Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   "Paul E. McKenney" <paulmck@kernel.org>
To:     rcu@vger.kernel.org
Cc:     linux-kernel@vger.kernel.org, kernel-team@meta.com,
        rostedt@goodmis.org, "Paul E. McKenney" <paulmck@kernel.org>,
        Ziwei Dai <ziwei.dai@unisoc.com>
Subject: [PATCH rcu 2/8] rcu/kvfree: Add debug to check grace periods
Date:   Wed, 10 May 2023 10:02:36 -0700
Message-Id: <20230510170242.2187714-2-paulmck@kernel.org>
In-Reply-To: <1c01c38f-3783-44d7-8c11-7416cd5b849c@paulmck-laptop>
References: <1c01c38f-3783-44d7-8c11-7416cd5b849c@paulmck-laptop>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

This commit adds debugging checks to verify that the required RCU
grace period has elapsed for each kvfree_rcu_bulk_data structure that
arrives at the kvfree_rcu_bulk() function.  These checks make use
of that structure's ->gp_snap field, which has been upgraded from an
unsigned long to an rcu_gp_oldstate structure.  This upgrade reduces
the chances of false positives to nearly zero, even on 32-bit systems,
for which this structure carries 64 bits of state.

Cc: Ziwei Dai <ziwei.dai@unisoc.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 kernel/rcu/tree.c | 37 +++++++++++++++++++------------------
 1 file changed, 19 insertions(+), 18 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f52ff7241041..91d75fd6c579 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2756,7 +2756,7 @@ EXPORT_SYMBOL_GPL(call_rcu);
  */
 struct kvfree_rcu_bulk_data {
 	struct list_head list;
-	unsigned long gp_snap;
+	struct rcu_gp_oldstate gp_snap;
 	unsigned long nr_records;
 	void *records[];
 };
@@ -2921,23 +2921,24 @@ kvfree_rcu_bulk(struct kfree_rcu_cpu *krcp,
 	int i;
 
 	debug_rcu_bhead_unqueue(bnode);
-
-	rcu_lock_acquire(&rcu_callback_map);
-	if (idx == 0) { // kmalloc() / kfree().
-		trace_rcu_invoke_kfree_bulk_callback(
-			rcu_state.name, bnode->nr_records,
-			bnode->records);
-
-		kfree_bulk(bnode->nr_records, bnode->records);
-	} else { // vmalloc() / vfree().
-		for (i = 0; i < bnode->nr_records; i++) {
-			trace_rcu_invoke_kvfree_callback(
-				rcu_state.name, bnode->records[i], 0);
-
-			vfree(bnode->records[i]);
+	if (!WARN_ON_ONCE(!poll_state_synchronize_rcu_full(&bnode->gp_snap))) {
+		rcu_lock_acquire(&rcu_callback_map);
+		if (idx == 0) { // kmalloc() / kfree().
+			trace_rcu_invoke_kfree_bulk_callback(
+				rcu_state.name, bnode->nr_records,
+				bnode->records);
+
+			kfree_bulk(bnode->nr_records, bnode->records);
+		} else { // vmalloc() / vfree().
+			for (i = 0; i < bnode->nr_records; i++) {
+				trace_rcu_invoke_kvfree_callback(
+					rcu_state.name, bnode->records[i], 0);
+
+				vfree(bnode->records[i]);
+			}
 		}
+		rcu_lock_release(&rcu_callback_map);
 	}
-	rcu_lock_release(&rcu_callback_map);
 
 	raw_spin_lock_irqsave(&krcp->lock, flags);
 	if (put_cached_bnode(krcp, bnode))
@@ -3081,7 +3082,7 @@ kvfree_rcu_drain_ready(struct kfree_rcu_cpu *krcp)
 		INIT_LIST_HEAD(&bulk_ready[i]);
 
 		list_for_each_entry_safe_reverse(bnode, n, &krcp->bulk_head[i], list) {
-			if (!poll_state_synchronize_rcu(bnode->gp_snap))
+			if (!poll_state_synchronize_rcu_full(&bnode->gp_snap))
 				break;
 
 			atomic_sub(bnode->nr_records, &krcp->bulk_count[i]);
@@ -3285,7 +3286,7 @@ add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp,
 
 	// Finally insert and update the GP for this page.
 	bnode->records[bnode->nr_records++] = ptr;
-	bnode->gp_snap = get_state_synchronize_rcu();
+	get_state_synchronize_rcu_full(&bnode->gp_snap);
 	atomic_inc(&(*krcp)->bulk_count[idx]);
 
 	return true;
-- 
2.40.1