feat(channel): migrate Inner to RawMutex; two-class lock order (Leaf -> Channel)

Phase 2 surfaced the hole this closes: channel guards were held with
preemption enabled, so a timeslice switch inside a channel critical
section could release the pthread mutex from a different OS thread (UB).
RawMutex disables preemption for the guard span and is
cross-thread-release sound by construction; poison goes away with it.

The strict single-class leaf rule cannot survive the migration: finalize
clones the supervisor/trap senders and monitor() clones the Down sender,
all under a cold lock, and those senders live in the slot - the nesting
is structural. The leaf check is therefore generalized to two classes:
Leaf (cold locks, free list, stack pool) and Channel. Order is
Leaf -> Channel, at most one of each; both directions of violation are
debug-asserted at the acquisition site. Channel critical sections call
only the lock-free unpark protocol, so the order is acyclic.

Tests: class-ordering unit tests in raw_mutex (allowed nesting + all
three rejected shapes), plus a multi-scheduler integration test driving
channels through monitor churn and actor death so any ordering
regression trips the debug assert instead of deadlocking.

src/channel.rs

@@ -1,9 +1,23 @@
 //! Unbounded MPSC channels.
 //!
-//! Inner state is `Arc<Mutex<Inner<T>>>` so channels can be sent across OS
+//! Inner state is `Arc<RawMutex<Inner<T>>>` so channels can be sent across OS
 //! threads (required for the multi-scheduler runtime where a sender and
 //! receiver may run on different scheduler threads simultaneously).
 //!
+//! ## Why `RawMutex` (Channel class), not `std::sync::Mutex`
+//!
+//! An actor holding a guard with preemption *enabled* can be timesliced
+//! inside the critical section and resume on a different OS thread — the
+//! pthread mutex would then be released from a thread that didn't lock it,
+//! which is UB (Linux futexes happen to tolerate it, but it's not
+//! guaranteed). `RawMutex` disables preemption for the guard's span and is
+//! cross-thread-release sound by construction, closing the hole. It also
+//! cannot poison. Channel locks form their own [`LockClass::Channel`]
+//! (raw_mutex.rs): they may be taken under a cold (Leaf) lock — finalize and
+//! `monitor()` clone senders that live in slots — but nothing may be locked
+//! under them, which the debug build enforces. `recv_match` runs its user
+//! predicate under this lock: keep it cheap, pure, and channel-free.
+//!
 //! Semantics:
 //!   - Senders are clonable; the last sender drop closes the channel.
 //!   - `Receiver::recv` on an empty open channel parks the receiver.
@@ -15,11 +29,12 @@
 //!     parked, the receiver is unparked.
 
 use crate::pid::Pid;
+use crate::raw_mutex::RawMutex;
 use std::collections::VecDeque;
-use std::sync::{Arc, Mutex};
+use std::sync::Arc;
 
 pub fn channel<T>() -> (Sender<T>, Receiver<T>) {
-    let inner = Arc::new(Mutex::new(Inner {
+    let inner = Arc::new(RawMutex::new_channel(Inner {
         queue: VecDeque::new(),
         parked_receiver: None,
         senders: 1,
@@ -36,11 +51,11 @@ struct Inner<T> {
 }
 
 pub struct Sender<T> {
-    inner: Arc<Mutex<Inner<T>>>,
+    inner: Arc<RawMutex<Inner<T>>>,
 }
 
 pub struct Receiver<T> {
-    inner: Arc<Mutex<Inner<T>>>,
+    inner: Arc<RawMutex<Inner<T>>>,
 }
 
 #[derive(Debug, PartialEq, Eq)]
@@ -59,7 +74,7 @@ impl std::error::Error for RecvError {}
 
 impl<T> Clone for Sender<T> {
     fn clone(&self) -> Self {
-        self.inner.lock().unwrap().senders += 1;
+        self.inner.lock().senders += 1;
         Sender { inner: self.inner.clone() }
     }
 }
@@ -67,7 +82,7 @@ impl<T> Clone for Sender<T> {
 impl<T> Drop for Sender<T> {
     fn drop(&mut self) {
         let unpark = {
-            let mut g = self.inner.lock().unwrap();
+            let mut g = self.inner.lock();
             g.senders -= 1;
             // Wake the parked receiver on the last sender drop regardless of
             // whether the queue is empty. A plain `recv` only ever parks on an
@@ -89,14 +104,14 @@ impl<T> Drop for Sender<T> {
 
 impl<T> Drop for Receiver<T> {
     fn drop(&mut self) {
-        self.inner.lock().unwrap().receiver_alive = false;
+        self.inner.lock().receiver_alive = false;
     }
 }
 
 impl<T> Sender<T> {
     pub fn send(&self, value: T) -> Result<(), SendError<T>> {
         let unpark = {
-            let mut g = self.inner.lock().unwrap();
+            let mut g = self.inner.lock();
             if !g.receiver_alive {
                 return Err(SendError(value));
             }
@@ -117,7 +132,7 @@ impl<T> Receiver<T> {
     pub fn recv(&self) -> Result<T, RecvError> {
         loop {
             {
-                let mut g = self.inner.lock().unwrap();
+                let mut g = self.inner.lock();
                 if let Some(v) = g.queue.pop_front() {
                     return Ok(v);
                 }
@@ -156,7 +171,7 @@ impl<T> Receiver<T> {
     {
         loop {
             {
-                let mut g = self.inner.lock().unwrap();
+                let mut g = self.inner.lock();
                 if let Some(i) = g.queue.iter().position(|v| pred(v)) {
                     // position() found it, so remove() returns Some.
                     return Ok(g.queue.remove(i).unwrap());
@@ -188,7 +203,7 @@ impl<T> Receiver<T> {
     where
         F: Fn(&T) -> bool,
     {
-        let mut g = self.inner.lock().unwrap();
+        let mut g = self.inner.lock();
         if let Some(i) = g.queue.iter().position(|v| pred(v)) {
             return Ok(Some(g.queue.remove(i).unwrap()));
         }
@@ -201,7 +216,7 @@ impl<T> Receiver<T> {
     /// Non-blocking. `Ok(Some(v))` if a message was available, `Ok(None)` if
     /// the channel is empty but open, `Err(RecvError)` if closed and drained.
     pub fn try_recv(&self) -> Result<Option<T>, RecvError> {
-        let mut g = self.inner.lock().unwrap();
+        let mut g = self.inner.lock();
         if let Some(v) = g.queue.pop_front() {
             return Ok(Some(v));
         }

src/monitor.rs

@@ -109,10 +109,11 @@ pub struct Monitor {
 pub fn monitor(target: Pid) -> Monitor {
     let (tx, rx) = channel::<Down>();
 
-    // Register under the target's cold lock. `tx.clone()` only touches the
+    // Register under the target's cold lock. `tx.clone()` takes the channel's
-    // channel's own mutex, never any runtime lock, so it is safe here — but
+    // own lock — a Channel-class RawMutex, explicitly permitted *under* a Leaf
-    // we must not *send* under the lock, as `Sender::send` can unpark a
+    // (cold) lock by the lock order (see raw_mutex.rs). We must still not
-    // parked receiver, and there's no reason to nest that.
+    // *send* under the lock, as `Sender::send` can unpark a parked receiver,
+    // and there's no reason to nest that.
     let (id, registered) = with_runtime(|inner| {
         let id = inner.alloc_monitor_id();
         let registered = match inner.slot_at(target) {

src/raw_mutex.rs

@@ -25,12 +25,20 @@
 //! Tricky", mutex3). 0 = unlocked, 1 = locked, 2 = locked with (possible)
 //! waiters. Uncontended lock/unlock is one CAS / one swap, no syscall.
 //!
-//! Lock-order position: slot cold locks, the free list, and the stack pool
+//! Lock-order position — two classes (see [`LockClass`]):
-//! are all `RawMutex`es and all *leaves among themselves* — never hold two at
+//!
-//! once. Holding a `RawMutex` while pushing to the run queue is permitted
+//! - **Leaf**: slot cold locks, the free list, the stack pool, the name
-//! (e.g. unpark from inside a cold section); the reverse — taking any
+//!   registry. Mutual leaves — never hold two at once.
-//! `RawMutex` from inside a run-queue op — cannot arise (queue ops call
+//! - **Channel**: a channel's internal lock. May be acquired *under* a Leaf
-//! nothing).
+//!   (finalize clones the supervisor/trap senders, and `monitor()` clones the
+//!   Down sender, all under a cold lock — structural, the sender lives in the
+//!   slot), but nothing may be acquired under a Channel lock: channel
+//!   critical sections call only the lock-free unpark protocol.
+//!
+//! So the total order is Leaf → Channel, one of each at most. Holding either
+//! while pushing to the run queue is permitted (unpark from inside a cold or
+//! channel section); the reverse — taking any `RawMutex` from inside a
+//! run-queue op — cannot arise (queue ops call nothing).
 
 use std::cell::UnsafeCell;
 use std::ops::{Deref, DerefMut};
@@ -45,37 +53,78 @@ const CONTENDED: u32 = 2;
 /// sender), so a short spin almost always avoids the syscall.
 const SPIN_LIMIT: u32 = 64;
 
-// The leaf rule, mechanically enforced (debug builds): slot cold locks, the
+/// Which rung of the two-rung lock order a `RawMutex` occupies. Debug builds
-// free list, and the stack pool — i.e. every RawMutex — are mutual leaves.
+/// enforce the order mechanically (see the module docs); release builds carry
-// Holding two at once is a deadlock waiting for the right interleaving, so
+/// no state and no checks.
-// fail at the acquisition that violates it, not in the eventual hang.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub(crate) enum LockClass {
+    /// Runtime cold data: slot cold locks, free list, stack pool, registry.
+    /// Mutual leaves among themselves; a Channel lock may be taken under one.
+    Leaf,
+    /// A channel's internal lock. One at a time, nothing acquired under it;
+    /// may itself be acquired under a Leaf.
+    Channel,
+}
+
+// The ordering rules, mechanically enforced (debug builds): a deadlock from a
+// violated order is a hang waiting for the right interleaving, so fail at the
+// acquisition that violates it, not in the eventual hang.
 #[cfg(debug_assertions)]
 thread_local! {
-    static RAW_MUTEXES_HELD: std::cell::Cell<u32> = const { std::cell::Cell::new(0) };
+    static LEAVES_HELD: std::cell::Cell<u32> = const { std::cell::Cell::new(0) };
+    static CHANNELS_HELD: std::cell::Cell<u32> = const { std::cell::Cell::new(0) };
 }
 
 #[inline]
-fn leaf_check_acquire() {
+fn order_check_acquire(class: LockClass) {
     #[cfg(debug_assertions)]
-    RAW_MUTEXES_HELD.with(|c| {
+    match class {
+        LockClass::Leaf => LEAVES_HELD.with(|l| {
+            debug_assert_eq!(
+                l.get(),
+                0,
+                "lock order violated: acquiring a Leaf RawMutex while already \
+                 holding one (cold locks / free list / stack pool / registry \
+                 are mutual leaves)"
+            );
+            CHANNELS_HELD.with(|c| {
                 debug_assert_eq!(
                     c.get(),
                     0,
-            "leaf rule violated: acquiring a RawMutex while already holding one \
+                    "lock order violated: acquiring a Leaf RawMutex under a \
-             (cold locks / free list / stack pool are mutual leaves)"
+                     channel lock (order is Leaf -> Channel, never the reverse)"
+                );
+            });
+            l.set(l.get() + 1);
+        }),
+        LockClass::Channel => CHANNELS_HELD.with(|c| {
+            debug_assert_eq!(
+                c.get(),
+                0,
+                "lock order violated: acquiring a channel lock while already \
+                 holding one (channel locks are mutual leaves)"
             );
             c.set(c.get() + 1);
-    });
+        }),
+    }
+    #[cfg(not(debug_assertions))]
+    let _ = class;
 }
 
 #[inline]
-fn leaf_check_release() {
+fn order_check_release(class: LockClass) {
     #[cfg(debug_assertions)]
-    RAW_MUTEXES_HELD.with(|c| c.set(c.get() - 1));
+    match class {
+        LockClass::Leaf => LEAVES_HELD.with(|c| c.set(c.get() - 1)),
+        LockClass::Channel => CHANNELS_HELD.with(|c| c.set(c.get() - 1)),
+    }
+    #[cfg(not(debug_assertions))]
+    let _ = class;
 }
 
 pub(crate) struct RawMutex<T> {
     state: AtomicU32,
+    class: LockClass,
     data: UnsafeCell<T>,
 }
 
@@ -86,9 +135,20 @@ unsafe impl<T: Send> Send for RawMutex<T> {}
 unsafe impl<T: Send> Sync for RawMutex<T> {}
 
 impl<T> RawMutex<T> {
+    /// A Leaf-class mutex — the default for runtime cold data.
     pub(crate) const fn new(data: T) -> Self {
+        Self::with_class(data, LockClass::Leaf)
+    }
+
+    /// A Channel-class mutex — for channel internals only.
+    pub(crate) const fn new_channel(data: T) -> Self {
+        Self::with_class(data, LockClass::Channel)
+    }
+
+    pub(crate) const fn with_class(data: T, class: LockClass) -> Self {
         Self {
             state: AtomicU32::new(UNLOCKED),
+            class,
             data: UnsafeCell::new(data),
         }
     }
@@ -98,7 +158,7 @@ impl<T> RawMutex<T> {
         // Enter NoPreempt *before* acquiring, so a preemption can't fire
         // between acquisition and guard construction.
         let prev_preempt = crate::preempt::PREEMPTION_ENABLED.with(|c| c.replace(false));
-        leaf_check_acquire();
+        order_check_acquire(self.class);
         if self
             .state
             .compare_exchange(UNLOCKED, LOCKED, Ordering::Acquire, Ordering::Relaxed)
@@ -172,7 +232,7 @@ impl<T> Drop for RawMutexGuard<'_, T> {
     #[inline]
     fn drop(&mut self) {
         self.m.unlock();
-        leaf_check_release();
+        order_check_release(self.m.class);
         // Restore preemption only after the lock is released.
         crate::preempt::PREEMPTION_ENABLED.with(|c| c.set(self.prev_preempt));
     }
@@ -257,4 +317,44 @@ mod tests {
         *m.lock() += 1;
         assert_eq!(*m.lock(), 1);
     }
+
+    #[test]
+    fn channel_lock_nests_under_leaf() {
+        // The permitted ordering: Leaf -> Channel (finalize/monitor clone a
+        // sender under a cold lock). Must not trip the order check.
+        let leaf = RawMutex::new(0u64);
+        let chan = RawMutex::new_channel(0u64);
+        let _l = leaf.lock();
+        let _c = chan.lock();
+    }
+
+    #[cfg(debug_assertions)]
+    #[test]
+    #[should_panic(expected = "lock order violated")]
+    fn leaf_under_channel_is_rejected() {
+        let leaf = RawMutex::new(0u64);
+        let chan = RawMutex::new_channel(0u64);
+        let _c = chan.lock();
+        let _l = leaf.lock(); // Channel -> Leaf: forbidden
+    }
+
+    #[cfg(debug_assertions)]
+    #[test]
+    #[should_panic(expected = "lock order violated")]
+    fn two_leaves_are_rejected() {
+        let a = RawMutex::new(0u64);
+        let b = RawMutex::new(0u64);
+        let _ga = a.lock();
+        let _gb = b.lock(); // leaves are mutual: forbidden
+    }
+
+    #[cfg(debug_assertions)]
+    #[test]
+    #[should_panic(expected = "lock order violated")]
+    fn two_channel_locks_are_rejected() {
+        let a = RawMutex::new_channel(0u64);
+        let b = RawMutex::new_channel(0u64);
+        let _ga = a.lock();
+        let _gb = b.lock(); // channel locks are mutual leaves: forbidden
+    }
 }

tests/channel.rs

@@ -108,3 +108,51 @@ fn recv_returns_err_when_all_senders_dropped() {
 
     assert!(saw_err.load(std::sync::atomic::Ordering::SeqCst));
 }
+
+#[test]
+fn channel_ops_interleaved_with_monitor_churn_multi_thread() {
+    // Regression for the RawMutex migration: monitor registration clones the
+    // Down sender under the target's cold (Leaf) lock, which now nests a
+    // Channel-class lock under it. Debug builds enforce the Leaf -> Channel
+    // ordering on every acquisition, so driving channels, monitors, and actor
+    // death concurrently across schedulers makes any ordering regression
+    // panic here rather than deadlock in the field.
+    use std::sync::atomic::{AtomicI64, Ordering};
+    use std::sync::Arc;
+
+    let total = Arc::new(AtomicI64::new(0));
+    let total2 = total.clone();
+    smarm::init(smarm::Config::exact(4)).run(move || {
+        let (tx, rx) = channel::<i64>();
+        let consumer = spawn(move || {
+            let mut sum = 0;
+            while let Ok(v) = rx.recv() {
+                sum += v;
+            }
+            OUT.with(|c| c.set(sum)); // not asserted cross-thread; see total
+            total2.fetch_add(sum, Ordering::Relaxed);
+        });
+
+        let mut handles = Vec::new();
+        for i in 0..32i64 {
+            let tx = tx.clone();
+            handles.push(spawn(move || {
+                // Short-lived target whose death fires the monitor below.
+                let t = spawn(move || {
+                    tx.send(i).unwrap();
+                });
+                let m = smarm::monitor(t.pid());
+                t.join().unwrap();
+                // Down delivery exercises send-from-finalize.
+                let d = m.rx.recv().unwrap();
+                assert_eq!(d.reason, smarm::DownReason::Exit);
+            }));
+        }
+        drop(tx);
+        for h in handles {
+            h.join().unwrap();
+        }
+        consumer.join().unwrap();
+    });
+    assert_eq!(total.load(std::sync::atomic::Ordering::Relaxed), (0..32).sum::<i64>());
+}