tcp/dccp: fix possible race __inet_lookup_established()

commit 8dbd76e79a16b45b2ccb01d2f2e08dbf64e71e40 upstream.

Michal Kubecek and Firo Yang did a very nice analysis of crashes
happening in __inet_lookup_established().

Since a TCP socket can go from TCP_ESTABLISH to TCP_LISTEN
(via a close()/socket()/listen() cycle) without a RCU grace period,
I should not have changed listeners linkage in their hash table.

They must use the nulls protocol (Documentation/RCU/rculist_nulls.txt),
so that a lookup can detect a socket in a hash list was moved in
another one.

Since we added code in commit d296ba60d8e2 ("soreuseport: Resolve
merge conflict for v4/v6 ordering fix"), we have to add
hlist_nulls_add_tail_rcu() helper.

Fixes: 3b24d854cb35 ("tcp/dccp: do not touch listener sk_refcnt under synflood")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Michal Kubecek <mkubecek@suse.cz>
Reported-by: Firo Yang <firo.yang@suse.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Link: https://lore.kernel.org/netdev/20191120083919.GH27852@unicorn.suse.cz/
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
[stable-4.9: we also need to update code in __inet_lookup_listener() and
 inet6_lookup_listener() which has been removed in 5.0-rc1.]
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 15 insertions, 13 deletions

diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index e4d16fc5bbb3..4273576e1475 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -868,12 +868,13 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
 
 		for (i = s_i; i < INET_LHTABLE_SIZE; i++) {
 			struct inet_listen_hashbucket *ilb;
+			struct hlist_nulls_node *node;
 			struct sock *sk;
 
 			num = 0;
 			ilb = &hashinfo->listening_hash[i];
 			spin_lock_bh(&ilb->lock);
-			sk_for_each(sk, &ilb->head) {
+			sk_nulls_for_each(sk, node, &ilb->nulls_head) {
 				struct inet_sock *inet = inet_sk(sk);
 
 				if (!net_eq(sock_net(sk), net))
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index b9bcf3db3af9..4bf542f4d980 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -218,9 +218,10 @@ struct sock *__inet_lookup_listener(struct net *net,
 	int score, hiscore = 0, matches = 0, reuseport = 0;
 	bool exact_dif = inet_exact_dif_match(net, skb);
 	struct sock *sk, *result = NULL;
+	struct hlist_nulls_node *node;
 	u32 phash = 0;
 
-	sk_for_each_rcu(sk, &ilb->head) {
+	sk_nulls_for_each_rcu(sk, node, &ilb->nulls_head) {
 		score = compute_score(sk, net, hnum, daddr, dif, exact_dif);
 		if (score > hiscore) {
 			reuseport = sk->sk_reuseport;
@@ -441,10 +442,11 @@ static int inet_reuseport_add_sock(struct sock *sk,
 						     bool match_wildcard))
 {
 	struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash;
+	const struct hlist_nulls_node *node;
 	struct sock *sk2;
 	kuid_t uid = sock_i_uid(sk);
 
-	sk_for_each_rcu(sk2, &ilb->head) {
+	sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) {
 		if (sk2 != sk &&
 		    sk2->sk_family == sk->sk_family &&
 		    ipv6_only_sock(sk2) == ipv6_only_sock(sk) &&
@@ -482,9 +484,9 @@ int __inet_hash(struct sock *sk, struct sock *osk,
 	}
 	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
 		sk->sk_family == AF_INET6)
-		hlist_add_tail_rcu(&sk->sk_node, &ilb->head);
+		__sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head);
 	else
-		hlist_add_head_rcu(&sk->sk_node, &ilb->head);
+		__sk_nulls_add_node_rcu(sk, &ilb->nulls_head);
 	sock_set_flag(sk, SOCK_RCU_FREE);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
 unlock:
@@ -527,10 +529,7 @@ void inet_unhash(struct sock *sk)
 	spin_lock_bh(lock);
 	if (rcu_access_pointer(sk->sk_reuseport_cb))
 		reuseport_detach_sock(sk);
-	if (listener)
-		done = __sk_del_node_init(sk);
-	else
-		done = __sk_nulls_del_node_init_rcu(sk);
+	done = __sk_nulls_del_node_init_rcu(sk);
 	if (done)
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 	spin_unlock_bh(lock);
@@ -666,7 +665,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h)
 
 	for (i = 0; i < INET_LHTABLE_SIZE; i++) {
 		spin_lock_init(&h->listening_hash[i].lock);
-		INIT_HLIST_HEAD(&h->listening_hash[i].head);
+		INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head,
+				      i + LISTENING_NULLS_BASE);
 	}
 }
 EXPORT_SYMBOL_GPL(inet_hashinfo_init);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cced424e1176..e1cf810140b0 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1917,13 +1917,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
 	struct inet_listen_hashbucket *ilb;
+	struct hlist_nulls_node *node;
 	struct sock *sk = cur;
 
 	if (!sk) {
 get_head:
 		ilb = &tcp_hashinfo.listening_hash[st->bucket];
 		spin_lock_bh(&ilb->lock);
-		sk = sk_head(&ilb->head);
+		sk = sk_nulls_head(&ilb->nulls_head);
 		st->offset = 0;
 		goto get_sk;
 	}
@@ -1931,9 +1932,9 @@ get_head:
 	++st->num;
 	++st->offset;
 
-	sk = sk_next(sk);
+	sk = sk_nulls_next(sk);
 get_sk:
-	sk_for_each_from(sk) {
+	sk_nulls_for_each_from(sk, node) {
 		if (!net_eq(sock_net(sk), net))
 			continue;
 		if (sk->sk_family == st->family)