mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-16 16:46:52 +01:00
Compare commits
18
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
aa880d85b6 | ||
|
|
553e874122 | ||
|
|
f62c54a4f2 | ||
|
|
5bb0622192 | ||
|
|
f3705cbb67 | ||
|
|
94be454f4f | ||
|
|
5f26c1a7e5 | ||
|
|
d47c8c71f1 | ||
|
|
f57539a163 | ||
|
|
8d8ae0f744 | ||
|
|
f9b0853476 | ||
|
|
d5062dacf0 | ||
|
|
7cfa47d569 | ||
|
|
e20569ce51 | ||
|
|
9651ffdb0d | ||
|
|
3a45c01656 | ||
|
|
019cc46a7f | ||
|
|
cf3f315cd3 |
No files matched your search
@@ -263,6 +263,20 @@ try {
|
||||
}
|
||||
Write-Host "OK: WSL peer -> windows lighthouse over v6"
|
||||
|
||||
# The NlMtu check above proves the value was written, not that windows honors it. A payload this size only
|
||||
# crosses the tunnel as fragments cut at NlMtu on the way out of the adapter. Left at the adapter default it
|
||||
# reaches nebula whole, overflows the udp.MTU (9001) write buffer and is dropped, so the ping never answers.
|
||||
# Anything smaller would ride out as one oversized datagram and survive on IP fragmentation of the underlay.
|
||||
$BigPayload = 9000
|
||||
foreach ($target in @(@{ Family = 'v4'; Ip = $Ip2 }, @{ Family = 'v6'; Ip = $Ip6_2 })) {
|
||||
Wait-Until -TimeoutSec 30 -What "$($target.Family) ping with a $BigPayload byte payload from windows lighthouse to WSL peer ($($target.Ip))" -Predicate {
|
||||
if ($peerProc.HasExited) { throw "peer exited (code $($peerProc.ExitCode)) before the large $($target.Family) ping succeeded" }
|
||||
$null = & ping.exe -n 1 -w 1000 -l $BigPayload $target.Ip
|
||||
$LASTEXITCODE -eq 0
|
||||
}
|
||||
Write-Host "OK: windows lighthouse -> WSL peer, $BigPayload byte $($target.Family) payload"
|
||||
}
|
||||
|
||||
Write-Host ''
|
||||
Write-Host 'All smoke checks passed.'
|
||||
}
|
||||
|
||||
@@ -7,6 +7,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
### Fixed
|
||||
|
||||
- `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.
|
||||
- A firewall rule with `group: []`, `groups:` with no value, or a `groups` entry that isn't a string, such as
|
||||
`groups: [1, 2]`, no longer crashes Nebula on startup or reload. A null `group` or `groups` means none was
|
||||
provided. An unquoted int or bool group, such as `group: 7`, is still read as a string but logs a warning to
|
||||
quote it, since YAML has already turned a value like `007` into `7`. A float, a date, an empty array, a null
|
||||
entry, a nested array, or a map is rejected with an error.
|
||||
|
||||
## [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.
|
||||
|
||||
@@ -242,11 +242,14 @@ test-cov-html:
|
||||
go test -coverprofile=coverage.out
|
||||
go tool cover -html=coverage.out
|
||||
|
||||
# The package builds only compile. The final line links an android binary so a linker-only failure
|
||||
# cannot pass CI.
|
||||
build-test-mobile:
|
||||
GOARCH=amd64 GOOS=ios go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
||||
GOARCH=arm64 GOOS=ios go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
||||
GOARCH=amd64 GOOS=android go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
||||
GOARCH=arm64 GOOS=android go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
||||
GOARCH=arm64 GOOS=android go build -o /dev/null ${NEBULA_CMD_PATH}
|
||||
|
||||
bench:
|
||||
go test -bench=.
|
||||
|
||||
@@ -174,10 +174,8 @@ func (cm *connectionManager) doTrafficCheck(localIndex uint32, p, nb, out []byte
|
||||
|
||||
switch decision {
|
||||
case deleteTunnel:
|
||||
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)
|
||||
}
|
||||
// Local delete only, clearing the lighthouse cache if this was the last hostinfo for the vpn addr
|
||||
cm.intf.closeTunnel(hostinfo)
|
||||
|
||||
case closeTunnel:
|
||||
cm.intf.sendCloseTunnel(hostinfo)
|
||||
|
||||
@@ -7,6 +7,7 @@ import (
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/overlay/overlaytest"
|
||||
@@ -21,6 +22,8 @@ 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{}{}
|
||||
|
||||
+2
-2
@@ -410,8 +410,8 @@ logging:
|
||||
#try_interval: 100ms
|
||||
#retries: 20
|
||||
|
||||
# query_buffer is the size of the buffer channel for querying lighthouses
|
||||
#query_buffer: 64
|
||||
# query_buffer is the size of the buffer channel for querying lighthouses, drops are recorded in the lighthouse.query.dropped metric.
|
||||
#query_buffer: 1024
|
||||
|
||||
# trigger_buffer is the size of the buffer channel for quickly sending handshakes
|
||||
# after receiving the response for lighthouse queries
|
||||
|
||||
+65
-17
@@ -967,33 +967,54 @@ func convertRule(l *slog.Logger, p any, table string, i int) (rule, error) {
|
||||
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")
|
||||
// A null value, `group:` with nothing after it, is the same as no group
|
||||
var singleGroup string
|
||||
if g, ok := m["group"]; ok && g != nil {
|
||||
// Make sure group isn't an array
|
||||
v, isArray := g.([]any)
|
||||
if isArray {
|
||||
if len(v) > 1 {
|
||||
return r, errors.New("group should contain a single value, an array with more than one entry was provided")
|
||||
}
|
||||
if len(v) == 0 {
|
||||
return r, errors.New("group should contain a single value, an empty array was provided")
|
||||
}
|
||||
g = v[0]
|
||||
}
|
||||
|
||||
l.Warn("group was an array with a single value, converting to simple value",
|
||||
"table", table,
|
||||
"rule", i,
|
||||
)
|
||||
m["group"] = v[0]
|
||||
var err error
|
||||
singleGroup, err = groupName(l, g, table, i)
|
||||
if err != nil {
|
||||
return r, fmt.Errorf("group should contain a single value, %w", err)
|
||||
}
|
||||
|
||||
if isArray {
|
||||
l.Warn("group was an array with a single value, converting to simple value",
|
||||
"table", table,
|
||||
"rule", i,
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
singleGroup := toString("group", m)
|
||||
|
||||
if rg, ok := m["groups"]; ok {
|
||||
// A null value, `groups:` with nothing after it, is the same as no groups
|
||||
if rg, ok := m["groups"]; ok && rg != nil {
|
||||
switch reflect.TypeOf(rg).Kind() {
|
||||
case reflect.Slice:
|
||||
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)
|
||||
for gi := 0; gi < v.Len(); gi++ {
|
||||
name, err := groupName(l, v.Index(gi).Interface(), table, i)
|
||||
if err != nil {
|
||||
return r, fmt.Errorf("groups entry #%d should contain a single value, %w", gi, err)
|
||||
}
|
||||
r.Groups[gi] = name
|
||||
}
|
||||
case reflect.String:
|
||||
r.Groups = []string{rg.(string)}
|
||||
default:
|
||||
r.Groups = []string{fmt.Sprintf("%v", rg)}
|
||||
name, err := groupName(l, rg, table, i)
|
||||
if err != nil {
|
||||
return r, fmt.Errorf("groups should contain an array or a single value, %w", err)
|
||||
}
|
||||
r.Groups = []string{name}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1009,6 +1030,33 @@ func convertRule(l *slog.Logger, p any, table string, i int) (rule, error) {
|
||||
return r, nil
|
||||
}
|
||||
|
||||
// groupName reads a group name from config. YAML has already parsed an unquoted value by the time we see it, so `007`
|
||||
// arrives as 7, `1.10` as 1.1, and a date as a time.Time, and the text that was written is gone. Strings are used as
|
||||
// is. Ints and bools are converted so `group: 7` keeps working, with a warning to quote them. Anything else would
|
||||
// become a name that may not match what was written, or matches nothing like "<nil>" or "map[a:b]", so it is rejected.
|
||||
func groupName(l *slog.Logger, v any, table string, i int) (string, error) {
|
||||
if v == nil {
|
||||
return "", errors.New("a null was provided")
|
||||
}
|
||||
switch reflect.TypeOf(v).Kind() {
|
||||
case reflect.String:
|
||||
return reflect.ValueOf(v).String(), nil
|
||||
case reflect.Int, reflect.Int8, reflect.Int16, reflect.Int32, reflect.Int64,
|
||||
reflect.Uint, reflect.Uint8, reflect.Uint16, reflect.Uint32, reflect.Uint64, reflect.Bool:
|
||||
l.Warn("group was not a string and should be quoted to match as written",
|
||||
"table", table,
|
||||
"rule", i,
|
||||
"group", v,
|
||||
)
|
||||
return fmt.Sprintf("%v", v), nil
|
||||
case reflect.Slice, reflect.Array:
|
||||
return "", errors.New("an array was provided")
|
||||
case reflect.Map:
|
||||
return "", errors.New("a map was provided")
|
||||
}
|
||||
return "", fmt.Errorf("%v was read as a %T, quote it to use it as a group name", v, v)
|
||||
}
|
||||
|
||||
// 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 {
|
||||
|
||||
@@ -1439,6 +1439,56 @@ func TestAddFirewallRulesFromConfig(t *testing.T) {
|
||||
require.NoError(t, AddFirewallRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, addRuleCall{incoming: true, proto: firewall.ProtoAny, startPort: 1, endPort: 1, groups: []string{"a", "b"}, ip: "", localIp: ""}, mf.lastCall)
|
||||
|
||||
// Test group and groups values that used to crash or become a group that matches nothing: an empty array,
|
||||
// a null, an array, or a map is rejected
|
||||
badGroups := []struct {
|
||||
key string
|
||||
value any
|
||||
err string
|
||||
}{
|
||||
{"group", []any{}, "group should contain a single value, an empty array was provided"},
|
||||
{"group", []any{nil}, "group should contain a single value, a null was provided"},
|
||||
{"group", []any{[]any{"a"}}, "group should contain a single value, an array was provided"},
|
||||
{"group", map[string]any{"a": "b"}, "group should contain a single value, a map was provided"},
|
||||
{"groups", []any{nil}, "groups entry #0 should contain a single value, a null was provided"},
|
||||
{"groups", []any{"a", []any{"b"}}, "groups entry #1 should contain a single value, an array was provided"},
|
||||
{"groups", []any{map[string]any{"a": "b"}}, "groups entry #0 should contain a single value, a map was provided"},
|
||||
{"groups", map[string]any{"a": "b"}, "groups should contain an array or a single value, a map was provided"},
|
||||
{"group", 1.1, "group should contain a single value, 1.1 was read as a float64, quote it to use it as a group name"},
|
||||
{"group", []any{1.1}, "group should contain a single value, 1.1 was read as a float64, quote it to use it as a group name"},
|
||||
{"groups", []any{"a", 1.1}, "groups entry #1 should contain a single value, 1.1 was read as a float64, quote it to use it as a group name"},
|
||||
{"groups", time.Date(2001, 12, 14, 0, 0, 0, 0, time.UTC), "groups should contain an array or a single value, 2001-12-14 00:00:00 +0000 UTC was read as a time.Time, quote it to use it as a group name"},
|
||||
}
|
||||
for _, tc := range badGroups {
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", tc.key: tc.value}}}
|
||||
require.EqualError(t, AddFirewallRulesFromConfig(l, true, conf, mf), "firewall.inbound rule #0; "+tc.err, "%s: %v", tc.key, tc.value)
|
||||
}
|
||||
|
||||
// Test int and bool groups entries are read as strings
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "groups": []any{1, true}}}}
|
||||
require.NoError(t, AddFirewallRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, []string{"1", "true"}, mf.lastCall.groups)
|
||||
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", "group": 1}}}
|
||||
require.NoError(t, AddFirewallRulesFromConfig(l, true, conf, mf))
|
||||
assert.Equal(t, []string{"1"}, mf.lastCall.groups)
|
||||
|
||||
// Test a null group or groups is the same as not providing it
|
||||
for _, key := range []string{"group", "groups"} {
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
conf.Settings["firewall"] = map[string]any{"inbound": []any{map[string]any{"port": "1", "proto": "any", key: nil, "host": "a"}}}
|
||||
require.NoError(t, AddFirewallRulesFromConfig(l, true, conf, mf))
|
||||
assert.Empty(t, mf.lastCall.groups)
|
||||
assert.Equal(t, "a", mf.lastCall.host)
|
||||
}
|
||||
|
||||
// Test Add error
|
||||
conf = config.NewC(test.NewLogger())
|
||||
mf = &mockFirewall{}
|
||||
|
||||
@@ -5,6 +5,7 @@ go 1.26.0
|
||||
require (
|
||||
dario.cat/mergo v1.0.2
|
||||
filippo.io/bigmod v0.1.0
|
||||
github.com/DefinedNet/netlink v1.3.2-dn.1
|
||||
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be
|
||||
github.com/armon/go-radix v1.0.0
|
||||
github.com/flynn/noise v1.1.0
|
||||
@@ -20,7 +21,6 @@ require (
|
||||
github.com/skip2/go-qrcode v0.0.0-20200617195104-da1b6568686e
|
||||
github.com/stefanberger/go-pkcs11uri v0.0.0-20230803200340-78284954bff6
|
||||
github.com/stretchr/testify v1.12.1
|
||||
github.com/vishvananda/netlink v1.3.1
|
||||
go.uber.org/goleak v1.3.0
|
||||
go.yaml.in/yaml/v3 v3.0.5
|
||||
golang.org/x/crypto v0.57.0
|
||||
|
||||
@@ -3,6 +3,8 @@ dario.cat/mergo v1.0.2 h1:85+piFYR1tMbRrLcDwR18y4UKJ3aH1Tbzi24VRW1TK8=
|
||||
dario.cat/mergo v1.0.2/go.mod h1:E/hbnu0NxMFBjpMIE34DRGLWqDy0g5FuKDhCb31ngxA=
|
||||
filippo.io/bigmod v0.1.0 h1:UNzDk7y9ADKST+axd9skUpBQeW7fG2KrTZyOE4uGQy8=
|
||||
filippo.io/bigmod v0.1.0/go.mod h1:OjOXDNlClLblvXdwgFFOQFJEocLhhtai8vGLy0JCZlI=
|
||||
github.com/DefinedNet/netlink v1.3.2-dn.1 h1:Md2PsUE1Xuy1Zxs/Bm6356n1kt5bq2HspXlPJ6pEspg=
|
||||
github.com/DefinedNet/netlink v1.3.2-dn.1/go.mod h1:o4YSn8Jw7zoDcYXDmV77TRd4eS5sSLuE+vu2zAN67C8=
|
||||
github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
|
||||
github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
|
||||
github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
|
||||
@@ -138,8 +140,6 @@ github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81P
|
||||
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
|
||||
github.com/stretchr/testify v1.12.1 h1:EuwCh5fleGS7H32xRwO3wRGT7DxrDhLAT6FF8MpWDWE=
|
||||
github.com/stretchr/testify v1.12.1/go.mod h1:MDEgiDPPsNp5cuIrHPPCyornHKgEVbtFUmoNlxoYthg=
|
||||
github.com/vishvananda/netlink v1.3.1 h1:3AEMt62VKqz90r0tmNhog0r/PpWKmrEShJU0wJW6bV0=
|
||||
github.com/vishvananda/netlink v1.3.1/go.mod h1:ARtKouGSTGchR8aMwmkzC0qiNPrrWO5JS/XMVl45+b4=
|
||||
github.com/vishvananda/netns v0.0.5 h1:DfiHV+j8bA32MFM7bfEunvT8IAqQ/NzSJHtcmW5zdEY=
|
||||
github.com/vishvananda/netns v0.0.5/go.mod h1:SpkAiCQRtJ6TvvxPnOSyH3BMl6unz3xZlaprSwhNNJM=
|
||||
github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
|
||||
@@ -195,8 +195,6 @@ golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7w
|
||||
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
||||
golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
||||
golang.org/x/sys v0.0.0-20210603081109-ebe580a85c40/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||
golang.org/x/sys v0.2.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||
golang.org/x/sys v0.10.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||
golang.org/x/sys v0.48.0 h1:bbX/i/6MgT9BVLM9RT1thmxL04yeTAhbEz4SyadbXoo=
|
||||
golang.org/x/sys v0.48.0/go.mod h1:hNLxWAXmnKAxqDtdwIYC4bM9oQPEecfsnNMuSxOs3og=
|
||||
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
|
||||
|
||||
+18
-5
@@ -31,6 +31,7 @@ package nebula
|
||||
|
||||
import (
|
||||
"bufio"
|
||||
"context"
|
||||
"fmt"
|
||||
"net"
|
||||
"strconv"
|
||||
@@ -51,17 +52,29 @@ 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 on failed connections.
|
||||
func graphiteOnce(c graphiteConfigExport) error {
|
||||
// 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 {
|
||||
now := time.Now().Unix()
|
||||
du := float64(c.DurationUnit)
|
||||
flushSeconds := float64(c.FlushInterval) / float64(time.Second)
|
||||
conn, err := net.DialTCP("tcp", nil, c.Addr)
|
||||
deadline := time.Now().Add(timeout)
|
||||
d := net.Dialer{Deadline: deadline}
|
||||
conn, err := d.DialContext(ctx, "tcp", c.Addr.String())
|
||||
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) {
|
||||
@@ -111,7 +124,7 @@ func graphiteOnce(c graphiteConfigExport) error {
|
||||
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()
|
||||
})
|
||||
return nil
|
||||
// A failed write sticks, so this reports the first one
|
||||
return w.Flush()
|
||||
}
|
||||
@@ -0,0 +1,315 @@
|
||||
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")
|
||||
}
|
||||
+9
-12
@@ -54,7 +54,8 @@ type HandshakeConfig struct {
|
||||
}
|
||||
|
||||
type HandshakeManager struct {
|
||||
// Mutex for interacting with the vpnIps and indexes maps
|
||||
// Mutex for interacting with the vpnIps and indexes maps.
|
||||
// Lock order is hostmap, then this lock, then the lighthouse, then a RemoteList.
|
||||
sync.RWMutex
|
||||
|
||||
vpnIps map[netip.Addr]*HandshakeHostInfo
|
||||
@@ -259,14 +260,6 @@ 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)
|
||||
|
||||
@@ -371,6 +364,9 @@ 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{},
|
||||
@@ -946,13 +942,14 @@ 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
|
||||
}
|
||||
|
||||
|
||||
@@ -11,6 +11,7 @@ import (
|
||||
"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) {
|
||||
@@ -42,8 +43,6 @@ 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)
|
||||
|
||||
@@ -235,3 +234,70 @@ func TestHandleIncomingDispatch(t *testing.T) {
|
||||
assert.Empty(t, hm.indexes, "orphan stage-2 must not create state")
|
||||
})
|
||||
}
|
||||
|
||||
// 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)
|
||||
}
|
||||
-58
@@ -6,7 +6,6 @@ import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
"slices"
|
||||
"sync"
|
||||
@@ -18,7 +17,6 @@ import (
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/logging"
|
||||
)
|
||||
|
||||
const defaultPromoteEvery = 1000 // Count of packets sent before we try moving a tunnel to a preferred underlay ip address
|
||||
@@ -930,59 +928,3 @@ func (i *HostInfo) logger(l *slog.Logger) *slog.Logger {
|
||||
|
||||
return li
|
||||
}
|
||||
|
||||
// Utility functions
|
||||
|
||||
func localAddrs(l *slog.Logger, allowList *LocalAllowList) []netip.Addr {
|
||||
//FIXME: This function is pretty garbage
|
||||
var finalAddrs []netip.Addr
|
||||
ifaces, _ := net.Interfaces()
|
||||
for _, i := range ifaces {
|
||||
allow := allowList.AllowName(i.Name)
|
||||
if l.Enabled(context.Background(), logging.LevelTrace) {
|
||||
l.Log(context.Background(), logging.LevelTrace, "localAllowList.AllowName",
|
||||
"interfaceName", i.Name,
|
||||
"allow", allow,
|
||||
)
|
||||
}
|
||||
|
||||
if !allow {
|
||||
continue
|
||||
}
|
||||
addrs, _ := i.Addrs()
|
||||
for _, rawAddr := range addrs {
|
||||
var addr netip.Addr
|
||||
switch v := rawAddr.(type) {
|
||||
case *net.IPNet:
|
||||
//continue
|
||||
addr, _ = netip.AddrFromSlice(v.IP)
|
||||
case *net.IPAddr:
|
||||
addr, _ = netip.AddrFromSlice(v.IP)
|
||||
}
|
||||
|
||||
if !addr.IsValid() {
|
||||
if l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
l.Debug("addr was invalid", "localAddr", rawAddr)
|
||||
}
|
||||
continue
|
||||
}
|
||||
addr = addr.Unmap()
|
||||
|
||||
if addr.IsLoopback() == false && addr.IsLinkLocalUnicast() == false {
|
||||
isAllowed := allowList.Allow(addr)
|
||||
if l.Enabled(context.Background(), logging.LevelTrace) {
|
||||
l.Log(context.Background(), logging.LevelTrace, "localAllowList.Allow",
|
||||
"localAddr", addr,
|
||||
"allowed", isAllowed,
|
||||
)
|
||||
}
|
||||
if !isAllowed {
|
||||
continue
|
||||
}
|
||||
|
||||
finalAddrs = append(finalAddrs, addr)
|
||||
}
|
||||
}
|
||||
}
|
||||
return finalAddrs
|
||||
}
|
||||
@@ -10,6 +10,7 @@ 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"
|
||||
@@ -517,7 +518,9 @@ func (f *Interface) SendVia(via *HostInfo, relay *Relay, ad, nb, out []byte, noc
|
||||
|
||||
err = f.writers[q].WriteTo(toSend, via.GetRemote())
|
||||
if err != nil {
|
||||
via.logger(f.l).Info("Failed to WriteTo in sendVia", "error", err)
|
||||
if l, ok := logging.RateLimited(f.l, f.udpRelayTxErrLimiter); ok {
|
||||
via.logger(l).Info("Failed to WriteTo in sendVia", "error", err)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -582,18 +585,22 @@ func (f *Interface) sendNoMetrics(t header.MessageType, st header.MessageSubType
|
||||
if remote.IsValid() {
|
||||
err = f.writers[q].WriteTo(out, remote)
|
||||
if err != nil {
|
||||
hostinfo.logger(f.l).Error("Failed to write outgoing packet",
|
||||
"error", err,
|
||||
"udpAddr", remote,
|
||||
)
|
||||
if l, ok := logging.RateLimited(f.l, f.udpTxErrLimiter); ok {
|
||||
hostinfo.logger(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 {
|
||||
hostinfo.logger(f.l).Error("Failed to write outgoing packet",
|
||||
"error", err,
|
||||
"udpAddr", hr,
|
||||
)
|
||||
if l, ok := logging.RateLimited(f.l, f.udpTxErrLimiter); ok {
|
||||
hostinfo.logger(l).Error("Failed to write outgoing packet",
|
||||
"error", err,
|
||||
"udpAddr", hr,
|
||||
)
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// Try to send via a relay
|
||||
|
||||
+18
-18
@@ -24,6 +24,7 @@ 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"
|
||||
)
|
||||
|
||||
@@ -124,6 +125,9 @@ 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
|
||||
|
||||
// fatalErr holds the first unexpected reader error that caused shutdown.
|
||||
// nil means "no fatal error" (yet)
|
||||
fatalErr atomic.Pointer[error]
|
||||
@@ -198,6 +202,15 @@ 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
|
||||
}
|
||||
|
||||
if c.routines <= 1 {
|
||||
c.PinThreads = false //pinning is not useful unless there's more than one tun reader
|
||||
}
|
||||
@@ -230,6 +243,8 @@ func NewInterface(ctx context.Context, c *InterfaceConfig) (*Interface, error) {
|
||||
conntrackCacheTimeout: c.ConntrackCacheTimeout,
|
||||
cpuAffinity: c.CpuAffinity,
|
||||
pinThreads: c.PinThreads,
|
||||
udpTxErrLimiter: udpTxErrLimiter,
|
||||
udpRelayTxErrLimiter: udpRelayTxErrLimiter,
|
||||
|
||||
metricHandshakes: metrics.GetOrRegisterHistogram("handshakes", nil, metrics.NewExpDecaySample(1028, 0.015)),
|
||||
metricTxDropped: metrics.GetOrRegisterCounter("udp.tx.dropped", nil),
|
||||
@@ -624,17 +639,15 @@ func (f *Interface) reloadMisc(c *config.C) {
|
||||
}
|
||||
}
|
||||
|
||||
func (f *Interface) emitStats(ctx context.Context, i time.Duration) {
|
||||
ticker := time.NewTicker(i)
|
||||
defer ticker.Stop()
|
||||
|
||||
// statsEmitter updates the interface's gauges, the stats server runs it on its capture loop.
|
||||
func (f *Interface) statsEmitter() func() {
|
||||
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)
|
||||
|
||||
emit := func() {
|
||||
return func() {
|
||||
f.firewall.EmitStats()
|
||||
f.handshakeManager.EmitStats()
|
||||
udpStats()
|
||||
@@ -651,19 +664,6 @@ func (f *Interface) emitStats(ctx context.Context, i time.Duration) {
|
||||
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 {
|
||||
|
||||
+5
-14
@@ -3,7 +3,6 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
@@ -18,11 +17,8 @@ import (
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// 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) {
|
||||
// Priming before the first tick (issue #907) is Start's job, see TestStatsServer_Start_primes.
|
||||
func Test_statsEmitter_setsGauges(t *testing.T) {
|
||||
defer metrics.DefaultRegistry.UnregisterAll()
|
||||
|
||||
l := test.NewLogger()
|
||||
@@ -56,17 +52,12 @@ func Test_emitStats_primesGauges(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 emitStats runs")
|
||||
require.Zero(t, ttlGauge.Value(), "gauge should be zero before the emitter runs")
|
||||
|
||||
// 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)
|
||||
ifce.statsEmitter()()
|
||||
|
||||
ttl := ttlGauge.Value()
|
||||
assert.Positive(t, ttl, "ttl gauge should be primed by emitStats before its first tick")
|
||||
assert.Positive(t, ttl, "ttl gauge should be set by one run of the emitter")
|
||||
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())
|
||||
|
||||
+3
-13
@@ -45,8 +45,7 @@ func setTransportChecksum4(packet []byte) {
|
||||
if ihl < ipv4.HeaderLen || end < ihl || end > len(packet) {
|
||||
return
|
||||
}
|
||||
// The checksum covers the whole datagram, which a fragment (MF set or a
|
||||
// non-zero offset) does not carry.
|
||||
// do not attempt to set checksums for fragments
|
||||
if binary.BigEndian.Uint16(packet[6:8])&0x3fff != 0 {
|
||||
return
|
||||
}
|
||||
@@ -68,10 +67,7 @@ func setTransportChecksum6(packet []byte) {
|
||||
return
|
||||
}
|
||||
|
||||
// The checksum covers the whole datagram, which a fragment does not carry.
|
||||
// An unknown extension header hides where the transport header starts. A
|
||||
// chain longer than the walk's budget ends it early, at an offset that was
|
||||
// never checked against the packet.
|
||||
// we must find the transport header in order to write a checksum
|
||||
proto, offset, _, anyFragment, err := IPv6FindUpperProtocol(packet[:end])
|
||||
if err != nil || anyFragment || offset >= end {
|
||||
return
|
||||
@@ -109,8 +105,7 @@ func transportExtent(transport []byte, proto uint8) ([]byte, bool) {
|
||||
// writeTransportChecksum stores the checksum of transport, taken over the
|
||||
// pseudo-header sum csum, in the header's checksum field. A UDP checksum that
|
||||
// computes to zero goes on the wire as 0xffff: zero means no checksum was
|
||||
// computed (RFC 768), and over IPv6 the checksum is mandatory (RFC 8200
|
||||
// section 8.1).
|
||||
// computed (RFC 768), and over IPv6 the checksum is mandatory (RFC 8200 section 8.1).
|
||||
func writeTransportChecksum(transport []byte, proto uint8, csum uint32) {
|
||||
var at, minLen int
|
||||
switch proto {
|
||||
@@ -133,11 +128,6 @@ func writeTransportChecksum(transport []byte, proto uint8, csum uint32) {
|
||||
binary.BigEndian.PutUint16(transport[at:], sum)
|
||||
}
|
||||
|
||||
// fold reduces a pseudo-header sum to the 16 bit seed Checksum takes. Carrying
|
||||
// the high half back into the low half is what keeps the reduction lossless, so
|
||||
// the seed sums exactly as the wider value would; 0xffff is its fixed point.
|
||||
// Every term of that sum comes from a 16 bit field, so it stays far below the
|
||||
// width at which the accumulator would wrap.
|
||||
func fold(csum uint32) uint16 {
|
||||
for csum > 0xffff {
|
||||
csum = (csum >> 16) + (csum & 0xffff)
|
||||
|
||||
+13
-16
@@ -345,14 +345,11 @@ func ipv6CreateRejectTCPPacket(packet []byte, out []byte, offset int) []byte {
|
||||
return out
|
||||
}
|
||||
|
||||
// IPv6FindUpperProtocol walks the ipv6 extension header chain and returns the upper layer protocol, the
|
||||
// offset it begins at, and whether the packet is a non-first fragment. Only the RFC 8200 and IANA extension
|
||||
// headers below are walked. Everything else, including Mobility (135), HIP (139), Shim6 (140), experimental
|
||||
// 253/254, and real upper layer protocols like SCTP or GRE, is terminal. Walking those as extension headers
|
||||
// is a firewall bypass, so they fail closed. For a non-first fragment the returned protocol is the fragmented
|
||||
// protocol and offset points at the fragment header, there is no transport header to locate. Returns
|
||||
// ErrIPv6CouldNotFindPayload if packet is smaller than an ipv6 header or the chain is truncated before a
|
||||
// terminal protocol is reached.
|
||||
// IPv6FindUpperProtocol walks the ipv6 extension header chain and returns the upper layer protocol, the offset it begins at, and whether the packet is a non-first fragment.
|
||||
// Only the RFC 8200 and IANA extension headers below are walked.
|
||||
// Everything else, including Mobility (135), HIP (139), Shim6 (140), experimental 253/254, and real upper layer protocols like SCTP or GRE, is terminal.
|
||||
// For a non-first fragment the returned protocol is the fragmented protocol and offset points at the fragment header, there is no transport header to locate.
|
||||
// Returns ErrIPv6CouldNotFindPayload if packet is smaller than an ipv6 header, or the chain is truncated, or if more than 8 extension headers are present.
|
||||
func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragment bool, anyFragment bool, err error) {
|
||||
const maxIPv6ExtHeaders = 8
|
||||
if len(packet) < ipv6.HeaderLen {
|
||||
@@ -365,14 +362,14 @@ func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragm
|
||||
switch nextHeader {
|
||||
case 0, 43, 60: // Hop-by-Hop, Routing, Destination
|
||||
if len(packet) < offset+2 {
|
||||
return nextHeader, offset, isFragment, anyFragment, ErrIPv6CouldNotFindPayload
|
||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
||||
}
|
||||
nextHeader = packet[offset]
|
||||
offset += (int(packet[offset+1]) + 1) << 3
|
||||
|
||||
case 44: // Fragment
|
||||
if len(packet) < offset+8 {
|
||||
return nextHeader, offset, isFragment, anyFragment, ErrIPv6CouldNotFindPayload
|
||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
||||
}
|
||||
anyFragment = true
|
||||
// Non-first fragments carry no transport header, report the fragmented protocol and stop
|
||||
@@ -384,21 +381,21 @@ func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragm
|
||||
|
||||
case 51: // AH
|
||||
if len(packet) < offset+2 {
|
||||
return nextHeader, offset, isFragment, anyFragment, ErrIPv6CouldNotFindPayload
|
||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
||||
}
|
||||
nextHeader = packet[offset]
|
||||
offset += (int(packet[offset+1]) + 2) << 2
|
||||
|
||||
default:
|
||||
// A prior extension header can declare a length that advances offset past the packet. The terminal
|
||||
// protocol's header isn't actually here, so treat the chain as truncated rather than classifying it.
|
||||
if offset > len(packet) {
|
||||
return nextHeader, offset, isFragment, anyFragment, ErrIPv6CouldNotFindPayload
|
||||
// A prior extension header can declare a length that advances offset past the packet, reject this.
|
||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
||||
}
|
||||
return nextHeader, offset, isFragment, anyFragment, nil
|
||||
return nextHeader, offset, isFragment, anyFragment, nil //success!
|
||||
}
|
||||
}
|
||||
return nextHeader, offset, isFragment, anyFragment, nil
|
||||
// Fail closed
|
||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
||||
}
|
||||
|
||||
func CreateICMPEchoResponse(packet, out []byte) []byte {
|
||||
|
||||
+17
-5
@@ -529,6 +529,17 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
|
||||
firstFragToUDP := []byte{17, 0, 0, 1, 0, 0, 0, 1} // frag offset 0, M=1, next = UDP
|
||||
nonFirstFrag := []byte{17, 0, 0, 9, 0, 0, 0, 1} // frag offset non-zero, next = UDP
|
||||
transport := []byte{0, 80, 1, 187, 0, 0, 0, 0} // stand-in bytes, IPv6FindUpperProtocol never reads ports
|
||||
extToHbH := []byte{0, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = Hop-by-Hop
|
||||
|
||||
// 8 walked headers spend the budget before the 9th slot's terminal is ever classified. This is the
|
||||
// report 4040546 shape: without failing closed the walk hands back offset 104, and a caller reads ports
|
||||
// from the attacker's bytes there.
|
||||
var budgetChain []byte
|
||||
for range 7 {
|
||||
budgetChain = append(budgetChain, extToHbH...)
|
||||
}
|
||||
budgetChain = append(budgetChain, extToTCP...)
|
||||
budgetChain = append(budgetChain, transport...)
|
||||
|
||||
tests := []struct {
|
||||
name string
|
||||
@@ -549,9 +560,10 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
|
||||
{"first fragment walks to transport", 44, append(firstFragToUDP, transport...), 17, ipv6.HeaderLen + 8, false, true, nil},
|
||||
{"non-first fragment stops", 44, append(nonFirstFrag, transport...), 17, ipv6.HeaderLen, true, true, nil},
|
||||
{"unknown protocol is terminal", 132, transport, 132, ipv6.HeaderLen, false, false, nil}, // SCTP
|
||||
{"truncated extension header", 0, nil, 0, ipv6.HeaderLen, false, false, ErrIPv6CouldNotFindPayload},
|
||||
{"truncated extension header", 0, nil, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
|
||||
// Destination Options with a declared length (255+1)*8 = 2048 that runs past the 48 byte buffer, next = SCTP
|
||||
{"extension length past buffer", 60, []byte{132, 255, 0, 0, 0, 0, 0, 0}, 132, ipv6.HeaderLen + 2048, false, false, ErrIPv6CouldNotFindPayload},
|
||||
{"extension length past buffer", 0, []byte{132, 255, 0, 0, 0, 0, 0, 0}, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
|
||||
{"budget exhausted fails closed", 0, budgetChain, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
|
||||
}
|
||||
|
||||
for _, tt := range tests {
|
||||
@@ -559,10 +571,10 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
|
||||
packet := makeIPv6Packet(src, dst, tt.nextHeader, tt.payload)
|
||||
proto, offset, isFragment, anyFragment, err := IPv6FindUpperProtocol(packet)
|
||||
if tt.wantErr != nil {
|
||||
assert.ErrorIs(t, err, tt.wantErr)
|
||||
return
|
||||
require.ErrorIs(t, err, tt.wantErr)
|
||||
} else {
|
||||
require.NoError(t, err)
|
||||
}
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, tt.wantProto, proto)
|
||||
assert.Equal(t, tt.wantOffset, offset)
|
||||
assert.Equal(t, tt.wantFragment, isFragment)
|
||||
|
||||
+56
-6
@@ -15,10 +15,12 @@ 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"
|
||||
"github.com/slackhq/nebula/logging"
|
||||
"github.com/slackhq/nebula/nicfinder"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/slackhq/nebula/util"
|
||||
)
|
||||
@@ -42,6 +44,10 @@ type LightHouse struct {
|
||||
// addresses rather than whatever this machine's NICs happen to be. Set it before Start.
|
||||
localAddrsFn func(*LocalAllowList) []netip.Addr
|
||||
|
||||
// lastLocalAddrsErr is the previous localAddrsFn failure. Enumeration runs on every update, so an
|
||||
// unchanged failure is demoted to Debug rather than warning every lighthouse.interval forever.
|
||||
lastLocalAddrsErr atomic.Pointer[string]
|
||||
|
||||
// Local cache of answers from light houses
|
||||
// map of vpn addr to answers
|
||||
addrMap map[netip.Addr]*RemoteList
|
||||
@@ -76,6 +82,8 @@ 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
|
||||
|
||||
@@ -111,11 +119,14 @@ 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", 64)),
|
||||
queryChan: make(chan netip.Addr, c.GetUint32("handshakes.query_buffer", 1024)),
|
||||
queryDropped: metrics.GetOrRegisterCounter("lighthouse.query.dropped", nil),
|
||||
l: l,
|
||||
}
|
||||
h.localAddrsFn = func(al *LocalAllowList) []netip.Addr {
|
||||
return localAddrs(h.l, al)
|
||||
addrs, err := nicfinder.Find(ctx, h.l, al)
|
||||
h.logLocalAddrsErr(err)
|
||||
return addrs
|
||||
}
|
||||
|
||||
lighthouses := make([]netip.Addr, 0)
|
||||
@@ -348,7 +359,13 @@ func (lh *LightHouse) reload(c *config.C, initial bool) error {
|
||||
}
|
||||
}
|
||||
|
||||
if initial || c.HasChanged("relay.relays") {
|
||||
// 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()
|
||||
}
|
||||
|
||||
switch c.GetBool("relay.am_relay", false) {
|
||||
case true:
|
||||
// Relays aren't allowed to specify other relays
|
||||
@@ -373,6 +390,11 @@ func (lh *LightHouse) reload(c *config.C, initial bool) 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
|
||||
@@ -505,14 +527,19 @@ func (lh *LightHouse) Query(vpnAddr netip.Addr) *RemoteList {
|
||||
return nil
|
||||
}
|
||||
|
||||
// QueryServer is asynchronous so no reply should be expected
|
||||
// QueryServer is asynchronous and non-blocking, no reply should be expected.
|
||||
// If the query channel is full, the query is dropped.
|
||||
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
|
||||
}
|
||||
|
||||
lh.queryChan <- vpnAddr
|
||||
select {
|
||||
case lh.queryChan <- vpnAddr:
|
||||
default:
|
||||
lh.queryDropped.Inc(1)
|
||||
}
|
||||
}
|
||||
|
||||
func (lh *LightHouse) QueryCache(vpnAddrs []netip.Addr) *RemoteList {
|
||||
@@ -916,6 +943,26 @@ func (lh *LightHouse) TriggerUpdate() {
|
||||
}
|
||||
}
|
||||
|
||||
// logLocalAddrsErr reports a localAddrs failure at Warn the first time it is seen and at Debug while
|
||||
// it persists unchanged, so a permanent failure does not warn on every update forever.
|
||||
func (lh *LightHouse) logLocalAddrsErr(err error) {
|
||||
if err == nil {
|
||||
lh.lastLocalAddrsErr.Store(nil)
|
||||
return
|
||||
}
|
||||
|
||||
msg := err.Error()
|
||||
prev := lh.lastLocalAddrsErr.Swap(&msg)
|
||||
if prev != nil && *prev == msg {
|
||||
if lh.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
lh.l.Debug("Failed to collect local addresses to advertise", "error", err)
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
lh.l.Warn("Failed to collect local addresses to advertise", "error", err)
|
||||
}
|
||||
|
||||
func (lh *LightHouse) SendUpdate() {
|
||||
var v4 []*V4AddrPort
|
||||
var v6 []*V6AddrPort
|
||||
@@ -1208,10 +1255,13 @@ 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
|
||||
|
||||
@@ -1,16 +1,21 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/binary"
|
||||
"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"
|
||||
@@ -764,3 +769,231 @@ func TestLighthouse_DeletesWork(t *testing.T) {
|
||||
out = lh.Query(testHost)
|
||||
assert.Nil(t, out)
|
||||
}
|
||||
|
||||
func TestLightHouse_logLocalAddrsErr(t *testing.T) {
|
||||
out := &bytes.Buffer{}
|
||||
lh := &LightHouse{l: test.NewLoggerWithOutput(out)}
|
||||
|
||||
// The first sighting of a failure warns.
|
||||
lh.logLocalAddrsErr(errors.New("permission denied"))
|
||||
assert.Contains(t, out.String(), "level=WARN")
|
||||
assert.Contains(t, out.String(), "permission denied")
|
||||
|
||||
// Repeating unchanged does not warn again, which is what keeps a permanent failure from warning
|
||||
// on every lighthouse.interval for the life of the process.
|
||||
out.Reset()
|
||||
lh.logLocalAddrsErr(errors.New("permission denied"))
|
||||
assert.NotContains(t, out.String(), "level=WARN")
|
||||
|
||||
// A different failure is a new event and warns.
|
||||
out.Reset()
|
||||
lh.logLocalAddrsErr(errors.New("something else"))
|
||||
assert.Contains(t, out.String(), "level=WARN")
|
||||
assert.Contains(t, out.String(), "something else")
|
||||
|
||||
// Recovering resets, so the same failure returning later warns again.
|
||||
out.Reset()
|
||||
lh.logLocalAddrsErr(nil)
|
||||
assert.Empty(t, out.String())
|
||||
lh.logLocalAddrsErr(errors.New("something else"))
|
||||
assert.Contains(t, out.String(), "level=WARN")
|
||||
}
|
||||
|
||||
// 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"))
|
||||
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"))
|
||||
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"))
|
||||
assert.Empty(t, lh.GetRelaysForMe())
|
||||
require.Len(t, lh.updateTrigger, 1)
|
||||
<-lh.updateTrigger
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(base+" am_relay: false\n"))
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
|
||||
require.Len(t, lh.updateTrigger, 1)
|
||||
}
|
||||
@@ -0,0 +1,31 @@
|
||||
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
|
||||
}
|
||||
@@ -0,0 +1,106 @@
|
||||
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
|
||||
}
|
||||
@@ -32,9 +32,12 @@ const _ = noiseutil.RejectHeadroom - 4*maxRoutines
|
||||
|
||||
func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, deviceFactory overlay.DeviceFactory) (retcon *Control, reterr error) {
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
// Automatically cancel the context if Main returns an error, to signal all created goroutines to quit.
|
||||
// The goroutines started below stop only when this context does, and only a caller holding the
|
||||
// Control can arrange that. Cancel whenever we are not handing one back, which covers an error
|
||||
// and a config test alike: a config test used to leave the lighthouse query worker, and a
|
||||
// hostname resolver per dns named static host, running for the life of the process.
|
||||
defer func() {
|
||||
if reterr != nil {
|
||||
if retcon == nil {
|
||||
cancel()
|
||||
}
|
||||
}()
|
||||
@@ -297,6 +300,7 @@ 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 {
|
||||
@@ -315,9 +319,12 @@ 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)
|
||||
stats, err := newStatsServerFromConfig(ctx, l, c, buildVersion, configTest, emitStats)
|
||||
if err != nil {
|
||||
return nil, util.ContextualizeIfNeeded("Failed to start stats emitter", err)
|
||||
}
|
||||
@@ -326,8 +333,6 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
go ifce.emitStats(ctx, c.GetDuration("stats.interval", time.Second*10))
|
||||
|
||||
attachCommands(l, c, ssh, ifce)
|
||||
|
||||
networkChanges := udp.NewNetworkChangeMonitor(ctx, l, c)
|
||||
|
||||
@@ -1,12 +1,21 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"net/netip"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/cert"
|
||||
cert_test "github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/util"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
"go.uber.org/goleak"
|
||||
)
|
||||
|
||||
func TestParseCpuAffinity(t *testing.T) {
|
||||
@@ -49,3 +58,68 @@ func TestParseCpuAffinity(t *testing.T) {
|
||||
assert.Nil(t, parseCpuAffinity(newConfig([]any{1 << 20}), l, 1))
|
||||
}
|
||||
}
|
||||
|
||||
// TestMain_ConfigTestReleasesItsGoroutines pins the rule that Main only leaves goroutines running
|
||||
// when it hands back a Control to stop them with.
|
||||
//
|
||||
// A config test gets no Control, so anything it started had nothing to stop it: the lighthouse
|
||||
// query worker, and a hostname resolver per dns named static host, ran for the life of the
|
||||
// process. That matters to every embedder that validates a config in process rather than by
|
||||
// exec'ing, dnclient and the apple clients included, because they do it on each config load and
|
||||
// the leak accumulates.
|
||||
func TestMain_ConfigTestReleasesItsGoroutines(t *testing.T) {
|
||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
||||
|
||||
l := test.NewLogger()
|
||||
dir := t.TempDir()
|
||||
|
||||
before := time.Now().Add(-time.Hour)
|
||||
after := time.Now().Add(time.Hour)
|
||||
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, before, after, nil, nil, nil)
|
||||
networks := []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")}
|
||||
_, _, keyPEM, certPEM := cert_test.NewTestCert(
|
||||
cert.Version2, cert.Curve_CURVE25519, ca, caKey, "config-test", before, after, networks, nil, nil)
|
||||
|
||||
caPath := filepath.Join(dir, "ca.pem")
|
||||
certPath := filepath.Join(dir, "cert.pem")
|
||||
keyPath := filepath.Join(dir, "key.pem")
|
||||
require.NoError(t, os.WriteFile(caPath, caPEM, 0o600))
|
||||
require.NoError(t, os.WriteFile(certPath, certPEM, 0o600))
|
||||
require.NoError(t, os.WriteFile(keyPath, keyPEM, 0o600))
|
||||
|
||||
// A static host by address, not by name: the query worker is the goroutine under test and a
|
||||
// hostname would drag a real dns lookup into a unit test.
|
||||
configBody := fmt.Sprintf(`
|
||||
pki:
|
||||
ca: %s
|
||||
cert: %s
|
||||
key: %s
|
||||
static_host_map:
|
||||
"10.0.0.2": ["192.0.2.1:4242"]
|
||||
lighthouse:
|
||||
hosts:
|
||||
- "10.0.0.2"
|
||||
listen:
|
||||
host: 127.0.0.1
|
||||
port: 0
|
||||
tun:
|
||||
disabled: true
|
||||
firewall:
|
||||
outbound:
|
||||
- port: any
|
||||
proto: any
|
||||
host: any
|
||||
inbound:
|
||||
- port: any
|
||||
proto: any
|
||||
host: any
|
||||
`, caPath, certPath, keyPath)
|
||||
require.NoError(t, os.WriteFile(filepath.Join(dir, "config.yml"), []byte(configBody), 0o600))
|
||||
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.Load(dir))
|
||||
|
||||
ctrl, err := Main(c, true, "config-test", l, nil)
|
||||
require.NoError(t, err)
|
||||
require.Nil(t, ctrl, "a config test hands back nothing to stop, so it must stop itself")
|
||||
}
|
||||
@@ -0,0 +1,39 @@
|
||||
//go:build !android
|
||||
|
||||
package nicfinder
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
)
|
||||
|
||||
func localAddrs(ctx context.Context, l *slog.Logger, filter Filter) ([]netip.Addr, error) {
|
||||
ifaces, err := net.Interfaces()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to enumerate local interfaces: %w", err)
|
||||
}
|
||||
|
||||
var out []netip.Addr
|
||||
var errs []error
|
||||
|
||||
for _, i := range ifaces {
|
||||
if !allowName(ctx, l, filter, i.Name) {
|
||||
continue
|
||||
}
|
||||
addrs, err := i.Addrs()
|
||||
if err != nil {
|
||||
errs = append(errs, fmt.Errorf("failed to get addresses for %s: %w", i.Name, err))
|
||||
continue
|
||||
}
|
||||
for _, rawAddr := range addrs {
|
||||
if addr, ok := allowedAddr(ctx, l, filter, rawAddr); ok {
|
||||
out = append(out, addr)
|
||||
}
|
||||
}
|
||||
}
|
||||
return out, errors.Join(errs...)
|
||||
}
|
||||
@@ -0,0 +1,104 @@
|
||||
//go:build android
|
||||
|
||||
package nicfinder
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"os"
|
||||
|
||||
"github.com/DefinedNet/netlink"
|
||||
"github.com/DefinedNet/netlink/nl"
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// Android denies bind() on netlink route sockets and RTM_GETLINK, so net.Interfaces fails with EACCES.
|
||||
// Enumerate with an RTM_GETADDR dump on an unbound socket instead.
|
||||
|
||||
// localInterfaces returns every interface that has an address, with its addresses. It lists
|
||||
// addresses over a netlink socket that is never bound and names each index with SIOCGIFNAME, the
|
||||
// same operations Bionic's getifaddrs uses for app UIDs, which the sandbox permits.
|
||||
func localAddrs(ctx context.Context, l *slog.Logger, filter Filter) ([]netip.Addr, error) {
|
||||
var errs []error
|
||||
addrs, err := netlinkAddrList()
|
||||
if err != nil {
|
||||
if !errors.Is(err, netlink.ErrDumpInterrupted) {
|
||||
return nil, fmt.Errorf("failed to enumerate local interfaces: %w", err)
|
||||
}
|
||||
// The address table kept changing under the dump and netlink gave up retrying. What it
|
||||
// returned is still worth advertising.
|
||||
errs = append(errs, fmt.Errorf("local addresses may be incomplete: %w", err))
|
||||
}
|
||||
|
||||
// Any socket will do for SIOCGIFNAME.
|
||||
sfd, err := unix.Socket(unix.AF_INET, unix.SOCK_DGRAM|unix.SOCK_CLOEXEC, 0)
|
||||
if err != nil {
|
||||
return nil, os.NewSyscallError("socket", err)
|
||||
}
|
||||
defer unix.Close(sfd)
|
||||
|
||||
var out []netip.Addr
|
||||
nameAllowed := make(map[int]bool) // by interface index, once named
|
||||
for _, a := range addrs {
|
||||
allow, named := nameAllowed[a.LinkIndex]
|
||||
if (named && !allow) || a.IPNet == nil {
|
||||
continue
|
||||
}
|
||||
addr, ok := allowedAddr(ctx, l, filter, a.IPNet)
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
if !named {
|
||||
name, err := interfaceNameByIndex(sfd, a.LinkIndex)
|
||||
// ENODEV means the interface went away after the dump. Any other failure is reported
|
||||
// and the interface skipped, so the rest are still returned.
|
||||
if err != nil && !errors.Is(err, unix.ENODEV) {
|
||||
errs = append(errs, fmt.Errorf("failed to resolve name of interface %d: %w", a.LinkIndex, err))
|
||||
}
|
||||
allow = err == nil && allowName(ctx, l, filter, name)
|
||||
nameAllowed[a.LinkIndex] = allow
|
||||
}
|
||||
if allow {
|
||||
out = append(out, addr)
|
||||
}
|
||||
}
|
||||
return out, errors.Join(errs...)
|
||||
}
|
||||
|
||||
// netlinkAddrList is netlink.AddrList over a socket that is never bound. The kernel autobinds it
|
||||
// on the first send, which the sandbox permits.
|
||||
func netlinkAddrList() ([]netlink.Addr, error) {
|
||||
fd, err := unix.Socket(unix.AF_NETLINK, unix.SOCK_RAW|unix.SOCK_CLOEXEC, unix.NETLINK_ROUTE)
|
||||
if err != nil {
|
||||
return nil, os.NewSyscallError("socket", err)
|
||||
}
|
||||
s, err := nl.NewNetlinkSocketFromFd(fd)
|
||||
if err != nil {
|
||||
unix.Close(fd)
|
||||
return nil, err
|
||||
}
|
||||
|
||||
h := netlink.NewHandleFromSockets(
|
||||
map[int]*nl.SocketHandle{unix.NETLINK_ROUTE: {Socket: s}},
|
||||
netlink.HandleOptions{RetryInterrupted: true},
|
||||
)
|
||||
defer h.Close()
|
||||
if err := h.SetSocketTimeout(netlink.GetSocketTimeout()); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
return h.AddrList(nil, netlink.FAMILY_ALL)
|
||||
}
|
||||
|
||||
// interfaceNameByIndex resolves an interface index with SIOCGIFNAME.
|
||||
func interfaceNameByIndex(fd int, index int) (string, error) {
|
||||
var ifr unix.Ifreq
|
||||
ifr.SetUint32(uint32(index)) // ifr_ifindex is in the ifr_ifru union
|
||||
if err := unix.IoctlIfreq(fd, unix.SIOCGIFNAME, &ifr); err != nil {
|
||||
return "", err
|
||||
}
|
||||
return ifr.Name(), nil
|
||||
}
|
||||
@@ -0,0 +1,59 @@
|
||||
package nicfinder
|
||||
|
||||
import (
|
||||
"context"
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
|
||||
"github.com/slackhq/nebula/logging"
|
||||
)
|
||||
|
||||
// Filter decides which interfaces, by name, and which of their addresses Find returns.
|
||||
type Filter interface {
|
||||
AllowName(string) bool
|
||||
Allow(netip.Addr) bool
|
||||
}
|
||||
|
||||
// Find returns the addresses of this host's network interfaces that allowList accepts, with
|
||||
// loopback and link-local addresses left out. When only some interfaces could be read it returns
|
||||
// their addresses alongside an error for the rest. allowList must not be nil; it is called as
|
||||
// given, so a nil pointer of a type whose methods accept a nil receiver is fine.
|
||||
func Find(ctx context.Context, l *slog.Logger, allowList Filter) ([]netip.Addr, error) {
|
||||
return localAddrs(ctx, l, allowList)
|
||||
}
|
||||
|
||||
// allowName asks filter about an interface name and traces the answer.
|
||||
func allowName(ctx context.Context, l *slog.Logger, filter Filter, name string) bool {
|
||||
allow := filter.AllowName(name)
|
||||
if l.Enabled(ctx, logging.LevelTrace) {
|
||||
l.Log(ctx, logging.LevelTrace, "localAllowList.AllowName", "interfaceName", name, "allow", allow)
|
||||
}
|
||||
return allow
|
||||
}
|
||||
|
||||
// allowedAddr converts one address a platform reports and says whether to advertise it: it must
|
||||
// be a *net.IPNet or *net.IPAddr carrying an IP, not be loopback or link-local, and be accepted by
|
||||
// filter, whose answer is traced. IPv4 comes back unmapped.
|
||||
func allowedAddr(ctx context.Context, l *slog.Logger, filter Filter, rawAddr net.Addr) (netip.Addr, bool) {
|
||||
var ip net.IP
|
||||
switch v := rawAddr.(type) {
|
||||
case *net.IPNet:
|
||||
ip = v.IP
|
||||
case *net.IPAddr:
|
||||
ip = v.IP
|
||||
}
|
||||
addr, ok := netip.AddrFromSlice(ip)
|
||||
if !ok {
|
||||
return netip.Addr{}, false
|
||||
}
|
||||
addr = addr.Unmap()
|
||||
if addr.IsLoopback() || addr.IsLinkLocalUnicast() {
|
||||
return netip.Addr{}, false
|
||||
}
|
||||
isAllowed := filter.Allow(addr)
|
||||
if l.Enabled(ctx, logging.LevelTrace) {
|
||||
l.Log(ctx, logging.LevelTrace, "localAllowList.Allow", "localAddr", addr, "allowed", isAllowed)
|
||||
}
|
||||
return addr, isAllowed
|
||||
}
|
||||
@@ -0,0 +1,117 @@
|
||||
package nicfinder
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net"
|
||||
"net/netip"
|
||||
"regexp"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
)
|
||||
|
||||
type allowAll struct{}
|
||||
|
||||
func (allowAll) Allow(netip.Addr) bool { return true }
|
||||
func (allowAll) AllowName(string) bool { return true }
|
||||
|
||||
type testAllowList struct {
|
||||
bannedName *regexp.Regexp
|
||||
bannedAddr netip.Addr
|
||||
}
|
||||
|
||||
func (l *testAllowList) Allow(addr netip.Addr) bool {
|
||||
return addr != l.bannedAddr
|
||||
}
|
||||
|
||||
func (l *testAllowList) AllowName(n string) bool {
|
||||
return !l.bannedName.MatchString(n)
|
||||
}
|
||||
|
||||
func newTestAllowList(bannedName string) *testAllowList {
|
||||
return &testAllowList{
|
||||
bannedName: regexp.MustCompile(bannedName),
|
||||
}
|
||||
}
|
||||
|
||||
func TestAllowedAddr(t *testing.T) {
|
||||
ctx, l := context.Background(), test.NewLogger()
|
||||
allowed := func(filter Filter, addrs []net.Addr) []netip.Addr {
|
||||
var out []netip.Addr
|
||||
for _, rawAddr := range addrs {
|
||||
if addr, ok := allowedAddr(ctx, l, filter, rawAddr); ok {
|
||||
out = append(out, addr)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
addrs := []net.Addr{
|
||||
&net.IPNet{IP: net.ParseIP("127.0.0.1"), Mask: net.CIDRMask(8, 32)},
|
||||
&net.IPNet{IP: net.ParseIP("::1"), Mask: net.CIDRMask(128, 128)},
|
||||
&net.IPNet{IP: net.ParseIP("10.0.0.5"), Mask: net.CIDRMask(24, 32)},
|
||||
&net.IPNet{IP: net.ParseIP("169.254.10.10"), Mask: net.CIDRMask(16, 32)},
|
||||
&net.IPNet{IP: net.ParseIP("fe80::1"), Mask: net.CIDRMask(64, 128)},
|
||||
&net.IPAddr{IP: net.ParseIP("fd00::5")},
|
||||
&net.IPNet{},
|
||||
otherAddr{},
|
||||
nil,
|
||||
}
|
||||
|
||||
// Loopback, link local and anything without an IP are dropped, and IPv4 comes back unmapped
|
||||
// even though net.ParseIP hands over a 16 byte slice.
|
||||
assert.Equal(t, []netip.Addr{
|
||||
netip.MustParseAddr("10.0.0.5"),
|
||||
netip.MustParseAddr("fd00::5"),
|
||||
}, allowed(allowAll{}, addrs))
|
||||
|
||||
// The filter sees the unmapped form and can drop a single address.
|
||||
al := newTestAllowList("none")
|
||||
al.bannedAddr = netip.MustParseAddr("10.0.0.5")
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("fd00::5")}, allowed(al, addrs))
|
||||
}
|
||||
|
||||
// otherAddr is a net.Addr that is neither *net.IPNet nor *net.IPAddr. netlink.Addr is one such
|
||||
// type: it satisfies net.Addr through an embedded *net.IPNet, and passing it directly once
|
||||
// silently produced no addresses.
|
||||
type otherAddr struct{}
|
||||
|
||||
func (otherAddr) Network() string { return "other" }
|
||||
func (otherAddr) String() string { return "other" }
|
||||
|
||||
// hostFilter counts AllowName calls and can reject every name or every address.
|
||||
type hostFilter struct {
|
||||
rejectNames bool
|
||||
rejectAddrs bool
|
||||
asked map[string]int
|
||||
}
|
||||
|
||||
func (f *hostFilter) Allow(netip.Addr) bool { return !f.rejectAddrs }
|
||||
func (f *hostFilter) AllowName(name string) bool {
|
||||
f.asked[name]++
|
||||
return !f.rejectNames
|
||||
}
|
||||
|
||||
// Runs this platform's localAddrs against the host and checks it honors the whole filter.
|
||||
func TestLocalAddrsAppliesFilter(t *testing.T) {
|
||||
ctx, l := context.Background(), test.NewLogger()
|
||||
|
||||
f := &hostFilter{asked: map[string]int{}}
|
||||
all, err := localAddrs(ctx, l, f)
|
||||
if len(f.asked) == 0 {
|
||||
t.Skipf("no interfaces to enumerate here: %v", err)
|
||||
}
|
||||
for name, n := range f.asked {
|
||||
assert.Equal(t, 1, n, "AllowName asked %d times for %s", n, name)
|
||||
}
|
||||
// Loopback and link-local never come back, whatever the filter says.
|
||||
for _, addr := range all {
|
||||
assert.False(t, addr.IsLoopback() || addr.IsLinkLocalUnicast(), "%s", addr)
|
||||
}
|
||||
|
||||
none, _ := localAddrs(ctx, l, &hostFilter{rejectNames: true, asked: map[string]int{}})
|
||||
assert.Empty(t, none, "addresses got past a filter that rejects every interface name")
|
||||
|
||||
none, _ = localAddrs(ctx, l, &hostFilter{rejectAddrs: true, asked: map[string]int{}})
|
||||
assert.Empty(t, none, "addresses got past a filter that rejects every address")
|
||||
}
|
||||
+73
-10
@@ -2,13 +2,14 @@ package noiseutil
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"crypto/aes"
|
||||
"crypto/cipher"
|
||||
"crypto/fips140"
|
||||
"encoding/binary"
|
||||
"errors"
|
||||
"fmt"
|
||||
"reflect"
|
||||
"runtime"
|
||||
"unsafe"
|
||||
|
||||
// unsafe needed for go:linkname
|
||||
_ "crypto/tls"
|
||||
@@ -17,6 +18,16 @@ import (
|
||||
"github.com/flynn/noise"
|
||||
)
|
||||
|
||||
// TODO: Use NewGCMWithCounterNonce or NewGCMForQUIC once available:
|
||||
// - https://github.com/golang/go/issues/73110
|
||||
// - https://github.com/golang/go/issues/79219
|
||||
// Using tls.aeadAESGCMTLS13 gives us the TLS 1.3 GCM, which also verifies
|
||||
// that the nonce is strictly increasing. This works for both boringcrypto
|
||||
// and fips140.
|
||||
//
|
||||
//go:linkname aeadAESGCMTLS13 crypto/tls.aeadAESGCMTLS13
|
||||
func aeadAESGCMTLS13(key, noncePrefix []byte) cipher.AEAD
|
||||
|
||||
type cipherFn struct {
|
||||
fn func([32]byte) noise.Cipher
|
||||
name string
|
||||
@@ -32,14 +43,8 @@ var CipherAESGCMFIPS140 noise.CipherFunc = cipherFn{cipherAESGCMFIPS140, "AESGCM
|
||||
var emptyNonce = []byte{0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}
|
||||
|
||||
func cipherAESGCMFIPS140(k [32]byte) noise.Cipher {
|
||||
c, err := aes.NewCipher(k[:])
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
gcm, err := cipher.NewGCMWithCounterNonce(c)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
gcm := aeadAESGCMTLS13(k[:], emptyNonce)
|
||||
gcm = extractFIPSAEAD(gcm)
|
||||
return &aeadGCMFIPS140Cipher{
|
||||
AEAD: gcm,
|
||||
}
|
||||
@@ -47,6 +52,57 @@ func cipherAESGCMFIPS140(k [32]byte) noise.Cipher {
|
||||
|
||||
type aeadGCMFIPS140Cipher struct {
|
||||
cipher.AEAD
|
||||
ready bool
|
||||
}
|
||||
|
||||
// Extract the internal FIPS GCM implementation from the tls wrapper. The TLS
|
||||
// wrapper is not thread safe around Open, so instead of locking around it we
|
||||
// can grab the internal implementation that is thread safe. This is the FIPS
|
||||
// module implementation: `crypto/internal/fips140/aes/gcm.GCMWithXORCounterNonce`
|
||||
//
|
||||
// - https://github.com/golang/go/blob/go1.26.4/src/crypto/internal/fips140/aes/gcm/gcm_nonces.go#L212-L287
|
||||
//
|
||||
// The wrapper is struct `crypto/tls.xorNonceAEAD` , with field `aead`:
|
||||
//
|
||||
// - https://github.com/golang/go/blob/go1.26.4/src/crypto/tls/cipher_suites.go#L482-L487
|
||||
//
|
||||
// This can be cleaned up once these FIPS implementations are exposed directly:
|
||||
//
|
||||
// - https://github.com/golang/go/issues/73110
|
||||
func extractFIPSAEAD(xorNonceAEAD cipher.AEAD) cipher.AEAD {
|
||||
r := reflect.ValueOf(xorNonceAEAD)
|
||||
v := r.Elem().FieldByName("aead")
|
||||
if !v.IsValid() {
|
||||
// The internal crypto/tls.xorNonceAEAD struct no longer has an `aead`
|
||||
// field. This can only happen on a Go version this code was not built
|
||||
// against; the package init() self-test guards against ever reaching
|
||||
// this at runtime, so this is a defensive fail-fast.
|
||||
panic(fmt.Sprintf("noiseutil: could not extract FIPS AEAD from %T on %s: no `aead` field (incompatible Go version)", xorNonceAEAD, runtime.Version()))
|
||||
}
|
||||
v2 := reflect.NewAt(v.Type(), unsafe.Pointer(v.UnsafeAddr())).Elem()
|
||||
aead, ok := v2.Interface().(cipher.AEAD)
|
||||
if !ok {
|
||||
panic(fmt.Sprintf("noiseutil: extracted FIPS `aead` field is %s, not a cipher.AEAD, on %s (incompatible Go version)", v2.Type(), runtime.Version()))
|
||||
}
|
||||
return aead
|
||||
}
|
||||
|
||||
func (c *aeadGCMFIPS140Cipher) init(nonce []byte) {
|
||||
// GCMWithXORCounterNonce expects that the first call to Seal
|
||||
// is with a counter of `0`, this is how it extracts the nonce mask.
|
||||
// We can clean this up in the future when NewGCMWithCounterNonce or
|
||||
// NewGCMForQUIC are available:
|
||||
if !bytes.Equal(emptyNonce, nonce) {
|
||||
c.AEAD.Seal([]byte{}, emptyNonce, []byte{}, []byte{})
|
||||
}
|
||||
c.ready = true
|
||||
}
|
||||
|
||||
func (c *aeadGCMFIPS140Cipher) Seal(dst, nonce, plaintext, additionalData []byte) []byte {
|
||||
if !c.ready {
|
||||
c.init(nonce)
|
||||
}
|
||||
return c.AEAD.Seal(dst, nonce, plaintext, additionalData)
|
||||
}
|
||||
|
||||
func (c *aeadGCMFIPS140Cipher) Encrypt(out []byte, n uint64, ad, plaintext []byte) []byte {
|
||||
@@ -77,8 +133,15 @@ func (c *aeadGCMFIPS140Cipher) DecryptDanger(out, ad, ciphertext []byte, n uint6
|
||||
return c.Open(out, nb, ciphertext, ad)
|
||||
}
|
||||
|
||||
func (c *aeadGCMFIPS140Cipher) Overhead() int {
|
||||
if c == nil {
|
||||
return 0
|
||||
}
|
||||
return c.AEAD.Overhead()
|
||||
}
|
||||
|
||||
func aeadGCMFIPS140CipherNonce(n uint64) []byte {
|
||||
// GCMWithCounterNonce uses a 4 byte static prefix and an 8 byte nonce
|
||||
// GCMWithXORCounterNonce uses a 4 byte static prefix and an 8 byte nonce
|
||||
var nonce [12]byte
|
||||
binary.BigEndian.PutUint64(nonce[4:], n)
|
||||
return nonce[:]
|
||||
|
||||
+10
-5
@@ -263,11 +263,16 @@ 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) {
|
||||
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)
|
||||
// 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
|
||||
}
|
||||
|
||||
// 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
|
||||
@@ -354,7 +359,7 @@ func parseV6(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
|
||||
// and cannot drift into misreading an unknown protocol (SCTP, GRE, etc.) as a forged transport.
|
||||
proto, offset, isFragment, anyFragment, err := iputil.IPv6FindUpperProtocol(data)
|
||||
if err != nil {
|
||||
return ErrIPv6PacketTooShort
|
||||
return err
|
||||
}
|
||||
|
||||
fp.Protocol = proto
|
||||
|
||||
+7
-7
@@ -117,7 +117,7 @@ func Test_newPacket_v6(t *testing.T) {
|
||||
require.NoError(t, err)
|
||||
|
||||
err = newPacket(buffer.Bytes(), true, p)
|
||||
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
||||
|
||||
// A v6 packet with a hop-by-hop extension
|
||||
// ICMPv6 Payload (Echo Request)
|
||||
@@ -151,12 +151,12 @@ func Test_newPacket_v6(t *testing.T) {
|
||||
// A full IPv6 header and 1 byte in the first extension, but missing
|
||||
// the length byte.
|
||||
err = newPacket(buffer.Bytes()[:41], true, p)
|
||||
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
||||
|
||||
// A full IPv6 header plus 1 full extension, but only 1 byte of the
|
||||
// next layer, missing length byte
|
||||
err = newPacket(buffer.Bytes()[:49], true, p)
|
||||
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
||||
err = nil
|
||||
|
||||
// A good ICMP packet
|
||||
@@ -354,12 +354,12 @@ func Test_newPacket_v6(t *testing.T) {
|
||||
|
||||
// Ensure buffer bounds checking during processing, a truncated AH header can't reach the payload
|
||||
err = newPacket(b[:41], true, p)
|
||||
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
||||
|
||||
// Invalid AH header
|
||||
b = buffer.Bytes()
|
||||
err = newPacket(b, true, p)
|
||||
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
||||
}
|
||||
|
||||
func Test_newPacket_ipv6Fragment(t *testing.T) {
|
||||
@@ -466,7 +466,7 @@ func Test_newPacket_ipv6Fragment(t *testing.T) {
|
||||
|
||||
// Too short of a fragment packet
|
||||
err = newPacket(secondFrag[:len(secondFrag)-10], false, p)
|
||||
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
||||
}
|
||||
|
||||
func BenchmarkParseV6(b *testing.B) {
|
||||
@@ -707,7 +707,7 @@ func Test_newPacket_v6ExtHeaderPastBuffer(t *testing.T) {
|
||||
pkt[40] = byte(layers.IPProtocolSCTP) // Dest Options next header = SCTP
|
||||
pkt[41] = 255 // declared length (255+1)*8 = 2048, past the 48 byte buffer
|
||||
|
||||
require.ErrorIs(t, newPacket(pkt, true, p), ErrIPv6PacketTooShort)
|
||||
require.ErrorIs(t, newPacket(pkt, true, p), iputil.ErrIPv6CouldNotFindPayload)
|
||||
}
|
||||
|
||||
// Test_newPacket_v6ExtHeaderConfusion is a regression test for parseV6 walking any unrecognized
|
||||
|
||||
@@ -0,0 +1,57 @@
|
||||
//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
|
||||
}
|
||||
+61
-3
@@ -29,7 +29,10 @@ type tun struct {
|
||||
Routes atomic.Pointer[[]Route]
|
||||
routeTree atomic.Pointer[bart.Table[routing.Gateways]]
|
||||
linkAddr *netroute.LinkAddr
|
||||
l *slog.Logger
|
||||
// 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
|
||||
}
|
||||
|
||||
type ifReq struct {
|
||||
@@ -149,8 +152,48 @@ func (t *tun) deviceBytes() (o [16]byte) {
|
||||
return
|
||||
}
|
||||
|
||||
func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
|
||||
return nil, fmt.Errorf("newTunFromFd not supported in Darwin")
|
||||
// newTunFromFd adopts a utun the host already created and configured, which is how a darwin
|
||||
// network extension is handed its device. Everything about moving packets is shared with newTun,
|
||||
// only the setup differs: the host owns addressing and routing here.
|
||||
func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip.Prefix) (*tun, error) {
|
||||
if err := unix.SetNonblock(deviceFd, true); err != nil {
|
||||
// We own the fd from the moment it is handed to us
|
||||
_ = unix.Close(deviceFd)
|
||||
return nil, fmt.Errorf("failed to set the tun fd to non-blocking mode: %w", err)
|
||||
}
|
||||
|
||||
file := os.NewFile(uintptr(deviceFd), "/dev/tun")
|
||||
t := &tun{
|
||||
f: file,
|
||||
Device: utunNameFromFd(deviceFd),
|
||||
vpnNetworks: vpnNetworks,
|
||||
DefaultMTU: c.GetInt("tun.mtu", DefaultMTU),
|
||||
hostOwned: true,
|
||||
l: l,
|
||||
}
|
||||
|
||||
if err := t.reload(c, true); err != nil {
|
||||
_ = file.Close()
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
if err := t.reload(c, false); err != nil {
|
||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
||||
}
|
||||
})
|
||||
|
||||
return t, nil
|
||||
}
|
||||
|
||||
// utunNameFromFd asks the socket what interface it is, for logs. A blank name is not worth
|
||||
// failing a tunnel over, so an error just leaves it empty.
|
||||
func utunNameFromFd(fd int) string {
|
||||
name, err := unix.GetsockoptString(fd, unix.AF_SYS_CONTROL, _UTUN_OPT_IFNAME)
|
||||
if err != nil {
|
||||
return ""
|
||||
}
|
||||
return name
|
||||
}
|
||||
|
||||
func (t *tun) Close() error {
|
||||
@@ -161,6 +204,12 @@ func (t *tun) Close() error {
|
||||
}
|
||||
|
||||
func (t *tun) Activate() error {
|
||||
// The host handed us a configured device. Its addresses, mtu and routes come from the network
|
||||
// settings it applied, and a sandboxed extension cannot change them anyway.
|
||||
if t.hostOwned {
|
||||
return nil
|
||||
}
|
||||
|
||||
devName := t.deviceBytes()
|
||||
|
||||
s, err := unix.Socket(
|
||||
@@ -374,6 +423,11 @@ func getLinkAddr(name string) (*netroute.LinkAddr, error) {
|
||||
}
|
||||
|
||||
func (t *tun) addRoutes(logErrors bool) error {
|
||||
// The route tree is still ours, the system routing table is not
|
||||
if t.hostOwned {
|
||||
return nil
|
||||
}
|
||||
|
||||
routes := *t.Routes.Load()
|
||||
|
||||
for _, r := range routes {
|
||||
@@ -403,6 +457,10 @@ func (t *tun) addRoutes(logErrors bool) error {
|
||||
}
|
||||
|
||||
func (t *tun) removeRoutes(routes []Route) error {
|
||||
if t.hostOwned {
|
||||
return nil
|
||||
}
|
||||
|
||||
for _, r := range routes {
|
||||
if !r.Install {
|
||||
continue
|
||||
|
||||
+11
-2
@@ -15,12 +15,12 @@ import (
|
||||
"time"
|
||||
"unsafe"
|
||||
|
||||
"github.com/DefinedNet/netlink"
|
||||
"github.com/gaissmai/bart"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/overlay/tio"
|
||||
"github.com/slackhq/nebula/routing"
|
||||
"github.com/slackhq/nebula/util"
|
||||
"github.com/vishvananda/netlink"
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
@@ -253,6 +253,15 @@ func (t *tun) reload(c *config.C, initial bool) 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(c, t.vpnNetworks, true)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
routeTree, err := makeRouteTree(t.l, routes, true)
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -274,7 +283,7 @@ func (t *tun) reload(c *config.C, initial bool) error {
|
||||
routes[i].MTU = newDefaultMTU
|
||||
}
|
||||
|
||||
if r.MTU > t.MaxMTU {
|
||||
if r.MTU > newMaxMTU {
|
||||
newMaxMTU = r.MTU
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,56 @@
|
||||
//go:build !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"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))
|
||||
|
||||
require.NoError(t, c.ReloadConfigString("tun:\n mtu: 1400\n"+routes))
|
||||
_ = tn.reload(c, false)
|
||||
|
||||
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))
|
||||
assert.Equal(t, 1500, tn.MaxMTU)
|
||||
assert.Equal(t, 1300, tn.DefaultMTU)
|
||||
}
|
||||
@@ -104,6 +104,9 @@ 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) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
|
||||
@@ -0,0 +1,91 @@
|
||||
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
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,264 @@
|
||||
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())
|
||||
}
|
||||
}
|
||||
@@ -684,10 +684,14 @@ func sshCreateTunnel(ifce *Interface, fs any, a []string, w sshd.StringWriter) e
|
||||
}
|
||||
}
|
||||
|
||||
hostInfo = ifce.handshakeManager.StartHandshake(vpnAddr, nil)
|
||||
if addr.IsValid() {
|
||||
hostInfo.SetRemote(addr)
|
||||
}
|
||||
// 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")
|
||||
}
|
||||
|
||||
@@ -38,6 +38,11 @@ type statsServer struct {
|
||||
runMu sync.Mutex
|
||||
runCfg *statsConfig
|
||||
run *statsRuntime // non-nil while a runtime is live
|
||||
// Closed when the last runtime's capture loop has returned. Stop waits on it so nothing captures once it returns,
|
||||
// and a reload's new runtime never overlaps the old one, go-metrics keeps its GC capture state in unguarded globals
|
||||
loopDone chan struct{}
|
||||
// See newStatsServerFromConfig, never changes after it
|
||||
emitStats func()
|
||||
}
|
||||
|
||||
// statsRuntime is the live state owned by a single Start invocation. Start
|
||||
@@ -82,12 +87,16 @@ type promConfig struct {
|
||||
//
|
||||
// Start is safe to call unconditionally: it no-ops when stats are disabled.
|
||||
// The returned pointer is always non-nil, even on error.
|
||||
func newStatsServerFromConfig(ctx context.Context, l *slog.Logger, c *config.C, buildVersion string, configTest bool) (*statsServer, error) {
|
||||
//
|
||||
// emitStats, if set, updates metrics on every capture, ahead of the exporters so each export sees what it just set. It
|
||||
// is fixed here, before the reload callback exists, so every runtime has it.
|
||||
func newStatsServerFromConfig(ctx context.Context, l *slog.Logger, c *config.C, buildVersion string, configTest bool, emitStats func()) (*statsServer, error) {
|
||||
s := &statsServer{
|
||||
l: l,
|
||||
ctx: ctx,
|
||||
buildVersion: buildVersion,
|
||||
configTest: configTest,
|
||||
emitStats: emitStats,
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
@@ -120,7 +129,6 @@ func (s *statsServer) reload(c *config.C, initial bool) error {
|
||||
s.runMu.Lock()
|
||||
sameCfg := s.runCfg != nil && *s.runCfg == newCfg
|
||||
s.runCfg = &newCfg
|
||||
running := s.run != nil
|
||||
s.runMu.Unlock()
|
||||
|
||||
s.enabled.Store(enabled)
|
||||
@@ -129,9 +137,8 @@ func (s *statsServer) reload(c *config.C, initial bool) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
if running {
|
||||
s.Stop()
|
||||
}
|
||||
// Even with nothing running, a runtime whose listener failed can still be finishing its last pass
|
||||
s.Stop()
|
||||
if enabled && !s.configTest {
|
||||
go s.Start()
|
||||
}
|
||||
@@ -153,13 +160,19 @@ func (s *statsServer) Start() {
|
||||
return
|
||||
}
|
||||
cfg := *s.runCfg
|
||||
captureFns, listener := s.buildRuntime(cfg)
|
||||
runCtx, cancel := context.WithCancel(s.ctx)
|
||||
captureFns, listener := s.buildRuntime(runCtx, cfg)
|
||||
rt := &statsRuntime{cancel: cancel, listener: listener}
|
||||
s.run = rt
|
||||
done := make(chan struct{})
|
||||
s.loopDone = done
|
||||
s.runMu.Unlock()
|
||||
|
||||
go captureStatsLoop(runCtx, cfg.interval, captureFns)
|
||||
// Prime before serving, so a scrape that lands before the first tick sees real values instead of zeros (issue #907)
|
||||
for _, fn := range captureFns {
|
||||
fn()
|
||||
}
|
||||
go captureStatsLoop(runCtx, cfg.interval, captureFns, done)
|
||||
|
||||
cleanExit := true
|
||||
if listener == nil {
|
||||
@@ -218,26 +231,32 @@ func (s *statsServer) serveListener(listener *http.Server) bool {
|
||||
|
||||
// Stop tears down the active runtime, if any. Idempotent.
|
||||
func (s *statsServer) Stop() {
|
||||
// Held until the last pass is done, a Start that slipped in after s.run cleared would capture alongside it
|
||||
s.runMu.Lock()
|
||||
defer s.runMu.Unlock()
|
||||
rt := s.run
|
||||
s.run = nil
|
||||
s.runMu.Unlock()
|
||||
if rt == nil {
|
||||
return
|
||||
}
|
||||
rt.cancel()
|
||||
if rt.listener != nil {
|
||||
shutdownCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
|
||||
if err := rt.listener.Shutdown(shutdownCtx); err != nil {
|
||||
s.l.Warn("Failed to shut down prometheus stats listener", "error", err)
|
||||
if rt != nil {
|
||||
rt.cancel()
|
||||
if rt.listener != nil {
|
||||
shutdownCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
|
||||
if err := rt.listener.Shutdown(shutdownCtx); err != nil {
|
||||
s.l.Warn("Failed to shut down prometheus stats listener", "error", err)
|
||||
}
|
||||
cancel()
|
||||
}
|
||||
cancel()
|
||||
}
|
||||
// Nothing captures once Stop returns. The last runtime is cancelled by now, whoever cleared it, so this is at most
|
||||
// the pass it was in. Nothing in a pass takes runMu
|
||||
if s.loopDone != nil {
|
||||
<-s.loopDone
|
||||
}
|
||||
}
|
||||
|
||||
// buildRuntime produces the capture functions and, for prometheus, an un-served
|
||||
// http.Server from cfg. cfg has already been validated by loadStatsConfig.
|
||||
func (s *statsServer) buildRuntime(cfg statsConfig) ([]func(), *http.Server) {
|
||||
// A graphite send in progress is abandoned when ctx is done.
|
||||
func (s *statsServer) buildRuntime(ctx context.Context, cfg statsConfig) ([]func(), *http.Server) {
|
||||
// rcrowley/go-metrics guards these registrations with a private sync.Once,
|
||||
// so subsequent reloads are no-ops.
|
||||
metrics.RegisterDebugGCStats(metrics.DefaultRegistry)
|
||||
@@ -247,6 +266,9 @@ func (s *statsServer) buildRuntime(cfg statsConfig) ([]func(), *http.Server) {
|
||||
func() { metrics.CaptureDebugGCStatsOnce(metrics.DefaultRegistry) },
|
||||
func() { metrics.CaptureRuntimeMemStatsOnce(metrics.DefaultRegistry) },
|
||||
}
|
||||
if s.emitStats != nil {
|
||||
captureFns = append(captureFns, s.emitStats)
|
||||
}
|
||||
|
||||
switch cfg.typ {
|
||||
case "graphite":
|
||||
@@ -262,7 +284,7 @@ func (s *statsServer) buildRuntime(cfg statsConfig) ([]func(), *http.Server) {
|
||||
Percentiles: []float64{0.5, 0.75, 0.95, 0.99, 0.999},
|
||||
}
|
||||
captureFns = append(captureFns, func() {
|
||||
if err := graphiteOnce(gcfg); err != nil {
|
||||
if err := graphiteOnce(ctx, gcfg, graphiteTimeout); err != nil && ctx.Err() == nil {
|
||||
s.l.Error("Graphite export failed", "error", err)
|
||||
}
|
||||
})
|
||||
@@ -309,8 +331,10 @@ func (s *statsServer) buildRuntime(cfg statsConfig) ([]func(), *http.Server) {
|
||||
return captureFns, nil
|
||||
}
|
||||
|
||||
// captureStatsLoop runs each fn on every tick of d until ctx is cancelled.
|
||||
func captureStatsLoop(ctx context.Context, d time.Duration, fns []func()) {
|
||||
// captureStatsLoop runs each fn on every tick of d until ctx is cancelled, then
|
||||
// closes done.
|
||||
func captureStatsLoop(ctx context.Context, d time.Duration, fns []func(), done chan struct{}) {
|
||||
defer close(done)
|
||||
t := time.NewTicker(d)
|
||||
defer t.Stop()
|
||||
for {
|
||||
|
||||
+294
-29
@@ -2,13 +2,18 @@ package nebula
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"io"
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"strconv"
|
||||
"sync/atomic"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
@@ -110,15 +115,14 @@ func TestStatsServer_reload_initial_prometheus(t *testing.T) {
|
||||
}
|
||||
|
||||
func TestStatsServer_Start_graphite_blocksUntilStop(t *testing.T) {
|
||||
sink := newGraphiteSink(t)
|
||||
defer sink.Close()
|
||||
h := newGraphiteHost(t, 0)
|
||||
|
||||
s, c := newTestStatsServer(t)
|
||||
setStatsConfig(c, map[string]any{
|
||||
"type": "graphite",
|
||||
"interval": "1s",
|
||||
"protocol": "tcp",
|
||||
"host": sink.Addr(),
|
||||
"host": h.ln.Addr().String(),
|
||||
"prefix": "test",
|
||||
})
|
||||
require.NoError(t, s.reload(c, true))
|
||||
@@ -371,35 +375,19 @@ func waitForListening(t *testing.T, addr string) {
|
||||
})
|
||||
}
|
||||
|
||||
// graphiteSink is a minimal TCP accept-and-discard server so graphiteOnce
|
||||
// calls in tests don't spam error logs or wedge on connection refused.
|
||||
type graphiteSink struct {
|
||||
ln net.Listener
|
||||
}
|
||||
|
||||
func newGraphiteSink(t *testing.T) *graphiteSink {
|
||||
t.Helper()
|
||||
ln, err := net.Listen("tcp", "127.0.0.1:0")
|
||||
require.NoError(t, err)
|
||||
g := &graphiteSink{ln: ln}
|
||||
go func() {
|
||||
for {
|
||||
conn, err := ln.Accept()
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
go func(c net.Conn) {
|
||||
_, _ = io.Copy(io.Discard, c)
|
||||
_ = c.Close()
|
||||
}(conn)
|
||||
// stopAtCleanup returns the ctx to build *s with, and stops it when the test ends. Cancelling first turns away a Start
|
||||
// a reload spawned that hasn't run yet, then Stop waits out the last pass, so nothing captures into the next test
|
||||
func stopAtCleanup(t *testing.T, s **statsServer) context.Context {
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
t.Cleanup(func() {
|
||||
cancel()
|
||||
if *s != nil {
|
||||
(*s).Stop()
|
||||
}
|
||||
}()
|
||||
return g
|
||||
})
|
||||
return ctx
|
||||
}
|
||||
|
||||
func (g *graphiteSink) Addr() string { return g.ln.Addr().String() }
|
||||
func (g *graphiteSink) Close() { _ = g.ln.Close() }
|
||||
|
||||
func freeTCPPort(t *testing.T) string {
|
||||
t.Helper()
|
||||
ln, err := net.Listen("tcp", "127.0.0.1:0")
|
||||
@@ -408,3 +396,280 @@ func freeTCPPort(t *testing.T) string {
|
||||
require.NoError(t, ln.Close())
|
||||
return strconv.Itoa(port)
|
||||
}
|
||||
|
||||
// Each export has to see what emitStats set in the same pass
|
||||
func TestStatsServer_emitStatsRunsBeforeExport(t *testing.T) {
|
||||
defer metrics.DefaultRegistry.Unregister("emitter.order.test")
|
||||
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
setStatsConfig(c, map[string]any{
|
||||
"type": "prometheus",
|
||||
"interval": "1s",
|
||||
"listen": "127.0.0.1:0",
|
||||
"path": "/metrics",
|
||||
})
|
||||
gauge := metrics.GetOrRegisterGauge("emitter.order.test", nil)
|
||||
s, err := newStatsServerFromConfig(t.Context(), l, c, "", false, func() { gauge.Update(42) })
|
||||
require.NoError(t, err)
|
||||
|
||||
s.runMu.Lock()
|
||||
fns, srv := s.buildRuntime(t.Context(), *s.runCfg)
|
||||
s.runMu.Unlock()
|
||||
require.NotNil(t, srv)
|
||||
for _, fn := range fns {
|
||||
fn()
|
||||
}
|
||||
|
||||
rec := httptest.NewRecorder()
|
||||
srv.Handler.ServeHTTP(rec, httptest.NewRequest("GET", "/metrics", nil))
|
||||
assert.Contains(t, rec.Body.String(), "emitter_order_test 42")
|
||||
}
|
||||
|
||||
// A scrape that lands the moment the listener is up already sees what emitStats set (issue #907)
|
||||
func TestStatsServer_Start_primesBeforeServing(t *testing.T) {
|
||||
defer metrics.DefaultRegistry.Unregister("prime.before.serving")
|
||||
|
||||
port := freeTCPPort(t)
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
setStatsConfig(c, map[string]any{
|
||||
"type": "prometheus",
|
||||
"interval": "1h",
|
||||
"listen": "127.0.0.1:" + port,
|
||||
"path": "/metrics",
|
||||
})
|
||||
gauge := metrics.GetOrRegisterGauge("prime.before.serving", nil)
|
||||
// The pause would let a listener that came up before the prime serve the zero value
|
||||
var s *statsServer
|
||||
ctx := stopAtCleanup(t, &s)
|
||||
s, err := newStatsServerFromConfig(ctx, l, c, "", false, func() {
|
||||
time.Sleep(200 * time.Millisecond)
|
||||
gauge.Update(42)
|
||||
})
|
||||
require.NoError(t, err)
|
||||
|
||||
go s.Start()
|
||||
waitForListening(t, "127.0.0.1:"+port)
|
||||
|
||||
resp, err := http.Get("http://127.0.0.1:" + port + "/metrics")
|
||||
require.NoError(t, err)
|
||||
defer resp.Body.Close()
|
||||
body, err := io.ReadAll(resp.Body)
|
||||
require.NoError(t, err)
|
||||
assert.Contains(t, string(body), "prime_before_serving 42")
|
||||
}
|
||||
|
||||
// Start captures once before the first tick, the interval here is an hour
|
||||
func TestStatsServer_Start_primes(t *testing.T) {
|
||||
ln, err := net.Listen("tcp", "127.0.0.1:0")
|
||||
require.NoError(t, err)
|
||||
defer ln.Close()
|
||||
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": ln.Addr().String()})
|
||||
primed := make(chan struct{}, 1)
|
||||
var s *statsServer
|
||||
ctx := stopAtCleanup(t, &s)
|
||||
s, err = newStatsServerFromConfig(ctx, l, c, "", false, func() {
|
||||
select {
|
||||
case primed <- struct{}{}:
|
||||
default:
|
||||
}
|
||||
})
|
||||
require.NoError(t, err)
|
||||
|
||||
go s.Start()
|
||||
select {
|
||||
case <-primed:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("nothing was captured before the first tick")
|
||||
}
|
||||
}
|
||||
|
||||
// Graphite has to ship what emitStats set in the same pass, not the pass before
|
||||
func TestStatsServer_emitStatsRunsBeforeGraphiteExport(t *testing.T) {
|
||||
defer metrics.DefaultRegistry.Unregister("emitter.graphite.test")
|
||||
|
||||
ln, err := net.Listen("tcp", "127.0.0.1:0")
|
||||
require.NoError(t, err)
|
||||
defer ln.Close()
|
||||
received := make(chan string, 1)
|
||||
go func() {
|
||||
conn, err := ln.Accept()
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
defer conn.Close()
|
||||
b, _ := io.ReadAll(conn)
|
||||
received <- string(b)
|
||||
}()
|
||||
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": ln.Addr().String()})
|
||||
gauge := metrics.GetOrRegisterGauge("emitter.graphite.test", nil)
|
||||
s, err := newStatsServerFromConfig(t.Context(), l, c, "", false, func() { gauge.Update(42) })
|
||||
require.NoError(t, err)
|
||||
|
||||
s.runMu.Lock()
|
||||
fns, _ := s.buildRuntime(t.Context(), *s.runCfg)
|
||||
s.runMu.Unlock()
|
||||
for _, fn := range fns {
|
||||
fn()
|
||||
}
|
||||
|
||||
select {
|
||||
case body := <-received:
|
||||
assert.Contains(t, body, ".emitter.graphite.test.value 42 ")
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("graphite sent nothing")
|
||||
}
|
||||
}
|
||||
|
||||
// stats.interval reloads, and the runtime a reload starts still has emitStats
|
||||
func TestStatsServer_reloadMovesTheInterval(t *testing.T) {
|
||||
var passes atomic.Int64
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
// Nothing listens here, each export fails at once
|
||||
host := "127.0.0.1:" + freeTCPPort(t)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": host})
|
||||
var s *statsServer
|
||||
ctx := stopAtCleanup(t, &s)
|
||||
s, err := newStatsServerFromConfig(ctx, l, c, "", false, func() { passes.Add(1) })
|
||||
require.NoError(t, err)
|
||||
go s.Start()
|
||||
waitFor(t, func() bool { return passes.Load() == 1 })
|
||||
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "20ms", "host": host})
|
||||
require.NoError(t, s.reload(c, false))
|
||||
waitFor(t, func() bool { return passes.Load() >= 6 })
|
||||
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": host})
|
||||
require.NoError(t, s.reload(c, false))
|
||||
// The reload's Stop waited out the 20ms loop. The new runtime's prime may land either side of this read, it is the
|
||||
// only pass left to come
|
||||
stopped := passes.Load()
|
||||
time.Sleep(300 * time.Millisecond)
|
||||
assert.LessOrEqual(t, passes.Load()-stopped, int64(1), "the 20ms loop kept running after the reload")
|
||||
}
|
||||
|
||||
// A reload's new runtime never captures while the old one is still in a pass, go-metrics keeps its GC capture state
|
||||
// in unguarded globals
|
||||
func TestStatsServer_reloadWaitsForTheLastPass(t *testing.T) {
|
||||
var active, most atomic.Int64
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
host := "127.0.0.1:" + freeTCPPort(t)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "10ms", "host": host})
|
||||
var s *statsServer
|
||||
ctx := stopAtCleanup(t, &s)
|
||||
s, err := newStatsServerFromConfig(ctx, l, c, "", false, func() {
|
||||
n := active.Add(1)
|
||||
for {
|
||||
m := most.Load()
|
||||
if n <= m || most.CompareAndSwap(m, n) {
|
||||
break
|
||||
}
|
||||
}
|
||||
// Long enough that a reload almost always lands mid pass
|
||||
time.Sleep(50 * time.Millisecond)
|
||||
active.Add(-1)
|
||||
})
|
||||
require.NoError(t, err)
|
||||
go s.Start()
|
||||
|
||||
for i := range 6 {
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": fmt.Sprintf("%dms", 11-i%2), "host": host})
|
||||
require.NoError(t, s.reload(c, false))
|
||||
time.Sleep(30 * time.Millisecond)
|
||||
}
|
||||
assert.Equal(t, int64(1), most.Load())
|
||||
}
|
||||
|
||||
// Nothing captures once Stop returns, a pass in progress is waited out
|
||||
func TestStatsServer_Stop_waitsForThePass(t *testing.T) {
|
||||
var inPass atomic.Bool
|
||||
entered := make(chan struct{}, 1)
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": "127.0.0.1:" + freeTCPPort(t)})
|
||||
var s *statsServer
|
||||
ctx := stopAtCleanup(t, &s)
|
||||
s, err := newStatsServerFromConfig(ctx, l, c, "", false, func() {
|
||||
inPass.Store(true)
|
||||
select {
|
||||
case entered <- struct{}{}:
|
||||
default:
|
||||
}
|
||||
time.Sleep(100 * time.Millisecond)
|
||||
inPass.Store(false)
|
||||
})
|
||||
require.NoError(t, err)
|
||||
|
||||
go s.Start()
|
||||
select {
|
||||
case <-entered:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("never captured")
|
||||
}
|
||||
s.Stop()
|
||||
assert.False(t, inPass.Load(), "Stop returned with a pass still running")
|
||||
}
|
||||
|
||||
// A Start that arrives while Stop waits out the last pass doesn't capture alongside it
|
||||
func TestStatsServer_Start_duringStopWaitsForThePass(t *testing.T) {
|
||||
var active, most atomic.Int64
|
||||
entered := make(chan struct{}, 1)
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": "127.0.0.1:" + freeTCPPort(t)})
|
||||
var s *statsServer
|
||||
ctx := stopAtCleanup(t, &s)
|
||||
s, err := newStatsServerFromConfig(ctx, l, c, "", false, func() {
|
||||
n := active.Add(1)
|
||||
for {
|
||||
m := most.Load()
|
||||
if n <= m || most.CompareAndSwap(m, n) {
|
||||
break
|
||||
}
|
||||
}
|
||||
select {
|
||||
case entered <- struct{}{}:
|
||||
default:
|
||||
}
|
||||
time.Sleep(200 * time.Millisecond)
|
||||
active.Add(-1)
|
||||
})
|
||||
require.NoError(t, err)
|
||||
|
||||
go s.Start()
|
||||
select {
|
||||
case <-entered:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("never captured")
|
||||
}
|
||||
stopped := make(chan struct{})
|
||||
go func() {
|
||||
s.Stop()
|
||||
close(stopped)
|
||||
}()
|
||||
// Stop holds runMu for its whole wait, the next Start has to arrive after it took it
|
||||
waitFor(t, func() bool {
|
||||
if s.runMu.TryLock() {
|
||||
s.runMu.Unlock()
|
||||
return false
|
||||
}
|
||||
return true
|
||||
})
|
||||
go s.Start()
|
||||
select {
|
||||
case <-stopped:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("Stop did not return")
|
||||
}
|
||||
waitFor(t, func() bool { return len(entered) == 1 })
|
||||
assert.Equal(t, int64(1), most.Load(), "a Start captured alongside the pass Stop was waiting out")
|
||||
}
|
||||
Reference in new issue
Block a user