1 files changed, 22 insertions, 17 deletions

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index d039b4e732a3..e41fdc38ce19 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -116,6 +116,7 @@ static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb,
 #endif
 		tb->rcv_saddr = sk->sk_rcv_saddr;
 	INIT_HLIST_HEAD(&tb->owners);
+	INIT_HLIST_HEAD(&tb->deathrow);
 	hlist_add_head(&tb->node, &head->chain);
 }
 
@@ -137,7 +138,7 @@ struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep,
 /* Caller must hold hashbucket lock for this tb with local BH disabled */
 void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb)
 {
-	if (hlist_empty(&tb->owners)) {
+	if (hlist_empty(&tb->owners) && hlist_empty(&tb->deathrow)) {
 		__hlist_del(&tb->node);
 		kmem_cache_free(cachep, tb);
 	}
@@ -649,8 +650,20 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
 	spin_lock(lock);
 	if (osk) {
 		WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
-		ret = sk_nulls_del_node_init_rcu(osk);
-	} else if (found_dup_sk) {
+		ret = sk_hashed(osk);
+		if (ret) {
+			/* Before deleting the node, we insert a new one to make
+			 * sure that the look-up-sk process would not miss either
+			 * of them and that at least one node would exist in ehash
+			 * table all the time. Otherwise there's a tiny chance
+			 * that lookup process could find nothing in ehash table.
+			 */
+			__sk_nulls_add_node_tail_rcu(sk, list);
+			sk_nulls_del_node_init_rcu(osk);
+		}
+		goto unlock;
+	}
+	if (found_dup_sk) {
 		*found_dup_sk = inet_ehash_lookup_by_sk(sk, list);
 		if (*found_dup_sk)
 			ret = false;
@@ -659,6 +672,7 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
 	if (ret)
 		__sk_nulls_add_node_rcu(sk, list);
 
+unlock:
 	spin_unlock(lock);
 
 	return ret;
@@ -994,17 +1008,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 	u32 index;
 
 	if (port) {
-		head = &hinfo->bhash[inet_bhashfn(net, port,
-						  hinfo->bhash_size)];
-		tb = inet_csk(sk)->icsk_bind_hash;
-		spin_lock_bh(&head->lock);
-		if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
-			inet_ehash_nolisten(sk, NULL, NULL);
-			spin_unlock_bh(&head->lock);
-			return 0;
-		}
-		spin_unlock(&head->lock);
-		/* No definite answer... Walk to established hash table */
+		local_bh_disable();
 		ret = check_established(death_row, sk, port, NULL);
 		local_bh_enable();
 		return ret;
@@ -1012,7 +1016,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 
 	l3mdev = inet_sk_bound_l3mdev(sk);
 
-	inet_get_local_port_range(net, &low, &high);
+	inet_sk_get_local_port_range(sk, &low, &high);
 	high++; /* [32768, 60999] -> [32768, 61000[ */
 	remaining = high - low;
 	if (likely(remaining > 1))
@@ -1103,15 +1107,16 @@ ok:
 	/* Head lock still held and bh's disabled */
 	inet_bind_hash(sk, tb, tb2, port);
 
-	spin_unlock(&head2->lock);
-
 	if (sk_unhashed(sk)) {
 		inet_sk(sk)->inet_sport = htons(port);
 		inet_ehash_nolisten(sk, (struct sock *)tw, NULL);
 	}
 	if (tw)
 		inet_twsk_bind_unhash(tw, hinfo);
+
+	spin_unlock(&head2->lock);
 	spin_unlock(&head->lock);
+
 	if (tw)
 		inet_twsk_deschedule_put(tw);
 	local_bh_enable();