srcu: Reduce scans of srcu_data in counter wrap check

Currently, given a multi-level srcu_node tree, SRCU can scan the full
set of srcu_data structures at each level when cleaning up after a grace
period.  This, though harmless otherwise, represents pointless overhead.
This commit therefore eliminates this overhead by scanning the srcu_data
structures only when traversing the leaf srcu_node structures.

Signed-off-by: Ildar Ismagilov <devix84@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

kernel/rcu/srcutree.c

@@ -527,6 +527,7 @@ static void srcu_gp_end(struct srcu_struct *sp)
 {
 	unsigned long cbdelay;
 	bool cbs;
+	bool last_lvl;
 	int cpu;
 	unsigned long flags;
 	unsigned long gpseq;
@@ -559,7 +560,8 @@ static void srcu_gp_end(struct srcu_struct *sp)
 	rcu_for_each_node_breadth_first(sp, snp) {
 		spin_lock_irq_rcu_node(snp);
 		cbs = false;
-		if (snp >= sp->level[rcu_num_lvls - 1])
+		last_lvl = snp >= sp->level[rcu_num_lvls - 1];
+		if (last_lvl)
 			cbs = snp->srcu_have_cbs[idx] == gpseq;
 		snp->srcu_have_cbs[idx] = gpseq;
 		rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1);
@@ -572,7 +574,7 @@ static void srcu_gp_end(struct srcu_struct *sp)
 			srcu_schedule_cbs_snp(sp, snp, mask, cbdelay);
 
 		/* Occasionally prevent srcu_data counter wrap. */
-		if (!(gpseq & counter_wrap_check))
+		if (!(gpseq & counter_wrap_check) && last_lvl)
 			for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
 				sdp = per_cpu_ptr(sp->sda, cpu);
 				spin_lock_irqsave_rcu_node(sdp, flags);