2 files changed, 60 insertions, 17 deletions

diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 025895eb6ec5..001ee5c4d962 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -218,6 +218,41 @@ static int __init inet_frag_wq_init(void)
 
 pure_initcall(inet_frag_wq_init);
 
+void fqdir_pre_exit(struct fqdir *fqdir)
+{
+	struct inet_frag_queue *fq;
+	struct rhashtable_iter hti;
+
+	/* Prevent creation of new frags.
+	 * Pairs with READ_ONCE() in inet_frag_find().
+	 */
+	WRITE_ONCE(fqdir->high_thresh, 0);
+
+	/* Pairs with READ_ONCE() in inet_frag_kill(), ip_expire()
+	 * and ip6frag_expire_frag_queue().
+	 */
+	WRITE_ONCE(fqdir->dead, true);
+
+	rhashtable_walk_enter(&fqdir->rhashtable, &hti);
+	rhashtable_walk_start(&hti);
+
+	while ((fq = rhashtable_walk_next(&hti))) {
+		if (IS_ERR(fq)) {
+			if (PTR_ERR(fq) != -EAGAIN)
+				break;
+			continue;
+		}
+		spin_lock_bh(&fq->lock);
+		if (!(fq->flags & INET_FRAG_COMPLETE))
+			inet_frag_queue_flush(fq, 0);
+		spin_unlock_bh(&fq->lock);
+	}
+
+	rhashtable_walk_stop(&hti);
+	rhashtable_walk_exit(&hti);
+}
+EXPORT_SYMBOL(fqdir_pre_exit);
+
 void fqdir_exit(struct fqdir *fqdir)
 {
 	INIT_WORK(&fqdir->destroy_work, fqdir_work_fn);
@@ -263,8 +298,8 @@ static void inet_frag_destroy_rcu(struct rcu_head *head)
 	kmem_cache_free(f->frags_cachep, q);
 }
 
-unsigned int inet_frag_rbtree_purge(struct rb_root *root,
-				    enum skb_drop_reason reason)
+static unsigned int
+inet_frag_rbtree_purge(struct rb_root *root, enum skb_drop_reason reason)
 {
 	struct rb_node *p = rb_first(root);
 	unsigned int sum = 0;
@@ -284,7 +319,17 @@ unsigned int inet_frag_rbtree_purge(struct rb_root *root,
 	}
 	return sum;
 }
-EXPORT_SYMBOL(inet_frag_rbtree_purge);
+
+void inet_frag_queue_flush(struct inet_frag_queue *q,
+			   enum skb_drop_reason reason)
+{
+	unsigned int sum;
+
+	reason = reason ?: SKB_DROP_REASON_FRAG_REASM_TIMEOUT;
+	sum = inet_frag_rbtree_purge(&q->rb_fragments, reason);
+	sub_frag_mem_limit(q->fqdir, sum);
+}
+EXPORT_SYMBOL(inet_frag_queue_flush);
 
 void inet_frag_destroy(struct inet_frag_queue *q)
 {
@@ -327,7 +372,9 @@ static struct inet_frag_queue *inet_frag_alloc(struct fqdir *fqdir,
 
 	timer_setup(&q->timer, f->frag_expire, 0);
 	spin_lock_init(&q->lock);
-	/* One reference for the timer, one for the hash table. */
+	/* One reference for the timer, one for the hash table.
+	 * We never take any extra references, only decrement this field.
+	 */
 	refcount_set(&q->refcnt, 2);
 
 	return q;
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index f7012479713b..56b0f738d2f2 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -134,11 +134,6 @@ static void ip_expire(struct timer_list *t)
 	net = qp->q.fqdir->net;
 
 	rcu_read_lock();
-
-	/* Paired with WRITE_ONCE() in fqdir_pre_exit(). */
-	if (READ_ONCE(qp->q.fqdir->dead))
-		goto out_rcu_unlock;
-
 	spin_lock(&qp->q.lock);
 
 	if (qp->q.flags & INET_FRAG_COMPLETE)
@@ -146,6 +141,13 @@ static void ip_expire(struct timer_list *t)
 
 	qp->q.flags |= INET_FRAG_DROP;
 	inet_frag_kill(&qp->q, &refs);
+
+	/* Paired with WRITE_ONCE() in fqdir_pre_exit(). */
+	if (READ_ONCE(qp->q.fqdir->dead)) {
+		inet_frag_queue_flush(&qp->q, 0);
+		goto out;
+	}
+
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
 
@@ -240,16 +242,10 @@ static int ip_frag_too_far(struct ipq *qp)
 
 static int ip_frag_reinit(struct ipq *qp)
 {
-	unsigned int sum_truesize = 0;
-
-	if (!mod_timer(&qp->q.timer, jiffies + qp->q.fqdir->timeout)) {
-		refcount_inc(&qp->q.refcnt);
+	if (!mod_timer_pending(&qp->q.timer, jiffies + qp->q.fqdir->timeout))
 		return -ETIMEDOUT;
-	}
 
-	sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments,
-					      SKB_DROP_REASON_FRAG_TOO_FAR);
-	sub_frag_mem_limit(qp->q.fqdir, sum_truesize);
+	inet_frag_queue_flush(&qp->q, SKB_DROP_REASON_FRAG_TOO_FAR);
 
 	qp->q.flags = 0;
 	qp->q.len = 0;