net: l3mdev: Add hook in ip and ipv6

Currently the VRF driver uses the rx_handler to switch the skb device
to the VRF device. Switching the dev prior to the ip / ipv6 layer
means the VRF driver has to duplicate IP/IPv6 processing which adds
overhead and makes features such as retaining the ingress device index
more complicated than necessary.

This patch moves the hook to the L3 layer just after the first NF_HOOK
for PRE_ROUTING. This location makes exposing the original ingress device
trivial (next patch) and allows adding other NF_HOOKs to the VRF driver
in the future.

dev_queue_xmit_nit is exported so that the VRF driver can cycle the skb
with the switched device through the packet taps to maintain current
behavior (tcpdump can be used on either the vrf device or the enslaved
devices).

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

2 files changed, 45 insertions, 1 deletions

diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
index 78872bd1dc2c..374388dc01c8 100644
--- a/include/net/l3mdev.h
+++ b/include/net/l3mdev.h
@@ -25,6 +25,8 @@
 
 struct l3mdev_ops {
         u32             (*l3mdev_fib_table)(const struct net_device *dev);
+        struct sk_buff * (*l3mdev_l3_rcv)(struct net_device *dev,
+                                          struct sk_buff *skb, u16 proto);
 
         /* IPv4 ops */
         struct rtable * (*l3mdev_get_rtable)(const struct net_device *dev,
@@ -134,6 +136,34 @@ int l3mdev_get_saddr(struct net *net, int ifindex, struct flowi4 *fl4);
 
 struct dst_entry *l3mdev_get_rt6_dst(struct net *net, const struct flowi6 *fl6);
 
+static inline
+struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto)
+{
+        struct net_device *master = NULL;
+
+        if (netif_is_l3_slave(skb->dev))
+                master = netdev_master_upper_dev_get_rcu(skb->dev);
+        else if (netif_is_l3_master(skb->dev))
+                master = skb->dev;
+
+        if (master && master->l3mdev_ops->l3mdev_l3_rcv)
+                skb = master->l3mdev_ops->l3mdev_l3_rcv(master, skb, proto);
+
+        return skb;
+}
+
+static inline
+struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb)
+{
+        return l3mdev_l3_rcv(skb, AF_INET);
+}
+
+static inline
+struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb)
+{
+        return l3mdev_l3_rcv(skb, AF_INET6);
+}
+
 #else
 
 static inline int l3mdev_master_ifindex_rcu(const struct net_device *dev)
@@ -194,6 +224,18 @@ struct dst_entry *l3mdev_get_rt6_dst(struct net *net, const struct flowi6 *fl6)
 {
         return NULL;
 }
+
+static inline
+struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb)
+{
+        return skb;
+}
+
+static inline
+struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb)
+{
+        return skb;
+}
 #endif
 
 #endif /* _NET_L3MDEV_H_ */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index c9ab561387c4..0bcc70f4e1fb 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -786,7 +786,9 @@ struct tcp_skb_cb {
  */
 static inline int tcp_v6_iif(const struct sk_buff *skb)
 {
-        return TCP_SKB_CB(skb)->header.h6.iif;
+        bool l3_slave = skb_l3mdev_slave(TCP_SKB_CB(skb)->header.h6.flags);
+
+        return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif;
 }
 #endif