diff --git a/src/backend/port/atomics.c b/src/backend/port/atomics.c
index c0c2b312703..099858723f1 100644
--- a/src/backend/port/atomics.c
+++ b/src/backend/port/atomics.c
@@ -68,18 +68,35 @@ pg_atomic_init_flag_impl(volatile pg_atomic_flag *ptr)
 #else
 	SpinLockInit((slock_t *) &ptr->sema);
 #endif
+
+	ptr->value = false;
 }
 
 bool
 pg_atomic_test_set_flag_impl(volatile pg_atomic_flag *ptr)
 {
-	return TAS((slock_t *) &ptr->sema);
+	uint32		oldval;
+
+	SpinLockAcquire((slock_t *) &ptr->sema);
+	oldval = ptr->value;
+	ptr->value = true;
+	SpinLockRelease((slock_t *) &ptr->sema);
+
+	return oldval == 0;
 }
 
 void
 pg_atomic_clear_flag_impl(volatile pg_atomic_flag *ptr)
 {
-	S_UNLOCK((slock_t *) &ptr->sema);
+	SpinLockAcquire((slock_t *) &ptr->sema);
+	ptr->value = false;
+	SpinLockRelease((slock_t *) &ptr->sema);
+}
+
+bool
+pg_atomic_unlocked_test_flag_impl(volatile pg_atomic_flag *ptr)
+{
+	return ptr->value == 0;
 }
 
 #endif							/* PG_HAVE_ATOMIC_FLAG_SIMULATION */
diff --git a/src/include/port/atomics/fallback.h b/src/include/port/atomics/fallback.h
index 4e07add0a4f..59be29cf0ee 100644
--- a/src/include/port/atomics/fallback.h
+++ b/src/include/port/atomics/fallback.h
@@ -80,6 +80,7 @@ typedef struct pg_atomic_flag
 #else
 	int			sema;
 #endif
+	volatile bool value;
 } pg_atomic_flag;
 
 #endif /* PG_HAVE_ATOMIC_FLAG_SUPPORT */
@@ -132,17 +133,7 @@ extern bool pg_atomic_test_set_flag_impl(volatile pg_atomic_flag *ptr);
 extern void pg_atomic_clear_flag_impl(volatile pg_atomic_flag *ptr);
 
 #define PG_HAVE_ATOMIC_UNLOCKED_TEST_FLAG
-static inline bool
-pg_atomic_unlocked_test_flag_impl(volatile pg_atomic_flag *ptr)
-{
-	/*
-	 * Can't do this efficiently in the semaphore based implementation - we'd
-	 * have to try to acquire the semaphore - so always return true. That's
-	 * correct, because this is only an unlocked test anyway. Do this in the
-	 * header so compilers can optimize the test away.
-	 */
-	return true;
-}
+extern bool pg_atomic_unlocked_test_flag_impl(volatile pg_atomic_flag *ptr);
 
 #endif /* PG_HAVE_ATOMIC_FLAG_SIMULATION */
 
diff --git a/src/test/regress/regress.c b/src/test/regress/regress.c
index a6af6d59c39..884c40ee2f8 100644
--- a/src/test/regress/regress.c
+++ b/src/test/regress/regress.c
@@ -881,7 +881,6 @@ wait_pid(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
-#ifndef PG_HAVE_ATOMIC_FLAG_SIMULATION
 static void
 test_atomic_flag(void)
 {
@@ -911,7 +910,6 @@ test_atomic_flag(void)
 
 	pg_atomic_clear_flag(&flag);
 }
-#endif							/* PG_HAVE_ATOMIC_FLAG_SIMULATION */
 
 static void
 test_atomic_uint32(void)
@@ -1094,19 +1092,7 @@ PG_FUNCTION_INFO_V1(test_atomic_ops);
 Datum
 test_atomic_ops(PG_FUNCTION_ARGS)
 {
-	/* ---
-	 * Can't run the test under the semaphore emulation, it doesn't handle
-	 * checking two edge cases well:
-	 * - pg_atomic_unlocked_test_flag() always returns true
-	 * - locking a already locked flag blocks
-	 * it seems better to not test the semaphore fallback here, than weaken
-	 * the checks for the other cases. The semaphore code will be the same
-	 * everywhere, whereas the efficient implementations wont.
-	 * ---
-	 */
-#ifndef PG_HAVE_ATOMIC_FLAG_SIMULATION
 	test_atomic_flag();
-#endif
 
 	test_atomic_uint32();