rcu/kvfree: Move need_offload_krc() out of krcp->lock

The need_offload_krc() function currently holds the krcp->lock in order
to safely check krcp->head.  This commit removes the need for this lock
in that function by updating the krcp->head pointer using WRITE_ONCE()
macro so that readers can carry out lockless loads of that pointer.

Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

Author: urezki

kernel/rcu/tree.c

@@ -3194,7 +3194,7 @@ static void kfree_rcu_monitor(struct work_struct *work)
 			// objects queued on the linked list.
 			if (!krwp->head_free) {
 				krwp->head_free = krcp->head;
-				krcp->head = NULL;
+				WRITE_ONCE(krcp->head, NULL);
 			}
 
 			WRITE_ONCE(krcp->count, 0);
@@ -3208,15 +3208,15 @@ static void kfree_rcu_monitor(struct work_struct *work)
 		}
 	}
 
+	raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
 	// If there is nothing to detach, it means that our job is
 	// successfully done here. In case of having at least one
 	// of the channels that is still busy we should rearm the
 	// work to repeat an attempt. Because previous batches are
 	// still in progress.
 	if (need_offload_krc(krcp))
 		schedule_delayed_monitor_work(krcp);
-
-	raw_spin_unlock_irqrestore(&krcp->lock, flags);
 }
 
 static enum hrtimer_restart
@@ -3386,7 +3386,7 @@ void kvfree_call_rcu(struct rcu_head *head, void *ptr)
 
 		head->func = ptr;
 		head->next = krcp->head;
-		krcp->head = head;
+		WRITE_ONCE(krcp->head, head);
 		success = true;
 	}
 
@@ -3463,15 +3463,12 @@ static struct shrinker kfree_rcu_shrinker = {
 void __init kfree_rcu_scheduler_running(void)
 {
 	int cpu;
-	unsigned long flags;
 
 	for_each_possible_cpu(cpu) {
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
 
-		raw_spin_lock_irqsave(&krcp->lock, flags);
 		if (need_offload_krc(krcp))
 			schedule_delayed_monitor_work(krcp);
-		raw_spin_unlock_irqrestore(&krcp->lock, flags);
 	}
 }