[RFC] Simplify debug_objects handling in kfree_rcu

["Joel Fernandes (Google)" <joel@joelfernandes.org>]

In order to prepare for future changes to headless RCU support, make the
debug_objects handling in kfree_rcu use the final 'pointer' value of the
object, instead of depending on the head.

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
---
Paul, Vlad, I am adding this to my rcu/kfree tree for further testing. Let me know any
comments. I have only build-tested this patch.

 kernel/rcu/tree.c | 30 +++++++++++++-----------------
 1 file changed, 13 insertions(+), 17 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 32152be9a09ac..0e2632622176b 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2758,7 +2758,6 @@ 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;
 };
 
 /**
@@ -2808,11 +2807,11 @@ 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);
+	for (int i = 0; i < bhead->nr_records; i++)
+		debug_rcu_head_unqueue((struct rcu_head *)(bhead->records[i]));
 #endif
 }
 
@@ -2842,7 +2841,7 @@ 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,
@@ -2864,14 +2863,15 @@ 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_kvfree_callback(rcu_state.name, head, offset);
 
 		if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset)))
-			kvfree((void *)head - offset);
+			kvfree(ptr);
 
 		rcu_lock_release(&rcu_callback_map);
 		cond_resched_tasks_rcu_qs();
@@ -2995,18 +2995,11 @@ 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;
@@ -3030,14 +3023,17 @@ void kvfree_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)
 		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);
@@ -3054,8 +3050,8 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 	 * Under high memory pressure GFP_NOWAIT can fail,
 	 * in that case the emergency path is maintained.
 	 */
-	if (is_vmalloc_addr((void *) head - (unsigned long) func) ||
-			!kfree_call_rcu_add_ptr_to_bulk(krcp, head, func)) {
+	if (is_vmalloc_addr(ptr) ||
+	    !kfree_call_rcu_add_ptr_to_bulk(krcp, head, func)) {
 		head->func = func;
 		head->next = krcp->head;
 		krcp->head = head;
-- 
2.25.1.481.gfbce0eb801-goog