add swarm-authelia-bridge: the only thing allowed to write swarm-authelia's users database

This commit is contained in:
damocles 2026-08-16 21:38:53 +02:00 committed by mara
commit fb5d461e52
10 changed files with 876 additions and 0 deletions

View file

@ -0,0 +1,247 @@
//! `swarm-authelia-bridge` — the only thing allowed to write
//! `swarm-authelia`'s users database.
//!
//! Runs **inside the `swarm-authelia` container**, as
//! `User = "authelia-swarm";` (the literal name
//! `swarm-authelia.nix`'s `unitName` already derives) — the same user
//! authelia's own instance runs as, and therefore the file's actual
//! owner. That is the whole answer to "how does an unprivileged
//! `swarm-controller` write a file it doesn't own": it doesn't — this
//! process does, sidestepping the uid boundary instead of bridging it
//! with root/`CAP_CHOWN`/a shared group (all examined and rejected — see
//! `swarmctl/README.md`'s own identical analysis of this same file).
//!
//! Network-facing, not unix-socket-only: `swarm-authelia`'s container
//! shares the host netns (`privateNetwork = false`, same as `hive-forge`/
//! `hive-matrix`), so one listener serves a co-located `swarm-controller`
//! (loopback) and a split-host one (bind wider, firewall it) with the
//! same code path — no separate transport for the cross-host case.
//! Bearer-authenticated via authelia's own OIDC token introspection (RFC
//! 7662) against `swarm-controller`'s **existing** machine-client
//! identity (already minted for the queue connection) — no new
//! credential to mint or deliver, and always local/fast to verify since
//! this process runs right next to the authelia it asks.
//!
//! One endpoint, `POST /requests`, body =
//! [`swarm_authelia_bridge_sock::BridgeRequest`] verbatim — one variant
//! today (`EnsureAgentIdentity`, idempotently ensure an agent exists as
//! an authelia subject). Not a wholesale-replace-the-file API — this
//! process owns rendering `users.yml` internally; see `store` module.
mod introspect;
mod store;
use std::sync::Arc;
use anyhow::{Context, Result, bail};
use axum::extract::State;
use axum::http::{HeaderMap, StatusCode};
use axum::response::{IntoResponse, Response};
use axum::routing::post;
use axum::{Json, Router};
use swarm_authelia_bridge_sock::{BridgeRequest, BridgeResponse};
/// Where the introspecting bearer token is authenticated *to* — this
/// bridge's own authelia machine client, distinct from
/// `swarm-controller`'s (the token being checked). Set by the nix module
/// that provisions this bridge's own client alongside authelia.
struct Config {
bind: String,
store_path: std::path::PathBuf,
users_file: std::path::PathBuf,
authelia_bin: std::path::PathBuf,
introspection_url: String,
client_id: String,
client_secret: String,
}
impl Config {
fn from_env() -> Result<Self> {
Ok(Self {
bind: env_var("SWARM_AUTHELIA_BRIDGE_BIND")?,
store_path: env_var("SWARM_AUTHELIA_BRIDGE_STORE")?.into(),
users_file: env_var("SWARM_AUTHELIA_BRIDGE_USERS_FILE")?.into(),
authelia_bin: env_var("SWARM_AUTHELIA_BRIDGE_AUTHELIA_BIN")?.into(),
introspection_url: env_var("SWARM_AUTHELIA_BRIDGE_INTROSPECTION_URL")?,
client_id: env_var("SWARM_AUTHELIA_BRIDGE_CLIENT_ID")?,
client_secret: read_secret_file(&env_var("SWARM_AUTHELIA_BRIDGE_CLIENT_SECRET_FILE")?)?,
})
}
}
fn env_var(name: &str) -> Result<String> {
std::env::var(name).with_context(|| format!("{name} is unset"))
}
fn read_secret_file(path: &str) -> Result<String> {
let raw =
std::fs::read_to_string(path).with_context(|| format!("reading secret file {path}"))?;
let trimmed = raw.trim();
if trimmed.is_empty() {
bail!("secret file {path} is empty");
}
Ok(trimmed.to_owned())
}
struct AppState {
config: Config,
http: reqwest::Client,
}
#[tokio::main]
async fn main() -> Result<()> {
tracing_subscriber::fmt()
.with_env_filter(
tracing_subscriber::EnvFilter::try_from_default_env().unwrap_or_else(|_| "info".into()),
)
.init();
let config = Config::from_env()?;
let bind = config.bind.clone();
let state = Arc::new(AppState {
config,
http: reqwest::Client::new(),
});
let app = Router::new()
.route("/requests", post(handle_request))
.with_state(state);
let listener = tokio::net::TcpListener::bind(&bind)
.await
.with_context(|| format!("binding {bind}"))?;
tracing::info!(%bind, "swarm-authelia-bridge listening");
axum::serve(listener, app)
.await
.context("serving swarm-authelia-bridge")
}
/// The single endpoint — body is the wire-crate's [`BridgeRequest`]
/// verbatim (JSON), not a per-operation REST route. One variant today,
/// but this is what keeps a second operation from needing a new route +
/// a new extractor shape: it just becomes a new match arm below.
async fn handle_request(
State(state): State<Arc<AppState>>,
headers: HeaderMap,
Json(req): Json<BridgeRequest>,
) -> Response {
if let Err(resp) = authorize(&state, &headers).await {
return resp;
}
let BridgeRequest::EnsureAgentIdentity { name } = req;
match handle(&state, name).await {
Ok(body) => (StatusCode::OK, Json(body)).into_response(),
Err(e) => {
let detail = format!("{e:#}");
tracing::warn!(error = %detail, "ensure_identity failed");
(
StatusCode::INTERNAL_SERVER_ERROR,
Json(BridgeResponse::Error { message: detail }),
)
.into_response()
}
}
}
/// Extract + introspect the bearer token. `Err` carries the response to
/// return outright (401 for anything short of an active token) — kept
/// separate from `handle`'s error path, which is "the op itself failed,"
/// a different case from "the caller was never let in."
async fn authorize(state: &AppState, headers: &HeaderMap) -> Result<(), Response> {
let deny = || {
(
StatusCode::UNAUTHORIZED,
Json(BridgeResponse::Error {
message: "missing or invalid bearer token".to_owned(),
}),
)
.into_response()
};
let Some(auth) = headers.get(axum::http::header::AUTHORIZATION) else {
return Err(deny());
};
let Ok(auth) = auth.to_str() else {
return Err(deny());
};
let Some(token) = auth.strip_prefix("Bearer ") else {
return Err(deny());
};
match introspect::is_active(
&state.http,
&state.config.introspection_url,
&state.config.client_id,
&state.config.client_secret,
token,
)
.await
{
Ok(true) => Ok(()),
Ok(false) => Err(deny()),
Err(e) => {
tracing::warn!(error = %format!("{e:#}"), "introspection call failed; denying");
Err(deny())
}
}
}
async fn handle(state: &AppState, name: String) -> Result<BridgeResponse> {
store::validate_username(&name)?;
let cfg = &state.config;
let mut user_store = store::load_store(&cfg.store_path, &cfg.users_file)?;
if user_store.users.contains_key(&name) {
return Ok(BridgeResponse::AlreadyExists);
}
let generated = generate_password(&cfg.authelia_bin).await?;
user_store.users.insert(
name.clone(),
store::User {
displayname: name.clone(),
password: generated,
email: None,
groups: Vec::new(),
},
);
store::publish(&cfg.store_path, &cfg.users_file, &user_store)?;
tracing::info!(agent = %name, "created authelia identity");
Ok(BridgeResponse::Created)
}
/// Mint a password digest via the **configured** authelia — the argon2
/// parameters baked into a hash have to match the verifier's, same
/// reasoning `swarmctl::generate_password` documents (this is
/// deliberately a fresh async port of that function, not a shared one —
/// `swarmctl` is a separate binary crate with no lib target).
///
/// `--random`, not `--password <pw>`: `/proc/<pid>/cmdline` is
/// world-readable, so a password on argv would be readable by any local
/// process for the call's lifetime. Only the digest is kept — the
/// plaintext is generated and immediately discarded, since nothing reads
/// it back today (still an open question what an agent's login actually
/// uses this for).
async fn generate_password(bin: &std::path::Path) -> Result<String> {
let out = tokio::process::Command::new(bin)
.args(["crypto", "hash", "generate", "argon2", "--random"])
.output()
.await
.with_context(|| format!("running {}", bin.display()))?;
if !out.status.success() {
bail!(
"{} failed ({}): {}",
bin.display(),
out.status,
String::from_utf8_lossy(&out.stderr).trim()
);
}
let stdout = String::from_utf8(out.stdout).context("authelia printed non-UTF-8 output")?;
stdout
.lines()
.find_map(|line| line.trim().strip_prefix("Digest:"))
.map(|v| v.trim().to_owned())
.filter(|v| !v.is_empty())
.with_context(|| {
format!(
"could not parse {}'s output: missing 'Digest:'",
bin.display()
)
})
}