linux-kernel - [PATCH v2 rcu-dev 2/3] rcu/tree: Add a shrinker to prevent OOM due to kfree

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Mon, 16 Mar 2020 12:32:27 -0400
From:   "Joel Fernandes (Google)" <joel@...lfernandes.org>
To:     linux-kernel@...r.kernel.org
Cc:     "Joel Fernandes (Google)" <joel@...lfernandes.org>,
        urezki@...il.com, Davidlohr Bueso <dave@...olabs.net>,
        Josh Triplett <josh@...htriplett.org>,
        Lai Jiangshan <jiangshanlai@...il.com>,
        Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
        "Paul E. McKenney" <paulmck@...nel.org>, rcu@...r.kernel.org,
        Steven Rostedt <rostedt@...dmis.org>
Subject: [PATCH v2 rcu-dev 2/3] rcu/tree: Add a shrinker to prevent OOM due to kfree_rcu() batching

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

Otherwise it easily OOMs with the above parameters.

NOTE:
1. On systems with no memory pressure, the patch has no effect as intended.
2. In the future, we can use this same mechanism to prevent grace periods
   from happening even more, by relying on shrinkers carefully.

Cc: urezki@...il.com
Signed-off-by: Joel Fernandes (Google) <joel@...lfernandes.org>
---
 kernel/rcu/tree.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 4a885af2ff73e..dc570dff68d7b 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2801,6 +2801,8 @@ 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);
@@ -2914,6 +2916,8 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
 				krcp->head = NULL;
 			}
 
+			krcp->count = 0;
+
 			/*
 			 * One work is per one batch, so there are two "free channels",
 			 * "bhead_free" and "head_free" the batch can handle. It can be
@@ -3050,6 +3054,8 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 		krcp->head = head;
 	}
 
+	krcp->count++;
+
 	// Set timer to drain after KFREE_DRAIN_JIFFIES.
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
 	    !krcp->monitor_todo) {
@@ -3064,6 +3070,58 @@ 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;
@@ -3981,6 +4039,8 @@ 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)
-- 
2.25.1.481.gfbce0eb801-goog