refactor(wakes): epoch-stamp every registration-based wake; retire per-primitive wait seqs

The slot epoch is THE wait identity, so the hand-rolled per-primitive copies
go away: channel loses cur_wait/next_wait_seq/timed_out, mutex loses Wait.seq
and next_seq, TimerTarget::on_timeout takes the epoch. Registrations become
(pid, epoch) — channel parked_receiver, mutex waiters, io fd waiters,
Blocking io completions, sleep timers, joiner lists — and their wakers move
to unpark_at. begin_wait is lock-free, so each primitive opens the wait
inside the same critical section that publishes the registration.

recv_timeout's wake-classification loop collapses: wakes are precise, so
queue → Ok, senders==0 → Disconnected, else Timeout — the 'Defensive'
re-register branch is now unreachable by protocol, not by audit. Same for
Mutex::lock_timeout's one-shot park.

End-state invariant, auditable in one sentence: the only wildcard wake is
request_stop, which is terminal.

src/channel.rs

@@ -39,27 +39,22 @@ pub fn channel<T>() -> (Sender<T>, Receiver<T>) {
         parked_receiver: None,
         senders: 1,
         receiver_alive: true,
-        cur_wait: None,
-        next_wait_seq: 0,
-        timed_out: false,
     }));
     (Sender { inner: inner.clone() }, Receiver { inner })
 }
 
 struct Inner<T> {
     queue: VecDeque<T>,
-    parked_receiver: Option<Pid>,
+    /// The parked receiver's `(pid, park-epoch)`. The epoch is the slot
+    /// word's runtime-wide wait identity (see slot_state.rs): wakers call
+    /// `unpark_at(pid, epoch)`, so an entry left over from an already-woken
+    /// wait — a `select` loser arm, a satisfied `recv_timeout`'s timer — is
+    /// inert: the wake fails the word's epoch CAS and no-ops. This replaces
+    /// the old per-channel `cur_wait`/`next_wait_seq`/`timed_out` trio: wait
+    /// identity now exists exactly once, in the slot word.
+    parked_receiver: Option<(Pid, u32)>,
     senders: usize,
     receiver_alive: bool,
-    /// The seq of the receiver's current *bounded* wait (`recv_timeout`), or
-    /// `None` outside one. Lets `on_timeout` tell "this wait" apart from "a
-    /// later wait on the same channel" — same convention as `Mutex`.
-    cur_wait: Option<u64>,
-    /// Monotonic source for `cur_wait` seqs.
-    next_wait_seq: u64,
-    /// Set by `on_timeout` when it cancels the current bounded wait; consumed
-    /// by the woken receiver to distinguish a timeout from a message wake.
-    timed_out: bool,
 }
 
 pub struct Sender<T> {
@@ -129,8 +124,8 @@ impl<T> Drop for Sender<T> {
                 None
             }
         };
-        if let Some(pid) = unpark {
-            crate::scheduler::unpark(pid);
+        if let Some((pid, epoch)) = unpark {
+            crate::scheduler::unpark_at(pid, epoch);
         }
     }
 }
@@ -151,9 +146,9 @@ impl<T> Sender<T> {
             g.queue.push_back(value);
             g.parked_receiver.take()
         };
-        if let Some(pid) = unpark {
+        if let Some((pid, epoch)) = unpark {
             crate::te!(crate::trace::Event::Send { sender: crate::actor::current_pid().unwrap_or(crate::pid::Pid::new(u32::MAX, u32::MAX)), receiver: Some(pid) });
-            crate::scheduler::unpark(pid);
+            crate::scheduler::unpark_at(pid, epoch);
         } else {
             crate::te!(crate::trace::Event::Send { sender: crate::actor::current_pid().unwrap_or(crate::pid::Pid::new(u32::MAX, u32::MAX)), receiver: None });
         }
@@ -178,7 +173,10 @@ impl<T> Receiver<T> {
                     g.parked_receiver.is_none(),
                     "channel has more than one receiver"
                 );
-                g.parked_receiver = Some(me);
+                // begin_wait is lock-free — legal under the Channel lock;
+                // registering in the same critical section makes the epoch
+                // atomic with the senders' view of the registration.
+                g.parked_receiver = Some((me, crate::scheduler::begin_wait()));
                 crate::te!(crate::trace::Event::RecvPark(me));
             }
             // Release the lock before parking — the unparker will need it.
@@ -192,14 +190,21 @@ impl<T> Receiver<T> {
     /// `timeout` has elapsed, returning [`RecvTimeoutError::Timeout`].
     ///
     /// Built on the same timer machinery as `Mutex::lock_timeout`: the wait
-    /// registers a `WaitTimeout` entry tagged with a per-wait seq; on expiry
-    /// the channel (as the [`TimerTarget`](crate::timer::TimerTarget)) checks
-    /// whether *this* wait is still parked and, only then, cancels it. A wake
-    /// that races the deadline resolves message-first: if a message is
-    /// available when the receiver runs, it is delivered even if the timer
-    /// had already fired. A satisfied or abandoned wait leaves its timer
-    /// entry to expire as a no-op (seq mismatch), per the no-cancellation
-    /// convention in `timer.rs`.
+    /// registers a `WaitTimeout` entry stamped with the wait's park-epoch;
+    /// on expiry the channel (as the
+    /// [`TimerTarget`](crate::timer::TimerTarget)) checks whether *this*
+    /// wait is still parked and, only then, cancels it. A wake that races
+    /// the deadline resolves message-first: if a message is available when
+    /// the receiver runs, it is delivered even if the timer had already
+    /// fired. A satisfied or abandoned wait leaves its timer entry to expire
+    /// as a no-op (registration gone; epoch consumed), per the
+    /// no-cancellation convention in `timer.rs`.
+    ///
+    /// The wake is classified from state alone — wakes are precise (the only
+    /// stamped wakers of this wait are a send, the last-sender drop, and the
+    /// timer; a stop wake unwinds out of `park_current` and never reaches
+    /// the classification), so: message queued → `Ok`; `senders == 0` →
+    /// `Disconnected`; neither → it was the timer → `Timeout`.
     ///
     /// `Duration::ZERO` is a valid timeout: it parks until the immediately-
     /// due timer is drained, then reports `Timeout` unless a message was
@@ -212,7 +217,7 @@ impl<T> Receiver<T> {
             .expect("recv_timeout() called outside an actor");
 
         // Fast path + wait registration, one critical section.
-        let seq;
+        let epoch;
         {
             let mut g = self.inner.lock();
             if let Some(v) = g.queue.pop_front() {
@@ -225,11 +230,8 @@ impl<T> Receiver<T> {
                 g.parked_receiver.is_none(),
                 "channel has more than one receiver"
             );
-            seq = g.next_wait_seq;
-            g.next_wait_seq = g.next_wait_seq.wrapping_add(1);
-            g.cur_wait = Some(seq);
-            g.timed_out = false;
-            g.parked_receiver = Some(me);
+            epoch = crate::scheduler::begin_wait();
+            g.parked_receiver = Some((me, epoch));
             crate::te!(crate::trace::Event::RecvPark(me));
         }
 
@@ -239,34 +241,18 @@ impl<T> Receiver<T> {
         // protocol makes the park below return immediately in that case.
         let deadline = crate::timer::deadline_from_now(timeout);
         let target: std::sync::Arc<dyn crate::timer::TimerTarget> = self.inner.clone();
-        crate::scheduler::insert_wait_timer(deadline, me, target, seq);
+        crate::scheduler::insert_wait_timer(deadline, me, target, epoch);
 
-        loop {
-            crate::scheduler::park_current();
-            crate::te!(crate::trace::Event::RecvWake(crate::actor::current_pid().unwrap()));
-            let mut g = self.inner.lock();
-            if let Some(v) = g.queue.pop_front() {
-                g.cur_wait = None;
-                g.timed_out = false;
-                return Ok(v);
-            }
-            if g.senders == 0 {
-                g.cur_wait = None;
-                g.timed_out = false;
-                return Err(RecvTimeoutError::Disconnected);
-            }
-            if g.timed_out {
-                g.cur_wait = None;
-                g.timed_out = false;
-                return Err(RecvTimeoutError::Timeout);
-            }
-            // Defensive: no current wake source reaches here (a send leaves a
-            // message, closure zeroes senders, the timer sets timed_out, and
-            // a stop unwinds out of park_current) — but if one ever does,
-            // re-register and keep waiting; cur_wait == Some(seq) keeps the
-            // already-armed timer valid for this wait.
-            g.parked_receiver = Some(me);
+        crate::scheduler::park_current();
+        crate::te!(crate::trace::Event::RecvWake(crate::actor::current_pid().unwrap()));
+        let mut g = self.inner.lock();
+        if let Some(v) = g.queue.pop_front() {
+            return Ok(v);
         }
+        if g.senders == 0 {
+            return Err(RecvTimeoutError::Disconnected);
+        }
+        Err(RecvTimeoutError::Timeout)
     }
 
     /// Selective receive: remove and return the first queued message for which
@@ -300,7 +286,7 @@ impl<T> Receiver<T> {
                     g.parked_receiver.is_none(),
                     "channel has more than one receiver"
                 );
-                g.parked_receiver = Some(me);
+                g.parked_receiver = Some((me, crate::scheduler::begin_wait()));
                 crate::te!(crate::trace::Event::RecvPark(me));
             }
             // Release the lock before parking — the unparker will need it.
@@ -346,16 +332,18 @@ impl<T> Receiver<T> {
 // ---------------------------------------------------------------------------
 
 impl<T: Send + 'static> crate::timer::TimerTarget for RawMutex<Inner<T>> {
-    fn on_timeout(&self, pid: Pid, wait_seq: u64) {
-        // Cancel the wait only if THIS wait (seq match) is still parked. If a
-        // sender already took `parked_receiver`, the receiver is waking with
-        // a message — message wins, the timer no-ops. If `cur_wait` moved on,
-        // this entry is stale (the wait was satisfied or abandoned) — no-op.
+    fn on_timeout(&self, pid: Pid, epoch: u32) {
+        // Cancel the wait only if THIS wait (epoch match) is still
+        // registered. If a sender already took `parked_receiver`, the
+        // receiver is waking with a message — message wins, the timer
+        // no-ops. If a later wait by the same receiver is registered, the
+        // epoch mismatches — stale entry, no-op. (The unpark_at would fail
+        // its word CAS in either case anyway; checking under the lock keeps
+        // the registration bookkeeping exact.)
         let unpark = {
             let mut g = self.lock();
-            if g.cur_wait == Some(wait_seq) && g.parked_receiver == Some(pid) {
+            if g.parked_receiver == Some((pid, epoch)) {
                 g.parked_receiver = None;
-                g.timed_out = true;
                 true
             } else {
                 false
@@ -364,7 +352,7 @@ impl<T: Send + 'static> crate::timer::TimerTarget for RawMutex<Inner<T>> {
         // Unpark outside the channel lock — it may take the run-queue lock;
         // legal under a Channel lock, but pointless to nest.
         if unpark {
-            crate::scheduler::unpark(pid);
+            crate::scheduler::unpark_at(pid, epoch);
         }
     }
 }

src/io.rs

@@ -84,6 +84,9 @@ use std::thread::JoinHandle as OsJoinHandle;
 pub type IoResult = Result<Box<dyn Any + Send>, Box<dyn Any + Send>>;
 
 struct Request {
+    /// The submitter's park-epoch — carried through to the `Blocking`
+    /// completion so the wake is epoch-matched.
+    epoch: u32,
     pid: Pid,
     /// The work to perform. Returns the wire-form result directly.
     work: Box<dyn FnOnce() -> IoResult + Send>,
@@ -93,7 +96,7 @@ struct Request {
 pub enum Completion {
     /// A `block_on_io` closure has finished (Ok = return value, Err = panic
     /// payload).
-    Blocking { pid: Pid, result: IoResult },
+    Blocking { pid: Pid, epoch: u32, result: IoResult },
     /// An fd registered via `wait_readable`/`wait_writable` is ready. The
     /// scheduler looks up the parked pid in `waiters`, unparks it, and
     /// removes the entry. `pid` isn't in this variant because the epoll
@@ -131,7 +134,7 @@ pub struct IoThread {
     /// One parked actor per registered fd. Populated by `wait_readable` /
     /// `wait_writable` and drained by the scheduler when a `FdReady`
     /// completion is processed.
-    pub waiters: HashMap<RawFd, Pid>,
+    pub waiters: HashMap<RawFd, (Pid, u32)>,
 
     // ----- Threads -----
 
@@ -231,12 +234,12 @@ impl IoThread {
     }
 
     /// Hand a request to the pool. Increments `outstanding`.
-    pub fn submit(&mut self, pid: Pid, work: Box<dyn FnOnce() -> IoResult + Send>) {
+    pub fn submit(&mut self, pid: Pid, epoch: u32, work: Box<dyn FnOnce() -> IoResult + Send>) {
         self.outstanding += 1;
         // Send can only fail if the pool has hung up, which only happens
         // on shutdown. submit during shutdown is a bug.
         self.tx
-            .send(Request { pid, work })
+            .send(Request { pid, epoch, work })
             .expect("io pool hung up unexpectedly");
     }
 
@@ -265,6 +268,7 @@ impl IoThread {
         &mut self,
         fd: RawFd,
         pid: Pid,
+        epoch: u32,
         readable: bool,
         writable: bool,
     ) -> io::Result<()> {
@@ -303,7 +307,7 @@ impl IoThread {
         if r < 0 {
             return Err(io::Error::last_os_error());
         }
-        self.waiters.insert(fd, pid);
+        self.waiters.insert(fd, (pid, epoch));
         Ok(())
     }
 
@@ -369,7 +373,7 @@ fn pool_loop(
     completions: Arc<Mutex<VecDeque<Completion>>>,
     wake_write: RawFd,
 ) {
-    while let Ok(Request { pid, work }) = rx.recv() {
+    while let Ok(Request { pid, epoch, work }) = rx.recv() {
         let result: IoResult = match panic::catch_unwind(panic::AssertUnwindSafe(work)) {
             Ok(r) => r,
             Err(payload) => Err(payload),
@@ -377,7 +381,7 @@ fn pool_loop(
         completions
             .lock()
             .unwrap()
-            .push_back(Completion::Blocking { pid, result });
+            .push_back(Completion::Blocking { pid, epoch, result });
         wake_scheduler(wake_write);
     }
 }

src/mutex.rs

@@ -33,13 +33,15 @@ impl std::error::Error for LockTimeout {}
 
 struct Wait {
     pid: Pid,
-    seq: u64,
+    /// The wait's park-epoch (slot-word wait identity, see slot_state.rs).
+    /// Grants and timeouts wake via `unpark_at(pid, epoch)`; a stale entry
+    /// can neither be granted by mistake nor wake the wrong wait.
+    epoch: u32,
 }
 
 struct MutexState {
     holder: Option<Pid>,
     waiters: VecDeque<Wait>,
-    next_seq: u64,
     default_timeout: Duration,
 }
 
@@ -53,7 +55,6 @@ impl MutexCore {
             state: StdMutex::new(MutexState {
                 holder: None,
                 waiters: VecDeque::new(),
-                next_seq: 0,
                 default_timeout,
             }),
         }
@@ -61,17 +62,17 @@ impl MutexCore {
 }
 
 impl TimerTarget for MutexCore {
-    fn on_timeout(&self, pid: Pid, wait_seq: u64) {
+    fn on_timeout(&self, pid: Pid, epoch: u32) {
         let unpark = {
             let mut st = self.state.lock().unwrap();
-            // Remove from waiters only if still there with matching seq.
+            // Remove from waiters only if still there with matching epoch.
             // If the lock was already granted (holder == Some(pid)), the
             // timer fired after the grant — treat as no-op; the actor
             // will see `is_holder == true` and return Ok.
             if st.holder == Some(pid) {
                 return;
             }
-            let pos = st.waiters.iter().position(|w| w.pid == pid && w.seq == wait_seq);
+            let pos = st.waiters.iter().position(|w| w.pid == pid && w.epoch == epoch);
             if pos.is_some() {
                 st.waiters.remove(pos.unwrap());
                 true
@@ -80,7 +81,7 @@ impl TimerTarget for MutexCore {
             }
         };
         if unpark {
-            scheduler::unpark(pid);
+            scheduler::unpark_at(pid, epoch);
         }
     }
 }
@@ -133,20 +134,25 @@ impl<T> Mutex<T> {
 
         // Slow path: register as a waiter, set timeout, park.
         let _np = scheduler::NoPreempt::enter();
-        let seq = {
+        let epoch = {
             let mut st = self.core.state.lock().unwrap();
-            let seq = st.next_seq;
-            st.next_seq = st.next_seq.wrapping_add(1);
-            st.waiters.push_back(Wait { pid: me, seq });
-            seq
+            // begin_wait is lock-free — legal under the state lock; this
+            // makes the epoch atomic with the registration's visibility to
+            // grants and timeouts.
+            let epoch = scheduler::begin_wait();
+            st.waiters.push_back(Wait { pid: me, epoch });
+            epoch
         };
 
         let target: Arc<dyn TimerTarget> = self.core.clone();
         let deadline = timer::deadline_from_now(timeout);
-        scheduler::insert_wait_timer(deadline, me, target, seq);
+        scheduler::insert_wait_timer(deadline, me, target, epoch);
         scheduler::park_current();
 
-        // Resumed. Are we the holder?
+        // Resumed — precisely: only our grant or our timer can wake this
+        // wait (both epoch-stamped; a stop wake unwinds out of
+        // park_current). The one-shot interpretation below is therefore
+        // exhaustive. Are we the holder?
         let is_holder = self.core.state.lock().unwrap().holder == Some(me);
         if is_holder {
             let value = self.value.lock().unwrap().take()
@@ -228,12 +234,12 @@ impl<T> Drop for MutexGuard<'_, T> {
         let v = self.value.take().expect("MutexGuard: double drop");
         *self.mutex.value.lock().unwrap() = Some(v);
 
-        let next_pid = {
+        let next = {
             let mut st = self.mutex.core.state.lock().unwrap();
             match st.waiters.pop_front() {
                 Some(w) => {
                     st.holder = Some(w.pid);
-                    Some(w.pid)
+                    Some((w.pid, w.epoch))
                 }
                 None => {
                     st.holder = None;
@@ -241,8 +247,8 @@ impl<T> Drop for MutexGuard<'_, T> {
                 }
             }
         };
-        if let Some(pid) = next_pid {
-            scheduler::unpark(pid);
+        if let Some((pid, epoch)) = next {
+            scheduler::unpark_at(pid, epoch);
         }
     }
 }

src/runtime.rs

@@ -17,7 +17,7 @@
 //!  }
 //!
 //!  Slot {
-//!    word:    AtomicU64           ← (generation << 32) | state — THE state machine
+//!    word:    AtomicU64           ← (gen << 32) | (epoch << 8) | state — THE state machine
 //!    sp:      AtomicUsize         ← saved stack pointer
 //!    stop_ptr:AtomicPtr<...>      ← into the actor's Arc<AtomicBool>
 //!    closure: AtomicPtr<...>      ← first-resume closure, swap-to-take
@@ -320,7 +320,9 @@ pub(crate) type Closure = Box<dyn FnOnce() + Send>;
 /// link / finalize), never on the yield/park/unpark hot path.
 pub(crate) struct SlotCold {
     pub(crate) actor: Option<Actor>,
-    pub(crate) waiters: Vec<Pid>,
+    /// Parked joiners as `(pid, park-epoch)`; finalize wakes each via the
+    /// epoch-matched unpark.
+    pub(crate) waiters: Vec<(Pid, u32)>,
     pub(crate) outcome: Option<Outcome>,
     pub(crate) supervisor_channel: Option<Sender<Signal>>,
     /// Watchers registered via `monitor()`, each tagged with its
@@ -543,6 +545,14 @@ impl RuntimeInner {
         self.unpark_inner(pid, Some(epoch));
     }
 
+    /// Open a new wait for `pid` (the calling actor itself): bump its
+    /// park-epoch and return it. See slot_state.rs for the rules.
+    #[must_use]
+    pub(crate) fn begin_wait(&self, pid: Pid) -> u32 {
+        let slot = self.slot_at(pid).expect("begin_wait: own slot vanished");
+        slot.word.begin_wait(pid.generation())
+    }
+
     fn unpark_inner(&self, pid: Pid, want: Option<u32>) {
         if let Some(slot) = self.slot_at(pid) {
             match slot.word.unpark(pid.generation(), want) {
@@ -937,9 +947,9 @@ fn finalize_actor(inner: &Arc<RuntimeInner>, pid: Pid, outcome: Outcome) {
         }
     }
 
-    // Unpark joiners.
-    for joiner in waiters {
-        inner.unpark(joiner);
+    // Unpark joiners (epoch-matched: each registered under the cold lock).
+    for (joiner, epoch) in waiters {
+        inner.unpark_at(joiner, epoch);
     }
 
     // Reclaim if no outstanding handles (re-verified inside).
@@ -990,17 +1000,19 @@ fn schedule_loop(inner: &Arc<RuntimeInner>, slot_idx: usize) {
                     // actor is between `timers.insert_sleep` and
                     // `park_current`; RunningNotified makes the upcoming park
                     // re-queue), or gone (no-op).
-                    crate::timer::Reason::Sleep => inner.unpark(entry.pid),
-                    crate::timer::Reason::WaitTimeout { target, wait_seq } => {
-                        // The callback may call unpark itself.
-                        target.on_timeout(entry.pid, wait_seq);
+                    crate::timer::Reason::Sleep { epoch } => {
+                        inner.unpark_at(entry.pid, epoch)
+                    }
+                    crate::timer::Reason::WaitTimeout { target, epoch } => {
+                        // The callback may call unpark_at itself.
+                        target.on_timeout(entry.pid, epoch);
                     }
                 }
             }
 
             for completion in completions {
                 match completion {
-                    crate::io::Completion::Blocking { pid, result } => {
+                    crate::io::Completion::Blocking { pid, epoch, result } => {
                         if let Some(io) = inner.io.lock().unwrap().as_mut() {
                             io.outstanding = io.outstanding.saturating_sub(1);
                         }
@@ -1018,19 +1030,19 @@ fn schedule_loop(inner: &Arc<RuntimeInner>, slot_idx: usize) {
                                     // flight; discard the result.
                                 }
                             }
-                            inner.unpark(pid);
+                            inner.unpark_at(pid, epoch);
                         }
                     }
                     crate::io::Completion::FdReady { fd, events: _ } => {
                         // Resolve the parked pid under the io lock, then wake
                         // through the protocol. Lock order: io before all.
-                        let parked_pid = inner.io.lock().unwrap().as_mut().and_then(|io| {
-                            let pid = io.waiters.remove(&fd);
+                        let parked = inner.io.lock().unwrap().as_mut().and_then(|io| {
+                            let entry = io.waiters.remove(&fd);
                             io.epoll_deregister(fd);
-                            pid
+                            entry
                         });
-                        if let Some(pid) = parked_pid {
-                            inner.unpark(pid);
+                        if let Some((pid, epoch)) = parked {
+                            inner.unpark_at(pid, epoch);
                         }
                     }
                 }

src/scheduler.rs

@@ -96,7 +96,10 @@ impl JoinHandle {
                         Some(cold.outcome.take().expect("Done slot must have outcome"))
                     }
                     crate::slot_state::Status::Live => {
-                        cold.waiters.push(me);
+                        // begin_wait is lock-free, legal under the cold lock;
+                        // registering under it makes the epoch atomic with
+                        // the check-Done-or-register linearization point.
+                        cold.waiters.push((me, begin_wait()));
                         None
                     }
                 }
@@ -219,11 +222,30 @@ pub fn park_current() {
 }
 
 pub fn unpark(pid: Pid) {
-    // The whole protocol lives on the slot's packed word (gen + state in one
-    // CAS) — see Slot::unpark_action. No runtime lock unless we enqueue.
+    // The whole protocol lives on the slot's packed word (gen + epoch +
+    // state in one CAS) — see slot_state.rs. No runtime lock unless we
+    // enqueue. WILDCARD form: reserved for terminal wakes (request_stop);
+    // every registration-based waker must use `unpark_at`.
     let _ = try_with_runtime(|inner| inner.unpark(pid));
 }
 
+/// Epoch-matched unpark: wake `pid` only if its current wait is still the
+/// one this waker registered for. The form every registration-based waker
+/// (channel senders, mutex grants, wait-timers, io completions, joiner
+/// wakes) must use — see slot_state.rs for the consuming-wake rules.
+pub(crate) fn unpark_at(pid: Pid, epoch: u32) {
+    let _ = try_with_runtime(|inner| inner.unpark_at(pid, epoch));
+}
+
+/// Open a new wait for the CURRENT actor: bump its park-epoch and return
+/// it. Call once per wait, before registering `(pid, epoch)` with any
+/// waker. Lock-free (one CAS on the own slot word), so it is legal under
+/// any lock, including a Channel-class lock.
+pub(crate) fn begin_wait() -> u32 {
+    let me = current_pid().expect("begin_wait() called outside an actor");
+    with_runtime(|inner| inner.begin_wait(me))
+}
+
 /// Request cooperative cancellation of `pid`.
 ///
 /// Sets the actor's stop flag and wakes it so it observes the flag promptly:
@@ -281,8 +303,9 @@ impl Drop for NoPreempt {
 pub fn sleep(duration: std::time::Duration) {
     let me = current_pid().expect("sleep() called outside an actor");
     let _np = NoPreempt::enter();
+    let epoch = begin_wait();
     let deadline = crate::timer::deadline_from_now(duration);
-    with_runtime(|inner| inner.timers.lock().unwrap().insert_sleep(deadline, me));
+    with_runtime(|inner| inner.timers.lock().unwrap().insert_sleep(deadline, me, epoch));
     park_current();
 }
 
@@ -290,13 +313,13 @@ pub fn insert_wait_timer(
     deadline: std::time::Instant,
     pid: Pid,
     target: std::sync::Arc<dyn crate::timer::TimerTarget>,
-    wait_seq: u64,
+    epoch: u32,
 ) {
     with_runtime(|inner| {
         inner.timers.lock().unwrap().insert(
             deadline,
             pid,
-            crate::timer::Reason::WaitTimeout { target, wait_seq },
+            crate::timer::Reason::WaitTimeout { target, epoch },
         );
     });
 }
@@ -317,9 +340,10 @@ where
     });
     {
         let _np = NoPreempt::enter();
+        let epoch = begin_wait();
         with_runtime(|inner| {
             let mut io = inner.io.lock().unwrap();
-            io.as_mut().expect("io thread not started").submit(me, work);
+            io.as_mut().expect("io thread not started").submit(me, epoch, work);
         });
         park_current();
     }
@@ -351,9 +375,10 @@ pub fn wait_writable(fd: std::os::fd::RawFd) -> std::io::Result<()> {
 fn wait_fd(fd: std::os::fd::RawFd, readable: bool, writable: bool) -> std::io::Result<()> {
     let me = current_pid().expect("wait_*() called outside an actor");
     let _np = NoPreempt::enter();
+    let epoch = begin_wait();
     with_runtime(|inner| {
         let mut io = inner.io.lock().unwrap();
-        io.as_mut().expect("io thread not started").epoll_register(fd, me, readable, writable)
+        io.as_mut().expect("io thread not started").epoll_register(fd, me, epoch, readable, writable)
     })?;
     park_current();
     Ok(())

src/timer.rs

@@ -18,9 +18,9 @@
 //! No cancellation. When a non-timer wakeup happens (e.g. lock granted
 //! before timeout), the timer entry is left in the heap. It will be popped
 //! eventually and the dispatch will observe "actor is no longer parked /
-//! wait_seq is stale" and no-op. Cost is ~32 bytes per stale entry plus a
-//! few cycles on pop; acceptable given the upper bound is "one entry per
-//! parked actor".
+//! the wait's epoch was consumed" and no-op. Cost is ~32 bytes per stale
+//! entry plus a few cycles on pop; acceptable given the upper bound is "one
+//! entry per parked actor".
 //!
 //! Stale pids (slot reused since the timer was inserted) are filtered on
 //! pop by the scheduler — same convention as the run queue.
@@ -35,18 +35,21 @@ use std::time::{Duration, Instant};
 ///
 /// Held inside `Entry`, dispatched by the scheduler in `pop_due`.
 pub enum Reason {
-    /// `loom::sleep(d)`. Unpark `pid` unconditionally (modulo the usual
-    /// "still parked?" check the scheduler applies).
-    Sleep,
-    /// A bounded wait — currently only `Mutex::lock_timeout`. On expiry the
-    /// scheduler calls `target.on_timeout(pid, wait_seq)`. The target then
-    /// decides whether `pid` was actually still waiting, and if so unparks
-    /// it with whatever error the wait was bounded for. `wait_seq` lets the
-    /// target tell apart "this wait" from "a later wait by the same actor
-    /// on the same target".
+    /// `sleep(d)`. Wake `pid` via the epoch-matched unpark: if anything
+    /// else (necessarily a terminal wake) already consumed the wait, the
+    /// entry is stale and no-ops at the CAS.
+    Sleep { epoch: u32 },
+    /// A bounded wait (`Mutex::lock_timeout`, `Receiver::recv_timeout`,
+    /// `select_timeout`). On expiry the scheduler calls
+    /// `target.on_timeout(pid, epoch)`. The target then decides whether
+    /// `pid` was actually still waiting (registration still present under
+    /// its lock), and if so takes the registration and unparks via
+    /// `unpark_at`. The epoch is the slot-word park-epoch — the runtime-wide
+    /// wait identity — so a stale entry is doubly inert: the registration
+    /// check misses, and even a racing unpark fails the word's epoch CAS.
     WaitTimeout {
         target: Arc<dyn TimerTarget>,
-        wait_seq: u64,
+        epoch: u32,
     },
 }
 
@@ -55,7 +58,7 @@ pub enum Reason {
 /// Implementors: do not touch `SchedulerState` other than via the public
 /// `unpark` / channel APIs. The scheduler is mid-iteration when this fires.
 pub trait TimerTarget: Send + Sync {
-    fn on_timeout(&self, pid: Pid, wait_seq: u64);
+    fn on_timeout(&self, pid: Pid, epoch: u32);
 }
 
 pub struct Entry {
@@ -104,8 +107,8 @@ impl Timers {
     }
 
     /// Insert a `Sleep` timer. Convenience for the common case.
-    pub fn insert_sleep(&mut self, deadline: Instant, pid: Pid) {
-        self.insert(deadline, pid, Reason::Sleep);
+    pub fn insert_sleep(&mut self, deadline: Instant, pid: Pid, epoch: u32) {
+        self.insert(deadline, pid, Reason::Sleep { epoch });
     }
 
     /// Insert an arbitrary timer entry.