net: ipv6: add second dif to udp socket lookups

Add a second device index, sdif, to udp 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.

Early demux lookups are handled in the next patch as part of INET_MATCH
changes.

Signed-off-by: David Ahern <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: dsahern

include/linux/ipv6.h

@@ -158,6 +158,16 @@ static inline bool inet6_is_jumbogram(const struct sk_buff *skb)
 	return !!(IP6CB(skb)->flags & IP6SKB_JUMBOGRAM);
 }
 
+/* can not be used in TCP layer after tcp_v6_fill_cb */
+static inline int inet6_sdif(const struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	if (skb && ipv6_l3mdev_skb(IP6CB(skb)->flags))
+		return IP6CB(skb)->iif;
+#endif
+	return 0;
+}
+
 /* can not be used in TCP layer after tcp_v6_fill_cb */
 static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb)
 {

include/net/udp.h

@@ -298,7 +298,7 @@ struct sock *udp6_lib_lookup(struct net *net,
 struct sock *__udp6_lib_lookup(struct net *net,
 			       const struct in6_addr *saddr, __be16 sport,
 			       const struct in6_addr *daddr, __be16 dport,
-			       int dif, struct udp_table *tbl,
+			       int dif, int sdif, struct udp_table *tbl,
 			       struct sk_buff *skb);
 struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
 				 __be16 sport, __be16 dport);

net/ipv4/udp_diag.c

@@ -53,7 +53,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
 				req->id.idiag_sport,
 				(struct in6_addr *)req->id.idiag_dst,
 				req->id.idiag_dport,
-				req->id.idiag_if, tbl, NULL);
+				req->id.idiag_if, 0, tbl, NULL);
 #endif
 	if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
 		sk = NULL;
@@ -198,7 +198,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb,
 					req->id.idiag_dport,
 					(struct in6_addr *)req->id.idiag_src,
 					req->id.idiag_sport,
-					req->id.idiag_if, tbl, NULL);
+					req->id.idiag_if, 0, tbl, NULL);
 	}
 #endif
 	else {

net/ipv6/udp.c

@@ -129,7 +129,7 @@ static void udp_v6_rehash(struct sock *sk)
 static int compute_score(struct sock *sk, struct net *net,
 			 const struct in6_addr *saddr, __be16 sport,
 			 const struct in6_addr *daddr, unsigned short hnum,
-			 int dif, bool exact_dif)
+			 int dif, int sdif, bool exact_dif)
 {
 	int score;
 	struct inet_sock *inet;
@@ -161,9 +161,13 @@ static int compute_score(struct sock *sk, struct net *net,
 	}
 
 	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++;
+		if (sk->sk_bound_dev_if && dev_match)
+			score++;
 	}
 
 	if (sk->sk_incoming_cpu == raw_smp_processor_id())
@@ -175,9 +179,9 @@ static int compute_score(struct sock *sk, struct net *net,
 /* called with rcu_read_lock() */
 static struct sock *udp6_lib_lookup2(struct net *net,
 		const struct in6_addr *saddr, __be16 sport,
-		const struct in6_addr *daddr, unsigned int hnum, int dif,
-		bool exact_dif, struct udp_hslot *hslot2,
-		struct sk_buff *skb)
+		const struct in6_addr *daddr, unsigned int hnum,
+		int dif, int sdif, bool exact_dif,
+		struct udp_hslot *hslot2, struct sk_buff *skb)
 {
 	struct sock *sk, *result;
 	int score, badness, matches = 0, reuseport = 0;
@@ -187,7 +191,7 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 	badness = -1;
 	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
 		score = compute_score(sk, net, saddr, sport,
-				      daddr, hnum, dif, exact_dif);
+				      daddr, hnum, dif, sdif, exact_dif);
 		if (score > badness) {
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
@@ -214,10 +218,10 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 
 /* rcu_read_lock() must be held */
 struct sock *__udp6_lib_lookup(struct net *net,
-				      const struct in6_addr *saddr, __be16 sport,
-				      const struct in6_addr *daddr, __be16 dport,
-				      int dif, struct udp_table *udptable,
-				      struct sk_buff *skb)
+			       const struct in6_addr *saddr, __be16 sport,
+			       const struct in6_addr *daddr, __be16 dport,
+			       int dif, int sdif, struct udp_table *udptable,
+			       struct sk_buff *skb)
 {
 	struct sock *sk, *result;
 	unsigned short hnum = ntohs(dport);
@@ -235,7 +239,7 @@ struct sock *__udp6_lib_lookup(struct net *net,
 			goto begin;
 
 		result = udp6_lib_lookup2(net, saddr, sport,
-					  daddr, hnum, dif, exact_dif,
+					  daddr, hnum, dif, sdif, exact_dif,
 					  hslot2, skb);
 		if (!result) {
 			unsigned int old_slot2 = slot2;
@@ -250,7 +254,7 @@ struct sock *__udp6_lib_lookup(struct net *net,
 				goto begin;
 
 			result = udp6_lib_lookup2(net, saddr, sport,
-						  daddr, hnum, dif,
+						  daddr, hnum, dif, sdif,
 						  exact_dif, hslot2,
 						  skb);
 		}
@@ -261,7 +265,7 @@ struct sock *__udp6_lib_lookup(struct net *net,
 	badness = -1;
 	sk_for_each_rcu(sk, &hslot->head) {
 		score = compute_score(sk, net, saddr, sport, daddr, hnum, dif,
-				      exact_dif);
+				      sdif, exact_dif);
 		if (score > badness) {
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
@@ -294,7 +298,7 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
 
 	return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
 				 &iph->daddr, dport, inet6_iif(skb),
-				 udptable, skb);
+				 inet6_sdif(skb), udptable, skb);
 }
 
 struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
@@ -304,7 +308,7 @@ struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
 
 	return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
 				 &iph->daddr, dport, inet6_iif(skb),
-				 &udp_table, skb);
+				 inet6_sdif(skb), &udp_table, skb);
 }
 EXPORT_SYMBOL_GPL(udp6_lib_lookup_skb);
 
@@ -320,7 +324,7 @@ struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be
 	struct sock *sk;
 
 	sk =  __udp6_lib_lookup(net, saddr, sport, daddr, dport,
-				dif, &udp_table, NULL);
+				dif, 0, &udp_table, NULL);
 	if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
 		sk = NULL;
 	return sk;
@@ -501,7 +505,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	struct net *net = dev_net(skb->dev);
 
 	sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
-			       inet6_iif(skb), udptable, skb);
+			       inet6_iif(skb), 0, udptable, skb);
 	if (!sk) {
 		__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
 				  ICMP6_MIB_INERRORS);