Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   "Joel Fernandes (Google)" <joel@joelfernandes.org>
To:     linux-kernel@vger.kernel.org
Cc:     "Joel Fernandes (Google)" <joel@joelfernandes.org>,
        urezki@gmail.com, Davidlohr Bueso <dave@stgolabs.net>,
        Josh Triplett <josh@joshtriplett.org>,
        Lai Jiangshan <jiangshanlai@gmail.com>,
        Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
        "Paul E. McKenney" <paulmck@kernel.org>, rcu@vger.kernel.org,
        Steven Rostedt <rostedt@goodmis.org>
Subject: [PATCH linus/master 2/2] rcu/tree: Add a shrinker to prevent OOM due to kfree_rcu() batching
Date:   Thu,  5 Mar 2020 17:13:23 -0500
Message-Id: <20200305221323.66051-2-joel@joelfernandes.org>
In-Reply-To: <20200305221323.66051-1-joel@joelfernandes.org>
References: <20200305221323.66051-1-joel@joelfernandes.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

To reduce grace periods and improve kfree() performance, we have done
batching recently dramatically bringing down the number of grace periods
while giving us the ability to use kfree_bulk() for efficient kfree'ing.

However, this has increased the likelihood of OOM condition under heavy
kfree_rcu() flood on small memory systems. This patch introduces a
shrinker which starts grace periods right away if the system is under
memory pressure due to existence of objects that have still not started
a grace period.

With this patch, I do not observe an OOM anymore on a system with 512MB
RAM and 8 CPUs, with the following rcuperf options:

rcuperf.kfree_loops=20000 rcuperf.kfree_alloc_num=8000
rcuperf.kfree_rcu_test=1 rcuperf.kfree_mult=2

NOTE:
On systems with no memory pressure, the patch has no effect as intended.

Cc: urezki@gmail.com
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>

---
 kernel/rcu/tree.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 58 insertions(+)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index d91c9156fab2e..28ec35e15529d 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2723,6 +2723,8 @@ struct kfree_rcu_cpu {
 	struct delayed_work monitor_work;
 	bool monitor_todo;
 	bool initialized;
+	// Number of objects for which GP not started
+	int count;
 };
 
 static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc);
@@ -2791,6 +2793,7 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
 
 	krwp->head_free = krcp->head;
 	krcp->head = NULL;
+	krcp->count = 0;
 	INIT_RCU_WORK(&krwp->rcu_work, kfree_rcu_work);
 	queue_rcu_work(system_wq, &krwp->rcu_work);
 	return true;
@@ -2864,6 +2867,7 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 	head->func = func;
 	head->next = krcp->head;
 	krcp->head = head;
+	krcp->count++;
 
 	// Set timer to drain after KFREE_DRAIN_JIFFIES.
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
@@ -2879,6 +2883,58 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 }
 EXPORT_SYMBOL_GPL(kfree_call_rcu);
 
+static unsigned long
+kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+	int cpu;
+	unsigned long flags, count = 0;
+
+	/* Snapshot count of all CPUs */
+	for_each_online_cpu(cpu) {
+		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+		spin_lock_irqsave(&krcp->lock, flags);
+		count += krcp->count;
+		spin_unlock_irqrestore(&krcp->lock, flags);
+	}
+
+	return count;
+}
+
+static unsigned long
+kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+	int cpu, freed = 0;
+	unsigned long flags;
+
+	for_each_online_cpu(cpu) {
+		int count;
+		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+		count = krcp->count;
+		spin_lock_irqsave(&krcp->lock, flags);
+		if (krcp->monitor_todo)
+			kfree_rcu_drain_unlock(krcp, flags);
+		else
+			spin_unlock_irqrestore(&krcp->lock, flags);
+
+		sc->nr_to_scan -= count;
+		freed += count;
+
+		if (sc->nr_to_scan <= 0)
+			break;
+	}
+
+	return freed;
+}
+
+static struct shrinker kfree_rcu_shrinker = {
+	.count_objects = kfree_rcu_shrink_count,
+	.scan_objects = kfree_rcu_shrink_scan,
+	.batch = 0,
+	.seeks = DEFAULT_SEEKS,
+};
+
 void __init kfree_rcu_scheduler_running(void)
 {
 	int cpu;
@@ -3774,6 +3830,8 @@ static void __init kfree_rcu_batch_init(void)
 		INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
 		krcp->initialized = true;
 	}
+	if (register_shrinker(&kfree_rcu_shrinker))
+		pr_err("Failed to register kfree_rcu() shrinker!\n");
 }
 
 void __init rcu_init(void)
-- 
2.25.0.265.gbab2e86ba0-goog