bpo-40010: Optimize signal handling in multithreaded applications (GH-19067)

If a thread different than the main thread gets a signal, the
bytecode evaluation loop is no longer interrupted at each bytecode
instruction to check for pending signals which cannot be handled.
Only the main thread of the main interpreter can handle signals.

Previously, the bytecode evaluation loop was interrupted at each
instruction until the main thread handles signals.

Changes:

* COMPUTE_EVAL_BREAKER() and SIGNAL_PENDING_SIGNALS() no longer set
  eval_breaker to 1 if the current thread cannot handle signals.
* take_gil() now always recomputes eval_breaker.

2 files changed, 23 insertions, 4 deletions

diff --git a/Python/ceval.c b/Python/ceval.c
index b183cda..d9a3ee0 100644
--- a/Python/ceval.c
+++ b/Python/ceval.c
@@ -120,6 +120,15 @@ static size_t opcache_global_hits = 0;
 static size_t opcache_global_misses = 0;
 #endif
 
+
+/* Only handle signals on the main thread of the main interpreter. */
+static int
+thread_can_handle_signals(void)
+{
+    return (PyThread_get_thread_ident() == _PyRuntime.main_thread);
+}
+
+
 /* This can set eval_breaker to 0 even though gil_drop_request became
    1.  We believe this is all right because the eval loop will release
    the GIL eventually anyway. */
@@ -127,7 +136,8 @@ static size_t opcache_global_misses = 0;
     _Py_atomic_store_relaxed( \
         &(ceval2)->eval_breaker, \
         _Py_atomic_load_relaxed(&(ceval)->gil_drop_request) | \
-        _Py_atomic_load_relaxed(&(ceval)->signals_pending) | \
+        (_Py_atomic_load_relaxed(&(ceval)->signals_pending) \
+            && thread_can_handle_signals()) | \
         _Py_atomic_load_relaxed(&(ceval2)->pending.calls_to_do) | \
         (ceval2)->pending.async_exc)
 
@@ -156,10 +166,11 @@ static size_t opcache_global_misses = 0;
         COMPUTE_EVAL_BREAKER(ceval, ceval2); \
     } while (0)
 
+/* eval_breaker is not set to 1 if thread_can_handle_signals() is false. */
 #define SIGNAL_PENDING_SIGNALS(ceval, ceval2) \
     do { \
         _Py_atomic_store_relaxed(&(ceval)->signals_pending, 1); \
-        _Py_atomic_store_relaxed(&(ceval2)->eval_breaker, 1); \
+        COMPUTE_EVAL_BREAKER(ceval, ceval2); \
     } while (0)
 
 #define UNSIGNAL_PENDING_SIGNALS(ceval, ceval2) \
@@ -540,8 +551,7 @@ handle_signals(PyThreadState *tstate)
 {
     _PyRuntimeState *runtime = tstate->interp->runtime;
 
-    /* Only handle signals on main thread */
-    if (PyThread_get_thread_ident() != runtime->main_thread) {
+    if (!thread_can_handle_signals()) {
         return 0;
     }
     /*
diff --git a/Python/ceval_gil.h b/Python/ceval_gil.h
index b359e3c..da2a1d6 100644
--- a/Python/ceval_gil.h
+++ b/Python/ceval_gil.h
@@ -280,9 +280,18 @@ _ready:
     COND_SIGNAL(gil->switch_cond);
     MUTEX_UNLOCK(gil->switch_mutex);
 #endif
+
     if (_Py_atomic_load_relaxed(&ceval->gil_drop_request)) {
         RESET_GIL_DROP_REQUEST(ceval, ceval2);
     }
+    else {
+        /* bpo-40010: eval_breaker should be recomputed to be set to 1 if there
+           a pending signal: signal received by another thread which cannot
+           handle signals.
+
+           Note: RESET_GIL_DROP_REQUEST() calls COMPUTE_EVAL_BREAKER(). */
+        COMPUTE_EVAL_BREAKER(ceval, ceval2);
+    }
 
     int must_exit = tstate_must_exit(tstate);