diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 1ce2d6b8f0c3..984192160e9b 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -92,7 +92,31 @@ static inline void rcu_virt_note_context_switch(int cpu)
 }
 
 /*
- * Return the number of grace periods.
+ * Return the number of grace periods started.
+ */
+static inline unsigned long rcu_batches_started(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of bottom-half grace periods started.
+ */
+static inline unsigned long rcu_batches_started_bh(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of sched grace periods started.
+ */
+static inline unsigned long rcu_batches_started_sched(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of grace periods completed.
  */
 static inline unsigned long rcu_batches_completed(void)
 {
@@ -100,7 +124,7 @@ static inline unsigned long rcu_batches_completed(void)
 }
 
 /*
- * Return the number of bottom-half grace periods.
+ * Return the number of bottom-half grace periods completed.
  */
 static inline unsigned long rcu_batches_completed_bh(void)
 {
@@ -108,7 +132,7 @@ static inline unsigned long rcu_batches_completed_bh(void)
 }
 
 /*
- * Return the number of sched grace periods.
+ * Return the number of sched grace periods completed.
  */
 static inline unsigned long rcu_batches_completed_sched(void)
 {
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 9885bfb6b123..c0dd124e69ec 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -81,6 +81,9 @@ void cond_synchronize_rcu(unsigned long oldstate);
 
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
+unsigned long rcu_batches_started(void);
+unsigned long rcu_batches_started_bh(void);
+unsigned long rcu_batches_started_sched(void);
 unsigned long rcu_batches_completed(void);
 unsigned long rcu_batches_completed_bh(void);
 unsigned long rcu_batches_completed_sched(void);
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index aadbc072ccf4..24142c200901 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -244,6 +244,7 @@ struct rcu_torture_ops {
 	int (*readlock)(void);
 	void (*read_delay)(struct torture_random_state *rrsp);
 	void (*readunlock)(int idx);
+	unsigned long (*started)(void);
 	unsigned long (*completed)(void);
 	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
@@ -372,6 +373,7 @@ static struct rcu_torture_ops rcu_ops = {
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,
 	.readunlock	= rcu_torture_read_unlock,
+	.started	= rcu_batches_started,
 	.completed	= rcu_batches_completed,
 	.deferred_free	= rcu_torture_deferred_free,
 	.sync		= synchronize_rcu,
@@ -413,6 +415,7 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.readlock	= rcu_bh_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_bh_torture_read_unlock,
+	.started	= rcu_batches_started_bh,
 	.completed	= rcu_batches_completed_bh,
 	.deferred_free	= rcu_bh_torture_deferred_free,
 	.sync		= synchronize_rcu_bh,
@@ -456,6 +459,7 @@ static struct rcu_torture_ops rcu_busted_ops = {
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_torture_read_unlock,
+	.started	= rcu_no_completed,
 	.completed	= rcu_no_completed,
 	.deferred_free	= rcu_busted_torture_deferred_free,
 	.sync		= synchronize_rcu_busted,
@@ -554,6 +558,7 @@ static struct rcu_torture_ops srcu_ops = {
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock,
+	.started	= NULL,
 	.completed	= srcu_torture_completed,
 	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
@@ -590,6 +595,7 @@ static struct rcu_torture_ops sched_ops = {
 	.readlock	= sched_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= sched_torture_read_unlock,
+	.started	= rcu_batches_started_sched,
 	.completed	= rcu_batches_completed_sched,
 	.deferred_free	= rcu_sched_torture_deferred_free,
 	.sync		= synchronize_sched,
@@ -628,6 +634,7 @@ static struct rcu_torture_ops tasks_ops = {
 	.readlock	= tasks_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= tasks_torture_read_unlock,
+	.started	= rcu_no_completed,
 	.completed	= rcu_no_completed,
 	.deferred_free	= rcu_tasks_torture_deferred_free,
 	.sync		= synchronize_rcu_tasks,
@@ -1005,8 +1012,8 @@ static void rcutorture_trace_dump(void)
 static void rcu_torture_timer(unsigned long unused)
 {
 	int idx;
+	unsigned long started;
 	unsigned long completed;
-	unsigned long completed_end;
 	static DEFINE_TORTURE_RANDOM(rand);
 	static DEFINE_SPINLOCK(rand_lock);
 	struct rcu_torture *p;
@@ -1014,7 +1021,10 @@ static void rcu_torture_timer(unsigned long unused)
 	unsigned long long ts;
 
 	idx = cur_ops->readlock();
-	completed = cur_ops->completed();
+	if (cur_ops->started)
+		started = cur_ops->started();
+	else
+		started = cur_ops->completed();
 	ts = rcu_trace_clock_local();
 	p = rcu_dereference_check(rcu_torture_current,
 				  rcu_read_lock_bh_held() ||
@@ -1037,14 +1047,16 @@ static void rcu_torture_timer(unsigned long unused)
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
 	}
-	completed_end = cur_ops->completed();
+	completed = cur_ops->completed();
 	if (pipe_count > 1) {
 		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts,
-					  completed, completed_end);
+					  started, completed);
 		rcutorture_trace_dump();
 	}
 	__this_cpu_inc(rcu_torture_count[pipe_count]);
-	completed = completed_end - completed;
+	completed = completed - started;
+	if (cur_ops->started)
+		completed++;
 	if (completed > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		completed = RCU_TORTURE_PIPE_LEN;
@@ -1063,8 +1075,8 @@ static void rcu_torture_timer(unsigned long unused)
 static int
 rcu_torture_reader(void *arg)
 {
+	unsigned long started;
 	unsigned long completed;
-	unsigned long completed_end;
 	int idx;
 	DEFINE_TORTURE_RANDOM(rand);
 	struct rcu_torture *p;
@@ -1083,7 +1095,10 @@ rcu_torture_reader(void *arg)
 				mod_timer(&t, jiffies + 1);
 		}
 		idx = cur_ops->readlock();
-		completed = cur_ops->completed();
+		if (cur_ops->started)
+			started = cur_ops->started();
+		else
+			started = cur_ops->completed();
 		ts = rcu_trace_clock_local();
 		p = rcu_dereference_check(rcu_torture_current,
 					  rcu_read_lock_bh_held() ||
@@ -1104,14 +1119,16 @@ rcu_torture_reader(void *arg)
 			/* Should not happen, but... */
 			pipe_count = RCU_TORTURE_PIPE_LEN;
 		}
-		completed_end = cur_ops->completed();
+		completed = cur_ops->completed();
 		if (pipe_count > 1) {
 			do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
-						  ts, completed, completed_end);
+						  ts, started, completed);
 			rcutorture_trace_dump();
 		}
 		__this_cpu_inc(rcu_torture_count[pipe_count]);
-		completed = completed_end - completed;
+		completed = completed - started;
+		if (cur_ops->started)
+			completed++;
 		if (completed > RCU_TORTURE_PIPE_LEN) {
 			/* Should not happen, but... */
 			completed = RCU_TORTURE_PIPE_LEN;
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index e26d78712e16..c0faad51ae87 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -315,7 +315,43 @@ static void force_quiescent_state(struct rcu_state *rsp);
 static int rcu_pending(void);
 
 /*
- * Return the number of RCU-sched batches processed thus far for debug & stats.
+ * Return the number of RCU batches started thus far for debug & stats.
+ */
+unsigned long rcu_batches_started(void)
+{
+	return rcu_state_p->gpnum;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_started);
+
+/*
+ * Return the number of RCU-sched batches started thus far for debug & stats.
+ */
+unsigned long rcu_batches_started_sched(void)
+{
+	return rcu_sched_state.gpnum;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_started_sched);
+
+/*
+ * Return the number of RCU BH batches started thus far for debug & stats.
+ */
+unsigned long rcu_batches_started_bh(void)
+{
+	return rcu_bh_state.gpnum;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_started_bh);
+
+/*
+ * Return the number of RCU batches completed thus far for debug & stats.
+ */
+unsigned long rcu_batches_completed(void)
+{
+	return rcu_state_p->completed;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_completed);
+
+/*
+ * Return the number of RCU-sched batches completed thus far for debug & stats.
  */
 unsigned long rcu_batches_completed_sched(void)
 {
@@ -324,7 +360,7 @@ unsigned long rcu_batches_completed_sched(void)
 EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
 
 /*
- * Return the number of RCU BH batches processed thus far for debug & stats.
+ * Return the number of RCU BH batches completed thus far for debug & stats.
  */
 unsigned long rcu_batches_completed_bh(void)
 {
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index f69300d4a51f..07e61a04de1d 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -113,25 +113,6 @@ static void __init rcu_bootup_announce(void)
 	rcu_bootup_announce_oddness();
 }
 
-/*
- * Return the number of RCU-preempt batches processed thus far
- * for debug and statistics.
- */
-static unsigned long rcu_batches_completed_preempt(void)
-{
-	return rcu_preempt_state.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed_preempt);
-
-/*
- * Return the number of RCU batches processed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed(void)
-{
-	return rcu_batches_completed_preempt();
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
-
 /*
  * Record a preemptible-RCU quiescent state for the specified CPU.  Note
  * that this just means that the task currently running on the CPU is
@@ -932,15 +913,6 @@ static void __init rcu_bootup_announce(void)
 	rcu_bootup_announce_oddness();
 }
 
-/*
- * Return the number of RCU batches processed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed(void)
-{
-	return rcu_batches_completed_sched();
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
-
 /*
  * Because preemptible RCU does not exist, we never have to check for
  * CPUs being in quiescent states.