Merge branch 'net-l3mdev-Support-for-sockets-bound-to-enslaved-device'

David Ahern says:

====================
net: l3mdev: Support for sockets bound to enslaved device

A missing piece to the VRF puzzle is the ability to bind sockets to
devices enslaved to a VRF. This patch set adds the enslaved device
index, sdif, to IPv4 and IPv6 socket lookups. The end result for users
is the following scope options for services:

1. "global" services - sockets not bound to any device

   Allows 1 service to work across all network interfaces with
   connected sockets bound to the VRF the connection originates
   (Requires net.ipv4.tcp_l3mdev_accept=1 for TCP and
    net.ipv4.udp_l3mdev_accept=1 for UDP)

2. "VRF" local services - sockets bound to a VRF

   Sockets work across all network interfaces enslaved to a VRF but
   are limited to just the one VRF.

3. "device" services - sockets bound to a specific network interface

   Service works only through the one specific interface.

v3
- convert __inet_lookup_established in dccp_v4_err; missed in v2

v2
- remove sk_lookup struct and add sdif as an argument to existing
  functions

Changes since RFC:
- no significant logic changes; mainly whitespace cleanups
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/igmp.h

@@ -118,7 +118,8 @@ extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf,
 		struct ip_msfilter __user *optval, int __user *optlen);
 extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf,
 		struct group_filter __user *optval, int __user *optlen);
-extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif);
+extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt,
+			  int dif, int sdif);
 extern void ip_mc_init_dev(struct in_device *);
 extern void ip_mc_destroy_dev(struct in_device *);
 extern void ip_mc_up(struct in_device *);

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/inet6_hashtables.h

@@ -49,15 +49,17 @@ 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,
 				   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);
 
 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 */

include/net/inet_hashtables.h

@@ -221,16 +221,16 @@ struct sock *__inet_lookup_listener(struct net *net,
 				    const __be32 saddr, const __be16 sport,
 				    const __be32 daddr,
 				    const unsigned short hnum,
-				    const int dif);
+				    const int dif, const int sdif);
 
 static inline struct sock *inet_lookup_listener(struct net *net,
 		struct inet_hashinfo *hashinfo,
 		struct sk_buff *skb, int doff,
 		__be32 saddr, __be16 sport,
-		__be32 daddr, __be16 dport, int dif)
+		__be32 daddr, __be16 dport, int dif, int sdif)
 {
 	return __inet_lookup_listener(net, hashinfo, skb, doff, saddr, sport,
-				      daddr, ntohs(dport), dif);
+				      daddr, ntohs(dport), dif, sdif);
 }
 
 /* Socket demux engine toys. */
@@ -262,22 +262,24 @@ static inline struct sock *inet_lookup_listener(struct net *net,
 				   (((__force __u64)(__be32)(__daddr)) << 32) | \
 				   ((__force __u64)(__be32)(__saddr)))
 #endif /* __BIG_ENDIAN */
-#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif)	\
+#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \
 	(((__sk)->sk_portpair == (__ports))			&&	\
 	 ((__sk)->sk_addrpair == (__cookie))			&&	\
 	 (!(__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)))
 #else /* 32-bit arch */
 #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
 	const int __name __deprecated __attribute__((unused))
 
-#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif) \
+#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \
 	(((__sk)->sk_portpair == (__ports))		&&		\
 	 ((__sk)->sk_daddr	== (__saddr))		&&		\
 	 ((__sk)->sk_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 /* 64-bit arch */
 
@@ -288,7 +290,7 @@ 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);
 
 static inline struct sock *
 	inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo,
@@ -297,28 +299,28 @@ static inline struct sock *
 				const int dif)
 {
 	return __inet_lookup_established(net, hashinfo, saddr, sport, daddr,
-					 ntohs(dport), dif);
+					 ntohs(dport), dif, 0);
 }
 
 static inline struct sock *__inet_lookup(struct net *net,
 					 struct inet_hashinfo *hashinfo,
 					 struct sk_buff *skb, int doff,
 					 const __be32 saddr, const __be16 sport,
 					 const __be32 daddr, const __be16 dport,
-					 const int dif,
+					 const int dif, const int sdif,
 					 bool *refcounted)
 {
 	u16 hnum = ntohs(dport);
 	struct sock *sk;
 
 	sk = __inet_lookup_established(net, hashinfo, saddr, sport,
-				       daddr, hnum, dif);
+				       daddr, hnum, dif, sdif);
 	*refcounted = true;
 	if (sk)
 		return sk;
 	*refcounted = false;
 	return __inet_lookup_listener(net, hashinfo, skb, doff, saddr,
-				      sport, daddr, hnum, dif);
+				      sport, daddr, hnum, dif, sdif);
 }
 
 static inline struct sock *inet_lookup(struct net *net,
@@ -332,7 +334,7 @@ static inline struct sock *inet_lookup(struct net *net,
 	bool refcounted;
 
 	sk = __inet_lookup(net, hashinfo, skb, doff, saddr, sport, daddr,
-			   dport, dif, &refcounted);
+			   dport, dif, 0, &refcounted);
 
 	if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt))
 		sk = NULL;
@@ -344,6 +346,7 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
 					     int doff,
 					     const __be16 sport,
 					     const __be16 dport,
+					     const int sdif,
 					     bool *refcounted)
 {
 	struct sock *sk = skb_steal_sock(skb);
@@ -355,7 +358,7 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
 
 	return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
 			     doff, iph->saddr, sport,
-			     iph->daddr, dport, inet_iif(skb),
+			     iph->daddr, dport, inet_iif(skb), sdif,
 			     refcounted);
 }
 

include/net/ip.h

@@ -78,6 +78,16 @@ struct ipcm_cookie {
 #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
 #define PKTINFO_SKB_CB(skb) ((struct in_pktinfo *)((skb)->cb))
 
+/* return enslaved device index if relevant */
+static inline int inet_sdif(struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	if (skb && ipv4_l3mdev_skb(IPCB(skb)->flags))
+		return IPCB(skb)->iif;
+#endif
+	return 0;
+}
+
 struct ip_ra_chain {
 	struct ip_ra_chain __rcu *next;
 	struct sock		*sk;

include/net/raw.h

@@ -26,7 +26,7 @@ extern struct proto raw_prot;
 extern struct raw_hashinfo raw_v4_hashinfo;
 struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
 			     unsigned short num, __be32 raddr,
-			     __be32 laddr, int dif);
+			     __be32 laddr, int dif, int sdif);
 
 int raw_abort(struct sock *sk, int err);
 void raw_icmp_error(struct sk_buff *, int, u32);

include/net/rawv6.h

@@ -6,7 +6,7 @@
 extern struct raw_hashinfo raw_v6_hashinfo;
 struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
 			     unsigned short num, const struct in6_addr *loc_addr,
-			     const struct in6_addr *rmt_addr, int dif);
+			     const struct in6_addr *rmt_addr, int dif, int sdif);
 
 int raw_abort(struct sock *sk, int err);
 

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 */
@@ -840,6 +850,16 @@ static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb)
 	return false;
 }
 
+/* TCP_SKB_CB reference means this can not be used from early demux */
+static inline int tcp_v4_sdif(struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	if (skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags))
+		return TCP_SKB_CB(skb)->header.h4.iif;
+#endif
+	return 0;
+}
+
 /* Due to TSO, an SKB can be composed of multiple actual
  * packets.  To keep these tracked properly, we use this.
  */

include/net/udp.h

@@ -287,7 +287,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
 			     __be32 daddr, __be16 dport, int dif);
 struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
-			       __be32 daddr, __be16 dport, int dif,
+			       __be32 daddr, __be16 dport, int dif, int sdif,
 			       struct udp_table *tbl, struct sk_buff *skb);
 struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
 				 __be16 sport, __be16 dport);
@@ -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/dccp/ipv4.c

@@ -256,7 +256,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 	sk = __inet_lookup_established(net, &dccp_hashinfo,
 				       iph->daddr, dh->dccph_dport,
 				       iph->saddr, ntohs(dh->dccph_sport),
-				       inet_iif(skb));
+				       inet_iif(skb), 0);
 	if (!sk) {
 		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
 		return;
@@ -804,7 +804,7 @@ static int dccp_v4_rcv(struct sk_buff *skb)
 
 lookup:
 	sk = __inet_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh),
-			       dh->dccph_sport, dh->dccph_dport, &refcounted);
+			       dh->dccph_sport, dh->dccph_dport, 0, &refcounted);
 	if (!sk) {
 		dccp_pr_debug("failed to look up flow ID in table and "
 			      "get corresponding socket\n");

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");

net/ipv4/igmp.c

@@ -2549,7 +2549,8 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf,
 /*
  * check if a multicast source filter allows delivery for a given <src,dst,intf>
  */
-int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif)
+int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr,
+		   int dif, int sdif)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct ip_mc_socklist *pmc;
@@ -2564,7 +2565,8 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif)
 	rcu_read_lock();
 	for_each_pmc_rcu(inet, pmc) {
 		if (pmc->multi.imr_multiaddr.s_addr == loc_addr &&
-		    pmc->multi.imr_ifindex == dif)
+		    (pmc->multi.imr_ifindex == dif ||
+		     (sdif && pmc->multi.imr_ifindex == sdif)))
 			break;
 	}
 	ret = inet->mc_all;