1 files changed, 62 insertions, 4 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a42a4693f161..37c0cd0332f8 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -175,6 +175,15 @@ module_param(gp_init_delay, int, 0444);
 static int gp_cleanup_delay;
 module_param(gp_cleanup_delay, int, 0444);
 
+/*
+ * This rcu parameter is runtime-read-only. It reflects
+ * a minimum allowed number of objects which can be cached
+ * per-CPU. Object size is equal to one page. This value
+ * can be changed at boot time.
+ */
+static int rcu_min_cached_objs = 2;
+module_param(rcu_min_cached_objs, int, 0444);
+
 /* Retrieve RCU kthreads priority for rcutorture */
 int rcu_get_gp_kthreads_prio(void)
 {
@@ -2997,7 +3006,6 @@ struct kfree_rcu_cpu_work {
  * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period
  * @head: List of kfree_rcu() objects not yet waiting for a grace period
  * @bhead: Bulk-List of kfree_rcu() objects not yet waiting for a grace period
- * @bcached: Keeps at most one object for later reuse when build chain blocks
  * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period
  * @lock: Synchronize access to this structure
  * @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES
@@ -3013,13 +3021,22 @@ struct kfree_rcu_cpu_work {
 struct kfree_rcu_cpu {
 	struct rcu_head *head;
 	struct kfree_rcu_bulk_data *bhead;
-	struct kfree_rcu_bulk_data *bcached;
 	struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES];
 	raw_spinlock_t lock;
 	struct delayed_work monitor_work;
 	bool monitor_todo;
 	bool initialized;
 	int count;
+
+	/*
+	 * A simple cache list that contains objects for
+	 * reuse purpose. 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.
+	 */
+	struct llist_head bkvcache;
+	int nr_bkv_objs;
 };
 
 static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc) = {
@@ -3056,6 +3073,31 @@ krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags)
 	local_irq_restore(flags);
 }
 
+static inline struct kfree_rcu_bulk_data *
+get_cached_bnode(struct kfree_rcu_cpu *krcp)
+{
+	if (!krcp->nr_bkv_objs)
+		return NULL;
+
+	krcp->nr_bkv_objs--;
+	return (struct kfree_rcu_bulk_data *)
+		llist_del_first(&krcp->bkvcache);
+}
+
+static inline bool
+put_cached_bnode(struct kfree_rcu_cpu *krcp,
+	struct kfree_rcu_bulk_data *bnode)
+{
+	// Check the limit.
+	if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
+		return false;
+
+	llist_add((struct llist_node *) bnode, &krcp->bkvcache);
+	krcp->nr_bkv_objs++;
+	return true;
+
+}
+
 /*
  * This function is invoked in workqueue context after a grace period.
  * It frees all the objects queued on ->bhead_free or ->head_free.
@@ -3091,7 +3133,12 @@ static void kfree_rcu_work(struct work_struct *work)
 		kfree_bulk(bhead->nr_records, bhead->records);
 		rcu_lock_release(&rcu_callback_map);
 
-		if (cmpxchg(&krcp->bcached, NULL, bhead))
+		krcp = krc_this_cpu_lock(&flags);
+		if (put_cached_bnode(krcp, bhead))
+			bhead = NULL;
+		krc_this_cpu_unlock(krcp, flags);
+
+		if (bhead)
 			free_page((unsigned long) bhead);
 
 		cond_resched_tasks_rcu_qs();
@@ -3224,7 +3271,7 @@ kfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp,
 	/* Check if a new block is required. */
 	if (!krcp->bhead ||
 			krcp->bhead->nr_records == KFREE_BULK_MAX_ENTR) {
-		bnode = xchg(&krcp->bcached, NULL);
+		bnode = get_cached_bnode(krcp);
 		if (!bnode) {
 			WARN_ON_ONCE(sizeof(struct kfree_rcu_bulk_data) > PAGE_SIZE);
 
@@ -4277,12 +4324,23 @@ static void __init kfree_rcu_batch_init(void)
 
 	for_each_possible_cpu(cpu) {
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+		struct kfree_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 kfree_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);
 		krcp->initialized = true;
 	}