Files
smarm/tests/poison_stop.rs
T
Claude 453f6f491f fix(runtime): stale-PID pop retries immediately instead of taking the idle path
The phase-1 split filled Idle::next_deadline from the timers lock after the
shared lock was released, which turned the stale-PID branch (formerly a 100µs
poll) into a potential sleep-until-timer-deadline while runnable actors sat in
the queue — a hard stall on exact(1). Stale pops are now PopResult::Retry and
loop without sleeping.

test(poison): strengthen regression coverage. The stop-storm test never fired
the sentinel under a lock (its actors only allocate at lock-free points). Add
self_stop_during_spawn_does_not_poison_shared_mutex: a stop-flagged actor whose
next allocation is the Box::new(closure) inside spawn's with_shared. Validated
both ways: passes with the gate, SIGABRTs (unwind-in-allocator) with the gate
removed. Also alloc_interval(1) so every allocation is an observation point.
2026-06-09 19:08:25 +00:00

90 lines
3.9 KiB
Rust

//! Regression: request_stop racing an alloc-under-lock must not poison any
//! runtime mutex. Before the fix, check_cancelled() fired regardless of
//! PREEMPTION_ENABLED, so a sentinel unwind could trigger inside with_shared
//! (which allocates: run_queue.push_back, waiters.push, etc), poisoning the
//! shared mutex and cascading lock().unwrap() panics.
use smarm::runtime::{init, Config};
use std::sync::atomic::{AtomicUsize, Ordering};
use std::sync::Arc;
#[test]
fn stop_storm_does_not_poison_runtime() {
// alloc_interval(1): every allocation is an observation point, so pre-fix
// the sentinel fires inside with_shared's alloc sites (run_queue.push_back,
// waiters.push, ...) with near-certainty rather than 1-in-128.
let rt = init(Config::exact(4).alloc_interval(1));
let completed = Arc::new(AtomicUsize::new(0));
let c = completed.clone();
rt.run(move || {
// Spawn many short actors that allocate + yield heavily (hammering
// with_shared), and request_stop each one mid-flight from siblings.
let mut handles = Vec::new();
for _ in 0..200 {
let h = smarm::spawn(|| {
for _ in 0..50 {
let _v: Vec<u8> = Vec::with_capacity(64); // alloc → maybe_preempt
smarm::yield_now();
}
});
handles.push(h);
}
// Cancel half of them; the others run to completion. If any lock got
// poisoned the runtime would panic on a subsequent lock().unwrap().
for (i, h) in handles.iter().enumerate() {
if i % 2 == 0 {
smarm::request_stop(h.pid());
}
}
for h in handles {
let _ = h.join();
}
c.fetch_add(1, Ordering::SeqCst);
});
assert_eq!(completed.load(Ordering::SeqCst), 1, "root completed cleanly");
}
/// The sharper repro: a stop-flagged actor whose *next allocation* is the
/// `Box::new(closure)` inside `spawn`'s `with_shared` critical section.
/// Pre-fix, the ungated `check_cancelled` in `maybe_preempt` raises the
/// sentinel right there, unwinding while the global shared mutex is held →
/// poisoned → every later `with_shared` panics on every scheduler thread and
/// the whole runtime collapses. Post-fix, observation is deferred to the next
/// lock-free point and each actor dies a clean `Outcome::Stopped`.
///
/// `request_stop(self_pid())` sets the flag without parking (we're running),
/// and the capturing closure makes `Box::new(f)` a real allocation. With
/// `alloc_interval(1)` the check fires every other allocation, so each actor
/// has ~50% odds of the check landing on the under-lock alloc; 64 actors make
/// a pre-fix escape astronomically unlikely.
#[test]
fn self_stop_during_spawn_does_not_poison_shared_mutex() {
let rt = init(Config::exact(4).alloc_interval(1));
let completed = Arc::new(AtomicUsize::new(0));
let c = completed.clone();
rt.run(move || {
let mut handles = Vec::new();
for i in 0..64usize {
let h = smarm::spawn(move || {
// Vary pre-stop allocation count to cover both phases of the
// every-other-allocation check cadence.
for _ in 0..(i % 2) {
let _phase: Vec<u8> = Vec::with_capacity(8);
}
let payload = vec![0u8; 64]; // captured → Box::new(f) allocates
smarm::request_stop(smarm::self_pid());
let grandchild = smarm::spawn(move || drop(payload));
let _ = grandchild.join();
});
handles.push(h);
}
for h in handles {
// Stopped reports Ok from join; the point is that join itself
// (with_shared) doesn't panic on a poisoned mutex.
let _ = h.join();
}
c.fetch_add(1, Ordering::SeqCst);
});
assert_eq!(completed.load(Ordering::SeqCst), 1, "root completed cleanly");
}