[PATCH v2 1/5] kvfree_rcu: Release a page cache under memory pressure

["Uladzislau Rezki (Sony)" <urezki@gmail.com>]

From: Zhang Qiang <qiang.zhang@windriver.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. By default a page cache work is delayed
with 5 seconds interval until a memory pressure disappears, if
needed it can be changed. See a rcu_delay_page_cache_fill_msec
module parameter.

Co-developed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Zqiang <qiang.zhang@windriver.com>
---
 .../admin-guide/kernel-parameters.txt         |  5 ++
 kernel/rcu/tree.c                             | 82 +++++++++++++++++--
 2 files changed, 78 insertions(+), 9 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 78dc87435ca7..6b769f5cf14c 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4154,6 +4154,11 @@
 			whole algorithm to behave better in low memory
 			condition.
 
+	rcutree.rcu_delay_page_cache_fill_msec= [KNL]
+			Set delay for a page-cache refill when a low memory
+			condition occurs. That is in milliseconds. Allowed
+			value is within a 0:100000 range.
+
 	rcutree.jiffies_till_first_fqs= [KNL]
 			Set delay from grace-period initialization to
 			first attempt to force quiescent states.
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 2c9cf4df942c..742152d6b952 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -186,6 +186,17 @@ module_param(rcu_unlock_delay, int, 0444);
 static int rcu_min_cached_objs = 5;
 module_param(rcu_min_cached_objs, int, 0444);
 
+// 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 we should hold on
+// a bit with page cache filling.
+//
+// Default value is 5 seconds. That is long enough to reduce
+// an interfering and racing with a shrinker where the cache
+// is drained.
+static int rcu_delay_page_cache_fill_msec = 5000;
+module_param(rcu_delay_page_cache_fill_msec, int, 0444);
+
 /* Retrieve RCU kthreads priority for rcutorture */
 int rcu_get_gp_kthreads_prio(void)
 {
@@ -3144,6 +3155,7 @@ struct kfree_rcu_cpu_work {
  *	Even though it is lockless an access has to be protected by the
  *	per-cpu lock.
  * @page_cache_work: A work to refill the cache when it is empty
+ * @backoff_page_cache_fill: Delay a cache filling
  * @work_in_progress: Indicates that page_cache_work is running
  * @hrtimer: A hrtimer for scheduling a page_cache_work
  * @nr_bkv_objs: number of allocated objects at @bkvcache.
@@ -3163,7 +3175,8 @@ struct kfree_rcu_cpu {
 	bool initialized;
 	int count;
 
-	struct work_struct page_cache_work;
+	struct delayed_work page_cache_work;
+	atomic_t backoff_page_cache_fill;
 	atomic_t work_in_progress;
 	struct hrtimer hrtimer;
 
@@ -3229,6 +3242,26 @@ 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 +3452,7 @@ 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;
 }
 
@@ -3428,12 +3461,16 @@ 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;
+	int nr_pages;
 	bool pushed;
 	int i;
 
-	for (i = 0; i < rcu_min_cached_objs; i++) {
+	nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
+		1 : rcu_min_cached_objs;
+
+	for (i = 0; i < nr_pages; i++) {
 		bnode = (struct kvfree_rcu_bulk_data *)
 			__get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
 
@@ -3450,6 +3487,7 @@ static void fill_page_cache_func(struct work_struct *work)
 	}
 
 	atomic_set(&krcp->work_in_progress, 0);
+	atomic_set(&krcp->backoff_page_cache_fill, 0);
 }
 
 static void
@@ -3457,10 +3495,15 @@ 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 (atomic_read(&krcp->backoff_page_cache_fill)) {
+			queue_delayed_work(system_wq,
+				&krcp->page_cache_work,
+					msecs_to_jiffies(rcu_delay_page_cache_fill_msec));
+		} 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);
+		}
 	}
 }
 
@@ -3612,12 +3655,19 @@ 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);
+
+		atomic_set(&krcp->backoff_page_cache_fill, 1);
 	}
 
 	return count;
@@ -3634,6 +3684,8 @@ 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);
@@ -4599,6 +4651,18 @@ static void __init kfree_rcu_batch_init(void)
 	int cpu;
 	int i;
 
+	/* Clamp it to [0:100] seconds interval. */
+	if (rcu_delay_page_cache_fill_msec < 0 ||
+		rcu_delay_page_cache_fill_msec > 100 * MSEC_PER_SEC) {
+
+		rcu_delay_page_cache_fill_msec =
+			clamp(rcu_delay_page_cache_fill_msec, 0,
+				(int) (100 * MSEC_PER_SEC));
+
+		pr_info("Adjusting a cache fill delay interval to %d ms.\n",
+			rcu_delay_page_cache_fill_msec);
+	}
+
 	for_each_possible_cpu(cpu) {
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
 
@@ -4608,7 +4672,7 @@ 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