Compare commits

..

3 Commits

Author SHA1 Message Date
mlsmaycon
cfa37cedb2 [client] Drop gopsutil v3 dependency 2026-07-08 01:40:24 +02:00
mlsmaycon
aeae853677 [client] Bump gopsutil library to v4 2026-07-08 01:37:48 +02:00
mlsmaycon
8114c94dbe [client] Update gopsutil to v4 2026-07-08 01:37:48 +02:00
490 changed files with 8401 additions and 36003 deletions

View File

@@ -3,8 +3,8 @@ updates:
- package-ecosystem: "github-actions"
directory: "/"
schedule:
interval: "weekly"
open-pull-requests-limit: 3
interval: "daily"
open-pull-requests-limit: 15
groups:
actions:
patterns:
@@ -22,12 +22,9 @@ updates:
directories:
- "/"
schedule:
interval: "weekly"
interval: "daily"
open-pull-requests-limit: 15
groups:
golang-x-packages:
patterns:
- "golang.org/x/*"
aws-sdk:
patterns:
- "github.com/aws/aws-sdk-go-v2/*"

View File

@@ -2,12 +2,6 @@
## Issue ticket number and link
<!--
Required for anything that changes behavior. Link the issue (or the validated
discussion it came from) that the NetBird team already agreed on. See
https://github.com/netbirdio/netbird/blob/main/CONTRIBUTING.md#ticket-first-pr-second
-->
## Stack
<!-- branch-stack -->
@@ -18,9 +12,7 @@ https://github.com/netbirdio/netbird/blob/main/CONTRIBUTING.md#ticket-first-pr-s
- [ ] Is a feature enhancement
- [ ] It is a refactor
- [ ] Created tests that fail without the change (if possible)
- [ ] I ran and tested this change locally — I did not rely on CI to find out whether it works
- [ ] This PR has a single purpose (not a fix + refactor + feature in one)
- [ ] This change is a trivial fix, **OR** it links an issue the NetBird team agreed on beforehand. Changes to the public API, gRPC protocols, functionality behavior, CLI / service flags, or new features always need that agreement first. See [CONTRIBUTING.md](https://github.com/netbirdio/netbird/blob/main/CONTRIBUTING.md#ticket-first-pr-second).
- [ ] This change does **not** modify the public API, gRPC protocols, functionality behavior, CLI / service flags, or introduce a new feature — **OR** I have discussed it with the NetBird team beforehand (link the issue / Slack thread in the description). See [CONTRIBUTING.md](https://github.com/netbirdio/netbird/blob/main/CONTRIBUTING.md#discuss-changes-with-the-netbird-team-first).
> By submitting this pull request, you confirm that you have read and agree to the terms of the [Contributor License Agreement](https://github.com/netbirdio/netbird/blob/main/CONTRIBUTOR_LICENSE_AGREEMENT.md).

View File

@@ -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 }}

View File

@@ -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

View File

@@ -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

View File

@@ -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

View File

@@ -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

View File

@@ -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

View File

@@ -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

514
AGENTS.md
View File

@@ -1,514 +0,0 @@
# NetBird Agent Guidelines
**NetBird** is an open source connectivity platform: a WireGuard®-based overlay
network with a control plane. The **agent** (`client/`) runs on user machines as
a privileged daemon and manages the WireGuard interface, routing, firewall, and
DNS. **Management** (`management/`) is the control plane and REST/gRPC API,
**Signal** (`signal/`) brokers peer handshakes, **Relay** (`relay/`) carries
traffic when a direct tunnel is impossible, and **Proxy** (`proxy/`) is the
identity-aware proxy behind Agent Network.
This file applies to the whole repository, and is the single source of truth for
agent guidance here. `CLAUDE.md` is a one-line pointer to it — keep the guidance
in this file, not duplicated there.
## Contents
- [NetBird Agent Guidelines](#netbird-agent-guidelines)
- [Contents](#contents)
- [STOP and ask the user before](#stop-and-ask-the-user-before)
- [Quick reference](#quick-reference)
- [Structure](#structure)
- [Where to look](#where-to-look)
- [Repo-wide principles](#repo-wide-principles)
- [Error handling](#error-handling)
- [Comments](#comments)
- [Testing](#testing)
- [Pitfalls](#pitfalls)
- [Commits, PRs, releases](#commits-prs-releases)
- [After you push: CI and review bots](#after-you-push-ci-and-review-bots)
- [Discussion and support](#discussion-and-support)
## STOP and ask the user before
- **Opening a pull request for anything beyond a trivial fix, without an agreed
ticket.** Ask the user directly: *"Is there a discussion or issue for this
change?"* NetBird is discussion-first — community reports start in
[Discussions](https://github.com/netbirdio/netbird/discussions), DevRel
validates them, and only validated discussions become issues. A PR that
changes behavior with no linked issue may be closed on arrival. If there is no
ticket, offer to draft the discussion post **instead of** the PR, and wait for
the user's call. Only typos, broken links, documentation corrections, and
one-line fixes that already have an issue can skip this.
- **Designing in any high-risk area** (see
[CONTRIBUTING.md](CONTRIBUTING.md#high-risk-areas)): public API and OpenAPI
schema, gRPC protos, behavior existing deployments would notice after an
upgrade, peer connectivity (ICE, NAT traversal, relay selection, WireGuard® or
Rosenpass key handling), client system integration (routing, firewall, DNS,
interface), authentication and authorization, CLI or service flags, config
file format, daemon IPC, store schema and migrations, or a new feature. The
design gets agreed in the ticket before code is written.
- **Writing a store migration or changing a persisted model.** Migrations are
one-way in the field and both the GORM and pgx paths may need the change.
- **Hand-editing generated code.** `*.pb.go`, `*.gen.go`, and mocks are outputs.
Edit the source (`.proto`, `openapi.yml`) and rerun the matching
`generate.sh`.
- **Adding, removing, or bumping a dependency**, and never vendor a fork.
- **Weakening a security control** — authentication, authorization, certificate
verification, privilege dropping, or peer identity checks — even when it is
the fastest way to make a test pass.
- **Force-pushing to `main`**, force-pushing any branch that is already under
review, amending pushed commits, or bypassing hooks with `--no-verify`.
## Quick reference
```bash
# Build
go build ./...
cd client && CGO_ENABLED=0 go build . # agent
cd management && go build . # management service
cd signal && go build . # signal service
# Verify (run before every push)
go fmt ./...
make lint # golangci-lint on files changed vs origin/main (also the pre-push hook)
make lint-all # full-repository lint, matches CI
make test-unit # host-safe unit tests, -tags devcert, no sudo
make test-privileged # privileged-tagged suite in a Docker container with NET_ADMIN
make setup-hooks # wire make lint into .githooks/pre-push
# Narrow runs
go test ./client/internal/dns/...
go test -race -run TestPeerConn ./client/internal/peer/...
PRIV_RUN=TestNftablesManager PRIV_PKGS=./client/firewall/nftables/... make test-privileged
# Code generation (never hand-edit the output)
./shared/management/http/api/generate.sh # REST types from openapi.yml
./shared/management/proto/generate.sh
./shared/signal/proto/generate.sh
./client/proto/generate.sh
./flow/proto/generate.sh
# Run locally (lab only, never on a machine you rely on)
sudo ./client/netbird up --log-level debug --log-file console
sudo ./client/netbird down # teardown: restores routing, firewall, DNS
./signal/signal run --log-level debug --log-file console
./management/management management --log-level debug --log-file console --config ./management.json
```
`netbird up` needs root and rewrites the host's routing table, firewall rules,
DNS configuration, and WireGuard® interface. Run it only in a disposable test
environment (a VM, container, or throwaway host) that you can rebuild, never on
a workstation or server whose connectivity matters. Run `sudo netbird down`
before you stop working, before rebuilding the binary, and on every failure
path, so the host's networking state is restored instead of left half-applied.
See [Pitfalls](#pitfalls) for why cleanup on every exit path matters.
## Structure
```text
netbird/
├── client/ NetBird agent
│ ├── cmd/ agent CLI
│ ├── internal/ agent business logic (engine, peer, dns, routemanager, ...)
│ ├── server/ daemon for background execution
│ ├── proto/ daemon gRPC protos
│ ├── iface/ WireGuard® interface management
│ ├── firewall/ nftables, iptables, pf, WFP, userspace backends
│ ├── ssh/ built-in SSH server and client
│ ├── ui/ desktop UI (Wails v3 + React)
│ ├── android/, ios/ mobile bindings
│ ├── wasm/ WebAssembly build
│ └── mdm/, system/ MDM policy, host information
├── management/ control plane
│ └── server/ account, peer, groups, networks, posture, permissions,
│ settings, store, http (REST), idp, integrations, migration
├── signal/ handshake broker (peer/, server/)
├── relay/ relay service (protocol/, server/, healthcheck/)
├── proxy/ identity-aware proxy (llm/, acme/, accesslog/, middleware/, tcp/, udp/)
├── agent-network/ Agent Network overview
├── shared/ imported by both agent and services
│ ├── management/ proto/, client/, http/api (OpenAPI + generated types)
│ ├── signal/ proto/, client/
│ └── relay/, auth/, sshauth/, metrics/
├── e2e/ end-to-end suites and harness
├── encryption/, dns/, route/, stun/, sharedsock/, util/, flow/
├── infrastructure_files/ docker compose and getting-started templates
└── release_files/ files packaged into releases
```
## Where to look
| Task | Location |
| --------------------------- | ------------------------------------------------------------ |
| REST API / OpenAPI | `shared/management/http/api/` + `management/server/http/` |
| Management gRPC protocol | `shared/management/proto/` |
| Signal protocol | `shared/signal/proto/` |
| Daemon IPC protocol | `client/proto/` |
| Peer connection and NAT | `client/internal/peer/` |
| Network map handling | `client/internal/engine.go`, `shared/management/networkmap/` |
| Routing | `client/internal/routemanager/`, `route/` |
| Firewall backends | `client/firewall/` |
| DNS | `client/internal/dns/`, `dns/` |
| WireGuard® interface | `client/iface/` |
| Persistence and migrations | `management/server/store/`, `management/server/migration/` |
| IdP integrations | `management/server/idp/` |
| Permissions model | `management/server/permissions/` |
| LLM routing / Agent Network | `proxy/internal/llm/`, `agent-network/` |
| End-to-end tests | `e2e/` |
## Repo-wide principles
1. **Run `go fmt` on every modified Go file.** Formatting is not optional.
2. **Zero unaddressed diagnostics.** Fix IDE and linter warnings on code you
touch, and delete imports, helpers, and parameters your refactor orphaned.
Exception: unused parameters in shared code may be consumed by builds outside
this repository — do not remove them, ask instead.
3. **Function comments are mandatory for exported functions**, written as full
sentences with a period, starting with the identifier name.
4. **Prefer private functions and constants.** Export only what a caller outside
the package genuinely needs.
5. **Early returns and guard clauses.** Handle errors and edge cases first
instead of nesting `if`/`else` chains.
6. **Split complex functions.** If a function trips a complexity warning, break
it into named helpers rather than silencing the warning.
7. **Avoid LLM-slop tells:** em dashes, hedging narration, restating the diff in
prose, trailing summaries. Defaults, not absolute bans. Applies to code,
comments, commit messages, and PR descriptions alike.
8. **Concurrency: do a two-pass race analysis after every change** that adds
shared state. Guard maps and slices with a mutex, keep critical sections
short, and run `go test -race` on the touched packages.
9. **Cross-platform builds must keep working.** The agent targets Linux, macOS,
Windows, FreeBSD, Android, and iOS. When you add a platform-specific file,
add the counterpart or a build-tagged fallback for the others.
10. **Never hand-edit generated files.** Change the source and regenerate.
11. **Never log secrets** — private keys, setup keys, tokens, PAT values — and
keep peer IPs and hostnames out of logs above debug level.
## Error handling
Use single-assignment form when the error is only needed inside the `if`:
```go
// Good
if err := someCall(); err != nil {
return fmt.Errorf("context: %w", err)
}
// Bad - unnecessary split
err := someCall()
if err != nil {
return fmt.Errorf("context: %w", err)
}
```
Use multiple assignment when the value is needed after the block:
```go
result, err := someCall()
if err != nil {
return fmt.Errorf("context: %w", err)
}
```
Add short, meaningful context, and **do not** start `fmt.Errorf` messages with
obvious words like "failed to" or "error":
```go
// Good
return fmt.Errorf("parse remote address: %w", err)
return fmt.Errorf("listen on %s: %w", addr, err)
// Bad
return fmt.Errorf("failed to parse remote address: %w", err)
return fmt.Errorf("error listening on %s: %w", addr, err)
// "failed" is fine in log messages
log.Debugf("failed to parse remote address: %v", err)
```
Skip the wrapping when a function only extracts or delegates and the wrap would
add nothing:
```go
func parseAddr(addr string) (string, int, error) {
host, portStr, err := net.SplitHostPort(addr)
if err != nil {
return "", 0, err
}
// ...
}
```
Log the errors you choose not to act on:
- `log.Debugf()` for errors that do not affect program flow but help debugging.
- `log.Tracef()` for very verbose errors that would otherwise spam logs.
- **Never ignore** errors from writes, network sends, or critical cleanup.
- Close errors may be ignored for read-only operations; log them at debug for
writes.
## Comments
Comment the **why**, never the **what**. Default to no comment, and add one only
when a hidden constraint or workaround would surprise a future reader. Never
reference the current task, PR, or your own changes in a comment.
```go
// Bad - trailing comments explaining the obvious
defer localConn.Close() // Close the connection
if err != nil { // Check if error occurred
// Good
defer localConn.Close()
// Good - explains a non-obvious constraint
// Use incremental checksum update per RFC 1624 for performance.
checksum = updateChecksum(checksum, oldPort, newPort)
```
### Length budget
- **90 characters per line.** Wrap the comment, do not run past it.
- **250 characters per comment**, roughly three wrapped lines. Doc comments on
exported identifiers may exceed it when the API genuinely needs the
explanation; inline comments inside a function body may not.
The budget is a smell detector, not a rule to game. Do not compress a needed
explanation into cryptic shorthand to fit — if a block of code needs more than
250 characters of prose, the code is doing too much. Fix the code:
- **Extract a named function.** A well-named function replaces the comment: the
name says *what*, the body shows *how*, and the comment you no longer write
was the *what* anyway. Clean Code calls this "explain yourself in code".
- **Extract a named constant or predicate.** `if isExpiredSetupKey(key)` needs
no comment; `if key.ExpiresAt.Before(now) && !key.Revoked && key.UsageLimit > 0`
does.
- **Keep the surviving comment for the why** — the RFC, the kernel quirk, the
ordering constraint. That part is usually one or two lines.
### Long switch and if/else chains
A `switch` whose cases carry multi-line explanations is the usual place this
budget is breached, and the comment is a symptom. In order of preference:
1. **Extract each case body into a named function.** The case becomes one line,
the name carries the meaning, and the switch reads as a table of contents.
2. **Replace the switch with a lookup table**`map[Kind]handlerFunc` — when the
branches are uniform. Adding a case stops meaning editing a growing function.
3. **Replace conditional with polymorphism** when branches vary by type and the
same switch shape starts appearing in more than one place. Clean Code's rule
of thumb: tolerate a switch statement if it appears **once**, is buried in a
factory that returns an interface, and no other switch dispatches on the same
type. A second switch over the same enum is the signal to introduce the
interface.
Do not restructure a switch purely to satisfy the budget when the cases are one
line each and self-evident — a flat, boring `switch` over an enum is fine and
needs no comments at all.
Explanatory comments in tests are welcome — they document the scenario being set
up, and the 250-character budget does not apply to them.
## Testing
- **Unit tests** live beside the code as `_test.go`. `make test-unit` runs the
host-safe set with `-tags devcert` and no sudo.
- **Privileged tests** carry the `privileged` build tag and mutate host
networking. They run through `make test-privileged`, inside a Docker container
with `NET_ADMIN`. Never bypass that harness by running them directly on the
host.
- **End-to-end suites** live in `e2e/` with a shared harness.
- **Test real behavior, not API existence.** Assert on the observable end state
a consumer would see — bytes that arrived, the packet after translation, the
row after the write — not merely that a method exists or returns an error.
- **Avoid mocks for code we own.** Exercise the real store, manager, or
controller and assert what the caller actually receives.
- **`require` for setup and preconditions, `assert` for the conditions under
test.** Use `require` whenever a later line would panic or be meaningless
otherwise.
- **Message guidance:** optional for `NoError`/`Error`; always give context for
comparison, boolean, and collection assertions.
```go
server, err := StartTestServer()
require.NoError(t, err, "Test server setup must succeed")
defer server.Close()
result, err := client.DoOperation()
assert.NoError(t, err)
assert.Equal(t, expectedResult, result, "Result should match expected")
```
## Pitfalls
- **The agent runs as root.** Anything touching routing, firewall, DNS, or the
interface can take a user's machine off the network. Prefer a reversible
change and make sure cleanup runs on every exit path.
- **Management has two account loaders** (GORM and pgx). Adding a relation to an
account often means updating both, or it silently comes back empty in
production.
- **`go test ./...` without `-tags devcert` skips tests** that need the
development certificate. Use `make test-unit`.
- **`make lint` only checks the diff against `origin/main`.** CI runs
`make lint-all`; run it too before pushing a large change.
- **Protos are consumed by released clients.** An old agent must keep working
against a new Management, so fields are added, never renumbered or removed.
- **Windows requires the wintun driver**, and the daemon serves a named pipe
(`npipe://netbird`) rather than loopback TCP. Loopback TCP carries no caller
identity, so privileged operations are refused over it.
## Commits, PRs, releases
- **PR titles must start with a bracketed tag.** Before you propose a title,
**read [`.github/workflows/pr-title-check.yml`](.github/workflows/pr-title-check.yml)
and take the allowed tags from the `allowedTags` array in that file.** It is
the only source of truth, it changes as components are added, and the check
runs on every title edit — a tag that is not in that array is a red build. Do
not rely on a list memorized from anywhere else, including this file.
```text
[client] Authorize daemon IPC callers by their local identity
[management,client] Add MDM policy support
```
Multiple tags are comma-separated inside one pair of brackets. Match the tag
to the component you actually changed, not to the one you read the most.
- **Use the repository's PR template.** Fill in
[`.github/pull_request_template.md`](.github/pull_request_template.md) rather
than replacing it with your own summary: describe the change, link the issue,
tick the checklist honestly (including "ran locally" and "single purpose"),
and complete the documentation section. Do not tick a box you have not
verified, and do not delete rows that do not apply.
- **Keep the PR description short.** Under 1000 words on top of the template's
own text, and usually far less — a few paragraphs. Reviewers read the diff;
the description exists to explain what the diff cannot say for itself. This is
well below what an agent will produce by default, so cut before you post.
- **Body: why before what.** Lead with the problem and the reason for this
approach, then the shape of the change. No bullet list of files changed, no
per-function walkthrough, no restating the diff in prose, no trailing summary
section, no self-congratulatory closing line.
- **No `Co-Authored-By` or tool-attribution trailers in the PR description**,
and none in commits either. Contributors own their contributions. Whatever
tooling produced the diff, the person opening the PR is its author: they have
read every line, they can explain why it works, they can answer review
questions without going back to a model, and they are accountable for the
consequences of merging it. Do not add a trailer, footer, or description line
that spreads that ownership onto a tool.
- **Commit subjects follow the same `[scope] Subject` convention.** Keep the
subject short, and use the body for why before what. No bullet lists of files
changed.
- **Push review fixes as separate commits.** The PR is squashed on merge, so
there is no reason to rewrite history mid-review; many small commits make the
re-review readable.
- **Do not force-push a branch that is under review.** A force-push detaches
existing review comments from the lines they were written against, destroys
the "changes since your last review" diff a reviewer relies on, and discards
the CI history that showed which commit broke what. Add commits instead —
including for fixups and reverts. Force-push only when there is no
alternative: a rebase to clear a genuine conflict, or removing a secret or a
large binary that was committed by mistake. When you must, ask the user first,
then say so in a PR comment so reviewers know their anchors moved. Never
force-push `main`, and never force-push a branch you do not own.
- **One PR, one purpose.** Split refactors out of fixes and fixes out of
features.
- **Keep the PR small.** Size is the single strongest predictor of how long a PR
waits. Aim for **under ~400 changed lines across under ~20 files**; past
roughly **1000 lines or 50 files** a community PR is likely to be sent back to
be split, or left unreviewed until it is. Large PRs from outside the core team
may be blocked outright when the size was never agreed in the ticket —
reviewing a sprawling change against a privileged networking daemon is a
security risk in itself, not just a time cost.
Judge the size by hand-written code: exclude generated output, `go.sum`,
vendored files, and test fixtures from the estimate, but do not use their
presence to argue a 3000-line PR is small.
When a change genuinely cannot be small — a protocol migration, a
cross-component rename — agree the split in the ticket **before** writing
code, and land it as a sequence of PRs that each build, test, and make sense
on their own. Propose that split to the user rather than opening one large PR
and hoping.
- **User-facing changes need a docs PR** in
[netbirdio/docs](https://github.com/netbirdio/docs), linked from the PR
description.
## After you push: CI and review bots
Opening the PR is not the end of the task. Watch the run, read what the bots
say, and drive the PR to green before you report the work as done.
```bash
gh pr checks <pr> --watch # all checks, live
gh run view <run-id> --log-failed # only the failing steps
gh pr view <pr> --comments # bot and human review comments
```
**Never report a change as finished while checks are pending or red**, and never
describe a red PR as passing. If you ran out of turn before CI finished, say
which checks were still running.
### The checks
- **Go tests** — `golang-test-{linux,darwin,windows,freebsd}.yml`, sharded per
component. A failure in a component you did not touch is usually a real
interaction, not noise; read the log before assuming flake.
- **golangci-lint** — `golangci-lint.yml` runs the full repository, while
`make lint` only checks your diff. A clean local lint does not guarantee green
CI on a large change.
- **PR Title Check** — `pr-title-check.yml`, see above.
- **Codecov** — uploaded from the Linux test workflow with per-component flags
(`unit,client`, `unit,management`, `unit,relay`, `unit,proxy`, `unit,signal`,
`integration,management`). Coverage on new code should not go backwards. Add
tests for the paths you introduced; do not adjust thresholds or exclude files
to clear the report.
- **CodeRabbit** — configured in [`.coderabbit.yaml`](.coderabbit.yaml): `chill`
profile, auto-review on every non-draft PR, TypeScript/JavaScript/SVG paths
filtered out. Chat auto-reply is on, so `@coderabbitai` in a comment reaches
it.
- **SonarCloud** — project `netbirdio_netbird`, quality gate on new code (bugs,
vulnerabilities, code smells, duplication, coverage).
- **Snyk** — dependency and code scanning.
Sonar and Snyk report as GitHub App checks rather than workflows in this
repository, so their detail lives on the PR check, not in the Actions logs.
### Handling bot findings
- **Read every comment and act on it.** Either fix it, or reply with the reason
it does not apply. Do not bulk-resolve threads to clear the count, and do not
silently ignore a finding because the check is advisory.
- **Bots are frequently wrong here.** NetBird has privileged, platform-specific,
and concurrency-heavy code that static analysis reads poorly. A confident
CodeRabbit or Sonar comment can still be nonsense. Verify the claim against
the code before you change anything — never edit correct code just to silence
a bot.
- **Security findings get the opposite default.** For a Snyk or Sonar
vulnerability, or a CodeRabbit comment about authentication, authorization,
certificate verification, or key handling, assume it is real until you have
disproved it. Surface it to the user rather than dismissing it yourself.
- **A new vulnerable dependency is a stop.** Bumping or replacing dependencies
needs the user's decision, as above.
- **Never change a workflow, threshold, lint exclusion, or bot config to make a
check pass.** If a check is genuinely wrong, say so and let the user decide.
- **Do not paper over flakes with blind re-runs.** Identify the failure first. If
it is a known flake, name it; if you cannot tell, report it as unresolved
rather than re-running until it goes green.
## Discussion and support
- Discussions: <https://github.com/netbirdio/netbird/discussions>
- Slack: <https://docs.netbird.io/slack-url>
- Docs: <https://docs.netbird.io>
- Security: <https://github.com/netbirdio/netbird/security/policy> — never in public
- Contribution process: [CONTRIBUTING.md](CONTRIBUTING.md)

View File

@@ -1 +0,0 @@
See [AGENTS.md](AGENTS.md) for the agent guidelines in this repository.

View File

@@ -1,6 +1,6 @@
# Contributing to NetBird
Thanks for your interest in contributing to NetBird.
Thanks for your interest in contributing to NetBird.
There are many ways that you can contribute:
- Reporting issues
@@ -10,99 +10,12 @@ There are many ways that you can contribute:
If you haven't already, join our slack workspace [here](https://docs.netbird.io/slack-url), we would love to discuss topics that need community contribution and enhancements to existing features.
## Ticket first, PR second
**Open a ticket and wait for feedback before you open a pull request.** Every PR
that changes behavior must link to an issue the NetBird team has agreed on. A PR
that arrives without one may be closed and redirected to a discussion, no matter
how good the code is.
Issues in this repository are maintainer-curated work items, so the flow starts
in [Discussions](https://github.com/netbirdio/netbird/discussions):
1. **Open a discussion.** Use
[Issue Triage](https://github.com/netbirdio/netbird/discussions/new?category=issue-triage)
for a bug, regression, or unexpected behavior, and
[Ideas & Feature Requests](https://github.com/netbirdio/netbird/discussions/new?category=ideas-feature-requests)
for a feature, enhancement, or integration idea. Setup and usage questions
belong in
[Q&A / Support](https://github.com/netbirdio/netbird/discussions/new?category=q-a-support).
Never report a security vulnerability in public — follow the
[security policy](https://github.com/netbirdio/netbird/security/policy)
instead.
2. **Wait for feedback.** DevRel validates and reproduces the report, and a
maintainer confirms the direction. We may ask for more detail or propose a
different approach. Validated discussions become issues.
3. **Then write the code**, following the approach agreed in the issue, and open
the PR linking that issue.
Trivial fixes — a typo, a broken link, a documentation correction, or a one-line
fix that already has an issue — can go straight to a PR. Everything else starts
with a ticket. When in doubt, ask in the discussion or on
[Slack](https://docs.netbird.io/slack-url); an hour of conversation up front
regularly saves a week of rework.
### High-risk areas
These always need the design discussed and agreed in the issue **before** you
write code:
- **Public API** — REST / management API, OpenAPI schema, dashboard-facing contracts
- **gRPC protocols** — management, signal, relay, and client daemon protos
- **Functionality behavior** — anything existing deployments would experience differently after an upgrade
- **Peer connectivity** — ICE and NAT traversal, relay selection, WireGuard® and Rosenpass key handling
- **Client system integration** — routing, firewall, DNS, and interface management
- **Authentication and authorization** — IdP integration, tokens, permissions, cryptography
- **CLI / service flags**, configuration file format, and daemon IPC
- **Store and database schema** — models and migrations
- **New features**
These surfaces are NetBird's contract with operators, self-hosters, and
downstream integrators, and changes to them have compatibility, security, and
release-planning implications. Agreeing on the direction early lets the PR
review focus on implementation rather than design.
Typical bug fixes, internal refactors, documentation updates, and tests do not
need a design discussion, but should still be tied to an issue so the work is
visible and nobody duplicates it.
### Using AI coding agents
We have no policy for or against using an AI agent to write NetBird code. That
choice is yours, and we are not going to interrogate anyone about their tools.
What we do have is a lot of incoming contributions that were plainly drafted with
one, and enough experience reviewing them to see the same avoidable problems
again and again: no ticket behind the change, a diff far too large to review, a
description longer than the code it describes, an approach that was never going
to be accepted, and an author who cannot answer questions about their own PR.
None of that is caused by the tooling — it is what happens when a tool is pointed
at a repository whose expectations it has never been told.
So rather than a rule, there is a guide. [AGENTS.md](AGENTS.md) restates the
expectations from this document in the form agents read automatically
(`CLAUDE.md` points to it), so pointing your tool at the repository is usually
enough. Among other things it tells the agent to ask you for the
discussion or issue before drafting a PR, to keep the change small and
single-purpose, to run the tests locally, to use this repository's PR template
and title tags, and to write a description a reviewer can get through.
The guardrails are the point, and they are the same ones we apply to everyone: an
agreed ticket, a change you have actually run, a diff small enough to review with
care, and an author who can explain it. Whatever wrote the diff, you are its
author — you own every line you submit and the consequences of opening a PR with it.
We may assess whether a contribution is maintainable and whether its merged code
aligns with our security standards and design expectations.
## Contents
- [Contributing to NetBird](#contributing-to-netbird)
- [Ticket first, PR second](#ticket-first-pr-second)
- [High-risk areas](#high-risk-areas)
- [Using AI coding agents](#using-ai-coding-agents)
- [Contents](#contents)
- [Code of conduct](#code-of-conduct)
- [Discuss changes with the NetBird team first](#discuss-changes-with-the-netbird-team-first)
- [Directory structure](#directory-structure)
- [Development setup](#development-setup)
- [Requirements](#requirements)
@@ -111,7 +24,6 @@ aligns with our security standards and design expectations.
- [Build and start](#build-and-start)
- [Test suite](#test-suite)
- [Checklist before submitting a PR](#checklist-before-submitting-a-pr)
- [When we close a PR](#when-we-close-a-pr)
- [Other project repositories](#other-project-repositories)
- [Contributor License Agreement](#contributor-license-agreement)
@@ -122,66 +34,42 @@ Conduct which can be found in the file [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md).
By participating, you are expected to uphold this code. Please report
unacceptable behavior to community@netbird.io.
## Discuss changes with the NetBird team first
Changes to the **public API**, **gRPC protocols**, **functionality behavior**, **CLI / service flags**, or **new features** should be discussed with the NetBird team before you start the work. These surfaces are part of NetBird's contract with operators, self-hosters, and downstream integrators, and changes to them have compatibility, security, and release-planning implications that benefit from an early conversation.
Open an issue or reach out on [Slack](https://docs.netbird.io/slack-url) to talk through what you have in mind. We'll help shape the change, flag any constraints we know about, and confirm the direction so the PR review can focus on implementation rather than design.
Typical bug fixes, internal refactors, documentation updates, and tests do not need pre-discussion — open the PR directly.
## Directory structure
The NetBird project monorepo keeps most of each component's code within its own
directory, except for a few auxiliary or shared packages. Protocol definitions
and the client-side service clients live under [/shared](/shared), because both
the agent and the services import them.
The NetBird project monorepo is organized to maintain most of its individual dependencies code within their directories, except for a few auxiliary or shared packages.
**Agent**
The most important directories are:
- [/.github](/.github) - Github actions workflow files and issue templates
- [/client](/client) - NetBird agent code
- [/client/cmd](/client/cmd) - NetBird agent CLI code
- [/client/cmd](/client/cmd) - NetBird agent cli code
- [/client/internal](/client/internal) - NetBird agent business logic code
- [/client/proto](/client/proto) - NetBird agent daemon GRPC proto files
- [/client/server](/client/server) - NetBird agent daemon code for background execution
- [/client/proto](/client/proto) - NetBird agent daemon gRPC proto files
- [/client/iface](/client/iface) - WireGuard® interface code
- [/client/firewall](/client/firewall) - Platform firewall backends (nftables, iptables, pf, WFP, userspace)
- [/client/ssh](/client/ssh) - Built-in SSH server and client
- [/client/ui](/client/ui) - NetBird agent UI code (Wails v3 + React)
- [/client/android](/client/android), [/client/ios](/client/ios) - Mobile platform bindings
- [/client/wasm](/client/wasm) - WebAssembly build of the agent
- [/client/mdm](/client/mdm) - MDM-delivered policy handling
- [/client/system](/client/system) - Host and system information collection
**Control plane services**
- [/client/ui](/client/ui) - NetBird agent UI code
- [/encryption](/encryption) - Contain main encryption code for agent communication
- [/iface](/iface) - Wireguard® interface code
- [/infrastructure_files](/infrastructure_files) - Getting started files containing docker and template scripts
- [/management](/management) - Management service code
- [/management/client](/management/client) - Management service client code which is imported by the agent code
- [/management/proto](/management/proto) - Management service GRPC proto files
- [/management/server](/management/server) - Management service server code
- [/management/server/http](/management/server/http) - Management service REST API code
- [/management/server/store](/management/server/store) - Persistence layer and migrations
- [/management/server/idp](/management/server/idp) - Management service IDP management code
- [/management/server/peer](/management/server/peer), [/management/server/groups](/management/server/groups), [/management/server/networks](/management/server/networks), [/management/server/posture](/management/server/posture), [/management/server/permissions](/management/server/permissions) - Core domain packages
- [/signal](/signal) - Signal service code
- [/signal/peer](/signal/peer) - Signal service peer message logic
- [/signal/server](/signal/server) - Signal service server code
- [/relay](/relay) - Relay service code
- [/relay/protocol](/relay/protocol) - Relay wire protocol
- [/proxy](/proxy) - Identity-aware proxy used by Agent Network (LLM routing, ACME, access logs)
- [/agent-network](/agent-network) - Agent Network overview and documentation
- [/upload-server](/upload-server) - Debug bundle upload service
**Shared code**
- [/shared/management/proto](/shared/management/proto) - Management service gRPC proto files
- [/shared/management/client](/shared/management/client) - Management service client code which is imported by the agent code
- [/shared/management/http/api](/shared/management/http/api) - OpenAPI specification and generated REST API types
- [/shared/signal/proto](/shared/signal/proto) - Signal service gRPC proto files
- [/shared/signal/client](/shared/signal/client) - Signal service client code which is imported by the agent code
- [/shared/relay](/shared/relay) - Relay client and shared relay types
- [/shared/auth](/shared/auth), [/shared/sshauth](/shared/sshauth) - Shared authentication primitives
- [/encryption](/encryption) - Contain main encryption code for agent communication
- [/dns](/dns), [/route](/route), [/stun](/stun), [/sharedsock](/sharedsock), [/util](/util) - Shared networking and utility primitives
- [/flow](/flow) - Flow event protocol shared by the agent and Management
**Build, test, and packaging**
- [/.github](/.github) - Github actions workflow files, issue templates, and the pull request template
- [/e2e](/e2e) - End-to-end test suites and harness
- [/infrastructure_files](/infrastructure_files) - Getting started files containing docker and template scripts
- [/release_files](/release_files) - Files that goes into release packages
- [/tools](/tools) - Development and maintenance tooling
- [/signal](/signal) - Signal service code
- [/signal/client](/signal/client) - Signal service client code which is imported by the agent code
- [/signal/peer](/signal/peer) - Signal service peer message logic
- [/signal/proto](/signal/proto) - Signal service GRPC proto files
- [/signal/server](/signal/server) - Signal service server code
## Development setup
@@ -346,22 +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/`):
```
@@ -446,172 +324,23 @@ The installer `netbird-installer.exe` will be created in root directory.
### Test suite
The host-safe unit tests run as a normal user and leave host networking
untouched:
The tests can be started via:
```
make test-unit
cd netbird
go test -exec sudo ./...
```
Tests that need root and mutate host networking (firewall, routing, interface
management) carry the `privileged` build tag and run inside a
`--privileged --cap-add=NET_ADMIN` Docker container:
```
make test-privileged
```
Narrow a privileged run with environment variables:
```
PRIV_RUN=TestNftablesManager PRIV_PKGS=./client/firewall/nftables/... make test-privileged
```
Single packages can be run directly, adding `-race` when the change touches
shared state:
```
go test -race ./client/internal/dns/...
```
> On Windows use a powershell with administrator privileges
## Checklist before submitting a PR
As a critical network service and open source project, we must enforce a few
things before submitting a pull request. The
[pull request template](/.github/pull_request_template.md) mirrors this list —
fill it in rather than deleting it.
### Link the issue
The PR description must link the agreed issue (or the validated discussion it
came from). See [Ticket first, PR second](#ticket-first-pr-second).
### Run it locally
**If you can't run it, you can't submit it.** Build the affected components and
exercise the change on a real setup — see [Build and start](#build-and-start).
"CI will tell me" is not acceptable for a VPN agent that runs as root on other
people's machines.
### Green CI, and answer the bots
We do not start reviewing while CI is red. Get the pipeline green first — a
failing build, lint, or test means the PR is not ready for review.
Alongside the test workflows, your PR is reviewed by CodeRabbit and scanned by
SonarCloud, Snyk, and Codecov. Read what they report and either fix it or reply
with why it does not apply; please do not resolve the threads without a
response. They are not always right — this codebase has privileged,
platform-specific, and concurrency-heavy paths that static analysis reads poorly
— so push back when a finding is wrong rather than changing correct code to
silence it. Security and dependency findings are the exception: treat those as
real until shown otherwise. Do not edit workflows, thresholds, or scanner
configuration to make a check pass.
### One PR, one purpose
Bug fix, refactor, feature: separate PRs. Mixed PRs are slow to review, hard to
revert, and may be closed with a request to split them.
### Keep it small
Size is the strongest predictor of how long a PR waits for review. Aim for under
roughly 400 changed lines across under 20 files. Past about 1000 lines or 50
files, expect to be asked to split the change — and large PRs from outside the
core team may be blocked until the scope has been agreed in a ticket. This is
not only about reviewer time: NetBird's agent runs as root on other people's
machines, and a sprawling diff cannot be reviewed with the care that deserves.
Measure by hand-written code, excluding generated output, `go.sum`, and
fixtures. If a change genuinely cannot be small — a protocol migration, a
cross-component rename — agree the split in the issue before you start, and land
it as a series of PRs that each build and make sense on their own.
### Avoid force-pushing during review
Once a PR is open, push new commits instead of rewriting history. A force-push
detaches existing review comments from their lines, throws away the
"changes since your last review" diff, and loses the CI history that showed
which commit broke what. Since we squash on merge, there is nothing to gain from
a tidy branch history.
Force-pushing is sometimes unavoidable — rebasing to clear a real conflict, or
removing a secret or large binary committed by mistake. When that happens, leave
a comment on the PR so reviewers know their anchors moved.
### Quality checks
Run these from the repository root before pushing:
```shell
go fmt ./...
make lint # golangci-lint on files changed against origin/main
make lint-all # full-repository lint, matches CI
make test-unit # host-safe unit tests
```
`make setup-hooks` wires `make lint` into a pre-push hook so the fast lint runs
automatically. If your change touches privileged paths (firewall, routing,
interface management), also run `make test-privileged`, which executes the
`privileged`-tagged suite inside a Docker container with `NET_ADMIN`.
### Code standards
As a critical network service and open-source project, we must enforce a few things before submitting the pull-requests:
- Keep functions as simple as possible, with a single purpose
- Use private functions and constants where possible
- Comment on any new public functions
- Add unit tests for any new public function
- Comment the **why**, not the **what** — explain non-obvious decisions, invariants, and constraints, not the line below
- Keep comments within 90 characters per line and roughly 250 characters per comment; when a block needs more explanation than that, extract a named function instead of writing a longer comment (see [AGENTS.md](AGENTS.md#length-budget))
### PR title and commits
PR titles must start with a bracketed tag, enforced by
[pr-title-check.yml](/.github/workflows/pr-title-check.yml):
```text
[client] Authorize daemon IPC callers by their local identity
[management,client] Add MDM policy support
```
Use a comma-separated list inside a single pair of brackets when a change spans
components. The `allowedTags` array in
[pr-title-check.yml](/.github/workflows/pr-title-check.yml) is the source of
truth — at the time of writing it accepts `management`, `client`, `signal`,
`proxy`, `relay`, `misc`, `infrastructure`, `self-hosted`, and `doc`.
Commit subjects follow the same convention — keep them short and put the
reasoning in the body, why before what, with no bullet list of files changed.
Keep the PR description itself under 1000 words on top of the template text.
Reviewers read the diff; the description explains what the diff cannot.
> When pushing fixes to the PR comments, please push as separate commits; we will squash the PR before merging, so there is no need to squash it before pushing it, and we are more than okay with 10-100 commits in a single PR. This helps review the fixes to the requested changes.
### Documentation
User-facing changes need a matching PR in
[netbirdio/docs](https://github.com/netbirdio/docs); link it in the PR
description, or state why documentation is not needed.
## When we close a PR
We would rather redirect early than let a PR sit. We may close one if:
- It changes behavior with no linked issue, or the approach was never agreed with a maintainer
- The change was clearly never run or tested locally
- CI has been red without a response
- It mixes unrelated purposes, or the purpose is not clear
- It is far too large to review and the scope was never agreed in a ticket
- The author cannot answer questions about their own change — including PRs that read as unreviewed model output, where review turns into a relay between the maintainer and an LLM. Tooling is fine; unreviewed output is not, you are responsible for the code you sign your name to
- There has been no activity for 14 days after we requested changes
A closed PR is not a rejected idea. Take it back to the
[discussion](https://github.com/netbirdio/netbird/discussions), settle the
approach, and reopen the work from there.
## Other project repositories
NetBird project is composed of 3 main repositories:

View File

@@ -130,7 +130,7 @@ In November 2022, NetBird joined the [StartUpSecure program](https://www.forschu
![CISPA_Logo_BLACK_EN_RZ_RGB (1)](https://user-images.githubusercontent.com/700848/203091324-c6d311a0-22b5-4b05-a288-91cbc6cdcc46.png)
### Acknowledgements
We build on open source technologies like [WireGuard®](https://www.wireguard.com/), [Pion ICE](https://github.com/pion/ice), and [Rosenpass](https://rosenpass.eu). We greatly appreciate the work these projects are doing, and we'd love it if you could support them too (e.g., by starring or contributing).
We build on open-source technologies like [WireGuard®](https://www.wireguard.com/), [Pion ICE](https://github.com/pion/ice), and [Rosenpass](https://rosenpass.eu). We greatly appreciate the work these projects are doing, and we'd love it if you could support them too (e.g., by starring or contributing).
### Legal
This repository is licensed under the BSD-3-Clause license, which applies to all parts of the repository except for the directories management/, signal/ and relay/.

View File

@@ -1,70 +1,12 @@
# Security Policy
NetBird's goal is to provide a secure network. The client runs as a privileged service on every machine it is installed on,
so we take reports about it seriously and we publish what we fix.
NetBird's goal is to provide a secure network. If you find a vulnerability or bug, please report it by opening an issue [here](https://github.com/netbirdio/netbird/issues/new?assignees=&labels=&template=bug-issue-report.md&title=) or by contacting us by email.
There has yet to be an official bug bounty program for the NetBird project.
## Supported Versions
- We currently support only the latest version
## Reporting a Vulnerability
**Please do not open a public issue for a security vulnerability.** Public issues are visible to everyone, including before
a fix is available.
Report security issues one of these two ways:
- **GitHub private vulnerability reporting** — [open a private report](https://github.com/netbirdio/netbird/security/advisories/new)
on this repository. This is the preferred route: it keeps the discussion, the draft advisory, and the credit in one place.
- **Email** — `security@netbird.io`.
If the finding affects NetBird Cloud or our hosted infrastructure rather than the open source code, email us rather than
filing a repository report.
### What to include
A report is easier to act on when it contains:
- The affected component (client, management, signal, relay, dashboard) and the version or commit you tested
- The platform and configuration, where relevant — operating system, self-hosted or NetBird Cloud, container or host install
- What an attacker needs before they can exploit it: network position, an account, local access, a specific privilege level
- Steps to reproduce, and a proof of concept if you have one
- The impact you believe it has
Partial reports are still welcome. If you are unsure whether something is a security issue, send it to `security@netbird.io`
and let us make that call.
## What to expect from us
- **We acknowledge your report** and tell you whether we can reproduce it.
- **We work with you on severity and scope.** If we assess it differently than you do, we will explain why rather than
silently downgrade it.
- **We fix and release**, then publish a [GitHub Security Advisory](https://github.com/netbirdio/netbird/security/advisories)
naming the affected version range and the patched version.
- **We credit reporters who want to be credited.** Tell us the name or handle you would like used, or that you would rather
stay anonymous.
- **We keep you in the loop** until the advisory is published.
We ask that you give us a reasonable opportunity to ship a fix before disclosing the issue publicly, and that you avoid
accessing, modifying, or exfiltrating data belonging to other people while testing. Testing against your own installation
or your own account is always fine.
## Supported Versions
We support the latest release. Security fixes ship in the next version rather than as backports to older releases, so
upgrading to the current release is how you get them.
Release notifications are available by watching [releases](https://github.com/netbirdio/netbird/releases).
## Published advisories
Every vulnerability we fix is published as a GitHub Security Advisory on the
[advisories page](https://github.com/netbirdio/netbird/security/advisories), including the affected version range, the
patched version, and the reporter's credit. Advisories for the Go module are also distributed through the Go vulnerability
database, so `govulncheck` will report them against your dependencies.
## Bug bounty
There is no official bug bounty program for the NetBird project. We credit reporters in advisories, and we are grateful for
the work, but we cannot currently offer payment for reports.
## Non-security bugs
For bugs that are not security issues, please use the
[issue tracker](https://github.com/netbirdio/netbird/discussions/new/choose).
Please report security issues to `security@netbird.io`

View File

@@ -1,47 +1,16 @@
# NetBird Agent Network
Agent Network is NetBird's access control layer for AI agents and the people who run them.
It gives every agent a real identity, tied to an identity provider (IdP), and governs what it can reach: LLM APIs and
AI gateways it can call, and the internal resources it can access. Traffic flows only over the encrypted NetBird tunnel,
scoped by policy, with no API keys or other credentials to leak. It also gives you control over cost and token usage.
Agent Network is NetBird's access control layer for AI agents and the people who run
them. It gives every agent a real identity, tied to your identity provider (IdP), and
governs what it can reach — the LLM APIs and AI gateways it can call, and the internal
resources it can access. Traffic flows only over the encrypted NetBird tunnel, scoped by
policy, with no API keys to leak.
Because every LLM request passes through an
identity-aware proxy, you can:
- **Set spending and rate limits** per agent, per user, or per team — with hard caps
that stop requests once a budget is reached.
- **Restrict models and providers** so agents can only call approved (and cost-appropriate)
endpoints, keeping expensive models off-limits unless explicitly allowed.
- **Attribute usage** by tracking token consumption and cost per identity, group, or cost center so every
request is tied back to the agent and person responsible.
- **Reuse your existing AI gateway** — point the proxy at a gateway you already run,
keeping its routing and config in place while it adds identity on top, so you skip
API key distribution.
https://github.com/user-attachments/assets/44d18286-d8ab-49f8-a457-98ccd66f3268
> **Beta.** Agent Network is in beta, but it's stable and already running in
> production environments. It's fully open source and can be self-hosted on your own
> infrastructure, with no vendor lock-in and no data leaving your environment.
> **Beta.** Agent Network is open source and can be self-hosted on your own
> infrastructure.
## How it works
Say you have a simple use case: your Engineering or IT team needs access to Claude Code or Codex, and you want visibility into usage plus the ability to enforce budgets.
How can you do that without creating a dedicated API key for every team?
With Agent Network you get a private endpoint inside your network, for example: https://mirror.netbird.ai
Teams configure their agents to point to that endpoint instead of using individual API keys directly.
This endpoint is only reachable when users are connected to your NetBird network and authenticated through your IdP. Otherwise, it is not accessible from the public internet.
You can then use this private endpoint to configure your AI agents, whether that is Claude Code, Codex, or another tool.
## Quickstart
Full step-by-step setup:
**https://docs.netbird.io/agent-network/quickstart**
## Architecture
Agent Network is built on two existing NetBird capabilities:
- **Overlay network** — the encrypted WireGuard mesh between peers.
@@ -53,9 +22,6 @@ LLM traffic is routed through the proxy's identity-aware pipeline, while interna
resources (databases, internal APIs, self-hosted models) are reached directly over
peer-to-peer WireGuard tunnels, governed by the same identities and access policies.
<img width="4720" height="2218" alt="image" src="https://github.com/user-attachments/assets/1afa5da1-4b82-4f8a-a7a8-f417efadf1eb" />
## Where the code lives
There is no separate "agent-network" service — it reuses the reverse-proxy and management

View File

@@ -7,7 +7,6 @@ import (
"fmt"
"os"
"slices"
"strings"
"sync"
"time"
@@ -76,24 +75,6 @@ type Client struct {
connectClient *internal.ConnectClient
config *profilemanager.Config
cacheDir string
stateChangeMu sync.Mutex
stateChangeSubID string
eventSub *peer.EventSubscription
// Closed to stop the watch goroutines from delivering buffered items to a
// listener that has been removed or replaced. See stopStateChangeWatchLocked.
stateChangeDone chan struct{}
// Latched "the server wants an interactive login": survives the engine
// restarts that replace the run loop's context state. See Client.Status.
// Guarded by loginRequiredMu together with loginCleared, which counts
// clears so a stale observation cannot re-latch over one.
loginRequiredMu sync.Mutex
loginRequired bool
loginCleared uint64
extendMu sync.Mutex
extendCancel context.CancelFunc
}
func (c *Client) setState(cfg *profilemanager.Config, cacheDir string, cc *internal.ConnectClient) {
@@ -167,16 +148,11 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
if err != nil {
return err
}
// todo do not throw error in case of cancelled context
ctx = internal.CtxInitState(ctx)
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
c.setState(cfg, cacheDir, connectClient)
// This path runs the interactive SSO flow, so reaching here means the peer
// is authenticated again — release the latch Status() reports from. Clear
// only once the fresh connect client is installed: until then Status()
// still reads the previous run's context state, which holds the NeedsLogin
// that prompted this login, and would re-latch what was just cleared.
c.clearLoginRequired()
return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
}
@@ -271,9 +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
}
@@ -301,7 +274,7 @@ func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool) (strin
uploadCtx, cancel := context.WithTimeout(context.Background(), 2*time.Minute)
defer cancel()
key, err := debug.UploadDebugBundle(uploadCtx, types.DefaultBundleURL, cfg.ManagementURL.String(), path, false)
key, err := debug.UploadDebugBundle(uploadCtx, types.DefaultBundleURL, cfg.ManagementURL.String(), path)
if err != nil {
return "", fmt.Errorf("upload debug bundle: %w", err)
}
@@ -323,13 +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))
@@ -340,20 +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
}
@@ -484,6 +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 {
@@ -503,22 +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
@@ -553,28 +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")
}

View File

@@ -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 {

View File

@@ -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)

View 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)
}

View File

@@ -1,309 +0,0 @@
//go:build android
package android
import (
"context"
"fmt"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/internal"
"github.com/netbirdio/netbird/client/internal/auth"
"github.com/netbirdio/netbird/client/internal/auth/sessionwatch"
"github.com/netbirdio/netbird/client/internal/peer"
cProto "github.com/netbirdio/netbird/client/proto"
)
// StateChangeListener receives client state notifications.
//
// OnStateChanged is a payload-free wake-up whenever the state snapshot
// changed: connection state, the run-loop status label (e.g. NeedsLogin) or
// the session deadline. It mirrors the daemon's SubscribeStatus stream
// trigger — on each signal the consumer pulls the fresh values via
// Status() / SessionExpiresAtUnix().
//
// OnSessionExpiring forwards the engine's session-expiry warnings, fired at
// sessionwatch.WarningLead before the deadline and again at FinalWarningLead
// (finalWarning true). The second one is suppressed when the user dismissed
// the first via DismissSessionWarning. The daemon turns the same events into
// its tray notification.
type StateChangeListener interface {
OnStateChanged()
OnSessionExpiring(expiresAtUnix int64, leadMinutes int64, finalWarning bool)
}
// Status returns the connect run-loop's status label — the same value the
// desktop daemon serves in StatusResponse.Status. "NeedsLogin" means the
// management server rejected the peer and an interactive login is required.
//
// The label is latched: the run loop keeps its status in a per-run context
// state, which a restart replaces with a fresh Idle one, so an engine restart
// (network change, always-on) would otherwise erase the fact that the peer
// still needs to log in. Only a successful interactive login or extend clears
// it — see clearLoginRequired.
func (c *Client) Status() string {
latched, generation := c.loginRequiredState()
if latched {
return string(internal.StatusNeedsLogin)
}
cc := c.getConnectClient()
if cc == nil {
return string(internal.StatusIdle)
}
status := cc.Status()
if status == internal.StatusNeedsLogin {
c.latchLoginRequired(generation)
}
return string(status)
}
func (c *Client) loginRequiredState() (bool, uint64) {
c.loginRequiredMu.Lock()
defer c.loginRequiredMu.Unlock()
return c.loginRequired, c.loginCleared
}
// latchLoginRequired records a NeedsLogin observation, unless a clear landed
// while the caller was reading the run loop's status: cc.Status() is read
// outside the lock, so a login or extend completing in that window would
// otherwise be undone by this stale observation, stranding the UI on
// "login required" over a healthy session.
func (c *Client) latchLoginRequired(observedGeneration uint64) {
c.loginRequiredMu.Lock()
defer c.loginRequiredMu.Unlock()
if c.loginCleared != observedGeneration {
return
}
c.loginRequired = true
}
// clearLoginRequired releases the latch after a successful interactive login
// or session extend, and invalidates any observation already in flight.
func (c *Client) clearLoginRequired() {
c.loginRequiredMu.Lock()
defer c.loginRequiredMu.Unlock()
c.loginRequired = false
c.loginCleared++
}
// SessionExpiresAtUnix returns the SSO session deadline as unix seconds, or 0
// when no deadline is known (not SSO-registered, expiry disabled, or the
// engine has not received one yet). A past value means the session expired.
// Mirror of StatusResponse.sessionExpiresAt on the desktop daemon.
func (c *Client) SessionExpiresAtUnix() int64 {
deadline := c.recorder.GetSessionExpiresAt()
if deadline.IsZero() {
return 0
}
return deadline.Unix()
}
// SetStateChangeListener registers the state notification listener.
// Replaces any previously registered listener; remove it with
// RemoveStateChangeListener.
func (c *Client) SetStateChangeListener(listener StateChangeListener) {
c.stateChangeMu.Lock()
defer c.stateChangeMu.Unlock()
c.stopStateChangeWatchLocked()
if listener == nil {
return
}
// Both subscriptions are buffered (one pending tick, ten pending events),
// so unsubscribing is not enough to stop callbacks: the loops would drain
// what is already queued and deliver it to a listener the caller has
// already removed or replaced. Gate every callback on this registration's
// own signal, which is closed before unsubscribing.
done := make(chan struct{})
c.stateChangeDone = done
id, ch := c.recorder.SubscribeToStateChanges()
c.stateChangeSubID = id
// The channel is closed by UnsubscribeFromStateChanges, which ends the
// goroutine. Ticks are coalesced (buffer of one), so a burst of changes
// wakes the listener once.
go func() {
for range ch {
select {
case <-done:
return
default:
}
listener.OnStateChanged()
}
}()
c.eventSub = c.recorder.SubscribeToEvents()
go watchSessionWarnings(c.eventSub, listener, done)
}
// RemoveStateChangeListener unregisters the state notification listener.
func (c *Client) RemoveStateChangeListener() {
c.stateChangeMu.Lock()
defer c.stateChangeMu.Unlock()
c.stopStateChangeWatchLocked()
}
// DismissSessionWarning records the user's "Dismiss" on the first expiry
// warning and suppresses the final one for the current deadline. A refreshed
// deadline re-arms both. No-op while the engine is not running.
func (c *Client) DismissSessionWarning() {
cc := c.getConnectClient()
if cc == nil {
return
}
engine := cc.Engine()
if engine == nil {
return
}
engine.DismissSessionWarning()
}
// ExtendAuthSession runs the interactive SSO flow to obtain a fresh JWT and
// asks the management server to extend the session deadline. The tunnel is
// untouched: no resync, no reconnect. Async; the result arrives on the
// listener. Mirror of the daemon's RequestExtendAuthSession /
// WaitExtendAuthSession RPC pair, with URLOpener playing the "UI opens the
// browser" role.
//
// Only one flow may be in flight: the PKCE step binds a fixed loopback port,
// so a second concurrent flow would fail on that bind. Call
// CancelExtendAuthSession when the user abandons the browser.
func (c *Client) ExtendAuthSession(urlOpener URLOpener, isAndroidTV bool, resultListener ErrListener) {
ctx, err := c.beginExtend()
if err != nil {
resultListener.OnError(err)
return
}
go func() {
defer c.endExtend()
if err := c.extendAuthSession(ctx, urlOpener, isAndroidTV); err != nil {
resultListener.OnError(err)
return
}
resultListener.OnSuccess()
}()
}
// CancelExtendAuthSession aborts an in-flight ExtendAuthSession. The tunnel is
// left alone — unlike the login flow, which cancels the whole client context
// by stopping the engine. Without this the abandoned PKCE wait keeps its
// loopback port for the full flow timeout and blocks every later attempt.
// No-op when no flow is running.
func (c *Client) CancelExtendAuthSession() {
c.extendMu.Lock()
defer c.extendMu.Unlock()
if c.extendCancel != nil {
c.extendCancel()
}
}
func (c *Client) stopStateChangeWatchLocked() {
// Signal first, unsubscribe second: closing the channels only stops new
// items, and the loops would still hand whatever is buffered to a listener
// that is no longer registered.
if c.stateChangeDone != nil {
close(c.stateChangeDone)
c.stateChangeDone = nil
}
if c.stateChangeSubID != "" {
c.recorder.UnsubscribeFromStateChanges(c.stateChangeSubID)
c.stateChangeSubID = ""
}
if c.eventSub != nil {
// Closes the channel, which ends watchSessionWarnings.
c.recorder.UnsubscribeFromEvents(c.eventSub)
c.eventSub = nil
}
}
// watchSessionWarnings forwards the engine's session-expiry warnings to the
// listener. The event stream also carries unrelated traffic — network-map
// updates on every sync, DNS and route errors — so everything but an
// AUTHENTICATION event carrying the session-warning marker is dropped. Exits
// when the subscription is closed by UnsubscribeFromEvents, or earlier when
// done is closed — the stream buffers up to ten events, and a deregistered
// listener must not receive the ones already queued.
func watchSessionWarnings(sub *peer.EventSubscription, listener StateChangeListener, done <-chan struct{}) {
for ev := range sub.Events() {
select {
case <-done:
return
default:
}
if ev.GetCategory() != cProto.SystemEvent_AUTHENTICATION {
continue
}
meta := ev.GetMetadata()
if meta[sessionwatch.MetaSessionWarning] != "true" {
// Other AUTHENTICATION events exist (e.g. a deadline rejected as
// out of range); they carry no warning marker.
continue
}
deadline, err := sessionwatch.ParseExpiresAt(meta[sessionwatch.MetaSessionExpiresAt])
if err != nil {
log.Warnf("session warning event with unparsable deadline: %v", err)
continue
}
lead, err := sessionwatch.ParseLeadMinutes(meta[sessionwatch.MetaSessionLeadMinutes])
if err != nil {
// Informational only — the deadline above is what drives the UI.
lead = 0
}
listener.OnSessionExpiring(deadline.Unix(), int64(lead),
meta[sessionwatch.MetaSessionFinal] == "true")
}
}
func (c *Client) beginExtend() (context.Context, error) {
c.extendMu.Lock()
defer c.extendMu.Unlock()
if c.extendCancel != nil {
return nil, fmt.Errorf("session extend already in progress")
}
ctx, cancel := context.WithCancel(context.Background())
c.extendCancel = cancel
return ctx, nil
}
func (c *Client) endExtend() {
c.extendMu.Lock()
defer c.extendMu.Unlock()
if c.extendCancel != nil {
c.extendCancel()
c.extendCancel = nil
}
}
func (c *Client) extendAuthSession(ctx context.Context, urlOpener URLOpener, isAndroidTV bool) error {
cfg, _, cc := c.stateSnapshot()
if cfg == nil || cc == nil {
return fmt.Errorf("engine is not running")
}
engine := cc.Engine()
if engine == nil {
return fmt.Errorf("engine is not initialized")
}
authClient, err := auth.NewAuth(ctx, cfg.PrivateKey, cfg.ManagementURL, cfg)
if err != nil {
return fmt.Errorf("failed to create auth client: %v", err)
}
defer authClient.Close()
a := &Auth{ctx: ctx, config: cfg}
tokenInfo, err := a.foregroundGetTokenInfo(authClient, urlOpener, isAndroidTV)
if err != nil {
return fmt.Errorf("interactive sso login failed: %v", err)
}
if _, err := engine.ExtendAuthSession(ctx, tokenInfo.GetTokenToUse()); err != nil {
return err
}
c.clearLoginRequired()
go urlOpener.OnLoginSuccess()
return nil
}

View File

@@ -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
}

View File

@@ -29,9 +29,8 @@ const errCloseConnection = "Failed to close connection: %v"
var (
logFileCount uint32
systemInfoFlag bool
uploadBundleFlag bool
uploadBundleURLFlag string
uploadBundleInsecureFlag bool
uploadBundleFlag bool
uploadBundleURLFlag string
)
var debugCmd = &cobra.Command{
@@ -175,11 +174,10 @@ func debugBundle(cmd *cobra.Command, _ []string) error {
}
if uploadBundleFlag {
request.UploadURL = uploadBundleURLFlag
request.UploadInsecure = uploadBundleInsecureFlag
}
resp, err := client.DebugBundle(cmd.Context(), request)
if err != nil {
return daemonCallError("bundle debug", err)
return fmt.Errorf("failed to bundle debug: %v", status.Convert(err).Message())
}
cmd.Printf("Local file:\n%s\n", resp.GetPath())
@@ -375,11 +373,10 @@ func runForDuration(cmd *cobra.Command, args []string) error {
}
if uploadBundleFlag {
request.UploadURL = uploadBundleURLFlag
request.UploadInsecure = uploadBundleInsecureFlag
}
resp, err := client.DebugBundle(cmd.Context(), request)
if err != nil {
return daemonCallError("bundle debug", err)
return fmt.Errorf("failed to bundle debug: %v", status.Convert(err).Message())
}
if needsRestoreUp {
@@ -527,12 +524,10 @@ func init() {
debugBundleCmd.Flags().BoolVarP(&systemInfoFlag, "system-info", "S", true, "Adds system information to the debug bundle")
debugBundleCmd.Flags().BoolVarP(&uploadBundleFlag, "upload-bundle", "U", false, "Uploads the debug bundle to a server")
debugBundleCmd.Flags().StringVar(&uploadBundleURLFlag, "upload-bundle-url", types.DefaultBundleURL, "Service URL to get an URL to upload the debug bundle")
debugBundleCmd.Flags().BoolVar(&uploadBundleInsecureFlag, "upload-bundle-insecure", false, "Allow uploading to an http or untrusted-TLS upload server (self-hosted); requires root")
forCmd.Flags().Uint32VarP(&logFileCount, "log-file-count", "C", 1, "Number of rotated log files to include in debug bundle")
forCmd.Flags().BoolVarP(&systemInfoFlag, "system-info", "S", true, "Adds system information to the debug bundle")
forCmd.Flags().BoolVarP(&uploadBundleFlag, "upload-bundle", "U", false, "Uploads the debug bundle to a server")
forCmd.Flags().StringVar(&uploadBundleURLFlag, "upload-bundle-url", types.DefaultBundleURL, "Service URL to get an URL to upload the debug bundle")
forCmd.Flags().BoolVar(&uploadBundleInsecureFlag, "upload-bundle-insecure", false, "Allow uploading to an http or untrusted-TLS upload server (self-hosted); requires root")
forCmd.Flags().Bool("capture", false, "Capture packets during the debug duration and include in bundle")
}

View File

@@ -17,9 +17,7 @@ import (
"github.com/netbirdio/netbird/client/internal"
"github.com/netbirdio/netbird/client/internal/auth"
"github.com/netbirdio/netbird/client/internal/profilemanager"
nbnet "github.com/netbirdio/netbird/client/net"
"github.com/netbirdio/netbird/client/proto"
"github.com/netbirdio/netbird/client/server"
"github.com/netbirdio/netbird/client/system"
"github.com/netbirdio/netbird/util"
)
@@ -333,14 +331,6 @@ func doForegroundLogin(ctx context.Context, cmd *cobra.Command, setupKey string,
return fmt.Errorf("read config file %s: %v", configFilePath, err)
}
// Mirror runInForegroundMode: recover residual state (DNS, firewall,
// ssh config, legacy routing) from a previous unclean shutdown and
// enable advanced routing before dialing management.
if err := server.RestoreResidualState(ctx, profilemanager.NewServiceManager(configFilePath).GetStatePath()); err != nil {
log.Warnf("failed to restore residual state: %v", err)
}
nbnet.Init()
err = foregroundLogin(ctx, cmd, config, setupKey, activeProf.ID)
if err != nil {
return fmt.Errorf("foreground login failed: %v", err)

View File

@@ -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")

View File

@@ -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.

View File

@@ -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

View File

@@ -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 {

View File

@@ -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() {

View File

@@ -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")
}
}

View File

@@ -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 != "" {

View File

@@ -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")
}

View File

@@ -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...)
}

View File

@@ -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)

View File

@@ -22,8 +22,6 @@ import (
"github.com/netbirdio/netbird/client/internal/peer"
"github.com/netbirdio/netbird/client/internal/profilemanager"
"github.com/netbirdio/netbird/client/proto"
nbnet "github.com/netbirdio/netbird/client/net"
"github.com/netbirdio/netbird/client/server"
"github.com/netbirdio/netbird/client/system"
"github.com/netbirdio/netbird/shared/management/domain"
"github.com/netbirdio/netbird/util"
@@ -231,24 +229,6 @@ func runInForegroundMode(ctx context.Context, cmd *cobra.Command, activeProf *pr
_, _ = profilemanager.UpdateOldManagementURL(ctx, config, configFilePath)
// Restore residual state left by a previous run that did not shut down
// cleanly, mirroring what the daemon does before connecting: it recovers
// DNS config (a stale resolv.conf takeover can make the management
// hostname unresolvable), firewall rules, ssh config and legacy routing.
// Route cleanup itself happens at engine start; nbnet.Init() below lets
// the management dial bypass a leftover fwmark rule until then.
// Foreground mode is particularly exposed in containers: a crashed
// container restarts inside the same (pod) network namespace, so stale
// state survives while the process does not.
if err := server.RestoreResidualState(ctx, profilemanager.NewServiceManager(configPath).GetStatePath()); err != nil {
log.Warnf("failed to restore residual state: %v", err)
}
// Enable advanced routing (as the daemon does on startup) so the
// management dial bypasses a leftover fwmark rule instead of being
// shunted into a stale routing table.
nbnet.Init()
err = foregroundLogin(ctx, cmd, config, providedSetupKey, activeProf.ID)
if err != nil {
return fmt.Errorf("foreground login failed: %v", err)
@@ -325,7 +305,7 @@ 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 +359,7 @@ 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 +372,7 @@ 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

View File

@@ -6,11 +6,6 @@ import (
"runtime"
)
// UILogFile is the file name the desktop UI writes its log to. It is defined
// here so the UI (writer), the daemon's RegisterUILog validation, and the debug
// bundle collector all share one definition.
const UILogFile = "gui-client.log"
var StateDir string
func init() {

View File

@@ -1,60 +0,0 @@
package nftables
import (
"testing"
"github.com/google/nftables/expr"
"github.com/stretchr/testify/require"
)
func TestBuildLegacyRouteRuleExpressions(t *testing.T) {
sourcePayload := &expr.Payload{}
sourceCmp := &expr.Cmp{}
destinationPayload := &expr.Payload{}
destinationCmp := &expr.Cmp{}
nilSourceDestination := &expr.Payload{}
nilDestinationSource := &expr.Cmp{}
tests := []struct {
name string
source []expr.Any
destination []expr.Any
matches []expr.Any
}{
{
name: "both non-empty",
source: []expr.Any{sourcePayload, sourceCmp},
destination: []expr.Any{destinationPayload, destinationCmp},
matches: []expr.Any{sourcePayload, sourceCmp, destinationPayload, destinationCmp},
},
{
name: "nil source",
destination: []expr.Any{nilSourceDestination},
matches: []expr.Any{nilSourceDestination},
},
{
name: "nil destination",
source: []expr.Any{nilDestinationSource},
matches: []expr.Any{nilDestinationSource},
},
{
name: "both nil",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got := buildLegacyRouteRuleExpressions(tt.source, tt.destination)
require.Len(t, got, len(tt.matches)+2)
for i, match := range tt.matches {
require.Same(t, match, got[i])
}
require.IsType(t, &expr.Counter{}, got[len(tt.matches)])
verdict, ok := got[len(tt.matches)+1].(*expr.Verdict)
require.True(t, ok)
require.Equal(t, expr.VerdictAccept, verdict.Kind)
})
}
}

View File

@@ -953,17 +953,6 @@ func (r *router) addMSSClampingRules() error {
return r.conn.Flush()
}
func buildLegacyRouteRuleExpressions(sourceExp, destExp []expr.Any) []expr.Any {
exprs := make([]expr.Any, 0, len(sourceExp)+len(destExp)+2)
exprs = append(exprs, sourceExp...)
exprs = append(exprs, destExp...)
exprs = append(exprs,
&expr.Counter{},
&expr.Verdict{Kind: expr.VerdictAccept},
)
return exprs
}
// addLegacyRouteRule adds a legacy routing rule for mgmt servers pre route acls
func (r *router) addLegacyRouteRule(pair firewall.RouterPair) error {
sourceExp, err := r.applyNetwork(pair.Source, nil, true)
@@ -976,7 +965,15 @@ func (r *router) addLegacyRouteRule(pair firewall.RouterPair) error {
return fmt.Errorf("apply destination: %w", err)
}
exprs := buildLegacyRouteRuleExpressions(sourceExp, destExp)
exprs := []expr.Any{
&expr.Counter{},
&expr.Verdict{
Kind: expr.VerdictAccept,
},
}
exprs = append(exprs, sourceExp...)
exprs = append(exprs, destExp...)
ruleKey := firewall.GenKey(firewall.ForwardingFormat, pair)

View File

@@ -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
}

View File

@@ -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")
}

View File

@@ -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()
}

View File

@@ -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))
}
}

View File

@@ -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")
}

View File

@@ -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")
}

View File

@@ -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)
}

View File

@@ -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)
}
})
}
}

View File

@@ -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,

View File

@@ -259,18 +259,12 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn
ticker := time.NewTicker(interval)
defer ticker.Stop()
log.Infof("device flow: waiting for user authorization, polling token endpoint every %s, code expires in %s", interval, timeout)
start := time.Now()
polls := 0
for {
select {
case <-waitCtx.Done():
return TokenInfo{}, waitCtx.Err()
case <-ticker.C:
polls++
tokenResponse, err := d.requestToken(info)
if err != nil {
return TokenInfo{}, fmt.Errorf("parsing token response failed with error: %v", err)
@@ -278,12 +272,10 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn
if tokenResponse.Error != "" {
if tokenResponse.Error == "authorization_pending" {
log.Tracef("device flow: authorization still pending after poll %d", polls)
continue
} else if tokenResponse.Error == "slow_down" {
interval += (3 * time.Second)
ticker.Reset(interval)
log.Infof("device flow: IdP requested slow_down, polling interval increased to %s", interval)
continue
}
@@ -299,12 +291,11 @@ 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)
}
log.Infof("device flow: user authorization confirmed after %d polls in %s", polls, time.Since(start).Round(time.Second))
return tokenInfo, err
}
}

View File

@@ -188,8 +188,6 @@ func (p *PKCEAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowInfo
waitCtx, cancel := context.WithTimeout(ctx, timeout)
defer cancel()
log.Infof("pkce flow: waiting for authorization callback on %s, timeout %s", p.oAuthConfig.RedirectURL, timeout)
tokenChan := make(chan *oauth2.Token, 1)
errChan := make(chan error, 1)
@@ -223,7 +221,6 @@ func (p *PKCEAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowInfo
func (p *PKCEAuthorizationFlow) startServer(server *http.Server, tokenChan chan<- *oauth2.Token, errChan chan<- error) {
mux := http.NewServeMux()
mux.HandleFunc("/", func(w http.ResponseWriter, req *http.Request) {
log.Infof("pkce flow: received authorization callback from IdP")
cert := p.providerConfig.ClientCertPair
if cert != nil {
tr := &http.Transport{
@@ -274,18 +271,11 @@ func (p *PKCEAuthorizationFlow) handleRequest(req *http.Request) (*oauth2.Token,
return nil, fmt.Errorf("authentication failed: missing code")
}
exchangeStart := time.Now()
token, err := p.oAuthConfig.Exchange(
return p.oAuthConfig.Exchange(
req.Context(),
code,
oauth2.SetAuthURLParam("code_verifier", p.codeVerifier),
)
if err != nil {
return nil, err
}
log.Infof("pkce flow: authorization code exchanged for token in %s", time.Since(exchangeStart).Round(time.Millisecond))
return token, nil
}
func (p *PKCEAuthorizationFlow) parseOAuthToken(token *oauth2.Token) (TokenInfo, error) {
@@ -306,7 +296,7 @@ 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 +310,6 @@ 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 {

View File

@@ -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

View File

@@ -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)
}
}

View File

@@ -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
}

View File

@@ -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)
}
}
}

View File

@@ -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,
@@ -125,7 +109,7 @@ func (e *ConnMgr) UpdatedRemoteFeatureFlag(ctx context.Context, enabled bool) er
return nil
}
log.Infof("lazy connection manager is enabled by the management feature flag")
log.Warnf("lazy connection manager is enabled by management feature flag")
e.initLazyManager(ctx)
e.statusRecorder.UpdateLazyConnection(true)
return e.addPeersToLazyConnManager()
@@ -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
}

View File

@@ -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 }

View File

@@ -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,

View File

@@ -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)
}

View File

@@ -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())
}

View File

@@ -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)
}
})
}
}

View File

@@ -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
}

View File

@@ -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
}

View File

@@ -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")
}

View File

@@ -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)
}
}

View File

@@ -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)
}

View File

@@ -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
}

View File

@@ -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
}

View File

@@ -229,6 +229,7 @@ scutil_dns.txt (macOS only):
const (
clientLogFile = "client.log"
uiLogFile = "gui-client.log"
errorLogFile = "netbird.err"
stdoutLogFile = "netbird.out"
@@ -247,20 +248,6 @@ type MetricsExporter interface {
Export(w io.Writer) error
}
// LogOpener opens a log file for inclusion in the bundle. It exists so that log
// files whose path was supplied by an IPC caller can be opened under a check
// the daemon defines, instead of being opened with the daemon's privileges
// unconditionally.
type LogOpener func(path string) (*os.File, error)
func openLogFile(path string) (*os.File, error) {
f, err := os.Open(path)
if err != nil {
return nil, fmt.Errorf("open %s: %w", path, err)
}
return f, nil
}
type BundleGenerator struct {
anonymizer *anonymize.Anonymizer
@@ -270,7 +257,6 @@ type BundleGenerator struct {
syncResponse *mgmProto.SyncResponse
logPath string
uiLogPath string
uiLogOpener LogOpener
tempDir string
statePath string
cpuProfile []byte
@@ -299,20 +285,14 @@ type GeneratorDependencies struct {
SyncResponse *mgmProto.SyncResponse
LogPath string
UILogPath string // Absolute path to the desktop UI's gui-client.log, reported via RegisterUILog. Empty if no UI registered one.
// UILogOpener opens the UI log and its rotated siblings. The path comes from
// a local IPC caller, so the daemon must not open it with plain os.Open: the
// opener is where the caller's right to that file is enforced. Defaults to
// os.Open, which is only correct where the path is not caller-supplied
// (mobile).
UILogOpener LogOpener
TempDir string // Directory for temporary bundle zip files. If empty, os.TempDir() is used.
StatePath string // Path to the state file. If empty, the ServiceManager default path is used.
CPUProfile []byte
CapturePath string
RefreshStatus func()
ClientMetrics MetricsExporter
DaemonVersion string
CliVersion string
TempDir string // Directory for temporary bundle zip files. If empty, os.TempDir() is used.
StatePath string // Path to the state file. If empty, the ServiceManager default path is used.
CPUProfile []byte
CapturePath string
RefreshStatus func()
ClientMetrics MetricsExporter
DaemonVersion string
CliVersion string
}
func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGenerator {
@@ -322,11 +302,6 @@ func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGen
logFileCount = 1
}
uiLogOpener := deps.UILogOpener
if uiLogOpener == nil {
uiLogOpener = openLogFile
}
return &BundleGenerator{
anonymizer: anonymize.NewAnonymizer(anonymize.DefaultAddresses()),
@@ -335,7 +310,6 @@ func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGen
syncResponse: deps.SyncResponse,
logPath: deps.LogPath,
uiLogPath: deps.UILogPath,
uiLogOpener: uiLogOpener,
tempDir: deps.TempDir,
statePath: deps.StatePath,
cpuProfile: deps.CPUProfile,
@@ -506,6 +480,7 @@ func (g *BundleGenerator) addStatus() error {
fullStatus := g.statusRecorder.GetFullStatus()
protoFullStatus := nbstatus.ToProtoFullStatus(fullStatus)
protoFullStatus.Events = g.statusRecorder.GetEventHistory()
overview := nbstatus.ConvertToStatusOutputOverview(protoFullStatus, nbstatus.ConvertOptions{
Anonymize: g.anonymize,
ProfileName: profName,
@@ -702,7 +677,6 @@ 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))
@@ -1022,11 +996,11 @@ func (g *BundleGenerator) addLogfile() error {
logDir := filepath.Dir(g.logPath)
if err := g.addSingleLogfile(openLogFile, g.logPath, clientLogFile); err != nil {
if err := g.addSingleLogfile(g.logPath, clientLogFile); err != nil {
return fmt.Errorf("add client log file to zip: %w", err)
}
g.addRotatedLogFiles(openLogFile, logDir, clientLogPrefix)
g.addRotatedLogFiles(logDir, clientLogPrefix)
stdErrLogPath := filepath.Join(logDir, errorLogFile)
stdoutLogPath := filepath.Join(logDir, stdoutLogFile)
@@ -1035,11 +1009,11 @@ func (g *BundleGenerator) addLogfile() error {
stdoutLogPath = darwinStdoutLogPath
}
if err := g.addSingleLogfile(openLogFile, stdErrLogPath, errorLogFile); err != nil {
if err := g.addSingleLogfile(stdErrLogPath, errorLogFile); err != nil {
log.Warnf("Failed to add %s to zip: %v", errorLogFile, err)
}
if err := g.addSingleLogfile(openLogFile, stdoutLogPath, stdoutLogFile); err != nil {
if err := g.addSingleLogfile(stdoutLogPath, stdoutLogFile); err != nil {
log.Warnf("Failed to add %s to zip: %v", stdoutLogFile, err)
}
@@ -1056,18 +1030,18 @@ func (g *BundleGenerator) addUILog() error {
return nil
}
if err := g.addSingleLogfile(g.uiLogOpener, g.uiLogPath, configs.UILogFile); err != nil {
if err := g.addSingleLogfile(g.uiLogPath, uiLogFile); err != nil {
return fmt.Errorf("add UI log file to zip: %w", err)
}
g.addRotatedLogFiles(g.uiLogOpener, filepath.Dir(g.uiLogPath), uiLogPrefix)
g.addRotatedLogFiles(filepath.Dir(g.uiLogPath), uiLogPrefix)
return nil
}
// addSingleLogfile adds a single log file to the archive
func (g *BundleGenerator) addSingleLogfile(open LogOpener, logPath, targetName string) error {
logFile, err := open(logPath)
func (g *BundleGenerator) addSingleLogfile(logPath, targetName string) error {
logFile, err := os.Open(logPath)
if err != nil {
return fmt.Errorf("open log file %s: %w", targetName, err)
}
@@ -1092,8 +1066,8 @@ func (g *BundleGenerator) addSingleLogfile(open LogOpener, logPath, targetName s
}
// addSingleLogFileGz adds a single gzipped log file to the archive
func (g *BundleGenerator) addSingleLogFileGz(open LogOpener, logPath, targetName string) error {
f, err := open(logPath)
func (g *BundleGenerator) addSingleLogFileGz(logPath, targetName string) error {
f, err := os.Open(logPath)
if err != nil {
return fmt.Errorf("open gz log file %s: %w", targetName, err)
}
@@ -1140,7 +1114,7 @@ func (g *BundleGenerator) addSingleLogFileGz(open LogOpener, logPath, targetName
// addRotatedLogFiles adds rotated log files to the bundle based on logFileCount.
// prefix is the base log name without extension (e.g. "client", "gui-client");
// the glob matches both files rotated by us and by logrotate on linux.
func (g *BundleGenerator) addRotatedLogFiles(open LogOpener, logDir, prefix string) {
func (g *BundleGenerator) addRotatedLogFiles(logDir, prefix string) {
if g.logFileCount == 0 {
return
}
@@ -1180,9 +1154,9 @@ func (g *BundleGenerator) addRotatedLogFiles(open LogOpener, logDir, prefix stri
for i := 0; i < maxFiles; i++ {
name := filepath.Base(files[i])
if strings.HasSuffix(name, ".gz") {
err = g.addSingleLogFileGz(open, files[i], name)
err = g.addSingleLogFileGz(files[i], name)
} else {
err = g.addSingleLogfile(open, files[i], name)
err = g.addSingleLogfile(files[i], name)
}
if err != nil {
log.Warnf("failed to add rotated log %s: %v", name, err)

View File

@@ -27,7 +27,7 @@ func (g *BundleGenerator) addPlatformLog() error {
}
swiftLogPath := filepath.Join(filepath.Dir(g.logPath), swiftLogFile)
if err := g.addSingleLogfile(openLogFile, swiftLogPath, swiftLogFile); err != nil {
if err := g.addSingleLogfile(swiftLogPath, swiftLogFile); err != nil {
// The Swift log is best-effort: the app may not have written it yet.
log.Warnf("failed to add %s to debug bundle: %v", swiftLogFile, err)
}

View File

@@ -97,7 +97,7 @@ func runAddRotatedLogFilesPrefix(t *testing.T, dir, prefix string, logFileCount
archive: zip.NewWriter(&buf),
logFileCount: logFileCount,
}
g.addRotatedLogFiles(openLogFile, dir, prefix)
g.addRotatedLogFiles(dir, prefix)
require.NoError(t, g.archive.Close())
zr, err := zip.NewReader(bytes.NewReader(buf.Bytes()), int64(buf.Len()))

View File

@@ -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} {

View File

@@ -1,64 +0,0 @@
package debug
import (
"archive/zip"
"bytes"
"fmt"
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/client/configs"
)
// bundleEntries generates a bundle with the given generator and returns the
// set of entry names in the resulting archive.
func bundleEntries(t *testing.T, g *BundleGenerator) map[string]struct{} {
t.Helper()
path, err := g.Generate()
require.NoError(t, err)
t.Cleanup(func() { _ = os.Remove(path) })
data, err := os.ReadFile(path)
require.NoError(t, err)
zr, err := zip.NewReader(bytes.NewReader(data), int64(len(data)))
require.NoError(t, err)
names := make(map[string]struct{}, len(zr.File))
for _, f := range zr.File {
names[f.Name] = struct{}{}
}
return names
}
func TestBundleIncludesUILogWhenOpenerAllows(t *testing.T) {
path := filepath.Join(t.TempDir(), configs.UILogFile)
require.NoError(t, os.WriteFile(path, []byte("gui log"), 0600))
g := NewBundleGenerator(GeneratorDependencies{
UILogPath: path,
UILogOpener: openLogFile,
}, BundleConfig{})
require.Contains(t, bundleEntries(t, g), configs.UILogFile)
}
// A UILogOpener that refuses (as the ownership check does for a foreign file)
// keeps the UI log out of the bundle without failing bundle generation.
func TestBundleExcludesUILogWhenOpenerRefuses(t *testing.T) {
path := filepath.Join(t.TempDir(), configs.UILogFile)
require.NoError(t, os.WriteFile(path, []byte("secret"), 0600))
g := NewBundleGenerator(GeneratorDependencies{
UILogPath: path,
UILogOpener: func(string) (*os.File, error) {
return nil, fmt.Errorf("not owned by the caller")
},
}, BundleConfig{})
require.NotContains(t, bundleEntries(t, g), configs.UILogFile)
}

View File

@@ -3,12 +3,10 @@ package debug
import (
"context"
"crypto/sha256"
"crypto/tls"
"encoding/json"
"fmt"
"io"
"net/http"
neturl "net/url"
"os"
"github.com/netbirdio/netbird/upload-server/types"
@@ -16,80 +14,20 @@ import (
const maxBundleUploadSize = 50 * 1024 * 1024
// requireHTTPS refuses any URL the daemon would fetch or upload to that is not
// https. The daemon runs as root and the bundle carries its logs and state, so a
// plaintext hop is a place to intercept the bundle or the presigned redirect.
// The server-side gate already enforces this for the desktop path; this also
// covers the mobile and job-runner callers that reach this package directly.
// Skipped when the caller opted into an insecure upload (self-hosted server).
func requireHTTPS(what, rawURL string) error {
parsed, err := neturl.Parse(rawURL)
if err != nil {
return fmt.Errorf("parse %s: %w", what, err)
}
if parsed.Scheme != "https" {
return fmt.Errorf("%s must use https, got scheme %q", what, parsed.Scheme)
}
return nil
}
// uploadClient returns the HTTP client for the upload requests. The default
// client verifies TLS and refuses a redirect that would downgrade to a non-https
// hop, so a bundle can never leave over http after an https start. The insecure
// variant accepts http and untrusted certificates, and is only reachable for a
// privileged caller that passed --upload-bundle-insecure (see
// requirePrivilegeForUploadURL).
func uploadClient(insecure bool) *http.Client {
if !insecure {
return &http.Client{CheckRedirect: rejectInsecureRedirect}
}
return &http.Client{
Transport: &http.Transport{
//nolint:gosec // opt-in, privileged, self-hosted upload servers
TLSClientConfig: &tls.Config{InsecureSkipVerify: true, MinVersion: tls.VersionTLS12},
},
}
}
// rejectInsecureRedirect refuses a redirect to a non-https target and keeps the
// standard library's 10-hop limit that a custom CheckRedirect would otherwise
// disable.
func rejectInsecureRedirect(req *http.Request, via []*http.Request) error {
if req.URL.Scheme != "https" {
return fmt.Errorf("refusing redirect to non-https URL %s", req.URL.Redacted())
}
if len(via) >= 10 {
return fmt.Errorf("stopped after 10 redirects")
}
return nil
}
func UploadDebugBundle(ctx context.Context, url, managementURL, filePath string, insecure bool) (key string, err error) {
if !insecure {
if err := requireHTTPS("upload service URL", url); err != nil {
return "", err
}
}
response, err := getUploadURL(ctx, url, managementURL, insecure)
func UploadDebugBundle(ctx context.Context, url, managementURL, filePath string) (key string, err error) {
response, err := getUploadURL(ctx, url, managementURL)
if err != nil {
return "", err
}
if !insecure {
if err := requireHTTPS("upload URL from service", response.URL); err != nil {
return "", err
}
}
err = upload(ctx, filePath, response, insecure)
err = upload(ctx, filePath, response)
if err != nil {
return "", err
}
return response.Key, nil
}
func upload(ctx context.Context, filePath string, response *types.GetURLResponse, insecure bool) error {
func upload(ctx context.Context, filePath string, response *types.GetURLResponse) error {
fileData, err := os.Open(filePath)
if err != nil {
return fmt.Errorf("open file: %w", err)
@@ -114,7 +52,7 @@ func upload(ctx context.Context, filePath string, response *types.GetURLResponse
req.ContentLength = stat.Size()
req.Header.Set("Content-Type", "application/octet-stream")
putResp, err := uploadClient(insecure).Do(req)
putResp, err := http.DefaultClient.Do(req)
if err != nil {
return fmt.Errorf("upload failed: %v", err)
}
@@ -127,23 +65,16 @@ func upload(ctx context.Context, filePath string, response *types.GetURLResponse
return nil
}
func getUploadURL(ctx context.Context, serviceURL string, managementURL string, insecure bool) (*types.GetURLResponse, error) {
parsed, err := neturl.Parse(serviceURL)
if err != nil {
return nil, fmt.Errorf("parse upload service URL: %w", err)
}
q := parsed.Query()
q.Set("id", getURLHash(managementURL))
parsed.RawQuery = q.Encode()
getReq, err := http.NewRequestWithContext(ctx, "GET", parsed.String(), nil)
func getUploadURL(ctx context.Context, url string, managementURL string) (*types.GetURLResponse, error) {
id := getURLHash(managementURL)
getReq, err := http.NewRequestWithContext(ctx, "GET", url+"?id="+id, nil)
if err != nil {
return nil, fmt.Errorf("create GET request: %w", err)
}
getReq.Header.Set(types.ClientHeader, types.ClientHeaderValue)
resp, err := uploadClient(insecure).Do(getReq)
resp, err := http.DefaultClient.Do(getReq)
if err != nil {
return nil, fmt.Errorf("get presigned URL: %w", err)
}

View File

@@ -5,7 +5,6 @@ import (
"errors"
"net"
"net/http"
"net/http/httptest"
"os"
"path/filepath"
"testing"
@@ -44,7 +43,7 @@ func TestUpload(t *testing.T) {
fileContent := []byte("test file content")
err := os.WriteFile(file, fileContent, 0640)
require.NoError(t, err)
key, err := UploadDebugBundle(context.Background(), testURL+types.GetURLPath, testURL, file, true)
key, err := UploadDebugBundle(context.Background(), testURL+types.GetURLPath, testURL, file)
require.NoError(t, err)
id := getURLHash(testURL)
require.Contains(t, key, id+"/")
@@ -80,47 +79,3 @@ func waitForServer(t *testing.T, addr string) {
}
t.Fatalf("server did not start listening on %s in time", addr)
}
func TestRequireHTTPS(t *testing.T) {
require.NoError(t, requireHTTPS("upload URL", "https://upload.example/path"))
require.Error(t, requireHTTPS("upload URL", "http://upload.example/path"))
require.Error(t, requireHTTPS("upload URL", "ftp://upload.example/path"))
require.Error(t, requireHTTPS("upload URL", "://malformed"))
}
func TestRejectInsecureRedirect(t *testing.T) {
httpsReq, err := http.NewRequest(http.MethodGet, "https://a.example/", nil)
require.NoError(t, err)
require.NoError(t, rejectInsecureRedirect(httpsReq, nil), "https redirect target must be allowed")
httpReq, err := http.NewRequest(http.MethodGet, "http://a.example/", nil)
require.NoError(t, err)
require.Error(t, rejectInsecureRedirect(httpReq, nil), "http redirect target must be refused")
require.Error(t, rejectInsecureRedirect(httpsReq, make([]*http.Request, 10)), "the 10-redirect limit must be enforced")
}
// The secure client refuses to follow an https response that redirects to http,
// so a bundle can't be downgraded onto plaintext mid-flight.
func TestUploadClientRefusesHTTPSToHTTPRedirect(t *testing.T) {
plain := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
w.WriteHeader(http.StatusOK)
}))
t.Cleanup(plain.Close)
secure := httptest.NewTLSServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
http.Redirect(w, r, plain.URL, http.StatusFound)
}))
t.Cleanup(secure.Close)
client := uploadClient(false)
// Trust the test server's cert without disabling verification globally.
client.Transport = secure.Client().Transport
resp, err := client.Get(secure.URL)
if resp != nil {
_ = resp.Body.Close()
}
require.Error(t, err, "redirect from https to http must be refused")
require.Contains(t, err.Error(), "non-https")
}

View File

@@ -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

View File

@@ -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
}

View File

@@ -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)
})
}

View File

@@ -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

View File

@@ -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
}

View File

@@ -292,16 +292,18 @@ func (s *serviceViaListener) generateFreePort() (uint16, error) {
return customPort, nil
}
probeListener, err := net.ListenUDP("udp4", &net.UDPAddr{})
udpAddr := net.UDPAddrFromAddrPort(netip.MustParseAddrPort("0.0.0.0:0"))
probeListener, err := net.ListenUDP("udp", udpAddr)
if err != nil {
log.Debugf("failed to bind random port for DNS: %s", err)
return 0, err
}
port := uint16(probeListener.LocalAddr().(*net.UDPAddr).Port)
if err = probeListener.Close(); err != nil {
addrPort := netip.MustParseAddrPort(probeListener.LocalAddr().String()) // might panic if address is incorrect
err = probeListener.Close()
if err != nil {
log.Debugf("failed to free up DNS port: %s", err)
return 0, err
}
return port, nil
return addrPort.Port(), nil
}

View File

@@ -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:
}
}
}

View File

@@ -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")
}

View File

@@ -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;
}

View File

@@ -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;
}

View File

@@ -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
@@ -562,7 +551,7 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
} else {
log.Infof("running rosenpass in strict mode")
}
e.rpManager, err = rosenpass.NewManager(e.config.PreSharedKey, e.config.WgIfaceName, publicKey)
e.rpManager, err = rosenpass.NewManager(e.config.PreSharedKey, e.config.WgIfaceName)
if err != nil {
return fmt.Errorf("create rosenpass manager: %w", err)
}
@@ -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,
@@ -2694,14 +2605,13 @@ func (e *Engine) updateForwardRules(rules []*mgmProto.ForwardingRule) ([]firewal
func (e *Engine) toExcludedLazyPeers(rules []firewallManager.ForwardRule, peers []*mgmProto.RemotePeerConfig) map[string]bool {
excludedPeers := make(map[string]bool)
// Ingress forward targets: inbound forwarded traffic is initiated remotely and
// cannot wake a lazy connection, so the peer routing the target must stay
// permanently connected. AllowedIPs are already parsed on the peer conn, so
// reuse those typed prefixes instead of re-parsing the network map strings.
for _, r := range rules {
ip := r.TranslatedAddress
for _, p := range peers {
if e.peerRoutesAddr(p, r.TranslatedAddress) {
for _, allowedIP := range p.GetAllowedIps() {
if allowedIP != ip.String() {
continue
}
log.Infof("exclude forwarder peer from lazy connection: %s", p.GetWgPubKey())
excludedPeers[p.GetWgPubKey()] = true
}
@@ -2711,27 +2621,6 @@ func (e *Engine) toExcludedLazyPeers(rules []firewallManager.ForwardRule, peers
return excludedPeers
}
// peerRoutesAddr reports whether the peer is a router for addr, matched against
// the peer's already-parsed AllowedIPs from the store (the same typed value the
// lazy manager consumes) rather than re-parsing the network map strings.
func (e *Engine) peerRoutesAddr(p *mgmProto.RemotePeerConfig, addr netip.Addr) bool {
prefixes, ok := e.peerStore.AllowedIPs(p.GetWgPubKey())
if !ok {
return false
}
return prefixesContain(prefixes, addr)
}
// prefixesContain reports whether addr falls within any of the prefixes.
func prefixesContain(prefixes []netip.Prefix, addr netip.Addr) bool {
for _, prefix := range prefixes {
if prefix.Contains(addr) {
return true
}
}
return false
}
// isChecksEqual checks if two slices of checks are equal.
func isChecksEqual(checks1, checks2 []*mgmProto.Checks) bool {
normalize := func(checks []*mgmProto.Checks) []string {

View File

@@ -1,87 +0,0 @@
package internal
import (
"net/netip"
"testing"
"github.com/stretchr/testify/require"
firewallManager "github.com/netbirdio/netbird/client/firewall/manager"
"github.com/netbirdio/netbird/client/internal/peer"
"github.com/netbirdio/netbird/client/internal/peerstore"
mgmProto "github.com/netbirdio/netbird/shared/management/proto"
)
func TestPrefixesContain(t *testing.T) {
tests := []struct {
name string
prefixes []string
addr string
want bool
}{
{name: "own overlay /32 matches", prefixes: []string{"100.110.8.145/32"}, addr: "100.110.8.145", want: true},
{name: "addr inside routed subnet", prefixes: []string{"10.121.0.0/16"}, addr: "10.121.208.4", want: true},
{name: "addr outside subnet", prefixes: []string{"10.121.0.0/16"}, addr: "10.122.0.1", want: false},
{name: "different /32", prefixes: []string{"100.110.8.145/32"}, addr: "100.110.8.146", want: false},
{name: "ipv6 /128 matches", prefixes: []string{"fd00::1/128"}, addr: "fd00::1", want: true},
{name: "no prefixes", prefixes: nil, addr: "10.121.208.4", want: false},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
prefixes := make([]netip.Prefix, 0, len(tt.prefixes))
for _, p := range tt.prefixes {
prefixes = append(prefixes, netip.MustParsePrefix(p))
}
require.Equal(t, tt.want, prefixesContain(prefixes, netip.MustParseAddr(tt.addr)))
})
}
}
// TestToExcludedLazyPeers_ForwardTarget guards a regression: the forward-target
// peer (the peer routing a ForwardRule.TranslatedAddress) must be excluded from
// lazy connections, matched via the peer's already-parsed AllowedIPs.
func TestToExcludedLazyPeers_ForwardTarget(t *testing.T) {
const targetPeerKey = "cccccccccccccccccccccccccccccccccccccccccc0="
const otherPeerKey = "dddddddddddddddddddddddddddddddddddddddddd0="
store := peerstore.NewConnStore()
store.AddPeerConn(targetPeerKey, newTestConn(t, targetPeerKey, "100.110.8.145/32"))
store.AddPeerConn(otherPeerKey, newTestConn(t, otherPeerKey, "100.110.9.10/32"))
e := &Engine{peerStore: store}
peers := []*mgmProto.RemotePeerConfig{
{WgPubKey: targetPeerKey, AllowedIps: []string{"100.110.8.145/32"}},
{WgPubKey: otherPeerKey, AllowedIps: []string{"100.110.9.10/32"}},
}
rules := []firewallManager.ForwardRule{
{TranslatedAddress: netip.MustParseAddr("100.110.8.145")},
}
excluded := e.toExcludedLazyPeers(rules, peers)
require.True(t, excluded[targetPeerKey], "forward-target peer must be excluded from lazy connections")
require.False(t, excluded[otherPeerKey], "non-target peer must not be excluded")
require.Len(t, excluded, 1)
}
func TestToExcludedLazyPeers_NoRules(t *testing.T) {
e := &Engine{peerStore: peerstore.NewConnStore()}
peers := []*mgmProto.RemotePeerConfig{
{WgPubKey: "peer-a", AllowedIps: []string{"100.110.8.145/32"}},
}
require.Empty(t, e.toExcludedLazyPeers(nil, peers))
}
func newTestConn(t *testing.T, key, allowedIP string) *peer.Conn {
t.Helper()
conn, err := peer.NewConn(peer.ConnConfig{
Key: key,
WgConfig: peer.WgConfig{AllowedIps: []netip.Prefix{netip.MustParsePrefix(allowedIP)}},
}, peer.ServiceDependencies{})
require.NoError(t, err)
return conn
}

View File

@@ -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")
})
}

View File

@@ -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
}

View File

@@ -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 }

View File

@@ -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
}

View File

@@ -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)
}

View File

@@ -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)
}
})
}
}

View File

@@ -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
}

View File

@@ -1,63 +0,0 @@
package ipcauth
import (
"fmt"
"os"
)
// OpenOwnedFile opens path for reading on behalf of the IPC caller identified by
// id, and fails unless the opened file is a regular file that id owns.
//
// It exists for the paths a local caller hands to the daemon over the IPC. The
// daemon runs as root, so opening such a path unchecked lets any local user read
// any file through it. Ownership is the invariant that keeps the daemon from
// reading, with its own privileges, a file the caller could not read itself: a
// symlink or hard link planted at the path resolves to a file someone else owns
// and is refused.
//
// The check is made against the open descriptor rather than the path, so
// swapping the path between the check and the read cannot change the answer.
//
// A privileged caller is exempt: it can read the file directly, so refusing it
// here would protect nothing. The regular-file requirement still applies to
// everyone, since a fifo or device planted at the path is never a log file.
func OpenOwnedFile(id Identity, path string) (*os.File, error) {
f, err := openForRead(path)
if err != nil {
return nil, err
}
if err := checkOwnership(id, f); err != nil {
if cerr := f.Close(); cerr != nil {
return nil, fmt.Errorf("%w (close: %v)", err, cerr)
}
return nil, err
}
return f, nil
}
func checkOwnership(id Identity, f *os.File) error {
info, err := f.Stat()
if err != nil {
return fmt.Errorf("stat %s: %w", f.Name(), err)
}
if !info.Mode().IsRegular() {
return fmt.Errorf("%s is not a regular file", f.Name())
}
if IsPrivilegedCaller(id) {
return nil
}
owned, err := fileOwnedBy(id, f)
if err != nil {
return fmt.Errorf("read owner of %s: %w", f.Name(), err)
}
if !owned {
return fmt.Errorf("%s is not owned by the caller (%s)", f.Name(), id)
}
return nil
}

View File

@@ -1,64 +0,0 @@
package ipcauth
import (
"io"
"os"
"path/filepath"
"runtime"
"testing"
"github.com/stretchr/testify/require"
)
// otherIdentity is an unprivileged caller that owns nothing the test creates.
func otherIdentity(t *testing.T) Identity {
t.Helper()
if runtime.GOOS == "windows" {
return Identity{SID: "S-1-5-21-1-2-3-1001"}
}
return Identity{UID: uint32(os.Geteuid() + 1), GID: uint32(os.Getegid() + 1)}
}
func TestOpenOwnedFileReadsFileOwnedByCaller(t *testing.T) {
path := filepath.Join(t.TempDir(), "gui-client.log")
require.NoError(t, os.WriteFile(path, []byte("hello"), 0600))
id, err := CurrentProcessIdentity()
require.NoError(t, err)
f, err := OpenOwnedFile(id, path)
require.NoError(t, err)
t.Cleanup(func() { _ = f.Close() })
content, err := io.ReadAll(f)
require.NoError(t, err)
require.Equal(t, "hello", string(content))
}
func TestOpenOwnedFileRefusesFileOwnedByAnother(t *testing.T) {
path := filepath.Join(t.TempDir(), "gui-client.log")
require.NoError(t, os.WriteFile(path, []byte("secret"), 0600))
_, err := OpenOwnedFile(otherIdentity(t), path)
require.ErrorContains(t, err, "not owned by the caller")
}
func TestOpenOwnedFileRefusesNonRegularFile(t *testing.T) {
dir := t.TempDir()
// The caller owns the directory, so this is the regular-file requirement
// talking, not the ownership check.
id, err := CurrentProcessIdentity()
require.NoError(t, err)
_, err = OpenOwnedFile(id, dir)
require.ErrorContains(t, err, "not a regular file")
}
func TestOpenOwnedFileRefusesMissingFile(t *testing.T) {
id, err := CurrentProcessIdentity()
require.NoError(t, err)
_, err = OpenOwnedFile(id, filepath.Join(t.TempDir(), "absent.log"))
require.Error(t, err)
}

View File

@@ -1,35 +0,0 @@
//go:build !windows
package ipcauth
import (
"fmt"
"os"
"syscall"
)
// openForRead opens a caller-supplied path without following a symlink at its
// final component and without blocking: a fifo planted at the path would
// otherwise stall the open until a writer appears, and the daemon holds a lock
// while it collects the file.
func openForRead(path string) (*os.File, error) {
f, err := os.OpenFile(path, os.O_RDONLY|syscall.O_NOFOLLOW|syscall.O_NONBLOCK, 0)
if err != nil {
return nil, fmt.Errorf("open %s: %w", path, err)
}
return f, nil
}
func fileOwnedBy(id Identity, f *os.File) (bool, error) {
info, err := f.Stat()
if err != nil {
return false, err
}
stat, ok := info.Sys().(*syscall.Stat_t)
if !ok {
return false, fmt.Errorf("no owner information in %T", info.Sys())
}
return stat.Uid == id.UID, nil
}

View File

@@ -1,57 +0,0 @@
//go:build !windows
package ipcauth
import (
"errors"
"os"
"path/filepath"
"syscall"
"testing"
"time"
"github.com/stretchr/testify/require"
)
// A symlink is the shape the arbitrary-read attempt takes: the caller owns the
// link, the file it points at belongs to someone else.
func TestOpenOwnedFileRefusesSymlink(t *testing.T) {
dir := t.TempDir()
target := filepath.Join(dir, "target.log")
require.NoError(t, os.WriteFile(target, []byte("secret"), 0600))
link := filepath.Join(dir, "gui-client.log")
require.NoError(t, os.Symlink(target, link))
id, err := CurrentProcessIdentity()
require.NoError(t, err)
_, err = OpenOwnedFile(id, link)
// O_NOFOLLOW on a symlink reports ELOOP on Linux/Darwin and EMLINK on FreeBSD.
if !errors.Is(err, syscall.ELOOP) && !errors.Is(err, syscall.EMLINK) {
t.Fatalf("symlink open: got %v, want ELOOP or EMLINK", err)
}
}
// A fifo would block the open until a writer showed up, stalling the daemon
// while it holds its lock.
func TestOpenOwnedFileRefusesFifoWithoutBlocking(t *testing.T) {
path := filepath.Join(t.TempDir(), "gui-client.log")
require.NoError(t, syscall.Mkfifo(path, 0600))
id, err := CurrentProcessIdentity()
require.NoError(t, err)
done := make(chan error, 1)
go func() {
_, err := OpenOwnedFile(id, path)
done <- err
}()
select {
case err := <-done:
require.ErrorContains(t, err, "not a regular file")
case <-time.After(5 * time.Second):
t.Fatal("opening a fifo blocked")
}
}

View File

@@ -1,59 +0,0 @@
//go:build windows
package ipcauth
import (
"fmt"
"os"
"golang.org/x/sys/windows"
)
// openForRead opens a caller-supplied path without following a reparse point at
// it. FILE_FLAG_OPEN_REPARSE_POINT is the Windows analogue of O_NOFOLLOW: it
// opens a symlink/junction itself rather than its target, so the regular-file
// check in checkOwnership refuses a link the caller planted to redirect the
// read. FILE_FLAG_BACKUP_SEMANTICS lets a directory open too (as os.Open does),
// so a directory planted at the path is refused as non-regular rather than
// erroring here. The share mode matches os.Open so a log being written stays
// openable.
func openForRead(path string) (*os.File, error) {
p, err := windows.UTF16PtrFromString(path)
if err != nil {
return nil, fmt.Errorf("convert path %s: %w", path, err)
}
handle, err := windows.CreateFile(
p,
windows.GENERIC_READ,
windows.FILE_SHARE_READ|windows.FILE_SHARE_WRITE|windows.FILE_SHARE_DELETE,
nil,
windows.OPEN_EXISTING,
windows.FILE_FLAG_OPEN_REPARSE_POINT|windows.FILE_FLAG_BACKUP_SEMANTICS,
0,
)
if err != nil {
return nil, fmt.Errorf("open %s: %w", path, err)
}
return os.NewFile(uintptr(handle), path), nil
}
// fileOwnedBy compares the file's owner SID with the caller's. Files an elevated
// process creates are owned by BUILTIN\Administrators rather than by the user,
// but such a caller is privileged and never reaches this check.
func fileOwnedBy(id Identity, f *os.File) (bool, error) {
// x/sys/windows GetSecurityInfo frees the OS buffer itself and returns a
// Go-heap copy, so there is nothing to LocalFree here.
sd, err := windows.GetSecurityInfo(windows.Handle(f.Fd()), windows.SE_FILE_OBJECT, windows.OWNER_SECURITY_INFORMATION)
if err != nil {
return false, fmt.Errorf("read security info: %w", err)
}
owner, _, err := sd.Owner()
if err != nil {
return false, fmt.Errorf("read owner: %w", err)
}
return id.SID != "" && owner.String() == id.SID, nil
}

View File

@@ -1,78 +0,0 @@
//go:build windows
package ipcauth
import (
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/require"
"golang.org/x/sys/windows"
)
// fileOwnerSID reads the owner SID of path the same way OpenOwnedFile does, so
// the test can construct an Identity that matches (or deliberately does not).
func fileOwnerSID(t *testing.T, path string) string {
t.Helper()
f, err := os.Open(path)
require.NoError(t, err)
t.Cleanup(func() { _ = f.Close() })
sd, err := windows.GetSecurityInfo(windows.Handle(f.Fd()), windows.SE_FILE_OBJECT, windows.OWNER_SECURITY_INFORMATION)
require.NoError(t, err)
owner, _, err := sd.Owner()
require.NoError(t, err)
return owner.String()
}
// The allow branch of fileOwnedBy is the SID-equality path the legitimate GUI
// flow depends on. Running elevated, a created file is owned by
// BUILTIN\Administrators; an Identity carrying that SID with Elevated=false and
// no groups is unprivileged by IsPrivileged (which reads the token, not the
// SID's RID), so this exercises the real GetSecurityInfo equality rather than
// the privileged-caller shortcut.
func TestOpenOwnedFileWindowsOwnerMatchAllows(t *testing.T) {
path := filepath.Join(t.TempDir(), "gui-client.log")
require.NoError(t, os.WriteFile(path, []byte("hello"), 0600))
ownerSID := fileOwnerSID(t, path)
id := Identity{SID: ownerSID}
require.False(t, id.IsPrivileged(), "identity built from the owner SID must be unprivileged for this to test the match path")
f, err := OpenOwnedFile(id, path)
require.NoError(t, err)
_ = f.Close()
}
func TestOpenOwnedFileWindowsOwnerMismatchRefuses(t *testing.T) {
path := filepath.Join(t.TempDir(), "gui-client.log")
require.NoError(t, os.WriteFile(path, []byte("secret"), 0600))
other := Identity{SID: "S-1-5-21-9-9-9-9999"}
require.False(t, other.IsPrivileged())
_, err := OpenOwnedFile(other, path)
require.ErrorContains(t, err, "not owned by the caller")
}
// FILE_FLAG_OPEN_REPARSE_POINT must make OpenOwnedFile refuse a symlink the same
// way O_NOFOLLOW does on Unix, so a planted link can't redirect the read to
// another file. Creating a symlink needs a privilege the runner may lack, so the
// test skips rather than fails when it can't.
func TestOpenOwnedFileWindowsRefusesSymlink(t *testing.T) {
dir := t.TempDir()
target := filepath.Join(dir, "target.log")
require.NoError(t, os.WriteFile(target, []byte("secret"), 0600))
link := filepath.Join(dir, "gui-client.log")
if err := os.Symlink(target, link); err != nil {
t.Skipf("cannot create symlink (privilege not held?): %v", err)
}
id, err := CurrentProcessIdentity()
require.NoError(t, err)
_, err = OpenOwnedFile(id, link)
require.Error(t, err, "a symlink must be refused")
}

View File

@@ -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
}

Some files were not shown because too many files have changed in this diff Show More