diff --git a/.github/dependabot.yml b/.github/dependabot.yml index b78b1417a..647e04936 100644 --- a/.github/dependabot.yml +++ b/.github/dependabot.yml @@ -3,8 +3,8 @@ updates: - package-ecosystem: "github-actions" directory: "/" schedule: - interval: "daily" - open-pull-requests-limit: 15 + interval: "weekly" + open-pull-requests-limit: 3 groups: actions: patterns: @@ -22,9 +22,12 @@ updates: directories: - "/" schedule: - interval: "daily" + interval: "weekly" open-pull-requests-limit: 15 groups: + golang-x-packages: + patterns: + - "golang.org/x/*" aws-sdk: patterns: - "github.com/aws/aws-sdk-go-v2/*" diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md index 8e68054bd..9b796f262 100644 --- a/.github/pull_request_template.md +++ b/.github/pull_request_template.md @@ -2,6 +2,12 @@ ## Issue ticket number and link + + ## Stack @@ -12,7 +18,9 @@ - [ ] Is a feature enhancement - [ ] It is a refactor - [ ] Created tests that fail without the change (if possible) -- [ ] 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). +- [ ] 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). > 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). diff --git a/.github/workflows/agent-network-e2e.yml b/.github/workflows/agent-network-e2e.yml index d78e3bbd3..88b98293d 100644 --- a/.github/workflows/agent-network-e2e.yml +++ b/.github/workflows/agent-network-e2e.yml @@ -5,6 +5,13 @@ 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 }} @@ -51,6 +58,9 @@ 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 }} @@ -59,6 +69,8 @@ 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 }} diff --git a/.github/workflows/frontend-ui.yml b/.github/workflows/frontend-ui.yml index bb5bb4528..552ccef29 100644 --- a/.github/workflows/frontend-ui.yml +++ b/.github/workflows/frontend-ui.yml @@ -86,7 +86,7 @@ jobs: ${{ runner.os }}-pnpm- - name: Install dependencies - run: pnpm install --frozen-lockfile + run: pnpm install --frozen-lockfile --ignore-scripts - name: Generate Wails bindings run: pnpm run bindings diff --git a/.github/workflows/golangci-lint.yml b/.github/workflows/golangci-lint.yml index b444a9900..586e1235b 100644 --- a/.github/workflows/golangci-lint.yml +++ b/.github/workflows/golangci-lint.yml @@ -45,7 +45,7 @@ jobs: display_name: Linux name: ${{ matrix.display_name }} runs-on: ${{ matrix.os }} - timeout-minutes: 15 + timeout-minutes: 25 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=12m + args: --timeout=20m diff --git a/.github/workflows/test-infrastructure-files.yml b/.github/workflows/test-infrastructure-files.yml index 0a4f2e371..965d8aa5d 100644 --- a/.github/workflows/test-infrastructure-files.yml +++ b/.github/workflows/test-infrastructure-files.yml @@ -249,78 +249,35 @@ 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-getting-started-script: + test-legacy-getting-started-scripts: 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: run script with Zitadel PostgreSQL - run: NETBIRD_DOMAIN=use-ip bash -x infrastructure_files/getting-started-with-zitadel.sh - - - 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 + - name: Verify Dex retirement notice run: | - set -x - test -f turnserver.conf - grep external-ip turnserver.conf + 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: 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 + - name: Verify Zitadel retirement notice 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 + 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 diff --git a/.goreleaser.yaml b/.goreleaser.yaml index 0753b1012..8dd05a192 100644 --- a/.goreleaser.yaml +++ b/.goreleaser.yaml @@ -273,8 +273,8 @@ dockers_v2: - netbirdio/netbird - ghcr.io/netbirdio/netbird tags: - - "v{{ .Version }}-rootless" - - "{{ if eq .Env.SKIP_PUBLISH \"false\" }}latest{{ end }}" + - "{{ .Version }}-rootless" + - "{{ if eq .Env.SKIP_PUBLISH \"false\" }}rootless-latest{{ end }}" dockerfile: client/Dockerfile-rootless extra_files: - client/netbird-entrypoint.sh diff --git a/.goreleaser_ui.yaml b/.goreleaser_ui.yaml index 197fcd440..1157e6379 100644 --- a/.goreleaser_ui.yaml +++ b/.goreleaser_ui.yaml @@ -24,6 +24,8 @@ 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 @@ -39,6 +41,8 @@ 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 @@ -55,6 +59,8 @@ 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 diff --git a/.goreleaser_ui_darwin.yaml b/.goreleaser_ui_darwin.yaml index 96e15371a..47b991344 100644 --- a/.goreleaser_ui_darwin.yaml +++ b/.goreleaser_ui_darwin.yaml @@ -29,6 +29,8 @@ 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 diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 261083783..3b8017788 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -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 @@ -10,12 +10,69 @@ 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. + ## Contents - [Contributing to NetBird](#contributing-to-netbird) + - [Ticket first, PR second](#ticket-first-pr-second) + - [High-risk areas](#high-risk-areas) - [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) @@ -24,6 +81,7 @@ If you haven't already, join our slack workspace [here](https://docs.netbird.io/ - [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) @@ -34,42 +92,66 @@ 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 is organized to maintain most of its individual dependencies code within their directories, except for a few auxiliary or shared packages. +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 most important directories are: +**Agent** -- [/.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/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 +- [/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** + - [/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 -- [/release_files](/release_files) - Files that goes into release packages +- [/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/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 +- [/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 ## Development setup @@ -234,12 +316,22 @@ cd client/ui task dev ``` -Pass daemon flags after `--`: +Pass daemon flags after `--`, pointing the UI at the socket the daemon serves: ``` -task dev -- --daemon-addr=tcp://127.0.0.1:41731 +task dev -- --daemon-addr=unix:///var/run/netbird.sock # Linux, macOS +task dev -- --daemon-addr=npipe://netbird # Windows ``` +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/`): ``` @@ -324,23 +416,172 @@ The installer `netbird-installer.exe` will be created in root directory. ### Test suite -The tests can be started via: +The host-safe unit tests run as a normal user and leave host networking +untouched: ``` -cd netbird -go test -exec sudo ./... +make test-unit ``` + +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 the pull-requests: + +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 + - 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: diff --git a/SECURITY.md b/SECURITY.md index 745c66e61..bdf88d670 100644 --- a/SECURITY.md +++ b/SECURITY.md @@ -1,12 +1,70 @@ # Security Policy -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 +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. ## Reporting a Vulnerability -Please report security issues to `security@netbird.io` +**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). diff --git a/agent-network/README.md b/agent-network/README.md index a09d3979e..1997ea299 100644 --- a/agent-network/README.md +++ b/agent-network/README.md @@ -1,16 +1,47 @@ # 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 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. +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. -> **Beta.** Agent Network is open source and can be self-hosted on your own -> infrastructure. +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. ## 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. @@ -22,6 +53,9 @@ 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. +image + + ## Where the code lives There is no separate "agent-network" service — it reuses the reverse-proxy and management diff --git a/client/android/client.go b/client/android/client.go index 99ccdf393..501d7f77c 100644 --- a/client/android/client.go +++ b/client/android/client.go @@ -7,6 +7,7 @@ import ( "fmt" "os" "slices" + "strings" "sync" "time" @@ -75,6 +76,24 @@ 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) { @@ -148,11 +167,16 @@ 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) } @@ -247,6 +271,9 @@ 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 } @@ -274,7 +301,7 @@ 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) + key, err := debug.UploadDebugBundle(uploadCtx, types.DefaultBundleURL, cfg.ManagementURL.String(), path, false) if err != nil { return "", fmt.Errorf("upload debug bundle: %w", err) } @@ -296,6 +323,13 @@ 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)) @@ -306,6 +340,20 @@ 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 } @@ -436,10 +484,6 @@ 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 { @@ -459,22 +503,22 @@ func (c *Client) getRouteManager() (routemanager.Manager, error) { return manager, nil } -func (c *Client) SelectRoute(route string) error { +func (c *Client) SelectRoute(id string) error { manager, err := c.getRouteManager() if err != nil { return err } - return c.toggleRoute(selectRouteCommand{route: route, manager: manager}) + return manager.SelectRoutes([]route.NetID{route.NetID(id)}, true) } -func (c *Client) DeselectRoute(route string) error { +func (c *Client) DeselectRoute(id string) error { manager, err := c.getRouteManager() if err != nil { return err } - return c.toggleRoute(deselectRouteCommand{route: route, manager: manager}) + return manager.DeselectRoutes([]route.NetID{route.NetID(id)}) } // getNetworkDomainsFromRoute extracts domains from a route and enriches each domain @@ -509,3 +553,28 @@ 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") +} diff --git a/client/android/peer_notifier.go b/client/android/peer_notifier.go index c2595e574..f525055bb 100644 --- a/client/android/peer_notifier.go +++ b/client/android/peer_notifier.go @@ -12,12 +12,30 @@ 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 { diff --git a/client/android/profile_manager.go b/client/android/profile_manager.go index 87c001396..9a051137c 100644 --- a/client/android/profile_manager.go +++ b/client/android/profile_manager.go @@ -189,6 +189,19 @@ 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) diff --git a/client/android/route_command.go b/client/android/route_command.go deleted file mode 100644 index 5e7357335..000000000 --- a/client/android/route_command.go +++ /dev/null @@ -1,70 +0,0 @@ -//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) -} diff --git a/client/android/session.go b/client/android/session.go new file mode 100644 index 000000000..961d52528 --- /dev/null +++ b/client/android/session.go @@ -0,0 +1,309 @@ +//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 +} diff --git a/client/cmd/daemon_error.go b/client/cmd/daemon_error.go new file mode 100644 index 000000000..0d5b1307e --- /dev/null +++ b/client/cmd/daemon_error.go @@ -0,0 +1,66 @@ +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 +} diff --git a/client/cmd/debug.go b/client/cmd/debug.go index 57e75f663..7ddc3afc4 100644 --- a/client/cmd/debug.go +++ b/client/cmd/debug.go @@ -29,8 +29,9 @@ const errCloseConnection = "Failed to close connection: %v" var ( logFileCount uint32 systemInfoFlag bool - uploadBundleFlag bool - uploadBundleURLFlag string + uploadBundleFlag bool + uploadBundleURLFlag string + uploadBundleInsecureFlag bool ) var debugCmd = &cobra.Command{ @@ -174,10 +175,11 @@ 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 fmt.Errorf("failed to bundle debug: %v", status.Convert(err).Message()) + return daemonCallError("bundle debug", err) } cmd.Printf("Local file:\n%s\n", resp.GetPath()) @@ -373,10 +375,11 @@ 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 fmt.Errorf("failed to bundle debug: %v", status.Convert(err).Message()) + return daemonCallError("bundle debug", err) } if needsRestoreUp { @@ -524,10 +527,12 @@ 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") } diff --git a/client/cmd/login.go b/client/cmd/login.go index ee32a3727..a53cb6d5f 100644 --- a/client/cmd/login.go +++ b/client/cmd/login.go @@ -17,7 +17,9 @@ 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" ) @@ -331,6 +333,14 @@ 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) diff --git a/client/cmd/logout.go b/client/cmd/logout.go index 1a5281acb..dcd7b5075 100644 --- a/client/cmd/logout.go +++ b/client/cmd/logout.go @@ -46,7 +46,7 @@ var logoutCmd = &cobra.Command{ } if _, err := daemonClient.Logout(ctx, req); err != nil { - return fmt.Errorf("deregister: %v", err) + return daemonCallError("deregister", err) } cmd.Println("Deregistered successfully") diff --git a/client/cmd/root.go b/client/cmd/root.go index f1ef32717..ebaae7e3e 100644 --- a/client/cmd/root.go +++ b/client/cmd/root.go @@ -20,7 +20,6 @@ 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" @@ -91,6 +90,7 @@ 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 = "tcp://127.0.0.1:41731" + defaultDaemonAddr = daddr.WindowsPipeAddr } - rootCmd.PersistentFlags().StringVar(&daemonAddr, "daemon-addr", defaultDaemonAddr, "Daemon service address to serve CLI requests [unix|tcp]://[path|host:port]") + rootCmd.PersistentFlags().StringVar(&daemonAddr, "daemon-addr", defaultDaemonAddr, "Daemon service address to serve CLI requests [unix|tcp|npipe]://[path|host:port|name]") 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") @@ -269,12 +269,10 @@ func DialClientGRPCServer(ctx context.Context, addr string) (*grpc.ClientConn, e ctx, cancel := context.WithTimeout(ctx, time.Second*10) defer cancel() - return grpc.DialContext( - ctx, - strings.TrimPrefix(addr, "tcp://"), - grpc.WithTransportCredentials(insecure.NewCredentials()), - grpc.WithBlock(), - ) + target, opts := daddr.DialTarget(addr) + opts = append(opts, grpc.WithBlock()) + + return grpc.DialContext(ctx, target, opts...) } // WithBackOff execute function in backoff cycle. diff --git a/client/cmd/service.go b/client/cmd/service.go index b0a56c71a..7410d60ea 100644 --- a/client/cmd/service.go +++ b/client/cmd/service.go @@ -33,10 +33,15 @@ var ( ) type program struct { - ctx context.Context - cancel context.CancelFunc - serv *grpc.Server - jsonServ *http.Server + 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 jsonServMu sync.Mutex serverInstance *server.Server serverInstanceMu sync.Mutex diff --git a/client/cmd/service_controller.go b/client/cmd/service_controller.go index 5ef13a0a6..9ba3bce25 100644 --- a/client/cmd/service_controller.go +++ b/client/cmd/service_controller.go @@ -5,6 +5,7 @@ package cmd import ( "context" "fmt" + "runtime" "time" "github.com/kardianos/service" @@ -13,6 +14,8 @@ 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" @@ -26,6 +29,31 @@ 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 @@ -37,68 +65,106 @@ func (p *program) Start(svc service.Service) error { // Collect static system and platform information system.UpdateStaticInfoAsync() - // in any case, even if configuration does not exists we run daemon to serve CLI gRPC API. - p.serv = grpc.NewServer() - - daemonListener, err := listenOnAddress(daemonAddr) - if err != nil { - return fmt.Errorf("listen daemon interface: %w", err) + // 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 } - 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) + 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)...) + + daemonListener, jsonListener, err := listenDaemonSockets() + if err != nil { + return err } go func() { - 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) + // 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) } }() 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 { @@ -113,8 +179,13 @@ func (p *program) Stop(srv service.Service) error { p.cancel() p.jsonServMu.Lock() - jsonServ := p.jsonServ + jsonServ, jsonClient := p.jsonServ, p.jsonClient 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 { diff --git a/client/cmd/service_json_gateway.go b/client/cmd/service_json_gateway.go index 29c1a6456..b6864f338 100644 --- a/client/cmd/service_json_gateway.go +++ b/client/cmd/service_json_gateway.go @@ -5,27 +5,123 @@ package cmd import ( "context" "errors" + "fmt" "net" "net/http" - "strings" + "sync" "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" ) -func grpcGatewayEndpoint(addr string) string { - return strings.TrimPrefix(addr, "tcp://") +// 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-" +// 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 (p *program) startJSONGateway(jsonListener *socketListener, daemonEndpoint string) error { - mux := runtime.NewServeMux() - opts := []grpc.DialOption{grpc.WithTransportCredentials(insecure.NewCredentials())} - if err := proto.RegisterDaemonServiceHandlerFromEndpoint(p.ctx, mux, grpcGatewayEndpoint(daemonEndpoint), opts); err != nil { + 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) + } return err } @@ -35,10 +131,12 @@ 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() { diff --git a/client/cmd/service_json_gateway_test.go b/client/cmd/service_json_gateway_test.go new file mode 100644 index 000000000..dfeef1c46 --- /dev/null +++ b/client/cmd/service_json_gateway_test.go @@ -0,0 +1,261 @@ +//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- 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") + } +} diff --git a/client/cmd/service_params.go b/client/cmd/service_params.go index f25087a69..750b22ae6 100644 --- a/client/cmd/service_params.go +++ b/client/cmd/service_params.go @@ -13,6 +13,7 @@ import ( "github.com/spf13/cobra" "github.com/netbirdio/netbird/client/configs" + "github.com/netbirdio/netbird/client/internal/daemonaddr" "github.com/netbirdio/netbird/util" ) @@ -125,6 +126,13 @@ 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 != "" { diff --git a/client/cmd/service_pipe_other.go b/client/cmd/service_pipe_other.go new file mode 100644 index 000000000..c7cc72469 --- /dev/null +++ b/client/cmd/service_pipe_other.go @@ -0,0 +1,14 @@ +//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") +} diff --git a/client/cmd/service_pipe_windows.go b/client/cmd/service_pipe_windows.go new file mode 100644 index 000000000..b6e860f51 --- /dev/null +++ b/client/cmd/service_pipe_windows.go @@ -0,0 +1,41 @@ +//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...) +} diff --git a/client/cmd/service_socket.go b/client/cmd/service_socket.go index f825a4062..ed1f001a7 100644 --- a/client/cmd/service_socket.go +++ b/client/cmd/service_socket.go @@ -26,6 +26,14 @@ 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) } @@ -41,11 +49,11 @@ 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]://[path|host:port] format: %q", addr) + return "", "", fmt.Errorf("address must be in [unix|tcp|npipe]://[path|host:port|name] format: %q", addr) } switch network { - case "unix", "tcp": + case "unix", "tcp", "npipe": return network, address, nil default: return "", "", fmt.Errorf("unsupported daemon address protocol: %v", network) diff --git a/client/cmd/up.go b/client/cmd/up.go index 8b3de3c66..142bcf6bd 100644 --- a/client/cmd/up.go +++ b/client/cmd/up.go @@ -22,6 +22,8 @@ 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" @@ -229,6 +231,24 @@ 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) @@ -305,7 +325,7 @@ func runInDaemonMode(ctx context.Context, cmd *cobra.Command, pm *profilemanager if st, ok := gstatus.FromError(err); ok && st.Code() == codes.Unavailable { log.Warnf("setConfig method is not available in the daemon: %s", st.Message()) } else { - return fmt.Errorf("call service setConfig method: %v", err) + return daemonCallError("call service setConfig method", err) } } @@ -359,7 +379,7 @@ func doDaemonUp(ctx context.Context, cmd *cobra.Command, client proto.DaemonServ } if loginErr != nil { - return fmt.Errorf("login failed: %v", loginErr) + return daemonCallError("login failed", loginErr) } if loginResp.NeedsSSOLogin { @@ -372,7 +392,7 @@ func doDaemonUp(ctx context.Context, cmd *cobra.Command, client proto.DaemonServ ProfileName: &profileID, Username: &username, }); err != nil { - return fmt.Errorf("call service up method: %v", err) + return daemonCallError("call service up method", err) } return nil diff --git a/client/configs/configs.go b/client/configs/configs.go index 8f9c3ba28..a1ecf0feb 100644 --- a/client/configs/configs.go +++ b/client/configs/configs.go @@ -6,6 +6,11 @@ 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() { diff --git a/client/firewall/nftables/legacy_rule_linux_test.go b/client/firewall/nftables/legacy_rule_linux_test.go new file mode 100644 index 000000000..dc2f1c7a0 --- /dev/null +++ b/client/firewall/nftables/legacy_rule_linux_test.go @@ -0,0 +1,60 @@ +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) + }) + } +} diff --git a/client/firewall/nftables/routing_linux.go b/client/firewall/nftables/routing_linux.go index c526102ee..00d5f86f0 100644 --- a/client/firewall/nftables/routing_linux.go +++ b/client/firewall/nftables/routing_linux.go @@ -297,6 +297,17 @@ func (r *family) 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 +} + func (r *family) addLegacyRouteRule(pair firewall.RouterPair) error { sourceExp, err := r.applyNetwork(pair.Source, nil, true) if err != nil { @@ -309,13 +320,7 @@ func (r *family) addLegacyRouteRule(pair firewall.RouterPair) error { return fmt.Errorf("apply destination: %w", err) } - var exprs []expr.Any - exprs = append(exprs, sourceExp...) - exprs = append(exprs, destExp...) - exprs = append(exprs, - &expr.Counter{}, - &expr.Verdict{Kind: expr.VerdictAccept}, - ) + exprs := buildLegacyRouteRuleExpressions(sourceExp, destExp) ruleID := pair.GenKey(firewall.ForwardingFormat) diff --git a/client/firewall/uspfilter/filter.go b/client/firewall/uspfilter/filter.go index 112a03eda..5e1366c1f 100644 --- a/client/firewall/uspfilter/filter.go +++ b/client/firewall/uspfilter/filter.go @@ -185,6 +185,7 @@ 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 @@ -247,6 +248,41 @@ 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 +} + func parseCreateEnv() (bool, bool, bool) { var disableConntrack, enableLocalForwarding, disableMSSClamping bool var err error @@ -331,6 +367,7 @@ func Create(cfg Config) (_ *Manager, err error) { if err := m.localipmanager.UpdateLocalIPs(cfg.IFace); err != nil { return nil, fmt.Errorf("update local IPs: %w", err) } + m.fragments = newFragmentTracker(m.logger) m.setupConntrack(disableConntrack) if m.netstack && m.localForwarding { if err := m.initForwarder(); err != nil { @@ -338,6 +375,7 @@ func Create(cfg Config) (_ *Manager, err error) { } } if err := cfg.IFace.SetFilter(m); err != nil { + m.fragments.Close() return nil, fmt.Errorf("set filter: %w", err) } @@ -823,6 +861,10 @@ 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() @@ -1169,19 +1211,20 @@ func (m *Manager) filterInbound(packetData []byte, size int) bool { return true } - // TODO: pass fragments of routed packets to forwarder + // 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. if fragment { - 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.filterInboundFragment(d, srcIP, dstIP, size) } + 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 @@ -1212,33 +1255,226 @@ func (m *Manager) filterInbound(packetData []byte, size int) bool { 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 { - 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), - }) + m.storeDropFlow("Dropping local packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d", + d, srcIP, dstIP, ruleID, size) return true } @@ -1291,27 +1527,8 @@ func (m *Manager) handleRoutedTraffic(d *decoder, srcIP, dstIP netip.Addr, packe ruleID, pass := m.routeACLsPass(srcIP, dstIP, protoLayer, srcPort, dstPort) if !pass { - 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), - }) + m.storeDropFlow("Dropping routed packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d", + d, srcIP, dstIP, ruleID, size) return true } diff --git a/client/firewall/uspfilter/forwarder/forwarder.go b/client/firewall/uspfilter/forwarder/forwarder.go index 15499872c..7308b38bd 100644 --- a/client/firewall/uspfilter/forwarder/forwarder.go +++ b/client/firewall/uspfilter/forwarder/forwarder.go @@ -5,7 +5,9 @@ import ( "fmt" "net" "net/netip" + "os" "runtime" + "strconv" "sync" "time" @@ -32,6 +34,11 @@ 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" ) // IFace provides the WireGuard device and overlay addresses the forwarder needs. @@ -159,6 +166,8 @@ func New(iface IFace, logger *nblog.Logger, flowLogger nftypes.FlowLogger, netst maxInFlight = iosMaxInFlight } + configureTCPRecovery(s) + tcpForwarder := tcp.NewForwarder(s, receiveWindow, maxInFlight, f.handleTCP) s.SetTransportProtocolHandler(tcp.ProtocolNumber, tcpForwarder.HandlePacket) @@ -473,3 +482,31 @@ 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") +} diff --git a/client/firewall/uspfilter/fragment.go b/client/firewall/uspfilter/fragment.go new file mode 100644 index 000000000..accc54365 --- /dev/null +++ b/client/firewall/uspfilter/fragment.go @@ -0,0 +1,204 @@ +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() +} diff --git a/client/firewall/uspfilter/fragment_bench_test.go b/client/firewall/uspfilter/fragment_bench_test.go new file mode 100644 index 000000000..a9e6d2d13 --- /dev/null +++ b/client/firewall/uspfilter/fragment_bench_test.go @@ -0,0 +1,115 @@ +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)) + } +} diff --git a/client/firewall/uspfilter/fragment_test.go b/client/firewall/uspfilter/fragment_test.go new file mode 100644 index 000000000..8f99864be --- /dev/null +++ b/client/firewall/uspfilter/fragment_test.go @@ -0,0 +1,554 @@ +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(Config{IFace: ifaceMock, FlowLogger: flowLogger, MTU: 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.AddFilterRule(nil, pfx(net.ParseIP(fragTestSrc)), fw.Network{}, 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.AddFilterRule(nil, pfx(net.ParseIP(fragTestSrc)), fw.Network{}, 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.AddFilterRule(nil, pfx(net.ParseIP(fragTestSrc)), fw.Network{}, 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.AddFilterRule(nil, pfx(net.ParseIP(fragTestSrc)), fw.Network{}, 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.AddFilterRule( + []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.AddFilterRule(nil, pfx(net.ParseIP(fragTestSrcV6)), fw.Network{}, 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.AddFilterRule(nil, pfx(net.ParseIP(fragTestSrcV6)), fw.Network{}, 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") +} diff --git a/client/iface/iface_test.go b/client/iface/iface_test.go index 8ff2bbb54..89c8cd16e 100644 --- a/client/iface/iface_test.go +++ b/client/iface/iface_test.go @@ -464,6 +464,8 @@ 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() @@ -505,12 +507,8 @@ func Test_ConnectPeers(t *testing.T) { t.Fatal(err) } - localIP, err := getLocalIP() - if err != nil { - t.Fatal(err) - } - - peer1endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP, peer1wgPort)) + localIP1 := "127.0.0.1" + peer1endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP1, peer1wgPort)) if err != nil { t.Fatal(err) } @@ -546,7 +544,8 @@ func Test_ConnectPeers(t *testing.T) { t.Fatal(err) } - peer2endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP, peer2wgPort)) + localIP2 := "127.0.0.1" + peer2endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP2, peer2wgPort)) if err != nil { t.Fatal(err) } @@ -569,17 +568,17 @@ func Test_ConnectPeers(t *testing.T) { if err != nil { t.Fatal(err) } - // todo: investigate why in some tests execution we need 30s + // 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. 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) @@ -588,6 +587,12 @@ 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: + } } } @@ -615,28 +620,3 @@ 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") -} diff --git a/client/iface/netstack/env.go b/client/iface/netstack/env.go index dd8cf29a3..b069301c1 100644 --- a/client/iface/netstack/env.go +++ b/client/iface/netstack/env.go @@ -3,14 +3,31 @@ package netstack import ( - "fmt" + "net" "os" "strconv" log "github.com/sirupsen/logrus" ) -const EnvUseNetstackMode = "NB_USE_NETSTACK_MODE" +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" +) // IsEnabled todo: move these function to cmd layer func IsEnabled() bool { @@ -18,24 +35,40 @@ func IsEnabled() bool { } func ListenAddr() string { - sPort := os.Getenv("NB_SOCKS5_LISTENER_PORT") + 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) if sPort == "" { - return listenAddr(DefaultSocks5Port) + return 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 listenAddr(DefaultSocks5Port) + return 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 listenAddr(DefaultSocks5Port) + return DefaultSocks5Port } - return listenAddr(port) -} - -func listenAddr(port int) string { - return fmt.Sprintf("0.0.0.0:%d", port) + return port } diff --git a/client/iface/netstack/env_test.go b/client/iface/netstack/env_test.go new file mode 100644 index 000000000..1083435a4 --- /dev/null +++ b/client/iface/netstack/env_test.go @@ -0,0 +1,63 @@ +//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) + } + }) + } +} diff --git a/client/internal/auth/auth.go b/client/internal/auth/auth.go index 51f56b644..153727a6c 100644 --- a/client/internal/auth/auth.go +++ b/client/internal/auth/auth.go @@ -351,6 +351,7 @@ 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, diff --git a/client/internal/auth/device_flow.go b/client/internal/auth/device_flow.go index e33765300..9dec7cf53 100644 --- a/client/internal/auth/device_flow.go +++ b/client/internal/auth/device_flow.go @@ -259,12 +259,18 @@ 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) @@ -272,10 +278,12 @@ 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 } @@ -291,11 +299,12 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn UseIDToken: d.providerConfig.UseIDToken, } - err = isValidAccessToken(tokenInfo.GetTokenToUse(), d.providerConfig.Audience) + err = validateTokenAudience(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 } } diff --git a/client/internal/auth/pkce_flow.go b/client/internal/auth/pkce_flow.go index 84fa8a214..be64cc6a8 100644 --- a/client/internal/auth/pkce_flow.go +++ b/client/internal/auth/pkce_flow.go @@ -188,6 +188,8 @@ 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) @@ -221,6 +223,7 @@ 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{ @@ -271,11 +274,18 @@ func (p *PKCEAuthorizationFlow) handleRequest(req *http.Request) (*oauth2.Token, return nil, fmt.Errorf("authentication failed: missing code") } - return p.oAuthConfig.Exchange( + exchangeStart := time.Now() + token, err := 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) { @@ -296,7 +306,7 @@ func (p *PKCEAuthorizationFlow) parseOAuthToken(token *oauth2.Token) (TokenInfo, audience = p.providerConfig.ClientID } - if err := isValidAccessToken(tokenInfo.GetTokenToUse(), audience); err != nil { + if err := validateTokenAudience(tokenInfo.GetTokenToUse(), audience); err != nil { return TokenInfo{}, fmt.Errorf("authentication failed: invalid access token - %w", err) } @@ -310,6 +320,11 @@ 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 { diff --git a/client/internal/auth/sessionwatch/watcher.go b/client/internal/auth/sessionwatch/watcher.go index e75a7022e..e685c28d0 100644 --- a/client/internal/auth/sessionwatch/watcher.go +++ b/client/internal/auth/sessionwatch/watcher.go @@ -24,11 +24,7 @@ import ( ) const ( - // 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 + maxPastHorizon = 30 * 24 * time.Hour // maxDeadlineHorizon caps how far in the future an accepted deadline // can sit. A timestamp beyond this is almost certainly a protocol @@ -57,7 +53,7 @@ var ( ErrDeadlineTooFarFuture = errors.New("session deadline too far in the future") // ErrDeadlineInPast is returned by Update when the supplied deadline - // is more than Skew in the past. + // is more than maxPastHorizon in the past. ErrDeadlineInPast = errors.New("session deadline in the past") ) @@ -66,15 +62,14 @@ var ( // for deadline change/clear, PublishEvent for the two warnings); tests pass // a fake recorder so the same surface is observable without an engine. // -// 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. +// 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. // // PublishEvent's signature mirrors peer.Status.PublishEvent: the watcher // composes the metadata internally so the wire format (MetaSession*) is @@ -135,10 +130,13 @@ 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" guard, and arms a new one. +// 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. // // Returns one of the sentinel Err* values when the deadline fails the -// sanity checks (pre-epoch, far future, or in the past beyond Skew). +// sanity checks (pre-epoch, far future, or past beyond maxPastHorizon). // 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 @@ -163,7 +161,7 @@ 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(-Skew)): + case deadline.Before(now.Add(-maxPastHorizon)): w.clearLocked() return fmt.Errorf("%w: %v (now=%v)", ErrDeadlineInPast, deadline, now) } @@ -183,7 +181,9 @@ func (w *Watcher) Update(deadline time.Time) error { w.finalFiredAt = time.Time{} w.dismissedAt = time.Time{} - w.armTimerLocked(deadline) + if deadline.After(now) { + w.armTimerLocked(deadline) + } recorder := w.recorder w.mu.Unlock() if recorder != nil { @@ -227,30 +227,25 @@ func (w *Watcher) Dismiss() { log.Infof("auth session final-warning dismissed for deadline %s", w.current.Format(time.RFC3339)) } -// 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. +// 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). 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 diff --git a/client/internal/auth/sessionwatch/watcher_test.go b/client/internal/auth/sessionwatch/watcher_test.go index da2b6add6..4b49a94b6 100644 --- a/client/internal/auth/sessionwatch/watcher_test.go +++ b/client/internal/auth/sessionwatch/watcher_test.go @@ -224,11 +224,13 @@ func TestNewDeadlineCancelsPriorTimer(t *testing.T) { func TestRefreshAfterFireArmsNewWarning(t *testing.T) { r := &fakeRecorder{} - lead := 30 * time.Millisecond + lead := 150 * time.Millisecond w := newWatcher(lead, r) defer w.Close() - first := time.Now().Add(50 * time.Millisecond) + // 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) _ = w.Update(first) // Wait for stateChange + warning of the first cycle. @@ -306,7 +308,29 @@ func TestUpdateRejectsTooFarFuture(t *testing.T) { } } -func TestUpdateInPastClearsDeadline(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) { r := &fakeRecorder{} w := newWatcher(50*time.Millisecond, r) defer w.Close() @@ -318,12 +342,12 @@ func TestUpdateInPastClearsDeadline(t *testing.T) { // Drain the stateChange from the seed. waitForEvents(t, r, 1) - err := w.Update(time.Now().Add(-1 * time.Hour)) + err := w.Update(time.Now().Add(-31 * 24 * time.Hour)) if !errors.Is(err, ErrDeadlineInPast) { t.Fatalf("want ErrDeadlineInPast, got %v", err) } if !w.Deadline().IsZero() { - t.Fatalf("in-past update must clear the deadline, got %v", w.Deadline()) + t.Fatalf("rejected ancient-past update must clear the deadline, got %v", w.Deadline()) } events := waitForEvents(t, r, 2) if events[1].kind != stateChange { @@ -331,39 +355,25 @@ func TestUpdateInPastClearsDeadline(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() - _ = w.Update(time.Now().Add(time.Hour)) - - time.Sleep(20 * time.Millisecond) + if err := w.Update(time.Now().Add(time.Hour)); err != nil { + t.Fatalf("Update after Close: want nil, got %v", err) + } if got := r.snapshot(); len(got) != 0 { t.Fatalf("expected no events after Close, got %+v", got) } } -// 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) { +// 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) { r := &fakeRecorder{} w := newWatcher(time.Hour, r) @@ -377,8 +387,8 @@ func TestCloseClearsRecorderDeadline(t *testing.T) { w.Close() - if got := r.deadline(); !got.IsZero() { - t.Fatalf("recorder deadline after Close = %v, want zero", got) + if got := r.deadline(); !got.Equal(d) { + t.Fatalf("recorder deadline after Close = %v, want %v", got, d) } } diff --git a/client/internal/auth/util.go b/client/internal/auth/util.go index 31c81d701..1800584a2 100644 --- a/client/internal/auth/util.go +++ b/client/internal/auth/util.go @@ -20,14 +20,26 @@ func randomBytesInHex(count int) (string, error) { return hex.EncodeToString(buf), nil } -// isValidAccessToken is a simple validation of the access token -func isValidAccessToken(token string, audience string) error { +// 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 { if token == "" { return fmt.Errorf("token received is empty") } - encodedClaims := strings.Split(token, ".")[1] - claimsString, err := base64.RawURLEncoding.DecodeString(encodedClaims) + 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]) if err != nil { return err } diff --git a/client/internal/auth/util_test.go b/client/internal/auth/util_test.go new file mode 100644 index 000000000..7f225bb86 --- /dev/null +++ b/client/internal/auth/util_test.go @@ -0,0 +1,108 @@ +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) + } + } +} diff --git a/client/internal/conn_mgr.go b/client/internal/conn_mgr.go index a82a4ca8b..ad0f00c5d 100644 --- a/client/internal/conn_mgr.go +++ b/client/internal/conn_mgr.go @@ -34,6 +34,8 @@ 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 @@ -42,12 +44,26 @@ 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, @@ -109,7 +125,7 @@ func (e *ConnMgr) UpdatedRemoteFeatureFlag(ctx context.Context, enabled bool) er return nil } - log.Warnf("lazy connection manager is enabled by management feature flag") + log.Infof("lazy connection manager is enabled by the management feature flag") e.initLazyManager(ctx) e.statusRecorder.UpdateLazyConnection(true) return e.addPeersToLazyConnManager() @@ -238,12 +254,20 @@ 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) { - if !e.isStartedWithLazyMgr() { + e.lazyConnMgrMu.RLock() + lazyConnMgr := e.lazyConnMgr + started := lazyConnMgr != nil && e.lazyCtxCancel != nil + e.lazyConnMgrMu.RUnlock() + if !started { return } - if found := e.lazyConnMgr.ActivatePeer(conn.GetKey()); found { + if found := lazyConnMgr.ActivatePeer(conn.GetKey()); found { if err := conn.Open(ctx); err != nil { conn.Log.Errorf("failed to open connection: %v", err) } @@ -268,16 +292,22 @@ 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.lazyConnMgr = manager.NewManager(cfg, engineCtx, e.peerStore, e.iface) + 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() { @@ -316,7 +346,10 @@ 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) @@ -352,11 +385,20 @@ func inactivityThresholdEnv() *time.Duration { return nil } - parsedMinutes, err := strconv.Atoi(envValue) - if err != nil || parsedMinutes <= 0 { - 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 } - d := time.Duration(parsedMinutes) * time.Minute - return &d + // 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 } diff --git a/client/internal/conn_mgr_test.go b/client/internal/conn_mgr_test.go index 5e2c53e35..ac5d6f2c8 100644 --- a/client/internal/conn_mgr_test.go +++ b/client/internal/conn_mgr_test.go @@ -1,10 +1,21 @@ 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) { @@ -38,3 +49,93 @@ 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 } diff --git a/client/internal/connect.go b/client/internal/connect.go index c2fc2fd73..87126b222 100644 --- a/client/internal/connect.go +++ b/client/internal/connect.go @@ -34,6 +34,7 @@ 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" @@ -136,10 +137,13 @@ 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: networkChangeListener, - DnsManager: dnsManager, + NetworkChangeListener: notifier, + DnsManager: notifier, StateFilePath: stateFilePath, TempDir: cacheDir, } @@ -257,7 +261,10 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan log.Errorf("failed to clean up temporary installer file: %v", err) } - defer c.statusRecorder.ClientStop() + defer func() { + c.statusRecorder.SetSessionExpiresAt(time.Time{}) + c.statusRecorder.ClientStop() + }() operation := func() error { // if context cancelled we not start new backoff cycle if c.ctx.Err() != nil { @@ -618,6 +625,7 @@ 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), @@ -693,6 +701,7 @@ func loginToManagement(ctx context.Context, client mgm.Client, pubSSHKey []byte, config.BlockLANAccess, config.BlockInbound, config.DisableIPv6, + config.SyncMessageVersion, config.EnableSSHRoot, config.EnableSSHSFTP, config.EnableSSHLocalPortForwarding, diff --git a/client/internal/daemonaddr/owner.go b/client/internal/daemonaddr/owner.go new file mode 100644 index 000000000..c476f9ae6 --- /dev/null +++ b/client/internal/daemonaddr/owner.go @@ -0,0 +1,15 @@ +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) +} diff --git a/client/internal/daemonaddr/owner_unix.go b/client/internal/daemonaddr/owner_unix.go new file mode 100644 index 000000000..493e6528d --- /dev/null +++ b/client/internal/daemonaddr/owner_unix.go @@ -0,0 +1,40 @@ +//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()) +} diff --git a/client/internal/daemonaddr/owner_unix_test.go b/client/internal/daemonaddr/owner_unix_test.go new file mode 100644 index 000000000..363c7d95d --- /dev/null +++ b/client/internal/daemonaddr/owner_unix_test.go @@ -0,0 +1,62 @@ +//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) + } + }) + } +} diff --git a/client/internal/daemonaddr/owner_windows.go b/client/internal/daemonaddr/owner_windows.go new file mode 100644 index 000000000..1cd2bba15 --- /dev/null +++ b/client/internal/daemonaddr/owner_windows.go @@ -0,0 +1,42 @@ +//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 +} diff --git a/client/internal/daemonaddr/pipe.go b/client/internal/daemonaddr/pipe.go new file mode 100644 index 000000000..51815ef5e --- /dev/null +++ b/client/internal/daemonaddr/pipe.go @@ -0,0 +1,103 @@ +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 +} diff --git a/client/internal/daemonaddr/pipe_other.go b/client/internal/daemonaddr/pipe_other.go new file mode 100644 index 000000000..04e8e7331 --- /dev/null +++ b/client/internal/daemonaddr/pipe_other.go @@ -0,0 +1,15 @@ +//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") +} diff --git a/client/internal/daemonaddr/pipe_test.go b/client/internal/daemonaddr/pipe_test.go new file mode 100644 index 000000000..b9dfd90f1 --- /dev/null +++ b/client/internal/daemonaddr/pipe_test.go @@ -0,0 +1,30 @@ +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) + } +} diff --git a/client/internal/daemonaddr/pipe_windows.go b/client/internal/daemonaddr/pipe_windows.go new file mode 100644 index 000000000..3cd10a6c3 --- /dev/null +++ b/client/internal/daemonaddr/pipe_windows.go @@ -0,0 +1,59 @@ +//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) +} diff --git a/client/internal/daemonaddr/resolve_pipe_other.go b/client/internal/daemonaddr/resolve_pipe_other.go new file mode 100644 index 000000000..1aede8453 --- /dev/null +++ b/client/internal/daemonaddr/resolve_pipe_other.go @@ -0,0 +1,9 @@ +//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 +} diff --git a/client/internal/daemonaddr/resolve_pipe_windows.go b/client/internal/daemonaddr/resolve_pipe_windows.go new file mode 100644 index 000000000..d12ddb15d --- /dev/null +++ b/client/internal/daemonaddr/resolve_pipe_windows.go @@ -0,0 +1,82 @@ +//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 +} diff --git a/client/internal/debug/debug.go b/client/internal/debug/debug.go index 3a7c0ebff..0f81844f6 100644 --- a/client/internal/debug/debug.go +++ b/client/internal/debug/debug.go @@ -229,7 +229,6 @@ scutil_dns.txt (macOS only): const ( clientLogFile = "client.log" - uiLogFile = "gui-client.log" errorLogFile = "netbird.err" stdoutLogFile = "netbird.out" @@ -248,6 +247,20 @@ 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 @@ -257,6 +270,7 @@ type BundleGenerator struct { syncResponse *mgmProto.SyncResponse logPath string uiLogPath string + uiLogOpener LogOpener tempDir string statePath string cpuProfile []byte @@ -285,14 +299,20 @@ 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. - 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 + // 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 } func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGenerator { @@ -302,6 +322,11 @@ func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGen logFileCount = 1 } + uiLogOpener := deps.UILogOpener + if uiLogOpener == nil { + uiLogOpener = openLogFile + } + return &BundleGenerator{ anonymizer: anonymize.NewAnonymizer(anonymize.DefaultAddresses()), @@ -310,6 +335,7 @@ 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, @@ -480,7 +506,6 @@ 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, @@ -677,6 +702,7 @@ 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)) @@ -996,11 +1022,11 @@ func (g *BundleGenerator) addLogfile() error { logDir := filepath.Dir(g.logPath) - if err := g.addSingleLogfile(g.logPath, clientLogFile); err != nil { + if err := g.addSingleLogfile(openLogFile, g.logPath, clientLogFile); err != nil { return fmt.Errorf("add client log file to zip: %w", err) } - g.addRotatedLogFiles(logDir, clientLogPrefix) + g.addRotatedLogFiles(openLogFile, logDir, clientLogPrefix) stdErrLogPath := filepath.Join(logDir, errorLogFile) stdoutLogPath := filepath.Join(logDir, stdoutLogFile) @@ -1009,11 +1035,11 @@ func (g *BundleGenerator) addLogfile() error { stdoutLogPath = darwinStdoutLogPath } - if err := g.addSingleLogfile(stdErrLogPath, errorLogFile); err != nil { + if err := g.addSingleLogfile(openLogFile, stdErrLogPath, errorLogFile); err != nil { log.Warnf("Failed to add %s to zip: %v", errorLogFile, err) } - if err := g.addSingleLogfile(stdoutLogPath, stdoutLogFile); err != nil { + if err := g.addSingleLogfile(openLogFile, stdoutLogPath, stdoutLogFile); err != nil { log.Warnf("Failed to add %s to zip: %v", stdoutLogFile, err) } @@ -1030,18 +1056,18 @@ func (g *BundleGenerator) addUILog() error { return nil } - if err := g.addSingleLogfile(g.uiLogPath, uiLogFile); err != nil { + if err := g.addSingleLogfile(g.uiLogOpener, g.uiLogPath, configs.UILogFile); err != nil { return fmt.Errorf("add UI log file to zip: %w", err) } - g.addRotatedLogFiles(filepath.Dir(g.uiLogPath), uiLogPrefix) + g.addRotatedLogFiles(g.uiLogOpener, filepath.Dir(g.uiLogPath), uiLogPrefix) return nil } // addSingleLogfile adds a single log file to the archive -func (g *BundleGenerator) addSingleLogfile(logPath, targetName string) error { - logFile, err := os.Open(logPath) +func (g *BundleGenerator) addSingleLogfile(open LogOpener, logPath, targetName string) error { + logFile, err := open(logPath) if err != nil { return fmt.Errorf("open log file %s: %w", targetName, err) } @@ -1066,8 +1092,8 @@ func (g *BundleGenerator) addSingleLogfile(logPath, targetName string) error { } // addSingleLogFileGz adds a single gzipped log file to the archive -func (g *BundleGenerator) addSingleLogFileGz(logPath, targetName string) error { - f, err := os.Open(logPath) +func (g *BundleGenerator) addSingleLogFileGz(open LogOpener, logPath, targetName string) error { + f, err := open(logPath) if err != nil { return fmt.Errorf("open gz log file %s: %w", targetName, err) } @@ -1114,7 +1140,7 @@ func (g *BundleGenerator) addSingleLogFileGz(logPath, targetName string) error { // 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(logDir, prefix string) { +func (g *BundleGenerator) addRotatedLogFiles(open LogOpener, logDir, prefix string) { if g.logFileCount == 0 { return } @@ -1154,9 +1180,9 @@ func (g *BundleGenerator) addRotatedLogFiles(logDir, prefix string) { for i := 0; i < maxFiles; i++ { name := filepath.Base(files[i]) if strings.HasSuffix(name, ".gz") { - err = g.addSingleLogFileGz(files[i], name) + err = g.addSingleLogFileGz(open, files[i], name) } else { - err = g.addSingleLogfile(files[i], name) + err = g.addSingleLogfile(open, files[i], name) } if err != nil { log.Warnf("failed to add rotated log %s: %v", name, err) diff --git a/client/internal/debug/debug_ios.go b/client/internal/debug/debug_ios.go index a07c23dbd..001d64241 100644 --- a/client/internal/debug/debug_ios.go +++ b/client/internal/debug/debug_ios.go @@ -27,7 +27,7 @@ func (g *BundleGenerator) addPlatformLog() error { } swiftLogPath := filepath.Join(filepath.Dir(g.logPath), swiftLogFile) - if err := g.addSingleLogfile(swiftLogPath, swiftLogFile); err != nil { + if err := g.addSingleLogfile(openLogFile, 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) } diff --git a/client/internal/debug/debug_logfiles_test.go b/client/internal/debug/debug_logfiles_test.go index 3749b3e9b..31420711f 100644 --- a/client/internal/debug/debug_logfiles_test.go +++ b/client/internal/debug/debug_logfiles_test.go @@ -97,7 +97,7 @@ func runAddRotatedLogFilesPrefix(t *testing.T, dir, prefix string, logFileCount archive: zip.NewWriter(&buf), logFileCount: logFileCount, } - g.addRotatedLogFiles(dir, prefix) + g.addRotatedLogFiles(openLogFile, dir, prefix) require.NoError(t, g.archive.Close()) zr, err := zip.NewReader(bytes.NewReader(buf.Bytes()), int64(buf.Len())) diff --git a/client/internal/debug/debug_test.go b/client/internal/debug/debug_test.go index 8286f6852..7fe93a5c1 100644 --- a/client/internal/debug/debug_test.go +++ b/client/internal/debug/debug_test.go @@ -887,6 +887,8 @@ 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} { diff --git a/client/internal/debug/uilog_test.go b/client/internal/debug/uilog_test.go new file mode 100644 index 000000000..103e98c6f --- /dev/null +++ b/client/internal/debug/uilog_test.go @@ -0,0 +1,64 @@ +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) +} diff --git a/client/internal/debug/upload.go b/client/internal/debug/upload.go index cdf52409d..88fde6d6f 100644 --- a/client/internal/debug/upload.go +++ b/client/internal/debug/upload.go @@ -3,10 +3,12 @@ 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" @@ -14,20 +16,80 @@ import ( const maxBundleUploadSize = 50 * 1024 * 1024 -func UploadDebugBundle(ctx context.Context, url, managementURL, filePath string) (key string, err error) { - response, err := getUploadURL(ctx, url, managementURL) +// 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) if err != nil { return "", err } - err = upload(ctx, filePath, response) + if !insecure { + if err := requireHTTPS("upload URL from service", response.URL); err != nil { + return "", err + } + } + + err = upload(ctx, filePath, response, insecure) if err != nil { return "", err } return response.Key, nil } -func upload(ctx context.Context, filePath string, response *types.GetURLResponse) error { +func upload(ctx context.Context, filePath string, response *types.GetURLResponse, insecure bool) error { fileData, err := os.Open(filePath) if err != nil { return fmt.Errorf("open file: %w", err) @@ -52,7 +114,7 @@ func upload(ctx context.Context, filePath string, response *types.GetURLResponse req.ContentLength = stat.Size() req.Header.Set("Content-Type", "application/octet-stream") - putResp, err := http.DefaultClient.Do(req) + putResp, err := uploadClient(insecure).Do(req) if err != nil { return fmt.Errorf("upload failed: %v", err) } @@ -65,16 +127,23 @@ func upload(ctx context.Context, filePath string, response *types.GetURLResponse return 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) +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) if err != nil { return nil, fmt.Errorf("create GET request: %w", err) } getReq.Header.Set(types.ClientHeader, types.ClientHeaderValue) - resp, err := http.DefaultClient.Do(getReq) + resp, err := uploadClient(insecure).Do(getReq) if err != nil { return nil, fmt.Errorf("get presigned URL: %w", err) } diff --git a/client/internal/debug/upload_test.go b/client/internal/debug/upload_test.go index f224b8d3f..f3927cb81 100644 --- a/client/internal/debug/upload_test.go +++ b/client/internal/debug/upload_test.go @@ -5,6 +5,7 @@ import ( "errors" "net" "net/http" + "net/http/httptest" "os" "path/filepath" "testing" @@ -43,7 +44,7 @@ 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) + key, err := UploadDebugBundle(context.Background(), testURL+types.GetURLPath, testURL, file, true) require.NoError(t, err) id := getURLHash(testURL) require.Contains(t, key, id+"/") @@ -79,3 +80,47 @@ 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") +} diff --git a/client/internal/dns/local/local.go b/client/internal/dns/local/local.go index d0268186c..fef35fd41 100644 --- a/client/internal/dns/local/local.go +++ b/client/internal/dns/local/local.go @@ -6,6 +6,7 @@ import ( "fmt" "net" "net/netip" + "os" "slices" "strings" "sync" @@ -36,7 +37,43 @@ 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 string) (known, connected bool) + 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 } type Resolver struct { @@ -51,6 +88,12 @@ 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 @@ -59,11 +102,12 @@ 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), - ctx: ctx, - cancel: cancel, + 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, } } @@ -76,6 +120,14 @@ 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 } @@ -122,6 +174,9 @@ 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 @@ -495,8 +550,8 @@ func (d *Resolver) filterDisconnectedPeerAnswers(logger *log.Entry, question dns kept := make([]dns.RR, 0, len(records)) var dropped int for _, rr := range records { - ip := extractRecordIP(rr) - if ip == "" { + ip, ok := extractRecordAddr(rr) + if !ok { kept = append(kept, rr) continue } @@ -518,22 +573,57 @@ func (d *Resolver) filterDisconnectedPeerAnswers(logger *log.Entry, question dns return kept } -// 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 { +// 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) { switch r := rr.(type) { case *dns.A: - if r.A == nil { - return "" - } - return r.A.String() + addr, ok := netip.AddrFromSlice(r.A) + return addr.Unmap(), ok case *dns.AAAA: - if r.AAAA == nil { - return "" - } - return r.AAAA.String() + addr, ok := netip.AddrFromSlice(r.AAAA) + return addr.Unmap(), ok } - return "" + return netip.Addr{}, false } // Update replaces all zones and their records diff --git a/client/internal/dns/local/local_test.go b/client/internal/dns/local/local_test.go index 9b7dac231..89e896c0a 100644 --- a/client/internal/dns/local/local_test.go +++ b/client/internal/dns/local/local_test.go @@ -37,8 +37,8 @@ type mockPeerConnectivity struct { byIP map[string]struct{ known, connected bool } } -func (m mockPeerConnectivity) IsConnectedByIP(ip string) (known, connected bool) { - v, ok := m.byIP[ip] +func (m mockPeerConnectivity) IsConnectedByIP(ip netip.Addr) (known, connected bool) { + v, ok := m.byIP[ip.String()] if !ok { return false, false } diff --git a/client/internal/dns/local/warmup_test.go b/client/internal/dns/local/warmup_test.go new file mode 100644 index 000000000..0e77aa963 --- /dev/null +++ b/client/internal/dns/local/warmup_test.go @@ -0,0 +1,204 @@ +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) + }) +} diff --git a/client/internal/dns/mock_server.go b/client/internal/dns/mock_server.go index 31fedd9e5..b19862c2f 100644 --- a/client/internal/dns/mock_server.go +++ b/client/internal/dns/mock_server.go @@ -8,6 +8,7 @@ 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" @@ -92,6 +93,11 @@ 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 diff --git a/client/internal/dns/server.go b/client/internal/dns/server.go index 7556c66cc..f79454457 100644 --- a/client/internal/dns/server.go +++ b/client/internal/dns/server.go @@ -82,6 +82,7 @@ type Server interface { PopulateManagementDomain(mgmtURL *url.URL) error SetRouteSources(selected, active func() route.HAMap) SetFirewall(Firewall) + SetPeerActivator(local.PeerActivator) } type nsGroupsByDomain struct { @@ -491,6 +492,13 @@ 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() @@ -1435,11 +1443,11 @@ 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 string) (known, connected bool) { +func (l localPeerConnectivity) IsConnectedByIP(ip netip.Addr) (known, connected bool) { if l.status == nil { return false, false } - state, ok := l.status.PeerStateByIP(ip) + state, ok := l.status.PeerStateByIP(ip.String()) if !ok { return false, false } diff --git a/client/internal/dns/service_listener.go b/client/internal/dns/service_listener.go index 9c0e52af8..3dc29c4dc 100644 --- a/client/internal/dns/service_listener.go +++ b/client/internal/dns/service_listener.go @@ -292,18 +292,16 @@ func (s *serviceViaListener) generateFreePort() (uint16, error) { return customPort, nil } - udpAddr := net.UDPAddrFromAddrPort(netip.MustParseAddrPort("0.0.0.0:0")) - probeListener, err := net.ListenUDP("udp", udpAddr) + probeListener, err := net.ListenUDP("udp4", &net.UDPAddr{}) if err != nil { log.Debugf("failed to bind random port for DNS: %s", err) return 0, err } - addrPort := netip.MustParseAddrPort(probeListener.LocalAddr().String()) // might panic if address is incorrect - err = probeListener.Close() - if err != nil { + port := uint16(probeListener.LocalAddr().(*net.UDPAddr).Port) + if err = probeListener.Close(); err != nil { log.Debugf("failed to free up DNS port: %s", err) return 0, err } - return addrPort.Port(), nil + return port, nil } diff --git a/client/internal/dns_peer_activator.go b/client/internal/dns_peer_activator.go new file mode 100644 index 000000000..c283d6251 --- /dev/null +++ b/client/internal/dns_peer_activator.go @@ -0,0 +1,76 @@ +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: + } + } +} diff --git a/client/internal/dns_peer_activator_test.go b/client/internal/dns_peer_activator_test.go new file mode 100644 index 000000000..8c3b75e59 --- /dev/null +++ b/client/internal/dns_peer_activator_test.go @@ -0,0 +1,129 @@ +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") +} diff --git a/client/internal/ebpf/ebpf/bpf_bpfeb.o b/client/internal/ebpf/ebpf/bpf_bpfeb.o index 6e9cda44a..7433ad740 100644 Binary files a/client/internal/ebpf/ebpf/bpf_bpfeb.o and b/client/internal/ebpf/ebpf/bpf_bpfeb.o differ diff --git a/client/internal/ebpf/ebpf/bpf_bpfel.o b/client/internal/ebpf/ebpf/bpf_bpfel.o index 6338f4774..779f43a00 100644 Binary files a/client/internal/ebpf/ebpf/bpf_bpfel.o and b/client/internal/ebpf/ebpf/bpf_bpfel.o differ diff --git a/client/internal/ebpf/ebpf/src/dns_fwd.c b/client/internal/ebpf/ebpf/src/dns_fwd.c index 5f3fbcc32..9f8de2001 100644 --- a/client/internal/ebpf/ebpf/src/dns_fwd.c +++ b/client/internal/ebpf/ebpf/src/dns_fwd.c @@ -52,11 +52,14 @@ 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; } diff --git a/client/internal/ebpf/ebpf/src/wg_proxy.c b/client/internal/ebpf/ebpf/src/wg_proxy.c index 88fea65cf..5e7474928 100644 --- a/client/internal/ebpf/ebpf/src/wg_proxy.c +++ b/client/internal/ebpf/ebpf/src/wg_proxy.c @@ -50,5 +50,11 @@ 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; } diff --git a/client/internal/engine.go b/client/internal/engine.go index f44400c52..791b46ee3 100644 --- a/client/internal/engine.go +++ b/client/internal/engine.go @@ -64,7 +64,10 @@ 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" @@ -147,6 +150,7 @@ 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. @@ -220,6 +224,13 @@ 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 @@ -551,7 +562,7 @@ 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) + e.rpManager, err = rosenpass.NewManager(e.config.PreSharedKey, e.config.WgIfaceName, publicKey) if err != nil { return fmt.Errorf("create rosenpass manager: %w", err) } @@ -652,8 +663,24 @@ 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()) @@ -968,8 +995,12 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error { e.ApplySessionDeadline(update.GetSessionExpiresAt()) - if update.NetworkMap != nil && update.NetworkMap.PeerConfig != nil { - e.handleAutoUpdateVersion(update.NetworkMap.PeerConfig.AutoUpdate) + // 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()) } done := e.phase("netbird_config") @@ -979,12 +1010,47 @@ 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 = "." — 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 } @@ -997,6 +1063,14 @@ 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() @@ -1010,6 +1084,19 @@ 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. @@ -1169,6 +1256,7 @@ 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, @@ -2037,6 +2125,7 @@ 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, @@ -2610,13 +2699,14 @@ 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 { - for _, allowedIP := range p.GetAllowedIps() { - if allowedIP != ip.String() { - continue - } + if e.peerRoutesAddr(p, r.TranslatedAddress) { log.Infof("exclude forwarder peer from lazy connection: %s", p.GetWgPubKey()) excludedPeers[p.GetWgPubKey()] = true } @@ -2626,6 +2716,27 @@ 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 { diff --git a/client/internal/engine_lazy_exclude_test.go b/client/internal/engine_lazy_exclude_test.go new file mode 100644 index 000000000..b5ef16c3b --- /dev/null +++ b/client/internal/engine_lazy_exclude_test.go @@ -0,0 +1,87 @@ +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 +} diff --git a/client/internal/engine_session_deadline_test.go b/client/internal/engine_session_deadline_test.go index 6127e5bb0..5a67f103a 100644 --- a/client/internal/engine_session_deadline_test.go +++ b/client/internal/engine_session_deadline_test.go @@ -75,4 +75,14 @@ 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") + }) } diff --git a/client/internal/ipcauth/creds_stub.go b/client/internal/ipcauth/creds_stub.go new file mode 100644 index 000000000..154948716 --- /dev/null +++ b/client/internal/ipcauth/creds_stub.go @@ -0,0 +1,31 @@ +//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 +} diff --git a/client/internal/ipcauth/creds_unix.go b/client/internal/ipcauth/creds_unix.go new file mode 100644 index 000000000..688fe4623 --- /dev/null +++ b/client/internal/ipcauth/creds_unix.go @@ -0,0 +1,56 @@ +//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 } diff --git a/client/internal/ipcauth/creds_windows.go b/client/internal/ipcauth/creds_windows.go new file mode 100644 index 000000000..37f902c52 --- /dev/null +++ b/client/internal/ipcauth/creds_windows.go @@ -0,0 +1,194 @@ +//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 +} diff --git a/client/internal/ipcauth/forward.go b/client/internal/ipcauth/forward.go new file mode 100644 index 000000000..57749528c --- /dev/null +++ b/client/internal/ipcauth/forward.go @@ -0,0 +1,272 @@ +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-" 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) +} diff --git a/client/internal/ipcauth/forward_test.go b/client/internal/ipcauth/forward_test.go new file mode 100644 index 000000000..d9adf05da --- /dev/null +++ b/client/internal/ipcauth/forward_test.go @@ -0,0 +1,214 @@ +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- 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) + } + }) + } +} diff --git a/client/internal/ipcauth/identity.go b/client/internal/ipcauth/identity.go new file mode 100644 index 000000000..ff70c209a --- /dev/null +++ b/client/internal/ipcauth/identity.go @@ -0,0 +1,127 @@ +// 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 +} diff --git a/client/internal/ipcauth/ownedfile.go b/client/internal/ipcauth/ownedfile.go new file mode 100644 index 000000000..be7bf4864 --- /dev/null +++ b/client/internal/ipcauth/ownedfile.go @@ -0,0 +1,63 @@ +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 +} diff --git a/client/internal/ipcauth/ownedfile_test.go b/client/internal/ipcauth/ownedfile_test.go new file mode 100644 index 000000000..b8178ad45 --- /dev/null +++ b/client/internal/ipcauth/ownedfile_test.go @@ -0,0 +1,64 @@ +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) +} diff --git a/client/internal/ipcauth/ownedfile_unix.go b/client/internal/ipcauth/ownedfile_unix.go new file mode 100644 index 000000000..4a6afcea7 --- /dev/null +++ b/client/internal/ipcauth/ownedfile_unix.go @@ -0,0 +1,35 @@ +//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 +} diff --git a/client/internal/ipcauth/ownedfile_unix_test.go b/client/internal/ipcauth/ownedfile_unix_test.go new file mode 100644 index 000000000..9e7831991 --- /dev/null +++ b/client/internal/ipcauth/ownedfile_unix_test.go @@ -0,0 +1,57 @@ +//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") + } +} diff --git a/client/internal/ipcauth/ownedfile_windows.go b/client/internal/ipcauth/ownedfile_windows.go new file mode 100644 index 000000000..19acaec4d --- /dev/null +++ b/client/internal/ipcauth/ownedfile_windows.go @@ -0,0 +1,59 @@ +//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 +} diff --git a/client/internal/ipcauth/ownedfile_windows_test.go b/client/internal/ipcauth/ownedfile_windows_test.go new file mode 100644 index 000000000..ab68fdf39 --- /dev/null +++ b/client/internal/ipcauth/ownedfile_windows_test.go @@ -0,0 +1,78 @@ +//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") +} diff --git a/client/internal/ipcauth/peercred_bsd.go b/client/internal/ipcauth/peercred_bsd.go new file mode 100644 index 000000000..6d9c5247f --- /dev/null +++ b/client/internal/ipcauth/peercred_bsd.go @@ -0,0 +1,43 @@ +//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 +} diff --git a/client/internal/ipcauth/peercred_linux.go b/client/internal/ipcauth/peercred_linux.go new file mode 100644 index 000000000..417cc1e00 --- /dev/null +++ b/client/internal/ipcauth/peercred_linux.go @@ -0,0 +1,39 @@ +//go:build linux + +package ipcauth + +import ( + "fmt" + "net" + + "golang.org/x/sys/unix" +) + +// PeerIdentity reads the kernel-authenticated identity of the process on the +// other end of a Unix socket via SO_PEERCRED. The credentials are recorded by +// the kernel at connect() time and cannot be changed for the life of the +// connection, so they are not spoofable by the caller. +func PeerIdentity(conn net.Conn) (Identity, error) { + uc, ok := conn.(*net.UnixConn) + if !ok { + return Identity{}, fmt.Errorf("connection is not a unix socket: %T", conn) + } + + raw, err := uc.SyscallConn() + if err != nil { + return Identity{}, fmt.Errorf("raw conn: %w", err) + } + + var cred *unix.Ucred + var credErr error + if err := raw.Control(func(fd uintptr) { + cred, credErr = unix.GetsockoptUcred(int(fd), unix.SOL_SOCKET, unix.SO_PEERCRED) + }); err != nil { + return Identity{}, fmt.Errorf("control raw conn: %w", err) + } + if credErr != nil { + return Identity{}, fmt.Errorf("read SO_PEERCRED: %w", credErr) + } + + return Identity{UID: cred.Uid, GID: cred.Gid, PID: cred.Pid}, nil +} diff --git a/client/internal/ipcauth/pipeserver_windows.go b/client/internal/ipcauth/pipeserver_windows.go new file mode 100644 index 000000000..7ba59d574 --- /dev/null +++ b/client/internal/ipcauth/pipeserver_windows.go @@ -0,0 +1,87 @@ +//go:build windows + +package ipcauth + +import ( + "fmt" + "net" + + log "github.com/sirupsen/logrus" + "golang.org/x/sys/windows" +) + +// PipeServerTrusted reports an error unless the pipe behind conn was created by a +// principal this client may hand secrets to. Clients call it for a pipe whose name +// carries no guarantee of its own, which is any name outside the +// ProtectedPrefix\Administrators namespace: that namespace already restricts +// creation to administrators and LocalSystem, while a plain name can be created by +// any local user before the daemon gets there. +// +// The decision is made from the pipe object's owner, not from the serving process, +// because a client cannot open a process running as another user at all, and the +// legitimate case is precisely an unprivileged client talking to a privileged +// daemon. Trusted owners are the service accounts, BUILTIN\Administrators, and +// this client's own user, the last of which is the daemon a user runs themselves +// as in netstack mode. A pipe owned by anyone else gets no setup key, pre-shared +// key or SSO prompt out of this client. +func PipeServerTrusted(conn net.Conn) error { + // go-winio's pipe connection embeds *win32File, which exposes Fd(). + fdConn, ok := conn.(interface{ Fd() uintptr }) + if !ok { + return fmt.Errorf("connection %T does not expose a pipe handle", conn) + } + + owner, err := pipeOwnerSID(windows.Handle(fdConn.Fd())) + if err != nil { + return err + } + + if !trustedPipeOwner(owner) { + return fmt.Errorf("pipe owned by %s, which is neither an administrator nor this user", owner) + } + return nil +} + +// PipeOwnedBySelf reports whether the pipe behind conn was created by this very +// user, which is how a client recognises a daemon running as itself. Ownership it +// cannot read is reported as false. +func PipeOwnedBySelf(conn net.Conn) bool { + fdConn, ok := conn.(interface{ Fd() uintptr }) + if !ok { + return false + } + + owner, err := pipeOwnerSID(windows.Handle(fdConn.Fd())) + if err != nil { + log.Debugf("read daemon pipe owner: %v", err) + return false + } + return selfKnown && selfIdentity.SID != "" && owner == selfIdentity.SID +} + +// pipeOwnerSID reads the owner of the pipe object a client is connected to. The +// handle was opened with GENERIC_READ, which includes READ_CONTROL, so no extra +// access is needed. +func pipeOwnerSID(handle windows.Handle) (string, error) { + sd, err := windows.GetSecurityInfo(handle, windows.SE_KERNEL_OBJECT, windows.OWNER_SECURITY_INFORMATION) + if err != nil { + return "", fmt.Errorf("read pipe security info: %w", err) + } + + owner, _, err := sd.Owner() + if err != nil { + return "", fmt.Errorf("read pipe owner: %w", err) + } + return owner.String(), nil +} + +// trustedPipeOwner reports whether a pipe's owner is a principal a client may +// speak to. An elevated process's objects are owned by BUILTIN\Administrators by +// default, an unelevated one's by the user, which is why both forms appear here. +func trustedPipeOwner(owner string) bool { + switch owner { + case sidLocalSystem, sidLocalService, sidNetworkService, sidAdministrators: + return true + } + return selfKnown && selfIdentity.SID != "" && owner == selfIdentity.SID +} diff --git a/client/internal/ipcauth/privileged.go b/client/internal/ipcauth/privileged.go new file mode 100644 index 000000000..95f2a50e9 --- /dev/null +++ b/client/internal/ipcauth/privileged.go @@ -0,0 +1,125 @@ +package ipcauth + +import ( + "os" + "runtime" +) + +// Fields of the ErrorInfo detail the daemon attaches to a PermissionDenied it +// raises for an operation that requires root/administrator. Clients match on +// Reason and Domain rather than on the message text, and render the summary and +// command themselves so the user gets guidance instead of a gRPC error dump. +const ( + // ErrorReasonPrivilegeRequired identifies the detail. + ErrorReasonPrivilegeRequired = "PRIVILEGE_REQUIRED" + // ErrorDomain scopes the reason to the NetBird daemon. + ErrorDomain = "daemon.netbird.io" + // ErrorMetaSummary is the one-sentence explanation of what was refused. + ErrorMetaSummary = "summary" + // ErrorMetaCommand is the command that performs the same operation with the + // privileges it needs, ready to copy and run. + ErrorMetaCommand = "command" +) + +// The identity of the process evaluating callers, captured once because it cannot +// change. selfKnown is false when it could not be read, in which case nothing is +// ever treated as this process. selfMayDelegate additionally requires this +// process to be unprivileged: see IsPrivilegedCaller. +var ( + selfIdentity Identity + selfKnown bool + selfMayDelegate bool + // selfPID is this process's PID, used to recognise the daemon dialling itself. + selfPID = os.Getpid() +) + +func init() { + id, err := CurrentProcessIdentity() + if err != nil { + return + } + selfIdentity, selfKnown = id, true + // Only an unprivileged daemon delegates its authority to its own identity. + // When it is root or LocalSystem, sharing its identity does not mean sharing + // its power: on Windows a filtered and a full token carry the same SID, so + // matching there would let a non-elevated shell of an administrator account + // act as an administrator, which is the boundary the token check exists to + // keep. + selfMayDelegate = !id.IsPrivileged() +} + +// IsDaemonSelf reports whether an identity is this very process. The JSON gateway +// runs inside the daemon and re-dials it locally, so this is what distinguishes +// the gateway from any other caller, whatever user the daemon runs as. +func IsDaemonSelf(id Identity) bool { + if !selfKnown || id.IsWindows() != selfIdentity.IsWindows() { + return false + } + if id.IsWindows() { + return id.SID != "" && id.SID == selfIdentity.SID + } + return id.UID == selfIdentity.UID +} + +// IsPrivilegedCaller reports whether an identity may make the changes the daemon +// restricts to the platform administrator. This is the daemon's own rule and +// cannot be evaluated by a client, which does not know what the daemon runs as. +// +// Beyond root/administrator it accepts a caller running as the daemon's own +// identity when the daemon is itself unprivileged. That keeps a rootless container +// working, where there is no uid 0 at all, and a Windows daemon in netstack mode, +// which needs no administrator rights. In those setups a caller sharing the +// daemon's identity can already rewrite the config files it reads and replace the +// binary it runs, so refusing it a config change would protect nothing; and an +// unprivileged daemon cannot hand out a root shell in the first place. +func IsPrivilegedCaller(id Identity) bool { + if id.IsPrivileged() { + return true + } + return selfMayDelegate && IsDaemonSelf(id) +} + +// SelfDelegatesTo returns the identity this process delegates its authority to, +// and whether it delegates at all. Only an unprivileged daemon does: see +// IsPrivilegedCaller. It exists so a refusal can name who may actually perform the +// operation, because on such a host root is neither required nor necessarily +// available. +func SelfDelegatesTo() (Identity, bool) { + if !selfKnown || !selfMayDelegate { + return Identity{}, false + } + return selfIdentity, true +} + +// PrivilegedActor names the principal a privileged operation requires, for use +// in messages shown to the user. +func PrivilegedActor() string { + if runtime.GOOS == "windows" { + return "administrator privileges" + } + return "root" +} + +// ElevatedCommand renders a command so that running it grants the privileges the +// operation needs. Windows has no in-line equivalent of sudo, so the command is +// returned unchanged and the user is expected to run it from an elevated +// terminal. +func ElevatedCommand(command string) string { + if runtime.GOOS == "windows" { + return command + } + return "sudo " + command +} + +// UpCommand renders an elevated `netbird up` with the given flags, preceded by a +// `down`. The down is what makes the command work on a connected client: `netbird +// up` prints "Already connected" and returns without applying any config flag, so +// on its own the command would appear to do nothing. It is a no-op, exit 0, when +// the client is not connected. +// +// ";" rather than "&&" so the line can be pasted into any of the shells a user +// might have: PowerShell 5.1, still the default on Windows Server, rejects "&&" +// as a syntax error. +func UpCommand(flags string) string { + return ElevatedCommand("netbird down") + "; " + ElevatedCommand("netbird up "+flags) +} diff --git a/client/internal/ipcauth/privileged_test.go b/client/internal/ipcauth/privileged_test.go new file mode 100644 index 000000000..c1c7c1543 --- /dev/null +++ b/client/internal/ipcauth/privileged_test.go @@ -0,0 +1,134 @@ +package ipcauth + +import "testing" + +// The self rule is the one place privilege is granted to something other than the +// platform administrator, so its two guards matter: it must apply only when the +// daemon is itself unprivileged, and only to a caller with the daemon's identity. +func TestIsPrivilegedCaller_SelfRule(t *testing.T) { + tests := []struct { + name string + // self stands in for the process the daemon runs as. + self Identity + selfKnown bool + caller Identity + want bool + }{ + { + name: "root is privileged whatever the daemon runs as", + self: Identity{UID: 1000}, + selfKnown: true, + caller: Identity{UID: 0}, + want: true, + }, + { + name: "an unprivileged daemon delegates to its own user (rootless container)", + self: Identity{UID: 1000}, + selfKnown: true, + caller: Identity{UID: 1000}, + want: true, + }, + { + name: "an unprivileged daemon delegates to nobody else", + self: Identity{UID: 1000}, + selfKnown: true, + caller: Identity{UID: 1001}, + want: false, + }, + { + // The daemon is root on a normal install, so sharing its identity is + // already covered by being root; nothing else may match. + name: "a root daemon delegates to nobody", + self: Identity{UID: 0}, + selfKnown: true, + caller: Identity{UID: 1000}, + want: false, + }, + { + // Windows netstack mode: the daemon needs no administrator rights. + name: "an unprivileged windows daemon delegates to its own SID", + self: Identity{SID: "S-1-5-21-1-2-3-1001"}, + selfKnown: true, + caller: Identity{SID: "S-1-5-21-1-2-3-1001"}, + want: true, + }, + { + name: "an unprivileged windows daemon delegates to no other SID", + self: Identity{SID: "S-1-5-21-1-2-3-1001"}, + selfKnown: true, + caller: Identity{SID: "S-1-5-21-1-2-3-1002"}, + want: false, + }, + { + // The UAC boundary: a filtered and a full token of the same account + // carry the same SID but not the same power, so an elevated daemon must + // never delegate to its own SID. + name: "an elevated windows daemon does not delegate to its own SID", + self: Identity{SID: "S-1-5-21-1-2-3-500", Elevated: true}, + selfKnown: true, + caller: Identity{SID: "S-1-5-21-1-2-3-500"}, + want: false, + }, + { + name: "LocalSystem is privileged on its own merits, not by delegation", + self: Identity{SID: sidLocalSystem}, + selfKnown: true, + caller: Identity{SID: sidLocalSystem}, + want: true, // LocalSystem is privileged on its own merits + }, + { + name: "identities of different kinds never match", + self: Identity{UID: 1000}, + selfKnown: true, + caller: Identity{SID: "S-1-5-21-1-2-3-1001"}, + want: false, + }, + { + name: "an unknown self identity delegates to nobody", + self: Identity{}, + selfKnown: false, + caller: Identity{UID: 1000}, + want: false, + }, + } + + for _, tt := range tests { + t.Run(tt.name, func(t *testing.T) { + prevID, prevKnown, prevDelegate := selfIdentity, selfKnown, selfMayDelegate + t.Cleanup(func() { selfIdentity, selfKnown, selfMayDelegate = prevID, prevKnown, prevDelegate }) + + selfIdentity, selfKnown = tt.self, tt.selfKnown + selfMayDelegate = tt.selfKnown && !tt.self.IsPrivileged() + + if got := IsPrivilegedCaller(tt.caller); got != tt.want { + t.Fatalf("IsPrivilegedCaller(%v) with daemon %v = %t, want %t", + tt.caller, tt.self, got, tt.want) + } + }) + } +} + +// The real process must never accidentally delegate: a test binary running as a +// normal user is unprivileged, so it may match itself, but nothing else. +func TestIsPrivilegedCaller_ThisProcess(t *testing.T) { + id, err := CurrentProcessIdentity() + if err != nil { + t.Skipf("cannot read this process's identity: %v", err) + } + + // This process is always allowed to act as itself: either it is privileged, or + // it is unprivileged and therefore delegates to its own identity. + if !IsPrivilegedCaller(id) { + t.Errorf("this process %v was refused its own identity", id) + } + + // A caller that is neither root nor this process must be refused, whatever + // this process happens to be. + other := Identity{UID: id.UID + 1} + if id.IsWindows() { + other = Identity{SID: id.SID + "9"} + } + if IsPrivilegedCaller(other) { + t.Errorf("an unrelated identity %v was treated as privileged", other) + } +} diff --git a/client/internal/ipcauth/self_unix.go b/client/internal/ipcauth/self_unix.go new file mode 100644 index 000000000..1b86c4fc0 --- /dev/null +++ b/client/internal/ipcauth/self_unix.go @@ -0,0 +1,17 @@ +//go:build !windows + +package ipcauth + +import "os" + +// CurrentProcessIdentity returns this process's identity as the daemon would +// see it if this process connected to the local IPC. It lets a client (the UI) +// decide up front whether a privileged operation can succeed, without a +// round-trip and without duplicating the rules: the answer comes from the same +// Identity.IsPrivileged the daemon applies. +func CurrentProcessIdentity() (Identity, error) { + return Identity{ + UID: uint32(os.Geteuid()), + GID: uint32(os.Getegid()), + }, nil +} diff --git a/client/internal/ipcauth/self_windows.go b/client/internal/ipcauth/self_windows.go new file mode 100644 index 000000000..5474cc101 --- /dev/null +++ b/client/internal/ipcauth/self_windows.go @@ -0,0 +1,35 @@ +//go:build windows + +package ipcauth + +import ( + "fmt" + + "golang.org/x/sys/windows" +) + +// CurrentProcessIdentity returns this process's identity as the daemon would see +// it if this process connected to the local IPC. It lets a client (the UI) +// decide up front whether a privileged operation can succeed, without a +// round-trip and without duplicating the rules: the answer comes from the same +// Identity.IsPrivileged the daemon applies to the token it reads off the pipe. +func CurrentProcessIdentity() (Identity, error) { + // A pseudo-token, so it must not be closed. + token := windows.GetCurrentProcessToken() + + user, err := token.GetTokenUser() + if err != nil { + return Identity{}, fmt.Errorf("read token user: %w", err) + } + + groups, err := tokenGroupSIDs(token) + if err != nil { + return Identity{}, err + } + + return Identity{ + SID: user.User.Sid.String(), + Groups: groups, + Elevated: token.IsElevated(), + }, nil +} diff --git a/client/internal/lazyconn/manager/manager.go b/client/internal/lazyconn/manager/manager.go index 3868e37e8..b7424bb2f 100644 --- a/client/internal/lazyconn/manager/manager.go +++ b/client/internal/lazyconn/manager/manager.go @@ -29,6 +29,11 @@ type managedPeer struct { type Config struct { InactivityThreshold *time.Duration + // ReconcileAllowedIPs re-applies a peer's routed allowed IPs after its wake endpoint is + // armed. The activity listener creates the wake peer with the overlay /32 only; without the + // routed prefixes WireGuard would not steer subnet-bound traffic to the wake endpoint, so an + // idle routing peer could never be woken by that traffic. Optional; nil disables the reconcile. + ReconcileAllowedIPs func(peerKey string) error } // Manager manages lazy connections @@ -56,6 +61,9 @@ type Manager struct { peerToHAGroups map[string][]route.HAUniqueID // peer ID -> HA groups they belong to haGroupToPeers map[route.HAUniqueID][]string // HA group -> peer IDs in the group routesMu sync.RWMutex + + // reconcileAllowedIPs re-applies a peer's routed allowed IPs after its wake endpoint is armed. + reconcileAllowedIPs func(peerKey string) error } // NewManager creates a new lazy connection manager @@ -73,6 +81,7 @@ func NewManager(config Config, engineCtx context.Context, peerStore *peerstore.S activityManager: activity.NewManager(wgIface), peerToHAGroups: make(map[string][]route.HAUniqueID), haGroupToPeers: make(map[route.HAUniqueID][]string), + reconcileAllowedIPs: config.ReconcileAllowedIPs, } if wgIface.IsUserspaceBind() { @@ -201,7 +210,7 @@ func (m *Manager) AddPeer(peerCfg lazyconn.PeerConfig) (bool, error) { return false, nil } - if err := m.activityManager.MonitorPeerActivity(peerCfg); err != nil { + if err := m.armActivityListener(peerCfg); err != nil { return false, err } @@ -288,7 +297,7 @@ func (m *Manager) DeactivatePeer(peerID peerid.ConnID) { m.inactivityManager.RemovePeer(mp.peerCfg.PublicKey) - if err := m.activityManager.MonitorPeerActivity(*mp.peerCfg); err != nil { + if err := m.armActivityListener(*mp.peerCfg); err != nil { mp.peerCfg.Log.Errorf("failed to create activity monitor: %v", err) return } @@ -465,6 +474,31 @@ func (m *Manager) close() { } // shouldDeferIdleForHA checks if peer should stay connected due to HA group requirements +// armRoutedAllowedIPs re-applies the peer's routed allowed IPs onto its freshly armed wake +// endpoint. The activity listener creates the wake peer with the overlay /32 only, so without +// this the routed prefixes would be missing and traffic to a routed subnet could not wake the +// idle routing peer. It is a no-op when no reconciler is configured. +// armActivityListener (re)arms the peer's wake endpoint via the activity manager and then +// re-applies its routed allowed IPs, so traffic to a routed subnet can wake an idle routing +// peer. The routed prefixes must be re-applied after the wake endpoint exists because the +// listener creates it with the overlay /32 only. +func (m *Manager) armActivityListener(peerCfg lazyconn.PeerConfig) error { + if err := m.activityManager.MonitorPeerActivity(peerCfg); err != nil { + return err + } + m.armRoutedAllowedIPs(&peerCfg) + return nil +} + +func (m *Manager) armRoutedAllowedIPs(peerCfg *lazyconn.PeerConfig) { + if m.reconcileAllowedIPs == nil { + return + } + if err := m.reconcileAllowedIPs(peerCfg.PublicKey); err != nil { + peerCfg.Log.Errorf("failed to reconcile routed allowed IPs on wake endpoint: %v", err) + } +} + func (m *Manager) shouldDeferIdleForHA(inactivePeers map[string]struct{}, peerID string) bool { m.routesMu.RLock() defer m.routesMu.RUnlock() @@ -577,7 +611,7 @@ func (m *Manager) onPeerInactivityTimedOut(peerIDs map[string]struct{}) { mp.peerCfg.Log.Infof("start activity monitor") - if err := m.activityManager.MonitorPeerActivity(*mp.peerCfg); err != nil { + if err := m.armActivityListener(*mp.peerCfg); err != nil { mp.peerCfg.Log.Errorf("failed to create activity monitor: %v", err) continue } diff --git a/client/internal/mobile_dependency.go b/client/internal/mobile_dependency.go index 310d61a25..0234432b1 100644 --- a/client/internal/mobile_dependency.go +++ b/client/internal/mobile_dependency.go @@ -11,12 +11,14 @@ import ( // MobileDependency collect all dependencies for mobile platform type MobileDependency struct { - // Android only - TunAdapter device.TunAdapter - IFaceDiscover stdnet.ExternalIFaceDiscover + // Android and iOS NetworkChangeListener listener.NetworkChangeListener - HostDNSAddresses []netip.AddrPort - DnsReadyListener dns.ReadyListener + + // Android only + TunAdapter device.TunAdapter + IFaceDiscover stdnet.ExternalIFaceDiscover + HostDNSAddresses []netip.AddrPort + DnsReadyListener dns.ReadyListener // iOS only DnsManager dns.IosDnsManager diff --git a/client/internal/netflow/store/event_aggregation_test.go b/client/internal/netflow/store/event_aggregation_test.go index c0422e8b7..8abe0d162 100644 --- a/client/internal/netflow/store/event_aggregation_test.go +++ b/client/internal/netflow/store/event_aggregation_test.go @@ -175,7 +175,9 @@ func TestFlowAggregationOfUnknownProtocols(t *testing.T) { } func TestResetAggregationWindow(t *testing.T) { - store := NewAggregatingMemoryStore() + now := time.Now() + nowFunc := func() time.Time { return now } + store := NewAggregatingMemoryStoreWithTimeFunc(nowFunc) store.StoreEvent(&types.Event{ ID: uuid.New(), Timestamp: time.Now(), @@ -198,6 +200,7 @@ func TestResetAggregationWindow(t *testing.T) { }, }) + now = now.Add(1 * time.Second) reset := store.ResetAggregationWindow() previousEvents, ok := reset.(*AggregatingMemory) assert.True(t, ok) diff --git a/client/internal/netflow/store/memory.go b/client/internal/netflow/store/memory.go index a34e4be63..dfe764032 100644 --- a/client/internal/netflow/store/memory.go +++ b/client/internal/netflow/store/memory.go @@ -29,6 +29,7 @@ type AggregatingMemory struct { WindowStart time.Time WindowEnd time.Time rnd *v2.PCG + nowFunc func() time.Time } func (m *Memory) StoreEvent(event *types.Event) { @@ -62,14 +63,19 @@ func (m *Memory) DeleteEvents(ids []uuid.UUID) { } func NewAggregatingMemoryStore() *AggregatingMemory { - return &AggregatingMemory{WindowStart: time.Now(), Memory: Memory{events: make(map[uuid.UUID]*types.Event)}, rnd: v2.NewPCG(rand.Uint64(), rand.Uint64())} + return NewAggregatingMemoryStoreWithTimeFunc(defaultNowFunc) +} + +// used in tests when deterministic (less random) time intervals are required +func NewAggregatingMemoryStoreWithTimeFunc(nowFunc func() time.Time) *AggregatingMemory { + return &AggregatingMemory{WindowStart: nowFunc(), Memory: Memory{events: make(map[uuid.UUID]*types.Event)}, nowFunc: nowFunc, rnd: v2.NewPCG(rand.Uint64(), rand.Uint64())} } func (am *AggregatingMemory) ResetAggregationWindow() types.FlowEventAggregator { am.mux.Lock() defer am.mux.Unlock() - now := time.Now() + now := am.nowFunc() toret := AggregatingMemory{WindowStart: am.WindowStart, WindowEnd: now, Memory: Memory{events: am.events}, rnd: v2.NewPCG(rand.Uint64(), rand.Uint64())} am.events = make(map[uuid.UUID]*types.Event) @@ -152,3 +158,7 @@ func (am *AggregatingMemory) GetAggregatedEvents() []*types.Event { return slices.Collect(maps.Values(aggregated)) // could return an iterator instead here } + +func defaultNowFunc() time.Time { + return time.Now() +} diff --git a/client/internal/peer/conn.go b/client/internal/peer/conn.go index fb468696f..09a4e8b02 100644 --- a/client/internal/peer/conn.go +++ b/client/internal/peer/conn.go @@ -30,6 +30,11 @@ import ( relayClient "github.com/netbirdio/netbird/shared/relay/client" ) +// wgTimeoutEscalationThreshold is the number of consecutive WireGuard +// handshake timeouts after which the rosenpass state for the peer is +// considered desynced and gets reset. +const wgTimeoutEscalationThreshold = 3 + // MetricsRecorder is an interface for recording peer connection metrics type MetricsRecorder interface { RecordConnectionStages( @@ -118,6 +123,9 @@ type Conn struct { wgWatcher *WGWatcher wgWatcherWg sync.WaitGroup wgWatcherCancel context.CancelFunc + // wgTimeouts counts consecutive WireGuard handshake timeouts without a + // successful handshake in between. Guarded by mu. + wgTimeouts int // used to store the remote Rosenpass key for Relayed connection in case of connection update from ice rosenpassRemoteKey []byte @@ -195,7 +203,6 @@ func NewConn(config ConnConfig, services ServiceDependencies) (*Conn, error) { statusICE: worker.NewAtomicStatus(), dumpState: dumpState, endpointUpdater: NewEndpointUpdater(connLog, config.WgConfig, isController(config)), - wgWatcher: NewWGWatcher(connLog, config.WgConfig.WgInterface, config.Key, dumpState), metricsRecorder: services.MetricsRecorder, } @@ -663,11 +670,12 @@ func (conn *Conn) onGuardEvent() { } } -func (conn *Conn) onWGDisconnected() { +func (conn *Conn) onWGDisconnected(watcherCtx context.Context) { conn.mu.Lock() defer conn.mu.Unlock() - if conn.ctx.Err() != nil { + // watcherCtx guards against a stale watcher tearing down a connection that already superseded it. + if conn.ctx.Err() != nil || watcherCtx.Err() != nil { return } @@ -683,6 +691,29 @@ func (conn *Conn) onWGDisconnected() { default: conn.Log.Debugf("No active connection to close on WG timeout") } + + conn.escalateWGTimeoutLocked() +} + +// escalateWGTimeoutLocked resets the peer's rosenpass state after repeated +// handshake timeouts. With rosenpass enabled, persistent timeouts mean the +// preshared keys have desynced; the renewal exchange runs over the dead +// tunnel and cannot resync them. Reporting the peer disconnected drops its +// rosenpass state, so the next connection configuration programs the +// rendezvous key and the tunnel can bootstrap again. Callers must hold mu. +func (conn *Conn) escalateWGTimeoutLocked() { + if conn.config.RosenpassConfig.PubKey == nil { + return + } + + conn.wgTimeouts++ + if conn.wgTimeouts < wgTimeoutEscalationThreshold || conn.onDisconnected == nil { + return + } + conn.wgTimeouts = 0 + + conn.Log.Warnf("%d consecutive WireGuard handshake timeouts, resetting rosenpass state for peer", wgTimeoutEscalationThreshold) + conn.onDisconnected(conn.config.WgConfig.RemoteKey) } func (conn *Conn) updateRelayStatus(relayServerAddr string, rosenpassPubKey []byte, updateTime time.Time) { @@ -802,25 +833,39 @@ func (conn *Conn) isConnectedOnAllWay() (status guard.ConnStatus) { }) } +// enableWgWatcherIfNeeded starts a fresh watcher instance per connection attempt, so its +// lifecycle stays bound to conn.mu and enable/disable can't race an old goroutine's shutdown. +// Caller must hold conn.mu. func (conn *Conn) enableWgWatcherIfNeeded(enabledTime time.Time) { - if !conn.wgWatcher.PrepareInitialHandshake() { + if conn.wgWatcher != nil { return } + watcher := NewWGWatcher(conn.Log, conn.config.WgConfig.WgInterface, conn.config.Key, conn.dumpState) + watcher.PrepareInitialHandshake() + wgWatcherCtx, wgWatcherCancel := context.WithCancel(conn.ctx) + conn.wgWatcher = watcher conn.wgWatcherCancel = wgWatcherCancel + conn.wgWatcherWg.Add(1) go func() { defer conn.wgWatcherWg.Done() - conn.wgWatcher.EnableWgWatcher(wgWatcherCtx, enabledTime, conn.onWGDisconnected, conn.onWGHandshakeSuccess) + onDisconnected := func() { conn.onWGDisconnected(wgWatcherCtx) } + watcher.EnableWgWatcher(wgWatcherCtx, enabledTime, onDisconnected, conn.onWGHandshakeSuccess, conn.onWGCheckSuccess) }() } +// disableWgWatcherIfNeeded cancels and drops the watcher once no transport is active. It never +// waits for the goroutine: the timeout path reentrantly calls back here under conn.mu, so +// blocking would deadlock. Caller must hold conn.mu. func (conn *Conn) disableWgWatcherIfNeeded() { - if conn.currentConnPriority == conntype.None && conn.wgWatcherCancel != nil { - conn.wgWatcherCancel() - conn.wgWatcherCancel = nil + if conn.currentConnPriority != conntype.None || conn.wgWatcher == nil { + return } + conn.wgWatcherCancel() + conn.wgWatcher = nil + conn.wgWatcherCancel = nil } func (conn *Conn) newProxy(remoteConn net.Conn) (wgproxy.Proxy, error) { @@ -843,7 +888,9 @@ func (conn *Conn) resetEndpoint() { return } conn.Log.Infof("reset wg endpoint") - conn.wgWatcher.Reset() + if conn.wgWatcher != nil { + conn.wgWatcher.Reset() + } if err := conn.endpointUpdater.RemoveEndpointAddress(); err != nil { conn.Log.Warnf("failed to remove endpoint address before update: %v", err) } @@ -892,6 +939,15 @@ func (conn *Conn) onWGHandshakeSuccess(when time.Time) { conn.recordConnectionMetrics() } +// onWGCheckSuccess is called for every watcher check that observed a fresh +// handshake, including handshakes of connections that were already up when +// the watcher started. +func (conn *Conn) onWGCheckSuccess() { + conn.mu.Lock() + conn.wgTimeouts = 0 + conn.mu.Unlock() +} + // recordConnectionMetrics records connection stage timestamps as metrics func (conn *Conn) recordConnectionMetrics() { if conn.metricsRecorder == nil { diff --git a/client/internal/peer/conn_test.go b/client/internal/peer/conn_test.go index 59216b647..49979ea83 100644 --- a/client/internal/peer/conn_test.go +++ b/client/internal/peer/conn_test.go @@ -7,6 +7,7 @@ import ( "testing" "time" + log "github.com/sirupsen/logrus" "github.com/stretchr/testify/assert" "github.com/netbirdio/netbird/client/iface" @@ -304,3 +305,84 @@ func TestConn_presharedKey_RosenpassManaged(t *testing.T) { t.Fatalf("expected non-nil presharedKey before Rosenpass manages PSK") } } + +func newWGTimeoutTestConn(rosenpassEnabled bool, disconnected *[]string) *Conn { + cfg := ConnConfig{ + Key: "LLHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=", + LocalKey: "RRHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=", + WgConfig: WgConfig{RemoteKey: "LLHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU="}, + } + if rosenpassEnabled { + cfg.RosenpassConfig = RosenpassConfig{PubKey: []byte("dummykey")} + } + + conn := &Conn{ + ctx: context.Background(), + config: cfg, + Log: log.WithField("peer", cfg.Key), + metricsStages: &MetricsStages{}, + } + conn.SetOnDisconnected(func(remotePeer string) { + *disconnected = append(*disconnected, remotePeer) + }) + return conn +} + +// TestConn_onWGDisconnected_EscalatesToRosenpassReset: repeated handshake +// timeouts with rosenpass enabled mean the preshared keys have desynced. The +// renewal exchange runs over the dead tunnel and cannot resync them, so after +// wgTimeoutEscalationThreshold consecutive timeouts the conn must report the +// peer disconnected, dropping its rosenpass state so the next configuration +// programs the rendezvous key. +func TestConn_onWGDisconnected_EscalatesToRosenpassReset(t *testing.T) { + var disconnected []string + conn := newWGTimeoutTestConn(true, &disconnected) + + for i := 0; i < wgTimeoutEscalationThreshold-1; i++ { + conn.onWGDisconnected(conn.ctx) + } + assert.Empty(t, disconnected, "escalation must not fire below the threshold") + + conn.onWGDisconnected(conn.ctx) + assert.Equal(t, []string{conn.config.WgConfig.RemoteKey}, disconnected, + "reaching the threshold must report the peer disconnected once") + + for i := 0; i < wgTimeoutEscalationThreshold-1; i++ { + conn.onWGDisconnected(conn.ctx) + } + assert.Len(t, disconnected, 1, "escalation must restart counting after firing") + + conn.onWGDisconnected(conn.ctx) + assert.Len(t, disconnected, 2, "continued timeouts must escalate again") +} + +// TestConn_onWGDisconnected_CheckSuccessResetsEscalation: a successful +// handshake between timeouts means the tunnel recovered; the counter must +// start over. +func TestConn_onWGDisconnected_CheckSuccessResetsEscalation(t *testing.T) { + var disconnected []string + conn := newWGTimeoutTestConn(true, &disconnected) + + for i := 0; i < wgTimeoutEscalationThreshold-1; i++ { + conn.onWGDisconnected(conn.ctx) + } + conn.onWGCheckSuccess() + + for i := 0; i < wgTimeoutEscalationThreshold-1; i++ { + conn.onWGDisconnected(conn.ctx) + } + assert.Empty(t, disconnected, "handshake success must reset the timeout count") +} + +// TestConn_onWGDisconnected_NoEscalationWithoutRosenpass: without rosenpass +// there is no per-peer key state to reset; repeated timeouts must not report +// disconnects. +func TestConn_onWGDisconnected_NoEscalationWithoutRosenpass(t *testing.T) { + var disconnected []string + conn := newWGTimeoutTestConn(false, &disconnected) + + for i := 0; i < wgTimeoutEscalationThreshold*3; i++ { + conn.onWGDisconnected(conn.ctx) + } + assert.Empty(t, disconnected, "escalation must be limited to rosenpass connections") +} diff --git a/client/internal/peer/status.go b/client/internal/peer/status.go index a987482fe..423ce9b23 100644 --- a/client/internal/peer/status.go +++ b/client/internal/peer/status.go @@ -813,19 +813,14 @@ func (d *Status) SetSessionExpiresAt(deadline time.Time) { } // GetSessionExpiresAt returns the most recently recorded SSO session deadline, -// or the zero value when no deadline is tracked. A deadline that has already -// slipped into the past reports as "none": once the session has expired it is -// no longer a meaningful countdown, and the sessionwatch.Watcher does not -// arm a timer at the deadline itself to clear it (only the two pre-expiry -// warnings). Without this guard the UI would keep painting a stale -// "expires in …" against a moment that has passed until the next login, -// extend, or teardown rewrote the value. +// or the zero value when no deadline is tracked. A deadline in the past is +// returned as-is: it means the session has expired, and consumers (tray row, +// CLI status) render it as "expired" rather than hiding it — masking it as +// "none" would blank the UI at the exact moment it should say the session +// ended. func (d *Status) GetSessionExpiresAt() time.Time { d.mux.Lock() defer d.mux.Unlock() - if !d.sessionExpiresAt.IsZero() && d.sessionExpiresAt.Before(time.Now()) { - return time.Time{} - } return d.sessionExpiresAt } diff --git a/client/internal/peer/wg_watcher.go b/client/internal/peer/wg_watcher.go index 4fc883d17..39e3d3264 100644 --- a/client/internal/peer/wg_watcher.go +++ b/client/internal/peer/wg_watcher.go @@ -3,7 +3,6 @@ package peer import ( "context" "fmt" - "sync" "time" log "github.com/sirupsen/logrus" @@ -24,14 +23,14 @@ type WGInterfaceStater interface { GetStats() (map[string]configurer.WGStats, error) } +// WGWatcher is single-shot: one instance per connection attempt, run once, then discarded. +// Lifecycle is owned by Conn under conn.mu, so it keeps no "enabled" state to go stale. type WGWatcher struct { log *log.Entry wgIfaceStater WGInterfaceStater peerKey string stateDump *stateDump - enabled bool - muEnabled sync.Mutex // initialHandshake is not thread-safe; never call PrepareInitialHandshake and EnableWgWatcher concurrently. initialHandshake time.Time @@ -48,36 +47,23 @@ func NewWGWatcher(log *log.Entry, wgIfaceStater WGInterfaceStater, peerKey strin } } -// PrepareInitialHandshake reserves the watcher and reads the peer's current WireGuard -// handshake time. It must be called before the peer is (re)configured on the WireGuard -// interface, so the captured baseline reflects the state prior to this connection attempt -// instead of racing with that configuration. Returns ok=false if the watcher is already -// running, in which case EnableWgWatcher must not be called. -func (w *WGWatcher) PrepareInitialHandshake() (ok bool) { - w.muEnabled.Lock() - if w.enabled { - w.muEnabled.Unlock() - return false - } - +// PrepareInitialHandshake reads the peer's current WireGuard handshake time. It must be +// called before the peer is (re)configured on the WireGuard interface, so the captured +// baseline reflects the state prior to this connection attempt instead of racing with +// that configuration. +func (w *WGWatcher) PrepareInitialHandshake() { w.log.Debugf("enable WireGuard watcher") - w.enabled = true - w.muEnabled.Unlock() - handshake, _ := w.wgState() w.initialHandshake = handshake - return true } // EnableWgWatcher runs the WireGuard watcher loop using the handshake baseline captured by // PrepareInitialHandshake. The watcher runs until ctx is cancelled. Caller is responsible -// for context lifecycle management. -func (w *WGWatcher) EnableWgWatcher(ctx context.Context, enabledTime time.Time, onDisconnectedFn func(), onHandshakeSuccessFn func(when time.Time)) { - w.periodicHandshakeCheck(ctx, onDisconnectedFn, onHandshakeSuccessFn, enabledTime, w.initialHandshake) - - w.muEnabled.Lock() - w.enabled = false - w.muEnabled.Unlock() +// for context lifecycle management. onHandshakeSuccessFn is called only for the first +// handshake observed by this run, onCheckSuccessFn for every check that observed a fresh +// handshake, including the first. +func (w *WGWatcher) EnableWgWatcher(ctx context.Context, enabledTime time.Time, onDisconnectedFn func(), onHandshakeSuccessFn func(when time.Time), onCheckSuccessFn func()) { + w.periodicHandshakeCheck(ctx, onDisconnectedFn, onHandshakeSuccessFn, onCheckSuccessFn, enabledTime, w.initialHandshake) } // Reset signals the watcher that the WireGuard peer has been reset and a new @@ -90,7 +76,7 @@ func (w *WGWatcher) Reset() { } // wgStateCheck help to check the state of the WireGuard handshake and relay connection -func (w *WGWatcher) periodicHandshakeCheck(ctx context.Context, onDisconnectedFn func(), onHandshakeSuccessFn func(when time.Time), enabledTime time.Time, initialHandshake time.Time) { +func (w *WGWatcher) periodicHandshakeCheck(ctx context.Context, onDisconnectedFn func(), onHandshakeSuccessFn func(when time.Time), onCheckSuccessFn func(), enabledTime time.Time, initialHandshake time.Time) { w.log.Infof("WireGuard watcher started") timer := time.NewTimer(wgHandshakeOvertime) @@ -103,6 +89,7 @@ func (w *WGWatcher) periodicHandshakeCheck(ctx context.Context, onDisconnectedFn case <-timer.C: handshake, ok := w.handshakeCheck(lastHandshake) if !ok { + // early ctx cancel check return if ctx.Err() != nil { return } @@ -117,6 +104,10 @@ func (w *WGWatcher) periodicHandshakeCheck(ctx context.Context, onDisconnectedFn } } + if onCheckSuccessFn != nil && ctx.Err() == nil { + onCheckSuccessFn() + } + lastHandshake = *handshake resetTime := time.Until(handshake.Add(checkPeriod)) @@ -147,9 +138,9 @@ func (w *WGWatcher) handshakeCheck(lastHandshake time.Time) (*time.Time, bool) { w.log.Tracef("previous handshake, handshake: %v, %v", lastHandshake, handshake) - // the current know handshake did not change + // the current known handshake did not change if handshake.Equal(lastHandshake) { - w.log.Warnf("WireGuard handshake timed out: %v", handshake) + w.log.Warnf("WireGuard handshake not updated: %v", handshake) return nil, false } diff --git a/client/internal/peer/wg_watcher_test.go b/client/internal/peer/wg_watcher_test.go index 634d7974f..6a5a9acfe 100644 --- a/client/internal/peer/wg_watcher_test.go +++ b/client/internal/peer/wg_watcher_test.go @@ -7,7 +7,6 @@ import ( "time" log "github.com/sirupsen/logrus" - "github.com/stretchr/testify/require" "github.com/netbirdio/netbird/client/iface/configurer" ) @@ -24,6 +23,72 @@ func (m *MocWgIface) disconnect() { m.stop = true } +type mockHandshakeStats struct { + mu sync.Mutex + handshake time.Time +} + +func (m *mockHandshakeStats) GetStats() (map[string]configurer.WGStats, error) { + m.mu.Lock() + defer m.mu.Unlock() + return map[string]configurer.WGStats{"": {LastHandshake: m.handshake}}, nil +} + +func (m *mockHandshakeStats) advance() { + m.mu.Lock() + defer m.mu.Unlock() + m.handshake = time.Now() +} + +// TestWGWatcher_CheckSuccessCallback: onCheckSuccessFn must fire for a fresh +// handshake even when the watcher started with an existing handshake baseline, +// the case where onHandshakeSuccessFn stays silent. +func TestWGWatcher_CheckSuccessCallback(t *testing.T) { + // checkPeriod bounds how stale a handshake may be before the watcher treats it + // as a suspended-machine timeout. The first check fires after wgHandshakeOvertime, + // so keep checkPeriod well above any scheduling jitter to avoid a false timeout + // converting the expected success into a disconnect on a loaded runner. + checkPeriod = 1 * time.Minute + wgHandshakeOvertime = 1 * time.Second + + mlog := log.WithField("peer", "tet") + // Use an old baseline so advance() yields a strictly newer handshake even on + // platforms with coarse clock resolution (Windows), where two time.Now() calls + // microseconds apart can return the same instant and read as a timed-out handshake. + stats := &mockHandshakeStats{handshake: time.Now().Add(-time.Hour)} + watcher := NewWGWatcher(mlog, stats, "", newStateDump("peer", mlog, &Status{})) + + ctx, cancel := context.WithCancel(context.Background()) + defer cancel() + + watcher.PrepareInitialHandshake() + + firstHandshake := make(chan struct{}, 1) + checkSuccess := make(chan struct{}, 1) + go watcher.EnableWgWatcher(ctx, time.Now(), func() {}, func(when time.Time) { + firstHandshake <- struct{}{} + }, func() { + select { + case checkSuccess <- struct{}{}: + default: + } + }) + + stats.advance() + + select { + case <-checkSuccess: + case <-time.After(10 * time.Second): + t.Errorf("timeout waiting for check success callback") + } + + select { + case <-firstHandshake: + t.Errorf("first-handshake callback must not fire for a non-zero baseline") + default: + } +} + func TestWGWatcher_EnableWgWatcher(t *testing.T) { checkPeriod = 5 * time.Second wgHandshakeOvertime = 1 * time.Second @@ -35,8 +100,7 @@ func TestWGWatcher_EnableWgWatcher(t *testing.T) { ctx, cancel := context.WithCancel(context.Background()) defer cancel() - ok := watcher.PrepareInitialHandshake() - require.True(t, ok, "watcher should not be enabled yet") + watcher.PrepareInitialHandshake() onDisconnected := make(chan struct{}, 1) go watcher.EnableWgWatcher(ctx, time.Now(), func() { @@ -44,7 +108,7 @@ func TestWGWatcher_EnableWgWatcher(t *testing.T) { onDisconnected <- struct{}{} }, func(when time.Time) { mlog.Infof("onHandshakeSuccess: %v", when) - }) + }, nil) // wait for initial reading time.Sleep(2 * time.Second) @@ -66,14 +130,13 @@ func TestWGWatcher_ReEnable(t *testing.T) { watcher := NewWGWatcher(mlog, mocWgIface, "", newStateDump("peer", mlog, &Status{})) ctx, cancel := context.WithCancel(context.Background()) - ok := watcher.PrepareInitialHandshake() - require.True(t, ok, "watcher should not be enabled yet") + watcher.PrepareInitialHandshake() wg := &sync.WaitGroup{} wg.Add(1) go func() { defer wg.Done() - watcher.EnableWgWatcher(ctx, time.Now(), func() {}, func(when time.Time) {}) + watcher.EnableWgWatcher(ctx, time.Now(), func() {}, func(when time.Time) {}, nil) }() cancel() @@ -83,13 +146,12 @@ func TestWGWatcher_ReEnable(t *testing.T) { ctx, cancel = context.WithCancel(context.Background()) defer cancel() - ok = watcher.PrepareInitialHandshake() - require.True(t, ok, "watcher should be re-enabled after the previous run stopped") + watcher.PrepareInitialHandshake() onDisconnected := make(chan struct{}, 1) go watcher.EnableWgWatcher(ctx, time.Now(), func() { onDisconnected <- struct{}{} - }, func(when time.Time) {}) + }, func(when time.Time) {}, nil) time.Sleep(2 * time.Second) mocWgIface.disconnect() diff --git a/client/internal/profilemanager/config.go b/client/internal/profilemanager/config.go index ed2f21999..e1668238e 100644 --- a/client/internal/profilemanager/config.go +++ b/client/internal/profilemanager/config.go @@ -96,6 +96,7 @@ type ConfigInput struct { BlockLANAccess *bool BlockInbound *bool DisableIPv6 *bool + SyncMessageVersion *int DisableNotifications *bool @@ -137,6 +138,7 @@ type Config struct { BlockLANAccess bool BlockInbound bool DisableIPv6 bool + SyncMessageVersion *int DisableNotifications *bool @@ -587,6 +589,12 @@ func (config *Config) apply(input ConfigInput) (updated bool, err error) { updated = true } + if input.SyncMessageVersion != nil && *input.SyncMessageVersion != *config.SyncMessageVersion { + log.Infof("setting SyncMessageVersion to %v", *input.SyncMessageVersion) + *config.SyncMessageVersion = *input.SyncMessageVersion + updated = true + } + if input.DisableNotifications != nil && (config.DisableNotifications == nil || *input.DisableNotifications != *config.DisableNotifications) { if *input.DisableNotifications { log.Infof("disabling notifications") @@ -738,6 +746,13 @@ func (config *Config) applyMDMPolicy(policy *mdm.Policy) { // appended for https or ":80" for http. The serviceName parameter is // used to contextualise error messages. On success returns the parsed // *url.URL; on failure returns a non-nil error. +// ParseServiceURL normalises a service URL exactly as the config layer does when +// it stores one, so callers comparing a requested URL against a stored one do not +// have to reimplement the scheme validation and default-port handling. +func ParseServiceURL(serviceName, serviceURL string) (*url.URL, error) { + return parseURL(serviceName, serviceURL) +} + func parseURL(serviceName, serviceURL string) (*url.URL, error) { parsedMgmtURL, err := url.ParseRequestURI(serviceURL) if err != nil { diff --git a/client/internal/profilemanager/service.go b/client/internal/profilemanager/service.go index 5ddd11b04..696a60310 100644 --- a/client/internal/profilemanager/service.go +++ b/client/internal/profilemanager/service.go @@ -11,6 +11,7 @@ import ( "runtime" "sort" "strings" + "syscall" log "github.com/sirupsen/logrus" @@ -439,7 +440,11 @@ func (s *ServiceManager) GetStatePath() string { activeProf, err := s.GetActiveProfileState() if err != nil { - log.Warnf("failed to get active profile state: %v", err) + if errors.Is(err, syscall.ENOSYS) { + log.Debugf("active profile state unavailable on this platform: %v", err) + } else { + log.Warnf("failed to get active profile state: %v", err) + } return defaultStatePath } diff --git a/client/internal/rosenpass/manager.go b/client/internal/rosenpass/manager.go index 903753753..21dd751df 100644 --- a/client/internal/rosenpass/manager.go +++ b/client/internal/rosenpass/manager.go @@ -39,6 +39,7 @@ type rpServer interface { type Manager struct { ifaceName string + localWgKey wgtypes.Key spk []byte ssk []byte rpKeyHash string @@ -51,8 +52,9 @@ type Manager struct { wgIface PresharedKeySetter } -// NewManager creates a new Rosenpass manager -func NewManager(preSharedKey *wgtypes.Key, wgIfaceName string) (*Manager, error) { +// NewManager creates a new Rosenpass manager. localWgKey is the local +// WireGuard public key, used to derive the per-peer rendezvous key. +func NewManager(preSharedKey *wgtypes.Key, wgIfaceName string, localWgKey wgtypes.Key) (*Manager, error) { public, secret, err := rp.GenerateKeyPair() if err != nil { return nil, err @@ -62,6 +64,7 @@ func NewManager(preSharedKey *wgtypes.Key, wgIfaceName string) (*Manager, error) log.Tracef("generated new rosenpass key pair with public key %s", rpKeyHash) return &Manager{ ifaceName: wgIfaceName, + localWgKey: localWgKey, rpKeyHash: rpKeyHash, spk: public, ssk: secret, @@ -73,7 +76,7 @@ func NewManager(preSharedKey *wgtypes.Key, wgIfaceName string) (*Manager, error) // nil receiver in addPeer -> m.rpWgHandler.AddPeer. generateConfig will // replace it with a fresh handler on each Run() to clear stale peer // state from previous engine sessions. - rpWgHandler: NewNetbirdHandler(), + rpWgHandler: NewNetbirdHandler((*[32]byte)(preSharedKey), localWgKey), lock: sync.Mutex{}, }, nil } @@ -161,7 +164,7 @@ func (m *Manager) generateConfig() (rp.Config, error) { cfg.Peers = []rp.PeerConfig{} m.lock.Lock() - m.rpWgHandler = NewNetbirdHandler() + m.rpWgHandler = NewNetbirdHandler(m.preSharedKey, m.localWgKey) if m.wgIface != nil { m.rpWgHandler.SetInterface(m.wgIface) } diff --git a/client/internal/rosenpass/manager_test.go b/client/internal/rosenpass/manager_test.go index d74960d0d..69e18ac88 100644 --- a/client/internal/rosenpass/manager_test.go +++ b/client/internal/rosenpass/manager_test.go @@ -85,7 +85,7 @@ func newTestManager(spkFirstByte byte, mock *mockServer) *Manager { ssk: make([]byte, 32), rpKeyHash: "test-hash", rpPeerIDs: make(map[string]*rp.PeerID), - rpWgHandler: NewNetbirdHandler(), + rpWgHandler: NewNetbirdHandler(nil, wgtypes.Key{0x01}), server: mock, } } @@ -255,7 +255,7 @@ func TestAddPeer_NilServer_ReturnsErrorNoCrash(t *testing.T) { // issue #4341 cannot occur in the window between NewManager and Run(). func TestNewManager_PreInitializesHandler(t *testing.T) { psk := wgtypes.Key{} - m, err := NewManager(&psk, "wt0") + m, err := NewManager(&psk, "wt0", wgtypes.Key{0x01}) require.NoError(t, err) require.NotNil(t, m.rpWgHandler, "rpWgHandler must be initialized in NewManager") } @@ -329,10 +329,10 @@ func TestIsPresharedKeyInitialized_AddedButNotHandshaken_ReturnsFalse(t *testing require.False(t, m.IsPresharedKeyInitialized(wgKey)) } -// --- NetbirdHandler.outputKey ---------------------------------------------- +// --- NetbirdHandler.applyKey ---------------------------------------------- -func TestHandler_OutputKey_FirstCallUsesUpdateOnlyFalse(t *testing.T) { - h := NewNetbirdHandler() +func TestHandler_ApplyKey_FirstCallUsesUpdateOnlyFalse(t *testing.T) { + h := NewNetbirdHandler(nil, wgtypes.Key{0x01}) iface := &mockIface{} h.SetInterface(iface) @@ -348,8 +348,8 @@ func TestHandler_OutputKey_FirstCallUsesUpdateOnlyFalse(t *testing.T) { require.Equal(t, wgKey.String(), iface.calls[0].peerKey) } -func TestHandler_OutputKey_SubsequentCallsUseUpdateOnlyTrue(t *testing.T) { - h := NewNetbirdHandler() +func TestHandler_ApplyKey_SubsequentCallsUseUpdateOnlyTrue(t *testing.T) { + h := NewNetbirdHandler(nil, wgtypes.Key{0x01}) iface := &mockIface{} h.SetInterface(iface) @@ -364,8 +364,8 @@ func TestHandler_OutputKey_SubsequentCallsUseUpdateOnlyTrue(t *testing.T) { require.True(t, iface.calls[1].updateOnly, "subsequent rotations must use updateOnly=true") } -func TestHandler_OutputKey_NilInterface_NoCrashNoCall(t *testing.T) { - h := NewNetbirdHandler() +func TestHandler_ApplyKey_NilInterface_NoCrashNoCall(t *testing.T) { + h := NewNetbirdHandler(nil, wgtypes.Key{0x01}) // no SetInterface — iface remains nil pid := rp.PeerID{0x03} h.AddPeer(pid, "wt0", rp.Key(wgtypes.Key{})) @@ -374,8 +374,8 @@ func TestHandler_OutputKey_NilInterface_NoCrashNoCall(t *testing.T) { h.HandshakeCompleted(pid, rp.Key{}) } -func TestHandler_OutputKey_UnknownPeer_NoCall(t *testing.T) { - h := NewNetbirdHandler() +func TestHandler_ApplyKey_UnknownPeer_NoCall(t *testing.T) { + h := NewNetbirdHandler(nil, wgtypes.Key{0x01}) iface := &mockIface{} h.SetInterface(iface) @@ -384,7 +384,7 @@ func TestHandler_OutputKey_UnknownPeer_NoCall(t *testing.T) { } func TestHandler_RemovePeer_ClearsInitializedState(t *testing.T) { - h := NewNetbirdHandler() + h := NewNetbirdHandler(nil, wgtypes.Key{0x01}) iface := &mockIface{} h.SetInterface(iface) @@ -398,7 +398,7 @@ func TestHandler_RemovePeer_ClearsInitializedState(t *testing.T) { } func TestHandler_SetInterfaceAfterAddPeer_StillReceivesKey(t *testing.T) { - h := NewNetbirdHandler() + h := NewNetbirdHandler(nil, wgtypes.Key{0x01}) pid := rp.PeerID{0x05} wgKey := wgtypes.Key{0xEE} h.AddPeer(pid, "wt0", rp.Key(wgKey)) diff --git a/client/internal/rosenpass/netbird_handler.go b/client/internal/rosenpass/netbird_handler.go index 9de2409ef..672650ca7 100644 --- a/client/internal/rosenpass/netbird_handler.go +++ b/client/internal/rosenpass/netbird_handler.go @@ -18,19 +18,34 @@ type PresharedKeySetter interface { type wireGuardPeer struct { Interface string PublicKey rp.Key + // initialized is true once a completed exchange has set a + // Rosenpass-managed PSK for this peer. + initialized bool + // chainKey is the key output by the last completed exchange, advanced by + // one ratchet step on expiry. Nil until the first exchange completes and + // after the peer has fallen back to the rendezvous key. + chainKey *wgtypes.Key + // expiries counts failed renewals since the last completed exchange. + expiries int } type NetbirdHandler struct { - mu sync.Mutex - iface PresharedKeySetter - peers map[rp.PeerID]wireGuardPeer - initializedPeers map[rp.PeerID]bool + mu sync.Mutex + iface PresharedKeySetter + // preSharedKey is the account-level preshared key, used as the rendezvous + // key when set. Nil means the deterministic seed key is used instead. + preSharedKey *[32]byte + // localWgKey is the local WireGuard public key, one of the two inputs to + // the deterministic seed key. + localWgKey wgtypes.Key + peers map[rp.PeerID]*wireGuardPeer } -func NewNetbirdHandler() *NetbirdHandler { +func NewNetbirdHandler(preSharedKey *[32]byte, localWgKey wgtypes.Key) *NetbirdHandler { return &NetbirdHandler{ - peers: map[rp.PeerID]wireGuardPeer{}, - initializedPeers: map[rp.PeerID]bool{}, + preSharedKey: preSharedKey, + localWgKey: localWgKey, + peers: map[rp.PeerID]*wireGuardPeer{}, } } @@ -42,10 +57,16 @@ func (h *NetbirdHandler) SetInterface(iface PresharedKeySetter) { h.iface = iface } +// AddPeer registers a peer with the handler. Re-adding a known peer (every +// reconnection does) keeps its key recovery state. func (h *NetbirdHandler) AddPeer(pid rp.PeerID, intf string, pk rp.Key) { h.mu.Lock() defer h.mu.Unlock() - h.peers[pid] = wireGuardPeer{ + if existing, ok := h.peers[pid]; ok && existing.PublicKey == pk { + existing.Interface = intf + return + } + h.peers[pid] = &wireGuardPeer{ Interface: intf, PublicKey: pk, } @@ -55,7 +76,6 @@ func (h *NetbirdHandler) RemovePeer(pid rp.PeerID) { h.mu.Lock() defer h.mu.Unlock() delete(h.peers, pid) - delete(h.initializedPeers, pid) } // IsPeerInitialized returns true if Rosenpass has completed a handshake @@ -63,50 +83,120 @@ func (h *NetbirdHandler) RemovePeer(pid rp.PeerID) { func (h *NetbirdHandler) IsPeerInitialized(pid rp.PeerID) bool { h.mu.Lock() defer h.mu.Unlock() - return h.initializedPeers[pid] + peer, ok := h.peers[pid] + return ok && peer.initialized } +// HandshakeCompleted programs the freshly exchanged output key and resets the +// peer's key recovery state. func (h *NetbirdHandler) HandshakeCompleted(pid rp.PeerID, key rp.Key) { - h.outputKey(rp.KeyOutputReasonStale, pid, key) -} + psk := wgtypes.Key(key) -func (h *NetbirdHandler) HandshakeExpired(pid rp.PeerID) { - key, _ := rp.GeneratePresharedKey() - h.outputKey(rp.KeyOutputReasonStale, pid, key) -} - -func (h *NetbirdHandler) outputKey(_ rp.KeyOutputReason, pid rp.PeerID, psk rp.Key) { h.mu.Lock() - iface := h.iface - wg, ok := h.peers[pid] - isInitialized := h.initializedPeers[pid] - h.mu.Unlock() + defer h.mu.Unlock() - if iface == nil { - log.Warn("rosenpass: interface not set, cannot update preshared key") + peer, ok := h.peers[pid] + if !ok { return } + if peer.expiries > 0 { + log.Infof("rosenpass exchange completed for peer %s after %d expired renewals", wgtypes.Key(peer.PublicKey), peer.expiries) + } + // chainKey tracks the shared exchange output regardless of the local write + // outcome, so both ends still converge on the next expiry. + peer.chainKey = &psk + peer.expiries = 0 + if !h.applyKeyLocked(pid, psk, peer.initialized) { + return + } + peer.initialized = true +} +// HandshakeExpired replaces the expired key. The renewal exchange runs over +// the tunnel keyed by the PSK itself, so the replacement must be derivable on +// both ends without communication: the first expiry ratchets the last shared +// key forward, repeated expiries (and expiries without a completed exchange) +// fall back to the rendezvous key and drop the peer out of the initialized +// state so connection reconfigurations reprogram the rendezvous key as well. +func (h *NetbirdHandler) HandshakeExpired(pid rp.PeerID) { + h.mu.Lock() + defer h.mu.Unlock() + + peer, ok := h.peers[pid] if !ok { return } - peerKey := wgtypes.Key(wg.PublicKey).String() - pskKey := wgtypes.Key(psk) + peer.expiries++ - // Use updateOnly=true for later rotations (peer already has Rosenpass PSK) - // Use updateOnly=false for first rotation (peer has original/empty PSK) - if err := iface.SetPresharedKey(peerKey, pskKey, isInitialized); err != nil { + var psk wgtypes.Key + if peer.chainKey != nil && peer.expiries == 1 { + log.Infof("rosenpass key for peer %s expired without renewal, advancing to ratcheted key", wgtypes.Key(peer.PublicKey)) + psk = RatchetKey(*peer.chainKey) + peer.chainKey = &psk + } else { + rendezvous, err := h.rendezvousKey(peer) + if err != nil { + // Fail closed: without a rendezvous key the expired key must + // still be rotated out, even if the replacement is unusable. + log.Errorf("failed to derive rendezvous key, replacing expired key with a random one: %v", err) + h.applyRandomKeyLocked(pid) + return + } + log.Warnf("rosenpass key for peer %s expired %d times without renewal, falling back to the rendezvous key", wgtypes.Key(peer.PublicKey), peer.expiries) + psk = rendezvous + peer.chainKey = nil + peer.initialized = false + } + + h.applyKeyLocked(pid, psk, true) +} + +// rendezvousKey returns the key both ends converge on without communication: +// the account-level preshared key when configured, the deterministic seed key +// otherwise. It mirrors the key that peer connections program when Rosenpass +// does not manage the peer yet. +func (h *NetbirdHandler) rendezvousKey(peer *wireGuardPeer) (wgtypes.Key, error) { + if h.preSharedKey != nil { + return *h.preSharedKey, nil + } + + seed, err := DeterministicSeedKey(h.localWgKey.String(), wgtypes.Key(peer.PublicKey).String()) + if err != nil { + return wgtypes.Key{}, err + } + return *seed, nil +} + +// applyKeyLocked writes the preshared key for the peer to the WireGuard +// interface and reports whether the write succeeded. Callers must hold h.mu +// for the whole state-mutation-plus-write so that a concurrent completion and +// expiry cannot reorder their writes relative to the in-memory chain key. +func (h *NetbirdHandler) applyKeyLocked(pid rp.PeerID, psk wgtypes.Key, updateOnly bool) bool { + peer, ok := h.peers[pid] + if !ok { + return false + } + + if h.iface == nil { + log.Warn("rosenpass: interface not set, cannot update preshared key") + return false + } + + peerKey := wgtypes.Key(peer.PublicKey).String() + if err := h.iface.SetPresharedKey(peerKey, psk, updateOnly); err != nil { log.Errorf("Failed to apply rosenpass key: %v", err) + return false + } + + return true +} + +func (h *NetbirdHandler) applyRandomKeyLocked(pid rp.PeerID) { + key, err := rp.GeneratePresharedKey() + if err != nil { + log.Errorf("failed to generate random preshared key: %v", err) return } - - // Mark peer as isInitialized after the successful first rotation - if !isInitialized { - h.mu.Lock() - if _, exists := h.peers[pid]; exists { - h.initializedPeers[pid] = true - } - h.mu.Unlock() - } + h.applyKeyLocked(pid, wgtypes.Key(key), true) } diff --git a/client/internal/rosenpass/netbird_handler_test.go b/client/internal/rosenpass/netbird_handler_test.go new file mode 100644 index 000000000..9d91ba93b --- /dev/null +++ b/client/internal/rosenpass/netbird_handler_test.go @@ -0,0 +1,250 @@ +package rosenpass + +import ( + "testing" + + rp "cunicu.li/go-rosenpass" + "github.com/stretchr/testify/require" + "golang.zx2c4.com/wireguard/wgctrl/wgtypes" +) + +// handlerTestLink wires two NetbirdHandlers as the two ends of a single +// tunnel: handler A manages the rosenpass peer B and vice versa, the way two +// NetBird clients see each other. +type handlerTestLink struct { + handlerA, handlerB *NetbirdHandler + ifaceA, ifaceB *mockIface + pidA, pidB rp.PeerID + wgKeyA, wgKeyB wgtypes.Key +} + +func newHandlerTestLink(t *testing.T, preSharedKey *[32]byte) *handlerTestLink { + t.Helper() + + link := &handlerTestLink{ + ifaceA: &mockIface{}, + ifaceB: &mockIface{}, + } + link.pidA[0] = 0xaa + link.pidB[0] = 0xbb + link.wgKeyA[31] = 1 + link.wgKeyB[31] = 2 + + link.handlerA = NewNetbirdHandler(preSharedKey, link.wgKeyA) + link.handlerB = NewNetbirdHandler(preSharedKey, link.wgKeyB) + + link.handlerA.SetInterface(link.ifaceA) + link.handlerB.SetInterface(link.ifaceB) + + link.handlerA.AddPeer(link.pidB, "wt0", rp.Key(link.wgKeyB)) + link.handlerB.AddPeer(link.pidA, "wt0", rp.Key(link.wgKeyA)) + + return link +} + +// complete simulates a completed rosenpass exchange: both ends derive the +// same output key. +func (l *handlerTestLink) complete(osk rp.Key) { + l.handlerA.HandshakeCompleted(l.pidB, osk) + l.handlerB.HandshakeCompleted(l.pidA, osk) +} + +// expire simulates a failed key renewal on both ends. +func (l *handlerTestLink) expire() { + l.handlerA.HandshakeExpired(l.pidB) + l.handlerB.HandshakeExpired(l.pidA) +} + +func lastPSK(t *testing.T, m *mockIface) wgtypes.Key { + t.Helper() + m.mu.Lock() + defer m.mu.Unlock() + require.NotEmpty(t, m.calls, "expected at least one SetPresharedKey call") + return m.calls[len(m.calls)-1].psk +} + +func TestHandshakeCompleted_SetsKeyAndInitializes(t *testing.T) { + link := newHandlerTestLink(t, nil) + + var osk rp.Key + osk[0] = 0x42 + link.complete(osk) + + require.Equal(t, wgtypes.Key(osk), lastPSK(t, link.ifaceA), "completed exchange must program the osk") + require.False(t, link.ifaceA.calls[0].updateOnly, "first rotation must not be update-only") + require.True(t, link.handlerA.IsPeerInitialized(link.pidB), "peer must be initialized after first completed exchange") + + link.complete(osk) + require.True(t, link.ifaceA.calls[1].updateOnly, "later rotations must be update-only") +} + +// TestHandshakeExpired_BothSidesConverge encodes the core recovery invariant: +// rosenpass renewals run over the tunnel that the PSK itself keys, so when a +// renewal fails on both ends, both ends must fall back to the same key or the +// tunnel can never handshake again. +func TestHandshakeExpired_BothSidesConverge(t *testing.T) { + link := newHandlerTestLink(t, nil) + + var osk rp.Key + osk[0] = 0x42 + link.complete(osk) + + link.expire() + keyA := lastPSK(t, link.ifaceA) + keyB := lastPSK(t, link.ifaceB) + require.NotEqual(t, wgtypes.Key(osk), keyA, "expired key must be rotated out") + require.Equal(t, keyA, keyB, "both ends must converge on the same key after expiry") + + link.expire() + require.Equal(t, lastPSK(t, link.ifaceA), lastPSK(t, link.ifaceB), + "both ends must still converge after repeated expiries") +} + +// TestHandshakeExpired_ExpiryWithoutCompletionConverges covers the bootstrap +// case: the initial exchange never completed (the tunnel ran on the rendezvous +// key), so an expiry must not replace the working key with an unrecoverable +// one on either end. +func TestHandshakeExpired_ExpiryWithoutCompletionConverges(t *testing.T) { + link := newHandlerTestLink(t, nil) + + link.expire() + require.Equal(t, lastPSK(t, link.ifaceA), lastPSK(t, link.ifaceB), + "both ends must converge when the exchange never completed") +} + +// TestHandshakeExpired_RepeatedExpiryClearsInitialized: once renewals keep +// failing, the peer must drop out of the initialized state so the next +// connection reconfiguration reprograms the rendezvous key instead of +// preserving a poisoned rosenpass-managed key. +func TestHandshakeExpired_RepeatedExpiryClearsInitialized(t *testing.T) { + link := newHandlerTestLink(t, nil) + + var osk rp.Key + osk[0] = 0x42 + link.complete(osk) + + link.expire() + link.expire() + + require.False(t, link.handlerA.IsPeerInitialized(link.pidB), + "repeated expiries must clear the initialized state") + require.False(t, link.handlerB.IsPeerInitialized(link.pidA), + "repeated expiries must clear the initialized state") +} + +// TestHandshakeCompleted_AfterExpiryRecovers: a completed exchange after a +// desync must fully reset the recovery state. +func TestHandshakeCompleted_AfterExpiryRecovers(t *testing.T) { + link := newHandlerTestLink(t, nil) + + var osk1, osk2 rp.Key + osk1[0] = 1 + osk2[0] = 2 + + link.complete(osk1) + link.expire() + link.expire() + + link.complete(osk2) + require.Equal(t, wgtypes.Key(osk2), lastPSK(t, link.ifaceA), "new exchange must program the fresh osk") + require.True(t, link.handlerA.IsPeerInitialized(link.pidB), "peer must be initialized again after recovery") + + link.expire() + require.Equal(t, lastPSK(t, link.ifaceA), lastPSK(t, link.ifaceB), + "recovered link must converge again on the next expiry") + require.NotEqual(t, wgtypes.Key(osk2), lastPSK(t, link.ifaceA), "expired key must be rotated out") +} + +// TestHandshakeExpired_FirstExpiryRatchetsLastKey: the first expiry must +// derive the replacement from the last shared key, so an attacker who only +// blocks the renewal exchange gains nothing over the previous key. +func TestHandshakeExpired_FirstExpiryRatchetsLastKey(t *testing.T) { + link := newHandlerTestLink(t, nil) + + var osk rp.Key + osk[0] = 0x42 + link.complete(osk) + + link.expire() + require.Equal(t, RatchetKey(wgtypes.Key(osk)), lastPSK(t, link.ifaceA), + "first expiry must program the ratcheted key") + require.True(t, link.handlerA.IsPeerInitialized(link.pidB), + "ratchet step must keep the peer initialized so reconfigurations preserve the key") +} + +// TestHandshakeExpired_RepeatedExpiryFallsBackToSeed: once the ratchet key +// also fails, both ends must land on the same key that peer connections +// program for uninitialized peers, so a reconnect completes the recovery. +func TestHandshakeExpired_RepeatedExpiryFallsBackToSeed(t *testing.T) { + link := newHandlerTestLink(t, nil) + + var osk rp.Key + osk[0] = 0x42 + link.complete(osk) + + link.expire() + link.expire() + + seed, err := DeterministicSeedKey(link.wgKeyA.String(), link.wgKeyB.String()) + require.NoError(t, err) + require.Equal(t, *seed, lastPSK(t, link.ifaceA), "repeated expiry must fall back to the seed key") + require.Equal(t, *seed, lastPSK(t, link.ifaceB), "repeated expiry must fall back to the seed key") +} + +// TestHandshakeExpired_ConfiguredPSKUsedAsRendezvous: with an account-level +// preshared key configured, the fallback must be that key, matching what peer +// connections program for uninitialized peers. +func TestHandshakeExpired_ConfiguredPSKUsedAsRendezvous(t *testing.T) { + psk := &[32]byte{0x77} + link := newHandlerTestLink(t, psk) + + var osk rp.Key + osk[0] = 0x42 + link.complete(osk) + + link.expire() + link.expire() + + require.Equal(t, wgtypes.Key(*psk), lastPSK(t, link.ifaceA), + "fallback must be the configured preshared key") + require.Equal(t, wgtypes.Key(*psk), lastPSK(t, link.ifaceB), + "fallback must be the configured preshared key on both ends") +} + +// TestHandshakeExpired_ExpiryWritesAreUpdateOnly: expiry replacements must +// never create a WireGuard peer that connection management has removed. +func TestHandshakeExpired_ExpiryWritesAreUpdateOnly(t *testing.T) { + link := newHandlerTestLink(t, nil) + + var osk rp.Key + osk[0] = 0x42 + link.complete(osk) + + link.expire() + link.expire() + + for _, call := range link.ifaceA.calls[1:] { + require.True(t, call.updateOnly, "expiry writes must be update-only") + } +} + +// TestAddPeer_ReAddKeepsRecoveryState: reconnections re-add the peer on every +// OnConnected; that must not reset the expiry chain state. +func TestAddPeer_ReAddKeepsRecoveryState(t *testing.T) { + link := newHandlerTestLink(t, nil) + + var osk rp.Key + osk[0] = 0x42 + link.complete(osk) + link.expire() + + link.handlerA.AddPeer(link.pidB, "wt0", rp.Key(link.wgKeyB)) + require.True(t, link.handlerA.IsPeerInitialized(link.pidB), + "re-adding a known peer must keep its state") + + link.expire() + seed, err := DeterministicSeedKey(link.wgKeyA.String(), link.wgKeyB.String()) + require.NoError(t, err) + require.Equal(t, *seed, lastPSK(t, link.ifaceA), + "second expiry after re-add must continue to the seed fallback") +} diff --git a/client/internal/rosenpass/seed.go b/client/internal/rosenpass/seed.go index 83aba1e0e..052c11ed4 100644 --- a/client/internal/rosenpass/seed.go +++ b/client/internal/rosenpass/seed.go @@ -1,11 +1,28 @@ package rosenpass import ( + "crypto/sha256" "fmt" "golang.zx2c4.com/wireguard/wgctrl/wgtypes" ) +// ratchetLabel domain-separates the expiry ratchet from other uses of the +// rosenpass output key. +const ratchetLabel = "netbird-rosenpass-expiry-ratchet" + +// RatchetKey derives the successor preshared key from the previous Rosenpass +// output key. When a key expires without a completed renewal, both peers +// advance their last shared key by one ratchet step: the expired key is +// rotated out while both ends still converge on an identical, non-public +// replacement without communicating. +func RatchetKey(prev wgtypes.Key) wgtypes.Key { + input := make([]byte, 0, len(ratchetLabel)+len(prev)) + input = append(input, ratchetLabel...) + input = append(input, prev[:]...) + return sha256.Sum256(input) +} + // DeterministicSeedKey derives a 32-byte WireGuard preshared key from a pair // of peer public keys. Both peers, given the same key pair, produce the same // output regardless of which side runs the function: the inputs are ordered diff --git a/client/internal/routemanager/dnsinterceptor/handler.go b/client/internal/routemanager/dnsinterceptor/handler.go index b784cc274..f92300bfd 100644 --- a/client/internal/routemanager/dnsinterceptor/handler.go +++ b/client/internal/routemanager/dnsinterceptor/handler.go @@ -95,7 +95,7 @@ func (d *DnsInterceptor) RemoveRoute() error { // AllowedIPs should use real IPs if d.currentPeerKey != "" { - if _, err := d.allowedIPsRefcounter.Decrement(prefix); err != nil { + if _, err := d.allowedIPsRefcounter.Decrement(prefix, d.currentPeerKey); err != nil { merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %v", prefix, err)) } } @@ -172,7 +172,7 @@ func (d *DnsInterceptor) removeAllowedIP(realPrefix netip.Prefix) error { } // AllowedIPs use real IPs - if _, err := d.allowedIPsRefcounter.Decrement(realPrefix); err != nil { + if _, err := d.allowedIPsRefcounter.Decrement(realPrefix, d.currentPeerKey); err != nil { return fmt.Errorf("remove allowed IP %s: %v", realPrefix, err) } @@ -205,7 +205,7 @@ func (d *DnsInterceptor) RemoveAllowedIPs() error { for _, prefixes := range d.interceptedDomains { for _, prefix := range prefixes { // AllowedIPs use real IPs - if _, err := d.allowedIPsRefcounter.Decrement(prefix); err != nil { + if _, err := d.allowedIPsRefcounter.Decrement(prefix, d.currentPeerKey); err != nil { merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %v", prefix, err)) } } diff --git a/client/internal/routemanager/dynamic/route.go b/client/internal/routemanager/dynamic/route.go index f0efd7b22..bb3b1c59c 100644 --- a/client/internal/routemanager/dynamic/route.go +++ b/client/internal/routemanager/dynamic/route.go @@ -135,7 +135,7 @@ func (r *Route) RemoveAllowedIPs() error { var merr *multierror.Error for _, domainPrefixes := range r.dynamicDomains { for _, prefix := range domainPrefixes { - if _, err := r.allowedIPsRefcounter.Decrement(prefix); err != nil { + if _, err := r.allowedIPsRefcounter.Decrement(prefix, r.currentPeerKey); err != nil { merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %w", prefix, err)) } } @@ -185,7 +185,7 @@ func (r *Route) startResolver(ctx context.Context) { } func (r *Route) update(ctx context.Context) error { - resolved, err := r.resolveDomains() + resolved, err := r.resolveDomains(ctx) if err != nil { if len(resolved) == 0 { return fmt.Errorf("resolve domains: %w", err) @@ -199,9 +199,9 @@ func (r *Route) update(ctx context.Context) error { return nil } -func (r *Route) resolveDomains() (domainMap, error) { +func (r *Route) resolveDomains(ctx context.Context) (domainMap, error) { results := make(chan resolveResult) - go r.resolve(results) + go r.resolve(ctx, results) resolved := domainMap{} var merr *multierror.Error @@ -217,7 +217,7 @@ func (r *Route) resolveDomains() (domainMap, error) { return resolved, nberrors.FormatErrorOrNil(merr) } -func (r *Route) resolve(results chan resolveResult) { +func (r *Route) resolve(ctx context.Context, results chan resolveResult) { var wg sync.WaitGroup for _, d := range r.route.Domains { @@ -225,10 +225,10 @@ func (r *Route) resolve(results chan resolveResult) { go func(domain domain.Domain) { defer wg.Done() - ips, err := r.getIPsFromResolver(domain) + ips, err := r.getIPsFromResolver(ctx, domain) if err != nil { log.Tracef("Failed to resolve domain %s with private resolver: %v", domain.SafeString(), err) - ips, err = net.LookupIP(domain.PunycodeString()) + ips, err = lookupHostIPs(ctx, domain) if err != nil { results <- resolveResult{domain: domain, err: fmt.Errorf("resolve d %s: %w", domain.SafeString(), err)} return @@ -320,7 +320,7 @@ func (r *Route) removeRoutes(prefixes []netip.Prefix) ([]netip.Prefix, error) { merr = multierror.Append(merr, fmt.Errorf("remove dynamic route for IP %s: %w", prefix, err)) } if r.currentPeerKey != "" { - if _, err := r.allowedIPsRefcounter.Decrement(prefix); err != nil { + if _, err := r.allowedIPsRefcounter.Decrement(prefix, r.currentPeerKey); err != nil { merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %w", prefix, err)) } } @@ -364,6 +364,20 @@ func determinePrefixChanges(oldPrefixes, newPrefixes []netip.Prefix) (toAdd, toR return } +// lookupHostIPs resolves d via the system resolver, honoring ctx cancellation. +func lookupHostIPs(ctx context.Context, d domain.Domain) ([]net.IP, error) { + addrs, err := net.DefaultResolver.LookupIPAddr(ctx, d.PunycodeString()) + if err != nil { + return nil, err + } + + ips := make([]net.IP, 0, len(addrs)) + for _, addr := range addrs { + ips = append(ips, addr.IP) + } + return ips, nil +} + func combinePrefixes(oldPrefixes, removedPrefixes, addedPrefixes []netip.Prefix) []netip.Prefix { prefixSet := make(map[netip.Prefix]struct{}) for _, prefix := range oldPrefixes { diff --git a/client/internal/routemanager/dynamic/route_generic.go b/client/internal/routemanager/dynamic/route_generic.go index 56fd63fba..8bc2dd3df 100644 --- a/client/internal/routemanager/dynamic/route_generic.go +++ b/client/internal/routemanager/dynamic/route_generic.go @@ -3,11 +3,12 @@ package dynamic import ( + "context" "net" "github.com/netbirdio/netbird/shared/management/domain" ) -func (r *Route) getIPsFromResolver(domain domain.Domain) ([]net.IP, error) { - return net.LookupIP(domain.PunycodeString()) +func (r *Route) getIPsFromResolver(ctx context.Context, domain domain.Domain) ([]net.IP, error) { + return lookupHostIPs(ctx, domain) } diff --git a/client/internal/routemanager/dynamic/route_ios.go b/client/internal/routemanager/dynamic/route_ios.go index 1ae281d56..6a3d262b8 100644 --- a/client/internal/routemanager/dynamic/route_ios.go +++ b/client/internal/routemanager/dynamic/route_ios.go @@ -3,6 +3,7 @@ package dynamic import ( + "context" "fmt" "net" "time" @@ -16,7 +17,7 @@ import ( const dialTimeout = 10 * time.Second -func (r *Route) getIPsFromResolver(domain domain.Domain) ([]net.IP, error) { +func (r *Route) getIPsFromResolver(ctx context.Context, domain domain.Domain) ([]net.IP, error) { privateClient, err := nbdns.GetClientPrivate(r.wgInterface, r.resolverAddr.Addr(), dialTimeout) if err != nil { return nil, fmt.Errorf("error while creating private client: %s", err) @@ -32,7 +33,7 @@ func (r *Route) getIPsFromResolver(domain domain.Domain) ([]net.IP, error) { msg := new(dns.Msg) msg.SetQuestion(fqdn, qtype) - response, _, err := nbdns.ExchangeWithFallback(nil, privateClient, msg, r.resolverAddr.String()) + response, _, err := nbdns.ExchangeWithFallback(ctx, privateClient, msg, r.resolverAddr.String()) if err != nil { if queryErr == nil { queryErr = fmt.Errorf("DNS query for %s (type %d) after %s: %w", domain.SafeString(), qtype, time.Since(startTime), err) diff --git a/client/internal/routemanager/manager.go b/client/internal/routemanager/manager.go index 16f8d48fa..2ab7e2a85 100644 --- a/client/internal/routemanager/manager.go +++ b/client/internal/routemanager/manager.go @@ -12,6 +12,7 @@ import ( "strings" "sync" "sync/atomic" + "syscall" "time" "github.com/google/uuid" @@ -51,6 +52,10 @@ type Manager interface { UpdateRoutes(updateSerial uint64, serverRoutes map[route.ID]*route.Route, clientRoutes route.HAMap, useNewDNSRoute bool) error ClassifyRoutes(newRoutes []*route.Route) (map[route.ID]*route.Route, route.HAMap) TriggerSelection(route.HAMap) + SelectRoutes(ids []route.NetID, appendRoute bool) error + DeselectRoutes(ids []route.NetID) error + SelectAllRoutes() + DeselectAllRoutes() GetRouteSelector() *routeselector.RouteSelector GetClientRoutes() route.HAMap GetSelectedClientRoutes() route.HAMap @@ -60,6 +65,7 @@ type Manager interface { InitialRouteRange() []string SetFirewall(firewall.Manager) error SetDNSForwarderPort(port uint16) + ReconcilePeerAllowedIPs(peerKey string) error Stop(stateManager *statemanager.Manager) } @@ -214,7 +220,7 @@ func (m *DefaultManager) setupRefCounters(useNoop bool) { ) } - m.allowedIPsRefCounter = refcounter.New( + m.allowedIPsRefCounter = refcounter.NewAllowedIPs( func(prefix netip.Prefix, peerKey string) (string, error) { // save peerKey to use it in the remove function return peerKey, m.wgInterface.AddAllowedIP(peerKey, prefix) @@ -231,6 +237,30 @@ func (m *DefaultManager) setupRefCounters(useNoop bool) { ) } +// ReconcilePeerAllowedIPs re-applies every routed allowed IP currently tracked for the peer +// onto the WireGuard device. The allowed-IP refcounter only calls its AddFunc (which pushes to +// the device) on a prefix's 0->1 transition, so a peer whose device entry was rebuilt without a +// matching refcounter change — e.g. a lazy connection cycling through idle->wake, which recreates +// the WireGuard peer with the overlay /32 only — ends up missing routed prefixes the refcounter +// still considers installed, and nothing retries. Calling this when the peer's WireGuard entry is +// (re)created restores convergence. It is add-only and idempotent: AddAllowedIP is update-only, so +// prefixes are re-added to an existing peer and an absent peer is left untouched. +func (m *DefaultManager) ReconcilePeerAllowedIPs(peerKey string) error { + if m.allowedIPsRefCounter == nil { + return nil + } + + return m.allowedIPsRefCounter.ReapplyMatching( + func(out string) bool { return out == peerKey }, + func(prefix netip.Prefix) error { + if err := m.wgInterface.AddAllowedIP(peerKey, prefix); err != nil { + return fmt.Errorf("add allowed IP %s for peer %s: %w", prefix, peerKey, err) + } + return nil + }, + ) +} + // Init sets up the routing func (m *DefaultManager) Init() error { m.routeSelector = m.initSelector() @@ -264,7 +294,11 @@ func (m *DefaultManager) initSelector() *routeselector.RouteSelector { // restore selector state if it exists if err := m.stateManager.LoadState(state); err != nil { - log.Warnf("failed to load state: %v", err) + if errors.Is(err, syscall.ENOSYS) { + log.Debugf("route selector state unavailable on this platform: %v", err) + } else { + log.Warnf("failed to load state: %v", err) + } return routeselector.NewRouteSelector() } @@ -770,7 +804,7 @@ func (m *DefaultManager) collectExitNodeInfo(clientRoutes route.HAMap) exitNodeI var info exitNodeInfo for haID, routes := range clientRoutes { - if !m.isExitNodeRoute(routes) { + if !isExitNodeRoutes(routes) { continue } @@ -790,13 +824,6 @@ func (m *DefaultManager) collectExitNodeInfo(clientRoutes route.HAMap) exitNodeI return info } -func (m *DefaultManager) isExitNodeRoute(routes []*route.Route) bool { - if len(routes) == 0 { - return false - } - return route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network) -} - func (m *DefaultManager) categorizeUserSelection(netID route.NetID, info *exitNodeInfo) { if m.routeSelector.IsSelected(netID) { info.userSelected = append(info.userSelected, netID) diff --git a/client/internal/routemanager/mock.go b/client/internal/routemanager/mock.go index 937314995..cf761091d 100644 --- a/client/internal/routemanager/mock.go +++ b/client/internal/routemanager/mock.go @@ -16,6 +16,8 @@ type MockManager struct { ClassifyRoutesFunc func(routes []*route.Route) (map[route.ID]*route.Route, route.HAMap) UpdateRoutesFunc func(updateSerial uint64, serverRoutes map[route.ID]*route.Route, clientRoutes route.HAMap, useNewDNSRoute bool) error TriggerSelectionFunc func(haMap route.HAMap) + SelectRoutesFunc func(ids []route.NetID, appendRoute bool) error + DeselectRoutesFunc func(ids []route.NetID) error GetRouteSelectorFunc func() *routeselector.RouteSelector GetClientRoutesFunc func() route.HAMap GetSelectedClientRoutesFunc func() route.HAMap @@ -55,6 +57,30 @@ func (m *MockManager) TriggerSelection(networks route.HAMap) { } } +// SelectRoutes mock implementation of SelectRoutes from Manager interface +func (m *MockManager) SelectRoutes(ids []route.NetID, appendRoute bool) error { + if m.SelectRoutesFunc != nil { + return m.SelectRoutesFunc(ids, appendRoute) + } + return nil +} + +// DeselectRoutes mock implementation of DeselectRoutes from Manager interface +func (m *MockManager) DeselectRoutes(ids []route.NetID) error { + if m.DeselectRoutesFunc != nil { + return m.DeselectRoutesFunc(ids) + } + return nil +} + +// SelectAllRoutes mock implementation of SelectAllRoutes from Manager interface +func (m *MockManager) SelectAllRoutes() { +} + +// DeselectAllRoutes mock implementation of DeselectAllRoutes from Manager interface +func (m *MockManager) DeselectAllRoutes() { +} + // GetRouteSelector mock implementation of GetRouteSelector from Manager interface func (m *MockManager) GetRouteSelector() *routeselector.RouteSelector { if m.GetRouteSelectorFunc != nil { @@ -112,6 +138,11 @@ func (m *MockManager) SetFirewall(firewall.Manager) error { func (m *MockManager) SetDNSForwarderPort(port uint16) { } +// ReconcilePeerAllowedIPs mock implementation of ReconcilePeerAllowedIPs from Manager interface +func (m *MockManager) ReconcilePeerAllowedIPs(peerKey string) error { + return nil +} + // Stop mock implementation of Stop from Manager interface func (m *MockManager) Stop(stateManager *statemanager.Manager) { if m.StopFunc != nil { diff --git a/client/internal/routemanager/notifier/notifier_ios.go b/client/internal/routemanager/notifier/notifier_ios.go index d0888f3a1..c91a76551 100644 --- a/client/internal/routemanager/notifier/notifier_ios.go +++ b/client/internal/routemanager/notifier/notifier_ios.go @@ -3,7 +3,6 @@ package notifier import ( - "container/list" "net/netip" "slices" "sort" @@ -16,20 +15,12 @@ import ( type Notifier struct { mu sync.Mutex - cond *sync.Cond currentPrefixes []string listener listener.NetworkChangeListener - queue *list.List - closed bool } func NewNotifier() *Notifier { - n := &Notifier{ - queue: list.New(), - } - n.cond = sync.NewCond(&n.mu) - go n.deliverLoop() - return n + return &Notifier{} } func (n *Notifier) SetListener(listener listener.NetworkChangeListener) { @@ -59,44 +50,19 @@ func (n *Notifier) OnNewPrefixes(prefixes []netip.Prefix) { sort.Strings(newNets) n.mu.Lock() + defer n.mu.Unlock() if slices.Equal(n.currentPrefixes, newNets) { - n.mu.Unlock() return } n.currentPrefixes = newNets - routes := strings.Join(n.currentPrefixes, ",") - n.queue.PushBack(routes) - n.cond.Signal() - n.mu.Unlock() + if n.listener != nil { + n.listener.OnNetworkChanged(strings.Join(n.currentPrefixes, ",")) + } } func (n *Notifier) Close() { - n.mu.Lock() - n.closed = true - n.cond.Signal() - n.mu.Unlock() } func (n *Notifier) GetInitialRouteRanges() []string { return nil } - -func (n *Notifier) deliverLoop() { - for { - n.mu.Lock() - for n.queue.Len() == 0 && !n.closed { - n.cond.Wait() - } - if n.closed && n.queue.Len() == 0 { - n.mu.Unlock() - return - } - routes := n.queue.Remove(n.queue.Front()).(string) - l := n.listener - n.mu.Unlock() - - if l != nil { - l.OnNetworkChanged(routes) - } - } -} diff --git a/client/internal/routemanager/reconcile_test.go b/client/internal/routemanager/reconcile_test.go new file mode 100644 index 000000000..c6806a6cd --- /dev/null +++ b/client/internal/routemanager/reconcile_test.go @@ -0,0 +1,90 @@ +//go:build !windows + +package routemanager + +import ( + "net" + "net/netip" + "sync" + "testing" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + "golang.zx2c4.com/wireguard/tun/netstack" + + "github.com/netbirdio/netbird/client/iface/device" + "github.com/netbirdio/netbird/client/iface/wgaddr" + "github.com/netbirdio/netbird/client/internal/routemanager/refcounter" +) + +// reconcileWGMock is a minimal iface.WGIface that only records AddAllowedIP calls; every other +// method is an inert stub because ReconcilePeerAllowedIPs exercises none of them. +type reconcileWGMock struct { + mu sync.Mutex + adds map[string][]netip.Prefix +} + +func (m *reconcileWGMock) AddAllowedIP(peerKey string, allowedIP netip.Prefix) error { + m.mu.Lock() + defer m.mu.Unlock() + if m.adds == nil { + m.adds = map[string][]netip.Prefix{} + } + m.adds[peerKey] = append(m.adds[peerKey], allowedIP) + return nil +} + +func (m *reconcileWGMock) added(peerKey string) []netip.Prefix { + m.mu.Lock() + defer m.mu.Unlock() + return m.adds[peerKey] +} + +func (m *reconcileWGMock) RemoveAllowedIP(string, netip.Prefix) error { return nil } +func (m *reconcileWGMock) Name() string { return "utun-test" } +func (m *reconcileWGMock) Address() wgaddr.Address { return wgaddr.Address{} } +func (m *reconcileWGMock) ToInterface() *net.Interface { return nil } +func (m *reconcileWGMock) IsUserspaceBind() bool { return false } +func (m *reconcileWGMock) GetFilter() device.PacketFilter { return nil } +func (m *reconcileWGMock) GetDevice() *device.FilteredDevice { return nil } +func (m *reconcileWGMock) GetNet() *netstack.Net { return nil } + +// TestReconcilePeerAllowedIPs verifies the declarative reconcile re-applies every routed prefix +// tracked for the peer (self-heal, independent of refcount level) and stays scoped to that peer. +func TestReconcilePeerAllowedIPs(t *testing.T) { + wg := &reconcileWGMock{} + m := &DefaultManager{wgInterface: wg} + m.allowedIPsRefCounter = refcounter.NewAllowedIPs( + func(_ netip.Prefix, peerKey string) (string, error) { return peerKey, nil }, + func(netip.Prefix, string) error { return nil }, + ) + + peerA1 := netip.MustParsePrefix("10.0.0.0/24") + peerA2 := netip.MustParsePrefix("10.1.0.0/24") + peerB1 := netip.MustParsePrefix("10.2.0.0/24") + + for prefix, peer := range map[netip.Prefix]string{peerA1: "peerA", peerA2: "peerA", peerB1: "peerB"} { + _, err := m.allowedIPsRefCounter.Increment(prefix, peer) + require.NoError(t, err) + } + // Extra reference: reconcile must still re-apply the prefix even though its refcount never + // hit 0 again (the exact case the plain incremental path skips). + _, err := m.allowedIPsRefCounter.Increment(peerA1, "peerA") + require.NoError(t, err) + + require.NoError(t, m.ReconcilePeerAllowedIPs("peerA")) + + assert.ElementsMatch(t, []netip.Prefix{peerA1, peerA2}, wg.added("peerA"), + "reconcile must re-apply all routed prefixes of the peer") + assert.Empty(t, wg.added("peerB"), "reconcile must not touch another peer's prefixes") +} + +// TestReconcilePeerAllowedIPsNoCounter verifies reconcile is a safe no-op before the refcounter is +// set up. +func TestReconcilePeerAllowedIPsNoCounter(t *testing.T) { + wg := &reconcileWGMock{} + m := &DefaultManager{wgInterface: wg} + + require.NoError(t, m.ReconcilePeerAllowedIPs("peerA")) + assert.Empty(t, wg.added("peerA")) +} diff --git a/client/internal/routemanager/refcounter/allowedips.go b/client/internal/routemanager/refcounter/allowedips.go new file mode 100644 index 000000000..6d682e8a9 --- /dev/null +++ b/client/internal/routemanager/refcounter/allowedips.go @@ -0,0 +1,206 @@ +package refcounter + +import ( + "errors" + "fmt" + "net/netip" + "sort" + "sync" + + "github.com/hashicorp/go-multierror" + + nberrors "github.com/netbirdio/netbird/client/errors" +) + +// allowedIPsEntry holds the per-peer reference counts for a single prefix and which peer is +// currently installed in WireGuard. WireGuard allows a prefix on exactly one peer, so at most +// one peer is active at a time even when several peers reference the prefix. +type allowedIPsEntry struct { + // peers maps a peerKey to the number of references holding the prefix for that peer. + peers map[string]int + // active is the peerKey currently installed in WireGuard for this prefix ("" if none). + active string + // total is the sum of all per-peer reference counts (kept in sync with peers). + total int +} + +// AllowedIPsRefCounter is a peer-aware reference counter for WireGuard AllowedIPs. +// +// The generic Counter keys only by prefix and remembers a single Out value set by the first +// caller, which it never changes. That is wrong for AllowedIPs: two independent watchers (or +// multiple resolved domains) can reference the same prefix through different peers, and when the +// peer currently installed in WireGuard releases its last reference the prefix must be handed over +// to a surviving peer instead of being left pointing at the released one. +// +// It calls add/remove (which program WireGuard) only on the transitions that matter: +// - add on the first reference for a prefix, or when swapping the active peer; +// - remove on the last reference for a prefix, or on the old peer during a swap. +type AllowedIPsRefCounter struct { + mu sync.Mutex + entries map[netip.Prefix]*allowedIPsEntry + add AddFunc[netip.Prefix, string, string] + remove RemoveFunc[netip.Prefix, string] +} + +// NewAllowedIPs creates a new peer-aware AllowedIPs reference counter. +// add programs a prefix on a peer in WireGuard and returns the peerKey to store as the active peer. +// remove unprograms the prefix from the given peer. +func NewAllowedIPs(add AddFunc[netip.Prefix, string, string], remove RemoveFunc[netip.Prefix, string]) *AllowedIPsRefCounter { + return &AllowedIPsRefCounter{ + entries: map[netip.Prefix]*allowedIPsEntry{}, + add: add, + remove: remove, + } +} + +// Increment adds a reference to prefix for peerKey. WireGuard is programmed only for the first +// reference to a prefix; while a different peer is already installed the prefix is left with it +// (first peer wins, HA at the WireGuard layer is not possible) and only the reference count is kept. +func (rm *AllowedIPsRefCounter) Increment(prefix netip.Prefix, peerKey string) (Ref[string], error) { + rm.mu.Lock() + defer rm.mu.Unlock() + + e, ok := rm.entries[prefix] + if !ok { + e = &allowedIPsEntry{peers: map[string]int{}} + rm.entries[prefix] = e + } + + logCallerF("Increasing allowed IP ref count for prefix %v peer %s [peer %d -> %d, total %d -> %d, active %q]", + prefix, peerKey, e.peers[peerKey], e.peers[peerKey]+1, e.total, e.total+1, e.active) + + // Program WireGuard only when nothing is installed yet for this prefix. + if e.active == "" { + out, err := rm.add(prefix, peerKey) + if errors.Is(err, ErrIgnore) { + if e.total == 0 { + delete(rm.entries, prefix) + } + return Ref[string]{Count: e.total, Out: e.active}, nil + } + if err != nil { + if e.total == 0 { + delete(rm.entries, prefix) + } + return Ref[string]{}, fmt.Errorf("failed to add allowed IP %v for peer %s: %w", prefix, peerKey, err) + } + e.active = out + } + + e.peers[peerKey]++ + e.total++ + + return Ref[string]{Count: e.total, Out: e.active}, nil +} + +// Decrement removes a reference to prefix for peerKey. When the peer currently installed in +// WireGuard releases its last reference, the prefix is swapped to a surviving peer if one exists, +// otherwise it is removed from WireGuard. +func (rm *AllowedIPsRefCounter) Decrement(prefix netip.Prefix, peerKey string) (Ref[string], error) { + rm.mu.Lock() + defer rm.mu.Unlock() + + e, ok := rm.entries[prefix] + if !ok { + logCallerF("No allowed IP reference found for prefix %v", prefix) + return Ref[string]{}, nil + } + + if e.peers[peerKey] > 0 { + logCallerF("Decreasing allowed IP ref count for prefix %v peer %s [peer %d -> %d, total %d -> %d, active %q]", + prefix, peerKey, e.peers[peerKey], e.peers[peerKey]-1, e.total, e.total-1, e.active) + e.peers[peerKey]-- + e.total-- + if e.peers[peerKey] == 0 { + delete(e.peers, peerKey) + } + } else { + logCallerF("No allowed IP reference found for prefix %v peer %s", prefix, peerKey) + } + + // If the peer currently installed in WireGuard still holds references, nothing to reprogram. + // Keying the check on the active peer (not the one just released) makes this self-healing: + // a prior swap whose remove/add failed leaves e.active pointing at a peer with no references, + // and this retries the hand-off on the next Decrement instead of getting stuck. + if e.active != "" && e.peers[e.active] > 0 { + return Ref[string]{Count: e.total, Out: e.active}, nil + } + + // Detach the stale/gone active peer from WireGuard before reprogramming. + if e.active != "" { + if err := rm.remove(prefix, e.active); err != nil { + return Ref[string]{Count: e.total, Out: e.active}, fmt.Errorf("remove allowed IP %v for peer %s: %w", prefix, e.active, err) + } + e.active = "" + } + + // Hand the prefix over to a surviving peer, or drop the entry when none remain. + if survivor, ok := pickSurvivor(e.peers); ok { + out, err := rm.add(prefix, survivor) + if err != nil { + return Ref[string]{Count: e.total, Out: ""}, fmt.Errorf("swap allowed IP %v to peer %s: %w", prefix, survivor, err) + } + e.active = out + return Ref[string]{Count: e.total, Out: e.active}, nil + } + + delete(rm.entries, prefix) + return Ref[string]{Count: 0, Out: ""}, nil +} + +// Flush removes all prefixes from WireGuard and clears the counter. +func (rm *AllowedIPsRefCounter) Flush() error { + rm.mu.Lock() + defer rm.mu.Unlock() + + var merr *multierror.Error + for prefix, e := range rm.entries { + if e.active == "" { + continue + } + logCallerF("Flushing allowed IP for prefix %v peer %s", prefix, e.active) + if err := rm.remove(prefix, e.active); err != nil { + merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %v for peer %s: %w", prefix, e.active, err)) + } + } + + clear(rm.entries) + + return nberrors.FormatErrorOrNil(merr) +} + +// ReapplyMatching calls apply for every prefix whose currently installed (active) peer satisfies +// pred, holding the lock for the whole pass. It is used to re-push allowed IPs onto a peer whose +// WireGuard entry was rebuilt (e.g. a lazy connection cycling idle->wake) without a matching +// refcounter change, which would otherwise leave the prefix installed in the counter but missing +// on the device. Only the active peer is considered — a prefix that lost its installed peer to a +// failed swap is skipped here and reconciled by the next Increment/Decrement. +func (rm *AllowedIPsRefCounter) ReapplyMatching(pred func(out string) bool, apply func(key netip.Prefix) error) error { + rm.mu.Lock() + defer rm.mu.Unlock() + + var merr *multierror.Error + for prefix, e := range rm.entries { + if e.active != "" && pred(e.active) { + if err := apply(prefix); err != nil { + merr = multierror.Append(merr, err) + } + } + } + return nberrors.FormatErrorOrNil(merr) +} + +// pickSurvivor deterministically selects a peer still referencing the prefix. WireGuard cannot do +// multipath for a single prefix, so any surviving peer is a valid winner; the choice is made stable +// (lowest peerKey) for predictable behavior and testability. +func pickSurvivor(peers map[string]int) (string, bool) { + if len(peers) == 0 { + return "", false + } + keys := make([]string, 0, len(peers)) + for k := range peers { + keys = append(keys, k) + } + sort.Strings(keys) + return keys[0], true +} diff --git a/client/internal/routemanager/refcounter/allowedips_test.go b/client/internal/routemanager/refcounter/allowedips_test.go new file mode 100644 index 000000000..835142083 --- /dev/null +++ b/client/internal/routemanager/refcounter/allowedips_test.go @@ -0,0 +1,241 @@ +package refcounter + +import ( + "errors" + "net/netip" + "testing" +) + +// fakeWG models WireGuard's cryptokey routing: a prefix can be installed on exactly one peer. +// failAdd/failRemove make the next add/remove fail once, to exercise the self-healing error paths. +type fakeWG struct { + installed map[netip.Prefix]string + adds int + removes int + failAdd bool + failRemove bool +} + +func newFakeWG() *fakeWG { + return &fakeWG{installed: map[netip.Prefix]string{}} +} + +func (f *fakeWG) counter() *AllowedIPsRefCounter { + return NewAllowedIPs( + func(prefix netip.Prefix, peerKey string) (string, error) { + if f.failAdd { + f.failAdd = false + return "", errors.New("add failed") + } + f.adds++ + f.installed[prefix] = peerKey + return peerKey, nil + }, + func(prefix netip.Prefix, peerKey string) error { + if f.failRemove { + f.failRemove = false + return errors.New("remove failed") + } + f.removes++ + // only clear if this peer is the one installed, mirroring wg semantics + if f.installed[prefix] == peerKey { + delete(f.installed, prefix) + } + return nil + }, + ) +} + +func mustPrefix(t *testing.T, s string) netip.Prefix { + t.Helper() + p, err := netip.ParsePrefix(s) + if err != nil { + t.Fatalf("parse prefix %q: %v", s, err) + } + return p +} + +func mustIncrement(t *testing.T, c *AllowedIPsRefCounter, p netip.Prefix, peer string) Ref[string] { + t.Helper() + ref, err := c.Increment(p, peer) + if err != nil { + t.Fatalf("Increment(%v, %s): %v", p, peer, err) + } + return ref +} + +func mustDecrement(t *testing.T, c *AllowedIPsRefCounter, p netip.Prefix, peer string) Ref[string] { + t.Helper() + ref, err := c.Decrement(p, peer) + if err != nil { + t.Fatalf("Decrement(%v, %s): %v", p, peer, err) + } + return ref +} + +// TestAllowedIPs_SwapOnActivePeerRemoval reproduces the reported bug: two networks with the same +// prefix routed by different peers. Removing the network whose peer is installed must hand the +// prefix over to the surviving peer instead of leaving it on the removed one. +func TestAllowedIPs_SwapOnActivePeerRemoval(t *testing.T) { + f := newFakeWG() + c := f.counter() + p := mustPrefix(t, "10.44.8.0/24") + + mustIncrement(t, c, p, "peerA") + mustIncrement(t, c, p, "peerB") + // First peer wins while both are present. + if got := f.installed[p]; got != "peerA" { + t.Fatalf("expected peerA installed, got %q", got) + } + + // Remove the active peer's network -> must swap to peerB. + mustDecrement(t, c, p, "peerA") + if got := f.installed[p]; got != "peerB" { + t.Fatalf("BUG: prefix stuck on removed peer, want peerB got %q", got) + } + + // Remove the last one -> prefix gone. + mustDecrement(t, c, p, "peerB") + if _, ok := f.installed[p]; ok { + t.Fatalf("expected prefix removed, still installed on %q", f.installed[p]) + } +} + +// TestAllowedIPs_RemoveNonActivePeer removing a non-installed peer must not touch WireGuard. +func TestAllowedIPs_RemoveNonActivePeer(t *testing.T) { + f := newFakeWG() + c := f.counter() + p := mustPrefix(t, "10.44.8.0/24") + + mustIncrement(t, c, p, "peerA") + mustIncrement(t, c, p, "peerB") + removesBefore := f.removes + + mustDecrement(t, c, p, "peerB") + if f.installed[p] != "peerA" { + t.Fatalf("active peer must stay peerA, got %q", f.installed[p]) + } + if f.removes != removesBefore { + t.Fatalf("removing a non-active peer must not call wg remove") + } +} + +// TestAllowedIPs_SamePeerMultipleRefs two references via the same peer must keep the prefix until +// the last reference is released (the reason the per-peer count must be an int, not a set). +func TestAllowedIPs_SamePeerMultipleRefs(t *testing.T) { + f := newFakeWG() + c := f.counter() + p := mustPrefix(t, "10.44.8.0/24") + + mustIncrement(t, c, p, "peerA") + mustIncrement(t, c, p, "peerA") + if f.adds != 1 { + t.Fatalf("expected a single wg add for the same peer, got %d", f.adds) + } + + mustDecrement(t, c, p, "peerA") + if f.installed[p] != "peerA" { + t.Fatalf("prefix must stay while a reference remains, got %q", f.installed[p]) + } + if f.removes != 0 { + t.Fatalf("no wg remove expected while a reference remains, got %d", f.removes) + } + + mustDecrement(t, c, p, "peerA") + if _, ok := f.installed[p]; ok { + t.Fatalf("prefix must be removed after last reference") + } +} + +// TestAllowedIPs_RefCountAndActive checks the Ref returned to callers (used for the HA-disabled log). +func TestAllowedIPs_RefCountAndActive(t *testing.T) { + f := newFakeWG() + c := f.counter() + p := mustPrefix(t, "10.44.8.0/24") + + ref := mustIncrement(t, c, p, "peerA") + if ref.Count != 1 || ref.Out != "peerA" { + t.Fatalf("want {1, peerA}, got {%d, %q}", ref.Count, ref.Out) + } + ref = mustIncrement(t, c, p, "peerB") + if ref.Count != 2 || ref.Out != "peerA" { + t.Fatalf("want {2, peerA}, got {%d, %q}", ref.Count, ref.Out) + } +} + +// TestAllowedIPs_Flush removes everything installed and clears the counter. +func TestAllowedIPs_Flush(t *testing.T) { + f := newFakeWG() + c := f.counter() + p1 := mustPrefix(t, "10.44.8.0/24") + p2 := mustPrefix(t, "10.44.9.0/24") + + mustIncrement(t, c, p1, "peerA") + mustIncrement(t, c, p2, "peerB") + + if err := c.Flush(); err != nil { + t.Fatal(err) + } + if len(f.installed) != 0 { + t.Fatalf("expected all prefixes removed, got %v", f.installed) + } + // After flush, a fresh increment must add again. + mustIncrement(t, c, p1, "peerC") + if f.installed[p1] != "peerC" { + t.Fatalf("counter not reset after flush") + } +} + +// TestAllowedIPs_SelfHealAfterSwapAddError ensures a failed add during a swap does not permanently +// strand the prefix: the next Decrement (or Increment) must retry and install a surviving peer. +func TestAllowedIPs_SelfHealAfterSwapAddError(t *testing.T) { + f := newFakeWG() + c := f.counter() + p := mustPrefix(t, "10.44.8.0/24") + + mustIncrement(t, c, p, "peerA") + mustIncrement(t, c, p, "peerB") + mustIncrement(t, c, p, "peerC") + + // Removing the active peerA triggers a swap to a survivor; make the add fail once. + f.failAdd = true + if _, err := c.Decrement(p, "peerA"); err == nil { + t.Fatalf("expected error from failed swap add") + } + if _, ok := f.installed[p]; ok { + t.Fatalf("nothing should be installed after a failed swap add, got %q", f.installed[p]) + } + + // A later Decrement of a non-active survivor must retry the hand-off (self-heal), not stay stuck. + ref := mustDecrement(t, c, p, "peerC") + if got := f.installed[p]; got == "" { + t.Fatalf("self-heal failed: prefix left unrouted after add recovered") + } + if ref.Out == "" { + t.Fatalf("expected an active peer after self-heal, got empty") + } +} + +// TestAllowedIPs_SelfHealAfterRemoveError ensures a failed remove during a swap is retried instead +// of leaving e.active stuck on a peer that no longer holds references. +func TestAllowedIPs_SelfHealAfterRemoveError(t *testing.T) { + f := newFakeWG() + c := f.counter() + p := mustPrefix(t, "10.44.8.0/24") + + mustIncrement(t, c, p, "peerA") + mustIncrement(t, c, p, "peerB") + + // Releasing active peerA must detach it (remove) then add peerB; fail the remove once. + f.failRemove = true + if _, err := c.Decrement(p, "peerA"); err == nil { + t.Fatalf("expected error from failed remove") + } + + // Next Decrement of the non-active survivor retries: removes stale peerA, installs peerB. + mustDecrement(t, c, p, "peerB") + // peerB had only one ref, so after retry the prefix is fully released. + if _, ok := f.installed[p]; ok { + t.Fatalf("expected prefix released after self-heal, still on %q", f.installed[p]) + } +} diff --git a/client/internal/routemanager/refcounter/refcounter.go b/client/internal/routemanager/refcounter/refcounter.go index 27a724f50..917120275 100644 --- a/client/internal/routemanager/refcounter/refcounter.go +++ b/client/internal/routemanager/refcounter/refcounter.go @@ -94,6 +94,26 @@ func (rm *Counter[Key, I, O]) Get(key Key) (Ref[O], bool) { return ref, ok } +// ReapplyMatching calls apply for every key whose stored Out satisfies pred, holding the +// counter lock for the whole pass. Running apply under the lock keeps it atomic with respect +// to Increment/Decrement: a prefix dropped to zero is removed from the map (and had its +// RemoveFunc called) before this pass observes it, so a stale key can never be re-applied. +// pred and apply are invoked under the lock, so they must not call back into the counter. +func (rm *Counter[Key, I, O]) ReapplyMatching(pred func(out O) bool, apply func(key Key) error) error { + rm.mu.Lock() + defer rm.mu.Unlock() + + var merr *multierror.Error + for key, ref := range rm.refCountMap { + if pred(ref.Out) { + if err := apply(key); err != nil { + merr = multierror.Append(merr, err) + } + } + } + return nberrors.FormatErrorOrNil(merr) +} + // Increment increments the reference count for the given key. // If this is the first reference to the key, the AddFunc is called. func (rm *Counter[Key, I, O]) Increment(key Key, in I) (Ref[O], error) { diff --git a/client/internal/routemanager/refcounter/refcounter_test.go b/client/internal/routemanager/refcounter/refcounter_test.go new file mode 100644 index 000000000..79a99c388 --- /dev/null +++ b/client/internal/routemanager/refcounter/refcounter_test.go @@ -0,0 +1,47 @@ +package refcounter + +import ( + "net/netip" + "testing" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" +) + +// TestReapplyMatching verifies ReapplyMatching invokes apply for exactly the keys whose stored +// Out satisfies the predicate (no duplicates for multiply-referenced keys) — the primitive +// ReconcilePeerAllowedIPs relies on to re-apply a single peer's routed prefixes. +func TestReapplyMatching(t *testing.T) { + rc := New[netip.Prefix, string, string]( + func(_ netip.Prefix, peerKey string) (string, error) { return peerKey, nil }, + func(netip.Prefix, string) error { return nil }, + ) + + peerA1 := netip.MustParsePrefix("10.0.0.0/24") + peerA2 := netip.MustParsePrefix("10.1.0.0/24") + peerB1 := netip.MustParsePrefix("10.2.0.0/24") + + for prefix, peer := range map[netip.Prefix]string{peerA1: "peerA", peerA2: "peerA", peerB1: "peerB"} { + _, err := rc.Increment(prefix, peer) + require.NoError(t, err) + } + // a second reference must not make the key applied twice + _, err := rc.Increment(peerA1, "peerA") + require.NoError(t, err) + + var applied []netip.Prefix + err = rc.ReapplyMatching( + func(out string) bool { return out == "peerA" }, + func(key netip.Prefix) error { applied = append(applied, key); return nil }, + ) + require.NoError(t, err) + assert.ElementsMatch(t, []netip.Prefix{peerA1, peerA2}, applied) + + var none []netip.Prefix + err = rc.ReapplyMatching( + func(out string) bool { return out == "missing" }, + func(key netip.Prefix) error { none = append(none, key); return nil }, + ) + require.NoError(t, err) + assert.Empty(t, none) +} diff --git a/client/internal/routemanager/refcounter/types.go b/client/internal/routemanager/refcounter/types.go index aadac3e25..7da0e17e3 100644 --- a/client/internal/routemanager/refcounter/types.go +++ b/client/internal/routemanager/refcounter/types.go @@ -5,5 +5,7 @@ import "net/netip" // RouteRefCounter is a Counter for Route, it doesn't take any input on Increment and doesn't use any output on Decrement type RouteRefCounter = Counter[netip.Prefix, struct{}, struct{}] -// AllowedIPsRefCounter is a Counter for AllowedIPs, it takes a peer key on Increment and passes it back to Decrement -type AllowedIPsRefCounter = Counter[netip.Prefix, string, string] +// AllowedIPsRefCounter tracks WireGuard AllowedIPs per prefix. Unlike the generic Counter it is peer-aware: +// a prefix can be claimed by several peers at once and WireGuard allows a given prefix on exactly one peer, +// so the counter records the per-peer reference count and swaps the installed peer when the active one is released. +// See allowedips.go. diff --git a/client/internal/routemanager/selection.go b/client/internal/routemanager/selection.go new file mode 100644 index 000000000..6d5feec79 --- /dev/null +++ b/client/internal/routemanager/selection.go @@ -0,0 +1,138 @@ +package routemanager + +import ( + "fmt" + "slices" + + "github.com/hashicorp/go-multierror" + log "github.com/sirupsen/logrus" + "golang.org/x/exp/maps" + + nberrors "github.com/netbirdio/netbird/client/errors" + "github.com/netbirdio/netbird/route" +) + +// SelectRoutes selects the routes with the given network IDs and applies the +// new selection. V4/v6 exit-node pairs are expanded automatically. Exit nodes +// are mutually exclusive: if the selection activates an exit node, every other +// available exit node is deselected so two can't be active at once. With +// appendRoute=false the previous selection is replaced instead of extended. +func (m *DefaultManager) SelectRoutes(ids []route.NetID, appendRoute bool) error { + if err := m.selectRoutes(ids, appendRoute); err != nil { + return err + } + m.TriggerSelection(m.GetClientRoutes()) + return nil +} + +// DeselectRoutes removes the routes with the given network IDs from the +// selection and applies the change. V4/v6 exit-node pairs are expanded +// automatically. +func (m *DefaultManager) DeselectRoutes(ids []route.NetID) error { + if err := m.deselectRoutes(ids); err != nil { + return err + } + m.TriggerSelection(m.GetClientRoutes()) + return nil +} + +func (m *DefaultManager) deselectRoutes(ids []route.NetID) error { + routesMap := m.GetClientRoutesWithNetID() + routes := route.ExpandV6ExitPairs(slices.Clone(ids), routesMap) + + log.Debugf("deselecting routes with ids: %v", routes) + + if err := m.routeSelector.DeselectRoutes(routes, maps.Keys(routesMap)); err != nil { + return fmt.Errorf("deselect routes: %w", err) + } + + return nil +} + +// SelectAllRoutes selects every available route and applies the selection. +// Exit nodes stay mutually exclusive: at most one remains active. +func (m *DefaultManager) SelectAllRoutes() { + m.selectAllRoutes() + m.TriggerSelection(m.GetClientRoutes()) +} + +func (m *DefaultManager) selectAllRoutes() { + m.routeSelector.SelectAllRoutes() + + // Select-all wipes every explicit selection, so exit nodes fall back to + // management's auto-apply flags — which may mark several at once. + // Reconcile immediately so at most one exit node stays active instead of + // waiting for the next network map to enforce it. + m.mux.Lock() + defer m.mux.Unlock() + m.updateRouteSelectorFromManagement(m.clientRoutes) +} + +// DeselectAllRoutes deselects every route and applies the change. +func (m *DefaultManager) DeselectAllRoutes() { + m.routeSelector.DeselectAllRoutes() + m.TriggerSelection(m.GetClientRoutes()) +} + +func (m *DefaultManager) selectRoutes(ids []route.NetID, appendRoute bool) error { + routesMap := m.GetClientRoutesWithNetID() + routes := route.ExpandV6ExitPairs(slices.Clone(ids), routesMap) + allIDs := maps.Keys(routesMap) + + log.Debugf("selecting routes with ids: %v", routes) + + // A partial failure (e.g. an unknown ID in the request) still selects the + // valid routes, so exclusivity below must run regardless of the error. + var merr *multierror.Error + if err := m.routeSelector.SelectRoutes(routes, appendRoute, allIDs); err != nil { + merr = multierror.Append(merr, fmt.Errorf("select routes: %w", err)) + } + + // Exit nodes are mutually exclusive: if this selection activates an + // exit node, deselect every other available exit node so two can't be + // selected at once. Non-exit route selections are left untouched. + if requestActivatesExitNode(routes, routesMap) { + if others := otherExitNodeIDs(routesMap, routes); len(others) > 0 { + if err := m.routeSelector.DeselectRoutes(others, allIDs); err != nil { + merr = multierror.Append(merr, fmt.Errorf("deselect sibling exit nodes: %w", err)) + } + } + } + + return nberrors.FormatErrorOrNil(merr) +} + +func isExitNodeRoutes(routes []*route.Route) bool { + return len(routes) > 0 && (route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network)) +} + +// requestActivatesExitNode reports whether any requested NetID maps to an exit +// node (default route) in the current route table. +func requestActivatesExitNode(requested []route.NetID, routesMap map[route.NetID][]*route.Route) bool { + for _, id := range requested { + if isExitNodeRoutes(routesMap[id]) { + return true + } + } + return false +} + +// otherExitNodeIDs returns every available exit-node NetID that is not in the +// requested set — the siblings to deselect so a single exit node stays active. +func otherExitNodeIDs(routesMap map[route.NetID][]*route.Route, requested []route.NetID) []route.NetID { + keep := make(map[route.NetID]struct{}, len(requested)) + for _, id := range requested { + keep[id] = struct{}{} + } + var others []route.NetID + for id, routes := range routesMap { + if !isExitNodeRoutes(routes) { + continue + } + if _, ok := keep[id]; ok { + continue + } + others = append(others, id) + } + return others +} diff --git a/client/internal/routemanager/selection_test.go b/client/internal/routemanager/selection_test.go new file mode 100644 index 000000000..6066b5661 --- /dev/null +++ b/client/internal/routemanager/selection_test.go @@ -0,0 +1,129 @@ +package routemanager + +import ( + "net/netip" + "testing" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + + "github.com/netbirdio/netbird/client/internal/routeselector" + "github.com/netbirdio/netbird/route" +) + +func v6ExitRoute(netID, peer string) *route.Route { + return &route.Route{ + NetID: route.NetID(netID), + Network: netip.MustParsePrefix("::/0"), + Peer: peer, + } +} + +func newSelectionTestManager() *DefaultManager { + return &DefaultManager{ + routeSelector: routeselector.NewRouteSelector(), + clientRoutes: route.HAMap{ + "exitA|0.0.0.0/0": {exitRoute("exitA", "p1", true)}, + "exitA-v6|::/0": {v6ExitRoute("exitA-v6", "p1")}, + "exitB|0.0.0.0/0": {exitRoute("exitB", "p2", true)}, + "lan|192.168.1.0/24": {{NetID: "lan", Network: netip.MustParsePrefix("192.168.1.0/24"), Peer: "p3"}}, + }, + } +} + +func TestSelectRoutes_ExitNodeExclusivity(t *testing.T) { + m := newSelectionTestManager() + + // Selecting an exit node selects its v6 pair and deselects the sibling. + require.NoError(t, m.selectRoutes([]route.NetID{"exitA"}, true)) + assert.True(t, m.routeSelector.IsSelected("exitA"), "exitA should be selected") + assert.True(t, m.routeSelector.IsSelected("exitA-v6"), "the v6 pair follows its v4 base") + assert.False(t, m.routeSelector.IsSelected("exitB"), "the sibling exit node must be deselected") + + // Switching to the sibling deselects the previous exit node and its v6 pair. + require.NoError(t, m.selectRoutes([]route.NetID{"exitB"}, true)) + assert.True(t, m.routeSelector.IsSelected("exitB"), "exitB should now be selected") + assert.False(t, m.routeSelector.IsSelected("exitA"), "the previous exit node must be deselected") + assert.False(t, m.routeSelector.IsSelected("exitA-v6"), "the previous exit node's v6 pair must be deselected") + assert.True(t, m.routeSelector.IsSelected("lan"), "non-exit route selection is untouched") + + // Selecting a non-exit route leaves the active exit node alone. + require.NoError(t, m.selectRoutes([]route.NetID{"lan"}, true)) + assert.True(t, m.routeSelector.IsSelected("exitB"), "selecting a non-exit route keeps the exit node") + + // Deselecting the active exit node turns every exit node off. + require.NoError(t, m.deselectRoutes([]route.NetID{"exitB"})) + assert.False(t, m.routeSelector.IsSelected("exitB"), "exitB should be deselected") + assert.False(t, m.routeSelector.IsSelected("exitA"), "exitA stays deselected") + assert.True(t, m.routeSelector.IsSelected("lan"), "non-exit route selection is untouched") +} + +func TestSelectRoutes_PartialErrorStillEnforcesExclusivity(t *testing.T) { + // The unknown ID must be reported, but the valid exit node in the same + // request is still selected — so its sibling must still be deselected. + // Both orderings are covered: processing must continue past the invalid + // ID wherever it sits in the request. + requests := map[string][]route.NetID{ + "invalid id first": {"missing", "exitB"}, + "invalid id last": {"exitB", "missing"}, + } + + for name, ids := range requests { + t.Run(name, func(t *testing.T) { + m := newSelectionTestManager() + + require.NoError(t, m.selectRoutes([]route.NetID{"exitA"}, true)) + + err := m.selectRoutes(ids, true) + assert.Error(t, err, "unknown id must be reported") + assert.True(t, m.routeSelector.IsSelected("exitB"), "valid exit node from the request is selected") + assert.False(t, m.routeSelector.IsSelected("exitA"), "sibling exit node must be deselected despite the error") + assert.False(t, m.routeSelector.IsSelected("exitA-v6"), "sibling's v6 pair must be deselected too") + }) + } +} + +func TestSelectAllRoutes_KeepsSingleExitNode(t *testing.T) { + // Both exit nodes are marked for auto-apply by management + // (SkipAutoApply=false), the state where select-all could turn on two at + // once without the immediate reconciliation. + m := &DefaultManager{ + routeSelector: routeselector.NewRouteSelector(), + clientRoutes: route.HAMap{ + "exitA|0.0.0.0/0": {exitRoute("exitA", "p1", false)}, + "exitB|0.0.0.0/0": {exitRoute("exitB", "p2", false)}, + "lan|192.168.1.0/24": {{NetID: "lan", Network: netip.MustParsePrefix("192.168.1.0/24"), Peer: "p3"}}, + }, + } + + require.NoError(t, m.selectRoutes([]route.NetID{"exitB"}, true)) + + m.selectAllRoutes() + + assert.True(t, m.routeSelector.IsSelected("lan"), "non-exit routes are all selected") + assert.True(t, m.routeSelector.IsSelected("exitA"), "the deterministic management pick stays active") + assert.False(t, m.routeSelector.IsSelected("exitB"), "select-all must not leave a second exit node active") +} + +func TestSelectRoutes_UnknownRoute(t *testing.T) { + m := newSelectionTestManager() + + assert.Error(t, m.selectRoutes([]route.NetID{"missing"}, true), "selecting an unavailable route must fail") + assert.Error(t, m.deselectRoutes([]route.NetID{"missing"}), "deselecting an unavailable route must fail") +} + +func TestExitNodeSelectionHelpers(t *testing.T) { + routesMap := map[route.NetID][]*route.Route{ + "exitA": {{Network: netip.MustParsePrefix("0.0.0.0/0")}}, + "exitB": {{Network: netip.MustParsePrefix("::/0")}}, + "lan": {{Network: netip.MustParsePrefix("192.168.0.0/16")}}, + } + + assert.True(t, requestActivatesExitNode([]route.NetID{"exitA"}, routesMap), "v4 default route is an exit node") + assert.True(t, requestActivatesExitNode([]route.NetID{"exitB"}, routesMap), "v6 default route is an exit node") + assert.False(t, requestActivatesExitNode([]route.NetID{"lan"}, routesMap), "lan route is not an exit node") + assert.False(t, requestActivatesExitNode([]route.NetID{"missing"}, routesMap), "unknown id is not an exit node") + + others := otherExitNodeIDs(routesMap, []route.NetID{"exitB"}) + assert.ElementsMatch(t, []route.NetID{"exitA"}, others, "only the other exit node is a sibling; the lan route is ignored") +} diff --git a/client/internal/routemanager/static/route.go b/client/internal/routemanager/static/route.go index d480fdf00..8ba03d090 100644 --- a/client/internal/routemanager/static/route.go +++ b/client/internal/routemanager/static/route.go @@ -15,6 +15,11 @@ type Route struct { route *route.Route routeRefCounter *refcounter.RouteRefCounter allowedIPsRefcounter *refcounter.AllowedIPsRefCounter + // currentPeerKey is the routing peer this watcher currently has the prefix installed on + // (the HA winner elected by the watcher). It can differ from route.Peer and change on + // failover, so it is recorded on AddAllowedIPs and used on RemoveAllowedIPs to decrement + // the exact peer that was incremented. + currentPeerKey string } func NewRoute(params common.HandlerParams) *Route { @@ -52,12 +57,15 @@ func (r *Route) AddAllowedIPs(peerKey string) error { ref.Out, ) } + r.currentPeerKey = peerKey return nil } func (r *Route) RemoveAllowedIPs() error { - if _, err := r.allowedIPsRefcounter.Decrement(r.route.Network); err != nil { - return err + var err error + if _, decErr := r.allowedIPsRefcounter.Decrement(r.route.Network, r.currentPeerKey); decErr != nil { + err = fmt.Errorf("remove allowed IP %s: %w", r.route.Network, decErr) } - return nil + r.currentPeerKey = "" + return err } diff --git a/client/internal/routemanager/sysctl/sysctl_linux.go b/client/internal/routemanager/sysctl/sysctl_linux.go index f96a57f37..46b7c9fb7 100644 --- a/client/internal/routemanager/sysctl/sysctl_linux.go +++ b/client/internal/routemanager/sysctl/sysctl_linux.go @@ -20,6 +20,8 @@ const ( rpFilterPath = "net.ipv4.conf.all.rp_filter" rpFilterInterfacePath = "net.ipv4.conf.%s.rp_filter" srcValidMarkPath = "net.ipv4.conf.all.src_valid_mark" + percentEscape = "%25" + dotEscape = "%2E" ) type iface interface { @@ -56,7 +58,11 @@ func Setup(wgIface iface) (map[string]int, error) { continue } - i := fmt.Sprintf(rpFilterInterfacePath, intf.Name) + // Escape '%' and '.' so they survive the dot-to-slash conversion in Set() + safeName := strings.ReplaceAll(intf.Name, "%", percentEscape) + safeName = strings.ReplaceAll(safeName, ".", dotEscape) + + i := fmt.Sprintf(rpFilterInterfacePath, safeName) oldVal, err := Set(i, 2, true) if err != nil { result = multierror.Append(result, err) @@ -70,7 +76,11 @@ func Setup(wgIface iface) (map[string]int, error) { // Set sets a sysctl configuration, if onlyIfOne is true it will only set the new value if it's set to 1 func Set(key string, desiredValue int, onlyIfOne bool) (int, error) { - path := fmt.Sprintf("/proc/sys/%s", strings.ReplaceAll(key, ".", "/")) + path := strings.ReplaceAll(key, ".", "/") + // Unescape interface dots and percent signs + path = strings.ReplaceAll(path, dotEscape, ".") + path = strings.ReplaceAll(path, percentEscape, "%") + path = fmt.Sprintf("/proc/sys/%s", path) currentValue, err := os.ReadFile(path) if err != nil { return -1, fmt.Errorf("read sysctl %s: %w", key, err) diff --git a/client/internal/statemanager/manager.go b/client/internal/statemanager/manager.go index 566905985..ca4194690 100644 --- a/client/internal/statemanager/manager.go +++ b/client/internal/statemanager/manager.go @@ -1,6 +1,7 @@ package statemanager import ( + "bytes" "context" "encoding/json" "errors" @@ -305,6 +306,11 @@ func (m *Manager) loadStateFile(deleteCorrupt bool) (map[string]json.RawMessage, var rawStates map[string]json.RawMessage if err := json.Unmarshal(data, &rawStates); err != nil { + if len(bytes.TrimSpace(data)) == 0 { + log.Warnf("state file %s is empty (%d bytes)", m.filePath, len(data)) + } else { + log.Warnf("state file %s has malformed content (%d bytes)", m.filePath, len(data)) + } m.handleCorruptedState(deleteCorrupt) return nil, fmt.Errorf("unmarshal states: %w", err) } diff --git a/client/internal/tunnelnotifier/notifier.go b/client/internal/tunnelnotifier/notifier.go new file mode 100644 index 000000000..b62923a6e --- /dev/null +++ b/client/internal/tunnelnotifier/notifier.go @@ -0,0 +1,124 @@ +package tunnelnotifier + +import ( + "container/list" + "sync" + + "github.com/netbirdio/netbird/client/internal/dns" + "github.com/netbirdio/netbird/client/internal/listener" +) + +type eventKind int + +const ( + eventRoutes eventKind = iota + eventIfaceIP + eventIfaceIPv6 + eventDNS +) + +var ( + _ listener.NetworkChangeListener = (*Notifier)(nil) + _ dns.IosDnsManager = (*Notifier)(nil) +) + +type event struct { + kind eventKind + payload string +} + +type Notifier struct { + mu sync.Mutex + cond *sync.Cond + queue *list.List + closed bool + done chan struct{} + + listener listener.NetworkChangeListener + dnsManager dns.IosDnsManager +} + +func New(l listener.NetworkChangeListener, dm dns.IosDnsManager) *Notifier { + n := &Notifier{ + queue: list.New(), + done: make(chan struct{}), + listener: l, + dnsManager: dm, + } + n.cond = sync.NewCond(&n.mu) + go n.deliverLoop() + return n +} + +func (n *Notifier) OnNetworkChanged(routes string) { + n.enqueue(event{kind: eventRoutes, payload: routes}) +} + +func (n *Notifier) SetInterfaceIP(ip string) { + n.enqueue(event{kind: eventIfaceIP, payload: ip}) +} + +func (n *Notifier) SetInterfaceIPv6(ip string) { + n.enqueue(event{kind: eventIfaceIPv6, payload: ip}) +} + +func (n *Notifier) ApplyDns(config string) { + n.enqueue(event{kind: eventDNS, payload: config}) +} + +// Close stops accepting new events and blocks until the delivery loop has +// drained all queued events and exited. +func (n *Notifier) Close() { + n.mu.Lock() + n.closed = true + n.cond.Signal() + n.mu.Unlock() + <-n.done +} + +func (n *Notifier) enqueue(ev event) { + n.mu.Lock() + defer n.mu.Unlock() + if n.closed { + return + } + n.queue.PushBack(ev) + n.cond.Signal() +} + +func (n *Notifier) deliverLoop() { + defer close(n.done) + for { + n.mu.Lock() + for n.queue.Len() == 0 && !n.closed { + n.cond.Wait() + } + if n.closed && n.queue.Len() == 0 { + n.mu.Unlock() + return + } + ev := n.queue.Remove(n.queue.Front()).(event) + l := n.listener + dm := n.dnsManager + n.mu.Unlock() + + switch ev.kind { + case eventRoutes: + if l != nil { + l.OnNetworkChanged(ev.payload) + } + case eventIfaceIP: + if l != nil { + l.SetInterfaceIP(ev.payload) + } + case eventIfaceIPv6: + if l != nil { + l.SetInterfaceIPv6(ev.payload) + } + case eventDNS: + if dm != nil { + dm.ApplyDns(ev.payload) + } + } + } +} diff --git a/client/internal/tunnelnotifier/notifier_test.go b/client/internal/tunnelnotifier/notifier_test.go new file mode 100644 index 000000000..ffbcdc15c --- /dev/null +++ b/client/internal/tunnelnotifier/notifier_test.go @@ -0,0 +1,192 @@ +package tunnelnotifier + +import ( + "fmt" + "sync" + "sync/atomic" + "testing" + "time" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" +) + +type call struct { + kind string + payload string +} + +type recorder struct { + mu sync.Mutex + calls []call + inFlight atomic.Int32 + overlap atomic.Bool + delay time.Duration +} + +func (r *recorder) record(kind, payload string) { + if r.inFlight.Add(1) != 1 { + r.overlap.Store(true) + } + if r.delay > 0 { + time.Sleep(r.delay) + } + r.mu.Lock() + r.calls = append(r.calls, call{kind: kind, payload: payload}) + r.mu.Unlock() + r.inFlight.Add(-1) +} + +func (r *recorder) count() int { + r.mu.Lock() + defer r.mu.Unlock() + return len(r.calls) +} + +func (r *recorder) snapshot() []call { + r.mu.Lock() + defer r.mu.Unlock() + out := make([]call, len(r.calls)) + copy(out, r.calls) + return out +} + +type fakeListener struct { + rec *recorder +} + +func (f *fakeListener) OnNetworkChanged(routes string) { + f.rec.record("routes", routes) +} + +func (f *fakeListener) SetInterfaceIP(ip string) { + f.rec.record("ip", ip) +} + +func (f *fakeListener) SetInterfaceIPv6(ip string) { + f.rec.record("ipv6", ip) +} + +type fakeDNSManager struct { + rec *recorder +} + +func (f *fakeDNSManager) ApplyDns(config string) { + f.rec.record("dns", config) +} + +func TestFIFOOrder(t *testing.T) { + rec := &recorder{} + n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec}) + defer n.Close() + + n.SetInterfaceIP("10.0.0.1") + n.SetInterfaceIPv6("fd00::1") + n.ApplyDns(`{"domains":[]}`) + n.OnNetworkChanged("10.0.0.0/8,192.168.0.0/16") + n.ApplyDns(`{"domains":["example.com"]}`) + + require.Eventually(t, func() bool { return rec.count() == 5 }, time.Second, time.Millisecond) + + expected := []call{ + {kind: "ip", payload: "10.0.0.1"}, + {kind: "ipv6", payload: "fd00::1"}, + {kind: "dns", payload: `{"domains":[]}`}, + {kind: "routes", payload: "10.0.0.0/8,192.168.0.0/16"}, + {kind: "dns", payload: `{"domains":["example.com"]}`}, + } + assert.Equal(t, expected, rec.snapshot()) +} + +func TestNoOverlappingCalls(t *testing.T) { + rec := &recorder{delay: 100 * time.Microsecond} + n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec}) + defer n.Close() + + const producers = 8 + const perProducer = 25 + + var wg sync.WaitGroup + for i := 0; i < producers; i++ { + wg.Add(1) + go func(id int) { + defer wg.Done() + for j := 0; j < perProducer; j++ { + payload := fmt.Sprintf("%d-%d", id, j) + switch j % 4 { + case 0: + n.OnNetworkChanged(payload) + case 1: + n.SetInterfaceIP(payload) + case 2: + n.SetInterfaceIPv6(payload) + case 3: + n.ApplyDns(payload) + } + } + }(i) + } + wg.Wait() + + require.Eventually(t, func() bool { return rec.count() == producers*perProducer }, 5*time.Second, time.Millisecond) + assert.False(t, rec.overlap.Load()) +} + +func TestDNSAndRoutesInterleaved(t *testing.T) { + rec := &recorder{delay: 100 * time.Microsecond} + n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec}) + defer n.Close() + + const events = 50 + + var wg sync.WaitGroup + wg.Add(2) + go func() { + defer wg.Done() + for i := 0; i < events; i++ { + n.ApplyDns(fmt.Sprintf("dns-%d", i)) + } + }() + go func() { + defer wg.Done() + for i := 0; i < events; i++ { + n.OnNetworkChanged(fmt.Sprintf("routes-%d", i)) + } + }() + wg.Wait() + + require.Eventually(t, func() bool { return rec.count() == 2*events }, 5*time.Second, time.Millisecond) + assert.False(t, rec.overlap.Load()) + + var dnsSeen, routesSeen int + for _, c := range rec.snapshot() { + switch c.kind { + case "dns": + assert.Equal(t, fmt.Sprintf("dns-%d", dnsSeen), c.payload) + dnsSeen++ + case "routes": + assert.Equal(t, fmt.Sprintf("routes-%d", routesSeen), c.payload) + routesSeen++ + } + } + assert.Equal(t, events, dnsSeen) + assert.Equal(t, events, routesSeen) +} + +func TestCloseDrainsQueue(t *testing.T) { + rec := &recorder{delay: time.Millisecond} + n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec}) + + const events = 20 + for i := 0; i < events; i++ { + n.OnNetworkChanged(fmt.Sprintf("routes-%d", i)) + } + n.Close() + + require.Equal(t, events, rec.count(), "Close must not return before all queued events are delivered") + + n.OnNetworkChanged("after-close") + n.ApplyDns("after-close") + time.Sleep(50 * time.Millisecond) + assert.Equal(t, events, rec.count()) +} diff --git a/client/ios/NetBirdSDK/client.go b/client/ios/NetBirdSDK/client.go index 359a83556..37d3e5d99 100644 --- a/client/ios/NetBirdSDK/client.go +++ b/client/ios/NetBirdSDK/client.go @@ -13,7 +13,6 @@ import ( "time" log "github.com/sirupsen/logrus" - "golang.org/x/exp/maps" "github.com/netbirdio/netbird/client/internal" "github.com/netbirdio/netbird/client/internal/auth" @@ -233,6 +232,9 @@ func (c *Client) DebugBundle(anonymize bool) (string, error) { 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 } @@ -260,7 +262,7 @@ func (c *Client) DebugBundle(anonymize bool) (string, error) { uploadCtx, cancel := context.WithTimeout(context.Background(), 2*time.Minute) defer cancel() - key, err := debug.UploadDebugBundle(uploadCtx, types.DefaultBundleURL, cfg.ManagementURL.String(), path) + key, err := debug.UploadDebugBundle(uploadCtx, types.DefaultBundleURL, cfg.ManagementURL.String(), path, false) if err != nil { return "", fmt.Errorf("upload debug bundle: %w", err) } @@ -634,23 +636,18 @@ func (c *Client) SelectRoute(id string) error { } routeManager := engine.GetRouteManager() - routeSelector := routeManager.GetRouteSelector() if id == "All" { log.Debugf("select all routes") - routeSelector.SelectAllRoutes() - } else { - log.Debugf("select route with id: %s", id) - routes := toNetIDs([]string{id}) - routesMap := routeManager.GetClientRoutesWithNetID() - routes = route.ExpandV6ExitPairs(routes, routesMap) - if err := routeSelector.SelectRoutes(routes, true, maps.Keys(routesMap)); err != nil { - log.Debugf("error when selecting routes: %s", err) - return fmt.Errorf("select routes: %w", err) - } + routeManager.SelectAllRoutes() + return nil } - routeManager.TriggerSelection(routeManager.GetClientRoutes()) - return nil + log.Debugf("select route with id: %s", id) + if err := routeManager.SelectRoutes(toNetIDs([]string{id}), true); err != nil { + log.Debugf("error when selecting routes: %s", err) + return err + } + return nil } func (c *Client) DeselectRoute(id string) error { @@ -664,21 +661,17 @@ func (c *Client) DeselectRoute(id string) error { } routeManager := engine.GetRouteManager() - routeSelector := routeManager.GetRouteSelector() if id == "All" { log.Debugf("deselect all routes") - routeSelector.DeselectAllRoutes() - } else { - log.Debugf("deselect route with id: %s", id) - routes := toNetIDs([]string{id}) - routesMap := routeManager.GetClientRoutesWithNetID() - routes = route.ExpandV6ExitPairs(routes, routesMap) - if err := routeSelector.DeselectRoutes(routes, maps.Keys(routesMap)); err != nil { - log.Debugf("error when deselecting routes: %s", err) - return fmt.Errorf("deselect routes: %w", err) - } + routeManager.DeselectAllRoutes() + return nil + } + + log.Debugf("deselect route with id: %s", id) + if err := routeManager.DeselectRoutes(toNetIDs([]string{id})); err != nil { + log.Debugf("error when deselecting routes: %s", err) + return err } - routeManager.TriggerSelection(routeManager.GetClientRoutes()) return nil } diff --git a/client/ios/NetBirdSDK/login.go b/client/ios/NetBirdSDK/login.go index 432133999..99486839b 100644 --- a/client/ios/NetBirdSDK/login.go +++ b/client/ios/NetBirdSDK/login.go @@ -44,10 +44,25 @@ type Auth struct { // NewAuth instantiate Auth struct and validate the management URL func NewAuth(cfgPath string, mgmURL string) (*Auth, error) { inputCfg := profilemanager.ConfigInput{ + ConfigPath: cfgPath, ManagementURL: mgmURL, } - cfg, err := profilemanager.CreateInMemoryConfig(inputCfg) + // Load the existing config when a config file is already present so an + // interactive re-login reuses the peer's persisted WireGuard private key + // (and thus its identity) instead of generating a fresh one. Generating a + // new key registers a brand-new peer on the management server on every + // re-auth (named after the fallback hostname). Only fall back to a fresh + // in-memory config for the first-time login when no config file exists yet. + // DirectUpdateOrCreateConfig uses non-atomic writes so it also works inside + // the tvOS App Group sandbox where atomic temp-file+rename is blocked. + var cfg *profilemanager.Config + var err error + if cfgPath != "" { + cfg, err = profilemanager.DirectUpdateOrCreateConfig(inputCfg) + } else { + cfg, err = profilemanager.CreateInMemoryConfig(inputCfg) + } if err != nil { return nil, err } diff --git a/client/ios/NetBirdSDK/version.go b/client/ios/NetBirdSDK/version.go new file mode 100644 index 000000000..606ad18e2 --- /dev/null +++ b/client/ios/NetBirdSDK/version.go @@ -0,0 +1,12 @@ +//go:build ios + +package NetBirdSDK + +import "github.com/netbirdio/netbird/version" + +// GoClientVersion returns the NetBird Go client version that was baked into +// the framework at compile time via +// -ldflags "-X github.com/netbirdio/netbird/version.version=". +func GoClientVersion() string { + return version.NetbirdVersion() +} diff --git a/client/jobexec/executor.go b/client/jobexec/executor.go index e29cc8840..9401acacc 100644 --- a/client/jobexec/executor.go +++ b/client/jobexec/executor.go @@ -54,7 +54,7 @@ func (e *Executor) BundleJob(ctx context.Context, debugBundleDependencies debug. } }() - key, err := debug.UploadDebugBundle(ctx, types.DefaultBundleURL, mgmURL, path) + key, err := debug.UploadDebugBundle(ctx, types.DefaultBundleURL, mgmURL, path, false) if err != nil { log.Errorf("failed to upload debug bundle: %v", err) return "", fmt.Errorf("upload debug bundle: %w", err) diff --git a/client/mdm/canonical_loaders.go b/client/mdm/canonical_loaders.go index cb9af9ccb..29288b511 100644 --- a/client/mdm/canonical_loaders.go +++ b/client/mdm/canonical_loaders.go @@ -22,6 +22,7 @@ var allKeys = []string{ KeyDisableMetricsCollection, KeyAllowServerSSH, KeyDisableAutoConnect, + KeyDisableAutostart, KeyPreSharedKey, KeyRosenpassEnabled, KeyRosenpassPermissive, diff --git a/client/mdm/policy.go b/client/mdm/policy.go index b76c70a75..1feff28f8 100644 --- a/client/mdm/policy.go +++ b/client/mdm/policy.go @@ -20,10 +20,10 @@ import ( // names (lowerCamelCase) so the daemon can map a Policy key directly to a // configuration field. const ( - KeyManagementURL = "managementURL" - KeyDisableUpdateSettings = "disableUpdateSettings" - KeyDisableProfiles = "disableProfiles" - KeyDisableNetworks = "disableNetworks" + KeyManagementURL = "managementURL" + KeyDisableUpdateSettings = "disableUpdateSettings" + KeyDisableProfiles = "disableProfiles" + KeyDisableNetworks = "disableNetworks" // KeyDisableAdvancedView gates the advanced-view section in the // upcoming UI revision. UI-only: NOT stored on Config, not // applied by applyMDMPolicy, not rejectable via SetConfig. The @@ -37,10 +37,16 @@ const ( KeyDisableMetricsCollection = "disableMetricsCollection" KeyAllowServerSSH = "allowServerSSH" KeyDisableAutoConnect = "disableAutoConnect" - KeyPreSharedKey = "preSharedKey" - KeyRosenpassEnabled = "rosenpassEnabled" - KeyRosenpassPermissive = "rosenpassPermissive" - KeyWireguardPort = "wireguardPort" + // KeyDisableAutostart suppresses the GUI's fresh-install + // launch-on-login default and marks the Settings toggle as + // MDM-managed. UI-only: NOT stored on Config and not applied by + // applyMDMPolicy; the GUI reads it directly and it appears in + // GetConfigResponse.mDMManagedFields when set. + KeyDisableAutostart = "disableAutostart" + KeyPreSharedKey = "preSharedKey" + KeyRosenpassEnabled = "rosenpassEnabled" + KeyRosenpassPermissive = "rosenpassPermissive" + KeyWireguardPort = "wireguardPort" // Split tunnel is modeled as a single conceptual policy with two // registry/plist values. KeySplitTunnelMode is the discriminator diff --git a/client/proto/daemon.pb.go b/client/proto/daemon.pb.go index 6fbb09958..d4deeb8ec 100644 --- a/client/proto/daemon.pb.go +++ b/client/proto/daemon.pb.go @@ -2771,14 +2771,18 @@ func (x *ForwardingRulesResponse) GetRules() []*ForwardingRule { // DebugBundler type DebugBundleRequest struct { - state protoimpl.MessageState `protogen:"open.v1"` - Anonymize bool `protobuf:"varint,1,opt,name=anonymize,proto3" json:"anonymize,omitempty"` - SystemInfo bool `protobuf:"varint,3,opt,name=systemInfo,proto3" json:"systemInfo,omitempty"` - UploadURL string `protobuf:"bytes,4,opt,name=uploadURL,proto3" json:"uploadURL,omitempty"` - LogFileCount uint32 `protobuf:"varint,5,opt,name=logFileCount,proto3" json:"logFileCount,omitempty"` - CliVersion string `protobuf:"bytes,6,opt,name=cliVersion,proto3" json:"cliVersion,omitempty"` - unknownFields protoimpl.UnknownFields - sizeCache protoimpl.SizeCache + state protoimpl.MessageState `protogen:"open.v1"` + Anonymize bool `protobuf:"varint,1,opt,name=anonymize,proto3" json:"anonymize,omitempty"` + SystemInfo bool `protobuf:"varint,3,opt,name=systemInfo,proto3" json:"systemInfo,omitempty"` + UploadURL string `protobuf:"bytes,4,opt,name=uploadURL,proto3" json:"uploadURL,omitempty"` + LogFileCount uint32 `protobuf:"varint,5,opt,name=logFileCount,proto3" json:"logFileCount,omitempty"` + CliVersion string `protobuf:"bytes,6,opt,name=cliVersion,proto3" json:"cliVersion,omitempty"` + // uploadInsecure allows uploading to an http endpoint or one with an + // untrusted TLS certificate. Restricted to privileged callers; for + // self-hosted upload servers. + UploadInsecure bool `protobuf:"varint,7,opt,name=uploadInsecure,proto3" json:"uploadInsecure,omitempty"` + unknownFields protoimpl.UnknownFields + sizeCache protoimpl.SizeCache } func (x *DebugBundleRequest) Reset() { @@ -2846,6 +2850,13 @@ func (x *DebugBundleRequest) GetCliVersion() string { return "" } +func (x *DebugBundleRequest) GetUploadInsecure() bool { + if x != nil { + return x.UploadInsecure + } + return false +} + type DebugBundleResponse struct { state protoimpl.MessageState `protogen:"open.v1"` Path string `protobuf:"bytes,1,opt,name=path,proto3" json:"path,omitempty"` @@ -7242,7 +7253,7 @@ const file_daemon_proto_rawDesc = "" + "\x12translatedHostname\x18\x04 \x01(\tR\x12translatedHostname\x128\n" + "\x0etranslatedPort\x18\x05 \x01(\v2\x10.daemon.PortInfoR\x0etranslatedPort\"G\n" + "\x17ForwardingRulesResponse\x12,\n" + - "\x05rules\x18\x01 \x03(\v2\x16.daemon.ForwardingRuleR\x05rules\"\xb4\x01\n" + + "\x05rules\x18\x01 \x03(\v2\x16.daemon.ForwardingRuleR\x05rules\"\xdc\x01\n" + "\x12DebugBundleRequest\x12\x1c\n" + "\tanonymize\x18\x01 \x01(\bR\tanonymize\x12\x1e\n" + "\n" + @@ -7252,7 +7263,8 @@ const file_daemon_proto_rawDesc = "" + "\flogFileCount\x18\x05 \x01(\rR\flogFileCount\x12\x1e\n" + "\n" + "cliVersion\x18\x06 \x01(\tR\n" + - "cliVersion\"}\n" + + "cliVersion\x12&\n" + + "\x0euploadInsecure\x18\a \x01(\bR\x0euploadInsecure\"}\n" + "\x13DebugBundleResponse\x12\x12\n" + "\x04path\x18\x01 \x01(\tR\x04path\x12 \n" + "\vuploadedKey\x18\x02 \x01(\tR\vuploadedKey\x120\n" + diff --git a/client/proto/daemon.proto b/client/proto/daemon.proto index 8d5294eb7..3c31156ec 100644 --- a/client/proto/daemon.proto +++ b/client/proto/daemon.proto @@ -536,6 +536,10 @@ message DebugBundleRequest { string uploadURL = 4; uint32 logFileCount = 5; string cliVersion = 6; + // uploadInsecure allows uploading to an http endpoint or one with an + // untrusted TLS certificate. Restricted to privileged callers; for + // self-hosted upload servers. + bool uploadInsecure = 7; } message DebugBundleResponse { diff --git a/client/server/debug.go b/client/server/debug.go index 0b6ac4b53..60a401b0e 100644 --- a/client/server/debug.go +++ b/client/server/debug.go @@ -7,18 +7,62 @@ import ( "context" "errors" "fmt" + "path/filepath" "runtime/pprof" + "strings" + "time" log "github.com/sirupsen/logrus" + "google.golang.org/grpc/codes" + gstatus "google.golang.org/grpc/status" "github.com/netbirdio/netbird/client/internal/debug" + "github.com/netbirdio/netbird/client/internal/ipcauth" "github.com/netbirdio/netbird/client/proto" mgmProto "github.com/netbirdio/netbird/shared/management/proto" "github.com/netbirdio/netbird/version" ) // DebugBundle creates a debug bundle and returns the location. -func (s *Server) DebugBundle(_ context.Context, req *proto.DebugBundleRequest) (resp *proto.DebugBundleResponse, err error) { +func (s *Server) DebugBundle(callerCtx context.Context, req *proto.DebugBundleRequest) (resp *proto.DebugBundleResponse, err error) { + if err := requirePrivilegeForUploadURL(callerCtx, req.GetUploadURL(), req.GetUploadInsecure()); err != nil { + return nil, err + } + + // The UI log is opened as whoever asked for this bundle, so a caller only + // collects a log it owns (privileged callers excepted). ok is false on a + // socket that carries no identity, which skips the UI log. + callerID, callerIdentified := ipcauth.CallerIdentity(callerCtx) + + path, managementURL, err := s.generateDebugBundle(req, uiLogOpener(callerID, callerIdentified)) + if err != nil { + return nil, err + } + + if req.GetUploadURL() == "" { + return &proto.DebugBundleResponse{Path: path}, nil + } + + // The upload runs without s.mutex held: it does network I/O to a possibly + // slow destination and must not block the other RPCs that take the lock. The + // bounded context is a backstop against a hung connection. + uploadCtx, cancel := context.WithTimeout(context.Background(), 2*time.Minute) + defer cancel() + key, err := debug.UploadDebugBundle(uploadCtx, req.GetUploadURL(), managementURL, path, req.GetUploadInsecure()) + if err != nil { + log.Errorf("failed to upload debug bundle to %s: %v", req.GetUploadURL(), err) + return &proto.DebugBundleResponse{Path: path, UploadFailureReason: err.Error()}, nil + } + + log.Infof("debug bundle uploaded to %s with key %s", req.GetUploadURL(), key) + + return &proto.DebugBundleResponse{Path: path, UploadedKey: key}, nil +} + +// generateDebugBundle builds the bundle under s.mutex and returns its path plus +// the management URL captured under the lock, so the caller can run the upload +// without holding the lock. +func (s *Server) generateDebugBundle(req *proto.DebugBundleRequest, uiOpener debug.LogOpener) (path string, managementURL string, err error) { s.mutex.Lock() defer s.mutex.Unlock() @@ -68,6 +112,7 @@ func (s *Server) DebugBundle(_ context.Context, req *proto.DebugBundleRequest) ( SyncResponse: syncResponse, LogPath: s.logFile, UILogPath: s.uiLogPath, + UILogOpener: uiOpener, CPUProfile: cpuProfileData, CapturePath: capturePath, RefreshStatus: refreshStatus, @@ -82,23 +127,16 @@ func (s *Server) DebugBundle(_ context.Context, req *proto.DebugBundleRequest) ( }, ) - path, err := bundleGenerator.Generate() + path, err = bundleGenerator.Generate() if err != nil { - return nil, fmt.Errorf("generate debug bundle: %w", err) + return "", "", fmt.Errorf("generate debug bundle: %w", err) } - if req.GetUploadURL() == "" { - return &proto.DebugBundleResponse{Path: path}, nil - } - key, err := debug.UploadDebugBundle(context.Background(), req.GetUploadURL(), s.config.ManagementURL.String(), path) - if err != nil { - log.Errorf("failed to upload debug bundle to %s: %v", req.GetUploadURL(), err) - return &proto.DebugBundleResponse{Path: path, UploadFailureReason: err.Error()}, nil + if s.config != nil && s.config.ManagementURL != nil { + managementURL = s.config.ManagementURL.String() } - log.Infof("debug bundle uploaded to %s with key %s", req.GetUploadURL(), key) - - return &proto.DebugBundleResponse{Path: path, UploadedKey: key}, nil + return path, managementURL, nil } // GetLogLevel gets the current logging level for the server. @@ -138,12 +176,34 @@ func (s *Server) SetLogLevel(_ context.Context, req *proto.SetLogLevelRequest) ( // RegisterUILog records the desktop UI's absolute log path so DebugBundle can // collect the GUI log. The daemon runs as root and can't resolve the user's // config dir, so the UI reports it. Last-writer-wins (one UI per socket). -func (s *Server) RegisterUILog(_ context.Context, req *proto.RegisterUILogRequest) (*proto.RegisterUILogResponse, error) { +// +// The path arrives over an IPC any local user can reach and is later opened by +// a root daemon, so it is constrained to the file name the UI writes and to a +// local absolute path. Authorization happens when DebugBundle opens it: the +// bundle refuses a file its requester does not own. A caller the daemon cannot +// identify cannot register a path at all. +func (s *Server) RegisterUILog(callerCtx context.Context, req *proto.RegisterUILogRequest) (*proto.RegisterUILogResponse, error) { + if _, ok := ipcauth.CallerIdentity(callerCtx); !ok { + return nil, gstatus.Error(codes.PermissionDenied, + "registering a UI log path requires a control channel that carries the caller's identity") + } + + path := filepath.Clean(req.GetPath()) + if !filepath.IsAbs(path) || filepath.Base(path) != uiLogFileName { + return nil, gstatus.Errorf(codes.InvalidArgument, "UI log path must be an absolute path ending in %s", uiLogFileName) + } + // filepath.IsAbs accepts a Windows UNC path (\\host\share\...) and a device + // path (\\.\, \\?\); opening one would make the root daemon reach a remote + // or device namespace. Require a plain local path. + if strings.HasPrefix(path, `\\`) { + return nil, gstatus.Error(codes.InvalidArgument, "UI log path must be a local path, not a UNC or device path") + } + s.mutex.Lock() defer s.mutex.Unlock() - s.uiLogPath = req.GetPath() - log.Infof("registered UI log path: %s", s.uiLogPath) + s.uiLogPath = path + log.Infof("registered UI log path %s", s.uiLogPath) return &proto.RegisterUILogResponse{}, nil } diff --git a/client/server/debug_gate.go b/client/server/debug_gate.go new file mode 100644 index 000000000..983a13aaf --- /dev/null +++ b/client/server/debug_gate.go @@ -0,0 +1,99 @@ +//go:build !android && !ios + +package server + +import ( + "context" + "fmt" + "net/url" + "os" + "strings" + + "google.golang.org/grpc/codes" + gstatus "google.golang.org/grpc/status" + + "github.com/netbirdio/netbird/client/configs" + "github.com/netbirdio/netbird/client/internal/debug" + "github.com/netbirdio/netbird/client/internal/ipcauth" + "github.com/netbirdio/netbird/upload-server/types" +) + +// uiLogFileName is the only file name the daemon accepts as a UI log path. The +// UI (writer), this validation, and the bundle collector all read it from +// configs so they cannot drift. +const uiLogFileName = configs.UILogFile + +// uiLogOpener opens the registered UI log, and its rotated siblings, on behalf +// of the caller requesting the bundle: OpenOwnedFile then collects the log only +// when that caller owns it (or is privileged). identified is false on a socket +// that carries no caller identity, in which case nothing is opened. +func uiLogOpener(id ipcauth.Identity, identified bool) debug.LogOpener { + return func(path string) (*os.File, error) { + if !identified { + return nil, fmt.Errorf("bundle requester has no verified identity") + } + return ipcauth.OpenOwnedFile(id, path) + } +} + +// requirePrivilegeForUploadURL restricts where the daemon may send a debug +// bundle. The bundle holds the daemon's own logs and state, and the daemon +// fetches the upload URL itself, so an unrestricted endpoint turns the daemon +// into both an exfiltration channel and a request forwarder that reaches +// services only it can talk to. +// +// The upload service NetBird publishes is open to any caller, since that is what +// the CLI and the desktop UI use. Any other endpoint, self-hosted upload servers +// included, requires a privileged caller. Plaintext is refused for everyone: the +// daemon fetches the URL and then PUTs the bundle to whatever that fetch returns, +// so an http hop is a place to intercept the bundle or the redirect. +// +// insecure relaxes transport security (http, or an untrusted TLS certificate) +// for a self-hosted server. It weakens a root-privileged upload, so it is +// refused for an unprivileged caller regardless of the host. +func requirePrivilegeForUploadURL(ctx context.Context, rawURL string, insecure bool) error { + if rawURL == "" { + return nil + } + + parsed, err := url.Parse(rawURL) + if err != nil { + return gstatus.Errorf(codes.InvalidArgument, "parse upload URL: %v", err) + } + + // --insecure relaxes https to http or an untrusted certificate; it does not + // widen the URL to arbitrary schemes, so a host and http/https are required + // before the insecure branch takes over. + if parsed.Host == "" || (parsed.Scheme != "https" && parsed.Scheme != "http") { + return gstatus.Errorf(codes.InvalidArgument, "upload URL must be http or https with a host") + } + + if insecure { + return denyPrivileged(ctx, + "uploading a debug bundle without transport security (--upload-bundle-insecure)", + ipcauth.ElevatedCommand("netbird debug bundle -U --upload-bundle-insecure --upload-bundle-url ")) + } + + if parsed.Scheme != "https" { + return gstatus.Errorf(codes.InvalidArgument, "upload URL must use https, got scheme %q", parsed.Scheme) + } + + if isDefaultUploadService(parsed) { + return nil + } + + return denyPrivileged(ctx, + "uploading a debug bundle to an upload service other than the default one", + ipcauth.ElevatedCommand("netbird debug bundle -U --upload-bundle-url ")) +} + +// isDefaultUploadService reports whether the URL points at the upload service +// NetBird runs. Only the host is compared: the service's path may differ between +// releases, and the host is what decides who receives the bundle. +func isDefaultUploadService(parsed *url.URL) bool { + defaultURL, err := url.Parse(types.DefaultBundleURL) + if err != nil { + return false + } + return parsed.Scheme == defaultURL.Scheme && strings.EqualFold(parsed.Host, defaultURL.Host) +} diff --git a/client/server/debug_gate_test.go b/client/server/debug_gate_test.go new file mode 100644 index 000000000..e958fc581 --- /dev/null +++ b/client/server/debug_gate_test.go @@ -0,0 +1,157 @@ +//go:build !android && !ios + +package server + +import ( + "os" + "path/filepath" + "runtime" + "testing" + + "google.golang.org/grpc/codes" + gstatus "google.golang.org/grpc/status" + + "github.com/netbirdio/netbird/client/internal/ipcauth" + "github.com/netbirdio/netbird/client/proto" + "github.com/netbirdio/netbird/upload-server/types" +) + +func TestRegisterUILogRefusesUnidentifiedCaller(t *testing.T) { + s := &Server{} + + _, err := s.RegisterUILog(noIdentityCtx(), &proto.RegisterUILogRequest{ + Path: filepath.Join(t.TempDir(), uiLogFileName), + }) + + if gstatus.Code(err) != codes.PermissionDenied { + t.Fatalf("code = %v, want PermissionDenied", gstatus.Code(err)) + } +} + +func TestRegisterUILogRefusesForeignPath(t *testing.T) { + secret := "/etc/shadow" + if runtime.GOOS == "windows" { + secret = `C:\Windows\System32\config\SAM` + } + + tests := []struct { + name string + path string + }{ + {"empty", ""}, + {"relative", filepath.Join("netbird", uiLogFileName)}, + {"another file", secret}, + {"directory of the log", t.TempDir()}, + {"unc path", `\\attacker\share\` + uiLogFileName}, + {"device path", `\\.\C:\` + uiLogFileName}, + } + + for _, tc := range tests { + t.Run(tc.name, func(t *testing.T) { + s := &Server{} + + _, err := s.RegisterUILog(userCtx(), &proto.RegisterUILogRequest{Path: tc.path}) + + if gstatus.Code(err) != codes.InvalidArgument { + t.Fatalf("code = %v, want InvalidArgument", gstatus.Code(err)) + } + if s.uiLogPath != "" { + t.Fatalf("path %q was recorded despite the refusal", s.uiLogPath) + } + }) + } +} + +func TestRegisterUILogRecordsPath(t *testing.T) { + s := &Server{} + path := filepath.Join(t.TempDir(), uiLogFileName) + + if _, err := s.RegisterUILog(userCtx(), &proto.RegisterUILogRequest{Path: path}); err != nil { + t.Fatalf("register: %v", err) + } + + if s.uiLogPath != path { + t.Fatalf("path = %q, want %q", s.uiLogPath, path) + } +} + +// The UI log is opened as the bundle requester, so a second local user cannot +// collect a log they do not own, and an unidentified requester collects nothing. +func TestUILogOpenerBindsToRequester(t *testing.T) { + path := filepath.Join(t.TempDir(), uiLogFileName) + if err := os.WriteFile(path, []byte("log line"), 0600); err != nil { + t.Fatalf("write log: %v", err) + } + + // A different unprivileged user than the file's owner: refused. + if _, err := uiLogOpener(unprivilegedIdentity(), true)(path); err == nil { + t.Fatal("expected a file the requester does not own to be refused") + } + + // No verified identity: refused. + if _, err := uiLogOpener(ipcauth.Identity{}, false)(path); err == nil { + t.Fatal("expected an unidentified requester to be refused") + } + + // The requester that owns the file: allowed. The test process created it, so + // its own identity is the owner (and a privileged runner is exempt anyway). + owner, err := ipcauth.CurrentProcessIdentity() + if err != nil { + t.Fatalf("current identity: %v", err) + } + f, err := uiLogOpener(owner, true)(path) + if err != nil { + t.Fatalf("expected the owning requester to be allowed, got %v", err) + } + _ = f.Close() +} + +func TestRequirePrivilegeForUploadURL(t *testing.T) { + tests := []struct { + name string + url string + insecure bool + unprivOK bool + invalid bool + rootAlso bool + }{ + {name: "no upload", url: "", unprivOK: true}, + {name: "default service", url: types.DefaultBundleURL, unprivOK: true}, + {name: "default service, other path", url: "https://upload.debug.netbird.io/other", unprivOK: true}, + {name: "loopback exfiltration endpoint", url: "https://127.0.0.1:8080/upload-url", rootAlso: true}, + {name: "custom upload service", url: "https://attacker.example/upload-url", rootAlso: true}, + {name: "plaintext default host", url: "http://upload.debug.netbird.io/upload-url", invalid: true}, + {name: "plaintext custom host", url: "http://attacker.example/upload-url", invalid: true}, + {name: "unsupported scheme", url: "file:///etc/shadow", invalid: true}, + // insecure relaxes transport security; privileged only, whatever the host. + {name: "insecure http custom", url: "http://selfhosted.local/upload-url", insecure: true, rootAlso: true}, + {name: "insecure https custom", url: "https://selfhosted.local/upload-url", insecure: true, rootAlso: true}, + {name: "insecure default host", url: types.DefaultBundleURL, insecure: true, rootAlso: true}, + // --insecure must not widen the URL to non-http(s) schemes or a hostless URL. + {name: "insecure file scheme", url: "file:///etc/shadow", insecure: true, invalid: true}, + {name: "insecure hostless", url: "https:///upload-url", insecure: true, invalid: true}, + } + + for _, tc := range tests { + t.Run(tc.name, func(t *testing.T) { + err := requirePrivilegeForUploadURL(userCtx(), tc.url, tc.insecure) + + switch { + case tc.invalid: + if gstatus.Code(err) != codes.InvalidArgument { + t.Fatalf("code = %v, want InvalidArgument", gstatus.Code(err)) + } + return + case tc.unprivOK: + assertAllowed(t, err) + return + default: + assertDenied(t, err) + } + + if tc.rootAlso { + assertAllowed(t, requirePrivilegeForUploadURL(rootCtx(), tc.url, tc.insecure)) + } + }) + } +} diff --git a/client/server/lock_order_test.go b/client/server/lock_order_test.go new file mode 100644 index 000000000..457e3db34 --- /dev/null +++ b/client/server/lock_order_test.go @@ -0,0 +1,51 @@ +package server + +import ( + "testing" + "time" + + "github.com/stretchr/testify/require" + + "github.com/netbirdio/netbird/client/proto" +) + +// The daemon takes guardedConfigMu before s.mutex. authorizeAndPrepareLogin +// takes s.mutex while holding guardedConfigMu, so a SetConfig that grabbed +// s.mutex first and then waited for guardedConfigMu would deadlock the daemon +// against a concurrent login: two unprivileged IPC calls are enough. +// +// The held guardedConfigMu below stands in for that login. While SetConfig waits +// for it, s.mutex must stay free, otherwise the login waiting for s.mutex could +// never release guardedConfigMu. +func TestSetConfig_TakesGuardedConfigMuBeforeServerMutex(t *testing.T) { + s, ctx, profName, username, _ := setupServerWithProfile(t) + + s.guardedConfigMu.Lock() + + done := make(chan error, 1) + go func() { + _, err := s.SetConfig(ctx, &proto.SetConfigRequest{ + ProfileName: profName, + Username: username, + }) + done <- err + }() + + require.Never(t, func() bool { + if !s.mutex.TryLock() { + return true + } + s.mutex.Unlock() + return false + }, 500*time.Millisecond, 10*time.Millisecond, + "SetConfig held s.mutex while waiting for guardedConfigMu, which deadlocks against a concurrent login") + + s.guardedConfigMu.Unlock() + + select { + case err := <-done: + require.NoError(t, err) + case <-time.After(5 * time.Second): + t.Fatal("SetConfig did not finish after guardedConfigMu was released") + } +} diff --git a/client/server/login_gate_test.go b/client/server/login_gate_test.go new file mode 100644 index 000000000..de62a8180 --- /dev/null +++ b/client/server/login_gate_test.go @@ -0,0 +1,127 @@ +package server + +import ( + "context" + "path/filepath" + "testing" + + "github.com/stretchr/testify/require" + "google.golang.org/grpc/codes" + gstatus "google.golang.org/grpc/status" + + "github.com/netbirdio/netbird/client/internal" + "github.com/netbirdio/netbird/client/internal/profilemanager" + "github.com/netbirdio/netbird/client/proto" +) + +// A refused login must not leave the profile switched. Login can both switch +// profiles and carry the guarded config fields, so the gate has to run before the +// switch: otherwise a caller whose change is refused still gets the side effect of +// activating whichever profile the request named. +func TestLogin_RefusedChangeLeavesTheProfileAlone(t *testing.T) { + s, _, activeProfile, username, _ := setupServerWithProfile(t) + + // Login reads process state off the daemon's root context. + s.rootCtx = internal.CtxInitState(context.Background()) + + // A second profile that runs the SSH server, which is what makes repointing + // its management binding a privileged change. + target := "ssh-enabled" + _, err := profilemanager.UpdateOrCreateConfig(profilemanager.ConfigInput{ + ConfigPath: filepath.Join(profilemanager.DefaultConfigPathDir, target+".json"), + ManagementURL: "https://api.netbird.io:443", + ServerSSHAllowed: boolPtr(true), + }) + require.NoError(t, err) + + _, err = s.Login(userCtx(), &proto.LoginRequest{ + ProfileName: &target, + Username: &username, + ManagementUrl: "https://mgmt.attacker.example:443", + }) + require.Error(t, err, "an unprivileged caller must not move the management URL of an SSH-enabled profile") + require.Equal(t, codes.PermissionDenied, gstatus.Code(err), "want a privilege refusal, got %v", err) + + active, err := s.profileManager.GetActiveProfileState() + require.NoError(t, err) + require.Equal(t, profilemanager.ID(activeProfile), active.ID, + "the refused login switched the active profile anyway") +} + +// A caller whose change becomes privileged only after its first check must be +// refused without having cancelled a login or switched profiles: the first check is +// unsynchronized, so the SSH server can be enabled by a concurrent privileged +// request in between, and the authoritative check happens before any side effect. +func TestLogin_ChangeThatBecomesPrivilegedMidRequestHasNoSideEffects(t *testing.T) { + s, _, activeProfile, username, _ := setupServerWithProfile(t) + s.rootCtx = internal.CtxInitState(context.Background()) + + // The target profile has SSH off, so the first check lets the request through. + target := "ssh-later" + targetPath := filepath.Join(profilemanager.DefaultConfigPathDir, target+".json") + _, err := profilemanager.UpdateOrCreateConfig(profilemanager.ConfigInput{ + ConfigPath: targetPath, + ManagementURL: "https://api.netbird.io:443", + ServerSSHAllowed: boolPtr(false), + }) + require.NoError(t, err) + + cancelled := false + s.actCancel = func() { cancelled = true } + + // Stand in for a privileged SetConfig that enables the SSH server between the + // two checks, which is the interleaving the lock has to make safe. + afterLoginPreCheck = func() { + _, err := profilemanager.UpdateOrCreateConfig(profilemanager.ConfigInput{ + ConfigPath: targetPath, + ServerSSHAllowed: boolPtr(true), + }) + require.NoError(t, err) + } + t.Cleanup(func() { afterLoginPreCheck = nil }) + + _, err = s.Login(userCtx(), &proto.LoginRequest{ + ProfileName: &target, + Username: &username, + ManagementUrl: "https://mgmt.attacker.example:443", + }) + require.Error(t, err) + require.Equal(t, codes.PermissionDenied, gstatus.Code(err), "want a privilege refusal, got %v", err) + require.False(t, cancelled, "the refused login cancelled the login already in progress") + + active, err := s.profileManager.GetActiveProfileState() + require.NoError(t, err) + require.Equal(t, profilemanager.ID(activeProfile), active.ID, "the refused login switched the active profile anyway") + + stored, err := profilemanager.ReadConfig(targetPath) + require.NoError(t, err) + require.Equal(t, "https://api.netbird.io:443", stored.ManagementURL.String(), "the refused login moved the management URL") +} + +// Login cancels whatever login is already in progress before starting its own. A +// refused caller must not get that far, otherwise anyone able to reach the socket +// can abort someone else's login by sending a request that is denied. +func TestLogin_RefusedChangeLeavesAnInProgressLoginAlone(t *testing.T) { + s, _, _, username, _ := setupServerWithProfile(t) + s.rootCtx = internal.CtxInitState(context.Background()) + + target := "ssh-enabled" + _, err := profilemanager.UpdateOrCreateConfig(profilemanager.ConfigInput{ + ConfigPath: filepath.Join(profilemanager.DefaultConfigPathDir, target+".json"), + ManagementURL: "https://api.netbird.io:443", + ServerSSHAllowed: boolPtr(true), + }) + require.NoError(t, err) + + cancelled := false + s.actCancel = func() { cancelled = true } + + _, err = s.Login(userCtx(), &proto.LoginRequest{ + ProfileName: &target, + Username: &username, + ManagementUrl: "https://mgmt.attacker.example:443", + }) + require.Error(t, err) + require.Equal(t, codes.PermissionDenied, gstatus.Code(err), "want a privilege refusal, got %v", err) + require.False(t, cancelled, "the refused login cancelled the login already in progress") +} diff --git a/client/server/network.go b/client/server/network.go index c38715256..c390b8180 100644 --- a/client/server/network.go +++ b/client/server/network.go @@ -8,7 +8,6 @@ import ( "sort" "strings" - "golang.org/x/exp/maps" "google.golang.org/grpc/codes" gstatus "google.golang.org/grpc/status" @@ -161,30 +160,11 @@ func (s *Server) SelectNetworks(_ context.Context, req *proto.SelectNetworksRequ return nil, fmt.Errorf("no route manager") } - routeSelector := routeManager.GetRouteSelector() if req.GetAll() { - routeSelector.SelectAllRoutes() - } else { - routes := toNetIDs(req.GetNetworkIDs()) - routesMap := routeManager.GetClientRoutesWithNetID() - routes = route.ExpandV6ExitPairs(routes, routesMap) - netIdRoutes := maps.Keys(routesMap) - if err := routeSelector.SelectRoutes(routes, req.GetAppend(), netIdRoutes); err != nil { - return nil, fmt.Errorf("select routes: %w", err) - } - - // Exit nodes are mutually exclusive: if this selection activates an - // exit node, deselect every other available exit node so two can't be - // selected at once. Non-exit route selections are left untouched. - if requestActivatesExitNode(routes, routesMap) { - if others := otherExitNodeIDs(routesMap, routes); len(others) > 0 { - if err := routeSelector.DeselectRoutes(others, netIdRoutes); err != nil { - return nil, fmt.Errorf("deselect sibling exit nodes: %w", err) - } - } - } + routeManager.SelectAllRoutes() + } else if err := routeManager.SelectRoutes(toNetIDs(req.GetNetworkIDs()), req.GetAppend()); err != nil { + return nil, err } - routeManager.TriggerSelection(routeManager.GetClientRoutes()) s.statusRecorder.PublishEvent( proto.SystemEvent_INFO, @@ -224,19 +204,11 @@ func (s *Server) DeselectNetworks(_ context.Context, req *proto.SelectNetworksRe return nil, fmt.Errorf("no route manager") } - routeSelector := routeManager.GetRouteSelector() if req.GetAll() { - routeSelector.DeselectAllRoutes() - } else { - routes := toNetIDs(req.GetNetworkIDs()) - routesMap := routeManager.GetClientRoutesWithNetID() - routes = route.ExpandV6ExitPairs(routes, routesMap) - netIdRoutes := maps.Keys(routesMap) - if err := routeSelector.DeselectRoutes(routes, netIdRoutes); err != nil { - return nil, fmt.Errorf("deselect routes: %w", err) - } + routeManager.DeselectAllRoutes() + } else if err := routeManager.DeselectRoutes(toNetIDs(req.GetNetworkIDs())); err != nil { + return nil, err } - routeManager.TriggerSelection(routeManager.GetClientRoutes()) s.statusRecorder.PublishEvent( proto.SystemEvent_INFO, @@ -261,37 +233,3 @@ func toNetIDs(routes []string) []route.NetID { return netIDs } -func isExitNodeRoutes(routes []*route.Route) bool { - return len(routes) > 0 && (route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network)) -} - -// requestActivatesExitNode reports whether any requested NetID maps to an exit -// node (default route) in the current route table. -func requestActivatesExitNode(requested []route.NetID, routesMap map[route.NetID][]*route.Route) bool { - for _, id := range requested { - if isExitNodeRoutes(routesMap[id]) { - return true - } - } - return false -} - -// otherExitNodeIDs returns every available exit-node NetID that is not in the -// requested set — the siblings to deselect so a single exit node stays active. -func otherExitNodeIDs(routesMap map[route.NetID][]*route.Route, requested []route.NetID) []route.NetID { - keep := make(map[route.NetID]struct{}, len(requested)) - for _, id := range requested { - keep[id] = struct{}{} - } - var others []route.NetID - for id, routes := range routesMap { - if !isExitNodeRoutes(routes) { - continue - } - if _, ok := keep[id]; ok { - continue - } - others = append(others, id) - } - return others -} diff --git a/client/server/network_exitnode_test.go b/client/server/network_exitnode_test.go deleted file mode 100644 index 1c0ba0ecb..000000000 --- a/client/server/network_exitnode_test.go +++ /dev/null @@ -1,26 +0,0 @@ -package server - -import ( - "net/netip" - "testing" - - "github.com/stretchr/testify/assert" - - "github.com/netbirdio/netbird/route" -) - -func TestExitNodeSelectionHelpers(t *testing.T) { - routesMap := map[route.NetID][]*route.Route{ - "exitA": {{Network: netip.MustParsePrefix("0.0.0.0/0")}}, - "exitB": {{Network: netip.MustParsePrefix("::/0")}}, - "lan": {{Network: netip.MustParsePrefix("192.168.0.0/16")}}, - } - - assert.True(t, requestActivatesExitNode([]route.NetID{"exitA"}, routesMap), "v4 default route is an exit node") - assert.True(t, requestActivatesExitNode([]route.NetID{"exitB"}, routesMap), "v6 default route is an exit node") - assert.False(t, requestActivatesExitNode([]route.NetID{"lan"}, routesMap), "lan route is not an exit node") - assert.False(t, requestActivatesExitNode([]route.NetID{"missing"}, routesMap), "unknown id is not an exit node") - - others := otherExitNodeIDs(routesMap, []route.NetID{"exitB"}) - assert.ElementsMatch(t, []route.NetID{"exitA"}, others, "only the other exit node is a sibling; the lan route is ignored") -} diff --git a/client/server/server.go b/client/server/server.go index 363f716a9..aaab5cc02 100644 --- a/client/server/server.go +++ b/client/server/server.go @@ -72,6 +72,9 @@ type Server struct { // RegisterUILog. Guarded by mutex. Consumed by DebugBundle so the bundle // can collect the GUI log even though the daemon runs as root and can't // resolve the user's config dir. Last-writer-wins (one UI per socket). + // DebugBundle opens it on behalf of the bundle requester and refuses a file + // that caller does not own, so a local user cannot read another user's log + // or a root-only file through it. uiLogPath string oauthAuthFlow oauthAuthFlow @@ -82,6 +85,12 @@ type Server struct { // extend flow or vice versa. extendAuthSessionFlow *auth.PendingFlow + // guardedConfigMu serializes a privilege check against the write it + // authorizes. Without it the two are separate steps over the same file, and a + // change that was allowed because the profile had the SSH server disabled + // could land after a concurrent privileged request enabled it. + guardedConfigMu sync.Mutex + mutex sync.Mutex config *profilemanager.Config proto.UnimplementedDaemonServiceServer @@ -181,7 +190,7 @@ func (s *Server) Start() error { log.Warnf("failed to redirect stderr: %v", err) } - if err := restoreResidualState(s.rootCtx, s.profileManager.GetStatePath()); err != nil { + if err := RestoreResidualState(s.rootCtx, s.profileManager.GetStatePath()); err != nil { log.Warnf(errRestoreResidualState, err) } @@ -387,6 +396,16 @@ func (s *Server) loginAttempt(ctx context.Context, setupKey, jwtToken string) (i // Login uses setup key to prepare configuration for the daemon. func (s *Server) SetConfig(callerCtx context.Context, msg *proto.SetConfigRequest) (*proto.SetConfigResponse, error) { + // Privilege gate: refuse the parts of the request that would let a local + // user turn the root daemon into a root shell. Held across the write so the + // config cannot gain the SSH server between the decision and the update. + // + // Taken before s.mutex: authorizeAndPrepareLogin takes s.mutex while holding + // guardedConfigMu, so acquiring the two in the other order here would let a + // concurrent login deadlock the daemon. + s.guardedConfigMu.Lock() + defer s.guardedConfigMu.Unlock() + s.mutex.Lock() defer s.mutex.Unlock() @@ -411,6 +430,14 @@ func (s *Server) SetConfig(callerCtx context.Context, msg *proto.SetConfigReques return nil, err } + stored, err := s.storedProfileConfig(msg.ProfileName, msg.Username) + if err != nil { + return nil, err + } + if err := requirePrivilegeForConfigChange(callerCtx, stored, privilegedChangeFromSetConfig(msg)); err != nil { + return nil, err + } + config, err := s.setConfigInputFromRequest(msg) if err != nil { return nil, err @@ -537,22 +564,23 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro } } - s.mutex.Lock() - if s.actCancel != nil { - s.actCancel() - } - ctx, cancel := context.WithCancel(callerCtx) - - md, ok := metadata.FromIncomingContext(callerCtx) - if ok { - ctx = metadata.NewOutgoingContext(ctx, md) + activeProf, err := s.profileManager.GetActiveProfileState() + if err != nil { + log.Errorf("failed to get active profile state: %v", err) + return nil, fmt.Errorf("failed to get active profile state: %w", err) } - s.actCancel = cancel - s.mutex.Unlock() - - if err := restoreResidualState(s.rootCtx, s.profileManager.GetStatePath()); err != nil { - log.Warnf(errRestoreResidualState, err) + // Privilege gate: same restrictions as SetConfig, since LoginRequest can carry + // the same fields. It runs before anything here changes daemon state, so a + // refused login neither switches the profile nor cancels a login already in + // progress, and it reads the profile the request targets, which is the one the + // switch below would activate. + stored, err := s.storedLoginConfig(activeProf, msg) + if err != nil { + return nil, err + } + if err := requirePrivilegeForConfigChange(callerCtx, stored, privilegedChangeFromLogin(msg)); err != nil { + return nil, err } state := internal.CtxGetState(s.rootCtx) @@ -563,23 +591,16 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro } }() - activeProf, err := s.profileManager.GetActiveProfileState() + ctx, activeProf, err := s.authorizeAndPrepareLogin(callerCtx, msg, activeProf) if err != nil { - log.Errorf("failed to get active profile state: %v", err) - return nil, fmt.Errorf("failed to get active profile state: %w", err) - } - - if msg.ProfileName != nil { - if _, err := s.switchProfileIfNeeded(*msg.ProfileName, msg.Username, activeProf); err != nil { - log.Errorf("failed to switch profile: %v", err) - return nil, err + // The RPC boundary is where this gets recorded: nothing logs handler + // errors for us, and a caller that retries would otherwise leave no + // trace in the daemon log. A refusal is skipped because the gate has + // already logged the decision, with the caller's identity. + if gstatus.Code(err) != codes.PermissionDenied { + log.Errorf("failed to prepare login: %v", err) } - } - - activeProf, err = s.profileManager.GetActiveProfileState() - if err != nil { - log.Errorf("failed to get active profile state: %v", err) - return nil, fmt.Errorf("failed to get active profile state: %w", err) + return nil, err } log.Infof("active profile: %s for %s", activeProf.ID, activeProf.Username) @@ -593,11 +614,6 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro s.mutex.Unlock() - if err := persistLoginOverrides(activeProf, msg.ManagementUrl, msg.OptionalPreSharedKey); err != nil { - log.Errorf("failed to persist login overrides: %v", err) - return nil, fmt.Errorf("persist login overrides: %w", err) - } - config, _, err := s.getConfig(activeProf) if err != nil { log.Errorf("failed to get active profile config: %v", err) @@ -828,6 +844,7 @@ func (s *Server) WaitSSOLogin(callerCtx context.Context, msg *proto.WaitSSOLogin return nil, err } + log.Infof("SSO login flow finished, returning success to caller") return &proto.WaitSSOLoginResponse{ Email: tokenInfo.Email, }, nil @@ -835,6 +852,7 @@ func (s *Server) WaitSSOLogin(callerCtx context.Context, msg *proto.WaitSSOLogin // Up starts engine work in the daemon. func (s *Server) Up(callerCtx context.Context, msg *proto.UpRequest) (*proto.UpResponse, error) { + log.Infof("up request received") s.mutex.Lock() // clientRunning is the daemon-intent flag (set by previous Up/Start, cleared // by Down). connectionGoroutineRunning() reports whether the previous retry-loop @@ -856,7 +874,7 @@ func (s *Server) Up(callerCtx context.Context, msg *proto.UpRequest) (*proto.UpR return s.waitForUp(callerCtx) } - if err := restoreResidualState(callerCtx, s.profileManager.GetStatePath()); err != nil { + if err := RestoreResidualState(callerCtx, s.profileManager.GetStatePath()); err != nil { log.Warnf(errRestoreResidualState, err) } @@ -978,6 +996,63 @@ func (s *Server) waitForUp(callerCtx context.Context) (*proto.UpResponse, error) } } +// storedProfileConfig loads the on-disk config of the profile a request +// targets, so a privileged-change decision can be made against the values the +// profile currently holds. A profile that has no config file yet yields nil, +// which every caller must read as "nothing enabled yet". +func (s *Server) storedProfileConfig(handle, username string) (*profilemanager.Config, error) { + resolved, err := s.resolveProfileHandle(handle, username) + if err != nil { + return nil, err + } + + path := resolved.Path + if path == "" { + path = profilemanager.DefaultConfigPath + } + + return s.storedConfigAtPath(path) +} + +// storedLoginConfig loads the on-disk config of the profile a login request +// targets: the one it names, or the active one when it names none. Used to decide +// a privileged change before the request is allowed to switch profiles. +func (s *Server) storedLoginConfig(activeProf *profilemanager.ActiveProfileState, msg *proto.LoginRequest) (*profilemanager.Config, error) { + if msg.ProfileName == nil { + cfgPath, err := activeProf.FilePath() + if err != nil { + return nil, fmt.Errorf("active profile file path: %w", err) + } + return s.storedConfigAtPath(cfgPath) + } + + // Mirrors switchProfileIfNeeded: the default profile resolves without a + // username, so this reads the same profile the switch would activate. + handle := *msg.ProfileName + username := "" + if handle != profilemanager.DefaultProfileName { + username = msg.GetUsername() + } + return s.storedProfileConfig(handle, username) +} + +// storedConfigAtPath reads a profile config file, yielding nil when it does not +// exist yet. +func (s *Server) storedConfigAtPath(path string) (*profilemanager.Config, error) { + if _, err := os.Stat(path); err != nil { + if os.IsNotExist(err) { + return nil, nil //nolint:nilnil + } + return nil, fmt.Errorf("stat profile config: %w", err) + } + + cfg, err := profilemanager.GetConfig(path) + if err != nil { + return nil, fmt.Errorf("read profile config: %w", err) + } + return cfg, nil +} + // resolveProfileHandle resolves a wire-level profile handle (display // name, ID, or unique ID prefix) to a concrete profile. Returns gRPC // status errors so handlers can return them directly. @@ -1079,7 +1154,10 @@ func (s *Server) Down(ctx context.Context, _ *proto.DownRequest) (*proto.DownRes if err := s.cleanupConnection(); err != nil { s.mutex.Unlock() - // todo review to update the status in case any type of error + if errors.Is(err, ErrServiceNotUp) { + log.Debugf("Down called while service not up: %v", err) + return nil, err + } log.Errorf("failed to shut down properly: %v", err) return nil, err } @@ -1152,7 +1230,7 @@ func (s *Server) cleanupConnection() error { // making the run loop the sole owner of engine shutdown. if engine != nil { if err := engine.Stop(); err != nil { - return err + log.Errorf("failed to stop engine during cleanup: %v", err) } } @@ -1192,6 +1270,12 @@ func (s *Server) handleProfileLogout(ctx context.Context, msg *proto.LogoutReque if err := s.logoutFromProfile(ctx, resolved); err != nil { log.Errorf("failed to logout from profile %s: %v", resolved.ID, err) + // A refused deregistration is already a status error carrying the reason + // and the command to run; rewrapping it as Internal would flatten both + // into a gRPC dump for the user. + if _, isStatus := gstatus.FromError(err); isStatus { + return nil, err + } return nil, gstatus.Errorf(codes.Internal, "logout: %v", err) } @@ -1313,6 +1397,13 @@ func (s *Server) sendLogoutRequest(ctx context.Context) error { } func (s *Server) sendLogoutRequestWithConfig(ctx context.Context, config *profilemanager.Config) error { + // Privilege gate: deregistering frees this machine's key to be registered + // against another management server, which is only restricted while the SSH + // server makes that a privilege handover. + if err := requirePrivilegeForDeregistration(ctx, config); err != nil { + return err + } + key, err := wgtypes.ParseKey(config.PrivateKey) if err != nil { return fmt.Errorf("parse private key: %w", err) @@ -2058,7 +2149,10 @@ func (s *Server) RemoveProfile(ctx context.Context, msg *proto.RemoveProfileRequ } if err := s.logoutFromProfile(ctx, resolved); err != nil { - log.Warnf("failed to logout from profile %s before removal: %v", resolved.ID, err) + // Deregistration is best-effort here: the local profile is removed + // either way, so an unprivileged caller leaves the peer registered on + // the management server rather than being blocked from removing it. + log.Warnf("removing profile %s locally without deregistering it: %v", resolved.ID, err) } if err := s.profileManager.RemoveProfile(resolved.ID, msg.Username); err != nil { @@ -2355,6 +2449,69 @@ func sendTerminalNotification() error { // persistLoginOverrides writes management URL and pre-shared key from a LoginRequest to the // active profile config so that subsequent reads pick them up. Empty/nil values are ignored. +// afterLoginPreCheck is a seam for tests to run a concurrent config change +// between Login's first privilege check and the authoritative one. +var afterLoginPreCheck func() + +// authorizeAndPrepareLogin makes the authoritative privilege decision for a login +// and, when it passes, carries out every state change that decision authorizes: +// cancelling an login already in progress, switching to the requested profile, and +// persisting the config overrides the request carries. +// +// All of it happens under guardedConfigMu, which SetConfig also holds across its +// own check and write. Login's earlier check refuses the ordinary case before any +// of this is reached; this one exists because that check is not synchronized +// against a concurrent privileged request that enables the SSH server, and a +// caller refused here must not have cancelled or switched anything either. +func (s *Server) authorizeAndPrepareLogin(callerCtx context.Context, msg *proto.LoginRequest, activeProf *profilemanager.ActiveProfileState) (context.Context, *profilemanager.ActiveProfileState, error) { + if afterLoginPreCheck != nil { + afterLoginPreCheck() + } + + s.guardedConfigMu.Lock() + defer s.guardedConfigMu.Unlock() + + stored, err := s.storedLoginConfig(activeProf, msg) + if err != nil { + return nil, nil, err + } + if err := requirePrivilegeForConfigChange(callerCtx, stored, privilegedChangeFromLogin(msg)); err != nil { + return nil, nil, err + } + + s.mutex.Lock() + if s.actCancel != nil { + s.actCancel() + } + ctx, cancel := context.WithCancel(callerCtx) + if md, ok := metadata.FromIncomingContext(callerCtx); ok { + ctx = metadata.NewOutgoingContext(ctx, md) + } + s.actCancel = cancel + s.mutex.Unlock() + + if err := RestoreResidualState(s.rootCtx, s.profileManager.GetStatePath()); err != nil { + log.Warnf(errRestoreResidualState, err) + } + + if msg.ProfileName != nil { + if _, err := s.switchProfileIfNeeded(*msg.ProfileName, msg.Username, activeProf); err != nil { + return nil, nil, fmt.Errorf("switch profile: %w", err) + } + } + + activeProf, err = s.profileManager.GetActiveProfileState() + if err != nil { + return nil, nil, fmt.Errorf("active profile state: %w", err) + } + + if err := persistLoginOverrides(activeProf, msg.ManagementUrl, msg.OptionalPreSharedKey); err != nil { + return nil, nil, fmt.Errorf("persist login overrides: %w", err) + } + + return ctx, activeProf, nil +} + func persistLoginOverrides(activeProf *profilemanager.ActiveProfileState, managementURL string, preSharedKey *string) error { if preSharedKey != nil && *preSharedKey == "" { preSharedKey = nil diff --git a/client/server/setconfig_mdm_test.go b/client/server/setconfig_mdm_test.go index 9baf16136..ae323ea8c 100644 --- a/client/server/setconfig_mdm_test.go +++ b/client/server/setconfig_mdm_test.go @@ -66,7 +66,11 @@ func setupServerWithProfile(t *testing.T) (s *Server, ctx context.Context, profN Username: currUser.Username, })) - ctx = context.Background() + // The privileged-change gate reads the caller's kernel identity from the + // context, which a real caller gets from the daemon's transport credentials. + // This test drives the handler directly, so it stands in for a root caller; + // without an identity the gate would (correctly) refuse the SSH fields. + ctx = privilegedTestCtx() s = New(ctx, "console", "", false, false, false, false) return s, ctx, profName, currUser.Username, cfgPath } diff --git a/client/server/setconfig_test.go b/client/server/setconfig_test.go index 0e55257a9..db7a26f03 100644 --- a/client/server/setconfig_test.go +++ b/client/server/setconfig_test.go @@ -1,7 +1,6 @@ package server import ( - "context" "os/user" "path/filepath" "reflect" @@ -52,7 +51,11 @@ func TestSetConfig_AllFieldsSaved(t *testing.T) { }) require.NoError(t, err) - ctx := context.Background() + // The privileged-change gate reads the caller's kernel identity from the + // context, which a real caller gets from the daemon's transport credentials. + // This test drives the handler directly, so it stands in for a root caller; + // without an identity the gate would (correctly) refuse the SSH fields. + ctx := privilegedTestCtx() s := New(ctx, "console", "", false, false, false, false) rosenpassEnabled := true diff --git a/client/server/ssh_gate.go b/client/server/ssh_gate.go new file mode 100644 index 000000000..ca1b4c4ee --- /dev/null +++ b/client/server/ssh_gate.go @@ -0,0 +1,282 @@ +package server + +import ( + "context" + "fmt" + "net/url" + "runtime" + "strings" + + log "github.com/sirupsen/logrus" + "google.golang.org/genproto/googleapis/rpc/errdetails" + "google.golang.org/grpc/codes" + gstatus "google.golang.org/grpc/status" + + "github.com/netbirdio/netbird/client/internal/daemonaddr" + "github.com/netbirdio/netbird/client/internal/ipcauth" + "github.com/netbirdio/netbird/client/internal/profilemanager" + "github.com/netbirdio/netbird/client/proto" + "github.com/netbirdio/netbird/util" +) + +// The daemon runs as root/LocalSystem, so a handful of config changes cross the +// user-to-root boundary and are restricted to privileged callers: +// +// - Enabling SSH root login, or disabling SSH authentication, turns the +// daemon's SSH server into a root (or unauthenticated) shell. +// - Enabling the SSH server at all is what makes the above reachable, and a +// profile the caller owns is not a privilege they hold. +// - While the SSH server is enabled, repointing the profile at another +// management identity hands SSH authorization decisions, including which +// keys and users are accepted, to whoever controls that identity. Changing +// the management URL and deregistering the peer are both ways to do that. +// +// Everything else stays unauthenticated, so this is not an authorization model: +// it only refuses the changes that would let a local user become root. A caller +// whose identity cannot be established is refused as well. + +// privilegedConfigChange is the subset of a config request that crosses the +// user-to-root boundary. Fields are nil or empty when the request leaves them +// untouched. +type privilegedConfigChange struct { + managementURL string + serverSSHAllowed *bool + enableSSHRoot *bool + disableSSHAuth *bool +} + +func privilegedChangeFromSetConfig(msg *proto.SetConfigRequest) privilegedConfigChange { + return privilegedConfigChange{ + managementURL: msg.GetManagementUrl(), + serverSSHAllowed: msg.ServerSSHAllowed, + enableSSHRoot: msg.EnableSSHRoot, + disableSSHAuth: msg.DisableSSHAuth, + } +} + +func privilegedChangeFromLogin(msg *proto.LoginRequest) privilegedConfigChange { + return privilegedConfigChange{ + managementURL: msg.GetManagementUrl(), + serverSSHAllowed: msg.ServerSSHAllowed, + enableSSHRoot: msg.EnableSSHRoot, + disableSSHAuth: msg.DisableSSHAuth, + } +} + +// requirePrivilegeForConfigChange refuses the privileged parts of a config +// change when the caller is not root/administrator. stored is the profile's +// current config, or nil when it has none yet. +// +// Each check compares against the stored value so that a request restating a +// value it does not change is never refused: a UI that submits the whole +// settings form must not start failing once an administrator has enabled SSH. +func requirePrivilegeForConfigChange(ctx context.Context, stored *profilemanager.Config, change privilegedConfigChange) error { + if enables(storedFlag(stored, func(c *profilemanager.Config) *bool { return c.EnableSSHRoot }), change.enableSSHRoot) { + return denyPrivileged(ctx, "enabling SSH root login", ipcauth.UpCommand("--enable-ssh-root")) + } + + if enables(storedFlag(stored, func(c *profilemanager.Config) *bool { return c.DisableSSHAuth }), change.disableSSHAuth) { + return denyPrivileged(ctx, "disabling SSH authentication", ipcauth.UpCommand("--disable-ssh-auth")) + } + + if enables(sshServerCurrentlyAllowed(stored), change.serverSSHAllowed) { + return denyPrivileged(ctx, "enabling the NetBird SSH server", ipcauth.UpCommand("--allow-server-ssh")) + } + + // Only guard the management binding while the SSH server is enabled: that is + // when the management identity decides who may open a shell here. + if !sshServerEnabled(stored) { + return nil + } + + if change.managementURL != "" && !sameManagementURL(stored.ManagementURL, change.managementURL) { + return denyPrivileged(ctx, + "changing the management URL while the NetBird SSH server is enabled", + ipcauth.UpCommand("-m "+change.managementURL)) + } + + return nil +} + +// requirePrivilegeForDeregistration refuses to deregister the peer from the +// management server when the caller is not privileged and the profile has the +// SSH server enabled. Deregistering frees the peer's key to be registered +// against another management identity, which is the same handover the +// management URL check refuses. +// +// Callers that treat deregistration as best-effort (profile removal) continue +// without it; callers that were asked to deregister surface the error. +func requirePrivilegeForDeregistration(ctx context.Context, cfg *profilemanager.Config) error { + if !sshServerEnabled(cfg) { + return nil + } + + return denyPrivileged(ctx, + "deregistering this peer while the NetBird SSH server is enabled", + ipcauth.ElevatedCommand("netbird logout")) +} + +// denyPrivileged returns nil when the caller is privileged, and otherwise a +// PermissionDenied whose message names the action and the command that performs +// it with the privileges it needs. The same summary and command ride along as an +// ErrorInfo detail so the CLI and the UI can present them without parsing text. +// +// action reads as the subject of a sentence ("enabling SSH root login"), and +// command is the equivalent command, already elevated for the platform. +func denyPrivileged(ctx context.Context, action, command string) error { + id, ok := ipcauth.CallerIdentity(ctx) + if !ok { + log.Warnf("denying %s: the caller's identity cannot be verified on this control channel", action) + return privilegeError(unidentifiedSummary(action), reinstallCommand()) + } + + if ipcauth.IsPrivilegedCaller(id) { + log.Infof("allowing %s for privileged caller %s", action, id) + return nil + } + + log.Warnf("denying %s for unprivileged caller %s", action, id) + actor, command := requiredActor(command) + return privilegeError(privilegeSummary(action, actor), command) +} + +// requiredActor names who may perform the operation and adjusts the command to +// match. A daemon that is not itself privileged delegates to its own identity, so +// telling that host's user to become root is wrong twice over: root is not what the +// daemon checks for, and a rootless container has neither root nor sudo. +func requiredActor(command string) (string, string) { + self, delegates := ipcauth.SelfDelegatesTo() + if !delegates { + return ipcauth.PrivilegedActor(), command + } + return fmt.Sprintf("the user the daemon runs as (%s)", self), strings.ReplaceAll(command, "sudo ", "") +} + +// privilegeError builds the PermissionDenied carrying summary and command. +func privilegeError(summary, command string) error { + st := gstatus.New(codes.PermissionDenied, fmt.Sprintf("%s\n\n%s", summary, command)) + + detailed, err := st.WithDetails(&errdetails.ErrorInfo{ + Reason: ipcauth.ErrorReasonPrivilegeRequired, + Domain: ipcauth.ErrorDomain, + Metadata: map[string]string{ + ipcauth.ErrorMetaSummary: summary, + ipcauth.ErrorMetaCommand: command, + }, + }) + if err != nil { + log.Debugf("attach privilege error detail: %v", err) + return st.Err() + } + return detailed.Err() +} + +// privilegeSummary states what is refused and what it needs, in one sentence +// that reads the same in a dialog and in a terminal. +func privilegeSummary(action, actor string) string { + return fmt.Sprintf("%s requires %s.", capitalize(action), actor) +} + +// unidentifiedSummary covers a control channel that carries no caller identity. +// Elevating does not help there, so it points at the daemon's socket instead. +func unidentifiedSummary(action string) string { + return fmt.Sprintf("%s requires %s, and the daemon cannot verify who is calling over its current socket. "+ + "Reinstall the service on a socket that carries the caller's identity.", capitalize(action), ipcauth.PrivilegedActor()) +} + +// reinstallCommand is the command that moves the daemon onto a socket whose +// callers can be identified. +func reinstallCommand() string { + if runtime.GOOS == "windows" { + return fmt.Sprintf("netbird service install --daemon-addr %s", daemonaddr.WindowsPipeAddr) + } + return "sudo netbird service install --daemon-addr unix:///var/run/netbird.sock" +} + +func capitalize(s string) string { + if s == "" { + return s + } + return strings.ToUpper(s[:1]) + s[1:] +} + +// enables reports whether requested turns a flag on that is currently off. A +// request that restates the stored value, or turns the flag off, is not a +// privileged change. +func enables(stored, requested *bool) bool { + if requested == nil || !*requested { + return false + } + return stored == nil || !*stored +} + +// storedFlag reads a flag from the stored config, tolerating a config that does +// not exist yet. +func storedFlag(cfg *profilemanager.Config, get func(*profilemanager.Config) *bool) *bool { + if cfg == nil { + return nil + } + return get(cfg) +} + +// sshServerEnabled reports whether the profile currently runs the SSH server. +// +// A nil flag means ON, matching what the engine does with the same config +// (util.ReturnBoolWithDefaultTrue in internal/connect.go, kept for configs written +// before the flag existed). Reading it as OFF here would open the management-URL +// and deregistration guards on exactly those legacy hosts, whose SSH server is +// running. Configs loaded through profilemanager have already been materialised by +// apply(), so this is the same answer by a route that does not depend on that. +func sshServerEnabled(cfg *profilemanager.Config) bool { + if cfg == nil { + return false + } + return util.ReturnBoolWithDefaultTrue(cfg.ServerSSHAllowed) +} + +// sshServerCurrentlyAllowed is the value an enable request is compared against. It +// shares sshServerEnabled's nil-means-on default, so restating "on" for a legacy +// config is correctly seen as no change. +func sshServerCurrentlyAllowed(cfg *profilemanager.Config) *bool { + enabled := sshServerEnabled(cfg) + if cfg == nil { + return nil + } + return &enabled +} + +// sameManagementURL reports whether requested addresses the same management +// server as stored, comparing scheme, host and effective port so that an +// equivalent spelling ("https://api.netbird.io" for a stored +// "https://api.netbird.io:443") is not treated as a change. It fails closed: +// anything unparseable counts as a change and therefore needs privilege. +func sameManagementURL(stored *url.URL, requested string) bool { + if stored == nil { + return false + } + + // Normalise the requested URL through the config layer's own parser, so the + // comparison cannot drift from how the value would actually be stored. + parsed, err := profilemanager.ParseServiceURL("Management URL", requested) + if err != nil { + return false + } + + return stored.Scheme == parsed.Scheme && + stored.Hostname() == parsed.Hostname() && + effectivePort(stored) == effectivePort(parsed) +} + +func effectivePort(u *url.URL) string { + if port := u.Port(); port != "" { + return port + } + switch u.Scheme { + case "https": + return "443" + case "http": + return "80" + default: + return "" + } +} diff --git a/client/server/ssh_gate_test.go b/client/server/ssh_gate_test.go new file mode 100644 index 000000000..cbd345f16 --- /dev/null +++ b/client/server/ssh_gate_test.go @@ -0,0 +1,348 @@ +package server + +import ( + "context" + "net/url" + "os" + "runtime" + "strings" + "testing" + + "google.golang.org/genproto/googleapis/rpc/errdetails" + "google.golang.org/grpc/codes" + "google.golang.org/grpc/credentials" + "google.golang.org/grpc/peer" + gstatus "google.golang.org/grpc/status" + + "github.com/netbirdio/netbird/client/internal/ipcauth" + "github.com/netbirdio/netbird/client/internal/profilemanager" +) + +// ctxWithIdentity builds a request context carrying the identity the transport +// credentials would have attached. +func ctxWithIdentity(id ipcauth.Identity) context.Context { + return peer.NewContext(context.Background(), &peer.Peer{ + AuthInfo: ipcauth.AuthInfo{ + CommonAuthInfo: credentials.CommonAuthInfo{SecurityLevel: credentials.NoSecurity}, + Identity: id, + }, + }) +} + +// unprivUID is deliberately not this process's own uid. An unprivileged daemon +// treats a caller sharing its identity as privileged (rootless containers), and +// the test binary would otherwise stand in for both the daemon and the caller. +// os.Geteuid returns -1 on Windows, where identities are SIDs instead and this is +// unused. +var unprivUID = uint32(os.Geteuid() + 1) + +// The fabricated identities have to be shaped like the platform's: a uid says +// nothing on Windows, and a zero uid there would read as root and be privileged. +func rootCtx() context.Context { return ctxWithIdentity(privilegedIdentity()) } +func userCtx() context.Context { return ctxWithIdentity(unprivilegedIdentity()) } + +func privilegedIdentity() ipcauth.Identity { + if runtime.GOOS == "windows" { + // LocalSystem, which is what the Windows service account is. + return ipcauth.Identity{SID: "S-1-5-18"} + } + return ipcauth.Identity{UID: 0} +} + +func unprivilegedIdentity() ipcauth.Identity { + if runtime.GOOS == "windows" { + // A plain user SID: no groups, so no BUILTIN\Administrators, and not + // elevated. + return ipcauth.Identity{SID: "S-1-5-21-1-2-3-1001"} + } + return ipcauth.Identity{UID: unprivUID, GID: unprivUID} +} +func noIdentityCtx() context.Context { return context.Background() } + +func boolPtr(v bool) *bool { return &v } + +func mustURL(t *testing.T, raw string) *url.URL { + t.Helper() + u, err := url.Parse(raw) + if err != nil { + t.Fatalf("parse %q: %v", raw, err) + } + return u +} + +func assertDenied(t *testing.T, err error) { + t.Helper() + if err == nil { + t.Fatal("expected the change to be refused, got nil") + } + st := gstatus.Convert(err) + if st.Code() != codes.PermissionDenied { + t.Fatalf("code = %v, want PermissionDenied", st.Code()) + } + // The refusal must be machine-readable: the CLI and the UI render the + // summary and command from the detail rather than parsing the message. + var info *errdetails.ErrorInfo + for _, d := range st.Details() { + if got, ok := d.(*errdetails.ErrorInfo); ok { + info = got + } + } + if info == nil { + t.Fatal("refusal carries no ErrorInfo detail") + } + if info.GetReason() != ipcauth.ErrorReasonPrivilegeRequired || info.GetDomain() != ipcauth.ErrorDomain { + t.Fatalf("detail = %s/%s, want %s/%s", info.GetDomain(), info.GetReason(), ipcauth.ErrorDomain, ipcauth.ErrorReasonPrivilegeRequired) + } + if info.GetMetadata()[ipcauth.ErrorMetaSummary] == "" { + t.Error("detail carries no summary") + } + if info.GetMetadata()[ipcauth.ErrorMetaCommand] == "" { + t.Error("detail carries no command") + } +} + +func assertAllowed(t *testing.T, err error) { + t.Helper() + if err != nil { + t.Fatalf("expected the change to be allowed, got %v", err) + } +} + +func TestRequirePrivilegeForConfigChange_SSHFlags(t *testing.T) { + tests := []struct { + name string + stored *profilemanager.Config + change privilegedConfigChange + privileged bool + wantDeny bool + }{ + { + name: "enabling the ssh server unprivileged is refused", + stored: &profilemanager.Config{ServerSSHAllowed: boolPtr(false)}, + change: privilegedConfigChange{serverSSHAllowed: boolPtr(true)}, + wantDeny: true, + }, + { + name: "enabling the ssh server as root is allowed", + stored: &profilemanager.Config{ServerSSHAllowed: boolPtr(false)}, + change: privilegedConfigChange{serverSSHAllowed: boolPtr(true)}, + privileged: true, + }, + { + name: "restating an already enabled ssh server is not a change", + stored: &profilemanager.Config{ServerSSHAllowed: boolPtr(true)}, + change: privilegedConfigChange{serverSSHAllowed: boolPtr(true)}, + }, + { + name: "turning the ssh server off is not guarded", + stored: &profilemanager.Config{ServerSSHAllowed: boolPtr(true)}, + change: privilegedConfigChange{serverSSHAllowed: boolPtr(false)}, + }, + { + name: "a profile with no config yet counts as off, so enabling is refused", + stored: nil, + change: privilegedConfigChange{serverSSHAllowed: boolPtr(true)}, + wantDeny: true, + }, + { + name: "enabling ssh root login unprivileged is refused", + stored: &profilemanager.Config{EnableSSHRoot: boolPtr(false)}, + change: privilegedConfigChange{enableSSHRoot: boolPtr(true)}, + wantDeny: true, + }, + { + name: "restating ssh root login is not a change", + stored: &profilemanager.Config{EnableSSHRoot: boolPtr(true)}, + change: privilegedConfigChange{enableSSHRoot: boolPtr(true)}, + }, + { + name: "turning ssh root login off is not guarded", + stored: &profilemanager.Config{EnableSSHRoot: boolPtr(true)}, + change: privilegedConfigChange{enableSSHRoot: boolPtr(false)}, + }, + { + name: "disabling ssh authentication unprivileged is refused", + stored: &profilemanager.Config{DisableSSHAuth: boolPtr(false)}, + change: privilegedConfigChange{disableSSHAuth: boolPtr(true)}, + wantDeny: true, + }, + { + name: "re-enabling ssh authentication is not guarded", + stored: &profilemanager.Config{DisableSSHAuth: boolPtr(true)}, + change: privilegedConfigChange{disableSSHAuth: boolPtr(false)}, + }, + { + name: "a request that touches none of the guarded fields is allowed", + stored: &profilemanager.Config{ServerSSHAllowed: boolPtr(false)}, + change: privilegedConfigChange{}, + }, + } + + for _, tt := range tests { + t.Run(tt.name, func(t *testing.T) { + ctx := userCtx() + if tt.privileged { + ctx = rootCtx() + } + err := requirePrivilegeForConfigChange(ctx, tt.stored, tt.change) + if tt.wantDeny { + assertDenied(t, err) + return + } + assertAllowed(t, err) + }) + } +} + +func TestRequirePrivilegeForConfigChange_ManagementURL(t *testing.T) { + sshOn := func(raw string) *profilemanager.Config { + return &profilemanager.Config{ServerSSHAllowed: boolPtr(true), ManagementURL: mustURL(t, raw)} + } + sshOff := func(raw string) *profilemanager.Config { + return &profilemanager.Config{ServerSSHAllowed: boolPtr(false), ManagementURL: mustURL(t, raw)} + } + + tests := []struct { + name string + stored *profilemanager.Config + requested string + privileged bool + wantDeny bool + }{ + { + name: "moving the binding while ssh is enabled is refused", + stored: sshOn("https://api.netbird.io:443"), + requested: "https://attacker.example.com:443", + wantDeny: true, + }, + { + name: "moving the binding as root is allowed", + stored: sshOn("https://api.netbird.io:443"), + requested: "https://selfhosted.example.com:443", + privileged: true, + }, + { + name: "the same url restated is not a change", + stored: sshOn("https://api.netbird.io:443"), + requested: "https://api.netbird.io:443", + }, + { + name: "an equivalent spelling of the same url is not a change", + stored: sshOn("https://api.netbird.io:443"), + requested: "https://api.netbird.io", + }, + { + name: "an equivalent spelling with an explicit http port is not a change", + stored: sshOn("http://mgmt.internal:80"), + requested: "http://mgmt.internal", + }, + { + name: "a different port on the same host is a change", + stored: sshOn("https://api.netbird.io:443"), + requested: "https://api.netbird.io:8443", + wantDeny: true, + }, + { + name: "a different scheme on the same host is a change", + stored: sshOn("https://mgmt.internal:443"), + requested: "http://mgmt.internal:443", + wantDeny: true, + }, + { + name: "with ssh disabled the binding is not guarded at all", + stored: sshOff("https://api.netbird.io:443"), + requested: "https://attacker.example.com:443", + }, + { + name: "an unparseable url fails closed", + stored: sshOn("https://api.netbird.io:443"), + requested: "ht tp://%zz", + wantDeny: true, + }, + { + name: "an empty url leaves the binding alone", + stored: sshOn("https://api.netbird.io:443"), + requested: "", + }, + } + + for _, tt := range tests { + t.Run(tt.name, func(t *testing.T) { + ctx := userCtx() + if tt.privileged { + ctx = rootCtx() + } + err := requirePrivilegeForConfigChange(ctx, tt.stored, privilegedConfigChange{managementURL: tt.requested}) + if tt.wantDeny { + assertDenied(t, err) + return + } + assertAllowed(t, err) + }) + } +} + +// A caller the daemon cannot identify must be refused, not trusted: that is the +// state on a TCP daemon socket, where no peer credentials exist. +func TestRequirePrivilegeForConfigChange_UnidentifiedCallerIsRefused(t *testing.T) { + err := requirePrivilegeForConfigChange(noIdentityCtx(), + &profilemanager.Config{ServerSSHAllowed: boolPtr(false)}, + privilegedConfigChange{serverSSHAllowed: boolPtr(true)}) + assertDenied(t, err) + + // The guidance must point at the socket rather than at sudo, since elevating + // would not help. + st := gstatus.Convert(err) + if !strings.Contains(st.Message(), "service install") { + t.Errorf("message %q does not tell the operator how to fix the socket", st.Message()) + } +} + +func TestRequirePrivilegeForDeregistration(t *testing.T) { + tests := []struct { + name string + cfg *profilemanager.Config + privileged bool + wantDeny bool + }{ + { + name: "deregistering while ssh is enabled is refused", + cfg: &profilemanager.Config{ServerSSHAllowed: boolPtr(true)}, + wantDeny: true, + }, + { + name: "deregistering while ssh is enabled is allowed for root", + cfg: &profilemanager.Config{ServerSSHAllowed: boolPtr(true)}, + privileged: true, + }, + { + name: "deregistering with ssh disabled is not guarded", + cfg: &profilemanager.Config{ServerSSHAllowed: boolPtr(false)}, + }, + { + name: "deregistering a profile with no config is not guarded", + cfg: nil, + }, + } + + for _, tt := range tests { + t.Run(tt.name, func(t *testing.T) { + ctx := userCtx() + if tt.privileged { + ctx = rootCtx() + } + err := requirePrivilegeForDeregistration(ctx, tt.cfg) + if tt.wantDeny { + assertDenied(t, err) + return + } + assertAllowed(t, err) + }) + } +} + +// privilegedTestCtx is the context a handler-level test should use when it is +// standing in for a root/administrator caller. Tests that drive the handlers +// directly have no transport credentials, and the privileged-change gate refuses +// a caller it cannot identify. +func privilegedTestCtx() context.Context { return rootCtx() } diff --git a/client/server/state.go b/client/server/state.go index f2d823465..a4e91468e 100644 --- a/client/server/state.go +++ b/client/server/state.go @@ -46,7 +46,7 @@ func (s *Server) CleanState(ctx context.Context, req *proto.CleanStateRequest) ( if req.All { // Reuse existing cleanup logic for all states - if err := restoreResidualState(ctx, statePath); err != nil { + if err := RestoreResidualState(ctx, statePath); err != nil { return nil, status.Errorf(codes.Internal, "failed to clean all states: %v", err) } @@ -113,9 +113,9 @@ func (s *Server) DeleteState(ctx context.Context, req *proto.DeleteStateRequest) }, nil } -// restoreResidualState checks if the client was not shut down in a clean way and restores residual if required. +// RestoreResidualState checks if the client was not shut down in a clean way and restores residual if required. // Otherwise, we might not be able to connect to the management server to retrieve new config. -func restoreResidualState(ctx context.Context, statePath string) error { +func RestoreResidualState(ctx context.Context, statePath string) error { if statePath == "" { return nil } diff --git a/client/ssh/client/client.go b/client/ssh/client/client.go index ebf8eb794..4180849cd 100644 --- a/client/ssh/client/client.go +++ b/client/ssh/client/client.go @@ -9,7 +9,6 @@ import ( "path/filepath" "runtime" "strconv" - "strings" "time" log "github.com/sirupsen/logrus" @@ -17,7 +16,6 @@ import ( "golang.org/x/crypto/ssh/knownhosts" "golang.org/x/term" "google.golang.org/grpc" - "google.golang.org/grpc/credentials/insecure" "github.com/netbirdio/netbird/client/internal/daemonaddr" "github.com/netbirdio/netbird/client/internal/profilemanager" @@ -32,7 +30,7 @@ const ( // DefaultDaemonAddr is the default address for the NetBird daemon DefaultDaemonAddr = "unix:///var/run/netbird.sock" // DefaultDaemonAddrWindows is the default address for the NetBird daemon on Windows - DefaultDaemonAddrWindows = "tcp://127.0.0.1:41731" + DefaultDaemonAddrWindows = daemonaddr.WindowsPipeAddr ) // Client wraps crypto/ssh Client for simplified SSH operations @@ -268,7 +266,7 @@ func getDefaultDaemonAddr() string { return addr } if runtime.GOOS == "windows" { - return DefaultDaemonAddrWindows + return daemonaddr.ResolveDaemonAddr(DefaultDaemonAddrWindows) } return daemonaddr.ResolveUnixDaemonAddr(DefaultDaemonAddr) } @@ -410,12 +408,9 @@ func verifyHostKeyViaDaemon(hostname string, remote net.Addr, key ssh.PublicKey, } func connectToDaemon(daemonAddr string) (*grpc.ClientConn, error) { - addr := strings.TrimPrefix(daemonAddr, "tcp://") + target, opts := daemonaddr.DialTarget(daemonAddr) - conn, err := grpc.NewClient( - addr, - grpc.WithTransportCredentials(insecure.NewCredentials()), - ) + conn, err := grpc.NewClient(target, opts...) if err != nil { log.Debugf("failed to create gRPC client for NetBird daemon at %s: %v", daemonAddr, err) return nil, fmt.Errorf("failed to connect to NetBird daemon: %w", err) diff --git a/client/ssh/config/manager.go b/client/ssh/config/manager.go index 20695cb4d..e15330739 100644 --- a/client/ssh/config/manager.go +++ b/client/ssh/config/manager.go @@ -14,6 +14,7 @@ import ( log "github.com/sirupsen/logrus" nbssh "github.com/netbirdio/netbird/client/ssh" + "github.com/netbirdio/netbird/shared/management/domain" ) const ( @@ -218,11 +219,20 @@ func (m *Manager) buildHostPatterns(peer PeerSSHInfo) []string { if peer.IPv6.IsValid() { hostPatterns = append(hostPatterns, peer.IPv6.String()) } - if peer.FQDN != "" { + // Peer FQDNs and hostnames originate from remote peers, so they must be + // validated as plain DNS names before being embedded in the ssh_config + // "Match host" pattern list. This prevents injection of arbitrary + // ssh_config directives via embedded quotes, whitespace, newlines, the + // comma pattern separator, or the "*"/"?" pattern metacharacters. + if domain.IsValidDomainNoWildcard(peer.FQDN) { hostPatterns = append(hostPatterns, peer.FQDN) + } else if peer.FQDN != "" { + log.Warnf("skipping peer FQDN with invalid characters in SSH config: %q", peer.FQDN) } - if peer.Hostname != "" && peer.Hostname != peer.FQDN { + if peer.Hostname != peer.FQDN && domain.IsValidDomainNoWildcard(peer.Hostname) { hostPatterns = append(hostPatterns, peer.Hostname) + } else if peer.Hostname != "" && peer.Hostname != peer.FQDN { + log.Warnf("skipping peer hostname with invalid characters in SSH config: %q", peer.Hostname) } return hostPatterns } diff --git a/client/ssh/config/manager_test.go b/client/ssh/config/manager_test.go index 8e6be40a3..f65d0ba6d 100644 --- a/client/ssh/config/manager_test.go +++ b/client/ssh/config/manager_test.go @@ -148,6 +148,45 @@ func TestManager_MatchHostFormat(t *testing.T) { "should use Match host with comma-separated patterns") } +func TestManager_HostPatternInjection(t *testing.T) { + tempDir, err := os.MkdirTemp("", "netbird-ssh-config-test") + require.NoError(t, err) + defer func() { assert.NoError(t, os.RemoveAll(tempDir)) }() + + manager := &Manager{ + sshConfigDir: filepath.Join(tempDir, "ssh_config.d"), + sshConfigFile: "99-netbird.conf", + } + + // A malicious peer FQDN/hostname attempts to break out of the Match host + // directive and inject arbitrary ssh_config (a ProxyCommand executing a + // command). It must be rejected, not written to the config. + peers := []PeerSSHInfo{ + { + Hostname: "evil\"\n ProxyCommand touch /tmp/pwned\nHost x", + IP: netip.MustParseAddr("100.125.1.1"), + FQDN: "evil\"\n ProxyCommand touch /tmp/pwned\nHost x.nb.internal", + }, + {Hostname: "peer2", IP: netip.MustParseAddr("100.125.1.2"), FQDN: "peer2.nb.internal"}, + } + + err = manager.SetupSSHClientConfig(peers) + require.NoError(t, err) + + configPath := filepath.Join(manager.sshConfigDir, manager.sshConfigFile) + content, err := os.ReadFile(configPath) + require.NoError(t, err) + configStr := string(content) + + assert.NotContains(t, configStr, "ProxyCommand touch /tmp/pwned", + "injected directive must not appear in generated config") + assert.NotContains(t, configStr, "evil", + "malicious pattern must be dropped entirely") + // The valid peer must still be present, on a single Match host line. + assert.Contains(t, configStr, "Match host \"100.125.1.1,100.125.1.2,peer2.nb.internal,peer2\"", + "valid peers must survive, injected patterns dropped") +} + func TestManager_ForcedSSHConfig(t *testing.T) { // Set force environment variable t.Setenv(EnvForceSSHConfig, "true") diff --git a/client/ssh/proxy/proxy.go b/client/ssh/proxy/proxy.go index 73b50122c..721810edb 100644 --- a/client/ssh/proxy/proxy.go +++ b/client/ssh/proxy/proxy.go @@ -9,7 +9,6 @@ import ( "net" "os" "strconv" - "strings" "sync" "time" @@ -17,8 +16,8 @@ import ( log "github.com/sirupsen/logrus" cryptossh "golang.org/x/crypto/ssh" "google.golang.org/grpc" - "google.golang.org/grpc/credentials/insecure" + "github.com/netbirdio/netbird/client/internal/daemonaddr" "github.com/netbirdio/netbird/client/internal/profilemanager" "github.com/netbirdio/netbird/client/proto" nbssh "github.com/netbirdio/netbird/client/ssh" @@ -55,8 +54,8 @@ type SSHProxy struct { } func New(daemonAddr, targetHost string, targetPort int, stderr io.Writer, browserOpener func(string) error) (*SSHProxy, error) { - grpcAddr := strings.TrimPrefix(daemonAddr, "tcp://") - grpcConn, err := grpc.NewClient(grpcAddr, grpc.WithTransportCredentials(insecure.NewCredentials())) + target, opts := daemonaddr.DialTarget(daemonAddr) + grpcConn, err := grpc.NewClient(target, opts...) if err != nil { return nil, fmt.Errorf("connect to daemon: %w", err) } diff --git a/client/ssh/server/getent_unix.go b/client/ssh/server/getent_unix.go index 18edb2fdf..a3a9641f8 100644 --- a/client/ssh/server/getent_unix.go +++ b/client/ssh/server/getent_unix.go @@ -69,7 +69,8 @@ func parseGetentPasswd(output string) (*user.User, string, error) { // validateGetentInput checks that the input is safe to pass to getent or id. // Allows POSIX usernames, numeric UIDs, and common NSS extensions -// (@ for Kerberos, $ for Samba, + for NIS compat). +// (@ for Kerberos, $ for Samba, + for NIS compat). A leading hyphen is +// rejected so the input can never be parsed as a command-line flag. func validateGetentInput(input string) bool { maxLen := 32 if runtime.GOOS == "linux" { @@ -80,6 +81,10 @@ func validateGetentInput(input string) bool { return false } + if input[0] == '-' { + return false + } + for _, r := range input { if isAllowedGetentChar(r) { continue diff --git a/client/ssh/server/getent_unix_test.go b/client/ssh/server/getent_unix_test.go index e44563b79..a73214e17 100644 --- a/client/ssh/server/getent_unix_test.go +++ b/client/ssh/server/getent_unix_test.go @@ -157,6 +157,9 @@ func TestValidateGetentInput(t *testing.T) { {"numeric UID", "1001", true}, {"dots and underscores", "alice.bob_test", true}, {"hyphen", "alice-bob", true}, + {"leading hyphen rejected", "-i", false}, + {"leading double hyphen rejected", "--no-idn", false}, + {"lone hyphen rejected", "-", false}, {"kerberos principal", "user@REALM", true}, {"samba machine account", "MACHINE$", true}, {"NIS compat", "+user", true}, diff --git a/client/status/status.go b/client/status/status.go index a53585c99..e8276d0fa 100644 --- a/client/status/status.go +++ b/client/status/status.go @@ -746,6 +746,8 @@ func ToProtoFullStatus(fullStatus peer.FullStatus) *proto.FullStatus { pbFullStatus.DnsServers = append(pbFullStatus.DnsServers, pbDnsState) } + pbFullStatus.Events = fullStatus.Events + return &pbFullStatus } diff --git a/client/system/info.go b/client/system/info.go index 1838204b8..daeabca13 100644 --- a/client/system/info.go +++ b/client/system/info.go @@ -79,13 +79,15 @@ type Info struct { EnableSSHLocalPortForwarding bool EnableSSHRemotePortForwarding bool DisableSSHAuth bool + + SyncMessageVersion *int } func (i *Info) SetFlags( rosenpassEnabled, rosenpassPermissive bool, serverSSHAllowed *bool, disableClientRoutes, disableServerRoutes, - disableDNS, disableFirewall, blockLANAccess, blockInbound, disableIPv6 bool, + disableDNS, disableFirewall, blockLANAccess, blockInbound, disableIPv6 bool, syncMessageVersion *int, enableSSHRoot, enableSSHSFTP, enableSSHLocalPortForwarding, enableSSHRemotePortForwarding *bool, disableSSHAuth *bool, ) { @@ -103,6 +105,8 @@ func (i *Info) SetFlags( i.BlockInbound = blockInbound i.DisableIPv6 = disableIPv6 + i.SyncMessageVersion = syncMessageVersion + if enableSSHRoot != nil { i.EnableSSHRoot = *enableSSHRoot } diff --git a/client/system/process.go b/client/system/process.go index 07f69a212..fefa7d913 100644 --- a/client/system/process.go +++ b/client/system/process.go @@ -7,7 +7,7 @@ import ( "os" "slices" - "github.com/shirou/gopsutil/v3/process" + "github.com/shirou/gopsutil/v4/process" ) // getRunningProcesses returns a list of running process paths. The context bounds the work: diff --git a/client/system/process_test.go b/client/system/process_test.go index 44a1c8ba0..9d0a6b935 100644 --- a/client/system/process_test.go +++ b/client/system/process_test.go @@ -4,7 +4,7 @@ import ( "context" "testing" - "github.com/shirou/gopsutil/v3/process" + "github.com/shirou/gopsutil/v4/process" ) func Benchmark_getRunningProcesses(b *testing.B) { diff --git a/client/ui/autostart_default.go b/client/ui/autostart_default.go new file mode 100644 index 000000000..162922579 --- /dev/null +++ b/client/ui/autostart_default.go @@ -0,0 +1,121 @@ +//go:build !android && !ios && !freebsd && !js + +package main + +import ( + "context" + "os" + "path/filepath" + + log "github.com/sirupsen/logrus" + + "github.com/netbirdio/netbird/client/internal/profilemanager" + "github.com/netbirdio/netbird/client/mdm" + "github.com/netbirdio/netbird/client/ui/preferences" + "github.com/netbirdio/netbird/client/ui/services" +) + +// autostartDefaultState carries the guard inputs of the one-time autostart +// default decision so the decision itself stays a pure, testable function. +type autostartDefaultState struct { + supported bool + mdmDisabled bool + priorInstall bool +} + +// shouldEnableAutostartDefault applies the first-run guards in order and +// returns whether autostart may be enabled, plus the reason when it may not. +func shouldEnableAutostartDefault(s autostartDefaultState) (bool, string) { + switch { + case !s.supported: + return false, "autostart not supported on this platform" + case s.mdmDisabled: + return false, "autostart disabled by MDM policy" + case s.priorInstall: + return false, "existing NetBird installation" + } + return true, "" +} + +// autostartDisabledByMDM reports whether the MDM policy manages the +// disableAutostart key in a way that must suppress the default. An +// unparseable managed value is treated as disabled to stay on the safe side. +func autostartDisabledByMDM(policy *mdm.Policy) bool { + if !policy.HasKey(mdm.KeyDisableAutostart) { + return false + } + disabled, ok := policy.GetBool(mdm.KeyDisableAutostart) + return !ok || disabled +} + +// netbirdFootprintExists reports whether the machine already carries NetBird +// daemon config or state, meaning this is not a genuinely fresh install. It is +// the update-safety gate for the autostart default: upgrading users always +// have a footprint, so an update can never trigger a autostart entry write. +func netbirdFootprintExists() bool { + candidates := []string{ + profilemanager.DefaultConfigPath, + filepath.Join(profilemanager.DefaultConfigPathDir, "config.json"), + filepath.Join(profilemanager.DefaultConfigPathDir, "state.json"), + } + for _, path := range candidates { + if path != "" && fileExists(path) { + return true + } + } + return false +} + +// applyAutostartDefault runs the one-time launch-on-login default for genuinely +// fresh installs. The autostartInitialized marker is persisted before any +// enable attempt so a crash mid-flow degrades to "never enabled" instead of +// retrying autostart entry writes on every launch. A user's later disable in +// Settings is never overridden: the marker guarantees at-most-once, ever. +func applyAutostartDefault(ctx context.Context, autostart *services.Autostart, prefs *preferences.Store, prefsFileExisted bool) { + mdmDisabled := autostartDisabledByMDM(mdm.LoadPolicy()) + + if mdmDisabled { + if enabled, err := autostart.IsEnabled(ctx); err != nil { + log.Warnf("MDM disableAutostart: read autostart state: %v", err) + } else if enabled { + if err := autostart.SetEnabled(ctx, false); err != nil { + log.Warnf("MDM disableAutostart: force off failed: %v", err) + } else { + log.Info("MDM disableAutostart enforced: autostart turned off") + } + } + } + + priorFootprint := netbirdFootprintExists() || prefsFileExisted + + if prefs.Get().AutostartInitialized { + return + } + if err := prefs.SetAutostartInitialized(true); err != nil { + log.Warnf("persist autostart marker, skipping autostart default: %v", err) + return + } + + state := autostartDefaultState{ + supported: autostart.Supported(ctx), + mdmDisabled: mdmDisabled, + priorInstall: priorFootprint, + } + enable, reason := shouldEnableAutostartDefault(state) + if !enable { + log.Debugf("skipping autostart default: %s", reason) + return + } + + if err := autostart.SetEnabled(ctx, true); err != nil { + log.Warnf("enable autostart on fresh install: %v", err) + return + } + log.Info("autostart enabled by default on fresh install") +} + +// fileExists reports whether path exists. +func fileExists(path string) bool { + _, err := os.Stat(path) + return err == nil +} diff --git a/client/ui/autostart_default_test.go b/client/ui/autostart_default_test.go new file mode 100644 index 000000000..b7bdf9f2a --- /dev/null +++ b/client/ui/autostart_default_test.go @@ -0,0 +1,125 @@ +//go:build !android && !ios && !freebsd && !js + +package main + +import ( + "testing" + + "github.com/stretchr/testify/assert" + + "github.com/netbirdio/netbird/client/mdm" +) + +func TestShouldEnableAutostartDefault(t *testing.T) { + allPass := autostartDefaultState{ + supported: true, + mdmDisabled: false, + priorInstall: false, + } + + tests := []struct { + name string + mutate func(*autostartDefaultState) + wantEnable bool + wantReason string + }{ + { + name: "fresh install with all guards passing enables", + mutate: func(*autostartDefaultState) {}, + wantEnable: true, + }, + { + name: "unsupported platform skips", + mutate: func(s *autostartDefaultState) { s.supported = false }, + wantReason: "autostart not supported on this platform", + }, + { + name: "MDM disable skips", + mutate: func(s *autostartDefaultState) { s.mdmDisabled = true }, + wantReason: "autostart disabled by MDM policy", + }, + { + name: "existing installation (upgrade) skips", + mutate: func(s *autostartDefaultState) { s.priorInstall = true }, + wantReason: "existing NetBird installation", + }, + { + name: "unsupported wins over every other guard", + mutate: func(s *autostartDefaultState) { + s.supported = false + s.mdmDisabled = true + s.priorInstall = true + }, + wantReason: "autostart not supported on this platform", + }, + { + name: "MDM disable wins over prior install", + mutate: func(s *autostartDefaultState) { + s.mdmDisabled = true + s.priorInstall = true + }, + wantReason: "autostart disabled by MDM policy", + }, + } + + for _, tc := range tests { + t.Run(tc.name, func(t *testing.T) { + state := allPass + tc.mutate(&state) + enable, reason := shouldEnableAutostartDefault(state) + assert.Equal(t, tc.wantEnable, enable, "enable decision should match for state %+v", state) + assert.Equal(t, tc.wantReason, reason, "skip reason should identify the failing guard") + }) + } +} + +func TestAutostartDisabledByMDM(t *testing.T) { + tests := []struct { + name string + values map[string]any + want bool + }{ + { + name: "empty policy does not disable", + values: nil, + want: false, + }, + { + name: "unrelated managed keys do not disable", + values: map[string]any{mdm.KeyDisableAutoConnect: true}, + want: false, + }, + { + name: "disableAutostart true disables", + values: map[string]any{mdm.KeyDisableAutostart: true}, + want: true, + }, + { + name: "disableAutostart registry DWORD 1 disables", + values: map[string]any{mdm.KeyDisableAutostart: int64(1)}, + want: true, + }, + { + name: "disableAutostart string true disables", + values: map[string]any{mdm.KeyDisableAutostart: "true"}, + want: true, + }, + { + name: "disableAutostart explicit false allows", + values: map[string]any{mdm.KeyDisableAutostart: false}, + want: false, + }, + { + name: "unparseable managed value is treated as disabled", + values: map[string]any{mdm.KeyDisableAutostart: "not-a-bool"}, + want: true, + }, + } + + for _, tc := range tests { + t.Run(tc.name, func(t *testing.T) { + got := autostartDisabledByMDM(mdm.NewPolicy(tc.values)) + assert.Equal(t, tc.want, got, "MDM disable decision should match for values %v", tc.values) + }) + } +} diff --git a/client/ui/frontend/src/app.tsx b/client/ui/frontend/src/app.tsx index c7b12e538..7f1359510 100644 --- a/client/ui/frontend/src/app.tsx +++ b/client/ui/frontend/src/app.tsx @@ -16,10 +16,13 @@ import LoginWaitingForBrowserDialog from "@/modules/login/LoginWaitingForBrowser import { initI18n } from "@/lib/i18n"; import { initPlatform } from "@/lib/platform"; import { initLogForwarding } from "@/lib/logs"; +import { initStallWatch } from "@/lib/stallwatch"; // Must run first so even init-time logs reach the Go log pipeline. initLogForwarding(); +initStallWatch(); + welcome(); Promise.all([ diff --git a/client/ui/frontend/src/components/CopyToClipboard.tsx b/client/ui/frontend/src/components/CopyToClipboard.tsx index 1b2a87da4..3cf681a1c 100644 --- a/client/ui/frontend/src/components/CopyToClipboard.tsx +++ b/client/ui/frontend/src/components/CopyToClipboard.tsx @@ -18,6 +18,9 @@ type CopyToClipboardProps = { className?: string; iconClassName?: string; alwaysShowIcon?: boolean; + // wrap lets long content (a shell command, a path) break across lines + // instead of being truncated to one line. + wrap?: boolean; variant?: CopyToClipboardVariant; "aria-label"?: string; tabIndex?: number; @@ -32,6 +35,7 @@ export const CopyToClipboard = ({ className, iconClassName, alwaysShowIcon = false, + wrap = false, variant = "default", "aria-label": ariaLabel, tabIndex = 0, @@ -83,7 +87,8 @@ export const CopyToClipboard = ({ > globalThis.open(url, "_blank")); @@ -12,7 +15,26 @@ function openUrl(url: string) { export const DaemonOutdatedOverlay = () => { const { t } = useTranslation(); - const { isDaemonOutdated } = useStatus(); + const { status, isDaemonOutdated } = useStatus(); + + const [guiVersion, setGuiVersion] = useState("-"); + const clientVersion = status?.daemonVersion ?? "—"; + + const isRc = /-rc/i.test(guiVersion) || /-rc/i.test(clientVersion); + const downloadUrl = isRc ? RC_RELEASES_URL : RELEASES_URL; + + useEffect(() => { + if (!isDaemonOutdated) return; + let cancelled = false; + Version.GUI() + .then((v) => { + if (!cancelled) setGuiVersion(v); + }) + .catch((err) => console.error("[DaemonOutdatedOverlay] GUI version error", err)); + return () => { + cancelled = true; + }; + }, [isDaemonOutdated]); if (!isDaemonOutdated) return null; @@ -38,10 +60,37 @@ export const DaemonOutdatedOverlay = () => {

{t("daemon.outdated.description")}

+
+

+ {clientVersion === "development" ? ( + + {t("settings.about.clientName")}{" "} + + {t("settings.about.development")} + + + ) : ( + t("settings.about.client", { version: clientVersion }) + )} +

+

+ {guiVersion === "development" ? ( + + {t("settings.about.guiName")}{" "} + + {t("settings.about.development")} + + + ) : ( + t("settings.about.gui", { version: guiVersion }) + )} +

+
+
-
diff --git a/client/ui/frontend/src/contexts/ProfileContext.tsx b/client/ui/frontend/src/contexts/ProfileContext.tsx index 4dd3eaa7a..62377f1bc 100644 --- a/client/ui/frontend/src/contexts/ProfileContext.tsx +++ b/client/ui/frontend/src/contexts/ProfileContext.tsx @@ -28,6 +28,7 @@ type ProfileContextValue = { loaded: boolean; refresh: () => Promise; switchProfile: (id: string) => Promise; + switchProfileNoConnect: (id: string) => Promise; addProfile: (name: string) => Promise; removeProfile: (id: string) => Promise; renameProfile: (id: string, newName: string) => Promise; @@ -112,6 +113,16 @@ export const ProfileProvider = ({ children }: { children: ReactNode }) => { [username, refresh], ); + // Manage-profiles variant: switches without connecting, so the user can + // still adjust the management URL before bringing the connection up. + const switchProfileNoConnect = useCallback( + async (id: string) => { + await ProfileSwitcher.SwitchActiveNoConnect({ profileName: id, username }); + await refresh(); + }, + [username, refresh], + ); + // addProfile creates a profile by display name and returns the // daemon-generated ID, so the caller can immediately address it by ID. const addProfile = useCallback( @@ -158,6 +169,7 @@ export const ProfileProvider = ({ children }: { children: ReactNode }) => { loaded, refresh, switchProfile, + switchProfileNoConnect, addProfile, removeProfile, renameProfile, @@ -171,6 +183,7 @@ export const ProfileProvider = ({ children }: { children: ReactNode }) => { loaded, refresh, switchProfile, + switchProfileNoConnect, addProfile, removeProfile, renameProfile, diff --git a/client/ui/frontend/src/contexts/SettingsContext.tsx b/client/ui/frontend/src/contexts/SettingsContext.tsx index 37627bc76..3f4b2d0d2 100644 --- a/client/ui/frontend/src/contexts/SettingsContext.tsx +++ b/client/ui/frontend/src/contexts/SettingsContext.tsx @@ -14,7 +14,7 @@ import type { Config } from "@bindings/services/models.js"; import i18next from "@/lib/i18n"; import { useProfile } from "@/contexts/ProfileContext.tsx"; import { SettingsSkeleton } from "@/modules/settings/SettingsSkeleton.tsx"; -import { errorDialog, formatErrorMessage as errorMessage } from "@/lib/errors.ts"; +import { errorCommand, errorDialog, formatErrorMessage as errorMessage } from "@/lib/errors.ts"; const SAVE_DEBOUNCE_MS = 400; @@ -68,6 +68,21 @@ const useSettingsState = () => { loadedRef.current = loaded; }, [loaded]); + // reload re-reads the daemon's config, which is authoritative. Used on + // mount, on the daemon's config_changed event, and to undo an optimistic + // update the daemon then rejected. + const reload = useCallback( + async (profileName: string) => { + try { + const data = await SettingsSvc.GetConfig({ profileName, username }); + setLoaded({ profileName, data }); + } catch (e) { + console.warn("[SettingsContext] reload after rejected save failed", e); + } + }, + [username], + ); + useEffect(() => { if (!profileLoaded || !activeProfileId) return; let cancelled = false; @@ -133,13 +148,20 @@ const useSettingsState = () => { username, }); } catch (e) { + // The optimistic update is wrong now: the daemon refused it + // (a change that needs elevated privileges, an MDM-managed + // field, ...). Snap the controls back to what it actually + // holds before reporting, so the UI never shows a value the + // daemon does not have. + await reload(profileName); await errorDialog({ Title: i18next.t("settings.error.saveTitle"), Message: errorMessage(e), + Command: errorCommand(e), }); } }, - [username], + [username, reload], ); const setField = useCallback( diff --git a/client/ui/frontend/src/hooks/usePrivilege.ts b/client/ui/frontend/src/hooks/usePrivilege.ts new file mode 100644 index 000000000..05e9a7ce0 --- /dev/null +++ b/client/ui/frontend/src/hooks/usePrivilege.ts @@ -0,0 +1,32 @@ +import { useEffect, useState } from "react"; +import { Settings as SettingsSvc } from "@bindings/services"; +import { Privilege } from "@bindings/services/models.js"; + +// usePrivilege reports whether this UI process may perform the changes the daemon +// restricts to root/administrator. It is answered in-process from our own token +// with the daemon's own rule, so there is no round-trip and it works while the +// daemon is down. +// +// null means "not known yet", which includes the read having failed. Callers must +// treat that as "do not restrict": the daemon enforces this regardless, so the +// only thing a wrong guess here costs is a control that looks unavailable when it +// is not, or a save that fails with the daemon's own guidance. +export const usePrivilege = (): Privilege | null => { + const [privilege, setPrivilege] = useState(null); + + useEffect(() => { + let cancelled = false; + SettingsSvc.Privilege() + .then((p) => { + if (!cancelled) setPrivilege(p); + }) + .catch((e: unknown) => { + console.warn("[usePrivilege] read failed, not restricting controls", e); + }); + return () => { + cancelled = true; + }; + }, []); + + return privilege; +}; diff --git a/client/ui/frontend/src/lib/connection.ts b/client/ui/frontend/src/lib/connection.ts index b9e98bf24..fca03fc87 100644 --- a/client/ui/frontend/src/lib/connection.ts +++ b/client/ui/frontend/src/lib/connection.ts @@ -51,7 +51,14 @@ async function runSsoLogin( if (uri) await openBrowserLoginUri(uri); const cancelPromise = buildSsoCancelPromise(state, signal); - const waitPromise = Connection.WaitSSOLogin({ userCode: result.userCode, hostname: "" }); + // Combine wait + up in Go so the connection comes up the moment SSO + // completes. During SSO the tray window is hidden and the webview is + // suspended, so a frontend-driven Up (a promise continuation) would not + // fire until the user woke the window (e.g. hovering the tray icon). + const waitPromise = Connection.WaitSSOLoginAndUp( + { userCode: result.userCode, hostname: "" }, + { profileName: "", username: "" }, + ); try { await Promise.race([waitPromise, cancelPromise]); @@ -89,13 +96,13 @@ export async function startConnection(onSettled?: () => void, signal?: AbortSign if (signal?.aborted) state.cancelled = true; if (!state.cancelled && result.needsSsoLogin) { + // runSsoLogin brings the connection up in Go once SSO completes. await runSsoLogin(result, state, signal); - } - - if (!state.cancelled && signal?.aborted) state.cancelled = true; - - if (!state.cancelled) { - await Connection.Up({ profileName: "", username: "" }); + } else { + if (!state.cancelled && signal?.aborted) state.cancelled = true; + if (!state.cancelled) { + await Connection.Up({ profileName: "", username: "" }); + } } } catch (e) { WindowManager.CloseBrowserLogin().catch(console.error); diff --git a/client/ui/frontend/src/lib/errors.ts b/client/ui/frontend/src/lib/errors.ts index 34a90dace..b4dee2717 100644 --- a/client/ui/frontend/src/lib/errors.ts +++ b/client/ui/frontend/src/lib/errors.ts @@ -1,6 +1,6 @@ import { WindowManager } from "@bindings/services"; -type ClassifiedError = { short: string; long: string }; +type ClassifiedError = { short: string; long: string; command: string }; const asObject = (v: unknown): Record | null => v && typeof v === "object" ? (v as Record) : null; @@ -22,20 +22,24 @@ const toWailsEnvelope = (e: unknown): Record | null => { return asObject(obj.cause) ?? parseJsonObject(obj.message); }; -// Read { short, long } from wherever the classified error sits in the envelope +// Read { short, long, command } from wherever the classified error sits in the envelope const toClassifiedError = (v: unknown): ClassifiedError | null => { const o = asObject(v); if (!o) return null; const short = typeof o.short === "string" ? o.short : ""; const long = typeof o.long === "string" ? o.long : ""; - return short || long ? { short, long } : null; + const command = typeof o.command === "string" ? o.command : ""; + return short || long ? { short, long, command } : null; +}; + +const classify = (e: unknown): ClassifiedError | null => { + const envelope = toWailsEnvelope(e); + return toClassifiedError(envelope?.cause) ?? toClassifiedError(envelope); }; export const formatErrorMessage = (e: unknown): string => { - const envelope = toWailsEnvelope(e); - // Prefer the structured { short, long } the daemon classifier produced. - const classified = toClassifiedError(envelope?.cause) ?? toClassifiedError(envelope); + const classified = classify(e); if (classified) { const { short, long } = classified; if (short && long && long !== short) return `${short} Details: ${long}`; @@ -44,17 +48,26 @@ export const formatErrorMessage = (e: unknown): string => { } // Unclassified (a service returned the raw daemon error) + const envelope = toWailsEnvelope(e); const message = envelope?.message; if (typeof message === "string" && message) return message; if (e instanceof Error) return e.message; return String(e); }; +// errorCommand returns a command the user can run to complete an operation the +// daemon refused, when the error carries one (a change that needs elevated +// privileges). Empty for every other error. +export const errorCommand = (e: unknown): string => classify(e)?.command ?? ""; + export type ErrorDialogOptions = { Title: string; Message: string; + // Command is shown for copying below the message. Defaults to the one the + // error carries, so callers only pass it to override. + Command?: string; }; export function errorDialog(options: ErrorDialogOptions): Promise { - return WindowManager.OpenError(options.Title, options.Message); + return WindowManager.OpenError(options.Title, options.Message, options.Command ?? ""); } diff --git a/client/ui/frontend/src/lib/stallwatch.ts b/client/ui/frontend/src/lib/stallwatch.ts new file mode 100644 index 000000000..aca7d75bb --- /dev/null +++ b/client/ui/frontend/src/lib/stallwatch.ts @@ -0,0 +1,31 @@ +// Detects webview suspension (macOS App Nap / hidden-window timer throttling). +// While the webview is suspended no JS runs at all, so detection happens on +// resume: a 1s interval measures wall-clock drift and reports how long timers +// were frozen. Silent unless a stall actually occurred; a stalled webview is +// what delays promise continuations such as the WaitSSOLogin → Up handoff. + +const INTERVAL_MS = 1000; +const STALL_THRESHOLD_MS = 5000; +const REPORT_COOLDOWN_MS = 60_000; + +let started = false; + +export function initStallWatch() { + if (started) return; + started = true; + + let last = Date.now(); + let lastReport = 0; + setInterval(() => { + const now = Date.now(); + const stall = now - last - INTERVAL_MS; + last = now; + if (stall < STALL_THRESHOLD_MS) return; + if (now - lastReport < REPORT_COOLDOWN_MS) return; + lastReport = now; + console.warn( + `webview timers were suspended for ${(stall / 1000).toFixed(1)}s ` + + `(App Nap / hidden-window throttling); pending UI work ran late`, + ); + }, INTERVAL_MS); +} diff --git a/client/ui/frontend/src/modules/auto-update/UpdateVersionCard.tsx b/client/ui/frontend/src/modules/auto-update/UpdateVersionCard.tsx index 4fb5e2586..4861c492a 100644 --- a/client/ui/frontend/src/modules/auto-update/UpdateVersionCard.tsx +++ b/client/ui/frontend/src/modules/auto-update/UpdateVersionCard.tsx @@ -2,6 +2,7 @@ import { type ReactNode } from "react"; import { useTranslation } from "react-i18next"; import { Browser } from "@wailsio/runtime"; import { DownloadIcon, NotepadText } from "lucide-react"; +import { Update as UpdateSvc } from "@bindings/services"; import { Button } from "@/components/buttons/Button"; import { useClientVersion } from "@/contexts/ClientVersionContext"; import { cn } from "@/lib/cn"; @@ -14,6 +15,12 @@ function openUrl(url: string) { }); } +function openInstallerDownload() { + UpdateSvc.DownloadURL() + .then(openUrl) + .catch(() => openUrl(GITHUB_RELEASES)); +} + export function UpdateVersionCard() { const { t } = useTranslation(); const { updateVersion, enforced, triggerUpdate } = useClientVersion(); @@ -37,11 +44,7 @@ export function UpdateVersionCard() { {t("update.card.installNow")} ) : ( - diff --git a/client/ui/frontend/src/modules/error/ErrorDialog.tsx b/client/ui/frontend/src/modules/error/ErrorDialog.tsx index f7929fad2..4fbb78052 100644 --- a/client/ui/frontend/src/modules/error/ErrorDialog.tsx +++ b/client/ui/frontend/src/modules/error/ErrorDialog.tsx @@ -3,6 +3,7 @@ import { useTranslation } from "react-i18next"; import { useSearchParams } from "react-router-dom"; import { AlertCircleIcon } from "lucide-react"; import { Button } from "@/components/buttons/Button"; +import { CopyToClipboard } from "@/components/CopyToClipboard"; import { ConfirmDialog } from "@/components/dialog/ConfirmDialog"; import { DialogActions } from "@/components/dialog/DialogActions"; import { DialogDescription } from "@/components/dialog/DialogDescription"; @@ -12,14 +13,22 @@ import { WindowManager } from "@bindings/services"; import { useAutoSizeWindow } from "@/hooks/useAutoSizeWindow"; const WINDOW_WIDTH = 380; +// A command needs the room to wrap at a sensible number of characters instead of +// breaking every few words. +const WINDOW_WIDTH_WITH_COMMAND = 460; export default function ErrorDialog() { const { t } = useTranslation(); - const contentRef = useAutoSizeWindow(WINDOW_WIDTH); const [params] = useSearchParams(); const title = params.get("title") || t("window.title.error"); const message = params.get("message") || ""; + // Set when the daemon refused an operation that needs elevated privileges: + // the command that performs it, offered for copying. + const command = params.get("command") || ""; + const contentRef = useAutoSizeWindow( + command ? WINDOW_WIDTH_WITH_COMMAND : WINDOW_WIDTH, + ); const close = useCallback(() => { WindowManager.CloseError().catch(console.error); @@ -37,15 +46,37 @@ export default function ErrorDialog() { -
+
{title} {message && ( - {message} + {/* select-text: the message often names a path, a flag or an + address the user needs to act on. */} + + {message} + )} + {command && ( + + + {command} + + + )}
diff --git a/client/ui/frontend/src/modules/profiles/ProfilesTab.tsx b/client/ui/frontend/src/modules/profiles/ProfilesTab.tsx index c1ce2e449..97261ccc9 100644 --- a/client/ui/frontend/src/modules/profiles/ProfilesTab.tsx +++ b/client/ui/frontend/src/modules/profiles/ProfilesTab.tsx @@ -45,7 +45,7 @@ export function ProfilesTab() { activeProfileId, loaded, username, - switchProfile, + switchProfileNoConnect, addProfile, removeProfile, renameProfile, @@ -100,7 +100,7 @@ export function ProfilesTab() { confirmLabel: t("profile.switch.confirm"), }); if (!ok) return; - await guarded(i18next.t("profile.error.switchTitle"), () => switchProfile(id)); + await guarded(i18next.t("profile.error.switchTitle"), () => switchProfileNoConnect(id)); }; const handleDeregister = async (id: string, name: string) => { @@ -129,14 +129,13 @@ export function ProfilesTab() { await guarded(i18next.t("profile.error.createTitle"), async () => { const id = await addProfile(name); // SetConfig is keyed by the new profile's ID, so it writes the - // not-yet-active profile. Write before switching so any reconnect - // targets the right deployment. + // not-yet-active profile before the switch makes it current. if (!isNetbirdCloud(managementUrl)) { await SettingsSvc.SetConfig( new SetConfigParams({ profileName: id, username, managementUrl }), ); } - await switchProfile(id); + await switchProfileNoConnect(id); }); }; diff --git a/client/ui/frontend/src/modules/session/SessionExpirationDialog.tsx b/client/ui/frontend/src/modules/session/SessionExpirationDialog.tsx index 2ceb958d4..10e71babb 100644 --- a/client/ui/frontend/src/modules/session/SessionExpirationDialog.tsx +++ b/client/ui/frontend/src/modules/session/SessionExpirationDialog.tsx @@ -73,6 +73,13 @@ export default function SessionExpirationDialog() { let offCancel: (() => void) | undefined; + // Return the dialog to its interactive state and dismiss the browser popup + const resetDialog = () => { + offCancel?.(); + WindowManager.CloseBrowserLogin().catch(console.error); + setBusy(false); + }; + try { const start = await Session.RequestExtend({ hint: "" }); const uri = start.verificationUriComplete || start.verificationUri; @@ -105,25 +112,22 @@ export default function SessionExpirationDialog() { if (outcome.kind === "cancel") { waitPromise.cancel?.(); waitPromise.catch(() => {}); + resetDialog(); return; } // Another surface owns this flow; keep the dialog open to retry. if (outcome.result.preempted) { + resetDialog(); return; } - - // Close before the popup so the restore can't flash this window back. - WindowManager.CloseSessionExpiration().catch(console.error); + WindowManager.CloseRenewFlow().catch(console.error); } catch (e) { + resetDialog(); await errorDialog({ Title: t("sessionExpiration.extendFailedTitle"), Message: formatErrorMessage(e), }); - } finally { - offCancel?.(); - WindowManager.CloseBrowserLogin().catch(console.error); - setBusy(false); } }, [busy, t]); @@ -139,12 +143,11 @@ export default function SessionExpirationDialog() { }); WindowManager.CloseSessionExpiration().catch(console.error); } catch (e) { + setBusy(false); await errorDialog({ Title: t("sessionExpiration.logoutFailedTitle"), Message: formatErrorMessage(e), }); - } finally { - setBusy(false); } }, [busy, t]); diff --git a/client/ui/frontend/src/modules/settings/SettingsSSH.tsx b/client/ui/frontend/src/modules/settings/SettingsSSH.tsx index f18fd9493..bd91e520c 100644 --- a/client/ui/frontend/src/modules/settings/SettingsSSH.tsx +++ b/client/ui/frontend/src/modules/settings/SettingsSSH.tsx @@ -1,4 +1,5 @@ import { useTranslation } from "react-i18next"; +import { CopyToClipboard } from "@/components/CopyToClipboard"; import FancyToggleSwitch from "@/components/switches/FancyToggleSwitch"; import { HelpText } from "@/components/typography/HelpText"; import { Input } from "@/components/inputs/Input"; @@ -6,12 +7,50 @@ import { Label } from "@/components/typography/Label"; import { cn } from "@/lib/cn"; import { SectionGroup } from "@/modules/settings/SettingsSection.tsx"; import { useSettings } from "@/contexts/SettingsContext.tsx"; -import { type ChangeEvent, useEffect, useId, useState } from "react"; +import { usePrivilege } from "@/hooks/usePrivilege.ts"; +import { Privilege } from "@bindings/services/models.js"; +import { type ChangeEvent, type ReactNode, useEffect, useId, useState } from "react"; export function SettingsSSH() { const { t } = useTranslation(); const { config, setField } = useSettings(); + const privilege = usePrivilege(); const isSSHServerEnabled = config.serverSshAllowed; + + // The daemon restricts only the direction that hands out shells from a process + // running as root. So for an unprivileged user a guarded control is either + // unavailable (it is off and only they could turn it on) or a one-way switch + // (it is on, they may turn it off, but not back on) — say which, either way. + // + // A null privilege means we could not determine it: leave the control alone + // rather than greying it out with nothing to explain why. The daemon enforces + // this regardless, and a rejected save reports its own guidance. + const guarded = ( + guardedDirectionActive: boolean, + command: (p: Privilege) => string, + // inverted marks a control whose guarded direction is switching it off, so + // the one-way warning has to read the other way round. + inverted = false, + ) => { + if (!privilege || privilege.privileged) { + return { disabled: false, hint: undefined }; + } + const hint = ( + + ); + return { disabled: !guardedDirectionActive, hint }; + }; + + const sshServer = guarded(config.serverSshAllowed, (p) => p.allowSshServer); + const sshRoot = guarded(config.enableSshRoot, (p) => p.enableSshRoot); + // Inverted control: the guarded direction is switching authentication off, so + // it is the already-disabled state that is the one-way one. + const sshAuth = guarded(config.disableSshAuth, (p) => p.disableSshAuth, true); const jwtTtlId = useId(); const [jwtTtlInput, setJwtTtlInput] = useState(String(config.sshJwtCacheTtl)); @@ -46,9 +85,11 @@ export function SettingsSSH() { setField("serverSshAllowed", v)} + disabled={sshServer.disabled} label={t("settings.ssh.server.label")} helpText={t("settings.ssh.server.help")} /> + {sshServer.hint} setField("enableSshRoot", v)} + disabled={sshRoot.disabled} label={t("settings.ssh.root.label")} helpText={t("settings.ssh.root.help")} /> + {sshRoot.hint} setField("enableSshSftp", v)} @@ -88,9 +131,11 @@ export function SettingsSSH() { setField("disableSshAuth", !v)} + disabled={sshAuth.disabled} label={t("settings.ssh.jwt.label")} helpText={t("settings.ssh.jwt.help")} /> + {sshAuth.hint}
); } + +// PrivilegeHint explains what an unprivileged user can and cannot do with a +// guarded control, and offers the command that does it with the privileges the +// daemon requires. oneWay covers the control being in the guarded state already: +// switching it back is the part that needs privileges. +function PrivilegeHint({ + actor, + command, + oneWay, + inverted, +}: { + actor: string; + command: string; + oneWay: boolean; + inverted: boolean; +}): ReactNode { + const { t } = useTranslation(); + if (!command) return null; + return ( +
+ + {!oneWay + ? t("settings.ssh.privilege.hint", { actor }) + : inverted + ? t("settings.ssh.privilege.oneWayInverted", { actor }) + : t("settings.ssh.privilege.oneWay", { actor })} + + + + {command} + + +
+ ); +} diff --git a/client/ui/frontend/src/modules/welcome/WelcomeStepTray.tsx b/client/ui/frontend/src/modules/welcome/WelcomeStepTray.tsx index fe06abc20..5a8b0d015 100644 --- a/client/ui/frontend/src/modules/welcome/WelcomeStepTray.tsx +++ b/client/ui/frontend/src/modules/welcome/WelcomeStepTray.tsx @@ -22,6 +22,9 @@ type WelcomeStepTrayProps = { export function WelcomeStepTray({ onContinue }: Readonly) { const { t } = useTranslation(); const trayScreenshot = trayScreenshotForOS(); + // macOS has no tray — the icon sits in the menu bar, so the copy says so. + const titleKey = isMacOS() ? "welcome.titleMac" : "welcome.title"; + const descriptionKey = isMacOS() ? "welcome.descriptionMac" : "welcome.description"; return ( <> @@ -36,9 +39,9 @@ export function WelcomeStepTray({ onContinue }: Readonly)
- {t("welcome.title")} + {t(titleKey)} - {t("welcome.description")} + {t(descriptionKey)}
diff --git a/client/ui/grpc.go b/client/ui/grpc.go index c8e3aed76..5450e136d 100644 --- a/client/ui/grpc.go +++ b/client/ui/grpc.go @@ -5,14 +5,13 @@ package main import ( "fmt" "runtime" - "strings" "sync" "time" "google.golang.org/grpc" "google.golang.org/grpc/backoff" - "google.golang.org/grpc/credentials/insecure" + "github.com/netbirdio/netbird/client/internal/daemonaddr" "github.com/netbirdio/netbird/client/proto" "github.com/netbirdio/netbird/client/ui/desktop" ) @@ -36,9 +35,10 @@ func (c *Conn) Client() (proto.DaemonServiceClient, error) { return c.client, nil } - cc, err := grpc.NewClient( - strings.TrimPrefix(c.addr, "tcp://"), - grpc.WithTransportCredentials(insecure.NewCredentials()), + // Lazy on purpose: grpc.NewClient does not connect here, so a daemon that + // is down surfaces as a per-RPC Unavailable instead of blocking the UI. + target, opts := daemonaddr.DialTarget(daemonaddr.ResolveDaemonAddr(c.addr)) + opts = append(opts, grpc.WithUserAgent(desktop.GetUIUserAgent()), // Cap reconnect backoff at 5s; gRPC's default 120s MaxDelay would // leave the UI waiting 30-60s to notice a freshly-started daemon. @@ -51,6 +51,8 @@ func (c *Conn) Client() (proto.DaemonServiceClient, error) { }, }), ) + + cc, err := grpc.NewClient(target, opts...) if err != nil { return nil, fmt.Errorf("dial daemon: %w", err) } @@ -58,10 +60,12 @@ func (c *Conn) Client() (proto.DaemonServiceClient, error) { return c.client, nil } -// DaemonAddr returns the default daemon gRPC address: a Unix socket on Linux/macOS, TCP loopback on Windows. +// DaemonAddr returns the default daemon gRPC address: a Unix socket on +// Linux/macOS, a named pipe on Windows. The pipe carries the caller's token, +// which loopback TCP does not, so the daemon can tell who is calling. func DaemonAddr() string { if runtime.GOOS == "windows" { - return "tcp://127.0.0.1:41731" + return daemonaddr.WindowsPipeAddr } return "unix:///var/run/netbird.sock" } diff --git a/client/ui/i18n/locales/_index.json b/client/ui/i18n/locales/_index.json index 58b5c484f..419358d36 100644 --- a/client/ui/i18n/locales/_index.json +++ b/client/ui/i18n/locales/_index.json @@ -8,6 +8,7 @@ {"code": "fr", "displayName": "Français", "englishName": "French"}, {"code": "it", "displayName": "Italiano", "englishName": "Italian"}, {"code": "pt", "displayName": "Português", "englishName": "Portuguese"}, - {"code": "zh-CN", "displayName": "简体中文", "englishName": "Simplified Chinese"} + {"code": "zh-CN", "displayName": "简体中文", "englishName": "Simplified Chinese"}, + {"code": "ja", "displayName": "日本語", "englishName": "Japanese"} ] } diff --git a/client/ui/i18n/locales/de/common.json b/client/ui/i18n/locales/de/common.json index 5e0d8096d..5e91e8d88 100644 --- a/client/ui/i18n/locales/de/common.json +++ b/client/ui/i18n/locales/de/common.json @@ -1034,9 +1034,15 @@ "welcome.title": { "message": "Suchen Sie NetBird in der Taskleiste" }, + "welcome.titleMac": { + "message": "Suchen Sie NetBird in der Menüleiste" + }, "welcome.description": { "message": "NetBird läuft in Ihrer Taskleiste. Klicken Sie auf das Symbol, um sich zu verbinden, Profile zu wechseln oder die Einstellungen zu öffnen." }, + "welcome.descriptionMac": { + "message": "NetBird läuft in Ihrer Menüleiste. Klicken Sie auf das Symbol, um sich zu verbinden, Profile zu wechseln oder die Einstellungen zu öffnen." + }, "welcome.continue": { "message": "Weiter" }, @@ -1293,10 +1299,13 @@ "message": "Dokumentation" }, "daemon.outdated.title": { - "message": "NetBird-Dienst ist veraltet" + "message": "NetBird Client ist veraltet" }, "daemon.outdated.description": { - "message": "Aktualisieren Sie den NetBird-Dienst, um diese App zu verwenden." + "message": "Die neue GUI ist nicht mit Ihrem älteren Client kompatibel. Aktualisieren Sie Ihren Client, um die neue Anwendung zu verwenden." + }, + "daemon.outdated.download": { + "message": "Neueste Version herunterladen" }, "error.jwt_clock_skew": { "message": "Anmeldung fehlgeschlagen: Die Uhr dieses Geräts ist nicht mit dem Server synchron. Bitte synchronisieren Sie die Systemuhr und versuchen Sie es erneut." diff --git a/client/ui/i18n/locales/en/common.json b/client/ui/i18n/locales/en/common.json index 42d40ec30..b668146e8 100644 --- a/client/ui/i18n/locales/en/common.json +++ b/client/ui/i18n/locales/en/common.json @@ -1377,11 +1377,19 @@ }, "welcome.title": { "message": "Look for NetBird in your tray", - "description": "Heading on the first onboarding step, pointing the user to the tray icon. 'tray' = system tray / menu bar." + "description": "Heading on the first onboarding step, pointing the user to the tray icon. Shown on Windows and Linux; macOS uses welcome.titleMac." + }, + "welcome.titleMac": { + "message": "Look for NetBird in your menu bar", + "description": "Heading on the first onboarding step on macOS, pointing the user to the menu bar icon. Use your language's Apple term for the macOS menu bar." }, "welcome.description": { "message": "NetBird lives in your tray. Click the icon to connect, switch profiles, or open settings.", - "description": "Body of the first onboarding step explaining the tray icon." + "description": "Body of the first onboarding step explaining the tray icon. Shown on Windows and Linux; macOS uses welcome.descriptionMac." + }, + "welcome.descriptionMac": { + "message": "NetBird lives in your menu bar. Click the icon to connect, switch profiles, or open settings.", + "description": "Body of the first onboarding step on macOS explaining the menu bar icon. Use your language's Apple term for the macOS menu bar." }, "welcome.continue": { "message": "Continue", @@ -1724,12 +1732,16 @@ "description": "Documentation link on the daemon-unavailable overlay." }, "daemon.outdated.title": { - "message": "NetBird Service Is Outdated", - "description": "Title of the overlay shown when the NetBird background service is too old to drive this UI." + "message": "NetBird Client Is Outdated", + "description": "Title of the overlay shown when the NetBird client (daemon) is too old to drive this UI." }, "daemon.outdated.description": { - "message": "Update the NetBird service to use this app.", - "description": "Body of the daemon-outdated overlay telling the user to upgrade the service." + "message": "The new GUI isn't compatible with the older NetBird client. Update your client to use the new application.", + "description": "Body of the daemon-outdated overlay explaining that the GUI is newer than the client and the client must be updated." + }, + "daemon.outdated.download": { + "message": "Download Latest", + "description": "Button on the daemon-outdated overlay that opens the download page for the latest release." }, "error.jwt_clock_skew": { "message": "Sign-in failed: this device's clock is out of sync with the server. Please sync your system clock and try again.", @@ -1762,5 +1774,17 @@ "error.unknown": { "message": "Operation failed.", "description": "Generic fallback error message used when no specific error applies." + }, + "settings.ssh.privilege.hint": { + "message": "Requires {actor}. Run this instead:", + "description": "Help text under an SSH setting the user cannot change: it needs elevated privileges. {actor} is 'root' on Linux/macOS or 'administrator privileges' on Windows. Followed by a copyable command." + }, + "settings.ssh.privilege.oneWay": { + "message": "You can switch this off, but switching it back on needs {actor}:", + "description": "Warning under an SSH setting an unprivileged user may disable but not re-enable. {actor} is 'root' on Linux/macOS or 'administrator privileges' on Windows. Followed by a copyable command." + }, + "settings.ssh.privilege.oneWayInverted": { + "message": "You can switch this on, but switching it back off needs {actor}:", + "description": "Warning under the SSH authentication setting, which an unprivileged user may re-enable but not disable again. {actor} is 'root' on Linux/macOS or 'administrator privileges' on Windows. Followed by a copyable command." } } diff --git a/client/ui/i18n/locales/es/common.json b/client/ui/i18n/locales/es/common.json index 47faee61f..c036e4f75 100644 --- a/client/ui/i18n/locales/es/common.json +++ b/client/ui/i18n/locales/es/common.json @@ -1034,9 +1034,15 @@ "welcome.title": { "message": "Busque NetBird en su bandeja del sistema" }, + "welcome.titleMac": { + "message": "Busque NetBird en su barra de menús" + }, "welcome.description": { "message": "NetBird reside en su bandeja del sistema. Haga clic en el icono para conectarse, cambiar de perfil o abrir la configuración." }, + "welcome.descriptionMac": { + "message": "NetBird reside en su barra de menús. Haga clic en el icono para conectarse, cambiar de perfil o abrir la configuración." + }, "welcome.continue": { "message": "Continuar" }, @@ -1293,10 +1299,13 @@ "message": "Documentación" }, "daemon.outdated.title": { - "message": "El servicio de NetBird está desactualizado" + "message": "NetBird Client está desactualizado" }, "daemon.outdated.description": { - "message": "Actualice el servicio de NetBird para usar esta aplicación." + "message": "La nueva GUI no es compatible con su cliente anterior. Actualice su cliente para usar la nueva aplicación." + }, + "daemon.outdated.download": { + "message": "Descargar la última versión" }, "error.jwt_clock_skew": { "message": "Error al iniciar sesión: el reloj de este dispositivo no está sincronizado con el servidor. Sincronice el reloj del sistema e inténtelo de nuevo." diff --git a/client/ui/i18n/locales/fr/common.json b/client/ui/i18n/locales/fr/common.json index be0836e93..c6b91fb25 100644 --- a/client/ui/i18n/locales/fr/common.json +++ b/client/ui/i18n/locales/fr/common.json @@ -1034,9 +1034,15 @@ "welcome.title": { "message": "Cherchez NetBird dans votre barre d’état système" }, + "welcome.titleMac": { + "message": "Cherchez NetBird dans votre barre des menus" + }, "welcome.description": { "message": "NetBird se trouve dans votre barre d’état système. Cliquez sur l’icône pour vous connecter, changer de profil ou ouvrir les paramètres." }, + "welcome.descriptionMac": { + "message": "NetBird se trouve dans votre barre des menus. Cliquez sur l’icône pour vous connecter, changer de profil ou ouvrir les paramètres." + }, "welcome.continue": { "message": "Continuer" }, @@ -1293,10 +1299,13 @@ "message": "Documentation" }, "daemon.outdated.title": { - "message": "Le service NetBird est obsolète" + "message": "Le Client NetBird est obsolète" }, "daemon.outdated.description": { - "message": "Mettez à jour le service NetBird pour utiliser cette application." + "message": "La nouvelle GUI n'est pas compatible avec votre ancien client. Mettez à jour votre client pour utiliser la nouvelle application." + }, + "daemon.outdated.download": { + "message": "Télécharger la dernière version" }, "error.jwt_clock_skew": { "message": "Échec de la connexion : l’horloge de cet appareil n’est pas synchronisée avec le serveur. Veuillez synchroniser l’horloge de votre système et réessayer." diff --git a/client/ui/i18n/locales/hu/common.json b/client/ui/i18n/locales/hu/common.json index b54918364..dd5a1af6c 100644 --- a/client/ui/i18n/locales/hu/common.json +++ b/client/ui/i18n/locales/hu/common.json @@ -1034,9 +1034,15 @@ "welcome.title": { "message": "Keresse a NetBirdöt a tálcán" }, + "welcome.titleMac": { + "message": "Keresse a NetBirdöt a menüsorban" + }, "welcome.description": { "message": "A NetBird a tálcán fut. Kattintson az ikonra a csatlakozáshoz, profilváltáshoz vagy a beállítások megnyitásához." }, + "welcome.descriptionMac": { + "message": "A NetBird a menüsorban fut. Kattintson az ikonra a csatlakozáshoz, profilváltáshoz vagy a beállítások megnyitásához." + }, "welcome.continue": { "message": "Folytatás" }, @@ -1293,10 +1299,13 @@ "message": "Dokumentáció" }, "daemon.outdated.title": { - "message": "A NetBird szolgáltatás elavult" + "message": "A NetBird Kliens elavult" }, "daemon.outdated.description": { - "message": "Frissítsd a NetBird szolgáltatást az alkalmazás használatához." + "message": "Az új GUI nem kompatibilis a régebbi klienseddel. Frissítsd a klienst az új alkalmazás használatához." + }, + "daemon.outdated.download": { + "message": "Legújabb letöltése" }, "error.jwt_clock_skew": { "message": "A bejelentkezés sikertelen: az eszköz órája eltér a szerverétől. Kérjük, szinkronizálja a rendszer óráját, majd próbálja újra." diff --git a/client/ui/i18n/locales/it/common.json b/client/ui/i18n/locales/it/common.json index 603364fa2..7a2eb610c 100644 --- a/client/ui/i18n/locales/it/common.json +++ b/client/ui/i18n/locales/it/common.json @@ -1034,9 +1034,15 @@ "welcome.title": { "message": "Cerchi NetBird nella tray" }, + "welcome.titleMac": { + "message": "Cerchi NetBird nella barra dei menu" + }, "welcome.description": { "message": "NetBird risiede nella tray. Clicchi sull'icona per connettersi, cambiare profilo o aprire le impostazioni." }, + "welcome.descriptionMac": { + "message": "NetBird risiede nella barra dei menu. Clicchi sull'icona per connettersi, cambiare profilo o aprire le impostazioni." + }, "welcome.continue": { "message": "Continua" }, @@ -1293,10 +1299,13 @@ "message": "Documentazione" }, "daemon.outdated.title": { - "message": "Il servizio NetBird è obsoleto" + "message": "NetBird Client è obsoleto" }, "daemon.outdated.description": { - "message": "Aggiorna il servizio NetBird per usare questa app." + "message": "La nuova GUI non è compatibile con il tuo client precedente. Aggiorna il client per usare la nuova applicazione." + }, + "daemon.outdated.download": { + "message": "Scarica l'ultima versione" }, "error.jwt_clock_skew": { "message": "Accesso non riuscito: l'orologio di questo dispositivo non è sincronizzato con il server. Sincronizzi l'orologio di sistema e riprovi." diff --git a/client/ui/i18n/locales/ja/common.json b/client/ui/i18n/locales/ja/common.json new file mode 100644 index 000000000..326c825bf --- /dev/null +++ b/client/ui/i18n/locales/ja/common.json @@ -0,0 +1,1331 @@ +{ + "tray.tooltip": { + "message": "NetBird" + }, + "tray.status.disconnected": { + "message": "未接続" + }, + "tray.status.daemonUnavailable": { + "message": "実行されていません" + }, + "tray.status.error": { + "message": "エラー" + }, + "tray.status.connected": { + "message": "接続済み" + }, + "tray.status.connecting": { + "message": "接続中" + }, + "tray.status.needsLogin": { + "message": "ログインが必要" + }, + "tray.status.loginFailed": { + "message": "ログインに失敗しました" + }, + "tray.status.sessionExpired": { + "message": "セッションが期限切れ" + }, + "tray.session.expiresIn": { + "message": "セッションはあと{remaining}で期限切れ" + }, + "tray.session.unit.lessThanMinute": { + "message": "1分未満" + }, + "tray.session.unit.minute": { + "message": "1分" + }, + "tray.session.unit.minutes": { + "message": "{count}分" + }, + "tray.session.unit.hour": { + "message": "1時間" + }, + "tray.session.unit.hours": { + "message": "{count}時間" + }, + "tray.session.unit.day": { + "message": "1日" + }, + "tray.session.unit.days": { + "message": "{count}日" + }, + "tray.menu.open": { + "message": "NetBird を開く" + }, + "tray.menu.connect": { + "message": "接続" + }, + "tray.menu.disconnect": { + "message": "切断" + }, + "tray.menu.exitNode": { + "message": "出口ノード" + }, + "tray.menu.networks": { + "message": "リソース" + }, + "tray.menu.profiles": { + "message": "プロファイル" + }, + "tray.menu.manageProfiles": { + "message": "プロファイルの管理" + }, + "tray.menu.settings": { + "message": "設定..." + }, + "tray.menu.debugBundle": { + "message": "デバッグバンドルを作成" + }, + "tray.menu.about": { + "message": "ヘルプとサポート" + }, + "tray.menu.github": { + "message": "GitHub" + }, + "tray.menu.documentation": { + "message": "ドキュメント" + }, + "tray.menu.troubleshoot": { + "message": "トラブルシューティング" + }, + "tray.menu.downloadLatest": { + "message": "最新バージョンをダウンロード" + }, + "tray.menu.installVersion": { + "message": "バージョン {version} をインストール" + }, + "tray.menu.guiVersion": { + "message": "GUI: {version}" + }, + "tray.menu.daemonVersion": { + "message": "デーモン: {version}" + }, + "tray.menu.versionUnknown": { + "message": "—" + }, + "tray.menu.quit": { + "message": "NetBird を終了" + }, + "notify.daemonOutdated.title": { + "message": "NetBird サービスが古くなっています" + }, + "notify.daemonOutdated.body": { + "message": "このアプリを使用するには NetBird サービスを更新してください。" + }, + "notify.update.title": { + "message": "NetBird の更新が利用可能" + }, + "notify.update.body": { + "message": "NetBird {version} が利用可能です。" + }, + "notify.update.enforcedSuffix": { + "message": "管理者がこの更新を必須にしています。" + }, + "notify.error.title": { + "message": "エラー" + }, + "notify.error.connect": { + "message": "接続に失敗しました" + }, + "notify.error.disconnect": { + "message": "切断に失敗しました" + }, + "notify.error.switchProfile": { + "message": "{profile} への切り替えに失敗しました" + }, + "notify.error.exitNode": { + "message": "出口ノード {name} の更新に失敗しました" + }, + "notify.sessionExpired.title": { + "message": "NetBird セッションが期限切れ" + }, + "notify.sessionExpired.body": { + "message": "NetBird セッションの有効期限が切れました。もう一度ログインしてください。" + }, + "notify.sessionWarning.title": { + "message": "まもなくセッションが期限切れ" + }, + "notify.sessionWarning.body": { + "message": "NetBird セッションはあと{remaining}で期限切れになります。更新するには「今すぐ延長」をクリックしてください。" + }, + "notify.sessionWarning.bodyGeneric": { + "message": "NetBird セッションはまもなく期限切れになります。更新するには「今すぐ延長」をクリックしてください。" + }, + "notify.sessionWarning.extend": { + "message": "今すぐ延長" + }, + "notify.sessionWarning.dismiss": { + "message": "閉じる" + }, + "notify.sessionWarning.failed": { + "message": "NetBird セッションの延長に失敗しました" + }, + "notify.sessionWarning.successTitle": { + "message": "NetBird セッションを延長しました" + }, + "notify.sessionWarning.successBody": { + "message": "セッションが更新されました。" + }, + "notify.sessionDeadlineRejected.title": { + "message": "セッション期限が拒否されました" + }, + "notify.sessionDeadlineRejected.body": { + "message": "サーバーが無効なセッション期限を送信しました。もう一度サインインしてください。" + }, + "notify.mdm.policyApplied.title": { + "message": "NetBird 設定が更新されました" + }, + "notify.mdm.policyApplied.body": { + "message": "NetBird の構成が IT ポリシーによって更新されました。" + }, + "common.cancel": { + "message": "キャンセル" + }, + "common.save": { + "message": "保存" + }, + "common.saveChanges": { + "message": "変更を保存" + }, + "common.saving": { + "message": "保存中…" + }, + "common.close": { + "message": "閉じる" + }, + "common.copy": { + "message": "コピー" + }, + "common.togglePasswordVisibility": { + "message": "パスワードの表示を切り替え" + }, + "common.increase": { + "message": "増やす" + }, + "common.decrease": { + "message": "減らす" + }, + "common.delete": { + "message": "削除" + }, + "common.create": { + "message": "作成" + }, + "common.add": { + "message": "追加" + }, + "common.remove": { + "message": "削除" + }, + "common.refresh": { + "message": "更新" + }, + "common.loading": { + "message": "読み込み中…" + }, + "common.netbird": { + "message": "NetBird" + }, + "common.noResults.title": { + "message": "結果が見つかりませんでした" + }, + "common.noResults.description": { + "message": "結果が見つかりませんでした。別の検索語を試すか、フィルターを変更してください。" + }, + "notConnected.title": { + "message": "未接続" + }, + "notConnected.description": { + "message": "ピア、ネットワークリソース、出口ノードの詳細情報を表示するには、まず NetBird に接続してください。" + }, + "connect.status.disconnected": { + "message": "未接続" + }, + "connect.status.connecting": { + "message": "接続中..." + }, + "connect.status.connected": { + "message": "接続済み" + }, + "connect.status.disconnecting": { + "message": "切断中..." + }, + "connect.status.daemonUnavailable": { + "message": "デーモンが利用できません" + }, + "connect.status.loginRequired": { + "message": "ログインが必要" + }, + "connect.error.loginTitle": { + "message": "ログインに失敗しました" + }, + "connect.error.connectTitle": { + "message": "接続に失敗しました" + }, + "connect.error.disconnectTitle": { + "message": "切断に失敗しました" + }, + "nav.peers.title": { + "message": "ピア" + }, + "nav.peers.description": { + "message": "{total}台中{connected}台接続中" + }, + "nav.resources.title": { + "message": "リソース" + }, + "nav.resources.description": { + "message": "{total}件中{active}件有効" + }, + "nav.exitNode.title": { + "message": "出口ノード" + }, + "nav.exitNode.none": { + "message": "未使用" + }, + "nav.exitNode.using": { + "message": "{name} 経由" + }, + "header.openSettings": { + "message": "設定を開く" + }, + "header.togglePanel": { + "message": "サイドパネルを切り替え" + }, + "profile.selector.loading": { + "message": "読み込み中..." + }, + "profile.selector.noProfile": { + "message": "プロファイルなし" + }, + "profile.selector.searchPlaceholder": { + "message": "名前でプロファイルを検索..." + }, + "profile.selector.emptyTitle": { + "message": "プロファイルが見つかりません" + }, + "profile.selector.emptyDescription": { + "message": "別の検索語を試すか、新しいプロファイルを作成してください。" + }, + "profile.selector.newProfile": { + "message": "新しいプロファイル" + }, + "profile.selector.moreOptions": { + "message": "その他のオプション" + }, + "profile.selector.deregister": { + "message": "登録解除" + }, + "profile.selector.delete": { + "message": "削除" + }, + "profile.selector.switchTo": { + "message": "このプロファイルに切り替え" + }, + "profile.selector.edit": { + "message": "編集" + }, + "profile.edit.title": { + "message": "プロファイルを編集" + }, + "profile.edit.submit": { + "message": "変更を保存" + }, + "profile.dialog.title": { + "message": "プロファイル名を入力" + }, + "profile.dialog.nameLabel": { + "message": "プロファイル名" + }, + "profile.dialog.description": { + "message": "分かりやすいプロファイル名を設定してください。" + }, + "profile.dialog.placeholder": { + "message": "例: 仕事" + }, + "profile.dialog.submit": { + "message": "プロファイルを追加" + }, + "profile.dialog.required": { + "message": "プロファイル名を入力してください（例: 仕事、自宅）" + }, + "profile.dialog.managementHelp": { + "message": "NetBird Cloud または独自のサーバーを使用します。" + }, + "profile.dialog.urlUnreachable": { + "message": "このサーバーに到達できませんでした。URLを確認するか、正しいことが確実な場合はそのままプロファイルを追加してください。" + }, + "header.menu.settings": { + "message": "設定..." + }, + "header.menu.defaultView": { + "message": "デフォルト表示" + }, + "header.menu.advancedView": { + "message": "詳細表示" + }, + "header.menu.updateAvailable": { + "message": "更新が利用可能" + }, + "header.menu.open": { + "message": "メニューを開く" + }, + "header.profile.switch": { + "message": "プロファイルを切り替え" + }, + "connect.toggle.label": { + "message": "NetBird 接続を切り替え" + }, + "connect.localIp.label": { + "message": "ローカル IP アドレス" + }, + "common.search": { + "message": "検索" + }, + "common.filter": { + "message": "フィルター" + }, + "exitNodes.dropdown.trigger": { + "message": "出口ノードを選択" + }, + "peers.row.label": { + "message": "{name} の詳細を開く、{status}" + }, + "peers.dialog.title": { + "message": "ピアの詳細" + }, + "networks.row.toggle": { + "message": "{name} を切り替え" + }, + "networks.bulk.label": { + "message": "表示中のすべてのリソースを切り替え" + }, + "profile.switch.title": { + "message": "プロファイルを「{name}」に切り替えますか？" + }, + "profile.switch.message": { + "message": "プロファイルを切り替えてもよろしいですか？\n現在のプロファイルは切断されます。" + }, + "profile.switch.confirm": { + "message": "確認" + }, + "profile.deregister.title": { + "message": "プロファイル「{name}」の登録を解除しますか？" + }, + "profile.deregister.message": { + "message": "このプロファイルの登録を解除してもよろしいですか？\n再度使用するにはログインが必要になります。" + }, + "profile.deregister.confirm": { + "message": "登録解除" + }, + "profile.delete.title": { + "message": "プロファイル「{name}」を削除しますか？" + }, + "profile.delete.message": { + "message": "このプロファイルを削除してもよろしいですか？\nこの操作は取り消せません。" + }, + "profile.delete.disabledActive": { + "message": "使用中のプロファイルは削除できません。削除する前に別のプロファイルに切り替えてください。" + }, + "profile.delete.disabledDefault": { + "message": "デフォルトのプロファイルは削除できません。" + }, + "profile.error.switchTitle": { + "message": "プロファイルの切り替えに失敗しました" + }, + "profile.error.deregisterTitle": { + "message": "プロファイルの登録解除に失敗しました" + }, + "profile.error.deleteTitle": { + "message": "プロファイルの削除に失敗しました" + }, + "profile.error.createTitle": { + "message": "プロファイルの作成に失敗しました" + }, + "profile.error.editTitle": { + "message": "プロファイルの編集に失敗しました" + }, + "profile.error.loadTitle": { + "message": "プロファイルの読み込みに失敗しました" + }, + "profile.dropdown.activeProfile": { + "message": "使用中のプロファイル" + }, + "profile.dropdown.switchProfile": { + "message": "プロファイルを切り替え" + }, + "profile.dropdown.noEmail": { + "message": "その他" + }, + "profile.dropdown.addProfile": { + "message": "プロファイルを追加" + }, + "profile.dropdown.manageProfiles": { + "message": "プロファイルの管理" + }, + "profile.dropdown.settings": { + "message": "設定" + }, + "settings.profiles.section.profiles": { + "message": "プロファイル" + }, + "settings.profiles.intro": { + "message": "仕事用と個人用のアカウント、あるいは異なる管理サーバーなど、複数の NetBird ID を並行して管理できます。以下でプロファイルの追加、登録解除、削除ができます。" + }, + "settings.profiles.addProfile": { + "message": "プロファイルを追加" + }, + "settings.profiles.active": { + "message": "使用中" + }, + "settings.profiles.emptyTitle": { + "message": "プロファイルがありません" + }, + "settings.profiles.emptyDescription": { + "message": "NetBird 管理サーバーに接続するプロファイルを作成してください。" + }, + "settings.error.loadTitle": { + "message": "設定の読み込みに失敗しました" + }, + "settings.error.saveTitle": { + "message": "設定の保存に失敗しました" + }, + "settings.error.debugBundleTitle": { + "message": "デバッグバンドルの作成に失敗しました" + }, + "settings.nav.label": { + "message": "設定セクション" + }, + "settings.tabs.general": { + "message": "一般" + }, + "settings.tabs.network": { + "message": "ネットワーク" + }, + "settings.tabs.security": { + "message": "セキュリティ" + }, + "settings.tabs.profiles": { + "message": "プロファイル" + }, + "settings.tabs.ssh": { + "message": "SSH" + }, + "settings.tabs.advanced": { + "message": "詳細設定" + }, + "settings.tabs.troubleshooting": { + "message": "トラブルシューティング" + }, + "settings.tabs.about": { + "message": "情報" + }, + "settings.tabs.updateAvailable": { + "message": "更新が利用可能" + }, + "settings.general.section.general": { + "message": "一般" + }, + "settings.general.section.connection": { + "message": "接続" + }, + "settings.general.connectOnStartup.label": { + "message": "起動時に接続" + }, + "settings.general.connectOnStartup.help": { + "message": "サービスの起動時に自動的に接続を確立します。" + }, + "settings.general.notifications.label": { + "message": "デスクトップ通知" + }, + "settings.general.notifications.help": { + "message": "新しい更新や接続イベントに関するデスクトップ通知を表示します。" + }, + "settings.general.autostart.label": { + "message": "ログイン時に NetBird UI を起動" + }, + "settings.general.autostart.help": { + "message": "ログイン時に NetBird インターフェースを自動的に起動します。これはグラフィカルインターフェースにのみ影響し、バックグラウンドサービスには影響しません。" + }, + "settings.general.autostart.errorTitle": { + "message": "自動起動の変更に失敗しました" + }, + "settings.general.language.label": { + "message": "表示言語" + }, + "settings.general.language.help": { + "message": "NetBird インターフェースの言語を選択します。" + }, + "settings.general.language.search": { + "message": "言語を検索…" + }, + "settings.general.language.empty": { + "message": "一致する言語がありません。" + }, + "settings.general.management.label": { + "message": "管理サーバー" + }, + "settings.general.management.help": { + "message": "NetBird Cloud または自身のセルフホスト管理サーバーに接続します。変更するとクライアントが再接続します。" + }, + "settings.general.management.cloud": { + "message": "クラウド" + }, + "settings.general.management.selfHosted": { + "message": "セルフホスト" + }, + "settings.general.management.urlPlaceholder": { + "message": "https://netbird.selfhosted.com:443" + }, + "settings.general.management.urlError": { + "message": "有効なURLを入力してください（例: https://netbird.selfhosted.com:443）" + }, + "settings.general.management.urlUnreachable": { + "message": "このサーバーに到達できませんでした。URLを確認するか、正しいことが確実な場合はそのまま保存してください。" + }, + "settings.general.management.switchCloudTitle": { + "message": "NetBird Cloud に切り替えますか？" + }, + "settings.general.management.switchCloudMessage": { + "message": "セルフホストサーバーが切断されます。\n再度ログインが必要になる場合があります。" + }, + "settings.general.management.switchCloudConfirm": { + "message": "クラウドに切り替え" + }, + "settings.network.section.connectivity": { + "message": "ネットワーク接続" + }, + "settings.network.section.routingDns": { + "message": "ルーティングとDNS" + }, + "settings.network.monitor.label": { + "message": "ネットワーク変更時に再接続" + }, + "settings.network.monitor.help": { + "message": "ネットワークを監視し、Wi-Fiの切り替え、イーサネットの変更、スリープからの復帰などの変化時に自動的に再接続します。" + }, + "settings.network.dns.label": { + "message": "DNSを有効にする" + }, + "settings.network.dns.help": { + "message": "NetBird が管理する DNS 設定をホストのリゾルバに適用します。" + }, + "settings.network.clientRoutes.label": { + "message": "クライアントルートを有効にする" + }, + "settings.network.clientRoutes.help": { + "message": "他のピアからルートを受け入れ、そのネットワークに到達できるようにします。" + }, + "settings.network.serverRoutes.label": { + "message": "サーバールートを有効にする" + }, + "settings.network.serverRoutes.help": { + "message": "このホストのローカルルートを他のピアにアドバタイズします。" + }, + "settings.network.ipv6.label": { + "message": "IPv6を有効にする" + }, + "settings.network.ipv6.help": { + "message": "NetBird オーバーレイネットワークで IPv6 アドレッシングを使用します。" + }, + "settings.security.section.firewall": { + "message": "ファイアウォール" + }, + "settings.security.section.encryption": { + "message": "暗号化" + }, + "settings.security.blockInbound.label": { + "message": "受信トラフィックをブロック" + }, + "settings.security.blockInbound.help": { + "message": "このデバイスおよびこのデバイスがルーティングするネットワークへの、ピアからの要求されていない接続を拒否します。送信トラフィックには影響しません。" + }, + "settings.security.blockLan.label": { + "message": "LANアクセスをブロック" + }, + "settings.security.blockLan.help": { + "message": "このデバイスがピアのトラフィックをルーティングする際に、ピアがローカルネットワークやそのデバイスに到達できないようにします。" + }, + "settings.security.rosenpass.label": { + "message": "量子耐性を有効にする" + }, + "settings.security.rosenpass.help": { + "message": "WireGuard® に加えて Rosenpass によるポスト量子鍵交換を追加します。" + }, + "settings.security.rosenpassPermissive.label": { + "message": "寛容モードを有効にする" + }, + "settings.security.rosenpassPermissive.help": { + "message": "量子耐性に対応していないピアへの接続を許可します。" + }, + "settings.ssh.section.server": { + "message": "サーバー" + }, + "settings.ssh.section.capabilities": { + "message": "機能" + }, + "settings.ssh.section.authentication": { + "message": "認証" + }, + "settings.ssh.server.label": { + "message": "SSHサーバーを有効にする" + }, + "settings.ssh.server.help": { + "message": "このホストで NetBird SSH サーバーを実行し、他のピアが接続できるようにします。" + }, + "settings.ssh.root.label": { + "message": "rootログインを許可" + }, + "settings.ssh.root.help": { + "message": "ピアが root ユーザーとしてサインインできるようにします。無効にすると非特権アカウントが必要になります。" + }, + "settings.ssh.sftp.label": { + "message": "SFTPを許可" + }, + "settings.ssh.sftp.help": { + "message": "ネイティブの SFTP または SCP クライアントを使用してファイルを安全に転送します。" + }, + "settings.ssh.localForward.label": { + "message": "ローカルポート転送" + }, + "settings.ssh.localForward.help": { + "message": "接続するピアが、このホストから到達可能なサービスへローカルポートをトンネリングできるようにします。" + }, + "settings.ssh.remoteForward.label": { + "message": "リモートポート転送" + }, + "settings.ssh.remoteForward.help": { + "message": "接続するピアが、このホスト上のポートを自身のマシンに公開できるようにします。" + }, + "settings.ssh.jwt.label": { + "message": "JWT認証を有効にする" + }, + "settings.ssh.jwt.help": { + "message": "各 SSH セッションを IdP に対して検証し、ユーザー ID と監査を行います。無効にするとネットワークの ACL ポリシーのみに依存します。IdP が利用できない場合に便利です。" + }, + "settings.ssh.jwtTtl.label": { + "message": "JWTキャッシュTTL" + }, + "settings.ssh.jwtTtl.help": { + "message": "発信 SSH 接続で再度認証を求めるまでに、このクライアントが JWT をキャッシュする期間です。0 に設定するとキャッシュを無効にし、接続ごとに認証します。" + }, + "settings.ssh.jwtTtl.suffix": { + "message": "秒" + }, + "settings.advanced.section.interface": { + "message": "インターフェース" + }, + "settings.advanced.section.security": { + "message": "セキュリティ" + }, + "settings.advanced.interfaceName.label": { + "message": "名前" + }, + "settings.advanced.interfaceName.error": { + "message": "1〜15文字の英字、数字、ドット、ハイフン、アンダースコアを使用してください。" + }, + "settings.advanced.interfaceName.errorMac": { + "message": "「utun」に続けて数字で始まる必要があります（例: utun100）。" + }, + "settings.advanced.port.label": { + "message": "ポート" + }, + "settings.advanced.port.error": { + "message": "{min}〜{max}の範囲でポートを入力してください。" + }, + "settings.advanced.port.help": { + "message": "0 に設定すると、ランダムな空きポートが使用されます。" + }, + "settings.advanced.mtu.label": { + "message": "MTU" + }, + "settings.advanced.mtu.error": { + "message": "{min}〜{max}の範囲で MTU 値を入力してください。" + }, + "settings.advanced.psk.label": { + "message": "事前共有鍵" + }, + "settings.advanced.psk.help": { + "message": "追加の対称暗号化のためのオプションの WireGuard PSK です。NetBird セットアップキーとは異なります。同じ事前共有鍵を使用するピアとのみ通信できます。" + }, + "settings.troubleshooting.section.title": { + "message": "デバッグバンドル" + }, + "settings.troubleshooting.anonymize.label": { + "message": "機密情報を匿名化" + }, + "settings.troubleshooting.anonymize.help": { + "message": "ログからパブリック IP アドレスと NetBird 以外のドメインを隠します。" + }, + "settings.troubleshooting.systemInfo.label": { + "message": "システム情報を含める" + }, + "settings.troubleshooting.systemInfo.help": { + "message": "OS、カーネル、ネットワークインターフェース、ルーティングテーブルを含めます。" + }, + "settings.troubleshooting.upload.label": { + "message": "バンドルを NetBird サーバーにアップロード" + }, + "settings.troubleshooting.upload.help": { + "message": "NetBird サポートと共有するためのアップロードキーを返します。" + }, + "settings.troubleshooting.trace.label": { + "message": "トレースログを有効にする" + }, + "settings.troubleshooting.trace.help": { + "message": "ログレベルを TRACE に引き上げ、その後元に戻します。" + }, + "settings.troubleshooting.capture.label": { + "message": "キャプチャセッション" + }, + "settings.troubleshooting.capture.help": { + "message": "再接続して待機し、問題を再現できるようにします。" + }, + "settings.troubleshooting.packets.label": { + "message": "ネットワークパケットをキャプチャ" + }, + "settings.troubleshooting.packets.help": { + "message": "キャプチャ期間中のネットワークトラフィックを .pcap として保存します。" + }, + "settings.troubleshooting.duration.label": { + "message": "キャプチャ時間" + }, + "settings.troubleshooting.duration.help": { + "message": "キャプチャセッションを実行する時間です。" + }, + "settings.troubleshooting.duration.suffix": { + "message": "分" + }, + "settings.troubleshooting.create": { + "message": "バンドルを作成" + }, + "settings.troubleshooting.progress.description": { + "message": "ログ、システムの詳細、接続状態を収集しています。通常はしばらくで完了します。完了するまで NetBird を使い続けても、設定を閉じても構いません。" + }, + "settings.troubleshooting.cancelling": { + "message": "キャンセル中…" + }, + "settings.troubleshooting.done.uploadedTitle": { + "message": "デバッグバンドルのアップロードに成功しました！" + }, + "settings.troubleshooting.done.savedTitle": { + "message": "バンドルを保存しました" + }, + "settings.troubleshooting.done.uploadedDescription": { + "message": "下記のアップロードキーを NetBird サポート と共有してください。ローカルコピーもお使いのデバイスに保存されました。" + }, + "settings.troubleshooting.done.savedDescription": { + "message": "デバッグバンドルはローカルに保存されました。" + }, + "settings.troubleshooting.done.copyKey": { + "message": "キーをコピー" + }, + "settings.troubleshooting.done.openFolder": { + "message": "フォルダを開く" + }, + "settings.troubleshooting.done.openFileLocation": { + "message": "ファイルの場所を開く" + }, + "settings.troubleshooting.uploadFailedWithReason": { + "message": "アップロードに失敗しました: {reason} バンドルはローカルに保存されています。" + }, + "settings.troubleshooting.uploadFailed": { + "message": "アップロードに失敗しました。バンドルはローカルに保存されています。" + }, + "settings.troubleshooting.stage.reconnecting": { + "message": "NetBird を再接続しています…" + }, + "settings.troubleshooting.stage.capturing": { + "message": "デバッグログをキャプチャしています" + }, + "settings.troubleshooting.stage.bundling": { + "message": "デバッグバンドルを生成しています…" + }, + "settings.troubleshooting.stage.uploading": { + "message": "NetBird にアップロードしています…" + }, + "settings.troubleshooting.stage.cancelling": { + "message": "キャンセル中…" + }, + "settings.about.client": { + "message": "NetBird Client v{version}" + }, + "settings.about.clientName": { + "message": "NetBird Client" + }, + "settings.about.development": { + "message": "[開発版]" + }, + "settings.about.gui": { + "message": "GUI v{version}" + }, + "settings.about.guiName": { + "message": "GUI" + }, + "settings.about.copyright": { + "message": "© {year} NetBird. All Rights Reserved." + }, + "settings.about.links.imprint": { + "message": "運営者情報" + }, + "settings.about.links.privacy": { + "message": "プライバシー" + }, + "settings.about.links.cla": { + "message": "CLA" + }, + "settings.about.links.terms": { + "message": "利用規約" + }, + "settings.about.community.github": { + "message": "GitHub" + }, + "settings.about.community.slack": { + "message": "Slack" + }, + "settings.about.community.forum": { + "message": "フォーラム" + }, + "settings.about.community.documentation": { + "message": "ドキュメント" + }, + "settings.about.community.feedback": { + "message": "フィードバック" + }, + "update.banner.message": { + "message": "NetBird {version} をインストールする準備ができました。" + }, + "update.banner.later": { + "message": "後で" + }, + "update.banner.installNow": { + "message": "今すぐインストール" + }, + "update.card.versionAvailableDownload": { + "message": "バージョン {version} がダウンロード可能です。" + }, + "update.card.versionAvailableInstall": { + "message": "バージョン {version} がインストール可能です。" + }, + "update.card.whatsNew": { + "message": "新機能は？" + }, + "update.card.installNow": { + "message": "今すぐインストール" + }, + "update.card.getInstaller": { + "message": "ダウンロード" + }, + "update.card.autoCheckInterval": { + "message": "NetBird はバックグラウンドで更新を確認します。" + }, + "update.card.changelog": { + "message": "変更履歴" + }, + "update.card.onLatestVersion": { + "message": "最新バージョンを使用しています" + }, + "update.header.tooltip": { + "message": "更新が利用可能" + }, + "update.overlay.updatingVersion": { + "message": "NetBird を v{version} に更新しています" + }, + "update.overlay.updating": { + "message": "NetBird を更新しています" + }, + "update.overlay.description": { + "message": "新しいバージョンが利用可能で、インストール中です。更新が完了すると NetBird は自動的に再起動します。" + }, + "update.overlay.error.timeoutTitle": { + "message": "更新に時間がかかっています" + }, + "update.overlay.error.timeoutDescription": { + "message": "{target} のインストールに時間がかかりすぎ、完了しませんでした。" + }, + "update.overlay.error.canceledTitle": { + "message": "更新が停止されました" + }, + "update.overlay.error.canceledDescription": { + "message": "{target} への更新は完了前にキャンセルされました。" + }, + "update.overlay.error.failTitle": { + "message": "更新をインストールできませんでした" + }, + "update.overlay.error.failDescription": { + "message": "{target} をインストールできませんでした。" + }, + "update.overlay.error.unknownMessage": { + "message": "不明なエラー" + }, + "update.overlay.error.targetVersion": { + "message": "v{version}" + }, + "update.overlay.error.targetFallback": { + "message": "新しいバージョン" + }, + "update.error.loadStateTitle": { + "message": "更新状態の読み込みに失敗しました" + }, + "update.error.triggerTitle": { + "message": "更新の開始に失敗しました" + }, + "update.page.versionLine": { + "message": "クライアントを次のバージョンに更新しています: {version}。" + }, + "update.page.versionLineGeneric": { + "message": "クライアントを更新しています。" + }, + "update.page.outdated": { + "message": "クライアントのバージョンが、管理サーバーで設定された自動更新バージョンより古くなっています。" + }, + "update.page.status.running": { + "message": "更新中" + }, + "update.page.status.timeout": { + "message": "更新がタイムアウトしました。もう一度お試しください。" + }, + "update.page.status.canceled": { + "message": "更新がキャンセルされました。" + }, + "update.page.status.failed": { + "message": "更新に失敗しました: {message}" + }, + "update.page.status.unknownError": { + "message": "不明な更新エラー" + }, + "update.page.failedTitle": { + "message": "更新に失敗しました" + }, + "update.page.timeoutMessage": { + "message": "更新がタイムアウトしました。" + }, + "update.page.dontClose": { + "message": "このウィンドウを閉じないでください。" + }, + "update.page.updating": { + "message": "更新中…" + }, + "update.page.complete": { + "message": "更新が完了しました" + }, + "update.page.failed": { + "message": "更新に失敗しました" + }, + "window.title.settings": { + "message": "設定" + }, + "window.title.signIn": { + "message": "サインイン" + }, + "window.title.sessionExpiration": { + "message": "セッションの期限切れ" + }, + "window.title.updating": { + "message": "更新中" + }, + "window.title.welcome": { + "message": "NetBird へようこそ" + }, + "window.title.error": { + "message": "エラー" + }, + "welcome.title": { + "message": "トレイの NetBird を確認してください" + }, + "welcome.titleMac": { + "message": "メニューバーの NetBird を確認してください" + }, + "welcome.description": { + "message": "NetBird はトレイに常駐します。アイコンをクリックして、接続、プロファイルの切り替え、設定を開くことができます。" + }, + "welcome.descriptionMac": { + "message": "NetBird はメニューバーに常駐します。アイコンをクリックして、接続、プロファイルの切り替え、設定を開くことができます。" + }, + "welcome.continue": { + "message": "続ける" + }, + "welcome.back": { + "message": "戻る" + }, + "welcome.management.title": { + "message": "NetBird をセットアップ" + }, + "welcome.management.description": { + "message": "「続ける」をクリックして開始するか、独自の NetBird サーバーをお持ちの場合は「セルフホスト」を選択してください。" + }, + "welcome.management.cloud.title": { + "message": "NetBird Cloud" + }, + "welcome.management.cloud.description": { + "message": "当社のホスト型サービスを使用します。セットアップは不要です。" + }, + "welcome.management.selfHosted.title": { + "message": "セルフホスト" + }, + "welcome.management.selfHosted.description": { + "message": "独自の管理サーバーに接続します。" + }, + "welcome.management.urlLabel": { + "message": "管理サーバーのURL" + }, + "welcome.management.urlPlaceholder": { + "message": "https://netbird.selfhosted.com:443" + }, + "welcome.management.urlInvalid": { + "message": "有効なURLを入力してください（例: https://netbird.selfhosted.com:443）" + }, + "welcome.management.urlUnreachable": { + "message": "このサーバーに到達できませんでした。URLまたはネットワークを確認し、正しいことが確実な場合は続行してください。" + }, + "welcome.management.checking": { + "message": "確認中…" + }, + "browserLogin.title": { + "message": "ブラウザでログインを完了してください" + }, + "browserLogin.notSeeing": { + "message": "サインインを完了できるようブラウザのタブを開きました。表示されませんか？" + }, + "browserLogin.tryAgain": { + "message": "再試行" + }, + "browserLogin.openFailedTitle": { + "message": "ブラウザの起動に失敗しました" + }, + "sessionExpiration.title": { + "message": "まもなくセッションが期限切れになります" + }, + "sessionExpiration.titleLater": { + "message": "セッションが期限切れになります" + }, + "sessionExpiration.description": { + "message": "このデバイスはまもなく切断されます。ブラウザでのサインインで更新してください。" + }, + "sessionExpiration.descriptionLater": { + "message": "ブラウザでサインインすると、このデバイスがネットワークに接続されたままになります。" + }, + "sessionExpiration.stay": { + "message": "セッションを更新" + }, + "sessionExpiration.authenticate": { + "message": "認証" + }, + "sessionExpiration.logout": { + "message": "ログアウト" + }, + "sessionExpiration.expired": { + "message": "セッションが期限切れになりました" + }, + "sessionExpiration.expiredDescription": { + "message": "デバイスが切断されました。再接続するにはブラウザでサインインして認証してください。" + }, + "sessionExpiration.close": { + "message": "閉じる" + }, + "sessionExpiration.extendFailedTitle": { + "message": "セッションの延長に失敗しました" + }, + "sessionExpiration.logoutFailedTitle": { + "message": "ログアウトに失敗しました" + }, + "peers.search.placeholder": { + "message": "名前または IP で検索" + }, + "peers.filter.all": { + "message": "すべて" + }, + "peers.filter.online": { + "message": "オンライン" + }, + "peers.filter.offline": { + "message": "オフライン" + }, + "peers.empty.title": { + "message": "利用可能なピアがありません" + }, + "peers.empty.description": { + "message": "利用可能なピアがないか、いずれのピアにもアクセス権がありません。" + }, + "peers.details.domain": { + "message": "ドメイン" + }, + "peers.details.netbirdIp": { + "message": "NetBird IP" + }, + "peers.details.netbirdIpv6": { + "message": "NetBird IPv6" + }, + "peers.details.publicKey": { + "message": "公開鍵" + }, + "peers.details.connection": { + "message": "接続" + }, + "peers.details.latency": { + "message": "レイテンシ" + }, + "peers.details.lastHandshake": { + "message": "最終ハンドシェイク" + }, + "peers.details.statusSince": { + "message": "最終接続更新" + }, + "peers.details.bytes": { + "message": "バイト" + }, + "peers.details.bytesSent": { + "message": "送信" + }, + "peers.details.bytesReceived": { + "message": "受信" + }, + "peers.details.localIce": { + "message": "ローカル ICE" + }, + "peers.details.remoteIce": { + "message": "リモート ICE" + }, + "peers.details.never": { + "message": "なし" + }, + "peers.details.justNow": { + "message": "たった今" + }, + "peers.details.refresh": { + "message": "更新" + }, + "peers.status.connected": { + "message": "接続済み" + }, + "peers.status.connecting": { + "message": "接続中" + }, + "peers.status.disconnected": { + "message": "未接続" + }, + "peers.details.relayAddress": { + "message": "リレー" + }, + "peers.details.networks": { + "message": "リソース" + }, + "peers.details.relayed": { + "message": "リレー経由" + }, + "peers.details.p2p": { + "message": "P2P" + }, + "peers.details.rosenpass": { + "message": "Rosenpass 有効" + }, + "networks.search.placeholder": { + "message": "ネットワークまたはドメインで検索" + }, + "networks.filter.all": { + "message": "すべて" + }, + "networks.filter.active": { + "message": "有効" + }, + "networks.filter.overlapping": { + "message": "重複" + }, + "networks.empty.title": { + "message": "利用可能なリソースがありません" + }, + "networks.empty.description": { + "message": "利用可能なネットワークリソースがないか、いずれのリソースにもアクセス権がありません。" + }, + "networks.selected": { + "message": "選択中" + }, + "networks.unselected": { + "message": "未選択" + }, + "networks.ips.heading": { + "message": "解決された IP" + }, + "networks.bulk.selectionCount": { + "message": "{total}件中{selected}件有効" + }, + "networks.bulk.enableAll": { + "message": "すべて有効化" + }, + "networks.bulk.disableAll": { + "message": "すべて無効化" + }, + "exitNodes.search.placeholder": { + "message": "出口ノードを検索" + }, + "exitNodes.none": { + "message": "なし" + }, + "exitNodes.empty.title": { + "message": "利用可能な出口ノードがありません" + }, + "exitNodes.empty.description": { + "message": "このピアと共有されている出口ノードはありません。" + }, + "exitNodes.card.title": { + "message": "出口ノード" + }, + "exitNodes.card.statusActive": { + "message": "有効" + }, + "exitNodes.card.statusInactive": { + "message": "無効" + }, + "exitNodes.dropdown.noneTitle": { + "message": "なし" + }, + "exitNodes.dropdown.noneDescription": { + "message": "出口ノードを使用しない直接接続" + }, + "quickActions.connect": { + "message": "接続" + }, + "quickActions.disconnect": { + "message": "切断" + }, + "daemon.unavailable.title": { + "message": "NetBird サービスが実行されていません" + }, + "daemon.unavailable.description": { + "message": "サービスが実行されると、アプリは自動的に再接続します。" + }, + "daemon.unavailable.docsLink": { + "message": "ドキュメント" + }, + "daemon.outdated.title": { + "message": "NetBird サービスが古くなっています" + }, + "daemon.outdated.description": { + "message": "このアプリを使用するには NetBird サービスを更新してください。" + }, + "error.jwt_clock_skew": { + "message": "サインインに失敗しました: このデバイスの時計がサーバーと同期していません。システムの時計を同期してからもう一度お試しください。" + }, + "error.jwt_expired": { + "message": "サインイントークンの有効期限が切れました。もう一度サインインしてください。" + }, + "error.jwt_signature_invalid": { + "message": "サインインに失敗しました: トークンの署名が無効です。管理者にお問い合わせください。" + }, + "error.session_expired": { + "message": "セッションの有効期限が切れました。もう一度サインインしてください。" + }, + "error.invalid_setup_key": { + "message": "セットアップキーがないか、無効です。" + }, + "error.permission_denied": { + "message": "サインインがサーバーによって拒否されました。" + }, + "error.daemon_unreachable": { + "message": "NetBird デーモンが応答していません。サービスが実行されているか確認してください。" + }, + "error.unknown": { + "message": "操作に失敗しました。" + } +} diff --git a/client/ui/i18n/locales/pt/common.json b/client/ui/i18n/locales/pt/common.json index 2ed0a94c5..37b02d5a8 100644 --- a/client/ui/i18n/locales/pt/common.json +++ b/client/ui/i18n/locales/pt/common.json @@ -1034,9 +1034,15 @@ "welcome.title": { "message": "Procure o NetBird na sua bandeja" }, + "welcome.titleMac": { + "message": "Procure o NetBird na sua barra de menus" + }, "welcome.description": { "message": "O NetBird fica na sua bandeja. Clique no ícone para conectar, alternar perfis ou abrir as configurações." }, + "welcome.descriptionMac": { + "message": "O NetBird fica na sua barra de menus. Clique no ícone para conectar, alternar perfis ou abrir as configurações." + }, "welcome.continue": { "message": "Continuar" }, @@ -1293,10 +1299,13 @@ "message": "Documentação" }, "daemon.outdated.title": { - "message": "O serviço NetBird está desatualizado" + "message": "O NetBird Client está desatualizado" }, "daemon.outdated.description": { - "message": "Atualize o serviço NetBird para usar este aplicativo." + "message": "A nova GUI não é compatível com o seu cliente mais antigo. Atualize o seu cliente para usar o novo aplicativo." + }, + "daemon.outdated.download": { + "message": "Baixar a versão mais recente" }, "error.jwt_clock_skew": { "message": "Falha no login: o relógio deste dispositivo está fora de sincronia com o servidor. Sincronize o relógio do sistema e tente novamente." diff --git a/client/ui/i18n/locales/ru/common.json b/client/ui/i18n/locales/ru/common.json index 6ba7de8cc..b9ae59df2 100644 --- a/client/ui/i18n/locales/ru/common.json +++ b/client/ui/i18n/locales/ru/common.json @@ -1034,9 +1034,15 @@ "welcome.title": { "message": "Найдите NetBird в системном трее" }, + "welcome.titleMac": { + "message": "Найдите NetBird в строке меню" + }, "welcome.description": { "message": "NetBird находится в системном трее. Нажмите на значок, чтобы подключиться, переключить профиль или открыть настройки." }, + "welcome.descriptionMac": { + "message": "NetBird находится в строке меню. Нажмите на значок, чтобы подключиться, переключить профиль или открыть настройки." + }, "welcome.continue": { "message": "Продолжить" }, @@ -1293,10 +1299,13 @@ "message": "Документация" }, "daemon.outdated.title": { - "message": "Служба NetBird устарела" + "message": "Клиент NetBird устарел" }, "daemon.outdated.description": { - "message": "Обновите службу NetBird, чтобы использовать это приложение." + "message": "Новый GUI несовместим с вашим более старым клиентом. Обновите клиент, чтобы использовать новое приложение." + }, + "daemon.outdated.download": { + "message": "Скачать последнюю версию" }, "error.jwt_clock_skew": { "message": "Не удалось войти: часы этого устройства рассинхронизированы с сервером. Синхронизируйте системные часы и повторите попытку." diff --git a/client/ui/i18n/locales/zh-CN/common.json b/client/ui/i18n/locales/zh-CN/common.json index 609344fc0..2141a770d 100644 --- a/client/ui/i18n/locales/zh-CN/common.json +++ b/client/ui/i18n/locales/zh-CN/common.json @@ -1034,9 +1034,15 @@ "welcome.title": { "message": "在托盘中查找 NetBird" }, + "welcome.titleMac": { + "message": "在菜单栏中查找 NetBird" + }, "welcome.description": { "message": "NetBird 驻留在您的托盘中。点击图标即可连接、切换配置文件或打开设置。" }, + "welcome.descriptionMac": { + "message": "NetBird 驻留在您的菜单栏中。点击图标即可连接、切换配置文件或打开设置。" + }, "welcome.continue": { "message": "继续" }, @@ -1293,10 +1299,13 @@ "message": "文档" }, "daemon.outdated.title": { - "message": "NetBird 服务版本过旧" + "message": "NetBird 客户端版本过旧" }, "daemon.outdated.description": { - "message": "请更新 NetBird 服务以使用此应用。" + "message": "新版 GUI 与您较旧的客户端不兼容。请更新客户端以使用新应用。" + }, + "daemon.outdated.download": { + "message": "下载最新版本" }, "error.jwt_clock_skew": { "message": "登录失败：此设备的时钟与服务器不同步。请同步您的系统时钟后重试。" diff --git a/client/ui/main.go b/client/ui/main.go index e6b77762c..782e76d1c 100644 --- a/client/ui/main.go +++ b/client/ui/main.go @@ -96,7 +96,6 @@ func main() { } }) - settings := services.NewSettings(conn) profiles := services.NewProfiles(conn) // updater.Holder owns the typed update State; DaemonFeed feeds it and the // Update service is a thin Wails-bound facade over it plus the install RPCs. @@ -117,6 +116,7 @@ func main() { bundle, prefStore, localizer := buildI18n(app) // After bundle + prefStore: both are used to localise daemon errors. + settings := services.NewSettings(conn, bundle, prefStore, daemonAddr) connection := services.NewConnection(conn, bundle, prefStore) profileSwitcher := services.NewProfileSwitcher(profiles, connection, daemonFeed) // authsession.Session owns the full extend + dismiss surface the tray @@ -197,6 +197,9 @@ func main() { // daemon may keep the main window from showing, so the OS toast is the // only reliable signal the user gets. go notifyIfDaemonOutdated(compat, notifier, localizer) + // One-time launch-on-login default for fresh installs; gated by the + // NetBird footprint check, MDM policy, and the persisted marker. + go applyAutostartDefault(context.Background(), services.NewAutostart(app.Autostart), prefStore, prefStore.ExistedAtLoad()) }) if err := app.Run(); err != nil { @@ -278,6 +281,9 @@ func newApplication(onSecondInstance func()) *application.App { Linux: application.LinuxOptions{ ProgramName: "netbird", }, + Windows: application.WindowsOptions{ + WndProcInterceptor: endSessionInterceptor(), + }, SingleInstance: &application.SingleInstanceOptions{ UniqueID: "io.netbird.ui", OnSecondInstanceLaunch: func(_ application.SecondInstanceData) { @@ -364,6 +370,9 @@ func newMainWindow(app *application.App, prefStore *preferences.Store) *applicat // Hide instead of quit on close; "really quit" is reached via tray -> Quit. window.RegisterHook(events.Common.WindowClosing, func(e *application.WindowEvent) { + if services.ShuttingDown() { + return + } e.Cancel() window.Hide() }) diff --git a/client/ui/netbird-ui.rb.tmpl b/client/ui/netbird-ui.rb.tmpl index 06971909d..1c77e6717 100644 --- a/client/ui/netbird-ui.rb.tmpl +++ b/client/ui/netbird-ui.rb.tmpl @@ -29,8 +29,13 @@ cask "{{ $projectName }}" do end uninstall_preflight do - system_command "#{appdir}/Netbird UI.app/uninstaller.sh", - sudo: false + system_command "/bin/sh", + args: ["-c", <<~CMD], + launchctl bootout system/netbird 2>/dev/null || \ + launchctl unload /Library/LaunchDaemons/netbird.plist 2>/dev/null || true + rm -f /Library/LaunchDaemons/netbird.plist + CMD + sudo: true end name "Netbird UI" diff --git a/client/ui/preferences/store.go b/client/ui/preferences/store.go index afc854185..df6fbbb16 100644 --- a/client/ui/preferences/store.go +++ b/client/ui/preferences/store.go @@ -54,6 +54,10 @@ type UIPreferences struct { Language i18n.LanguageCode `json:"language"` ViewMode ViewMode `json:"viewMode"` OnboardingCompleted bool `json:"onboardingCompleted"` + // AutostartInitialized records that the one-time autostart default + // decision has run for this OS user. It only ever transitions to true + // and is never reset, so the default-on flow runs at most once, ever. + AutostartInitialized bool `json:"autostartInitialized"` } // LanguageValidator rejects SetLanguage inputs with no shipped bundle. @@ -72,8 +76,9 @@ type Emitter interface { type Store struct { path string - mu sync.RWMutex - current UIPreferences + mu sync.RWMutex + current UIPreferences + existedAtLoad bool subsMu sync.Mutex subs []chan UIPreferences @@ -157,6 +162,27 @@ func (s *Store) SetOnboardingCompleted(done bool) error { return nil } +// SetAutostartInitialized persists the one-time autostart decision marker. +// No-op if unchanged. +func (s *Store) SetAutostartInitialized(done bool) error { + s.mu.Lock() + if s.current.AutostartInitialized == done { + s.mu.Unlock() + return nil + } + next := s.current + next.AutostartInitialized = done + if err := s.persistLocked(next); err != nil { + s.mu.Unlock() + return fmt.Errorf("persist preferences: %w", err) + } + s.current = next + s.mu.Unlock() + + s.broadcast(next) + return nil +} + // SetLanguage validates, persists, and broadcasts. No-op if unchanged. func (s *Store) SetLanguage(lang i18n.LanguageCode) error { if lang == "" { @@ -206,13 +232,29 @@ func (s *Store) Subscribe() (<-chan UIPreferences, func()) { return ch, unsubscribe } +// ExistedAtLoad reports whether the backing preferences file was present on +// disk when the store loaded. It distinguishes a user who ran a prior GUI +// version from a brand-new OS user with no preferences yet. +func (s *Store) ExistedAtLoad() bool { + s.mu.RLock() + defer s.mu.RUnlock() + return s.existedAtLoad +} + // load reads the file into current. A missing file is not an error (the // in-memory default stands); malformed contents return an error. func (s *Store) load() error { - if _, err := os.Stat(s.path); errors.Is(err, os.ErrNotExist) { - return nil + if _, err := os.Stat(s.path); err != nil { + if errors.Is(err, os.ErrNotExist) { + return nil + } + return fmt.Errorf("stat preferences: %w", err) } + s.mu.Lock() + s.existedAtLoad = true + s.mu.Unlock() + var loaded UIPreferences if _, err := util.ReadJson(s.path, &loaded); err != nil { return err diff --git a/client/ui/preferences/store_test.go b/client/ui/preferences/store_test.go index 0d1cc7b54..6384fddb8 100644 --- a/client/ui/preferences/store_test.go +++ b/client/ui/preferences/store_test.go @@ -215,6 +215,46 @@ func TestStore_FileShapeIsJSON(t *testing.T) { assert.Equal(t, i18n.LanguageCode("hu"), parsed.Language) } +func TestStore_SetAutostartInitializedPersistsAcrossReload(t *testing.T) { + withTempConfigDir(t) + emitter := &recordingEmitter{} + s, err := NewStore(nil, emitter) + require.NoError(t, err) + + assert.False(t, s.Get().AutostartInitialized, "marker must default to false when no file is on disk") + + require.NoError(t, s.SetAutostartInitialized(true)) + assert.True(t, s.Get().AutostartInitialized, "Get should reflect the persisted marker") + require.Len(t, emitter.calledWith(EventPreferencesChanged), 1, "first marker write should broadcast") + + // Re-setting the same value must be a no-op: no disk write, no broadcast. + require.NoError(t, s.SetAutostartInitialized(true)) + assert.Len(t, emitter.calledWith(EventPreferencesChanged), 1, "idempotent marker write should not broadcast again") + + // A fresh Store (new GUI launch) must see the marker so the autostart + // default decision never runs twice. + reloaded, err := NewStore(nil, nil) + require.NoError(t, err) + assert.True(t, reloaded.Get().AutostartInitialized, "marker must survive a reload from disk") +} + +func TestStore_ExistedAtLoad(t *testing.T) { + withTempConfigDir(t) + + // Brand-new OS user: no preferences file on disk yet. + fresh, err := NewStore(nil, nil) + require.NoError(t, err) + assert.False(t, fresh.ExistedAtLoad(), "ExistedAtLoad must be false when no file is on disk") + + // Persisting a value writes the file to disk. + require.NoError(t, fresh.SetLanguage("en")) + + // A subsequent GUI launch reopens the now-present file. + reopened, err := NewStore(nil, nil) + require.NoError(t, err) + assert.True(t, reopened.ExistedAtLoad(), "ExistedAtLoad must be true after the store has persisted and is reopened") +} + func TestStore_ErrUnsupportedSentinel(t *testing.T) { // Verifies callers can match on the sentinel error rather than parsing // strings — protects against accidental %v -> %w changes that would diff --git a/client/ui/services/autostart.go b/client/ui/services/autostart.go index f7e3aeea0..98e893f04 100644 --- a/client/ui/services/autostart.go +++ b/client/ui/services/autostart.go @@ -10,7 +10,7 @@ import ( "github.com/wailsapp/wails/v3/pkg/application" ) -// Autostart facade over Wails' AutostartManager. The OS login-item registration +// Autostart facade over Wails' AutostartManager. The OS autostart entry registration // is the single source of truth; nothing is mirrored to preferences. type Autostart struct { mgr *application.AutostartManager diff --git a/client/ui/services/connection.go b/client/ui/services/connection.go index a23a526e6..fae7ddd23 100644 --- a/client/ui/services/connection.go +++ b/client/ui/services/connection.go @@ -35,7 +35,7 @@ type LoginResult struct { VerificationURIComplete string `json:"verificationUriComplete"` } -// WaitSSOParams are the inputs to WaitSSOLogin. +// WaitSSOParams are the inputs to waitSSOLogin. type WaitSSOParams struct { UserCode string `json:"userCode"` Hostname string `json:"hostname"` @@ -116,6 +116,7 @@ func (s *Connection) Login(ctx context.Context, p LoginParams) (LoginResult, err if err != nil { return LoginResult{}, s.classifyDaemonError(err) } + log.Infof("daemon login response received, needs SSO login: %v", resp.GetNeedsSSOLogin()) return LoginResult{ NeedsSSOLogin: resp.GetNeedsSSOLogin(), UserCode: resp.GetUserCode(), @@ -124,26 +125,12 @@ func (s *Connection) Login(ctx context.Context, p LoginParams) (LoginResult, err }, nil } -func (s *Connection) WaitSSOLogin(ctx context.Context, p WaitSSOParams) (string, error) { - cli, err := s.conn.Client() - if err != nil { - return "", err - } - resp, err := cli.WaitSSOLogin(ctx, &proto.WaitSSOLoginRequest{ - UserCode: p.UserCode, - Hostname: p.Hostname, - }) - if err != nil { - return "", s.classifyDaemonError(err) - } - return resp.GetEmail(), nil -} - func (s *Connection) Up(ctx context.Context, p UpParams) error { cli, err := s.conn.Client() if err != nil { return err } + log.Infof("sending up request to daemon") // Always async: status updates flow via SubscribeStatus. req := &proto.UpRequest{Async: true} if p.ProfileName != "" { @@ -158,6 +145,27 @@ func (s *Connection) Up(ctx context.Context, p UpParams) error { return nil } +// WaitSSOLoginAndUp blocks until the SSO login completes and then brings the +// connection up, both from the Go side. Keeping the post-login Up here rather +// than as a frontend continuation is deliberate: during SSO the tray window is +// hidden and the webview is suspended (macOS App Nap / hidden-window timer +// throttling), so a frontend-driven Up would not run until the user woke the +// window (e.g. by hovering the tray icon). Doing it in Go connects the moment +// the daemon reports SSO success. Returns the authenticated user's email. +func (s *Connection) WaitSSOLoginAndUp(ctx context.Context, wait WaitSSOParams, up UpParams) (string, error) { + email, err := s.waitSSOLogin(ctx, wait) + if err != nil { + return "", err + } + if err := ctx.Err(); err != nil { + return "", err + } + if err := s.Up(ctx, up); err != nil { + return "", err + } + return email, nil +} + func (s *Connection) Down(ctx context.Context) error { cli, err := s.conn.Client() if err != nil { @@ -217,6 +225,26 @@ func (s *Connection) Logout(ctx context.Context, p LogoutParams) error { return nil } +// waitSSOLogin blocks until the daemon reports the SSO login result and returns +// the authenticated user's email. It is unexported because the frontend drives +// SSO through the exported WaitSSOLoginAndUp. +func (s *Connection) waitSSOLogin(ctx context.Context, p WaitSSOParams) (string, error) { + cli, err := s.conn.Client() + if err != nil { + return "", err + } + log.Infof("waiting for SSO login to complete") + resp, err := cli.WaitSSOLogin(ctx, &proto.WaitSSOLoginRequest{ + UserCode: p.UserCode, + Hostname: p.Hostname, + }) + if err != nil { + return "", s.classifyDaemonError(err) + } + log.Infof("SSO login completed, daemon reported success") + return resp.GetEmail(), nil +} + // classifyDaemonError maps a gRPC error to a localised ClientError. func (s *Connection) classifyDaemonError(err error) *ClientError { return s.classifier.classify(err) diff --git a/client/ui/services/errors.go b/client/ui/services/errors.go index f1679e764..0c6f2f20f 100644 --- a/client/ui/services/errors.go +++ b/client/ui/services/errors.go @@ -6,13 +6,30 @@ import ( "encoding/json" "strings" + "google.golang.org/genproto/googleapis/rpc/errdetails" gcodes "google.golang.org/grpc/codes" gstatus "google.golang.org/grpc/status" + "github.com/netbirdio/netbird/client/internal/ipcauth" "github.com/netbirdio/netbird/client/ui/i18n" "github.com/netbirdio/netbird/client/ui/preferences" ) +// privilegeErrorInfo returns the daemon's privilege-refusal detail, if the error +// carries one. +func privilegeErrorInfo(err error) (*errdetails.ErrorInfo, bool) { + 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 +} + // ErrorTranslator localises daemon errors; runtime impl is *i18n.Bundle. type ErrorTranslator interface { Translate(lang i18n.LanguageCode, key string, args ...string) string @@ -30,6 +47,10 @@ type ClientError struct { Code string `json:"code"` Short string `json:"short"` Long string `json:"long"` + // Command is a command the user can run to complete the operation + // themselves, set when the daemon refused it for want of privileges. The + // frontend offers it for copying. + Command string `json:"command,omitempty"` } // Error returns the short message for plain Go callers. @@ -72,6 +93,24 @@ func (c errorClassifier) classify(err error) *ClientError { msg = st.Message() grpcCode = st.Code() } + + // A refusal for want of privileges carries its own summary and the command + // that performs the operation, both written for the user. Surface them + // verbatim: no substring guessing, and no localisation of a message the + // daemon composed. + if info, ok := privilegeErrorInfo(err); ok { + summary := info.GetMetadata()[ipcauth.ErrorMetaSummary] + if summary == "" { + summary = msg + } + return &ClientError{ + Code: "privilege_required", + Short: summary, + Long: summary, + Command: info.GetMetadata()[ipcauth.ErrorMetaCommand], + } + } + lower := strings.ToLower(msg) code := "unknown" diff --git a/client/ui/services/profileswitcher.go b/client/ui/services/profileswitcher.go index c27b62d92..727b2473f 100644 --- a/client/ui/services/profileswitcher.go +++ b/client/ui/services/profileswitcher.go @@ -12,13 +12,15 @@ import ( "github.com/netbirdio/netbird/client/internal/profilemanager" ) -// ProfileSwitcher holds the reconnect policy shared by the tray and React -// frontend so both flip profiles identically. The policy keys off prevStatus -// from DaemonFeed.Get at SwitchActive entry: +// ProfileSwitcher holds the switch policy shared by the tray and React +// frontend so both flip profiles identically. SwitchActive (plain selection: +// header dropdown, tray submenu) always connects after the switch; +// SwitchActiveNoConnect (manage-profiles screen) never does, so the user can +// still adjust the management URL before connecting. prevStatus from +// DaemonFeed.Get at entry only decides the teardown: // -// Connected/Connecting → Switch + Down + Up; optimistic Connecting paint. -// NeedsLogin/LoginFailed/SessionExpired → Switch + Down; clear stale error for re-login. -// Idle → Switch only. +// Connected/Connecting/NeedsLogin/LoginFailed/SessionExpired → Down first. +// Idle → no Down. type ProfileSwitcher struct { profiles *Profiles connection *Connection @@ -29,29 +31,40 @@ func NewProfileSwitcher(profiles *Profiles, connection *Connection, feed *Daemon return &ProfileSwitcher{profiles: profiles, connection: connection, feed: feed} } -// SwitchActive switches to the named profile applying the reconnect policy. +// SwitchActive switches to the named profile and always connects afterwards. func (s *ProfileSwitcher) SwitchActive(ctx context.Context, p ProfileRef) error { + return s.switchActive(ctx, p, true) +} + +// SwitchActiveNoConnect switches to the named profile without connecting, +// tearing down any existing connection first. +func (s *ProfileSwitcher) SwitchActiveNoConnect(ctx context.Context, p ProfileRef) error { + return s.switchActive(ctx, p, false) +} + +func (s *ProfileSwitcher) switchActive(ctx context.Context, p ProfileRef, connect bool) error { prevStatus := "" - if st, err := s.feed.Get(ctx); err == nil { - prevStatus = st.Status - } else { - log.Warnf("profileswitcher: get status: %v", err) + if s.feed != nil { + if st, err := s.feed.Get(ctx); err == nil { + prevStatus = st.Status + } else { + log.Warnf("profileswitcher: get status: %v", err) + } } - wasActive := strings.EqualFold(prevStatus, StatusConnected) || - strings.EqualFold(prevStatus, StatusConnecting) - needsDown := wasActive || + needsDown := strings.EqualFold(prevStatus, StatusConnected) || + strings.EqualFold(prevStatus, StatusConnecting) || strings.EqualFold(prevStatus, StatusNeedsLogin) || strings.EqualFold(prevStatus, StatusLoginFailed) || strings.EqualFold(prevStatus, StatusSessionExpired) - log.Infof("profileswitcher: switch profile=%q prevStatus=%q wasActive=%v needsDown=%v", - p.ProfileName, prevStatus, wasActive, needsDown) + log.Infof("profileswitcher: switch profile=%q prevStatus=%q connect=%v needsDown=%v", + p.ProfileName, prevStatus, connect, needsDown) - // Optimistic Connecting paint only when wasActive: those prevStatuses emit - // stale Connected + transient Idle pushes during Down that must be - // suppressed until Up resumes the stream (see DaemonFeed suppression table). - if wasActive { + // Optimistic Connecting paint plus stale-push suppression during Down (see + // DaemonFeed suppression table); also arms the login-watch that pops + // browser-login when the new profile turns out to need SSO. + if connect && s.feed != nil { s.feed.BeginProfileSwitch() } @@ -76,9 +89,9 @@ func (s *ProfileSwitcher) SwitchActive(ctx context.Context, p ProfileRef) error } } - if wasActive { + if connect { if err := s.connection.Up(ctx, UpParams(p)); err != nil { - return fmt.Errorf("reconnect %q: %w", p.ProfileName, err) + return fmt.Errorf("connect %q: %w", p.ProfileName, err) } } diff --git a/client/ui/services/settings.go b/client/ui/services/settings.go index 1c16795ae..74e6f913c 100644 --- a/client/ui/services/settings.go +++ b/client/ui/services/settings.go @@ -7,6 +7,10 @@ import ( "fmt" "reflect" + log "github.com/sirupsen/logrus" + + "github.com/netbirdio/netbird/client/internal/daemonaddr" + "github.com/netbirdio/netbird/client/internal/ipcauth" "github.com/netbirdio/netbird/client/proto" ) @@ -20,11 +24,12 @@ type MDMFields struct { DisableServerRoutes bool `json:"disableServerRoutes"` AllowServerSSH *bool `json:"allowServerSSH"` DisableAutoConnect bool `json:"disableAutoConnect"` + DisableAutostart bool `json:"disableAutostart"` BlockInbound bool `json:"blockInbound"` DisableMetricsCollection bool `json:"disableMetricsCollection"` SplitTunnelMode bool `json:"splitTunnelMode"` SplitTunnelApps bool `json:"splitTunnelApps"` - DisableAdvancedView bool `json:"disableAdvancedView"` + DisableAdvancedView bool `json:"disableAdvancedView"` } type Features struct { @@ -38,6 +43,19 @@ type Restrictions struct { Features Features `json:"features"` } +// Privilege tells the frontend whether this process may perform the changes the +// daemon restricts to root/administrator, and carries the command for each so a +// disabled control can show the way to do it. +type Privilege struct { + Privileged bool `json:"privileged"` + // Actor names what the operation requires ("root", "administrator privileges"). + Actor string `json:"actor"` + // Commands equivalent to the settings the daemon guards, ready to copy. + AllowSSHServer string `json:"allowSshServer"` + EnableSSHRoot string `json:"enableSshRoot"` + DisableSSHAuth string `json:"disableSshAuth"` +} + type ConfigParams struct { ProfileName string `json:"profileName"` Username string `json:"username"` @@ -105,11 +123,19 @@ type SetConfigParams struct { } type Settings struct { - conn DaemonConn + conn DaemonConn + classifier errorClassifier + // daemonAddr is where the daemon listens, used to tell whether it runs as + // this user and would therefore authorize us: see Privilege. + daemonAddr string } -func NewSettings(conn DaemonConn) *Settings { - return &Settings{conn: conn} +func NewSettings(conn DaemonConn, translator ErrorTranslator, prefs LanguagePreference, daemonAddr string) *Settings { + return &Settings{ + conn: conn, + classifier: errorClassifier{translator: translator, prefs: prefs}, + daemonAddr: daemonAddr, + } } func (s *Settings) GetConfig(ctx context.Context, p ConfigParams) (Config, error) { @@ -188,8 +214,47 @@ func (s *Settings) SetConfig(ctx context.Context, p SetConfigParams) error { DisableSSHAuth: p.DisableSSHAuth, SshJWTCacheTTL: p.SSHJWTCacheTTL, } - _, err = cli.SetConfig(ctx, req) - return err + if _, err := cli.SetConfig(ctx, req); err != nil { + // Classified so the frontend gets the daemon's guidance instead of the + // gRPC envelope, which is what a refused privileged change looks like. + return s.classifier.classify(err) + } + return nil +} + +// Privilege reports whether this UI process could carry out the changes the +// daemon restricts to root/administrator, and the command that performs the one +// users hit in the SSH settings. It applies the daemon's own rule to what it can +// see locally, so the frontend can present those controls as unavailable up front +// instead of letting a save fail. No daemon round-trip, so it also works while the +// daemon is down. +// +// Being root or an elevated administrator is one way. The other is running as the +// daemon's own user while the daemon is unprivileged, which the daemon accepts +// because such a caller can already rewrite the config it reads; that is the +// rootless-container and Windows netstack-mode case, and it is read from the +// ownership of the socket or pipe the daemon created. +func (s *Settings) Privilege() Privilege { + id, err := ipcauth.CurrentProcessIdentity() + if err != nil { + // Fail closed: report unprivileged, which only ever disables controls. + log.Warnf("cannot read this process's identity, treating it as unprivileged: %v", err) + return newPrivilege(false) + } + if id.IsPrivileged() { + return newPrivilege(true) + } + return newPrivilege(daemonaddr.DaemonRunsAsSelf(s.daemonAddr)) +} + +func newPrivilege(privileged bool) Privilege { + return Privilege{ + Privileged: privileged, + Actor: ipcauth.PrivilegedActor(), + AllowSSHServer: ipcauth.UpCommand("--allow-server-ssh"), + EnableSSHRoot: ipcauth.UpCommand("--enable-ssh-root"), + DisableSSHAuth: ipcauth.UpCommand("--disable-ssh-auth"), + } } func (s *Settings) GetRestrictions(ctx context.Context) (Restrictions, error) { diff --git a/client/ui/services/shutdown.go b/client/ui/services/shutdown.go new file mode 100644 index 000000000..0da51940c --- /dev/null +++ b/client/ui/services/shutdown.go @@ -0,0 +1,24 @@ +package services + +import "sync/atomic" + +var ( + sessionEnding atomic.Bool + quitting atomic.Bool +) + +func BeginSessionEnd() { + sessionEnding.Store(true) +} + +func AbortSessionEnd() { + sessionEnding.Store(false) +} + +func BeginShutdown() { + quitting.Store(true) +} + +func ShuttingDown() bool { + return sessionEnding.Load() || quitting.Load() +} diff --git a/client/ui/services/update.go b/client/ui/services/update.go index 753177d45..b743b9858 100644 --- a/client/ui/services/update.go +++ b/client/ui/services/update.go @@ -10,6 +10,7 @@ import ( "github.com/netbirdio/netbird/client/proto" "github.com/netbirdio/netbird/client/ui/updater" + "github.com/netbirdio/netbird/version" ) // UpdateResult mirrors TriggerUpdateResponse. @@ -33,6 +34,12 @@ func (s *Update) GetState() updater.State { return s.holder.Get() } +// DownloadURL returns the platform-appropriate installer download link for +// manual (non-enforced) updates. +func (s *Update) DownloadURL() string { + return version.DownloadUrl() +} + // Quit exits the app. Scheduled off the calling goroutine so the JS caller's // response returns before the runtime tears down. func (s *Update) Quit() { diff --git a/client/ui/services/windowmanager.go b/client/ui/services/windowmanager.go index 3316dadaa..5f7aaa7bd 100644 --- a/client/ui/services/windowmanager.go +++ b/client/ui/services/windowmanager.go @@ -154,6 +154,9 @@ func NewWindowManager(app *application.App, mainWindow *application.WebviewWindo }) // Hide (not destroy) on close to keep React state; reset to General for a flash-free reopen. s.settings.RegisterHook(events.Common.WindowClosing, func(e *application.WindowEvent) { + if ShuttingDown() { + return + } e.Cancel() s.app.Event.Emit(EventSettingsOpen, "general") s.settings.Hide() @@ -185,37 +188,38 @@ func (s *WindowManager) OpenBrowserLogin(uri string) { startURL = "/#/dialog/browser-login?uri=" + url.QueryEscape(uri) } s.hideOtherWindowsLocked("browser-login") - // Prefer the main window's screen (multi-monitor); falls back to OS-default centering. - var screen *application.Screen - if s.mainWindow != nil { - if sc, err := s.mainWindow.GetScreen(); err == nil { - screen = sc - } - } opts := DialogWindowOptions("browser-login", s.title("window.title.signIn"), startURL, s.linuxIcon) // Not always-on-top: it would obscure the browser tab the user logs in through. opts.AlwaysOnTop = false opts.InitialPosition = application.WindowCentered - opts.Screen = screen + // Open on the active (where users cursor is) display, like the session-expiration dialog. + opts.Screen = s.getScreenBasedOnCursorPosition() s.browserLogin = s.app.Window.NewWithOptions(opts) bl := s.browserLogin - // Red-X close means cancel: emit the event so startLogin() tears down the SSO wait. bl.OnWindowEvent(events.Common.WindowClosing, func(_ *application.WindowEvent) { - s.app.Event.Emit(EventBrowserLoginCancel) s.mu.Lock() - s.browserLogin = nil - s.restoreHiddenWindowsLocked() + // Only a live user red-X still has this registered; programmatic closers + // nil s.browserLogin first and clean up themselves. Guarding here stops a + // stale close event from wiping a replacement popup's state. + userClosed := s.browserLogin == bl + if userClosed { + s.browserLogin = nil + s.restoreHiddenWindowsLocked() + } s.mu.Unlock() + if userClosed { + s.app.Event.Emit(EventBrowserLoginCancel) + } }) - s.centerWhenReady(s.browserLogin) + s.centerOnCursorScreen(s.browserLogin) return } if uri != "" { s.browserLogin.SetURL("/#/dialog/browser-login?uri=" + url.QueryEscape(uri)) } + s.centerOnCursorScreen(s.browserLogin) s.browserLogin.Show() s.browserLogin.Focus() - s.centerWhenReady(s.browserLogin) } // BrowserLoginWindow returns the live SSO popup, or nil. While non-nil it is the @@ -238,6 +242,15 @@ func (s *WindowManager) CloseBrowserLogin() { s.mu.Lock() w := s.browserLogin s.browserLogin = nil + // The WindowClosing hook no-ops on a programmatic close, so restore here — + // but only if a popup was actually open. The frontend calls this even when no + // popup was ever shown (e.g. resetDialog() after an early RequestExtend failure, + // or connection.ts's catch path), and hiddenForLogin is shared with + // OpenInstallProgress, so an unconditional restore could re-show windows a + // still-running install-progress is hiding. + if w != nil { + s.restoreHiddenWindowsLocked() + } s.mu.Unlock() if w != nil { w.Close() @@ -279,6 +292,35 @@ func (s *WindowManager) CloseSessionExpiration() { } } +// CloseRenewFlow tears down the SSO session-renewal UI in a single call: it +// closes the browser-login popup and the session-expiration window together. +func (s *WindowManager) CloseRenewFlow() { + s.mu.Lock() + bl := s.browserLogin + se := s.sessionExpiration + s.browserLogin = nil + s.sessionExpiration = nil + if se != nil { + kept := s.hiddenForLogin[:0] + for _, w := range s.hiddenForLogin { + if w != se { + kept = append(kept, w) + } + } + s.hiddenForLogin = kept + } + s.restoreHiddenWindowsLocked() + s.mu.Unlock() + + // Close after unlock so the re-entrant handlers can take s.mu. + if bl != nil { + bl.Close() + } + if se != nil { + se.Close() + } +} + // OpenInstallProgress shows the install-progress window and hides the rest for the duration // (restored on close). It owns its own result polling since the daemon restarts mid-install. func (s *WindowManager) OpenInstallProgress(version string) { @@ -351,12 +393,17 @@ func (s *WindowManager) CloseWelcome() { } } -// OpenError shows the custom error dialog; title/message are pre-localised and ride in the -// start URL. A second error replaces the open one via SetURL. Singleton, destroyed on close. -func (s *WindowManager) OpenError(title, message string) { +// OpenError shows the custom error dialog; title/message/command are pre-localised +// and ride in the start URL. command is optional and, when set, is offered for +// copying so the user can run the operation the daemon refused. A second error +// replaces the open one via SetURL. Singleton, destroyed on close. +func (s *WindowManager) OpenError(title, message, command string) { + if ShuttingDown() { + return + } s.mu.Lock() defer s.mu.Unlock() - startURL := errorDialogURL(title, message) + startURL := errorDialogURL(title, message, command) if s.errorDialog == nil { s.errorDialog = s.app.Window.NewWithOptions( DialogWindowOptions("error", s.title("window.title.error"), startURL, s.linuxIcon), @@ -556,8 +603,8 @@ func (s *WindowManager) getScreenBasedOnCursorPosition() *application.Screen { return nil } -// errorDialogURL builds the error window's start URL with title/message as escaped query params. -func errorDialogURL(title, message string) string { +// errorDialogURL builds the error window's start URL with title/message/command as escaped query params. +func errorDialogURL(title, message, command string) string { q := url.Values{} if title != "" { q.Set("title", title) @@ -565,6 +612,9 @@ func errorDialogURL(title, message string) string { if message != "" { q.Set("message", message) } + if command != "" { + q.Set("command", command) + } startURL := "/#/dialog/error" if enc := q.Encode(); enc != "" { startURL += "?" + enc diff --git a/client/ui/services/windowtheme_windows.go b/client/ui/services/windowtheme_windows.go new file mode 100644 index 000000000..7dbc1164b --- /dev/null +++ b/client/ui/services/windowtheme_windows.go @@ -0,0 +1,14 @@ +package services + +import "github.com/wailsapp/wails/v3/pkg/w32" + +// Wails assigns w32.AllowDarkModeForWindow only on builds >= 18334 but calls it +// without a nil check when a window requests the Dark theme, crashing older +// builds such as Windows Server 2019 (17763). Those builds still get a dark +// title bar via the pre-20H1 DWM attribute that w32.SetTheme applies, so a +// no-op stub keeps the Dark theme fully working there. +func init() { + if w32.AllowDarkModeForWindow == nil { + w32.AllowDarkModeForWindow = func(w32.HWND, bool) uintptr { return 0 } + } +} diff --git a/client/ui/shutdown_other.go b/client/ui/shutdown_other.go new file mode 100644 index 000000000..6e617233f --- /dev/null +++ b/client/ui/shutdown_other.go @@ -0,0 +1,7 @@ +//go:build !windows && !android && !ios && !freebsd && !js + +package main + +func endSessionInterceptor() func(hwnd uintptr, msg uint32, wParam, lParam uintptr) (uintptr, bool) { + return nil +} diff --git a/client/ui/shutdown_windows.go b/client/ui/shutdown_windows.go new file mode 100644 index 000000000..fbb92a518 --- /dev/null +++ b/client/ui/shutdown_windows.go @@ -0,0 +1,36 @@ +//go:build windows + +package main + +import ( + "os" + + log "github.com/sirupsen/logrus" + + "github.com/netbirdio/netbird/client/ui/services" +) + +const ( + wmQueryEndSession = 0x0011 + wmEndSession = 0x0016 +) + +func endSessionInterceptor() func(hwnd uintptr, msg uint32, wParam, lParam uintptr) (uintptr, bool) { + return func(_ uintptr, msg uint32, wParam, _ uintptr) (uintptr, bool) { + switch msg { + case wmQueryEndSession: + services.BeginSessionEnd() + return 1, true + case wmEndSession: + if wParam == 0 { + services.AbortSessionEnd() + return 0, true + } + log.Info("windows session is ending; exiting immediately") + os.Exit(0) + return 0, true + default: + return 0, false + } + } +} diff --git a/client/ui/tray.go b/client/ui/tray.go index 700d94098..3050d159a 100644 --- a/client/ui/tray.go +++ b/client/ui/tray.go @@ -30,9 +30,10 @@ const ( statusError = "Error" - urlGitHubRepo = "https://github.com/netbirdio/netbird" - urlGitHubReleases = "https://github.com/netbirdio/netbird/releases/latest" - urlDocs = "https://docs.netbird.io" + quitDownTimeout = 5 * time.Second + + urlGitHubRepo = "https://github.com/netbirdio/netbird" + urlDocs = "https://docs.netbird.io" ) // TrayServices bundles the services the tray menu needs, grouped so NewTray @@ -315,8 +316,7 @@ func (t *Tray) relayoutMenu() { if sessionDeadline.IsZero() { t.sessionExpiresItem.SetHidden(true) } else { - remaining := t.formatSessionRemaining(time.Until(sessionDeadline)) - t.sessionExpiresItem.SetLabel(t.loc.T("tray.session.expiresIn", "remaining", remaining)) + t.sessionExpiresItem.SetLabel(t.sessionRowLabel(sessionDeadline)) t.sessionExpiresItem.SetHidden(false) } } @@ -446,11 +446,29 @@ func (t *Tray) buildMenu() *application.Menu { menu.AddSeparator() menu.Add(t.loc.T("tray.menu.quit")). SetAccelerator("CmdOrCtrl+Q"). - OnClick(func(*application.Context) { t.app.Quit() }) + OnClick(func(*application.Context) { t.handleQuit() }) return menu } +func (t *Tray) handleQuit() { + services.BeginShutdown() + t.profileMu.Lock() + if t.switchCancel != nil { + t.switchCancel() + t.switchCancel = nil + } + t.profileMu.Unlock() + t.svc.DaemonFeed.CancelProfileSwitch() + + ctx, cancel := context.WithTimeout(context.Background(), quitDownTimeout) + defer cancel() + if err := t.svc.Connection.Down(ctx); err != nil { + log.Errorf("disconnect on quit: %v", err) + } + t.app.Quit() +} + // handleConnect receives the clicked item from the buildMenu closure — // t.upItem is menuMu-guarded and must not be read here. func (t *Tray) handleConnect(upItem *application.MenuItem) { diff --git a/client/ui/tray_notify.go b/client/ui/tray_notify.go index 6c60e3d4b..d1117b57b 100644 --- a/client/ui/tray_notify.go +++ b/client/ui/tray_notify.go @@ -25,6 +25,9 @@ type sendFn func(notifications.NotificationOptions) error // event-dispatch goroutine that panic is fatal process-wide; recover() turns // it into a logged no-op. func safeSendNotification(send sendFn, what string, opts notifications.NotificationOptions) (err error) { + if services.ShuttingDown() { + return nil + } defer func() { if r := recover(); r != nil { log.Errorf("notify %s: recovered from panic (notification bus unavailable): %v", what, r) diff --git a/client/ui/tray_session.go b/client/ui/tray_session.go index 6b73ddb49..885fdb348 100644 --- a/client/ui/tray_session.go +++ b/client/ui/tray_session.go @@ -64,11 +64,42 @@ func (t *Tray) applySessionExpiry(deadline *time.Time, connected bool) bool { return changed } -// runSessionExpiryTicker recomputes the "Expires in …" row label every 30s. Runs until process exit. +// runSessionExpiryTicker recomputes the "Expires in …" row label until process exit. +// The interval scales with the remaining time: coarse when the deadline is far off, +// down to 10s in the final two minutes so the label doesn't lag the ceiling-rounded +// countdown near expiry. The cached deadline is re-read every iteration, so an extend +// or reconnect that moves it is picked up on the next tick. func (t *Tray) runSessionExpiryTicker() { - tk := time.NewTicker(30 * time.Second) - for range tk.C { + tm := time.NewTimer(sessionRefreshInterval(t.sessionRemaining())) + defer tm.Stop() + for range tm.C { t.refreshSessionExpiresLabel() + tm.Reset(sessionRefreshInterval(t.sessionRemaining())) + } +} + +// sessionRemaining returns the time left on the cached SSO deadline, or 0 when unknown. +func (t *Tray) sessionRemaining() time.Duration { + t.sessionMu.Lock() + deadline := t.sessionExpiresAt + t.sessionMu.Unlock() + if deadline.IsZero() { + return 0 + } + return time.Until(deadline) +} + +// sessionRefreshInterval picks how long to wait before the next label recompute. +func sessionRefreshInterval(remaining time.Duration) time.Duration { + switch { + case remaining <= 0: + return 30 * time.Second + case remaining <= 2*time.Minute: + return 10 * time.Second + case remaining <= time.Hour: + return 30 * time.Second + default: + return time.Minute } } @@ -87,30 +118,39 @@ func (t *Tray) refreshSessionExpiresLabel() { if deadline.IsZero() { return } - remaining := t.formatSessionRemaining(time.Until(deadline)) - item.SetLabel(t.loc.T("tray.session.expiresIn", "remaining", remaining)) + item.SetLabel(t.sessionRowLabel(deadline)) +} + +func (t *Tray) sessionRowLabel(deadline time.Time) string { + remaining := time.Until(deadline) + if remaining <= 0 { + return t.loc.T("tray.status.sessionExpired") + } + return t.loc.T("tray.session.expiresIn", "remaining", t.formatSessionRemaining(remaining)) } // formatSessionRemaining renders d as a localised long-form string picking the largest non-zero unit. +// Each unit is rounded up so the label never claims less time than actually remains, matching the +// upper-bound sense of the sub-minute "less than a minute" fragment. // Singular/plural keys are split per language for proper translation. func (t *Tray) formatSessionRemaining(d time.Duration) string { switch { case d < time.Minute: return t.loc.T("tray.session.unit.lessThanMinute") - case d < time.Hour: - m := int(d / time.Minute) + case d <= 59*time.Minute: + m := ceilDiv(d, time.Minute) if m == 1 { return t.loc.T("tray.session.unit.minute") } return t.loc.T("tray.session.unit.minutes", "count", strconv.Itoa(m)) - case d < 24*time.Hour: - h := int((d + 30*time.Minute) / time.Hour) + case d <= 23*time.Hour: + h := ceilDiv(d, time.Hour) if h == 1 { return t.loc.T("tray.session.unit.hour") } return t.loc.T("tray.session.unit.hours", "count", strconv.Itoa(h)) default: - days := int((d + 12*time.Hour) / (24 * time.Hour)) + days := ceilDiv(d, 24*time.Hour) if days == 1 { return t.loc.T("tray.session.unit.day") } @@ -118,6 +158,11 @@ func (t *Tray) formatSessionRemaining(d time.Duration) string { } } +// ceilDiv divides d by unit rounding up, assuming d > 0. +func ceilDiv(d, unit time.Duration) int { + return int((d + unit - time.Nanosecond) / unit) +} + // registerSessionWarningCategory wires the OS notification category and response handler for the expiry warning. // Errors are swallowed since the worst case is a plain notification without buttons. func (t *Tray) registerSessionWarningCategory() { @@ -252,11 +297,9 @@ func (t *Tray) openSessionExpiration() { } // openSessionExtendFlow opens the SessionExpiration window seeded with the cached deadline's remaining time, -// for the "Expires in …" tray row. No-ops when the deadline is unknown or elapsed. +// for the "Expires in …" tray row. Once the deadline has elapsed the row reads "Session expired" and the +// click routes to the login flow instead. No-op when the deadline is unknown. func (t *Tray) openSessionExtendFlow() { - if t.svc.WindowManager == nil { - return - } t.sessionMu.Lock() deadline := t.sessionExpiresAt t.sessionMu.Unlock() @@ -265,6 +308,14 @@ func (t *Tray) openSessionExtendFlow() { } seconds := int(time.Until(deadline).Seconds()) if seconds <= 0 { + if t.window != nil { + t.window.SetURL("/#/login") + t.window.Show() + t.window.Focus() + } + return + } + if t.svc.WindowManager == nil { return } t.svc.WindowManager.OpenSessionExpiration(seconds) diff --git a/client/ui/tray_update.go b/client/ui/tray_update.go index 2d79cff05..1a377dfa3 100644 --- a/client/ui/tray_update.go +++ b/client/ui/tray_update.go @@ -13,6 +13,7 @@ import ( "github.com/netbirdio/netbird/client/ui/services" "github.com/netbirdio/netbird/client/ui/updater" + "github.com/netbirdio/netbird/version" ) // trayUpdater owns the tray UI that reacts to auto-update. Composed inside Tray. @@ -76,15 +77,15 @@ func (u *trayUpdater) applyLanguage() { u.refreshMenuItem(state) } -// handleClick opens the GitHub releases page when not Enforced, otherwise shows -// the progress page and asks the daemon to start the installer. +// handleClick opens the installer download link when not Enforced, otherwise +// shows the progress page and asks the daemon to start the installer. func (u *trayUpdater) handleClick() { u.mu.Lock() state := u.state u.mu.Unlock() if !state.Enforced { - _ = u.app.Browser.OpenURL(urlGitHubReleases) + _ = u.app.Browser.OpenURL(version.DownloadUrl()) return } diff --git a/client/ui/uilogpath.go b/client/ui/uilogpath.go index 96fbb9637..6fa400e01 100644 --- a/client/ui/uilogpath.go +++ b/client/ui/uilogpath.go @@ -8,21 +8,19 @@ import ( log "github.com/sirupsen/logrus" + "github.com/netbirdio/netbird/client/configs" "github.com/netbirdio/netbird/client/ui/guilog" ) -// uiLogFileName must stay in sync with the daemon's "gui-client*.log.*" glob -// for rotated siblings (addUILog in client/internal/debug). -const uiLogFileName = "gui-client.log" - // uiLogPath returns the GUI log path with native separators, since the daemon -// opens it directly for debug-bundle collection. +// opens it directly for debug-bundle collection. The file name comes from +// configs.UILogFile so the daemon validates and collects the same name. func uiLogPath() (string, error) { dir, err := os.UserConfigDir() if err != nil { return "", err } - return filepath.Join(dir, "netbird", uiLogFileName), nil + return filepath.Join(dir, "netbird", configs.UILogFile), nil } // newDebugLog builds the GUI debug log, disabled when userSetLogFile is set diff --git a/client/wasm/internal/rdp/rdcleanpath.go b/client/wasm/internal/rdp/rdcleanpath.go index ee420dca4..3d8be8950 100644 --- a/client/wasm/internal/rdp/rdcleanpath.go +++ b/client/wasm/internal/rdp/rdcleanpath.go @@ -23,7 +23,7 @@ const ( RDCleanPathProxyHost = "rdcleanpath.proxy.local" RDCleanPathProxyScheme = "ws" - rdpDialTimeout = 15 * time.Second + rdpDialTimeout = 30 * time.Second GeneralErrorCode = 1 WSAETimedOut = 10060 diff --git a/combined/cmd/admin.go b/combined/cmd/admin.go new file mode 100644 index 000000000..66fac4ac9 --- /dev/null +++ b/combined/cmd/admin.go @@ -0,0 +1,151 @@ +package cmd + +import ( + "context" + "fmt" + + "github.com/dexidp/dex/storage" + log "github.com/sirupsen/logrus" + "github.com/spf13/cobra" + + "github.com/netbirdio/netbird/formatter/hook" + admincmd "github.com/netbirdio/netbird/management/cmd/admin" + tokencmd "github.com/netbirdio/netbird/management/cmd/token" + nbconfig "github.com/netbirdio/netbird/management/internals/server/config" + "github.com/netbirdio/netbird/management/server/activity" + activitystore "github.com/netbirdio/netbird/management/server/activity/store" + "github.com/netbirdio/netbird/management/server/store" + "github.com/netbirdio/netbird/management/server/types" + "github.com/netbirdio/netbird/util" +) + +// newAdminCommands creates the admin command tree with combined-specific resource openers. +func newAdminCommands() *cobra.Command { + return admincmd.NewCommands(admincmd.Openers{ + Resources: withAdminResources, + Store: withAdminStoreOnly, + IDP: withAdminIDPOnly, + }) +} + +func newLegacyTokenCommand() *cobra.Command { + cmd := tokencmd.NewCommands(tokencmd.StoreOpener(withAdminStoreOnly)) + cmd.Deprecated = "use 'admin token' instead" + return cmd +} + +// withAdminResources loads the combined YAML config, initializes stores, and calls fn. +func withAdminResources(cmd *cobra.Command, fn func(ctx context.Context, resources admincmd.Resources) error) error { + return withAdminConfig(cmd, func(ctx context.Context, cfg *CombinedConfig) error { + mgmtConfig, err := adminManagementConfig(cfg) + if err != nil { + return err + } + + managementStore, err := openAdminStore(ctx, cfg) + if err != nil { + return err + } + defer admincmd.CloseStore(ctx, managementStore) + + idpStorage, idpStorageFile, err := admincmd.OpenIDPStorage(mgmtConfig) + if err != nil { + return err + } + defer admincmd.CloseIDPStorage(idpStorage) + + eventStore, esErr := openAdminEventStore(ctx, cfg, mgmtConfig) + if esErr != nil { + _, _ = fmt.Fprintf(cmd.ErrOrStderr(), "Warning: audit events will not be recorded: %v\n", esErr) + } + if eventStore != nil { + defer func() { + if err := eventStore.Close(ctx); err != nil { + log.Debugf("close activity event store: %v", err) + } + }() + } + + return fn(ctx, admincmd.Resources{Store: managementStore, IDPStorage: idpStorage, IDPStorageFile: idpStorageFile, EventStore: eventStore}) + }) +} + +// withAdminStoreOnly opens only the management store for admin subcommands that do not +// need embedded IdP storage. +func withAdminStoreOnly(cmd *cobra.Command, fn func(ctx context.Context, s store.Store) error) error { + return withAdminConfig(cmd, func(ctx context.Context, cfg *CombinedConfig) error { + managementStore, err := openAdminStore(ctx, cfg) + if err != nil { + return err + } + defer admincmd.CloseStore(ctx, managementStore) + + return fn(ctx, managementStore) + }) +} + +func withAdminIDPOnly(cmd *cobra.Command, fn func(ctx context.Context, idpStorage storage.Storage, storageFile string) error) error { + return withAdminConfig(cmd, func(ctx context.Context, cfg *CombinedConfig) error { + mgmtConfig, err := adminManagementConfig(cfg) + if err != nil { + return err + } + idpStorage, idpStorageFile, err := admincmd.OpenIDPStorage(mgmtConfig) + if err != nil { + return err + } + defer admincmd.CloseIDPStorage(idpStorage) + + return fn(ctx, idpStorage, idpStorageFile) + }) +} + +func withAdminConfig(cmd *cobra.Command, fn func(ctx context.Context, cfg *CombinedConfig) error) error { + if err := util.InitLog("error", "console"); err != nil { + return fmt.Errorf("init log: %w", err) + } + + ctx := context.WithValue(cmd.Context(), hook.ExecutionContextKey, hook.SystemSource) //nolint:staticcheck + + cfg, err := LoadConfig(configPath) + if err != nil { + return fmt.Errorf("load config: %w", err) + } + cfg.ApplyAdminDefaults() + applyServerStoreEnv(cfg.Server.Store) + + return fn(ctx, cfg) +} + +func adminManagementConfig(cfg *CombinedConfig) (*nbconfig.Config, error) { + mgmtConfig, err := cfg.ToManagementConfig() + if err != nil { + return nil, fmt.Errorf("create management config: %w", err) + } + return mgmtConfig, nil +} + +func openAdminStore(ctx context.Context, cfg *CombinedConfig) (store.Store, error) { + managementStore, err := store.NewStore(ctx, types.Engine(cfg.Management.Store.Engine), cfg.Management.DataDir, nil, true) + if err != nil { + return nil, fmt.Errorf("create store: %w", err) + } + return managementStore, nil +} + +func openAdminEventStore(ctx context.Context, cfg *CombinedConfig, config *nbconfig.Config) (activity.Store, error) { + if config.DataStoreEncryptionKey == "" { + return nil, fmt.Errorf("data store encryption key is not configured") + } + if err := applyActivityStoreEnv(cfg.Server.ActivityStore); err != nil { + return nil, fmt.Errorf("configure activity event store: %w", err) + } + eventStore, err := activitystore.NewSqlStore(ctx, config.Datadir, config.DataStoreEncryptionKey) + if err != nil { + return nil, fmt.Errorf("open activity event store: %w", err) + } + if eventStore == nil { + return nil, fmt.Errorf("open activity event store: returned nil store") + } + return eventStore, nil +} diff --git a/combined/cmd/admin_config_test.go b/combined/cmd/admin_config_test.go new file mode 100644 index 000000000..ff7045d38 --- /dev/null +++ b/combined/cmd/admin_config_test.go @@ -0,0 +1,47 @@ +package cmd + +import ( + "context" + "os" + "testing" + + "github.com/stretchr/testify/require" + + nbconfig "github.com/netbirdio/netbird/management/internals/server/config" +) + +func TestApplyAdminDefaultsCopiesServerStoreWithoutExposedAddress(t *testing.T) { + cfg := DefaultConfig() + cfg.Server.ExposedAddress = "" + cfg.Server.DataDir = "/srv/netbird" + cfg.Server.Store = StoreConfig{ + Engine: "postgres", + DSN: "postgres://user:pass@example.com/netbird", + } + + cfg.ApplyAdminDefaults() + + require.Equal(t, "/srv/netbird", cfg.Management.DataDir) + require.Equal(t, "postgres", cfg.Management.Store.Engine) + require.Equal(t, cfg.Server.Store.DSN, cfg.Management.Store.DSN) +} + +func TestOpenAdminEventStoreMissingEncryptionKeyReturnsNilInterface(t *testing.T) { + eventStore, err := openAdminEventStore(context.Background(), &CombinedConfig{}, &nbconfig.Config{}) + require.Error(t, err) + require.Contains(t, err.Error(), "encryption key") + require.Nil(t, eventStore) +} + +func TestApplyServerStoreEnv(t *testing.T) { + t.Setenv("NB_STORE_ENGINE_POSTGRES_DSN", "") + t.Setenv("NB_STORE_ENGINE_MYSQL_DSN", "") + t.Setenv("NB_STORE_ENGINE_SQLITE_FILE", "") + + applyServerStoreEnv(StoreConfig{Engine: "postgres", DSN: "postgres-dsn", File: "store.db"}) + require.Equal(t, "postgres-dsn", os.Getenv("NB_STORE_ENGINE_POSTGRES_DSN")) + require.Equal(t, "store.db", os.Getenv("NB_STORE_ENGINE_SQLITE_FILE")) + + applyServerStoreEnv(StoreConfig{Engine: "mysql", DSN: "mysql-dsn"}) + require.Equal(t, "mysql-dsn", os.Getenv("NB_STORE_ENGINE_MYSQL_DSN")) +} diff --git a/combined/cmd/config.go b/combined/cmd/config.go index fe350e52a..890c86876 100644 --- a/combined/cmd/config.go +++ b/combined/cmd/config.go @@ -6,8 +6,7 @@ import ( "net" "net/netip" "os" - "path" - "path/filepath" + filePath "path/filepath" "strings" "time" @@ -74,6 +73,16 @@ type ServerConfig struct { ActivityStore StoreConfig `yaml:"activityStore"` AuthStore StoreConfig `yaml:"authStore"` ReverseProxy ReverseProxyConfig `yaml:"reverseProxy"` + + SupportedSyncMessageVersions *int `yaml:"supportedSyncMessageVersions,omitempty"` + PerAccountSupportedSyncMessageVersions map[string]int `yaml:"perAccountSupportedSyncMessageVersions,omitempty"` + + AgentNetwork AgentNetworkConfig `yaml:"agentNetwork"` +} + +// AgentNetworkConfig contains agent-network (LLM gateway) configuration. +type AgentNetworkConfig struct { + PricingDefaultsFile string `yaml:"pricingDefaultsFile"` } // TLSConfig contains TLS/HTTPS settings @@ -145,6 +154,7 @@ type AuthConfig struct { CLIRedirectURIs []string `yaml:"cliRedirectURIs"` Owner *AuthOwnerConfig `yaml:"owner,omitempty"` DashboardPostLogoutRedirectURIs []string `yaml:"dashboardPostLogoutRedirectURIs"` + GrantTypes []string `yaml:"grantTypes"` } // AuthStorageConfig contains auth storage settings @@ -299,6 +309,19 @@ func (c *CombinedConfig) ApplySimplifiedDefaults() { c.autoConfigureClientSettings(exposedProto, exposedHost, exposedHostPort, hasExternalStuns, hasExternalRelay, hasExternalSignal) } +// ApplyAdminDefaults applies the management settings needed by admin commands even +// when the full server config is invalid and ApplySimplifiedDefaults cannot run. +func (c *CombinedConfig) ApplyAdminDefaults() { + if c.Management.DataDir == "" || c.Management.DataDir == "/var/lib/netbird/" { + c.Management.DataDir = c.Server.DataDir + } + if c.Management.Store.Engine == "" || c.Management.Store.Engine == "sqlite" { + if c.Server.Store.Engine != "" || c.Server.Store.File != "" || c.Server.Store.DSN != "" { + c.Management.Store = c.Server.Store + } + } +} + // applyRelayDefaults configures the relay service if no external relay is configured. func (c *CombinedConfig) applyRelayDefaults(exposedProto, exposedHostPort string, hasExternalRelay, hasExternalStuns bool) { if hasExternalRelay { @@ -576,11 +599,11 @@ func (c *CombinedConfig) buildEmbeddedIdPConfig(mgmt ManagementConfig) (*idp.Emb return nil, fmt.Errorf("authStore.dsn is required when authStore.engine is postgres") } } else { - authStorageFile = path.Join(mgmt.DataDir, "idp.db") + authStorageFile = filePath.Join(mgmt.DataDir, "idp.db") if c.Server.AuthStore.File != "" { authStorageFile = c.Server.AuthStore.File - if !filepath.IsAbs(authStorageFile) { - authStorageFile = filepath.Join(mgmt.DataDir, authStorageFile) + if !filePath.IsAbs(authStorageFile) { + authStorageFile = filePath.Join(mgmt.DataDir, authStorageFile) } } } @@ -604,6 +627,7 @@ func (c *CombinedConfig) buildEmbeddedIdPConfig(mgmt ManagementConfig) (*idp.Emb DashboardRedirectURIs: mgmt.Auth.DashboardRedirectURIs, CLIRedirectURIs: mgmt.Auth.CLIRedirectURIs, DashboardPostLogoutRedirectURIs: mgmt.Auth.DashboardPostLogoutRedirectURIs, + GrantTypes: mgmt.Auth.GrantTypes, } if mgmt.Auth.Owner != nil && mgmt.Auth.Owner.Email != "" { @@ -694,16 +718,21 @@ func (c *CombinedConfig) ToManagementConfig() (*nbconfig.Config, error) { httpConfig.AuthCallbackURL = callbackURL + types.ProxyCallbackEndpointFull return &nbconfig.Config{ - Stuns: stuns, - Relay: relayConfig, - Signal: signalConfig, - Datadir: mgmt.DataDir, - DataStoreEncryptionKey: mgmt.Store.EncryptionKey, - HttpConfig: httpConfig, - StoreConfig: storeConfig, - ReverseProxy: reverseProxy, - DisableDefaultPolicy: mgmt.DisableDefaultPolicy, - EmbeddedIdP: embeddedIdP, + Stuns: stuns, + Relay: relayConfig, + Signal: signalConfig, + Datadir: mgmt.DataDir, + DataStoreEncryptionKey: mgmt.Store.EncryptionKey, + HttpConfig: httpConfig, + StoreConfig: storeConfig, + ReverseProxy: reverseProxy, + DisableDefaultPolicy: mgmt.DisableDefaultPolicy, + EmbeddedIdP: embeddedIdP, + HighestSupportedSyncMessageVersion: c.Server.SupportedSyncMessageVersions, + PerAccountHighestSupportedSyncMessageVersion: c.Server.PerAccountSupportedSyncMessageVersions, + AgentNetwork: nbconfig.AgentNetwork{ + PricingDefaultsFile: c.Server.AgentNetwork.PricingDefaultsFile, + }, }, nil } @@ -727,7 +756,7 @@ func ApplyEmbeddedIdPConfig(ctx context.Context, cfg *nbconfig.Config, mgmtPort cfg.EmbeddedIdP.Storage.Type = "sqlite3" } if cfg.EmbeddedIdP.Storage.Config.File == "" && cfg.Datadir != "" { - cfg.EmbeddedIdP.Storage.Config.File = path.Join(cfg.Datadir, "idp.db") + cfg.EmbeddedIdP.Storage.Config.File = filePath.Join(cfg.Datadir, "idp.db") } issuer := cfg.EmbeddedIdP.Issuer diff --git a/combined/cmd/root.go b/combined/cmd/root.go index 31e0580fb..7eac84ce5 100644 --- a/combined/cmd/root.go +++ b/combined/cmd/root.go @@ -10,6 +10,7 @@ import ( "net/http" "os" "os/signal" + "path/filepath" "strconv" "strings" "sync" @@ -24,6 +25,7 @@ import ( "google.golang.org/grpc" "github.com/netbirdio/netbird/encryption" + agentnetworkpricing "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/pricing" mgmtServer "github.com/netbirdio/netbird/management/internals/server" nbconfig "github.com/netbirdio/netbird/management/internals/server/config" "github.com/netbirdio/netbird/management/server/telemetry" @@ -31,6 +33,7 @@ import ( relayServer "github.com/netbirdio/netbird/relay/server" "github.com/netbirdio/netbird/relay/server/listener" "github.com/netbirdio/netbird/relay/server/listener/ws" + syncgrpc "github.com/netbirdio/netbird/shared/management/grpc" sharedMetrics "github.com/netbirdio/netbird/shared/metrics" "github.com/netbirdio/netbird/shared/relay/auth" "github.com/netbirdio/netbird/shared/signal/proto" @@ -64,7 +67,8 @@ func init() { rootCmd.PersistentFlags().StringVarP(&configPath, "config", "c", "", "path to YAML configuration file (required)") _ = rootCmd.MarkPersistentFlagRequired("config") - rootCmd.AddCommand(newTokenCommands()) + rootCmd.AddCommand(newAdminCommands()) + rootCmd.AddCommand(newLegacyTokenCommand()) } func RootCmd() *cobra.Command { @@ -122,6 +126,37 @@ func execute(cmd *cobra.Command, _ []string) error { } // initializeConfig loads and validates the configuration, then initializes logging. +func applyServerStoreEnv(storeConfig StoreConfig) { + if dsn := storeConfig.DSN; dsn != "" { + switch strings.ToLower(storeConfig.Engine) { + case "postgres": + os.Setenv("NB_STORE_ENGINE_POSTGRES_DSN", dsn) + case "mysql": + os.Setenv("NB_STORE_ENGINE_MYSQL_DSN", dsn) + } + } + if file := storeConfig.File; file != "" { + os.Setenv("NB_STORE_ENGINE_SQLITE_FILE", file) + } +} + +func applyActivityStoreEnv(storeConfig StoreConfig) error { + if engine := storeConfig.Engine; engine != "" { + engineLower := strings.ToLower(engine) + if engineLower == "postgres" && storeConfig.DSN == "" { + return fmt.Errorf("activityStore.dsn is required when activityStore.engine is postgres") + } + os.Setenv("NB_ACTIVITY_EVENT_STORE_ENGINE", engineLower) + if dsn := storeConfig.DSN; dsn != "" { + os.Setenv("NB_ACTIVITY_EVENT_POSTGRES_DSN", dsn) + } + } + if file := storeConfig.File; file != "" { + os.Setenv("NB_ACTIVITY_EVENT_SQLITE_FILE", file) + } + return nil +} + func initializeConfig() error { var err error config, err = LoadConfig(configPath) @@ -137,30 +172,10 @@ func initializeConfig() error { return fmt.Errorf("failed to initialize log: %w", err) } - if dsn := config.Server.Store.DSN; dsn != "" { - switch strings.ToLower(config.Server.Store.Engine) { - case "postgres": - os.Setenv("NB_STORE_ENGINE_POSTGRES_DSN", dsn) - case "mysql": - os.Setenv("NB_STORE_ENGINE_MYSQL_DSN", dsn) - } - } - if file := config.Server.Store.File; file != "" { - os.Setenv("NB_STORE_ENGINE_SQLITE_FILE", file) - } + applyServerStoreEnv(config.Server.Store) - if engine := config.Server.ActivityStore.Engine; engine != "" { - engineLower := strings.ToLower(engine) - if engineLower == "postgres" && config.Server.ActivityStore.DSN == "" { - return fmt.Errorf("activityStore.dsn is required when activityStore.engine is postgres") - } - os.Setenv("NB_ACTIVITY_EVENT_STORE_ENGINE", engineLower) - if dsn := config.Server.ActivityStore.DSN; dsn != "" { - os.Setenv("NB_ACTIVITY_EVENT_POSTGRES_DSN", dsn) - } - } - if file := config.Server.ActivityStore.File; file != "" { - os.Setenv("NB_ACTIVITY_EVENT_SQLITE_FILE", file) + if err := applyActivityStoreEnv(config.Server.ActivityStore); err != nil { + return err } log.Infof("Starting combined NetBird server") @@ -226,7 +241,7 @@ func (s *serverInstances) createRelayServer(cfg *CombinedConfig, tlsSupport bool } hashedSecret := sha256.Sum256([]byte(cfg.Relay.AuthSecret)) - authenticator := auth.NewTimedHMACValidator(hashedSecret[:], 24*time.Hour) + authenticator := auth.NewTimedHMACValidator(hashedSecret[:]) relayCfg := relayServer.Config{ Meter: s.metricsServer.Meter, @@ -275,6 +290,11 @@ func (s *serverInstances) createManagementServer(ctx context.Context, cfg *Combi return fmt.Errorf("failed to ensure encryption key: %w", err) } + if err := loadAgentNetworkPricing(ctx, mgmtConfig); err != nil { + cleanupSTUNListeners(s.stunListeners) + return fmt.Errorf("failed to load agent-network pricing defaults: %w", err) + } + LogConfigInfo(mgmtConfig) s.mgmtSrv, err = createManagementServer(cfg, mgmtConfig) @@ -505,6 +525,16 @@ func createManagementServer(cfg *CombinedConfig, mgmtConfig *nbconfig.Config) (m } mgmtPort, _ := strconv.Atoi(portStr) + if err := syncgrpc.ValidateSyncMessageVersion(mgmtConfig.HighestSupportedSyncMessageVersion); err != nil { + return nil, err + } + + for accountId, version := range mgmtConfig.PerAccountHighestSupportedSyncMessageVersion { + if err := syncgrpc.ValidateSyncMessageVersion(&version); err != nil { + return nil, fmt.Errorf("unrecognized sync message version in perAccountSupportedSyncMessageVersions for account %s %w", accountId, err) + } + } + mgmtSrv := newServer( &mgmtServer.Config{ NbConfig: mgmtConfig, @@ -599,6 +629,32 @@ func handleRelayWebSocket(w http.ResponseWriter, r *http.Request, acceptFn func( acceptFn(conn) } +// loadAgentNetworkPricing loads the management-side LLM pricing defaults +// file for the combined server and starts its periodic reloader. An +// explicitly configured PricingDefaultsFile is required to load (a typo +// must fail startup rather than silently bill with built-ins the operator +// believes they replaced); a relative path is resolved against the data +// directory so a bare filename like "pricing.yaml" lands in the datadir +// alongside the store. With no path configured, / +// is probed and may be absent (compiled-in defaults serve). +func loadAgentNetworkPricing(ctx context.Context, mgmtConfig *nbconfig.Config) error { + pricingPath := mgmtConfig.AgentNetwork.PricingDefaultsFile + required := pricingPath != "" + if !required { + pricingPath = agentnetworkpricing.DefaultFileName + } + if !filepath.IsAbs(pricingPath) { + pricingPath = filepath.Join(mgmtConfig.Datadir, pricingPath) + } + + log.Infof("loading agent-network pricing defaults from %s (required: %v)", pricingPath, required) + if err := agentnetworkpricing.LoadFile(pricingPath, required); err != nil { + return err + } + agentnetworkpricing.StartReloader(ctx, agentnetworkpricing.ReloadInterval) + return nil +} + // logConfig prints all configuration parameters for debugging func logConfig(cfg *CombinedConfig) { log.Info("=== Configuration ===") @@ -675,6 +731,25 @@ func logManagementConfig(cfg *CombinedConfig) { log.Infof(" Relay addresses: %v", cfg.Management.Relays.Addresses) log.Infof(" Relay credentials TTL: %s", cfg.Management.Relays.CredentialsTTL) } + + logAgentNetworkConfig(cfg) +} + +func logAgentNetworkConfig(cfg *CombinedConfig) { + log.Info(" Agent Network:") + pricingPath := cfg.Server.AgentNetwork.PricingDefaultsFile + configured := pricingPath != "" + if !configured { + pricingPath = agentnetworkpricing.DefaultFileName + } + if !filepath.IsAbs(pricingPath) { + pricingPath = filepath.Join(cfg.Management.DataDir, pricingPath) + } + if configured { + log.Infof(" Pricing defaults file: %s", pricingPath) + } else { + log.Infof(" Pricing defaults file: %s (default, optional)", pricingPath) + } } // logEnvVars logs all NB_ environment variables that are currently set diff --git a/combined/cmd/token.go b/combined/cmd/token.go deleted file mode 100644 index 550480062..000000000 --- a/combined/cmd/token.go +++ /dev/null @@ -1,63 +0,0 @@ -package cmd - -import ( - "context" - "fmt" - "os" - "strings" - - log "github.com/sirupsen/logrus" - "github.com/spf13/cobra" - - "github.com/netbirdio/netbird/formatter/hook" - tokencmd "github.com/netbirdio/netbird/management/cmd/token" - "github.com/netbirdio/netbird/management/server/store" - "github.com/netbirdio/netbird/management/server/types" - "github.com/netbirdio/netbird/util" -) - -// newTokenCommands creates the token command tree with combined-specific store opener. -func newTokenCommands() *cobra.Command { - return tokencmd.NewCommands(withTokenStore) -} - -// withTokenStore loads the combined YAML config, initializes the store, and calls fn. -func withTokenStore(cmd *cobra.Command, fn func(ctx context.Context, s store.Store) error) error { - if err := util.InitLog("error", "console"); err != nil { - return fmt.Errorf("init log: %w", err) - } - - ctx := context.WithValue(cmd.Context(), hook.ExecutionContextKey, hook.SystemSource) //nolint:staticcheck - - cfg, err := LoadConfig(configPath) - if err != nil { - return fmt.Errorf("load config: %w", err) - } - - if dsn := cfg.Server.Store.DSN; dsn != "" { - switch strings.ToLower(cfg.Server.Store.Engine) { - case "postgres": - os.Setenv("NB_STORE_ENGINE_POSTGRES_DSN", dsn) - case "mysql": - os.Setenv("NB_STORE_ENGINE_MYSQL_DSN", dsn) - } - } - if file := cfg.Server.Store.File; file != "" { - os.Setenv("NB_STORE_ENGINE_SQLITE_FILE", file) - } - - datadir := cfg.Management.DataDir - engine := types.Engine(cfg.Management.Store.Engine) - - s, err := store.NewStore(ctx, engine, datadir, nil, true) - if err != nil { - return fmt.Errorf("create store: %w", err) - } - defer func() { - if err := s.Close(ctx); err != nil { - log.Debugf("close store: %v", err) - } - }() - - return fn(ctx, s) -} diff --git a/combined/config.yaml.example b/combined/config.yaml.example index 66bc71703..085e4344f 100644 --- a/combined/config.yaml.example +++ b/combined/config.yaml.example @@ -134,3 +134,16 @@ server: # trustedPeers: [] # CIDRs of trusted peer networks (e.g. ["100.64.0.0/10"]) # accessLogRetentionDays: 7 # Days to retain HTTP access logs. 0 (or unset) defaults to 7. Negative values disable cleanup (logs kept indefinitely). # accessLogCleanupIntervalHours: 24 # How often (in hours) to run the access-log cleanup job. 0 (or unset) is treated as "not set" and defaults to 24 hours; cleanup remains enabled. To disable cleanup, set accessLogRetentionDays to a negative value. + + # Agent network (LLM gateway) settings (optional) + # agentNetwork: + # # Path to the YAML file holding the default LLM pricing table. A relative + # # path is resolved against dataDir, so a bare filename like "pricing.yaml" + # # lands in the data directory. When empty, {dataDir}/defaults_llm_pricing.yaml + # # is probed; if no file is present the compiled-in defaults are used. + # # Schema: surface ("openai"/"anthropic"/"bedrock") -> model -> rates in USD + # # per 1k tokens (input_per_1k, output_per_1k, and the optional + # # cached_input_per_1k / cache_read_per_1k / cache_creation_per_1k). The file + # # is re-read periodically (mtime poll). An explicitly configured path that + # # fails to load fails startup; runtime reload errors keep the previous table. + # pricingDefaultsFile: "pricing.yaml" diff --git a/dns/nameserver.go b/dns/nameserver.go index 81c616c50..84e83e2b4 100644 --- a/dns/nameserver.go +++ b/dns/nameserver.go @@ -53,6 +53,7 @@ type NameServerGroup struct { ID string `gorm:"primaryKey"` // AccountID is a reference to Account that this object belongs AccountID string `gorm:"index"` + PublicID string `json:"-"` // Name group name Name string // Description group description diff --git a/docs/agent-networks/01-end-to-end-flows.md b/docs/agent-networks/01-end-to-end-flows.md index 7264f3768..b8891001b 100644 --- a/docs/agent-networks/01-end-to-end-flows.md +++ b/docs/agent-networks/01-end-to-end-flows.md @@ -109,7 +109,7 @@ sequenceDiagram Chk->>Inj: continue Inj->>Inj: inject NetBird identity headers per provider config Inj->>Grd: continue - Grd->>Grd: enforce model allowlist + Grd->>Grd: enforce per-provider allowlist (fail-closed backstop) Grd->>Up: forward (over WireGuard) Up-->>Resp: response (JSON or SSE stream) Resp->>Resp: parse usage tokens, completion @@ -135,6 +135,21 @@ sequenceDiagram (`redact_pii = settings.RedactPii`). Phones, emails, credit cards, PII names — see `redact.go` for the full set. See [`modules/31-proxy-middleware-builtin.md`](modules/31-proxy-middleware-builtin.md). +- The model allowlist is enforced in TWO places. `CheckLLMPolicyLimits` + is authoritative: it resolves the policy that governs this + (provider, caller-groups) and denies (`deny_code = llm_policy.model_blocked`) + when no applicable policy permits the model — so an allowlist scoped to + one group/provider never leaks to another, and an un-guardrailed policy + is genuinely unrestricted. `llm_guardrail` is a per-provider fail-closed + backstop: it only carries an allowlist for a provider every authorising + policy restricts, and blocks unknown/undetermined models even when + management is unreachable. Because that backstop allowlist is the UNION + of every restricting policy's models, per-group narrowing lives only in + the authoritative check: during a `CheckLLMPolicyLimits` outage + `llm_limit_check` fails open, so a caller can reach any model in the + provider's union — a group scoped to model A could reach model B if + another group restricts the same provider to B. This is the documented + fail-open trade-off; a future flag may switch it to fail-closed. - SSE streaming requires special handling on the response side; the parser must handle partial chunks without buffering the whole stream. See [`modules/32-proxy-llm-parsers.md`](modules/32-proxy-llm-parsers.md). diff --git a/docs/agent-networks/modules/21-management-agentnetwork.md b/docs/agent-networks/modules/21-management-agentnetwork.md index b64c1ba20..cc74206e9 100644 --- a/docs/agent-networks/modules/21-management-agentnetwork.md +++ b/docs/agent-networks/modules/21-management-agentnetwork.md @@ -122,7 +122,7 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest | on_request | 1 | `llm_router` | `{"providers":[{id, models[], upstream_*, auth_header_*, allowed_group_ids[]}]}` | **true** | | on_request | 2 | `llm_limit_check` | `{}` | – | | on_request | 3 | `llm_identity_inject` | `{"providers":[{provider_id, header_pair?, json_metadata?, extra_headers?}]}` | **true** | - | on_request | 4 | `llm_guardrail` | `{"model_allowlist"?, "prompt_capture":{enabled,redact_pii}}` | – | + | on_request | 4 | `llm_guardrail` | `{"provider_allowlists"?: {providerID: []model}, "prompt_capture":{enabled,redact_pii}}` | – | | on_response | 5 | `llm_limit_record` | `{}` (runs LAST at runtime) | – | | on_response | 6 | `cost_meter` | `{}` | – | | on_response | 7 | `llm_response_parser` | `{"capture_completion": , "redact_pii"?: true}` | – | diff --git a/docs/agent-networks/modules/31-proxy-middleware-builtin.md b/docs/agent-networks/modules/31-proxy-middleware-builtin.md index 904de6424..efe1bc4ce 100644 --- a/docs/agent-networks/modules/31-proxy-middleware-builtin.md +++ b/docs/agent-networks/modules/31-proxy-middleware-builtin.md @@ -244,7 +244,7 @@ no mocks. Tests: `TestChain_AllowPath_StampsAttributionAndRecordsCounter` | `llm_router` | `{providers: [{id, models, upstream_scheme, upstream_host, upstream_path?, auth_header_name, auth_header_value, allowed_group_ids}]}` | | `llm_limit_check` | `{}` — pulls `MgmtClient` from `FactoryContext` | | `llm_identity_inject` | `{providers: [{provider_id, header_pair?|json_metadata?, extra_headers?}]}` | -| `llm_guardrail` | `{model_allowlist: []string, prompt_capture: {enabled, redact_pii}}` | +| `llm_guardrail` | `{provider_allowlists: {providerID: []string}, prompt_capture: {enabled, redact_pii}}` — allowlist keyed by resolved provider id; a provider absent from the map is unrestricted (fail-closed backstop; authoritative per-policy/group check is management's `CheckLLMPolicyLimits`) | | `llm_response_parser` | `{redact_pii?, capture_completion?: *bool}` | | `cost_meter` | `{pricing_path?}` (basename inside data-dir; defaults `pricing.yaml`) | | `llm_limit_record` | `{}` — same pattern as `llm_limit_check` | diff --git a/docs/io.netbird.client.plist b/docs/io.netbird.client.plist index 800ecead1..fe10b5b63 100644 --- a/docs/io.netbird.client.plist +++ b/docs/io.netbird.client.plist @@ -66,6 +66,9 @@ disableAutoConnect + disableAutostart + + disableClientRoutes diff --git a/docs/netbird-macos.mobileconfig b/docs/netbird-macos.mobileconfig index 9bf616094..8216dd55d 100644 --- a/docs/netbird-macos.mobileconfig +++ b/docs/netbird-macos.mobileconfig @@ -103,6 +103,8 @@