probed++
|
||||
ifce.sendTo(header.Test, header.TestRequest, i.ConnectionState, i, addr, []byte(""), nb, out)
|
||||
})
|
||||
|
||||
if ifce.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
i.logger(ifce.l).Debug("Remote unreachable, probing other remotes",
|
||||
"udpAddr", dead,
|
||||
"probed", probed,
|
||||
)
|
||||
}
|
||||
|
||||
if probed == 0 {
|
||||
// With nothing else to try, the lighthouse is our only way to learn of another remote. The peer may not have
|
||||
// one, so ask on the usual requery schedule rather than every probe for as long as the tunnel sits here.
|
||||
if now < i.nextLHQuery.Load() {
|
||||
return
|
||||
}
|
||||
i.nextLHQuery.Store(now + ifce.reQueryWait.Load())
|
||||
}
|
||||
|
||||
// With other remotes to probe we ask on every probe, without backing off. A repeat re-sends the peer its punch
|
||||
// notification in case the last one or its punches were lost. If the tunnel stays up on inbound traffic while
|
||||
// our sends to its remote keep failing (only one direction broken), this continues once a second for as long as
|
||||
// that lasts. That is a bounded cost for a rare state, and the probe that would clear it has to keep running.
|
||||
ifce.lightHouse.QueryServer(i.vpnAddrs[0])
|
||||
}
|
||||
|
||||
// Bits within HostInfo.state, everything above stateEpochShift is the epoch
|
||||
const (
|
||||
stateIn uint32 = 1 << iota
|
||||
|
||||
@@ -447,16 +447,3 @@ func TestHostInfo_markOutOnly(t *testing.T) {
|
||||
assert.True(t, h.markOut(6), "a relayed send must not consume the epoch edge")
|
||||
assert.False(t, h.markOut(6))
|
||||
}
|
||||
|
||||
// A preferred range that doesn't parse is skipped and the rest are used, the reload says one was skipped
|
||||
func TestHostMap_reloadBadPreferredRangeFails(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.LoadString("preferred_ranges: [10.0.0.0/8]\n"))
|
||||
hm := NewHostMapFromConfig(l, c)
|
||||
|
||||
res := c.ReloadConfigString("preferred_ranges: [10.0.0.0/8, nope]\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.Equal(t, []netip.Prefix{netip.MustParsePrefix("10.0.0.0/8")}, hm.GetPreferredRanges())
|
||||
}
|
||||
@@ -10,12 +10,10 @@ import (
|
||||
"github.com/slackhq/nebula/firewall"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/iputil"
|
||||
"github.com/slackhq/nebula/logging"
|
||||
"github.com/slackhq/nebula/noiseutil"
|
||||
"github.com/slackhq/nebula/overlay/batch"
|
||||
"github.com/slackhq/nebula/overlay/tio"
|
||||
"github.com/slackhq/nebula/routing"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
)
|
||||
|
||||
func (f *Interface) consumeInsidePacket(pkt tio.Packet, fwPacket *firewall.ParsedPacket, nb []byte, sendBatch *batch.SendBatch, rejectBuf []byte, q int, localCache firewall.ConntrackCache) {
|
||||
@@ -200,8 +198,8 @@ func (f *Interface) sendInsideMessage(hostinfo *HostInfo, pkt tio.Packet, nb []b
|
||||
}
|
||||
|
||||
err = tio.SegmentSuperpacket(pkt, func(seg []byte) error {
|
||||
//relay header + header + plaintext + AEAD tag + relay tag
|
||||
scratch := sendBatch.Reserve(len(seg) + header.MaxOverhead)
|
||||
//relay header + header + plaintext + AEAD tag (16 bytes for both AES-GCM and ChaCha20-Poly1305) + relay tag
|
||||
scratch := sendBatch.Reserve(header.Len + header.Len + len(seg) + 16 + 16)
|
||||
|
||||
innerPacket := f.sendInsideEncrypt(hostinfo, ci, seg, scratch[header.Len:], nb)
|
||||
if innerPacket == nil {
|
||||
@@ -519,9 +517,7 @@ func (f *Interface) SendVia(via *HostInfo, relay *Relay, ad, nb, out []byte, noc
|
||||
|
||||
err = f.writers[q].WriteTo(toSend, via.GetRemote())
|
||||
if err != nil {
|
||||
if l, ok := logging.RateLimited(f.l, f.udpRelayTxErrLimiter); ok {
|
||||
via.logger(l).Info("Failed to WriteTo in sendVia", "error", err)
|
||||
}
|
||||
via.logger(f.l).Info("Failed to WriteTo in sendVia", "error", err)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -530,26 +526,16 @@ func (f *Interface) sendNoMetrics(t header.MessageType, st header.MessageSubType
|
||||
return
|
||||
}
|
||||
useRelay := !remote.IsValid() && !hostinfo.GetRemote().IsValid()
|
||||
|
||||
// The encrypt appends to out in place and a relayed packet is then wrapped in place,
|
||||
// so out has to fit the whole packet up front or the encrypt reallocates out from under SendVia.
|
||||
// We cap the MTU of tun devices and routes we create ourselves, so only a host that set a bigger MTU than we allow gets here.
|
||||
need := header.Len + len(p) + ci.eKey.Overhead()
|
||||
if useRelay {
|
||||
// The relay tunnel runs the same cipher, and adds its own header and tag
|
||||
need += header.Len + ci.eKey.Overhead()
|
||||
}
|
||||
if cap(out) < need {
|
||||
if l, ok := logging.RateLimited(f.l, f.txOversizeLimiter); ok {
|
||||
hostinfo.logger(l).Error("Dropping outbound packet, out buffer not large enough", "outCap", cap(out), "payloadLen", len(p), "relayed", useRelay)
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
fullOut := out
|
||||
|
||||
if useRelay {
|
||||
if len(out) < header.Len {
|
||||
// out always has a capacity of mtu, but not always a length greater than the header.Len.
|
||||
// Grow it to make sure the next operation works.
|
||||
out = out[:header.Len]
|
||||
}
|
||||
// Save a header's worth of data at the front of the 'out' buffer.
|
||||
out = out[header.Len:header.Len]
|
||||
out = out[header.Len:]
|
||||
}
|
||||
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
@@ -596,26 +582,18 @@ func (f *Interface) sendNoMetrics(t header.MessageType, st header.MessageSubType
|
||||
if remote.IsValid() {
|
||||
err = f.writers[q].WriteTo(out, remote)
|
||||
if err != nil {
|
||||
if l, ok := logging.RateLimited(f.l, f.udpTxErrLimiter); ok {
|
||||
hostinfo.logger(l).Error("Failed to write outgoing packet",
|
||||
"error", err,
|
||||
"udpAddr", remote,
|
||||
)
|
||||
}
|
||||
hostinfo.logger(f.l).Error("Failed to write outgoing packet",
|
||||
"error", err,
|
||||
"udpAddr", remote,
|
||||
)
|
||||
}
|
||||
} else if hr := hostinfo.GetRemote(); hr.IsValid() {
|
||||
err = f.writers[q].WriteTo(out, hr)
|
||||
if err != nil {
|
||||
if l, ok := logging.RateLimited(f.l, f.udpTxErrLimiter); ok {
|
||||
hostinfo.logger(l).Error("Failed to write outgoing packet",
|
||||
"error", err,
|
||||
"udpAddr", hr,
|
||||
)
|
||||
}
|
||||
// A closing tunnel is about to be torn down, there is no point looking for another path for it
|
||||
if t != header.CloseTunnel && udp.IsUnreachable(err) {
|
||||
hostinfo.remoteUnreachable(f, hr)
|
||||
}
|
||||
hostinfo.logger(f.l).Error("Failed to write outgoing packet",
|
||||
"error", err,
|
||||
"udpAddr", hr,
|
||||
)
|
||||
}
|
||||
} else {
|
||||
// Try to send via a relay
|
||||
|
||||
+29
-78
@@ -1,7 +1,6 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"context"
|
||||
"crypto/fips140"
|
||||
"errors"
|
||||
@@ -25,7 +24,6 @@ import (
|
||||
"github.com/slackhq/nebula/overlay"
|
||||
"github.com/slackhq/nebula/overlay/batch"
|
||||
"github.com/slackhq/nebula/overlay/tio"
|
||||
"github.com/slackhq/nebula/ratelimit"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
)
|
||||
|
||||
@@ -126,10 +124,6 @@ type Interface struct {
|
||||
batchers []*batch.MultiCoalescer
|
||||
wg sync.WaitGroup
|
||||
|
||||
udpTxErrLimiter *ratelimit.Limiter // udp direct transmit error log limiter
|
||||
udpRelayTxErrLimiter *ratelimit.Limiter // udp relay transmit error log limiter
|
||||
txOversizeLimiter *ratelimit.Limiter // oversized outbound packet drop log limiter
|
||||
|
||||
// fatalErr holds the first unexpected reader error that caused shutdown.
|
||||
// nil means "no fatal error" (yet)
|
||||
fatalErr atomic.Pointer[error]
|
||||
@@ -204,19 +198,6 @@ func NewInterface(ctx context.Context, c *InterfaceConfig) (*Interface, error) {
|
||||
return nil, errors.New("no connection manager")
|
||||
}
|
||||
|
||||
udpTxErrLimiter, err := ratelimit.New(1, time.Second)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
udpRelayTxErrLimiter, err := ratelimit.New(1, time.Second)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
txOversizeLimiter, err := ratelimit.New(1, time.Second)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
if c.routines <= 1 {
|
||||
c.PinThreads = false //pinning is not useful unless there's more than one tun reader
|
||||
}
|
||||
@@ -249,9 +230,6 @@ func NewInterface(ctx context.Context, c *InterfaceConfig) (*Interface, error) {
|
||||
conntrackCacheTimeout: c.ConntrackCacheTimeout,
|
||||
cpuAffinity: c.CpuAffinity,
|
||||
pinThreads: c.PinThreads,
|
||||
udpTxErrLimiter: udpTxErrLimiter,
|
||||
udpRelayTxErrLimiter: udpRelayTxErrLimiter,
|
||||
txOversizeLimiter: txOversizeLimiter,
|
||||
|
||||
metricHandshakes: metrics.GetOrRegisterHistogram("handshakes", nil, metrics.NewExpDecaySample(1028, 0.015)),
|
||||
metricTxDropped: metrics.GetOrRegisterCounter("udp.tx.dropped", nil),
|
||||
@@ -496,8 +474,7 @@ func (f *Interface) listenIn(queue tio.Queue, i int) {
|
||||
|
||||
// flushSendBatch drains sb to the underlay and accounts for anything it could not deliver. A shortfall means
|
||||
// specific destinations were undeliverable (a stale remote, a reject rule), which the backend logs per peer at
|
||||
// debug; here it is only a counter, so one unreachable peer cannot spam a log line per batch. Tunnels whose remote
|
||||
// we no longer have a route to go looking for another path.
|
||||
// debug; here it is only a counter, so one unreachable peer cannot spam a log line per batch.
|
||||
func (f *Interface) flushSendBatch(sb *batch.SendBatch, q int) {
|
||||
queued := sb.Len()
|
||||
written, err := sb.Flush()
|
||||
@@ -507,53 +484,14 @@ func (f *Interface) flushSendBatch(sb *batch.SendBatch, q int) {
|
||||
if dropped := queued - written; dropped > 0 {
|
||||
f.metricTxDropped.Inc(int64(dropped))
|
||||
}
|
||||
|
||||
if f.lightHouse == nil || f.lightHouse.amLighthouse {
|
||||
// Lighthouses never probe, see remoteUnreachable, so skip finding the tunnels
|
||||
return
|
||||
}
|
||||
|
||||
// A tunnel's packets tend to fail together, so skip straight past a repeat of the one before. The first 8 bytes
|
||||
// of a header say whose packet it is, the counter after them changes with every packet.
|
||||
var last batch.Failure
|
||||
for i, fail := range sb.Failures() {
|
||||
if i > 0 && fail.Dst == last.Dst && bytes.Equal(fail.Head[:8], last.Head[:8]) {
|
||||
continue
|
||||
}
|
||||
last = fail
|
||||
|
||||
if udp.IsUnreachable(fail.Err) {
|
||||
f.sendUnreachable(fail.Head[:], fail.Dst)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// sendUnreachable finds the tunnel a packet we had no route for was sent on, from the start of the packet, and has it
|
||||
// look for another path to its peer.
|
||||
func (f *Interface) sendUnreachable(head []byte, dst netip.AddrPort) {
|
||||
var h header.H
|
||||
if h.Parse(head) != nil {
|
||||
return
|
||||
}
|
||||
|
||||
if h.Type == header.Message && h.Subtype == header.MessageRelay {
|
||||
// TODO: a relayed packet's header carries the relay session's index, not the relay tunnel's, so it does not
|
||||
// lead us to the tunnel whose remote failed. The relay tunnel's own traffic finds out soon enough.
|
||||
return
|
||||
}
|
||||
|
||||
if hostinfo := f.hostMap.QueryReverseIndex(h.RemoteIndex); hostinfo != nil {
|
||||
hostinfo.remoteUnreachable(f, dst)
|
||||
}
|
||||
}
|
||||
|
||||
func (f *Interface) RegisterConfigChangeCallbacks(c *config.C) {
|
||||
c.RegisterReloadCallback(f.reloadFirewall)
|
||||
for _, reload := range []func(*config.C){
|
||||
f.reloadSendRecvError, f.reloadAcceptRecvError, f.reloadDisconnectInvalid, f.reloadMisc,
|
||||
} {
|
||||
c.RegisterReloadCallback(func(c *config.C, _ *config.Reload) { reload(c) })
|
||||
}
|
||||
c.RegisterReloadCallback(f.reloadSendRecvError)
|
||||
c.RegisterReloadCallback(f.reloadAcceptRecvError)
|
||||
c.RegisterReloadCallback(f.reloadDisconnectInvalid)
|
||||
c.RegisterReloadCallback(f.reloadMisc)
|
||||
|
||||
for _, udpConn := range f.writers {
|
||||
c.RegisterReloadCallback(udpConn.ReloadConfig)
|
||||
@@ -570,19 +508,18 @@ func (f *Interface) reloadDisconnectInvalid(c *config.C) {
|
||||
}
|
||||
}
|
||||
|
||||
func (f *Interface) reloadFirewall(c *config.C, r *config.Reload) {
|
||||
func (f *Interface) reloadFirewall(c *config.C) {
|
||||
cs := f.pki.getCertState()
|
||||
curCert := cs.getCertificate(cert.Version2)
|
||||
if curCert == nil {
|
||||
curCert = cs.getCertificate(cert.Version1)
|
||||
}
|
||||
|
||||
// Compare with what the running firewall was built from, not the last config, so a firewall that failed to build
|
||||
// is tried again. The cert is the one this reload brought, PKI registers its reload callback before this one
|
||||
src := c.Render("firewall")
|
||||
if src != "" && src == f.firewall.source && curCert != nil &&
|
||||
slices.Equal(curCert.Networks(), f.firewall.assignedNetworks) &&
|
||||
slices.Equal(curCert.UnsafeNetworks(), f.firewall.unsafeNetworks) {
|
||||
// The firewall builds its routableNetworks set from the certificate's UnsafeNetworks at construction.
|
||||
// Check to see if that set has changed, and if so, rebuild the firewall.
|
||||
certUnsafeChanged := curCert != nil && !slices.Equal(curCert.UnsafeNetworks(), f.firewall.unsafeNetworks)
|
||||
|
||||
if !c.HasChanged("firewall") && !certUnsafeChanged {
|
||||
f.l.Debug("No firewall config change detected")
|
||||
return
|
||||
}
|
||||
@@ -590,7 +527,6 @@ func (f *Interface) reloadFirewall(c *config.C, r *config.Reload) {
|
||||
fw, err := NewFirewallFromConfig(f.l, cs, c)
|
||||
if err != nil {
|
||||
f.l.Error("Error while creating firewall during reload", "error", err)
|
||||
r.Failed()
|
||||
return
|
||||
}
|
||||
|
||||
@@ -688,15 +624,17 @@ func (f *Interface) reloadMisc(c *config.C) {
|
||||
}
|
||||
}
|
||||
|
||||
// statsEmitter updates the interface's gauges, the stats server runs it on its capture loop.
|
||||
func (f *Interface) statsEmitter() func() {
|
||||
func (f *Interface) emitStats(ctx context.Context, i time.Duration) {
|
||||
ticker := time.NewTicker(i)
|
||||
defer ticker.Stop()
|
||||
|
||||
udpStats := udp.NewUDPStatsEmitter(f.writers)
|
||||
|
||||
certExpirationGauge := metrics.GetOrRegisterGauge("certificate.ttl_seconds", nil)
|
||||
certInitiatingVersion := metrics.GetOrRegisterGauge("certificate.initiating_version", nil)
|
||||
certMaxVersion := metrics.GetOrRegisterGauge("certificate.max_version", nil)
|
||||
|
||||
return func() {
|
||||
emit := func() {
|
||||
f.firewall.EmitStats()
|
||||
f.handshakeManager.EmitStats()
|
||||
udpStats()
|
||||
@@ -713,6 +651,19 @@ func (f *Interface) statsEmitter() func() {
|
||||
certMaxVersion.Update(int64(certState.v1Cert.Version()))
|
||||
}
|
||||
}
|
||||
|
||||
// Prime gauges so a Prometheus scrape that lands before the first tick
|
||||
// sees real values instead of the zero defaults (issue #907).
|
||||
emit()
|
||||
|
||||
for {
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return
|
||||
case <-ticker.C:
|
||||
emit()
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func (f *Interface) GetHostInfo(vpnIp netip.Addr) *HostInfo {
|
||||
|
||||
+14
-5
@@ -3,6 +3,7 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
@@ -17,8 +18,11 @@ import (
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// Priming before the first tick (issue #907) is Start's job, see TestStatsServer_Start_primes.
|
||||
func Test_statsEmitter_setsGauges(t *testing.T) {
|
||||
// Test_emitStats_primesGauges covers issue #907: a Prometheus scrape that
|
||||
// landed before the first ticker fire used to read 0 for the cert gauges.
|
||||
// emitStats now primes the gauges before entering the ticker loop. We assert
|
||||
// the gauge is zero before the first call and non-zero after.
|
||||
func Test_emitStats_primesGauges(t *testing.T) {
|
||||
defer metrics.DefaultRegistry.UnregisterAll()
|
||||
|
||||
l := test.NewLogger()
|
||||
@@ -52,12 +56,17 @@ func Test_statsEmitter_setsGauges(t *testing.T) {
|
||||
ifce.pki.cs.Store(cs)
|
||||
|
||||
ttlGauge := metrics.GetOrRegisterGauge("certificate.ttl_seconds", nil)
|
||||
require.Zero(t, ttlGauge.Value(), "gauge should be zero before the emitter runs")
|
||||
require.Zero(t, ttlGauge.Value(), "gauge should be zero before emitStats runs")
|
||||
|
||||
ifce.statsEmitter()()
|
||||
// Pre-cancel the context so emitStats returns after priming the gauges
|
||||
// without ever reading from ticker.C. The one hour interval is just a
|
||||
// belt-and-suspenders, the test does not expect the ticker to fire.
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
cancel()
|
||||
ifce.emitStats(ctx, time.Hour)
|
||||
|
||||
ttl := ttlGauge.Value()
|
||||
assert.Positive(t, ttl, "ttl gauge should be set by one run of the emitter")
|
||||
assert.Positive(t, ttl, "ttl gauge should be primed by emitStats before its first tick")
|
||||
assert.LessOrEqual(t, ttl, int64(3600))
|
||||
assert.Equal(t, int64(cert.Version1), metrics.GetOrRegisterGauge("certificate.initiating_version", nil).Value())
|
||||
assert.Equal(t, int64(cert.Version1), metrics.GetOrRegisterGauge("certificate.max_version", nil).Value())
|
||||
|
||||
+4
-81
@@ -65,10 +65,10 @@ func TestReloadFirewall_CertUnsafeNetworksChanged(t *testing.T) {
|
||||
pki.cs.Store(&CertState{v2Cert: c2, initiatingVersion: cert.Version2})
|
||||
|
||||
// Reload with the same YAML so HasChanged("firewall") reports false.
|
||||
require.NoError(t, cfg.ReloadConfigString(rawYAML).Err)
|
||||
require.NoError(t, cfg.ReloadConfigString(rawYAML))
|
||||
require.False(t, cfg.HasChanged("firewall"))
|
||||
|
||||
f.reloadFirewall(cfg, nil)
|
||||
f.reloadFirewall(cfg)
|
||||
|
||||
assert.NotSame(t, fw, f.firewall, "firewall pointer should have been replaced")
|
||||
assert.Equal(t, newUnsafe, f.firewall.unsafeNetworks)
|
||||
@@ -113,85 +113,8 @@ func TestReloadFirewall_NoChange(t *testing.T) {
|
||||
l: l,
|
||||
}
|
||||
|
||||
require.NoError(t, cfg.ReloadConfigString(rawYAML).Err)
|
||||
f.reloadFirewall(cfg, nil)
|
||||
require.NoError(t, cfg.ReloadConfigString(rawYAML))
|
||||
f.reloadFirewall(cfg)
|
||||
|
||||
assert.Same(t, fw, f.firewall, "firewall should not have been replaced")
|
||||
}
|
||||
|
||||
// Rules that don't parse keep the old firewall, and the reload says it could not apply them
|
||||
func TestReloadFirewall_BadRulesFailTheReload(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
pki := &PKI{}
|
||||
pki.cs.Store(&CertState{v2Cert: &dummyCert{version: cert.Version2, networks: []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")}}, initiatingVersion: cert.Version2})
|
||||
|
||||
rules := func(proto string) string {
|
||||
return "firewall:\n outbound:\n - port: any\n proto: any\n host: any\n inbound:\n - port: any\n proto: " + proto + "\n host: any\n"
|
||||
}
|
||||
cfg := config.NewC(l)
|
||||
require.NoError(t, cfg.LoadString(rules("any")))
|
||||
fw, err := NewFirewallFromConfig(l, pki.getCertState(), cfg)
|
||||
require.NoError(t, err)
|
||||
f := &Interface{pki: pki, firewall: fw, l: l}
|
||||
cfg.RegisterReloadCallback(f.reloadFirewall)
|
||||
|
||||
// The running firewall still isn't built from what the config asks for, so the same reload fails again
|
||||
for range 2 {
|
||||
res := cfg.ReloadConfigString(rules("nope"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.Same(t, fw, f.firewall)
|
||||
}
|
||||
|
||||
res := cfg.ReloadConfigString(rules("tcp"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.NotSame(t, fw, f.firewall)
|
||||
}
|
||||
|
||||
// Every input the firewall is built from rebuilds it when it changes, and nothing else does
|
||||
func TestReloadFirewall_RebuildsOnAnyInput(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
networks := []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")}
|
||||
base := "firewall:\n inbound:\n - port: any\n proto: any\n host: any\n"
|
||||
setup := func() (*config.C, *Interface, *PKI) {
|
||||
pki := &PKI{}
|
||||
pki.cs.Store(&CertState{v2Cert: &dummyCert{version: cert.Version2, networks: networks}, initiatingVersion: cert.Version2})
|
||||
cfg := config.NewC(l)
|
||||
require.NoError(t, cfg.LoadString(base))
|
||||
fw, err := NewFirewallFromConfig(l, pki.getCertState(), cfg)
|
||||
require.NoError(t, err)
|
||||
f := &Interface{pki: pki, firewall: fw, l: l}
|
||||
cfg.RegisterReloadCallback(f.reloadFirewall)
|
||||
return cfg, f, pki
|
||||
}
|
||||
setCert := func(pki *PKI, networks, unsafe []netip.Prefix) {
|
||||
pki.cs.Store(&CertState{v2Cert: &dummyCert{version: cert.Version2, networks: networks, unsafeNetworks: unsafe}, initiatingVersion: cert.Version2})
|
||||
}
|
||||
|
||||
cases := map[string]struct {
|
||||
cfg string
|
||||
cert func(*PKI)
|
||||
want bool
|
||||
}{
|
||||
"nothing": {base + "punchy:\n punch: true\n", nil, false},
|
||||
"rules": {base + " outbound:\n - port: any\n proto: any\n host: any\n", nil, true},
|
||||
"inbound_action": {base + " inbound_action: reject\n", nil, true},
|
||||
"conntrack": {base + " conntrack:\n tcp_timeout: 1m\n", nil, true},
|
||||
"networks": {base, func(p *PKI) { setCert(p, []netip.Prefix{netip.MustParsePrefix("10.0.0.2/24")}, nil) }, true},
|
||||
"unsafe_networks": {base, func(p *PKI) { setCert(p, networks, []netip.Prefix{netip.MustParsePrefix("192.168.0.0/24")}) }, true},
|
||||
}
|
||||
for name, tc := range cases {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
cfg, f, pki := setup()
|
||||
old := f.firewall
|
||||
if tc.cert != nil {
|
||||
tc.cert(pki)
|
||||
}
|
||||
res := cfg.ReloadConfigString(tc.cfg)
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.Equal(t, tc.want, f.firewall != old)
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -32,6 +32,9 @@ const (
|
||||
IPProtocolICMPv6 = 58
|
||||
IPProtocolTCP = 6
|
||||
IPProtocolUDP = 17
|
||||
IPProtocolUDPLite = 136
|
||||
IPProtocolDCCP = 33
|
||||
IPProtocolSCTP = 132
|
||||
ICMPv6TypeEchoRequest = 128
|
||||
ICMPv6TypeEchoReply = 129
|
||||
)
|
||||
|
||||
+9
-38
@@ -15,7 +15,6 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/gaissmai/bart"
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/header"
|
||||
@@ -82,8 +81,6 @@ type LightHouse struct {
|
||||
|
||||
updateTrigger chan struct{}
|
||||
queryChan chan netip.Addr
|
||||
// queryDropped counts queries QueryServer dropped because queryChan was full.
|
||||
queryDropped metrics.Counter
|
||||
|
||||
calculatedRemotes atomic.Pointer[bart.Table[[]*calculatedRemote]] // Maps VpnAddr to []*calculatedRemote
|
||||
|
||||
@@ -119,8 +116,7 @@ func NewLightHouseFromConfig(ctx context.Context, l *slog.Logger, c *config.C, c
|
||||
nebulaPort: nebulaPort,
|
||||
punchy: p,
|
||||
updateTrigger: make(chan struct{}, 1),
|
||||
queryChan: make(chan netip.Addr, c.GetUint32("handshakes.query_buffer", 1024)),
|
||||
queryDropped: metrics.GetOrRegisterCounter("lighthouse.query.dropped", nil),
|
||||
queryChan: make(chan netip.Addr, c.GetUint32("handshakes.query_buffer", 64)),
|
||||
l: l,
|
||||
}
|
||||
h.localAddrsFn = func(al *LocalAllowList) []netip.Addr {
|
||||
@@ -138,21 +134,18 @@ func NewLightHouseFromConfig(ctx context.Context, l *slog.Logger, c *config.C, c
|
||||
h.metrics = newLighthouseMetrics()
|
||||
}
|
||||
|
||||
err := h.reload(c, true, nil)
|
||||
err := h.reload(c, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("lighthouse.am_lighthouse", "listen.port", "handshakes.query_buffer", "stats.lighthouse_metrics")
|
||||
err := h.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := h.reload(c, false)
|
||||
switch v := err.(type) {
|
||||
case *util.ContextualError:
|
||||
v.Log(l)
|
||||
r.Failed()
|
||||
case error:
|
||||
l.Error("failed to reload lighthouse", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -193,8 +186,7 @@ func (lh *LightHouse) GetUpdateInterval() int64 {
|
||||
return lh.interval.Load()
|
||||
}
|
||||
|
||||
// r is nil on the initial load
|
||||
func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
func (lh *LightHouse) reload(c *config.C, initial bool) error {
|
||||
if initial || c.HasChanged("lighthouse.advertise_addrs") {
|
||||
rawAdvAddrs := c.GetStringSlice("lighthouse.advertise_addrs", []string{})
|
||||
advAddrs := make([]netip.AddrPort, 0)
|
||||
@@ -229,7 +221,6 @@ func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error
|
||||
"addr", rawAddr,
|
||||
"entry", i+1,
|
||||
)
|
||||
r.Failed()
|
||||
continue
|
||||
}
|
||||
|
||||
@@ -364,13 +355,7 @@ func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error
|
||||
}
|
||||
}
|
||||
|
||||
// am_relay decides whether relay.relays applies to us at all
|
||||
if initial || c.HasChanged("relay.relays") || c.HasChanged("relay.am_relay") {
|
||||
var before []netip.Addr
|
||||
if !initial {
|
||||
before = lh.GetRelaysForMe()
|
||||
}
|
||||
|
||||
if initial || c.HasChanged("relay.relays") {
|
||||
switch c.GetBool("relay.am_relay", false) {
|
||||
case true:
|
||||
// Relays aren't allowed to specify other relays
|
||||
@@ -388,7 +373,6 @@ func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error
|
||||
"relay", v,
|
||||
"error", err,
|
||||
)
|
||||
r.Failed()
|
||||
} else {
|
||||
lh.l.Info("Read relay from config", "relay", v)
|
||||
relaysForMe = append(relaysForMe, configRIP)
|
||||
@@ -396,11 +380,6 @@ func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error
|
||||
}
|
||||
lh.relaysForMe.Store(&relaysForMe)
|
||||
}
|
||||
|
||||
// Tell the lighthouses now rather than at the next interval, but only when what we advertise changed
|
||||
if !initial && !slices.Equal(before, lh.GetRelaysForMe()) {
|
||||
lh.TriggerUpdate()
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
@@ -533,19 +512,14 @@ func (lh *LightHouse) Query(vpnAddr netip.Addr) *RemoteList {
|
||||
return nil
|
||||
}
|
||||
|
||||
// QueryServer is asynchronous and non-blocking, no reply should be expected.
|
||||
// If the query channel is full, the query is dropped.
|
||||
// QueryServer is asynchronous so no reply should be expected
|
||||
func (lh *LightHouse) QueryServer(vpnAddr netip.Addr) {
|
||||
// Don't put lighthouse addrs in the query channel because we can't query lighthouses about lighthouses
|
||||
if lh.amLighthouse || lh.IsLighthouseAddr(vpnAddr) {
|
||||
return
|
||||
}
|
||||
|
||||
select {
|
||||
case lh.queryChan <- vpnAddr:
|
||||
default:
|
||||
lh.queryDropped.Inc(1)
|
||||
}
|
||||
lh.queryChan <- vpnAddr
|
||||
}
|
||||
|
||||
func (lh *LightHouse) QueryCache(vpnAddrs []netip.Addr) *RemoteList {
|
||||
@@ -1261,13 +1235,10 @@ func (lhh *LightHouseHandler) handleHostQuery(n *NebulaMeta, fromVpnAddrs []neti
|
||||
// sendHostPunchNotification signals the other side to punch some zero byte udp packets
|
||||
func (lhh *LightHouseHandler) sendHostPunchNotification(n *NebulaMeta, fromVpnAddrs []netip.Addr, punchNotifDest netip.Addr, w EncWriter) {
|
||||
whereToPunch := fromVpnAddrs[0]
|
||||
// Resolve the target before taking the querier's RemoteList lock below. GetHostInfo takes the
|
||||
// hostmap lock, and the hostmap is taken before the lighthouse, which is taken before a
|
||||
// RemoteList, so looking it up inside the callback would deadlock.
|
||||
targetHI := lhh.lh.ifce.GetHostInfo(punchNotifDest)
|
||||
found, ln, err := lhh.lh.queryAndPrepMessage(whereToPunch, func(c *cache) (int, error) {
|
||||
n = lhh.resetMeta()
|
||||
n.Type = NebulaMeta_HostPunchNotification
|
||||
targetHI := lhh.lh.ifce.GetHostInfo(punchNotifDest)
|
||||
var useVersion cert.Version
|
||||
if targetHI == nil {
|
||||
useVersion = lhh.lh.ifce.GetCertState().initiatingVersion
|
||||
|
||||
+10
-257
@@ -6,16 +6,13 @@ import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"net/netip"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/gaissmai/bart"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
"go.yaml.in/yaml/v3"
|
||||
@@ -87,15 +84,15 @@ func TestReloadLighthouseInterval(t *testing.T) {
|
||||
lh.ifce = &mockEncWriter{}
|
||||
|
||||
// The first one routine is kicked off by main.go currently, lets make sure that one dies
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 5").Err)
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 5"))
|
||||
assert.Equal(t, int64(5), lh.interval.Load())
|
||||
|
||||
// Subsequent calls are killed off by the LightHouse.Reload function
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 10").Err)
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 10"))
|
||||
assert.Equal(t, int64(10), lh.interval.Load())
|
||||
|
||||
// If this completes then nothing is stealing our reload routine
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 11").Err)
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 11"))
|
||||
assert.Equal(t, int64(11), lh.interval.Load())
|
||||
}
|
||||
|
||||
@@ -296,7 +293,7 @@ func TestLighthouse_reload(t *testing.T) {
|
||||
require.NoError(t, err)
|
||||
c.ReloadConfigString(string(rc))
|
||||
|
||||
err = lh.reload(c, false, nil)
|
||||
err = lh.reload(c, false)
|
||||
require.NoError(t, err)
|
||||
}
|
||||
|
||||
@@ -334,7 +331,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
rc, err := yaml.Marshal(nc)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
|
||||
rl := lh.Query(staticHost)
|
||||
require.NotNil(t, rl)
|
||||
@@ -350,7 +347,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
rc, err = yaml.Marshal(nc)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
|
||||
rl = lh.Query(staticHost)
|
||||
require.NotNil(t, rl)
|
||||
@@ -358,7 +355,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("1.1.1.1:4242")}, rl.CopyAddrs([]netip.Prefix{}))
|
||||
|
||||
// Reload with the same config. An unchanged entry must not duplicate.
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
|
||||
rl = lh.Query(staticHost)
|
||||
require.NotNil(t, rl)
|
||||
@@ -373,7 +370,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
rc, err = yaml.Marshal(nc)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
|
||||
// Add a second host alongside the first. Both should be present, neither duplicated.
|
||||
nc = map[string]any{
|
||||
@@ -384,7 +381,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
rc, err = yaml.Marshal(nc)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
|
||||
rl = lh.Query(staticHost)
|
||||
require.NotNil(t, rl)
|
||||
@@ -406,7 +403,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
rc, err = yaml.Marshal(nc)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
|
||||
_, isStatic := lh.GetStaticHostList()[staticHost]
|
||||
assert.False(t, isStatic)
|
||||
@@ -798,247 +795,3 @@ func TestLightHouse_logLocalAddrsErr(t *testing.T) {
|
||||
lh.logLocalAddrsErr(errors.New("something else"))
|
||||
assert.Contains(t, out.String(), "level=WARN")
|
||||
}
|
||||
|
||||
// heldEncWriter holds the query worker in its first GetHostInfo until release closes.
|
||||
type heldEncWriter struct {
|
||||
mockEncWriter
|
||||
once sync.Once
|
||||
held chan struct{}
|
||||
release chan struct{}
|
||||
}
|
||||
|
||||
func (w *heldEncWriter) GetHostInfo(netip.Addr) *HostInfo {
|
||||
w.once.Do(func() { close(w.held) })
|
||||
<-w.release
|
||||
return nil
|
||||
}
|
||||
|
||||
// QueryServer never waits on the query worker, since the packet readers call it and nothing drains the channel at
|
||||
// shutdown; a query that finds the channel full is dropped and counted. The worker is held on its first query so the
|
||||
// channel fills.
|
||||
func TestLighthouse_QueryServerDoesNotBlock(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
cs := testCertState(netip.MustParsePrefix("10.128.0.1/16"))
|
||||
lh1 := "10.128.0.2"
|
||||
c := config.NewC(l)
|
||||
c.Settings["lighthouse"] = map[string]any{"hosts": []any{lh1}}
|
||||
c.Settings["static_host_map"] = map[string]any{lh1: []any{"1.1.1.1:4242"}}
|
||||
c.Settings["handshakes"] = map[string]any{"query_buffer": 1}
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
|
||||
require.NoError(t, err)
|
||||
w := &heldEncWriter{held: make(chan struct{}), release: make(chan struct{})}
|
||||
lh.ifce = w
|
||||
t.Cleanup(func() { close(w.release) })
|
||||
|
||||
lh.QueryServer(netip.MustParseAddr("10.128.0.10"))
|
||||
select {
|
||||
case <-w.held:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("the query worker never took the first query")
|
||||
}
|
||||
dropped := lh.queryDropped.Count()
|
||||
done := make(chan struct{})
|
||||
go func() {
|
||||
lh.QueryServer(netip.MustParseAddr("10.128.0.11"))
|
||||
lh.QueryServer(netip.MustParseAddr("10.128.0.12"))
|
||||
close(done)
|
||||
}()
|
||||
select {
|
||||
case <-done:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("QueryServer blocked on a full query channel")
|
||||
}
|
||||
assert.EqualValues(t, 1, lh.queryDropped.Count()-dropped)
|
||||
}
|
||||
|
||||
// hostmapEncWriter answers GetHostInfo from a real hostmap, the way Interface does.
|
||||
type hostmapEncWriter struct {
|
||||
mockEncWriter
|
||||
hm *HostMap
|
||||
}
|
||||
|
||||
func (w *hostmapEncWriter) GetHostInfo(a netip.Addr) *HostInfo { return w.hm.QueryVpnAddr(a) }
|
||||
func (w *hostmapEncWriter) GetCertState() *CertState {
|
||||
return &CertState{initiatingVersion: cert.Version1}
|
||||
}
|
||||
|
||||
// A lighthouse runs four paths that each hold one lock while waiting for the next: CheckAndComplete
|
||||
// holds the hostmap and takes the handshake manager, StartHandshake holds the handshake manager and
|
||||
// takes the lighthouse, a host update holds the lighthouse and takes the sender's RemoteList, and a
|
||||
// punch notification holds the querier's RemoteList while it resolves the target. If that last step
|
||||
// reaches the hostmap under the RemoteList lock, the four deadlock. Drive them all at once.
|
||||
func TestLighthouse_PunchNotificationDoesNotCloseLockCycle(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
myVpnNet := netip.MustParsePrefix("10.128.0.1/24")
|
||||
|
||||
c := config.NewC(l)
|
||||
c.Settings["lighthouse"] = map[string]any{"am_lighthouse": true}
|
||||
c.Settings["listen"] = map[string]any{"port": 4242}
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(myVpnNet), nil, nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
mainHM := newHostMap(l)
|
||||
pr := []netip.Prefix{}
|
||||
mainHM.preferredRanges.Store(&pr)
|
||||
lh.ifce = &hostmapEncWriter{hm: mainHM}
|
||||
|
||||
hm := NewHandshakeManager(l, mainHM, lh, &udp.NoopConn{}, defaultHandshakeConfig)
|
||||
f := &Interface{hostMap: mainHM, lightHouse: lh, handshakeManager: hm, l: l}
|
||||
hm.f = f
|
||||
|
||||
peer := netip.MustParseAddr("10.128.0.2")
|
||||
peerUdp := netip.MustParseAddrPort("10.0.0.2:4242")
|
||||
target := netip.MustParseAddr("10.128.0.3")
|
||||
targetUdp := netip.MustParseAddrPort("10.0.0.3:4242")
|
||||
outbound := netip.MustParseAddr("10.128.0.4")
|
||||
inbound := netip.MustParseAddr("10.128.0.5")
|
||||
|
||||
seed := lh.NewRequestHandler()
|
||||
newLHHostUpdate(peerUdp, peer, []netip.AddrPort{peerUdp}, seed)
|
||||
newLHHostUpdate(targetUdp, target, []netip.AddrPort{targetUdp}, seed)
|
||||
|
||||
stop := make(chan struct{})
|
||||
var wg sync.WaitGroup
|
||||
loop := func(body func()) {
|
||||
defer wg.Done()
|
||||
for {
|
||||
select {
|
||||
case <-stop:
|
||||
return
|
||||
default:
|
||||
body()
|
||||
}
|
||||
}
|
||||
}
|
||||
wg.Add(4)
|
||||
|
||||
// Outbound handshakes keep starting and being dropped.
|
||||
go loop(func() {
|
||||
hm.DeleteHostInfo(hm.StartHandshake(outbound, nil))
|
||||
})
|
||||
|
||||
// Inbound handshakes keep completing and being torn down.
|
||||
var idx uint32
|
||||
go loop(func() {
|
||||
idx++
|
||||
hi := &HostInfo{
|
||||
vpnAddrs: []netip.Addr{inbound},
|
||||
localIndexId: idx,
|
||||
remoteIndexId: idx,
|
||||
remotes: lh.QueryCache([]netip.Addr{inbound}),
|
||||
HandshakePacket: map[uint8][]byte{handshakePacketStage0: {byte(idx)}},
|
||||
}
|
||||
if _, err := hm.CheckAndComplete(hi, handshakePacketStage0, f); err == nil {
|
||||
mainHM.DeleteHostInfo(hi)
|
||||
}
|
||||
})
|
||||
|
||||
// The peer keeps sending host updates.
|
||||
updates := lh.NewRequestHandler()
|
||||
go loop(func() {
|
||||
newLHHostUpdate(peerUdp, peer, []netip.AddrPort{peerUdp}, updates)
|
||||
})
|
||||
|
||||
// The same peer keeps querying for the target, which ends in a punch notification.
|
||||
queries := lh.NewRequestHandler()
|
||||
go loop(func() {
|
||||
sendLHHostRequest(peerUdp, peer, target, queries, nil)
|
||||
})
|
||||
|
||||
time.Sleep(time.Second)
|
||||
close(stop)
|
||||
done := make(chan struct{})
|
||||
go func() { wg.Wait(); close(done) }()
|
||||
select {
|
||||
case <-done:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("deadlock: the lighthouse paths never finished after stop was signalled")
|
||||
}
|
||||
}
|
||||
|
||||
func TestLighthouse_reloadRelaysTriggersUpdate(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
base := "lighthouse:\n am_lighthouse: true\nlisten:\n port: 4242\n"
|
||||
require.NoError(t, c.LoadString(base+"relay:\n relays: [10.128.0.5]\n"))
|
||||
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
|
||||
require.NoError(t, err)
|
||||
assert.Empty(t, lh.updateTrigger)
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6]\n").Err)
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
|
||||
require.Len(t, lh.updateTrigger, 1)
|
||||
<-lh.updateTrigger
|
||||
|
||||
// The config changed but what we advertise did not, a bad entry is skipped
|
||||
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6, nope]\n").Err)
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
|
||||
assert.Empty(t, lh.updateTrigger)
|
||||
}
|
||||
|
||||
func TestLighthouse_reloadAmRelayAlone(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
base := "lighthouse:\n am_lighthouse: true\nlisten:\n port: 4242\nrelay:\n relays: [10.128.0.5]\n"
|
||||
require.NoError(t, c.LoadString(base+" am_relay: false\n"))
|
||||
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
|
||||
|
||||
// Relays aren't allowed to have relays, flipping am_relay alone must drop them and tell the lighthouses
|
||||
require.NoError(t, c.ReloadConfigString(base+" am_relay: true\n").Err)
|
||||
assert.Empty(t, lh.GetRelaysForMe())
|
||||
require.Len(t, lh.updateTrigger, 1)
|
||||
<-lh.updateTrigger
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(base+" am_relay: false\n").Err)
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
|
||||
require.Len(t, lh.updateTrigger, 1)
|
||||
}
|
||||
|
||||
func TestLighthouse_reloadRestartRequired(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
base := "lighthouse:\n am_lighthouse: true\n"
|
||||
require.NoError(t, c.LoadString(base+"listen:\n port: 4242\n"))
|
||||
|
||||
_, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
res := c.ReloadConfigString(base + "listen:\n port: 4242\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.RestartRequired)
|
||||
res = c.ReloadConfigString(base + "listen:\n port: 4243\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.RestartRequired)
|
||||
}
|
||||
|
||||
// A relay that doesn't parse is skipped and the rest are used, the reload says one was skipped
|
||||
func TestLighthouse_reloadBadRelayFails(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.LoadString("listen:\n port: 4242\n"))
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
res := c.ReloadConfigString("listen:\n port: 4242\nrelay:\n relays: [10.128.0.2, nope]\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.2")}, lh.GetRelaysForMe())
|
||||
}
|
||||
|
||||
// An advertise_addrs entry inside our own network is skipped and the rest are used, the reload says one was skipped
|
||||
func TestLighthouse_reloadAdvertiseAddrInNetworkFails(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.LoadString("listen:\n port: 4242\n"))
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
res := c.ReloadConfigString("listen:\n port: 4242\nlighthouse:\n advertise_addrs: [\"1.2.3.4:4242\", \"10.128.0.5:4242\"]\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("1.2.3.4:4242")}, lh.GetAdvertiseAddrs())
|
||||
}
|
||||
@@ -1,31 +0,0 @@
|
||||
package logging
|
||||
|
||||
import "log/slog"
|
||||
|
||||
// RateLimiter is what RateLimited needs from a rate limiter, such as a *ratelimit.Limiter.
|
||||
// Allow reports whether this call may proceed, and how many calls were denied since the last one that did.
|
||||
type RateLimiter interface {
|
||||
Allow() (denied uint64, ok bool)
|
||||
}
|
||||
|
||||
// RateLimited checks lim before anything is built.
|
||||
// When allowed it returns l, with a "suppressed" count attached if lim denied calls since its last allowed one.
|
||||
// A nil lim allows everything.
|
||||
//
|
||||
// if l, ok := logging.RateLimited(f.l, f.udpTxErrLimiter); ok {
|
||||
// hostinfo.logger(l).Error("Failed to write outgoing packet", "error", err)
|
||||
// }
|
||||
func RateLimited(l *slog.Logger, lim RateLimiter) (*slog.Logger, bool) {
|
||||
if lim == nil {
|
||||
return l, true
|
||||
}
|
||||
|
||||
denied, ok := lim.Allow()
|
||||
if !ok {
|
||||
return nil, false
|
||||
}
|
||||
if denied > 0 {
|
||||
return l.With("suppressed", denied), true
|
||||
}
|
||||
return l, true
|
||||
}
|
||||
@@ -1,106 +0,0 @@
|
||||
package logging
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"errors"
|
||||
"io"
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/ratelimit"
|
||||
)
|
||||
|
||||
type fakeLimiter struct {
|
||||
denied uint64
|
||||
ok bool
|
||||
}
|
||||
|
||||
func (f fakeLimiter) Allow() (uint64, bool) { return f.denied, f.ok }
|
||||
|
||||
func TestRateLimited(t *testing.T) {
|
||||
var buf bytes.Buffer
|
||||
base := NewLogger(&buf)
|
||||
|
||||
if l, ok := RateLimited(base, fakeLimiter{ok: false}); ok || l != nil {
|
||||
t.Fatalf("denied call: ok=%v logger=%v", ok, l)
|
||||
}
|
||||
|
||||
if l, ok := RateLimited(base, fakeLimiter{ok: true}); !ok || l != base {
|
||||
t.Fatal("nothing denied should hand back the same logger")
|
||||
}
|
||||
|
||||
if l, ok := RateLimited(base, nil); !ok || l != base {
|
||||
t.Fatal("a nil limiter should allow with the same logger")
|
||||
}
|
||||
|
||||
l, ok := RateLimited(base, fakeLimiter{denied: 7, ok: true})
|
||||
if !ok {
|
||||
t.Fatal("allowed call denied")
|
||||
}
|
||||
l.Info("hello", "k", "v")
|
||||
if !strings.Contains(buf.String(), "suppressed=7") {
|
||||
t.Fatalf("want suppressed=7, got %q", buf.String())
|
||||
}
|
||||
}
|
||||
|
||||
// The benchmarks compare a log line through slog directly against the same line behind RateLimited: logged with
|
||||
// nothing denied, denied, and logged after denials.
|
||||
|
||||
var (
|
||||
benchErr = errors.New("sendto: no buffer space available")
|
||||
benchAddr = netip.MustParseAddrPort("192.0.2.1:4242")
|
||||
)
|
||||
|
||||
func benchLogger() *slog.Logger {
|
||||
return NewLogger(io.Discard).With("localIndex", 1234, "remoteIndex", 5678)
|
||||
}
|
||||
|
||||
func BenchmarkRateLimitedBaseline(b *testing.B) {
|
||||
lg := benchLogger()
|
||||
b.ReportAllocs()
|
||||
for i := 0; i < b.N; i++ {
|
||||
lg.Error("Failed to write outgoing packet", "error", benchErr, "udpAddr", benchAddr)
|
||||
}
|
||||
}
|
||||
|
||||
func BenchmarkRateLimitedAllowed(b *testing.B) {
|
||||
lg, lim := benchLogger(), mustLimiter(b, 1, 0)
|
||||
b.ReportAllocs()
|
||||
for i := 0; i < b.N; i++ {
|
||||
if l, ok := RateLimited(lg, lim); ok {
|
||||
l.Error("Failed to write outgoing packet", "error", benchErr, "udpAddr", benchAddr)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func BenchmarkRateLimitedDenied(b *testing.B) {
|
||||
lg, lim := benchLogger(), mustLimiter(b, 1, time.Hour)
|
||||
lim.Allow()
|
||||
b.ReportAllocs()
|
||||
for i := 0; i < b.N; i++ {
|
||||
if l, ok := RateLimited(lg, lim); ok {
|
||||
l.Error("Failed to write outgoing packet", "error", benchErr, "udpAddr", benchAddr)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func BenchmarkRateLimitedAfterDenied(b *testing.B) {
|
||||
lg, lim := benchLogger(), fakeLimiter{denied: 5, ok: true}
|
||||
b.ReportAllocs()
|
||||
for i := 0; i < b.N; i++ {
|
||||
if l, ok := RateLimited(lg, lim); ok {
|
||||
l.Error("Failed to write outgoing packet", "error", benchErr, "udpAddr", benchAddr)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func mustLimiter(b *testing.B, burst int, every time.Duration) *ratelimit.Limiter {
|
||||
l, err := ratelimit.New(burst, every)
|
||||
if err != nil {
|
||||
b.Fatal(err)
|
||||
}
|
||||
return l
|
||||
}
|
||||
@@ -12,7 +12,6 @@ import (
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/commands"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/cpupick"
|
||||
"github.com/slackhq/nebula/noiseutil"
|
||||
@@ -72,18 +71,14 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
}
|
||||
l.Info("Firewall started", "firewallHashes", fw.GetRuleHashes())
|
||||
|
||||
// The command registry is shared by every surface that exposes these commands, so a
|
||||
// command cannot reach one of them without reaching the others.
|
||||
cmdRegistry := commands.New()
|
||||
|
||||
ssh, err := sshd.NewSSHServer(ctx, l.With("subsystem", "sshd"), cmdRegistry)
|
||||
ssh, err := sshd.NewSSHServer(ctx, l.With("subsystem", "sshd"))
|
||||
if err != nil {
|
||||
return nil, util.ContextualizeIfNeeded("Error while creating SSH server", err)
|
||||
}
|
||||
wireSSHReload(l, ssh, c)
|
||||
var sshStart func()
|
||||
if c.GetBool("sshd.enabled", false) {
|
||||
sshStart, err = configSSH(l, ssh, c, nil)
|
||||
sshStart, err = configSSH(l, ssh, c)
|
||||
if err != nil {
|
||||
l.Warn("Failed to configure sshd, ssh debugging will not be available", "error", err)
|
||||
sshStart = nil
|
||||
@@ -202,7 +197,7 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
if err != nil {
|
||||
return nil, util.NewContextualError("Failed to open udp listener", m{"queue": i}, err)
|
||||
}
|
||||
udpServer.ReloadConfig(c, nil)
|
||||
udpServer.ReloadConfig(c)
|
||||
udpConns[i] = udpServer
|
||||
|
||||
// If port is dynamic, discover it before the next pass through the for loop
|
||||
@@ -305,7 +300,6 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
}
|
||||
|
||||
var ifce *Interface
|
||||
var emitStats func()
|
||||
if !configTest {
|
||||
ifce, err = NewInterface(ctx, ifConfig)
|
||||
if err != nil {
|
||||
@@ -316,16 +310,6 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
lightHouse.ifce = ifce
|
||||
|
||||
ifce.RegisterConfigChangeCallbacks(c)
|
||||
// These are only read at startup
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged(
|
||||
"routines", "tun.routines", "listen.routines", "firewall.conntrack.routine_cache_timeout",
|
||||
"listen.port", "listen.host", "stats.message_metrics",
|
||||
"handshakes.try_interval", "handshakes.retries", "handshakes.trigger_buffer",
|
||||
"tun.drop_local_broadcast", "tun.drop_multicast",
|
||||
)
|
||||
r.RestartRequiredIfChanged(osStartupOnlyKeys...)
|
||||
})
|
||||
ifce.reloadDisconnectInvalid(c)
|
||||
ifce.reloadSendRecvError(c)
|
||||
ifce.reloadAcceptRecvError(c)
|
||||
@@ -334,12 +318,9 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
go handshakeManager.Run(ctx)
|
||||
|
||||
punchy.Start(ctx, ifce, hostMap, lightHouse)
|
||||
|
||||
// On the stats server's loop, so the gauges follow the interval it accepted
|
||||
emitStats = ifce.statsEmitter()
|
||||
}
|
||||
|
||||
stats, err := newStatsServerFromConfig(ctx, l, c, buildVersion, configTest, emitStats)
|
||||
stats, err := newStatsServerFromConfig(ctx, l, c, buildVersion, configTest)
|
||||
if err != nil {
|
||||
return nil, util.ContextualizeIfNeeded("Failed to start stats emitter", err)
|
||||
}
|
||||
@@ -348,14 +329,15 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
attachCommands(l, c, cmdRegistry, ifce)
|
||||
go ifce.emitStats(ctx, c.GetDuration("stats.interval", time.Second*10))
|
||||
|
||||
attachCommands(l, c, ssh, ifce)
|
||||
|
||||
networkChanges := udp.NewNetworkChangeMonitor(ctx, l, c)
|
||||
|
||||
return &Control{
|
||||
state: StateReady,
|
||||
f: ifce,
|
||||
commands: cmdRegistry,
|
||||
l: l,
|
||||
ctx: ctx,
|
||||
cancel: cancel,
|
||||
|
||||
@@ -1,6 +0,0 @@
|
||||
//go:build linux && !android && !e2e_testing
|
||||
|
||||
package nebula
|
||||
|
||||
// osStartupOnlyKeys are startup only keys that only matter on linux: udp batch size, udp offloads and thread pinning
|
||||
var osStartupOnlyKeys = []string{"listen.batch", "listen.udp_offloads", "tun.pin_threads", "tun.pin_threads_key", "tun.cpu_affinity"}
|
||||
@@ -1,6 +0,0 @@
|
||||
//go:build !linux || android || e2e_testing
|
||||
|
||||
package nebula
|
||||
|
||||
// osStartupOnlyKeys is empty, none of the OS specific startup keys matter here
|
||||
var osStartupOnlyKeys []string
|
||||
+28
-21
@@ -160,7 +160,9 @@ func (f *Interface) readOutsidePackets(via ViaSender, packet []byte, rxc *rxCont
|
||||
case header.TestReply:
|
||||
// No-op, useful for the Roaming and connectionManager side-effects above
|
||||
case header.TestRequest:
|
||||
if header.MaxOverhead+len(out) > len(rxc.scratch) {
|
||||
const maxCipherOverhead = 16 //todo we use this too often, needs a real importable const
|
||||
const maxOverhead = header.Len + header.Len + maxCipherOverhead + maxCipherOverhead
|
||||
if maxOverhead+len(out) > len(rxc.scratch) {
|
||||
// A reply that cannot fit in scratch is dropped no matter the log level.
|
||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
hostinfo.logger(f.l).Debug("dropping oversized test request", "payloadLen", len(out), "from", via)
|
||||
@@ -261,16 +263,11 @@ func (f *Interface) handleOutsideRelayPacket(hostinfo *HostInfo, via ViaSender,
|
||||
|
||||
// closeTunnel closes a tunnel locally, it does not send a closeTunnel packet to the remote
|
||||
func (f *Interface) closeTunnel(hostInfo *HostInfo) {
|
||||
// Hold the hostmap lock across both the delete and the lighthouse eviction,
|
||||
// to avoid a race with handshake completion.
|
||||
f.hostMap.Lock()
|
||||
defer f.hostMap.Unlock()
|
||||
if !f.hostMap.unlockedDeleteHostInfo(hostInfo) {
|
||||
return
|
||||
final := f.hostMap.DeleteHostInfo(hostInfo)
|
||||
if final {
|
||||
// We no longer have any tunnels with this vpn addr, clear learned lighthouse state to lower memory usage
|
||||
f.lightHouse.DeleteVpnAddrs(hostInfo.vpnAddrs)
|
||||
}
|
||||
|
||||
// We no longer have any tunnels with this vpn addr, clear learned lighthouse state to lower memory usage
|
||||
f.lightHouse.DeleteVpnAddrs(hostInfo.vpnAddrs)
|
||||
}
|
||||
|
||||
// sendCloseTunnel is a helper function to send a proper close tunnel packet to a remote
|
||||
@@ -388,7 +385,7 @@ func parseV6(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
|
||||
fp.RemotePort = 0
|
||||
}
|
||||
|
||||
case iputil.IPProtocolTCP, iputil.IPProtocolUDP:
|
||||
case iputil.IPProtocolTCP, iputil.IPProtocolUDP, iputil.IPProtocolDCCP, iputil.IPProtocolSCTP, iputil.IPProtocolUDPLite:
|
||||
if dataLen < offset+4 {
|
||||
return ErrIPv6PacketTooShort
|
||||
}
|
||||
@@ -459,15 +456,27 @@ func parseV4(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
|
||||
if fp.Fragment {
|
||||
fp.RemotePort = 0
|
||||
fp.LocalPort = 0
|
||||
} else if fp.Protocol == iputil.IPProtocolICMP { //note that orientation doesn't matter on ICMP
|
||||
return nil
|
||||
}
|
||||
|
||||
switch fp.Protocol {
|
||||
case iputil.IPProtocolICMP: //note that orientation doesn't matter on ICMP
|
||||
fp.RemotePort = binary.BigEndian.Uint16(data[ihl+4 : ihl+6]) //identifier
|
||||
fp.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
|
||||
|
||||
case iputil.IPProtocolTCP, iputil.IPProtocolUDP, iputil.IPProtocolDCCP, iputil.IPProtocolSCTP, iputil.IPProtocolUDPLite:
|
||||
if incoming {
|
||||
fp.RemotePort = binary.BigEndian.Uint16(data[ihl : ihl+2]) //src port
|
||||
fp.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
|
||||
}
|
||||
|
||||
default:
|
||||
// don't set ports for protocols Nebula doesn't inspect, the first 4 bytes of GRE, IPIP, AH, etc. are not ports
|
||||
fp.RemotePort = 0
|
||||
fp.LocalPort = 0
|
||||
}
|
||||
|
||||
return nil
|
||||
@@ -476,9 +485,7 @@ func parseV4(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
|
||||
func (f *Interface) handleOutsideMessagePacket(hostinfo *HostInfo, messageCounter uint64, out []byte, rxc *rxContext) {
|
||||
err := newPacket(out, true, rxc.fwPacket)
|
||||
if err != nil {
|
||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
hostinfo.logger(f.l).Debug("Error while validating inbound packet", "error", err, "packet", out)
|
||||
}
|
||||
hostinfo.logger(f.l).Warn("Error while validating inbound packet", "error", err, "packet", out)
|
||||
return
|
||||
}
|
||||
|
||||
|
||||
+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)
|
||||
|
||||
@@ -1,27 +1,12 @@
|
||||
package batch
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
|
||||
"github.com/slackhq/nebula/header"
|
||||
)
|
||||
import "net/netip"
|
||||
|
||||
const SendBatchCap = 128
|
||||
|
||||
// FailureHeadLen is how much of a refused packet a Failure keeps, nebula's header, which says whose packet it was
|
||||
const FailureHeadLen = header.Len
|
||||
|
||||
// batchWriter is the minimal subset of udp.Conn needed by SendBatch to flush.
|
||||
type batchWriter interface {
|
||||
WriteBatch(bufs [][]byte, addrs []netip.AddrPort, failed func(i int, err error)) (int, error)
|
||||
}
|
||||
|
||||
// Failure is a packet the underlay would not send
|
||||
type Failure struct {
|
||||
// Head is the start of the packet, zero padded if the packet was shorter
|
||||
Head [FailureHeadLen]byte
|
||||
Dst netip.AddrPort
|
||||
Err error
|
||||
WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error)
|
||||
}
|
||||
|
||||
// SendBatch accumulates encrypted UDP packets and flushes them via WriteBatch.
|
||||
@@ -32,28 +17,16 @@ type SendBatch struct {
|
||||
bufs [][]byte
|
||||
dsts []netip.AddrPort
|
||||
arena *Arena
|
||||
|
||||
failures []Failure
|
||||
// recordFailure is bound once so handing it to WriteBatch does not allocate on every Flush
|
||||
recordFailure func(i int, err error)
|
||||
}
|
||||
|
||||
// NewSendBatch makes a SendBatch with batchCap slots and an arenaSize byte buffer for slices to back those slots
|
||||
func NewSendBatch(out batchWriter, batchCap, arenaSize int) *SendBatch {
|
||||
b := &SendBatch{
|
||||
return &SendBatch{
|
||||
out: out,
|
||||
bufs: make([][]byte, 0, batchCap),
|
||||
dsts: make([]netip.AddrPort, 0, batchCap),
|
||||
arena: NewArena(arenaSize),
|
||||
}
|
||||
b.recordFailure = b.failed
|
||||
return b
|
||||
}
|
||||
|
||||
func (b *SendBatch) failed(i int, err error) {
|
||||
f := Failure{Dst: b.dsts[i], Err: err}
|
||||
copy(f.Head[:], b.bufs[i])
|
||||
b.failures = append(b.failures, f)
|
||||
}
|
||||
|
||||
func (b *SendBatch) Reserve(sz int) []byte {
|
||||
@@ -71,15 +44,12 @@ func (b *SendBatch) Commit(pkt []byte, dst netip.AddrPort) {
|
||||
}
|
||||
|
||||
// Flush writes every queued packet and reports how many actually went out. A short count means some destinations
|
||||
// were undeliverable, Failures says which; the batch is drained either way.
|
||||
// were undeliverable; the batch is drained either way.
|
||||
func (b *SendBatch) Flush() (int, error) {
|
||||
clear(b.failures)
|
||||
b.failures = b.failures[:0]
|
||||
|
||||
var err error
|
||||
written := 0
|
||||
if len(b.bufs) > 0 {
|
||||
written, err = b.out.WriteBatch(b.bufs, b.dsts, b.recordFailure)
|
||||
written, err = b.out.WriteBatch(b.bufs, b.dsts)
|
||||
}
|
||||
clear(b.bufs)
|
||||
b.bufs = b.bufs[:0]
|
||||
@@ -87,9 +57,3 @@ func (b *SendBatch) Flush() (int, error) {
|
||||
b.arena.Reset()
|
||||
return written, err
|
||||
}
|
||||
|
||||
// Failures returns every packet the last Flush could not send, in the order they were committed. Valid until the
|
||||
// next Flush.
|
||||
func (b *SendBatch) Failures() []Failure {
|
||||
return b.failures
|
||||
}
|
||||
@@ -1,9 +1,7 @@
|
||||
package batch
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"net/netip"
|
||||
"slices"
|
||||
"testing"
|
||||
)
|
||||
|
||||
@@ -12,7 +10,7 @@ type fakeBatchWriter struct {
|
||||
addrs []netip.AddrPort
|
||||
}
|
||||
|
||||
func (w *fakeBatchWriter) WriteBatch(bufs [][]byte, addrs []netip.AddrPort, _ func(int, error)) (int, error) {
|
||||
func (w *fakeBatchWriter) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error) {
|
||||
// Snapshot — SendBatch.Flush nils its slot pointers right after WriteBatch
|
||||
// returns, so tests must capture data before that happens.
|
||||
w.bufs = make([][]byte, len(bufs))
|
||||
@@ -122,84 +120,3 @@ func TestSendBatchGrowPreservesCommitted(t *testing.T) {
|
||||
t.Errorf("second packet on the wire: %x", fw.bufs[1])
|
||||
}
|
||||
}
|
||||
|
||||
// failingBatchWriter refuses every packet whose first byte is in refuse
|
||||
type failingBatchWriter struct {
|
||||
refuse map[byte]error
|
||||
}
|
||||
|
||||
func (w *failingBatchWriter) WriteBatch(bufs [][]byte, _ []netip.AddrPort, failed func(int, error)) (int, error) {
|
||||
written := 0
|
||||
for i, b := range bufs {
|
||||
if err, ok := w.refuse[b[0]]; ok {
|
||||
failed(i, err)
|
||||
continue
|
||||
}
|
||||
written++
|
||||
}
|
||||
return written, nil
|
||||
}
|
||||
|
||||
func TestSendBatchReportsFailures(t *testing.T) {
|
||||
errNoRoute := errors.New("no route")
|
||||
fw := &failingBatchWriter{refuse: map[byte]error{2: errNoRoute, 3: errNoRoute}}
|
||||
b := NewSendBatch(fw, 4, 128)
|
||||
|
||||
// pkt is n bytes starting with the refuse key, each later byte its offset plus 0x10 so the head is recognizable
|
||||
pkt := func(key byte, n int) []byte {
|
||||
p := b.Reserve(n)[:n]
|
||||
p[0] = key
|
||||
for i := 1; i < n; i++ {
|
||||
p[i] = byte(0x10 + i)
|
||||
}
|
||||
return p
|
||||
}
|
||||
head := func(p []byte) (h [FailureHeadLen]byte) {
|
||||
copy(h[:], p)
|
||||
return h
|
||||
}
|
||||
|
||||
dsts := []netip.AddrPort{
|
||||
netip.MustParseAddrPort("10.0.0.1:4242"),
|
||||
netip.MustParseAddrPort("[fd00::2]:4242"),
|
||||
netip.MustParseAddrPort("[fd00::3]:4242"),
|
||||
netip.MustParseAddrPort("10.0.0.4:4242"),
|
||||
}
|
||||
long := pkt(2, FailureHeadLen+8) // only its head is kept
|
||||
short := pkt(3, 4) // zero padded
|
||||
b.Commit(pkt(1, 20), dsts[0])
|
||||
b.Commit(long, dsts[1])
|
||||
b.Commit(short, dsts[2])
|
||||
b.Commit(pkt(1, 20), dsts[3])
|
||||
|
||||
written, err := b.Flush()
|
||||
if err != nil {
|
||||
t.Fatalf("Flush: %v", err)
|
||||
}
|
||||
if written != 2 {
|
||||
t.Errorf("written = %d, want 2", written)
|
||||
}
|
||||
want := []Failure{{head(long), dsts[1], errNoRoute}, {head(short), dsts[2], errNoRoute}}
|
||||
if got := b.Failures(); !slices.Equal(got, want) {
|
||||
t.Errorf("failures = %v, want %v", got, want)
|
||||
}
|
||||
|
||||
// Failures do not leak into the next flush
|
||||
again := pkt(2, 20)
|
||||
b.Commit(again, dsts[0])
|
||||
if _, err := b.Flush(); err != nil {
|
||||
t.Fatalf("Flush: %v", err)
|
||||
}
|
||||
if want := []Failure{{head(again), dsts[0], errNoRoute}}; !slices.Equal(b.Failures(), want) {
|
||||
t.Errorf("second flush failures = %v, want %v", b.Failures(), want)
|
||||
}
|
||||
|
||||
// A clean flush forgets the last one's failures
|
||||
b.Commit(pkt(1, 20), dsts[0])
|
||||
if _, err := b.Flush(); err != nil {
|
||||
t.Fatalf("Flush: %v", err)
|
||||
}
|
||||
if got := b.Failures(); len(got) != 0 {
|
||||
t.Errorf("clean flush failures = %v, want none", got)
|
||||
}
|
||||
}
|
||||
@@ -1,57 +0,0 @@
|
||||
//go:build !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"log/slog"
|
||||
|
||||
"golang.org/x/sys/windows"
|
||||
"golang.org/x/sys/windows/registry"
|
||||
)
|
||||
|
||||
var tcpipInterfaceKeys = []string{
|
||||
`SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces`,
|
||||
`SYSTEM\CurrentControlSet\Services\Tcpip6\Parameters\Interfaces`,
|
||||
}
|
||||
|
||||
// disableDNSRegistration prevents publishing overlay addresses in the host's
|
||||
// DNS records, where clients outside the overlay cannot reach them.
|
||||
// Failures are non-fatal so registry access cannot prevent tunnel creation.
|
||||
func disableDNSRegistration(l *slog.Logger, guid windows.GUID) {
|
||||
id := guid.String()
|
||||
for _, base := range tcpipInterfaceKeys {
|
||||
path := base + `\` + id
|
||||
if err := setDNSRegistrationValues(path); err != nil {
|
||||
l.Warn("Failed to disable DNS registration on the tun adapter", "error", err, "key", path)
|
||||
continue
|
||||
}
|
||||
l.Debug("Disabled DNS registration on the tun adapter", "key", path)
|
||||
}
|
||||
}
|
||||
|
||||
func setDNSRegistrationValues(path string) error {
|
||||
// The stack may not have created the adapter's interface key yet.
|
||||
k, _, err := registry.CreateKey(registry.LOCAL_MACHINE, path, registry.SET_VALUE)
|
||||
if err != nil {
|
||||
return fmt.Errorf("open HKLM\\%s: %w", path, err)
|
||||
}
|
||||
defer k.Close()
|
||||
|
||||
// Neither RegistrationEnabled nor DisableDynamicUpdate alone reliably
|
||||
// prevents registration, so all three settings are required.
|
||||
values := []struct {
|
||||
name string
|
||||
data uint32
|
||||
}{
|
||||
{"RegistrationEnabled", 0},
|
||||
{"DisableDynamicUpdate", 1},
|
||||
{"MaxNumberOfAddressesToRegister", 0},
|
||||
}
|
||||
for _, v := range values {
|
||||
if err := k.SetDWordValue(v.name, v.data); err != nil {
|
||||
return fmt.Errorf("set %s: %w", v.name, err)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
+4
-28
@@ -50,13 +50,7 @@ func (r Route) String() string {
|
||||
|
||||
func makeRouteTree(l *slog.Logger, routes []Route, allowMTU bool) (*bart.Table[routing.Gateways], error) {
|
||||
routeTree := new(bart.Table[routing.Gateways])
|
||||
seen := make(map[netip.Prefix]bool, len(routes))
|
||||
for _, r := range routes {
|
||||
if seen[r.Cidr] {
|
||||
l.Warn("route is listed more than once, only the last entry's via is used", "route", r)
|
||||
}
|
||||
seen[r.Cidr] = true
|
||||
|
||||
if !allowMTU && r.MTU > 0 {
|
||||
l.Warn("route MTU is not supported on this platform",
|
||||
"goos", runtime.GOOS,
|
||||
@@ -104,11 +98,7 @@ func parseRoutes(c *config.C, networks []netip.Prefix) ([]Route, error) {
|
||||
|
||||
mtu, ok := rMtu.(int)
|
||||
if !ok {
|
||||
s, ok := rMtu.(string)
|
||||
if !ok {
|
||||
return nil, fmt.Errorf("entry %v.mtu in tun.routes is not an integer: %v", i+1, rMtu)
|
||||
}
|
||||
mtu, err = strconv.Atoi(s)
|
||||
mtu, err = strconv.Atoi(rMtu.(string))
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("entry %v.mtu in tun.routes is not an integer: %v", i+1, err)
|
||||
}
|
||||
@@ -184,11 +174,7 @@ func parseUnsafeRoutes(c *config.C, networks []netip.Prefix) ([]Route, error) {
|
||||
if rMtu, ok := m["mtu"]; ok {
|
||||
mtu, ok = rMtu.(int)
|
||||
if !ok {
|
||||
s, ok := rMtu.(string)
|
||||
if !ok {
|
||||
return nil, fmt.Errorf("entry %v.mtu in tun.unsafe_routes is not an integer: %v", i+1, rMtu)
|
||||
}
|
||||
mtu, err = strconv.Atoi(s)
|
||||
mtu, err = strconv.Atoi(rMtu.(string))
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("entry %v.mtu in tun.unsafe_routes is not an integer: %v", i+1, err)
|
||||
}
|
||||
@@ -206,15 +192,10 @@ func parseUnsafeRoutes(c *config.C, networks []netip.Prefix) ([]Route, error) {
|
||||
|
||||
metric, ok := rMetric.(int)
|
||||
if !ok {
|
||||
s, ok := rMetric.(string)
|
||||
if !ok {
|
||||
return nil, fmt.Errorf("entry %v.metric in tun.unsafe_routes is not an integer: %v", i+1, rMetric)
|
||||
}
|
||||
n, err := strconv.ParseInt(s, 10, 32)
|
||||
_, err = strconv.ParseInt(rMetric.(string), 10, 32)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("entry %v.metric in tun.unsafe_routes is not an integer: %v", i+1, err)
|
||||
}
|
||||
metric = int(n)
|
||||
}
|
||||
|
||||
if metric < 0 || metric > math.MaxInt32 {
|
||||
@@ -267,15 +248,10 @@ func parseUnsafeRoutes(c *config.C, networks []netip.Prefix) ([]Route, error) {
|
||||
|
||||
gatewayWeight, ok := rGatewayWeight.(int)
|
||||
if !ok {
|
||||
s, ok := rGatewayWeight.(string)
|
||||
if !ok {
|
||||
return nil, fmt.Errorf("entry .weight in tun.unsafe_routes[%v].via[%v] is not an integer", i+1, ig+1)
|
||||
}
|
||||
w, err := strconv.ParseInt(s, 10, 32)
|
||||
_, err = strconv.ParseInt(rGatewayWeight.(string), 10, 32)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("entry .weight in tun.unsafe_routes[%v].via[%v] is not an integer", i+1, ig+1)
|
||||
}
|
||||
gatewayWeight = int(w)
|
||||
}
|
||||
|
||||
if gatewayWeight < 1 || gatewayWeight > math.MaxInt32 {
|
||||
|
||||
@@ -1,17 +1,13 @@
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"net/netip"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/routing"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
@@ -406,115 +402,3 @@ func Test_makeMultipathUnsafeRouteTree(t *testing.T) {
|
||||
routing.CalculateBucketsForGateways(expectedGateways)
|
||||
assert.ElementsMatch(t, expectedGateways, r)
|
||||
}
|
||||
|
||||
func Test_getMTU(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
|
||||
// unset
|
||||
assert.Equal(t, DefaultMTU, getMTU(l, c))
|
||||
|
||||
// the largest a relayed packet can carry in one underlay buffer
|
||||
require.Equal(t, udp.MTU, MaxMTU+header.MaxOverhead)
|
||||
c.Settings["tun"] = map[string]any{"mtu": MaxMTU}
|
||||
assert.Equal(t, MaxMTU, getMTU(l, c))
|
||||
|
||||
// too big is capped
|
||||
c.Settings["tun"] = map[string]any{"mtu": 9000}
|
||||
assert.Equal(t, MaxMTU, getMTU(l, c))
|
||||
}
|
||||
|
||||
func Test_getAllRoutesFromConfigCapsMTU(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
c.Settings["tun"] = map[string]any{
|
||||
"routes": []any{
|
||||
map[string]any{"mtu": "9000", "route": "10.0.0.0/29"},
|
||||
map[string]any{"mtu": "1300", "route": "10.0.0.8/29"},
|
||||
},
|
||||
"unsafe_routes": []any{
|
||||
map[string]any{"via": "127.0.0.1", "mtu": "9000", "route": "1.0.0.0/29"},
|
||||
},
|
||||
}
|
||||
|
||||
changed, routes, err := getAllRoutesFromConfig(l, c, []netip.Prefix{netip.MustParsePrefix("10.0.0.0/24")}, true)
|
||||
require.NoError(t, err)
|
||||
assert.True(t, changed)
|
||||
|
||||
mtus := map[string]int{}
|
||||
for _, r := range routes {
|
||||
mtus[r.Cidr.String()] = r.MTU
|
||||
}
|
||||
assert.Equal(t, map[string]int{"10.0.0.0/29": MaxMTU, "10.0.0.8/29": 1300, "1.0.0.0/29": MaxMTU}, mtus)
|
||||
}
|
||||
|
||||
// The route tree keeps one entry per CIDR, so a CIDR listed twice only routes by the last one. Say so instead of
|
||||
// letting the earlier via, or on Windows the earlier metric, quietly lose
|
||||
func Test_makeRouteTree_WarnsOnDuplicate(t *testing.T) {
|
||||
buf := &bytes.Buffer{}
|
||||
l := test.NewLoggerWithOutput(buf)
|
||||
via := func(s string) routing.Gateways {
|
||||
return routing.Gateways{routing.NewGateway(netip.MustParseAddr(s), 1)}
|
||||
}
|
||||
cidr := netip.MustParsePrefix("10.251.1.0/24")
|
||||
|
||||
_, err := makeRouteTree(l, []Route{
|
||||
{Cidr: cidr, Via: via("10.250.0.2"), Install: true, Metric: 100},
|
||||
{Cidr: netip.MustParsePrefix("10.251.2.0/24"), Via: via("10.250.0.2"), Install: true},
|
||||
}, false)
|
||||
require.NoError(t, err)
|
||||
assert.Empty(t, buf.String())
|
||||
|
||||
tree, err := makeRouteTree(l, []Route{
|
||||
{Cidr: cidr, Via: via("10.250.0.2"), Install: true, Metric: 100},
|
||||
{Cidr: cidr, Via: via("10.250.0.3"), Install: true, Metric: 200},
|
||||
}, false)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, 1, strings.Count(buf.String(), "route is listed more than once, only the last entry's via is used"))
|
||||
gw, ok := tree.Lookup(netip.MustParseAddr("10.251.1.1"))
|
||||
require.True(t, ok)
|
||||
assert.Equal(t, netip.MustParseAddr("10.250.0.3"), gw[0].Addr(), "the last entry wins")
|
||||
}
|
||||
|
||||
// A quoted metric or weight is a number written as a string, it means that number. Anything else is an error, not a
|
||||
// panic
|
||||
func Test_parseUnsafeRoutes_QuotedNumbers(t *testing.T) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
n := netip.MustParsePrefix("10.0.0.1/24")
|
||||
route := func(metric, weight any) {
|
||||
c.Settings["tun"] = map[string]any{"unsafe_routes": []any{map[string]any{
|
||||
"route": "1.0.0.0/8",
|
||||
"metric": metric,
|
||||
"via": []any{map[string]any{"gateway": "10.0.0.2", "weight": weight}},
|
||||
}}}
|
||||
}
|
||||
|
||||
route("100", "5")
|
||||
routes, err := parseUnsafeRoutes(c, []netip.Prefix{n})
|
||||
require.NoError(t, err)
|
||||
require.Len(t, routes, 1)
|
||||
assert.Equal(t, 100, routes[0].Metric)
|
||||
assert.Equal(t, "{addr: 10.0.0.2, weight: 5}", routes[0].Via[0].String())
|
||||
|
||||
route(1.5, 1)
|
||||
_, err = parseUnsafeRoutes(c, []netip.Prefix{n})
|
||||
require.EqualError(t, err, "entry 1.metric in tun.unsafe_routes is not an integer: 1.5")
|
||||
|
||||
route(1, true)
|
||||
_, err = parseUnsafeRoutes(c, []netip.Prefix{n})
|
||||
require.EqualError(t, err, "entry .weight in tun.unsafe_routes[1].via[1] is not an integer")
|
||||
}
|
||||
|
||||
// An mtu that is neither a number nor a quoted one is an error, not a panic
|
||||
func Test_parseRoutes_MTUNotANumber(t *testing.T) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
n := netip.MustParsePrefix("10.0.0.1/24")
|
||||
|
||||
c.Settings["tun"] = map[string]any{"routes": []any{map[string]any{"route": "1.0.0.0/8", "mtu": 1500.5}}}
|
||||
_, err := parseRoutes(c, []netip.Prefix{n})
|
||||
require.EqualError(t, err, "entry 1.mtu in tun.routes is not an integer: 1500.5")
|
||||
|
||||
c.Settings["tun"] = map[string]any{"unsafe_routes": []any{map[string]any{"route": "1.0.0.0/8", "via": "10.0.0.2", "mtu": 1500.5}}}
|
||||
_, err = parseUnsafeRoutes(c, []netip.Prefix{n})
|
||||
require.EqualError(t, err, "entry 1.mtu in tun.unsafe_routes is not an integer: 1500.5")
|
||||
}
|
||||
+2
-31
@@ -7,27 +7,11 @@ import (
|
||||
"net/netip"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/slackhq/nebula/util"
|
||||
)
|
||||
|
||||
const DefaultMTU = 1300
|
||||
|
||||
// MaxMTU is the largest tun.mtu, or route mtu, the underlay can carry.
|
||||
// Every underlay buffer is udp.MTU bytes, and a relayed packet adds header.MaxOverhead to its plaintext.
|
||||
const MaxMTU = udp.MTU - header.MaxOverhead
|
||||
|
||||
// getMTU reads tun.mtu, capping a value too big for the underlay to carry.
|
||||
func getMTU(l *slog.Logger, c *config.C) int {
|
||||
mtu := c.GetInt("tun.mtu", DefaultMTU)
|
||||
if mtu > MaxMTU {
|
||||
l.Warn("tun.mtu is too big for the underlay to carry, capping it", "mtu", mtu, "maxMTU", MaxMTU)
|
||||
return MaxMTU
|
||||
}
|
||||
return mtu
|
||||
}
|
||||
|
||||
type NameError struct {
|
||||
Name string
|
||||
Underlying error
|
||||
@@ -41,16 +25,9 @@ func (e *NameError) Error() string {
|
||||
type DeviceFactory func(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, routines int) (Device, error)
|
||||
|
||||
func NewDeviceFromConfig(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, routines int) (Device, error) {
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.disabled")
|
||||
})
|
||||
|
||||
switch {
|
||||
case c.GetBool("tun.disabled", false):
|
||||
tun := newDisabledTun(vpnNetworks, c.GetInt("tun.tx_queue", 5000), c.GetBool("stats.message_metrics", false), l)
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.tx_queue", "stats.message_metrics")
|
||||
})
|
||||
tun := newDisabledTun(vpnNetworks, c.GetInt("tun.tx_queue", 500), c.GetBool("stats.message_metrics", false), l)
|
||||
return tun, nil
|
||||
|
||||
default:
|
||||
@@ -64,7 +41,7 @@ func NewFdDeviceFromConfig(fd *int) DeviceFactory {
|
||||
}
|
||||
}
|
||||
|
||||
func getAllRoutesFromConfig(l *slog.Logger, c *config.C, vpnNetworks []netip.Prefix, initial bool) (bool, []Route, error) {
|
||||
func getAllRoutesFromConfig(c *config.C, vpnNetworks []netip.Prefix, initial bool) (bool, []Route, error) {
|
||||
if !initial && !c.HasChanged("tun.routes") && !c.HasChanged("tun.unsafe_routes") {
|
||||
return false, nil, nil
|
||||
}
|
||||
@@ -80,12 +57,6 @@ func getAllRoutesFromConfig(l *slog.Logger, c *config.C, vpnNetworks []netip.Pre
|
||||
}
|
||||
|
||||
routes = append(routes, unsafeRoutes...)
|
||||
for i, r := range routes {
|
||||
if r.MTU > MaxMTU {
|
||||
l.Warn("route mtu is too big for the underlay to carry, capping it", "route", r.Cidr, "mtu", r.MTU, "maxMTU", MaxMTU)
|
||||
routes[i].MTU = MaxMTU
|
||||
}
|
||||
}
|
||||
return true, routes, nil
|
||||
}
|
||||
|
||||
|
||||
@@ -38,17 +38,16 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
|
||||
l: l,
|
||||
}
|
||||
|
||||
err := t.reload(c, true, nil)
|
||||
err := t.reload(c, true)
|
||||
if err != nil {
|
||||
_ = file.Close()
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -68,8 +67,8 @@ func (t *tun) Activate() error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
@@ -1,45 +0,0 @@
|
||||
//go:build (openbsd || netbsd) && !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"os"
|
||||
"regexp"
|
||||
"runtime"
|
||||
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
var deviceNameRE = regexp.MustCompile(`^tun[0-9]+$`)
|
||||
|
||||
// tunDevNeedsRestart is true when tun.dev asks for a particular tun that isn't the running one. Anything else takes the
|
||||
// first free one, and the one we have will do
|
||||
func tunDevNeedsRestart(name, running string) bool {
|
||||
return deviceNameRE.MatchString(name) && name != running
|
||||
}
|
||||
|
||||
// openTun opens /dev/name, or the first /dev/tunN nothing else has open when name is empty or not tunN
|
||||
func openTun(l *slog.Logger, name string) (int, string, error) {
|
||||
if name != "" && !deviceNameRE.MatchString(name) {
|
||||
// The name doesn't mean anything here, so like darwin a bad one isn't worth refusing to start over
|
||||
l.Warn("interface name must be tun[0-9]+ on "+runtime.GOOS+", ignoring", "name", name)
|
||||
name = ""
|
||||
}
|
||||
if name != "" {
|
||||
fd, err := unix.Open("/dev/"+name, os.O_RDWR, 0)
|
||||
return fd, name, err
|
||||
}
|
||||
for i := 0; ; i++ {
|
||||
name = fmt.Sprintf("tun%d", i)
|
||||
fd, err := unix.Open("/dev/"+name, os.O_RDWR, 0)
|
||||
if err == nil {
|
||||
return fd, name, nil
|
||||
}
|
||||
if !errors.Is(err, unix.EBUSY) {
|
||||
return -1, "", fmt.Errorf("no free tun device, %s: %w", name, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,80 +0,0 @@
|
||||
//go:build (openbsd || netbsd) && !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// A tun.dev that isn't tunN is ignored like darwin does, and the first free tun is used. Only naming a different tun
|
||||
// asks for a restart
|
||||
func TestTunReloadDevRestart(t *testing.T) {
|
||||
newWithDev := func(dev string) (*config.C, *tun, error) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("tun:\n dev: "+dev+"\n"))
|
||||
tn, err := newTun(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, false)
|
||||
if err == nil {
|
||||
t.Cleanup(func() { _ = tn.Close() })
|
||||
}
|
||||
return c, tn, err
|
||||
}
|
||||
if _, _, err := newWithDev(""); err != nil {
|
||||
t.Skipf("can't create a tun device here: %v", err)
|
||||
}
|
||||
c, tn, err := newWithDev("nope")
|
||||
require.NoError(t, err, "a bad name should fall back to a free tun")
|
||||
require.Regexp(t, `^tun[0-9]+$`, tn.Device)
|
||||
|
||||
for _, dev := range []string{"nope", "", tn.Device, "nope"} {
|
||||
res := c.ReloadConfigString("tun:\n dev: " + dev + "\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed, dev)
|
||||
assert.False(t, res.RestartRequired, dev)
|
||||
}
|
||||
|
||||
other := "tun0"
|
||||
if tn.Device == other {
|
||||
other = "tun1"
|
||||
}
|
||||
res := c.ReloadConfigString("tun:\n dev: " + other + "\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.Equal(t, []string{"tun.dev"}, res.RestartKeys)
|
||||
}
|
||||
|
||||
// An empty tun.dev takes the first tun nothing else has open. Reloading it empty, or naming the one we have, needs
|
||||
// no restart
|
||||
func TestTunEmptyDevPicksAFreeOne(t *testing.T) {
|
||||
newEmpty := func() (*config.C, *tun, error) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("tun: {}\n"))
|
||||
tn, err := newTun(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, false)
|
||||
if err == nil {
|
||||
t.Cleanup(func() { _ = tn.Close() })
|
||||
}
|
||||
return c, tn, err
|
||||
}
|
||||
c, first, err := newEmpty()
|
||||
if err != nil {
|
||||
t.Skipf("can't create a tun device here: %v", err)
|
||||
}
|
||||
_, second, err := newEmpty()
|
||||
require.NoError(t, err, "the second tun should skip the one the first has open")
|
||||
assert.NotEqual(t, first.Device, second.Device)
|
||||
|
||||
for _, cfg := range []string{
|
||||
"tun: {}\npunchy:\n punch: true\n",
|
||||
"tun:\n dev: " + first.Device + "\n",
|
||||
"tun: {}\n",
|
||||
} {
|
||||
res := c.ReloadConfigString(cfg)
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.False(t, res.RestartRequired, cfg)
|
||||
}
|
||||
}
|
||||
@@ -10,9 +10,6 @@ import (
|
||||
"github.com/slackhq/nebula/wfp"
|
||||
)
|
||||
|
||||
// interfaceBypassKeys are only read when the interface bypass is installed
|
||||
var interfaceBypassKeys = []string{"tun.windows_bypass_wdf"}
|
||||
|
||||
// installInterfaceBypass installs a WFP PERMIT filter scoped to the wintun interface LUID so inbound traffic on the
|
||||
// nebula adapter bypasses Windows Defender Firewall.
|
||||
func installInterfaceBypass(l *slog.Logger, luid uint64) closer {
|
||||
|
||||
@@ -4,9 +4,6 @@ package overlay
|
||||
|
||||
import "log/slog"
|
||||
|
||||
// interfaceBypassKeys is empty, windows-386 has no bypass
|
||||
var interfaceBypassKeys []string
|
||||
|
||||
// installInterfaceBypass is a no-op on windows-386 because we don't currently build for it.
|
||||
func installInterfaceBypass(_ *slog.Logger, _ uint64) closer {
|
||||
return nil
|
||||
|
||||
+93
-174
@@ -3,15 +3,13 @@
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"math/bits"
|
||||
"net/netip"
|
||||
"os"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
"time"
|
||||
"unsafe"
|
||||
|
||||
"github.com/gaissmai/bart"
|
||||
@@ -30,31 +28,11 @@ type tun struct {
|
||||
DefaultMTU int
|
||||
Routes atomic.Pointer[[]Route]
|
||||
routeTree atomic.Pointer[bart.Table[routing.Gateways]]
|
||||
linkAddr atomic.Pointer[netroute.LinkAddr]
|
||||
linkAddr *netroute.LinkAddr
|
||||
// hostOwned means the fd arrived from the OS, which has already configured addressing, mtu
|
||||
// and routes for it. NEPacketTunnelProvider on darwin does this.
|
||||
hostOwned bool
|
||||
l *slog.Logger
|
||||
|
||||
// routesMu serializes changes to the system routing table between reload and the route watcher, and guards the
|
||||
// fields below it
|
||||
routesMu sync.Mutex
|
||||
// routeStates is who held each installable unsafe_route prefix when we last looked
|
||||
routeStates map[netip.Prefix]routeState
|
||||
// routeWatch is the routing socket watchRoutes reads, Close closes it
|
||||
routeWatch *os.File
|
||||
// routeSweep reconciles the unsafe_routes every routeSweepEvery
|
||||
routeSweep *time.Timer
|
||||
routeSweepEvery time.Duration
|
||||
closed bool
|
||||
|
||||
// routeMovers is who last changed each unsafe_route prefix since the last reconcile, for its logs. It has its own
|
||||
// lock so the route watcher never waits on a reconcile
|
||||
routeMoversMu sync.Mutex
|
||||
routeMovers map[netip.Prefix]routeMover
|
||||
|
||||
// lastRouteEvent is when the routing socket last reported something that may have moved a prefix, in unix nanos
|
||||
lastRouteEvent atomic.Int64
|
||||
}
|
||||
|
||||
type ifReq struct {
|
||||
@@ -100,31 +78,17 @@ type ifreqAlias6 struct {
|
||||
Lifetime addrLifetime
|
||||
}
|
||||
|
||||
// utunIndex is the utun tun.dev asks for, or -1 for whichever is free. ok is false for a name that isn't utunN, which
|
||||
// also gets whichever is free
|
||||
func utunIndex(name string) (index int, ok bool) {
|
||||
if name == "" || name == "utun" {
|
||||
return -1, true
|
||||
}
|
||||
if _, err := fmt.Sscanf(name, "utun%d", &index); err != nil || index < 0 {
|
||||
return -1, false
|
||||
}
|
||||
return index, true
|
||||
}
|
||||
|
||||
// tunDevNeedsRestart is true when tun.dev asks for a particular utun that isn't the running one. Anything else takes
|
||||
// whichever is free, and the one we have will do
|
||||
func tunDevNeedsRestart(name, running string) bool {
|
||||
index, _ := utunIndex(name)
|
||||
return index >= 0 && fmt.Sprintf("utun%d", index) != running
|
||||
}
|
||||
|
||||
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
|
||||
ifIndex, ok := utunIndex(c.GetString("tun.dev", ""))
|
||||
if !ok {
|
||||
// NOTE: we don't make this error so we don't break existing
|
||||
// configs that set a name before it was used.
|
||||
l.Warn("interface name must be utun[0-9]+ on Darwin, ignoring")
|
||||
name := c.GetString("tun.dev", "")
|
||||
ifIndex := -1
|
||||
if name != "" && name != "utun" {
|
||||
_, err := fmt.Sscanf(name, "utun%d", &ifIndex)
|
||||
if err != nil || ifIndex < 0 {
|
||||
// NOTE: we don't make this error so we don't break existing
|
||||
// configs that set a name before it was used.
|
||||
l.Warn("interface name must be utun[0-9]+ on Darwin, ignoring")
|
||||
ifIndex = -1
|
||||
}
|
||||
}
|
||||
|
||||
fd, err := unix.Socket(unix.AF_SYSTEM, unix.SOCK_DGRAM, unix.AF_SYS_CONTROL)
|
||||
@@ -148,7 +112,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
return nil, fmt.Errorf("SYS_CONNECT: %v", err)
|
||||
}
|
||||
|
||||
name, err := unix.GetsockoptString(fd, unix.AF_SYS_CONTROL, _UTUN_OPT_IFNAME)
|
||||
name, err = unix.GetsockoptString(fd, unix.AF_SYS_CONTROL, _UTUN_OPT_IFNAME)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to retrieve tun name: %w", err)
|
||||
}
|
||||
@@ -159,28 +123,22 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
}
|
||||
|
||||
t := &tun{
|
||||
f: os.NewFile(uintptr(fd), ""),
|
||||
Device: name,
|
||||
vpnNetworks: vpnNetworks,
|
||||
DefaultMTU: getMTU(l, c),
|
||||
routeSweepEvery: routeSweepInterval,
|
||||
l: l,
|
||||
f: os.NewFile(uintptr(fd), ""),
|
||||
Device: name,
|
||||
vpnNetworks: vpnNetworks,
|
||||
DefaultMTU: c.GetInt("tun.mtu", DefaultMTU),
|
||||
l: l,
|
||||
}
|
||||
|
||||
err = t.reload(c, true, nil)
|
||||
err = t.reload(c, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.mtu")
|
||||
if tunDevNeedsRestart(c.GetString("tun.dev", ""), t.Device) {
|
||||
r.RestartRequiredIfChanged("tun.dev")
|
||||
}
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -209,20 +167,19 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
|
||||
f: file,
|
||||
Device: utunNameFromFd(deviceFd),
|
||||
vpnNetworks: vpnNetworks,
|
||||
DefaultMTU: getMTU(l, c),
|
||||
DefaultMTU: c.GetInt("tun.mtu", DefaultMTU),
|
||||
hostOwned: true,
|
||||
l: l,
|
||||
}
|
||||
|
||||
if err := t.reload(c, true, nil); err != nil {
|
||||
if err := t.reload(c, true); err != nil {
|
||||
_ = file.Close()
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
if err := t.reload(c, false, r); err != nil {
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
if err := t.reload(c, false); err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -240,16 +197,6 @@ func utunNameFromFd(fd int) string {
|
||||
}
|
||||
|
||||
func (t *tun) Close() error {
|
||||
t.routesMu.Lock()
|
||||
t.closed = true
|
||||
if t.routeWatch != nil {
|
||||
_ = t.routeWatch.Close()
|
||||
}
|
||||
if t.routeSweep != nil {
|
||||
t.routeSweep.Stop()
|
||||
}
|
||||
t.routesMu.Unlock()
|
||||
|
||||
if t.f != nil {
|
||||
return t.f.Close()
|
||||
}
|
||||
@@ -296,7 +243,7 @@ func (t *tun) Activate() error {
|
||||
if linkAddr == nil {
|
||||
return fmt.Errorf("unable to discover link_addr for tun interface")
|
||||
}
|
||||
t.linkAddr.Store(linkAddr)
|
||||
t.linkAddr = linkAddr
|
||||
|
||||
for _, network := range t.vpnNetworks {
|
||||
if network.Addr().Is4() {
|
||||
@@ -318,25 +265,10 @@ func (t *tun) Activate() error {
|
||||
return fmt.Errorf("failed to run tun device: %s", err)
|
||||
}
|
||||
|
||||
// Watch before adding so a route removed in between is still noticed
|
||||
watch, err := openRouteSocket()
|
||||
if err != nil {
|
||||
t.l.Error("Failed to watch the system routing table, unsafe_routes held by another interface are only retried every minute", "error", err)
|
||||
}
|
||||
|
||||
// Unsafe path routes
|
||||
if err = t.addRoutes(false, nil); err != nil {
|
||||
if watch != nil {
|
||||
_ = watch.Close()
|
||||
}
|
||||
return err
|
||||
}
|
||||
|
||||
t.startRouteWatch(watch)
|
||||
return nil
|
||||
return t.addRoutes(false)
|
||||
}
|
||||
|
||||
// activate4 assigns our vpn address as a /32 and routes the vpn network to the tun explicitly.
|
||||
func (t *tun) activate4(network netip.Prefix) error {
|
||||
s, err := unix.Socket(
|
||||
unix.AF_INET,
|
||||
@@ -363,32 +295,22 @@ func (t *tun) activate4(network netip.Prefix) error {
|
||||
MaskAddr: unix.RawSockaddrInet4{
|
||||
Len: unix.SizeofSockaddrInet4,
|
||||
Family: unix.AF_INET,
|
||||
Addr: [4]byte{255, 255, 255, 255}, //always make the address a /32
|
||||
Addr: prefixToMask(network).As4(),
|
||||
},
|
||||
}
|
||||
|
||||
// On Darwin, VPNs don't edit the routing table directly.
|
||||
// A network extension hands its routes to the system, and configd installs them.
|
||||
// configd replaces any route already holding the same prefix, including ours.
|
||||
// As an example, Tailscale with an exit node treats any interface prefix wider than one address as a LAN.
|
||||
// With LAN access off, it routes each LAN into Tailscale's utun.
|
||||
// With LAN access on, it excludes each LAN from its tunnel.
|
||||
// configd routes an excluded prefix like its own routes would, ignoring ours, so it goes out the default route.
|
||||
// Either way our route is replaced, and traffic for the vpn network no longer reaches nebula.
|
||||
// A single address isn't a LAN to Tailscale, so our route is left alone.
|
||||
// We route the vpn network to the tun explicitly instead.
|
||||
|
||||
if err := ioctl(uintptr(s), unix.SIOCAIFADDR, uintptr(unsafe.Pointer(&ifr))); err != nil {
|
||||
return fmt.Errorf("failed to set tun v4 address: %s", err)
|
||||
}
|
||||
|
||||
if err := addRoute(network, t.linkAddr.Load()); err != nil {
|
||||
return fmt.Errorf("failed to add route for %v: %w", network.Masked(), err)
|
||||
err = addRoute(network, t.linkAddr)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// activate6 is activate4 for IPv6
|
||||
func (t *tun) activate6(network netip.Prefix) error {
|
||||
s, err := unix.Socket(
|
||||
unix.AF_INET6,
|
||||
@@ -410,36 +332,31 @@ func (t *tun) activate6(network netip.Prefix) error {
|
||||
PrefixMask: unix.RawSockaddrInet6{
|
||||
Len: unix.SizeofSockaddrInet6,
|
||||
Family: unix.AF_INET6,
|
||||
// Always set the netmask to be a /128. See activate4 for why we do this.
|
||||
Addr: [16]byte{255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255},
|
||||
Addr: prefixToMask(network).As16(),
|
||||
},
|
||||
Lifetime: addrLifetime{
|
||||
// never expires
|
||||
Vltime: 0xffffffff,
|
||||
Pltime: 0xffffffff,
|
||||
},
|
||||
Flags: _IN6_IFF_NODAD, // No DAD, a utun has no neighbors.
|
||||
Flags: _IN6_IFF_NODAD,
|
||||
}
|
||||
|
||||
if err := ioctl(uintptr(s), _SIOCAIFADDR_IN6, uintptr(unsafe.Pointer(&ifr))); err != nil {
|
||||
return fmt.Errorf("failed to set tun address: %s", err)
|
||||
}
|
||||
|
||||
if err := addRoute(network, t.linkAddr.Load()); err != nil {
|
||||
return fmt.Errorf("failed to add route for %v: %w", network.Masked(), err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
if !initial && !change {
|
||||
// Any reload puts back the unsafe_routes someone deleted
|
||||
return t.addRoutes(true, r)
|
||||
return nil
|
||||
}
|
||||
|
||||
routeTree, err := makeRouteTree(t.l, routes, false)
|
||||
@@ -453,18 +370,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
|
||||
if !initial {
|
||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
|
||||
// Ensure any routes we actually want are installed
|
||||
err = t.addRoutes(true, r)
|
||||
err = t.addRoutes(true)
|
||||
if err != nil {
|
||||
// Catch any stray logs
|
||||
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -479,56 +394,6 @@ func (t *tun) RoutesFor(ip netip.Addr) routing.Gateways {
|
||||
return routing.Gateways{}
|
||||
}
|
||||
|
||||
func fetchRoutes() ([]netroute.Message, error) {
|
||||
rib, err := netroute.FetchRIB(unix.AF_UNSPEC, unix.NET_RT_DUMP, 0)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return netroute.ParseRIB(unix.NET_RT_DUMP, rib)
|
||||
}
|
||||
|
||||
// routeInterfaceIn returns the index of the interface prefix is routed through, or 0 if msgs has no route for exactly
|
||||
// that prefix. Routes scoped to an interface are skipped, they don't stop us adding ours.
|
||||
func routeInterfaceIn(msgs []netroute.Message, prefix netip.Prefix) int {
|
||||
for _, msg := range msgs {
|
||||
m, ok := msg.(*netroute.RouteMessage)
|
||||
if !ok || len(m.Addrs) <= unix.RTAX_NETMASK || m.Flags&unix.RTF_IFSCOPE != 0 {
|
||||
continue
|
||||
}
|
||||
if p, ok := routePrefix(m.Addrs[unix.RTAX_DST], m.Addrs[unix.RTAX_NETMASK]); ok && p == prefix.Masked() {
|
||||
return m.Index
|
||||
}
|
||||
}
|
||||
return 0
|
||||
}
|
||||
|
||||
// routePrefix returns the prefix a route covers. Host routes have no netmask.
|
||||
func routePrefix(dst, mask netroute.Addr) (netip.Prefix, bool) {
|
||||
switch d := dst.(type) {
|
||||
case *netroute.Inet4Addr:
|
||||
bits := 32
|
||||
if m, ok := mask.(*netroute.Inet4Addr); ok {
|
||||
bits = maskBits(m.IP[:])
|
||||
}
|
||||
return netip.PrefixFrom(netip.AddrFrom4(d.IP), bits), true
|
||||
case *netroute.Inet6Addr:
|
||||
bits := 128
|
||||
if m, ok := mask.(*netroute.Inet6Addr); ok {
|
||||
bits = maskBits(m.IP[:])
|
||||
}
|
||||
return netip.PrefixFrom(netip.AddrFrom16(d.IP), bits), true
|
||||
}
|
||||
return netip.Prefix{}, false
|
||||
}
|
||||
|
||||
func maskBits(mask []byte) int {
|
||||
n := 0
|
||||
for _, b := range mask {
|
||||
n += bits.OnesCount8(b)
|
||||
}
|
||||
return n
|
||||
}
|
||||
|
||||
// Get the LinkAddr for the interface of the given name
|
||||
// Is there an easier way to fetch this when we create the interface?
|
||||
// Maybe SIOCGIFINDEX? but this doesn't appear to exist in the darwin headers.
|
||||
@@ -557,6 +422,60 @@ func getLinkAddr(name string) (*netroute.LinkAddr, error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
func (t *tun) addRoutes(logErrors bool) error {
|
||||
// The route tree is still ours, the system routing table is not
|
||||
if t.hostOwned {
|
||||
return nil
|
||||
}
|
||||
|
||||
routes := *t.Routes.Load()
|
||||
|
||||
for _, r := range routes {
|
||||
if len(r.Via) == 0 || !r.Install {
|
||||
// We don't allow route MTUs so only install routes with a via
|
||||
continue
|
||||
}
|
||||
|
||||
err := addRoute(r.Cidr, t.linkAddr)
|
||||
if err != nil {
|
||||
if errors.Is(err, unix.EEXIST) {
|
||||
t.l.Warn("unable to add unsafe_route, identical route already exists", "route", r.Cidr)
|
||||
} else {
|
||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||
if logErrors {
|
||||
retErr.Log(t.l)
|
||||
} else {
|
||||
return retErr
|
||||
}
|
||||
}
|
||||
} else {
|
||||
t.l.Info("Added route", "route", r)
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) removeRoutes(routes []Route) error {
|
||||
if t.hostOwned {
|
||||
return nil
|
||||
}
|
||||
|
||||
for _, r := range routes {
|
||||
if !r.Install {
|
||||
continue
|
||||
}
|
||||
|
||||
err := delRoute(r.Cidr, t.linkAddr)
|
||||
if err != nil {
|
||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||
} else {
|
||||
t.l.Info("Removed route", "route", r)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func addRoute(prefix netip.Prefix, gateway netroute.Addr) error {
|
||||
sock, err := unix.Socket(unix.AF_ROUTE, unix.SOCK_RAW, unix.AF_UNSPEC)
|
||||
if err != nil {
|
||||
|
||||
@@ -1,484 +0,0 @@
|
||||
//go:build darwin && !ios && !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
"encoding/hex"
|
||||
"fmt"
|
||||
"net"
|
||||
"net/netip"
|
||||
"os"
|
||||
"os/exec"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/routing"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
netroute "golang.org/x/net/route"
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// Every mac routes loopback through lo0
|
||||
func TestRouteInterfaceIn(t *testing.T) {
|
||||
msgs, err := fetchRoutes()
|
||||
require.NoError(t, err)
|
||||
routeInterface := func(s string) int { return routeInterfaceIn(msgs, netip.MustParsePrefix(s)) }
|
||||
|
||||
lo0, err := net.InterfaceByName("lo0")
|
||||
require.NoError(t, err)
|
||||
|
||||
assert.Equal(t, lo0.Index, routeInterface("127.0.0.0/8"))
|
||||
assert.Equal(t, lo0.Index, routeInterface("127.0.0.1/32"), "a host route has no netmask")
|
||||
assert.Equal(t, lo0.Index, routeInterface("::1/128"))
|
||||
assert.Equal(t, 0, routeInterface("127.0.0.0/16"), "only an exact prefix counts")
|
||||
|
||||
// Most macs also list the default route scoped to their other interfaces
|
||||
out, err := exec.Command("route", "-n", "get", "default").Output()
|
||||
require.NoError(t, err)
|
||||
var name string
|
||||
for _, line := range strings.Split(string(out), "\n") {
|
||||
if v, ok := strings.CutPrefix(strings.TrimSpace(line), "interface: "); ok {
|
||||
name = v
|
||||
}
|
||||
}
|
||||
if name == "" {
|
||||
t.Skip("no default route")
|
||||
}
|
||||
def, err := net.InterfaceByName(name)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, def.Index, routeInterface("0.0.0.0/0"))
|
||||
}
|
||||
|
||||
func TestRouteInterfaceIn_SkipsScopedCopies(t *testing.T) {
|
||||
route := func(index, flags int) netroute.Message {
|
||||
addrs := make([]netroute.Addr, unix.RTAX_MAX)
|
||||
addrs[unix.RTAX_DST] = &netroute.Inet4Addr{IP: [4]byte{192, 168, 1, 0}}
|
||||
addrs[unix.RTAX_NETMASK] = &netroute.Inet4Addr{IP: [4]byte{255, 255, 255, 0}}
|
||||
return &netroute.RouteMessage{Index: index, Flags: flags, Addrs: addrs}
|
||||
}
|
||||
p := netip.MustParsePrefix("192.168.1.0/24")
|
||||
assert.Equal(t, 7, routeInterfaceIn([]netroute.Message{route(4, unix.RTF_UP|unix.RTF_IFSCOPE), route(7, unix.RTF_UP)}, p))
|
||||
assert.Equal(t, 0, routeInterfaceIn([]netroute.Message{route(4, unix.RTF_UP|unix.RTF_IFSCOPE)}, p))
|
||||
}
|
||||
|
||||
// A reload can happen before Activate
|
||||
func TestTunRoutesBeforeActivate(t *testing.T) {
|
||||
tn := &tun{l: test.NewLogger()}
|
||||
routes := []Route{{
|
||||
Cidr: netip.MustParsePrefix("10.253.1.0/24"),
|
||||
Via: routing.Gateways{routing.NewGateway(netip.MustParseAddr("10.250.0.2"), 1)},
|
||||
Install: true,
|
||||
}}
|
||||
tn.Routes.Store(&routes)
|
||||
|
||||
assert.NoError(t, tn.addRoutes(true, nil))
|
||||
assert.NoError(t, tn.removeRoutes(routes, nil))
|
||||
}
|
||||
|
||||
// A tun.routes entry with no via is never installed, so removing it must not delete a route for the same cidr that
|
||||
// belongs to someone else
|
||||
func TestTunReloadLeavesRoutesItNeverInstalled(t *testing.T) {
|
||||
if os.Geteuid() != 0 {
|
||||
t.Skip("creating a utun and adding routes needs root")
|
||||
}
|
||||
lo0, err := net.InterfaceByName("lo0")
|
||||
require.NoError(t, err)
|
||||
cidr := "10.250.0.128/25"
|
||||
require.NoError(t, exec.Command("route", "-q", "-n", "add", "-net", cidr, "-interface", "lo0").Run())
|
||||
t.Cleanup(func() { _ = exec.Command("route", "-q", "-n", "delete", "-net", cidr).Run() })
|
||||
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.LoadString("tun:\n routes:\n - route: "+cidr+"\n mtu: 1300\n"))
|
||||
tn, err := newTun(c, l, []netip.Prefix{netip.MustParsePrefix("10.250.0.1/24")}, false)
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() { _ = tn.Close() })
|
||||
require.NoError(t, tn.Activate())
|
||||
|
||||
res := c.ReloadConfigString("tun: {}\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed, "removing a route we never installed failed the reload")
|
||||
msgs, err := fetchRoutes()
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, lo0.Index, routeInterfaceIn(msgs, netip.MustParsePrefix(cidr)))
|
||||
}
|
||||
|
||||
// Captured on macOS 15.6 while adding and removing 198.51.100.77/24 on a feth
|
||||
const (
|
||||
// The kernel deleting the address's subnet route. It packs its sockaddrs without padding, x/net/route can't parse it
|
||||
kernelSubnetDelete = "870005022300000000010002070000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000010020000c63364000000000000000000141223000600000000000000000000000000000007ffffffffffff"
|
||||
addressRemoved = "5000050db400000001010000230000000000000007020000ffffff00141223000606060066657468373766657468004d10020000c633644d000000000000000010020000c63364ff0000000000000000"
|
||||
// With no interface address, which x/net/route skips
|
||||
interfaceChanged = "7000050e000000004288000023000000060000060e000000dc05000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000073e5ce6a0000000000000000000001000000000000000000"
|
||||
)
|
||||
|
||||
func TestRoutesMayHaveMoved(t *testing.T) {
|
||||
cidr := netip.MustParsePrefix("192.168.1.0/24")
|
||||
via := routing.Gateways{routing.NewGateway(netip.MustParseAddr("10.250.0.2"), 1)}
|
||||
routes := []Route{{Cidr: cidr, Via: via, Install: true}}
|
||||
// A request like route(8) sends, the kernel echoes it to every routing socket
|
||||
request := func(typ, flags int, dst, mask [4]byte) []byte {
|
||||
m := &netroute.RouteMessage{
|
||||
Version: unix.RTM_VERSION,
|
||||
Type: typ,
|
||||
Flags: flags,
|
||||
ID: 1234,
|
||||
Addrs: []netroute.Addr{
|
||||
unix.RTAX_DST: &netroute.Inet4Addr{IP: dst},
|
||||
unix.RTAX_GATEWAY: &netroute.LinkAddr{Index: 4},
|
||||
unix.RTAX_NETMASK: &netroute.Inet4Addr{IP: mask},
|
||||
},
|
||||
}
|
||||
b, err := m.Marshal()
|
||||
require.NoError(t, err)
|
||||
return b
|
||||
}
|
||||
raw := func(s string) []byte {
|
||||
b, err := hex.DecodeString(s)
|
||||
require.NoError(t, err)
|
||||
return b
|
||||
}
|
||||
lan, mask := [4]byte{192, 168, 1, 0}, [4]byte{255, 255, 255, 0}
|
||||
routesMayHaveMoved := func(b []byte, routes []Route) bool {
|
||||
moved, _, _ := routesMayHaveMoved(b, routes)
|
||||
return moved
|
||||
}
|
||||
|
||||
assert.True(t, routesMayHaveMoved(request(unix.RTM_DELETE, unix.RTF_UP, lan, mask), routes))
|
||||
assert.True(t, routesMayHaveMoved(request(unix.RTM_ADD, unix.RTF_UP, lan, mask), routes))
|
||||
assert.True(t, routesMayHaveMoved(request(unix.RTM_CHANGE, unix.RTF_UP, lan, mask), routes))
|
||||
assert.False(t, routesMayHaveMoved(request(unix.RTM_GET, unix.RTF_UP, lan, mask), routes))
|
||||
assert.False(t, routesMayHaveMoved(request(unix.RTM_DELETE, unix.RTF_UP|unix.RTF_IFSCOPE, lan, mask), routes), "a scoped route never held the prefix")
|
||||
assert.False(t, routesMayHaveMoved(request(unix.RTM_ADD, unix.RTF_UP|unix.RTF_IFSCOPE, lan, mask), routes), "configd adds a scoped copy for each interface")
|
||||
assert.False(t, routesMayHaveMoved(request(unix.RTM_DELETE, unix.RTF_UP, lan, [4]byte{255, 255, 0, 0}), routes), "only an exact prefix counts")
|
||||
assert.False(t, routesMayHaveMoved(request(unix.RTM_DELETE, unix.RTF_UP, lan, mask), []Route{{Cidr: cidr, Install: true}}), "a route with no via is never installed")
|
||||
assert.False(t, routesMayHaveMoved(request(unix.RTM_DELETE, unix.RTF_UP, lan, mask), []Route{{Cidr: cidr, Via: via}}), "install: false")
|
||||
|
||||
failed := request(unix.RTM_DELETE, unix.RTF_UP, lan, mask)
|
||||
binary.NativeEndian.PutUint32(failed[24:28], uint32(unix.ESRCH))
|
||||
assert.False(t, routesMayHaveMoved(failed, routes), "a failed request is echoed too")
|
||||
|
||||
_, err := netroute.ParseRIB(unix.NET_RT_DUMP, raw(kernelSubnetDelete))
|
||||
require.Error(t, err, "if x/net/route learns to parse these, match their prefix instead")
|
||||
assert.True(t, routesMayHaveMoved(raw(kernelSubnetDelete), routes), "the kernel's own deletes could be any prefix")
|
||||
neighbor := raw(kernelSubnetDelete)
|
||||
binary.NativeEndian.PutUint32(neighbor[8:12], unix.RTF_UP|unix.RTF_HOST|unix.RTF_LLINFO)
|
||||
assert.False(t, routesMayHaveMoved(neighbor, routes), "a neighbor expiring")
|
||||
|
||||
assert.True(t, routesMayHaveMoved(raw(addressRemoved), routes))
|
||||
assert.True(t, routesMayHaveMoved(raw(interfaceChanged), routes), "detaching an interface deletes its routes without a message for each")
|
||||
}
|
||||
|
||||
// A request names its prefix and who made it, the kernel's own and interface changes name neither
|
||||
func TestRoutesMayHaveMovedSaysWho(t *testing.T) {
|
||||
cidr := netip.MustParsePrefix("192.168.1.0/24")
|
||||
routes := []Route{{Cidr: cidr, Via: routing.Gateways{routing.NewGateway(netip.MustParseAddr("10.250.0.2"), 1)}, Install: true}}
|
||||
m := &netroute.RouteMessage{
|
||||
Version: unix.RTM_VERSION,
|
||||
Type: unix.RTM_CHANGE,
|
||||
Flags: unix.RTF_UP,
|
||||
ID: 1234,
|
||||
Addrs: []netroute.Addr{
|
||||
unix.RTAX_DST: &netroute.Inet4Addr{IP: [4]byte{192, 168, 1, 0}},
|
||||
unix.RTAX_GATEWAY: &netroute.LinkAddr{Index: 4},
|
||||
unix.RTAX_NETMASK: &netroute.Inet4Addr{IP: [4]byte{255, 255, 255, 0}},
|
||||
},
|
||||
}
|
||||
b, err := m.Marshal()
|
||||
require.NoError(t, err)
|
||||
moved, p, pid := routesMayHaveMoved(b, routes)
|
||||
assert.True(t, moved)
|
||||
assert.Equal(t, cidr, p)
|
||||
assert.Equal(t, int32(1234), pid)
|
||||
|
||||
for name, s := range map[string]string{"kernel": kernelSubnetDelete, "ifinfo": interfaceChanged} {
|
||||
b, err := hex.DecodeString(s)
|
||||
require.NoError(t, err)
|
||||
moved, p, pid := routesMayHaveMoved(b, routes)
|
||||
assert.True(t, moved, name)
|
||||
assert.False(t, p.IsValid(), name)
|
||||
assert.Zero(t, pid, name)
|
||||
}
|
||||
}
|
||||
|
||||
func TestProcessName(t *testing.T) {
|
||||
assert.Equal(t, "launchd", processName(1))
|
||||
self := filepath.Base(os.Args[0])
|
||||
assert.Equal(t, self[:min(len(self), 16)], processName(int32(os.Getpid())))
|
||||
assert.Empty(t, processName(-1))
|
||||
}
|
||||
|
||||
// newRouteTestTun is an activated tun for the root tests below with an unsafe_route for each of cidrs. sweep replaces
|
||||
// the minute between sweeps when it isn't zero.
|
||||
func newRouteTestTun(t *testing.T, sweep time.Duration, cidrs ...string) (*tun, *config.C, string) {
|
||||
requireRoot(t)
|
||||
|
||||
cfg := "tun:\n unsafe_routes:\n"
|
||||
for _, cidr := range cidrs {
|
||||
via := "10.250.0.2"
|
||||
if netip.MustParsePrefix(cidr).Addr().Is6() {
|
||||
via = "fd00:250::2"
|
||||
}
|
||||
cfg += " - route: " + cidr + "\n via: " + via + "\n"
|
||||
}
|
||||
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.LoadString(cfg))
|
||||
tn, err := newTun(c, l, []netip.Prefix{netip.MustParsePrefix("10.250.0.1/24"), netip.MustParsePrefix("fd00:250::1/64")}, false)
|
||||
require.NoError(t, err)
|
||||
if sweep != 0 {
|
||||
tn.routeSweepEvery = sweep
|
||||
}
|
||||
t.Cleanup(func() { _ = tn.Close() })
|
||||
require.NoError(t, tn.Activate())
|
||||
return tn, c, cfg
|
||||
}
|
||||
|
||||
func requireRoot(t *testing.T) {
|
||||
if os.Geteuid() != 0 {
|
||||
t.Skip("creating interfaces and adding routes needs root")
|
||||
}
|
||||
}
|
||||
|
||||
// routeVia is the index of the interface that routes cidr, 0 if none does
|
||||
func routeVia(t *testing.T, cidr string) int {
|
||||
msgs, err := fetchRoutes()
|
||||
require.NoError(t, err)
|
||||
return routeInterfaceIn(msgs, netip.MustParsePrefix(cidr))
|
||||
}
|
||||
|
||||
// routeStateOf is what tn made of cidr when it last looked
|
||||
func routeStateOf(tn *tun, cidr string) routeState {
|
||||
tn.routesMu.Lock()
|
||||
defer tn.routesMu.Unlock()
|
||||
return tn.routeStates[netip.MustParsePrefix(cidr)]
|
||||
}
|
||||
|
||||
func routeArgs(action, cidr string, extra ...string) []string {
|
||||
args := []string{"-q", "-n", action}
|
||||
if netip.MustParsePrefix(cidr).Addr().Is6() {
|
||||
args = append(args, "-inet6")
|
||||
}
|
||||
return append(append(args, "-net", cidr), extra...)
|
||||
}
|
||||
|
||||
func routeCmd(t *testing.T, action, cidr string, extra ...string) {
|
||||
requireRouteOK(t, exec.Command("route", routeArgs(action, cidr, extra...)...))
|
||||
}
|
||||
|
||||
// requireRouteOK runs cmd, which runs route(8). route exits 0 when the kernel rejects its request, only what it prints
|
||||
// says so
|
||||
func requireRouteOK(t *testing.T, cmd *exec.Cmd) {
|
||||
out, err := cmd.CombinedOutput()
|
||||
require.NoError(t, err, string(out))
|
||||
require.NotContains(t, string(out), "writing to routing socket")
|
||||
}
|
||||
|
||||
// cleanupRoute deletes cidr's route when the test ends, whoever holds it
|
||||
func cleanupRoute(t *testing.T, cidr string) {
|
||||
t.Cleanup(func() { _ = exec.Command("route", routeArgs("delete", cidr)...).Run() })
|
||||
}
|
||||
|
||||
// routeThroughLo0 routes cidr through lo0, like a lan nebula started on
|
||||
func routeThroughLo0(t *testing.T, cidr string) int {
|
||||
requireRoot(t)
|
||||
routeCmd(t, "add", cidr, "-interface", "lo0")
|
||||
cleanupRoute(t, cidr)
|
||||
lo0, err := net.InterfaceByName("lo0")
|
||||
require.NoError(t, err)
|
||||
return lo0.Index
|
||||
}
|
||||
|
||||
// Leaving the lan that held an unsafe_route's prefix must not need a restart to get the unsafe_route
|
||||
func TestTunAddsRouteOnceItsPrefixIsFree(t *testing.T) {
|
||||
for _, cidr := range []string{"10.251.0.0/24", "2001:db8:251::/64"} {
|
||||
t.Run(cidr, func(t *testing.T) {
|
||||
lo0 := routeThroughLo0(t, cidr)
|
||||
tn, _, _ := newRouteTestTun(t, 0, cidr)
|
||||
require.Equal(t, lo0, routeVia(t, cidr), "an existing route keeps its prefix")
|
||||
|
||||
routeCmd(t, "delete", cidr)
|
||||
assert.Eventually(t, func() bool { return routeVia(t, cidr) == tn.linkAddr.Load().Index }, 5*time.Second, 50*time.Millisecond)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// The kernel deletes a route by prefix alone, so dropping an unsafe_route someone else holds must not delete theirs
|
||||
func TestTunReloadLeavesRouteItYielded(t *testing.T) {
|
||||
cidr := "10.251.1.0/24"
|
||||
lo0 := routeThroughLo0(t, cidr)
|
||||
_, c, _ := newRouteTestTun(t, 0, cidr)
|
||||
|
||||
res := c.ReloadConfigString("tun: {}\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.Equal(t, lo0, routeVia(t, cidr))
|
||||
}
|
||||
|
||||
// configd takes a prefix by deleting the route holding it and adding its own. Ours goes back once theirs is removed
|
||||
func TestTunYieldsToARouteThatReplacesIt(t *testing.T) {
|
||||
cidr := "10.251.3.0/24"
|
||||
tn, _, _ := newRouteTestTun(t, 0, cidr)
|
||||
ours := tn.linkAddr.Load().Index
|
||||
require.Equal(t, ours, routeVia(t, cidr))
|
||||
|
||||
cleanupRoute(t, cidr)
|
||||
requireRouteOK(t, exec.Command("sh", "-c", "route -q -n delete -net "+cidr+" && route -q -n add -net "+cidr+" -interface lo0"))
|
||||
lo0, err := net.InterfaceByName("lo0")
|
||||
require.NoError(t, err)
|
||||
time.Sleep(2 * routeRetryDelay)
|
||||
require.Equal(t, lo0.Index, routeVia(t, cidr))
|
||||
|
||||
routeCmd(t, "delete", cidr)
|
||||
assert.Eventually(t, func() bool { return routeVia(t, cidr) == ours }, 5*time.Second, 50*time.Millisecond)
|
||||
}
|
||||
|
||||
// A route someone deleted, with nothing in its place, stays gone until a reload, so they can put their own there
|
||||
func TestTunLeavesRouteDeletedByHand(t *testing.T) {
|
||||
cidr := "10.251.4.0/24"
|
||||
tn, c, cfg := newRouteTestTun(t, 200*time.Millisecond, cidr)
|
||||
ours := tn.linkAddr.Load().Index
|
||||
require.Equal(t, ours, routeVia(t, cidr))
|
||||
|
||||
routeCmd(t, "delete", cidr)
|
||||
assert.Never(t, func() bool { return routeVia(t, cidr) != 0 }, 3*routeRetryDelay, 50*time.Millisecond)
|
||||
|
||||
// A reload with nothing changed is how to ask for it back
|
||||
res := c.ReloadConfigString(cfg)
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.Equal(t, ours, routeVia(t, cidr))
|
||||
}
|
||||
|
||||
// configd deleting ours and adding the lan's more than routeRetryDelay apart, or a sweep landing in between, looks like
|
||||
// a hand delete. Seeing the lan hold the prefix puts ours back in line, it goes back once theirs is removed
|
||||
func TestTunYieldsAfterLeavingARouteDeletedByHand(t *testing.T) {
|
||||
for name, tc := range map[string]struct {
|
||||
cidr string
|
||||
sweep time.Duration
|
||||
misfile func(t *testing.T, tn *tun, cidr string)
|
||||
}{
|
||||
// The table went quiet with nothing in its place. The minute sweep leaves noticing the lan's route to the watcher
|
||||
"settled": {"10.251.6.0/24", 0, func(t *testing.T, tn *tun, cidr string) {
|
||||
require.Eventually(t, func() bool { return routeStateOf(tn, cidr).kind == routeRemoved }, 5*time.Second, 50*time.Millisecond)
|
||||
}},
|
||||
// The sweep that caps a table that never settles
|
||||
"swept": {"10.251.7.0/24", 200 * time.Millisecond, func(t *testing.T, tn *tun, cidr string) {
|
||||
tn.reconcileRoutes()
|
||||
require.Equal(t, routeRemoved, routeStateOf(tn, cidr).kind)
|
||||
}},
|
||||
} {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
tn, _, _ := newRouteTestTun(t, tc.sweep, tc.cidr)
|
||||
ours := tn.linkAddr.Load().Index
|
||||
require.Equal(t, ours, routeVia(t, tc.cidr))
|
||||
|
||||
routeCmd(t, "delete", tc.cidr)
|
||||
tc.misfile(t, tn, tc.cidr)
|
||||
|
||||
lo0 := routeThroughLo0(t, tc.cidr)
|
||||
require.Eventually(t, func() bool {
|
||||
s := routeStateOf(tn, tc.cidr)
|
||||
return s.kind == routeYielded && s.holder == lo0
|
||||
}, 5*time.Second, 50*time.Millisecond)
|
||||
|
||||
routeCmd(t, "delete", tc.cidr)
|
||||
assert.Eventually(t, func() bool { return routeVia(t, tc.cidr) == ours }, 5*time.Second, 50*time.Millisecond)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Changing our route to another interface hands it the prefix, ours goes back once theirs is removed rather than being
|
||||
// taken for a hand delete
|
||||
func TestTunYieldsToARouteChangedAway(t *testing.T) {
|
||||
for _, cidr := range []string{"10.251.8.0/24", "2001:db8:258::/64"} {
|
||||
t.Run(cidr, func(t *testing.T) {
|
||||
tn, _, _ := newRouteTestTun(t, 0, cidr)
|
||||
ours := tn.linkAddr.Load().Index
|
||||
require.Equal(t, ours, routeVia(t, cidr))
|
||||
|
||||
cleanupRoute(t, cidr)
|
||||
routeCmd(t, "change", cidr, "-interface", "lo0")
|
||||
lo0, err := net.InterfaceByName("lo0")
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, lo0.Index, routeVia(t, cidr))
|
||||
require.Eventually(t, func() bool {
|
||||
s := routeStateOf(tn, cidr)
|
||||
return s.kind == routeYielded && s.holder == lo0.Index
|
||||
}, 5*time.Second, 50*time.Millisecond)
|
||||
|
||||
routeCmd(t, "delete", cidr)
|
||||
assert.Eventually(t, func() bool { return routeVia(t, cidr) == ours }, 5*time.Second, 50*time.Millisecond)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Detaching an interface deletes its routes without a routing socket message for each, like unplugging the dock whose
|
||||
// ethernet configd routed the lan through
|
||||
func TestTunAddsRouteWhenItsInterfaceDetaches(t *testing.T) {
|
||||
requireRoot(t)
|
||||
var feth string
|
||||
for i := 100; i < 200 && feth == ""; i++ {
|
||||
if _, err := net.InterfaceByName(fmt.Sprintf("feth%d", i)); err != nil {
|
||||
feth = fmt.Sprintf("feth%d", i)
|
||||
}
|
||||
}
|
||||
require.NotEmpty(t, feth)
|
||||
require.NoError(t, exec.Command("ifconfig", feth, "create").Run())
|
||||
t.Cleanup(func() { _ = exec.Command("ifconfig", feth, "destroy").Run() })
|
||||
require.NoError(t, exec.Command("ifconfig", feth, "inet", "198.51.100.5/24", "up").Run())
|
||||
|
||||
// Static and cloning with no gateway, like the lan routes configd installs. Named by the feth's address, macOS 27
|
||||
// refuses one named by the feth itself
|
||||
cidr := "10.251.2.0/24"
|
||||
routeCmd(t, "add", cidr, "-interface", "198.51.100.5")
|
||||
cleanupRoute(t, cidr)
|
||||
ifc, err := net.InterfaceByName(feth)
|
||||
require.NoError(t, err)
|
||||
|
||||
tn, _, _ := newRouteTestTun(t, 0, cidr)
|
||||
require.Equal(t, ifc.Index, routeVia(t, cidr))
|
||||
|
||||
// Losing the address first leaves the route, the reconcile finds it still held
|
||||
require.NoError(t, exec.Command("ifconfig", feth, "inet", "198.51.100.5", "-alias").Run())
|
||||
time.Sleep(2 * routeRetryDelay)
|
||||
require.Equal(t, ifc.Index, routeVia(t, cidr))
|
||||
|
||||
// Only RTM_IFINFO says the interface went, its route goes with no message of its own
|
||||
require.NoError(t, exec.Command("ifconfig", feth, "destroy").Run())
|
||||
assert.Eventually(t, func() bool { return routeVia(t, cidr) == tn.linkAddr.Load().Index }, 5*time.Second, 50*time.Millisecond)
|
||||
}
|
||||
|
||||
// The routing socket drops what doesn't fit its buffer without a word, the sweep finds what it missed
|
||||
func TestTunSweepAddsRouteTheWatcherMissed(t *testing.T) {
|
||||
cidr := "10.251.5.0/24"
|
||||
routeThroughLo0(t, cidr)
|
||||
tn, _, _ := newRouteTestTun(t, 200*time.Millisecond, cidr)
|
||||
|
||||
tn.routesMu.Lock()
|
||||
require.NoError(t, tn.routeWatch.Close())
|
||||
tn.routesMu.Unlock()
|
||||
|
||||
routeCmd(t, "delete", cidr)
|
||||
assert.Eventually(t, func() bool { return routeVia(t, cidr) == tn.linkAddr.Load().Index }, 5*time.Second, 50*time.Millisecond)
|
||||
}
|
||||
|
||||
// Only naming a different utun asks for a restart. Empty, plain utun and names that aren't utunN take whichever is free
|
||||
func TestTunDevNeedsRestart(t *testing.T) {
|
||||
for name, want := range map[string]bool{
|
||||
"": false,
|
||||
"utun": false,
|
||||
"nope": false,
|
||||
"utun7": false,
|
||||
"utun3": true,
|
||||
} {
|
||||
assert.Equal(t, want, tunDevNeedsRestart(name, "utun7"), name)
|
||||
}
|
||||
}
|
||||
@@ -1,121 +0,0 @@
|
||||
//go:build !ios && !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"os"
|
||||
"syscall"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
func TestTun_WriteFraming(t *testing.T) {
|
||||
r, w, err := os.Pipe()
|
||||
require.NoError(t, err)
|
||||
defer r.Close()
|
||||
defer w.Close()
|
||||
tn := &tun{f: w}
|
||||
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
pkt []byte
|
||||
af byte
|
||||
}{
|
||||
// Literal families rather than syscall.AF_*, so a wrong constant in Write can't also fix the expectation.
|
||||
{"ipv4", []byte{0x45, 1, 2, 3, 4, 5}, 2},
|
||||
{"ipv6", []byte{0x60, 1, 2, 3, 4, 5}, 30},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
n, err := tn.Write(tc.pkt)
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, len(tc.pkt), n)
|
||||
|
||||
got := make([]byte, 64)
|
||||
n, err = r.Read(got)
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, append([]byte{0, 0, 0, tc.af}, tc.pkt...), got[:n])
|
||||
})
|
||||
}
|
||||
|
||||
_, err = tn.Write([]byte{0x10, 1, 2, 3})
|
||||
require.Error(t, err)
|
||||
_, err = tn.Write([]byte{})
|
||||
require.ErrorIs(t, err, syscall.EIO)
|
||||
|
||||
// The rejected writes must not have put anything on the fd, so the next read sees only this packet.
|
||||
pkt := []byte{0x45, 9, 9}
|
||||
_, err = tn.Write(pkt)
|
||||
require.NoError(t, err)
|
||||
got := make([]byte, 64)
|
||||
n, err := r.Read(got)
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, append([]byte{0, 0, 0, 2}, pkt...), got[:n])
|
||||
}
|
||||
|
||||
func TestTun_ReadStripsHeader(t *testing.T) {
|
||||
r, w, err := os.Pipe()
|
||||
require.NoError(t, err)
|
||||
defer r.Close()
|
||||
defer w.Close()
|
||||
tn := &tun{f: r}
|
||||
|
||||
pkt := []byte{0x45, 1, 2, 3, 4, 5}
|
||||
_, err = w.Write(append([]byte{0, 0, 0, syscall.AF_INET}, pkt...))
|
||||
require.NoError(t, err)
|
||||
|
||||
got := make([]byte, 64)
|
||||
n, err := tn.Read(got)
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, pkt, got[:n])
|
||||
}
|
||||
|
||||
func TestTun_ReadShort(t *testing.T) {
|
||||
r, w, err := os.Pipe()
|
||||
require.NoError(t, err)
|
||||
defer r.Close()
|
||||
defer w.Close()
|
||||
tn := &tun{f: r}
|
||||
|
||||
// Fewer bytes than the protocol header is not a packet.
|
||||
_, err = w.Write([]byte{0, 0})
|
||||
require.NoError(t, err)
|
||||
n, err := tn.Read(make([]byte, 64))
|
||||
require.NoError(t, err)
|
||||
require.Zero(t, n)
|
||||
|
||||
// The next packet reads cleanly only if the short read consumed exactly what was written.
|
||||
pkt := []byte{0x45, 1, 2, 3}
|
||||
_, err = w.Write(append([]byte{0, 0, 0, syscall.AF_INET}, pkt...))
|
||||
require.NoError(t, err)
|
||||
got := make([]byte, 64)
|
||||
n, err = tn.Read(got)
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, pkt, got[:n])
|
||||
}
|
||||
|
||||
// A heap allocation per packet rarely shows in a short throughput run, only across GC pauses, so
|
||||
// this pins Read and Write to zero allocations directly.
|
||||
func TestTun_ReadWriteDoNotAllocate(t *testing.T) {
|
||||
r, w, err := os.Pipe()
|
||||
require.NoError(t, err)
|
||||
defer r.Close()
|
||||
defer w.Close()
|
||||
tw := &tun{f: w}
|
||||
tr := &tun{f: r}
|
||||
|
||||
pkts := [][]byte{bytes.Repeat([]byte{0x45}, 1300), bytes.Repeat([]byte{0x60}, 1300)}
|
||||
buf := make([]byte, 1500)
|
||||
i := 0
|
||||
allocs := testing.AllocsPerRun(1000, func() {
|
||||
i++
|
||||
if _, err := tw.Write(pkts[i%len(pkts)]); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := tr.Read(buf); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
})
|
||||
require.Zero(t, allocs)
|
||||
}
|
||||
+13
-23
@@ -370,7 +370,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
t := &tun{
|
||||
Device: deviceName,
|
||||
vpnNetworks: vpnNetworks,
|
||||
MTU: getMTU(l, c),
|
||||
MTU: c.GetInt("tun.mtu", DefaultMTU),
|
||||
l: l,
|
||||
fd: fd,
|
||||
shutdownR: shutdownR,
|
||||
@@ -385,18 +385,16 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
},
|
||||
}
|
||||
|
||||
err = t.reload(c, true, nil)
|
||||
err = t.reload(c, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
closeOnErr = false
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.dev", "tun.mtu")
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -495,7 +493,7 @@ func (t *tun) Activate() error {
|
||||
}
|
||||
}
|
||||
|
||||
return t.addRoutes(false, nil)
|
||||
return t.addRoutes(false)
|
||||
}
|
||||
|
||||
func (t *tun) setMTU() error {
|
||||
@@ -511,8 +509,8 @@ func (t *tun) setMTU() error {
|
||||
return err
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -532,18 +530,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
|
||||
if !initial {
|
||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
|
||||
// Ensure any routes we actually want are installed
|
||||
err = t.addRoutes(true, r)
|
||||
err = t.addRoutes(true)
|
||||
if err != nil {
|
||||
// Catch any stray logs
|
||||
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -567,7 +563,7 @@ func (t *tun) Queues(int) ([]tio.Queue, error) {
|
||||
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
||||
}
|
||||
|
||||
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
func (t *tun) addRoutes(logErrors bool) error {
|
||||
routes := *t.Routes.Load()
|
||||
for _, r := range routes {
|
||||
if len(r.Via) == 0 || !r.Install {
|
||||
@@ -580,7 +576,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||
if logErrors {
|
||||
retErr.Log(t.l)
|
||||
rl.Failed()
|
||||
} else {
|
||||
return retErr
|
||||
}
|
||||
@@ -592,20 +587,15 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
func (t *tun) removeRoutes(routes []Route) error {
|
||||
for _, r := range routes {
|
||||
if len(r.Via) == 0 || !r.Install {
|
||||
// addRoutes never installs these
|
||||
if !r.Install {
|
||||
continue
|
||||
}
|
||||
|
||||
err := delRoute(r.Cidr, t.linkAddr)
|
||||
if errors.Is(err, unix.ESRCH) {
|
||||
// Already gone, which is what we wanted
|
||||
t.l.Info("Route was already removed", "route", r)
|
||||
} else if err != nil {
|
||||
if err != nil {
|
||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||
rl.Failed()
|
||||
} else {
|
||||
t.l.Info("Removed route", "route", r)
|
||||
}
|
||||
|
||||
+5
-6
@@ -47,17 +47,16 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
|
||||
l: l,
|
||||
}
|
||||
|
||||
err := t.reload(c, true, nil)
|
||||
err := t.reload(c, true)
|
||||
if err != nil {
|
||||
_ = file.Close()
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -68,8 +67,8 @@ func (t *tun) Activate() error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
+18
-41
@@ -185,10 +185,6 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, multiqueue
|
||||
}
|
||||
|
||||
t.Device = name
|
||||
// Only read when we create the device, an fd handed to us already has its name and offloads
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.dev", "tun.use_offloads")
|
||||
})
|
||||
|
||||
return t, nil
|
||||
}
|
||||
@@ -225,32 +221,30 @@ func newTunGeneric(c *config.C, l *slog.Logger, fd int, vnetHdr bool, offloadFla
|
||||
vnetHdr: vnetHdr,
|
||||
offloadFlags: offloadFlags,
|
||||
vpnNetworks: vpnNetworks,
|
||||
TXQueueLen: c.GetInt("tun.tx_queue", 5000),
|
||||
TXQueueLen: c.GetInt("tun.tx_queue", 500),
|
||||
useSystemRoutes: c.GetBool("tun.use_system_route_table", false),
|
||||
useSystemRoutesBufferSize: c.GetInt("tun.use_system_route_table_buffer_size", 0),
|
||||
routesFromSystem: map[netip.Prefix]routing.Gateways{},
|
||||
l: l,
|
||||
}
|
||||
|
||||
if err = t.reload(c, true, nil); err != nil {
|
||||
if err = t.reload(c, true); err != nil {
|
||||
_ = t.Close()
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.tx_queue", "tun.use_system_route_table", "tun.use_system_route_table_buffer_size")
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
return t, nil
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
routeChange, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
routeChange, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -259,15 +253,6 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// Only the mtu changed. The routes are the same, parse them again so the ones without their own mtu pick up the
|
||||
// new default. Without this an mtu change would remove them all
|
||||
if !routeChange {
|
||||
_, routes, err = getAllRoutesFromConfig(t.l, c, t.vpnNetworks, true)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
routeTree, err := makeRouteTree(t.l, routes, true)
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -282,14 +267,14 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
|
||||
oldDefaultMTU := t.DefaultMTU
|
||||
oldMaxMTU := t.MaxMTU
|
||||
newDefaultMTU := getMTU(t.l, c)
|
||||
newDefaultMTU := c.GetInt("tun.mtu", DefaultMTU)
|
||||
newMaxMTU := newDefaultMTU
|
||||
for i, r := range routes {
|
||||
if r.MTU == 0 {
|
||||
routes[i].MTU = newDefaultMTU
|
||||
}
|
||||
|
||||
if r.MTU > newMaxMTU {
|
||||
if r.MTU > t.MaxMTU {
|
||||
newMaxMTU = r.MTU
|
||||
}
|
||||
}
|
||||
@@ -303,7 +288,7 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
|
||||
if !initial {
|
||||
if oldMaxMTU != newMaxMTU {
|
||||
t.setMTU(r)
|
||||
t.setMTU()
|
||||
t.l.Info("Set max MTU", "mtu", t.MaxMTU, "oldMTU", oldMaxMTU)
|
||||
}
|
||||
|
||||
@@ -311,8 +296,7 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
for i := range t.vpnNetworks {
|
||||
err := t.setDefaultRoute(t.vpnNetworks[i])
|
||||
if err != nil {
|
||||
t.l.Error(err.Error())
|
||||
r.Failed()
|
||||
t.l.Warn(err.Error())
|
||||
} else {
|
||||
t.l.Info("Set default MTU", "mtu", t.DefaultMTU, "oldMTU", oldDefaultMTU)
|
||||
}
|
||||
@@ -320,14 +304,13 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
}
|
||||
|
||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||
t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
|
||||
t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
||||
|
||||
// Ensure any routes we actually want are installed
|
||||
err = t.addRoutes(true, r)
|
||||
err = t.addRoutes(true)
|
||||
if err != nil {
|
||||
// This should never be called since addRoutes should log its own errors in a reload condition
|
||||
util.LogWithContextIfNeeded("Failed to refresh routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -482,7 +465,7 @@ func (t *tun) Activate() error {
|
||||
t.deviceIndex = link.Attrs().Index
|
||||
|
||||
// Setup our default MTU
|
||||
t.setMTU(nil)
|
||||
t.setMTU()
|
||||
|
||||
// Set the transmit queue length
|
||||
ifrq := ifreqQLEN{Name: devName, Value: int32(t.TXQueueLen)}
|
||||
@@ -514,7 +497,7 @@ func (t *tun) Activate() error {
|
||||
}
|
||||
|
||||
// Set the routes
|
||||
if err = t.addRoutes(false, nil); err != nil {
|
||||
if err = t.addRoutes(false); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
@@ -527,13 +510,12 @@ func (t *tun) Activate() error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) setMTU(r *config.Reload) {
|
||||
func (t *tun) setMTU() {
|
||||
// Set the MTU on the device
|
||||
ifm := ifreqMTU{Name: t.deviceBytes(), MTU: int32(t.MaxMTU)}
|
||||
if err := ioctl(t.ioctlFd, unix.SIOCSIFMTU, uintptr(unsafe.Pointer(&ifm))); err != nil {
|
||||
// This is currently a non fatal condition because the route table must have the MTU set appropriately as well
|
||||
t.l.Error("Failed to set tun mtu", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -586,7 +568,7 @@ func (t *tun) setDefaultRoute(cidr netip.Prefix) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
func (t *tun) addRoutes(logErrors bool) error {
|
||||
// Path routes
|
||||
routes := *t.Routes.Load()
|
||||
for _, r := range routes {
|
||||
@@ -616,7 +598,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||
if logErrors {
|
||||
retErr.Log(t.l)
|
||||
rl.Failed()
|
||||
} else {
|
||||
return retErr
|
||||
}
|
||||
@@ -628,7 +609,7 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) {
|
||||
func (t *tun) removeRoutes(routes []Route) {
|
||||
for _, r := range routes {
|
||||
if !r.Install {
|
||||
continue
|
||||
@@ -652,12 +633,8 @@ func (t *tun) removeRoutes(routes []Route, rl *config.Reload) {
|
||||
}
|
||||
|
||||
err := netlink.RouteDel(&nr)
|
||||
if errors.Is(err, unix.ESRCH) {
|
||||
// Already gone, which is what we wanted
|
||||
t.l.Info("Route was already removed", "route", r)
|
||||
} else if err != nil {
|
||||
if err != nil {
|
||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||
rl.Failed()
|
||||
} else {
|
||||
t.l.Info("Removed route", "route", r)
|
||||
}
|
||||
|
||||
+27
-27
@@ -8,6 +8,7 @@ import (
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"os"
|
||||
"regexp"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
"unsafe"
|
||||
@@ -66,12 +67,24 @@ type tun struct {
|
||||
fd int
|
||||
}
|
||||
|
||||
var deviceNameRE = regexp.MustCompile(`^tun[0-9]+$`)
|
||||
|
||||
func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
|
||||
return nil, fmt.Errorf("newTunFromFd not supported in NetBSD")
|
||||
}
|
||||
|
||||
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
|
||||
fd, deviceName, err := openTun(l, c.GetString("tun.dev", ""))
|
||||
// Try to open tun device
|
||||
var err error
|
||||
deviceName := c.GetString("tun.dev", "")
|
||||
if deviceName == "" {
|
||||
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
|
||||
}
|
||||
if !deviceNameRE.MatchString(deviceName) {
|
||||
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
|
||||
}
|
||||
|
||||
fd, err := unix.Open("/dev/"+deviceName, os.O_RDWR, 0)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
@@ -86,24 +99,19 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
fd: fd,
|
||||
Device: deviceName,
|
||||
vpnNetworks: vpnNetworks,
|
||||
MTU: getMTU(l, c),
|
||||
MTU: c.GetInt("tun.mtu", DefaultMTU),
|
||||
l: l,
|
||||
}
|
||||
|
||||
err = t.reload(c, true, nil)
|
||||
err = t.reload(c, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.mtu")
|
||||
if tunDevNeedsRestart(c.GetString("tun.dev", ""), t.Device) {
|
||||
r.RestartRequiredIfChanged("tun.dev")
|
||||
}
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -316,7 +324,7 @@ func (t *tun) Activate() error {
|
||||
}
|
||||
}
|
||||
|
||||
return t.addRoutes(false, nil)
|
||||
return t.addRoutes(false)
|
||||
}
|
||||
|
||||
func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
||||
@@ -331,8 +339,8 @@ func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
||||
return err
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -352,18 +360,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
|
||||
if !initial {
|
||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
|
||||
// Ensure any routes we actually want are installed
|
||||
err = t.addRoutes(true, r)
|
||||
err = t.addRoutes(true)
|
||||
if err != nil {
|
||||
// Catch any stray logs
|
||||
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -387,7 +393,7 @@ func (t *tun) Queues(int) ([]tio.Queue, error) {
|
||||
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
||||
}
|
||||
|
||||
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
func (t *tun) addRoutes(logErrors bool) error {
|
||||
routes := *t.Routes.Load()
|
||||
|
||||
for _, r := range routes {
|
||||
@@ -401,7 +407,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||
if logErrors {
|
||||
retErr.Log(t.l)
|
||||
rl.Failed()
|
||||
} else {
|
||||
return retErr
|
||||
}
|
||||
@@ -413,20 +418,15 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
func (t *tun) removeRoutes(routes []Route) error {
|
||||
for _, r := range routes {
|
||||
if len(r.Via) == 0 || !r.Install {
|
||||
// addRoutes never installs these
|
||||
if !r.Install {
|
||||
continue
|
||||
}
|
||||
|
||||
err := delRoute(r.Cidr, t.vpnNetworks)
|
||||
if errors.Is(err, unix.ESRCH) {
|
||||
// Already gone, which is what we wanted
|
||||
t.l.Info("Route was already removed", "route", r)
|
||||
} else if err != nil {
|
||||
if err != nil {
|
||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||
rl.Failed()
|
||||
} else {
|
||||
t.l.Info("Removed route", "route", r)
|
||||
}
|
||||
|
||||
+27
-27
@@ -8,6 +8,7 @@ import (
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"os"
|
||||
"regexp"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
"unsafe"
|
||||
@@ -57,12 +58,24 @@ type tun struct {
|
||||
fd int
|
||||
}
|
||||
|
||||
var deviceNameRE = regexp.MustCompile(`^tun[0-9]+$`)
|
||||
|
||||
func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
|
||||
return nil, fmt.Errorf("newTunFromFd not supported in openbsd")
|
||||
}
|
||||
|
||||
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*tun, error) {
|
||||
fd, deviceName, err := openTun(l, c.GetString("tun.dev", ""))
|
||||
// Try to open tun device
|
||||
var err error
|
||||
deviceName := c.GetString("tun.dev", "")
|
||||
if deviceName == "" {
|
||||
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
|
||||
}
|
||||
if !deviceNameRE.MatchString(deviceName) {
|
||||
return nil, fmt.Errorf("a device name in the format of /dev/tunN must be specified")
|
||||
}
|
||||
|
||||
fd, err := unix.Open("/dev/"+deviceName, os.O_RDWR, 0)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
@@ -77,24 +90,19 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
fd: fd,
|
||||
Device: deviceName,
|
||||
vpnNetworks: vpnNetworks,
|
||||
MTU: getMTU(l, c),
|
||||
MTU: c.GetInt("tun.mtu", DefaultMTU),
|
||||
l: l,
|
||||
}
|
||||
|
||||
err = t.reload(c, true, nil)
|
||||
err = t.reload(c, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.mtu")
|
||||
if tunDevNeedsRestart(c.GetString("tun.dev", ""), t.Device) {
|
||||
r.RestartRequiredIfChanged("tun.dev")
|
||||
}
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -295,7 +303,7 @@ func (t *tun) Activate() error {
|
||||
}
|
||||
}
|
||||
|
||||
return t.addRoutes(false, nil)
|
||||
return t.addRoutes(false)
|
||||
}
|
||||
|
||||
func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
||||
@@ -310,8 +318,8 @@ func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
||||
return err
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -331,18 +339,16 @@ func (t *tun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
|
||||
if !initial {
|
||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes), r)
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
|
||||
// Ensure any routes we actually want are installed
|
||||
err = t.addRoutes(true, r)
|
||||
err = t.addRoutes(true)
|
||||
if err != nil {
|
||||
// Catch any stray logs
|
||||
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -366,7 +372,7 @@ func (t *tun) Queues(int) ([]tio.Queue, error) {
|
||||
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
||||
}
|
||||
|
||||
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
func (t *tun) addRoutes(logErrors bool) error {
|
||||
routes := *t.Routes.Load()
|
||||
|
||||
for _, r := range routes {
|
||||
@@ -380,7 +386,6 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||
if logErrors {
|
||||
retErr.Log(t.l)
|
||||
rl.Failed()
|
||||
} else {
|
||||
return retErr
|
||||
}
|
||||
@@ -392,20 +397,15 @@ func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
func (t *tun) removeRoutes(routes []Route) error {
|
||||
for _, r := range routes {
|
||||
if len(r.Via) == 0 || !r.Install {
|
||||
// addRoutes never installs these
|
||||
if !r.Install {
|
||||
continue
|
||||
}
|
||||
|
||||
err := delRoute(r.Cidr, t.vpnNetworks)
|
||||
if errors.Is(err, unix.ESRCH) {
|
||||
// Already gone, which is what we wanted
|
||||
t.l.Info("Route was already removed", "route", r)
|
||||
} else if err != nil {
|
||||
if err != nil {
|
||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||
rl.Failed()
|
||||
} else {
|
||||
t.l.Info("Removed route", "route", r)
|
||||
}
|
||||
|
||||
@@ -1,107 +0,0 @@
|
||||
//go:build !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"os"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/routing"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// Only tun.mtu changes. The system calls fail without a real device, what matters is the routes nebula keeps
|
||||
func TestReloadMTUOnlyKeepsRoutes(t *testing.T) {
|
||||
routes := " unsafe_routes:\n - route: 192.168.100.0/24\n via: 10.1.0.1\n"
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("tun:\n mtu: 1300\n"+routes))
|
||||
|
||||
tn := &tun{
|
||||
l: test.NewLogger(),
|
||||
vpnNetworks: []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")},
|
||||
ioctlFd: ^uintptr(0),
|
||||
routesFromSystem: map[netip.Prefix]routing.Gateways{},
|
||||
}
|
||||
require.NoError(t, tn.reload(c, true, nil))
|
||||
|
||||
require.NoError(t, c.ReloadConfigString("tun:\n mtu: 1400\n"+routes).Err)
|
||||
_ = tn.reload(c, false, nil)
|
||||
|
||||
got := *tn.Routes.Load()
|
||||
require.Len(t, got, 1)
|
||||
assert.Equal(t, netip.MustParsePrefix("192.168.100.0/24"), got[0].Cidr)
|
||||
assert.Equal(t, 1400, got[0].MTU)
|
||||
assert.Equal(t, 1400, tn.DefaultMTU)
|
||||
}
|
||||
|
||||
// The device mtu has to fit the largest route mtu, wherever it sits in the list
|
||||
func TestReloadMaxMTUIsTheLargestRoute(t *testing.T) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("tun:\n mtu: 1300\n unsafe_routes:\n"+
|
||||
" - route: 192.168.100.0/24\n via: 10.1.0.1\n mtu: 1500\n"+
|
||||
" - route: 192.168.101.0/24\n via: 10.1.0.1\n mtu: 1400\n"))
|
||||
|
||||
tn := &tun{
|
||||
l: test.NewLogger(),
|
||||
vpnNetworks: []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")},
|
||||
ioctlFd: ^uintptr(0),
|
||||
routesFromSystem: map[netip.Prefix]routing.Gateways{},
|
||||
}
|
||||
require.NoError(t, tn.reload(c, true, nil))
|
||||
assert.Equal(t, 1500, tn.MaxMTU)
|
||||
assert.Equal(t, 1300, tn.DefaultMTU)
|
||||
}
|
||||
|
||||
// There is no device behind this tun, so adding a route always fails. Removing one is refused without root, as root the
|
||||
// kernel answers that the route isn't there, which is what we wanted
|
||||
func TestReloadRouteFailures(t *testing.T) {
|
||||
route := "tun:\n mtu: 1300\n unsafe_routes:\n - route: 192.168.100.0/24\n via: 10.1.0.1\n"
|
||||
cases := []struct {
|
||||
name string
|
||||
from, to string
|
||||
wantFails bool
|
||||
}{
|
||||
{"added", "tun:\n mtu: 1300\n", route, true},
|
||||
{"removed", route, "tun:\n mtu: 1300\n", os.Geteuid() != 0},
|
||||
{"unchanged", route, route + "punchy:\n punch: true\n", false},
|
||||
}
|
||||
for _, tc := range cases {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString(tc.from))
|
||||
tn := &tun{
|
||||
l: test.NewLogger(),
|
||||
vpnNetworks: []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")},
|
||||
ioctlFd: ^uintptr(0),
|
||||
routesFromSystem: map[netip.Prefix]routing.Gateways{},
|
||||
}
|
||||
require.NoError(t, tn.reload(c, true, nil))
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
require.NoError(t, tn.reload(c, false, r))
|
||||
})
|
||||
|
||||
res := c.ReloadConfigString(tc.to)
|
||||
require.NoError(t, res.Err)
|
||||
assert.Equal(t, tc.wantFails, res.Failed)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Keys only read when the device is created need a restart to apply
|
||||
func TestTunReloadRestartKeys(t *testing.T) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("tun:\n dev: nebrk0\n"))
|
||||
tn, err := NewDeviceFromConfig(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, 1)
|
||||
if err != nil {
|
||||
t.Skipf("can't create a tun device here: %v", err)
|
||||
}
|
||||
t.Cleanup(func() { _ = tn.Close() })
|
||||
|
||||
res := c.ReloadConfigString("tun:\n disabled: true\n dev: nebrk1\n tx_queue: 100\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.ElementsMatch(t, []string{"tun.disabled", "tun.dev", "tun.tx_queue"}, res.RestartKeys)
|
||||
}
|
||||
@@ -1,451 +0,0 @@
|
||||
//go:build !ios && !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"net"
|
||||
"net/netip"
|
||||
"os"
|
||||
"strconv"
|
||||
"sync/atomic"
|
||||
"time"
|
||||
"unsafe"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/util"
|
||||
netroute "golang.org/x/net/route"
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// Darwin has no route metrics, the routing table holds one unscoped route per prefix. When another interface already
|
||||
// routes an unsafe_route's prefix, like the lan we started on, theirs stays and ours is added once theirs is removed.
|
||||
// Our own route removed by someone else, with nothing in its place, was removed on purpose and stays gone until a reload
|
||||
// or until another interface takes the prefix, after which ours follows theirs like any other.
|
||||
|
||||
const (
|
||||
// routeRetryDelay is how long the system routing table must be quiet before we judge who holds a prefix. configd
|
||||
// replaces a route by deleting and adding, looking in between would find the prefix free
|
||||
routeRetryDelay = time.Second
|
||||
|
||||
// routeSweepInterval bounds how long a freed unsafe_route can go unnoticed. The routing socket drops messages that
|
||||
// don't fit its receive buffer without telling the reader, and detaching an interface deletes its routes without
|
||||
// a message for each
|
||||
routeSweepInterval = time.Minute
|
||||
|
||||
// routeSocketRcvBuf is well past the 8KiB default, which a burst of neighbor routes expiring can fill
|
||||
routeSocketRcvBuf = 1 << 20
|
||||
)
|
||||
|
||||
type routeStateKind int
|
||||
|
||||
const (
|
||||
routeUnknown routeStateKind = iota
|
||||
// routeInstalled is our route holding the prefix
|
||||
routeInstalled
|
||||
// routeYielded is another interface holding the prefix, ours is added once it lets go
|
||||
routeYielded
|
||||
// routeRemoved is our route deleted by someone else with nothing in its place, it is left alone until a reload or
|
||||
// another interface takes the prefix
|
||||
routeRemoved
|
||||
// routeFailed is adding our route failing for some other reason, it is retried
|
||||
routeFailed
|
||||
)
|
||||
|
||||
type routeState struct {
|
||||
kind routeStateKind
|
||||
// holder is the index of the interface holding the prefix when kind is routeYielded
|
||||
holder int
|
||||
}
|
||||
|
||||
// routeMover is the process that last added, changed or deleted a route for an unsafe_route's prefix, for logs. Its name
|
||||
// is looked up as the message arrives, route(8) has exited by the time the table settles
|
||||
type routeMover struct {
|
||||
pid int32
|
||||
name string
|
||||
}
|
||||
|
||||
// logArgs appends m to a log line's args, when we know who it was
|
||||
func (m routeMover) logArgs(args ...any) []any {
|
||||
if m.pid == 0 {
|
||||
return args
|
||||
}
|
||||
args = append(args, "pid", m.pid)
|
||||
if m.name != "" {
|
||||
args = append(args, "process", m.name)
|
||||
}
|
||||
return args
|
||||
}
|
||||
|
||||
// processName is the name of process pid, truncated to 16 bytes, or empty when it has already exited
|
||||
func processName(pid int32) string {
|
||||
kp, err := unix.SysctlKinfoProc("kern.proc.pid", int(pid))
|
||||
if err != nil || kp.Proc.P_pid != pid {
|
||||
return ""
|
||||
}
|
||||
return unix.ByteSliceToString(kp.Proc.P_comm[:])
|
||||
}
|
||||
|
||||
// installRoutes returns the routes we put in the system routing table, one per prefix
|
||||
func installRoutes(routes []Route) []Route {
|
||||
seen := make(map[netip.Prefix]struct{}, len(routes))
|
||||
var out []Route
|
||||
for _, r := range routes {
|
||||
if len(r.Via) == 0 || !r.Install {
|
||||
// We don't allow route MTUs so only install routes with a via
|
||||
continue
|
||||
}
|
||||
p := r.Cidr.Masked()
|
||||
if _, ok := seen[p]; ok {
|
||||
continue
|
||||
}
|
||||
seen[p] = struct{}{}
|
||||
out = append(out, r)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// addRoutes puts every unsafe_route in the system routing table, including ones someone deleted, unless another
|
||||
// interface holds its prefix. It runs on start and on every reload.
|
||||
func (t *tun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
// The route tree is still ours, the system routing table is not
|
||||
if t.hostOwned {
|
||||
return nil
|
||||
}
|
||||
|
||||
t.routesMu.Lock()
|
||||
defer t.routesMu.Unlock()
|
||||
|
||||
// Activate hasn't run yet, it will install the routes
|
||||
linkAddr := t.linkAddr.Load()
|
||||
if linkAddr == nil || t.closed {
|
||||
return nil
|
||||
}
|
||||
|
||||
var msgs []netroute.Message
|
||||
var msgsErr error
|
||||
fetched := false
|
||||
states := make(map[netip.Prefix]routeState)
|
||||
for _, r := range installRoutes(*t.Routes.Load()) {
|
||||
p := r.Cidr.Masked()
|
||||
prev := t.routeStates[p]
|
||||
|
||||
err := addRoute(p, linkAddr)
|
||||
if err == nil {
|
||||
t.l.Info("Added route", "route", r)
|
||||
states[p] = routeState{kind: routeInstalled}
|
||||
continue
|
||||
}
|
||||
|
||||
if !errors.Is(err, unix.EEXIST) {
|
||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||
if !logErrors {
|
||||
return retErr
|
||||
}
|
||||
retErr.Log(t.l)
|
||||
rl.Failed()
|
||||
states[p] = routeState{kind: routeFailed}
|
||||
continue
|
||||
}
|
||||
|
||||
// Every route we added already exists on a reload, only warn about someone else's
|
||||
if !fetched {
|
||||
msgs, msgsErr = fetchRoutes()
|
||||
fetched = true
|
||||
}
|
||||
if msgsErr != nil {
|
||||
t.l.Warn("unable to add unsafe_route, a route already exists but its interface could not be determined", "route", r.Cidr, "error", msgsErr)
|
||||
states[p] = prev
|
||||
continue
|
||||
}
|
||||
|
||||
switch holder := routeInterfaceIn(msgs, p); holder {
|
||||
case linkAddr.Index:
|
||||
states[p] = routeState{kind: routeInstalled}
|
||||
case 0:
|
||||
// Removed since the add, the watcher will see to it
|
||||
states[p] = prev
|
||||
default:
|
||||
if prev.kind != routeYielded || prev.holder != holder {
|
||||
t.l.Warn("unable to add unsafe_route, the destination is already routed through another interface, it will be added once that route is removed", "route", r.Cidr, "interface", interfaceName(holder))
|
||||
}
|
||||
states[p] = routeState{kind: routeYielded, holder: holder}
|
||||
}
|
||||
}
|
||||
|
||||
t.routeStates = states
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *tun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
if t.hostOwned {
|
||||
return nil
|
||||
}
|
||||
|
||||
t.routesMu.Lock()
|
||||
defer t.routesMu.Unlock()
|
||||
|
||||
linkAddr := t.linkAddr.Load()
|
||||
if linkAddr == nil || t.closed {
|
||||
return nil
|
||||
}
|
||||
|
||||
// The kernel deletes a route by its prefix alone, whichever interface holds it. Only delete the ones that are ours
|
||||
msgs, err := fetchRoutes()
|
||||
if err != nil {
|
||||
var left []netip.Prefix
|
||||
for _, r := range installRoutes(routes) {
|
||||
left = append(left, r.Cidr)
|
||||
}
|
||||
return fmt.Errorf("failed to read the system routing table, leaving routes %v installed: %w", left, err)
|
||||
}
|
||||
|
||||
for _, r := range installRoutes(routes) {
|
||||
p := r.Cidr.Masked()
|
||||
// Whatever happens next, the prefix is no longer one we know about
|
||||
delete(t.routeStates, p)
|
||||
if routeInterfaceIn(msgs, p) != linkAddr.Index {
|
||||
continue
|
||||
}
|
||||
|
||||
err = delRoute(p, linkAddr)
|
||||
if errors.Is(err, unix.ESRCH) {
|
||||
// Already gone, which is what we wanted
|
||||
t.l.Info("Route was already removed", "route", r)
|
||||
} else if err != nil {
|
||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||
rl.Failed()
|
||||
} else {
|
||||
t.l.Info("Removed route", "route", r)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// reconcileRoutes brings the unsafe_routes in line with who holds their prefix now. It is quiet unless something
|
||||
// changed since it last looked, it runs every routeSweepEvery.
|
||||
func (t *tun) reconcileRoutes() {
|
||||
t.routesMu.Lock()
|
||||
defer t.routesMu.Unlock()
|
||||
|
||||
linkAddr := t.linkAddr.Load()
|
||||
if linkAddr == nil || t.closed {
|
||||
return
|
||||
}
|
||||
|
||||
t.routeMoversMu.Lock()
|
||||
movers := t.routeMovers
|
||||
t.routeMovers = nil
|
||||
t.routeMoversMu.Unlock()
|
||||
|
||||
msgs, err := fetchRoutes()
|
||||
if err != nil {
|
||||
t.l.Error("Failed to read the system routing table", "error", err)
|
||||
return
|
||||
}
|
||||
|
||||
states := make(map[netip.Prefix]routeState)
|
||||
for _, r := range installRoutes(*t.Routes.Load()) {
|
||||
p := r.Cidr.Masked()
|
||||
prev := t.routeStates[p]
|
||||
by := movers[p]
|
||||
|
||||
holder := routeInterfaceIn(msgs, p)
|
||||
switch {
|
||||
case holder == linkAddr.Index:
|
||||
states[p] = routeState{kind: routeInstalled}
|
||||
|
||||
case holder != 0:
|
||||
// Another interface taking a prefix we left alone puts ours back in line behind theirs
|
||||
if prev.kind != routeYielded || prev.holder != holder {
|
||||
t.l.Info("unsafe_route is routed through another interface, it will be added back when that route is removed", by.logArgs("route", r.Cidr, "interface", interfaceName(holder))...)
|
||||
}
|
||||
states[p] = routeState{kind: routeYielded, holder: holder}
|
||||
|
||||
case prev.kind == routeInstalled:
|
||||
t.l.Warn("unsafe_route was removed outside nebula, leaving it until a reload or another interface takes its destination", by.logArgs("route", r.Cidr)...)
|
||||
states[p] = routeState{kind: routeRemoved}
|
||||
|
||||
case prev.kind == routeRemoved:
|
||||
states[p] = prev
|
||||
|
||||
default:
|
||||
err := addRoute(p, linkAddr)
|
||||
switch {
|
||||
case err == nil:
|
||||
if prev.kind == routeYielded {
|
||||
t.l.Info("unsafe_route's destination is free again, added it", by.logArgs("route", r)...)
|
||||
} else {
|
||||
t.l.Info("Added route", "route", r)
|
||||
}
|
||||
states[p] = routeState{kind: routeInstalled}
|
||||
case errors.Is(err, unix.EEXIST):
|
||||
// Taken since the fetch, the next look will see by whom
|
||||
states[p] = prev
|
||||
default:
|
||||
if prev.kind != routeFailed {
|
||||
util.NewContextualError("Failed to add route", map[string]any{"route": r}, err).Log(t.l)
|
||||
}
|
||||
states[p] = routeState{kind: routeFailed}
|
||||
}
|
||||
}
|
||||
}
|
||||
t.routeStates = states
|
||||
}
|
||||
|
||||
// startRouteWatch starts reconciling the unsafe_routes, every routeSweepEvery and, when watch isn't nil, once the
|
||||
// routing table settles after anything that may have moved a prefix
|
||||
func (t *tun) startRouteWatch(watch *os.File) {
|
||||
t.routesMu.Lock()
|
||||
defer t.routesMu.Unlock()
|
||||
if t.closed {
|
||||
if watch != nil {
|
||||
_ = watch.Close()
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
t.routeSweep = time.AfterFunc(t.routeSweepEvery, t.sweepRoutes)
|
||||
if watch != nil {
|
||||
t.routeWatch = watch
|
||||
go t.watchRoutes(watch)
|
||||
}
|
||||
}
|
||||
|
||||
func (t *tun) sweepRoutes() {
|
||||
// A table still changing gets reconciled once it settles
|
||||
if time.Since(time.Unix(0, t.lastRouteEvent.Load())) >= routeRetryDelay {
|
||||
t.reconcileRoutes()
|
||||
}
|
||||
|
||||
t.routesMu.Lock()
|
||||
defer t.routesMu.Unlock()
|
||||
if !t.closed {
|
||||
t.routeSweep.Reset(t.routeSweepEvery)
|
||||
}
|
||||
}
|
||||
|
||||
func openRouteSocket() (*os.File, error) {
|
||||
fd, err := unix.Socket(unix.AF_ROUTE, unix.SOCK_RAW, unix.AF_UNSPEC)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("unable to create AF_ROUTE socket: %w", err)
|
||||
}
|
||||
// Fewer drops, the sweep catches the rest
|
||||
_ = unix.SetsockoptInt(fd, unix.SOL_SOCKET, unix.SO_RCVBUF, routeSocketRcvBuf)
|
||||
// Non-blocking puts it on the poller, so Close interrupts a Read
|
||||
if err = unix.SetNonblock(fd, true); err != nil {
|
||||
_ = unix.Close(fd)
|
||||
return nil, fmt.Errorf("failed to set the AF_ROUTE socket to non-blocking mode: %w", err)
|
||||
}
|
||||
return os.NewFile(uintptr(fd), "route"), nil
|
||||
}
|
||||
|
||||
// watchRoutes reconciles the unsafe_routes once the routing table has been quiet for routeRetryDelay after a message
|
||||
// that may have moved a prefix. A table that keeps changing is reconciled every routeSweepEvery regardless.
|
||||
func (t *tun) watchRoutes(f *os.File) {
|
||||
var reconciled atomic.Int64
|
||||
settle := time.AfterFunc(time.Hour, func() {
|
||||
reconciled.Store(time.Now().UnixNano())
|
||||
t.reconcileRoutes()
|
||||
})
|
||||
settle.Stop()
|
||||
defer settle.Stop()
|
||||
|
||||
var burst time.Time
|
||||
self := int32(os.Getpid())
|
||||
b := make([]byte, os.Getpagesize())
|
||||
for {
|
||||
n, err := f.Read(b)
|
||||
if err != nil {
|
||||
if !errors.Is(err, os.ErrClosed) {
|
||||
t.l.Error("Stopped watching the system routing table, unsafe_routes held by another interface are only retried every minute", "error", err)
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
moved, p, pid := routesMayHaveMoved(b[:n], *t.Routes.Load())
|
||||
if !moved {
|
||||
continue
|
||||
}
|
||||
// Our own are already in routeStates
|
||||
if p.IsValid() && pid != self {
|
||||
t.routeMoversMu.Lock()
|
||||
if t.routeMovers == nil {
|
||||
t.routeMovers = make(map[netip.Prefix]routeMover)
|
||||
}
|
||||
t.routeMovers[p] = routeMover{pid: pid, name: processName(pid)}
|
||||
t.routeMoversMu.Unlock()
|
||||
}
|
||||
|
||||
now := time.Now()
|
||||
t.lastRouteEvent.Store(now.UnixNano())
|
||||
if burst.IsZero() || reconciled.Load() >= burst.UnixNano() {
|
||||
burst = now
|
||||
}
|
||||
settle.Reset(max(0, min(routeRetryDelay, time.Until(burst.Add(t.routeSweepEvery)))))
|
||||
}
|
||||
}
|
||||
|
||||
// routesMayHaveMoved reports whether b, one routing socket message, may have freed a prefix one of routes installs or
|
||||
// handed it to another interface. That's a route for it added, changed or removed, or an interface that lost an address
|
||||
// or changed state, since detaching an interface deletes its routes without a message of their own. The header is read
|
||||
// directly, x/net/route skips the RTM_IFINFO the socket sends, which has no interface address, and misreads the
|
||||
// unpadded sockaddrs in messages the kernel makes itself. A request naming one of the prefixes also returns that prefix
|
||||
// and the pid of the process that made it.
|
||||
func routesMayHaveMoved(b []byte, routes []Route) (moved bool, p netip.Prefix, pid int32) {
|
||||
if len(b) < 4 {
|
||||
return false, p, 0
|
||||
}
|
||||
switch int(b[3]) {
|
||||
case unix.RTM_IFINFO, unix.RTM_DELADDR:
|
||||
return true, p, 0
|
||||
case unix.RTM_ADD, unix.RTM_CHANGE, unix.RTM_DELETE:
|
||||
default:
|
||||
return false, p, 0
|
||||
}
|
||||
|
||||
if len(b) < unix.SizeofRtMsghdr {
|
||||
return false, p, 0
|
||||
}
|
||||
hdr := (*unix.RtMsghdr)(unsafe.Pointer(&b[0]))
|
||||
// A failed request is reported too, and a scoped route never held the prefix
|
||||
if hdr.Errno != 0 || hdr.Flags&unix.RTF_IFSCOPE != 0 {
|
||||
return false, p, 0
|
||||
}
|
||||
|
||||
if hdr.Pid == 0 {
|
||||
// The kernel's own, which x/net/route can't parse. Neighbors coming and going are host routes, anything else
|
||||
// could be holding a prefix
|
||||
return hdr.Flags&(unix.RTF_HOST|unix.RTF_LLINFO) == 0, p, 0
|
||||
}
|
||||
|
||||
// Replies to a request carry the requester's padded sockaddrs
|
||||
msgs, err := netroute.ParseRIB(unix.NET_RT_DUMP, b)
|
||||
if err != nil || len(msgs) != 1 {
|
||||
return false, p, 0
|
||||
}
|
||||
m, ok := msgs[0].(*netroute.RouteMessage)
|
||||
if !ok || len(m.Addrs) <= unix.RTAX_NETMASK {
|
||||
return false, p, 0
|
||||
}
|
||||
p, ok = routePrefix(m.Addrs[unix.RTAX_DST], m.Addrs[unix.RTAX_NETMASK])
|
||||
if !ok {
|
||||
return false, netip.Prefix{}, 0
|
||||
}
|
||||
p = p.Masked()
|
||||
for _, r := range installRoutes(routes) {
|
||||
if r.Cidr.Masked() == p {
|
||||
return true, p, hdr.Pid
|
||||
}
|
||||
}
|
||||
return false, netip.Prefix{}, 0
|
||||
}
|
||||
|
||||
// interfaceName is the name of the interface with index i, for logs
|
||||
func interfaceName(i int) string {
|
||||
if ifc, err := net.InterfaceByIndex(i); err == nil {
|
||||
return ifc.Name
|
||||
}
|
||||
return strconv.Itoa(i)
|
||||
}
|
||||
@@ -1,24 +0,0 @@
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// tun.disabled and the disabled tun's settings are only read when the device is made
|
||||
func TestDisabledTunRestartKeys(t *testing.T) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("tun:\n disabled: true\n"))
|
||||
d, err := NewDeviceFromConfig(c, test.NewLogger(), []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, 1)
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() { _ = d.Close() })
|
||||
|
||||
res := c.ReloadConfigString("tun:\n disabled: false\n tx_queue: 100\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.ElementsMatch(t, []string{"tun.disabled", "tun.tx_queue"}, res.RestartKeys)
|
||||
}
|
||||
@@ -31,7 +31,7 @@ type TestTun struct {
|
||||
}
|
||||
|
||||
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*TestTun, error) {
|
||||
_, routes, err := getAllRoutesFromConfig(l, c, vpnNetworks, true)
|
||||
_, routes, err := getAllRoutesFromConfig(c, vpnNetworks, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
+15
-107
@@ -4,7 +4,6 @@ package overlay
|
||||
|
||||
import (
|
||||
"crypto"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
@@ -76,7 +75,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*w
|
||||
t := &winTun{
|
||||
Device: deviceName,
|
||||
vpnNetworks: vpnNetworks,
|
||||
MTU: getMTU(l, c),
|
||||
MTU: c.GetInt("tun.mtu", DefaultMTU),
|
||||
guid: *guid,
|
||||
networkCategory: cat,
|
||||
setCategory: setCat,
|
||||
@@ -84,7 +83,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*w
|
||||
l: l,
|
||||
}
|
||||
|
||||
err = t.reload(c, true, nil)
|
||||
err = t.reload(c, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
@@ -105,32 +104,18 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*w
|
||||
}
|
||||
t.tun = tunDevice.(*wintun.NativeTun)
|
||||
|
||||
// Disable registration before Activate assigns addresses and triggers it.
|
||||
disableDNSRegistration(l, *guid)
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("tun.dev", "tun.mtu")
|
||||
// Compare with the running category, not the last config. A restart with one we can't parse would fail, so say
|
||||
// that now rather than ask for one, and going back to the running one after a bad reload needs no restart
|
||||
if cat, setCat, err := parseNetworkCategory(c.GetString("tun.network_category", "private")); err != nil {
|
||||
t.l.Error("Invalid tun.network_category, a restart with it would fail", "error", err)
|
||||
r.Failed()
|
||||
} else if cat != t.networkCategory || setCat != t.setCategory {
|
||||
r.RestartRequiredIfChanged("tun.network_category")
|
||||
}
|
||||
r.RestartRequiredIfChanged(interfaceBypassKeys...)
|
||||
err := t.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
return t, nil
|
||||
}
|
||||
|
||||
func (t *winTun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
func (t *winTun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -150,18 +135,16 @@ func (t *winTun) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
|
||||
if !initial {
|
||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||
err := t.removeRoutes(findRemovedSystemRoutes(routes, *oldRoutes), r)
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
|
||||
// Ensure any routes we actually want are installed
|
||||
err = t.addRoutes(true, r)
|
||||
err = t.addRoutes(true)
|
||||
if err != nil {
|
||||
// Catch any stray logs
|
||||
util.LogWithContextIfNeeded("Failed to add routes", err, t.l)
|
||||
r.Failed()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -176,7 +159,7 @@ func (t *winTun) Activate() error {
|
||||
return fmt.Errorf("failed to set address: %w", err)
|
||||
}
|
||||
|
||||
err = t.addRoutes(false, nil)
|
||||
err = t.addRoutes(false)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -195,49 +178,33 @@ func (t *winTun) Activate() error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *winTun) addRoutes(logErrors bool, rl *config.Reload) error {
|
||||
func (t *winTun) addRoutes(logErrors bool) error {
|
||||
luid := winipcfg.LUID(t.tun.LUID())
|
||||
routes := *t.Routes.Load()
|
||||
foundDefault4 := false
|
||||
carriesV6 := slices.ContainsFunc(t.vpnNetworks, func(p netip.Prefix) bool { return p.Addr().Is6() })
|
||||
|
||||
// A CIDR listed twice routes by its last entry, install only that one or each reload would flip between them. The
|
||||
// same rule as systemRoutes
|
||||
last := make(map[netip.Prefix]int, len(routes))
|
||||
for i, r := range routes {
|
||||
last[r.Cidr] = i
|
||||
}
|
||||
|
||||
for i, r := range routes {
|
||||
for _, r := range routes {
|
||||
if len(r.Via) == 0 || !r.Install {
|
||||
// We don't allow route MTUs so only install routes with a via
|
||||
continue
|
||||
}
|
||||
if last[r.Cidr] != i {
|
||||
continue
|
||||
}
|
||||
|
||||
// A v6 unsafe_route is legal under a v4-only cert; uninstalled ones put nothing on the adapter.
|
||||
carriesV6 = carriesV6 || r.Cidr.Addr().Is6()
|
||||
|
||||
// Add our unsafe route as an on-link route to the nebula tun device.
|
||||
result, err := addRoute(luid, r)
|
||||
err := luid.AddRoute(r.Cidr, unspecifiedNextHop(r.Cidr), uint32(r.Metric))
|
||||
if err != nil {
|
||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||
if logErrors {
|
||||
retErr.Log(t.l)
|
||||
rl.Failed()
|
||||
continue
|
||||
} else {
|
||||
return retErr
|
||||
}
|
||||
} else {
|
||||
switch result {
|
||||
case routeAdded:
|
||||
t.l.Info("Added route", "route", r)
|
||||
case routeMetricUpdated:
|
||||
t.l.Info("Updated route metric", "route", r)
|
||||
}
|
||||
t.l.Info("Added route", "route", r)
|
||||
}
|
||||
|
||||
if !foundDefault4 {
|
||||
@@ -288,7 +255,7 @@ func (t *winTun) setMTU(luid winipcfg.LUID, foundDefault4, carriesV6 bool) error
|
||||
return nil
|
||||
}
|
||||
|
||||
func (t *winTun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
func (t *winTun) removeRoutes(routes []Route) error {
|
||||
luid := winipcfg.LUID(t.tun.LUID())
|
||||
|
||||
for _, r := range routes {
|
||||
@@ -298,12 +265,8 @@ func (t *winTun) removeRoutes(routes []Route, rl *config.Reload) error {
|
||||
|
||||
// See comment on luid.AddRoute
|
||||
err := luid.DeleteRoute(r.Cidr, unspecifiedNextHop(r.Cidr))
|
||||
if errors.Is(err, windows.ERROR_NOT_FOUND) {
|
||||
// Already gone, which is what we wanted
|
||||
t.l.Info("Route was already removed", "route", r)
|
||||
} else if err != nil {
|
||||
if err != nil {
|
||||
t.l.Error("Failed to remove route", "error", err, "route", r)
|
||||
rl.Failed()
|
||||
} else {
|
||||
t.l.Info("Removed route", "route", r)
|
||||
}
|
||||
@@ -353,61 +316,6 @@ func (t *winTun) Close() error {
|
||||
return t.tun.Close()
|
||||
}
|
||||
|
||||
// systemRoutes maps each CIDR to the route that puts it in the system table. A CIDR's last entry decides, including
|
||||
// one that says not to install it
|
||||
func systemRoutes(routes []Route) map[netip.Prefix]Route {
|
||||
out := make(map[netip.Prefix]Route, len(routes))
|
||||
for _, r := range routes {
|
||||
if len(r.Via) > 0 && r.Install {
|
||||
out[r.Cidr] = r
|
||||
} else {
|
||||
delete(out, r.Cidr)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// findRemovedSystemRoutes is the routes to delete from the system table. Windows deletes by destination and next hop,
|
||||
// so only a CIDR nothing installs anymore goes, a changed metric is set on the route in place by addRoute
|
||||
func findRemovedSystemRoutes(newRoutes, oldRoutes []Route) []Route {
|
||||
keep := systemRoutes(newRoutes)
|
||||
var removed []Route
|
||||
for _, r := range systemRoutes(oldRoutes) {
|
||||
if _, ok := keep[r.Cidr]; !ok {
|
||||
removed = append(removed, r)
|
||||
}
|
||||
}
|
||||
return removed
|
||||
}
|
||||
|
||||
type routeResult int
|
||||
|
||||
const (
|
||||
routeAdded routeResult = iota
|
||||
routeMetricUpdated
|
||||
routeAlreadyInstalled
|
||||
)
|
||||
|
||||
// addRoute installs r on the interface. A reload re-adds every route to catch any the system dropped, and Windows
|
||||
// refuses one it has with the same destination and next hop whatever its metric. One that is there with another
|
||||
// metric, ours from before a metric change or someone else's, is brought to ours in place
|
||||
func addRoute(luid winipcfg.LUID, r Route) (routeResult, error) {
|
||||
nextHop := unspecifiedNextHop(r.Cidr)
|
||||
err := luid.AddRoute(r.Cidr, nextHop, uint32(r.Metric))
|
||||
if !errors.Is(err, windows.ERROR_OBJECT_ALREADY_EXISTS) {
|
||||
return routeAdded, err
|
||||
}
|
||||
row, err := luid.Route(r.Cidr, nextHop)
|
||||
if err != nil {
|
||||
return routeAlreadyInstalled, err
|
||||
}
|
||||
if row.Metric != uint32(r.Metric) {
|
||||
row.Metric = uint32(r.Metric)
|
||||
return routeMetricUpdated, row.Set()
|
||||
}
|
||||
return routeAlreadyInstalled, nil
|
||||
}
|
||||
|
||||
func unspecifiedNextHop(p netip.Prefix) netip.Addr {
|
||||
if p.Addr().Is4() {
|
||||
return netip.IPv4Unspecified()
|
||||
|
||||
@@ -1,209 +0,0 @@
|
||||
//go:build windows && !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"net/netip"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
"golang.org/x/sys/windows"
|
||||
"golang.zx2c4.com/wireguard/windows/tunnel/winipcfg"
|
||||
)
|
||||
|
||||
type routeTest struct {
|
||||
c *config.C
|
||||
tun *winTun
|
||||
luid winipcfg.LUID
|
||||
log *bytes.Buffer
|
||||
}
|
||||
|
||||
// newRouteTest makes a wintun device of its own, before installing tun.unsafe_routes from cfg
|
||||
func newRouteTest(t *testing.T, cfg string) *routeTest {
|
||||
t.Helper()
|
||||
if !windows.GetCurrentProcessToken().IsElevated() {
|
||||
t.Skip("creating a wintun device needs an elevated process")
|
||||
}
|
||||
if err := checkWinTunExists(); err != nil {
|
||||
t.Skipf("wintun.dll is not where nebula looks for it: %v", err)
|
||||
}
|
||||
rt := &routeTest{log: &bytes.Buffer{}}
|
||||
l := test.NewLoggerWithOutput(rt.log)
|
||||
rt.c = config.NewC(l)
|
||||
require.NoError(t, rt.c.LoadString(cfg))
|
||||
var err error
|
||||
rt.tun, err = newTun(rt.c, l, []netip.Prefix{netip.MustParsePrefix("10.250.0.1/24")}, false)
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() { _ = rt.tun.Close() })
|
||||
rt.luid = winipcfg.LUID(rt.tun.tun.LUID())
|
||||
return rt
|
||||
}
|
||||
|
||||
func (rt *routeTest) metric(t *testing.T, cidr string) uint32 {
|
||||
t.Helper()
|
||||
p := netip.MustParsePrefix(cidr)
|
||||
row, err := rt.luid.Route(p, unspecifiedNextHop(p))
|
||||
require.NoError(t, err)
|
||||
return row.Metric
|
||||
}
|
||||
|
||||
// reload applies cfg and expects nothing in it to fail
|
||||
func (rt *routeTest) reload(t *testing.T, cfg string) {
|
||||
t.Helper()
|
||||
res := rt.c.ReloadConfigString(cfg)
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed, "the reload reported a failure")
|
||||
}
|
||||
|
||||
func unsafeRoutes(routes ...string) string {
|
||||
var b strings.Builder
|
||||
b.WriteString("tun:\n dev: nebroutetest\n unsafe_routes:\n")
|
||||
// cidr[@metric][!], the ! for install: false
|
||||
for _, r := range routes {
|
||||
r, noInstall := strings.CutSuffix(r, "!")
|
||||
cidr, metric, _ := strings.Cut(r, "@")
|
||||
fmt.Fprintf(&b, " - route: %s\n via: 10.250.0.2\n", cidr)
|
||||
if metric != "" {
|
||||
fmt.Fprintf(&b, " metric: %s\n", metric)
|
||||
}
|
||||
if noInstall {
|
||||
b.WriteString(" install: false\n")
|
||||
}
|
||||
}
|
||||
return b.String()
|
||||
}
|
||||
|
||||
// A reload that adds a route re-adds the ones already installed, Windows refusing those as already there isn't a failure
|
||||
func TestWinTun_ReloadKeepsInstalledRoutes(t *testing.T) {
|
||||
forFamilies(t, func(t *testing.T, a, b string) {
|
||||
rt := newRouteTest(t, unsafeRoutes(a))
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
|
||||
rt.reload(t, unsafeRoutes(a, b))
|
||||
assert.NotContains(t, rt.log.String(), "Failed to add route")
|
||||
rt.metric(t, a)
|
||||
rt.metric(t, b)
|
||||
})
|
||||
}
|
||||
|
||||
// Windows calls a route the same by destination and next hop, so a changed metric is set on the installed route in
|
||||
// place rather than deleted and added, which would leave a moment with no route
|
||||
func TestWinTun_ReloadMetricChangeApplies(t *testing.T) {
|
||||
forFamilies(t, func(t *testing.T, a, b string) {
|
||||
rt := newRouteTest(t, unsafeRoutes(a+"@100"))
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
require.Equal(t, uint32(100), rt.metric(t, a))
|
||||
|
||||
rt.reload(t, unsafeRoutes(a+"@200"))
|
||||
assert.NotContains(t, rt.log.String(), "Failed to add route")
|
||||
assert.NotContains(t, rt.log.String(), "Removed route")
|
||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||
})
|
||||
}
|
||||
|
||||
// A route someone else put on the device with another metric is brought to ours, at startup too
|
||||
func TestWinTun_ForeignRouteGetsOurMetric(t *testing.T) {
|
||||
forFamilies(t, func(t *testing.T, a, b string) {
|
||||
rt := newRouteTest(t, unsafeRoutes(a+"@100"))
|
||||
p := netip.MustParsePrefix(a)
|
||||
require.NoError(t, rt.luid.AddRoute(p, unspecifiedNextHop(p), 50))
|
||||
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
assert.Equal(t, uint32(100), rt.metric(t, a))
|
||||
assert.Contains(t, rt.log.String(), "level=INFO msg=\"Updated route metric\"")
|
||||
})
|
||||
}
|
||||
|
||||
// A CIDR listed twice is installed once, by its last entry, and reloads leave it there instead of flipping between the
|
||||
// two metrics
|
||||
func TestWinTun_DuplicateCidrInstallsTheLastEntry(t *testing.T) {
|
||||
forFamilies(t, func(t *testing.T, a, b string) {
|
||||
rt := newRouteTest(t, unsafeRoutes(a+"@100", a+"@200"))
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||
|
||||
rt.reload(t, unsafeRoutes(a+"@100", a+"@200", b))
|
||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||
assert.NotContains(t, rt.log.String(), "Updated route metric")
|
||||
assert.NotContains(t, rt.log.String(), "Failed to add route")
|
||||
})
|
||||
}
|
||||
|
||||
// Dropping the duplicate that wasn't installed leaves the installed route alone. Windows deletes by destination and
|
||||
// next hop, deleting the dropped one would take the live route with it
|
||||
func TestWinTun_DroppingAnUninstalledDuplicateKeepsTheRoute(t *testing.T) {
|
||||
forFamilies(t, func(t *testing.T, a, b string) {
|
||||
rt := newRouteTest(t, unsafeRoutes(a+"@100", a+"@200"))
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
|
||||
rt.reload(t, unsafeRoutes(a+"@200"))
|
||||
assert.NotContains(t, rt.log.String(), "Removed route")
|
||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||
})
|
||||
}
|
||||
|
||||
// A reload ends where a fresh start with the same config would, a CIDR whose last entry says not to install it is
|
||||
// removed
|
||||
func TestWinTun_ReloadMatchesAFreshStart(t *testing.T) {
|
||||
forFamilies(t, func(t *testing.T, a, b string) {
|
||||
cidr := netip.MustParsePrefix(a)
|
||||
routes := unsafeRoutes(a+"@100", a+"@100!")
|
||||
|
||||
fresh := newRouteTest(t, routes)
|
||||
require.NoError(t, fresh.tun.Activate())
|
||||
_, err := fresh.luid.Route(cidr, unspecifiedNextHop(cidr))
|
||||
require.Error(t, err, "a fresh start installed it")
|
||||
require.NoError(t, fresh.tun.Close())
|
||||
|
||||
rt := newRouteTest(t, unsafeRoutes(a+"@100"))
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
rt.reload(t, routes)
|
||||
_, err = rt.luid.Route(cidr, unspecifiedNextHop(cidr))
|
||||
assert.Error(t, err, "the reload left it installed")
|
||||
})
|
||||
}
|
||||
|
||||
// Removing a route that is already gone is what we wanted, not a failure
|
||||
func TestWinTun_ReloadRouteAlreadyGone(t *testing.T) {
|
||||
forFamilies(t, func(t *testing.T, a, b string) {
|
||||
rt := newRouteTest(t, unsafeRoutes(a, b))
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
p := netip.MustParsePrefix(b)
|
||||
require.NoError(t, rt.luid.DeleteRoute(p, unspecifiedNextHop(p)))
|
||||
|
||||
rt.reload(t, unsafeRoutes(a))
|
||||
})
|
||||
}
|
||||
|
||||
// A network category we can't parse would fail the restart, so it fails the reload instead of asking for one
|
||||
func TestWinTun_ReloadInvalidNetworkCategoryFails(t *testing.T) {
|
||||
rt := newRouteTest(t, unsafeRoutes())
|
||||
for range 2 {
|
||||
res := rt.c.ReloadConfigString(unsafeRoutes() + " network_category: nope\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed, "a bad category that didn't change since the last reload is still bad")
|
||||
assert.False(t, res.RestartRequired)
|
||||
}
|
||||
|
||||
// Fixing it back to the running category needs nothing
|
||||
res := rt.c.ReloadConfigString(unsafeRoutes() + " network_category: private\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.False(t, res.RestartRequired)
|
||||
|
||||
res = rt.c.ReloadConfigString(unsafeRoutes() + " network_category: public\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.Equal(t, []string{"tun.network_category"}, res.RestartKeys)
|
||||
}
|
||||
|
||||
// forFamilies runs f with two unsafe_routes CIDRs of each address family, the tun's own network stays IPv4
|
||||
func forFamilies(t *testing.T, f func(t *testing.T, a, b string)) {
|
||||
t.Run("ipv4", func(t *testing.T) { f(t, "10.251.1.0/24", "10.251.2.0/24") })
|
||||
t.Run("ipv6", func(t *testing.T) { f(t, "fd00:251:1::/64", "fd00:251:2::/64") })
|
||||
}
|
||||
@@ -2,9 +2,7 @@ package nebula
|
||||
|
||||
import (
|
||||
"crypto/fips140"
|
||||
"crypto/sha256"
|
||||
"encoding/binary"
|
||||
"encoding/hex"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
@@ -52,30 +50,15 @@ type CertState struct {
|
||||
myVpnBroadcastAddrsTable *bart.Lite
|
||||
}
|
||||
|
||||
// errCertNeedsRestart marks a new cert that is refused on reload because only a restart can apply it
|
||||
var errCertNeedsRestart = errors.New("a restart is required to use the new cert")
|
||||
|
||||
func NewPKIFromConfig(l *slog.Logger, c *config.C) (*PKI, error) {
|
||||
pki := &PKI{l: l}
|
||||
err := pki.reload(c, true, nil)
|
||||
err := pki.reload(c, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
// Compare with the running cipher, not the last config. A restart with one we can't run would fail, so say that
|
||||
// now rather than ask for one, and going back to the running one after a bad reload needs no restart
|
||||
if cipher := c.GetString("cipher", "aes"); !validCipher(cipher) {
|
||||
l.Error("Unknown cipher, a restart with it would fail", "cipher", cipher)
|
||||
r.Failed()
|
||||
} else if cipher == "chachapoly" && fipsOnly() {
|
||||
// newCipherSuite refuses it at startup
|
||||
l.Error("ChaChaPoly is not allowed in FIPS 140-only mode, a restart with it would fail", "cipher", cipher)
|
||||
r.Failed()
|
||||
} else if cipher != pki.getCertState().cipher {
|
||||
r.RestartRequiredIfChanged("cipher")
|
||||
}
|
||||
rErr := pki.reload(c, false, r)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
rErr := pki.reload(c, false)
|
||||
if rErr != nil {
|
||||
util.LogWithContextIfNeeded("Failed to reload PKI from config", rErr, l)
|
||||
}
|
||||
@@ -92,29 +75,13 @@ func (p *PKI) getCertState() *CertState {
|
||||
return p.cs.Load()
|
||||
}
|
||||
|
||||
// r is nil on the initial load
|
||||
func (p *PKI) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
before := p.cs.Load()
|
||||
func (p *PKI) reload(c *config.C, initial bool) error {
|
||||
err := p.reloadCerts(c, initial)
|
||||
if err != nil {
|
||||
if initial {
|
||||
return err
|
||||
}
|
||||
err.Log(p.l)
|
||||
if errors.Is(err, errCertNeedsRestart) {
|
||||
r.RestartRequired()
|
||||
} else {
|
||||
r.Failed()
|
||||
}
|
||||
} else if !initial {
|
||||
// A cert for a version we weren't running is accepted without comparing its networks to ours. The tun and the
|
||||
// lighthouse keep the networks they started with
|
||||
after := p.cs.Load()
|
||||
if !slices.Equal(before.myVpnNetworks, after.myVpnNetworks) {
|
||||
p.l.Warn("The new cert changes our networks, a restart is required to use them",
|
||||
"old_networks", before.myVpnNetworks, "new_networks", after.myVpnNetworks)
|
||||
r.RestartRequired()
|
||||
}
|
||||
}
|
||||
|
||||
err = p.reloadCAPool(c)
|
||||
@@ -123,27 +90,21 @@ func (p *PKI) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
return err
|
||||
}
|
||||
err.Log(p.l)
|
||||
r.Failed()
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// fipsOnly is fips140.Enforced, a variable so a test can run the FIPS 140-only reload check without GODEBUG
|
||||
var fipsOnly = fips140.Enforced
|
||||
|
||||
// validCipher is true for the ciphers nebula can run. Each post-handshake CipherState in noiseutil hardcodes its own
|
||||
// nonce endianness, so there's nothing to set up for either.
|
||||
func validCipher(cipher string) bool {
|
||||
return cipher == "aes" || cipher == "chachapoly"
|
||||
}
|
||||
|
||||
func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
||||
var cipher string
|
||||
var currentState *CertState
|
||||
if initial {
|
||||
cipher = c.GetString("cipher", "aes")
|
||||
if !validCipher(cipher) {
|
||||
switch cipher {
|
||||
case "aes", "chachapoly":
|
||||
// Each post-handshake CipherState in noiseutil hardcodes its own
|
||||
// nonce endianness now, so there's nothing to set up here.
|
||||
default:
|
||||
return util.NewContextualError(
|
||||
"unknown cipher",
|
||||
m{"cipher": cipher},
|
||||
@@ -171,7 +132,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
||||
return util.NewContextualError(
|
||||
"Networks in new cert was different from old",
|
||||
m{"new_networks": newState.v1Cert.Networks(), "old_networks": currentState.v1Cert.Networks(), "cert_version": cert.Version1},
|
||||
errCertNeedsRestart,
|
||||
nil,
|
||||
)
|
||||
}
|
||||
|
||||
@@ -179,7 +140,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
||||
return util.NewContextualError(
|
||||
"Curve in new v1 cert was different from old",
|
||||
m{"new_curve": newState.v1Cert.Curve(), "old_curve": currentState.v1Cert.Curve(), "cert_version": cert.Version1},
|
||||
errCertNeedsRestart,
|
||||
nil,
|
||||
)
|
||||
}
|
||||
}
|
||||
@@ -194,7 +155,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
||||
return util.NewContextualError(
|
||||
"Networks in new cert was different from old",
|
||||
m{"new_networks": newState.v2Cert.Networks(), "old_networks": currentState.v2Cert.Networks(), "cert_version": cert.Version2},
|
||||
errCertNeedsRestart,
|
||||
nil,
|
||||
)
|
||||
}
|
||||
|
||||
@@ -202,7 +163,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
||||
return util.NewContextualError(
|
||||
"Curve in new cert was different from old",
|
||||
m{"new_curve": newState.v2Cert.Curve(), "old_curve": currentState.v2Cert.Curve(), "cert_version": cert.Version2},
|
||||
errCertNeedsRestart,
|
||||
nil,
|
||||
)
|
||||
}
|
||||
}
|
||||
@@ -217,7 +178,7 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
||||
return util.NewContextualError(
|
||||
"Removing a V2 cert is not permitted unless it has identical networks to the new V1 cert",
|
||||
m{"new_v1_networks": newState.v1Cert.Networks(), "old_v2_networks": currentState.v2Cert.Networks()},
|
||||
errCertNeedsRestart,
|
||||
nil,
|
||||
)
|
||||
}
|
||||
}
|
||||
@@ -235,14 +196,12 @@ func (p *PKI) reloadCerts(c *config.C, initial bool) *util.ContextualError {
|
||||
|
||||
func (p *PKI) reloadCAPool(c *config.C) *util.ContextualError {
|
||||
caPool, err := loadCAPoolFromConfig(p.l, c)
|
||||
if caPool != nil {
|
||||
p.caPool.Store(caPool)
|
||||
p.l.Debug("Trusted CA fingerprints", "fingerprints", caPool.GetFingerprints())
|
||||
}
|
||||
if err != nil {
|
||||
return util.NewContextualError("Failed to load ca from config", nil, err)
|
||||
}
|
||||
|
||||
p.caPool.Store(caPool)
|
||||
p.l.Debug("Trusted CA fingerprints", "fingerprints", caPool.GetFingerprints())
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -617,22 +576,11 @@ func loadCAPoolFromConfig(l *slog.Logger, c *config.C) (*cert.CAPool, error) {
|
||||
|
||||
bl := c.GetStringSlice("pki.blocklist", []string{})
|
||||
if len(bl) > 0 {
|
||||
var bad []string
|
||||
for i, raw := range bl {
|
||||
// Fingerprints are compared as lowercase hex strings, a malformed entry would silently block nothing
|
||||
fp := strings.ToLower(strings.TrimSpace(raw))
|
||||
if b, err := hex.DecodeString(fp); err != nil || len(b) != sha256.Size {
|
||||
bad = append(bad, fmt.Sprintf("entry %d %q", i+1, raw))
|
||||
continue
|
||||
}
|
||||
for _, fp := range bl {
|
||||
caPool.BlocklistFingerprint(fp)
|
||||
}
|
||||
|
||||
l.Info("Blocklisted certificates", "fingerprintCount", len(bl)-len(bad))
|
||||
if len(bad) > 0 {
|
||||
// The valid entries are still returned so a failed reload blocks them, startup refuses the error
|
||||
return caPool, fmt.Errorf("pki.blocklist entries are not hex certificate fingerprints: %s", strings.Join(bad, ", "))
|
||||
}
|
||||
l.Info("Blocklisted certificates", "fingerprintCount", len(bl))
|
||||
}
|
||||
|
||||
return caPool, nil
|
||||
|
||||
-168
@@ -1,17 +1,10 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"crypto/fips140"
|
||||
"fmt"
|
||||
"net/netip"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
@@ -99,164 +92,3 @@ func TestNewCipherSuiteUnsupportedCurve(t *testing.T) {
|
||||
assert.True(t, strings.HasPrefix(err.Error(), "unsupported curve:"), "got: %v", err)
|
||||
assert.Nil(t, cs)
|
||||
}
|
||||
|
||||
func TestPKIReloadRestartRequired(t *testing.T) {
|
||||
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
|
||||
pkiConfig := func(cipher, network string) string {
|
||||
_, _, keyPEM, certPEM := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix(network)}, nil, nil)
|
||||
return fmt.Sprintf("cipher: %s\npki:\n ca: %q\n cert: %q\n key: %q\n", cipher, caPEM, certPEM, keyPEM)
|
||||
}
|
||||
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString(pkiConfig("aes", "10.1.0.2/24")))
|
||||
p, err := NewPKIFromConfig(test.NewLogger(), c)
|
||||
require.NoError(t, err)
|
||||
|
||||
// A cert that changes our networks is refused and needs a restart, it is not a failure
|
||||
res := c.ReloadConfigString(pkiConfig("aes", "10.1.0.3/24"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.RestartRequired)
|
||||
assert.False(t, res.Failed)
|
||||
assert.Equal(t, []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, p.getCertState().myVpnNetworks)
|
||||
|
||||
// The cipher only applies at startup
|
||||
c2 := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c2.LoadString(pkiConfig("aes", "10.1.0.2/24")))
|
||||
p, err = NewPKIFromConfig(test.NewLogger(), c2)
|
||||
require.NoError(t, err)
|
||||
res = c2.ReloadConfigString(pkiConfig("chachapoly", "10.1.0.2/24"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.RestartRequired)
|
||||
assert.Equal(t, "aes", p.getCertState().cipher)
|
||||
|
||||
// A cipher we can't run would fail the restart, so it fails the reload instead of asking for one
|
||||
c4 := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c4.LoadString(pkiConfig("aes", "10.1.0.2/24")))
|
||||
_, err = NewPKIFromConfig(test.NewLogger(), c4)
|
||||
require.NoError(t, err)
|
||||
for range 2 {
|
||||
res = c4.ReloadConfigString(pkiConfig("nope", "10.1.0.2/24"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed, "a bad cipher that didn't change since the last reload is still bad")
|
||||
assert.False(t, res.RestartRequired)
|
||||
}
|
||||
// Fixing it back to the running cipher needs nothing
|
||||
res = c4.ReloadConfigString(pkiConfig("aes", "10.1.0.2/24"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.False(t, res.RestartRequired)
|
||||
|
||||
// A cert that keeps our networks applies without a restart
|
||||
c3 := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c3.LoadString(pkiConfig("aes", "10.1.0.2/24")))
|
||||
_, err = NewPKIFromConfig(test.NewLogger(), c3)
|
||||
require.NoError(t, err)
|
||||
res = c3.ReloadConfigString(pkiConfig("aes", "10.1.0.2/24"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.RestartRequired)
|
||||
|
||||
// A cert that can't be read is a failure, and a restart wouldn't help
|
||||
res = c3.ReloadConfigString(strings.Replace(pkiConfig("aes", "10.1.0.2/24"), "cert: \"", "cert: \"garbage", 1))
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.False(t, res.RestartRequired)
|
||||
}
|
||||
|
||||
// A cert for a version we weren't running is accepted without comparing networks, so switching to one with different
|
||||
// networks needs a restart. One with the same networks doesn't
|
||||
func TestPKIReloadNewVersionWithOtherNetworks(t *testing.T) {
|
||||
ca1, _, ca1Key, ca1PEM := cert_test.NewTestCaCert(cert.Version1, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
|
||||
ca2, _, ca2Key, ca2PEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
|
||||
caPEM := string(ca1PEM) + string(ca2PEM)
|
||||
pkiConfig := func(v cert.Version, network string) string {
|
||||
ca, caKey := ca1, ca1Key
|
||||
if v == cert.Version2 {
|
||||
ca, caKey = ca2, ca2Key
|
||||
}
|
||||
_, _, keyPEM, certPEM := cert_test.NewTestCert(v, cert.Curve_CURVE25519, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix(network)}, nil, nil)
|
||||
return fmt.Sprintf("pki:\n ca: %q\n cert: %q\n key: %q\n", caPEM, certPEM, keyPEM)
|
||||
}
|
||||
|
||||
for _, tc := range []struct {
|
||||
network string
|
||||
restart bool
|
||||
}{
|
||||
{"10.9.0.7/24", true},
|
||||
{"10.1.0.2/24", false},
|
||||
} {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString(pkiConfig(cert.Version1, "10.1.0.2/24")))
|
||||
p, err := NewPKIFromConfig(test.NewLogger(), c)
|
||||
require.NoError(t, err)
|
||||
|
||||
res := c.ReloadConfigString(pkiConfig(cert.Version2, tc.network))
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed, tc.network)
|
||||
assert.Equal(t, tc.restart, res.RestartRequired, tc.network)
|
||||
assert.Equal(t, []netip.Prefix{netip.MustParsePrefix(tc.network)}, p.getCertState().myVpnNetworks, "accepted either way, as before")
|
||||
}
|
||||
}
|
||||
|
||||
// FIPS 140-only mode refuses chachapoly at startup, so reloading to it fails rather than asks for a restart
|
||||
func TestPKIReloadChachapolyInFIPSOnlyFails(t *testing.T) {
|
||||
fipsOnly = func() bool { return true }
|
||||
t.Cleanup(func() { fipsOnly = fips140.Enforced })
|
||||
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_P256, time.Time{}, time.Time{}, nil, nil, nil)
|
||||
_, _, keyPEM, certPEM := cert_test.NewTestCert(cert.Version2, cert.Curve_P256, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, nil, nil)
|
||||
pkiConfig := func(cipher string) string {
|
||||
return fmt.Sprintf("cipher: %s\npki:\n ca: %q\n cert: %q\n key: %q\n", cipher, caPEM, certPEM, keyPEM)
|
||||
}
|
||||
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString(pkiConfig("aes")))
|
||||
_, err := NewPKIFromConfig(test.NewLogger(), c)
|
||||
require.NoError(t, err)
|
||||
|
||||
res := c.ReloadConfigString(pkiConfig("chachapoly"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.False(t, res.RestartRequired)
|
||||
}
|
||||
|
||||
func TestLoadCAPoolBlocklist(t *testing.T) {
|
||||
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
|
||||
crt, _, _, _ := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "host", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")}, nil, nil)
|
||||
fp, err := crt.Fingerprint()
|
||||
require.NoError(t, err)
|
||||
|
||||
load := func(entry string) (*cert.CAPool, error) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString(fmt.Sprintf("pki:\n ca: %q\n blocklist:\n - %q\n", caPEM, entry)))
|
||||
return loadCAPoolFromConfig(test.NewLogger(), c)
|
||||
}
|
||||
|
||||
for _, entry := range []string{fp, strings.ToUpper(fp), " " + fp + "\t"} {
|
||||
pool, err := load(entry)
|
||||
require.NoError(t, err, entry)
|
||||
assert.True(t, pool.IsBlocklisted(fp), entry)
|
||||
}
|
||||
|
||||
for _, entry := range []string{fp[1:], fp + "00", "sha256:" + fp, "zz" + fp[2:], ""} {
|
||||
_, err := load(entry)
|
||||
require.Error(t, err, entry)
|
||||
}
|
||||
|
||||
// A bad entry on reload fails it, the valid entries are still blocked
|
||||
_, _, keyPEM, certPEM := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "me", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.1/24")}, nil, nil)
|
||||
pkiConfig := func(entry string) string {
|
||||
return fmt.Sprintf("pki:\n ca: %q\n cert: %q\n key: %q\n blocklist:\n - %q\n", caPEM, certPEM, keyPEM, entry)
|
||||
}
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString(pkiConfig(fp)))
|
||||
p, err := NewPKIFromConfig(test.NewLogger(), c)
|
||||
require.NoError(t, err)
|
||||
|
||||
other, _, _, _ := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "other", time.Time{}, time.Time{}, []netip.Prefix{netip.MustParsePrefix("10.1.0.3/24")}, nil, nil)
|
||||
otherFp, err := other.Fingerprint()
|
||||
require.NoError(t, err)
|
||||
|
||||
res := c.ReloadConfigString(pkiConfig(fp) + fmt.Sprintf(" - %q\n - %q\n", otherFp, fp[1:]))
|
||||
assert.True(t, res.Failed)
|
||||
assert.True(t, p.GetCAPool().IsBlocklisted(fp))
|
||||
assert.True(t, p.GetCAPool().IsBlocklisted(otherFp))
|
||||
}
|
||||
@@ -67,8 +67,7 @@ func NewPunchyFromConfig(l *slog.Logger, c *config.C, punchConn udp.Conn) *Punch
|
||||
}
|
||||
|
||||
p.reload(c, true)
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("stats.lighthouse_metrics")
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
p.reload(c, false)
|
||||
})
|
||||
|
||||
@@ -165,24 +164,20 @@ func (p *Punchy) scheduleJob(job holepunchJob, delay time.Duration) {
|
||||
// SendPunch sends an immediate keepalive punch for an idle hostinfo.
|
||||
// The configured punchy.target_all_remotes mode picks the targets. Gated on punchy.punch and the lighthouse-skip rule
|
||||
// (lighthouses don't get keepalive punches because the regular update interval keeps their NAT state warm).
|
||||
// Returns the hostinfo's current remote and the error from punching it, an invalid remote if it was not punched.
|
||||
func (p *Punchy) SendPunch(hostinfo *HostInfo) (netip.AddrPort, error) {
|
||||
func (p *Punchy) SendPunch(hostinfo *HostInfo) {
|
||||
if !p.punch.Load() {
|
||||
return netip.AddrPort{}, nil
|
||||
return
|
||||
}
|
||||
if p.lh.IsAnyLighthouseAddr(hostinfo.vpnAddrs) {
|
||||
return netip.AddrPort{}, nil
|
||||
return
|
||||
}
|
||||
|
||||
hr := hostinfo.GetRemote()
|
||||
if p.punchEverything.Load() {
|
||||
return hr, p.sendPunchToAllRemotes(hostinfo, hr)
|
||||
p.sendPunchToAllRemotes(hostinfo)
|
||||
} else if hr := hostinfo.GetRemote(); hr.IsValid() {
|
||||
p.metricPunchyTx.Inc(1)
|
||||
p.punchConn.WriteTo([]byte{1}, hr)
|
||||
}
|
||||
if !hr.IsValid() {
|
||||
return hr, nil
|
||||
}
|
||||
p.metricPunchyTx.Inc(1)
|
||||
return hr, p.punchConn.WriteTo([]byte{1}, hr)
|
||||
}
|
||||
|
||||
// SendPunchToAll punches every known remote for hostinfo, but only when punchy.target_all_remotes is enabled.
|
||||
@@ -199,19 +194,14 @@ func (p *Punchy) SendPunchToAll(hostinfo *HostInfo) {
|
||||
if p.lh.IsAnyLighthouseAddr(hostinfo.vpnAddrs) {
|
||||
return
|
||||
}
|
||||
p.sendPunchToAllRemotes(hostinfo, netip.AddrPort{})
|
||||
p.sendPunchToAllRemotes(hostinfo)
|
||||
}
|
||||
|
||||
// sendPunchToAllRemotes punches every known remote for hostinfo and returns the error from punching current
|
||||
func (p *Punchy) sendPunchToAllRemotes(hostinfo *HostInfo, current netip.AddrPort) error {
|
||||
var currentErr error
|
||||
func (p *Punchy) sendPunchToAllRemotes(hostinfo *HostInfo) {
|
||||
hostinfo.remotes.ForEach(p.hm.GetPreferredRanges(), func(addr netip.AddrPort, preferred bool) {
|
||||
p.metricPunchyTx.Inc(1)
|
||||
if err := p.punchConn.WriteTo([]byte{1}, addr); addr == current {
|
||||
currentErr = err
|
||||
}
|
||||
p.punchConn.WriteTo([]byte{1}, addr)
|
||||
})
|
||||
return currentErr
|
||||
}
|
||||
|
||||
// Start wires the runtime dependencies and spawns the scheduler worker.
|
||||
|
||||
+6
-128
@@ -3,14 +3,11 @@ package nebula
|
||||
import (
|
||||
"context"
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
@@ -79,7 +76,7 @@ punchy:
|
||||
punch: true
|
||||
delay: 10m
|
||||
respond: true
|
||||
`).Err)
|
||||
`))
|
||||
p.reload(c, false)
|
||||
assert.True(t, p.punch.Load())
|
||||
assert.Equal(t, newDelay, time.Duration(p.delay.Load()))
|
||||
@@ -173,7 +170,7 @@ func TestPunchy_LogFormat_ReloadPunch(t *testing.T) {
|
||||
NewPunchyFromConfig(l, c, nil)
|
||||
hook.entries = nil
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {punch: true}`).Err)
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {punch: true}`))
|
||||
|
||||
entry := findEntry(t, hook.entries, "punchy.punch changed")
|
||||
assert.Equal(t, slog.LevelInfo, entry.Level)
|
||||
@@ -187,7 +184,7 @@ func TestPunchy_LogFormat_ReloadRespond(t *testing.T) {
|
||||
NewPunchyFromConfig(l, c, nil)
|
||||
hook.entries = nil
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {respond: true}`).Err)
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {respond: true}`))
|
||||
|
||||
entry := findEntry(t, hook.entries, "punchy.respond changed")
|
||||
assert.Equal(t, slog.LevelInfo, entry.Level)
|
||||
@@ -201,7 +198,7 @@ func TestPunchy_LogFormat_ReloadDelay(t *testing.T) {
|
||||
NewPunchyFromConfig(l, c, nil)
|
||||
hook.entries = nil
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {delay: 10s}`).Err)
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {delay: 10s}`))
|
||||
|
||||
entry := findEntry(t, hook.entries, "punchy.delay changed")
|
||||
assert.Equal(t, slog.LevelInfo, entry.Level)
|
||||
@@ -215,7 +212,7 @@ func TestPunchy_LogFormat_ReloadTargetAllRemotes(t *testing.T) {
|
||||
NewPunchyFromConfig(l, c, nil)
|
||||
hook.entries = nil
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {target_all_remotes: true}`).Err)
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {target_all_remotes: true}`))
|
||||
|
||||
entry := findEntry(t, hook.entries, "punchy.target_all_remotes changed")
|
||||
assert.Equal(t, slog.LevelInfo, entry.Level)
|
||||
@@ -229,128 +226,9 @@ func TestPunchy_LogFormat_ReloadRespondDelay(t *testing.T) {
|
||||
NewPunchyFromConfig(l, c, nil)
|
||||
hook.entries = nil
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {respond_delay: 15s}`).Err)
|
||||
require.NoError(t, c.ReloadConfigString(`punchy: {respond_delay: 15s}`))
|
||||
|
||||
entry := findEntry(t, hook.entries, "punchy.respond_delay changed")
|
||||
assert.Equal(t, slog.LevelInfo, entry.Level)
|
||||
assert.Equal(t, map[string]any{"respond_delay": 15 * time.Second}, entry.Attrs)
|
||||
}
|
||||
|
||||
func TestPunchyReloadRestartRequired(t *testing.T) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("stats:\n lighthouse_metrics: false\n"))
|
||||
NewPunchyFromConfig(test.NewLogger(), c, nil)
|
||||
|
||||
res := c.ReloadConfigString("stats:\n lighthouse_metrics: true\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.RestartRequired)
|
||||
}
|
||||
|
||||
// errNoRoute is the unreachable error every platform classifies the same way
|
||||
var errNoRoute = udp.ErrInvalidIPv6RemoteForSocket
|
||||
|
||||
// recordingConn records where every write went and what kind of message it was, and fails the ones to an address in
|
||||
// fail
|
||||
type recordingConn struct {
|
||||
udp.NoopConn
|
||||
fail map[netip.AddrPort]error
|
||||
wrote []netip.AddrPort
|
||||
// types is the message type of each write, a punch has none
|
||||
types []header.MessageType
|
||||
}
|
||||
|
||||
func (c *recordingConn) WriteTo(b []byte, addr netip.AddrPort) error {
|
||||
c.wrote = append(c.wrote, addr)
|
||||
var h header.H
|
||||
if h.Parse(b) == nil {
|
||||
c.types = append(c.types, h.Type)
|
||||
}
|
||||
return c.fail[addr]
|
||||
}
|
||||
|
||||
func (c *recordingConn) WriteBatch(bufs [][]byte, addrs []netip.AddrPort, failed func(int, error)) (int, error) {
|
||||
written := 0
|
||||
for i := range bufs {
|
||||
if err := c.WriteTo(bufs[i], addrs[i]); err != nil {
|
||||
failed(i, err)
|
||||
continue
|
||||
}
|
||||
written++
|
||||
}
|
||||
return written, nil
|
||||
}
|
||||
|
||||
type noLighthouses struct{}
|
||||
|
||||
func (noLighthouses) IsAnyLighthouseAddr([]netip.Addr) bool { return false }
|
||||
|
||||
var (
|
||||
punchTargetV4 = netip.MustParseAddrPort("10.0.0.3:4242")
|
||||
punchTargetV6 = netip.MustParseAddrPort("[fd00::3]:4242")
|
||||
)
|
||||
|
||||
// newPunchTarget is a tunnel on its IPv6 remote that also knows the peer's IPv4 one
|
||||
func newPunchTarget() *HostInfo {
|
||||
vpnAddr := netip.MustParseAddr("10.128.0.3")
|
||||
hostinfo := &HostInfo{
|
||||
vpnAddrs: []netip.Addr{vpnAddr},
|
||||
remotes: NewRemoteList([]netip.Addr{vpnAddr}, nil),
|
||||
}
|
||||
hostinfo.remotes.LearnRemote(vpnAddr, punchTargetV4)
|
||||
hostinfo.SetRemote(punchTargetV6)
|
||||
return hostinfo
|
||||
}
|
||||
|
||||
func newPunchyForTest(t *testing.T, settings map[string]any, conn udp.Conn) *Punchy {
|
||||
c := config.NewC(test.NewLogger())
|
||||
c.Settings["punchy"] = settings
|
||||
p := NewPunchyFromConfig(test.NewLogger(), c, conn)
|
||||
|
||||
hm := newHostMap(test.NewLogger())
|
||||
hm.preferredRanges.Store(&[]netip.Prefix{})
|
||||
p.hm = hm
|
||||
p.lh = noLighthouses{}
|
||||
return p
|
||||
}
|
||||
|
||||
func TestPunchy_SendPunchReportsCurrentRemote(t *testing.T) {
|
||||
t.Run("disabled", func(t *testing.T) {
|
||||
conn := &recordingConn{fail: map[netip.AddrPort]error{punchTargetV6: errNoRoute}}
|
||||
p := newPunchyForTest(t, map[string]any{"punch": false}, conn)
|
||||
|
||||
remote, err := p.SendPunch(newPunchTarget())
|
||||
assert.False(t, remote.IsValid())
|
||||
require.NoError(t, err)
|
||||
assert.Empty(t, conn.wrote)
|
||||
})
|
||||
|
||||
t.Run("current remote", func(t *testing.T) {
|
||||
conn := &recordingConn{fail: map[netip.AddrPort]error{punchTargetV6: errNoRoute}}
|
||||
p := newPunchyForTest(t, map[string]any{"punch": true}, conn)
|
||||
|
||||
remote, err := p.SendPunch(newPunchTarget())
|
||||
assert.Equal(t, punchTargetV6, remote)
|
||||
require.ErrorIs(t, err, errNoRoute)
|
||||
assert.Equal(t, []netip.AddrPort{punchTargetV6}, conn.wrote)
|
||||
})
|
||||
|
||||
t.Run("all remotes, current fails", func(t *testing.T) {
|
||||
conn := &recordingConn{fail: map[netip.AddrPort]error{punchTargetV6: errNoRoute}}
|
||||
p := newPunchyForTest(t, map[string]any{"punch": true, "target_all_remotes": true}, conn)
|
||||
|
||||
remote, err := p.SendPunch(newPunchTarget())
|
||||
assert.Equal(t, punchTargetV6, remote)
|
||||
require.ErrorIs(t, err, errNoRoute)
|
||||
assert.ElementsMatch(t, []netip.AddrPort{punchTargetV4, punchTargetV6}, conn.wrote)
|
||||
})
|
||||
|
||||
t.Run("all remotes, only another fails", func(t *testing.T) {
|
||||
conn := &recordingConn{fail: map[netip.AddrPort]error{punchTargetV4: errNoRoute}}
|
||||
p := newPunchyForTest(t, map[string]any{"punch": true, "target_all_remotes": true}, conn)
|
||||
|
||||
remote, err := p.SendPunch(newPunchTarget())
|
||||
assert.Equal(t, punchTargetV6, remote)
|
||||
require.NoError(t, err, "a failure on a remote we are not using says nothing about the current one")
|
||||
assert.ElementsMatch(t, []netip.AddrPort{punchTargetV4, punchTargetV6}, conn.wrote)
|
||||
})
|
||||
}
|
||||
@@ -1,91 +0,0 @@
|
||||
package ratelimit
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"math"
|
||||
"sync/atomic"
|
||||
"time"
|
||||
)
|
||||
|
||||
// Limiter is a token bucket: `burst` calls are allowed at once, then one more per `every`.
|
||||
// It counts the calls it denies and hands that count to the next allowed call.
|
||||
//
|
||||
// The budget belongs to the Limiter instance.
|
||||
// Every Allow that returns true spends from it, whatever the caller then does.
|
||||
//
|
||||
// Time follows Go's monotonic clock.
|
||||
//
|
||||
// Create one Limiter for each thing you want to limit,
|
||||
// sharing one between unrelated events lets the noisy one starve the quiet one.
|
||||
//
|
||||
// Check Allow before doing the work being limited, so a denied call stays cheap:
|
||||
//
|
||||
// if denied, ok := probeLimiter.Allow(); ok {
|
||||
// sendProbe()
|
||||
// probesDenied.Inc(int64(denied))
|
||||
// }
|
||||
//
|
||||
// For log lines use logging.RateLimited, which attaches the denied count to the logger as "suppressed".
|
||||
type Limiter struct {
|
||||
every int64
|
||||
slack int64
|
||||
tat atomic.Int64
|
||||
denied atomic.Uint64
|
||||
}
|
||||
|
||||
// maxSpan bounds `burst` * `every` to half of int64, leaving the other half for process uptime so the bucket
|
||||
// math can't overflow.
|
||||
const maxSpan = math.MaxInt64 / 2
|
||||
|
||||
// New returns a Limiter allowing `burst` calls at once and one more per `every`.
|
||||
// A `burst` under 1 is 1, and an `every` of 0 or less never limits.
|
||||
// It returns an error if `burst` * `every` is over about 146 years.
|
||||
func New(burst int, every time.Duration) (*Limiter, error) {
|
||||
l := &Limiter{}
|
||||
if every > 0 {
|
||||
burst = max(burst, 1)
|
||||
if int64(burst) > maxSpan/int64(every) {
|
||||
return nil, fmt.Errorf("ratelimit: burst %d * every %v is too long", burst, every)
|
||||
}
|
||||
l.every = int64(every)
|
||||
l.slack = int64(burst-1) * l.every
|
||||
}
|
||||
return l, nil
|
||||
}
|
||||
|
||||
var monoStart = time.Now()
|
||||
|
||||
func monoNow() int64 { return int64(time.Since(monoStart)) }
|
||||
|
||||
// Allow reports whether this call is allowed.
|
||||
// If a token is available it spends it and returns the calls denied since the last allowed one, and true.
|
||||
// Otherwise it returns 0 and false, and counts the denial.
|
||||
// A nil Limiter allows everything.
|
||||
func (l *Limiter) Allow() (uint64, bool) {
|
||||
if l == nil {
|
||||
return 0, true
|
||||
}
|
||||
return l.allow(monoNow())
|
||||
}
|
||||
|
||||
// allow is Allow at a given monotonic time.
|
||||
func (l *Limiter) allow(now int64) (uint64, bool) {
|
||||
// Concurrent Allow calls read the clock before racing for the bucket, so one can see a time another already spent
|
||||
// past and be denied. An unlimited Limiter must never deny, so it skips the bucket.
|
||||
if l.every == 0 {
|
||||
return 0, true
|
||||
}
|
||||
|
||||
for {
|
||||
tat := l.tat.Load()
|
||||
next := max(tat, now)
|
||||
if next-now > l.slack {
|
||||
l.denied.Add(1)
|
||||
return 0, false
|
||||
}
|
||||
|
||||
if l.tat.CompareAndSwap(tat, next+l.every) {
|
||||
return l.denied.Swap(0), true
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,264 +0,0 @@
|
||||
package ratelimit
|
||||
|
||||
import (
|
||||
"math"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
func mustLimiter(t testing.TB, burst int, every time.Duration) *Limiter {
|
||||
t.Helper()
|
||||
l, err := New(burst, every)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return l
|
||||
}
|
||||
|
||||
func TestLimiterBurstAndRefill(t *testing.T) {
|
||||
l, now := mustLimiter(t, 3, time.Second), int64(0)
|
||||
|
||||
for i := 0; i < 3; i++ {
|
||||
if n, ok := l.allow(now); !ok || n != 0 {
|
||||
t.Fatalf("burst line %d: ok=%v denied=%d", i, ok, n)
|
||||
}
|
||||
}
|
||||
for i := 0; i < 5; i++ {
|
||||
if _, ok := l.allow(now); ok {
|
||||
t.Fatalf("line %d past the burst logged", i)
|
||||
}
|
||||
}
|
||||
|
||||
now += int64(time.Second)
|
||||
if n, ok := l.allow(now); !ok || n != 5 {
|
||||
t.Fatalf("after one refill: ok=%v denied=%d, want true 5", ok, n)
|
||||
}
|
||||
if _, ok := l.allow(now); ok {
|
||||
t.Fatal("one refill earned more than one line")
|
||||
}
|
||||
|
||||
// A long quiet spell refills to burst, not past it, and the count reported above does not carry over.
|
||||
now += int64(time.Hour)
|
||||
for i, want := range []uint64{1, 0, 0} {
|
||||
if n, ok := l.allow(now); !ok || n != want {
|
||||
t.Fatalf("refilled line %d: ok=%v denied=%d, want true %d", i, ok, n, want)
|
||||
}
|
||||
}
|
||||
if _, ok := l.allow(now); ok {
|
||||
t.Fatal("bucket refilled past burst")
|
||||
}
|
||||
}
|
||||
|
||||
func TestLimiterBounds(t *testing.T) {
|
||||
for _, every := range []time.Duration{0, -time.Second} {
|
||||
l := mustLimiter(t, 1, every)
|
||||
for i := 0; i < 100; i++ {
|
||||
if _, ok := l.allow(0); !ok {
|
||||
t.Fatalf("every=%v limited line %d", every, i)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
l := mustLimiter(t, 0, time.Second)
|
||||
if _, ok := l.allow(0); !ok {
|
||||
t.Fatal("burst 0 should allow one line")
|
||||
}
|
||||
if _, ok := l.allow(0); ok {
|
||||
t.Fatal("burst 0 should allow only one line")
|
||||
}
|
||||
}
|
||||
|
||||
func TestLimiterOverflow(t *testing.T) {
|
||||
for _, c := range []struct {
|
||||
burst int
|
||||
every time.Duration
|
||||
}{
|
||||
{math.MaxInt, time.Second},
|
||||
{1, math.MaxInt64},
|
||||
{2, maxSpan/2 + 1},
|
||||
} {
|
||||
if _, err := New(c.burst, c.every); err == nil {
|
||||
t.Fatalf("burst %d every %d should not fit", c.burst, c.every)
|
||||
}
|
||||
}
|
||||
|
||||
l := mustLimiter(t, 2, maxSpan/2)
|
||||
for i := 0; i < 2; i++ {
|
||||
if _, ok := l.allow(0); !ok {
|
||||
t.Fatalf("the largest span should allow its burst, denied call %d", i)
|
||||
}
|
||||
}
|
||||
if _, ok := l.allow(0); ok {
|
||||
t.Fatal("the largest span allowed past its burst")
|
||||
}
|
||||
}
|
||||
|
||||
// Concurrent callers read the clock at slightly different times, which must not limit a Limiter that never limits.
|
||||
func TestLimiterUnlimitedConcurrent(t *testing.T) {
|
||||
l := mustLimiter(t, 1, 0)
|
||||
|
||||
var denied atomic.Int64
|
||||
var wg sync.WaitGroup
|
||||
for i := 0; i < 16; i++ {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
for j := 0; j < 10000; j++ {
|
||||
if _, ok := l.Allow(); !ok {
|
||||
denied.Add(1)
|
||||
}
|
||||
}
|
||||
}()
|
||||
}
|
||||
wg.Wait()
|
||||
|
||||
if got := denied.Load(); got != 0 {
|
||||
t.Fatalf("denied %d lines", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestLimiterNil(t *testing.T) {
|
||||
var l *Limiter
|
||||
for i := 0; i < 10; i++ {
|
||||
if _, ok := l.Allow(); !ok {
|
||||
t.Fatal("nil limiter limited")
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestLimiterConcurrent(t *testing.T) {
|
||||
l := mustLimiter(t, 10, time.Hour)
|
||||
|
||||
var allowed atomic.Int64
|
||||
var reported atomic.Uint64
|
||||
var wg sync.WaitGroup
|
||||
for i := 0; i < 16; i++ {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
for j := 0; j < 1000; j++ {
|
||||
if n, ok := l.allow(0); ok {
|
||||
allowed.Add(1)
|
||||
reported.Add(n)
|
||||
}
|
||||
}
|
||||
}()
|
||||
}
|
||||
wg.Wait()
|
||||
|
||||
if got := allowed.Load(); got != 10 {
|
||||
t.Fatalf("allowed %d lines, want the burst of 10", got)
|
||||
}
|
||||
// An allowed call that lands after some denials reports them, so the rest are still pending.
|
||||
if got := reported.Load() + l.denied.Load(); got != 16*1000-10 {
|
||||
t.Fatalf("denied %d, want %d", got, 16*1000-10)
|
||||
}
|
||||
}
|
||||
|
||||
func BenchmarkAllowAllowed(b *testing.B) {
|
||||
l := mustLimiter(b, 1, time.Nanosecond)
|
||||
b.ReportAllocs()
|
||||
for i := 0; i < b.N; i++ {
|
||||
l.tat.Store(0)
|
||||
l.Allow()
|
||||
}
|
||||
}
|
||||
|
||||
func BenchmarkAllowDenied(b *testing.B) {
|
||||
l := mustLimiter(b, 1, time.Hour)
|
||||
l.Allow()
|
||||
b.ReportAllocs()
|
||||
for i := 0; i < b.N; i++ {
|
||||
l.Allow()
|
||||
}
|
||||
}
|
||||
|
||||
func BenchmarkAllowDeniedParallel(b *testing.B) {
|
||||
l := mustLimiter(b, 1, time.Hour)
|
||||
l.Allow()
|
||||
b.ReportAllocs()
|
||||
b.RunParallel(func(pb *testing.PB) {
|
||||
for pb.Next() {
|
||||
l.Allow()
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
// FuzzLimiter checks the bucket against its exact definition over arbitrary call timings.
|
||||
// A call is denied if and only if some allowed call a would leave too many calls for the time since a:
|
||||
// (allowed calls since a, plus this one) * every > burst * every + (now - a).
|
||||
// Every denied call must also be reported exactly once, by a later allowed call or still pending.
|
||||
func FuzzLimiter(f *testing.F) {
|
||||
f.Add(uint8(3), uint16(1000), []byte{0, 0, 0, 0, 16, 0, 0, 200, 1, 1, 1, 15, 17, 0})
|
||||
f.Add(uint8(1), uint16(1), []byte{0, 16, 15, 16, 0, 255, 0, 0})
|
||||
f.Fuzz(func(t *testing.T, burst uint8, everyUs uint16, steps []byte) {
|
||||
if len(steps) > 512 {
|
||||
steps = steps[:512]
|
||||
}
|
||||
b := int64(burst%16) + 1
|
||||
every := int64(everyUs%1000+1) * int64(time.Microsecond)
|
||||
l := mustLimiter(t, int(b), time.Duration(every))
|
||||
|
||||
var now int64
|
||||
var allowedAt []int64
|
||||
var denied, reported uint64
|
||||
for _, s := range steps {
|
||||
// Each step advances by a sixteenth of every, so timings land on and around the refill.
|
||||
now += int64(s) * every / 16
|
||||
|
||||
over := false
|
||||
for i, a := range allowedAt {
|
||||
if int64(len(allowedAt)-i+1)*every > b*every+now-a {
|
||||
over = true
|
||||
break
|
||||
}
|
||||
}
|
||||
|
||||
n, ok := l.allow(now)
|
||||
if ok == over {
|
||||
t.Fatalf("at %d with %d allowed before: ok=%v, the definition says %v", now, len(allowedAt), ok, !over)
|
||||
}
|
||||
if !ok {
|
||||
denied++
|
||||
continue
|
||||
}
|
||||
reported += n
|
||||
allowedAt = append(allowedAt, now)
|
||||
}
|
||||
|
||||
if got := reported + l.denied.Load(); got != denied {
|
||||
t.Fatalf("reported %d denied calls, made %d", got, denied)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
// Concurrent callers on the real clock must account for every denied call exactly once.
|
||||
func TestLimiterDeniedConservedConcurrent(t *testing.T) {
|
||||
l := mustLimiter(t, 4, time.Microsecond)
|
||||
|
||||
var denied, reported atomic.Uint64
|
||||
var wg sync.WaitGroup
|
||||
for i := 0; i < 16; i++ {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
for j := 0; j < 20000; j++ {
|
||||
if n, ok := l.Allow(); ok {
|
||||
reported.Add(n)
|
||||
} else {
|
||||
denied.Add(1)
|
||||
}
|
||||
}
|
||||
}()
|
||||
}
|
||||
wg.Wait()
|
||||
|
||||
if denied.Load() == 0 {
|
||||
t.Fatal("nothing was denied, the test proves nothing")
|
||||
}
|
||||
if got := reported.Load() + l.denied.Load(); got != denied.Load() {
|
||||
t.Fatalf("reported %d denied calls, made %d", got, denied.Load())
|
||||
}
|
||||
}
|
||||
+1
-2
@@ -28,11 +28,10 @@ func NewRelayManager(ctx context.Context, l *slog.Logger, hostmap *HostMap, c *c
|
||||
hostmap: hostmap,
|
||||
}
|
||||
rm.reload(c, true)
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := rm.reload(c, false)
|
||||
if err != nil {
|
||||
rm.l.Error("Failed to reload relay_manager", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
return rm
|
||||
|
||||
+10
-27
@@ -1,8 +1,8 @@
|
||||
package service
|
||||
|
||||
import (
|
||||
"io"
|
||||
"net"
|
||||
"sync"
|
||||
)
|
||||
|
||||
type tcpListener struct {
|
||||
@@ -10,40 +10,23 @@ type tcpListener struct {
|
||||
s *Service
|
||||
addr *net.TCPAddr
|
||||
accept chan net.Conn
|
||||
|
||||
// closed is closed instead of accept so a handler blocked handing off a
|
||||
// connection can't send on a closed channel.
|
||||
closed chan struct{}
|
||||
closeOnce sync.Once
|
||||
}
|
||||
|
||||
func (l *tcpListener) Accept() (net.Conn, error) {
|
||||
// select picks randomly among ready cases, so without this a handler still
|
||||
// waiting to hand off could win over closed after Close has returned.
|
||||
select {
|
||||
case <-l.closed:
|
||||
return nil, net.ErrClosed
|
||||
default:
|
||||
}
|
||||
|
||||
select {
|
||||
case conn := <-l.accept:
|
||||
return conn, nil
|
||||
case <-l.closed:
|
||||
return nil, net.ErrClosed
|
||||
conn, ok := <-l.accept
|
||||
if !ok {
|
||||
return nil, io.EOF
|
||||
}
|
||||
return conn, nil
|
||||
}
|
||||
|
||||
func (l *tcpListener) Close() error {
|
||||
l.closeOnce.Do(func() {
|
||||
// Close before leaving the map so a concurrent closeListeners that
|
||||
// no longer sees this listener knows Accept is already released.
|
||||
close(l.closed)
|
||||
l.s.mu.Lock()
|
||||
defer l.s.mu.Unlock()
|
||||
delete(l.s.mu.listeners, uint16(l.addr.Port))
|
||||
|
||||
close(l.accept)
|
||||
|
||||
l.s.mu.Lock()
|
||||
delete(l.s.mu.listeners, l.port)
|
||||
l.s.mu.Unlock()
|
||||
})
|
||||
return nil
|
||||
}
|
||||
|
||||
|
||||
+10
-79
@@ -32,18 +32,13 @@ import (
|
||||
const nicID = 1
|
||||
|
||||
type Service struct {
|
||||
eg *errgroup.Group
|
||||
control *nebula.Control
|
||||
ipstack *stack.Stack
|
||||
|
||||
// done is closed once the forwarding goroutines have exited and the
|
||||
// netstack is torn down, at which point err holds the first fatal error.
|
||||
done chan struct{}
|
||||
err error
|
||||
|
||||
mu struct {
|
||||
sync.Mutex
|
||||
|
||||
closed bool
|
||||
listeners map[uint16]*tcpListener
|
||||
}
|
||||
}
|
||||
@@ -70,6 +65,7 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
||||
ctx := control.Context()
|
||||
eg, ctx := errgroup.WithContext(ctx)
|
||||
s := Service{
|
||||
eg: eg,
|
||||
control: control,
|
||||
}
|
||||
s.mu.listeners = map[uint16]*tcpListener{}
|
||||
@@ -78,12 +74,6 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
||||
NetworkProtocols: []stack.NetworkProtocolFactory{ipv4.NewProtocol, ipv6.NewProtocol},
|
||||
TransportProtocols: []stack.TransportProtocolFactory{tcp.NewProtocol, udp.NewProtocol, icmp.NewProtocol4, icmp.NewProtocol6},
|
||||
})
|
||||
// The teardown goroutine only owns the stack once New succeeds
|
||||
defer func() {
|
||||
if reterr != nil {
|
||||
s.ipstack.Destroy()
|
||||
}
|
||||
}()
|
||||
sackEnabledOpt := tcpip.TCPSACKEnabled(true) // TCP SACK is disabled by default
|
||||
tcpipErr := s.ipstack.SetTransportProtocolOption(tcp.ProtocolNumber, &sackEnabledOpt)
|
||||
if tcpipErr != nil {
|
||||
@@ -133,12 +123,6 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
||||
// this will read exactly one packet
|
||||
n, err := reader.Read(buf)
|
||||
if err != nil {
|
||||
// An error after shutdown began is noise from the device pipes
|
||||
// closing, anything else is fatal and must stop nebula too
|
||||
if ctx.Err() != nil {
|
||||
return nil
|
||||
}
|
||||
s.control.Stop()
|
||||
return err
|
||||
}
|
||||
packetBuf := stack.NewPacketBuffer(stack.PacketBufferOptions{
|
||||
@@ -146,8 +130,8 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
||||
})
|
||||
linkEP.InjectInbound(header.IPv4ProtocolNumber, packetBuf)
|
||||
|
||||
if ctx.Err() != nil {
|
||||
return nil
|
||||
if err := ctx.Err(); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
})
|
||||
@@ -155,18 +139,13 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
||||
for {
|
||||
packet := linkEP.ReadContext(ctx)
|
||||
if packet == nil {
|
||||
if ctx.Err() != nil {
|
||||
return nil
|
||||
if err := ctx.Err(); err != nil {
|
||||
return err
|
||||
}
|
||||
continue
|
||||
}
|
||||
bufView := packet.ToView()
|
||||
if _, err := bufView.WriteTo(writer); err != nil {
|
||||
// Same shutdown noise handling as the inbound reader
|
||||
if ctx.Err() != nil {
|
||||
return nil
|
||||
}
|
||||
s.control.Stop()
|
||||
return err
|
||||
}
|
||||
bufView.Release()
|
||||
@@ -179,22 +158,6 @@ func New(control *nebula.Control) (_ *Service, reterr error) {
|
||||
return control.Wait()
|
||||
})
|
||||
|
||||
// Tear down here rather than in Close so it also happens when nebula stops
|
||||
// on its own. The forwarding goroutines must exit before the stack they feed
|
||||
// is destroyed.
|
||||
s.done = make(chan struct{})
|
||||
go func() {
|
||||
s.err = eg.Wait()
|
||||
s.closeListeners()
|
||||
// Destroy aborts the endpoints that exist when it starts, then waits on
|
||||
// every endpoint, so a Dial registering in between would hold Wait until
|
||||
// its connect timed out. Without the NIC new dials fail route lookup.
|
||||
// RemoveNIC also closes linkEP.
|
||||
_ = s.ipstack.RemoveNIC(nicID)
|
||||
s.ipstack.Destroy()
|
||||
close(s.done)
|
||||
}()
|
||||
|
||||
return &s, nil
|
||||
}
|
||||
|
||||
@@ -268,15 +231,11 @@ func (s *Service) Listen(network, address string) (net.Listener, error) {
|
||||
s: s,
|
||||
addr: addr,
|
||||
accept: make(chan net.Conn),
|
||||
closed: make(chan struct{}),
|
||||
}
|
||||
|
||||
s.mu.Lock()
|
||||
defer s.mu.Unlock()
|
||||
|
||||
if s.mu.closed {
|
||||
return nil, net.ErrClosed
|
||||
}
|
||||
if _, ok := s.mu.listeners[port]; ok {
|
||||
return nil, fmt.Errorf("already listening on port %d", port)
|
||||
}
|
||||
@@ -285,44 +244,22 @@ func (s *Service) Listen(network, address string) (net.Listener, error) {
|
||||
return l, nil
|
||||
}
|
||||
|
||||
// Wait blocks until the service has fully stopped, either via Close or a fatal
|
||||
// error, and returns the first fatal error if there was one.
|
||||
func (s *Service) Wait() error {
|
||||
<-s.done
|
||||
return s.err
|
||||
return s.eg.Wait()
|
||||
}
|
||||
|
||||
// Close closes all listeners and stops nebula. Use Wait to block until
|
||||
// shutdown has completed.
|
||||
func (s *Service) Close() error {
|
||||
s.closeListeners()
|
||||
s.control.Stop()
|
||||
return nil
|
||||
}
|
||||
|
||||
// closeListeners unblocks pending Accept calls and rejects new listeners.
|
||||
func (s *Service) closeListeners() {
|
||||
// Every caller closes every listener rather than returning early once
|
||||
// closed is set, so none returns while another is still closing them.
|
||||
s.mu.Lock()
|
||||
s.mu.closed = true
|
||||
listeners := make([]*tcpListener, 0, len(s.mu.listeners))
|
||||
for _, l := range s.mu.listeners {
|
||||
listeners = append(listeners, l)
|
||||
}
|
||||
s.mu.Unlock()
|
||||
|
||||
for _, l := range listeners {
|
||||
_ = l.Close()
|
||||
}
|
||||
}
|
||||
|
||||
func (s *Service) tcpHandler(r *tcp.ForwarderRequest) {
|
||||
endpointID := r.ID()
|
||||
|
||||
s.mu.Lock()
|
||||
defer s.mu.Unlock()
|
||||
|
||||
l, ok := s.mu.listeners[endpointID.LocalPort]
|
||||
s.mu.Unlock()
|
||||
if !ok {
|
||||
r.Complete(true)
|
||||
return
|
||||
@@ -338,12 +275,6 @@ func (s *Service) tcpHandler(r *tcp.ForwarderRequest) {
|
||||
r.Complete(false)
|
||||
ep.SocketOptions().SetKeepAlive(true)
|
||||
|
||||
// The handoff blocks until Accept is called, so it must not hold s.mu or a
|
||||
// listener nobody accepts from stalls every other port.
|
||||
conn := gonet.NewTCPConn(&wq, ep)
|
||||
select {
|
||||
case l.accept <- conn:
|
||||
case <-l.closed:
|
||||
_ = conn.Close()
|
||||
}
|
||||
l.accept <- conn
|
||||
}
|
||||
Loaded 100 of 132 files, more files were not shown because too many files have changed in this diff.
Show more
Reference in new issue
Block a user