rcu: Prevent rcu_barrier() from starting needless grace periods

Currently rcu_barrier() uses call_rcu() to enqueue new callbacks
on each CPU with a non-empty callback list.  This works, but means
that rcu_barrier() forces grace periods that are not otherwise needed.
The key point is that rcu_barrier() never needs to wait for a grace
period, but instead only for all pre-existing callbacks to be invoked.
This means that rcu_barrier()'s new callbacks should be placed in
the callback-list segment containing the last pre-existing callback.

This commit makes this change using the new rcu_segcblist_entrain()
function.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

include/trace/events/rcu.h

@@ -742,6 +742,7 @@ TRACE_EVENT(rcu_torture_read,
  *	"OnlineQ": _rcu_barrier() found online CPU with callbacks.
  *	"OnlineNQ": _rcu_barrier() found online CPU, no callbacks.
  *	"IRQ": An rcu_barrier_callback() callback posted on remote CPU.
+ *	"IRQNQ": An rcu_barrier_callback() callback found no callbacks.
  *	"CB": An rcu_barrier_callback() invoked a callback, not the last.
  *	"LastCB": An rcu_barrier_callback() invoked the last callback.
  *	"Inc2": _rcu_barrier() piggyback check counter incremented.

kernel/rcu/tree.c

@@ -3578,8 +3578,14 @@ static void rcu_barrier_func(void *type)
 	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
 
 	_rcu_barrier_trace(rsp, "IRQ", -1, rsp->barrier_sequence);
+	rdp->barrier_head.func = rcu_barrier_callback;
+	debug_rcu_head_queue(&rdp->barrier_head);
+	if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head, 0)) {
 		atomic_inc(&rsp->barrier_cpu_count);
-	rsp->call(&rdp->barrier_head, rcu_barrier_callback);
+	} else {
+		debug_rcu_head_unqueue(&rdp->barrier_head);
+		_rcu_barrier_trace(rsp, "IRQNQ", -1, rsp->barrier_sequence);
+	}
 }
 
 /*