net: ipv4: add second dif to inet socket lookups

Add a second device index, sdif, to inet socket lookups. sdif is the
index for ingress devices enslaved to an l3mdev. It allows the lookups
to consider the enslaved device as well as the L3 domain when searching
for a socket.

TCP moves the data in the cb. Prior to tcp_v4_rcv (e.g., early demux) the
ingress index is obtained from IPCB using inet_sdif and after the cb move
in  tcp_v4_rcv the tcp_v4_sdif helper is used.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/ipv4/inet_hashtables.c

@@ -170,7 +170,7 @@ EXPORT_SYMBOL_GPL(__inet_inherit_port);
 
 static inline int compute_score(struct sock *sk, struct net *net,
 				const unsigned short hnum, const __be32 daddr,
-				const int dif, bool exact_dif)
+				const int dif, const int sdif, bool exact_dif)
 {
 	int score = -1;
 	struct inet_sock *inet = inet_sk(sk);
@@ -185,9 +185,13 @@ static inline int compute_score(struct sock *sk, struct net *net,
 			score += 4;
 		}
 		if (sk->sk_bound_dev_if || exact_dif) {
-			if (sk->sk_bound_dev_if != dif)
+			bool dev_match = (sk->sk_bound_dev_if == dif ||
+					  sk->sk_bound_dev_if == sdif);
+
+			if (exact_dif && !dev_match)
 				return -1;
-			score += 4;
+			if (sk->sk_bound_dev_if && dev_match)
+				score += 4;
 		}
 		if (sk->sk_incoming_cpu == raw_smp_processor_id())
 			score++;
@@ -208,7 +212,7 @@ struct sock *__inet_lookup_listener(struct net *net,
 				    struct sk_buff *skb, int doff,
 				    const __be32 saddr, __be16 sport,
 				    const __be32 daddr, const unsigned short hnum,
-				    const int dif)
+				    const int dif, const int sdif)
 {
 	unsigned int hash = inet_lhashfn(net, hnum);
 	struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
@@ -218,7 +222,8 @@ struct sock *__inet_lookup_listener(struct net *net,
 	u32 phash = 0;
 
 	sk_for_each_rcu(sk, &ilb->head) {
-		score = compute_score(sk, net, hnum, daddr, dif, exact_dif);
+		score = compute_score(sk, net, hnum, daddr,
+				      dif, sdif, exact_dif);
 		if (score > hiscore) {
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
@@ -268,7 +273,7 @@ struct sock *__inet_lookup_established(struct net *net,
 				  struct inet_hashinfo *hashinfo,
 				  const __be32 saddr, const __be16 sport,
 				  const __be32 daddr, const u16 hnum,
-				  const int dif)
+				  const int dif, const int sdif)
 {
 	INET_ADDR_COOKIE(acookie, saddr, daddr);
 	const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
@@ -286,11 +291,12 @@ begin:
 		if (sk->sk_hash != hash)
 			continue;
 		if (likely(INET_MATCH(sk, net, acookie,
-				      saddr, daddr, ports, dif))) {
+				      saddr, daddr, ports, dif, sdif))) {
 			if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
 				goto out;
 			if (unlikely(!INET_MATCH(sk, net, acookie,
-						 saddr, daddr, ports, dif))) {
+						 saddr, daddr, ports,
+						 dif, sdif))) {
 				sock_gen_put(sk);
 				goto begin;
 			}
@@ -321,9 +327,10 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 	__be32 daddr = inet->inet_rcv_saddr;
 	__be32 saddr = inet->inet_daddr;
 	int dif = sk->sk_bound_dev_if;
+	struct net *net = sock_net(sk);
+	int sdif = l3mdev_master_ifindex_by_index(net, dif);
 	INET_ADDR_COOKIE(acookie, saddr, daddr);
 	const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
-	struct net *net = sock_net(sk);
 	unsigned int hash = inet_ehashfn(net, daddr, lport,
 					 saddr, inet->inet_dport);
 	struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
@@ -339,7 +346,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 			continue;
 
 		if (likely(INET_MATCH(sk2, net, acookie,
-					 saddr, daddr, ports, dif))) {
+					 saddr, daddr, ports, dif, sdif))) {
 			if (sk2->sk_state == TCP_TIME_WAIT) {
 				tw = inet_twsk(sk2);
 				if (twsk_unique(sk, sk2, twp))

net/ipv4/tcp_ipv4.c

@@ -383,7 +383,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 
 	sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr,
 				       th->dest, iph->saddr, ntohs(th->source),
-				       inet_iif(icmp_skb));
+				       inet_iif(icmp_skb), 0);
 	if (!sk) {
 		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
 		return;
@@ -659,7 +659,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 		sk1 = __inet_lookup_listener(net, &tcp_hashinfo, NULL, 0,
 					     ip_hdr(skb)->saddr,
 					     th->source, ip_hdr(skb)->daddr,
-					     ntohs(th->source), inet_iif(skb));
+					     ntohs(th->source), inet_iif(skb),
+					     tcp_v4_sdif(skb));
 		/* don't send rst if it can't find key */
 		if (!sk1)
 			goto out;
@@ -1523,7 +1524,7 @@ void tcp_v4_early_demux(struct sk_buff *skb)
 	sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
 				       iph->saddr, th->source,
 				       iph->daddr, ntohs(th->dest),
-				       skb->skb_iif);
+				       skb->skb_iif, inet_sdif(skb));
 	if (sk) {
 		skb->sk = sk;
 		skb->destructor = sock_edemux;
@@ -1588,6 +1589,7 @@ EXPORT_SYMBOL(tcp_filter);
 int tcp_v4_rcv(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
+	int sdif = inet_sdif(skb);
 	const struct iphdr *iph;
 	const struct tcphdr *th;
 	bool refcounted;
@@ -1638,7 +1640,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
 
 lookup:
 	sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source,
-			       th->dest, &refcounted);
+			       th->dest, sdif, &refcounted);
 	if (!sk)
 		goto no_tcp_socket;
 
@@ -1766,7 +1768,8 @@ do_time_wait:
 							__tcp_hdrlen(th),
 							iph->saddr, th->source,
 							iph->daddr, th->dest,
-							inet_iif(skb));
+							inet_iif(skb),
+							sdif);
 		if (sk2) {
 			inet_twsk_deschedule_put(inet_twsk(sk));
 			sk = sk2;

net/ipv4/udp.c

@@ -2196,7 +2196,7 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
 static struct sock *__udp4_lib_demux_lookup(struct net *net,
 					    __be16 loc_port, __be32 loc_addr,
 					    __be16 rmt_port, __be32 rmt_addr,
-					    int dif)
+					    int dif, int sdif)
 {
 	unsigned short hnum = ntohs(loc_port);
 	unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum);
@@ -2208,7 +2208,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
 
 	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
 		if (INET_MATCH(sk, net, acookie, rmt_addr,
-			       loc_addr, ports, dif))
+			       loc_addr, ports, dif, sdif))
 			return sk;
 		/* Only check first socket in chain */
 		break;
@@ -2254,7 +2254,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
 						   dif, sdif);
 	} else if (skb->pkt_type == PACKET_HOST) {
 		sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
-					     uh->source, iph->saddr, dif);
+					     uh->source, iph->saddr, dif, sdif);
 	}
 
 	if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt))