mirror of
https://github.com/netbirdio/netbird.git
synced 2026-07-29 20:01:29 +02:00
Compare commits
1 Commits
ssh-ipc-pr
...
ci/trigger
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
fdabe10612 |
12
.github/workflows/agent-network-e2e.yml
vendored
12
.github/workflows/agent-network-e2e.yml
vendored
@@ -5,13 +5,6 @@ on:
|
||||
schedule:
|
||||
- cron: "0 3 * * *"
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
bedrock_model:
|
||||
description: >-
|
||||
Bedrock inference-profile id to drive the matrix with, exactly as
|
||||
AWS issues it. Leave empty for the Sonnet 4.6 default.
|
||||
required: false
|
||||
default: ""
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.ref }}
|
||||
@@ -58,9 +51,6 @@ jobs:
|
||||
# token (and URL, for gateways) is unset, so partial coverage is fine.
|
||||
OPENAI_TOKEN: ${{ secrets.E2E_OPENAI_TOKEN }}
|
||||
ANTHROPIC_TOKEN: ${{ secrets.E2E_ANTHROPIC_TOKEN }}
|
||||
# Moonshot AI platform key (platform.kimi.ai); drives both Kimi wire
|
||||
# shapes (OpenAI /v1 and Anthropic /anthropic) through kimi_api.
|
||||
KIMI_TOKEN: ${{ secrets.E2E_KIMI_TOKEN }}
|
||||
VERCEL_URL: ${{ secrets.E2E_VERCEL_URL }}
|
||||
VERCEL_TOKEN: ${{ secrets.E2E_VERCEL_TOKEN }}
|
||||
OPENROUTER_URL: ${{ secrets.E2E_OPENROUTER_URL }}
|
||||
@@ -69,8 +59,6 @@ jobs:
|
||||
CLOUDFLARE_TOKEN: ${{ secrets.E2E_CLOUDFLARE_TOKEN }}
|
||||
AWS_BEARER_TOKEN_BEDROCK: ${{ secrets.E2E_AWS_BEARER_TOKEN_BEDROCK }}
|
||||
AWS_REGION: ${{ secrets.E2E_AWS_REGION }}
|
||||
# Bedrock model override: dispatch input wins, then the repo variable, else the test default.
|
||||
AWS_BEDROCK_MODEL: ${{ inputs.bedrock_model || vars.E2E_AWS_BEDROCK_MODEL }}
|
||||
# Vertex (Anthropic-on-Vertex): SA + project required; region defaults
|
||||
# to "global", model to a pinned claude snapshot.
|
||||
GOOGLE_VERTEX_SA_BASE64: ${{ secrets.E2E_GOOGLE_VERTEX_SA_BASE64 }}
|
||||
|
||||
2
.github/workflows/frontend-ui.yml
vendored
2
.github/workflows/frontend-ui.yml
vendored
@@ -86,7 +86,7 @@ jobs:
|
||||
${{ runner.os }}-pnpm-
|
||||
|
||||
- name: Install dependencies
|
||||
run: pnpm install --frozen-lockfile --ignore-scripts
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Generate Wails bindings
|
||||
run: pnpm run bindings
|
||||
|
||||
4
.github/workflows/golangci-lint.yml
vendored
4
.github/workflows/golangci-lint.yml
vendored
@@ -45,7 +45,7 @@ jobs:
|
||||
display_name: Linux
|
||||
name: ${{ matrix.display_name }}
|
||||
runs-on: ${{ matrix.os }}
|
||||
timeout-minutes: 25
|
||||
timeout-minutes: 15
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||||
@@ -79,4 +79,4 @@ jobs:
|
||||
skip-cache: true
|
||||
skip-save-cache: true
|
||||
cache-invalidation-interval: 0
|
||||
args: --timeout=20m
|
||||
args: --timeout=12m
|
||||
|
||||
88
.github/workflows/release-tests.yml
vendored
Normal file
88
.github/workflows/release-tests.yml
vendored
Normal file
@@ -0,0 +1,88 @@
|
||||
name: Trigger release tests
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- "v*"
|
||||
release:
|
||||
types: [published]
|
||||
|
||||
jobs:
|
||||
trigger:
|
||||
name: "Release tests / ${{ matrix.scenario }}"
|
||||
if: >-
|
||||
${{ github.repository == 'netbirdio/netbird' &&
|
||||
((github.event_name == 'push' &&
|
||||
(!contains(github.ref_name, '-') || contains(github.ref_name, '-rc.'))) ||
|
||||
(github.event_name == 'release' && github.event.release.prerelease)) }}
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 10
|
||||
permissions:
|
||||
contents: read
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
scenario: [prerelease, upgrade]
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||||
with:
|
||||
ref: ${{ github.event.release.tag_name || github.ref }}
|
||||
fetch-depth: 0
|
||||
persist-credentials: false
|
||||
|
||||
- name: Resolve test versions
|
||||
id: versions
|
||||
env:
|
||||
RELEASE_TAG: ${{ github.event.release.tag_name || github.ref_name }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
if [[ ! "$RELEASE_TAG" =~ ^v([0-9]+)\.([0-9]+)\.[0-9]+(-[0-9A-Za-z][0-9A-Za-z.-]*)?$ ]]; then
|
||||
echo "Unsupported release tag: $RELEASE_TAG" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
major=$((10#${BASH_REMATCH[1]}))
|
||||
minor=$((10#${BASH_REMATCH[2]}))
|
||||
if (( minor < 2 )); then
|
||||
echo "Cannot select an N-2 release for $RELEASE_TAG" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
old_minor=$((minor - 2))
|
||||
old_version=$(git tag --list "v${major}.${old_minor}.*" --sort=-version:refname | grep -E "^v${major}\.${old_minor}\.[0-9]+$" | head -n 1)
|
||||
if [[ -z "$old_version" ]]; then
|
||||
echo "No stable v${major}.${old_minor}.x release found" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "target=sha-$(git rev-parse --short HEAD)" >> "$GITHUB_OUTPUT"
|
||||
echo "old=$old_version" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: Run prerelease scenarios
|
||||
if: matrix.scenario == 'prerelease'
|
||||
uses: benc-uk/workflow-dispatch@31e2b3319479a63f0ab15bf800eff9e913504e26 # v1.3.2
|
||||
with:
|
||||
workflow: netbird-prerelease.yml
|
||||
repo: netbirdio/pre-release-tests
|
||||
ref: main
|
||||
token: ${{ secrets.RELEASE_TESTS_GITHUB_TOKEN }}
|
||||
inputs: >-
|
||||
{ "netbird_version": "${{ steps.versions.outputs.target }}",
|
||||
"netbird_server_version": "${{ steps.versions.outputs.target }}",
|
||||
"netbird_server_image_repository": "ghcr.io/netbirdio/netbird-server" }
|
||||
|
||||
- name: Run upgrade scenarios
|
||||
if: matrix.scenario == 'upgrade'
|
||||
uses: benc-uk/workflow-dispatch@31e2b3319479a63f0ab15bf800eff9e913504e26 # v1.3.2
|
||||
with:
|
||||
workflow: netbird-selfhosted-upgrade.yml
|
||||
repo: netbirdio/pre-release-tests
|
||||
ref: main
|
||||
token: ${{ secrets.RELEASE_TESTS_GITHUB_TOKEN }}
|
||||
inputs: >-
|
||||
{ "netbird_version": "${{ steps.versions.outputs.target }}",
|
||||
"old_netbird_server_version": "${{ steps.versions.outputs.old }}",
|
||||
"netbird_server_version": "${{ steps.versions.outputs.target }}",
|
||||
"netbird_server_image_repository": "ghcr.io/netbirdio/netbird-server" }
|
||||
89
.github/workflows/test-infrastructure-files.yml
vendored
89
.github/workflows/test-infrastructure-files.yml
vendored
@@ -249,35 +249,78 @@ jobs:
|
||||
docker compose exec management ls -l /var/lib/netbird/ | grep -i GeoLite2-City_[0-9]*.mmdb
|
||||
docker compose exec management ls -l /var/lib/netbird/ | grep -i geonames_[0-9]*.db
|
||||
|
||||
test-legacy-getting-started-scripts:
|
||||
test-getting-started-script:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Install jq
|
||||
run: sudo apt-get install -y jq
|
||||
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Verify Dex retirement notice
|
||||
run: |
|
||||
if infrastructure_files/getting-started-with-dex.sh >stdout.txt 2>stderr.txt; then
|
||||
echo "Expected the retired Dex installer to fail"
|
||||
exit 1
|
||||
fi
|
||||
test ! -s stdout.txt
|
||||
grep -Fq "Dex support is not deprecated." stderr.txt
|
||||
grep -Fq "https://docs.netbird.io/selfhosted/selfhosted-quickstart" stderr.txt
|
||||
grep -Fq "https://docs.netbird.io/selfhosted/identity-providers/local" stderr.txt
|
||||
grep -Fq "removed in NetBird v0.80" stderr.txt
|
||||
- name: run script with Zitadel PostgreSQL
|
||||
run: NETBIRD_DOMAIN=use-ip bash -x infrastructure_files/getting-started-with-zitadel.sh
|
||||
|
||||
- name: Verify Zitadel retirement notice
|
||||
- name: test Caddy file gen postgres
|
||||
run: test -f Caddyfile
|
||||
|
||||
- name: test docker-compose file gen postgres
|
||||
run: test -f docker-compose.yml
|
||||
|
||||
- name: test management.json file gen postgres
|
||||
run: test -f management.json
|
||||
|
||||
- name: test turnserver.conf file gen postgres
|
||||
run: |
|
||||
if bash infrastructure_files/getting-started-with-zitadel.sh >stdout.txt 2>stderr.txt; then
|
||||
echo "Expected the retired Zitadel installer to fail"
|
||||
exit 1
|
||||
fi
|
||||
test ! -s stdout.txt
|
||||
grep -Fq "Zitadel support and existing Zitadel deployments are not deprecated." stderr.txt
|
||||
grep -Fq "https://docs.netbird.io/selfhosted/selfhosted-quickstart" stderr.txt
|
||||
grep -Fq "https://docs.netbird.io/selfhosted/identity-providers/zitadel" stderr.txt
|
||||
grep -Fq "https://docs.netbird.io/selfhosted/selfhosted-guide" stderr.txt
|
||||
grep -Fq "removed in NetBird v0.80" stderr.txt
|
||||
set -x
|
||||
test -f turnserver.conf
|
||||
grep external-ip turnserver.conf
|
||||
|
||||
- name: test zitadel.env file gen postgres
|
||||
run: test -f zitadel.env
|
||||
|
||||
- name: test dashboard.env file gen postgres
|
||||
run: test -f dashboard.env
|
||||
|
||||
- name: test relay.env file gen postgres
|
||||
run: test -f relay.env
|
||||
|
||||
- name: test zdb.env file gen postgres
|
||||
run: test -f zdb.env
|
||||
|
||||
- name: Postgres run cleanup
|
||||
run: |
|
||||
docker compose down --volumes --rmi all
|
||||
rm -rf docker-compose.yml Caddyfile zitadel.env dashboard.env machinekey/zitadel-admin-sa.token turnserver.conf management.json zdb.env
|
||||
|
||||
- name: run script with Zitadel CockroachDB
|
||||
run: bash -x infrastructure_files/getting-started-with-zitadel.sh
|
||||
env:
|
||||
NETBIRD_DOMAIN: use-ip
|
||||
ZITADEL_DATABASE: cockroach
|
||||
|
||||
- name: test Caddy file gen CockroachDB
|
||||
run: test -f Caddyfile
|
||||
|
||||
- name: test docker-compose file gen CockroachDB
|
||||
run: test -f docker-compose.yml
|
||||
|
||||
- name: test management.json file gen CockroachDB
|
||||
run: test -f management.json
|
||||
|
||||
- name: test turnserver.conf file gen CockroachDB
|
||||
run: |
|
||||
set -x
|
||||
test -f turnserver.conf
|
||||
grep external-ip turnserver.conf
|
||||
|
||||
- name: test zitadel.env file gen CockroachDB
|
||||
run: test -f zitadel.env
|
||||
|
||||
- name: test dashboard.env file gen CockroachDB
|
||||
run: test -f dashboard.env
|
||||
|
||||
- name: test relay.env file gen CockroachDB
|
||||
run: test -f relay.env
|
||||
|
||||
@@ -273,8 +273,8 @@ dockers_v2:
|
||||
- netbirdio/netbird
|
||||
- ghcr.io/netbirdio/netbird
|
||||
tags:
|
||||
- "{{ .Version }}-rootless"
|
||||
- "{{ if eq .Env.SKIP_PUBLISH \"false\" }}rootless-latest{{ end }}"
|
||||
- "v{{ .Version }}-rootless"
|
||||
- "{{ if eq .Env.SKIP_PUBLISH \"false\" }}latest{{ end }}"
|
||||
dockerfile: client/Dockerfile-rootless
|
||||
extra_files:
|
||||
- client/netbird-entrypoint.sh
|
||||
|
||||
@@ -24,8 +24,6 @@ builds:
|
||||
ldflags:
|
||||
- -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
|
||||
mod_timestamp: "{{ .CommitTimestamp }}"
|
||||
tags:
|
||||
- production
|
||||
|
||||
- id: netbird-ui-windows-amd64
|
||||
dir: client/ui
|
||||
@@ -41,8 +39,6 @@ builds:
|
||||
- -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
|
||||
- -H windowsgui
|
||||
mod_timestamp: "{{ .CommitTimestamp }}"
|
||||
tags:
|
||||
- production
|
||||
|
||||
- id: netbird-ui-windows-arm64
|
||||
dir: client/ui
|
||||
@@ -59,8 +55,6 @@ builds:
|
||||
- -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
|
||||
- -H windowsgui
|
||||
mod_timestamp: "{{ .CommitTimestamp }}"
|
||||
tags:
|
||||
- production
|
||||
|
||||
archives:
|
||||
- id: linux-arch
|
||||
|
||||
@@ -29,8 +29,6 @@ builds:
|
||||
ldflags:
|
||||
- -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
|
||||
mod_timestamp: "{{ .CommitTimestamp }}"
|
||||
tags:
|
||||
- production
|
||||
|
||||
universal_binaries:
|
||||
- id: netbird-ui-darwin
|
||||
|
||||
@@ -234,22 +234,12 @@ cd client/ui
|
||||
task dev
|
||||
```
|
||||
|
||||
Pass daemon flags after `--`, pointing the UI at the socket the daemon serves:
|
||||
Pass daemon flags after `--`:
|
||||
|
||||
```
|
||||
task dev -- --daemon-addr=unix:///var/run/netbird.sock # Linux, macOS
|
||||
task dev -- --daemon-addr=npipe://netbird # Windows
|
||||
task dev -- --daemon-addr=tcp://127.0.0.1:41731
|
||||
```
|
||||
|
||||
On Windows the daemon serves a named pipe (`npipe://netbird`). Which path that
|
||||
ends up being depends on what the daemon may create: as a service or elevated it
|
||||
serves `\\.\pipe\ProtectedPrefix\Administrators\netbird`, which no unprivileged
|
||||
process can take from it, and otherwise it falls back to `\\.\pipe\netbird`.
|
||||
Clients try both and check who owns the pipe before using the plain one. Avoid
|
||||
`tcp://127.0.0.1:41731`: loopback TCP carries no caller identity, so the daemon
|
||||
refuses the operations that require an administrator and you will not exercise
|
||||
those paths.
|
||||
|
||||
Production build (frontend assets embedded into the binary, output in `client/ui/bin/`):
|
||||
|
||||
```
|
||||
|
||||
@@ -7,7 +7,6 @@ import (
|
||||
"fmt"
|
||||
"os"
|
||||
"slices"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
@@ -248,9 +247,6 @@ func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool) (strin
|
||||
deps.SyncResponse = resp
|
||||
|
||||
if e := cc.Engine(); e != nil {
|
||||
deps.RefreshStatus = func() {
|
||||
e.RunHealthProbes(context.Background(), true)
|
||||
}
|
||||
if cm := e.GetClientMetrics(); cm != nil {
|
||||
deps.ClientMetrics = cm
|
||||
}
|
||||
@@ -300,13 +296,6 @@ func (c *Client) SetInfoLogLevel() {
|
||||
// PeersList return with the list of the PeerInfos
|
||||
func (c *Client) PeersList() *PeerInfoArray {
|
||||
|
||||
// The recorder only caches transfer counters and handshake times; nothing
|
||||
// refreshes them on its own, so without this they read as zero. The desktop
|
||||
// daemon does the same before serving a full peer status.
|
||||
if err := c.recorder.RefreshWireGuardStats(); err != nil {
|
||||
log.Debugf("failed to refresh WireGuard stats: %v", err)
|
||||
}
|
||||
|
||||
fullStatus := c.recorder.GetFullStatus()
|
||||
|
||||
peerInfos := make([]PeerInfo, len(fullStatus.Peers))
|
||||
@@ -317,20 +306,6 @@ func (c *Client) PeersList() *PeerInfoArray {
|
||||
FQDN: p.FQDN,
|
||||
ConnStatus: int(p.ConnStatus),
|
||||
Routes: PeerRoutes{routes: maps.Keys(p.GetRoutes())},
|
||||
|
||||
PubKey: p.PubKey,
|
||||
Latency: formatDuration(p.Latency),
|
||||
LatencyMs: p.Latency.Milliseconds(),
|
||||
BytesRx: p.BytesRx,
|
||||
BytesTx: p.BytesTx,
|
||||
ConnStatusUpdate: formatTime(p.ConnStatusUpdate),
|
||||
Relayed: p.Relayed,
|
||||
RosenpassEnabled: p.RosenpassEnabled,
|
||||
LastWireguardHandshake: formatTime(p.LastWireguardHandshake),
|
||||
LocalIceCandidateType: p.LocalIceCandidateType,
|
||||
RemoteIceCandidateType: p.RemoteIceCandidateType,
|
||||
LocalIceCandidateEndpoint: p.LocalIceCandidateEndpoint,
|
||||
RemoteIceCandidateEndpoint: p.RemoteIceCandidateEndpoint,
|
||||
}
|
||||
peerInfos[n] = pi
|
||||
}
|
||||
@@ -461,6 +436,10 @@ func (c *Client) RemoveConnectionListener() {
|
||||
c.recorder.RemoveConnectionListener()
|
||||
}
|
||||
|
||||
func (c *Client) toggleRoute(command routeCommand) error {
|
||||
return command.toggleRoute()
|
||||
}
|
||||
|
||||
func (c *Client) getRouteManager() (routemanager.Manager, error) {
|
||||
client := c.getConnectClient()
|
||||
if client == nil {
|
||||
@@ -480,22 +459,22 @@ func (c *Client) getRouteManager() (routemanager.Manager, error) {
|
||||
return manager, nil
|
||||
}
|
||||
|
||||
func (c *Client) SelectRoute(id string) error {
|
||||
func (c *Client) SelectRoute(route string) error {
|
||||
manager, err := c.getRouteManager()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
return manager.SelectRoutes([]route.NetID{route.NetID(id)}, true)
|
||||
return c.toggleRoute(selectRouteCommand{route: route, manager: manager})
|
||||
}
|
||||
|
||||
func (c *Client) DeselectRoute(id string) error {
|
||||
func (c *Client) DeselectRoute(route string) error {
|
||||
manager, err := c.getRouteManager()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
return manager.DeselectRoutes([]route.NetID{route.NetID(id)})
|
||||
return c.toggleRoute(deselectRouteCommand{route: route, manager: manager})
|
||||
}
|
||||
|
||||
// getNetworkDomainsFromRoute extracts domains from a route and enriches each domain
|
||||
@@ -530,28 +509,3 @@ func exportEnvList(list *EnvList) {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// formatDuration renders a duration for display, trimming the fractional part
|
||||
// to two digits so latencies read as "12.34ms" rather than "12.345678ms".
|
||||
func formatDuration(d time.Duration) string {
|
||||
ds := d.String()
|
||||
dotIndex := strings.Index(ds, ".")
|
||||
if dotIndex == -1 {
|
||||
return ds
|
||||
}
|
||||
|
||||
endIndex := min(dotIndex+3, len(ds))
|
||||
|
||||
// Skip the remaining digits so only the unit suffix is appended back.
|
||||
unitStart := endIndex
|
||||
for unitStart < len(ds) && ds[unitStart] >= '0' && ds[unitStart] <= '9' {
|
||||
unitStart++
|
||||
}
|
||||
return ds[:endIndex] + ds[unitStart:]
|
||||
}
|
||||
|
||||
// formatTime renders a timestamp in UTC using a fixed layout. The zero time is
|
||||
// passed through as-is so the UI can recognise it and show "never" instead.
|
||||
func formatTime(t time.Time) string {
|
||||
return t.UTC().Format("2006-01-02 15:04:05")
|
||||
}
|
||||
|
||||
@@ -12,30 +12,12 @@ const (
|
||||
)
|
||||
|
||||
// PeerInfo describe information about the peers. It designed for the UI usage
|
||||
//
|
||||
// The fields below ConnStatus back the peer detail screen. Durations and times
|
||||
// are pre-formatted into strings so the UI does not have to know Go's layouts;
|
||||
// Latency is additionally exposed as LatencyMs for colour coding.
|
||||
type PeerInfo struct {
|
||||
IP string
|
||||
IPv6 string
|
||||
FQDN string
|
||||
ConnStatus int
|
||||
Routes PeerRoutes
|
||||
|
||||
PubKey string
|
||||
Latency string
|
||||
LatencyMs int64
|
||||
BytesRx int64
|
||||
BytesTx int64
|
||||
ConnStatusUpdate string
|
||||
Relayed bool
|
||||
RosenpassEnabled bool
|
||||
LastWireguardHandshake string
|
||||
LocalIceCandidateType string
|
||||
RemoteIceCandidateType string
|
||||
LocalIceCandidateEndpoint string
|
||||
RemoteIceCandidateEndpoint string
|
||||
}
|
||||
|
||||
func (p *PeerInfo) GetPeerRoutes() *PeerRoutes {
|
||||
|
||||
@@ -189,19 +189,6 @@ func (pm *ProfileManager) LogoutProfile(id string) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// RenameProfile changes a profile's display name. The profile ID, and therefore
|
||||
// its on-disk filename, is left untouched: only the "name" field of the config
|
||||
// is rewritten. This works for the default profile too, whose config lives in
|
||||
// netbird.cfg rather than under profiles/.
|
||||
func (pm *ProfileManager) RenameProfile(id string, newName string) error {
|
||||
if err := pm.serviceMgr.RenameProfile(profilemanager.ID(id), androidUsername, newName); err != nil {
|
||||
return fmt.Errorf("failed to rename profile: %w", err)
|
||||
}
|
||||
|
||||
log.Infof("renamed profile %s to: %s", id, newName)
|
||||
return nil
|
||||
}
|
||||
|
||||
// RemoveProfile deletes a profile
|
||||
func (pm *ProfileManager) RemoveProfile(id string) error {
|
||||
// Use ServiceManager (removes profile from profiles/ directory)
|
||||
|
||||
70
client/android/route_command.go
Normal file
70
client/android/route_command.go
Normal file
@@ -0,0 +1,70 @@
|
||||
//go:build android
|
||||
|
||||
package android
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
|
||||
log "github.com/sirupsen/logrus"
|
||||
"golang.org/x/exp/maps"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/routemanager"
|
||||
"github.com/netbirdio/netbird/route"
|
||||
)
|
||||
|
||||
func executeRouteToggle(id string, manager routemanager.Manager,
|
||||
operationName string,
|
||||
routeOperation func(routes []route.NetID, allRoutes []route.NetID) error) error {
|
||||
netID := route.NetID(id)
|
||||
routes := []route.NetID{netID}
|
||||
|
||||
routesMap := manager.GetClientRoutesWithNetID()
|
||||
routes = route.ExpandV6ExitPairs(routes, routesMap)
|
||||
|
||||
log.Debugf("%s with ids: %v", operationName, routes)
|
||||
|
||||
if err := routeOperation(routes, maps.Keys(routesMap)); err != nil {
|
||||
log.Debugf("error when %s: %s", operationName, err)
|
||||
return fmt.Errorf("error %s: %w", operationName, err)
|
||||
}
|
||||
|
||||
manager.TriggerSelection(manager.GetClientRoutes())
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
type routeCommand interface {
|
||||
toggleRoute() error
|
||||
}
|
||||
|
||||
type selectRouteCommand struct {
|
||||
route string
|
||||
manager routemanager.Manager
|
||||
}
|
||||
|
||||
func (s selectRouteCommand) toggleRoute() error {
|
||||
routeSelector := s.manager.GetRouteSelector()
|
||||
if routeSelector == nil {
|
||||
return fmt.Errorf("no route selector available")
|
||||
}
|
||||
|
||||
routeOperation := func(routes []route.NetID, allRoutes []route.NetID) error {
|
||||
return routeSelector.SelectRoutes(routes, true, allRoutes)
|
||||
}
|
||||
|
||||
return executeRouteToggle(s.route, s.manager, "selecting route", routeOperation)
|
||||
}
|
||||
|
||||
type deselectRouteCommand struct {
|
||||
route string
|
||||
manager routemanager.Manager
|
||||
}
|
||||
|
||||
func (d deselectRouteCommand) toggleRoute() error {
|
||||
routeSelector := d.manager.GetRouteSelector()
|
||||
if routeSelector == nil {
|
||||
return fmt.Errorf("no route selector available")
|
||||
}
|
||||
|
||||
return executeRouteToggle(d.route, d.manager, "deselecting route", routeSelector.DeselectRoutes)
|
||||
}
|
||||
@@ -1,66 +0,0 @@
|
||||
package cmd
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"strings"
|
||||
|
||||
"google.golang.org/genproto/googleapis/rpc/errdetails"
|
||||
gstatus "google.golang.org/grpc/status"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/ipcauth"
|
||||
)
|
||||
|
||||
// daemonCallError prepares a daemon error for display. A refusal the daemon
|
||||
// raised because the operation needs root/administrator is already guidance
|
||||
// written for the user, so it is surfaced on its own instead of buried under the
|
||||
// gRPC envelope and the name of the RPC that hit it. Anything else is wrapped
|
||||
// with context as usual.
|
||||
func daemonCallError(context string, err error) error {
|
||||
if guidance, ok := privilegeGuidance(err); ok {
|
||||
return errors.New(guidance)
|
||||
}
|
||||
return fmt.Errorf("%s: %w", context, err)
|
||||
}
|
||||
|
||||
// privilegeGuidance renders the daemon's privilege refusal as a summary and the
|
||||
// command that performs the operation with the privileges it needs. It reports
|
||||
// false for any other error.
|
||||
func privilegeGuidance(err error) (string, bool) {
|
||||
info, ok := privilegeErrorInfo(err)
|
||||
if !ok {
|
||||
return "", false
|
||||
}
|
||||
|
||||
summary := info.GetMetadata()[ipcauth.ErrorMetaSummary]
|
||||
command := info.GetMetadata()[ipcauth.ErrorMetaCommand]
|
||||
if summary == "" {
|
||||
// Detail without a summary: fall back to the status message, which
|
||||
// carries the same text.
|
||||
summary = strings.TrimSpace(gstatus.Convert(err).Message())
|
||||
}
|
||||
if command == "" {
|
||||
return summary, true
|
||||
}
|
||||
|
||||
return fmt.Sprintf("%s\n\n %s\n", summary, command), true
|
||||
}
|
||||
|
||||
// privilegeErrorInfo returns the daemon's privilege-refusal detail, if the error
|
||||
// carries one.
|
||||
func privilegeErrorInfo(err error) (*errdetails.ErrorInfo, bool) {
|
||||
if err == nil {
|
||||
return nil, false
|
||||
}
|
||||
|
||||
for _, detail := range gstatus.Convert(err).Details() {
|
||||
info, ok := detail.(*errdetails.ErrorInfo)
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
if info.GetReason() == ipcauth.ErrorReasonPrivilegeRequired && info.GetDomain() == ipcauth.ErrorDomain {
|
||||
return info, true
|
||||
}
|
||||
}
|
||||
return nil, false
|
||||
}
|
||||
@@ -46,7 +46,7 @@ var logoutCmd = &cobra.Command{
|
||||
}
|
||||
|
||||
if _, err := daemonClient.Logout(ctx, req); err != nil {
|
||||
return daemonCallError("deregister", err)
|
||||
return fmt.Errorf("deregister: %v", err)
|
||||
}
|
||||
|
||||
cmd.Println("Deregistered successfully")
|
||||
|
||||
@@ -20,6 +20,7 @@ import (
|
||||
"github.com/spf13/cobra"
|
||||
"github.com/spf13/pflag"
|
||||
"google.golang.org/grpc"
|
||||
"google.golang.org/grpc/credentials/insecure"
|
||||
|
||||
daddr "github.com/netbirdio/netbird/client/internal/daemonaddr"
|
||||
"github.com/netbirdio/netbird/client/internal/profilemanager"
|
||||
@@ -90,7 +91,6 @@ var (
|
||||
// Don't resolve for service commands — they create the socket, not connect to it.
|
||||
if !isServiceCmd(cmd) {
|
||||
daemonAddr = daddr.ResolveUnixDaemonAddr(daemonAddr)
|
||||
daemonAddr = daddr.ResolveDaemonAddr(daemonAddr)
|
||||
}
|
||||
return nil
|
||||
},
|
||||
@@ -143,10 +143,10 @@ func init() {
|
||||
|
||||
defaultDaemonAddr := "unix:///var/run/netbird.sock"
|
||||
if runtime.GOOS == "windows" {
|
||||
defaultDaemonAddr = daddr.WindowsPipeAddr
|
||||
defaultDaemonAddr = "tcp://127.0.0.1:41731"
|
||||
}
|
||||
|
||||
rootCmd.PersistentFlags().StringVar(&daemonAddr, "daemon-addr", defaultDaemonAddr, "Daemon service address to serve CLI requests [unix|tcp|npipe]://[path|host:port|name]")
|
||||
rootCmd.PersistentFlags().StringVar(&daemonAddr, "daemon-addr", defaultDaemonAddr, "Daemon service address to serve CLI requests [unix|tcp]://[path|host:port]")
|
||||
rootCmd.PersistentFlags().StringVarP(&managementURL, "management-url", "m", "", fmt.Sprintf("Management Service URL [http|https]://[host]:[port] (default \"%s\")", profilemanager.DefaultManagementURL))
|
||||
rootCmd.PersistentFlags().StringVar(&adminURL, "admin-url", "", fmt.Sprintf("Admin Panel URL [http|https]://[host]:[port] (default \"%s\")", profilemanager.DefaultAdminURL))
|
||||
rootCmd.PersistentFlags().StringVarP(&logLevel, "log-level", "l", "info", "sets NetBird log level")
|
||||
@@ -269,10 +269,12 @@ func DialClientGRPCServer(ctx context.Context, addr string) (*grpc.ClientConn, e
|
||||
ctx, cancel := context.WithTimeout(ctx, time.Second*10)
|
||||
defer cancel()
|
||||
|
||||
target, opts := daddr.DialTarget(addr)
|
||||
opts = append(opts, grpc.WithBlock())
|
||||
|
||||
return grpc.DialContext(ctx, target, opts...)
|
||||
return grpc.DialContext(
|
||||
ctx,
|
||||
strings.TrimPrefix(addr, "tcp://"),
|
||||
grpc.WithTransportCredentials(insecure.NewCredentials()),
|
||||
grpc.WithBlock(),
|
||||
)
|
||||
}
|
||||
|
||||
// WithBackOff execute function in backoff cycle.
|
||||
|
||||
@@ -33,15 +33,10 @@ var (
|
||||
)
|
||||
|
||||
type program struct {
|
||||
ctx context.Context
|
||||
cancel context.CancelFunc
|
||||
serv *grpc.Server
|
||||
jsonServ *http.Server
|
||||
// jsonClient is the gateway's own connection to the daemon. It is held so
|
||||
// shutting the gateway down also closes it: nothing else references it once
|
||||
// the handlers are registered, so its transport goroutines would otherwise
|
||||
// outlive the server.
|
||||
jsonClient *grpc.ClientConn
|
||||
ctx context.Context
|
||||
cancel context.CancelFunc
|
||||
serv *grpc.Server
|
||||
jsonServ *http.Server
|
||||
jsonServMu sync.Mutex
|
||||
serverInstance *server.Server
|
||||
serverInstanceMu sync.Mutex
|
||||
|
||||
@@ -5,7 +5,6 @@ package cmd
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"runtime"
|
||||
"time"
|
||||
|
||||
"github.com/kardianos/service"
|
||||
@@ -14,8 +13,6 @@ import (
|
||||
"github.com/spf13/cobra"
|
||||
"google.golang.org/grpc"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/daemonaddr"
|
||||
"github.com/netbirdio/netbird/client/internal/ipcauth"
|
||||
"github.com/netbirdio/netbird/client/proto"
|
||||
"github.com/netbirdio/netbird/client/server"
|
||||
"github.com/netbirdio/netbird/client/system"
|
||||
@@ -29,31 +26,6 @@ func validateJSONSocketFlags() error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// daemonServerOptions installs the transport credentials that expose each
|
||||
// caller's kernel-authenticated identity to the handlers, which is what lets
|
||||
// the daemon require root/administrator for privileged operations.
|
||||
//
|
||||
// The handshake exchanges no bytes, so older CLI and UI binaries still
|
||||
// interoperate. Callers on a TCP socket carry no identity at all: the daemon
|
||||
// keeps serving them, and the privileged operations deny them, so a warning is
|
||||
// logged to make the loss of functionality visible.
|
||||
func daemonServerOptions(network string) []grpc.ServerOption {
|
||||
if network == "tcp" {
|
||||
log.Warnf("daemon is listening on TCP (%s): callers carry no verifiable identity over TCP, "+
|
||||
"so privileged operations (SSH root login, SSH auth, enabling the SSH server, management URL changes, "+
|
||||
"deregistration) will be denied. Use a unix socket, or npipe:// on Windows", daemonAddr)
|
||||
return nil
|
||||
}
|
||||
|
||||
creds := ipcauth.NewTransportCredentials()
|
||||
if creds == nil {
|
||||
log.Warnf("daemon IPC has no peer-identity primitive on %s: privileged operations will be denied", runtime.GOOS)
|
||||
return nil
|
||||
}
|
||||
|
||||
return []grpc.ServerOption{grpc.Creds(creds)}
|
||||
}
|
||||
|
||||
func (p *program) Start(svc service.Service) error {
|
||||
// Start should not block. Do the actual work async.
|
||||
log.Info("starting NetBird service") //nolint
|
||||
@@ -65,106 +37,68 @@ func (p *program) Start(svc service.Service) error {
|
||||
// Collect static system and platform information
|
||||
system.UpdateStaticInfoAsync()
|
||||
|
||||
// A daemon installed before named-pipe support has the loopback TCP address
|
||||
// persisted. Move it to the named pipe so an upgraded daemon can identify
|
||||
// its callers instead of silently serving an unauthenticated socket.
|
||||
if migrated, ok := daemonaddr.MigrateLegacy(daemonAddr); ok {
|
||||
log.Infof("daemon address %q predates named-pipe support, listening on %q so callers can be identified", daemonAddr, migrated)
|
||||
daemonAddr = migrated
|
||||
}
|
||||
|
||||
network, _, err := parseListenAddress(daemonAddr)
|
||||
if err != nil {
|
||||
return fmt.Errorf("parse daemon address: %w", err)
|
||||
}
|
||||
|
||||
// in any case, even if configuration does not exists we run daemon to serve CLI gRPC API.
|
||||
p.serv = grpc.NewServer(daemonServerOptions(network)...)
|
||||
p.serv = grpc.NewServer()
|
||||
|
||||
daemonListener, jsonListener, err := listenDaemonSockets()
|
||||
daemonListener, err := listenOnAddress(daemonAddr)
|
||||
if err != nil {
|
||||
return err
|
||||
return fmt.Errorf("listen daemon interface: %w", err)
|
||||
}
|
||||
|
||||
var jsonListener *socketListener
|
||||
if enableJSONSocket {
|
||||
jsonListener, err = listenOnAddress(jsonSocket)
|
||||
if err != nil {
|
||||
_ = daemonListener.Close()
|
||||
return fmt.Errorf("listen daemon JSON interface: %w", err)
|
||||
}
|
||||
} else {
|
||||
removeStaleUnixSocketForAddress(jsonSocket)
|
||||
}
|
||||
|
||||
go func() {
|
||||
// Fatal here rather than inside serve, so serve's deferred listener
|
||||
// closes run before the process exits.
|
||||
if err := p.serve(daemonListener, jsonListener); err != nil {
|
||||
log.Fatalf("failed to %v", err)
|
||||
defer daemonListener.Close()
|
||||
if jsonListener != nil {
|
||||
defer jsonListener.Close()
|
||||
}
|
||||
|
||||
if err := daemonListener.chmodUnixSocket("daemon"); err != nil {
|
||||
log.Error(err)
|
||||
return
|
||||
}
|
||||
if jsonListener != nil {
|
||||
if err := jsonListener.chmodUnixSocket("daemon JSON"); err != nil {
|
||||
log.Error(err)
|
||||
return
|
||||
}
|
||||
}
|
||||
|
||||
serverInstance := server.New(p.ctx, util.FindFirstLogPath(logFiles), configPath, profilesDisabled, updateSettingsDisabled, captureEnabled, networksDisabled)
|
||||
if err := serverInstance.Start(); err != nil {
|
||||
log.Fatalf("failed to start daemon: %v", err)
|
||||
}
|
||||
proto.RegisterDaemonServiceServer(p.serv, serverInstance)
|
||||
|
||||
p.serverInstanceMu.Lock()
|
||||
p.serverInstance = serverInstance
|
||||
p.serverInstanceMu.Unlock()
|
||||
|
||||
if jsonListener != nil {
|
||||
if err := p.startJSONGateway(jsonListener, daemonAddr); err != nil {
|
||||
log.Fatalf("failed to start daemon JSON server: %v", err)
|
||||
}
|
||||
} else {
|
||||
log.Debug("daemon JSON socket disabled")
|
||||
}
|
||||
|
||||
log.Printf("started daemon server: %v", daemonListener.address)
|
||||
if err := p.serv.Serve(daemonListener.Listener); err != nil {
|
||||
log.Errorf("failed to serve daemon requests: %v", err)
|
||||
}
|
||||
}()
|
||||
return nil
|
||||
}
|
||||
|
||||
// listenDaemonSockets opens the daemon control socket and, when it is enabled, the
|
||||
// JSON gateway socket. The control socket is closed again if the second one fails,
|
||||
// so a failed start leaves nothing listening. The returned JSON listener is nil
|
||||
// when the socket is disabled.
|
||||
func listenDaemonSockets() (*socketListener, *socketListener, error) {
|
||||
daemonListener, err := listenOnAddress(daemonAddr)
|
||||
if err != nil {
|
||||
return nil, nil, fmt.Errorf("listen daemon interface: %w", err)
|
||||
}
|
||||
|
||||
if !enableJSONSocket {
|
||||
removeStaleUnixSocketForAddress(jsonSocket)
|
||||
return daemonListener, nil, nil
|
||||
}
|
||||
|
||||
jsonListener, err := listenOnAddress(jsonSocket)
|
||||
if err != nil {
|
||||
if cerr := daemonListener.Close(); cerr != nil {
|
||||
log.Debugf("close daemon listener: %v", cerr)
|
||||
}
|
||||
return nil, nil, fmt.Errorf("listen daemon JSON interface: %w", err)
|
||||
}
|
||||
|
||||
return daemonListener, jsonListener, nil
|
||||
}
|
||||
|
||||
// serve brings up the daemon server on an already-open control socket and blocks
|
||||
// until it stops. jsonListener is nil when the JSON socket is disabled. A returned
|
||||
// error means the daemon cannot run at all and the caller is expected to exit; the
|
||||
// failures it recovers from on its own are logged here.
|
||||
func (p *program) serve(daemonListener, jsonListener *socketListener) error {
|
||||
defer daemonListener.Close()
|
||||
if jsonListener != nil {
|
||||
defer jsonListener.Close()
|
||||
}
|
||||
|
||||
// chmodUnixSocket is a no-op for a nil listener and for a non-unix one.
|
||||
if err := daemonListener.chmodUnixSocket("daemon"); err != nil {
|
||||
log.Error(err)
|
||||
return nil
|
||||
}
|
||||
if err := jsonListener.chmodUnixSocket("daemon JSON"); err != nil {
|
||||
log.Error(err)
|
||||
return nil
|
||||
}
|
||||
|
||||
serverInstance := server.New(p.ctx, util.FindFirstLogPath(logFiles), configPath, profilesDisabled, updateSettingsDisabled, captureEnabled, networksDisabled)
|
||||
if err := serverInstance.Start(); err != nil {
|
||||
return fmt.Errorf("start daemon: %w", err)
|
||||
}
|
||||
proto.RegisterDaemonServiceServer(p.serv, serverInstance)
|
||||
|
||||
p.serverInstanceMu.Lock()
|
||||
p.serverInstance = serverInstance
|
||||
p.serverInstanceMu.Unlock()
|
||||
|
||||
if jsonListener == nil {
|
||||
log.Debug("daemon JSON socket disabled")
|
||||
} else if err := p.startJSONGateway(jsonListener, daemonAddr); err != nil {
|
||||
return fmt.Errorf("start daemon JSON server: %w", err)
|
||||
}
|
||||
|
||||
log.Printf("started daemon server: %v", daemonListener.address)
|
||||
if err := p.serv.Serve(daemonListener.Listener); err != nil {
|
||||
log.Errorf("failed to serve daemon requests: %v", err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func (p *program) Stop(srv service.Service) error {
|
||||
p.serverInstanceMu.Lock()
|
||||
if p.serverInstance != nil {
|
||||
@@ -179,13 +113,8 @@ func (p *program) Stop(srv service.Service) error {
|
||||
p.cancel()
|
||||
|
||||
p.jsonServMu.Lock()
|
||||
jsonServ, jsonClient := p.jsonServ, p.jsonClient
|
||||
jsonServ := p.jsonServ
|
||||
p.jsonServMu.Unlock()
|
||||
if jsonClient != nil {
|
||||
if err := jsonClient.Close(); err != nil {
|
||||
log.Debugf("close daemon JSON gateway client: %v", err)
|
||||
}
|
||||
}
|
||||
if jsonServ != nil {
|
||||
shutdownCtx, shutdownCancel := context.WithTimeout(context.Background(), 2*time.Second)
|
||||
if err := jsonServ.Shutdown(shutdownCtx); err != nil {
|
||||
|
||||
@@ -5,123 +5,27 @@ package cmd
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"net"
|
||||
"net/http"
|
||||
"sync"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/grpc-ecosystem/grpc-gateway/v2/runtime"
|
||||
log "github.com/sirupsen/logrus"
|
||||
"google.golang.org/grpc"
|
||||
"google.golang.org/grpc/credentials/insecure"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/daemonaddr"
|
||||
"github.com/netbirdio/netbird/client/internal/ipcauth"
|
||||
"github.com/netbirdio/netbird/client/proto"
|
||||
)
|
||||
|
||||
// jsonPeerIdentity is the context key under which the connecting HTTP client's
|
||||
// identity is stashed for the lifetime of its connection.
|
||||
type jsonPeerIdentity struct{}
|
||||
|
||||
// jsonPeerIdentityValue pairs the identity with whether it could be read at
|
||||
// all, so an unreadable identity is forwarded as "unknown" rather than omitted.
|
||||
type jsonPeerIdentityValue struct {
|
||||
id ipcauth.Identity
|
||||
known bool
|
||||
}
|
||||
|
||||
// jsonConnContext reads the identity of the client connecting to the JSON
|
||||
// socket and stashes it on the connection's context. The gateway re-dials the
|
||||
// daemon in-process, so the daemon would otherwise see every JSON request as
|
||||
// coming from the daemon itself.
|
||||
func jsonConnContext(ctx context.Context, c net.Conn) context.Context {
|
||||
value := jsonPeerIdentityValue{}
|
||||
id, err := ipcauth.ConnIdentity(c)
|
||||
if err != nil {
|
||||
log.Warnf("json gateway: cannot read HTTP client identity, privileged operations will be denied for this connection: %v", err)
|
||||
} else {
|
||||
value.id = id
|
||||
value.known = true
|
||||
}
|
||||
return context.WithValue(ctx, jsonPeerIdentity{}, value)
|
||||
}
|
||||
|
||||
// forwardIdentity stamps the HTTP client's identity onto every call the gateway
|
||||
// makes to the daemon.
|
||||
//
|
||||
// It is an interceptor on the gateway's client connection rather than a
|
||||
// runtime.WithMetadata annotator because grpc-gateway skips annotators when no
|
||||
// request header maps to metadata, which an HTTP/1.0 request with no Host header
|
||||
// over a unix socket achieves. The daemon would then receive no marker, see its own
|
||||
// identity as the transport peer, and authorize the request as the daemon itself.
|
||||
// An interceptor runs for every RPC whatever the request looked like.
|
||||
func forwardIdentity(ctx context.Context) context.Context {
|
||||
value, ok := ctx.Value(jsonPeerIdentity{}).(jsonPeerIdentityValue)
|
||||
if !ok {
|
||||
// No ConnContext ran for this request, so forward an unknown identity:
|
||||
// the daemon must not mistake its own identity for the client's.
|
||||
return ipcauth.WithForwardedIdentity(ctx, ipcauth.Identity{}, false)
|
||||
}
|
||||
return ipcauth.WithForwardedIdentity(ctx, value.id, value.known)
|
||||
}
|
||||
|
||||
func forwardIdentityUnary(ctx context.Context, method string, req, reply any, cc *grpc.ClientConn, invoker grpc.UnaryInvoker, opts ...grpc.CallOption) error {
|
||||
return invoker(forwardIdentity(ctx), method, req, reply, cc, opts...)
|
||||
}
|
||||
|
||||
func forwardIdentityStream(ctx context.Context, desc *grpc.StreamDesc, cc *grpc.ClientConn, method string, streamer grpc.Streamer, opts ...grpc.CallOption) (grpc.ClientStream, error) {
|
||||
return streamer(forwardIdentity(ctx), desc, cc, method, opts...)
|
||||
}
|
||||
|
||||
// reservedHeaderWarning limits the dropped-header warning to the first occurrence.
|
||||
var reservedHeaderWarning sync.Once
|
||||
|
||||
// jsonIncomingHeaderMatcher keeps an HTTP client from supplying the metadata the
|
||||
// gateway uses to forward its identity. grpc-gateway turns "Grpc-Metadata-<key>"
|
||||
// headers into gRPC metadata and joins them ahead of what its annotators add, so
|
||||
// without this filter a JSON client could send its own x-netbird-fwd-uid and the
|
||||
// daemon would authorize that instead of the client's real identity.
|
||||
func jsonIncomingHeaderMatcher(key string) (string, bool) {
|
||||
mapped, ok := runtime.DefaultHeaderMatcher(key)
|
||||
if !ok {
|
||||
return "", false
|
||||
}
|
||||
if ipcauth.IsReservedForwardKey(mapped) {
|
||||
// Warn once: any client can send these on every request, so warning each
|
||||
// time hands it a way to fill the log. The rest are debug-level.
|
||||
reservedHeaderWarning.Do(func() {
|
||||
log.Warnf("json gateway: dropping reserved header %q from a request: only the gateway may set the caller's identity", key)
|
||||
})
|
||||
log.Debugf("json gateway: dropping reserved header %q", key)
|
||||
return "", false
|
||||
}
|
||||
return mapped, true
|
||||
func grpcGatewayEndpoint(addr string) string {
|
||||
return strings.TrimPrefix(addr, "tcp://")
|
||||
}
|
||||
|
||||
func (p *program) startJSONGateway(jsonListener *socketListener, daemonEndpoint string) error {
|
||||
if jsonListener.network == "tcp" {
|
||||
log.Warnf("daemon JSON socket is listening on TCP (%s): callers carry no verifiable identity over TCP, "+
|
||||
"so privileged operations will be denied for JSON clients", jsonListener.address)
|
||||
}
|
||||
|
||||
mux := runtime.NewServeMux(runtime.WithIncomingHeaderMatcher(jsonIncomingHeaderMatcher))
|
||||
|
||||
// grpc.NewClient does not connect until the first request, so registering
|
||||
// the handler here cannot block daemon startup.
|
||||
target, opts := daemonaddr.DialTarget(daemonEndpoint)
|
||||
opts = append(opts,
|
||||
grpc.WithChainUnaryInterceptor(forwardIdentityUnary),
|
||||
grpc.WithChainStreamInterceptor(forwardIdentityStream),
|
||||
)
|
||||
conn, err := grpc.NewClient(target, opts...)
|
||||
if err != nil {
|
||||
return fmt.Errorf("create daemon client for JSON gateway: %w", err)
|
||||
}
|
||||
if err := proto.RegisterDaemonServiceHandler(p.ctx, mux, conn); err != nil {
|
||||
if cerr := conn.Close(); cerr != nil {
|
||||
log.Debugf("close daemon client after failed JSON gateway registration: %v", cerr)
|
||||
}
|
||||
mux := runtime.NewServeMux()
|
||||
opts := []grpc.DialOption{grpc.WithTransportCredentials(insecure.NewCredentials())}
|
||||
if err := proto.RegisterDaemonServiceHandlerFromEndpoint(p.ctx, mux, grpcGatewayEndpoint(daemonEndpoint), opts); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
@@ -131,12 +35,10 @@ func (p *program) startJSONGateway(jsonListener *socketListener, daemonEndpoint
|
||||
BaseContext: func(net.Listener) context.Context {
|
||||
return p.ctx
|
||||
},
|
||||
ConnContext: jsonConnContext,
|
||||
}
|
||||
|
||||
p.jsonServMu.Lock()
|
||||
p.jsonServ = jsonServer
|
||||
p.jsonClient = conn
|
||||
p.jsonServMu.Unlock()
|
||||
|
||||
go func() {
|
||||
|
||||
@@ -1,261 +0,0 @@
|
||||
//go:build !windows && !ios && !android
|
||||
|
||||
package cmd
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net"
|
||||
"net/http"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/grpc-ecosystem/grpc-gateway/v2/runtime"
|
||||
"google.golang.org/grpc/credentials"
|
||||
"google.golang.org/grpc/metadata"
|
||||
"google.golang.org/grpc/peer"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/ipcauth"
|
||||
)
|
||||
|
||||
// The JSON gateway runs inside the daemon and re-dials it locally, so every JSON
|
||||
// request reaches a handler with the daemon's own identity as the transport peer.
|
||||
// The gateway therefore forwards its HTTP client's identity as metadata, and the
|
||||
// daemon authorizes that instead of itself. These tests drive the real wiring
|
||||
// (jsonConnContext, forwardIdentity, jsonIncomingHeaderMatcher) and check the
|
||||
// identity a handler would end up authorizing.
|
||||
|
||||
// daemonSideCtx is what a handler sees for a gateway-relayed call. The transport
|
||||
// peer must be this process's own identity: the gateway is the daemon, so the two
|
||||
// cannot differ, and hardcoding root here instead would describe a state that
|
||||
// never occurs.
|
||||
func daemonSideCtx(t *testing.T, md metadata.MD) context.Context {
|
||||
t.Helper()
|
||||
self, err := ipcauth.CurrentProcessIdentity()
|
||||
if err != nil {
|
||||
t.Skipf("cannot read this process's identity: %v", err)
|
||||
}
|
||||
ctx := peer.NewContext(context.Background(), &peer.Peer{
|
||||
AuthInfo: ipcauth.AuthInfo{
|
||||
CommonAuthInfo: credentials.CommonAuthInfo{SecurityLevel: credentials.NoSecurity},
|
||||
Identity: self,
|
||||
},
|
||||
})
|
||||
return metadata.NewIncomingContext(ctx, md)
|
||||
}
|
||||
|
||||
// gatewayMetadata reproduces what the daemon receives for a JSON request: the
|
||||
// mux annotates the context from the request's headers, then the interceptor on the
|
||||
// gateway's client connection stamps the caller's identity. The order matters,
|
||||
// since the interceptor must win over anything a header put there.
|
||||
func gatewayMetadata(t *testing.T, req *http.Request, ctx context.Context) metadata.MD {
|
||||
t.Helper()
|
||||
mux := runtime.NewServeMux(runtime.WithIncomingHeaderMatcher(jsonIncomingHeaderMatcher))
|
||||
annotated, err := runtime.AnnotateContext(ctx, mux, req,
|
||||
"/daemon.DaemonService/SetConfig",
|
||||
runtime.WithHTTPPathPattern("/daemon.DaemonService/SetConfig"))
|
||||
if err != nil {
|
||||
t.Fatalf("annotate: %v", err)
|
||||
}
|
||||
|
||||
md, ok := metadata.FromOutgoingContext(forwardIdentity(annotated))
|
||||
if !ok {
|
||||
t.Fatal("the interceptor produced no metadata")
|
||||
}
|
||||
return md
|
||||
}
|
||||
|
||||
// clientCtx is the connection context jsonConnContext would have produced for an
|
||||
// HTTP client whose identity the gateway could read.
|
||||
func clientCtx(id ipcauth.Identity, known bool) context.Context {
|
||||
return context.WithValue(context.Background(), jsonPeerIdentity{},
|
||||
jsonPeerIdentityValue{id: id, known: known})
|
||||
}
|
||||
|
||||
// An HTTP client must not be able to name its own identity. grpc-gateway turns
|
||||
// Grpc-Metadata-<key> headers into gRPC metadata, so without the header filter and
|
||||
// the interceptor overwriting the reserved keys, this request would authorize as
|
||||
// uid 0.
|
||||
func TestJSONGateway_ForgedIdentityHeaderIsDropped(t *testing.T) {
|
||||
req, err := http.NewRequest(http.MethodPost, "http://localhost/daemon.DaemonService/SetConfig", nil)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
req.Header.Set("Grpc-Metadata-X-Netbird-Fwd-Uid", "0")
|
||||
req.Header.Set("Grpc-Metadata-X-Netbird-Fwd-Gid", "0")
|
||||
req.Header.Set("Grpc-Metadata-X-Netbird-Fwd", "1")
|
||||
req.Header.Set("Grpc-Metadata-X-Netbird-Fwd-Sid", "S-1-5-18")
|
||||
|
||||
caller := ipcauth.Identity{UID: 31000, GID: 31000}
|
||||
md := gatewayMetadata(t, req, clientCtx(caller, true))
|
||||
|
||||
id, ok := ipcauth.CallerIdentity(daemonSideCtx(t, md))
|
||||
if !ok {
|
||||
t.Fatal("the forwarded identity should be usable")
|
||||
}
|
||||
if id.IsPrivileged() {
|
||||
t.Errorf("forged header was believed: authorized as %v", id)
|
||||
}
|
||||
if id.UID != caller.UID {
|
||||
t.Errorf("authorized as uid %d, want the real client %d", id.UID, caller.UID)
|
||||
}
|
||||
}
|
||||
|
||||
// A request with no headers at all (HTTP/1.0 needs no Host, and a unix socket
|
||||
// yields no host:port) makes grpc-gateway produce no metadata whatsoever and skip
|
||||
// its annotators: "if len(pairs) == 0 { return ctx, nil, nil }" in
|
||||
// runtime/context.go. That is why the identity is stamped by an interceptor
|
||||
// instead. This is the case that previously reached the gate as the daemon itself.
|
||||
func TestJSONGateway_HeaderlessRequestIsStillMarkedForwarded(t *testing.T) {
|
||||
req, err := http.NewRequest(http.MethodPost, "http://localhost/daemon.DaemonService/SetConfig", nil)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
req.Header = http.Header{}
|
||||
req.Host = ""
|
||||
|
||||
caller := ipcauth.Identity{UID: 31000, GID: 31000}
|
||||
ctx := clientCtx(caller, true)
|
||||
|
||||
// Pin the skip path itself: if grpc-gateway ever produced a pair here, this
|
||||
// test would still pass below while no longer covering what it was written for.
|
||||
mux := runtime.NewServeMux(runtime.WithIncomingHeaderMatcher(jsonIncomingHeaderMatcher))
|
||||
annotated, err := runtime.AnnotateContext(ctx, mux, req,
|
||||
"/daemon.DaemonService/SetConfig",
|
||||
runtime.WithHTTPPathPattern("/daemon.DaemonService/SetConfig"))
|
||||
if err != nil {
|
||||
t.Fatalf("annotate: %v", err)
|
||||
}
|
||||
if md, ok := metadata.FromOutgoingContext(annotated); ok {
|
||||
t.Fatalf("grpc-gateway produced metadata %v for a headerless request; "+
|
||||
"this test no longer covers the annotator-skip path", md)
|
||||
}
|
||||
|
||||
md := gatewayMetadata(t, req, ctx)
|
||||
|
||||
id, ok := ipcauth.CallerIdentity(daemonSideCtx(t, md))
|
||||
if !ok {
|
||||
t.Fatal("the forwarded identity should be usable")
|
||||
}
|
||||
if id.UID != caller.UID || id.IsPrivileged() {
|
||||
t.Errorf("authorized as %v, want the real client uid %d", id, caller.UID)
|
||||
}
|
||||
}
|
||||
|
||||
// When the gateway cannot read its client's identity (a TCP JSON socket, say) it
|
||||
// forwards the marker alone. The daemon must then report "unidentified" so the
|
||||
// privileged operations refuse, rather than falling back to the gateway's own
|
||||
// identity.
|
||||
func TestJSONGateway_UnreadableClientIdentityIsUnidentified(t *testing.T) {
|
||||
req, err := http.NewRequest(http.MethodPost, "http://localhost/daemon.DaemonService/SetConfig", nil)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
md := gatewayMetadata(t, req, clientCtx(ipcauth.Identity{}, false))
|
||||
|
||||
if id, ok := ipcauth.CallerIdentity(daemonSideCtx(t, md)); ok {
|
||||
t.Errorf("a request with no client identity was authorized as %v", id)
|
||||
}
|
||||
}
|
||||
|
||||
// A request that never passed through jsonConnContext (no stashed identity) must
|
||||
// also come out unidentified rather than as the daemon.
|
||||
func TestJSONGateway_MissingConnContextIsUnidentified(t *testing.T) {
|
||||
req, err := http.NewRequest(http.MethodPost, "http://localhost/daemon.DaemonService/SetConfig", nil)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
md := gatewayMetadata(t, req, context.Background())
|
||||
|
||||
if id, ok := ipcauth.CallerIdentity(daemonSideCtx(t, md)); ok {
|
||||
t.Errorf("a request with no connection context was authorized as %v", id)
|
||||
}
|
||||
}
|
||||
|
||||
// End to end over a real unix socket: the gateway reads the connecting client's
|
||||
// identity from the socket itself, so a client cannot present anything else.
|
||||
func TestJSONGateway_IdentityComesFromTheSocket(t *testing.T) {
|
||||
mux := runtime.NewServeMux(runtime.WithIncomingHeaderMatcher(jsonIncomingHeaderMatcher))
|
||||
|
||||
type observed struct {
|
||||
md metadata.MD
|
||||
}
|
||||
seen := make(chan observed, 1)
|
||||
|
||||
srv := &http.Server{
|
||||
Handler: http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
ctx, err := runtime.AnnotateContext(r.Context(), mux, r,
|
||||
"/daemon.DaemonService/SetConfig",
|
||||
runtime.WithHTTPPathPattern("/daemon.DaemonService/SetConfig"))
|
||||
if err != nil {
|
||||
t.Errorf("annotate: %v", err)
|
||||
return
|
||||
}
|
||||
md, _ := metadata.FromOutgoingContext(forwardIdentity(ctx))
|
||||
seen <- observed{md: md}
|
||||
w.WriteHeader(http.StatusOK)
|
||||
}),
|
||||
ReadHeaderTimeout: 5 * time.Second,
|
||||
ConnContext: jsonConnContext,
|
||||
}
|
||||
|
||||
sock := filepath.Join(t.TempDir(), "http.sock")
|
||||
ln, err := net.Listen("unix", sock)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
t.Cleanup(func() {
|
||||
if err := srv.Close(); err != nil {
|
||||
t.Logf("close server: %v", err)
|
||||
}
|
||||
})
|
||||
go func() {
|
||||
if err := srv.Serve(ln); err != nil && err != http.ErrServerClosed {
|
||||
t.Logf("serve: %v", err)
|
||||
}
|
||||
}()
|
||||
|
||||
conn, err := net.Dial("unix", sock)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
t.Cleanup(func() {
|
||||
if err := conn.Close(); err != nil {
|
||||
t.Logf("close conn: %v", err)
|
||||
}
|
||||
})
|
||||
|
||||
// Forge the identity headers on the wire as well.
|
||||
request := "POST /daemon.DaemonService/SetConfig HTTP/1.1\r\n" +
|
||||
"Host: localhost\r\n" +
|
||||
"Grpc-Metadata-X-Netbird-Fwd: 1\r\n" +
|
||||
"Grpc-Metadata-X-Netbird-Fwd-Uid: 0\r\n" +
|
||||
"Content-Length: 0\r\n\r\n"
|
||||
if _, err := conn.Write([]byte(request)); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
select {
|
||||
case got := <-seen:
|
||||
self, err := ipcauth.CurrentProcessIdentity()
|
||||
if err != nil {
|
||||
t.Skipf("cannot read this process's identity: %v", err)
|
||||
}
|
||||
// The socket peer is this test process, so that is the identity the
|
||||
// gateway must forward, not the uid 0 the request asked for.
|
||||
if uids := got.md.Get("x-netbird-fwd-uid"); len(uids) != 1 {
|
||||
t.Fatalf("x-netbird-fwd-uid = %v, want exactly the gateway's own value", uids)
|
||||
}
|
||||
id, ok := ipcauth.CallerIdentity(daemonSideCtx(t, got.md))
|
||||
if !ok {
|
||||
t.Fatal("the forwarded identity should be usable")
|
||||
}
|
||||
if id.UID != self.UID {
|
||||
t.Errorf("authorized as uid %d, want the socket peer %d", id.UID, self.UID)
|
||||
}
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("the gateway never handled the request")
|
||||
}
|
||||
}
|
||||
@@ -13,7 +13,6 @@ import (
|
||||
"github.com/spf13/cobra"
|
||||
|
||||
"github.com/netbirdio/netbird/client/configs"
|
||||
"github.com/netbirdio/netbird/client/internal/daemonaddr"
|
||||
"github.com/netbirdio/netbird/util"
|
||||
)
|
||||
|
||||
@@ -126,13 +125,6 @@ func applyServiceParams(cmd *cobra.Command, params *serviceParams) {
|
||||
|
||||
if !rootCmd.PersistentFlags().Changed("daemon-addr") && params.DaemonAddr != "" {
|
||||
daemonAddr = params.DaemonAddr
|
||||
// An install that predates named-pipe support has the loopback TCP
|
||||
// address saved. Callers carry no identity over TCP, so move it to the
|
||||
// pipe instead of restoring a socket the daemon cannot authorize on.
|
||||
if migrated, ok := daemonaddr.MigrateLegacy(daemonAddr); ok {
|
||||
cmd.Printf("Moving the saved daemon address from %s to %s so the daemon can identify its callers\n", daemonAddr, migrated)
|
||||
daemonAddr = migrated
|
||||
}
|
||||
}
|
||||
|
||||
if !serviceCmd.PersistentFlags().Changed("json-socket") && params.JSONSocket != "" {
|
||||
|
||||
@@ -1,14 +0,0 @@
|
||||
//go:build !windows
|
||||
|
||||
package cmd
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"net"
|
||||
)
|
||||
|
||||
// listenNamedPipe is Windows-only: no other platform serves the daemon on a
|
||||
// named pipe.
|
||||
func listenNamedPipe(string) (net.Listener, string, error) {
|
||||
return nil, "", fmt.Errorf("named pipes are only supported on Windows")
|
||||
}
|
||||
@@ -1,41 +0,0 @@
|
||||
//go:build windows
|
||||
|
||||
package cmd
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"net"
|
||||
|
||||
"github.com/Microsoft/go-winio"
|
||||
log "github.com/sirupsen/logrus"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/daemonaddr"
|
||||
"github.com/netbirdio/netbird/client/internal/ipcauth"
|
||||
)
|
||||
|
||||
// listenNamedPipe creates the daemon control pipe and reports the path it ended
|
||||
// up on. The security descriptor lets any local caller connect, as a Unix socket
|
||||
// at 0666 does, and the privileged operations are authorized separately from the
|
||||
// caller's token.
|
||||
//
|
||||
// The protected name comes first so that an unprivileged process cannot take the
|
||||
// name before the service does. Creating it requires being an administrator or
|
||||
// LocalSystem, so a daemon an ordinary user runs themselves, as in netstack mode,
|
||||
// falls back to the plain name; clients try both and check who serves them.
|
||||
func listenNamedPipe(name string) (net.Listener, string, error) {
|
||||
var errs []error
|
||||
for _, path := range daemonaddr.PipePaths(name) {
|
||||
listener, err := winio.ListenPipe(path, &winio.PipeConfig{
|
||||
SecurityDescriptor: ipcauth.DefaultPipeSDDL(),
|
||||
})
|
||||
if err != nil {
|
||||
log.Debugf("not serving the daemon on %s: %v", path, err)
|
||||
errs = append(errs, fmt.Errorf("%s: %w", path, err))
|
||||
continue
|
||||
}
|
||||
return listener, path, nil
|
||||
}
|
||||
|
||||
return nil, "", errors.Join(errs...)
|
||||
}
|
||||
@@ -26,14 +26,6 @@ func listenOnAddress(addr string) (*socketListener, error) {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
if network == "npipe" {
|
||||
listener, path, err := listenNamedPipe(address)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &socketListener{Listener: listener, network: network, address: path}, nil
|
||||
}
|
||||
|
||||
if network == "unix" {
|
||||
removeStaleUnixSocket(address)
|
||||
}
|
||||
@@ -49,11 +41,11 @@ func listenOnAddress(addr string) (*socketListener, error) {
|
||||
func parseListenAddress(addr string) (string, string, error) {
|
||||
network, address, ok := strings.Cut(addr, "://")
|
||||
if !ok || network == "" || address == "" {
|
||||
return "", "", fmt.Errorf("address must be in [unix|tcp|npipe]://[path|host:port|name] format: %q", addr)
|
||||
return "", "", fmt.Errorf("address must be in [unix|tcp]://[path|host:port] format: %q", addr)
|
||||
}
|
||||
|
||||
switch network {
|
||||
case "unix", "tcp", "npipe":
|
||||
case "unix", "tcp":
|
||||
return network, address, nil
|
||||
default:
|
||||
return "", "", fmt.Errorf("unsupported daemon address protocol: %v", network)
|
||||
|
||||
@@ -325,7 +325,7 @@ func runInDaemonMode(ctx context.Context, cmd *cobra.Command, pm *profilemanager
|
||||
if st, ok := gstatus.FromError(err); ok && st.Code() == codes.Unavailable {
|
||||
log.Warnf("setConfig method is not available in the daemon: %s", st.Message())
|
||||
} else {
|
||||
return daemonCallError("call service setConfig method", err)
|
||||
return fmt.Errorf("call service setConfig method: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -379,7 +379,7 @@ func doDaemonUp(ctx context.Context, cmd *cobra.Command, client proto.DaemonServ
|
||||
}
|
||||
|
||||
if loginErr != nil {
|
||||
return daemonCallError("login failed", loginErr)
|
||||
return fmt.Errorf("login failed: %v", loginErr)
|
||||
}
|
||||
|
||||
if loginResp.NeedsSSOLogin {
|
||||
@@ -392,7 +392,7 @@ func doDaemonUp(ctx context.Context, cmd *cobra.Command, client proto.DaemonServ
|
||||
ProfileName: &profileID,
|
||||
Username: &username,
|
||||
}); err != nil {
|
||||
return daemonCallError("call service up method", err)
|
||||
return fmt.Errorf("call service up method: %v", err)
|
||||
}
|
||||
|
||||
return nil
|
||||
|
||||
@@ -121,7 +121,6 @@ type Manager struct {
|
||||
udpTracker *conntrack.UDPTracker
|
||||
icmpTracker *conntrack.ICMPTracker
|
||||
tcpTracker *conntrack.TCPTracker
|
||||
fragments *fragmentTracker
|
||||
forwarder atomic.Pointer[forwarder.Forwarder]
|
||||
pendingCapture atomic.Pointer[forwarder.PacketCapture]
|
||||
logger *nblog.Logger
|
||||
@@ -184,41 +183,6 @@ func (d *decoder) decodePacket(data []byte) error {
|
||||
}
|
||||
}
|
||||
|
||||
// decodeTransport decodes the transport header of a first fragment (which
|
||||
// gopacket leaves undecoded) into the decoder and appends its layer type to
|
||||
// decoded, so the ACL pipeline can evaluate it like a normal packet. It returns
|
||||
// false if the protocol is unsupported or the header is truncated.
|
||||
func (d *decoder) decodeTransport(proto layers.IPProtocol, payload []byte) bool {
|
||||
var l4 gopacket.DecodingLayer
|
||||
var layerType gopacket.LayerType
|
||||
var minLen int
|
||||
switch proto {
|
||||
case layers.IPProtocolTCP:
|
||||
l4, layerType, minLen = &d.tcp, layers.LayerTypeTCP, 20
|
||||
case layers.IPProtocolUDP:
|
||||
l4, layerType, minLen = &d.udp, layers.LayerTypeUDP, 8
|
||||
case layers.IPProtocolICMPv4:
|
||||
l4, layerType, minLen = &d.icmp4, layers.LayerTypeICMPv4, 8
|
||||
case layers.IPProtocolICMPv6:
|
||||
l4, layerType, minLen = &d.icmp6, layers.LayerTypeICMPv6, 8
|
||||
default:
|
||||
return false
|
||||
}
|
||||
|
||||
// Reject a fragment too small to hold the full transport header before
|
||||
// decoding: it can't be ACL-evaluated (tiny-fragment attack), and skipping
|
||||
// the decode avoids gopacket allocating an error on the drop path.
|
||||
if len(payload) < minLen {
|
||||
return false
|
||||
}
|
||||
|
||||
if err := l4.DecodeFromBytes(payload, gopacket.NilDecodeFeedback); err != nil {
|
||||
return false
|
||||
}
|
||||
d.decoded = append(d.decoded, layerType)
|
||||
return true
|
||||
}
|
||||
|
||||
// Create userspace firewall manager constructor
|
||||
func Create(iface common.IFaceMapper, disableServerRoutes bool, flowLogger nftypes.FlowLogger, mtu uint16) (*Manager, error) {
|
||||
return create(iface, nil, disableServerRoutes, flowLogger, mtu)
|
||||
@@ -322,8 +286,6 @@ func create(iface common.IFaceMapper, nativeFirewall firewall.Manager, disableSe
|
||||
if err := m.localipmanager.UpdateLocalIPs(iface); err != nil {
|
||||
return nil, fmt.Errorf("update local IPs: %w", err)
|
||||
}
|
||||
m.fragments = newFragmentTracker(m.logger)
|
||||
|
||||
if disableConntrack {
|
||||
log.Info("conntrack is disabled")
|
||||
} else {
|
||||
@@ -337,7 +299,6 @@ func create(iface common.IFaceMapper, nativeFirewall firewall.Manager, disableSe
|
||||
}
|
||||
}
|
||||
if err := iface.SetFilter(m); err != nil {
|
||||
m.fragments.Close()
|
||||
return nil, fmt.Errorf("set filter: %w", err)
|
||||
}
|
||||
return m, nil
|
||||
@@ -733,10 +694,6 @@ func (m *Manager) resetState() {
|
||||
m.tcpTracker.Close()
|
||||
}
|
||||
|
||||
if m.fragments != nil {
|
||||
m.fragments.Close()
|
||||
}
|
||||
|
||||
if fwder := m.forwarder.Load(); fwder != nil {
|
||||
fwder.SetCapture(nil)
|
||||
fwder.Stop()
|
||||
@@ -1089,20 +1046,19 @@ func (m *Manager) filterInbound(packetData []byte, size int) bool {
|
||||
return true
|
||||
}
|
||||
|
||||
// gopacket does not decode the transport header of any IP fragment, so
|
||||
// fragments take a dedicated path: the first fragment's header is decoded
|
||||
// and ACL-evaluated here, and the remaining fragments inherit its verdict.
|
||||
// TODO: pass fragments of routed packets to forwarder
|
||||
if fragment {
|
||||
return m.filterInboundFragment(d, srcIP, dstIP, size)
|
||||
if m.logger.Enabled(nblog.LevelTrace) {
|
||||
if d.decoded[0] == layers.LayerTypeIPv4 {
|
||||
m.logger.Trace4("packet is a fragment: src=%v dst=%v id=%v flags=%v",
|
||||
srcIP, dstIP, d.ip4.Id, d.ip4.Flags)
|
||||
} else {
|
||||
m.logger.Trace2("packet is an IPv6 fragment: src=%v dst=%v", srcIP, dstIP)
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
return m.filterInboundDecoded(d, srcIP, dstIP, packetData, size)
|
||||
}
|
||||
|
||||
// filterInboundDecoded runs the ACL, DNAT and conntrack pipeline on a fully
|
||||
// decoded (non-fragment) inbound packet. It returns true if the packet should
|
||||
// be dropped.
|
||||
func (m *Manager) filterInboundDecoded(d *decoder, srcIP, dstIP netip.Addr, packetData []byte, size int) bool {
|
||||
// TODO: optimize port DNAT by caching matched rules in conntrack
|
||||
if translated := m.translateInboundPortDNAT(packetData, d, srcIP, dstIP); translated {
|
||||
// Re-decode after port DNAT translation to update port information
|
||||
@@ -1133,226 +1089,33 @@ func (m *Manager) filterInboundDecoded(d *decoder, srcIP, dstIP netip.Addr, pack
|
||||
return m.handleRoutedTraffic(d, srcIP, dstIP, packetData, size)
|
||||
}
|
||||
|
||||
// fragmentMeta holds the reassembly identity and layout of an IP fragment,
|
||||
// extracted uniformly for IPv4 and IPv6.
|
||||
type fragmentMeta struct {
|
||||
key fragmentKey
|
||||
// offset is the fragment offset in 8-byte units (zero for the first
|
||||
// fragment).
|
||||
offset uint16
|
||||
// moreFragments is the More Fragments bit. A first fragment with it unset is
|
||||
// an IPv6 atomic fragment (a complete datagram, RFC 6946): it has no trailing
|
||||
// fragments to inherit a verdict, so it must not be recorded.
|
||||
moreFragments bool
|
||||
proto layers.IPProtocol
|
||||
// l4payload is the fragmentable payload of this fragment. For the first
|
||||
// fragment it starts with the transport header.
|
||||
l4payload []byte
|
||||
// headerEndOctets is the first fragment's payload length in 8-byte units:
|
||||
// the smallest offset a trailing fragment may start at without overlapping
|
||||
// the inspected transport header.
|
||||
headerEndOctets uint16
|
||||
}
|
||||
|
||||
// fragmentMetadata extracts the fragment identity and layout from a decoded IP
|
||||
// fragment. It returns false for fragments it can't interpret (e.g. an IPv6
|
||||
// fragment header shorter than 8 bytes), which are then dropped.
|
||||
func fragmentMetadata(d *decoder, srcIP, dstIP netip.Addr) (fragmentMeta, bool) {
|
||||
switch d.decoded[0] {
|
||||
case layers.LayerTypeIPv4:
|
||||
payload := d.ip4.Payload
|
||||
return fragmentMeta{
|
||||
key: fragmentKey{srcIP: srcIP, dstIP: dstIP, id: uint32(d.ip4.Id), proto: uint8(d.ip4.Protocol)},
|
||||
offset: d.ip4.FragOffset,
|
||||
moreFragments: d.ip4.Flags&layers.IPv4MoreFragments != 0,
|
||||
proto: d.ip4.Protocol,
|
||||
l4payload: payload,
|
||||
headerEndOctets: octets(len(payload)),
|
||||
}, true
|
||||
|
||||
case layers.LayerTypeIPv6:
|
||||
// IPv6 fragment extension header: 8 bytes, followed by the fragmentable
|
||||
// payload. Layout: next header (1), reserved (1), offset+flags (2), id (4).
|
||||
payload := d.ip6.Payload
|
||||
if len(payload) < 8 {
|
||||
return fragmentMeta{}, false
|
||||
}
|
||||
nextHeader := layers.IPProtocol(payload[0])
|
||||
offsetFlags := binary.BigEndian.Uint16(payload[2:4])
|
||||
id := binary.BigEndian.Uint32(payload[4:8])
|
||||
l4 := payload[8:]
|
||||
return fragmentMeta{
|
||||
key: fragmentKey{srcIP: srcIP, dstIP: dstIP, id: id, proto: uint8(nextHeader)},
|
||||
offset: offsetFlags >> 3,
|
||||
moreFragments: offsetFlags&1 != 0,
|
||||
proto: nextHeader,
|
||||
l4payload: l4,
|
||||
headerEndOctets: octets(len(l4)),
|
||||
}, true
|
||||
|
||||
default:
|
||||
return fragmentMeta{}, false
|
||||
}
|
||||
}
|
||||
|
||||
// octets rounds a byte length up to whole 8-byte units, the granularity of the
|
||||
// IP fragment offset field.
|
||||
func octets(nbytes int) uint16 {
|
||||
return uint16((nbytes + 7) / 8)
|
||||
}
|
||||
|
||||
// filterInboundFragment decides the fate of an IP fragment. gopacket stops
|
||||
// decoding at the network layer for every fragment, so the first fragment's
|
||||
// transport header is decoded and ACL-evaluated here and its verdict recorded;
|
||||
// the remaining (headerless) fragments inherit that verdict. Anything that
|
||||
// cannot be tied to an allowed, non-overlapping first fragment is dropped.
|
||||
func (m *Manager) filterInboundFragment(d *decoder, srcIP, dstIP netip.Addr, size int) bool {
|
||||
meta, ok := fragmentMetadata(d, srcIP, dstIP)
|
||||
if !ok {
|
||||
if m.logger.Enabled(nblog.LevelTrace) {
|
||||
m.logger.Trace2("dropping unsupported fragment: src=%v dst=%v", srcIP, dstIP)
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
if meta.offset != 0 {
|
||||
return m.filterTrailingFragment(meta, srcIP, dstIP)
|
||||
}
|
||||
|
||||
// A new first fragment supersedes any recorded verdict for this datagram, so
|
||||
// a re-sent or overlapping offset-zero fragment can't inherit the old one.
|
||||
m.fragments.poison(meta.key)
|
||||
|
||||
// First fragment: decode its transport header so the ACL can evaluate it. A
|
||||
// decode failure means the fragment is too small to hold the full transport
|
||||
// header (RFC 1858 §3 tiny-fragment attack); it can't be evaluated, so drop it.
|
||||
if !d.decodeTransport(meta.proto, meta.l4payload) {
|
||||
if m.logger.Enabled(nblog.LevelTrace) {
|
||||
m.logger.Trace3("dropping first fragment without full L4 header: src=%v dst=%v id=%v",
|
||||
srcIP, dstIP, meta.key.id)
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
return m.filterFirstFragment(d, meta, srcIP, dstIP, size)
|
||||
}
|
||||
|
||||
// filterTrailingFragment applies a recorded first-fragment verdict to a
|
||||
// non-first fragment.
|
||||
func (m *Manager) filterTrailingFragment(meta fragmentMeta, srcIP, dstIP netip.Addr) bool {
|
||||
switch m.fragments.verdict(meta.key, meta.offset) {
|
||||
case fragmentAllow:
|
||||
return false
|
||||
case fragmentOverlap:
|
||||
if m.logger.Enabled(nblog.LevelTrace) {
|
||||
m.logger.Trace3("dropping overlapping fragment rewriting inspected header: src=%v dst=%v id=%v",
|
||||
srcIP, dstIP, meta.key.id)
|
||||
}
|
||||
return true
|
||||
default:
|
||||
if m.logger.Enabled(nblog.LevelTrace) {
|
||||
m.logger.Trace3("dropping fragment with no allowed first fragment: src=%v dst=%v id=%v",
|
||||
srcIP, dstIP, meta.key.id)
|
||||
}
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
// filterFirstFragment runs the verdict part of the inbound pipeline on a first
|
||||
// fragment with its transport header decoded. It mirrors filterInboundDecoded
|
||||
// but skips DNAT (port rewriting on fragments is unsupported) and forwarder
|
||||
// injection (fragments are left to the stack to reassemble, not forwarded).
|
||||
// Allowed fragments have their verdict recorded so the datagram's trailing
|
||||
// fragments inherit it.
|
||||
func (m *Manager) filterFirstFragment(d *decoder, meta fragmentMeta, srcIP, dstIP netip.Addr, size int) bool {
|
||||
if m.stateful && m.isValidTrackedConnection(d, srcIP, dstIP, size) {
|
||||
m.recordFirstFragment(meta)
|
||||
return false
|
||||
}
|
||||
|
||||
if m.localipmanager.IsLocalIP(dstIP) {
|
||||
ruleID, blocked := m.peerACLsBlock(srcIP, d, nil)
|
||||
if blocked {
|
||||
m.storeDropFlow("Dropping local first fragment (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
|
||||
d, srcIP, dstIP, ruleID, size)
|
||||
return true
|
||||
}
|
||||
m.trackInbound(d, srcIP, dstIP, ruleID, size)
|
||||
m.recordFirstFragment(meta)
|
||||
return false
|
||||
}
|
||||
|
||||
if !m.routingEnabled.Load() {
|
||||
if m.logger.Enabled(nblog.LevelTrace) {
|
||||
m.logger.Trace2("Dropping routed fragment (routing disabled): src=%s dst=%s", srcIP, dstIP)
|
||||
}
|
||||
return true
|
||||
}
|
||||
if m.nativeRouter.Load() {
|
||||
m.trackInbound(d, srcIP, dstIP, nil, size)
|
||||
m.recordFirstFragment(meta)
|
||||
return false
|
||||
}
|
||||
|
||||
// TODO: pass fragments of routed packets to the forwarder; until then
|
||||
// allowed routed fragments go to the native stack.
|
||||
srcPort, dstPort := getPortsFromPacket(d)
|
||||
ruleID, pass := m.routeACLsPass(srcIP, dstIP, d.decoded[1], srcPort, dstPort)
|
||||
if !pass {
|
||||
m.storeDropFlow("Dropping routed first fragment (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
|
||||
d, srcIP, dstIP, ruleID, size)
|
||||
return true
|
||||
}
|
||||
|
||||
m.recordFirstFragment(meta)
|
||||
return false
|
||||
}
|
||||
|
||||
// recordFirstFragment caches an allowed first fragment's verdict for its
|
||||
// trailing fragments to inherit. Atomic fragments (no More Fragments bit) are
|
||||
// complete datagrams with no trailing fragments, so they are not cached and
|
||||
// cannot exhaust the verdict table.
|
||||
func (m *Manager) recordFirstFragment(meta fragmentMeta) {
|
||||
if !meta.moreFragments {
|
||||
return
|
||||
}
|
||||
m.fragments.recordAllowed(meta.key, meta.headerEndOctets)
|
||||
}
|
||||
|
||||
// storeDropFlow logs and records a netflow drop event for an inbound packet
|
||||
// denied by the ACLs. msg is the trace format taking rule id, protocol, source
|
||||
// and destination.
|
||||
func (m *Manager) storeDropFlow(msg string, d *decoder, srcIP, dstIP netip.Addr, ruleID []byte, size int) {
|
||||
pnum := getProtocolFromPacket(d)
|
||||
srcPort, dstPort := getPortsFromPacket(d)
|
||||
|
||||
if m.logger.Enabled(nblog.LevelTrace) {
|
||||
m.logger.Trace6(msg, ruleID, pnum, srcIP, srcPort, dstIP, dstPort)
|
||||
}
|
||||
|
||||
m.flowLogger.StoreEvent(nftypes.EventFields{
|
||||
FlowID: uuid.New(),
|
||||
Type: nftypes.TypeDrop,
|
||||
RuleID: ruleID,
|
||||
Direction: nftypes.Ingress,
|
||||
Protocol: pnum,
|
||||
SourceIP: srcIP,
|
||||
DestIP: dstIP,
|
||||
SourcePort: srcPort,
|
||||
DestPort: dstPort,
|
||||
// TODO: icmp type/code
|
||||
RxPackets: 1,
|
||||
RxBytes: uint64(size),
|
||||
})
|
||||
}
|
||||
|
||||
// handleLocalTraffic handles local traffic.
|
||||
// If it returns true, the packet should be dropped.
|
||||
func (m *Manager) handleLocalTraffic(d *decoder, srcIP, dstIP netip.Addr, packetData []byte, size int) bool {
|
||||
ruleID, blocked := m.peerACLsBlock(srcIP, d, packetData)
|
||||
if blocked {
|
||||
m.storeDropFlow("Dropping local packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
|
||||
d, srcIP, dstIP, ruleID, size)
|
||||
pnum := getProtocolFromPacket(d)
|
||||
srcPort, dstPort := getPortsFromPacket(d)
|
||||
|
||||
if m.logger.Enabled(nblog.LevelTrace) {
|
||||
m.logger.Trace6("Dropping local packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
|
||||
ruleID, pnum, srcIP, srcPort, dstIP, dstPort)
|
||||
}
|
||||
|
||||
m.flowLogger.StoreEvent(nftypes.EventFields{
|
||||
FlowID: uuid.New(),
|
||||
Type: nftypes.TypeDrop,
|
||||
RuleID: ruleID,
|
||||
Direction: nftypes.Ingress,
|
||||
Protocol: pnum,
|
||||
SourceIP: srcIP,
|
||||
DestIP: dstIP,
|
||||
SourcePort: srcPort,
|
||||
DestPort: dstPort,
|
||||
// TODO: icmp type/code
|
||||
RxPackets: 1,
|
||||
RxBytes: uint64(size),
|
||||
})
|
||||
return true
|
||||
}
|
||||
|
||||
@@ -1405,8 +1168,27 @@ func (m *Manager) handleRoutedTraffic(d *decoder, srcIP, dstIP netip.Addr, packe
|
||||
|
||||
ruleID, pass := m.routeACLsPass(srcIP, dstIP, protoLayer, srcPort, dstPort)
|
||||
if !pass {
|
||||
m.storeDropFlow("Dropping routed packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
|
||||
d, srcIP, dstIP, ruleID, size)
|
||||
proto := getProtocolFromPacket(d)
|
||||
|
||||
if m.logger.Enabled(nblog.LevelTrace) {
|
||||
m.logger.Trace6("Dropping routed packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
|
||||
ruleID, proto, srcIP, srcPort, dstIP, dstPort)
|
||||
}
|
||||
|
||||
m.flowLogger.StoreEvent(nftypes.EventFields{
|
||||
FlowID: uuid.New(),
|
||||
Type: nftypes.TypeDrop,
|
||||
RuleID: ruleID,
|
||||
Direction: nftypes.Ingress,
|
||||
Protocol: proto,
|
||||
SourceIP: srcIP,
|
||||
DestIP: dstIP,
|
||||
SourcePort: srcPort,
|
||||
DestPort: dstPort,
|
||||
// TODO: icmp type/code
|
||||
RxPackets: 1,
|
||||
RxBytes: uint64(size),
|
||||
})
|
||||
return true
|
||||
}
|
||||
|
||||
|
||||
@@ -5,9 +5,7 @@ import (
|
||||
"fmt"
|
||||
"net"
|
||||
"net/netip"
|
||||
"os"
|
||||
"runtime"
|
||||
"strconv"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
@@ -33,11 +31,6 @@ const (
|
||||
defaultMaxInFlight = 1024
|
||||
iosReceiveWindow = 16384
|
||||
iosMaxInFlight = 256
|
||||
|
||||
// envForceTCPRACK overrides the platform default for gVisor's RACK loss
|
||||
// detection. Set to a truthy value to force RACK on, or a falsy value to
|
||||
// force it off, on any platform.
|
||||
envForceTCPRACK = "NB_FORCE_TCP_RACK"
|
||||
)
|
||||
|
||||
type Forwarder struct {
|
||||
@@ -159,8 +152,6 @@ func New(iface common.IFaceMapper, logger *nblog.Logger, flowLogger nftypes.Flow
|
||||
maxInFlight = iosMaxInFlight
|
||||
}
|
||||
|
||||
configureTCPRecovery(s)
|
||||
|
||||
tcpForwarder := tcp.NewForwarder(s, receiveWindow, maxInFlight, f.handleTCP)
|
||||
s.SetTransportProtocolHandler(tcp.ProtocolNumber, tcpForwarder.HandlePacket)
|
||||
|
||||
@@ -475,31 +466,3 @@ func probeRawICMP(network, addr string, logger *nblog.Logger) bool {
|
||||
logger.Debug1("forwarder: raw %s socket access available", network)
|
||||
return true
|
||||
}
|
||||
|
||||
// configureTCPRecovery disables gVisor's RACK loss detection on Windows, where
|
||||
// it interacts poorly with the host and collapses throughput on routed TCP
|
||||
// connections (gVisor issue #9778). Other platforms keep the default. The
|
||||
// EnvForceTCPRACK environment variable overrides the platform default.
|
||||
func configureTCPRecovery(s *stack.Stack) {
|
||||
disableRACK := runtime.GOOS == "windows"
|
||||
|
||||
if val := os.Getenv(envForceTCPRACK); val != "" {
|
||||
force, err := strconv.ParseBool(val)
|
||||
if err != nil {
|
||||
log.Warnf("parse %s: %v", envForceTCPRACK, err)
|
||||
} else {
|
||||
disableRACK = !force
|
||||
}
|
||||
}
|
||||
|
||||
if !disableRACK {
|
||||
return
|
||||
}
|
||||
|
||||
opt := tcpip.TCPRecovery(0)
|
||||
if err := s.SetTransportProtocolOption(tcp.ProtocolNumber, &opt); err != nil {
|
||||
log.Warnf("disable TCP RACK loss detection: %v", err)
|
||||
return
|
||||
}
|
||||
log.Info("forwarder: TCP RACK loss detection disabled")
|
||||
}
|
||||
|
||||
@@ -1,204 +0,0 @@
|
||||
package uspfilter
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/netip"
|
||||
"os"
|
||||
"strconv"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
nblog "github.com/netbirdio/netbird/client/firewall/uspfilter/log"
|
||||
)
|
||||
|
||||
const (
|
||||
// defaultFragmentTimeout bounds how long a first-fragment verdict is kept
|
||||
// while the remaining fragments arrive. It mirrors the Linux IP reassembly
|
||||
// timeout (net.ipv4.ipfrag_time).
|
||||
defaultFragmentTimeout = 30 * time.Second
|
||||
// fragmentCleanupInterval is how often expired verdicts are purged.
|
||||
fragmentCleanupInterval = 10 * time.Second
|
||||
// defaultMaxFragmentEntries caps the number of concurrently tracked
|
||||
// fragmented datagrams. The table stays bounded because each datagram is a
|
||||
// single small entry regardless of how many fragments it is split into, and
|
||||
// the 13-bit IPv4 fragment-offset field limits any datagram to 64 KiB.
|
||||
defaultMaxFragmentEntries = 16384
|
||||
|
||||
// EnvFragmentMaxEntries overrides defaultMaxFragmentEntries.
|
||||
EnvFragmentMaxEntries = "NB_FRAGMENT_MAX_ENTRIES"
|
||||
)
|
||||
|
||||
// fragmentVerdict is the decision for a trailing (headerless) fragment.
|
||||
type fragmentVerdict int
|
||||
|
||||
const (
|
||||
// fragmentDeny drops the fragment: no allowed first fragment is on record.
|
||||
fragmentDeny fragmentVerdict = iota
|
||||
// fragmentAllow passes the fragment: it belongs to an allowed datagram and
|
||||
// does not overlap the already-inspected transport header.
|
||||
fragmentAllow
|
||||
// fragmentOverlap drops the fragment and poisons its datagram: it overlaps
|
||||
// the transport header the ACL inspected (RFC 1858 §4, RFC 3128; RFC 5722
|
||||
// requires discarding the whole datagram on overlap for IPv6).
|
||||
fragmentOverlap
|
||||
)
|
||||
|
||||
// fragmentKey identifies a fragmented datagram. It matches the RFC 791 / RFC
|
||||
// 8200 reassembly key: source, destination, protocol and identification. The id
|
||||
// is 32-bit to hold both the IPv4 (16-bit) and IPv6 (32-bit) identification.
|
||||
type fragmentKey struct {
|
||||
srcIP netip.Addr
|
||||
dstIP netip.Addr
|
||||
id uint32
|
||||
proto uint8
|
||||
}
|
||||
|
||||
// fragmentEntry records the verdict of an allowed first fragment.
|
||||
type fragmentEntry struct {
|
||||
// headerEndOctets is the offset, in 8-byte units, at which the first
|
||||
// fragment's payload ended. A trailing fragment starting before this
|
||||
// overlaps bytes the ACL already inspected and is rejected.
|
||||
headerEndOctets uint16
|
||||
// recordedAt is when the first fragment was accepted. The verdict expires a
|
||||
// fixed timeout later and is not refreshed, mirroring the kernel reassembly
|
||||
// timer so a trailing-fragment flood can't keep a datagram alive.
|
||||
recordedAt time.Time
|
||||
}
|
||||
|
||||
// fragmentTracker records the ACL verdict of a datagram's first fragment so the
|
||||
// remaining fragments, which carry no L4 header, can inherit the decision
|
||||
// without reassembling the datagram. Only allowed first fragments are stored;
|
||||
// anything that cannot be tied to an allowed, non-overlapping first fragment is
|
||||
// dropped (fail closed).
|
||||
type fragmentTracker struct {
|
||||
logger *nblog.Logger
|
||||
mutex sync.Mutex
|
||||
entries map[fragmentKey]fragmentEntry
|
||||
timeout time.Duration
|
||||
// maxEntries caps the table; atCapacity dedups the capacity warning until
|
||||
// the table drains below the cap again.
|
||||
maxEntries int
|
||||
atCapacity bool
|
||||
cleanupTicker *time.Ticker
|
||||
cancel context.CancelFunc
|
||||
}
|
||||
|
||||
func newFragmentTracker(logger *nblog.Logger) *fragmentTracker {
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
t := &fragmentTracker{
|
||||
logger: logger,
|
||||
entries: make(map[fragmentKey]fragmentEntry),
|
||||
timeout: defaultFragmentTimeout,
|
||||
maxEntries: fragmentMaxEntries(logger),
|
||||
cleanupTicker: time.NewTicker(fragmentCleanupInterval),
|
||||
cancel: cancel,
|
||||
}
|
||||
go t.cleanupRoutine(ctx)
|
||||
return t
|
||||
}
|
||||
|
||||
func fragmentMaxEntries(logger *nblog.Logger) int {
|
||||
v := os.Getenv(EnvFragmentMaxEntries)
|
||||
if v == "" {
|
||||
return defaultMaxFragmentEntries
|
||||
}
|
||||
n, err := strconv.Atoi(v)
|
||||
if err != nil || n <= 0 {
|
||||
logger.Warn2("invalid %s=%q, using default", EnvFragmentMaxEntries, v)
|
||||
return defaultMaxFragmentEntries
|
||||
}
|
||||
return n
|
||||
}
|
||||
|
||||
// recordAllowed stores the verdict of an allowed first fragment. headerEndOctets
|
||||
// is the first fragment's payload length in 8-byte units. When the table is full
|
||||
// the record is dropped, which fails closed: the datagram's trailing fragments
|
||||
// will be denied.
|
||||
func (t *fragmentTracker) recordAllowed(key fragmentKey, headerEndOctets uint16) {
|
||||
t.mutex.Lock()
|
||||
defer t.mutex.Unlock()
|
||||
|
||||
if t.entries == nil {
|
||||
return
|
||||
}
|
||||
if _, ok := t.entries[key]; !ok && len(t.entries) >= t.maxEntries {
|
||||
if !t.atCapacity {
|
||||
t.atCapacity = true
|
||||
t.logger.Warn2("fragment verdict table at capacity (%d/%d): trailing fragments of new datagrams will be dropped",
|
||||
len(t.entries), t.maxEntries)
|
||||
}
|
||||
return
|
||||
}
|
||||
t.entries[key] = fragmentEntry{
|
||||
headerEndOctets: headerEndOctets,
|
||||
recordedAt: time.Now(),
|
||||
}
|
||||
}
|
||||
|
||||
// poison drops any recorded verdict for a datagram, so its later fragments are
|
||||
// denied until a new allowed first fragment is recorded. Called on every
|
||||
// offset-zero fragment to defeat offset-zero overlap rewrites (RFC 3128).
|
||||
func (t *fragmentTracker) poison(key fragmentKey) {
|
||||
t.mutex.Lock()
|
||||
defer t.mutex.Unlock()
|
||||
delete(t.entries, key)
|
||||
}
|
||||
|
||||
// verdict decides the fate of a trailing fragment at fragOffsetOctets (the IPv4
|
||||
// fragment offset, in 8-byte units). A fragment overlapping the inspected
|
||||
// header poisons the datagram: the entry is removed so all further fragments of
|
||||
// that datagram are denied too.
|
||||
func (t *fragmentTracker) verdict(key fragmentKey, fragOffsetOctets uint16) fragmentVerdict {
|
||||
t.mutex.Lock()
|
||||
defer t.mutex.Unlock()
|
||||
|
||||
entry, ok := t.entries[key]
|
||||
if !ok {
|
||||
return fragmentDeny
|
||||
}
|
||||
if time.Since(entry.recordedAt) > t.timeout {
|
||||
delete(t.entries, key)
|
||||
return fragmentDeny
|
||||
}
|
||||
if fragOffsetOctets < entry.headerEndOctets {
|
||||
delete(t.entries, key)
|
||||
return fragmentOverlap
|
||||
}
|
||||
return fragmentAllow
|
||||
}
|
||||
|
||||
func (t *fragmentTracker) cleanupRoutine(ctx context.Context) {
|
||||
defer t.cleanupTicker.Stop()
|
||||
for {
|
||||
select {
|
||||
case <-t.cleanupTicker.C:
|
||||
t.cleanup()
|
||||
case <-ctx.Done():
|
||||
return
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func (t *fragmentTracker) cleanup() {
|
||||
t.mutex.Lock()
|
||||
defer t.mutex.Unlock()
|
||||
|
||||
for key, entry := range t.entries {
|
||||
if time.Since(entry.recordedAt) > t.timeout {
|
||||
delete(t.entries, key)
|
||||
}
|
||||
}
|
||||
|
||||
if len(t.entries) < t.maxEntries {
|
||||
t.atCapacity = false
|
||||
}
|
||||
}
|
||||
|
||||
// Close stops the cleanup routine and releases resources.
|
||||
func (t *fragmentTracker) Close() {
|
||||
t.cancel()
|
||||
|
||||
t.mutex.Lock()
|
||||
t.entries = nil
|
||||
t.mutex.Unlock()
|
||||
}
|
||||
@@ -1,115 +0,0 @@
|
||||
package uspfilter
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// benchFilterInbound drives filterInbound over a fixed packet in a tight loop.
|
||||
// Packets are built once, outside the timed region, so the benchmark measures
|
||||
// only pipeline cost, which is what an attacker can amplify.
|
||||
func benchFilterInbound(b *testing.B, pkt []byte) {
|
||||
b.Helper()
|
||||
b.ReportAllocs()
|
||||
b.SetBytes(int64(len(pkt)))
|
||||
b.ResetTimer()
|
||||
for i := 0; i < b.N; i++ {
|
||||
m := benchManager
|
||||
m.filterInbound(pkt, len(pkt))
|
||||
}
|
||||
}
|
||||
|
||||
// benchManager is a package-level manager reused across fragment benchmarks so
|
||||
// setup cost stays out of the timed region.
|
||||
var benchManager *Manager
|
||||
|
||||
func setupBenchManager(b *testing.B) *Manager {
|
||||
b.Helper()
|
||||
m := newFragmentTestManager(b)
|
||||
allowUDP(b, m, 8080)
|
||||
// Disable conntrack so the allowed-first-fragment path measures transport
|
||||
// decode + ACL every iteration instead of matching the connection tracked
|
||||
// on the first iteration.
|
||||
m.stateful = false
|
||||
benchManager = m
|
||||
return m
|
||||
}
|
||||
|
||||
// BenchmarkInbound_NormalPacket is the baseline: a full, non-fragmented UDP
|
||||
// packet that passes the ACL. Fragment paths should stay comparable to this.
|
||||
func BenchmarkInbound_NormalPacket(b *testing.B) {
|
||||
setupBenchManager(b)
|
||||
pkt := normalUDPPacket(b, 8080, 32)
|
||||
benchFilterInbound(b, pkt)
|
||||
}
|
||||
|
||||
// BenchmarkInbound_FirstFragmentAllowed measures the first-fragment path:
|
||||
// transport decode + ACL evaluation + verdict record.
|
||||
func BenchmarkInbound_FirstFragmentAllowed(b *testing.B) {
|
||||
setupBenchManager(b)
|
||||
pkt := firstFragmentUDP(b, 0x2000, 8080, 32)
|
||||
benchFilterInbound(b, pkt)
|
||||
}
|
||||
|
||||
// BenchmarkInbound_TrailingFragmentAllowed measures the common trailing-fragment
|
||||
// path: a single map lookup after the first fragment is on record.
|
||||
func BenchmarkInbound_TrailingFragmentAllowed(b *testing.B) {
|
||||
m := setupBenchManager(b)
|
||||
first := firstFragmentUDP(b, 0x3000, 8080, 32)
|
||||
m.filterInbound(first, len(first))
|
||||
pkt := trailingFragment(b, 0x3000, 5, false, 24)
|
||||
benchFilterInbound(b, pkt)
|
||||
}
|
||||
|
||||
// BenchmarkInbound_TrailingFragmentNoFirst is the primary DoS vector: an
|
||||
// attacker floods trailing fragments with no first fragment on record. Each is
|
||||
// a map miss and must be cheap.
|
||||
func BenchmarkInbound_TrailingFragmentNoFirst(b *testing.B) {
|
||||
setupBenchManager(b)
|
||||
pkt := trailingFragment(b, 0x4000, 185, false, 40)
|
||||
benchFilterInbound(b, pkt)
|
||||
}
|
||||
|
||||
// BenchmarkInbound_TinyFirstFragment measures the tiny-fragment drop path: a
|
||||
// first fragment too small to decode a transport header.
|
||||
func BenchmarkInbound_TinyFirstFragment(b *testing.B) {
|
||||
setupBenchManager(b)
|
||||
pkt := trailingFragment(b, 0x5000, 0, true, 4)
|
||||
benchFilterInbound(b, pkt)
|
||||
}
|
||||
|
||||
// BenchmarkInbound_TrailingFragmentDistinctIDs is the worst case for the
|
||||
// verdict table: an attacker varies the datagram id on every packet so no first
|
||||
// fragment ever matches. Verdict lookups always miss and nothing is recorded,
|
||||
// so the table cannot grow. Each iteration rewrites the id field in place.
|
||||
func BenchmarkInbound_TrailingFragmentDistinctIDs(b *testing.B) {
|
||||
setupBenchManager(b)
|
||||
pkt := trailingFragment(b, 0x6000, 185, false, 40)
|
||||
m := benchManager
|
||||
|
||||
b.ReportAllocs()
|
||||
b.SetBytes(int64(len(pkt)))
|
||||
b.ResetTimer()
|
||||
for i := 0; i < b.N; i++ {
|
||||
// IPv4 identification field is at bytes 4:6.
|
||||
binary.BigEndian.PutUint16(pkt[4:6], uint16(i))
|
||||
m.filterInbound(pkt, len(pkt))
|
||||
}
|
||||
}
|
||||
|
||||
// BenchmarkInbound_FirstFragmentDistinctIDs measures sustained first-fragment
|
||||
// pressure with distinct ids: transport decode + ACL + verdict insert until the
|
||||
// table caps, exercising the map growth and capacity guard.
|
||||
func BenchmarkInbound_FirstFragmentDistinctIDs(b *testing.B) {
|
||||
setupBenchManager(b)
|
||||
pkt := firstFragmentUDP(b, 0x7000, 8080, 32)
|
||||
m := benchManager
|
||||
|
||||
b.ReportAllocs()
|
||||
b.SetBytes(int64(len(pkt)))
|
||||
b.ResetTimer()
|
||||
for i := 0; i < b.N; i++ {
|
||||
binary.BigEndian.PutUint16(pkt[4:6], uint16(i))
|
||||
m.filterInbound(pkt, len(pkt))
|
||||
}
|
||||
}
|
||||
@@ -1,554 +0,0 @@
|
||||
package uspfilter
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
"net"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/google/gopacket"
|
||||
"github.com/google/gopacket/layers"
|
||||
"github.com/stretchr/testify/require"
|
||||
|
||||
fw "github.com/netbirdio/netbird/client/firewall/manager"
|
||||
nbiface "github.com/netbirdio/netbird/client/iface"
|
||||
"github.com/netbirdio/netbird/client/iface/device"
|
||||
"github.com/netbirdio/netbird/client/iface/wgaddr"
|
||||
)
|
||||
|
||||
const (
|
||||
fragTestSrc = "100.10.0.1"
|
||||
fragTestDst = "100.10.0.100"
|
||||
fragTestSrcV6 = "fd00::1"
|
||||
fragTestDstV6 = "fd00::100"
|
||||
)
|
||||
|
||||
func newFragmentTestManager(tb testing.TB) *Manager {
|
||||
tb.Helper()
|
||||
|
||||
ifaceMock := &IFaceMock{
|
||||
SetFilterFunc: func(device.PacketFilter) error { return nil },
|
||||
AddressFunc: func() wgaddr.Address {
|
||||
return wgaddr.Address{
|
||||
IP: netip.MustParseAddr(fragTestDst),
|
||||
Network: netip.MustParsePrefix("100.10.0.0/16"),
|
||||
IPv6: netip.MustParseAddr(fragTestDstV6),
|
||||
IPv6Net: netip.MustParsePrefix("fd00::/64"),
|
||||
}
|
||||
},
|
||||
}
|
||||
|
||||
m, err := Create(ifaceMock, false, flowLogger, nbiface.DefaultMTU)
|
||||
require.NoError(tb, err)
|
||||
require.NoError(tb, m.UpdateLocalIPs())
|
||||
tb.Cleanup(func() { require.NoError(tb, m.Close(nil)) })
|
||||
return m
|
||||
}
|
||||
|
||||
// firstFragmentUDPTo builds the first fragment of a fragmented UDP datagram to
|
||||
// the given destination: it carries the full UDP header plus payloadLen bytes
|
||||
// of data, with the More Fragments flag set and offset zero.
|
||||
func firstFragmentUDPTo(tb testing.TB, dst string, id uint16, dstPort uint16, payloadLen int) []byte {
|
||||
tb.Helper()
|
||||
|
||||
ip := &layers.IPv4{
|
||||
Version: 4,
|
||||
TTL: 64,
|
||||
Id: id,
|
||||
Protocol: layers.IPProtocolUDP,
|
||||
SrcIP: net.ParseIP(fragTestSrc),
|
||||
DstIP: net.ParseIP(dst),
|
||||
Flags: layers.IPv4MoreFragments,
|
||||
}
|
||||
udp := &layers.UDP{SrcPort: 40000, DstPort: layers.UDPPort(dstPort)}
|
||||
require.NoError(tb, udp.SetNetworkLayerForChecksum(ip))
|
||||
|
||||
buf := gopacket.NewSerializeBuffer()
|
||||
opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
|
||||
require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, udp, gopacket.Payload(make([]byte, payloadLen))))
|
||||
return buf.Bytes()
|
||||
}
|
||||
|
||||
func firstFragmentUDP(tb testing.TB, id uint16, dstPort uint16, payloadLen int) []byte {
|
||||
tb.Helper()
|
||||
return firstFragmentUDPTo(tb, fragTestDst, id, dstPort, payloadLen)
|
||||
}
|
||||
|
||||
// firstFragmentTCP builds the first fragment of a fragmented TCP datagram: the
|
||||
// full 20-byte TCP header plus 12 bytes of data, with the More Fragments flag
|
||||
// set and offset zero.
|
||||
func firstFragmentTCP(tb testing.TB, id uint16, dstPort uint16) []byte {
|
||||
tb.Helper()
|
||||
|
||||
ip := &layers.IPv4{
|
||||
Version: 4,
|
||||
TTL: 64,
|
||||
Id: id,
|
||||
Protocol: layers.IPProtocolTCP,
|
||||
SrcIP: net.ParseIP(fragTestSrc),
|
||||
DstIP: net.ParseIP(fragTestDst),
|
||||
Flags: layers.IPv4MoreFragments,
|
||||
}
|
||||
tcp := &layers.TCP{SrcPort: 40000, DstPort: layers.TCPPort(dstPort), SYN: true, Window: 64240}
|
||||
require.NoError(tb, tcp.SetNetworkLayerForChecksum(ip))
|
||||
|
||||
buf := gopacket.NewSerializeBuffer()
|
||||
opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
|
||||
require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, tcp, gopacket.Payload(make([]byte, 12))))
|
||||
return buf.Bytes()
|
||||
}
|
||||
|
||||
// trailingFragmentTo builds a non-first fragment to the given destination: an
|
||||
// IPv4 header at the given fragment offset (in 8-byte units) carrying raw
|
||||
// payload and no L4 header.
|
||||
func trailingFragmentTo(tb testing.TB, dst string, proto layers.IPProtocol, id uint16, fragOffsetOctets uint16, moreFragments bool, payloadLen int) []byte {
|
||||
tb.Helper()
|
||||
|
||||
ip := &layers.IPv4{
|
||||
Version: 4,
|
||||
TTL: 64,
|
||||
Id: id,
|
||||
Protocol: proto,
|
||||
SrcIP: net.ParseIP(fragTestSrc),
|
||||
DstIP: net.ParseIP(dst),
|
||||
FragOffset: fragOffsetOctets,
|
||||
}
|
||||
if moreFragments {
|
||||
ip.Flags = layers.IPv4MoreFragments
|
||||
}
|
||||
|
||||
buf := gopacket.NewSerializeBuffer()
|
||||
opts := gopacket.SerializeOptions{FixLengths: true}
|
||||
require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, gopacket.Payload(make([]byte, payloadLen))))
|
||||
return buf.Bytes()
|
||||
}
|
||||
|
||||
func trailingFragment(tb testing.TB, id uint16, fragOffsetOctets uint16, moreFragments bool, payloadLen int) []byte {
|
||||
tb.Helper()
|
||||
return trailingFragmentTo(tb, fragTestDst, layers.IPProtocolUDP, id, fragOffsetOctets, moreFragments, payloadLen)
|
||||
}
|
||||
|
||||
// outboundUDPPacket builds a complete outbound UDP packet from the local
|
||||
// address, used to establish conntrack state for reply-direction tests.
|
||||
func outboundUDPPacket(tb testing.TB, srcPort, dstPort uint16) []byte {
|
||||
tb.Helper()
|
||||
|
||||
ip := &layers.IPv4{
|
||||
Version: 4,
|
||||
TTL: 64,
|
||||
Id: 1,
|
||||
Protocol: layers.IPProtocolUDP,
|
||||
SrcIP: net.ParseIP(fragTestDst),
|
||||
DstIP: net.ParseIP(fragTestSrc),
|
||||
}
|
||||
udp := &layers.UDP{SrcPort: layers.UDPPort(srcPort), DstPort: layers.UDPPort(dstPort)}
|
||||
require.NoError(tb, udp.SetNetworkLayerForChecksum(ip))
|
||||
|
||||
buf := gopacket.NewSerializeBuffer()
|
||||
opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
|
||||
require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, udp, gopacket.Payload(make([]byte, 16))))
|
||||
return buf.Bytes()
|
||||
}
|
||||
|
||||
// normalUDPPacket builds a complete, non-fragmented UDP packet for baseline
|
||||
// comparisons against the fragment paths.
|
||||
func normalUDPPacket(tb testing.TB, dstPort uint16, payloadLen int) []byte {
|
||||
tb.Helper()
|
||||
|
||||
ip := &layers.IPv4{
|
||||
Version: 4,
|
||||
TTL: 64,
|
||||
Id: 1,
|
||||
Protocol: layers.IPProtocolUDP,
|
||||
SrcIP: net.ParseIP(fragTestSrc),
|
||||
DstIP: net.ParseIP(fragTestDst),
|
||||
}
|
||||
udp := &layers.UDP{SrcPort: 40000, DstPort: layers.UDPPort(dstPort)}
|
||||
require.NoError(tb, udp.SetNetworkLayerForChecksum(ip))
|
||||
|
||||
buf := gopacket.NewSerializeBuffer()
|
||||
opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
|
||||
require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, udp, gopacket.Payload(make([]byte, payloadLen))))
|
||||
return buf.Bytes()
|
||||
}
|
||||
|
||||
func allowUDP(tb testing.TB, m *Manager, dstPort uint16) {
|
||||
tb.Helper()
|
||||
_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolUDP, nil,
|
||||
&fw.Port{Values: []uint16{dstPort}}, fw.ActionAccept, "")
|
||||
require.NoError(tb, err)
|
||||
}
|
||||
|
||||
// TestFragment_TrailingWithoutFirstDropped is the core bypass repro: a trailing
|
||||
// fragment with no allowed first fragment on record must be dropped. Before the
|
||||
// fix, filterInbound returned false (allow) for any fragment.
|
||||
func TestFragment_TrailingWithoutFirstDropped(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
|
||||
frag := trailingFragment(t, 0x1234, 185, false, 40)
|
||||
require.True(t, m.filterInbound(frag, len(frag)),
|
||||
"trailing fragment without an allowed first fragment must be dropped")
|
||||
}
|
||||
|
||||
// TestFragment_AllowedFirstPassesTrailing verifies that once a first fragment
|
||||
// passes the ACL, its trailing fragments inherit the allow verdict.
|
||||
func TestFragment_AllowedFirstPassesTrailing(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
allowUDP(t, m, 8080)
|
||||
|
||||
// First fragment: UDP header (8) + 32 payload = 40 octets -> headerEnd = 5.
|
||||
first := firstFragmentUDP(t, 0x2222, 8080, 32)
|
||||
require.False(t, m.filterInbound(first, len(first)),
|
||||
"allowed first fragment should pass and be recorded")
|
||||
|
||||
trailing := trailingFragment(t, 0x2222, 5, false, 24)
|
||||
require.False(t, m.filterInbound(trailing, len(trailing)),
|
||||
"trailing fragment of an allowed datagram should pass")
|
||||
}
|
||||
|
||||
// TestFragment_DeniedFirstDropsTrailing verifies that a first fragment blocked
|
||||
// by the ACL leaves no verdict, so its trailing fragments are dropped.
|
||||
func TestFragment_DeniedFirstDropsTrailing(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
// No accept rule: local traffic defaults to deny.
|
||||
|
||||
first := firstFragmentUDP(t, 0x3333, 9999, 32)
|
||||
require.True(t, m.filterInbound(first, len(first)),
|
||||
"first fragment to a blocked port should be dropped by the ACL")
|
||||
|
||||
trailing := trailingFragment(t, 0x3333, 5, false, 24)
|
||||
require.True(t, m.filterInbound(trailing, len(trailing)),
|
||||
"trailing fragment of a denied datagram must be dropped")
|
||||
}
|
||||
|
||||
// TestFragment_OverlappingHeaderDropped covers the RFC 1858 §4 / RFC 3128
|
||||
// overlapping-fragment rewrite: a trailing fragment starting inside the range
|
||||
// the ACL already inspected is dropped and poisons the datagram. TCP is used so
|
||||
// the overlap lands on real header bytes (the flags at byte 13).
|
||||
func TestFragment_OverlappingHeaderDropped(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolTCP, nil,
|
||||
&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
|
||||
require.NoError(t, err)
|
||||
|
||||
// First fragment: TCP header (20) + 12 data = 32 bytes -> headerEnd = 4 octets.
|
||||
first := firstFragmentTCP(t, 0x4444, 8080)
|
||||
require.False(t, m.filterInbound(first, len(first)))
|
||||
|
||||
// Overlapping fragment at offset 1 (byte 8) falls inside the inspected TCP
|
||||
// header, so it could rewrite the flags or port on reassembly.
|
||||
overlap := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x4444, 1, true, 32)
|
||||
require.True(t, m.filterInbound(overlap, len(overlap)),
|
||||
"fragment overlapping the inspected header must be dropped")
|
||||
|
||||
// The datagram is now poisoned: a later, non-overlapping fragment is also
|
||||
// dropped because the verdict was removed.
|
||||
later := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x4444, 4, false, 24)
|
||||
require.True(t, m.filterInbound(later, len(later)),
|
||||
"fragments after an overlap must be dropped (datagram poisoned)")
|
||||
}
|
||||
|
||||
// TestFragment_OffsetZeroOverlapPoisons covers the RFC 3128 offset-zero rewrite:
|
||||
// an allowed first fragment followed by a denied offset-zero fragment for the
|
||||
// same datagram must not leave the earlier allow verdict in place.
|
||||
func TestFragment_OffsetZeroOverlapPoisons(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
allowUDP(t, m, 8080)
|
||||
|
||||
allowed := firstFragmentUDP(t, 0x5A5A, 8080, 32)
|
||||
require.False(t, m.filterInbound(allowed, len(allowed)),
|
||||
"allowed first fragment should pass and be recorded")
|
||||
|
||||
// A second offset-zero fragment to a denied port supersedes the datagram's
|
||||
// verdict; it is dropped and must not leave the allow in place.
|
||||
denied := firstFragmentUDP(t, 0x5A5A, 9999, 32)
|
||||
require.True(t, m.filterInbound(denied, len(denied)),
|
||||
"denied offset-zero fragment must be dropped")
|
||||
|
||||
trailing := trailingFragment(t, 0x5A5A, 5, false, 24)
|
||||
require.True(t, m.filterInbound(trailing, len(trailing)),
|
||||
"trailing fragment must be denied after the datagram was poisoned")
|
||||
}
|
||||
|
||||
// TestFragment_TinyFirstDropped covers the tiny-fragment attack: a first
|
||||
// fragment too small to contain the full transport header can't be
|
||||
// ACL-evaluated and must be dropped.
|
||||
func TestFragment_TinyFirstDropped(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
allowUDP(t, m, 8080)
|
||||
|
||||
// IPv4 header + 4 raw bytes, MF set, offset 0: too small for the 8-byte UDP
|
||||
// header, so it decodes to L3 only.
|
||||
tiny := trailingFragment(t, 0x5555, 0, true, 4)
|
||||
require.True(t, m.filterInbound(tiny, len(tiny)),
|
||||
"tiny first fragment without a full L4 header must be dropped")
|
||||
}
|
||||
|
||||
// TestFragment_TCPFirstFragment verifies the TCP arm of the transport decode: a
|
||||
// first fragment carrying the full 20-byte TCP header is ACL-evaluated and its
|
||||
// trailing fragments inherit the verdict.
|
||||
func TestFragment_TCPFirstFragment(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolTCP, nil,
|
||||
&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
|
||||
require.NoError(t, err)
|
||||
|
||||
// TCP header (20) + 12 data = 32 bytes -> headerEnd = 4 octets.
|
||||
first := firstFragmentTCP(t, 0x6666, 8080)
|
||||
require.False(t, m.filterInbound(first, len(first)),
|
||||
"allowed TCP first fragment should pass and be recorded")
|
||||
|
||||
trailing := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x6666, 4, false, 24)
|
||||
require.False(t, m.filterInbound(trailing, len(trailing)),
|
||||
"trailing fragment of an allowed TCP datagram should pass")
|
||||
}
|
||||
|
||||
// TestFragment_TCPTinyFirstDropped verifies the TCP minimum header length: 12
|
||||
// bytes would satisfy a UDP header but falls short of the 20-byte TCP header.
|
||||
func TestFragment_TCPTinyFirstDropped(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolTCP, nil,
|
||||
&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
|
||||
require.NoError(t, err)
|
||||
|
||||
tiny := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x7777, 0, true, 12)
|
||||
require.True(t, m.filterInbound(tiny, len(tiny)),
|
||||
"first fragment shorter than the TCP header must be dropped")
|
||||
}
|
||||
|
||||
// TestFragment_ConntrackAllowsFirstFragment verifies the conntrack branch: reply
|
||||
// fragments of an outbound-established UDP flow pass without any inbound rule.
|
||||
func TestFragment_ConntrackAllowsFirstFragment(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
|
||||
out := outboundUDPPacket(t, 12345, 40000)
|
||||
require.False(t, m.filterOutbound(out, len(out)))
|
||||
|
||||
first := firstFragmentUDP(t, 0x8888, 12345, 32)
|
||||
require.False(t, m.filterInbound(first, len(first)),
|
||||
"reply first fragment should pass via conntrack")
|
||||
|
||||
trailing := trailingFragment(t, 0x8888, 5, false, 24)
|
||||
require.False(t, m.filterInbound(trailing, len(trailing)),
|
||||
"trailing fragment of a tracked flow should pass")
|
||||
}
|
||||
|
||||
// TestFragment_RoutingDisabledDropsFragment verifies routed first fragments are
|
||||
// dropped when routing is disabled.
|
||||
func TestFragment_RoutingDisabledDropsFragment(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
m.routingEnabled.Store(false)
|
||||
|
||||
first := firstFragmentUDPTo(t, "198.51.100.10", 0x9999, 8080, 32)
|
||||
require.True(t, m.filterInbound(first, len(first)),
|
||||
"routed first fragment must be dropped when routing is disabled")
|
||||
}
|
||||
|
||||
// TestFragment_RouteACL verifies the route-ACL branch: fragments to a non-local
|
||||
// destination follow the route rules, allowed datagrams pass their trailing
|
||||
// fragments and denied ones don't.
|
||||
func TestFragment_RouteACL(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
m.routingEnabled.Store(true)
|
||||
m.nativeRouter.Store(false)
|
||||
|
||||
_, err := m.AddRouteFiltering(
|
||||
[]byte("rt-1"),
|
||||
[]netip.Prefix{netip.MustParsePrefix("100.10.0.0/16")},
|
||||
fw.Network{Prefix: netip.MustParsePrefix("198.51.100.0/24")},
|
||||
fw.ProtocolUDP,
|
||||
nil,
|
||||
&fw.Port{Values: []uint16{8080}},
|
||||
fw.ActionAccept,
|
||||
)
|
||||
require.NoError(t, err)
|
||||
|
||||
first := firstFragmentUDPTo(t, "198.51.100.10", 0xAAAA, 8080, 32)
|
||||
require.False(t, m.filterInbound(first, len(first)),
|
||||
"route-ACL-allowed first fragment should pass")
|
||||
trailing := trailingFragmentTo(t, "198.51.100.10", layers.IPProtocolUDP, 0xAAAA, 5, false, 24)
|
||||
require.False(t, m.filterInbound(trailing, len(trailing)),
|
||||
"trailing fragment of an allowed routed datagram should pass")
|
||||
|
||||
denied := firstFragmentUDPTo(t, "198.51.100.10", 0xBBBB, 9999, 32)
|
||||
require.True(t, m.filterInbound(denied, len(denied)),
|
||||
"route-ACL-denied first fragment must be dropped")
|
||||
deniedTrailing := trailingFragmentTo(t, "198.51.100.10", layers.IPProtocolUDP, 0xBBBB, 5, false, 24)
|
||||
require.True(t, m.filterInbound(deniedTrailing, len(deniedTrailing)),
|
||||
"trailing fragment of a denied routed datagram must be dropped")
|
||||
}
|
||||
|
||||
// TestFragment_ExpiredVerdictDropsTrailing verifies a verdict older than the
|
||||
// tracker timeout no longer admits trailing fragments.
|
||||
func TestFragment_ExpiredVerdictDropsTrailing(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
allowUDP(t, m, 8080)
|
||||
|
||||
first := firstFragmentUDP(t, 0xCCCC, 8080, 32)
|
||||
require.False(t, m.filterInbound(first, len(first)))
|
||||
|
||||
m.fragments.mutex.Lock()
|
||||
for key, entry := range m.fragments.entries {
|
||||
entry.recordedAt = time.Now().Add(-defaultFragmentTimeout - time.Second)
|
||||
m.fragments.entries[key] = entry
|
||||
}
|
||||
m.fragments.mutex.Unlock()
|
||||
|
||||
trailing := trailingFragment(t, 0xCCCC, 5, false, 24)
|
||||
require.True(t, m.filterInbound(trailing, len(trailing)),
|
||||
"trailing fragment after verdict expiry must be dropped")
|
||||
}
|
||||
|
||||
// TestFragment_CapacityFailsClosed verifies the table cap: at capacity, new
|
||||
// datagram verdicts are not recorded (their trailing fragments are dropped)
|
||||
// while already-recorded datagrams keep working.
|
||||
func TestFragment_CapacityFailsClosed(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
allowUDP(t, m, 8080)
|
||||
|
||||
m.fragments.mutex.Lock()
|
||||
m.fragments.maxEntries = 1
|
||||
m.fragments.mutex.Unlock()
|
||||
|
||||
first1 := firstFragmentUDP(t, 0x0101, 8080, 32)
|
||||
require.False(t, m.filterInbound(first1, len(first1)))
|
||||
|
||||
first2 := firstFragmentUDP(t, 0x0202, 8080, 32)
|
||||
require.False(t, m.filterInbound(first2, len(first2)),
|
||||
"first fragment itself still passes at capacity")
|
||||
|
||||
trailing2 := trailingFragment(t, 0x0202, 5, false, 24)
|
||||
require.True(t, m.filterInbound(trailing2, len(trailing2)),
|
||||
"trailing fragment of an unrecorded datagram must be dropped at capacity")
|
||||
|
||||
trailing1 := trailingFragment(t, 0x0101, 5, false, 24)
|
||||
require.False(t, m.filterInbound(trailing1, len(trailing1)),
|
||||
"already-recorded datagram should keep passing at capacity")
|
||||
}
|
||||
|
||||
// v6FragmentHeader builds the 8-byte IPv6 fragment extension header for the
|
||||
// given inner protocol, offset (8-byte units), More Fragments bit and id.
|
||||
func v6FragmentHeader(proto layers.IPProtocol, offsetOctets uint16, moreFragments bool, id uint32) []byte {
|
||||
offsetFlags := offsetOctets << 3
|
||||
if moreFragments {
|
||||
offsetFlags |= 1
|
||||
}
|
||||
hdr := make([]byte, 8)
|
||||
hdr[0] = uint8(proto)
|
||||
binary.BigEndian.PutUint16(hdr[2:4], offsetFlags)
|
||||
binary.BigEndian.PutUint32(hdr[4:8], id)
|
||||
return hdr
|
||||
}
|
||||
|
||||
func v6UDPHeader(dstPort uint16, dataLen int) []byte {
|
||||
hdr := make([]byte, 8)
|
||||
binary.BigEndian.PutUint16(hdr[0:2], 40000)
|
||||
binary.BigEndian.PutUint16(hdr[2:4], dstPort)
|
||||
binary.BigEndian.PutUint16(hdr[4:6], uint16(8+dataLen))
|
||||
return hdr
|
||||
}
|
||||
|
||||
// firstFragmentUDPv6 builds the first fragment of a fragmented IPv6 UDP
|
||||
// datagram: fragment header (offset 0, More Fragments set) + full UDP header +
|
||||
// data.
|
||||
func firstFragmentUDPv6(tb testing.TB, id uint32, dstPort uint16, dataLen int) []byte {
|
||||
tb.Helper()
|
||||
return fragmentUDPv6(tb, id, dstPort, dataLen, true)
|
||||
}
|
||||
|
||||
// fragmentUDPv6 builds an offset-zero IPv6 UDP fragment. With moreFragments
|
||||
// false it is an atomic fragment (a complete datagram, RFC 6946).
|
||||
func fragmentUDPv6(tb testing.TB, id uint32, dstPort uint16, dataLen int, moreFragments bool) []byte {
|
||||
tb.Helper()
|
||||
|
||||
ip := &layers.IPv6{
|
||||
Version: 6,
|
||||
NextHeader: layers.IPProtocolIPv6Fragment,
|
||||
HopLimit: 64,
|
||||
SrcIP: net.ParseIP(fragTestSrcV6),
|
||||
DstIP: net.ParseIP(fragTestDstV6),
|
||||
}
|
||||
payload := append(v6FragmentHeader(layers.IPProtocolUDP, 0, moreFragments, id), v6UDPHeader(dstPort, dataLen)...)
|
||||
payload = append(payload, make([]byte, dataLen)...)
|
||||
|
||||
buf := gopacket.NewSerializeBuffer()
|
||||
require.NoError(tb, gopacket.SerializeLayers(buf, gopacket.SerializeOptions{FixLengths: true}, ip, gopacket.Payload(payload)))
|
||||
return buf.Bytes()
|
||||
}
|
||||
|
||||
// trailingFragmentV6 builds a non-first IPv6 fragment: fragment header at the
|
||||
// given offset carrying raw data and no transport header.
|
||||
func trailingFragmentV6(tb testing.TB, id uint32, offsetOctets uint16, moreFragments bool, dataLen int) []byte {
|
||||
tb.Helper()
|
||||
|
||||
ip := &layers.IPv6{
|
||||
Version: 6,
|
||||
NextHeader: layers.IPProtocolIPv6Fragment,
|
||||
HopLimit: 64,
|
||||
SrcIP: net.ParseIP(fragTestSrcV6),
|
||||
DstIP: net.ParseIP(fragTestDstV6),
|
||||
}
|
||||
payload := append(v6FragmentHeader(layers.IPProtocolUDP, offsetOctets, moreFragments, id), make([]byte, dataLen)...)
|
||||
|
||||
buf := gopacket.NewSerializeBuffer()
|
||||
require.NoError(tb, gopacket.SerializeLayers(buf, gopacket.SerializeOptions{FixLengths: true}, ip, gopacket.Payload(payload)))
|
||||
return buf.Bytes()
|
||||
}
|
||||
|
||||
// TestFragmentV6_TrailingWithoutFirstDropped verifies the IPv6 bypass is closed:
|
||||
// a trailing fragment with no allowed first fragment is dropped.
|
||||
func TestFragmentV6_TrailingWithoutFirstDropped(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
|
||||
frag := trailingFragmentV6(t, 0xAABBCCDD, 100, false, 40)
|
||||
require.True(t, m.filterInbound(frag, len(frag)),
|
||||
"IPv6 trailing fragment without an allowed first fragment must be dropped")
|
||||
}
|
||||
|
||||
// TestFragmentV6_AllowedFirstPassesTrailing verifies IPv6 fragments are
|
||||
// evaluated like IPv4: an allowed first fragment lets its trailing fragments
|
||||
// through.
|
||||
func TestFragmentV6_AllowedFirstPassesTrailing(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrcV6), fw.ProtocolUDP, nil,
|
||||
&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
|
||||
require.NoError(t, err)
|
||||
|
||||
// First fragment: UDP header (8) + 32 data = 40 octets -> headerEnd = 5.
|
||||
first := firstFragmentUDPv6(t, 0xAABBCCDD, 8080, 32)
|
||||
require.False(t, m.filterInbound(first, len(first)),
|
||||
"allowed IPv6 first fragment should pass and be recorded")
|
||||
|
||||
trailing := trailingFragmentV6(t, 0xAABBCCDD, 5, false, 24)
|
||||
require.False(t, m.filterInbound(trailing, len(trailing)),
|
||||
"trailing fragment of an allowed IPv6 datagram should pass")
|
||||
}
|
||||
|
||||
// TestFragmentV6_AtomicNotCached verifies an IPv6 atomic fragment (fragment
|
||||
// header with offset 0 and no More Fragments, a complete datagram per RFC 6946)
|
||||
// is evaluated but not recorded, so a flood of allowed atomic fragments can't
|
||||
// exhaust the verdict table.
|
||||
func TestFragmentV6_AtomicNotCached(t *testing.T) {
|
||||
m := newFragmentTestManager(t)
|
||||
_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrcV6), fw.ProtocolUDP, nil,
|
||||
&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
|
||||
require.NoError(t, err)
|
||||
|
||||
atomic := fragmentUDPv6(t, 0xA70301C, 8080, 16, false)
|
||||
require.False(t, m.filterInbound(atomic, len(atomic)),
|
||||
"allowed IPv6 atomic fragment should pass")
|
||||
|
||||
m.fragments.mutex.Lock()
|
||||
n := len(m.fragments.entries)
|
||||
m.fragments.mutex.Unlock()
|
||||
require.Zero(t, n, "atomic fragment must not create a verdict entry")
|
||||
|
||||
// A genuine fragmented datagram (More Fragments set) is still recorded.
|
||||
first := fragmentUDPv6(t, 0xBEEF, 8080, 32, true)
|
||||
require.False(t, m.filterInbound(first, len(first)))
|
||||
m.fragments.mutex.Lock()
|
||||
n = len(m.fragments.entries)
|
||||
m.fragments.mutex.Unlock()
|
||||
require.Equal(t, 1, n, "genuine first fragment must record a verdict")
|
||||
}
|
||||
@@ -464,8 +464,6 @@ func Test_RemovePeer(t *testing.T) {
|
||||
}
|
||||
|
||||
func Test_ConnectPeers(t *testing.T) {
|
||||
t.Setenv("NB_DISABLE_EBPF_WG_PROXY", "true")
|
||||
|
||||
peer1ifaceName := fmt.Sprintf("utun%d", WgIntNumber+400)
|
||||
peer1wgIP := netip.MustParsePrefix("10.99.99.17/30")
|
||||
peer1Key, _ := wgtypes.GeneratePrivateKey()
|
||||
@@ -507,8 +505,12 @@ func Test_ConnectPeers(t *testing.T) {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
localIP1 := "127.0.0.1"
|
||||
peer1endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP1, peer1wgPort))
|
||||
localIP, err := getLocalIP()
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
peer1endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP, peer1wgPort))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
@@ -544,8 +546,7 @@ func Test_ConnectPeers(t *testing.T) {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
localIP2 := "127.0.0.1"
|
||||
peer2endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP2, peer2wgPort))
|
||||
peer2endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP, peer2wgPort))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
@@ -568,17 +569,17 @@ func Test_ConnectPeers(t *testing.T) {
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
// The peers use userspace WireGuard (stdnet transport). A tight busy-loop
|
||||
// here starves the wireguard-go goroutines that process the handshake, so
|
||||
// poll on a ticker instead and yield the CPU between checks. WireGuard also
|
||||
// only retries a lost handshake initiation every REKEY_TIMEOUT (5s), which
|
||||
// is why the overall wait can occasionally stretch to tens of seconds.
|
||||
// todo: investigate why in some tests execution we need 30s
|
||||
timeout := 30 * time.Second
|
||||
timeoutChannel := time.After(timeout)
|
||||
ticker := time.NewTicker(500 * time.Millisecond)
|
||||
defer ticker.Stop()
|
||||
|
||||
for {
|
||||
select {
|
||||
case <-timeoutChannel:
|
||||
t.Fatalf("waiting for peer handshake timeout after %s", timeout.String())
|
||||
default:
|
||||
}
|
||||
|
||||
peer, gpErr := getPeer(peer1ifaceName, peer2Key.PublicKey().String())
|
||||
if gpErr != nil {
|
||||
t.Fatal(gpErr)
|
||||
@@ -587,12 +588,6 @@ func Test_ConnectPeers(t *testing.T) {
|
||||
t.Log("peers successfully handshake")
|
||||
break
|
||||
}
|
||||
|
||||
select {
|
||||
case <-timeoutChannel:
|
||||
t.Fatalf("waiting for peer handshake timeout after %s", timeout.String())
|
||||
case <-ticker.C:
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
@@ -620,3 +615,28 @@ func getPeer(ifaceName, peerPubKey string) (wgtypes.Peer, error) {
|
||||
}
|
||||
return wgtypes.Peer{}, fmt.Errorf("peer not found")
|
||||
}
|
||||
|
||||
func getLocalIP() (string, error) {
|
||||
// Get all interfaces
|
||||
addrs, err := net.InterfaceAddrs()
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
|
||||
for _, addr := range addrs {
|
||||
ipNet, ok := addr.(*net.IPNet)
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
if ipNet.IP.IsLoopback() {
|
||||
continue
|
||||
}
|
||||
|
||||
if ipNet.IP.To4() == nil {
|
||||
continue
|
||||
}
|
||||
return ipNet.IP.String(), nil
|
||||
}
|
||||
|
||||
return "", fmt.Errorf("no local IP found")
|
||||
}
|
||||
|
||||
@@ -3,31 +3,14 @@
|
||||
package netstack
|
||||
|
||||
import (
|
||||
"net"
|
||||
"fmt"
|
||||
"os"
|
||||
"strconv"
|
||||
|
||||
log "github.com/sirupsen/logrus"
|
||||
)
|
||||
|
||||
const (
|
||||
EnvUseNetstackMode = "NB_USE_NETSTACK_MODE"
|
||||
|
||||
// EnvSocks5ListenerPort overrides the port the SOCKS5 proxy listens on.
|
||||
EnvSocks5ListenerPort = "NB_SOCKS5_LISTENER_PORT"
|
||||
|
||||
// EnvSocks5ListenerAddress overrides the host/IP the SOCKS5 proxy binds to.
|
||||
// The proxy is a bridge for local host applications into the userspace
|
||||
// WireGuard netstack, so it binds to loopback by default. Override this only
|
||||
// when the proxy must be reachable from other hosts (e.g. a container
|
||||
// gateway); doing so exposes an unauthenticated SOCKS5 proxy on that
|
||||
// address.
|
||||
EnvSocks5ListenerAddress = "NB_SOCKS5_LISTENER_ADDRESS"
|
||||
|
||||
// defaultSocks5Host is the loopback address the SOCKS5 proxy binds to unless
|
||||
// overridden via EnvSocks5ListenerAddress.
|
||||
defaultSocks5Host = "127.0.0.1"
|
||||
)
|
||||
const EnvUseNetstackMode = "NB_USE_NETSTACK_MODE"
|
||||
|
||||
// IsEnabled todo: move these function to cmd layer
|
||||
func IsEnabled() bool {
|
||||
@@ -35,40 +18,24 @@ func IsEnabled() bool {
|
||||
}
|
||||
|
||||
func ListenAddr() string {
|
||||
return net.JoinHostPort(listenHost(), strconv.Itoa(listenPort()))
|
||||
}
|
||||
|
||||
// listenHost returns the host/IP the SOCKS5 proxy binds to. It defaults to
|
||||
// loopback and only honors EnvSocks5ListenerAddress when it holds a valid IP.
|
||||
func listenHost() string {
|
||||
addr := os.Getenv(EnvSocks5ListenerAddress)
|
||||
if addr == "" {
|
||||
return defaultSocks5Host
|
||||
}
|
||||
if net.ParseIP(addr) == nil {
|
||||
log.Warnf("invalid socks5 listener address %q, falling back to default: %s", addr, defaultSocks5Host)
|
||||
return defaultSocks5Host
|
||||
}
|
||||
return addr
|
||||
}
|
||||
|
||||
// listenPort returns the port the SOCKS5 proxy binds to, defaulting to
|
||||
// DefaultSocks5Port when EnvSocks5ListenerPort is unset or invalid.
|
||||
func listenPort() int {
|
||||
sPort := os.Getenv(EnvSocks5ListenerPort)
|
||||
sPort := os.Getenv("NB_SOCKS5_LISTENER_PORT")
|
||||
if sPort == "" {
|
||||
return DefaultSocks5Port
|
||||
return listenAddr(DefaultSocks5Port)
|
||||
}
|
||||
|
||||
port, err := strconv.Atoi(sPort)
|
||||
if err != nil {
|
||||
log.Warnf("invalid socks5 listener port, unable to convert it to int, falling back to default: %d", DefaultSocks5Port)
|
||||
return DefaultSocks5Port
|
||||
return listenAddr(DefaultSocks5Port)
|
||||
}
|
||||
if port < 1 || port > 65535 {
|
||||
log.Warnf("invalid socks5 listener port, it should be in the range 1-65535, falling back to default: %d", DefaultSocks5Port)
|
||||
return DefaultSocks5Port
|
||||
return listenAddr(DefaultSocks5Port)
|
||||
}
|
||||
|
||||
return port
|
||||
return listenAddr(port)
|
||||
}
|
||||
|
||||
func listenAddr(port int) string {
|
||||
return fmt.Sprintf("0.0.0.0:%d", port)
|
||||
}
|
||||
|
||||
@@ -1,63 +0,0 @@
|
||||
//go:build !js
|
||||
|
||||
package netstack
|
||||
|
||||
import (
|
||||
"net"
|
||||
"strconv"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestListenAddr_DefaultsToLoopback(t *testing.T) {
|
||||
// No env overrides: must bind loopback, never all interfaces.
|
||||
got := ListenAddr()
|
||||
want := net.JoinHostPort("127.0.0.1", strconv.Itoa(DefaultSocks5Port))
|
||||
if got != want {
|
||||
t.Fatalf("ListenAddr() = %q, want %q", got, want)
|
||||
}
|
||||
}
|
||||
|
||||
func TestListenAddr_AddressOverride(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
env string
|
||||
want string
|
||||
}{
|
||||
{name: "valid override honored", env: "0.0.0.0", want: "0.0.0.0"},
|
||||
{name: "valid specific ip honored", env: "10.0.0.5", want: "10.0.0.5"},
|
||||
{name: "ipv6 loopback bracketed", env: "::1", want: "::1"},
|
||||
{name: "invalid falls back to loopback", env: "not-an-ip", want: "127.0.0.1"},
|
||||
{name: "empty falls back to loopback", env: "", want: "127.0.0.1"},
|
||||
}
|
||||
for _, tc := range tests {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
t.Setenv(EnvSocks5ListenerAddress, tc.env)
|
||||
want := net.JoinHostPort(tc.want, strconv.Itoa(DefaultSocks5Port))
|
||||
if got := ListenAddr(); got != want {
|
||||
t.Fatalf("ListenAddr() = %q, want %q", got, want)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestListenAddr_PortOverride(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
env string
|
||||
want int
|
||||
}{
|
||||
{name: "valid port honored", env: "1081", want: 1081},
|
||||
{name: "non-numeric falls back", env: "abc", want: DefaultSocks5Port},
|
||||
{name: "out of range falls back", env: "70000", want: DefaultSocks5Port},
|
||||
{name: "zero falls back", env: "0", want: DefaultSocks5Port},
|
||||
}
|
||||
for _, tc := range tests {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
t.Setenv(EnvSocks5ListenerPort, tc.env)
|
||||
want := net.JoinHostPort("127.0.0.1", strconv.Itoa(tc.want))
|
||||
if got := ListenAddr(); got != want {
|
||||
t.Fatalf("ListenAddr() = %q, want %q", got, want)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -351,7 +351,6 @@ func (a *Auth) setSystemInfoFlags(info *system.Info) {
|
||||
a.config.BlockLANAccess,
|
||||
a.config.BlockInbound,
|
||||
a.config.DisableIPv6,
|
||||
a.config.SyncMessageVersion,
|
||||
a.config.EnableSSHRoot,
|
||||
a.config.EnableSSHSFTP,
|
||||
a.config.EnableSSHLocalPortForwarding,
|
||||
|
||||
@@ -299,7 +299,7 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn
|
||||
UseIDToken: d.providerConfig.UseIDToken,
|
||||
}
|
||||
|
||||
err = validateTokenAudience(tokenInfo.GetTokenToUse(), d.providerConfig.Audience)
|
||||
err = isValidAccessToken(tokenInfo.GetTokenToUse(), d.providerConfig.Audience)
|
||||
if err != nil {
|
||||
return TokenInfo{}, fmt.Errorf("validate access token failed with error: %v", err)
|
||||
}
|
||||
|
||||
@@ -306,7 +306,7 @@ func (p *PKCEAuthorizationFlow) parseOAuthToken(token *oauth2.Token) (TokenInfo,
|
||||
audience = p.providerConfig.ClientID
|
||||
}
|
||||
|
||||
if err := validateTokenAudience(tokenInfo.GetTokenToUse(), audience); err != nil {
|
||||
if err := isValidAccessToken(tokenInfo.GetTokenToUse(), audience); err != nil {
|
||||
return TokenInfo{}, fmt.Errorf("authentication failed: invalid access token - %w", err)
|
||||
}
|
||||
|
||||
@@ -320,11 +320,6 @@ func (p *PKCEAuthorizationFlow) parseOAuthToken(token *oauth2.Token) (TokenInfo,
|
||||
return tokenInfo, nil
|
||||
}
|
||||
|
||||
// parseEmailFromIDToken extracts the email (or name) claim from an ID token
|
||||
// without verifying its signature. The value is best-effort and used only as a
|
||||
// UX convenience (login hint prefill and display); it never drives an
|
||||
// authorization decision. The authoritative identity is established server-side
|
||||
// from the signature-verified token.
|
||||
func parseEmailFromIDToken(token string) (string, error) {
|
||||
parts := strings.Split(token, ".")
|
||||
if len(parts) < 2 {
|
||||
|
||||
@@ -24,7 +24,11 @@ import (
|
||||
)
|
||||
|
||||
const (
|
||||
maxPastHorizon = 30 * 24 * time.Hour
|
||||
// Skew tolerates a small clock difference between the management
|
||||
// server and this peer before treating a deadline as "in the past".
|
||||
// Slightly above typical NTP drift; tight enough that the UI doesn't
|
||||
// paint a stale expiry as if it were valid.
|
||||
Skew = 30 * time.Second
|
||||
|
||||
// maxDeadlineHorizon caps how far in the future an accepted deadline
|
||||
// can sit. A timestamp beyond this is almost certainly a protocol
|
||||
@@ -53,7 +57,7 @@ var (
|
||||
ErrDeadlineTooFarFuture = errors.New("session deadline too far in the future")
|
||||
|
||||
// ErrDeadlineInPast is returned by Update when the supplied deadline
|
||||
// is more than maxPastHorizon in the past.
|
||||
// is more than Skew in the past.
|
||||
ErrDeadlineInPast = errors.New("session deadline in the past")
|
||||
)
|
||||
|
||||
@@ -62,14 +66,15 @@ var (
|
||||
// for deadline change/clear, PublishEvent for the two warnings); tests pass
|
||||
// a fake recorder so the same surface is observable without an engine.
|
||||
//
|
||||
// While the watcher runs, it owns the deadline propagated to the recorder:
|
||||
// every set, clear and sanity-check rejection routes the value through
|
||||
// SetSessionExpiresAt, so the SubscribeStatus snapshot the UI reads can
|
||||
// never drift from the watcher's timer state. (SetSessionExpiresAt fans
|
||||
// out its own state-change notification, so no separate notify is needed.)
|
||||
// The recorder is server-scoped and outlives this engine-scoped watcher;
|
||||
// Close deliberately leaves the recorder value in place so transient engine
|
||||
// restarts don't blank it — the client run loop clears it on real teardown.
|
||||
// The watcher is the single owner of the deadline propagated to the
|
||||
// recorder: every set, clear, sanity-check rejection and Close routes the
|
||||
// value through SetSessionExpiresAt, so the SubscribeStatus snapshot the UI
|
||||
// reads can never drift from the watcher's timer state. (SetSessionExpiresAt
|
||||
// fans out its own state-change notification, so no separate notify is
|
||||
// needed.) The recorder is server-scoped and outlives this engine-scoped
|
||||
// watcher — without the Close-time clear a teardown (Down, or the Down+Up of
|
||||
// a profile switch) would leave the next session showing the previous one's
|
||||
// stale "expires in" value.
|
||||
//
|
||||
// PublishEvent's signature mirrors peer.Status.PublishEvent: the watcher
|
||||
// composes the metadata internally so the wire format (MetaSession*) is
|
||||
@@ -130,13 +135,10 @@ func NewWithLeads(lead, final time.Duration, recorder StatusRecorder) *Watcher {
|
||||
// was disabled).
|
||||
//
|
||||
// Same-value updates are no-ops. A different non-zero value cancels any
|
||||
// pending timer, resets the "already fired" guards, and — when the
|
||||
// deadline lies in the future — arms fresh warning timers. A deadline
|
||||
// already in the past (within maxPastHorizon) is recorded as-is with no
|
||||
// timers: the session has expired and consumers render it that way.
|
||||
// pending timer, resets the "already fired" guard, and arms a new one.
|
||||
//
|
||||
// Returns one of the sentinel Err* values when the deadline fails the
|
||||
// sanity checks (pre-epoch, far future, or past beyond maxPastHorizon).
|
||||
// sanity checks (pre-epoch, far future, or in the past beyond Skew).
|
||||
// In every error case the watcher first clears its state so it stays
|
||||
// consistent with what the caller will push into its other sinks (e.g.
|
||||
// applySessionDeadline forces a zero deadline into the status recorder
|
||||
@@ -161,7 +163,7 @@ func (w *Watcher) Update(deadline time.Time) error {
|
||||
case deadline.After(now.Add(maxDeadlineHorizon)):
|
||||
w.clearLocked()
|
||||
return fmt.Errorf("%w: %v", ErrDeadlineTooFarFuture, deadline)
|
||||
case deadline.Before(now.Add(-maxPastHorizon)):
|
||||
case deadline.Before(now.Add(-Skew)):
|
||||
w.clearLocked()
|
||||
return fmt.Errorf("%w: %v (now=%v)", ErrDeadlineInPast, deadline, now)
|
||||
}
|
||||
@@ -181,9 +183,7 @@ func (w *Watcher) Update(deadline time.Time) error {
|
||||
w.finalFiredAt = time.Time{}
|
||||
w.dismissedAt = time.Time{}
|
||||
|
||||
if deadline.After(now) {
|
||||
w.armTimerLocked(deadline)
|
||||
}
|
||||
w.armTimerLocked(deadline)
|
||||
recorder := w.recorder
|
||||
w.mu.Unlock()
|
||||
if recorder != nil {
|
||||
@@ -227,25 +227,30 @@ func (w *Watcher) Dismiss() {
|
||||
log.Infof("auth session final-warning dismissed for deadline %s", w.current.Format(time.RFC3339))
|
||||
}
|
||||
|
||||
// Close stops any pending timer. Update calls after Close are ignored.
|
||||
// The recorder keeps its deadline: the watcher is engine-scoped and closes
|
||||
// on every engine restart (network change, sleep/wake, stream errors)
|
||||
// while the SSO deadline stays valid across those, so clearing here would
|
||||
// blank the UI's "expires in" row on every transient reconnect. The
|
||||
// client run loop clears the server-scoped recorder when it exits for
|
||||
// real (Down, profile switch, permanent login failure).
|
||||
// Close stops any pending timer and drops the deadline on the status
|
||||
// recorder. Update calls after Close are ignored. Clearing the recorder
|
||||
// here is what keeps a teardown (Down, or the Down+Up of a profile switch)
|
||||
// from leaving the next session showing this one's stale "expires in"
|
||||
// value — the recorder is server-scoped and outlives this engine-scoped
|
||||
// watcher, so nothing else drops the anchor on teardown.
|
||||
func (w *Watcher) Close() {
|
||||
w.mu.Lock()
|
||||
defer w.mu.Unlock()
|
||||
if w.closed {
|
||||
w.mu.Unlock()
|
||||
return
|
||||
}
|
||||
w.closed = true
|
||||
w.stopTimerLocked()
|
||||
hadDeadline := !w.current.IsZero()
|
||||
w.current = time.Time{}
|
||||
w.firedAt = time.Time{}
|
||||
w.finalFiredAt = time.Time{}
|
||||
w.dismissedAt = time.Time{}
|
||||
recorder := w.recorder
|
||||
w.mu.Unlock()
|
||||
if recorder != nil && hadDeadline {
|
||||
recorder.SetSessionExpiresAt(time.Time{})
|
||||
}
|
||||
}
|
||||
|
||||
// clearLocked drops the tracked deadline and notifies the recorder so
|
||||
|
||||
@@ -224,13 +224,11 @@ func TestNewDeadlineCancelsPriorTimer(t *testing.T) {
|
||||
|
||||
func TestRefreshAfterFireArmsNewWarning(t *testing.T) {
|
||||
r := &fakeRecorder{}
|
||||
lead := 150 * time.Millisecond
|
||||
lead := 30 * time.Millisecond
|
||||
w := newWatcher(lead, r)
|
||||
defer w.Close()
|
||||
|
||||
// Warning fires ~20ms in; the deadline itself stays 150ms away so the
|
||||
// replacement below lands well before it.
|
||||
first := time.Now().Add(170 * time.Millisecond)
|
||||
first := time.Now().Add(50 * time.Millisecond)
|
||||
_ = w.Update(first)
|
||||
|
||||
// Wait for stateChange + warning of the first cycle.
|
||||
@@ -308,29 +306,7 @@ func TestUpdateRejectsTooFarFuture(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestUpdateRecentPastRecordedAsExpired(t *testing.T) {
|
||||
r := &fakeRecorder{}
|
||||
w := newWatcher(50*time.Millisecond, r)
|
||||
defer w.Close()
|
||||
|
||||
d := time.Now().Add(-1 * time.Hour)
|
||||
if err := w.Update(d); err != nil {
|
||||
t.Fatalf("recent-past Update should succeed, got %v", err)
|
||||
}
|
||||
if !w.Deadline().Equal(d) {
|
||||
t.Fatalf("expected deadline to be recorded, got %v want %v", w.Deadline(), d)
|
||||
}
|
||||
if got := r.deadline(); !got.Equal(d) {
|
||||
t.Fatalf("recorder deadline = %v, want %v", got, d)
|
||||
}
|
||||
|
||||
time.Sleep(80 * time.Millisecond)
|
||||
if n := countWhere(r.snapshot(), func(e event) bool { return e.kind == publish }); n != 0 {
|
||||
t.Fatalf("no warning events may fire for an already-past deadline, got %+v", r.snapshot())
|
||||
}
|
||||
}
|
||||
|
||||
func TestUpdateAncientPastRejected(t *testing.T) {
|
||||
func TestUpdateInPastClearsDeadline(t *testing.T) {
|
||||
r := &fakeRecorder{}
|
||||
w := newWatcher(50*time.Millisecond, r)
|
||||
defer w.Close()
|
||||
@@ -342,12 +318,12 @@ func TestUpdateAncientPastRejected(t *testing.T) {
|
||||
// Drain the stateChange from the seed.
|
||||
waitForEvents(t, r, 1)
|
||||
|
||||
err := w.Update(time.Now().Add(-31 * 24 * time.Hour))
|
||||
err := w.Update(time.Now().Add(-1 * time.Hour))
|
||||
if !errors.Is(err, ErrDeadlineInPast) {
|
||||
t.Fatalf("want ErrDeadlineInPast, got %v", err)
|
||||
}
|
||||
if !w.Deadline().IsZero() {
|
||||
t.Fatalf("rejected ancient-past update must clear the deadline, got %v", w.Deadline())
|
||||
t.Fatalf("in-past update must clear the deadline, got %v", w.Deadline())
|
||||
}
|
||||
events := waitForEvents(t, r, 2)
|
||||
if events[1].kind != stateChange {
|
||||
@@ -355,25 +331,39 @@ func TestUpdateAncientPastRejected(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestUpdateWithinSkewAccepted(t *testing.T) {
|
||||
r := &fakeRecorder{}
|
||||
w := newWatcher(50*time.Millisecond, r)
|
||||
defer w.Close()
|
||||
|
||||
// 5 seconds in the past is within the 30s Skew tolerance — accept it.
|
||||
d := time.Now().Add(-5 * time.Second)
|
||||
if err := w.Update(d); err != nil {
|
||||
t.Fatalf("within-skew Update should succeed, got %v", err)
|
||||
}
|
||||
if !w.Deadline().Equal(d) {
|
||||
t.Fatalf("expected deadline to be applied, got %v want %v", w.Deadline(), d)
|
||||
}
|
||||
}
|
||||
|
||||
func TestCloseSilencesUpdates(t *testing.T) {
|
||||
r := &fakeRecorder{}
|
||||
w := newWatcher(50*time.Millisecond, r)
|
||||
w.Close()
|
||||
|
||||
if err := w.Update(time.Now().Add(time.Hour)); err != nil {
|
||||
t.Fatalf("Update after Close: want nil, got %v", err)
|
||||
}
|
||||
_ = w.Update(time.Now().Add(time.Hour))
|
||||
|
||||
time.Sleep(20 * time.Millisecond)
|
||||
if got := r.snapshot(); len(got) != 0 {
|
||||
t.Fatalf("expected no events after Close, got %+v", got)
|
||||
}
|
||||
}
|
||||
|
||||
// TestCloseKeepsRecorderDeadline pins the reconnect-flap fix: the watcher
|
||||
// closes on every engine restart (network change, sleep/wake) while the
|
||||
// SSO deadline stays valid across those, so Close must leave the
|
||||
// server-scoped recorder's value in place. The client run loop clears the
|
||||
// recorder when it exits for real.
|
||||
func TestCloseKeepsRecorderDeadline(t *testing.T) {
|
||||
// TestCloseClearsRecorderDeadline pins the profile-switch fix: a watcher
|
||||
// holding a live deadline must zero the recorder on Close so the next
|
||||
// engine's watcher (and the UI reading the shared server-scoped recorder)
|
||||
// doesn't start out showing the previous session's stale "expires in".
|
||||
func TestCloseClearsRecorderDeadline(t *testing.T) {
|
||||
r := &fakeRecorder{}
|
||||
w := newWatcher(time.Hour, r)
|
||||
|
||||
@@ -387,8 +377,8 @@ func TestCloseKeepsRecorderDeadline(t *testing.T) {
|
||||
|
||||
w.Close()
|
||||
|
||||
if got := r.deadline(); !got.Equal(d) {
|
||||
t.Fatalf("recorder deadline after Close = %v, want %v", got, d)
|
||||
if got := r.deadline(); !got.IsZero() {
|
||||
t.Fatalf("recorder deadline after Close = %v, want zero", got)
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -20,26 +20,14 @@ func randomBytesInHex(count int) (string, error) {
|
||||
return hex.EncodeToString(buf), nil
|
||||
}
|
||||
|
||||
// validateTokenAudience checks that the token is a well-formed JWT whose
|
||||
// audience claim matches the expected audience.
|
||||
//
|
||||
// It does NOT verify the token's cryptographic signature and therefore must not
|
||||
// be treated as an authenticity check. The token is obtained by the client
|
||||
// directly from the IdP token endpoint over TLS, and its signature is verified
|
||||
// server-side by the management server against the IdP's JWKS
|
||||
// (see shared/auth/jwt/validator.go). This function is only a client-side
|
||||
// sanity check that the returned token targets the expected audience.
|
||||
func validateTokenAudience(token string, audience string) error {
|
||||
// isValidAccessToken is a simple validation of the access token
|
||||
func isValidAccessToken(token string, audience string) error {
|
||||
if token == "" {
|
||||
return fmt.Errorf("token received is empty")
|
||||
}
|
||||
|
||||
parts := strings.Split(token, ".")
|
||||
if len(parts) != 3 {
|
||||
return fmt.Errorf("token is not a well-formed JWT")
|
||||
}
|
||||
|
||||
claimsString, err := base64.RawURLEncoding.DecodeString(parts[1])
|
||||
encodedClaims := strings.Split(token, ".")[1]
|
||||
claimsString, err := base64.RawURLEncoding.DecodeString(encodedClaims)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
@@ -1,108 +0,0 @@
|
||||
package auth
|
||||
|
||||
import (
|
||||
"encoding/base64"
|
||||
"encoding/json"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// makeJWT builds an unsigned JWT-shaped string (header.payload.signature) with
|
||||
// the given claims payload. The signature part is arbitrary because
|
||||
// validateTokenAudience intentionally does not verify it.
|
||||
func makeJWT(t *testing.T, claims map[string]interface{}) string {
|
||||
t.Helper()
|
||||
header := base64.RawURLEncoding.EncodeToString([]byte(`{"alg":"RS256","typ":"JWT"}`))
|
||||
payloadBytes, err := json.Marshal(claims)
|
||||
if err != nil {
|
||||
t.Fatalf("marshal claims: %v", err)
|
||||
}
|
||||
payload := base64.RawURLEncoding.EncodeToString(payloadBytes)
|
||||
return header + "." + payload + ".unverified-signature"
|
||||
}
|
||||
|
||||
func TestValidateTokenAudience(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
token string
|
||||
audience string
|
||||
wantErr bool
|
||||
}{
|
||||
{
|
||||
name: "empty token",
|
||||
token: "",
|
||||
audience: "netbird",
|
||||
wantErr: true,
|
||||
},
|
||||
{
|
||||
name: "not a JWT - no dots",
|
||||
token: "notajwt",
|
||||
audience: "netbird",
|
||||
wantErr: true,
|
||||
},
|
||||
{
|
||||
name: "not a JWT - two parts only",
|
||||
token: "header.payload",
|
||||
audience: "netbird",
|
||||
wantErr: true,
|
||||
},
|
||||
{
|
||||
name: "matching string audience",
|
||||
token: makeJWT(t, map[string]interface{}{"aud": "netbird"}),
|
||||
audience: "netbird",
|
||||
wantErr: false,
|
||||
},
|
||||
{
|
||||
name: "mismatching string audience",
|
||||
token: makeJWT(t, map[string]interface{}{"aud": "other"}),
|
||||
audience: "netbird",
|
||||
wantErr: true,
|
||||
},
|
||||
{
|
||||
name: "matching audience in array",
|
||||
token: makeJWT(t, map[string]interface{}{"aud": []interface{}{"other", "netbird"}}),
|
||||
audience: "netbird",
|
||||
wantErr: false,
|
||||
},
|
||||
{
|
||||
name: "mismatching audience array",
|
||||
token: makeJWT(t, map[string]interface{}{"aud": []interface{}{"a", "b"}}),
|
||||
audience: "netbird",
|
||||
wantErr: true,
|
||||
},
|
||||
{
|
||||
name: "missing audience claim",
|
||||
token: makeJWT(t, map[string]interface{}{"sub": "user"}),
|
||||
audience: "netbird",
|
||||
wantErr: true,
|
||||
},
|
||||
{
|
||||
name: "invalid base64 payload",
|
||||
token: "header.!!!not-base64!!!.sig",
|
||||
audience: "netbird",
|
||||
wantErr: true,
|
||||
},
|
||||
}
|
||||
|
||||
for _, tc := range tests {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
err := validateTokenAudience(tc.token, tc.audience)
|
||||
if tc.wantErr && err == nil {
|
||||
t.Fatalf("expected error, got nil")
|
||||
}
|
||||
if !tc.wantErr && err != nil {
|
||||
t.Fatalf("expected no error, got %v", err)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestValidateTokenAudienceNoPanic guards the regression where a non-empty
|
||||
// token without the JWT dot structure caused an index-out-of-range panic.
|
||||
func TestValidateTokenAudienceNoPanic(t *testing.T) {
|
||||
inputs := []string{"a", ".", "a.", "aaaa", "no-dots-here"}
|
||||
for _, in := range inputs {
|
||||
if err := validateTokenAudience(in, "netbird"); err == nil {
|
||||
t.Fatalf("expected error for malformed token %q, got nil", in)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -34,8 +34,6 @@ const (
|
||||
// - Handling connection establishment based on peer signaling
|
||||
//
|
||||
// The implementation is not thread-safe; it is protected by engine.syncMsgMux.
|
||||
// The only exception is ActivatePeer, which is safe for concurrent use so the
|
||||
// DNS warm-up path can call it without contending on the engine mutex.
|
||||
type ConnMgr struct {
|
||||
peerStore *peerstore.Store
|
||||
statusRecorder *peer.Status
|
||||
@@ -44,26 +42,12 @@ type ConnMgr struct {
|
||||
rosenpassEnabled bool
|
||||
|
||||
lazyConnMgr *manager.Manager
|
||||
// lazyConnMgrMu guards the lazyConnMgr pointer for readers outside the
|
||||
// engine loop (ActivatePeer). Writers hold it in addition to
|
||||
// engine.syncMsgMux; all other reads stay under engine.syncMsgMux only.
|
||||
lazyConnMgrMu sync.RWMutex
|
||||
|
||||
// reconcileRoutedIPs re-applies a peer's routed allowed IPs after its lazy wake endpoint is
|
||||
// (re)armed (Mode A at arm time). Injected by the engine; nil disables the reconcile.
|
||||
reconcileRoutedIPs func(peerKey string) error
|
||||
|
||||
wg sync.WaitGroup
|
||||
lazyCtx context.Context
|
||||
lazyCtxCancel context.CancelFunc
|
||||
}
|
||||
|
||||
// SetRoutedIPsReconciler injects the callback used to re-apply a peer's routed allowed IPs when
|
||||
// its lazy wake endpoint is (re)armed. Must be called before the lazy manager starts.
|
||||
func (e *ConnMgr) SetRoutedIPsReconciler(fn func(peerKey string) error) {
|
||||
e.reconcileRoutedIPs = fn
|
||||
}
|
||||
|
||||
func NewConnMgr(engineConfig *EngineConfig, statusRecorder *peer.Status, peerStore *peerstore.Store, iface lazyconn.WGIface) *ConnMgr {
|
||||
e := &ConnMgr{
|
||||
peerStore: peerStore,
|
||||
@@ -254,20 +238,12 @@ func (e *ConnMgr) RemovePeerConn(peerKey string) {
|
||||
conn.Log.Infof("removed peer from lazy conn manager")
|
||||
}
|
||||
|
||||
// ActivatePeer wakes an idle lazy connection. Unlike the rest of ConnMgr it is
|
||||
// safe for concurrent use: the lazy manager pointer is read under lazyConnMgrMu
|
||||
// and the manager itself is internally synchronized, so callers outside the
|
||||
// engine loop (DNS warm-up) do not need engine.syncMsgMux.
|
||||
func (e *ConnMgr) ActivatePeer(ctx context.Context, conn *peer.Conn) {
|
||||
e.lazyConnMgrMu.RLock()
|
||||
lazyConnMgr := e.lazyConnMgr
|
||||
started := lazyConnMgr != nil && e.lazyCtxCancel != nil
|
||||
e.lazyConnMgrMu.RUnlock()
|
||||
if !started {
|
||||
if !e.isStartedWithLazyMgr() {
|
||||
return
|
||||
}
|
||||
|
||||
if found := lazyConnMgr.ActivatePeer(conn.GetKey()); found {
|
||||
if found := e.lazyConnMgr.ActivatePeer(conn.GetKey()); found {
|
||||
if err := conn.Open(ctx); err != nil {
|
||||
conn.Log.Errorf("failed to open connection: %v", err)
|
||||
}
|
||||
@@ -292,22 +268,16 @@ func (e *ConnMgr) Close() {
|
||||
|
||||
e.lazyCtxCancel()
|
||||
e.wg.Wait()
|
||||
|
||||
e.lazyConnMgrMu.Lock()
|
||||
e.lazyConnMgr = nil
|
||||
e.lazyConnMgrMu.Unlock()
|
||||
}
|
||||
|
||||
func (e *ConnMgr) initLazyManager(engineCtx context.Context) {
|
||||
cfg := manager.Config{
|
||||
InactivityThreshold: inactivityThresholdEnv(),
|
||||
ReconcileAllowedIPs: e.reconcileRoutedIPs,
|
||||
}
|
||||
|
||||
e.lazyConnMgrMu.Lock()
|
||||
e.lazyConnMgr = manager.NewManager(cfg, engineCtx, e.peerStore, e.iface)
|
||||
|
||||
e.lazyCtx, e.lazyCtxCancel = context.WithCancel(engineCtx)
|
||||
e.lazyConnMgrMu.Unlock()
|
||||
|
||||
e.wg.Add(1)
|
||||
go func() {
|
||||
@@ -346,10 +316,7 @@ func (e *ConnMgr) closeManager(ctx context.Context) {
|
||||
|
||||
e.lazyCtxCancel()
|
||||
e.wg.Wait()
|
||||
|
||||
e.lazyConnMgrMu.Lock()
|
||||
e.lazyConnMgr = nil
|
||||
e.lazyConnMgrMu.Unlock()
|
||||
|
||||
for _, peerID := range e.peerStore.PeersPubKey() {
|
||||
e.peerStore.PeerConnOpen(ctx, peerID)
|
||||
@@ -385,20 +352,11 @@ func inactivityThresholdEnv() *time.Duration {
|
||||
return nil
|
||||
}
|
||||
|
||||
// Documented format: a Go duration such as "30m" or "1h".
|
||||
if d, err := time.ParseDuration(envValue); err == nil {
|
||||
if d <= 0 {
|
||||
return nil
|
||||
}
|
||||
return &d
|
||||
parsedMinutes, err := strconv.Atoi(envValue)
|
||||
if err != nil || parsedMinutes <= 0 {
|
||||
return nil
|
||||
}
|
||||
|
||||
// Backwards compatibility: a bare integer used to be interpreted as minutes.
|
||||
if parsedMinutes, err := strconv.Atoi(envValue); err == nil && parsedMinutes > 0 {
|
||||
d := time.Duration(parsedMinutes) * time.Minute
|
||||
return &d
|
||||
}
|
||||
|
||||
log.Warnf("invalid %s value %q: expected a Go duration such as 30m or 1h", lazyconn.EnvInactivityThreshold, envValue)
|
||||
return nil
|
||||
d := time.Duration(parsedMinutes) * time.Minute
|
||||
return &d
|
||||
}
|
||||
|
||||
@@ -1,21 +1,10 @@
|
||||
package internal
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net"
|
||||
"net/netip"
|
||||
"os"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
|
||||
|
||||
"github.com/netbirdio/netbird/client/iface/wgaddr"
|
||||
"github.com/netbirdio/netbird/client/internal/lazyconn"
|
||||
"github.com/netbirdio/netbird/client/internal/peer"
|
||||
"github.com/netbirdio/netbird/client/internal/peerstore"
|
||||
"github.com/netbirdio/netbird/monotime"
|
||||
)
|
||||
|
||||
func TestResolveLazyForce(t *testing.T) {
|
||||
@@ -49,93 +38,3 @@ func TestResolveLazyForce(t *testing.T) {
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
type mockLazyWGIface struct{}
|
||||
|
||||
func (mockLazyWGIface) RemovePeer(string) error { return nil }
|
||||
func (mockLazyWGIface) UpdatePeer(string, []netip.Prefix, time.Duration, *net.UDPAddr, *wgtypes.Key) error {
|
||||
return nil
|
||||
}
|
||||
func (mockLazyWGIface) IsUserspaceBind() bool { return false }
|
||||
func (mockLazyWGIface) Address() wgaddr.Address { return wgaddr.Address{} }
|
||||
func (mockLazyWGIface) LastActivities() map[string]monotime.Time { return nil }
|
||||
func (mockLazyWGIface) MTU() uint16 { return 1280 }
|
||||
|
||||
// TestConnMgr_ActivatePeerConcurrentWithLifecycle exercises ActivatePeer from
|
||||
// non-engine goroutines (the DNS warm-up path) racing the manager lifecycle,
|
||||
// which stays on the engine loop. Run with -race: it fails if ActivatePeer
|
||||
// still requires engine.syncMsgMux for safety.
|
||||
func TestConnMgr_ActivatePeerConcurrentWithLifecycle(t *testing.T) {
|
||||
t.Setenv(lazyconn.EnvLazyConn, "on")
|
||||
|
||||
status := peer.NewRecorder("https://mgm")
|
||||
store := peerstore.NewConnStore()
|
||||
connMgr := NewConnMgr(&EngineConfig{}, status, store, mockLazyWGIface{})
|
||||
|
||||
conn := newTestPeerConn(t, "peerA")
|
||||
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
defer cancel()
|
||||
connMgr.Start(ctx)
|
||||
|
||||
done := make(chan struct{})
|
||||
var wg sync.WaitGroup
|
||||
for range 4 {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
for {
|
||||
select {
|
||||
case <-done:
|
||||
return
|
||||
default:
|
||||
connMgr.ActivatePeer(ctx, conn)
|
||||
}
|
||||
}
|
||||
}()
|
||||
}
|
||||
|
||||
// Let the activators spin against the started manager, then tear it down
|
||||
// underneath them and let them spin against the stopped manager.
|
||||
time.Sleep(100 * time.Millisecond)
|
||||
connMgr.Close()
|
||||
time.Sleep(50 * time.Millisecond)
|
||||
|
||||
close(done)
|
||||
wg.Wait()
|
||||
}
|
||||
|
||||
func TestInactivityThresholdEnv(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
val string
|
||||
want *time.Duration
|
||||
}{
|
||||
{name: "unset", val: "", want: nil},
|
||||
{name: "go duration minutes", val: "30m", want: durPtr(30 * time.Minute)},
|
||||
{name: "go duration hours", val: "1h", want: durPtr(time.Hour)},
|
||||
{name: "go duration seconds", val: "90s", want: durPtr(90 * time.Second)},
|
||||
{name: "bare integer is minutes (backwards compat)", val: "5", want: durPtr(5 * time.Minute)},
|
||||
{name: "zero duration", val: "0s", want: nil},
|
||||
{name: "zero integer", val: "0", want: nil},
|
||||
{name: "negative duration", val: "-5m", want: nil},
|
||||
{name: "garbage", val: "abc", want: nil},
|
||||
}
|
||||
|
||||
for _, tc := range tests {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
t.Setenv(lazyconn.EnvInactivityThreshold, tc.val)
|
||||
got := inactivityThresholdEnv()
|
||||
switch {
|
||||
case tc.want == nil && got != nil:
|
||||
t.Fatalf("want nil, got %v", *got)
|
||||
case tc.want != nil && got == nil:
|
||||
t.Fatalf("want %v, got nil", *tc.want)
|
||||
case tc.want != nil && *got != *tc.want:
|
||||
t.Fatalf("want %v, got %v", *tc.want, *got)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func durPtr(d time.Duration) *time.Duration { return &d }
|
||||
|
||||
@@ -34,7 +34,6 @@ import (
|
||||
"github.com/netbirdio/netbird/client/internal/profilemanager"
|
||||
"github.com/netbirdio/netbird/client/internal/statemanager"
|
||||
"github.com/netbirdio/netbird/client/internal/stdnet"
|
||||
"github.com/netbirdio/netbird/client/internal/tunnelnotifier"
|
||||
"github.com/netbirdio/netbird/client/internal/updater"
|
||||
"github.com/netbirdio/netbird/client/internal/updater/installer"
|
||||
nbnet "github.com/netbirdio/netbird/client/net"
|
||||
@@ -137,13 +136,10 @@ func (c *ConnectClient) RunOniOS(
|
||||
// Set GC percent to 5% to reduce memory usage as iOS only allows 50MB of memory for the extension.
|
||||
debug.SetGCPercent(5)
|
||||
|
||||
notifier := tunnelnotifier.New(networkChangeListener, dnsManager)
|
||||
defer notifier.Close()
|
||||
|
||||
mobileDependency := MobileDependency{
|
||||
FileDescriptor: fileDescriptor,
|
||||
NetworkChangeListener: notifier,
|
||||
DnsManager: notifier,
|
||||
NetworkChangeListener: networkChangeListener,
|
||||
DnsManager: dnsManager,
|
||||
StateFilePath: stateFilePath,
|
||||
TempDir: cacheDir,
|
||||
}
|
||||
@@ -261,10 +257,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
|
||||
log.Errorf("failed to clean up temporary installer file: %v", err)
|
||||
}
|
||||
|
||||
defer func() {
|
||||
c.statusRecorder.SetSessionExpiresAt(time.Time{})
|
||||
c.statusRecorder.ClientStop()
|
||||
}()
|
||||
defer c.statusRecorder.ClientStop()
|
||||
operation := func() error {
|
||||
// if context cancelled we not start new backoff cycle
|
||||
if c.ctx.Err() != nil {
|
||||
@@ -625,7 +618,6 @@ func createEngineConfig(key wgtypes.Key, config *profilemanager.Config, peerConf
|
||||
BlockLANAccess: config.BlockLANAccess,
|
||||
BlockInbound: config.BlockInbound,
|
||||
DisableIPv6: config.DisableIPv6,
|
||||
SyncMessageVersion: config.SyncMessageVersion,
|
||||
|
||||
LazyConnection: lazyconn.ParseState(config.LazyConnection),
|
||||
|
||||
@@ -701,7 +693,6 @@ func loginToManagement(ctx context.Context, client mgm.Client, pubSSHKey []byte,
|
||||
config.BlockLANAccess,
|
||||
config.BlockInbound,
|
||||
config.DisableIPv6,
|
||||
config.SyncMessageVersion,
|
||||
config.EnableSSHRoot,
|
||||
config.EnableSSHSFTP,
|
||||
config.EnableSSHLocalPortForwarding,
|
||||
|
||||
@@ -1,15 +0,0 @@
|
||||
package daemonaddr
|
||||
|
||||
// DaemonRunsAsSelf reports whether the daemon listening at addr runs as this very
|
||||
// user. That is what makes an unprivileged daemon authorize this process for the
|
||||
// changes it otherwise restricts to root or an administrator, so a client can tell
|
||||
// up front whether those controls are usable instead of letting a save fail.
|
||||
//
|
||||
// It is answered from the ownership of the socket or pipe the daemon created, so it
|
||||
// costs no round trip and needs no cooperation from the daemon. Ownership that
|
||||
// cannot be read is reported as false, including for a TCP address, so a caller
|
||||
// reading this as "the daemon would allow it" fails closed. The daemon remains the
|
||||
// only thing that authorizes anything: this only decides what a client offers.
|
||||
func DaemonRunsAsSelf(addr string) bool {
|
||||
return daemonRunsAsSelf(addr)
|
||||
}
|
||||
@@ -1,40 +0,0 @@
|
||||
//go:build !windows
|
||||
|
||||
package daemonaddr
|
||||
|
||||
import (
|
||||
"os"
|
||||
"strings"
|
||||
"syscall"
|
||||
|
||||
log "github.com/sirupsen/logrus"
|
||||
)
|
||||
|
||||
// daemonRunsAsSelf compares the owner of the daemon's Unix socket with this
|
||||
// process's uid. Root is not treated specially here: a root caller is privileged
|
||||
// on its own merits, and a root-owned socket says nothing about the caller.
|
||||
func daemonRunsAsSelf(addr string) bool {
|
||||
path, ok := strings.CutPrefix(addr, "unix://")
|
||||
if !ok {
|
||||
return false
|
||||
}
|
||||
|
||||
info, err := os.Stat(path)
|
||||
if err != nil {
|
||||
log.Debugf("stat daemon socket %s: %v", path, err)
|
||||
return false
|
||||
}
|
||||
|
||||
// Only a socket says anything about a daemon. A directory or a leftover
|
||||
// regular file at that path is not one, and reading it as "the daemon runs as
|
||||
// us" would offer controls the daemon then refuses.
|
||||
if info.Mode()&os.ModeSocket == 0 {
|
||||
return false
|
||||
}
|
||||
|
||||
stat, ok := info.Sys().(*syscall.Stat_t)
|
||||
if !ok {
|
||||
return false
|
||||
}
|
||||
return stat.Uid == uint32(os.Getuid())
|
||||
}
|
||||
@@ -1,62 +0,0 @@
|
||||
//go:build !windows
|
||||
|
||||
package daemonaddr
|
||||
|
||||
import (
|
||||
"net"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// A socket this user created means the daemon runs as this user, which is the
|
||||
// rootless case where the daemon delegates its authority to its own identity.
|
||||
func TestDaemonRunsAsSelf_OwnSocket(t *testing.T) {
|
||||
path := filepath.Join(t.TempDir(), "netbird.sock")
|
||||
ln, err := net.Listen("unix", path)
|
||||
if err != nil {
|
||||
t.Fatalf("listen: %v", err)
|
||||
}
|
||||
t.Cleanup(func() {
|
||||
if err := ln.Close(); err != nil {
|
||||
t.Logf("close listener: %v", err)
|
||||
}
|
||||
})
|
||||
|
||||
if !DaemonRunsAsSelf("unix://" + path) {
|
||||
t.Error("a socket owned by this user must count as the daemon running as us")
|
||||
}
|
||||
}
|
||||
|
||||
// Everything that is not a readable socket of ours has to answer false, because
|
||||
// the caller reads a true as "the daemon would authorize me".
|
||||
func TestDaemonRunsAsSelf_FailsClosed(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
|
||||
// A socket owned by another user, which is what a root-run daemon looks like
|
||||
// to an unprivileged client. Only assertable when we are not root ourselves.
|
||||
rootOwned := "unix:///var/run/netbird.sock"
|
||||
if _, err := os.Stat("/var/run/netbird.sock"); err == nil && os.Getuid() != 0 {
|
||||
if DaemonRunsAsSelf(rootOwned) {
|
||||
t.Error("a socket owned by another user must not count as ours")
|
||||
}
|
||||
}
|
||||
|
||||
for name, addr := range map[string]string{
|
||||
"missing socket": "unix://" + filepath.Join(dir, "absent.sock"),
|
||||
"tcp address": "tcp://127.0.0.1:41731",
|
||||
"named pipe": "npipe://netbird",
|
||||
"empty": "",
|
||||
"no scheme": filepath.Join(dir, "absent.sock"),
|
||||
"directory": "unix://" + dir,
|
||||
"unknown scheme": "http://localhost:8080",
|
||||
"scheme only": "unix://",
|
||||
"relative socket": "unix://netbird.sock",
|
||||
} {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
if DaemonRunsAsSelf(addr) {
|
||||
t.Errorf("%q must not count as a daemon running as us", addr)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -1,42 +0,0 @@
|
||||
//go:build windows
|
||||
|
||||
package daemonaddr
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
|
||||
log "github.com/sirupsen/logrus"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/ipcauth"
|
||||
)
|
||||
|
||||
// daemonRunsAsSelf reads the owner of the daemon's pipe. A daemon running as the
|
||||
// service account owns its pipe as LocalSystem, and an elevated one as
|
||||
// BUILTIN\Administrators, so only a daemon the user started themselves matches.
|
||||
func daemonRunsAsSelf(addr string) bool {
|
||||
name, ok := strings.CutPrefix(addr, pipeScheme)
|
||||
if !ok {
|
||||
return false
|
||||
}
|
||||
|
||||
for _, path := range PipePaths(name) {
|
||||
// Bounded: this runs on the UI's path for deciding which controls to
|
||||
// offer, so a pipe that does not answer promptly must not stall it. A
|
||||
// timeout leaves the caller unprivileged, which only disables controls.
|
||||
ctx, cancel := context.WithTimeout(context.Background(), probeTimeout)
|
||||
conn, err := dialPipe(ctx, path)
|
||||
cancel()
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
|
||||
owned := ipcauth.PipeOwnedBySelf(conn)
|
||||
if cerr := conn.Close(); cerr != nil {
|
||||
log.Debugf("close daemon pipe %s after ownership check: %v", path, cerr)
|
||||
}
|
||||
return owned
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
@@ -1,103 +0,0 @@
|
||||
package daemonaddr
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net"
|
||||
"runtime"
|
||||
"strings"
|
||||
|
||||
"google.golang.org/grpc"
|
||||
"google.golang.org/grpc/credentials/insecure"
|
||||
)
|
||||
|
||||
const (
|
||||
// WindowsPipeAddr is the default daemon address on Windows. A named pipe
|
||||
// carries the connecting process's token, which loopback TCP does not, so
|
||||
// it is the only Windows transport on which the daemon can tell who is
|
||||
// calling it.
|
||||
WindowsPipeAddr = "npipe://netbird"
|
||||
|
||||
// legacyWindowsAddr is the loopback-TCP address the Windows daemon used
|
||||
// before named-pipe support.
|
||||
legacyWindowsAddr = "tcp://127.0.0.1:41731"
|
||||
|
||||
pipeScheme = "npipe://"
|
||||
|
||||
// protectedPrefix is the NPFS namespace in which only LocalSystem and
|
||||
// members of BUILTIN\Administrators may create a pipe. A daemon running as
|
||||
// the service account creates its pipe there so that an unprivileged process
|
||||
// cannot pre-create the name, which would keep the daemon from starting and
|
||||
// leave callers talking to the squatter. Opening such a pipe needs no
|
||||
// privilege, so unprivileged clients still reach the daemon.
|
||||
protectedPrefix = `ProtectedPrefix\Administrators\`
|
||||
)
|
||||
|
||||
// DialTarget returns the gRPC dial target and transport options for a daemon
|
||||
// address. The npipe scheme needs a context dialer because gRPC has no
|
||||
// named-pipe resolver; unix and tcp are handled by gRPC itself.
|
||||
func DialTarget(addr string) (string, []grpc.DialOption) {
|
||||
opts := []grpc.DialOption{grpc.WithTransportCredentials(insecure.NewCredentials())}
|
||||
|
||||
if name, ok := strings.CutPrefix(addr, pipeScheme); ok {
|
||||
paths := PipePaths(name)
|
||||
opts = append(opts, grpc.WithContextDialer(func(ctx context.Context, _ string) (net.Conn, error) {
|
||||
return dialPipePaths(ctx, paths)
|
||||
}))
|
||||
return "passthrough:///netbird-daemon-pipe", opts
|
||||
}
|
||||
|
||||
return strings.TrimPrefix(addr, "tcp://"), opts
|
||||
}
|
||||
|
||||
// PipePath maps an npipe address name ("netbird", from "npipe://netbird") to a
|
||||
// Windows named-pipe path (\\.\pipe\netbird). A fully qualified path is left as
|
||||
// is.
|
||||
func PipePath(name string) string {
|
||||
if strings.HasPrefix(name, `\\`) {
|
||||
return name
|
||||
}
|
||||
return `\\.\pipe\` + name
|
||||
}
|
||||
|
||||
// PipePaths returns the paths a daemon control pipe may live at for an npipe
|
||||
// address name, in the order both sides must try them: the protected name first,
|
||||
// then the plain one.
|
||||
//
|
||||
// The daemon serves the first it can create, which is the protected name when it
|
||||
// runs as the service account and the plain one when it runs as an ordinary user,
|
||||
// as it does in netstack mode. Clients therefore have to try both, and because a
|
||||
// client cannot tell from the name alone who created the pipe, the plain name is
|
||||
// only usable once the server's identity has been checked: see
|
||||
// verifyPipeServer.
|
||||
//
|
||||
// A fully qualified path is what the operator asked for and is used as is.
|
||||
func PipePaths(name string) []string {
|
||||
if strings.HasPrefix(name, `\\`) {
|
||||
return []string{name}
|
||||
}
|
||||
return []string{PipePath(protectedPrefix + name), PipePath(name)}
|
||||
}
|
||||
|
||||
// IsProtectedPipePath reports whether a pipe path is in the namespace only an
|
||||
// administrator or LocalSystem can create in, which is what lets a client trust
|
||||
// such a pipe from its name alone.
|
||||
func IsProtectedPipePath(path string) bool {
|
||||
return strings.HasPrefix(path, `\\.\pipe\`+protectedPrefix)
|
||||
}
|
||||
|
||||
// MigrateLegacy upgrades the pre-named-pipe Windows daemon address to the named
|
||||
// pipe, reporting whether it rewrote the address. Existing installs persist the
|
||||
// daemon address, so without this an upgraded daemon would keep listening on
|
||||
// loopback TCP, where callers carry no identity and privileged operations would
|
||||
// have to be refused for everyone. Only the exact legacy default is rewritten:
|
||||
// a deliberately chosen custom address is left alone.
|
||||
func MigrateLegacy(addr string) (string, bool) {
|
||||
return migrateLegacyForOS(runtime.GOOS, addr)
|
||||
}
|
||||
|
||||
func migrateLegacyForOS(goos, addr string) (string, bool) {
|
||||
if goos == "windows" && addr == legacyWindowsAddr {
|
||||
return WindowsPipeAddr, true
|
||||
}
|
||||
return addr, false
|
||||
}
|
||||
@@ -1,15 +0,0 @@
|
||||
//go:build !windows
|
||||
|
||||
package daemonaddr
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"net"
|
||||
)
|
||||
|
||||
// dialPipePaths is Windows-only: no other platform serves the daemon on a named
|
||||
// pipe.
|
||||
func dialPipePaths(context.Context, []string) (net.Conn, error) {
|
||||
return nil, fmt.Errorf("named pipes are only supported on Windows")
|
||||
}
|
||||
@@ -1,30 +0,0 @@
|
||||
package daemonaddr
|
||||
|
||||
import (
|
||||
"slices"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// The protected name must be tried before the plain one on both sides: it is the
|
||||
// one an unprivileged process cannot create, so preferring it is what keeps a
|
||||
// squatter from owning the name the service daemon would otherwise use.
|
||||
func TestPipePaths_PrefersTheProtectedName(t *testing.T) {
|
||||
got := PipePaths("netbird")
|
||||
want := []string{
|
||||
`\\.\pipe\ProtectedPrefix\Administrators\netbird`,
|
||||
`\\.\pipe\netbird`,
|
||||
}
|
||||
if !slices.Equal(got, want) {
|
||||
t.Errorf("PipePaths = %q, want %q", got, want)
|
||||
}
|
||||
}
|
||||
|
||||
// An operator who passes a full path chose exactly one pipe, so neither side may
|
||||
// look anywhere else.
|
||||
func TestPipePaths_QualifiedPathIsUsedAsIs(t *testing.T) {
|
||||
path := `\\.\pipe\custom-netbird`
|
||||
got := PipePaths(path)
|
||||
if !slices.Equal(got, []string{path}) {
|
||||
t.Errorf("PipePaths = %q, want just %q", got, path)
|
||||
}
|
||||
}
|
||||
@@ -1,59 +0,0 @@
|
||||
//go:build windows
|
||||
|
||||
package daemonaddr
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"net"
|
||||
|
||||
"github.com/Microsoft/go-winio"
|
||||
log "github.com/sirupsen/logrus"
|
||||
"golang.org/x/sys/windows"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/ipcauth"
|
||||
)
|
||||
|
||||
// dialPipePaths connects to the first path that answers with a pipe server this
|
||||
// client may trust, and returns the last error when none does.
|
||||
func dialPipePaths(ctx context.Context, paths []string) (net.Conn, error) {
|
||||
var lastErr error
|
||||
for _, path := range paths {
|
||||
conn, err := dialPipe(ctx, path)
|
||||
if err != nil {
|
||||
log.Debugf("dial daemon pipe %s: %v", path, err)
|
||||
lastErr = err
|
||||
continue
|
||||
}
|
||||
|
||||
// A pipe in the protected namespace could only have been created by an
|
||||
// administrator or LocalSystem, so its name is the guarantee. Any other
|
||||
// name has to be checked, because any local user can create one.
|
||||
if !IsProtectedPipePath(path) {
|
||||
if err := ipcauth.PipeServerTrusted(conn); err != nil {
|
||||
if closeErr := conn.Close(); closeErr != nil {
|
||||
log.Debugf("close untrusted pipe %s: %v", path, closeErr)
|
||||
}
|
||||
lastErr = fmt.Errorf("%s: %w", path, err)
|
||||
continue
|
||||
}
|
||||
}
|
||||
|
||||
return conn, nil
|
||||
}
|
||||
|
||||
if lastErr == nil {
|
||||
lastErr = errors.New("no daemon pipe to connect to")
|
||||
}
|
||||
return nil, lastErr
|
||||
}
|
||||
|
||||
// dialPipe connects to the daemon control pipe at SECURITY_IDENTIFICATION.
|
||||
// winio's plain DialPipe connects at SECURITY_ANONYMOUS, under which the daemon
|
||||
// cannot read the caller's token at all. Identification lets the daemon read the
|
||||
// caller's SID and groups without granting it the ability to act as the caller.
|
||||
func dialPipe(ctx context.Context, path string) (net.Conn, error) {
|
||||
access := uint32(windows.GENERIC_READ | windows.GENERIC_WRITE)
|
||||
return winio.DialPipeAccessImpLevel(ctx, path, access, winio.PipeImpLevelIdentification)
|
||||
}
|
||||
@@ -1,9 +0,0 @@
|
||||
//go:build !windows
|
||||
|
||||
package daemonaddr
|
||||
|
||||
// ResolveDaemonAddr is a no-op off Windows, where there is no named-pipe
|
||||
// default to fall back from.
|
||||
func ResolveDaemonAddr(addr string) string {
|
||||
return addr
|
||||
}
|
||||
@@ -1,82 +0,0 @@
|
||||
//go:build windows
|
||||
|
||||
package daemonaddr
|
||||
|
||||
import (
|
||||
"net"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/Microsoft/go-winio"
|
||||
log "github.com/sirupsen/logrus"
|
||||
)
|
||||
|
||||
// probeTimeout bounds each transport probe. Both are local, so a daemon that is
|
||||
// listening answers immediately and one that is not fails immediately.
|
||||
const probeTimeout = 300 * time.Millisecond
|
||||
|
||||
// ResolveDaemonAddr keeps a client on the named pipe and never silently moves it
|
||||
// off. When the pipe does not answer it checks the legacy loopback TCP address, so
|
||||
// a client meeting a daemon that has not restarted since the upgrade can say what
|
||||
// is wrong, but it does not connect there.
|
||||
//
|
||||
// Using that address automatically would be a downgrade the user never asked for:
|
||||
// any local process can bind 127.0.0.1 while the daemon is not listening, and the
|
||||
// transport carries no caller identity, so a client that accepted whatever answered
|
||||
// would hand a setup key, a pre-shared key or an SSO prompt to a local impostor. An
|
||||
// operator who needs the legacy address during the upgrade window can still pass
|
||||
// --daemon-addr explicitly, which is a deliberate choice and still refuses the
|
||||
// privileged operations.
|
||||
//
|
||||
// Only the pipe address is resolved. A custom address is left alone, though passing
|
||||
// --daemon-addr npipe://netbird explicitly is indistinguishable from the default
|
||||
// here, so it is treated the same way.
|
||||
func ResolveDaemonAddr(addr string) string {
|
||||
if addr != WindowsPipeAddr {
|
||||
return addr
|
||||
}
|
||||
|
||||
for _, path := range PipePaths("netbird") {
|
||||
if pipeAvailable(path) {
|
||||
return addr
|
||||
}
|
||||
}
|
||||
|
||||
if tcpAvailable(legacyWindowsAddr) {
|
||||
log.Warnf("the daemon is not serving %s, but something is listening on the legacy %s. "+
|
||||
"Restart the NetBird service so it serves the pipe. That address is not used automatically: "+
|
||||
"any local user can bind it and it carries no caller identity, so pass --daemon-addr %s "+
|
||||
"explicitly if you accept that",
|
||||
WindowsPipeAddr, legacyWindowsAddr, legacyWindowsAddr)
|
||||
}
|
||||
|
||||
return addr
|
||||
}
|
||||
|
||||
func pipeAvailable(path string) bool {
|
||||
timeout := probeTimeout
|
||||
conn, err := winio.DialPipe(path, &timeout)
|
||||
if err != nil {
|
||||
return false
|
||||
}
|
||||
if err := conn.Close(); err != nil {
|
||||
log.Debugf("close daemon pipe probe: %v", err)
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
func tcpAvailable(addr string) bool {
|
||||
host := addr
|
||||
if _, after, ok := strings.Cut(addr, "://"); ok {
|
||||
host = after
|
||||
}
|
||||
|
||||
conn, err := net.DialTimeout("tcp", host, probeTimeout)
|
||||
if err != nil {
|
||||
return false
|
||||
}
|
||||
if err := conn.Close(); err != nil {
|
||||
log.Debugf("close daemon TCP probe: %v", err)
|
||||
}
|
||||
return true
|
||||
}
|
||||
@@ -676,7 +676,6 @@ func (g *BundleGenerator) addCommonConfigFields(configContent *strings.Builder)
|
||||
configContent.WriteString(fmt.Sprintf("BlockLANAccess: %v\n", g.internalConfig.BlockLANAccess))
|
||||
configContent.WriteString(fmt.Sprintf("BlockInbound: %v\n", g.internalConfig.BlockInbound))
|
||||
configContent.WriteString(fmt.Sprintf("DisableIPv6: %v\n", g.internalConfig.DisableIPv6))
|
||||
configContent.WriteString(fmt.Sprintf("SyncMessageVersion: %v\n", g.internalConfig.SyncMessageVersion))
|
||||
|
||||
if g.internalConfig.DisableNotifications != nil {
|
||||
configContent.WriteString(fmt.Sprintf("DisableNotifications: %v\n", *g.internalConfig.DisableNotifications))
|
||||
|
||||
@@ -887,8 +887,6 @@ func TestAddConfig_AllFieldsCovered(t *testing.T) {
|
||||
ClientCertKeyPath: "/tmp/key",
|
||||
LazyConnection: "on",
|
||||
MTU: 1280,
|
||||
DisableIPv6: true,
|
||||
SyncMessageVersion: func(v int) *int { return &v }(1),
|
||||
}
|
||||
|
||||
for _, anonymize := range []bool{false, true} {
|
||||
|
||||
@@ -6,7 +6,6 @@ import (
|
||||
"fmt"
|
||||
"net"
|
||||
"net/netip"
|
||||
"os"
|
||||
"slices"
|
||||
"strings"
|
||||
"sync"
|
||||
@@ -37,43 +36,7 @@ type resolver interface {
|
||||
// record is left alone (it points at something outside our mesh, e.g.
|
||||
// a non-peer upstream).
|
||||
type PeerConnectivity interface {
|
||||
IsConnectedByIP(ip netip.Addr) (known, connected bool)
|
||||
}
|
||||
|
||||
// PeerActivator wakes lazy-connection peers on demand. The local resolver calls
|
||||
// it with the tunnel IPs an answer points at, so a peer that is idle (lazily
|
||||
// disconnected) starts connecting at DNS-resolution time rather than racing the
|
||||
// client's first request packet. nil disables warm-up.
|
||||
type PeerActivator interface {
|
||||
// ActivatePeersByIP triggers wake-up for the peer(s) owning addrs and blocks
|
||||
// until one is connected or ctx (a short per-query budget) expires. It is a
|
||||
// fast no-op for unknown or already-connected addresses.
|
||||
ActivatePeersByIP(ctx context.Context, addrs []netip.Addr)
|
||||
}
|
||||
|
||||
const (
|
||||
defaultLazyWarmupTimeout = 2 * time.Second
|
||||
envLazyWarmupTimeout = "NB_DNS_LAZY_WARMUP_TIMEOUT"
|
||||
)
|
||||
|
||||
// lazyWarmupTimeoutFromEnv returns the per-query budget for waking a
|
||||
// lazy-connection peer a DNS answer points at. Tunable via
|
||||
// NB_DNS_LAZY_WARMUP_TIMEOUT (a Go duration). Parsed once at construction time.
|
||||
func lazyWarmupTimeoutFromEnv() time.Duration {
|
||||
v := os.Getenv(envLazyWarmupTimeout)
|
||||
if v == "" {
|
||||
return defaultLazyWarmupTimeout
|
||||
}
|
||||
d, err := time.ParseDuration(v)
|
||||
if err != nil {
|
||||
log.Warnf("invalid %s value %q, using default %s: %v", envLazyWarmupTimeout, v, defaultLazyWarmupTimeout, err)
|
||||
return defaultLazyWarmupTimeout
|
||||
}
|
||||
if d <= 0 {
|
||||
log.Warnf("non-positive %s value %q, using default %s", envLazyWarmupTimeout, v, defaultLazyWarmupTimeout)
|
||||
return defaultLazyWarmupTimeout
|
||||
}
|
||||
return d
|
||||
IsConnectedByIP(ip string) (known, connected bool)
|
||||
}
|
||||
|
||||
type Resolver struct {
|
||||
@@ -88,12 +51,6 @@ type Resolver struct {
|
||||
// filter and preserves the legacy "return whatever is registered"
|
||||
// behaviour for callers that never wire a status source.
|
||||
peerConn PeerConnectivity
|
||||
// peerActivator, when non-nil, is called at resolution time to warm the
|
||||
// lazy connection to the peer(s) an answer points at. nil disables warm-up.
|
||||
peerActivator PeerActivator
|
||||
// warmupTimeout is the per-query budget for the lazy-connection warm-up
|
||||
// wait, resolved from the environment once at construction time.
|
||||
warmupTimeout time.Duration
|
||||
|
||||
ctx context.Context
|
||||
cancel context.CancelFunc
|
||||
@@ -102,12 +59,11 @@ type Resolver struct {
|
||||
func NewResolver() *Resolver {
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
return &Resolver{
|
||||
records: make(map[dns.Question][]dns.RR),
|
||||
domains: make(map[domain.Domain]struct{}),
|
||||
zones: make(map[domain.Domain]bool),
|
||||
warmupTimeout: lazyWarmupTimeoutFromEnv(),
|
||||
ctx: ctx,
|
||||
cancel: cancel,
|
||||
records: make(map[dns.Question][]dns.RR),
|
||||
domains: make(map[domain.Domain]struct{}),
|
||||
zones: make(map[domain.Domain]bool),
|
||||
ctx: ctx,
|
||||
cancel: cancel,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -120,14 +76,6 @@ func (d *Resolver) SetPeerConnectivity(p PeerConnectivity) {
|
||||
d.peerConn = p
|
||||
}
|
||||
|
||||
// SetPeerActivator wires the DNS-time lazy-connection warm-up. Pass nil to
|
||||
// disable. Safe to call multiple times; the latest value wins.
|
||||
func (d *Resolver) SetPeerActivator(a PeerActivator) {
|
||||
d.mu.Lock()
|
||||
defer d.mu.Unlock()
|
||||
d.peerActivator = a
|
||||
}
|
||||
|
||||
func (d *Resolver) MatchSubdomains() bool {
|
||||
return true
|
||||
}
|
||||
@@ -174,9 +122,6 @@ func (d *Resolver) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
|
||||
replyMessage.RecursionAvailable = true
|
||||
|
||||
result := d.lookupRecords(logger, question)
|
||||
// Warm before filtering: activation flips a lazily-idle target to connected,
|
||||
// which then lets it survive the disconnected-peer filter below.
|
||||
d.warmLazyPeers(question, result.records)
|
||||
result.records = d.filterDisconnectedPeerAnswers(logger, question, result.records)
|
||||
replyMessage.Authoritative = !result.hasExternalData
|
||||
replyMessage.Answer = result.records
|
||||
@@ -550,8 +495,8 @@ func (d *Resolver) filterDisconnectedPeerAnswers(logger *log.Entry, question dns
|
||||
kept := make([]dns.RR, 0, len(records))
|
||||
var dropped int
|
||||
for _, rr := range records {
|
||||
ip, ok := extractRecordAddr(rr)
|
||||
if !ok {
|
||||
ip := extractRecordIP(rr)
|
||||
if ip == "" {
|
||||
kept = append(kept, rr)
|
||||
continue
|
||||
}
|
||||
@@ -573,57 +518,22 @@ func (d *Resolver) filterDisconnectedPeerAnswers(logger *log.Entry, question dns
|
||||
return kept
|
||||
}
|
||||
|
||||
// warmLazyPeers triggers lazy-connection wake-up for the peers a resolved
|
||||
// answer points at and waits briefly for one to connect, so the caller's first
|
||||
// request doesn't race the connection establishment. Warm-up is scoped to
|
||||
// match-only (non-authoritative) zones — the synthesized private-service zones
|
||||
// and user-created zones whose records point at specific peers. The account's
|
||||
// peer zone is authoritative, so plain peer-name lookups never trigger warm-up;
|
||||
// otherwise resolving any peer's name would wake its idle connection, defeating
|
||||
// laziness mesh-wide. No-op when no activator is wired (lazy connections
|
||||
// disabled) or the answer carries no peer IPs.
|
||||
func (d *Resolver) warmLazyPeers(question dns.Question, records []dns.RR) {
|
||||
if len(records) < 2 {
|
||||
return
|
||||
}
|
||||
d.mu.RLock()
|
||||
activator := d.peerActivator
|
||||
var nonAuth, found bool
|
||||
if activator != nil {
|
||||
nonAuth, found = d.findZone(question.Name)
|
||||
}
|
||||
d.mu.RUnlock()
|
||||
if activator == nil || !found || !nonAuth {
|
||||
return
|
||||
}
|
||||
|
||||
var addrs []netip.Addr
|
||||
for _, rr := range records {
|
||||
if addr, ok := extractRecordAddr(rr); ok {
|
||||
addrs = append(addrs, addr)
|
||||
}
|
||||
}
|
||||
if len(addrs) == 0 {
|
||||
return
|
||||
}
|
||||
|
||||
ctx, cancel := context.WithTimeout(d.ctx, d.warmupTimeout)
|
||||
defer cancel()
|
||||
activator.ActivatePeersByIP(ctx, addrs)
|
||||
}
|
||||
|
||||
// extractRecordAddr returns the IP address carried by an A or AAAA record.
|
||||
// ok is false for any other record type or a record with no address.
|
||||
func extractRecordAddr(rr dns.RR) (netip.Addr, bool) {
|
||||
// extractRecordIP returns the dotted-decimal / colon-hex IP carried by
|
||||
// an A or AAAA record, or "" for any other record type.
|
||||
func extractRecordIP(rr dns.RR) string {
|
||||
switch r := rr.(type) {
|
||||
case *dns.A:
|
||||
addr, ok := netip.AddrFromSlice(r.A)
|
||||
return addr.Unmap(), ok
|
||||
if r.A == nil {
|
||||
return ""
|
||||
}
|
||||
return r.A.String()
|
||||
case *dns.AAAA:
|
||||
addr, ok := netip.AddrFromSlice(r.AAAA)
|
||||
return addr.Unmap(), ok
|
||||
if r.AAAA == nil {
|
||||
return ""
|
||||
}
|
||||
return r.AAAA.String()
|
||||
}
|
||||
return netip.Addr{}, false
|
||||
return ""
|
||||
}
|
||||
|
||||
// Update replaces all zones and their records
|
||||
|
||||
@@ -37,8 +37,8 @@ type mockPeerConnectivity struct {
|
||||
byIP map[string]struct{ known, connected bool }
|
||||
}
|
||||
|
||||
func (m mockPeerConnectivity) IsConnectedByIP(ip netip.Addr) (known, connected bool) {
|
||||
v, ok := m.byIP[ip.String()]
|
||||
func (m mockPeerConnectivity) IsConnectedByIP(ip string) (known, connected bool) {
|
||||
v, ok := m.byIP[ip]
|
||||
if !ok {
|
||||
return false, false
|
||||
}
|
||||
|
||||
@@ -1,204 +0,0 @@
|
||||
package local
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net"
|
||||
"net/netip"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/miekg/dns"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/dns/test"
|
||||
nbdns "github.com/netbirdio/netbird/dns"
|
||||
)
|
||||
|
||||
// recordingActivator records the addresses it was asked to warm and returns
|
||||
// immediately, so ServeDNS is not blocked by the test.
|
||||
type recordingActivator struct {
|
||||
mu sync.Mutex
|
||||
called bool
|
||||
addrs []netip.Addr
|
||||
}
|
||||
|
||||
func (r *recordingActivator) ActivatePeersByIP(_ context.Context, addrs []netip.Addr) {
|
||||
r.mu.Lock()
|
||||
defer r.mu.Unlock()
|
||||
r.called = true
|
||||
r.addrs = append(r.addrs, addrs...)
|
||||
}
|
||||
|
||||
func serveA(t *testing.T, resolver *Resolver, name string) *dns.Msg {
|
||||
t.Helper()
|
||||
var resp *dns.Msg
|
||||
w := &test.MockResponseWriter{WriteMsgFunc: func(m *dns.Msg) error { resp = m; return nil }}
|
||||
resolver.ServeDNS(w, new(dns.Msg).SetQuestion(name, dns.TypeA))
|
||||
return resp
|
||||
}
|
||||
|
||||
// serviceZone registers rec in a match-only (non-authoritative) zone, the shape
|
||||
// the synthesized private-service zones arrive in.
|
||||
func serviceZone(t *testing.T, resolver *Resolver, zone string, records ...nbdns.SimpleRecord) {
|
||||
t.Helper()
|
||||
resolver.Update([]nbdns.CustomZone{{
|
||||
Domain: zone,
|
||||
Records: records,
|
||||
NonAuthoritative: true,
|
||||
}})
|
||||
}
|
||||
|
||||
func TestLocalResolver_WarmsLazyPeerOnResolve(t *testing.T) {
|
||||
// Warm-up fires only for multi-record answers (the HA / round-robin shape of
|
||||
// the synthesized private-service zones), so register two peer targets.
|
||||
const name = "svc.proxy.netbird.cloud."
|
||||
recs := []nbdns.SimpleRecord{
|
||||
{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"},
|
||||
{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.8"},
|
||||
}
|
||||
resolver := NewResolver()
|
||||
serviceZone(t, resolver, "proxy.netbird.cloud", recs...)
|
||||
|
||||
act := &recordingActivator{}
|
||||
resolver.SetPeerActivator(act)
|
||||
|
||||
resp := serveA(t, resolver, name)
|
||||
require.NotNil(t, resp, "resolver must answer")
|
||||
require.NotEmpty(t, resp.Answer, "answer must carry the A records")
|
||||
|
||||
act.mu.Lock()
|
||||
defer act.mu.Unlock()
|
||||
assert.True(t, act.called, "activator must be invoked for a multi-record service-zone answer")
|
||||
assert.Contains(t, act.addrs, netip.MustParseAddr("100.64.0.7"), "activator must receive the first peer IP")
|
||||
assert.Contains(t, act.addrs, netip.MustParseAddr("100.64.0.8"), "activator must receive the second peer IP")
|
||||
}
|
||||
|
||||
func TestLocalResolver_NoWarmupForSingleRecord(t *testing.T) {
|
||||
// A single-record answer does not trigger warm-up; the resolver only warms
|
||||
// multi-record answers.
|
||||
rec := nbdns.SimpleRecord{Name: "svc.proxy.netbird.cloud.", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"}
|
||||
resolver := NewResolver()
|
||||
serviceZone(t, resolver, "proxy.netbird.cloud", rec)
|
||||
|
||||
act := &recordingActivator{}
|
||||
resolver.SetPeerActivator(act)
|
||||
|
||||
resp := serveA(t, resolver, rec.Name)
|
||||
require.NotNil(t, resp, "resolver must answer")
|
||||
require.NotEmpty(t, resp.Answer, "answer must carry the A record")
|
||||
|
||||
act.mu.Lock()
|
||||
defer act.mu.Unlock()
|
||||
assert.False(t, act.called, "activator must not be invoked for a single-record answer")
|
||||
}
|
||||
|
||||
func TestLocalResolver_NoActivatorNoWarmup(t *testing.T) {
|
||||
// With no activator wired the resolver behaves exactly as before.
|
||||
rec := nbdns.SimpleRecord{Name: "svc.proxy.netbird.cloud.", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"}
|
||||
resolver := NewResolver()
|
||||
serviceZone(t, resolver, "proxy.netbird.cloud", rec)
|
||||
|
||||
resp := serveA(t, resolver, rec.Name)
|
||||
require.NotNil(t, resp, "resolver must still answer without an activator")
|
||||
require.NotEmpty(t, resp.Answer, "answer must carry the A record")
|
||||
}
|
||||
|
||||
func TestLocalResolver_NoWarmupForMissingRecord(t *testing.T) {
|
||||
// A query that resolves to nothing must not invoke the activator (no IPs).
|
||||
resolver := NewResolver()
|
||||
serviceZone(t, resolver, "proxy.netbird.cloud",
|
||||
nbdns.SimpleRecord{Name: "svc.proxy.netbird.cloud.", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"})
|
||||
|
||||
act := &recordingActivator{}
|
||||
resolver.SetPeerActivator(act)
|
||||
|
||||
serveA(t, resolver, "absent.proxy.netbird.cloud.")
|
||||
|
||||
act.mu.Lock()
|
||||
defer act.mu.Unlock()
|
||||
assert.False(t, act.called, "activator must not be invoked when there is no answer")
|
||||
}
|
||||
|
||||
func TestLocalResolver_NoWarmupInAuthoritativeZone(t *testing.T) {
|
||||
// The account's peer zone is authoritative; resolving a peer's name there
|
||||
// must not wake its lazy connection — warm-up is scoped to match-only
|
||||
// (non-authoritative) zones such as the synthesized private-service zones.
|
||||
// Use a multi-record answer so the authoritative-zone scoping is the only
|
||||
// reason warm-up is skipped, not the single-record guard.
|
||||
const name = "peer.netbird.cloud."
|
||||
recs := []nbdns.SimpleRecord{
|
||||
{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.9"},
|
||||
{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.10"},
|
||||
}
|
||||
resolver := NewResolver()
|
||||
resolver.Update([]nbdns.CustomZone{{
|
||||
Domain: "netbird.cloud",
|
||||
Records: recs,
|
||||
}})
|
||||
|
||||
act := &recordingActivator{}
|
||||
resolver.SetPeerActivator(act)
|
||||
|
||||
resp := serveA(t, resolver, name)
|
||||
require.NotNil(t, resp, "resolver must answer")
|
||||
require.NotEmpty(t, resp.Answer, "answer must carry the A records")
|
||||
|
||||
act.mu.Lock()
|
||||
defer act.mu.Unlock()
|
||||
assert.False(t, act.called, "activator must not be invoked for authoritative-zone answers")
|
||||
}
|
||||
|
||||
func TestLazyWarmupTimeoutFromEnv(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
value string
|
||||
envSet bool
|
||||
want time.Duration
|
||||
}{
|
||||
{name: "unset uses default", want: defaultLazyWarmupTimeout},
|
||||
{name: "valid overrides", value: "5s", envSet: true, want: 5 * time.Second},
|
||||
{name: "invalid falls back", value: "not-a-duration", envSet: true, want: defaultLazyWarmupTimeout},
|
||||
{name: "negative falls back", value: "-1s", envSet: true, want: defaultLazyWarmupTimeout},
|
||||
{name: "zero falls back", value: "0s", envSet: true, want: defaultLazyWarmupTimeout},
|
||||
}
|
||||
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
if tt.envSet {
|
||||
t.Setenv(envLazyWarmupTimeout, tt.value)
|
||||
}
|
||||
assert.Equal(t, tt.want, lazyWarmupTimeoutFromEnv())
|
||||
assert.Equal(t, tt.want, NewResolver().warmupTimeout, "constructor must resolve the timeout once")
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestExtractRecordAddr(t *testing.T) {
|
||||
t.Run("A record yields unmapped v4", func(t *testing.T) {
|
||||
// net.ParseIP returns the 16-byte v4-in-v6 form, the same shape
|
||||
// miekg/dns stores after parsing an A record; the extracted address
|
||||
// must compare equal to a plain v4 netip.Addr.
|
||||
addr, ok := extractRecordAddr(&dns.A{A: net.ParseIP("100.64.0.7")})
|
||||
require.True(t, ok)
|
||||
assert.True(t, addr.Is4())
|
||||
assert.Equal(t, netip.MustParseAddr("100.64.0.7"), addr)
|
||||
})
|
||||
|
||||
t.Run("AAAA record yields v6", func(t *testing.T) {
|
||||
addr, ok := extractRecordAddr(&dns.AAAA{AAAA: net.ParseIP("fd00::1")})
|
||||
require.True(t, ok)
|
||||
assert.Equal(t, netip.MustParseAddr("fd00::1"), addr)
|
||||
})
|
||||
|
||||
t.Run("A record without address", func(t *testing.T) {
|
||||
_, ok := extractRecordAddr(&dns.A{})
|
||||
assert.False(t, ok)
|
||||
})
|
||||
|
||||
t.Run("non-address record", func(t *testing.T) {
|
||||
_, ok := extractRecordAddr(&dns.CNAME{Target: "target.netbird.cloud."})
|
||||
assert.False(t, ok)
|
||||
})
|
||||
}
|
||||
@@ -8,7 +8,6 @@ import (
|
||||
"github.com/miekg/dns"
|
||||
|
||||
dnsconfig "github.com/netbirdio/netbird/client/internal/dns/config"
|
||||
"github.com/netbirdio/netbird/client/internal/dns/local"
|
||||
nbdns "github.com/netbirdio/netbird/dns"
|
||||
"github.com/netbirdio/netbird/route"
|
||||
"github.com/netbirdio/netbird/shared/management/domain"
|
||||
@@ -93,11 +92,6 @@ func (m *MockServer) SetFirewall(Firewall) {
|
||||
// Mock implementation - no-op
|
||||
}
|
||||
|
||||
// SetPeerActivator mock implementation of SetPeerActivator from Server interface
|
||||
func (m *MockServer) SetPeerActivator(local.PeerActivator) {
|
||||
// Mock implementation - no-op
|
||||
}
|
||||
|
||||
// BeginBatch mock implementation of BeginBatch from Server interface
|
||||
func (m *MockServer) BeginBatch() {
|
||||
// Mock implementation - no-op
|
||||
|
||||
@@ -82,7 +82,6 @@ type Server interface {
|
||||
PopulateManagementDomain(mgmtURL *url.URL) error
|
||||
SetRouteSources(selected, active func() route.HAMap)
|
||||
SetFirewall(Firewall)
|
||||
SetPeerActivator(local.PeerActivator)
|
||||
}
|
||||
|
||||
type nsGroupsByDomain struct {
|
||||
@@ -492,13 +491,6 @@ func (s *DefaultServer) SetFirewall(fw Firewall) {
|
||||
}
|
||||
}
|
||||
|
||||
// SetPeerActivator wires the DNS-time lazy-connection warm-up on the local
|
||||
// resolver. Injected after the connection manager exists (it does not at
|
||||
// DNS-server construction time). Pass nil to disable.
|
||||
func (s *DefaultServer) SetPeerActivator(a local.PeerActivator) {
|
||||
s.localResolver.SetPeerActivator(a)
|
||||
}
|
||||
|
||||
// Stop stops the server
|
||||
func (s *DefaultServer) Stop() {
|
||||
s.ctxCancel()
|
||||
@@ -1443,11 +1435,11 @@ type localPeerConnectivity struct {
|
||||
|
||||
// IsConnectedByIP looks the IP up in the peerstore and surfaces both
|
||||
// the known and connected bits. Used by Resolver.filterDisconnectedPeerAnswers.
|
||||
func (l localPeerConnectivity) IsConnectedByIP(ip netip.Addr) (known, connected bool) {
|
||||
func (l localPeerConnectivity) IsConnectedByIP(ip string) (known, connected bool) {
|
||||
if l.status == nil {
|
||||
return false, false
|
||||
}
|
||||
state, ok := l.status.PeerStateByIP(ip.String())
|
||||
state, ok := l.status.PeerStateByIP(ip)
|
||||
if !ok {
|
||||
return false, false
|
||||
}
|
||||
|
||||
@@ -1,76 +0,0 @@
|
||||
package internal
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/netip"
|
||||
"time"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/peer"
|
||||
"github.com/netbirdio/netbird/client/internal/peerstore"
|
||||
)
|
||||
|
||||
const dnsActivationPollInterval = 50 * time.Millisecond
|
||||
|
||||
// dnsPeerActivator wakes lazy-connection peers from the DNS resolution path. It
|
||||
// implements dns/local.PeerActivator. DNS queries run on their own goroutines,
|
||||
// so it only touches state that is safe for concurrent use — ConnMgr.ActivatePeer,
|
||||
// peerstore.Store and peer.Status — and never takes the engine's syncMsgMux,
|
||||
// keeping DNS resolution from contending with network-map processing.
|
||||
type dnsPeerActivator struct {
|
||||
connMgr *ConnMgr
|
||||
peerStore *peerstore.Store
|
||||
status *peer.Status
|
||||
// ctx is the engine's long-lived context. The connection dial is tied to it
|
||||
// (not the per-query DNS wait budget) so a handshake that outlasts the wait
|
||||
// still completes in the background rather than being cancelled at the deadline.
|
||||
ctx context.Context
|
||||
}
|
||||
|
||||
// ActivatePeersByIP triggers wake-up for the peer(s) owning addrs and waits
|
||||
// until one is connected or ctx (the per-query DNS wait budget) expires.
|
||||
// Activation itself is tied to the engine's long-lived context so the dial
|
||||
// survives a wait that times out. Unknown or already-connected addresses are
|
||||
// skipped, so the steady-state (warm) path adds no latency.
|
||||
func (a *dnsPeerActivator) ActivatePeersByIP(ctx context.Context, addrs []netip.Addr) {
|
||||
if a == nil || a.connMgr == nil {
|
||||
return
|
||||
}
|
||||
|
||||
var pending []string
|
||||
for _, addr := range addrs {
|
||||
ip := addr.String()
|
||||
st, ok := a.status.PeerStateByIP(ip)
|
||||
if !ok || st.ConnStatus == peer.StatusConnected {
|
||||
continue
|
||||
}
|
||||
conn, ok := a.peerStore.PeerConn(st.PubKey)
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
a.connMgr.ActivatePeer(a.ctx, conn)
|
||||
pending = append(pending, ip)
|
||||
}
|
||||
|
||||
if len(pending) == 0 {
|
||||
return
|
||||
}
|
||||
a.waitConnected(ctx, pending)
|
||||
}
|
||||
|
||||
// waitConnected blocks until any of ips reports a connected peer or ctx expires.
|
||||
func (a *dnsPeerActivator) waitConnected(ctx context.Context, ips []string) {
|
||||
ticker := time.NewTicker(dnsActivationPollInterval)
|
||||
defer ticker.Stop()
|
||||
for {
|
||||
for _, ip := range ips {
|
||||
if st, ok := a.status.PeerStateByIP(ip); ok && st.ConnStatus == peer.StatusConnected {
|
||||
return
|
||||
}
|
||||
}
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return
|
||||
case <-ticker.C:
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,129 +0,0 @@
|
||||
package internal
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/stretchr/testify/require"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/peer"
|
||||
"github.com/netbirdio/netbird/client/internal/peerstore"
|
||||
)
|
||||
|
||||
func newTestPeerConn(t *testing.T, key string) *peer.Conn {
|
||||
t.Helper()
|
||||
conn, err := peer.NewConn(peer.ConnConfig{
|
||||
Key: key,
|
||||
LocalKey: "local",
|
||||
WgConfig: peer.WgConfig{
|
||||
AllowedIps: []netip.Prefix{netip.MustParsePrefix("100.64.0.1/32")},
|
||||
},
|
||||
}, peer.ServiceDependencies{})
|
||||
require.NoError(t, err)
|
||||
return conn
|
||||
}
|
||||
|
||||
func newTestDNSPeerActivator(t *testing.T) (*dnsPeerActivator, *peer.Status, *peerstore.Store) {
|
||||
t.Helper()
|
||||
status := peer.NewRecorder("https://mgm")
|
||||
store := peerstore.NewConnStore()
|
||||
// ConnMgr without Start: the lazy manager is nil, so ActivatePeer is a
|
||||
// no-op — these tests exercise the activator's skip/wait logic.
|
||||
connMgr := NewConnMgr(&EngineConfig{}, status, store, nil)
|
||||
return &dnsPeerActivator{
|
||||
connMgr: connMgr,
|
||||
peerStore: store,
|
||||
status: status,
|
||||
ctx: context.Background(),
|
||||
}, status, store
|
||||
}
|
||||
|
||||
func TestDNSPeerActivator_NilSafe(t *testing.T) {
|
||||
var a *dnsPeerActivator
|
||||
a.ActivatePeersByIP(context.Background(), []netip.Addr{netip.MustParseAddr("100.64.0.1")})
|
||||
}
|
||||
|
||||
// TestDNSPeerActivator_SkipsUnknownAndConnectedPeers verifies the steady-state
|
||||
// (warm) path adds no latency: already-connected and unknown addresses never
|
||||
// enter the wait loop.
|
||||
func TestDNSPeerActivator_SkipsUnknownAndConnectedPeers(t *testing.T) {
|
||||
a, status, store := newTestDNSPeerActivator(t)
|
||||
|
||||
require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", "fd00::1"))
|
||||
require.NoError(t, status.UpdatePeerState(peer.State{PubKey: "peerA", ConnStatus: peer.StatusConnected}))
|
||||
store.AddPeerConn("peerA", newTestPeerConn(t, "peerA"))
|
||||
|
||||
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
|
||||
defer cancel()
|
||||
|
||||
start := time.Now()
|
||||
a.ActivatePeersByIP(ctx, []netip.Addr{
|
||||
netip.MustParseAddr("100.64.0.1"), // known, connected -> skipped
|
||||
netip.MustParseAddr("fd00::1"), // known via IPv6, connected -> skipped
|
||||
netip.MustParseAddr("100.64.0.99"), // unknown -> skipped
|
||||
})
|
||||
require.Less(t, time.Since(start), time.Second, "no pending peer must mean no wait")
|
||||
}
|
||||
|
||||
// TestDNSPeerActivator_WaitsForPendingPeerToConnect verifies the wait loop
|
||||
// returns as soon as a pending peer reports connected, well before the
|
||||
// per-query budget expires.
|
||||
func TestDNSPeerActivator_WaitsForPendingPeerToConnect(t *testing.T) {
|
||||
a, status, store := newTestDNSPeerActivator(t)
|
||||
|
||||
require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", ""))
|
||||
store.AddPeerConn("peerA", newTestPeerConn(t, "peerA"))
|
||||
|
||||
go func() {
|
||||
time.Sleep(150 * time.Millisecond)
|
||||
_ = status.UpdatePeerState(peer.State{PubKey: "peerA", ConnStatus: peer.StatusConnected})
|
||||
}()
|
||||
|
||||
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
|
||||
defer cancel()
|
||||
|
||||
start := time.Now()
|
||||
a.ActivatePeersByIP(ctx, []netip.Addr{netip.MustParseAddr("100.64.0.1")})
|
||||
elapsed := time.Since(start)
|
||||
|
||||
require.GreaterOrEqual(t, elapsed, 100*time.Millisecond, "must wait for the pending peer")
|
||||
require.Less(t, elapsed, 5*time.Second, "must return on connect, not at the deadline")
|
||||
}
|
||||
|
||||
// TestDNSPeerActivator_ReturnsAtBudgetWhenPeerStaysIdle verifies a peer that
|
||||
// never connects releases the DNS response at the per-query budget instead of
|
||||
// blocking it indefinitely.
|
||||
func TestDNSPeerActivator_ReturnsAtBudgetWhenPeerStaysIdle(t *testing.T) {
|
||||
a, status, store := newTestDNSPeerActivator(t)
|
||||
|
||||
require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", ""))
|
||||
store.AddPeerConn("peerA", newTestPeerConn(t, "peerA"))
|
||||
|
||||
ctx, cancel := context.WithTimeout(context.Background(), 300*time.Millisecond)
|
||||
defer cancel()
|
||||
|
||||
start := time.Now()
|
||||
a.ActivatePeersByIP(ctx, []netip.Addr{netip.MustParseAddr("100.64.0.1")})
|
||||
elapsed := time.Since(start)
|
||||
|
||||
require.GreaterOrEqual(t, elapsed, 250*time.Millisecond, "must wait out the budget for a pending peer")
|
||||
require.Less(t, elapsed, 5*time.Second, "must not block past the budget")
|
||||
}
|
||||
|
||||
// TestDNSPeerActivator_NoWaitWithoutPeerConn verifies a known-but-idle peer
|
||||
// with no connection object in the store is not waited on: there is nothing to
|
||||
// activate, so waiting could only ever time out.
|
||||
func TestDNSPeerActivator_NoWaitWithoutPeerConn(t *testing.T) {
|
||||
a, status, _ := newTestDNSPeerActivator(t)
|
||||
|
||||
require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", ""))
|
||||
|
||||
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
|
||||
defer cancel()
|
||||
|
||||
start := time.Now()
|
||||
a.ActivatePeersByIP(ctx, []netip.Addr{netip.MustParseAddr("100.64.0.1")})
|
||||
require.Less(t, time.Since(start), time.Second, "peer without a conn must not be waited on")
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
@@ -52,14 +52,11 @@ int xdp_dns_fwd(struct iphdr *ip, struct udphdr *udp) {
|
||||
|
||||
if (udp->dest == GENERAL_DNS_PORT && ip->daddr == dns_ip) {
|
||||
udp->dest = dns_port;
|
||||
// Clear the now-stale checksum; zero means "not computed" for IPv4.
|
||||
udp->check = 0;
|
||||
return XDP_PASS;
|
||||
}
|
||||
|
||||
if (udp->source == dns_port && ip->saddr == dns_ip) {
|
||||
udp->source = GENERAL_DNS_PORT;
|
||||
udp->check = 0;
|
||||
return XDP_PASS;
|
||||
}
|
||||
|
||||
|
||||
@@ -50,11 +50,5 @@ int xdp_wg_proxy(struct iphdr *ip, struct udphdr *udp) {
|
||||
__be16 new_dst_port = htons(proxy_port);
|
||||
udp->dest = new_dst_port;
|
||||
udp->source = new_src_port;
|
||||
|
||||
// The ports are covered by the UDP checksum. This is an IPv4 loopback hop
|
||||
// and the payload is already integrity-protected, so clear the checksum (a
|
||||
// zero UDP checksum means "not computed" for IPv4) rather than leave a
|
||||
// stale value the kernel would drop as UDP_CSUM.
|
||||
udp->check = 0;
|
||||
return XDP_PASS;
|
||||
}
|
||||
|
||||
@@ -64,10 +64,7 @@ import (
|
||||
"github.com/netbirdio/netbird/route"
|
||||
mgm "github.com/netbirdio/netbird/shared/management/client"
|
||||
"github.com/netbirdio/netbird/shared/management/domain"
|
||||
sharedgrpc "github.com/netbirdio/netbird/shared/management/grpc"
|
||||
nbnetworkmap "github.com/netbirdio/netbird/shared/management/networkmap"
|
||||
mgmProto "github.com/netbirdio/netbird/shared/management/proto"
|
||||
types "github.com/netbirdio/netbird/shared/management/types"
|
||||
"github.com/netbirdio/netbird/shared/netiputil"
|
||||
auth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
|
||||
relayClient "github.com/netbirdio/netbird/shared/relay/client"
|
||||
@@ -150,7 +147,6 @@ type EngineConfig struct {
|
||||
BlockLANAccess bool
|
||||
BlockInbound bool
|
||||
DisableIPv6 bool
|
||||
SyncMessageVersion *int
|
||||
|
||||
// LazyConnection is the MDM-sourced lazy-connection override; StateUnset defers to
|
||||
// the env var and management feature flag.
|
||||
@@ -224,13 +220,6 @@ type Engine struct {
|
||||
// networkSerial is the latest CurrentSerial (state ID) of the network sent by the Management service
|
||||
networkSerial uint64
|
||||
|
||||
// latestComponents is the most-recent NetworkMapComponents decoded from
|
||||
// a NetworkMapEnvelope (capability=3 peers only). Held alongside the
|
||||
// NetworkMap that Calculate() produced from it so future incremental
|
||||
// updates have a base to apply changes against. nil for legacy-format
|
||||
// peers. Guarded by syncMsgMux.
|
||||
latestComponents *types.NetworkMapComponents
|
||||
|
||||
networkMonitor *networkmonitor.NetworkMonitor
|
||||
|
||||
sshServer sshServer
|
||||
@@ -663,24 +652,8 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
|
||||
iceCfg := e.createICEConfig()
|
||||
|
||||
e.connMgr = NewConnMgr(e.config, e.statusRecorder, e.peerStore, wgIface)
|
||||
e.connMgr.SetRoutedIPsReconciler(func(peerKey string) error {
|
||||
if e.routeManager == nil {
|
||||
return nil
|
||||
}
|
||||
return e.routeManager.ReconcilePeerAllowedIPs(peerKey)
|
||||
})
|
||||
e.connMgr.Start(e.ctx)
|
||||
|
||||
// Wire DNS-time lazy-connection warm-up now that the connection manager
|
||||
// exists (it does not at DNS-server construction time). A DNS answer that
|
||||
// points at an idle peer then wakes it before the client's first request.
|
||||
e.dnsServer.SetPeerActivator(&dnsPeerActivator{
|
||||
connMgr: e.connMgr,
|
||||
peerStore: e.peerStore,
|
||||
status: e.statusRecorder,
|
||||
ctx: e.ctx,
|
||||
})
|
||||
|
||||
e.srWatcher = guard.NewSRWatcher(e.signal, e.relayManager, e.mobileDep.IFaceDiscover, iceCfg)
|
||||
e.srWatcher.Start(peer.IsForceRelayed())
|
||||
|
||||
@@ -990,12 +963,8 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
|
||||
|
||||
e.ApplySessionDeadline(update.GetSessionExpiresAt())
|
||||
|
||||
// Envelope sync responses carry PeerConfig at the top level; legacy
|
||||
// NetworkMap syncs carry it under NetworkMap.PeerConfig.
|
||||
if pc := update.GetPeerConfig(); pc != nil {
|
||||
e.handleAutoUpdateVersion(pc.GetAutoUpdate())
|
||||
} else if nm := update.GetNetworkMap(); nm != nil && nm.GetPeerConfig() != nil {
|
||||
e.handleAutoUpdateVersion(nm.GetPeerConfig().GetAutoUpdate())
|
||||
if update.NetworkMap != nil && update.NetworkMap.PeerConfig != nil {
|
||||
e.handleAutoUpdateVersion(update.NetworkMap.PeerConfig.AutoUpdate)
|
||||
}
|
||||
|
||||
done := e.phase("netbird_config")
|
||||
@@ -1005,47 +974,12 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
|
||||
return err
|
||||
}
|
||||
|
||||
// Decode the network map from either the components envelope or the
|
||||
// legacy proto.NetworkMap before the posture-check gating below, so the
|
||||
// "is there a network map" decision covers both wire shapes.
|
||||
var (
|
||||
nm *mgmProto.NetworkMap
|
||||
components *types.NetworkMapComponents
|
||||
)
|
||||
if version := update.GetVersion(); version == int32(sharedgrpc.ComponentNetworkMap) {
|
||||
// Components-format peer: decode the envelope back to typed
|
||||
// components, run Calculate() locally, and convert to the wire
|
||||
// NetworkMap shape the rest of the engine consumes. Components are
|
||||
// retained so future incremental updates can apply deltas instead
|
||||
// of doing a full reconstruction.
|
||||
envelope := update.GetNetworkMapEnvelope()
|
||||
if envelope == nil {
|
||||
return fmt.Errorf("received a SyncReponse indicating use of components network map, but components are missing")
|
||||
}
|
||||
|
||||
localKey := e.config.WgPrivateKey.PublicKey().String()
|
||||
dnsName := ""
|
||||
if pc := update.GetPeerConfig(); pc != nil {
|
||||
// PeerConfig.Fqdn = "<dns_label>.<dns_domain>" — extract the
|
||||
// shared domain by stripping the peer's own label prefix. Falls
|
||||
// back to empty if the FQDN doesn't have the expected shape.
|
||||
dnsName = extractDNSDomainFromFQDN(pc.GetFqdn())
|
||||
}
|
||||
result, err := nbnetworkmap.EnvelopeToNetworkMap(e.ctx, envelope, localKey, dnsName)
|
||||
if err != nil {
|
||||
return fmt.Errorf("decode network map envelope: %w", err)
|
||||
}
|
||||
nm = result.NetworkMap
|
||||
components = result.Components
|
||||
} else {
|
||||
nm = update.GetNetworkMap()
|
||||
}
|
||||
|
||||
// Posture checks are bound to the network map presence:
|
||||
// NetworkMap != nil, checks present -> apply the received checks
|
||||
// NetworkMap != nil, checks nil -> posture checks were removed, clear them
|
||||
// NetworkMap == nil -> config-only update (e.g. relay token rotation),
|
||||
// leave the previously applied checks untouched
|
||||
nm := update.GetNetworkMap()
|
||||
if nm == nil {
|
||||
return nil
|
||||
}
|
||||
@@ -1058,14 +992,6 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
|
||||
}
|
||||
|
||||
done = e.phase("persist")
|
||||
// Only retain the components view when the server sent the envelope
|
||||
// path. A legacy proto.NetworkMap means components == nil; writing it
|
||||
// here would clobber a previously-cached snapshot, breaking the
|
||||
// incremental-delta base on a future envelope sync.
|
||||
if components != nil {
|
||||
e.latestComponents = components
|
||||
}
|
||||
|
||||
e.persistSyncResponse(update)
|
||||
done()
|
||||
|
||||
@@ -1079,19 +1005,6 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// extractDNSDomainFromFQDN returns the trailing dotted domain part of the
|
||||
// receiving peer's FQDN — the same value the management server fills as
|
||||
// dnsName when it builds the legacy NetworkMap. "peer42.netbird.cloud" →
|
||||
// "netbird.cloud". An empty string is returned for unrecognized formats.
|
||||
func extractDNSDomainFromFQDN(fqdn string) string {
|
||||
for i := 0; i < len(fqdn); i++ {
|
||||
if fqdn[i] == '.' && i+1 < len(fqdn) {
|
||||
return fqdn[i+1:]
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// updateNetbirdConfig applies the management-provided NetBird configuration:
|
||||
// STUN/TURN and relay servers, flow logging and DNS settings. A nil config is a no-op,
|
||||
// which is the case for sync updates carrying only a network map.
|
||||
@@ -1251,7 +1164,6 @@ func (e *Engine) applyInfoFlags(info *system.Info) {
|
||||
e.config.BlockLANAccess,
|
||||
e.config.BlockInbound,
|
||||
e.config.DisableIPv6,
|
||||
e.config.SyncMessageVersion,
|
||||
e.config.EnableSSHRoot,
|
||||
e.config.EnableSSHSFTP,
|
||||
e.config.EnableSSHLocalPortForwarding,
|
||||
@@ -2120,7 +2032,6 @@ func (e *Engine) readInitialSettings() ([]*route.Route, *nbdns.Config, bool, err
|
||||
e.config.BlockLANAccess,
|
||||
e.config.BlockInbound,
|
||||
e.config.DisableIPv6,
|
||||
e.config.SyncMessageVersion,
|
||||
e.config.EnableSSHRoot,
|
||||
e.config.EnableSSHSFTP,
|
||||
e.config.EnableSSHLocalPortForwarding,
|
||||
|
||||
@@ -75,14 +75,4 @@ func TestApplySessionDeadline_ThreeState(t *testing.T) {
|
||||
require.True(t, e.statusRecorder.GetSessionExpiresAt().IsZero(),
|
||||
"invalid timestamp must clear the deadline")
|
||||
})
|
||||
|
||||
t.Run("recently expired timestamp stays visible as expired", func(t *testing.T) {
|
||||
e := newEngine()
|
||||
expired := time.Now().Add(-5 * time.Minute).UTC().Truncate(time.Second)
|
||||
|
||||
e.ApplySessionDeadline(timestamppb.New(expired))
|
||||
|
||||
require.True(t, e.statusRecorder.GetSessionExpiresAt().Equal(expired),
|
||||
"recently-expired deadline must stay on the recorder so consumers render it as expired")
|
||||
})
|
||||
}
|
||||
|
||||
@@ -1,31 +0,0 @@
|
||||
//go:build !linux && !darwin && !freebsd && !windows
|
||||
|
||||
package ipcauth
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"net"
|
||||
|
||||
"google.golang.org/grpc/credentials"
|
||||
)
|
||||
|
||||
// errUnsupported is returned on platforms with no local peer-identity
|
||||
// primitive, so consumers fail closed instead of guessing an identity.
|
||||
var errUnsupported = errors.New("peer identity is not available on this platform")
|
||||
|
||||
// NewTransportCredentials returns nil: without a peer-identity primitive the
|
||||
// daemon cannot authenticate local callers, and the caller must treat that as
|
||||
// "authorization cannot be enforced".
|
||||
func NewTransportCredentials() credentials.TransportCredentials {
|
||||
return nil
|
||||
}
|
||||
|
||||
// PeerIdentity always fails on this platform.
|
||||
func PeerIdentity(net.Conn) (Identity, error) {
|
||||
return Identity{}, errUnsupported
|
||||
}
|
||||
|
||||
// ConnIdentity always fails on this platform.
|
||||
func ConnIdentity(net.Conn) (Identity, error) {
|
||||
return Identity{}, errUnsupported
|
||||
}
|
||||
@@ -1,56 +0,0 @@
|
||||
//go:build linux || darwin || freebsd
|
||||
|
||||
package ipcauth
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net"
|
||||
|
||||
"google.golang.org/grpc/credentials"
|
||||
)
|
||||
|
||||
// NewTransportCredentials returns gRPC transport credentials that expose the
|
||||
// caller's kernel-authenticated identity via IdentityFromContext. It returns
|
||||
// nil on platforms that have no peer-identity primitive, which the caller must
|
||||
// treat as "authorization cannot be enforced".
|
||||
//
|
||||
// The handshake exchanges no bytes on the wire, so a client dialing with
|
||||
// insecure credentials interoperates with a server using these. That keeps
|
||||
// older CLI and UI binaries working against an upgraded daemon.
|
||||
func NewTransportCredentials() credentials.TransportCredentials {
|
||||
return unixCreds{}
|
||||
}
|
||||
|
||||
// ConnIdentity extracts the caller's identity from an accepted local IPC
|
||||
// connection. It is shared by the gRPC transport credentials and by the JSON
|
||||
// gateway, which reads the identity of its own HTTP clients.
|
||||
func ConnIdentity(conn net.Conn) (Identity, error) {
|
||||
return PeerIdentity(conn)
|
||||
}
|
||||
|
||||
type unixCreds struct{}
|
||||
|
||||
func (unixCreds) ClientHandshake(_ context.Context, _ string, conn net.Conn) (net.Conn, credentials.AuthInfo, error) {
|
||||
return conn, AuthInfo{}, nil
|
||||
}
|
||||
|
||||
// ServerHandshake extracts the peer identity and fails closed when it cannot
|
||||
// be read, so a connection whose caller is unknown never reaches a handler.
|
||||
func (unixCreds) ServerHandshake(conn net.Conn) (net.Conn, credentials.AuthInfo, error) {
|
||||
id, err := ConnIdentity(conn)
|
||||
if err != nil {
|
||||
return nil, nil, err
|
||||
}
|
||||
return conn, AuthInfo{
|
||||
CommonAuthInfo: credentials.CommonAuthInfo{SecurityLevel: credentials.NoSecurity},
|
||||
Identity: id,
|
||||
}, nil
|
||||
}
|
||||
|
||||
func (unixCreds) Info() credentials.ProtocolInfo {
|
||||
return credentials.ProtocolInfo{SecurityProtocol: AuthInfo{}.AuthType()}
|
||||
}
|
||||
|
||||
func (unixCreds) Clone() credentials.TransportCredentials { return unixCreds{} }
|
||||
|
||||
func (unixCreds) OverrideServerName(string) error { return nil }
|
||||
@@ -1,194 +0,0 @@
|
||||
//go:build windows
|
||||
|
||||
package ipcauth
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"net"
|
||||
"runtime"
|
||||
|
||||
log "github.com/sirupsen/logrus"
|
||||
"golang.org/x/sys/windows"
|
||||
"google.golang.org/grpc/credentials"
|
||||
)
|
||||
|
||||
var (
|
||||
modadvapi32 = windows.NewLazySystemDLL("advapi32.dll")
|
||||
procImpersonateNamedPipeClient = modadvapi32.NewProc("ImpersonateNamedPipeClient")
|
||||
)
|
||||
|
||||
// DefaultPipeSDDL is the security descriptor for the daemon control pipe.
|
||||
//
|
||||
// D:P protected DACL, no inheritance
|
||||
// (A;;GA;;;SY) allow GENERIC_ALL to LocalSystem (the daemon's service account)
|
||||
// (A;;GA;;;WD) allow GENERIC_ALL to Everyone
|
||||
//
|
||||
// Any local caller may connect, as with a Unix socket at 0666; what a caller may
|
||||
// actually do is decided from its token, not from the DACL. Remote callers are not
|
||||
// a concern here: winio.ListenPipe creates the pipe with
|
||||
// FILE_PIPE_REJECT_REMOTE_CLIENTS, so NPFS rejects connections from other machines
|
||||
// before the descriptor is consulted.
|
||||
//
|
||||
// A deny ACE on the NETWORK SID would not add anything and would break callers:
|
||||
// that SID is present in any network-logon token, which includes OpenSSH and WinRM
|
||||
// sessions, so it denies administrators driving the CLI over SSH and denies the
|
||||
// daemon itself when started from such a session.
|
||||
func DefaultPipeSDDL() string {
|
||||
return "D:P(A;;GA;;;SY)(A;;GA;;;WD)"
|
||||
}
|
||||
|
||||
// NewTransportCredentials returns gRPC transport credentials that derive the
|
||||
// caller's identity from the named-pipe client token.
|
||||
//
|
||||
// The client must connect at SECURITY_IDENTIFICATION for the daemon to be able
|
||||
// to read its token, which is what DialNamedPipe does.
|
||||
func NewTransportCredentials() credentials.TransportCredentials {
|
||||
return winpipeCreds{}
|
||||
}
|
||||
|
||||
// ConnIdentity extracts the caller's identity from an accepted named-pipe
|
||||
// connection by impersonating the pipe client and reading its token. It is
|
||||
// shared by the gRPC transport credentials and by the JSON gateway, which
|
||||
// reads the identity of its own HTTP clients.
|
||||
func ConnIdentity(conn net.Conn) (Identity, error) {
|
||||
// go-winio's pipe connection embeds *win32File, which exposes Fd().
|
||||
fdConn, ok := conn.(interface{ Fd() uintptr })
|
||||
if !ok {
|
||||
return Identity{}, fmt.Errorf("connection %T does not expose a pipe handle", conn)
|
||||
}
|
||||
return pipeClientIdentity(windows.Handle(fdConn.Fd()))
|
||||
}
|
||||
|
||||
type winpipeCreds struct{}
|
||||
|
||||
func (winpipeCreds) ClientHandshake(_ context.Context, _ string, conn net.Conn) (net.Conn, credentials.AuthInfo, error) {
|
||||
return conn, AuthInfo{}, nil
|
||||
}
|
||||
|
||||
// ServerHandshake extracts the connecting client's identity and fails closed
|
||||
// when the handle or token cannot be read, so a connection whose caller is
|
||||
// unknown never reaches a handler.
|
||||
func (winpipeCreds) ServerHandshake(conn net.Conn) (net.Conn, credentials.AuthInfo, error) {
|
||||
id, err := ConnIdentity(conn)
|
||||
if err != nil {
|
||||
return nil, nil, err
|
||||
}
|
||||
return conn, AuthInfo{
|
||||
CommonAuthInfo: credentials.CommonAuthInfo{SecurityLevel: credentials.NoSecurity},
|
||||
Identity: id,
|
||||
}, nil
|
||||
}
|
||||
|
||||
func (winpipeCreds) Info() credentials.ProtocolInfo {
|
||||
return credentials.ProtocolInfo{SecurityProtocol: AuthInfo{}.AuthType()}
|
||||
}
|
||||
|
||||
func (winpipeCreds) Clone() credentials.TransportCredentials { return winpipeCreds{} }
|
||||
|
||||
func (winpipeCreds) OverrideServerName(string) error { return nil }
|
||||
|
||||
// pipeClientIdentity reads the connecting client's user SID, usable group
|
||||
// SIDs, and elevation state by impersonating the pipe client on this thread
|
||||
// and reading the resulting impersonation token.
|
||||
func pipeClientIdentity(handle windows.Handle) (id Identity, err error) {
|
||||
// Impersonation is per-thread, so the goroutine must stay on this thread
|
||||
// until RevertToSelf, otherwise an unrelated goroutine could inherit the
|
||||
// impersonated context.
|
||||
runtime.LockOSThread()
|
||||
|
||||
// The thread only goes back to the runtime's pool once it is provably no
|
||||
// longer impersonating the client. If the revert fails, leaving it locked
|
||||
// makes Go terminate it when this goroutine exits, which costs one thread
|
||||
// and keeps a thread running as the client from ever being reused.
|
||||
clean := false
|
||||
defer func() {
|
||||
if clean {
|
||||
runtime.UnlockOSThread()
|
||||
}
|
||||
}()
|
||||
|
||||
if err = impersonateNamedPipeClient(handle); err != nil {
|
||||
clean = true
|
||||
return Identity{}, fmt.Errorf("impersonate named pipe client: %w", err)
|
||||
}
|
||||
defer func() {
|
||||
// Surface the revert failure only when nothing else failed: leaving
|
||||
// the thread impersonated is worse than the original error.
|
||||
revErr := windows.RevertToSelf()
|
||||
if revErr != nil {
|
||||
if err == nil {
|
||||
err = fmt.Errorf("revert impersonation: %w", revErr)
|
||||
}
|
||||
return
|
||||
}
|
||||
clean = true
|
||||
}()
|
||||
|
||||
// openAsSelf=true opens the token with the daemon's own process context
|
||||
// rather than the impersonated client's, so the open cannot fail because
|
||||
// the client lacks access to its own token.
|
||||
var token windows.Token
|
||||
if err = windows.OpenThreadToken(windows.CurrentThread(), windows.TOKEN_QUERY, true, &token); err != nil {
|
||||
return Identity{}, fmt.Errorf("open thread token: %w", err)
|
||||
}
|
||||
defer func() {
|
||||
if cerr := token.Close(); cerr != nil {
|
||||
log.Debugf("close client token: %v", cerr)
|
||||
}
|
||||
}()
|
||||
|
||||
return identityFromToken(token)
|
||||
}
|
||||
|
||||
// identityFromToken reads the user SID, usable group SIDs and elevation state
|
||||
// out of a Windows token.
|
||||
func identityFromToken(token windows.Token) (Identity, error) {
|
||||
user, err := token.GetTokenUser()
|
||||
if err != nil {
|
||||
return Identity{}, fmt.Errorf("read token user: %w", err)
|
||||
}
|
||||
|
||||
groups, err := tokenGroupSIDs(token)
|
||||
if err != nil {
|
||||
return Identity{}, err
|
||||
}
|
||||
|
||||
return Identity{
|
||||
SID: user.User.Sid.String(),
|
||||
Groups: groups,
|
||||
Elevated: token.IsElevated(),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// tokenGroupSIDs returns the SIDs of the groups the token can actually
|
||||
// exercise. Groups that are disabled or marked deny-only are skipped: a
|
||||
// UAC-filtered administrator carries BUILTIN\Administrators as deny-only, and
|
||||
// treating that as membership would hand every admin account privilege it
|
||||
// cannot currently use.
|
||||
func tokenGroupSIDs(token windows.Token) ([]string, error) {
|
||||
tg, err := token.GetTokenGroups()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("read token groups: %w", err)
|
||||
}
|
||||
|
||||
var sids []string
|
||||
for _, g := range tg.AllGroups() {
|
||||
if g.Attributes&windows.SE_GROUP_ENABLED == 0 {
|
||||
continue
|
||||
}
|
||||
if g.Attributes&windows.SE_GROUP_USE_FOR_DENY_ONLY != 0 {
|
||||
continue
|
||||
}
|
||||
sids = append(sids, g.Sid.String())
|
||||
}
|
||||
return sids, nil
|
||||
}
|
||||
|
||||
func impersonateNamedPipeClient(h windows.Handle) error {
|
||||
r, _, e := procImpersonateNamedPipeClient.Call(uintptr(h))
|
||||
if r == 0 {
|
||||
return e
|
||||
}
|
||||
return nil
|
||||
}
|
||||
@@ -1,272 +0,0 @@
|
||||
package ipcauth
|
||||
|
||||
import (
|
||||
"context"
|
||||
"crypto/rand"
|
||||
"crypto/subtle"
|
||||
"encoding/hex"
|
||||
"fmt"
|
||||
"slices"
|
||||
"strconv"
|
||||
"strings"
|
||||
|
||||
"google.golang.org/grpc/metadata"
|
||||
)
|
||||
|
||||
// Metadata keys the local JSON gateway uses to forward the identity of its own
|
||||
// HTTP client to the daemon. The gateway runs inside the daemon process and
|
||||
// re-dials the daemon over the control socket, so without forwarding every
|
||||
// JSON request would appear to come from the daemon itself.
|
||||
const (
|
||||
// mdFwd marks a request as forwarded by the JSON gateway. It is always
|
||||
// set, even when the gateway could not read its client's identity, so the
|
||||
// daemon can tell "no identity available" apart from "not forwarded".
|
||||
mdFwd = "x-netbird-fwd"
|
||||
mdFwdUID = "x-netbird-fwd-uid" // Unix user ID
|
||||
mdFwdGID = "x-netbird-fwd-gid" // Unix primary group ID
|
||||
mdFwdSID = "x-netbird-fwd-sid" // Windows user SID
|
||||
mdFwdGroup = "x-netbird-fwd-group" // Windows group SID, repeated
|
||||
mdFwdElevated = "x-netbird-fwd-elevated" // Windows, "1" when elevated
|
||||
|
||||
// mdFwdProof proves the forwarded identity was stamped by this process. The
|
||||
// gateway runs inside the daemon, so a secret held in memory is available to
|
||||
// the only legitimate producer and to nothing else.
|
||||
mdFwdProof = "x-netbird-fwd-proof"
|
||||
)
|
||||
|
||||
// forwardKeys is every metadata key the gateway sets. An HTTP client must never
|
||||
// be able to supply one itself: see IsReservedForwardKey.
|
||||
var forwardKeys = []string{mdFwd, mdFwdUID, mdFwdGID, mdFwdSID, mdFwdGroup, mdFwdElevated, mdFwdProof}
|
||||
|
||||
// forwardProof authenticates the gateway's forwarding metadata. It is generated
|
||||
// once per daemon process and never leaves it: it is not written to disk, not
|
||||
// logged, and not sent anywhere except over the daemon's own control socket to
|
||||
// itself.
|
||||
//
|
||||
// Without it, trusting a forwarded identity rests on every layer in front of it
|
||||
// stripping incoming forwarding keys, and on each key's value shape being
|
||||
// distinguishable from an injected one. A single injected group SID or an
|
||||
// injected "elevated" flag has the same shape as a legitimate one, so no
|
||||
// cardinality rule can catch it. Requiring the proof means metadata that did not
|
||||
// come from this process is refused whatever it contains.
|
||||
var forwardProof = mustForwardProof()
|
||||
|
||||
func mustForwardProof() string {
|
||||
var buf [32]byte
|
||||
if _, err := rand.Read(buf[:]); err != nil {
|
||||
// Continuing would leave the forwarded path authenticated by a
|
||||
// predictable value, which is worse than not starting.
|
||||
panic(fmt.Sprintf("generate identity forwarding proof: %v", err))
|
||||
}
|
||||
return hex.EncodeToString(buf[:])
|
||||
}
|
||||
|
||||
// IsReservedForwardKey reports whether a gRPC metadata key belongs to the
|
||||
// gateway's identity forwarding, and therefore must be dropped when it arrives
|
||||
// from outside.
|
||||
//
|
||||
// grpc-gateway maps "Grpc-Metadata-<key>" request headers into gRPC metadata and
|
||||
// joins them ahead of the values its own annotators add. Without dropping these,
|
||||
// an HTTP client could hand the daemon "x-netbird-fwd-uid: 0" and be believed,
|
||||
// because the daemon trusts forwarded metadata when the transport peer is the
|
||||
// (privileged) gateway.
|
||||
func IsReservedForwardKey(key string) bool {
|
||||
key = strings.ToLower(key)
|
||||
return slices.Contains(forwardKeys, key)
|
||||
}
|
||||
|
||||
// ForwardIdentityMetadata encodes an HTTP client's identity for the JSON
|
||||
// gateway to forward to the daemon. When known is false only the marker is
|
||||
// set, which makes the daemon treat the caller as unidentified rather than as
|
||||
// the daemon itself.
|
||||
func ForwardIdentityMetadata(id Identity, known bool) metadata.MD {
|
||||
md := metadata.MD{}
|
||||
md.Set(mdFwd, "1")
|
||||
md.Set(mdFwdProof, forwardProof)
|
||||
if !known {
|
||||
return md
|
||||
}
|
||||
|
||||
if id.IsWindows() {
|
||||
md.Set(mdFwdSID, id.SID)
|
||||
if len(id.Groups) > 0 {
|
||||
md.Set(mdFwdGroup, id.Groups...)
|
||||
}
|
||||
if id.Elevated {
|
||||
md.Set(mdFwdElevated, "1")
|
||||
}
|
||||
return md
|
||||
}
|
||||
|
||||
md.Set(mdFwdUID, strconv.FormatUint(uint64(id.UID), 10))
|
||||
md.Set(mdFwdGID, strconv.FormatUint(uint64(id.GID), 10))
|
||||
return md
|
||||
}
|
||||
|
||||
// CallerIdentity returns the identity to authorize a request against. For a
|
||||
// direct connection that is the transport peer's kernel identity. For a
|
||||
// request relayed by the local JSON gateway it is the identity the gateway
|
||||
// forwarded, since the transport peer is then the daemon itself.
|
||||
//
|
||||
// A forwarded identity is only honoured when the transport peer is the daemon's
|
||||
// own identity and the metadata carries this process's forwarding proof, so
|
||||
// forged forwarding metadata gains a caller nothing. A forwarded request that
|
||||
// carries no identity is reported as unidentified, never as the daemon.
|
||||
//
|
||||
// The second return value is false when no identity could be established, and
|
||||
// callers MUST fail closed in that case.
|
||||
func CallerIdentity(ctx context.Context) (Identity, bool) {
|
||||
id, ok := IdentityFromContext(ctx)
|
||||
if !ok {
|
||||
return Identity{}, false
|
||||
}
|
||||
|
||||
// A forwarding key that arrives more than once did not come from the gateway
|
||||
// alone, so nothing about the request can be trusted to describe its caller.
|
||||
// Refusing outright matters because the alternative reading, "not forwarded",
|
||||
// would authorize the request as the transport peer, which on the gateway's
|
||||
// connection is the daemon itself.
|
||||
if duplicatedForwardKey(ctx) {
|
||||
return Identity{}, false
|
||||
}
|
||||
|
||||
forwarded := isForwarded(ctx)
|
||||
|
||||
// Our own process on the other end of the socket is the JSON gateway, the only
|
||||
// thing that dials the daemon from inside it. Such a call must carry a
|
||||
// forwarded identity; without one there is no caller to authorize, and
|
||||
// treating it as the daemon would authorize whatever reached the JSON socket.
|
||||
// Only Linux reports the peer PID, so this is a belt on top of the gateway's
|
||||
// interceptor rather than the sole guarantee.
|
||||
if id.PID != 0 && int(id.PID) == selfPID && !forwarded {
|
||||
return Identity{}, false
|
||||
}
|
||||
|
||||
// Only the gateway's own connection may speak for someone else. Being
|
||||
// privileged is not enough and not the point: the gateway runs inside the
|
||||
// daemon, so it dials as the daemon's identity whatever user that is, which
|
||||
// also covers a rootless container.
|
||||
if !forwarded || !IsDaemonSelf(id) {
|
||||
return id, true
|
||||
}
|
||||
|
||||
// Speaking for someone else additionally requires the proof only this process
|
||||
// holds. Refusing is the only safe reading: the transport peer here is the
|
||||
// daemon itself, so falling back to it would authorize the request as the
|
||||
// daemon. This is also what makes the forwarded values trustworthy once
|
||||
// accepted, so they need no shape checks of their own.
|
||||
if !authenticForward(ctx) {
|
||||
return Identity{}, false
|
||||
}
|
||||
|
||||
return forwardedIdentity(ctx)
|
||||
}
|
||||
|
||||
// duplicatedForwardKey reports whether any forwarding key carries more than one
|
||||
// value. The gateway's interceptor sets each key exactly once and replaces what
|
||||
// was already there, so a repeat means a second source supplied it.
|
||||
func duplicatedForwardKey(ctx context.Context) bool {
|
||||
md, ok := metadata.FromIncomingContext(ctx)
|
||||
if !ok {
|
||||
return false
|
||||
}
|
||||
for _, key := range forwardKeys {
|
||||
// Group SIDs are legitimately repeated; the rest identify the caller.
|
||||
if key == mdFwdGroup {
|
||||
continue
|
||||
}
|
||||
if len(md.Get(key)) > 1 {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// authenticForward reports whether the request carries this process's forwarding
|
||||
// proof, which only the in-process JSON gateway can supply.
|
||||
func authenticForward(ctx context.Context) bool {
|
||||
md, ok := metadata.FromIncomingContext(ctx)
|
||||
if !ok {
|
||||
return false
|
||||
}
|
||||
got := mdSingle(md, mdFwdProof)
|
||||
return subtle.ConstantTimeCompare([]byte(got), []byte(forwardProof)) == 1
|
||||
}
|
||||
|
||||
// isForwarded reports whether the request carries the JSON gateway marker.
|
||||
func isForwarded(ctx context.Context) bool {
|
||||
md, ok := metadata.FromIncomingContext(ctx)
|
||||
if !ok {
|
||||
return false
|
||||
}
|
||||
return mdSingle(md, mdFwd) != ""
|
||||
}
|
||||
|
||||
// forwardedIdentity decodes the identity the JSON gateway attached.
|
||||
func forwardedIdentity(ctx context.Context) (Identity, bool) {
|
||||
md, ok := metadata.FromIncomingContext(ctx)
|
||||
if !ok {
|
||||
return Identity{}, false
|
||||
}
|
||||
|
||||
if sid := mdSingle(md, mdFwdSID); sid != "" {
|
||||
return Identity{
|
||||
SID: sid,
|
||||
// Repeated by design, one value per group, and only reachable once
|
||||
// the forwarding proof has been verified.
|
||||
Groups: md.Get(mdFwdGroup),
|
||||
Elevated: mdSingle(md, mdFwdElevated) == "1",
|
||||
}, true
|
||||
}
|
||||
|
||||
uid, err := strconv.ParseUint(mdSingle(md, mdFwdUID), 10, 32)
|
||||
if err != nil {
|
||||
return Identity{}, false
|
||||
}
|
||||
|
||||
id := Identity{UID: uint32(uid)}
|
||||
if gid, err := strconv.ParseUint(mdSingle(md, mdFwdGID), 10, 32); err == nil {
|
||||
id.GID = uint32(gid)
|
||||
}
|
||||
return id, true
|
||||
}
|
||||
|
||||
// mdSingle returns the value of a forwarded key only when exactly one was
|
||||
// supplied. The gateway's interceptor sets each key exactly once, so more than one
|
||||
// value means something else also supplied it, and the whole identity is treated as
|
||||
// unknown rather than picking a winner. Defence in depth behind the gateway's
|
||||
// header filter.
|
||||
func mdSingle(md metadata.MD, key string) string {
|
||||
if v := md.Get(key); len(v) == 1 {
|
||||
return v[0]
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// WithForwardedIdentity stamps id onto a context's outgoing metadata for the JSON
|
||||
// gateway's call to the daemon, replacing any forwarding keys already present so
|
||||
// values supplied from outside cannot survive alongside it.
|
||||
//
|
||||
// This is deliberately not done with runtime.WithMetadata: grpc-gateway skips its
|
||||
// annotators entirely when no request header maps to metadata ("if len(pairs) == 0
|
||||
// { return ctx, nil, nil }", runtime/context.go), which an HTTP/1.0 request with no
|
||||
// Host header over a unix socket achieves. The daemon would then see an unmarked
|
||||
// call whose transport peer is the daemon's own identity, and authorize it as the
|
||||
// daemon. A client interceptor runs for every RPC regardless of headers.
|
||||
func WithForwardedIdentity(ctx context.Context, id Identity, known bool) context.Context {
|
||||
md, ok := metadata.FromOutgoingContext(ctx)
|
||||
if !ok {
|
||||
md = metadata.MD{}
|
||||
} else {
|
||||
md = md.Copy()
|
||||
}
|
||||
|
||||
for _, key := range forwardKeys {
|
||||
delete(md, key)
|
||||
}
|
||||
for key, values := range ForwardIdentityMetadata(id, known) {
|
||||
md[key] = values
|
||||
}
|
||||
|
||||
return metadata.NewOutgoingContext(ctx, md)
|
||||
}
|
||||
@@ -1,214 +0,0 @@
|
||||
package ipcauth
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
|
||||
"google.golang.org/grpc/credentials"
|
||||
"google.golang.org/grpc/metadata"
|
||||
"google.golang.org/grpc/peer"
|
||||
)
|
||||
|
||||
// transportCtx builds a request context as the daemon's transport credentials
|
||||
// would: the identity of whoever opened the socket, plus whatever metadata the
|
||||
// request carried.
|
||||
func transportCtx(id Identity, md metadata.MD) context.Context {
|
||||
ctx := peer.NewContext(context.Background(), &peer.Peer{
|
||||
AuthInfo: AuthInfo{
|
||||
CommonAuthInfo: credentials.CommonAuthInfo{SecurityLevel: credentials.NoSecurity},
|
||||
Identity: id,
|
||||
},
|
||||
})
|
||||
if md != nil {
|
||||
ctx = metadata.NewIncomingContext(ctx, md)
|
||||
}
|
||||
return ctx
|
||||
}
|
||||
|
||||
var (
|
||||
root = Identity{UID: 0}
|
||||
unprivUser = Identity{UID: 1000, GID: 1000}
|
||||
)
|
||||
|
||||
// asDaemon pins which identity counts as this process for the duration of a test.
|
||||
// Without it the test binary's own uid decides, which silently changes what
|
||||
// "the gateway" means.
|
||||
func asDaemon(t *testing.T, id Identity) {
|
||||
t.Helper()
|
||||
prevID, prevKnown, prevDelegate := selfIdentity, selfKnown, selfMayDelegate
|
||||
t.Cleanup(func() { selfIdentity, selfKnown, selfMayDelegate = prevID, prevKnown, prevDelegate })
|
||||
selfIdentity, selfKnown = id, true
|
||||
selfMayDelegate = !id.IsPrivileged()
|
||||
}
|
||||
|
||||
func TestCallerIdentity_DirectConnections(t *testing.T) {
|
||||
t.Run("no transport credentials is not an identity", func(t *testing.T) {
|
||||
if _, ok := CallerIdentity(context.Background()); ok {
|
||||
t.Fatal("a caller with no credentials must not be identified")
|
||||
}
|
||||
})
|
||||
|
||||
t.Run("a direct caller is its transport identity", func(t *testing.T) {
|
||||
id, ok := CallerIdentity(transportCtx(unprivUser, nil))
|
||||
if !ok || id.UID != 1000 {
|
||||
t.Fatalf("got %v ok=%t, want uid 1000", id, ok)
|
||||
}
|
||||
})
|
||||
|
||||
// The whole point of honouring forwarded metadata only from a privileged
|
||||
// transport peer: an unprivileged caller can set any metadata it likes on its
|
||||
// own connection to the daemon socket.
|
||||
t.Run("an unprivileged caller cannot forge an identity", func(t *testing.T) {
|
||||
asDaemon(t, root)
|
||||
forged := metadata.Pairs(mdFwd, "1", mdFwdUID, "0", mdFwdGID, "0")
|
||||
id, ok := CallerIdentity(transportCtx(unprivUser, forged))
|
||||
if !ok {
|
||||
t.Fatal("caller should still be identified, as itself")
|
||||
}
|
||||
if id.IsPrivileged() || id.UID != 1000 {
|
||||
t.Fatalf("forged metadata was believed: got %v", id)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
func TestCallerIdentity_GatewayForwarding(t *testing.T) {
|
||||
t.Run("the gateway's client identity is used, not the gateway's own", func(t *testing.T) {
|
||||
asDaemon(t, root)
|
||||
md := ForwardIdentityMetadata(unprivUser, true)
|
||||
id, ok := CallerIdentity(transportCtx(root, md))
|
||||
if !ok {
|
||||
t.Fatal("forwarded identity should be usable")
|
||||
}
|
||||
if id.IsPrivileged() || id.UID != 1000 {
|
||||
t.Fatalf("got %v, want the forwarded uid 1000 and not privileged", id)
|
||||
}
|
||||
})
|
||||
|
||||
t.Run("a privileged gateway client stays privileged", func(t *testing.T) {
|
||||
asDaemon(t, root)
|
||||
md := ForwardIdentityMetadata(root, true)
|
||||
id, ok := CallerIdentity(transportCtx(root, md))
|
||||
if !ok || !id.IsPrivileged() {
|
||||
t.Fatalf("got %v ok=%t, want a privileged identity", id, ok)
|
||||
}
|
||||
})
|
||||
|
||||
// A JSON socket the gateway cannot read peer credentials from (a TCP socket,
|
||||
// say) must not make every request look like the daemon itself.
|
||||
t.Run("an unreadable client identity is unknown, not the daemon", func(t *testing.T) {
|
||||
asDaemon(t, root)
|
||||
md := ForwardIdentityMetadata(Identity{}, false)
|
||||
if _, ok := CallerIdentity(transportCtx(root, md)); ok {
|
||||
t.Fatal("a forwarded request with no identity must not be identified")
|
||||
}
|
||||
})
|
||||
|
||||
// grpc-gateway turns Grpc-Metadata-<key> headers into gRPC metadata and joins
|
||||
// them ahead of its annotators' values. If an HTTP client's header survived
|
||||
// that, this is the shape the daemon would see: the attacker's uid 0 first,
|
||||
// the real uid second. The gateway filters those headers out, and reading a
|
||||
// duplicated key as unknown makes the daemon safe even if it did not.
|
||||
t.Run("a duplicated key from an injected header is not believed", func(t *testing.T) {
|
||||
asDaemon(t, root)
|
||||
md := metadata.MD{}
|
||||
md.Append(mdFwd, "1")
|
||||
md.Append(mdFwdUID, "0") // injected by the HTTP client
|
||||
md.Append(mdFwdUID, "1000") // appended by the gateway's annotator
|
||||
if id, ok := CallerIdentity(transportCtx(root, md)); ok {
|
||||
t.Fatalf("injected uid was accepted: got %v", id)
|
||||
}
|
||||
})
|
||||
|
||||
t.Run("a duplicated marker is not believed either", func(t *testing.T) {
|
||||
asDaemon(t, root)
|
||||
md := metadata.MD{}
|
||||
md.Append(mdFwd, "1")
|
||||
md.Append(mdFwd, "1")
|
||||
md.Append(mdFwdUID, "1000")
|
||||
// A repeated marker must not be read as "not forwarded": that would
|
||||
// authorize the request as the transport peer, which on the gateway's
|
||||
// connection is the daemon itself.
|
||||
if id, ok := CallerIdentity(transportCtx(root, md)); ok {
|
||||
t.Fatalf("a duplicated marker was believed: got %v", id)
|
||||
}
|
||||
})
|
||||
|
||||
// The layers in front of this (the gateway's header matcher, and its
|
||||
// interceptor replacing every forwarding key) are what keep outside metadata
|
||||
// from arriving at all. The proof is what the daemon can check for itself, and
|
||||
// it is the only defence that works for a value whose legitimate shape is
|
||||
// indistinguishable from an injected one: a lone group SID, or "elevated".
|
||||
t.Run("forwarding metadata without this process's proof is refused", func(t *testing.T) {
|
||||
asDaemon(t, root)
|
||||
for name, md := range map[string]metadata.MD{
|
||||
"no proof": metadata.Pairs(mdFwd, "1", mdFwdUID, "0"),
|
||||
"wrong proof": metadata.Pairs(mdFwd, "1", mdFwdUID, "0", mdFwdProof, "deadbeef"),
|
||||
"windows identity without a proof": metadata.Pairs(mdFwd, "1",
|
||||
mdFwdSID, "S-1-5-21-1-2-3-1001", mdFwdGroup, sidAdministrators, mdFwdElevated, "1"),
|
||||
} {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
if id, ok := CallerIdentity(transportCtx(root, md)); ok {
|
||||
t.Fatalf("unstamped forwarding metadata was believed: got %v", id)
|
||||
}
|
||||
})
|
||||
}
|
||||
})
|
||||
|
||||
// A caller that reaches the gateway cannot see the proof, so it cannot append
|
||||
// a group of its own to a genuine forwarded identity: doing so would have to
|
||||
// go through the interceptor, which replaces the whole set.
|
||||
t.Run("a group appended to a stamped identity does not survive the interceptor", func(t *testing.T) {
|
||||
asDaemon(t, root)
|
||||
injected := metadata.MD{}
|
||||
injected.Append(mdFwdGroup, sidAdministrators)
|
||||
|
||||
ctx := WithForwardedIdentity(metadata.NewOutgoingContext(context.Background(), injected),
|
||||
Identity{SID: "S-1-5-21-1-2-3-1001"}, true)
|
||||
out, ok := metadata.FromOutgoingContext(ctx)
|
||||
if !ok {
|
||||
t.Fatal("no outgoing metadata")
|
||||
}
|
||||
if groups := out.Get(mdFwdGroup); len(groups) != 0 {
|
||||
t.Fatalf("injected group survived: %v", groups)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
func TestIsReservedForwardKey(t *testing.T) {
|
||||
for _, key := range forwardKeys {
|
||||
if !IsReservedForwardKey(key) {
|
||||
t.Errorf("%q must be reserved", key)
|
||||
}
|
||||
}
|
||||
|
||||
// grpc-gateway canonicalises header names, so the check has to be
|
||||
// case-insensitive.
|
||||
if !IsReservedForwardKey("X-Netbird-Fwd-Uid") {
|
||||
t.Error("the check must be case-insensitive")
|
||||
}
|
||||
|
||||
for _, key := range []string{"authorization", "x-netbird", "x-netbird-fwd-uid-extra", ""} {
|
||||
if IsReservedForwardKey(key) {
|
||||
t.Errorf("%q must not be reserved", key)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestForwardIdentityMetadata_AlwaysMarksForwarded(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
id Identity
|
||||
known bool
|
||||
}{
|
||||
{"known unix identity", unprivUser, true},
|
||||
{"unknown identity", Identity{}, false},
|
||||
{"windows identity", Identity{SID: "S-1-5-21-1-2-3-1001", Elevated: true}, true},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
md := ForwardIdentityMetadata(tc.id, tc.known)
|
||||
if got := md.Get(mdFwd); len(got) != 1 || got[0] != "1" {
|
||||
t.Fatalf("marker = %v, want exactly one \"1\"", got)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -1,127 +0,0 @@
|
||||
// Package ipcauth provides the kernel-authenticated identity of a local IPC
|
||||
// (gRPC) caller and the transport credentials that surface it into the gRPC
|
||||
// context, so the daemon can authorize individual RPCs by caller identity.
|
||||
//
|
||||
// On Unix the identity is read from the kernel via SO_PEERCRED (Linux) or
|
||||
// LOCAL_PEERCRED (Darwin/FreeBSD). On Windows it is derived from the
|
||||
// named-pipe client token. Platforms without a peer-identity primitive get no
|
||||
// credentials, and every consumer must fail closed when no identity is
|
||||
// available.
|
||||
package ipcauth
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"slices"
|
||||
|
||||
"google.golang.org/grpc/credentials"
|
||||
"google.golang.org/grpc/peer"
|
||||
)
|
||||
|
||||
// Well-known Windows SIDs that identify a fully privileged principal.
|
||||
const (
|
||||
sidLocalSystem = "S-1-5-18" // NT AUTHORITY\SYSTEM
|
||||
sidLocalService = "S-1-5-19" // NT AUTHORITY\LOCAL SERVICE
|
||||
sidNetworkService = "S-1-5-20" // NT AUTHORITY\NETWORK SERVICE
|
||||
sidAdministrators = "S-1-5-32-544" // BUILTIN\Administrators
|
||||
)
|
||||
|
||||
// Identity is the kernel-authenticated identity of a local IPC caller. The
|
||||
// zero value is not a valid identity: consumers must only use one obtained
|
||||
// with a true ok/nil error return.
|
||||
type Identity struct {
|
||||
// UID and GID are the caller's Unix user ID and primary group ID. Both are
|
||||
// zero on Windows, where SID is authoritative instead.
|
||||
UID uint32
|
||||
GID uint32
|
||||
|
||||
// SID is the caller's Windows security identifier, empty on Unix.
|
||||
SID string
|
||||
|
||||
// Groups holds the caller's Windows group SIDs, captured from the client
|
||||
// token at handshake time. Only groups that are enabled and not
|
||||
// deny-only are captured, so a group listed here is one the caller can
|
||||
// actually exercise. Empty on Unix.
|
||||
Groups []string
|
||||
|
||||
// Elevated reports whether the Windows client token is elevated (running
|
||||
// as administrator, or an administrator with UAC turned off). Always false
|
||||
// on Unix, where privilege is uid 0.
|
||||
Elevated bool
|
||||
|
||||
// PID is the caller's process ID where the platform reports it (Linux's
|
||||
// SO_PEERCRED), and 0 where it does not. It identifies the daemon's own
|
||||
// process dialling itself, which is what the JSON gateway does, and is never
|
||||
// used to grant anything.
|
||||
PID int32
|
||||
}
|
||||
|
||||
// IsWindows reports whether this identity is a Windows principal (SID-based)
|
||||
// rather than a Unix uid/gid principal.
|
||||
func (i Identity) IsWindows() bool {
|
||||
return i.SID != ""
|
||||
}
|
||||
|
||||
// IsPrivileged reports whether the caller is the platform's administrative
|
||||
// principal, which is what the daemon requires for changes that cross the
|
||||
// user-to-root boundary.
|
||||
//
|
||||
// On Windows the decision comes from the caller's token rather than from
|
||||
// account names or group RIDs: an elevated token, one of the service accounts
|
||||
// the daemon itself may run as, or a token with BUILTIN\Administrators
|
||||
// enabled. A UAC-filtered administrator has that group marked deny-only, and
|
||||
// deny-only groups are dropped when the identity is captured, so such a
|
||||
// caller is correctly reported as unprivileged. Domain group memberships
|
||||
// (Domain Admins and friends) are deliberately not consulted: they say
|
||||
// nothing about what this token may do on this machine.
|
||||
func (i Identity) IsPrivileged() bool {
|
||||
if !i.IsWindows() {
|
||||
return i.UID == 0
|
||||
}
|
||||
|
||||
if i.Elevated {
|
||||
return true
|
||||
}
|
||||
|
||||
switch i.SID {
|
||||
case sidLocalSystem, sidLocalService, sidNetworkService:
|
||||
return true
|
||||
}
|
||||
|
||||
return slices.Contains(i.Groups, sidAdministrators)
|
||||
}
|
||||
|
||||
// String renders the identity for audit logs and denial messages.
|
||||
func (i Identity) String() string {
|
||||
if i.IsWindows() {
|
||||
return fmt.Sprintf("sid=%s elevated=%t", i.SID, i.Elevated)
|
||||
}
|
||||
return fmt.Sprintf("uid=%d gid=%d", i.UID, i.GID)
|
||||
}
|
||||
|
||||
// AuthInfo carries the peer Identity as a gRPC credentials.AuthInfo so
|
||||
// handlers can retrieve it from the request context via IdentityFromContext.
|
||||
type AuthInfo struct {
|
||||
credentials.CommonAuthInfo
|
||||
Identity Identity
|
||||
}
|
||||
|
||||
// AuthType identifies the authentication scheme.
|
||||
func (AuthInfo) AuthType() string { return "netbird-ipc-peercred" }
|
||||
|
||||
// IdentityFromContext extracts the caller's kernel-authenticated identity from
|
||||
// the gRPC peer context. The second return value is false when no IPC
|
||||
// transport credentials were negotiated, which happens on a TCP daemon socket
|
||||
// and on platforms without a peer-identity primitive. Callers MUST fail closed
|
||||
// in that case.
|
||||
func IdentityFromContext(ctx context.Context) (Identity, bool) {
|
||||
p, ok := peer.FromContext(ctx)
|
||||
if !ok {
|
||||
return Identity{}, false
|
||||
}
|
||||
info, ok := p.AuthInfo.(AuthInfo)
|
||||
if !ok {
|
||||
return Identity{}, false
|
||||
}
|
||||
return info.Identity, true
|
||||
}
|
||||
@@ -1,43 +0,0 @@
|
||||
//go:build darwin || freebsd
|
||||
|
||||
package ipcauth
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"net"
|
||||
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// PeerIdentity reads the kernel-authenticated identity of the process on the
|
||||
// other end of a Unix socket via LOCAL_PEERCRED. The xucred is recorded by the
|
||||
// kernel at connect() time and carries the peer's uid and its group list, of
|
||||
// which the first entry is the primary group.
|
||||
func PeerIdentity(conn net.Conn) (Identity, error) {
|
||||
uc, ok := conn.(*net.UnixConn)
|
||||
if !ok {
|
||||
return Identity{}, fmt.Errorf("connection is not a unix socket: %T", conn)
|
||||
}
|
||||
|
||||
raw, err := uc.SyscallConn()
|
||||
if err != nil {
|
||||
return Identity{}, fmt.Errorf("raw conn: %w", err)
|
||||
}
|
||||
|
||||
var cred *unix.Xucred
|
||||
var credErr error
|
||||
if err := raw.Control(func(fd uintptr) {
|
||||
cred, credErr = unix.GetsockoptXucred(int(fd), unix.SOL_LOCAL, unix.LOCAL_PEERCRED)
|
||||
}); err != nil {
|
||||
return Identity{}, fmt.Errorf("control raw conn: %w", err)
|
||||
}
|
||||
if credErr != nil {
|
||||
return Identity{}, fmt.Errorf("read LOCAL_PEERCRED: %w", credErr)
|
||||
}
|
||||
|
||||
id := Identity{UID: cred.Uid}
|
||||
if cred.Ngroups > 0 {
|
||||
id.GID = cred.Groups[0]
|
||||
}
|
||||
return id, nil
|
||||
}
|
||||
@@ -1,39 +0,0 @@
|
||||
//go:build linux
|
||||
|
||||
package ipcauth
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"net"
|
||||
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// PeerIdentity reads the kernel-authenticated identity of the process on the
|
||||
// other end of a Unix socket via SO_PEERCRED. The credentials are recorded by
|
||||
// the kernel at connect() time and cannot be changed for the life of the
|
||||
// connection, so they are not spoofable by the caller.
|
||||
func PeerIdentity(conn net.Conn) (Identity, error) {
|
||||
uc, ok := conn.(*net.UnixConn)
|
||||
if !ok {
|
||||
return Identity{}, fmt.Errorf("connection is not a unix socket: %T", conn)
|
||||
}
|
||||
|
||||
raw, err := uc.SyscallConn()
|
||||
if err != nil {
|
||||
return Identity{}, fmt.Errorf("raw conn: %w", err)
|
||||
}
|
||||
|
||||
var cred *unix.Ucred
|
||||
var credErr error
|
||||
if err := raw.Control(func(fd uintptr) {
|
||||
cred, credErr = unix.GetsockoptUcred(int(fd), unix.SOL_SOCKET, unix.SO_PEERCRED)
|
||||
}); err != nil {
|
||||
return Identity{}, fmt.Errorf("control raw conn: %w", err)
|
||||
}
|
||||
if credErr != nil {
|
||||
return Identity{}, fmt.Errorf("read SO_PEERCRED: %w", credErr)
|
||||
}
|
||||
|
||||
return Identity{UID: cred.Uid, GID: cred.Gid, PID: cred.Pid}, nil
|
||||
}
|
||||
@@ -1,87 +0,0 @@
|
||||
//go:build windows
|
||||
|
||||
package ipcauth
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"net"
|
||||
|
||||
log "github.com/sirupsen/logrus"
|
||||
"golang.org/x/sys/windows"
|
||||
)
|
||||
|
||||
// PipeServerTrusted reports an error unless the pipe behind conn was created by a
|
||||
// principal this client may hand secrets to. Clients call it for a pipe whose name
|
||||
// carries no guarantee of its own, which is any name outside the
|
||||
// ProtectedPrefix\Administrators namespace: that namespace already restricts
|
||||
// creation to administrators and LocalSystem, while a plain name can be created by
|
||||
// any local user before the daemon gets there.
|
||||
//
|
||||
// The decision is made from the pipe object's owner, not from the serving process,
|
||||
// because a client cannot open a process running as another user at all, and the
|
||||
// legitimate case is precisely an unprivileged client talking to a privileged
|
||||
// daemon. Trusted owners are the service accounts, BUILTIN\Administrators, and
|
||||
// this client's own user, the last of which is the daemon a user runs themselves
|
||||
// as in netstack mode. A pipe owned by anyone else gets no setup key, pre-shared
|
||||
// key or SSO prompt out of this client.
|
||||
func PipeServerTrusted(conn net.Conn) error {
|
||||
// go-winio's pipe connection embeds *win32File, which exposes Fd().
|
||||
fdConn, ok := conn.(interface{ Fd() uintptr })
|
||||
if !ok {
|
||||
return fmt.Errorf("connection %T does not expose a pipe handle", conn)
|
||||
}
|
||||
|
||||
owner, err := pipeOwnerSID(windows.Handle(fdConn.Fd()))
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
if !trustedPipeOwner(owner) {
|
||||
return fmt.Errorf("pipe owned by %s, which is neither an administrator nor this user", owner)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// PipeOwnedBySelf reports whether the pipe behind conn was created by this very
|
||||
// user, which is how a client recognises a daemon running as itself. Ownership it
|
||||
// cannot read is reported as false.
|
||||
func PipeOwnedBySelf(conn net.Conn) bool {
|
||||
fdConn, ok := conn.(interface{ Fd() uintptr })
|
||||
if !ok {
|
||||
return false
|
||||
}
|
||||
|
||||
owner, err := pipeOwnerSID(windows.Handle(fdConn.Fd()))
|
||||
if err != nil {
|
||||
log.Debugf("read daemon pipe owner: %v", err)
|
||||
return false
|
||||
}
|
||||
return selfKnown && selfIdentity.SID != "" && owner == selfIdentity.SID
|
||||
}
|
||||
|
||||
// pipeOwnerSID reads the owner of the pipe object a client is connected to. The
|
||||
// handle was opened with GENERIC_READ, which includes READ_CONTROL, so no extra
|
||||
// access is needed.
|
||||
func pipeOwnerSID(handle windows.Handle) (string, error) {
|
||||
sd, err := windows.GetSecurityInfo(handle, windows.SE_KERNEL_OBJECT, windows.OWNER_SECURITY_INFORMATION)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("read pipe security info: %w", err)
|
||||
}
|
||||
|
||||
owner, _, err := sd.Owner()
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("read pipe owner: %w", err)
|
||||
}
|
||||
return owner.String(), nil
|
||||
}
|
||||
|
||||
// trustedPipeOwner reports whether a pipe's owner is a principal a client may
|
||||
// speak to. An elevated process's objects are owned by BUILTIN\Administrators by
|
||||
// default, an unelevated one's by the user, which is why both forms appear here.
|
||||
func trustedPipeOwner(owner string) bool {
|
||||
switch owner {
|
||||
case sidLocalSystem, sidLocalService, sidNetworkService, sidAdministrators:
|
||||
return true
|
||||
}
|
||||
return selfKnown && selfIdentity.SID != "" && owner == selfIdentity.SID
|
||||
}
|
||||
@@ -1,125 +0,0 @@
|
||||
package ipcauth
|
||||
|
||||
import (
|
||||
"os"
|
||||
"runtime"
|
||||
)
|
||||
|
||||
// Fields of the ErrorInfo detail the daemon attaches to a PermissionDenied it
|
||||
// raises for an operation that requires root/administrator. Clients match on
|
||||
// Reason and Domain rather than on the message text, and render the summary and
|
||||
// command themselves so the user gets guidance instead of a gRPC error dump.
|
||||
const (
|
||||
// ErrorReasonPrivilegeRequired identifies the detail.
|
||||
ErrorReasonPrivilegeRequired = "PRIVILEGE_REQUIRED"
|
||||
// ErrorDomain scopes the reason to the NetBird daemon.
|
||||
ErrorDomain = "daemon.netbird.io"
|
||||
// ErrorMetaSummary is the one-sentence explanation of what was refused.
|
||||
ErrorMetaSummary = "summary"
|
||||
// ErrorMetaCommand is the command that performs the same operation with the
|
||||
// privileges it needs, ready to copy and run.
|
||||
ErrorMetaCommand = "command"
|
||||
)
|
||||
|
||||
// The identity of the process evaluating callers, captured once because it cannot
|
||||
// change. selfKnown is false when it could not be read, in which case nothing is
|
||||
// ever treated as this process. selfMayDelegate additionally requires this
|
||||
// process to be unprivileged: see IsPrivilegedCaller.
|
||||
var (
|
||||
selfIdentity Identity
|
||||
selfKnown bool
|
||||
selfMayDelegate bool
|
||||
// selfPID is this process's PID, used to recognise the daemon dialling itself.
|
||||
selfPID = os.Getpid()
|
||||
)
|
||||
|
||||
func init() {
|
||||
id, err := CurrentProcessIdentity()
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
selfIdentity, selfKnown = id, true
|
||||
// Only an unprivileged daemon delegates its authority to its own identity.
|
||||
// When it is root or LocalSystem, sharing its identity does not mean sharing
|
||||
// its power: on Windows a filtered and a full token carry the same SID, so
|
||||
// matching there would let a non-elevated shell of an administrator account
|
||||
// act as an administrator, which is the boundary the token check exists to
|
||||
// keep.
|
||||
selfMayDelegate = !id.IsPrivileged()
|
||||
}
|
||||
|
||||
// IsDaemonSelf reports whether an identity is this very process. The JSON gateway
|
||||
// runs inside the daemon and re-dials it locally, so this is what distinguishes
|
||||
// the gateway from any other caller, whatever user the daemon runs as.
|
||||
func IsDaemonSelf(id Identity) bool {
|
||||
if !selfKnown || id.IsWindows() != selfIdentity.IsWindows() {
|
||||
return false
|
||||
}
|
||||
if id.IsWindows() {
|
||||
return id.SID != "" && id.SID == selfIdentity.SID
|
||||
}
|
||||
return id.UID == selfIdentity.UID
|
||||
}
|
||||
|
||||
// IsPrivilegedCaller reports whether an identity may make the changes the daemon
|
||||
// restricts to the platform administrator. This is the daemon's own rule and
|
||||
// cannot be evaluated by a client, which does not know what the daemon runs as.
|
||||
//
|
||||
// Beyond root/administrator it accepts a caller running as the daemon's own
|
||||
// identity when the daemon is itself unprivileged. That keeps a rootless container
|
||||
// working, where there is no uid 0 at all, and a Windows daemon in netstack mode,
|
||||
// which needs no administrator rights. In those setups a caller sharing the
|
||||
// daemon's identity can already rewrite the config files it reads and replace the
|
||||
// binary it runs, so refusing it a config change would protect nothing; and an
|
||||
// unprivileged daemon cannot hand out a root shell in the first place.
|
||||
func IsPrivilegedCaller(id Identity) bool {
|
||||
if id.IsPrivileged() {
|
||||
return true
|
||||
}
|
||||
return selfMayDelegate && IsDaemonSelf(id)
|
||||
}
|
||||
|
||||
// SelfDelegatesTo returns the identity this process delegates its authority to,
|
||||
// and whether it delegates at all. Only an unprivileged daemon does: see
|
||||
// IsPrivilegedCaller. It exists so a refusal can name who may actually perform the
|
||||
// operation, because on such a host root is neither required nor necessarily
|
||||
// available.
|
||||
func SelfDelegatesTo() (Identity, bool) {
|
||||
if !selfKnown || !selfMayDelegate {
|
||||
return Identity{}, false
|
||||
}
|
||||
return selfIdentity, true
|
||||
}
|
||||
|
||||
// PrivilegedActor names the principal a privileged operation requires, for use
|
||||
// in messages shown to the user.
|
||||
func PrivilegedActor() string {
|
||||
if runtime.GOOS == "windows" {
|
||||
return "administrator privileges"
|
||||
}
|
||||
return "root"
|
||||
}
|
||||
|
||||
// ElevatedCommand renders a command so that running it grants the privileges the
|
||||
// operation needs. Windows has no in-line equivalent of sudo, so the command is
|
||||
// returned unchanged and the user is expected to run it from an elevated
|
||||
// terminal.
|
||||
func ElevatedCommand(command string) string {
|
||||
if runtime.GOOS == "windows" {
|
||||
return command
|
||||
}
|
||||
return "sudo " + command
|
||||
}
|
||||
|
||||
// UpCommand renders an elevated `netbird up` with the given flags, preceded by a
|
||||
// `down`. The down is what makes the command work on a connected client: `netbird
|
||||
// up` prints "Already connected" and returns without applying any config flag, so
|
||||
// on its own the command would appear to do nothing. It is a no-op, exit 0, when
|
||||
// the client is not connected.
|
||||
//
|
||||
// ";" rather than "&&" so the line can be pasted into any of the shells a user
|
||||
// might have: PowerShell 5.1, still the default on Windows Server, rejects "&&"
|
||||
// as a syntax error.
|
||||
func UpCommand(flags string) string {
|
||||
return ElevatedCommand("netbird down") + "; " + ElevatedCommand("netbird up "+flags)
|
||||
}
|
||||
@@ -1,134 +0,0 @@
|
||||
package ipcauth
|
||||
|
||||
import "testing"
|
||||
|
||||
// The self rule is the one place privilege is granted to something other than the
|
||||
// platform administrator, so its two guards matter: it must apply only when the
|
||||
// daemon is itself unprivileged, and only to a caller with the daemon's identity.
|
||||
func TestIsPrivilegedCaller_SelfRule(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
// self stands in for the process the daemon runs as.
|
||||
self Identity
|
||||
selfKnown bool
|
||||
caller Identity
|
||||
want bool
|
||||
}{
|
||||
{
|
||||
name: "root is privileged whatever the daemon runs as",
|
||||
self: Identity{UID: 1000},
|
||||
selfKnown: true,
|
||||
caller: Identity{UID: 0},
|
||||
want: true,
|
||||
},
|
||||
{
|
||||
name: "an unprivileged daemon delegates to its own user (rootless container)",
|
||||
self: Identity{UID: 1000},
|
||||
selfKnown: true,
|
||||
caller: Identity{UID: 1000},
|
||||
want: true,
|
||||
},
|
||||
{
|
||||
name: "an unprivileged daemon delegates to nobody else",
|
||||
self: Identity{UID: 1000},
|
||||
selfKnown: true,
|
||||
caller: Identity{UID: 1001},
|
||||
want: false,
|
||||
},
|
||||
{
|
||||
// The daemon is root on a normal install, so sharing its identity is
|
||||
// already covered by being root; nothing else may match.
|
||||
name: "a root daemon delegates to nobody",
|
||||
self: Identity{UID: 0},
|
||||
selfKnown: true,
|
||||
caller: Identity{UID: 1000},
|
||||
want: false,
|
||||
},
|
||||
{
|
||||
// Windows netstack mode: the daemon needs no administrator rights.
|
||||
name: "an unprivileged windows daemon delegates to its own SID",
|
||||
self: Identity{SID: "S-1-5-21-1-2-3-1001"},
|
||||
selfKnown: true,
|
||||
caller: Identity{SID: "S-1-5-21-1-2-3-1001"},
|
||||
want: true,
|
||||
},
|
||||
{
|
||||
name: "an unprivileged windows daemon delegates to no other SID",
|
||||
self: Identity{SID: "S-1-5-21-1-2-3-1001"},
|
||||
selfKnown: true,
|
||||
caller: Identity{SID: "S-1-5-21-1-2-3-1002"},
|
||||
want: false,
|
||||
},
|
||||
{
|
||||
// The UAC boundary: a filtered and a full token of the same account
|
||||
// carry the same SID but not the same power, so an elevated daemon must
|
||||
// never delegate to its own SID.
|
||||
name: "an elevated windows daemon does not delegate to its own SID",
|
||||
self: Identity{SID: "S-1-5-21-1-2-3-500", Elevated: true},
|
||||
selfKnown: true,
|
||||
caller: Identity{SID: "S-1-5-21-1-2-3-500"},
|
||||
want: false,
|
||||
},
|
||||
{
|
||||
name: "LocalSystem is privileged on its own merits, not by delegation",
|
||||
self: Identity{SID: sidLocalSystem},
|
||||
selfKnown: true,
|
||||
caller: Identity{SID: sidLocalSystem},
|
||||
want: true, // LocalSystem is privileged on its own merits
|
||||
},
|
||||
{
|
||||
name: "identities of different kinds never match",
|
||||
self: Identity{UID: 1000},
|
||||
selfKnown: true,
|
||||
caller: Identity{SID: "S-1-5-21-1-2-3-1001"},
|
||||
want: false,
|
||||
},
|
||||
{
|
||||
name: "an unknown self identity delegates to nobody",
|
||||
self: Identity{},
|
||||
selfKnown: false,
|
||||
caller: Identity{UID: 1000},
|
||||
want: false,
|
||||
},
|
||||
}
|
||||
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
prevID, prevKnown, prevDelegate := selfIdentity, selfKnown, selfMayDelegate
|
||||
t.Cleanup(func() { selfIdentity, selfKnown, selfMayDelegate = prevID, prevKnown, prevDelegate })
|
||||
|
||||
selfIdentity, selfKnown = tt.self, tt.selfKnown
|
||||
selfMayDelegate = tt.selfKnown && !tt.self.IsPrivileged()
|
||||
|
||||
if got := IsPrivilegedCaller(tt.caller); got != tt.want {
|
||||
t.Fatalf("IsPrivilegedCaller(%v) with daemon %v = %t, want %t",
|
||||
tt.caller, tt.self, got, tt.want)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// The real process must never accidentally delegate: a test binary running as a
|
||||
// normal user is unprivileged, so it may match itself, but nothing else.
|
||||
func TestIsPrivilegedCaller_ThisProcess(t *testing.T) {
|
||||
id, err := CurrentProcessIdentity()
|
||||
if err != nil {
|
||||
t.Skipf("cannot read this process's identity: %v", err)
|
||||
}
|
||||
|
||||
// This process is always allowed to act as itself: either it is privileged, or
|
||||
// it is unprivileged and therefore delegates to its own identity.
|
||||
if !IsPrivilegedCaller(id) {
|
||||
t.Errorf("this process %v was refused its own identity", id)
|
||||
}
|
||||
|
||||
// A caller that is neither root nor this process must be refused, whatever
|
||||
// this process happens to be.
|
||||
other := Identity{UID: id.UID + 1}
|
||||
if id.IsWindows() {
|
||||
other = Identity{SID: id.SID + "9"}
|
||||
}
|
||||
if IsPrivilegedCaller(other) {
|
||||
t.Errorf("an unrelated identity %v was treated as privileged", other)
|
||||
}
|
||||
}
|
||||
@@ -1,17 +0,0 @@
|
||||
//go:build !windows
|
||||
|
||||
package ipcauth
|
||||
|
||||
import "os"
|
||||
|
||||
// CurrentProcessIdentity returns this process's identity as the daemon would
|
||||
// see it if this process connected to the local IPC. It lets a client (the UI)
|
||||
// decide up front whether a privileged operation can succeed, without a
|
||||
// round-trip and without duplicating the rules: the answer comes from the same
|
||||
// Identity.IsPrivileged the daemon applies.
|
||||
func CurrentProcessIdentity() (Identity, error) {
|
||||
return Identity{
|
||||
UID: uint32(os.Geteuid()),
|
||||
GID: uint32(os.Getegid()),
|
||||
}, nil
|
||||
}
|
||||
@@ -1,35 +0,0 @@
|
||||
//go:build windows
|
||||
|
||||
package ipcauth
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
|
||||
"golang.org/x/sys/windows"
|
||||
)
|
||||
|
||||
// CurrentProcessIdentity returns this process's identity as the daemon would see
|
||||
// it if this process connected to the local IPC. It lets a client (the UI)
|
||||
// decide up front whether a privileged operation can succeed, without a
|
||||
// round-trip and without duplicating the rules: the answer comes from the same
|
||||
// Identity.IsPrivileged the daemon applies to the token it reads off the pipe.
|
||||
func CurrentProcessIdentity() (Identity, error) {
|
||||
// A pseudo-token, so it must not be closed.
|
||||
token := windows.GetCurrentProcessToken()
|
||||
|
||||
user, err := token.GetTokenUser()
|
||||
if err != nil {
|
||||
return Identity{}, fmt.Errorf("read token user: %w", err)
|
||||
}
|
||||
|
||||
groups, err := tokenGroupSIDs(token)
|
||||
if err != nil {
|
||||
return Identity{}, err
|
||||
}
|
||||
|
||||
return Identity{
|
||||
SID: user.User.Sid.String(),
|
||||
Groups: groups,
|
||||
Elevated: token.IsElevated(),
|
||||
}, nil
|
||||
}
|
||||
@@ -29,11 +29,6 @@ type managedPeer struct {
|
||||
|
||||
type Config struct {
|
||||
InactivityThreshold *time.Duration
|
||||
// ReconcileAllowedIPs re-applies a peer's routed allowed IPs after its wake endpoint is
|
||||
// armed. The activity listener creates the wake peer with the overlay /32 only; without the
|
||||
// routed prefixes WireGuard would not steer subnet-bound traffic to the wake endpoint, so an
|
||||
// idle routing peer could never be woken by that traffic. Optional; nil disables the reconcile.
|
||||
ReconcileAllowedIPs func(peerKey string) error
|
||||
}
|
||||
|
||||
// Manager manages lazy connections
|
||||
@@ -61,9 +56,6 @@ type Manager struct {
|
||||
peerToHAGroups map[string][]route.HAUniqueID // peer ID -> HA groups they belong to
|
||||
haGroupToPeers map[route.HAUniqueID][]string // HA group -> peer IDs in the group
|
||||
routesMu sync.RWMutex
|
||||
|
||||
// reconcileAllowedIPs re-applies a peer's routed allowed IPs after its wake endpoint is armed.
|
||||
reconcileAllowedIPs func(peerKey string) error
|
||||
}
|
||||
|
||||
// NewManager creates a new lazy connection manager
|
||||
@@ -81,7 +73,6 @@ func NewManager(config Config, engineCtx context.Context, peerStore *peerstore.S
|
||||
activityManager: activity.NewManager(wgIface),
|
||||
peerToHAGroups: make(map[string][]route.HAUniqueID),
|
||||
haGroupToPeers: make(map[route.HAUniqueID][]string),
|
||||
reconcileAllowedIPs: config.ReconcileAllowedIPs,
|
||||
}
|
||||
|
||||
if wgIface.IsUserspaceBind() {
|
||||
@@ -210,7 +201,7 @@ func (m *Manager) AddPeer(peerCfg lazyconn.PeerConfig) (bool, error) {
|
||||
return false, nil
|
||||
}
|
||||
|
||||
if err := m.armActivityListener(peerCfg); err != nil {
|
||||
if err := m.activityManager.MonitorPeerActivity(peerCfg); err != nil {
|
||||
return false, err
|
||||
}
|
||||
|
||||
@@ -297,7 +288,7 @@ func (m *Manager) DeactivatePeer(peerID peerid.ConnID) {
|
||||
|
||||
m.inactivityManager.RemovePeer(mp.peerCfg.PublicKey)
|
||||
|
||||
if err := m.armActivityListener(*mp.peerCfg); err != nil {
|
||||
if err := m.activityManager.MonitorPeerActivity(*mp.peerCfg); err != nil {
|
||||
mp.peerCfg.Log.Errorf("failed to create activity monitor: %v", err)
|
||||
return
|
||||
}
|
||||
@@ -474,31 +465,6 @@ func (m *Manager) close() {
|
||||
}
|
||||
|
||||
// shouldDeferIdleForHA checks if peer should stay connected due to HA group requirements
|
||||
// armRoutedAllowedIPs re-applies the peer's routed allowed IPs onto its freshly armed wake
|
||||
// endpoint. The activity listener creates the wake peer with the overlay /32 only, so without
|
||||
// this the routed prefixes would be missing and traffic to a routed subnet could not wake the
|
||||
// idle routing peer. It is a no-op when no reconciler is configured.
|
||||
// armActivityListener (re)arms the peer's wake endpoint via the activity manager and then
|
||||
// re-applies its routed allowed IPs, so traffic to a routed subnet can wake an idle routing
|
||||
// peer. The routed prefixes must be re-applied after the wake endpoint exists because the
|
||||
// listener creates it with the overlay /32 only.
|
||||
func (m *Manager) armActivityListener(peerCfg lazyconn.PeerConfig) error {
|
||||
if err := m.activityManager.MonitorPeerActivity(peerCfg); err != nil {
|
||||
return err
|
||||
}
|
||||
m.armRoutedAllowedIPs(&peerCfg)
|
||||
return nil
|
||||
}
|
||||
|
||||
func (m *Manager) armRoutedAllowedIPs(peerCfg *lazyconn.PeerConfig) {
|
||||
if m.reconcileAllowedIPs == nil {
|
||||
return
|
||||
}
|
||||
if err := m.reconcileAllowedIPs(peerCfg.PublicKey); err != nil {
|
||||
peerCfg.Log.Errorf("failed to reconcile routed allowed IPs on wake endpoint: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
func (m *Manager) shouldDeferIdleForHA(inactivePeers map[string]struct{}, peerID string) bool {
|
||||
m.routesMu.RLock()
|
||||
defer m.routesMu.RUnlock()
|
||||
@@ -611,7 +577,7 @@ func (m *Manager) onPeerInactivityTimedOut(peerIDs map[string]struct{}) {
|
||||
|
||||
mp.peerCfg.Log.Infof("start activity monitor")
|
||||
|
||||
if err := m.armActivityListener(*mp.peerCfg); err != nil {
|
||||
if err := m.activityManager.MonitorPeerActivity(*mp.peerCfg); err != nil {
|
||||
mp.peerCfg.Log.Errorf("failed to create activity monitor: %v", err)
|
||||
continue
|
||||
}
|
||||
|
||||
@@ -11,14 +11,12 @@ import (
|
||||
|
||||
// MobileDependency collect all dependencies for mobile platform
|
||||
type MobileDependency struct {
|
||||
// Android and iOS
|
||||
NetworkChangeListener listener.NetworkChangeListener
|
||||
|
||||
// Android only
|
||||
TunAdapter device.TunAdapter
|
||||
IFaceDiscover stdnet.ExternalIFaceDiscover
|
||||
HostDNSAddresses []netip.AddrPort
|
||||
DnsReadyListener dns.ReadyListener
|
||||
TunAdapter device.TunAdapter
|
||||
IFaceDiscover stdnet.ExternalIFaceDiscover
|
||||
NetworkChangeListener listener.NetworkChangeListener
|
||||
HostDNSAddresses []netip.AddrPort
|
||||
DnsReadyListener dns.ReadyListener
|
||||
|
||||
// iOS only
|
||||
DnsManager dns.IosDnsManager
|
||||
|
||||
@@ -813,14 +813,19 @@ func (d *Status) SetSessionExpiresAt(deadline time.Time) {
|
||||
}
|
||||
|
||||
// GetSessionExpiresAt returns the most recently recorded SSO session deadline,
|
||||
// or the zero value when no deadline is tracked. A deadline in the past is
|
||||
// returned as-is: it means the session has expired, and consumers (tray row,
|
||||
// CLI status) render it as "expired" rather than hiding it — masking it as
|
||||
// "none" would blank the UI at the exact moment it should say the session
|
||||
// ended.
|
||||
// or the zero value when no deadline is tracked. A deadline that has already
|
||||
// slipped into the past reports as "none": once the session has expired it is
|
||||
// no longer a meaningful countdown, and the sessionwatch.Watcher does not
|
||||
// arm a timer at the deadline itself to clear it (only the two pre-expiry
|
||||
// warnings). Without this guard the UI would keep painting a stale
|
||||
// "expires in …" against a moment that has passed until the next login,
|
||||
// extend, or teardown rewrote the value.
|
||||
func (d *Status) GetSessionExpiresAt() time.Time {
|
||||
d.mux.Lock()
|
||||
defer d.mux.Unlock()
|
||||
if !d.sessionExpiresAt.IsZero() && d.sessionExpiresAt.Before(time.Now()) {
|
||||
return time.Time{}
|
||||
}
|
||||
return d.sessionExpiresAt
|
||||
}
|
||||
|
||||
|
||||
@@ -96,7 +96,6 @@ type ConfigInput struct {
|
||||
BlockLANAccess *bool
|
||||
BlockInbound *bool
|
||||
DisableIPv6 *bool
|
||||
SyncMessageVersion *int
|
||||
|
||||
DisableNotifications *bool
|
||||
|
||||
@@ -138,7 +137,6 @@ type Config struct {
|
||||
BlockLANAccess bool
|
||||
BlockInbound bool
|
||||
DisableIPv6 bool
|
||||
SyncMessageVersion *int
|
||||
|
||||
DisableNotifications *bool
|
||||
|
||||
@@ -589,12 +587,6 @@ func (config *Config) apply(input ConfigInput) (updated bool, err error) {
|
||||
updated = true
|
||||
}
|
||||
|
||||
if input.SyncMessageVersion != nil && *input.SyncMessageVersion != *config.SyncMessageVersion {
|
||||
log.Infof("setting SyncMessageVersion to %v", *input.SyncMessageVersion)
|
||||
*config.SyncMessageVersion = *input.SyncMessageVersion
|
||||
updated = true
|
||||
}
|
||||
|
||||
if input.DisableNotifications != nil && (config.DisableNotifications == nil || *input.DisableNotifications != *config.DisableNotifications) {
|
||||
if *input.DisableNotifications {
|
||||
log.Infof("disabling notifications")
|
||||
@@ -746,13 +738,6 @@ func (config *Config) applyMDMPolicy(policy *mdm.Policy) {
|
||||
// appended for https or ":80" for http. The serviceName parameter is
|
||||
// used to contextualise error messages. On success returns the parsed
|
||||
// *url.URL; on failure returns a non-nil error.
|
||||
// ParseServiceURL normalises a service URL exactly as the config layer does when
|
||||
// it stores one, so callers comparing a requested URL against a stored one do not
|
||||
// have to reimplement the scheme validation and default-port handling.
|
||||
func ParseServiceURL(serviceName, serviceURL string) (*url.URL, error) {
|
||||
return parseURL(serviceName, serviceURL)
|
||||
}
|
||||
|
||||
func parseURL(serviceName, serviceURL string) (*url.URL, error) {
|
||||
parsedMgmtURL, err := url.ParseRequestURI(serviceURL)
|
||||
if err != nil {
|
||||
|
||||
@@ -95,7 +95,7 @@ func (d *DnsInterceptor) RemoveRoute() error {
|
||||
|
||||
// AllowedIPs should use real IPs
|
||||
if d.currentPeerKey != "" {
|
||||
if _, err := d.allowedIPsRefcounter.Decrement(prefix, d.currentPeerKey); err != nil {
|
||||
if _, err := d.allowedIPsRefcounter.Decrement(prefix); err != nil {
|
||||
merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %v", prefix, err))
|
||||
}
|
||||
}
|
||||
@@ -172,7 +172,7 @@ func (d *DnsInterceptor) removeAllowedIP(realPrefix netip.Prefix) error {
|
||||
}
|
||||
|
||||
// AllowedIPs use real IPs
|
||||
if _, err := d.allowedIPsRefcounter.Decrement(realPrefix, d.currentPeerKey); err != nil {
|
||||
if _, err := d.allowedIPsRefcounter.Decrement(realPrefix); err != nil {
|
||||
return fmt.Errorf("remove allowed IP %s: %v", realPrefix, err)
|
||||
}
|
||||
|
||||
@@ -205,7 +205,7 @@ func (d *DnsInterceptor) RemoveAllowedIPs() error {
|
||||
for _, prefixes := range d.interceptedDomains {
|
||||
for _, prefix := range prefixes {
|
||||
// AllowedIPs use real IPs
|
||||
if _, err := d.allowedIPsRefcounter.Decrement(prefix, d.currentPeerKey); err != nil {
|
||||
if _, err := d.allowedIPsRefcounter.Decrement(prefix); err != nil {
|
||||
merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %v", prefix, err))
|
||||
}
|
||||
}
|
||||
|
||||
@@ -135,7 +135,7 @@ func (r *Route) RemoveAllowedIPs() error {
|
||||
var merr *multierror.Error
|
||||
for _, domainPrefixes := range r.dynamicDomains {
|
||||
for _, prefix := range domainPrefixes {
|
||||
if _, err := r.allowedIPsRefcounter.Decrement(prefix, r.currentPeerKey); err != nil {
|
||||
if _, err := r.allowedIPsRefcounter.Decrement(prefix); err != nil {
|
||||
merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %w", prefix, err))
|
||||
}
|
||||
}
|
||||
@@ -185,7 +185,7 @@ func (r *Route) startResolver(ctx context.Context) {
|
||||
}
|
||||
|
||||
func (r *Route) update(ctx context.Context) error {
|
||||
resolved, err := r.resolveDomains(ctx)
|
||||
resolved, err := r.resolveDomains()
|
||||
if err != nil {
|
||||
if len(resolved) == 0 {
|
||||
return fmt.Errorf("resolve domains: %w", err)
|
||||
@@ -199,9 +199,9 @@ func (r *Route) update(ctx context.Context) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (r *Route) resolveDomains(ctx context.Context) (domainMap, error) {
|
||||
func (r *Route) resolveDomains() (domainMap, error) {
|
||||
results := make(chan resolveResult)
|
||||
go r.resolve(ctx, results)
|
||||
go r.resolve(results)
|
||||
|
||||
resolved := domainMap{}
|
||||
var merr *multierror.Error
|
||||
@@ -217,7 +217,7 @@ func (r *Route) resolveDomains(ctx context.Context) (domainMap, error) {
|
||||
return resolved, nberrors.FormatErrorOrNil(merr)
|
||||
}
|
||||
|
||||
func (r *Route) resolve(ctx context.Context, results chan resolveResult) {
|
||||
func (r *Route) resolve(results chan resolveResult) {
|
||||
var wg sync.WaitGroup
|
||||
|
||||
for _, d := range r.route.Domains {
|
||||
@@ -225,10 +225,10 @@ func (r *Route) resolve(ctx context.Context, results chan resolveResult) {
|
||||
go func(domain domain.Domain) {
|
||||
defer wg.Done()
|
||||
|
||||
ips, err := r.getIPsFromResolver(ctx, domain)
|
||||
ips, err := r.getIPsFromResolver(domain)
|
||||
if err != nil {
|
||||
log.Tracef("Failed to resolve domain %s with private resolver: %v", domain.SafeString(), err)
|
||||
ips, err = lookupHostIPs(ctx, domain)
|
||||
ips, err = net.LookupIP(domain.PunycodeString())
|
||||
if err != nil {
|
||||
results <- resolveResult{domain: domain, err: fmt.Errorf("resolve d %s: %w", domain.SafeString(), err)}
|
||||
return
|
||||
@@ -320,7 +320,7 @@ func (r *Route) removeRoutes(prefixes []netip.Prefix) ([]netip.Prefix, error) {
|
||||
merr = multierror.Append(merr, fmt.Errorf("remove dynamic route for IP %s: %w", prefix, err))
|
||||
}
|
||||
if r.currentPeerKey != "" {
|
||||
if _, err := r.allowedIPsRefcounter.Decrement(prefix, r.currentPeerKey); err != nil {
|
||||
if _, err := r.allowedIPsRefcounter.Decrement(prefix); err != nil {
|
||||
merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %w", prefix, err))
|
||||
}
|
||||
}
|
||||
@@ -364,20 +364,6 @@ func determinePrefixChanges(oldPrefixes, newPrefixes []netip.Prefix) (toAdd, toR
|
||||
return
|
||||
}
|
||||
|
||||
// lookupHostIPs resolves d via the system resolver, honoring ctx cancellation.
|
||||
func lookupHostIPs(ctx context.Context, d domain.Domain) ([]net.IP, error) {
|
||||
addrs, err := net.DefaultResolver.LookupIPAddr(ctx, d.PunycodeString())
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
ips := make([]net.IP, 0, len(addrs))
|
||||
for _, addr := range addrs {
|
||||
ips = append(ips, addr.IP)
|
||||
}
|
||||
return ips, nil
|
||||
}
|
||||
|
||||
func combinePrefixes(oldPrefixes, removedPrefixes, addedPrefixes []netip.Prefix) []netip.Prefix {
|
||||
prefixSet := make(map[netip.Prefix]struct{})
|
||||
for _, prefix := range oldPrefixes {
|
||||
|
||||
@@ -3,12 +3,11 @@
|
||||
package dynamic
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net"
|
||||
|
||||
"github.com/netbirdio/netbird/shared/management/domain"
|
||||
)
|
||||
|
||||
func (r *Route) getIPsFromResolver(ctx context.Context, domain domain.Domain) ([]net.IP, error) {
|
||||
return lookupHostIPs(ctx, domain)
|
||||
func (r *Route) getIPsFromResolver(domain domain.Domain) ([]net.IP, error) {
|
||||
return net.LookupIP(domain.PunycodeString())
|
||||
}
|
||||
|
||||
@@ -3,7 +3,6 @@
|
||||
package dynamic
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"net"
|
||||
"time"
|
||||
@@ -17,7 +16,7 @@ import (
|
||||
|
||||
const dialTimeout = 10 * time.Second
|
||||
|
||||
func (r *Route) getIPsFromResolver(ctx context.Context, domain domain.Domain) ([]net.IP, error) {
|
||||
func (r *Route) getIPsFromResolver(domain domain.Domain) ([]net.IP, error) {
|
||||
privateClient, err := nbdns.GetClientPrivate(r.wgInterface, r.resolverAddr.Addr(), dialTimeout)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("error while creating private client: %s", err)
|
||||
@@ -33,7 +32,7 @@ func (r *Route) getIPsFromResolver(ctx context.Context, domain domain.Domain) ([
|
||||
msg := new(dns.Msg)
|
||||
msg.SetQuestion(fqdn, qtype)
|
||||
|
||||
response, _, err := nbdns.ExchangeWithFallback(ctx, privateClient, msg, r.resolverAddr.String())
|
||||
response, _, err := nbdns.ExchangeWithFallback(nil, privateClient, msg, r.resolverAddr.String())
|
||||
if err != nil {
|
||||
if queryErr == nil {
|
||||
queryErr = fmt.Errorf("DNS query for %s (type %d) after %s: %w", domain.SafeString(), qtype, time.Since(startTime), err)
|
||||
|
||||
@@ -52,10 +52,6 @@ type Manager interface {
|
||||
UpdateRoutes(updateSerial uint64, serverRoutes map[route.ID]*route.Route, clientRoutes route.HAMap, useNewDNSRoute bool) error
|
||||
ClassifyRoutes(newRoutes []*route.Route) (map[route.ID]*route.Route, route.HAMap)
|
||||
TriggerSelection(route.HAMap)
|
||||
SelectRoutes(ids []route.NetID, appendRoute bool) error
|
||||
DeselectRoutes(ids []route.NetID) error
|
||||
SelectAllRoutes()
|
||||
DeselectAllRoutes()
|
||||
GetRouteSelector() *routeselector.RouteSelector
|
||||
GetClientRoutes() route.HAMap
|
||||
GetSelectedClientRoutes() route.HAMap
|
||||
@@ -65,7 +61,6 @@ type Manager interface {
|
||||
InitialRouteRange() []string
|
||||
SetFirewall(firewall.Manager) error
|
||||
SetDNSForwarderPort(port uint16)
|
||||
ReconcilePeerAllowedIPs(peerKey string) error
|
||||
Stop(stateManager *statemanager.Manager)
|
||||
}
|
||||
|
||||
@@ -220,7 +215,7 @@ func (m *DefaultManager) setupRefCounters(useNoop bool) {
|
||||
)
|
||||
}
|
||||
|
||||
m.allowedIPsRefCounter = refcounter.NewAllowedIPs(
|
||||
m.allowedIPsRefCounter = refcounter.New(
|
||||
func(prefix netip.Prefix, peerKey string) (string, error) {
|
||||
// save peerKey to use it in the remove function
|
||||
return peerKey, m.wgInterface.AddAllowedIP(peerKey, prefix)
|
||||
@@ -237,30 +232,6 @@ func (m *DefaultManager) setupRefCounters(useNoop bool) {
|
||||
)
|
||||
}
|
||||
|
||||
// ReconcilePeerAllowedIPs re-applies every routed allowed IP currently tracked for the peer
|
||||
// onto the WireGuard device. The allowed-IP refcounter only calls its AddFunc (which pushes to
|
||||
// the device) on a prefix's 0->1 transition, so a peer whose device entry was rebuilt without a
|
||||
// matching refcounter change — e.g. a lazy connection cycling through idle->wake, which recreates
|
||||
// the WireGuard peer with the overlay /32 only — ends up missing routed prefixes the refcounter
|
||||
// still considers installed, and nothing retries. Calling this when the peer's WireGuard entry is
|
||||
// (re)created restores convergence. It is add-only and idempotent: AddAllowedIP is update-only, so
|
||||
// prefixes are re-added to an existing peer and an absent peer is left untouched.
|
||||
func (m *DefaultManager) ReconcilePeerAllowedIPs(peerKey string) error {
|
||||
if m.allowedIPsRefCounter == nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
return m.allowedIPsRefCounter.ReapplyMatching(
|
||||
func(out string) bool { return out == peerKey },
|
||||
func(prefix netip.Prefix) error {
|
||||
if err := m.wgInterface.AddAllowedIP(peerKey, prefix); err != nil {
|
||||
return fmt.Errorf("add allowed IP %s for peer %s: %w", prefix, peerKey, err)
|
||||
}
|
||||
return nil
|
||||
},
|
||||
)
|
||||
}
|
||||
|
||||
// Init sets up the routing
|
||||
func (m *DefaultManager) Init() error {
|
||||
m.routeSelector = m.initSelector()
|
||||
@@ -804,7 +775,7 @@ func (m *DefaultManager) collectExitNodeInfo(clientRoutes route.HAMap) exitNodeI
|
||||
var info exitNodeInfo
|
||||
|
||||
for haID, routes := range clientRoutes {
|
||||
if !isExitNodeRoutes(routes) {
|
||||
if !m.isExitNodeRoute(routes) {
|
||||
continue
|
||||
}
|
||||
|
||||
@@ -824,6 +795,13 @@ func (m *DefaultManager) collectExitNodeInfo(clientRoutes route.HAMap) exitNodeI
|
||||
return info
|
||||
}
|
||||
|
||||
func (m *DefaultManager) isExitNodeRoute(routes []*route.Route) bool {
|
||||
if len(routes) == 0 {
|
||||
return false
|
||||
}
|
||||
return route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network)
|
||||
}
|
||||
|
||||
func (m *DefaultManager) categorizeUserSelection(netID route.NetID, info *exitNodeInfo) {
|
||||
if m.routeSelector.IsSelected(netID) {
|
||||
info.userSelected = append(info.userSelected, netID)
|
||||
|
||||
@@ -16,8 +16,6 @@ type MockManager struct {
|
||||
ClassifyRoutesFunc func(routes []*route.Route) (map[route.ID]*route.Route, route.HAMap)
|
||||
UpdateRoutesFunc func(updateSerial uint64, serverRoutes map[route.ID]*route.Route, clientRoutes route.HAMap, useNewDNSRoute bool) error
|
||||
TriggerSelectionFunc func(haMap route.HAMap)
|
||||
SelectRoutesFunc func(ids []route.NetID, appendRoute bool) error
|
||||
DeselectRoutesFunc func(ids []route.NetID) error
|
||||
GetRouteSelectorFunc func() *routeselector.RouteSelector
|
||||
GetClientRoutesFunc func() route.HAMap
|
||||
GetSelectedClientRoutesFunc func() route.HAMap
|
||||
@@ -57,30 +55,6 @@ func (m *MockManager) TriggerSelection(networks route.HAMap) {
|
||||
}
|
||||
}
|
||||
|
||||
// SelectRoutes mock implementation of SelectRoutes from Manager interface
|
||||
func (m *MockManager) SelectRoutes(ids []route.NetID, appendRoute bool) error {
|
||||
if m.SelectRoutesFunc != nil {
|
||||
return m.SelectRoutesFunc(ids, appendRoute)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// DeselectRoutes mock implementation of DeselectRoutes from Manager interface
|
||||
func (m *MockManager) DeselectRoutes(ids []route.NetID) error {
|
||||
if m.DeselectRoutesFunc != nil {
|
||||
return m.DeselectRoutesFunc(ids)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// SelectAllRoutes mock implementation of SelectAllRoutes from Manager interface
|
||||
func (m *MockManager) SelectAllRoutes() {
|
||||
}
|
||||
|
||||
// DeselectAllRoutes mock implementation of DeselectAllRoutes from Manager interface
|
||||
func (m *MockManager) DeselectAllRoutes() {
|
||||
}
|
||||
|
||||
// GetRouteSelector mock implementation of GetRouteSelector from Manager interface
|
||||
func (m *MockManager) GetRouteSelector() *routeselector.RouteSelector {
|
||||
if m.GetRouteSelectorFunc != nil {
|
||||
@@ -138,11 +112,6 @@ func (m *MockManager) SetFirewall(firewall.Manager) error {
|
||||
func (m *MockManager) SetDNSForwarderPort(port uint16) {
|
||||
}
|
||||
|
||||
// ReconcilePeerAllowedIPs mock implementation of ReconcilePeerAllowedIPs from Manager interface
|
||||
func (m *MockManager) ReconcilePeerAllowedIPs(peerKey string) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// Stop mock implementation of Stop from Manager interface
|
||||
func (m *MockManager) Stop(stateManager *statemanager.Manager) {
|
||||
if m.StopFunc != nil {
|
||||
|
||||
@@ -3,6 +3,7 @@
|
||||
package notifier
|
||||
|
||||
import (
|
||||
"container/list"
|
||||
"net/netip"
|
||||
"slices"
|
||||
"sort"
|
||||
@@ -15,12 +16,20 @@ import (
|
||||
|
||||
type Notifier struct {
|
||||
mu sync.Mutex
|
||||
cond *sync.Cond
|
||||
currentPrefixes []string
|
||||
listener listener.NetworkChangeListener
|
||||
queue *list.List
|
||||
closed bool
|
||||
}
|
||||
|
||||
func NewNotifier() *Notifier {
|
||||
return &Notifier{}
|
||||
n := &Notifier{
|
||||
queue: list.New(),
|
||||
}
|
||||
n.cond = sync.NewCond(&n.mu)
|
||||
go n.deliverLoop()
|
||||
return n
|
||||
}
|
||||
|
||||
func (n *Notifier) SetListener(listener listener.NetworkChangeListener) {
|
||||
@@ -50,19 +59,44 @@ func (n *Notifier) OnNewPrefixes(prefixes []netip.Prefix) {
|
||||
sort.Strings(newNets)
|
||||
|
||||
n.mu.Lock()
|
||||
defer n.mu.Unlock()
|
||||
if slices.Equal(n.currentPrefixes, newNets) {
|
||||
n.mu.Unlock()
|
||||
return
|
||||
}
|
||||
n.currentPrefixes = newNets
|
||||
if n.listener != nil {
|
||||
n.listener.OnNetworkChanged(strings.Join(n.currentPrefixes, ","))
|
||||
}
|
||||
routes := strings.Join(n.currentPrefixes, ",")
|
||||
n.queue.PushBack(routes)
|
||||
n.cond.Signal()
|
||||
n.mu.Unlock()
|
||||
}
|
||||
|
||||
func (n *Notifier) Close() {
|
||||
n.mu.Lock()
|
||||
n.closed = true
|
||||
n.cond.Signal()
|
||||
n.mu.Unlock()
|
||||
}
|
||||
|
||||
func (n *Notifier) GetInitialRouteRanges() []string {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (n *Notifier) deliverLoop() {
|
||||
for {
|
||||
n.mu.Lock()
|
||||
for n.queue.Len() == 0 && !n.closed {
|
||||
n.cond.Wait()
|
||||
}
|
||||
if n.closed && n.queue.Len() == 0 {
|
||||
n.mu.Unlock()
|
||||
return
|
||||
}
|
||||
routes := n.queue.Remove(n.queue.Front()).(string)
|
||||
l := n.listener
|
||||
n.mu.Unlock()
|
||||
|
||||
if l != nil {
|
||||
l.OnNetworkChanged(routes)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,90 +0,0 @@
|
||||
//go:build !windows
|
||||
|
||||
package routemanager
|
||||
|
||||
import (
|
||||
"net"
|
||||
"net/netip"
|
||||
"sync"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
"golang.zx2c4.com/wireguard/tun/netstack"
|
||||
|
||||
"github.com/netbirdio/netbird/client/iface/device"
|
||||
"github.com/netbirdio/netbird/client/iface/wgaddr"
|
||||
"github.com/netbirdio/netbird/client/internal/routemanager/refcounter"
|
||||
)
|
||||
|
||||
// reconcileWGMock is a minimal iface.WGIface that only records AddAllowedIP calls; every other
|
||||
// method is an inert stub because ReconcilePeerAllowedIPs exercises none of them.
|
||||
type reconcileWGMock struct {
|
||||
mu sync.Mutex
|
||||
adds map[string][]netip.Prefix
|
||||
}
|
||||
|
||||
func (m *reconcileWGMock) AddAllowedIP(peerKey string, allowedIP netip.Prefix) error {
|
||||
m.mu.Lock()
|
||||
defer m.mu.Unlock()
|
||||
if m.adds == nil {
|
||||
m.adds = map[string][]netip.Prefix{}
|
||||
}
|
||||
m.adds[peerKey] = append(m.adds[peerKey], allowedIP)
|
||||
return nil
|
||||
}
|
||||
|
||||
func (m *reconcileWGMock) added(peerKey string) []netip.Prefix {
|
||||
m.mu.Lock()
|
||||
defer m.mu.Unlock()
|
||||
return m.adds[peerKey]
|
||||
}
|
||||
|
||||
func (m *reconcileWGMock) RemoveAllowedIP(string, netip.Prefix) error { return nil }
|
||||
func (m *reconcileWGMock) Name() string { return "utun-test" }
|
||||
func (m *reconcileWGMock) Address() wgaddr.Address { return wgaddr.Address{} }
|
||||
func (m *reconcileWGMock) ToInterface() *net.Interface { return nil }
|
||||
func (m *reconcileWGMock) IsUserspaceBind() bool { return false }
|
||||
func (m *reconcileWGMock) GetFilter() device.PacketFilter { return nil }
|
||||
func (m *reconcileWGMock) GetDevice() *device.FilteredDevice { return nil }
|
||||
func (m *reconcileWGMock) GetNet() *netstack.Net { return nil }
|
||||
|
||||
// TestReconcilePeerAllowedIPs verifies the declarative reconcile re-applies every routed prefix
|
||||
// tracked for the peer (self-heal, independent of refcount level) and stays scoped to that peer.
|
||||
func TestReconcilePeerAllowedIPs(t *testing.T) {
|
||||
wg := &reconcileWGMock{}
|
||||
m := &DefaultManager{wgInterface: wg}
|
||||
m.allowedIPsRefCounter = refcounter.NewAllowedIPs(
|
||||
func(_ netip.Prefix, peerKey string) (string, error) { return peerKey, nil },
|
||||
func(netip.Prefix, string) error { return nil },
|
||||
)
|
||||
|
||||
peerA1 := netip.MustParsePrefix("10.0.0.0/24")
|
||||
peerA2 := netip.MustParsePrefix("10.1.0.0/24")
|
||||
peerB1 := netip.MustParsePrefix("10.2.0.0/24")
|
||||
|
||||
for prefix, peer := range map[netip.Prefix]string{peerA1: "peerA", peerA2: "peerA", peerB1: "peerB"} {
|
||||
_, err := m.allowedIPsRefCounter.Increment(prefix, peer)
|
||||
require.NoError(t, err)
|
||||
}
|
||||
// Extra reference: reconcile must still re-apply the prefix even though its refcount never
|
||||
// hit 0 again (the exact case the plain incremental path skips).
|
||||
_, err := m.allowedIPsRefCounter.Increment(peerA1, "peerA")
|
||||
require.NoError(t, err)
|
||||
|
||||
require.NoError(t, m.ReconcilePeerAllowedIPs("peerA"))
|
||||
|
||||
assert.ElementsMatch(t, []netip.Prefix{peerA1, peerA2}, wg.added("peerA"),
|
||||
"reconcile must re-apply all routed prefixes of the peer")
|
||||
assert.Empty(t, wg.added("peerB"), "reconcile must not touch another peer's prefixes")
|
||||
}
|
||||
|
||||
// TestReconcilePeerAllowedIPsNoCounter verifies reconcile is a safe no-op before the refcounter is
|
||||
// set up.
|
||||
func TestReconcilePeerAllowedIPsNoCounter(t *testing.T) {
|
||||
wg := &reconcileWGMock{}
|
||||
m := &DefaultManager{wgInterface: wg}
|
||||
|
||||
require.NoError(t, m.ReconcilePeerAllowedIPs("peerA"))
|
||||
assert.Empty(t, wg.added("peerA"))
|
||||
}
|
||||
@@ -1,206 +0,0 @@
|
||||
package refcounter
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"net/netip"
|
||||
"sort"
|
||||
"sync"
|
||||
|
||||
"github.com/hashicorp/go-multierror"
|
||||
|
||||
nberrors "github.com/netbirdio/netbird/client/errors"
|
||||
)
|
||||
|
||||
// allowedIPsEntry holds the per-peer reference counts for a single prefix and which peer is
|
||||
// currently installed in WireGuard. WireGuard allows a prefix on exactly one peer, so at most
|
||||
// one peer is active at a time even when several peers reference the prefix.
|
||||
type allowedIPsEntry struct {
|
||||
// peers maps a peerKey to the number of references holding the prefix for that peer.
|
||||
peers map[string]int
|
||||
// active is the peerKey currently installed in WireGuard for this prefix ("" if none).
|
||||
active string
|
||||
// total is the sum of all per-peer reference counts (kept in sync with peers).
|
||||
total int
|
||||
}
|
||||
|
||||
// AllowedIPsRefCounter is a peer-aware reference counter for WireGuard AllowedIPs.
|
||||
//
|
||||
// The generic Counter keys only by prefix and remembers a single Out value set by the first
|
||||
// caller, which it never changes. That is wrong for AllowedIPs: two independent watchers (or
|
||||
// multiple resolved domains) can reference the same prefix through different peers, and when the
|
||||
// peer currently installed in WireGuard releases its last reference the prefix must be handed over
|
||||
// to a surviving peer instead of being left pointing at the released one.
|
||||
//
|
||||
// It calls add/remove (which program WireGuard) only on the transitions that matter:
|
||||
// - add on the first reference for a prefix, or when swapping the active peer;
|
||||
// - remove on the last reference for a prefix, or on the old peer during a swap.
|
||||
type AllowedIPsRefCounter struct {
|
||||
mu sync.Mutex
|
||||
entries map[netip.Prefix]*allowedIPsEntry
|
||||
add AddFunc[netip.Prefix, string, string]
|
||||
remove RemoveFunc[netip.Prefix, string]
|
||||
}
|
||||
|
||||
// NewAllowedIPs creates a new peer-aware AllowedIPs reference counter.
|
||||
// add programs a prefix on a peer in WireGuard and returns the peerKey to store as the active peer.
|
||||
// remove unprograms the prefix from the given peer.
|
||||
func NewAllowedIPs(add AddFunc[netip.Prefix, string, string], remove RemoveFunc[netip.Prefix, string]) *AllowedIPsRefCounter {
|
||||
return &AllowedIPsRefCounter{
|
||||
entries: map[netip.Prefix]*allowedIPsEntry{},
|
||||
add: add,
|
||||
remove: remove,
|
||||
}
|
||||
}
|
||||
|
||||
// Increment adds a reference to prefix for peerKey. WireGuard is programmed only for the first
|
||||
// reference to a prefix; while a different peer is already installed the prefix is left with it
|
||||
// (first peer wins, HA at the WireGuard layer is not possible) and only the reference count is kept.
|
||||
func (rm *AllowedIPsRefCounter) Increment(prefix netip.Prefix, peerKey string) (Ref[string], error) {
|
||||
rm.mu.Lock()
|
||||
defer rm.mu.Unlock()
|
||||
|
||||
e, ok := rm.entries[prefix]
|
||||
if !ok {
|
||||
e = &allowedIPsEntry{peers: map[string]int{}}
|
||||
rm.entries[prefix] = e
|
||||
}
|
||||
|
||||
logCallerF("Increasing allowed IP ref count for prefix %v peer %s [peer %d -> %d, total %d -> %d, active %q]",
|
||||
prefix, peerKey, e.peers[peerKey], e.peers[peerKey]+1, e.total, e.total+1, e.active)
|
||||
|
||||
// Program WireGuard only when nothing is installed yet for this prefix.
|
||||
if e.active == "" {
|
||||
out, err := rm.add(prefix, peerKey)
|
||||
if errors.Is(err, ErrIgnore) {
|
||||
if e.total == 0 {
|
||||
delete(rm.entries, prefix)
|
||||
}
|
||||
return Ref[string]{Count: e.total, Out: e.active}, nil
|
||||
}
|
||||
if err != nil {
|
||||
if e.total == 0 {
|
||||
delete(rm.entries, prefix)
|
||||
}
|
||||
return Ref[string]{}, fmt.Errorf("failed to add allowed IP %v for peer %s: %w", prefix, peerKey, err)
|
||||
}
|
||||
e.active = out
|
||||
}
|
||||
|
||||
e.peers[peerKey]++
|
||||
e.total++
|
||||
|
||||
return Ref[string]{Count: e.total, Out: e.active}, nil
|
||||
}
|
||||
|
||||
// Decrement removes a reference to prefix for peerKey. When the peer currently installed in
|
||||
// WireGuard releases its last reference, the prefix is swapped to a surviving peer if one exists,
|
||||
// otherwise it is removed from WireGuard.
|
||||
func (rm *AllowedIPsRefCounter) Decrement(prefix netip.Prefix, peerKey string) (Ref[string], error) {
|
||||
rm.mu.Lock()
|
||||
defer rm.mu.Unlock()
|
||||
|
||||
e, ok := rm.entries[prefix]
|
||||
if !ok {
|
||||
logCallerF("No allowed IP reference found for prefix %v", prefix)
|
||||
return Ref[string]{}, nil
|
||||
}
|
||||
|
||||
if e.peers[peerKey] > 0 {
|
||||
logCallerF("Decreasing allowed IP ref count for prefix %v peer %s [peer %d -> %d, total %d -> %d, active %q]",
|
||||
prefix, peerKey, e.peers[peerKey], e.peers[peerKey]-1, e.total, e.total-1, e.active)
|
||||
e.peers[peerKey]--
|
||||
e.total--
|
||||
if e.peers[peerKey] == 0 {
|
||||
delete(e.peers, peerKey)
|
||||
}
|
||||
} else {
|
||||
logCallerF("No allowed IP reference found for prefix %v peer %s", prefix, peerKey)
|
||||
}
|
||||
|
||||
// If the peer currently installed in WireGuard still holds references, nothing to reprogram.
|
||||
// Keying the check on the active peer (not the one just released) makes this self-healing:
|
||||
// a prior swap whose remove/add failed leaves e.active pointing at a peer with no references,
|
||||
// and this retries the hand-off on the next Decrement instead of getting stuck.
|
||||
if e.active != "" && e.peers[e.active] > 0 {
|
||||
return Ref[string]{Count: e.total, Out: e.active}, nil
|
||||
}
|
||||
|
||||
// Detach the stale/gone active peer from WireGuard before reprogramming.
|
||||
if e.active != "" {
|
||||
if err := rm.remove(prefix, e.active); err != nil {
|
||||
return Ref[string]{Count: e.total, Out: e.active}, fmt.Errorf("remove allowed IP %v for peer %s: %w", prefix, e.active, err)
|
||||
}
|
||||
e.active = ""
|
||||
}
|
||||
|
||||
// Hand the prefix over to a surviving peer, or drop the entry when none remain.
|
||||
if survivor, ok := pickSurvivor(e.peers); ok {
|
||||
out, err := rm.add(prefix, survivor)
|
||||
if err != nil {
|
||||
return Ref[string]{Count: e.total, Out: ""}, fmt.Errorf("swap allowed IP %v to peer %s: %w", prefix, survivor, err)
|
||||
}
|
||||
e.active = out
|
||||
return Ref[string]{Count: e.total, Out: e.active}, nil
|
||||
}
|
||||
|
||||
delete(rm.entries, prefix)
|
||||
return Ref[string]{Count: 0, Out: ""}, nil
|
||||
}
|
||||
|
||||
// Flush removes all prefixes from WireGuard and clears the counter.
|
||||
func (rm *AllowedIPsRefCounter) Flush() error {
|
||||
rm.mu.Lock()
|
||||
defer rm.mu.Unlock()
|
||||
|
||||
var merr *multierror.Error
|
||||
for prefix, e := range rm.entries {
|
||||
if e.active == "" {
|
||||
continue
|
||||
}
|
||||
logCallerF("Flushing allowed IP for prefix %v peer %s", prefix, e.active)
|
||||
if err := rm.remove(prefix, e.active); err != nil {
|
||||
merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %v for peer %s: %w", prefix, e.active, err))
|
||||
}
|
||||
}
|
||||
|
||||
clear(rm.entries)
|
||||
|
||||
return nberrors.FormatErrorOrNil(merr)
|
||||
}
|
||||
|
||||
// ReapplyMatching calls apply for every prefix whose currently installed (active) peer satisfies
|
||||
// pred, holding the lock for the whole pass. It is used to re-push allowed IPs onto a peer whose
|
||||
// WireGuard entry was rebuilt (e.g. a lazy connection cycling idle->wake) without a matching
|
||||
// refcounter change, which would otherwise leave the prefix installed in the counter but missing
|
||||
// on the device. Only the active peer is considered — a prefix that lost its installed peer to a
|
||||
// failed swap is skipped here and reconciled by the next Increment/Decrement.
|
||||
func (rm *AllowedIPsRefCounter) ReapplyMatching(pred func(out string) bool, apply func(key netip.Prefix) error) error {
|
||||
rm.mu.Lock()
|
||||
defer rm.mu.Unlock()
|
||||
|
||||
var merr *multierror.Error
|
||||
for prefix, e := range rm.entries {
|
||||
if e.active != "" && pred(e.active) {
|
||||
if err := apply(prefix); err != nil {
|
||||
merr = multierror.Append(merr, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
return nberrors.FormatErrorOrNil(merr)
|
||||
}
|
||||
|
||||
// pickSurvivor deterministically selects a peer still referencing the prefix. WireGuard cannot do
|
||||
// multipath for a single prefix, so any surviving peer is a valid winner; the choice is made stable
|
||||
// (lowest peerKey) for predictable behavior and testability.
|
||||
func pickSurvivor(peers map[string]int) (string, bool) {
|
||||
if len(peers) == 0 {
|
||||
return "", false
|
||||
}
|
||||
keys := make([]string, 0, len(peers))
|
||||
for k := range peers {
|
||||
keys = append(keys, k)
|
||||
}
|
||||
sort.Strings(keys)
|
||||
return keys[0], true
|
||||
}
|
||||
@@ -1,241 +0,0 @@
|
||||
package refcounter
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"net/netip"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// fakeWG models WireGuard's cryptokey routing: a prefix can be installed on exactly one peer.
|
||||
// failAdd/failRemove make the next add/remove fail once, to exercise the self-healing error paths.
|
||||
type fakeWG struct {
|
||||
installed map[netip.Prefix]string
|
||||
adds int
|
||||
removes int
|
||||
failAdd bool
|
||||
failRemove bool
|
||||
}
|
||||
|
||||
func newFakeWG() *fakeWG {
|
||||
return &fakeWG{installed: map[netip.Prefix]string{}}
|
||||
}
|
||||
|
||||
func (f *fakeWG) counter() *AllowedIPsRefCounter {
|
||||
return NewAllowedIPs(
|
||||
func(prefix netip.Prefix, peerKey string) (string, error) {
|
||||
if f.failAdd {
|
||||
f.failAdd = false
|
||||
return "", errors.New("add failed")
|
||||
}
|
||||
f.adds++
|
||||
f.installed[prefix] = peerKey
|
||||
return peerKey, nil
|
||||
},
|
||||
func(prefix netip.Prefix, peerKey string) error {
|
||||
if f.failRemove {
|
||||
f.failRemove = false
|
||||
return errors.New("remove failed")
|
||||
}
|
||||
f.removes++
|
||||
// only clear if this peer is the one installed, mirroring wg semantics
|
||||
if f.installed[prefix] == peerKey {
|
||||
delete(f.installed, prefix)
|
||||
}
|
||||
return nil
|
||||
},
|
||||
)
|
||||
}
|
||||
|
||||
func mustPrefix(t *testing.T, s string) netip.Prefix {
|
||||
t.Helper()
|
||||
p, err := netip.ParsePrefix(s)
|
||||
if err != nil {
|
||||
t.Fatalf("parse prefix %q: %v", s, err)
|
||||
}
|
||||
return p
|
||||
}
|
||||
|
||||
func mustIncrement(t *testing.T, c *AllowedIPsRefCounter, p netip.Prefix, peer string) Ref[string] {
|
||||
t.Helper()
|
||||
ref, err := c.Increment(p, peer)
|
||||
if err != nil {
|
||||
t.Fatalf("Increment(%v, %s): %v", p, peer, err)
|
||||
}
|
||||
return ref
|
||||
}
|
||||
|
||||
func mustDecrement(t *testing.T, c *AllowedIPsRefCounter, p netip.Prefix, peer string) Ref[string] {
|
||||
t.Helper()
|
||||
ref, err := c.Decrement(p, peer)
|
||||
if err != nil {
|
||||
t.Fatalf("Decrement(%v, %s): %v", p, peer, err)
|
||||
}
|
||||
return ref
|
||||
}
|
||||
|
||||
// TestAllowedIPs_SwapOnActivePeerRemoval reproduces the reported bug: two networks with the same
|
||||
// prefix routed by different peers. Removing the network whose peer is installed must hand the
|
||||
// prefix over to the surviving peer instead of leaving it on the removed one.
|
||||
func TestAllowedIPs_SwapOnActivePeerRemoval(t *testing.T) {
|
||||
f := newFakeWG()
|
||||
c := f.counter()
|
||||
p := mustPrefix(t, "10.44.8.0/24")
|
||||
|
||||
mustIncrement(t, c, p, "peerA")
|
||||
mustIncrement(t, c, p, "peerB")
|
||||
// First peer wins while both are present.
|
||||
if got := f.installed[p]; got != "peerA" {
|
||||
t.Fatalf("expected peerA installed, got %q", got)
|
||||
}
|
||||
|
||||
// Remove the active peer's network -> must swap to peerB.
|
||||
mustDecrement(t, c, p, "peerA")
|
||||
if got := f.installed[p]; got != "peerB" {
|
||||
t.Fatalf("BUG: prefix stuck on removed peer, want peerB got %q", got)
|
||||
}
|
||||
|
||||
// Remove the last one -> prefix gone.
|
||||
mustDecrement(t, c, p, "peerB")
|
||||
if _, ok := f.installed[p]; ok {
|
||||
t.Fatalf("expected prefix removed, still installed on %q", f.installed[p])
|
||||
}
|
||||
}
|
||||
|
||||
// TestAllowedIPs_RemoveNonActivePeer removing a non-installed peer must not touch WireGuard.
|
||||
func TestAllowedIPs_RemoveNonActivePeer(t *testing.T) {
|
||||
f := newFakeWG()
|
||||
c := f.counter()
|
||||
p := mustPrefix(t, "10.44.8.0/24")
|
||||
|
||||
mustIncrement(t, c, p, "peerA")
|
||||
mustIncrement(t, c, p, "peerB")
|
||||
removesBefore := f.removes
|
||||
|
||||
mustDecrement(t, c, p, "peerB")
|
||||
if f.installed[p] != "peerA" {
|
||||
t.Fatalf("active peer must stay peerA, got %q", f.installed[p])
|
||||
}
|
||||
if f.removes != removesBefore {
|
||||
t.Fatalf("removing a non-active peer must not call wg remove")
|
||||
}
|
||||
}
|
||||
|
||||
// TestAllowedIPs_SamePeerMultipleRefs two references via the same peer must keep the prefix until
|
||||
// the last reference is released (the reason the per-peer count must be an int, not a set).
|
||||
func TestAllowedIPs_SamePeerMultipleRefs(t *testing.T) {
|
||||
f := newFakeWG()
|
||||
c := f.counter()
|
||||
p := mustPrefix(t, "10.44.8.0/24")
|
||||
|
||||
mustIncrement(t, c, p, "peerA")
|
||||
mustIncrement(t, c, p, "peerA")
|
||||
if f.adds != 1 {
|
||||
t.Fatalf("expected a single wg add for the same peer, got %d", f.adds)
|
||||
}
|
||||
|
||||
mustDecrement(t, c, p, "peerA")
|
||||
if f.installed[p] != "peerA" {
|
||||
t.Fatalf("prefix must stay while a reference remains, got %q", f.installed[p])
|
||||
}
|
||||
if f.removes != 0 {
|
||||
t.Fatalf("no wg remove expected while a reference remains, got %d", f.removes)
|
||||
}
|
||||
|
||||
mustDecrement(t, c, p, "peerA")
|
||||
if _, ok := f.installed[p]; ok {
|
||||
t.Fatalf("prefix must be removed after last reference")
|
||||
}
|
||||
}
|
||||
|
||||
// TestAllowedIPs_RefCountAndActive checks the Ref returned to callers (used for the HA-disabled log).
|
||||
func TestAllowedIPs_RefCountAndActive(t *testing.T) {
|
||||
f := newFakeWG()
|
||||
c := f.counter()
|
||||
p := mustPrefix(t, "10.44.8.0/24")
|
||||
|
||||
ref := mustIncrement(t, c, p, "peerA")
|
||||
if ref.Count != 1 || ref.Out != "peerA" {
|
||||
t.Fatalf("want {1, peerA}, got {%d, %q}", ref.Count, ref.Out)
|
||||
}
|
||||
ref = mustIncrement(t, c, p, "peerB")
|
||||
if ref.Count != 2 || ref.Out != "peerA" {
|
||||
t.Fatalf("want {2, peerA}, got {%d, %q}", ref.Count, ref.Out)
|
||||
}
|
||||
}
|
||||
|
||||
// TestAllowedIPs_Flush removes everything installed and clears the counter.
|
||||
func TestAllowedIPs_Flush(t *testing.T) {
|
||||
f := newFakeWG()
|
||||
c := f.counter()
|
||||
p1 := mustPrefix(t, "10.44.8.0/24")
|
||||
p2 := mustPrefix(t, "10.44.9.0/24")
|
||||
|
||||
mustIncrement(t, c, p1, "peerA")
|
||||
mustIncrement(t, c, p2, "peerB")
|
||||
|
||||
if err := c.Flush(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(f.installed) != 0 {
|
||||
t.Fatalf("expected all prefixes removed, got %v", f.installed)
|
||||
}
|
||||
// After flush, a fresh increment must add again.
|
||||
mustIncrement(t, c, p1, "peerC")
|
||||
if f.installed[p1] != "peerC" {
|
||||
t.Fatalf("counter not reset after flush")
|
||||
}
|
||||
}
|
||||
|
||||
// TestAllowedIPs_SelfHealAfterSwapAddError ensures a failed add during a swap does not permanently
|
||||
// strand the prefix: the next Decrement (or Increment) must retry and install a surviving peer.
|
||||
func TestAllowedIPs_SelfHealAfterSwapAddError(t *testing.T) {
|
||||
f := newFakeWG()
|
||||
c := f.counter()
|
||||
p := mustPrefix(t, "10.44.8.0/24")
|
||||
|
||||
mustIncrement(t, c, p, "peerA")
|
||||
mustIncrement(t, c, p, "peerB")
|
||||
mustIncrement(t, c, p, "peerC")
|
||||
|
||||
// Removing the active peerA triggers a swap to a survivor; make the add fail once.
|
||||
f.failAdd = true
|
||||
if _, err := c.Decrement(p, "peerA"); err == nil {
|
||||
t.Fatalf("expected error from failed swap add")
|
||||
}
|
||||
if _, ok := f.installed[p]; ok {
|
||||
t.Fatalf("nothing should be installed after a failed swap add, got %q", f.installed[p])
|
||||
}
|
||||
|
||||
// A later Decrement of a non-active survivor must retry the hand-off (self-heal), not stay stuck.
|
||||
ref := mustDecrement(t, c, p, "peerC")
|
||||
if got := f.installed[p]; got == "" {
|
||||
t.Fatalf("self-heal failed: prefix left unrouted after add recovered")
|
||||
}
|
||||
if ref.Out == "" {
|
||||
t.Fatalf("expected an active peer after self-heal, got empty")
|
||||
}
|
||||
}
|
||||
|
||||
// TestAllowedIPs_SelfHealAfterRemoveError ensures a failed remove during a swap is retried instead
|
||||
// of leaving e.active stuck on a peer that no longer holds references.
|
||||
func TestAllowedIPs_SelfHealAfterRemoveError(t *testing.T) {
|
||||
f := newFakeWG()
|
||||
c := f.counter()
|
||||
p := mustPrefix(t, "10.44.8.0/24")
|
||||
|
||||
mustIncrement(t, c, p, "peerA")
|
||||
mustIncrement(t, c, p, "peerB")
|
||||
|
||||
// Releasing active peerA must detach it (remove) then add peerB; fail the remove once.
|
||||
f.failRemove = true
|
||||
if _, err := c.Decrement(p, "peerA"); err == nil {
|
||||
t.Fatalf("expected error from failed remove")
|
||||
}
|
||||
|
||||
// Next Decrement of the non-active survivor retries: removes stale peerA, installs peerB.
|
||||
mustDecrement(t, c, p, "peerB")
|
||||
// peerB had only one ref, so after retry the prefix is fully released.
|
||||
if _, ok := f.installed[p]; ok {
|
||||
t.Fatalf("expected prefix released after self-heal, still on %q", f.installed[p])
|
||||
}
|
||||
}
|
||||
@@ -94,26 +94,6 @@ func (rm *Counter[Key, I, O]) Get(key Key) (Ref[O], bool) {
|
||||
return ref, ok
|
||||
}
|
||||
|
||||
// ReapplyMatching calls apply for every key whose stored Out satisfies pred, holding the
|
||||
// counter lock for the whole pass. Running apply under the lock keeps it atomic with respect
|
||||
// to Increment/Decrement: a prefix dropped to zero is removed from the map (and had its
|
||||
// RemoveFunc called) before this pass observes it, so a stale key can never be re-applied.
|
||||
// pred and apply are invoked under the lock, so they must not call back into the counter.
|
||||
func (rm *Counter[Key, I, O]) ReapplyMatching(pred func(out O) bool, apply func(key Key) error) error {
|
||||
rm.mu.Lock()
|
||||
defer rm.mu.Unlock()
|
||||
|
||||
var merr *multierror.Error
|
||||
for key, ref := range rm.refCountMap {
|
||||
if pred(ref.Out) {
|
||||
if err := apply(key); err != nil {
|
||||
merr = multierror.Append(merr, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
return nberrors.FormatErrorOrNil(merr)
|
||||
}
|
||||
|
||||
// Increment increments the reference count for the given key.
|
||||
// If this is the first reference to the key, the AddFunc is called.
|
||||
func (rm *Counter[Key, I, O]) Increment(key Key, in I) (Ref[O], error) {
|
||||
|
||||
@@ -1,47 +0,0 @@
|
||||
package refcounter
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// TestReapplyMatching verifies ReapplyMatching invokes apply for exactly the keys whose stored
|
||||
// Out satisfies the predicate (no duplicates for multiply-referenced keys) — the primitive
|
||||
// ReconcilePeerAllowedIPs relies on to re-apply a single peer's routed prefixes.
|
||||
func TestReapplyMatching(t *testing.T) {
|
||||
rc := New[netip.Prefix, string, string](
|
||||
func(_ netip.Prefix, peerKey string) (string, error) { return peerKey, nil },
|
||||
func(netip.Prefix, string) error { return nil },
|
||||
)
|
||||
|
||||
peerA1 := netip.MustParsePrefix("10.0.0.0/24")
|
||||
peerA2 := netip.MustParsePrefix("10.1.0.0/24")
|
||||
peerB1 := netip.MustParsePrefix("10.2.0.0/24")
|
||||
|
||||
for prefix, peer := range map[netip.Prefix]string{peerA1: "peerA", peerA2: "peerA", peerB1: "peerB"} {
|
||||
_, err := rc.Increment(prefix, peer)
|
||||
require.NoError(t, err)
|
||||
}
|
||||
// a second reference must not make the key applied twice
|
||||
_, err := rc.Increment(peerA1, "peerA")
|
||||
require.NoError(t, err)
|
||||
|
||||
var applied []netip.Prefix
|
||||
err = rc.ReapplyMatching(
|
||||
func(out string) bool { return out == "peerA" },
|
||||
func(key netip.Prefix) error { applied = append(applied, key); return nil },
|
||||
)
|
||||
require.NoError(t, err)
|
||||
assert.ElementsMatch(t, []netip.Prefix{peerA1, peerA2}, applied)
|
||||
|
||||
var none []netip.Prefix
|
||||
err = rc.ReapplyMatching(
|
||||
func(out string) bool { return out == "missing" },
|
||||
func(key netip.Prefix) error { none = append(none, key); return nil },
|
||||
)
|
||||
require.NoError(t, err)
|
||||
assert.Empty(t, none)
|
||||
}
|
||||
@@ -5,7 +5,5 @@ import "net/netip"
|
||||
// RouteRefCounter is a Counter for Route, it doesn't take any input on Increment and doesn't use any output on Decrement
|
||||
type RouteRefCounter = Counter[netip.Prefix, struct{}, struct{}]
|
||||
|
||||
// AllowedIPsRefCounter tracks WireGuard AllowedIPs per prefix. Unlike the generic Counter it is peer-aware:
|
||||
// a prefix can be claimed by several peers at once and WireGuard allows a given prefix on exactly one peer,
|
||||
// so the counter records the per-peer reference count and swaps the installed peer when the active one is released.
|
||||
// See allowedips.go.
|
||||
// AllowedIPsRefCounter is a Counter for AllowedIPs, it takes a peer key on Increment and passes it back to Decrement
|
||||
type AllowedIPsRefCounter = Counter[netip.Prefix, string, string]
|
||||
|
||||
@@ -1,138 +0,0 @@
|
||||
package routemanager
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"slices"
|
||||
|
||||
"github.com/hashicorp/go-multierror"
|
||||
log "github.com/sirupsen/logrus"
|
||||
"golang.org/x/exp/maps"
|
||||
|
||||
nberrors "github.com/netbirdio/netbird/client/errors"
|
||||
"github.com/netbirdio/netbird/route"
|
||||
)
|
||||
|
||||
// SelectRoutes selects the routes with the given network IDs and applies the
|
||||
// new selection. V4/v6 exit-node pairs are expanded automatically. Exit nodes
|
||||
// are mutually exclusive: if the selection activates an exit node, every other
|
||||
// available exit node is deselected so two can't be active at once. With
|
||||
// appendRoute=false the previous selection is replaced instead of extended.
|
||||
func (m *DefaultManager) SelectRoutes(ids []route.NetID, appendRoute bool) error {
|
||||
if err := m.selectRoutes(ids, appendRoute); err != nil {
|
||||
return err
|
||||
}
|
||||
m.TriggerSelection(m.GetClientRoutes())
|
||||
return nil
|
||||
}
|
||||
|
||||
// DeselectRoutes removes the routes with the given network IDs from the
|
||||
// selection and applies the change. V4/v6 exit-node pairs are expanded
|
||||
// automatically.
|
||||
func (m *DefaultManager) DeselectRoutes(ids []route.NetID) error {
|
||||
if err := m.deselectRoutes(ids); err != nil {
|
||||
return err
|
||||
}
|
||||
m.TriggerSelection(m.GetClientRoutes())
|
||||
return nil
|
||||
}
|
||||
|
||||
func (m *DefaultManager) deselectRoutes(ids []route.NetID) error {
|
||||
routesMap := m.GetClientRoutesWithNetID()
|
||||
routes := route.ExpandV6ExitPairs(slices.Clone(ids), routesMap)
|
||||
|
||||
log.Debugf("deselecting routes with ids: %v", routes)
|
||||
|
||||
if err := m.routeSelector.DeselectRoutes(routes, maps.Keys(routesMap)); err != nil {
|
||||
return fmt.Errorf("deselect routes: %w", err)
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// SelectAllRoutes selects every available route and applies the selection.
|
||||
// Exit nodes stay mutually exclusive: at most one remains active.
|
||||
func (m *DefaultManager) SelectAllRoutes() {
|
||||
m.selectAllRoutes()
|
||||
m.TriggerSelection(m.GetClientRoutes())
|
||||
}
|
||||
|
||||
func (m *DefaultManager) selectAllRoutes() {
|
||||
m.routeSelector.SelectAllRoutes()
|
||||
|
||||
// Select-all wipes every explicit selection, so exit nodes fall back to
|
||||
// management's auto-apply flags — which may mark several at once.
|
||||
// Reconcile immediately so at most one exit node stays active instead of
|
||||
// waiting for the next network map to enforce it.
|
||||
m.mux.Lock()
|
||||
defer m.mux.Unlock()
|
||||
m.updateRouteSelectorFromManagement(m.clientRoutes)
|
||||
}
|
||||
|
||||
// DeselectAllRoutes deselects every route and applies the change.
|
||||
func (m *DefaultManager) DeselectAllRoutes() {
|
||||
m.routeSelector.DeselectAllRoutes()
|
||||
m.TriggerSelection(m.GetClientRoutes())
|
||||
}
|
||||
|
||||
func (m *DefaultManager) selectRoutes(ids []route.NetID, appendRoute bool) error {
|
||||
routesMap := m.GetClientRoutesWithNetID()
|
||||
routes := route.ExpandV6ExitPairs(slices.Clone(ids), routesMap)
|
||||
allIDs := maps.Keys(routesMap)
|
||||
|
||||
log.Debugf("selecting routes with ids: %v", routes)
|
||||
|
||||
// A partial failure (e.g. an unknown ID in the request) still selects the
|
||||
// valid routes, so exclusivity below must run regardless of the error.
|
||||
var merr *multierror.Error
|
||||
if err := m.routeSelector.SelectRoutes(routes, appendRoute, allIDs); err != nil {
|
||||
merr = multierror.Append(merr, fmt.Errorf("select routes: %w", err))
|
||||
}
|
||||
|
||||
// Exit nodes are mutually exclusive: if this selection activates an
|
||||
// exit node, deselect every other available exit node so two can't be
|
||||
// selected at once. Non-exit route selections are left untouched.
|
||||
if requestActivatesExitNode(routes, routesMap) {
|
||||
if others := otherExitNodeIDs(routesMap, routes); len(others) > 0 {
|
||||
if err := m.routeSelector.DeselectRoutes(others, allIDs); err != nil {
|
||||
merr = multierror.Append(merr, fmt.Errorf("deselect sibling exit nodes: %w", err))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return nberrors.FormatErrorOrNil(merr)
|
||||
}
|
||||
|
||||
func isExitNodeRoutes(routes []*route.Route) bool {
|
||||
return len(routes) > 0 && (route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network))
|
||||
}
|
||||
|
||||
// requestActivatesExitNode reports whether any requested NetID maps to an exit
|
||||
// node (default route) in the current route table.
|
||||
func requestActivatesExitNode(requested []route.NetID, routesMap map[route.NetID][]*route.Route) bool {
|
||||
for _, id := range requested {
|
||||
if isExitNodeRoutes(routesMap[id]) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// otherExitNodeIDs returns every available exit-node NetID that is not in the
|
||||
// requested set — the siblings to deselect so a single exit node stays active.
|
||||
func otherExitNodeIDs(routesMap map[route.NetID][]*route.Route, requested []route.NetID) []route.NetID {
|
||||
keep := make(map[route.NetID]struct{}, len(requested))
|
||||
for _, id := range requested {
|
||||
keep[id] = struct{}{}
|
||||
}
|
||||
var others []route.NetID
|
||||
for id, routes := range routesMap {
|
||||
if !isExitNodeRoutes(routes) {
|
||||
continue
|
||||
}
|
||||
if _, ok := keep[id]; ok {
|
||||
continue
|
||||
}
|
||||
others = append(others, id)
|
||||
}
|
||||
return others
|
||||
}
|
||||
@@ -1,129 +0,0 @@
|
||||
package routemanager
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/routeselector"
|
||||
"github.com/netbirdio/netbird/route"
|
||||
)
|
||||
|
||||
func v6ExitRoute(netID, peer string) *route.Route {
|
||||
return &route.Route{
|
||||
NetID: route.NetID(netID),
|
||||
Network: netip.MustParsePrefix("::/0"),
|
||||
Peer: peer,
|
||||
}
|
||||
}
|
||||
|
||||
func newSelectionTestManager() *DefaultManager {
|
||||
return &DefaultManager{
|
||||
routeSelector: routeselector.NewRouteSelector(),
|
||||
clientRoutes: route.HAMap{
|
||||
"exitA|0.0.0.0/0": {exitRoute("exitA", "p1", true)},
|
||||
"exitA-v6|::/0": {v6ExitRoute("exitA-v6", "p1")},
|
||||
"exitB|0.0.0.0/0": {exitRoute("exitB", "p2", true)},
|
||||
"lan|192.168.1.0/24": {{NetID: "lan", Network: netip.MustParsePrefix("192.168.1.0/24"), Peer: "p3"}},
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
func TestSelectRoutes_ExitNodeExclusivity(t *testing.T) {
|
||||
m := newSelectionTestManager()
|
||||
|
||||
// Selecting an exit node selects its v6 pair and deselects the sibling.
|
||||
require.NoError(t, m.selectRoutes([]route.NetID{"exitA"}, true))
|
||||
assert.True(t, m.routeSelector.IsSelected("exitA"), "exitA should be selected")
|
||||
assert.True(t, m.routeSelector.IsSelected("exitA-v6"), "the v6 pair follows its v4 base")
|
||||
assert.False(t, m.routeSelector.IsSelected("exitB"), "the sibling exit node must be deselected")
|
||||
|
||||
// Switching to the sibling deselects the previous exit node and its v6 pair.
|
||||
require.NoError(t, m.selectRoutes([]route.NetID{"exitB"}, true))
|
||||
assert.True(t, m.routeSelector.IsSelected("exitB"), "exitB should now be selected")
|
||||
assert.False(t, m.routeSelector.IsSelected("exitA"), "the previous exit node must be deselected")
|
||||
assert.False(t, m.routeSelector.IsSelected("exitA-v6"), "the previous exit node's v6 pair must be deselected")
|
||||
assert.True(t, m.routeSelector.IsSelected("lan"), "non-exit route selection is untouched")
|
||||
|
||||
// Selecting a non-exit route leaves the active exit node alone.
|
||||
require.NoError(t, m.selectRoutes([]route.NetID{"lan"}, true))
|
||||
assert.True(t, m.routeSelector.IsSelected("exitB"), "selecting a non-exit route keeps the exit node")
|
||||
|
||||
// Deselecting the active exit node turns every exit node off.
|
||||
require.NoError(t, m.deselectRoutes([]route.NetID{"exitB"}))
|
||||
assert.False(t, m.routeSelector.IsSelected("exitB"), "exitB should be deselected")
|
||||
assert.False(t, m.routeSelector.IsSelected("exitA"), "exitA stays deselected")
|
||||
assert.True(t, m.routeSelector.IsSelected("lan"), "non-exit route selection is untouched")
|
||||
}
|
||||
|
||||
func TestSelectRoutes_PartialErrorStillEnforcesExclusivity(t *testing.T) {
|
||||
// The unknown ID must be reported, but the valid exit node in the same
|
||||
// request is still selected — so its sibling must still be deselected.
|
||||
// Both orderings are covered: processing must continue past the invalid
|
||||
// ID wherever it sits in the request.
|
||||
requests := map[string][]route.NetID{
|
||||
"invalid id first": {"missing", "exitB"},
|
||||
"invalid id last": {"exitB", "missing"},
|
||||
}
|
||||
|
||||
for name, ids := range requests {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
m := newSelectionTestManager()
|
||||
|
||||
require.NoError(t, m.selectRoutes([]route.NetID{"exitA"}, true))
|
||||
|
||||
err := m.selectRoutes(ids, true)
|
||||
assert.Error(t, err, "unknown id must be reported")
|
||||
assert.True(t, m.routeSelector.IsSelected("exitB"), "valid exit node from the request is selected")
|
||||
assert.False(t, m.routeSelector.IsSelected("exitA"), "sibling exit node must be deselected despite the error")
|
||||
assert.False(t, m.routeSelector.IsSelected("exitA-v6"), "sibling's v6 pair must be deselected too")
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestSelectAllRoutes_KeepsSingleExitNode(t *testing.T) {
|
||||
// Both exit nodes are marked for auto-apply by management
|
||||
// (SkipAutoApply=false), the state where select-all could turn on two at
|
||||
// once without the immediate reconciliation.
|
||||
m := &DefaultManager{
|
||||
routeSelector: routeselector.NewRouteSelector(),
|
||||
clientRoutes: route.HAMap{
|
||||
"exitA|0.0.0.0/0": {exitRoute("exitA", "p1", false)},
|
||||
"exitB|0.0.0.0/0": {exitRoute("exitB", "p2", false)},
|
||||
"lan|192.168.1.0/24": {{NetID: "lan", Network: netip.MustParsePrefix("192.168.1.0/24"), Peer: "p3"}},
|
||||
},
|
||||
}
|
||||
|
||||
require.NoError(t, m.selectRoutes([]route.NetID{"exitB"}, true))
|
||||
|
||||
m.selectAllRoutes()
|
||||
|
||||
assert.True(t, m.routeSelector.IsSelected("lan"), "non-exit routes are all selected")
|
||||
assert.True(t, m.routeSelector.IsSelected("exitA"), "the deterministic management pick stays active")
|
||||
assert.False(t, m.routeSelector.IsSelected("exitB"), "select-all must not leave a second exit node active")
|
||||
}
|
||||
|
||||
func TestSelectRoutes_UnknownRoute(t *testing.T) {
|
||||
m := newSelectionTestManager()
|
||||
|
||||
assert.Error(t, m.selectRoutes([]route.NetID{"missing"}, true), "selecting an unavailable route must fail")
|
||||
assert.Error(t, m.deselectRoutes([]route.NetID{"missing"}), "deselecting an unavailable route must fail")
|
||||
}
|
||||
|
||||
func TestExitNodeSelectionHelpers(t *testing.T) {
|
||||
routesMap := map[route.NetID][]*route.Route{
|
||||
"exitA": {{Network: netip.MustParsePrefix("0.0.0.0/0")}},
|
||||
"exitB": {{Network: netip.MustParsePrefix("::/0")}},
|
||||
"lan": {{Network: netip.MustParsePrefix("192.168.0.0/16")}},
|
||||
}
|
||||
|
||||
assert.True(t, requestActivatesExitNode([]route.NetID{"exitA"}, routesMap), "v4 default route is an exit node")
|
||||
assert.True(t, requestActivatesExitNode([]route.NetID{"exitB"}, routesMap), "v6 default route is an exit node")
|
||||
assert.False(t, requestActivatesExitNode([]route.NetID{"lan"}, routesMap), "lan route is not an exit node")
|
||||
assert.False(t, requestActivatesExitNode([]route.NetID{"missing"}, routesMap), "unknown id is not an exit node")
|
||||
|
||||
others := otherExitNodeIDs(routesMap, []route.NetID{"exitB"})
|
||||
assert.ElementsMatch(t, []route.NetID{"exitA"}, others, "only the other exit node is a sibling; the lan route is ignored")
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user