rcu/tree: Make debug_objects logic independent of rcu_head

kfree_rcu()'s debug_objects logic uses the address of the object's
embedded rcu_head to queue/unqueue. Instead of this, make use of the
object's address itself as preparation for future headless kfree_rcu()
support.

Reviewed-by: Uladzislau Rezki <urezki@gmail.com>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

kernel/rcu/tree.c

@@ -2970,13 +2970,11 @@ EXPORT_SYMBOL_GPL(call_rcu);
  * @nr_records: Number of active pointers in the array
  * @records: Array of the kfree_rcu() pointers
  * @next: Next bulk object in the block chain
- * @head_free_debug: For debug, when CONFIG_DEBUG_OBJECTS_RCU_HEAD is set
  */
 struct kfree_rcu_bulk_data {
 	unsigned long nr_records;
 	void *records[KFREE_BULK_MAX_ENTR];
 	struct kfree_rcu_bulk_data *next;
-	struct rcu_head *head_free_debug;
 };
 
 /**
@@ -3026,11 +3024,13 @@ struct kfree_rcu_cpu {
 static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc);
 
 static __always_inline void
-debug_rcu_head_unqueue_bulk(struct rcu_head *head)
+debug_rcu_bhead_unqueue(struct kfree_rcu_bulk_data *bhead)
 {
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
-	for (; head; head = head->next)
-		debug_rcu_head_unqueue(head);
+	int i;
+
+	for (i = 0; i < bhead->nr_records; i++)
+		debug_rcu_head_unqueue((struct rcu_head *)(bhead->records[i]));
 #endif
 }
 
@@ -3060,7 +3060,7 @@ static void kfree_rcu_work(struct work_struct *work)
 	for (; bhead; bhead = bnext) {
 		bnext = bhead->next;
 
-		debug_rcu_head_unqueue_bulk(bhead->head_free_debug);
+		debug_rcu_bhead_unqueue(bhead);
 
 		rcu_lock_acquire(&rcu_callback_map);
 		trace_rcu_invoke_kfree_bulk_callback(rcu_state.name,
@@ -3082,14 +3082,15 @@ static void kfree_rcu_work(struct work_struct *work)
 	 */
 	for (; head; head = next) {
 		unsigned long offset = (unsigned long)head->func;
+		void *ptr = (void *)head - offset;
 
 		next = head->next;
-		debug_rcu_head_unqueue(head);
+		debug_rcu_head_unqueue((struct rcu_head *)ptr);
 		rcu_lock_acquire(&rcu_callback_map);
 		trace_rcu_invoke_kfree_callback(rcu_state.name, head, offset);
 
 		if (!WARN_ON_ONCE(!__is_kfree_rcu_offset(offset)))
-			kfree((void *)head - offset);
+			kfree(ptr);
 
 		rcu_lock_release(&rcu_callback_map);
 		cond_resched_tasks_rcu_qs();
@@ -3228,18 +3229,11 @@ kfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp,
 		/* Initialize the new block. */
 		bnode->nr_records = 0;
 		bnode->next = krcp->bhead;
-		bnode->head_free_debug = NULL;
 
 		/* Attach it to the head. */
 		krcp->bhead = bnode;
 	}
 
-#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
-	head->func = func;
-	head->next = krcp->bhead->head_free_debug;
-	krcp->bhead->head_free_debug = head;
-#endif
-
 	/* Finally insert. */
 	krcp->bhead->records[krcp->bhead->nr_records++] =
 		(void *) head - (unsigned long) func;
@@ -3263,14 +3257,17 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
 	unsigned long flags;
 	struct kfree_rcu_cpu *krcp;
+	void *ptr;
 
 	local_irq_save(flags);	// For safely calling this_cpu_ptr().
 	krcp = this_cpu_ptr(&krc);
 	if (krcp->initialized)
 		raw_spin_lock(&krcp->lock);
 
+	ptr = (void *)head - (unsigned long)func;
+
 	// Queue the object but don't yet schedule the batch.
-	if (debug_rcu_head_queue(head)) {
+	if (debug_rcu_head_queue(ptr)) {
 		// Probable double kfree_rcu(), just leak.
 		WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n",
 			  __func__, head);