From 36393395536064e483b73d173f6afc103eadfbc4 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 14 Jun 2012 22:21:46 -0700
Subject: ipv4: Handle PMTU in all ICMP error handlers.

With ip_rt_frag_needed() removed, we have to explicitly update PMTU
information in every ICMP error handler.

Create two helper functions to facilitate this.

1) ipv4_sk_update_pmtu()

   This updates the PMTU when we have a socket context to
   work with.

2) ipv4_update_pmtu()

   Raw version, used when no socket context is available.  For this
   interface, we essentially just pass in explicit arguments for
   the flow identity information we would have extracted from the
   socket.

   And you'll notice that ipv4_sk_update_pmtu() is simply implemented
   in terms of ipv4_update_pmtu()

Note that __ip_route_output_key() is used, rather than something like
ip_route_output_flow() or ip_route_output_key().  This is because we
absolutely do not want to end up with a route that does IPSEC
encapsulation and the like.  Instead, we only want the route that
would get us to the node described by the outermost IP header.

Reported-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

(limited to 'net/ipv4/ip_gre.c')

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index f49047b7960..594cec35ac4 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -516,9 +516,6 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
 		case ICMP_PORT_UNREACH:
 			/* Impossible event. */
 			return;
-		case ICMP_FRAG_NEEDED:
-			/* Soft state for pmtu is maintained by IP core. */
-			return;
 		default:
 			/* All others are translated to HOST_UNREACH.
 			   rfc2003 contains "deep thoughts" about NET_UNREACH,
@@ -538,7 +535,16 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
 				flags & GRE_KEY ?
 				*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
 				p[1]);
-	if (t == NULL || t->parms.iph.daddr == 0 ||
+	if (t == NULL)
+		goto out;
+
+	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
+		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
+				 t->parms.link, 0, IPPROTO_GRE, 0);
+		goto out;
+	}
+
+	if (t->parms.iph.daddr == 0 ||
 	    ipv4_is_multicast(t->parms.iph.daddr))
 		goto out;
 
-- 
cgit v1.2.3-70-g09d2


From 55be7a9c6074f749d617a7fc1914c9a23505438c Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 11 Jul 2012 21:27:49 -0700
Subject: ipv4: Add redirect support to all protocol icmp error handlers.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv4.c         | 11 +++++++++++
 net/ipv4/ah4.c          | 18 +++++++++++++-----
 net/ipv4/esp4.c         | 18 +++++++++++++-----
 net/ipv4/ip_gre.c       |  9 ++++++++-
 net/ipv4/ipcomp.c       | 18 +++++++++++++-----
 net/ipv4/ipip.c         |  9 +++++++++
 net/ipv4/ping.c         |  1 +
 net/ipv4/raw.c          |  2 ++
 net/ipv4/tcp_ipv4.c     | 11 +++++++++++
 net/ipv4/udp.c          |  3 +++
 net/ipv4/xfrm4_policy.c | 10 ++++++++++
 net/sctp/input.c        | 16 ++++++++++++++++
 12 files changed, 110 insertions(+), 16 deletions(-)

(limited to 'net/ipv4/ip_gre.c')

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 3eb76b5f221..8f41a319085 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -195,6 +195,14 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk,
 	} /* else let the usual retransmit timer handle it */
 }
 
+static void dccp_do_redirect(struct sk_buff *skb, struct sock *sk)
+{
+	struct dst_entry *dst = __sk_dst_check(sk, 0);
+
+	if (dst && dst->ops->redirect)
+		dst->ops->redirect(dst, skb);
+}
+
 /*
  * This routine is called by the ICMP module when it gets some sort of error
  * condition. If err < 0 then the socket should be closed and the error
@@ -259,6 +267,9 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 	}
 
 	switch (type) {
+	case ICMP_REDIRECT:
+		dccp_do_redirect(skb, sk);
+		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
 		goto out;
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 916d5ecaf6c..a0d8392491c 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -398,17 +398,25 @@ static void ah4_err(struct sk_buff *skb, u32 info)
 	struct ip_auth_hdr *ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2));
 	struct xfrm_state *x;
 
-	if (icmp_hdr(skb)->type != ICMP_DEST_UNREACH ||
-	    icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
+	switch (icmp_hdr(skb)->type) {
+	case ICMP_DEST_UNREACH:
+		if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
+			return;
+	case ICMP_REDIRECT:
+		break;
+	default:
 		return;
+	}
 
 	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
 			      ah->spi, IPPROTO_AH, AF_INET);
 	if (!x)
 		return;
-	pr_debug("pmtu discovery on SA AH/%08x/%08x\n",
-		 ntohl(ah->spi), ntohl(iph->daddr));
-	ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0);
+
+	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
+		ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0);
+	else
+		ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0);
 	xfrm_state_put(x);
 }
 
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 7b95b49a36c..b61e9deb7c7 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -484,17 +484,25 @@ static void esp4_err(struct sk_buff *skb, u32 info)
 	struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
 	struct xfrm_state *x;
 
-	if (icmp_hdr(skb)->type != ICMP_DEST_UNREACH ||
-	    icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
+	switch (icmp_hdr(skb)->type) {
+	case ICMP_DEST_UNREACH:
+		if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
+			return;
+	case ICMP_REDIRECT:
+		break;
+	default:
 		return;
+	}
 
 	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
 			      esph->spi, IPPROTO_ESP, AF_INET);
 	if (!x)
 		return;
-	NETDEBUG(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%08x\n",
-		 ntohl(esph->spi), ntohl(iph->daddr));
-	ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0);
+
+	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
+		ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0);
+	else
+		ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0);
 	xfrm_state_put(x);
 }
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 594cec35ac4..0c3123566d7 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -528,6 +528,9 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
 		if (code != ICMP_EXC_TTL)
 			return;
 		break;
+
+	case ICMP_REDIRECT:
+		break;
 	}
 
 	rcu_read_lock();
@@ -543,7 +546,11 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
 				 t->parms.link, 0, IPPROTO_GRE, 0);
 		goto out;
 	}
-
+	if (type == ICMP_REDIRECT) {
+		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
+			      IPPROTO_GRE, 0);
+		goto out;
+	}
 	if (t->parms.iph.daddr == 0 ||
 	    ipv4_is_multicast(t->parms.iph.daddr))
 		goto out;
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index b91375482d8..d3ab47e19a8 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -31,18 +31,26 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info)
 	struct ip_comp_hdr *ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2));
 	struct xfrm_state *x;
 
-	if (icmp_hdr(skb)->type != ICMP_DEST_UNREACH ||
-	    icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
+	switch (icmp_hdr(skb)->type) {
+	case ICMP_DEST_UNREACH:
+		if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
+			return;
+	case ICMP_REDIRECT:
+		break;
+	default:
 		return;
+	}
 
 	spi = htonl(ntohs(ipch->cpi));
 	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
 			      spi, IPPROTO_COMP, AF_INET);
 	if (!x)
 		return;
-	NETDEBUG(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/%pI4\n",
-		 spi, &iph->daddr);
-	ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0);
+
+	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
+		ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0);
+	else
+		ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0);
 	xfrm_state_put(x);
 }
 
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 715338a1b20..c2d0e6d8baa 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -360,6 +360,8 @@ static int ipip_err(struct sk_buff *skb, u32 info)
 		if (code != ICMP_EXC_TTL)
 			return 0;
 		break;
+	case ICMP_REDIRECT:
+		break;
 	}
 
 	err = -ENOENT;
@@ -376,6 +378,13 @@ static int ipip_err(struct sk_buff *skb, u32 info)
 		goto out;
 	}
 
+	if (type == ICMP_REDIRECT) {
+		ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
+			      IPPROTO_IPIP, 0);
+		err = 0;
+		goto out;
+	}
+
 	if (t->parms.iph.daddr == 0)
 		goto out;
 
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 340fcf29a96..6232d476f37 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -387,6 +387,7 @@ void ping_err(struct sk_buff *skb, u32 info)
 		break;
 	case ICMP_REDIRECT:
 		/* See ICMP_SOURCE_QUENCH */
+		ipv4_sk_redirect(skb, sk);
 		err = EREMOTEIO;
 		break;
 	}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 659ddfb1094..ff0f071969e 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -218,6 +218,8 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
 		ipv4_sk_update_pmtu(skb, sk, info);
+	else if (type == ICMP_REDIRECT)
+		ipv4_sk_redirect(skb, sk);
 
 	/* Report error on raw socket, if:
 	   1. User requested ip_recverr.
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 01545a3fc0f..087a8488843 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -321,6 +321,14 @@ static void do_pmtu_discovery(struct sock *sk, const struct iphdr *iph, u32 mtu)
 	} /* else let the usual retransmit timer handle it */
 }
 
+static void do_redirect(struct sk_buff *skb, struct sock *sk)
+{
+	struct dst_entry *dst = __sk_dst_check(sk, 0);
+
+	if (dst && dst->ops->redirect)
+		dst->ops->redirect(dst, skb);
+}
+
 /*
  * This routine is called by the ICMP module when it gets some
  * sort of error condition.  If err < 0 then the socket should
@@ -394,6 +402,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	}
 
 	switch (type) {
+	case ICMP_REDIRECT:
+		do_redirect(icmp_skb, sk);
+		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
 		goto out;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ee37d47d472..b4c3582a991 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -630,6 +630,9 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 			err = icmp_err_convert[code].errno;
 		}
 		break;
+	case ICMP_REDIRECT:
+		ipv4_sk_redirect(skb, sk);
+		break;
 	}
 
 	/*
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 87d3fcc302d..258ebd7b268 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -202,6 +202,15 @@ static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu)
 	path->ops->update_pmtu(path, mtu);
 }
 
+static void xfrm4_redirect(struct dst_entry *dst, struct sk_buff *skb)
+{
+	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
+	struct dst_entry *path = xdst->route;
+
+	if (path->ops->redirect)
+		path->ops->redirect(path, skb);
+}
+
 static void xfrm4_dst_destroy(struct dst_entry *dst)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
@@ -225,6 +234,7 @@ static struct dst_ops xfrm4_dst_ops = {
 	.protocol =		cpu_to_be16(ETH_P_IP),
 	.gc =			xfrm4_garbage_collect,
 	.update_pmtu =		xfrm4_update_pmtu,
+	.redirect =		xfrm4_redirect,
 	.cow_metrics =		dst_cow_metrics_generic,
 	.destroy =		xfrm4_dst_destroy,
 	.ifdown =		xfrm4_dst_ifdown,
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 80564fe0302..9fb4247f9a9 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -423,6 +423,18 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
 	sctp_retransmit(&asoc->outqueue, t, SCTP_RTXR_PMTUD);
 }
 
+static void sctp_icmp_redirect(struct sock *sk, struct sctp_transport *t,
+			       struct sk_buff *skb)
+{
+	struct dst_entry *dst;
+
+	if (!t)
+		return;
+	dst = sctp_transport_dst_check(t);
+	if (dst && dst->ops->redirect)
+		dst->ops->redirect(dst, skb);
+}
+
 /*
  * SCTP Implementer's Guide, 2.37 ICMP handling procedures
  *
@@ -628,6 +640,10 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info)
 
 		err = EHOSTUNREACH;
 		break;
+	case ICMP_REDIRECT:
+		sctp_icmp_redirect(sk, transport, skb);
+		err = 0;
+		break;
 	default:
 		goto out_unlock;
 	}
-- 
cgit v1.2.3-70-g09d2


From 6700c2709c08d74ae2c3c29b84a30da012dbc7f1 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 17 Jul 2012 03:29:28 -0700
Subject: net: Pass optional SKB and SK arguments to
 dst_ops->{update_pmtu,redirect}()

This will be used so that we can compose a full flow key.

Even though we have a route in this context, we need more.  In the
future the routes will be without destination address, source address,
etc. keying.  One ipv4 route will cover entire subnets, etc.

In this environment we have to have a way to possess persistent storage
for redirects and PMTU information.  This persistent storage will exist
in the FIB tables, and that's why we'll need to be able to rebuild a
full lookup flow key here.  Using that flow key will do a fib_lookup()
and create/update the persistent entry.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/ulp/ipoib/ipoib_cm.c |  2 +-
 include/net/dst_ops.h                   |  6 ++++--
 net/bridge/br_netfilter.c               |  6 ++++--
 net/dccp/ipv4.c                         |  2 +-
 net/dccp/ipv6.c                         |  2 +-
 net/decnet/dn_route.c                   | 12 ++++++++----
 net/ipv4/inet_connection_sock.c         |  2 +-
 net/ipv4/ip_gre.c                       |  2 +-
 net/ipv4/ipip.c                         |  2 +-
 net/ipv4/route.c                        | 21 +++++++++++++--------
 net/ipv4/tcp_ipv4.c                     |  2 +-
 net/ipv4/xfrm4_policy.c                 | 10 ++++++----
 net/ipv6/inet6_connection_sock.c        |  2 +-
 net/ipv6/ip6_tunnel.c                   |  6 +++---
 net/ipv6/route.c                        | 21 +++++++++++++--------
 net/ipv6/sit.c                          |  2 +-
 net/ipv6/tcp_ipv6.c                     |  2 +-
 net/ipv6/xfrm6_policy.c                 | 10 ++++++----
 net/netfilter/ipvs/ip_vs_xmit.c         |  4 ++--
 net/sctp/input.c                        |  2 +-
 net/sctp/transport.c                    |  2 +-
 21 files changed, 71 insertions(+), 49 deletions(-)

(limited to 'net/ipv4/ip_gre.c')

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 014504d8e43..1ca732201f3 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1397,7 +1397,7 @@ void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb,
 	int e = skb_queue_empty(&priv->cm.skb_queue);
 
 	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
 	skb_queue_tail(&priv->cm.skb_queue, skb);
 	if (e)
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 085931fa7ce..d079fc61c12 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -24,8 +24,10 @@ struct dst_ops {
 					  struct net_device *dev, int how);
 	struct dst_entry *	(*negative_advice)(struct dst_entry *);
 	void			(*link_failure)(struct sk_buff *);
-	void			(*update_pmtu)(struct dst_entry *dst, u32 mtu);
-	void			(*redirect)(struct dst_entry *dst, struct sk_buff *skb);
+	void			(*update_pmtu)(struct dst_entry *dst, struct sock *sk,
+					       struct sk_buff *skb, u32 mtu);
+	void			(*redirect)(struct dst_entry *dst, struct sock *sk,
+					    struct sk_buff *skb);
 	int			(*local_out)(struct sk_buff *skb);
 	struct neighbour *	(*neigh_lookup)(const struct dst_entry *dst,
 						struct sk_buff *skb,
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 81f76c402cf..68e8f364bbf 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -111,11 +111,13 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb)
 	 pppoe_proto(skb) == htons(PPP_IPV6) && \
 	 brnf_filter_pppoe_tagged)
 
-static void fake_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			     struct sk_buff *skb, u32 mtu)
 {
 }
 
-static void fake_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void fake_redirect(struct dst_entry *dst, struct sock *sk,
+			  struct sk_buff *skb)
 {
 }
 
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 683902fcc8e..ab4f44c9bb2 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -193,7 +193,7 @@ static void dccp_do_redirect(struct sk_buff *skb, struct sock *sk)
 	struct dst_entry *dst = __sk_dst_check(sk, 0);
 
 	if (dst)
-		dst->ops->redirect(dst, skb);
+		dst->ops->redirect(dst, sk, skb);
 }
 
 /*
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 3ee0342e1ce..56840b249f3 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -134,7 +134,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
 		if (dst)
-			dst->ops->redirect(dst, skb);
+			dst->ops->redirect(dst, sk, skb);
 	}
 
 	if (type == ICMPV6_PKT_TOOBIG) {
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index e9c4e2e864c..47de90d8fe9 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -117,8 +117,10 @@ static void dn_dst_destroy(struct dst_entry *);
 static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how);
 static struct dst_entry *dn_dst_negative_advice(struct dst_entry *);
 static void dn_dst_link_failure(struct sk_buff *);
-static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu);
-static void dn_dst_redirect(struct dst_entry *dst, struct sk_buff *skb);
+static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			       struct sk_buff *skb , u32 mtu);
+static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk,
+			    struct sk_buff *skb);
 static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst,
 					     struct sk_buff *skb,
 					     const void *daddr);
@@ -266,7 +268,8 @@ static int dn_dst_gc(struct dst_ops *ops)
  * We update both the mtu and the advertised mss (i.e. the segment size we
  * advertise to the other end).
  */
-static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			       struct sk_buff *skb, u32 mtu)
 {
 	struct dn_route *rt = (struct dn_route *) dst;
 	struct neighbour *n = rt->n;
@@ -294,7 +297,8 @@ static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu)
 	}
 }
 
-static void dn_dst_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk,
+			    struct sk_buff *skb)
 {
 }
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 200d2180937..3ea465286a3 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -840,7 +840,7 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu)
 		if (!dst)
 			goto out;
 	}
-	dst->ops->update_pmtu(dst, mtu);
+	dst->ops->update_pmtu(dst, sk, NULL, mtu);
 
 	dst = __sk_dst_check(sk, 0);
 	if (!dst)
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 0c3123566d7..42c44b1403c 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -833,7 +833,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 		mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
 
 	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		df |= (old_iph->frag_off&htons(IP_DF));
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index c2d0e6d8baa..2c2c35bace7 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -519,7 +519,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 
 		if (skb_dst(skb))
-			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
 		if ((old_iph->frag_off & htons(IP_DF)) &&
 		    mtu < ntohs(old_iph->tot_len)) {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index aad21819316..b35d3bfc66c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -148,8 +148,10 @@ static unsigned int	 ipv4_mtu(const struct dst_entry *dst);
 static void		 ipv4_dst_destroy(struct dst_entry *dst);
 static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
 static void		 ipv4_link_failure(struct sk_buff *skb);
-static void		 ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
-static void		 ip_do_redirect(struct dst_entry *dst, struct sk_buff *skb);
+static void		 ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
+					   struct sk_buff *skb, u32 mtu);
+static void		 ip_do_redirect(struct dst_entry *dst, struct sock *sk,
+					struct sk_buff *skb);
 static int rt_garbage_collect(struct dst_ops *ops);
 
 static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -1273,7 +1275,7 @@ static void rt_del(unsigned int hash, struct rtable *rt)
 	spin_unlock_bh(rt_hash_lock_addr(hash));
 }
 
-static void ip_do_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb)
 {
 	__be32 new_gw = icmp_hdr(skb)->un.gateway;
 	__be32 old_gw = ip_hdr(skb)->saddr;
@@ -1506,7 +1508,8 @@ out:	kfree_skb(skb);
 	return 0;
 }
 
-static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			      struct sk_buff *skb, u32 mtu)
 {
 	struct rtable *rt = (struct rtable *) dst;
 
@@ -1531,7 +1534,7 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
 			   iph->daddr, iph->saddr, 0, 0);
 	rt = __ip_route_output_key(net, &fl4);
 	if (!IS_ERR(rt)) {
-		ip_rt_update_pmtu(&rt->dst, mtu);
+		ip_rt_update_pmtu(&rt->dst, NULL, skb, mtu);
 		ip_rt_put(rt);
 	}
 }
@@ -1559,7 +1562,7 @@ void ipv4_redirect(struct sk_buff *skb, struct net *net,
 			   protocol, flow_flags, iph->daddr, iph->saddr, 0, 0);
 	rt = __ip_route_output_key(net, &fl4);
 	if (!IS_ERR(rt)) {
-		ip_do_redirect(&rt->dst, skb);
+		ip_do_redirect(&rt->dst, NULL, skb);
 		ip_rt_put(rt);
 	}
 }
@@ -2587,11 +2590,13 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
 	return mtu ? : dst->dev->mtu;
 }
 
-static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
+					  struct sk_buff *skb, u32 mtu)
 {
 }
 
-static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
+				       struct sk_buff *skb)
 {
 }
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b8e7e059540..d9caf5c07aa 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -319,7 +319,7 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk)
 	struct dst_entry *dst = __sk_dst_check(sk, 0);
 
 	if (dst)
-		dst->ops->redirect(dst, skb);
+		dst->ops->redirect(dst, sk, skb);
 }
 
 /*
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 737131cef37..fcf7678bc00 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -194,20 +194,22 @@ static inline int xfrm4_garbage_collect(struct dst_ops *ops)
 	return (dst_entries_get_slow(ops) > ops->gc_thresh * 2);
 }
 
-static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			      struct sk_buff *skb, u32 mtu)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->update_pmtu(path, mtu);
+	path->ops->update_pmtu(path, sk, skb, mtu);
 }
 
-static void xfrm4_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk,
+			   struct sk_buff *skb)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->redirect(path, skb);
+	path->ops->redirect(path, sk, skb);
 }
 
 static void xfrm4_dst_destroy(struct dst_entry *dst)
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 62539a4b2dc..4a0c4d2d8b0 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -269,7 +269,7 @@ struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu)
 
 	if (IS_ERR(dst))
 		return NULL;
-	dst->ops->update_pmtu(dst, mtu);
+	dst->ops->update_pmtu(dst, sk, NULL, mtu);
 
 	return inet6_csk_route_socket(sk);
 }
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 61d10659729..db328466796 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -609,10 +609,10 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (rel_info > dst_mtu(skb_dst(skb2)))
 			goto out;
 
-		skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), rel_info);
+		skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2, rel_info);
 	}
 	if (rel_type == ICMP_REDIRECT)
-		skb_dst(skb2)->ops->redirect(skb_dst(skb2), skb2);
+		skb_dst(skb2)->ops->redirect(skb_dst(skb2), NULL, skb2);
 
 	icmp_send(skb2, rel_type, rel_code, htonl(rel_info));
 
@@ -952,7 +952,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 	if (skb->len > mtu) {
 		*pmtu = mtu;
 		err = -EMSGSIZE;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 2a4c8d48977..31af1ed6c1d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -78,8 +78,10 @@ static int		 ip6_dst_gc(struct dst_ops *ops);
 static int		ip6_pkt_discard(struct sk_buff *skb);
 static int		ip6_pkt_discard_out(struct sk_buff *skb);
 static void		ip6_link_failure(struct sk_buff *skb);
-static void		ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
-static void		rt6_do_redirect(struct dst_entry *dst, struct sk_buff *skb);
+static void		ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
+					   struct sk_buff *skb, u32 mtu);
+static void		rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
+					struct sk_buff *skb);
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
 static struct rt6_info *rt6_add_route_info(struct net *net,
@@ -187,11 +189,13 @@ static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst)
 	return mtu ? : dst->dev->mtu;
 }
 
-static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
+					 struct sk_buff *skb, u32 mtu)
 {
 }
 
-static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
+				      struct sk_buff *skb)
 {
 }
 
@@ -1071,7 +1075,8 @@ static void ip6_link_failure(struct sk_buff *skb)
 	}
 }
 
-static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			       struct sk_buff *skb, u32 mtu)
 {
 	struct rt6_info *rt6 = (struct rt6_info*)dst;
 
@@ -1108,7 +1113,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
 
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (!dst->error)
-		ip6_rt_update_pmtu(dst, ntohl(mtu));
+		ip6_rt_update_pmtu(dst, NULL, skb, ntohl(mtu));
 	dst_release(dst);
 }
 EXPORT_SYMBOL_GPL(ip6_update_pmtu);
@@ -1136,7 +1141,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
 
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (!dst->error)
-		rt6_do_redirect(dst, skb);
+		rt6_do_redirect(dst, NULL, skb);
 	dst_release(dst);
 }
 EXPORT_SYMBOL_GPL(ip6_redirect);
@@ -1639,7 +1644,7 @@ static int ip6_route_del(struct fib6_config *cfg)
 	return err;
 }
 
-static void rt6_do_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
 	struct netevent_redirect netevent;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index fbf1622fdee..3bd1bfc01f8 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -807,7 +807,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		}
 
 		if (tunnel->parms.iph.daddr && skb_dst(skb))
-			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
 		if (skb->len > mtu) {
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index ecdf241cad0..c9dabdd832d 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -367,7 +367,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
 		if (dst)
-			dst->ops->redirect(dst,skb);
+			dst->ops->redirect(dst, sk, skb);
 	}
 
 	if (type == ICMPV6_PKT_TOOBIG) {
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index f5a9cb8257b..ef39812107b 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -207,20 +207,22 @@ static inline int xfrm6_garbage_collect(struct dst_ops *ops)
 	return dst_entries_get_fast(ops) > ops->gc_thresh * 2;
 }
 
-static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			      struct sk_buff *skb, u32 mtu)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->update_pmtu(path, mtu);
+	path->ops->update_pmtu(path, sk, skb, mtu);
 }
 
-static void xfrm6_redirect(struct dst_entry *dst, struct sk_buff *skb)
+static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk,
+			   struct sk_buff *skb)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->redirect(path, skb);
+	path->ops->redirect(path, sk, skb);
 }
 
 static void xfrm6_dst_destroy(struct dst_entry *dst)
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 71d6ecb6592..65b616ae171 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -797,7 +797,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		goto tx_error_put;
 	}
 	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
 	df |= (old_iph->frag_off & htons(IP_DF));
 
@@ -913,7 +913,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		goto tx_error_put;
 	}
 	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
 	if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) &&
 	    !skb_is_gso(skb)) {
diff --git a/net/sctp/input.c b/net/sctp/input.c
index a67bc31f49f..c201b26879a 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -432,7 +432,7 @@ void sctp_icmp_redirect(struct sock *sk, struct sctp_transport *t,
 		return;
 	dst = sctp_transport_dst_check(t);
 	if (dst)
-		dst->ops->redirect(dst, skb);
+		dst->ops->redirect(dst, sk, skb);
 }
 
 /*
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index e69e1a2175a..a6b7ee9ce28 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -249,7 +249,7 @@ void sctp_transport_update_pmtu(struct sock *sk, struct sctp_transport *t, u32 p
 		t->af_specific->get_dst(t, &t->saddr, &t->fl, sk);
 
 	if (dst) {
-		dst->ops->update_pmtu(dst, pmtu);
+		dst->ops->update_pmtu(dst, sk, NULL, pmtu);
 
 		dst = sctp_transport_dst_check(t);
 		if (!dst)
-- 
cgit v1.2.3-70-g09d2


From f8126f1d5136be1ca1a3536d43ad7a710b5620f8 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 13 Jul 2012 05:03:45 -0700
Subject: ipv4: Adjust semantics of rt->rt_gateway.

In order to allow prefixed routes, we have to adjust how rt_gateway
is set and interpreted.

The new interpretation is:

1) rt_gateway == 0, destination is on-link, nexthop is iph->daddr

2) rt_gateway != 0, destination requires a nexthop gateway

Abstract the fetching of the proper nexthop value using a new
inline helper, rt_nexthop(), as suggested by Joe Perches.

Signed-off-by: David S. Miller <davem@davemloft.net>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
---
 include/net/route.h                 |  7 +++++++
 net/ipv4/arp.c                      |  3 +--
 net/ipv4/inet_connection_sock.c     |  4 ++--
 net/ipv4/ip_gre.c                   |  2 +-
 net/ipv4/ip_output.c                |  2 +-
 net/ipv4/ipip.c                     |  2 +-
 net/ipv4/netfilter/ipt_MASQUERADE.c |  5 +++--
 net/ipv4/route.c                    | 17 +++++++++--------
 8 files changed, 25 insertions(+), 17 deletions(-)

(limited to 'net/ipv4/ip_gre.c')

diff --git a/include/net/route.h b/include/net/route.h
index 6d111bceb16..3c1eeab9749 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -70,6 +70,13 @@ static inline bool rt_is_output_route(const struct rtable *rt)
 	return rt->rt_route_iif == 0;
 }
 
+static inline __be32 rt_nexthop(const struct rtable *rt, __be32 daddr)
+{
+	if (rt->rt_gateway)
+		return rt->rt_gateway;
+	return daddr;
+}
+
 struct ip_rt_acct {
 	__u32 	o_bytes;
 	__u32 	o_packets;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index c38293f3816..a0124eb7dbe 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -475,8 +475,7 @@ int arp_find(unsigned char *haddr, struct sk_buff *skb)
 		return 1;
 	}
 
-	paddr = skb_rtable(skb)->rt_gateway;
-
+	paddr = rt_nexthop(skb_rtable(skb), ip_hdr(skb)->daddr);
 	if (arp_set_predefined(inet_addr_type(dev_net(dev), paddr), haddr,
 			       paddr, dev))
 		return 0;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index c7a4de05ca0..0a290d719bc 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -389,7 +389,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
-	if (opt && opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway)
+	if (opt && opt->opt.is_strictroute && rt->rt_gateway)
 		goto route_err;
 	return &rt->dst;
 
@@ -422,7 +422,7 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
-	if (opt && opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway)
+	if (opt && opt->opt.is_strictroute && rt->rt_gateway)
 		goto route_err;
 	return &rt->dst;
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 42c44b1403c..b062a98574f 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -766,7 +766,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 
 		if (skb->protocol == htons(ETH_P_IP)) {
 			rt = skb_rtable(skb);
-			dst = rt->rt_gateway;
+			dst = rt_nexthop(rt, old_iph->daddr);
 		}
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (skb->protocol == htons(ETH_P_IPV6)) {
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c528f841ca4..4494015f7e3 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -371,7 +371,7 @@ int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl)
 	skb_dst_set_noref(skb, &rt->dst);
 
 packet_routed:
-	if (inet_opt && inet_opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway)
+	if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gateway)
 		goto no_route;
 
 	/* OK, we know where to send it, allocate and build IP header. */
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 2c2c35bace7..99af1f0cc65 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -487,7 +487,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 			dev->stats.tx_fifo_errors++;
 			goto tx_error;
 		}
-		dst = rt->rt_gateway;
+		dst = rt_nexthop(rt, old_iph->daddr);
 	}
 
 	rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index 2f210c79dc8..cbb6a1a6f6f 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -52,7 +52,7 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	struct nf_nat_ipv4_range newrange;
 	const struct nf_nat_ipv4_multi_range_compat *mr;
 	const struct rtable *rt;
-	__be32 newsrc;
+	__be32 newsrc, nh;
 
 	NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING);
 
@@ -70,7 +70,8 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
 
 	mr = par->targinfo;
 	rt = skb_rtable(skb);
-	newsrc = inet_select_addr(par->out, rt->rt_gateway, RT_SCOPE_UNIVERSE);
+	nh = rt_nexthop(rt, ip_hdr(skb)->daddr);
+	newsrc = inet_select_addr(par->out, nh, RT_SCOPE_UNIVERSE);
 	if (!newsrc) {
 		pr_info("%s ate my IP address\n", par->out->name);
 		return NF_DROP;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 85d103fee88..d1d57963809 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1085,8 +1085,9 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
 		if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res) == 0)
 			src = FIB_RES_PREFSRC(dev_net(rt->dst.dev), res);
 		else
-			src = inet_select_addr(rt->dst.dev, rt->rt_gateway,
-					RT_SCOPE_UNIVERSE);
+			src = inet_select_addr(rt->dst.dev,
+					       rt_nexthop(rt, iph->daddr),
+					       RT_SCOPE_UNIVERSE);
 		rcu_read_unlock();
 	}
 	memcpy(addr, &src, 4);
@@ -1132,7 +1133,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	mtu = dst->dev->mtu;
 
 	if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
-		if (rt->rt_gateway != 0 && mtu > 576)
+		if (rt->rt_gateway && mtu > 576)
 			mtu = 576;
 	}
 
@@ -1274,7 +1275,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	rth->rt_iif	= dev->ifindex;
 	rth->rt_oif	= 0;
 	rth->rt_pmtu	= 0;
-	rth->rt_gateway	= daddr;
+	rth->rt_gateway	= 0;
 	rth->fi = NULL;
 	if (our) {
 		rth->dst.input= ip_local_deliver;
@@ -1392,7 +1393,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->rt_iif 	= in_dev->dev->ifindex;
 	rth->rt_oif 	= 0;
 	rth->rt_pmtu	= 0;
-	rth->rt_gateway	= daddr;
+	rth->rt_gateway	= 0;
 	rth->fi = NULL;
 
 	rth->dst.input = ip_forward;
@@ -1557,7 +1558,7 @@ local_input:
 	rth->rt_iif	= dev->ifindex;
 	rth->rt_oif	= 0;
 	rth->rt_pmtu	= 0;
-	rth->rt_gateway	= daddr;
+	rth->rt_gateway	= 0;
 	rth->fi = NULL;
 	if (res.type == RTN_UNREACHABLE) {
 		rth->dst.input= ip_error;
@@ -1707,7 +1708,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	rth->rt_iif	= orig_oif ? : dev_out->ifindex;
 	rth->rt_oif	= orig_oif;
 	rth->rt_pmtu	= 0;
-	rth->rt_gateway = fl4->daddr;
+	rth->rt_gateway = 0;
 	rth->fi = NULL;
 
 	RT_CACHE_STAT_INC(out_slow_tot);
@@ -2070,7 +2071,7 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 		if (nla_put_be32(skb, RTA_PREFSRC, fl4->saddr))
 			goto nla_put_failure;
 	}
-	if (fl4->daddr != rt->rt_gateway &&
+	if (rt->rt_gateway &&
 	    nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway))
 		goto nla_put_failure;
 
-- 
cgit v1.2.3-70-g09d2