Message-Id: <20210308194950.12320-1-urezki@gmail.com>
Date:   Mon,  8 Mar 2021 20:49:49 +0100
From:   "Uladzislau Rezki (Sony)" <urezki@...il.com>
To:     LKML <linux-kernel@...r.kernel.org>, RCU <rcu@...r.kernel.org>,
        "Paul E . McKenney" <paulmck@...nel.org>
Cc:     Michal Hocko <mhocko@...e.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Daniel Axtens <dja@...ens.net>,
        Frederic Weisbecker <frederic@...nel.org>,
        Neeraj Upadhyay <neeraju@...eaurora.org>,
        Joel Fernandes <joel@...lfernandes.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        "Theodore Y . Ts'o" <tytso@....edu>,
        Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
        Uladzislau Rezki <urezki@...il.com>,
        Oleksiy Avramchenko <oleksiy.avramchenko@...ymobile.com>,
        Zhang Qiang <qiang.zhang@...driver.com>
Subject: [PATCH 1/2] kvfree_rcu: Release a page cache under memory pressure

From: Zhang Qiang <qiang.zhang@...driver.com>

Add a drain_page_cache() function to drain a per-cpu page cache.
The reason behind of it is a system can run into a low memory
condition, in that case a page shrinker can ask for its users
to free their caches in order to get extra memory available for
other needs in a system.

When a system hits such condition, a page cache is drained for
all CPUs in a system. Apart of that a page cache work is delayed
with 5 seconds interval until a memory pressure disappears.

Co-developed-by: Uladzislau Rezki (Sony) <urezki@...il.com>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@...il.com>
Signed-off-by: Zqiang <qiang.zhang@...driver.com>
---
 kernel/rcu/tree.c | 59 ++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 51 insertions(+), 8 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 2c9cf4df942c..9c8cfb01e9a6 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3163,7 +3163,7 @@ struct kfree_rcu_cpu {
 	bool initialized;
 	int count;
 
-	struct work_struct page_cache_work;
+	struct delayed_work page_cache_work;
 	atomic_t work_in_progress;
 	struct hrtimer hrtimer;
 
@@ -3175,6 +3175,17 @@ static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc) = {
 	.lock = __RAW_SPIN_LOCK_UNLOCKED(krc.lock),
 };
 
+// A page shrinker can ask for freeing extra pages
+// to get them available for other needs in a system.
+// Usually it happens under low memory condition, in
+// that case hold on a bit with page cache filling.
+static bool backoff_page_cache_fill;
+
+// 5 seconds delay. That is long enough to reduce
+// an interfering and racing with a shrinker where
+// the cache is drained.
+#define PAGE_CACHE_FILL_DELAY (5 * HZ)
+
 static __always_inline void
 debug_rcu_bhead_unqueue(struct kvfree_rcu_bulk_data *bhead)
 {
@@ -3229,6 +3240,26 @@ put_cached_bnode(struct kfree_rcu_cpu *krcp,
 
 }
 
+static int
+drain_page_cache(struct kfree_rcu_cpu *krcp)
+{
+	unsigned long flags;
+	struct llist_node *page_list, *pos, *n;
+	int freed = 0;
+
+	raw_spin_lock_irqsave(&krcp->lock, flags);
+	page_list = llist_del_all(&krcp->bkvcache);
+	krcp->nr_bkv_objs = 0;
+	raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+	llist_for_each_safe(pos, n, page_list) {
+		free_page((unsigned long)pos);
+		freed++;
+	}
+
+	return freed;
+}
+
 /*
  * This function is invoked in workqueue context after a grace period.
  * It frees all the objects queued on ->bhead_free or ->head_free.
@@ -3419,7 +3450,7 @@ schedule_page_work_fn(struct hrtimer *t)
 	struct kfree_rcu_cpu *krcp =
 		container_of(t, struct kfree_rcu_cpu, hrtimer);
 
-	queue_work(system_highpri_wq, &krcp->page_cache_work);
+	queue_delayed_work(system_highpri_wq, &krcp->page_cache_work, 0);
 	return HRTIMER_NORESTART;
 }
 
@@ -3428,7 +3459,7 @@ static void fill_page_cache_func(struct work_struct *work)
 	struct kvfree_rcu_bulk_data *bnode;
 	struct kfree_rcu_cpu *krcp =
 		container_of(work, struct kfree_rcu_cpu,
-			page_cache_work);
+			page_cache_work.work);
 	unsigned long flags;
 	bool pushed;
 	int i;
@@ -3457,10 +3488,14 @@ run_page_cache_worker(struct kfree_rcu_cpu *krcp)
 {
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
 			!atomic_xchg(&krcp->work_in_progress, 1)) {
-		hrtimer_init(&krcp->hrtimer, CLOCK_MONOTONIC,
-			HRTIMER_MODE_REL);
-		krcp->hrtimer.function = schedule_page_work_fn;
-		hrtimer_start(&krcp->hrtimer, 0, HRTIMER_MODE_REL);
+		if (xchg(&backoff_page_cache_fill, false)) {
+			queue_delayed_work(system_wq,
+				&krcp->page_cache_work, PAGE_CACHE_FILL_DELAY);
+		} else {
+			hrtimer_init(&krcp->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+			krcp->hrtimer.function = schedule_page_work_fn;
+			hrtimer_start(&krcp->hrtimer, 0, HRTIMER_MODE_REL);
+		}
 	}
 }
 
@@ -3612,14 +3647,20 @@ kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 {
 	int cpu;
 	unsigned long count = 0;
+	unsigned long flags;
 
 	/* Snapshot count of all CPUs */
 	for_each_possible_cpu(cpu) {
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
 
 		count += READ_ONCE(krcp->count);
+
+		raw_spin_lock_irqsave(&krcp->lock, flags);
+		count += krcp->nr_bkv_objs;
+		raw_spin_unlock_irqrestore(&krcp->lock, flags);
 	}
 
+	WRITE_ONCE(backoff_page_cache_fill, true);
 	return count;
 }
 
@@ -3634,6 +3675,8 @@ kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
 
 		count = krcp->count;
+		count += drain_page_cache(krcp);
+
 		raw_spin_lock_irqsave(&krcp->lock, flags);
 		if (krcp->monitor_todo)
 			kfree_rcu_drain_unlock(krcp, flags);
@@ -4608,7 +4651,7 @@ static void __init kfree_rcu_batch_init(void)
 		}
 
 		INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
-		INIT_WORK(&krcp->page_cache_work, fill_page_cache_func);
+		INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func);
 		krcp->initialized = true;
 	}
 	if (register_shrinker(&kfree_rcu_shrinker))
-- 
2.20.1

Powered by blists - more mailing lists