[PATCH 16/16] rcu/tree: Use delayed work instead of hrtimer to refill the cache

[Uladzislau Rezki (Sony)]

A CONFIG_PREEMPT_COUNT is unconditionally enabled, thus a page
can be obtained directly from a kvfree_rcu() path. To distinguish
that and take a decision the preemptable() macro is used when it
is save to enter allocator.

It means that refilling a cache is not important from timing point
of view. Switch to a delayed work, so the actual work is queued from
the timer interrupt with 1 jiffy delay. An immediate placing a task
on a current CPU can lead to rq->lock double lock. That is why a
delayed method is in place.

Signed-off-by: Uladzislau Rezki (Sony) <urezki@xxxxxxxxx>
---
 kernel/rcu/tree.c | 26 +++++---------------------
 1 file changed, 5 insertions(+), 21 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 3f9b016a44dc..9ea55f800b4b 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3086,7 +3086,6 @@ struct kfree_rcu_cpu_work {
  *	per-cpu lock.
  * @page_cache_work: A work to refill the cache when it is empty
  * @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.
  *
  * This is a per-CPU structure.  The reason that it is not included in
@@ -3104,9 +3103,8 @@ 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;
 
 	struct llist_head bkvcache;
 	int nr_bkv_objs;
@@ -3355,22 +3353,12 @@ static void kfree_rcu_monitor(struct work_struct *work)
 		raw_spin_unlock_irqrestore(&krcp->lock, flags);
 }
 
-static enum hrtimer_restart
-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);
-	return HRTIMER_NORESTART;
-}
-
 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;
@@ -3398,12 +3386,8 @@ static void
 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);
-	}
+			!atomic_xchg(&krcp->work_in_progress, 1))
+		schedule_delayed_work(&krcp->page_cache_work, 1);
 }
 
 // Record ptr in a page managed by krcp, with the pre-krc_this_cpu_lock()
@@ -4503,7 +4487,7 @@ 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