[5.10,169/717] rcu/tree: Defer kvfree_rcu() allocation to a clean context

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 585bf112ee08d..593df7edfe97f 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -177,7 +177,7 @@  module_param(rcu_unlock_delay, int, 0444);
  * per-CPU. Object size is equal to one page. This value
  * can be changed at boot time.
  */
-static int rcu_min_cached_objs = 2;
+static int rcu_min_cached_objs = 5;
 module_param(rcu_min_cached_objs, int, 0444);
 
 /* Retrieve RCU kthreads priority for rcutorture */
@@ -3087,6 +3087,9 @@  struct kfree_rcu_cpu_work {
  *	In order to save some per-cpu space the list is singular.
  *	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
+ * @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
@@ -3103,6 +3106,11 @@  struct kfree_rcu_cpu {
 	bool monitor_todo;
 	bool initialized;
 	int count;
+
+	struct work_struct page_cache_work;
+	atomic_t work_in_progress;
+	struct hrtimer hrtimer;
+
 	struct llist_head bkvcache;
 	int nr_bkv_objs;
 };
@@ -3220,10 +3228,10 @@  static void kfree_rcu_work(struct work_struct *work)
 			}
 			rcu_lock_release(&rcu_callback_map);
 
-			krcp = krc_this_cpu_lock(&flags);
+			raw_spin_lock_irqsave(&krcp->lock, flags);
 			if (put_cached_bnode(krcp, bkvhead[i]))
 				bkvhead[i] = NULL;
-			krc_this_cpu_unlock(krcp, flags);
+			raw_spin_unlock_irqrestore(&krcp->lock, flags);
 
 			if (bkvhead[i])
 				free_page((unsigned long) bkvhead[i]);
@@ -3350,6 +3358,57 @@  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);
+	unsigned long flags;
+	bool pushed;
+	int i;
+
+	for (i = 0; i < rcu_min_cached_objs; i++) {
+		bnode = (struct kvfree_rcu_bulk_data *)
+			__get_free_page(GFP_KERNEL | __GFP_NOWARN);
+
+		if (bnode) {
+			raw_spin_lock_irqsave(&krcp->lock, flags);
+			pushed = put_cached_bnode(krcp, bnode);
+			raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+			if (!pushed) {
+				free_page((unsigned long) bnode);
+				break;
+			}
+		}
+	}
+
+	atomic_set(&krcp->work_in_progress, 0);
+}
+
+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);
+	}
+}
+
 static inline bool
 kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
 {
@@ -3366,32 +3425,8 @@  kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
 	if (!krcp->bkvhead[idx] ||
 			krcp->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
 		bnode = get_cached_bnode(krcp);
-		if (!bnode) {
-			/*
-			 * To keep this path working on raw non-preemptible
-			 * sections, prevent the optional entry into the
-			 * allocator as it uses sleeping locks. In fact, even
-			 * if the caller of kfree_rcu() is preemptible, this
-			 * path still is not, as krcp->lock is a raw spinlock.
-			 * With additional page pre-allocation in the works,
-			 * hitting this return is going to be much less likely.
-			 */
-			if (IS_ENABLED(CONFIG_PREEMPT_RT))
-				return false;
-
-			/*
-			 * NOTE: For one argument of kvfree_rcu() we can
-			 * drop the lock and get the page in sleepable
-			 * context. That would allow to maintain an array
-			 * for the CONFIG_PREEMPT_RT as well if no cached
-			 * pages are available.
-			 */
-			bnode = (struct kvfree_rcu_bulk_data *)
-				__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
-		}
-
 		/* Switch to emergency path. */
-		if (unlikely(!bnode))
+		if (!bnode)
 			return false;
 
 		/* Initialize the new block. */
@@ -3455,12 +3490,10 @@  void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 		goto unlock_return;
 	}
 
-	/*
-	 * Under high memory pressure GFP_NOWAIT can fail,
-	 * in that case the emergency path is maintained.
-	 */
 	success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr);
 	if (!success) {
+		run_page_cache_worker(krcp);
+
 		if (head == NULL)
 			// Inline if kvfree_rcu(one_arg) call.
 			goto unlock_return;
@@ -4452,24 +4485,14 @@  static void __init kfree_rcu_batch_init(void)
 
 	for_each_possible_cpu(cpu) {
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
-		struct kvfree_rcu_bulk_data *bnode;
 
 		for (i = 0; i < KFREE_N_BATCHES; i++) {
 			INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work);
 			krcp->krw_arr[i].krcp = krcp;
 		}
 
-		for (i = 0; i < rcu_min_cached_objs; i++) {
-			bnode = (struct kvfree_rcu_bulk_data *)
-				__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
-
-			if (bnode)
-				put_cached_bnode(krcp, bnode);
-			else
-				pr_err("Failed to preallocate for %d CPU!\n", cpu);
-		}
-
 		INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
+		INIT_WORK(&krcp->page_cache_work, fill_page_cache_func);
 		krcp->initialized = true;
 	}
 	if (register_shrinker(&kfree_rcu_shrinker))