[PATCH net-next 0/5] net: Refactor inetpeer cache and add support for VRFs

[PATCH net-next 0/5] net: Refactor inetpeer cache and add support for VRFs

[David Ahern]

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.

David Ahern (5):
  net: Introduce ipv4_addr_hash and use it for tcp metrics
  net: Add set,get helpers for inetpeer addresses
  net: Add helper function to compare inetpeer addresses
  net: Refactor inetpeer address struct
  net: Add support for VRFs to inetpeer cache

 include/net/inetpeer.h | 64 ++++++++++++++++++++++++++++++++-------
 include/net/ip.h       |  5 ++++
 net/ipv4/icmp.c        |  3 +-
 net/ipv4/inetpeer.c    | 20 ++-----------
 net/ipv4/ip_fragment.c |  3 +-
 net/ipv4/route.c       |  7 +++--
 net/ipv4/tcp_metrics.c | 81 ++++++++++++++++++++------------------------------
 7 files changed, 103 insertions(+), 80 deletions(-)

-- 
1.9.1

[PATCH net-next 1/5] net: Introduce ipv4_addr_hash and use it for tcp metrics

[David Ahern]

Refactors a common line into helper function.

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
 include/net/ip.h       |  5 +++++
 net/ipv4/tcp_metrics.c | 12 ++++++------
 2 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index bee5f3582e38..7b9e1c782aa3 100644
--- a/include/net/ip.h
+++ b/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);
 
 /*
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index b3d64f61d922..3a4289268f97 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -249,7 +249,7 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
 	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;
+		hash = ipv4_addr_hash(inet_rsk(req)->ir_rmt_addr);
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
@@ -289,7 +289,7 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock
 		saddr.addr.a4 = tw->tw_rcv_saddr;
 		daddr.family = AF_INET;
 		daddr.addr.a4 = tw->tw_daddr;
-		hash = (__force unsigned int) daddr.addr.a4;
+		hash = ipv4_addr_hash(tw->tw_daddr);
 	}
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (tw->tw_family == AF_INET6) {
@@ -298,7 +298,7 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock
 			saddr.addr.a4 = tw->tw_rcv_saddr;
 			daddr.family = AF_INET;
 			daddr.addr.a4 = tw->tw_daddr;
-			hash = (__force unsigned int) daddr.addr.a4;
+			hash = ipv4_addr_hash(tw->tw_daddr);
 		} else {
 			saddr.family = AF_INET6;
 			saddr.addr.in6 = tw->tw_v6_rcv_saddr;
@@ -339,7 +339,7 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 		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;
+		hash = ipv4_addr_hash(inet_sk(sk)->inet_daddr);
 	}
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (sk->sk_family == AF_INET6) {
@@ -348,7 +348,7 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 			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;
+			hash = ipv4_addr_hash(inet_sk(sk)->inet_daddr);
 		} else {
 			saddr.family = AF_INET6;
 			saddr.addr.in6 = sk->sk_v6_rcv_saddr;
@@ -959,7 +959,7 @@ static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr,
 		addr->family = AF_INET;
 		addr->addr.a4 = nla_get_in_addr(a);
 		if (hash)
-			*hash = (__force unsigned int) addr->addr.a4;
+			*hash = ipv4_addr_hash(addr->addr.a4);
 		return 0;
 	}
 	a = info->attrs[v6];
-- 
1.9.1

[PATCH net-next 2/5] net: Add set,get helpers for inetpeer addresses

[David Ahern]

Use inetpeer set,get helpers in tcp_metrics rather than peeking into
the inetpeer_addr struct.

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
 include/net/inetpeer.h | 23 ++++++++++++++++++
 net/ipv4/tcp_metrics.c | 65 +++++++++++++++++++++-----------------------------
 2 files changed, 50 insertions(+), 38 deletions(-)

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 002f0bd27001..f75b9e7036a2 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -71,6 +71,29 @@ 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->addr.a4 = ip;
+	iaddr->family = AF_INET;
+}
+
+static inline __be32 inetpeer_get_addr_v4(struct inetpeer_addr *iaddr)
+{
+	return iaddr->addr.a4;
+}
+
+static inline void inetpeer_set_addr_v6(struct inetpeer_addr *iaddr,
+					struct in6_addr *in6)
+{
+	iaddr->addr.in6 = *in6;
+	iaddr->family = AF_INET6;
+}
+
+static inline struct in6_addr *inetpeer_get_addr_v6(struct inetpeer_addr *iaddr)
+{
+	return &iaddr->addr.in6;
+}
+
 /* 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,
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 3a4289268f97..4ef4dd4bf38c 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -247,14 +247,14 @@ 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;
+		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 +285,19 @@ 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;
+		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;
+			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 +329,19 @@ 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;
+		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;
+			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 +784,18 @@ 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 +944,21 @@ 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 = ipv4_addr_hash(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;
-- 
1.9.1

[PATCH net-next 3/5] net: Add helper function to compare inetpeer addresses

[David Ahern]

tcp_metrics and inetpeer both have functions to compare inetpeer
addresses. Consolidate into 1 version.

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
 include/net/inetpeer.h | 16 ++++++++++++++++
 net/ipv4/inetpeer.c    | 20 ++------------------
 net/ipv4/tcp_metrics.c |  6 +-----
 3 files changed, 19 insertions(+), 23 deletions(-)

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index f75b9e7036a2..9d9b3446731d 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -121,6 +121,22 @@ static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base,
 	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 = (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;
+}
+
 /* 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);
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 241afd743d2c..86fa45809540 100644
--- a/net/ipv4/inetpeer.c
+++ b/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)
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 4ef4dd4bf38c..c8cbc2b4b792 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/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 {
-- 
1.9.1

[PATCH net-next 4/5] net: Refactor inetpeer address struct

[David Ahern]

Move the inetpeer_addr_base union to inetpeer_addr and drop
inetpeer_addr_base.

Both the a6 and in6_addr overlays are not needed; drop the __be32 version
and rename in6 to a6 for consistency with ipv4. Add a new u32 array to
the union which removes the need for the typecast in the compare function
and the use of a consistent arg for both ipv4 and ipv6 addresses which
makes the compare function more readable.

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
 include/net/inetpeer.h | 30 ++++++++++++++----------------
 1 file changed, 14 insertions(+), 16 deletions(-)

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 9d9b3446731d..e96bada9d19a 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -15,16 +15,14 @@
 #include <net/ipv6.h>
 #include <linux/atomic.h>
 
-struct inetpeer_addr_base {
+#define INETPEER_MAXKEYSZ   (sizeof(struct in6_addr) / sizeof(u32))
+
+struct inetpeer_addr {
 	union {
 		__be32			a4;
-		__be32			a6[4];
-		struct in6_addr		in6;
+		struct in6_addr		a6;
+		u32			key[INETPEER_MAXKEYSZ];
 	};
-};
-
-struct inetpeer_addr {
-	struct inetpeer_addr_base	addr;
 	__u16				family;
 };
 
@@ -73,25 +71,25 @@ void inet_initpeers(void) __init;
 
 static inline void inetpeer_set_addr_v4(struct inetpeer_addr *iaddr, __be32 ip)
 {
-	iaddr->addr.a4 = ip;
+	iaddr->a4 = ip;
 	iaddr->family = AF_INET;
 }
 
 static inline __be32 inetpeer_get_addr_v4(struct inetpeer_addr *iaddr)
 {
-	return iaddr->addr.a4;
+	return iaddr->a4;
 }
 
 static inline void inetpeer_set_addr_v6(struct inetpeer_addr *iaddr,
 					struct in6_addr *in6)
 {
-	iaddr->addr.in6 = *in6;
+	iaddr->a6 = *in6;
 	iaddr->family = AF_INET6;
 }
 
 static inline struct in6_addr *inetpeer_get_addr_v6(struct inetpeer_addr *iaddr)
 {
-	return &iaddr->addr.in6;
+	return &iaddr->a6;
 }
 
 /* can be called with or without local BH being disabled */
@@ -105,7 +103,7 @@ static inline struct inet_peer *inet_getpeer_v4(struct inet_peer_base *base,
 {
 	struct inetpeer_addr daddr;
 
-	daddr.addr.a4 = v4daddr;
+	daddr.a4 = v4daddr;
 	daddr.family = AF_INET;
 	return inet_getpeer(base, &daddr, create);
 }
@@ -116,7 +114,7 @@ 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);
 }
@@ -124,12 +122,12 @@ static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base,
 static inline int inetpeer_addr_cmp(const struct inetpeer_addr *a,
 				    const struct inetpeer_addr *b)
 {
-	int i, n = (a->family == AF_INET ? 1 : 4);
+	int i, n = (a->family == AF_INET ? sizeof(a->a4) : sizeof(a->a6));
 
 	for (i = 0; i < n; i++) {
-		if (a->addr.a6[i] == b->addr.a6[i])
+		if (a->key[i] == b->key[i])
 			continue;
-		if ((__force u32)a->addr.a6[i] < (__force u32)b->addr.a6[i])
+		if (a->key[i] < b->key[i])
 			return -1;
 		return 1;
 	}
-- 
1.9.1

[PATCH net-next 5/5] net: Add support for VRFs to inetpeer cache

[David Ahern]

inetpeer caches based on address only, so duplicate IP addresses within
a namespace return the same cached entry. Enhance the ipv4 address key
to contain both the IPv4 address and VRF device index.

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
 include/net/inetpeer.h | 17 ++++++++++++-----
 net/ipv4/icmp.c        |  3 ++-
 net/ipv4/ip_fragment.c |  3 ++-
 net/ipv4/route.c       |  7 +++++--
 4 files changed, 21 insertions(+), 9 deletions(-)

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index e96bada9d19a..b372004dca3e 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -15,11 +15,17 @@
 #include <net/ipv6.h>
 #include <linux/atomic.h>
 
+/* 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 {
 	union {
-		__be32			a4;
+		struct ipv4_addr_key	a4;
 		struct in6_addr		a6;
 		u32			key[INETPEER_MAXKEYSZ];
 	};
@@ -71,13 +77,13 @@ void inet_initpeers(void) __init;
 
 static inline void inetpeer_set_addr_v4(struct inetpeer_addr *iaddr, __be32 ip)
 {
-	iaddr->a4 = ip;
+	iaddr->a4.addr = ip;
 	iaddr->family = AF_INET;
 }
 
 static inline __be32 inetpeer_get_addr_v4(struct inetpeer_addr *iaddr)
 {
-	return iaddr->a4;
+	return iaddr->a4.addr;
 }
 
 static inline void inetpeer_set_addr_v6(struct inetpeer_addr *iaddr,
@@ -99,11 +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.a4 = v4daddr;
+	daddr.a4.addr = v4daddr;
+	daddr.a4.vif = vif;
 	daddr.family = AF_INET;
 	return inet_getpeer(base, &daddr, create);
 }
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index f16488efa1c8..79fe05befcae 100644
--- a/net/ipv4/icmp.c
+++ b/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)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 15762e758861..fa7f15305f9a 100644
--- a/net/ipv4/ip_fragment.c
+++ b/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)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 0b8a6531ef03..e1a60f6c1aad 100644
--- a/net/ipv4/route.c
+++ b/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) {
-- 
1.9.1

Re: [PATCH net-next 4/5] net: Refactor inetpeer address struct

[David Ahern]

On 8/27/15 2:16 PM, David Ahern wrote:
> @@ -124,12 +122,12 @@ static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base,
>   static inline int inetpeer_addr_cmp(const struct inetpeer_addr *a,
>   				    const struct inetpeer_addr *b)
>   {
> -	int i, n = (a->family == AF_INET ? 1 : 4);
> +	int i, n = (a->family == AF_INET ? sizeof(a->a4) : sizeof(a->a6));

Forgot the / by sizeof(u32) (key size) in this version of the patches. 
v2 coming.

>
>   	for (i = 0; i < n; i++) {
> -		if (a->addr.a6[i] == b->addr.a6[i])
> +		if (a->key[i] == b->key[i])
>   			continue;
> -		if ((__force u32)a->addr.a6[i] < (__force u32)b->addr.a6[i])
> +		if (a->key[i] < b->key[i])
>   			return -1;
>   		return 1;
>   	}
>

RE: [PATCH net-next 3/5] net: Add helper function to compare inetpeer addresses

[David Laight]

From: David Ahern
> Sent: 27 August 2015 22:17
ATCH net-next 3/5] net: Add helper function to compare inetpeer addresses
> 
> tcp_metrics and inetpeer both have functions to compare inetpeer
> addresses. Consolidate into 1 version.
> 
> Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
> ---
...
> diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
> index f75b9e7036a2..9d9b3446731d 100644
> --- a/include/net/inetpeer.h
> +++ b/include/net/inetpeer.h
> @@ -121,6 +121,22 @@ static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base,
>  	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 = (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;
> +}

If the performance of this matters then I'd not use the loop for IPv4
and use u64 comparisons (esp. on 64 bit systems) in an unrolled loop for IPv6.
(Might need to worry about the alignment.)

I presume nothing cares that the ordering relation is endian dependant?
With either byteswapping memory reads or a byteswapping instruction
then an endian-independant ordering should be almost as quick.

	David