Merge branch 'vrf-inetpeer'

David Ahern says:

====================
net: Refactor inetpeer cache and add support for VRFs

Per Dave's comment on the version 1 patch adding VRF support to inetpeer
cache by explicitly making the address + index a key. Refactored the
inetpeer code in the process; mostly impacts the use by tcp_metrics.
====================

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

include/net/inetpeer.h

@@ -15,16 +15,20 @@
 #include <net/ipv6.h>
 #include <linux/atomic.h>
 
-struct inetpeer_addr_base {
-	union {
-		__be32			a4;
-		__be32			a6[4];
-		struct in6_addr		in6;
-	};
+/* IPv4 address key for cache lookups */
+struct ipv4_addr_key {
+	__be32	addr;
+	int	vif;
 };
 
+#define INETPEER_MAXKEYSZ   (sizeof(struct in6_addr) / sizeof(u32))
+
 struct inetpeer_addr {
-	struct inetpeer_addr_base	addr;
+	union {
+		struct ipv4_addr_key	a4;
+		struct in6_addr		a6;
+		u32			key[INETPEER_MAXKEYSZ];
+	};
 	__u16				family;
 };
 
@@ -71,6 +75,29 @@ void inet_initpeers(void) __init;
 
 #define INETPEER_METRICS_NEW	(~(u32) 0)
 
+static inline void inetpeer_set_addr_v4(struct inetpeer_addr *iaddr, __be32 ip)
+{
+	iaddr->a4.addr = ip;
+	iaddr->family = AF_INET;
+}
+
+static inline __be32 inetpeer_get_addr_v4(struct inetpeer_addr *iaddr)
+{
+	return iaddr->a4.addr;
+}
+
+static inline void inetpeer_set_addr_v6(struct inetpeer_addr *iaddr,
+					struct in6_addr *in6)
+{
+	iaddr->a6 = *in6;
+	iaddr->family = AF_INET6;
+}
+
+static inline struct in6_addr *inetpeer_get_addr_v6(struct inetpeer_addr *iaddr)
+{
+	return &iaddr->a6;
+}
+
 /* can be called with or without local BH being disabled */
 struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 			       const struct inetpeer_addr *daddr,
@@ -78,11 +105,12 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 
 static inline struct inet_peer *inet_getpeer_v4(struct inet_peer_base *base,
 						__be32 v4daddr,
-						int create)
+						int vif, int create)
 {
 	struct inetpeer_addr daddr;
 
-	daddr.addr.a4 = v4daddr;
+	daddr.a4.addr = v4daddr;
+	daddr.a4.vif = vif;
 	daddr.family = AF_INET;
 	return inet_getpeer(base, &daddr, create);
 }
@@ -93,11 +121,32 @@ static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base,
 {
 	struct inetpeer_addr daddr;
 
-	daddr.addr.in6 = *v6daddr;
+	daddr.a6 = *v6daddr;
 	daddr.family = AF_INET6;
 	return inet_getpeer(base, &daddr, create);
 }
 
+static inline int inetpeer_addr_cmp(const struct inetpeer_addr *a,
+				    const struct inetpeer_addr *b)
+{
+	int i, n;
+
+	if (a->family == AF_INET)
+		n = sizeof(a->a4) / sizeof(u32);
+	else
+		n = sizeof(a->a6) / sizeof(u32);
+
+	for (i = 0; i < n; i++) {
+		if (a->key[i] == b->key[i])
+			continue;
+		if (a->key[i] < b->key[i])
+			return -1;
+		return 1;
+	}
+
+	return 0;
+}
+
 /* can be called from BH context or outside */
 void inet_putpeer(struct inet_peer *p);
 bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout);

include/net/ip.h

@@ -458,6 +458,11 @@ static __inline__ void inet_reset_saddr(struct sock *sk)
 
 #endif
 
+static inline unsigned int ipv4_addr_hash(__be32 ip)
+{
+	return (__force unsigned int) ip;
+}
+
 bool ip_call_ra_chain(struct sk_buff *skb);
 
 /*

net/ipv4/icmp.c

@@ -309,9 +309,10 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
 
 	rc = false;
 	if (icmp_global_allow()) {
+		int vif = vrf_master_ifindex(dst->dev);
 		struct inet_peer *peer;
 
-		peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, 1);
+		peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1);
 		rc = inet_peer_xrlim_allow(peer,
 					   net->ipv4.sysctl_icmp_ratelimit);
 		if (peer)

net/ipv4/inetpeer.c

@@ -157,22 +157,6 @@ void __init inet_initpeers(void)
 	INIT_DEFERRABLE_WORK(&gc_work, inetpeer_gc_worker);
 }
 
-static int addr_compare(const struct inetpeer_addr *a,
-			const struct inetpeer_addr *b)
-{
-	int i, n = (a->family == AF_INET ? 1 : 4);
-
-	for (i = 0; i < n; i++) {
-		if (a->addr.a6[i] == b->addr.a6[i])
-			continue;
-		if ((__force u32)a->addr.a6[i] < (__force u32)b->addr.a6[i])
-			return -1;
-		return 1;
-	}
-
-	return 0;
-}
-
 #define rcu_deref_locked(X, BASE)				\
 	rcu_dereference_protected(X, lockdep_is_held(&(BASE)->lock.lock))
 
@@ -188,7 +172,7 @@ static int addr_compare(const struct inetpeer_addr *a,
 	*stackptr++ = &_base->root;				\
 	for (u = rcu_deref_locked(_base->root, _base);		\
 	     u != peer_avl_empty;) {				\
-		int cmp = addr_compare(_daddr, &u->daddr);	\
+		int cmp = inetpeer_addr_cmp(_daddr, &u->daddr);	\
 		if (cmp == 0)					\
 			break;					\
 		if (cmp == -1)					\
@@ -215,7 +199,7 @@ static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr,
 	int count = 0;
 
 	while (u != peer_avl_empty) {
-		int cmp = addr_compare(daddr, &u->daddr);
+		int cmp = inetpeer_addr_cmp(daddr, &u->daddr);
 		if (cmp == 0) {
 			/* Before taking a reference, check if this entry was
 			 * deleted (refcnt=-1)

net/ipv4/ip_fragment.c

@@ -151,7 +151,8 @@ static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
 	qp->vif = arg->vif;
 	qp->user = arg->user;
 	qp->peer = sysctl_ipfrag_max_dist ?
-		inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, 1) : NULL;
+		inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) :
+		NULL;
 }
 
 static void ip4_frag_free(struct inet_frag_queue *q)

net/ipv4/route.c

@@ -838,6 +838,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	struct inet_peer *peer;
 	struct net *net;
 	int log_martians;
+	int vif;
 
 	rcu_read_lock();
 	in_dev = __in_dev_get_rcu(rt->dst.dev);
@@ -846,10 +847,11 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 		return;
 	}
 	log_martians = IN_DEV_LOG_MARTIANS(in_dev);
+	vif = vrf_master_ifindex_rcu(rt->dst.dev);
 	rcu_read_unlock();
 
 	net = dev_net(rt->dst.dev);
-	peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1);
+	peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif, 1);
 	if (!peer) {
 		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST,
 			  rt_nexthop(rt, ip_hdr(skb)->daddr));
@@ -938,7 +940,8 @@ static int ip_error(struct sk_buff *skb)
 		break;
 	}
 
-	peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1);
+	peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr,
+			       vrf_master_ifindex(skb->dev), 1);
 
 	send = true;
 	if (peer) {

net/ipv4/tcp_metrics.c

@@ -81,11 +81,7 @@ static void tcp_metric_set(struct tcp_metrics_block *tm,
 static bool addr_same(const struct inetpeer_addr *a,
 		      const struct inetpeer_addr *b)
 {
-	if (a->family != b->family)
-		return false;
-	if (a->family == AF_INET)
-		return a->addr.a4 == b->addr.a4;
-	return ipv6_addr_equal(&a->addr.in6, &b->addr.in6);
+	return inetpeer_addr_cmp(a, b) == 0;
 }
 
 struct tcpm_hash_bucket {
@@ -247,14 +243,14 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
 	daddr.family = req->rsk_ops->family;
 	switch (daddr.family) {
 	case AF_INET:
-		saddr.addr.a4 = inet_rsk(req)->ir_loc_addr;
-		daddr.addr.a4 = inet_rsk(req)->ir_rmt_addr;
-		hash = (__force unsigned int) daddr.addr.a4;
+		inetpeer_set_addr_v4(&saddr, inet_rsk(req)->ir_loc_addr);
+		inetpeer_set_addr_v4(&daddr, inet_rsk(req)->ir_rmt_addr);
+		hash = ipv4_addr_hash(inet_rsk(req)->ir_rmt_addr);
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
-		saddr.addr.in6 = inet_rsk(req)->ir_v6_loc_addr;
-		daddr.addr.in6 = inet_rsk(req)->ir_v6_rmt_addr;
+		inetpeer_set_addr_v6(&saddr, &inet_rsk(req)->ir_v6_loc_addr);
+		inetpeer_set_addr_v6(&daddr, &inet_rsk(req)->ir_v6_rmt_addr);
 		hash = ipv6_addr_hash(&inet_rsk(req)->ir_v6_rmt_addr);
 		break;
 #endif
@@ -285,25 +281,19 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock
 	struct net *net;
 
 	if (tw->tw_family == AF_INET) {
-		saddr.family = AF_INET;
-		saddr.addr.a4 = tw->tw_rcv_saddr;
-		daddr.family = AF_INET;
-		daddr.addr.a4 = tw->tw_daddr;
-		hash = (__force unsigned int) daddr.addr.a4;
+		inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr);
+		inetpeer_set_addr_v4(&daddr, tw->tw_daddr);
+		hash = ipv4_addr_hash(tw->tw_daddr);
 	}
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (tw->tw_family == AF_INET6) {
 		if (ipv6_addr_v4mapped(&tw->tw_v6_daddr)) {
-			saddr.family = AF_INET;
-			saddr.addr.a4 = tw->tw_rcv_saddr;
-			daddr.family = AF_INET;
-			daddr.addr.a4 = tw->tw_daddr;
-			hash = (__force unsigned int) daddr.addr.a4;
+			inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr);
+			inetpeer_set_addr_v4(&daddr, tw->tw_daddr);
+			hash = ipv4_addr_hash(tw->tw_daddr);
 		} else {
-			saddr.family = AF_INET6;
-			saddr.addr.in6 = tw->tw_v6_rcv_saddr;
-			daddr.family = AF_INET6;
-			daddr.addr.in6 = tw->tw_v6_daddr;
+			inetpeer_set_addr_v6(&saddr, &tw->tw_v6_rcv_saddr);
+			inetpeer_set_addr_v6(&daddr, &tw->tw_v6_daddr);
 			hash = ipv6_addr_hash(&tw->tw_v6_daddr);
 		}
 	}
@@ -335,25 +325,19 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 	struct net *net;
 
 	if (sk->sk_family == AF_INET) {
-		saddr.family = AF_INET;
-		saddr.addr.a4 = inet_sk(sk)->inet_saddr;
-		daddr.family = AF_INET;
-		daddr.addr.a4 = inet_sk(sk)->inet_daddr;
-		hash = (__force unsigned int) daddr.addr.a4;
+		inetpeer_set_addr_v4(&saddr, inet_sk(sk)->inet_saddr);
+		inetpeer_set_addr_v4(&daddr, inet_sk(sk)->inet_daddr);
+		hash = ipv4_addr_hash(inet_sk(sk)->inet_daddr);
 	}
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (sk->sk_family == AF_INET6) {
 		if (ipv6_addr_v4mapped(&sk->sk_v6_daddr)) {
-			saddr.family = AF_INET;
-			saddr.addr.a4 = inet_sk(sk)->inet_saddr;
-			daddr.family = AF_INET;
-			daddr.addr.a4 = inet_sk(sk)->inet_daddr;
-			hash = (__force unsigned int) daddr.addr.a4;
+			inetpeer_set_addr_v4(&saddr, inet_sk(sk)->inet_saddr);
+			inetpeer_set_addr_v4(&daddr, inet_sk(sk)->inet_daddr);
+			hash = ipv4_addr_hash(inet_sk(sk)->inet_daddr);
 		} else {
-			saddr.family = AF_INET6;
-			saddr.addr.in6 = sk->sk_v6_rcv_saddr;
-			daddr.family = AF_INET6;
-			daddr.addr.in6 = sk->sk_v6_daddr;
+			inetpeer_set_addr_v6(&saddr, &sk->sk_v6_rcv_saddr);
+			inetpeer_set_addr_v6(&daddr, &sk->sk_v6_daddr);
 			hash = ipv6_addr_hash(&sk->sk_v6_daddr);
 		}
 	}
@@ -796,18 +780,18 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
 	switch (tm->tcpm_daddr.family) {
 	case AF_INET:
 		if (nla_put_in_addr(msg, TCP_METRICS_ATTR_ADDR_IPV4,
-				    tm->tcpm_daddr.addr.a4) < 0)
+				    inetpeer_get_addr_v4(&tm->tcpm_daddr)) < 0)
 			goto nla_put_failure;
 		if (nla_put_in_addr(msg, TCP_METRICS_ATTR_SADDR_IPV4,
-				    tm->tcpm_saddr.addr.a4) < 0)
+				    inetpeer_get_addr_v4(&tm->tcpm_saddr)) < 0)
 			goto nla_put_failure;
 		break;
 	case AF_INET6:
 		if (nla_put_in6_addr(msg, TCP_METRICS_ATTR_ADDR_IPV6,
-				     &tm->tcpm_daddr.addr.in6) < 0)
+				     inetpeer_get_addr_v6(&tm->tcpm_daddr)) < 0)
 			goto nla_put_failure;
 		if (nla_put_in6_addr(msg, TCP_METRICS_ATTR_SADDR_IPV6,
-				     &tm->tcpm_saddr.addr.in6) < 0)
+				     inetpeer_get_addr_v6(&tm->tcpm_saddr)) < 0)
 			goto nla_put_failure;
 		break;
 	default:
@@ -956,20 +940,21 @@ static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr,
 
 	a = info->attrs[v4];
 	if (a) {
-		addr->family = AF_INET;
-		addr->addr.a4 = nla_get_in_addr(a);
+		inetpeer_set_addr_v4(addr, nla_get_in_addr(a));
 		if (hash)
-			*hash = (__force unsigned int) addr->addr.a4;
+			*hash = ipv4_addr_hash(inetpeer_get_addr_v4(addr));
 		return 0;
 	}
 	a = info->attrs[v6];
 	if (a) {
+		struct in6_addr in6;
+
 		if (nla_len(a) != sizeof(struct in6_addr))
 			return -EINVAL;
-		addr->family = AF_INET6;
-		addr->addr.in6 = nla_get_in6_addr(a);
+		in6 = nla_get_in6_addr(a);
+		inetpeer_set_addr_v6(addr, &in6);
 		if (hash)
-			*hash = ipv6_addr_hash(&addr->addr.in6);
+			*hash = ipv6_addr_hash(inetpeer_get_addr_v6(addr));
 		return 0;
 	}
 	return optional ? 1 : -EAFNOSUPPORT;