rcu: Shrinker for lazy rcu

The shrinker is used to speed up the free'ing of memory potentially held
by RCU lazy callbacks. RCU kernel module test cases show this to be
effective. Test is introduced in a later patch.
Signed-off-by: Vineeth Pillai <vineeth@bitbyteword.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

kernel/rcu/tree_nocb.h

@@ -1312,6 +1312,55 @@ int rcu_nocb_cpu_offload(int cpu)
 }
 EXPORT_SYMBOL_GPL(rcu_nocb_cpu_offload);
 
+static unsigned long
+lazy_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+	int cpu;
+	unsigned long count = 0;
+
+	/* Snapshot count of all CPUs */
+	for_each_possible_cpu(cpu) {
+		struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+
+		count +=  READ_ONCE(rdp->lazy_len);
+	}
+
+	return count ? count : SHRINK_EMPTY;
+}
+
+static unsigned long
+lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+	int cpu;
+	unsigned long flags;
+	unsigned long count = 0;
+
+	/* Snapshot count of all CPUs */
+	for_each_possible_cpu(cpu) {
+		struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+		int _count = READ_ONCE(rdp->lazy_len);
+
+		if (_count == 0)
+			continue;
+		rcu_nocb_lock_irqsave(rdp, flags);
+		WRITE_ONCE(rdp->lazy_len, 0);
+		rcu_nocb_unlock_irqrestore(rdp, flags);
+		wake_nocb_gp(rdp, false);
+		sc->nr_to_scan -= _count;
+		count += _count;
+		if (sc->nr_to_scan <= 0)
+			break;
+	}
+	return count ? count : SHRINK_STOP;
+}
+
+static struct shrinker lazy_rcu_shrinker = {
+	.count_objects = lazy_rcu_shrink_count,
+	.scan_objects = lazy_rcu_shrink_scan,
+	.batch = 0,
+	.seeks = DEFAULT_SEEKS,
+};
+
 void __init rcu_init_nohz(void)
 {
 	int cpu;
@@ -1342,6 +1391,9 @@ void __init rcu_init_nohz(void)
 	if (!rcu_state.nocb_is_setup)
 		return;
 
+	if (register_shrinker(&lazy_rcu_shrinker, "rcu-lazy"))
+		pr_err("Failed to register lazy_rcu shrinker!\n");
+
 	if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
 		pr_info("\tNote: kernel parameter 'rcu_nocbs=', 'nohz_full', or 'isolcpus=' contains nonexistent CPUs.\n");
 		cpumask_and(rcu_nocb_mask, cpu_possible_mask,