Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

tools/lib/bpf/ringbuf.c
  927cbb478adf ("libbpf: Handle size overflow for ringbuf mmap")
  b486d19a0ab0 ("libbpf: checkpatch: Fixed code alignments in ringbuf.c")
https://lore.kernel.org/all/20221121122707.44d1446a@canb.auug.org.au/

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

9 files changed, 98 insertions, 47 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 5b4d86701822..ab4a06be489b 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1230,7 +1230,6 @@ EXPORT_SYMBOL(inet_unregister_protosw);
 
 static int inet_sk_reselect_saddr(struct sock *sk)
 {
-	struct inet_bind_hashbucket *prev_addr_hashbucket;
 	struct inet_sock *inet = inet_sk(sk);
 	__be32 old_saddr = inet->inet_saddr;
 	__be32 daddr = inet->inet_daddr;
@@ -1260,16 +1259,8 @@ static int inet_sk_reselect_saddr(struct sock *sk)
 		return 0;
 	}
 
-	prev_addr_hashbucket =
-		inet_bhashfn_portaddr(tcp_or_dccp_get_hashinfo(sk), sk,
-				      sock_net(sk), inet->inet_num);
-
-	inet->inet_saddr = inet->inet_rcv_saddr = new_saddr;
-
-	err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk);
+	err = inet_bhash2_update_saddr(sk, &new_saddr, AF_INET);
 	if (err) {
-		inet->inet_saddr = old_saddr;
-		inet->inet_rcv_saddr = old_saddr;
 		ip_rt_put(rt);
 		return err;
 	}
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 170152772d33..3969fa805679 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -314,6 +314,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features_
 			xo->seq.low += skb_shinfo(skb)->gso_segs;
 	}
 
+	if (xo->seq.low < seq)
+		xo->seq.hi++;
+
 	esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32));
 
 	ip_hdr(skb)->tot_len = htons(skb->len);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index f721c308248b..19a662003eef 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -888,9 +888,11 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
 		return 1;
 	}
 
-	/* cannot match on nexthop object attributes */
-	if (fi->nh)
-		return 1;
+	if (fi->nh) {
+		if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_mp)
+			return 1;
+		return 0;
+	}
 
 	if (cfg->fc_oif || cfg->fc_gw_family) {
 		struct fib_nh *nh;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 452ff177e4da..74d403dbd2b4 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -126,7 +126,7 @@ struct key_vector {
 		/* This list pointer if valid if (pos | bits) == 0 (LEAF) */
 		struct hlist_head leaf;
 		/* This array is valid if (pos | bits) > 0 (TNODE) */
-		struct key_vector __rcu *tnode[0];
+		DECLARE_FLEX_ARRAY(struct key_vector __rcu *, tnode);
 	};
 };
 
@@ -1381,8 +1381,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
 
 	/* The alias was already inserted, so the node must exist. */
 	l = l ? l : fib_find_node(t, &tp, key);
-	if (WARN_ON_ONCE(!l))
+	if (WARN_ON_ONCE(!l)) {
+		err = -ENOENT;
 		goto out_free_new_fa;
+	}
 
 	if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) ==
 	    new_fa) {
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 033bf3c2538f..3cec471a2cd2 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -858,34 +858,80 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in
 	return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)];
 }
 
-int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk)
+static void inet_update_saddr(struct sock *sk, void *saddr, int family)
+{
+	if (family == AF_INET) {
+		inet_sk(sk)->inet_saddr = *(__be32 *)saddr;
+		sk_rcv_saddr_set(sk, inet_sk(sk)->inet_saddr);
+	}
+#if IS_ENABLED(CONFIG_IPV6)
+	else {
+		sk->sk_v6_rcv_saddr = *(struct in6_addr *)saddr;
+	}
+#endif
+}
+
+static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset)
 {
 	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
+	struct inet_bind_hashbucket *head, *head2;
 	struct inet_bind2_bucket *tb2, *new_tb2;
 	int l3mdev = inet_sk_bound_l3mdev(sk);
-	struct inet_bind_hashbucket *head2;
 	int port = inet_sk(sk)->inet_num;
 	struct net *net = sock_net(sk);
+	int bhash;
+
+	if (!inet_csk(sk)->icsk_bind2_hash) {
+		/* Not bind()ed before. */
+		if (reset)
+			inet_reset_saddr(sk);
+		else
+			inet_update_saddr(sk, saddr, family);
+
+		return 0;
+	}
 
 	/* Allocate a bind2 bucket ahead of time to avoid permanently putting
 	 * the bhash2 table in an inconsistent state if a new tb2 bucket
 	 * allocation fails.
 	 */
 	new_tb2 = kmem_cache_alloc(hinfo->bind2_bucket_cachep, GFP_ATOMIC);
-	if (!new_tb2)
+	if (!new_tb2) {
+		if (reset) {
+			/* The (INADDR_ANY, port) bucket might have already
+			 * been freed, then we cannot fixup icsk_bind2_hash,
+			 * so we give up and unlink sk from bhash/bhash2 not
+			 * to leave inconsistency in bhash2.
+			 */
+			inet_put_port(sk);
+			inet_reset_saddr(sk);
+		}
+
 		return -ENOMEM;
+	}
 
+	bhash = inet_bhashfn(net, port, hinfo->bhash_size);
+	head = &hinfo->bhash[bhash];
 	head2 = inet_bhashfn_portaddr(hinfo, sk, net, port);
 
-	if (prev_saddr) {
-		spin_lock_bh(&prev_saddr->lock);
-		__sk_del_bind2_node(sk);
-		inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep,
-					  inet_csk(sk)->icsk_bind2_hash);
-		spin_unlock_bh(&prev_saddr->lock);
-	}
+	/* If we change saddr locklessly, another thread
+	 * iterating over bhash might see corrupted address.
+	 */
+	spin_lock_bh(&head->lock);
 
-	spin_lock_bh(&head2->lock);
+	spin_lock(&head2->lock);
+	__sk_del_bind2_node(sk);
+	inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash);
+	spin_unlock(&head2->lock);
+
+	if (reset)
+		inet_reset_saddr(sk);
+	else
+		inet_update_saddr(sk, saddr, family);
+
+	head2 = inet_bhashfn_portaddr(hinfo, sk, net, port);
+
+	spin_lock(&head2->lock);
 	tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk);
 	if (!tb2) {
 		tb2 = new_tb2;
@@ -893,15 +939,29 @@ int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct soc
 	}
 	sk_add_bind2_node(sk, &tb2->owners);
 	inet_csk(sk)->icsk_bind2_hash = tb2;
-	spin_unlock_bh(&head2->lock);
+	spin_unlock(&head2->lock);
+
+	spin_unlock_bh(&head->lock);
 
 	if (tb2 != new_tb2)
 		kmem_cache_free(hinfo->bind2_bucket_cachep, new_tb2);
 
 	return 0;
 }
+
+int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family)
+{
+	return __inet_bhash2_update_saddr(sk, saddr, family, false);
+}
 EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr);
 
+void inet_bhash2_reset_saddr(struct sock *sk)
+{
+	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
+		__inet_bhash2_update_saddr(sk, NULL, 0, true);
+}
+EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr);
+
 /* RFC 6056 3.3.4.  Algorithm 4: Double-Hash Port Selection Algorithm
  * Note that we use 32bit integers (vs RFC 'short integers')
  * because 2^16 is not a multiple of num_ephemeral and this
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 1b512390b3cf..e880ce77322a 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -366,6 +366,11 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 					   iph->tos, dev);
 		if (unlikely(err))
 			goto drop_error;
+	} else {
+		struct in_device *in_dev = __in_dev_get_rcu(dev);
+
+		if (in_dev && IN_DEV_ORCONF(in_dev, NOPOLICY))
+			IPCB(skb)->flags |= IPSKB_NOPOLICY;
 	}
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index f8e176c77d1c..b3cc416ed292 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -435,7 +435,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
 
 	switch (ctinfo) {
 	case IP_CT_NEW:
-		ct->mark = hash;
+		WRITE_ONCE(ct->mark, hash);
 		break;
 	case IP_CT_RELATED:
 	case IP_CT_RELATED_REPLY:
@@ -452,7 +452,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
 #ifdef DEBUG
 	nf_ct_dump_tuple_ip(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
 #endif
-	pr_debug("hash=%u ct_hash=%u ", hash, ct->mark);
+	pr_debug("hash=%u ct_hash=%u ", hash, READ_ONCE(ct->mark));
 	if (!clusterip_responsible(cipinfo->config, hash)) {
 		pr_debug("not responsible\n");
 		return NF_DROP;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4a69c5fcfedc..24602a5184b0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3114,8 +3114,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	inet->inet_dport = 0;
 
-	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
-		inet_reset_saddr(sk);
+	inet_bhash2_reset_saddr(sk);
 
 	sk->sk_shutdown = 0;
 	sock_reset_flag(sk, SOCK_DONE);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f0343538d1f8..1215fa4c1b9f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -199,15 +199,14 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr,
 /* This will initiate an outgoing connection. */
 int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
-	struct inet_bind_hashbucket *prev_addr_hashbucket = NULL;
 	struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
 	struct inet_timewait_death_row *tcp_death_row;
-	__be32 daddr, nexthop, prev_sk_rcv_saddr;
 	struct inet_sock *inet = inet_sk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct ip_options_rcu *inet_opt;
 	struct net *net = sock_net(sk);
 	__be16 orig_sport, orig_dport;
+	__be32 daddr, nexthop;
 	struct flowi4 *fl4;
 	struct rtable *rt;
 	int err;
@@ -251,24 +250,13 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
 
 	if (!inet->inet_saddr) {
-		if (inet_csk(sk)->icsk_bind2_hash) {
-			prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo,
-								     sk, net, inet->inet_num);
-			prev_sk_rcv_saddr = sk->sk_rcv_saddr;
-		}
-		inet->inet_saddr = fl4->saddr;
-	}
-
-	sk_rcv_saddr_set(sk, inet->inet_saddr);
-
-	if (prev_addr_hashbucket) {
-		err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk);
+		err = inet_bhash2_update_saddr(sk,  &fl4->saddr, AF_INET);
 		if (err) {
-			inet->inet_saddr = 0;
-			sk_rcv_saddr_set(sk, prev_sk_rcv_saddr);
 			ip_rt_put(rt);
 			return err;
 		}
+	} else {
+		sk_rcv_saddr_set(sk, inet->inet_saddr);
 	}
 
 	if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) {
@@ -343,6 +331,7 @@ failure:
 	 * if necessary.
 	 */
 	tcp_set_state(sk, TCP_CLOSE);
+	inet_bhash2_reset_saddr(sk);
 	ip_rt_put(rt);
 	sk->sk_route_caps = 0;
 	inet->inet_dport = 0;