Merge branch 'L3_master_device'

David Ahern says:

====================
net: L3 master device

The VRF device is essentially a Layer 3 master device used to associate
netdevices with a specific routing table and to influence FIB lookups
via 'ip rules' and controlling the oif/iif used for the lookup.

This series generalizes the VRF into L3 master device, l3mdev. Similar
to switchdev it has a Kconfig option and separate set of operations
in net_device allowing it to be completely compiled out if not wanted.
The l3mdev methods rely on the 'master' aspect and use of
netdev_master_upper_dev_get_rcu to retrieve the master device from a
given netdevice if it is enslaved to an L3_MASTER.

The VRF device is converted to use the l3mdev operations. At the end the
vrf_ptr is no longer and removed, as are all direct references to VRF.
The end result is a much simpler implementation for VRF.

Thanks to Nikolay for suggestions (eg., use of the master linkage which
is the key to making this work) and to Roopa, Andy and Shrijeet for
early reviews.

v3
- added license header to l3mdev.c

- export symbols in l3mdev.c for use with GPL modules

- removed netdevice header from l3mdev.h (not needed) and fixed
  typo in comment

v2
- rebased to top of net-next
- addressed Niks comments (checking master, removing extra lines, and
  flipping the order of patches 1 and 2)
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

14 files changed, 141 insertions, 35 deletions

diff --git a/net/Kconfig b/net/Kconfig
index 7021c1bf44d6..127da94ae25e 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -232,6 +232,7 @@ source "net/netlink/Kconfig"
 source "net/mpls/Kconfig"
 source "net/hsr/Kconfig"
 source "net/switchdev/Kconfig"
+source "net/l3mdev/Kconfig"
 
 config RPS
 	bool
diff --git a/net/Makefile b/net/Makefile
index 3995613e5510..a5d04098dfce 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -74,3 +74,6 @@ obj-$(CONFIG_HSR)		+= hsr/
 ifneq ($(CONFIG_NET_SWITCHDEV),)
 obj-y				+= switchdev/
 endif
+ifneq ($(CONFIG_NET_L3_MASTER_DEV),)
+obj-y				+= l3mdev/
+endif
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 3af85eecbe11..11c4ca13ec3b 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -119,7 +119,7 @@
 #ifdef CONFIG_IP_MROUTE
 #include <linux/mroute.h>
 #endif
-#include <net/vrf.h>
+#include <net/l3mdev.h>
 
 
 /* The inetsw table contains everything that inet_create needs to
@@ -446,7 +446,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 			goto out;
 	}
 
-	tb_id = vrf_dev_table_ifindex(net, sk->sk_bound_dev_if) ? : tb_id;
+	tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id;
 	chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id);
 
 	/* Not specified by any standard per-se, however it breaks too
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 6fcbd215cdbc..fac172370276 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -45,7 +45,7 @@
 #include <net/ip_fib.h>
 #include <net/rtnetlink.h>
 #include <net/xfrm.h>
-#include <net/vrf.h>
+#include <net/l3mdev.h>
 #include <trace/events/fib.h>
 
 #ifndef CONFIG_IP_MULTIPLE_TABLES
@@ -255,7 +255,7 @@ EXPORT_SYMBOL(inet_addr_type);
 unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev,
 				__be32 addr)
 {
-	u32 rt_table = vrf_dev_table(dev) ? : RT_TABLE_LOCAL;
+	u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL;
 
 	return __inet_dev_addr_type(net, dev, addr, rt_table);
 }
@@ -268,7 +268,7 @@ unsigned int inet_addr_type_dev_table(struct net *net,
 				      const struct net_device *dev,
 				      __be32 addr)
 {
-	u32 rt_table = vrf_dev_table(dev) ? : RT_TABLE_LOCAL;
+	u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL;
 
 	return __inet_dev_addr_type(net, NULL, addr, rt_table);
 }
@@ -332,7 +332,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	bool dev_match;
 
 	fl4.flowi4_oif = 0;
-	fl4.flowi4_iif = vrf_master_ifindex_rcu(dev);
+	fl4.flowi4_iif = l3mdev_master_ifindex_rcu(dev);
 	if (!fl4.flowi4_iif)
 		fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX;
 	fl4.daddr = src;
@@ -366,7 +366,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 		if (nh->nh_dev == dev) {
 			dev_match = true;
 			break;
-		} else if (vrf_master_ifindex_rcu(nh->nh_dev) == dev->ifindex) {
+		} else if (l3mdev_master_ifindex_rcu(nh->nh_dev) == dev->ifindex) {
 			dev_match = true;
 			break;
 		}
@@ -803,7 +803,7 @@ out:
 static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa)
 {
 	struct net *net = dev_net(ifa->ifa_dev->dev);
-	u32 tb_id = vrf_dev_table_rtnl(ifa->ifa_dev->dev);
+	u32 tb_id = l3mdev_fib_table(ifa->ifa_dev->dev);
 	struct fib_table *tb;
 	struct fib_config cfg = {
 		.fc_protocol = RTPROT_KERNEL,
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index e5eb8ac4089d..6b96dee2800b 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -96,7 +96,7 @@
 #include <net/xfrm.h>
 #include <net/inet_common.h>
 #include <net/ip_fib.h>
-#include <net/vrf.h>
+#include <net/l3mdev.h>
 
 /*
  *	Build xmit assembly blocks
@@ -309,7 +309,7 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
 
 	rc = false;
 	if (icmp_global_allow()) {
-		int vif = vrf_master_ifindex(dst->dev);
+		int vif = l3mdev_master_ifindex(dst->dev);
 		struct inet_peer *peer;
 
 		peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1);
@@ -427,7 +427,7 @@ 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(skb->dev);
+	fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev);
 	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt))
@@ -461,7 +461,7 @@ 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(skb_in->dev);
+	fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev);
 
 	security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
 	rt = __ip_route_output_key(net, fl4);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index fa7f15305f9a..9772b789adf3 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -48,7 +48,7 @@
 #include <linux/inet.h>
 #include <linux/netfilter_ipv4.h>
 #include <net/inet_ecn.h>
-#include <net/vrf.h>
+#include <net/l3mdev.h>
 
 /* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6
  * code now. If you change something here, _PLEASE_ update ipv6/reassembly.c
@@ -78,7 +78,7 @@ struct ipq {
 	u8		ecn; /* RFC3168 support */
 	u16		max_df_size; /* largest frag with DF set seen */
 	int             iif;
-	int             vif;   /* VRF device index */
+	int             vif;   /* L3 master device index */
 	unsigned int    rid;
 	struct inet_peer *peer;
 };
@@ -657,7 +657,7 @@ out_fail:
 int ip_defrag(struct sk_buff *skb, u32 user)
 {
 	struct net_device *dev = skb->dev ? : skb_dst(skb)->dev;
-	int vif = vrf_master_ifindex_rcu(dev);
+	int vif = l3mdev_master_ifindex_rcu(dev);
 	struct net *net = dev_net(dev);
 	struct ipq *qp;
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 06d2c87ed505..aff6766922e8 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1571,7 +1571,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 	}
 
 	oif = arg->bound_dev_if;
-	if (!oif && netif_index_is_vrf(net, skb->skb_iif))
+	if (!oif && netif_index_is_l3_master(net, skb->skb_iif))
 		oif = skb->skb_iif;
 
 	flowi4_init_output(&fl4, oif,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8c84a6664b30..1441de1550e6 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -112,7 +112,7 @@
 #endif
 #include <net/secure_seq.h>
 #include <net/ip_tunnels.h>
-#include <net/vrf.h>
+#include <net/l3mdev.h>
 
 #define RT_FL_TOS(oldflp4) \
 	((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
@@ -847,7 +847,7 @@ 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);
+	vif = l3mdev_master_ifindex_rcu(rt->dst.dev);
 	rcu_read_unlock();
 
 	net = dev_net(rt->dst.dev);
@@ -941,7 +941,7 @@ static int ip_error(struct sk_buff *skb)
 	}
 
 	peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr,
-			       vrf_master_ifindex(skb->dev), 1);
+			       l3mdev_master_ifindex(skb->dev), 1);
 
 	send = true;
 	if (peer) {
@@ -1739,7 +1739,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	 *	Now we are ready to route packet.
 	 */
 	fl4.flowi4_oif = 0;
-	fl4.flowi4_iif = vrf_master_ifindex_rcu(dev) ? : dev->ifindex;
+	fl4.flowi4_iif = l3mdev_fib_oif_rcu(dev);
 	fl4.flowi4_mark = skb->mark;
 	fl4.flowi4_tos = tos;
 	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
@@ -2124,11 +2124,10 @@ 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);
+
+		rth = l3mdev_get_rtable(dev_out, fl4);
+		if (rth)
 			goto out;
-		}
 	}
 
 	if (!fl4->daddr) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index f7d1d5e19e95..156ba75b6000 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1021,7 +1021,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		 * device lookup source address from VRF table. This mimics
 		 * behavior of ip_route_connect{_init}.
 		 */
-		if (netif_index_is_vrf(net, ipc.oif)) {
+		if (netif_index_is_l3_master(net, ipc.oif)) {
 			flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
 					   RT_SCOPE_UNIVERSE, sk->sk_protocol,
 					   (flow_flags | FLOWI_FLAG_VRFSRC |
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 0304d1680ca2..f2606b9056bb 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -15,7 +15,7 @@
 #include <net/dst.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
-#include <net/vrf.h>
+#include <net/l3mdev.h>
 
 static struct xfrm_policy_afinfo xfrm4_policy_afinfo;
 
@@ -111,10 +111,8 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 	struct flowi4 *fl4 = &fl->u.ip4;
 	int oif = 0;
 
-	if (skb_dst(skb)) {
-		oif = vrf_master_ifindex(skb_dst(skb)->dev) ?
-			: skb_dst(skb)->dev->ifindex;
-	}
+	if (skb_dst(skb))
+		oif = l3mdev_fib_oif(skb_dst(skb)->dev);
 
 	memset(fl4, 0, sizeof(struct flowi4));
 	fl4->flowi4_mark = skb->mark;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 30caa289c5db..69cee4e0d728 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -20,7 +20,7 @@
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
-#include <net/vrf.h>
+#include <net/l3mdev.h>
 #if IS_ENABLED(CONFIG_IPV6_MIP6)
 #include <net/mip6.h>
 #endif
@@ -132,10 +132,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 
 	nexthdr = nh[nhoff];
 
-	if (skb_dst(skb)) {
-		oif = vrf_master_ifindex(skb_dst(skb)->dev) ?
-			: skb_dst(skb)->dev->ifindex;
-	}
+	if (skb_dst(skb))
+		oif = l3mdev_fib_oif(skb_dst(skb)->dev);
 
 	memset(fl6, 0, sizeof(struct flowi6));
 	fl6->flowi6_mark = skb->mark;
diff --git a/net/l3mdev/Kconfig b/net/l3mdev/Kconfig
new file mode 100644
index 000000000000..5d47325037bc
--- /dev/null
+++ b/net/l3mdev/Kconfig
@@ -0,0 +1,10 @@
+#
+# Configuration for L3 master device support
+#
+
+config NET_L3_MASTER_DEV
+	bool "L3 Master device support"
+	depends on INET || IPV6
+	---help---
+	  This module provides glue between core networking code and device
+	  drivers to support L3 master devices like VRF.
diff --git a/net/l3mdev/Makefile b/net/l3mdev/Makefile
new file mode 100644
index 000000000000..84a53a6f609a
--- /dev/null
+++ b/net/l3mdev/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the L3 device API
+#
+
+obj-$(CONFIG_NET_L3_MASTER_DEV) += l3mdev.o
diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c
new file mode 100644
index 000000000000..ddf75ad41713
--- /dev/null
+++ b/net/l3mdev/l3mdev.c
@@ -0,0 +1,92 @@
+/*
+ * net/l3mdev/l3mdev.c - L3 master device implementation
+ * Copyright (c) 2015 Cumulus Networks
+ * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/netdevice.h>
+#include <net/l3mdev.h>
+
+/**
+ *	l3mdev_master_ifindex - get index of L3 master device
+ *	@dev: targeted interface
+ */
+
+int l3mdev_master_ifindex_rcu(struct net_device *dev)
+{
+	int ifindex = 0;
+
+	if (!dev)
+		return 0;
+
+	if (netif_is_l3_master(dev)) {
+		ifindex = dev->ifindex;
+	} else if (dev->flags & IFF_SLAVE) {
+		struct net_device *master;
+
+		master = netdev_master_upper_dev_get_rcu(dev);
+		if (master && netif_is_l3_master(master))
+			ifindex = master->ifindex;
+	}
+
+	return ifindex;
+}
+EXPORT_SYMBOL_GPL(l3mdev_master_ifindex_rcu);
+
+/**
+ *	l3mdev_fib_table - get FIB table id associated with an L3
+ *                             master interface
+ *	@dev: targeted interface
+ */
+
+u32 l3mdev_fib_table_rcu(const struct net_device *dev)
+{
+	u32 tb_id = 0;
+
+	if (!dev)
+		return 0;
+
+	if (netif_is_l3_master(dev)) {
+		if (dev->l3mdev_ops->l3mdev_fib_table)
+			tb_id = dev->l3mdev_ops->l3mdev_fib_table(dev);
+	} else if (dev->flags & IFF_SLAVE) {
+		/* Users of netdev_master_upper_dev_get_rcu need non-const,
+		 * but current inet_*type functions take a const
+		 */
+		struct net_device *_dev = (struct net_device *) dev;
+		const struct net_device *master;
+
+		master = netdev_master_upper_dev_get_rcu(_dev);
+		if (master && netif_is_l3_master(master) &&
+		    master->l3mdev_ops->l3mdev_fib_table)
+			tb_id = master->l3mdev_ops->l3mdev_fib_table(master);
+	}
+
+	return tb_id;
+}
+EXPORT_SYMBOL_GPL(l3mdev_fib_table_rcu);
+
+u32 l3mdev_fib_table_by_index(struct net *net, int ifindex)
+{
+	struct net_device *dev;
+	u32 tb_id = 0;
+
+	if (!ifindex)
+		return 0;
+
+	rcu_read_lock();
+
+	dev = dev_get_by_index_rcu(net, ifindex);
+	if (dev)
+		tb_id = l3mdev_fib_table_rcu(dev);
+
+	rcu_read_unlock();
+
+	return tb_id;
+}
+EXPORT_SYMBOL_GPL(l3mdev_fib_table_by_index);