[PATCH 4/4] rcu/nocb: Make shrinker to iterate only NOCB CPUs

[Frederic Weisbecker <frederic@kernel.org>]

Callbacks can only be queued as lazy on NOCB CPUs, therefore iterating
over the NOCB mask is enough for both counting and scanning. Just lock
the mostly uncontended barrier mutex on counting as well in order to
keep rcu_nocb_mask stable.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
 kernel/rcu/tree_nocb.h | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index dfa9c10d6727..43229d2b0c44 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -1319,13 +1319,22 @@ lazy_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 	int cpu;
 	unsigned long count = 0;
 
+	if (WARN_ON_ONCE(!cpumask_available(rcu_nocb_mask)))
+		return 0;
+
+	/*  Protect rcu_nocb_mask against concurrent (de-)offloading. */
+	if (!mutex_trylock(&rcu_state.barrier_mutex))
+		return 0;
+
 	/* Snapshot count of all CPUs */
-	for_each_possible_cpu(cpu) {
+	for_each_cpu(cpu, rcu_nocb_mask) {
 		struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 
 		count +=  READ_ONCE(rdp->lazy_len);
 	}
 
+	mutex_unlock(&rcu_state.barrier_mutex);
+
 	return count ? count : SHRINK_EMPTY;
 }
 
@@ -1336,6 +1345,8 @@ lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	unsigned long flags;
 	unsigned long count = 0;
 
+	if (WARN_ON_ONCE(!cpumask_available(rcu_nocb_mask)))
+		return 0;
 	/*
 	 * Protect against concurrent (de-)offloading. Otherwise nocb locking
 	 * may be ignored or imbalanced.
@@ -1351,11 +1362,11 @@ lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	}
 
 	/* Snapshot count of all CPUs */
-	for_each_possible_cpu(cpu) {
+	for_each_cpu(cpu, rcu_nocb_mask) {
 		struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 		int _count;
 
-		if (!rcu_rdp_is_offloaded(rdp))
+		if (WARN_ON_ONCE(!rcu_rdp_is_offloaded(rdp)))
 			continue;
 
 		if (!READ_ONCE(rdp->lazy_len))
-- 
2.34.1