feat(harness): P1 lock-lifetime hardening — PDEATHSIG + SIGTERM/SIGALRM teardown funnel + 60-min hard deadline

- new harness/lifetime.py: install_lifetime_guards() arms PR_SET_PDEATHSIG(SIGTERM) (with
  post-prctl ppid==1 orphan refusal), a SIGTERM handler raising SystemExit through the run's
  finally: teardown funnel (exit 143), and signal.alarm(3600) funnelling SIGALRM the same way
  with a distinct deadline log line (exit 142). Re-entrant signals during teardown are logged
  and ignored (begin_teardown guard) so a second signal can't abort the running cleanup.
- run_recipe_ci.main(): guards installed first thing, before any abra call/lock; both teardown
  finally: blocks (cold + quick) mark begin_teardown().
- .drone.yml recipe-ci step: harness runs under setsid in its own process group; a trap forwards
  the step shell's TERM/EXIT to the whole group so drone cancel reaches the harness instead of
  leaking it (docs/concurrency.md §8.1).
- PEP 446 note on the recipe-lock open(): the fd is non-inheritable, children never carry it.

.drone.yml

@@ -70,4 +70,13 @@ steps:
       # build's custom params. CCCI_QUICK=1 makes run_recipe_ci take the opt-in fast lane (WC7);
       # absent => full cold (default). run_quick ignores STAGES (always upgrade+custom).
       - 'echo "recipe-ci: RECIPE=$RECIPE REF=$REF PR=$PR SRC=$SRC stages=$STAGES quick=${CCCI_QUICK:-0}"'
-      - cc-ci-run runner/run_recipe_ci.py
+      # P1 lock-lifetime hardening: run the harness in its own session/process group (setsid) and
+      # forward a drone cancel (TERM to this step shell) to the WHOLE group, so the harness's
+      # SIGTERM handler runs its teardown funnel instead of being leaked (the exec runner kills
+      # only the step shell, not the tree). PDEATHSIG inside the harness backstops the case where
+      # this shell dies without the trap firing. `wait` propagates the harness exit code.
+      - |
+        setsid cc-ci-run runner/run_recipe_ci.py &
+        PID=$!
+        trap 'kill -TERM -- "-$PID" 2>/dev/null' TERM EXIT
+        wait "$PID"

runner/harness/lifecycle.py

@@ -48,6 +48,7 @@ def acquire_recipe_lock(recipe: str):
     recipe is in flight. Returns the open lock file — the CALLER must keep a reference for the
     whole run; the lock is released only when the process exits and the fd closes."""
     path = os.path.join(RECIPE_LOCK_DIR, f"cc-ci-recipe-{recipe}.lock")
+    # PEP 446: the fd is non-inheritable, so subprocess children never carry the lock.
     f = open(path, "w")  # noqa: SIM115 — deliberately held for the lifetime of the run
     try:
         fcntl.flock(f, fcntl.LOCK_EX | fcntl.LOCK_NB)

runner/harness/lifetime.py

@@ -0,0 +1,95 @@
+"""Run-lifetime hardening (concurrency restructure P1).
+
+The concurrency model's invariant chain is:
+
+    lock lifetime ⊆ harness process lifetime ⊆ drone step lifetime ⊆ 60-min hard deadline
+
+Locks are kernel flocks released on process exit, so the only thing that needs managing is the
+PROCESS lifetime. Three guards, installed at run startup (before any abra call) by
+`install_lifetime_guards()`:
+
+  1. `PR_SET_PDEATHSIG(SIGTERM)`: if the parent (the drone step shell) dies — cancel, runner
+     crash, host shutdown of the step — the kernel delivers SIGTERM to the harness, so a dead
+     build can never leak a running harness that holds locks. Paired with a ppid==1 re-check
+     AFTER the prctl: a parent that died BEFORE the prctl took effect would never trigger the
+     death signal, so a harness that finds itself already reparented refuses to run.
+  2. SIGTERM handler: raise SystemExit so the run's `finally:` teardown funnel executes and the
+     process exits non-zero. Re-entrant deliveries during teardown are logged and IGNORED so a
+     second signal can't abort the cleanup the first one asked for (`begin_teardown()` guards
+     this; the run's own `finally:` blocks also call it so a signal landing mid-normal-teardown
+     can't abort that either).
+  3. `signal.alarm(3600)`: self-imposed hard deadline. SIGALRM funnels into the same teardown
+     path with a distinct log line. Teardown time after the deadline is not alarm-bounded —
+     interrupting a teardown buys nothing; the janitor (flock probe) is the backstop if a
+     teardown wedges and the process is killed harder.
+"""
+
+from __future__ import annotations
+
+import ctypes
+import os
+import signal
+import sys
+
+HARD_DEADLINE_SECONDS = 60 * 60
+
+_PR_SET_PDEATHSIG = 1  # linux/prctl.h
+
+_state = {"tearing_down": False}
+
+
+def begin_teardown() -> None:
+    """Mark the teardown funnel as running. From here on SIGTERM/SIGALRM must NOT raise — it
+    would abort the very cleanup it asks for — so the handlers log and return instead. Called by
+    the handlers themselves before raising, and at the top of the run's `finally:` blocks."""
+    _state["tearing_down"] = True
+
+
+def _funnel_handler(log_line: str, exit_code: int):
+    """A signal handler that routes into the teardown funnel exactly once: log, then raise
+    SystemExit (propagates through the run's try/finally → teardown executes → non-zero exit).
+    While teardown is already running, further signals are logged and swallowed."""
+
+    def handler(signum: int, frame) -> None:  # noqa: ARG001
+        print(log_line, flush=True)
+        if _state["tearing_down"]:
+            print(
+                f"== signal {signum} during teardown — ignored (teardown continues, "
+                "exit stays non-zero) ==",
+                flush=True,
+            )
+            return
+        begin_teardown()
+        raise SystemExit(exit_code)
+
+    return handler
+
+
+def install_lifetime_guards(deadline_seconds: int = HARD_DEADLINE_SECONDS) -> None:
+    """Install all three lifetime guards (see module docstring). Must run at harness startup,
+    before any abra call and before any lock is taken."""
+    libc = ctypes.CDLL("libc.so.6", use_errno=True)
+    if libc.prctl(_PR_SET_PDEATHSIG, signal.SIGTERM, 0, 0, 0) != 0:
+        err = ctypes.get_errno()
+        raise OSError(err, f"prctl(PR_SET_PDEATHSIG, SIGTERM) failed: {os.strerror(err)}")
+    # The prctl is armed now — but only fires for a parent death AFTER this point. If the parent
+    # already died, we are reparented (ppid 1) and would never get the signal: refuse to run, an
+    # orphaned harness would hold locks/apps with nothing managing its lifetime.
+    if os.getppid() == 1:
+        sys.exit("parent died before prctl(PR_SET_PDEATHSIG) — refusing to run orphaned")
+    signal.signal(
+        signal.SIGTERM,
+        _funnel_handler(
+            "== SIGTERM received (drone cancel / parent death) — tearing down ==",
+            128 + signal.SIGTERM,
+        ),
+    )
+    minutes = deadline_seconds // 60
+    signal.signal(
+        signal.SIGALRM,
+        _funnel_handler(
+            f"== run exceeded {minutes}-minute hard deadline — tearing down ==",
+            128 + signal.SIGALRM,
+        ),
+    )
+    signal.alarm(deadline_seconds)

runner/run_recipe_ci.py

@@ -47,6 +47,7 @@ from harness import (  # noqa: E402
     discovery,
     generic,
     lifecycle,
+    lifetime,
     naming,
     warm,
     warmsnap,
@@ -658,6 +659,8 @@ def run_quick(
             results["upgrade"] = "fail"
             results["custom"] = "skip"
     finally:
+        # Teardown funnel running: further SIGTERM/SIGALRM are logged + ignored (lifetime.py).
+        lifetime.begin_teardown()
         # F2-11 skip count (read before deciding pass/fail)
         requires_deps_skipped = 0
         try:
@@ -821,6 +824,9 @@ def promote_canonical(recipe: str, head_ref: str | None) -> None:
 
 
 def main() -> int:
+    # P1 lock-lifetime hardening: PDEATHSIG + SIGTERM/SIGALRM teardown funnel + 60-min hard
+    # deadline, armed before ANY abra call or lock acquisition (see harness/lifetime.py).
+    lifetime.install_lifetime_guards()
     recipe = os.environ.get("RECIPE")
     if not recipe:
         print("RECIPE env is required", file=sys.stderr)
@@ -1123,6 +1129,9 @@ def main() -> int:
                 if op in stages:
                     results[op] = "skip"
     finally:
+        # From here the teardown funnel runs: a SIGTERM/SIGALRM landing now is logged + ignored
+        # (lifetime.py) so a second signal can't abort the cleanup the first one asked for.
+        lifetime.begin_teardown()
         # Teardown the recipe under test FIRST, then deps in reverse declaration order.
         # Parent verify=False (Phase 1d): keep as-is so a parent residual doesn't mask a tier
         # failure. Dep teardown uses verify=True via teardown_deps (F2-5 fix); failures are