Compare commits

..

1 Commits

Author SHA1 Message Date
MechaCat02
156d9e427d feat: handle SIGTERM for graceful container stops (0.35.0)
`docker compose stop` and Kubernetes / Podman / systemd all send
SIGTERM first; SIGINT is for interactive shells. Without a SIGTERM
listener the container's stop-grace period elapses with the API still
running, then SIGKILL skips the daemon shutdown path and leaks
Chromium until the OS reaps the parent. Replace the bare
`tokio::signal::ctrl_c()` with a select over ctrl_c and
SignalKind::terminate() so the daemon.shutdown().await path runs in
both cases.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-28 18:59:33 +02:00
5 changed files with 36 additions and 117 deletions

View File

@@ -1,6 +1,6 @@
[package]
name = "mangalord"
version = "0.34.1"
version = "0.35.0"
edition = "2021"
default-run = "mangalord"

View File

@@ -4,8 +4,6 @@
//! expire naturally rather than being explicitly invalidated, so other
//! devices keep their existing logins).
use std::sync::OnceLock;
use axum::extract::{Path, State};
use axum::http::StatusCode;
use axum::response::IntoResponse;
@@ -104,15 +102,9 @@ async fn login(
));
}
let user = repo::user::find_by_username(&state.db, username).await?;
let Some(user) = user else {
// No such user. Run argon2 against a stable dummy hash so the
// response time matches the wrong-password branch — otherwise
// an attacker can enumerate usernames by timing the no-user
// 401 against the wrong-password 401.
let _ = verify_password(&input.password, dummy_password_hash());
return Err(AppError::Unauthenticated);
};
let user = repo::user::find_by_username(&state.db, username)
.await?
.ok_or(AppError::Unauthenticated)?;
if !verify_password(&input.password, &user.password_hash) {
return Err(AppError::Unauthenticated);
}
@@ -121,21 +113,6 @@ async fn login(
Ok((StatusCode::OK, jar, Json(AuthResponse { user })))
}
/// Lazily-computed argon2 hash used to equalise login response time
/// across the "no such user" and "wrong password" branches. Computing
/// it once (on the first login of the process) is enough — the hash is
/// never compared against a real password, only used to force argon2
/// to do the same amount of work it would for a real verify.
fn dummy_password_hash() -> &'static str {
static DUMMY: OnceLock<String> = OnceLock::new();
DUMMY
.get_or_init(|| {
crate::auth::password::hash_password("login-timing-equaliser")
.expect("hash_password on a fixed input cannot fail")
})
.as_str()
}
async fn logout(
State(state): State<AppState>,
jar: CookieJar,

View File

@@ -17,10 +17,7 @@ async fn main() -> anyhow::Result<()> {
tracing::info!(%addr, "mangalord listening");
let listener = tokio::net::TcpListener::bind(addr).await?;
axum::serve(listener, router)
.with_graceful_shutdown(async {
let _ = tokio::signal::ctrl_c().await;
tracing::info!("ctrl-c received; shutting down");
})
.with_graceful_shutdown(shutdown_signal())
.await?;
// Drain background tasks (crawler daemon) before exiting so Chromium
@@ -30,3 +27,33 @@ async fn main() -> anyhow::Result<()> {
}
Ok(())
}
/// Wait for either Ctrl-C (interactive shell) or SIGTERM (Docker /
/// Kubernetes / Podman / systemd stop) and log which arrived. Without
/// the SIGTERM branch, `docker compose stop` runs out its grace period
/// and skips straight to SIGKILL — the daemon never gets the
/// `daemon.shutdown().await` path, leaking Chromium.
async fn shutdown_signal() {
use tokio::signal::unix::{signal, SignalKind};
let mut sigterm = match signal(SignalKind::terminate()) {
Ok(s) => s,
Err(e) => {
// SignalKind::terminate() is supported on every Unix the
// tokio runtime runs on; if registration fails we still
// honour Ctrl-C so the process is at least
// interactive-shutdownable.
tracing::warn!(error = %e, "could not install SIGTERM handler; falling back to ctrl_c only");
let _ = tokio::signal::ctrl_c().await;
tracing::info!("ctrl-c received; shutting down");
return;
}
};
tokio::select! {
_ = tokio::signal::ctrl_c() => {
tracing::info!("ctrl-c received; shutting down");
}
_ = sigterm.recv() => {
tracing::info!("SIGTERM received; shutting down");
}
}
}

View File

@@ -567,91 +567,6 @@ async fn user_a_cannot_delete_user_b_token(pool: PgPool) {
assert_eq!(resp.status(), StatusCode::NO_CONTENT);
}
/// Username enumeration via login response time: an attacker probes
/// for valid usernames by measuring how long /auth/login takes. Before
/// the equalisation fix, the no-user branch returned 401 in <1 ms
/// while the wrong-password branch took ~50-100 ms (the argon2 verify
/// cost). This test asserts the no-user branch now spends at least
/// some meaningful fraction of the wrong-password branch's time.
///
/// Tolerance is intentionally loose so CI variance doesn't flap the
/// test. The unequalised gap is large enough (~50x) that even a noisy
/// CI run with a 5x slack still catches it.
#[sqlx::test(migrations = "./migrations")]
async fn login_no_user_branch_runs_argon2_for_timing_equalisation(pool: PgPool) {
use std::time::Instant;
let h = common::harness(pool);
// Register the victim user so the wrong-password branch has a real
// argon2 hash to verify against.
let _ = h
.app
.clone()
.oneshot(common::post_json(
"/api/v1/auth/register",
json!({ "username": "victim", "password": "hunter2hunter2" }),
))
.await
.unwrap();
// Warm-up: first login of the process initialises the dummy hash
// lazily. Skip that cost when measuring.
let _ = h
.app
.clone()
.oneshot(common::post_json(
"/api/v1/auth/login",
json!({ "username": "victim", "password": "wrong" }),
))
.await
.unwrap();
let _ = h
.app
.clone()
.oneshot(common::post_json(
"/api/v1/auth/login",
json!({ "username": "ghost", "password": "wrong" }),
))
.await
.unwrap();
// Median-of-N is more stable than a single sample.
async fn sample_min(
app: &axum::Router,
username: &str,
n: u32,
) -> std::time::Duration {
let mut samples = Vec::with_capacity(n as usize);
for _ in 0..n {
let req = common::post_json(
"/api/v1/auth/login",
json!({ "username": username, "password": "wrong-guess" }),
);
let t = Instant::now();
let resp = app.clone().oneshot(req).await.unwrap();
let d = t.elapsed();
assert_eq!(resp.status(), StatusCode::UNAUTHORIZED);
samples.push(d);
}
// Use the minimum: it's the floor that argon2 takes, robust
// against unrelated stalls (DB connection acquisition, etc.).
*samples.iter().min().unwrap()
}
let wrong_pwd = sample_min(&h.app, "victim", 3).await;
let no_user = sample_min(&h.app, "ghost", 3).await;
// 5x slack: argon2 dominates both branches, so they should be
// within an order of magnitude. Unequalised, no_user would be
// ~50-100x faster. Asserting "no_user >= wrong_pwd / 5" catches
// the bug without being flaky in CI.
assert!(
no_user * 5 >= wrong_pwd,
"login timing leaks user existence: no_user={no_user:?}, wrong_pwd={wrong_pwd:?}"
);
}
#[sqlx::test(migrations = "./migrations")]
async fn delete_unknown_token_is_404(pool: PgPool) {
let h = common::harness(pool);

View File

@@ -1,6 +1,6 @@
{
"name": "mangalord-frontend",
"version": "0.34.1",
"version": "0.35.0",
"private": true,
"type": "module",
"scripts": {