Files
archy/core/archipelago/src/fips/mod.rs
T

332 lines
15 KiB
Rust
Raw Normal View History

//! FIPS (Free Internetworking Peering System) daemon integration.
//!
//! github.com/jmcorgan/fips — a spanning-tree mesh routing protocol that
//! uses Nostr secp256k1 keys as native node identity. Archipelago ships
//! the daemon as an apt package, feeds it the seed-derived key from
//! `/data/identity/fips_key`, and supervises it via
//! `archipelago-fips.service`.
//!
//! This module is the in-process bridge:
//! - [`service`]: systemctl status / start / stop / restart / unmask.
//! - [`config`]: materialise `/etc/fips/fips.yaml` + install the key.
//! - [`update`]: query GitHub (tracking `main`) for a newer build,
//! verify SHA256, install via dpkg, restart.
//!
//! Privileged operations shell out via `sudo systemctl …` and `sudo dpkg …`
//! (mirroring the vpn/update patterns already in the codebase); the
//! sudoers rule shipped in the ISO whitelists exactly those commands for
//! the `archipelago` service user.
//!
//! FIPS is dark on the wire until onboarding writes the key. Before that,
//! `FipsStatus::installed` reports the package state and `service_active`
//! returns false; the transport router keeps routing via Tor.
// Consumers land in the next phase (RPC endpoints + onboarding hookup);
// the module is deliberately API-ready ahead of those call-sites.
#![allow(dead_code)]
pub mod anchors;
pub mod app_ports;
pub mod config;
pub mod dial;
pub mod endpoints;
pub mod iface;
pub mod service;
pub mod telemetry;
pub mod update;
use serde::{Deserialize, Serialize};
/// Auto-activate FIPS with no user interaction. Once seed onboarding has
/// materialised the fips key, install the daemon config + start the service if
/// it isn't already up. Idempotent and best-effort: FIPS is the preferred
/// transport and should come up on its own — the UI "Activate" button is now a
/// manual fallback, not a requirement. No-op pre-onboarding (no key yet) or
/// when the service is already active.
pub async fn ensure_activated(data_dir: &std::path::Path) {
let identity_dir = identity_dir_from(data_dir);
if !identity_dir.join("fips_key").exists() {
return; // pre-onboarding: nothing to activate yet
}
if dial::is_service_active().await {
return; // already up
}
tracing::info!("FIPS inactive — auto-activating (no user interaction needed)");
if let Err(e) = config::install(&identity_dir).await {
tracing::warn!("FIPS auto-activate: config install failed: {:#}", e);
return;
}
let unit = service::activation_unit().await;
if let Err(e) = service::activate(unit).await {
tracing::warn!("FIPS auto-activate: service activate failed: {:#}", e);
return;
}
tracing::info!("FIPS auto-activated");
}
/// Spawn the FIPS supervisor: every 25s it (1) auto-activates FIPS if onboarding
/// is done but the service is down — so it comes up with zero user interaction,
/// and (2) keeps hole-punched paths to known federation peers warm, so on-demand
/// dials land on FIPS instead of falling back to Tor. Warms peers concurrently
/// so one slow/offline peer doesn't delay the rest.
///
/// The interval MUST be shorter than the NAT/hole-punch cold window
/// (`warm_path` docs it at ~30-60s). The previous 45s sat at the edge of that
/// window: a path that went cold at ~30s stayed cold until the next 45s tick,
/// so real peer dials in that gap hit a cold path and fell back to Tor (~18s
/// onion latency instead of FIPS's ~2-3s). 25s keeps every path refreshed
/// inside the minimum cold window, which is what actually makes FIPS — not Tor —
/// the transport peer requests land on. Measured: warm FIPS browse ~2.6s vs a
/// cold-path fallback browse ~18-22s over Tor to the same peer.
pub fn spawn_fips_supervisor(data_dir: std::path::PathBuf) {
tokio::spawn(async move {
let mut tick = tokio::time::interval(std::time::Duration::from_secs(25));
// Connectivity watcher state: re-apply seed anchors the moment the
// anchor link drops (edge) or the data path degrades (dials keep
// failing with zero successes), instead of waiting for the 300s
// anchor tick. Bounded: at most one re-apply per RE_APPLY_BACKOFF.
const RE_APPLY_BACKOFF: std::time::Duration = std::time::Duration::from_secs(60);
let mut prev_connected: Option<bool> = None;
let mut prev_totals = telemetry::totals();
let mut last_apply: Option<std::time::Instant> = None;
loop {
tick.tick().await;
// Bring FIPS up on its own once onboarding has materialised the key.
ensure_activated(&data_dir).await;
if !dial::is_service_active().await {
prev_connected = None; // daemon restart = fresh edge detection
continue;
}
// ── Warm the union of federation peers + configured seed
// anchors. Warming only federation npubs left the direct
// anchors (vps2, LAN peers) to go cold between 300s ticks.
let nodes = crate::federation::load_nodes(&data_dir)
.await
.unwrap_or_default();
let seed = anchors::load(&data_dir).await.unwrap_or_default();
let mut warm_npubs: std::collections::BTreeSet<String> =
nodes.iter().filter_map(|n| n.fips_npub.clone()).collect();
warm_npubs.extend(seed.iter().map(|a| a.npub.clone()));
let mut handles = Vec::new();
for npub in warm_npubs {
// Service-active was checked once above for the whole batch.
handles.push(tokio::spawn(async move {
dial::warm_path_unchecked(&npub).await
}));
}
for h in handles {
let _ = h.await;
}
// ── Connectivity watcher: detect anchor-link loss AND silent
// data-path death (daemon reports "connected" but every dial
// connect-fails — observed live on .198, 2026-07-27, where the
// 300s tick never healed it).
let mut anchor_npubs = vec![service::PUBLIC_ANCHOR_NPUB.to_string()];
anchor_npubs.extend(seed.iter().map(|a| a.npub.clone()));
let (_, connected) = service::peer_connectivity_summary(&anchor_npubs).await;
let totals = telemetry::totals();
let link_dropped = prev_connected == Some(true) && !connected;
let never_connected = prev_connected.is_none() && !connected;
let data_path_dead =
totals.1.saturating_sub(prev_totals.1) >= 5 && totals.0 == prev_totals.0;
prev_connected = Some(connected);
prev_totals = totals;
let backoff_ok = last_apply.is_none_or(|t| t.elapsed() >= RE_APPLY_BACKOFF);
if (link_dropped || never_connected || data_path_dead) && backoff_ok && !seed.is_empty()
{
tracing::info!(
link_dropped,
never_connected,
data_path_dead,
"FIPS connectivity degraded — re-applying seed anchors now"
);
last_apply = Some(std::time::Instant::now());
let _ = anchors::apply(&seed).await;
}
}
});
}
use std::path::{Path, PathBuf};
/// Systemd unit name supervised by archipelago.
pub const SERVICE_UNIT: &str = "archipelago-fips.service";
/// Path the FIPS daemon reads its config from (Debian package default).
pub const DAEMON_CONFIG_PATH: &str = "/etc/fips/fips.yaml";
/// Path the FIPS daemon reads its private key from.
pub const DAEMON_KEY_PATH: &str = "/etc/fips/fips.key";
/// Path the FIPS daemon reads its public key from.
pub const DAEMON_PUB_PATH: &str = "/etc/fips/fips.pub";
/// Upstream repository the updater tracks (branch `main`).
pub const UPSTREAM_REPO: &str = "jmcorgan/fips";
/// Default UDP port the daemon listens on.
pub const DEFAULT_UDP_PORT: u16 = 8668;
/// UDP port archipelago actually publishes/binds for the daemon. The
/// container publishes `2121:2121/udp` (see `package/config.rs`) and every
/// peer roster in the fleet dials `<host>:2121`, but the rendered daemon
/// config used to bind upstream's 8668 — leaving inbound UDP dead on
/// bridged-network installs and everything silently riding TCP 8443. The
/// bind now uses this port so the published mapping, the fleet rosters,
/// and the pairing QR all agree.
pub const PUBLISHED_UDP_PORT: u16 = 2121;
/// Default TCP port the daemon listens on. Used as a fallback when a
/// peer can't be reached over UDP — common on networks that block UDP
/// (corporate/guest wifi) and the path the public fips.v0l.io anchor
/// currently accepts. Upstream factory default enables both transports
/// and archipelago intentionally matches that baseline so fresh nodes
/// can reach the broader FIPS mesh without operator config.
pub const DEFAULT_TCP_PORT: u16 = 8443;
/// Upstream systemd unit shipped by the `fips` debian package. Archipelago
/// prefers its own supervision (`archipelago-fips.service`) but respects an
/// already-running upstream unit so legacy/dev nodes — where no seed-derived
/// key exists — still report FIPS as active in the UI.
pub const UPSTREAM_SERVICE_UNIT: &str = "fips.service";
/// Aggregated runtime status of the FIPS subsystem, surfaced to the dashboard.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct FipsStatus {
/// Whether the `fips` debian package is installed on the host.
pub installed: bool,
/// Installed daemon version string reported by `fipsctl --version`,
/// or None if not installed / not queryable.
pub version: Option<String>,
/// `systemctl is-active archipelago-fips.service` result: "active",
/// "inactive", "failed", "masked", "unknown".
pub service_state: String,
/// State of the upstream `fips.service` (shipped by the debian package).
pub upstream_service_state: String,
/// True if either the archipelago-managed or upstream unit is active.
pub service_active: bool,
/// Whether the seed-derived FIPS key has been materialised on disk.
/// The archipelago-managed service cannot start meaningfully until
/// this is true; legacy nodes may still report FIPS active via the
/// upstream unit without this file.
pub key_present: bool,
/// Local FIPS npub (bech32). Prefers the seed-derived key when
/// present; falls back to the upstream daemon's own key on legacy
/// nodes where `/etc/fips/fips.pub` is readable.
pub npub: Option<String>,
/// Number of currently authenticated FIPS peers, per
/// `fipsctl show peers`. 0 → isolated / anchor unreachable;
/// >0 → DHT routing is viable.
#[serde(default)]
pub authenticated_peer_count: u32,
/// True when at least one peer in the identity cache is a known
/// public anchor (currently `fips.v0l.io`). Anchors bootstrap DHT
/// routing for general-case deployments, so a red anchor status is
/// the top UX indicator of "FIPS traffic will probably degrade to
/// Tor until the anchor is reachable."
#[serde(default)]
pub anchor_connected: bool,
}
impl FipsStatus {
/// Snapshot the current state across package, key, and service.
///
/// `data_dir` is the archipelago data-dir (used to load the
/// operator-configured seed-anchor list so "anchor_connected" means
/// "at least one authenticated peer matches a public or configured
/// seed anchor", not just "fips.v0l.io specifically").
pub async fn query(data_dir: &Path) -> Self {
let identity_dir = identity_dir_from(data_dir);
let installed = service::package_installed().await;
let version = if installed {
service::daemon_version().await.ok()
} else {
None
};
let service_state = service::unit_state(SERVICE_UNIT).await;
let upstream_service_state = service::unit_state(UPSTREAM_SERVICE_UNIT).await;
let service_active = service_state == "active" || upstream_service_state == "active";
let key_present = crate::identity::fips_key_exists(&identity_dir);
// Prefer the seed-derived npub; otherwise read the daemon's own
// key file at /etc/fips/fips.pub (world-readable per debian pkg).
let npub = match crate::identity::fips_npub(&identity_dir).await {
Ok(Some(n)) => Some(n),
_ => service::read_upstream_npub().await.ok().flatten(),
};
let (authenticated_peer_count, anchor_connected) = if service_active {
// Build the anchor-candidate list: hardcoded public anchor
// plus every entry in the operator's seed-anchors.json.
// The card lights up if any of them is authenticated.
let mut anchor_npubs = vec![service::PUBLIC_ANCHOR_NPUB.to_string()];
if let Ok(seed) = anchors::load(data_dir).await {
anchor_npubs.extend(seed.into_iter().map(|a| a.npub));
}
service::peer_connectivity_summary(&anchor_npubs).await
} else {
(0, false)
};
Self {
installed,
version,
service_state,
upstream_service_state,
service_active,
key_present,
npub,
authenticated_peer_count,
anchor_connected,
}
}
}
/// Compose a data-dirrelative identity directory path.
/// Mirrors the convention used elsewhere in the codebase so callers don't
/// have to repeat the `.join("identity")` each time.
pub fn identity_dir_from(data_dir: &Path) -> PathBuf {
data_dir.join("identity")
}
#[cfg(test)]
mod tests {
use super::*;
#[tokio::test]
async fn test_status_reports_no_key_pre_onboarding() {
let dir = tempfile::tempdir().unwrap();
// query() now takes a data_dir (parent) rather than identity_dir,
// since it also reads seed-anchors.json for the anchor check.
// No identity/ subdir → no key; no seed-anchors.json → public
// anchor is the only candidate.
let status = FipsStatus::query(dir.path()).await;
assert!(!status.key_present, "no key before onboarding");
// `npub` falls back to whatever an already-running local fips
// daemon advertises, so on a dev machine or node with fips
// installed this field can be Some(...) even when the test
// data_dir is empty. We only assert that key_present is false.
// `installed`, `service_state`, `version` depend on the host and are
// not asserted here — query() must return cleanly regardless.
}
#[test]
fn test_identity_dir_from() {
let data = Path::new("/var/lib/archipelago");
assert_eq!(
identity_dir_from(data),
Path::new("/var/lib/archipelago/identity")
);
}
#[test]
fn test_constants_have_expected_shape() {
assert!(SERVICE_UNIT.ends_with(".service"));
assert!(DAEMON_CONFIG_PATH.starts_with('/'));
assert!(DAEMON_KEY_PATH.starts_with('/'));
assert_eq!(UPSTREAM_REPO, "jmcorgan/fips");
}
}