testsuite: pthread: call sched_yield for non-preemptive targets

Systems without preemptive multi-threading require sched_yield calls
to be placed at points in which a context switch might be needed to
enable the test to complete.


for  gcc/testsuite/ChangeLog

	* gcc.dg/atomic/c11-atomic-exec-4.c: Call sched_yield.
	* gcc.dg/atomic/c11-atomic-exec-5.c: Likewise.
	* gcc.dg/atomic/pr80640-2.c: Likewise.
	* gcc.dg/atomic/pr80640.c: Likewise.
	* gcc.dg/atomic/pr81316.c: Likewise.
	* gcc.dg/di-sync-multithread.c: Likewise.

gcc/testsuite/gcc.dg/atomic/c11-atomic-exec-4.c

@@ -32,7 +32,10 @@ test_thread_##NAME (void *arg)						\
 {									\
   thread_ready = true;							\
   for (int i = 0; i < ITER_COUNT; i++)					\
-    PRE var_##NAME POST;						\
+    {									\
+      sched_yield ();							\
+      PRE var_##NAME POST;						\
+    }									\
   return NULL;								\
 }									\
 									\
@@ -49,9 +52,12 @@ test_main_##NAME (void)							\
       return 1;								\
     }									\
   while (!thread_ready)							\
-    ;									\
+    sched_yield ();							\
   for (int i = 0; i < ITER_COUNT; i++)					\
-    PRE var_##NAME POST;						\
+    {									\
+      PRE var_##NAME POST;						\
+      sched_yield ();							\
+    }									\
   pthread_join (thread_id, NULL);					\
   if (var_##NAME != (FINAL))						\
     {									\

gcc/testsuite/gcc.dg/atomic/c11-atomic-exec-5.c

@@ -53,8 +53,11 @@ test_thread_##NAME (void *arg)						\
   thread_ready = true;							\
   while (!thread_stop)							\
     {									\
+      sched_yield ();							\
       var_##NAME = (INIT1);						\
+      sched_yield ();							\
       var_##NAME = (INIT2);						\
+      sched_yield ();							\
     }									\
   return NULL;								\
 }									\
@@ -75,13 +78,14 @@ test_main_##NAME (void)							\
     }									\
   int num_1_pass = 0, num_1_fail = 0, num_2_pass = 0, num_2_fail = 0;	\
   while (!thread_ready)							\
-    ;									\
+    sched_yield ();							\
   for (int i = 0; i < ITER_COUNT; i++)					\
     {									\
       feclearexcept (FE_ALL_EXCEPT);					\
       feraiseexcept (BEXC);						\
       LHSTYPE r = (PRE var_##NAME POST);				\
       int rexc = fetestexcept (TEST_ALL_EXCEPT);			\
+      sched_yield ();							\
       if (VALTEST1 (r))							\
 	{								\
 	  if (rexc == ((BEXC) | (EXC1)))				\

gcc/testsuite/gcc.dg/atomic/pr80640-2.c

@@ -12,7 +12,8 @@ static void *f(void *va)
   void **p = va;
   if (*p) return *p;
   sem1 = 1;
-  while (!__atomic_load_n(&sem2, __ATOMIC_ACQUIRE));
+  while (!__atomic_load_n(&sem2, __ATOMIC_ACQUIRE))
+    sched_yield ();
   // GCC used to RTL-CSE this and the first load, causing 0 to be returned
   return *p;
 }
@@ -23,7 +24,8 @@ int main()
   pthread_t thr;
   if (pthread_create(&thr, 0, f, &p))
     return 2;
-  while (!sem1);
+  while (!sem1)
+    sched_yield ();
   __atomic_thread_fence(__ATOMIC_ACQUIRE);
   p = &p;
   __atomic_store_n(&sem2, 1, __ATOMIC_RELEASE);

gcc/testsuite/gcc.dg/atomic/pr80640.c

@@ -12,7 +12,8 @@ static void *f(void *va)
   void **p = va;
   if (*p) return *p;
   sem1 = 1;
-  while (!sem2);
+  while (!sem2)
+    sched_yield ();
   __atomic_thread_fence(__ATOMIC_ACQUIRE);
   // GCC used to RTL-CSE this and the first load, causing 0 to be returned
   return *p;
@@ -24,7 +25,8 @@ int main()
   pthread_t thr;
   if (pthread_create(&thr, 0, f, &p))
     return 2;
-  while (!sem1);
+  while (!sem1)
+    sched_yield ();
   __atomic_thread_fence(__ATOMIC_ACQUIRE);
   p = &p;
   __atomic_thread_fence(__ATOMIC_RELEASE);

gcc/testsuite/gcc.dg/atomic/pr81316.c

@@ -10,7 +10,8 @@ static _Atomic int sem1;
 static void *f(void *va)
 {
   void **p = va;
-  while (!__atomic_load_n(&sem1, __ATOMIC_ACQUIRE));
+  while (!__atomic_load_n(&sem1, __ATOMIC_ACQUIRE))
+    sched_yield ();
   exit(!*p);
 }
 
@@ -24,6 +25,10 @@ int main(int argc)
   p = &p;
   __atomic_store_n(&sem1, 1, __ATOMIC_RELEASE);
   int r = -1;
-  while (r < 0) asm("":"+r"(r));
+  while (r < 0)
+    {
+      sched_yield ();
+      asm("":"+r"(r));
+    }
   return r;
 }

gcc/testsuite/gcc.dg/di-sync-multithread.c

@@ -70,6 +70,8 @@ worker (void* data)
          case this to carry across the 32bit boundary.  */
       for (tmp2 = 0; tmp2 < 64; tmp2++)
 	{
+	  sched_yield ();
+
 	  /* Add 2 using the two different adds.  */
 	  tmp1 = __sync_add_and_fetch (&workspace, add1bit);
 	  tmp3 = __sync_fetch_and_add (&workspace, add1bit);
@@ -103,6 +105,8 @@ worker (void* data)
 
       for (tmp2 = 0; tmp2 < 64; tmp2++)
 	{
+	  sched_yield ();
+
 	  /* Subtract 2 using the two different subs.  */
 	  tmp1=__sync_sub_and_fetch (&workspace, add1bit);
 	  tmp3=__sync_fetch_and_sub (&workspace, add1bit);
@@ -178,6 +182,8 @@ main ()
 	t, err);
   };
 
+  sched_yield ();
+
 #ifdef _WIN32
   Sleep (5000);
 #else
@@ -187,6 +193,8 @@ main ()
   /* Stop please.  */
   __sync_lock_test_and_set (&doquit, 1ll);
 
+  sched_yield ();
+
   for (t = 0; t < 3; t++)
     {
       err=pthread_join (threads[t], NULL);