inet: refactor inet[6]_lookup functions to take skb

This is a preliminary step to allow fast socket lookup of SO_REUSEPORT
groups.  Doing so with a BPF filter will require access to the
skb in question.  This change plumbs the skb (and offset to payload
data) through the call stack to the listening socket lookup
implementations where it will be used in a following patch.

Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 41 insertions, 18 deletions

diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 3ab591e73ec0..7f4414d26a66 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -105,19 +105,24 @@ tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
  * belonging to established connections going through that one.
  */
 static inline struct sock *
-nf_tproxy_get_sock_v4(struct net *net, const u8 protocol,
+nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
+		      const u8 protocol,
 		      const __be32 saddr, const __be32 daddr,
 		      const __be16 sport, const __be16 dport,
 		      const struct net_device *in,
 		      const enum nf_tproxy_lookup_t lookup_type)
 {
 	struct sock *sk;
+	struct tcphdr *tcph;
 
 	switch (protocol) {
 	case IPPROTO_TCP:
 		switch (lookup_type) {
 		case NFT_LOOKUP_LISTENER:
-			sk = inet_lookup_listener(net, &tcp_hashinfo,
+			tcph = hp;
+			sk = inet_lookup_listener(net, &tcp_hashinfo, skb,
+						    ip_hdrlen(skb) +
+						      __tcp_hdrlen(tcph),
 						    saddr, sport,
 						    daddr, dport,
 						    in->ifindex);
@@ -169,19 +174,23 @@ nf_tproxy_get_sock_v4(struct net *net, const u8 protocol,
 
 #ifdef XT_TPROXY_HAVE_IPV6
 static inline struct sock *
-nf_tproxy_get_sock_v6(struct net *net, const u8 protocol,
+nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
+		      const u8 protocol,
 		      const struct in6_addr *saddr, const struct in6_addr *daddr,
 		      const __be16 sport, const __be16 dport,
 		      const struct net_device *in,
 		      const enum nf_tproxy_lookup_t lookup_type)
 {
 	struct sock *sk;
+	struct tcphdr *tcph;
 
 	switch (protocol) {
 	case IPPROTO_TCP:
 		switch (lookup_type) {
 		case NFT_LOOKUP_LISTENER:
-			sk = inet6_lookup_listener(net, &tcp_hashinfo,
+			tcph = hp;
+			sk = inet6_lookup_listener(net, &tcp_hashinfo, skb,
+						   thoff + __tcp_hdrlen(tcph),
 						   saddr, sport,
 						   daddr, ntohs(dport),
 						   in->ifindex);
@@ -267,7 +276,7 @@ tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb,
 		 * to a listener socket if there's one */
 		struct sock *sk2;
 
-		sk2 = nf_tproxy_get_sock_v4(net, iph->protocol,
+		sk2 = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
 					    iph->saddr, laddr ? laddr : iph->daddr,
 					    hp->source, lport ? lport : hp->dest,
 					    skb->dev, NFT_LOOKUP_LISTENER);
@@ -305,7 +314,7 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport,
 	 * addresses, this happens if the redirect already happened
 	 * and the current packet belongs to an already established
 	 * connection */
-	sk = nf_tproxy_get_sock_v4(net, iph->protocol,
+	sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
 				   iph->saddr, iph->daddr,
 				   hp->source, hp->dest,
 				   skb->dev, NFT_LOOKUP_ESTABLISHED);
@@ -321,7 +330,7 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport,
 	else if (!sk)
 		/* no, there's no established connection, check if
 		 * there's a listener on the redirected addr/port */
-		sk = nf_tproxy_get_sock_v4(net, iph->protocol,
+		sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
 					   iph->saddr, laddr,
 					   hp->source, lport,
 					   skb->dev, NFT_LOOKUP_LISTENER);
@@ -429,7 +438,7 @@ tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff,
 		 * to a listener socket if there's one */
 		struct sock *sk2;
 
-		sk2 = nf_tproxy_get_sock_v6(par->net, tproto,
+		sk2 = nf_tproxy_get_sock_v6(par->net, skb, thoff, hp, tproto,
 					    &iph->saddr,
 					    tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr),
 					    hp->source,
@@ -472,7 +481,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
 	 * addresses, this happens if the redirect already happened
 	 * and the current packet belongs to an already established
 	 * connection */
-	sk = nf_tproxy_get_sock_v6(par->net, tproto,
+	sk = nf_tproxy_get_sock_v6(par->net, skb, thoff, hp, tproto,
 				   &iph->saddr, &iph->daddr,
 				   hp->source, hp->dest,
 				   par->in, NFT_LOOKUP_ESTABLISHED);
@@ -487,8 +496,8 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
 	else if (!sk)
 		/* no there's no established connection, check if
 		 * there's a listener on the redirected addr/port */
-		sk = nf_tproxy_get_sock_v6(par->net, tproto,
-					   &iph->saddr, laddr,
+		sk = nf_tproxy_get_sock_v6(par->net, skb, thoff, hp,
+					   tproto, &iph->saddr, laddr,
 					   hp->source, lport,
 					   par->in, NFT_LOOKUP_LISTENER);
 
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 2ec08f04b816..49d14ecad444 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -112,14 +112,15 @@ extract_icmp4_fields(const struct sk_buff *skb,
  *     box.
  */
 static struct sock *
-xt_socket_get_sock_v4(struct net *net, const u8 protocol,
+xt_socket_get_sock_v4(struct net *net, struct sk_buff *skb, const int doff,
+		      const u8 protocol,
 		      const __be32 saddr, const __be32 daddr,
 		      const __be16 sport, const __be16 dport,
 		      const struct net_device *in)
 {
 	switch (protocol) {
 	case IPPROTO_TCP:
-		return __inet_lookup(net, &tcp_hashinfo,
+		return __inet_lookup(net, &tcp_hashinfo, skb, doff,
 				     saddr, sport, daddr, dport,
 				     in->ifindex);
 	case IPPROTO_UDP:
@@ -148,6 +149,8 @@ static struct sock *xt_socket_lookup_slow_v4(struct net *net,
 					     const struct net_device *indev)
 {
 	const struct iphdr *iph = ip_hdr(skb);
+	struct sk_buff *data_skb = NULL;
+	int doff = 0;
 	__be32 uninitialized_var(daddr), uninitialized_var(saddr);
 	__be16 uninitialized_var(dport), uninitialized_var(sport);
 	u8 uninitialized_var(protocol);
@@ -169,6 +172,10 @@ static struct sock *xt_socket_lookup_slow_v4(struct net *net,
 		sport = hp->source;
 		daddr = iph->daddr;
 		dport = hp->dest;
+		data_skb = (struct sk_buff *)skb;
+		doff = iph->protocol == IPPROTO_TCP ?
+			ip_hdrlen(skb) + __tcp_hdrlen((struct tcphdr *)hp) :
+			ip_hdrlen(skb) + sizeof(*hp);
 
 	} else if (iph->protocol == IPPROTO_ICMP) {
 		if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr,
@@ -198,8 +205,8 @@ static struct sock *xt_socket_lookup_slow_v4(struct net *net,
 	}
 #endif
 
-	return xt_socket_get_sock_v4(net, protocol, saddr, daddr,
-				     sport, dport, indev);
+	return xt_socket_get_sock_v4(net, data_skb, doff, protocol, saddr,
+				     daddr, sport, dport, indev);
 }
 
 static bool
@@ -318,14 +325,15 @@ extract_icmp6_fields(const struct sk_buff *skb,
 }
 
 static struct sock *
-xt_socket_get_sock_v6(struct net *net, const u8 protocol,
+xt_socket_get_sock_v6(struct net *net, struct sk_buff *skb, int doff,
+		      const u8 protocol,
 		      const struct in6_addr *saddr, const struct in6_addr *daddr,
 		      const __be16 sport, const __be16 dport,
 		      const struct net_device *in)
 {
 	switch (protocol) {
 	case IPPROTO_TCP:
-		return inet6_lookup(net, &tcp_hashinfo,
+		return inet6_lookup(net, &tcp_hashinfo, skb, doff,
 				    saddr, sport, daddr, dport,
 				    in->ifindex);
 	case IPPROTO_UDP:
@@ -343,6 +351,8 @@ static struct sock *xt_socket_lookup_slow_v6(struct net *net,
 	__be16 uninitialized_var(dport), uninitialized_var(sport);
 	const struct in6_addr *daddr = NULL, *saddr = NULL;
 	struct ipv6hdr *iph = ipv6_hdr(skb);
+	struct sk_buff *data_skb = NULL;
+	int doff = 0;
 	int thoff = 0, tproto;
 
 	tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
@@ -362,6 +372,10 @@ static struct sock *xt_socket_lookup_slow_v6(struct net *net,
 		sport = hp->source;
 		daddr = &iph->daddr;
 		dport = hp->dest;
+		data_skb = (struct sk_buff *)skb;
+		doff = tproto == IPPROTO_TCP ?
+			thoff + __tcp_hdrlen((struct tcphdr *)hp) :
+			thoff + sizeof(*hp);
 
 	} else if (tproto == IPPROTO_ICMPV6) {
 		struct ipv6hdr ipv6_var;
@@ -373,7 +387,7 @@ static struct sock *xt_socket_lookup_slow_v6(struct net *net,
 		return NULL;
 	}
 
-	return xt_socket_get_sock_v6(net, tproto, saddr, daddr,
+	return xt_socket_get_sock_v6(net, data_skb, doff, tproto, saddr, daddr,
 				     sport, dport, indev);
 }