feat(channel,runtime): off-runtime cross-thread wake for parked receivers and stop

Wakes issued from a non-scheduler OS thread were silent no-ops. Every
off-runtime wake primitive (unpark, unpark_at, request_stop) reaches the
runtime through the RUNTIME thread-local, which is unset on any foreign
thread — so a send from a plain std::thread enqueued its message but never
woke the parked receiver, and there was no way to drive a stop into a
runtime from an application thread (e.g. an OS-signal handler). The former
strands a parked recv forever; the latter is why a downstream server must
poll a shutdown flag instead of parking on it.

Generalize RFC 018's rule — a producer reaches the runtime through a Weak it
holds — from the IO backend to channel senders and to a new handle:

- A receiver captures a Weak<RuntimeInner> (provably live at that moment)
  alongside its (pid, epoch) when it parks. send() and the last-sender drop
  wake through scheduler::unpark_at_via, which takes the thread-local path
  when on a scheduler thread (preemption-gated, slot-eligible) and the
  captured Weak otherwise — the same cross-context wake the IO threads do.
- Runtime::handle() returns a Send + Sync RuntimeHandle carrying that Weak;
  RuntimeHandle::request_stop drives a cooperative stop from any thread and
  is a no-op once the runtime is dropped.

The in-runtime wake paths (recv/select timers) are unchanged; only the sites
reachable from a foreign thread route through the Weak. RuntimeHandle exposes
request_stop only: send-wake needs no user-facing handle, and off-runtime
unpark is covered because request_stop drives unpark on the upgraded inner.

tests/cross_thread_wake.rs: a foreign-thread send wakes a parked receiver; a
foreign-thread request_stop wakes and stops a parked actor; a RuntimeHandle
held across and beyond run never blocks all-done and degrades to a no-op.

src/channel.rs

@@ -90,8 +90,9 @@
 
 use crate::pid::Pid;
 use crate::raw_mutex::RawMutex;
+use crate::runtime::RuntimeInner;
 use std::collections::VecDeque;
-use std::sync::Arc;
+use std::sync::{Arc, Weak};
 
 /// Create a new channel and return its `(Sender, Receiver)` halves.
 ///
@@ -114,12 +115,15 @@ pub fn channel<T>() -> (Sender<T>, Receiver<T>) {
 
 struct Inner<T> {
     queue: VecDeque<T>,
-    /// The parked receiver's `(pid, park-epoch)`, if one is currently
+    /// The parked receiver's `(pid, park-epoch, runtime)`, if one is currently
     /// waiting. The epoch identifies exactly which wait this is, so a waker
     /// left over from a wait that already ended (a losing `select` arm, a
     /// `recv_timeout` whose timer fired after it was already satisfied) is
-    /// inert and does nothing when it fires.
-    parked_receiver: Option<(Pid, u32)>,
+    /// inert and does nothing when it fires. The `Weak<RuntimeInner>` is the
+    /// receiver's runtime, captured while it parked (so provably alive then);
+    /// it lets a sender on a foreign OS thread wake the receiver without the
+    /// `RUNTIME` thread-local, which is unset off a scheduler thread.
+    parked_receiver: Option<(Pid, u32, Weak<RuntimeInner>)>,
     senders: usize,
     receiver_alive: bool,
 }
@@ -206,8 +210,8 @@ impl<T> Drop for Sender<T> {
                 None
             }
         };
-        if let Some((pid, epoch)) = unpark {
-            crate::scheduler::unpark_at(pid, epoch);
+        if let Some((pid, epoch, rt)) = unpark {
+            crate::scheduler::unpark_at_via(pid, epoch, &rt);
         }
     }
 }
@@ -254,13 +258,13 @@ impl<T> Sender<T> {
             g.queue.push_back(value);
             g.parked_receiver.take()
         };
-        if let Some((pid, epoch)) = unpark {
+        if let Some((pid, epoch, rt)) = 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_at(pid, epoch);
+            crate::scheduler::unpark_at_via(pid, epoch, &rt);
         } else {
             crate::te!(crate::trace::Event::Send {
                 sender: crate::actor::current_pid()
@@ -293,13 +297,17 @@ impl<T> Receiver<T> {
                     None => panic!("smarm: recv() called outside an actor"),
                 };
                 debug_assert!(
-                    g.parked_receiver.is_none_or(|(p, _)| p == me),
+                    g.parked_receiver.as_ref().is_none_or(|(p, _, _)| *p == me),
                     "channel has more than one receiver"
                 );
                 // begin_wait is lock-free, so it's 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()));
+                g.parked_receiver = Some((
+                    me,
+                    crate::scheduler::begin_wait(),
+                    crate::scheduler::runtime_weak(),
+                ));
                 crate::te!(crate::trace::Event::RecvPark(me));
             }
             // Release the lock before parking: the unparker will need it.
@@ -347,11 +355,11 @@ impl<T> Receiver<T> {
                 return Err(RecvTimeoutError::Disconnected);
             }
             debug_assert!(
-                g.parked_receiver.is_none_or(|(p, _)| p == me),
+                g.parked_receiver.as_ref().is_none_or(|(p, _, _)| *p == me),
                 "channel has more than one receiver"
             );
             epoch = crate::scheduler::begin_wait();
-            g.parked_receiver = Some((me, epoch));
+            g.parked_receiver = Some((me, epoch, crate::scheduler::runtime_weak()));
             crate::te!(crate::trace::Event::RecvPark(me));
         }
 
@@ -423,10 +431,14 @@ impl<T> Receiver<T> {
                     None => panic!("smarm: recv_match() called outside an actor"),
                 };
                 debug_assert!(
-                    g.parked_receiver.is_none_or(|(p, _)| p == me),
+                    g.parked_receiver.as_ref().is_none_or(|(p, _, _)| *p == me),
                     "channel has more than one receiver"
                 );
-                g.parked_receiver = Some((me, crate::scheduler::begin_wait()));
+                g.parked_receiver = Some((
+                    me,
+                    crate::scheduler::begin_wait(),
+                    crate::scheduler::runtime_weak(),
+                ));
                 crate::te!(crate::trace::Event::RecvPark(me));
             }
             // Release the lock before parking: the unparker will need it.
@@ -497,11 +509,12 @@ impl<T: Send + 'static> crate::timer::TimerTarget for RawMutex<Inner<T>> {
         // keeps the registration bookkeeping exact.)
         let unpark = {
             let mut g = self.lock();
-            if g.parked_receiver == Some((pid, epoch)) {
-                g.parked_receiver = None;
-                true
-            } else {
-                false
+            match g.parked_receiver {
+                Some((p, e, _)) if p == pid && e == epoch => {
+                    g.parked_receiver = None;
+                    true
+                }
+                _ => false,
             }
         };
         // Unpark outside the channel lock: it may take the run-queue lock;
@@ -562,10 +575,10 @@ impl<T> Selectable for Receiver<T> {
             return Ok(false);
         }
         debug_assert!(
-            g.parked_receiver.is_none_or(|(p, _)| p == pid),
+            g.parked_receiver.as_ref().is_none_or(|(p, _, _)| *p == pid),
             "channel has more than one receiver"
         );
-        g.parked_receiver = Some((pid, epoch));
+        g.parked_receiver = Some((pid, epoch, crate::scheduler::runtime_weak()));
         Ok(true)
     }
 

src/lib.rs

@@ -85,7 +85,7 @@ pub use registry::{
     install, lookup_as, register, resolve_name, send, send_dyn, send_to, unregister, whereis,
     NameResolution, RegisterError, SendError,
 };
-pub use runtime::{init, Config, Runtime};
+pub use runtime::{init, Config, Runtime, RuntimeHandle};
 pub use scheduler::{
     block_on_io, cancel_timer, request_stop, run, self_pid, send_after, send_after_named,
     send_after_named_wall, send_after_wall, sleep, sleep_wall, spawn, spawn_addr, spawn_addr_with,

src/runtime.rs

@@ -127,7 +127,7 @@ use crate::supervisor::Signal;
 use crate::timer::Timers;
 
 use std::sync::atomic::{AtomicBool, AtomicPtr, AtomicU32, AtomicU64, AtomicUsize, Ordering};
-use std::sync::{Arc, Mutex};
+use std::sync::{Arc, Mutex, Weak};
 use std::thread;
 
 // ---------------------------------------------------------------------------
@@ -1457,6 +1457,59 @@ impl Runtime {
             inner: self.inner.clone(),
         }
     }
+
+    /// A `Send + Sync` handle to this runtime, usable from any thread —
+    /// including threads that are not smarm schedulers (an OS-signal handler
+    /// thread, an external event source). Grab it *before* [`run`](Self::run)
+    /// and hand it to e.g. a signal thread; that thread can then
+    /// [`request_stop`](RuntimeHandle::request_stop) the runtime's top
+    /// supervisor to drive an ordered shutdown from outside the runtime.
+    ///
+    /// The in-runtime primitives ([`scheduler::request_stop`](crate::request_stop)
+    /// and friends) reach the runtime through a thread-local that is unset on
+    /// any non-scheduler thread, so they are silent no-ops off-runtime; this
+    /// handle carries its own reference and closes that gap.
+    pub fn handle(&self) -> RuntimeHandle {
+        RuntimeHandle {
+            inner: Arc::downgrade(&self.inner),
+        }
+    }
+}
+
+// ---------------------------------------------------------------------------
+// RuntimeHandle — off-runtime wake/stop
+// ---------------------------------------------------------------------------
+
+/// A `Send + Sync` handle to a [`Runtime`], obtained from
+/// [`Runtime::handle`]. Lets a thread that is *not* a smarm scheduler thread
+/// drive a cooperative stop into the runtime — the off-runtime counterpart to
+/// [`scheduler::request_stop`](crate::request_stop).
+///
+/// Holds a [`Weak`] to the runtime, for the same reason the IO backend does
+/// (RFC 018): a lingering handle can never keep the runtime's slot table alive
+/// and can never block [`Runtime::run`] from finishing. Once the `Runtime` is
+/// dropped every method is a harmless no-op — the same end state as calling
+/// `request_stop` on an actor that has already exited.
+#[derive(Clone)]
+pub struct RuntimeHandle {
+    inner: Weak<RuntimeInner>,
+}
+
+impl RuntimeHandle {
+    /// Ask `pid` to stop cooperatively, from any thread. The off-runtime
+    /// equivalent of [`scheduler::request_stop`](crate::request_stop): it sets
+    /// the target's stop flag and wakes it, so a parked actor unwinds at its
+    /// next checkpoint exactly as it would for an in-runtime stop. A no-op if
+    /// the runtime has been dropped, or if the actor has already exited.
+    pub fn request_stop<A>(&self, pid: Pid<A>) {
+        let pid = pid.erase();
+        // Upgrade the Weak per call, like the IO backend does (io.rs): a live
+        // runtime yields the inner and we drive the same stop the in-runtime
+        // path would; a dropped runtime makes this a no-op.
+        if let Some(inner) = self.inner.upgrade() {
+            crate::scheduler::request_stop_inner(&inner, pid);
+        }
+    }
 }
 
 // ---------------------------------------------------------------------------

src/scheduler.rs

@@ -71,7 +71,7 @@ use crate::pid::{Name, Pid};
 use crate::runtime::{self, RuntimeInner, YieldIntent, RUNTIME};
 use crate::supervisor::Signal;
 use std::sync::atomic::Ordering;
-use std::sync::Arc;
+use std::sync::{Arc, Weak};
 
 // ---------------------------------------------------------------------------
 // with_runtime / try_with_runtime
@@ -544,6 +544,29 @@ pub(crate) fn unpark_at(pid: Pid, epoch: u32) {
     let _ = try_with_runtime(|inner| inner.unpark_at(pid, epoch));
 }
 
+// The current actor's runtime as a `Weak`, for a waker that must reach the
+// runtime from a foreign thread later. A channel captures this when its
+// receiver parks, so a cross-thread `send` can wake without the `RUNTIME`
+// thread-local (unset off a scheduler thread). Panics outside `Runtime::run()`,
+// the same contract as `begin_wait`.
+pub(crate) fn runtime_weak() -> Weak<RuntimeInner> {
+    with_runtime(Arc::downgrade)
+}
+
+// Epoch-matched wake of `pid` from a waker that may or may not be on a
+// scheduler thread. On a scheduler thread we take the thread-local path
+// (preemption-gated, slot-eligible); off one that path is a silent no-op, so
+// we reach the runtime through `rt` — the `Weak` the waker captured while it
+// was in-runtime. Mirrors the IO backend's cross-context wake (io.rs, RFC 018).
+pub(crate) fn unpark_at_via(pid: Pid, epoch: u32, rt: &Weak<RuntimeInner>) {
+    if try_with_runtime(|inner| inner.unpark_at(pid, epoch)).is_some() {
+        return;
+    }
+    if let Some(inner) = rt.upgrade() {
+        inner.unpark_at(pid, epoch);
+    }
+}
+
 // Open a new wait for the current actor and return its wait identity
 // ("epoch"). Call once per wait, before registering with any waker. Lock-free,
 // so it's legal to call while already holding another internal lock.