net: ipv6: add second dif to inet6 socket lookups

Add a second device index, sdif, to inet6 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 tcp_v4_rcv
tcp_v4_sdif is used.

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

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index b87becacd9d347d9a7dac23fb9e08133615a9d11..6e91e38a31da4cf53719d2ba270cf29c9dd98715 100644 (file)
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -49,7 +49,8 @@ struct sock *__inet6_lookup_established(struct net *net,
                                        const struct in6_addr *saddr,
                                        const __be16 sport,
                                        const struct in6_addr *daddr,
-                                       const u16 hnum, const int dif);
+                                       const u16 hnum, const int dif,
+                                       const int sdif);
 
 struct sock *inet6_lookup_listener(struct net *net,
                                   struct inet_hashinfo *hashinfo,
@@ -57,7 +58,8 @@ struct sock *inet6_lookup_listener(struct net *net,
                                   const struct in6_addr *saddr,
                                   const __be16 sport,
                                   const struct in6_addr *daddr,
-                                  const unsigned short hnum, const int dif);
+                                  const unsigned short hnum,
+                                  const int dif, const int sdif);
 
 static inline struct sock *__inet6_lookup(struct net *net,
                                          struct inet_hashinfo *hashinfo,
@@ -66,24 +68,25 @@ static inline struct sock *__inet6_lookup(struct net *net,
                                          const __be16 sport,
                                          const struct in6_addr *daddr,
                                          const u16 hnum,
-                                         const int dif,
+                                         const int dif, const int sdif,
                                          bool *refcounted)
 {
        struct sock *sk = __inet6_lookup_established(net, hashinfo, saddr,
-                                               sport, daddr, hnum, dif);
+                                                    sport, daddr, hnum,
+                                                    dif, sdif);
        *refcounted = true;
        if (sk)
                return sk;
        *refcounted = false;
        return inet6_lookup_listener(net, hashinfo, skb, doff, saddr, sport,
-                                    daddr, hnum, dif);
+                                    daddr, hnum, dif, sdif);
 }
 
 static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
                                              struct sk_buff *skb, int doff,
                                              const __be16 sport,
                                              const __be16 dport,
-                                             int iif,
+                                             int iif, int sdif,
                                              bool *refcounted)
 {
        struct sock *sk = skb_steal_sock(skb);
@@ -95,7 +98,7 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
        return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
                              doff, &ipv6_hdr(skb)->saddr, sport,
                              &ipv6_hdr(skb)->daddr, ntohs(dport),
-                             iif, refcounted);
+                             iif, sdif, refcounted);
 }
 
 struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
@@ -107,13 +110,14 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
 int inet6_hash(struct sock *sk);
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 
-#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif)     \
+#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif, __sdif) \
        (((__sk)->sk_portpair == (__ports))                     &&      \
         ((__sk)->sk_family == AF_INET6)                        &&      \
         ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr))               &&      \
         ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr))   &&      \
         (!(__sk)->sk_bound_dev_if      ||                              \
-          ((__sk)->sk_bound_dev_if == (__dif)))                &&      \
+          ((__sk)->sk_bound_dev_if == (__dif)) ||                      \
+          ((__sk)->sk_bound_dev_if == (__sdif)))               &&      \
         net_eq(sock_net(__sk), (__net)))
 
 #endif /* _INET6_HASHTABLES_H */

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 2b89f1ab85520d0bd426699f92f8c013c95bf35c..999f3efe572ba7ef1034b85d0cd0b448c56307e3 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -827,6 +827,16 @@ static inline int tcp_v6_iif(const struct sk_buff *skb)
 
        return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif;
 }
+
+/* TCP_SKB_CB reference means this can not be used from early demux */
+static inline int tcp_v6_sdif(const struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+       if (skb && ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags))
+               return TCP_SKB_CB(skb)->header.h6.iif;
+#endif
+       return 0;
+}
 #endif
 
 /* TCP_SKB_CB reference means this can not be used from early demux */

diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 1b58eac8aad326b6db09a4cee82fdcc178c2afad..47a7b59b355e4294bdc8580529acc778a612feb7 100644 (file)
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -89,7 +89,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
        sk = __inet6_lookup_established(net, &dccp_hashinfo,
                                        &hdr->daddr, dh->dccph_dport,
                                        &hdr->saddr, ntohs(dh->dccph_sport),
-                                       inet6_iif(skb));
+                                       inet6_iif(skb), 0);
 
        if (!sk) {
                __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
@@ -687,7 +687,7 @@ static int dccp_v6_rcv(struct sk_buff *skb)
 lookup:
        sk = __inet6_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh),
                                dh->dccph_sport, dh->dccph_dport,
-                               inet6_iif(skb), &refcounted);
+                               inet6_iif(skb), 0, &refcounted);
        if (!sk) {
                dccp_pr_debug("failed to look up flow ID in table and "
                              "get corresponding socket\n");

diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index b13b8f93079dae620e9e9fe58233baef01ecf84f..b01858f5deb1711f24c0c38cba0a3e61d43b390c 100644 (file)
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -56,7 +56,7 @@ struct sock *__inet6_lookup_established(struct net *net,
                                           const __be16 sport,
                                           const struct in6_addr *daddr,
                                           const u16 hnum,
-                                          const int dif)
+                                          const int dif, const int sdif)
 {
        struct sock *sk;
        const struct hlist_nulls_node *node;
@@ -73,12 +73,12 @@ begin:
        sk_nulls_for_each_rcu(sk, node, &head->chain) {
                if (sk->sk_hash != hash)
                        continue;
-               if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif))
+               if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif, sdif))
                        continue;
                if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
                        goto out;
 
-               if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif))) {
+               if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif, sdif))) {
                        sock_gen_put(sk);
                        goto begin;
                }
@@ -96,7 +96,7 @@ EXPORT_SYMBOL(__inet6_lookup_established);
 static inline int compute_score(struct sock *sk, struct net *net,
                                const unsigned short hnum,
                                const struct in6_addr *daddr,
-                               const int dif, bool exact_dif)
+                               const int dif, const int sdif, bool exact_dif)
 {
        int score = -1;
 
@@ -110,9 +110,13 @@ static inline int compute_score(struct sock *sk, struct net *net,
                        score++;
                }
                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())
                        score++;
@@ -126,7 +130,7 @@ struct sock *inet6_lookup_listener(struct net *net,
                struct sk_buff *skb, int doff,
                const struct in6_addr *saddr,
                const __be16 sport, const struct in6_addr *daddr,
-               const unsigned short hnum, const int dif)
+               const unsigned short hnum, const int dif, const int sdif)
 {
        unsigned int hash = inet_lhashfn(net, hnum);
        struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
@@ -136,7 +140,7 @@ struct sock *inet6_lookup_listener(struct net *net,
        u32 phash = 0;
 
        sk_for_each(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) {
@@ -171,7 +175,7 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
        bool refcounted;
 
        sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr,
-                           ntohs(dport), dif, &refcounted);
+                           ntohs(dport), dif, 0, &refcounted);
        if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt))
                sk = NULL;
        return sk;
@@ -187,8 +191,9 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
        const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr;
        const struct in6_addr *saddr = &sk->sk_v6_daddr;
        const int dif = sk->sk_bound_dev_if;
-       const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
        struct net *net = sock_net(sk);
+       const int sdif = l3mdev_master_ifindex_by_index(net, dif);
+       const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
        const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr,
                                                inet->inet_dport);
        struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
@@ -203,7 +208,8 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
                if (sk2->sk_hash != hash)
                        continue;
 
-               if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif))) {
+               if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports,
+                                      dif, sdif))) {
                        if (sk2->sk_state == TCP_TIME_WAIT) {
                                tw = inet_twsk(sk2);
                                if (twsk_unique(sk, sk2, twp))

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index ced5dcf3746599d8f9e2414ae249c6e929ff4687..f776ec4ecf6d76857c8ab05d30ad440c3584eff3 100644 (file)
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -350,7 +350,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
        sk = __inet6_lookup_established(net, &tcp_hashinfo,
                                        &hdr->daddr, th->dest,
                                        &hdr->saddr, ntohs(th->source),
-                                       skb->dev->ifindex);
+                                       skb->dev->ifindex, inet6_sdif(skb));
 
        if (!sk) {
                __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
@@ -918,7 +918,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
                                           &tcp_hashinfo, NULL, 0,
                                           &ipv6h->saddr,
                                           th->source, &ipv6h->daddr,
-                                          ntohs(th->source), tcp_v6_iif(skb));
+                                          ntohs(th->source), tcp_v6_iif(skb),
+                                          tcp_v6_sdif(skb));
                if (!sk1)
                        goto out;
 
@@ -1397,6 +1398,7 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
 
 static int tcp_v6_rcv(struct sk_buff *skb)
 {
+       int sdif = inet6_sdif(skb);
        const struct tcphdr *th;
        const struct ipv6hdr *hdr;
        bool refcounted;
@@ -1430,7 +1432,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 
 lookup:
        sk = __inet6_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th),
-                               th->source, th->dest, inet6_iif(skb),
+                               th->source, th->dest, inet6_iif(skb), sdif,
                                &refcounted);
        if (!sk)
                goto no_tcp_socket;
@@ -1563,7 +1565,8 @@ do_time_wait:
                                            skb, __tcp_hdrlen(th),
                                            &ipv6_hdr(skb)->saddr, th->source,
                                            &ipv6_hdr(skb)->daddr,
-                                           ntohs(th->dest), tcp_v6_iif(skb));
+                                           ntohs(th->dest), tcp_v6_iif(skb),
+                                           sdif);
                if (sk2) {
                        struct inet_timewait_sock *tw = inet_twsk(sk);
                        inet_twsk_deschedule_put(tw);
@@ -1610,7 +1613,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb)
        sk = __inet6_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
                                        &hdr->saddr, th->source,
                                        &hdr->daddr, ntohs(th->dest),
-                                       inet6_iif(skb));
+                                       inet6_iif(skb), inet6_sdif(skb));
        if (sk) {
                skb->sk = sk;
                skb->destructor = sock_edemux;

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d96a877798a73eac7e70130061aa9762c7492c1e..19afcaf4a22e036a8768fd1c4b4f870c8fa47d37 100644 (file)
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -897,7 +897,7 @@ discard:
 static struct sock *__udp6_lib_demux_lookup(struct net *net,
                        __be16 loc_port, const struct in6_addr *loc_addr,
                        __be16 rmt_port, const struct in6_addr *rmt_addr,
-                       int dif)
+                       int dif, int sdif)
 {
        unsigned short hnum = ntohs(loc_port);
        unsigned int hash2 = udp6_portaddr_hash(net, loc_addr, hnum);
@@ -908,7 +908,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net,
 
        udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
                if (sk->sk_state == TCP_ESTABLISHED &&
-                   INET6_MATCH(sk, net, rmt_addr, loc_addr, ports, dif))
+                   INET6_MATCH(sk, net, rmt_addr, loc_addr, ports, dif, sdif))
                        return sk;
                /* Only check first socket in chain */
                break;
@@ -923,6 +923,7 @@ static void udp_v6_early_demux(struct sk_buff *skb)
        struct sock *sk;
        struct dst_entry *dst;
        int dif = skb->dev->ifindex;
+       int sdif = inet6_sdif(skb);
 
        if (!pskb_may_pull(skb, skb_transport_offset(skb) +
            sizeof(struct udphdr)))
@@ -934,7 +935,7 @@ static void udp_v6_early_demux(struct sk_buff *skb)
                sk = __udp6_lib_demux_lookup(net, uh->dest,
                                             &ipv6_hdr(skb)->daddr,
                                             uh->source, &ipv6_hdr(skb)->saddr,
-                                            dif);
+                                            dif, sdif);
        else
                return;
 

diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 94fb0fd0c66708c3009c33a287e025863b747f6e..ade4c10c28c6de7ec4d35daa021b539162d6b13c 100644 (file)
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -195,7 +195,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
                                                   thoff + __tcp_hdrlen(tcph),
                                                   saddr, sport,
                                                   daddr, ntohs(dport),
-                                                  in->ifindex);
+                                                  in->ifindex, 0);
 
                        if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
                                sk = NULL;
@@ -208,7 +208,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
                case NFT_LOOKUP_ESTABLISHED:
                        sk = __inet6_lookup_established(net, &tcp_hashinfo,
                                                        saddr, sport, daddr, ntohs(dport),
-                                                       in->ifindex);
+                                                       in->ifindex, 0);
                        break;
                default:
                        BUG();