rcutorture: Make rcu_torture_barrier_cbs() post from corresponding CPU

Currently, rcu_torture_barrier_cbs() posts callbacks from whatever CPU
it is running on, which means that all these kthreads might well be
posting from the same CPU, which would drastically reduce the effectiveness
of this test.  This commit therefore uses IPIs to make the callbacks be
posted from the corresponding CPU (given by local variable myid).

If the IPI fails (which can happen if the target CPU is offline or does
not exist at all), the callback is posted on whatever CPU is currently
running.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

kernel/rcu/rcutorture.c

@@ -2053,6 +2053,14 @@ static void rcu_torture_barrier_cbf(struct rcu_head *rcu)
 	atomic_inc(&barrier_cbs_invoked);
 }
 
+/* IPI handler to get callback posted on desired CPU, if online. */
+static void rcu_torture_barrier1cb(void *rcu_void)
+{
+	struct rcu_head *rhp = rcu_void;
+
+	cur_ops->call(rhp, rcu_torture_barrier_cbf);
+}
+
 /* kthread function to register callbacks used to test RCU barriers. */
 static int rcu_torture_barrier_cbs(void *arg)
 {
@@ -2076,9 +2084,11 @@ static int rcu_torture_barrier_cbs(void *arg)
 		 * The above smp_load_acquire() ensures barrier_phase load
 		 * is ordered before the following ->call().
 		 */
-		local_irq_disable(); /* Just to test no-irq call_rcu(). */
+		if (smp_call_function_single(myid, rcu_torture_barrier1cb,
+					     &rcu, 1)) {
+			// IPI failed, so use direct call from current CPU.
 			cur_ops->call(&rcu, rcu_torture_barrier_cbf);
-		local_irq_enable();
+		}
 		if (atomic_dec_and_test(&barrier_cbs_count))
 			wake_up(&barrier_wq);
 	} while (!torture_must_stop());