Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   "Joel Fernandes (Google)" <joel@joelfernandes.org>
To:     rcu@vger.kernel.org
Cc:     linux-kernel@vger.kernel.org, rushikesh.s.kadam@intel.com,
        urezki@gmail.com, neeraj.iitr10@gmail.com, frederic@kernel.org,
        paulmck@kernel.org, rostedt@goodmis.org, vineeth@bitbyteword.org,
        Joel Fernandes <joel@joelfernandes.org>
Subject: [PATCH v2 2/8] rcu: shrinker for lazy rcu
Date:   Wed, 22 Jun 2022 22:50:56 +0000
Message-Id: <20220622225102.2112026-4-joel@joelfernandes.org>
In-Reply-To: <20220622225102.2112026-1-joel@joelfernandes.org>
References: <20220622225102.2112026-1-joel@joelfernandes.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Vineeth Pillai <vineeth@bitbyteword.org>

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>
---
 kernel/rcu/rcu_segcblist.h | 14 +++++++++--
 kernel/rcu/tree_nocb.h     | 48 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 60 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
index c3d7de65b689..cf71425dbb5e 100644
--- a/kernel/rcu/rcu_segcblist.h
+++ b/kernel/rcu/rcu_segcblist.h
@@ -15,16 +15,26 @@ static inline long rcu_cblist_n_cbs(struct rcu_cblist *rclp)
 	return READ_ONCE(rclp->len);
 }
 
+#ifdef CONFIG_RCU_LAZY
 /* Return number of callbacks in the specified callback list. */
 static inline long rcu_cblist_n_lazy_cbs(struct rcu_cblist *rclp)
 {
-#ifdef CONFIG_RCU_LAZY
 	return READ_ONCE(rclp->lazy_len);
+}
+
+static inline void rcu_cblist_reset_lazy_len(struct rcu_cblist *rclp)
+{
+	WRITE_ONCE(rclp->lazy_len, 0);
+}
 #else
+static inline long rcu_cblist_n_lazy_cbs(struct rcu_cblist *rclp)
+{
 	return 0;
-#endif
 }
 
+static inline void rcu_cblist_reset_lazy_len(struct rcu_cblist *rclp) {}
+#endif
+
 /* Return number of callbacks in segmented callback list by summing seglen. */
 long rcu_segcblist_n_segment_cbs(struct rcu_segcblist *rsclp);
 
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index b9244f22e102..2f5da12811a5 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -1207,6 +1207,51 @@ 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 += rcu_cblist_n_lazy_cbs(&rdp->nocb_bypass);
+	}
+
+	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 = rcu_cblist_n_lazy_cbs(&rdp->nocb_bypass);
+		if (_count == 0)
+			continue;
+		rcu_nocb_lock_irqsave(rdp, flags);
+		rcu_cblist_reset_lazy_len(&rdp->nocb_bypass);
+		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;
@@ -1244,6 +1289,9 @@ void __init rcu_init_nohz(void)
 	if (!rcu_state.nocb_is_setup)
 		return;
 
+	if (register_shrinker(&lazy_rcu_shrinker))
+		pr_err("Failed to register lazy_rcu shrinker!\n");
+
 #if defined(CONFIG_NO_HZ_FULL)
 	if (tick_nohz_full_running)
 		cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
-- 
2.37.0.rc0.104.g0611611a94-goog