net: l3mdev: Add hook to output path

This patch adds the infrastructure to the output path to pass an skb
to an l3mdev device if it has a hook registered. This is the Tx parallel
to l3mdev_ip{6}_rcv in the receive path and is the basis for removing
the existing hook that returns the vrf dst on the fib lookup.

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

include/net/l3mdev.h

@@ -11,6 +11,7 @@
 #ifndef _NET_L3MDEV_H_
 #define _NET_L3MDEV_H_
 
+#include <net/dst.h>
 #include <net/fib_rules.h>
 
 /**
@@ -18,6 +19,10 @@
  *
  * @l3mdev_fib_table: Get FIB table id to use for lookups
  *
+ * @l3mdev_l3_rcv:    Hook in L3 receive path
+ *
+ * @l3mdev_l3_out:    Hook in L3 output path
+ *
  * @l3mdev_get_rtable: Get cached IPv4 rtable (dst_entry) for device
  *
  * @l3mdev_get_saddr: Get source address for a flow
@@ -29,6 +34,9 @@ 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);
+	struct sk_buff * (*l3mdev_l3_out)(struct net_device *dev,
+					  struct sock *sk, struct sk_buff *skb,
+					  u16 proto);
 
 	/* IPv4 ops */
 	struct rtable *	(*l3mdev_get_rtable)(const struct net_device *dev,
@@ -201,6 +209,34 @@ struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb)
 	return l3mdev_l3_rcv(skb, AF_INET6);
 }
 
+static inline
+struct sk_buff *l3mdev_l3_out(struct sock *sk, struct sk_buff *skb, u16 proto)
+{
+	struct net_device *dev = skb_dst(skb)->dev;
+
+	if (netif_is_l3_slave(dev)) {
+		struct net_device *master;
+
+		master = netdev_master_upper_dev_get_rcu(dev);
+		if (master && master->l3mdev_ops->l3mdev_l3_out)
+			skb = master->l3mdev_ops->l3mdev_l3_out(master, sk,
+								skb, proto);
+	}
+
+	return skb;
+}
+
+static inline
+struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb)
+{
+	return l3mdev_l3_out(sk, skb, AF_INET);
+}
+
+static inline
+struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb)
+{
+	return l3mdev_l3_out(sk, skb, AF_INET6);
+}
 #else
 
 static inline int l3mdev_master_ifindex_rcu(const struct net_device *dev)
@@ -286,6 +322,18 @@ struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb)
 	return skb;
 }
 
+static inline
+struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb)
+{
+	return skb;
+}
+
+static inline
+struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb)
+{
+	return skb;
+}
+
 static inline
 int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
 			  struct fib_lookup_arg *arg)

net/ipv4/ip_output.c

@@ -99,6 +99,14 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 
 	iph->tot_len = htons(skb->len);
 	ip_send_check(iph);
+
+	/* if egress device is enslaved to an L3 master device pass the
+	 * skb to its handler for processing
+	 */
+	skb = l3mdev_ip_out(sk, skb);
+	if (unlikely(!skb))
+		return 0;
+
 	return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
 		       net, sk, skb, NULL, skb_dst(skb)->dev,
 		       dst_output);

net/ipv6/ip6_output.c

@@ -236,6 +236,14 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
 		IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
 			      IPSTATS_MIB_OUT, skb->len);
+
+		/* if egress device is enslaved to an L3 master device pass the
+		 * skb to its handler for processing
+		 */
+		skb = l3mdev_ip6_out((struct sock *)sk, skb);
+		if (unlikely(!skb))
+			return 0;
+
 		/* hooks should never assume socket lock is held.
 		 * we promote our socket to non const
 		 */

net/ipv6/output_core.c

@@ -148,6 +148,13 @@ int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 	ipv6_hdr(skb)->payload_len = htons(len);
 	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
 
+	/* if egress device is enslaved to an L3 master device pass the
+	 * skb to its handler for processing
+	 */
+	skb = l3mdev_ip6_out(sk, skb);
+	if (unlikely(!skb))
+		return 0;
+
 	return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
 		       net, sk, skb, NULL, skb_dst(skb)->dev,
 		       dst_output);

net/ipv6/raw.c

@@ -653,6 +653,13 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 	if (err)
 		goto error_fault;
 
+	/* if egress device is enslaved to an L3 master device pass the
+	 * skb to its handler for processing
+	 */
+	skb = l3mdev_ip6_out(sk, skb);
+	if (unlikely(!skb))
+		return 0;
+
 	IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
 	err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb,
 		      NULL, rt->dst.dev, dst_output);