net: Use VRF device index for lookups on TX

As with ingress use the index of VRF master device for route lookups on
egress. However, the oif should only be used to direct the lookups to a
specific table. Routes in the table are not based on the VRF device but
rather interfaces that are part of the VRF so do not consider the oif for
lookups within the table. The FLOWI_FLAG_VRFSRC is used to control this
latter part.

Signed-off-by: Shrijeet Mukherjee <shm@cumulusnetworks.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 18 insertions, 2 deletions

diff --git a/include/net/flow.h b/include/net/flow.h
index 3098ae3..f305588 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -33,6 +33,7 @@ struct flowi_common {
 	__u8	flowic_flags;
 #define FLOWI_FLAG_ANYSRC		0x01
 #define FLOWI_FLAG_KNOWN_NH		0x02
+#define FLOWI_FLAG_VRFSRC		0x04
 	__u32	flowic_secid;
 	struct flowi_tunnel flowic_tun_key;
 };
diff --git a/include/net/route.h b/include/net/route.h
index 2d45f41..94189d4 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -251,6 +251,9 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32
 	if (inet_sk(sk)->transparent)
 		flow_flags |= FLOWI_FLAG_ANYSRC;
 
+	if (netif_index_is_vrf(sock_net(sk), oif))
+		flow_flags |= FLOWI_FLAG_VRFSRC;
+
 	flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
 			   protocol, flow_flags, dst, src, dport, sport);
 }
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 37c4bb8..1243c79 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1423,8 +1423,11 @@ found:
 			    nh->nh_flags & RTNH_F_LINKDOWN &&
 			    !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
 				continue;
-			if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif)
-				continue;
+			if (!(flp->flowi4_flags & FLOWI_FLAG_VRFSRC)) {
+				if (flp->flowi4_oif &&
+				    flp->flowi4_oif != nh->nh_oif)
+					continue;
+			}
 
 			if (!(fib_flags & FIB_LOOKUP_NOREF))
 				atomic_inc(&fi->fib_clntref);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index c0556f1..1164fc4 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -96,6 +96,7 @@
 #include <net/xfrm.h>
 #include <net/inet_common.h>
 #include <net/ip_fib.h>
+#include <net/vrf.h>
 
 /*
  *	Build xmit assembly blocks
@@ -425,6 +426,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	fl4.flowi4_mark = mark;
 	fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
 	fl4.flowi4_proto = IPPROTO_ICMP;
+	fl4.flowi4_oif = vrf_master_ifindex_rcu(skb->dev) ? : skb->dev->ifindex;
 	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt))
@@ -458,6 +460,8 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	fl4->flowi4_proto = IPPROTO_ICMP;
 	fl4->fl4_icmp_type = type;
 	fl4->fl4_icmp_code = code;
+	fl4->flowi4_oif = vrf_master_ifindex_rcu(skb_in->dev) ? : skb_in->dev->ifindex;
+
 	security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
 	rt = __ip_route_output_key(net, fl4);
 	if (IS_ERR(rt))
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c26ff1f..2c89d29 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2131,6 +2131,11 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 				fl4->saddr = inet_select_addr(dev_out, 0,
 							      RT_SCOPE_HOST);
 		}
+		if (netif_is_vrf(dev_out) &&
+		    !(fl4->flowi4_flags & FLOWI_FLAG_VRFSRC)) {
+			rth = vrf_dev_get_rth(dev_out);
+			goto out;
+		}
 	}
 
 	if (!fl4->daddr) {