feat(serve): supervised listener pool (v0.2 chunk 1)

OneForOne supervisor on the root actor, Restart::Permanent per listener.
ChildSpec factory owns its fd via Arc<OwnedFd> (OwnedFd gains Sync);
restarts reuse the fd — no re-dup, no fd-less window. wait_readable
failure now exits-and-restarts instead of being fatal. Conn actors stay
unsupervised bare spawns. Test hook INJECT_LISTENER_PANICS panics before
accept so a pending connection must survive into the restarted listener.

Roadmap: chunk 1 marked done; chunk 3 fork resolved to smarm-native
timed waits (RFC 008 landed at 393cdd0, reaper option removed); chunk 2
drain-then-stop decided; v0.4-3(b) unblocked.

src/net.rs

@@ -52,6 +52,13 @@ impl Drop for OwnedFd {
 // becomes the unique closer.
 unsafe impl Send for OwnedFd {}
 
+// SAFETY: shared references only expose `as_raw(&self)` — reading an
+// integer. No interior mutability; `into_raw` takes `self` by value and is
+// unreachable through a shared reference. Needed so a supervisor
+// `ChildSpec` factory (an `Fn` closure, hence shared across restarts) can
+// own its listener fd via `Arc<OwnedFd>`.
+unsafe impl Sync for OwnedFd {}
+
 // ---------------------------------------------------------------------------
 // bind_and_listen
 // ---------------------------------------------------------------------------

src/serve.rs

@@ -16,9 +16,13 @@ use crate::conn_actor::{run_connection, ConnLimits};
 use crate::net::{accept_nonblocking, bind_and_listen, OwnedFd};
 use crate::plug::Pipeline;
 
+use smarm::{ChildSpec, OneForOne, Restart, Strategy};
+
 use std::io::{self, ErrorKind};
 use std::net::{SocketAddr, ToSocketAddrs};
 use std::os::fd::RawFd;
+use std::sync::atomic::{AtomicU32, Ordering};
+use std::sync::Arc;
 use std::time::Duration;
 
 // ---------------------------------------------------------------------------
@@ -85,9 +89,24 @@ fn dup_fd(fd: RawFd) -> io::Result<OwnedFd> {
 // listener actor body
 // ---------------------------------------------------------------------------
 
-fn listener_loop(listener: OwnedFd, pipeline: Pipeline, limits: ConnLimits) {
+/// Test-only fault injection. When nonzero, the next accept-loop iteration
+/// of whichever listener gets there first decrements this and panics —
+/// *before* calling `accept`, so a pending connection stays in the kernel
+/// backlog and must be picked up by the restarted listener. Cost when idle
+/// is one relaxed load per accept-loop iteration (each of which already
+/// pays a syscall). Not public API.
+#[doc(hidden)]
+pub static INJECT_LISTENER_PANICS: AtomicU32 = AtomicU32::new(0);
+
+fn listener_loop(listener: Arc<OwnedFd>, pipeline: Pipeline, limits: ConnLimits) {
     let fd = listener.as_raw();
     loop {
+        if INJECT_LISTENER_PANICS
+            .fetch_update(Ordering::Relaxed, Ordering::Relaxed, |n| n.checked_sub(1))
+            .is_ok()
+        {
+            panic!("urus: injected listener panic (test hook)");
+        }
         match accept_nonblocking(fd) {
             Ok(client) => {
                 // Hand the fd off to a new connection actor. spawn() is
@@ -101,7 +120,11 @@ fn listener_loop(listener: OwnedFd, pipeline: Pipeline, limits: ConnLimits) {
                 // No pending connection. Park until the listener is
                 // readable again, then retry.
                 if let Err(we) = smarm::wait_readable(fd) {
-                    // epoll registration failed — fatal for this listener.
+                    // epoll registration failed. Under supervision a
+                    // `return` is a `Signal::Exit` and `Restart::Permanent`
+                    // restarts us — a transient failure (e.g. EMFILE on
+                    // the epoll set) now heals instead of silently
+                    // shrinking the pool.
                     eprintln!("urus: listener wait_readable failed: {we}");
                     return;
                 }
@@ -119,57 +142,67 @@ fn listener_loop(listener: OwnedFd, pipeline: Pipeline, limits: ConnLimits) {
             }
         }
     }
-    // listener OwnedFd drops here, closing the dup'd fd.
+    // The Arc clone we were started with drops here (normal exit or
+    // unwind), but the ChildSpec factory holds another — the fd outlives
+    // any one incarnation of this listener.
 }
 
 // ---------------------------------------------------------------------------
-// serve_with — main entry. Boots smarm, spawns listeners, blocks.
+// serve_with — main entry. Boots smarm, supervises listeners, blocks.
 // ---------------------------------------------------------------------------
 //
 // Boots an smarm runtime (one OS thread per CPU by default — see smarm's
-// `Config::default()`) and runs until externally killed. We don't wire a
-// graceful-shutdown signal in v1; the runtime exits when all actors exit,
-// which they don't (listener loops are infinite). Ctrl-C is your friend.
+// `Config::default()`) and runs a one-for-one supervisor over the listener
+// pool on the root actor. A panicking listener is restarted on the same
+// (still-open) fd instead of silently shrinking the accept pool. Connection
+// actors stay unsupervised bare spawns — per spec, a connection is cheap
+// and its failure is local: a 500 path, not a restart path. (`spawn` from a
+// listener parents the conn actor under that listener, which never
+// registers a supervisor channel, so conn deaths are invisible to the pool
+// supervisor by construction.)
+//
+// No graceful-shutdown signal yet (v0.2 chunk 2); the supervisor loop never
+// returns because listeners never reach a terminal state. Ctrl-C is your
+// friend.
 
 pub fn serve_with(config: Config, pipeline: Pipeline) -> io::Result<()> {
     let listener = bind_and_listen(config.addr)?;
     println!("urus: listening on {}", config.addr);
 
-    // We want one connection-actor-spawning loop per listener pool slot.
-    // Each gets its own dup'd fd so epoll registrations don't collide.
+    // One connection-actor-spawning loop per listener pool slot. Each gets
+    // its own dup'd fd so epoll registrations don't collide. Each fd is
+    // owned by its ChildSpec's factory closure (via `Arc`): a restarted
+    // listener re-enters `accept`/`wait_readable` on the same fd — no
+    // re-dup, no window where the slot has no fd.
     let mut listener_fds = Vec::with_capacity(config.listener_pool);
-    listener_fds.push(listener); // primary keeps the original
+    listener_fds.push(Arc::new(listener)); // primary keeps the original
 
     for _ in 1..config.listener_pool {
         let dup = dup_fd(listener_fds[0].as_raw())?;
-        listener_fds.push(dup);
+        listener_fds.push(Arc::new(dup));
     }
 
-    let limits   = config.to_conn_limits();
+    let limits = config.to_conn_limits();
 
-    // smarm's runtime API: init(Config) then run(f). The closure is the
-    // root actor; from there we spawn one listener per fd in the pool.
     let smarm_cfg = match config.scheduler_threads {
         Some(n) => smarm::Config::exact(n),
         None    => smarm::Config::default(),
     };
     let rt = smarm::init(smarm_cfg);
     rt.run(move || {
-        let n = listener_fds.len();
-        let mut handles = Vec::with_capacity(n);
+        let mut sup = OneForOne::new().strategy(Strategy::OneForOne);
         for (i, lfd) in listener_fds.into_iter().enumerate() {
             let p = pipeline.clone();
-            let h = smarm::spawn(move || {
+            sup = sup.child(ChildSpec::new(Restart::Permanent, move || {
                 println!("urus: listener {} starting", i);
-                listener_loop(lfd, p, limits);
-            });
-            handles.push(h);
-        }
-        // Block forever (until ctrl-C) by joining the listeners. They
-        // never exit on their own in v1.
-        for h in handles {
-            let _ = h.join();
+                listener_loop(lfd.clone(), p.clone(), limits);
+            }));
         }
+        // Supervision loop on the root actor. Default intensity (3 per 5s)
+        // applies per the runtime; a listener crash-looping faster than
+        // that trips the cap and tears the pool down — loud failure over a
+        // zombie server.
+        sup.run();
     });
 
     Ok(())