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>

4 files changed, 159 insertions, 207 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d2ffeafc9998..b9450784ae06 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1258,7 +1258,7 @@ struct net_device_ops {
  * @IFF_LIVE_ADDR_CHANGE: device supports hardware address
  *	change when it's running
  * @IFF_MACVLAN: Macvlan device
- * @IFF_VRF_MASTER: device is a VRF master
+ * @IFF_L3MDEV_MASTER: device is an L3 master device
  * @IFF_NO_QUEUE: device can run without qdisc attached
  * @IFF_OPENVSWITCH: device is a Open vSwitch master
  */
@@ -1283,7 +1283,7 @@ enum netdev_priv_flags {
 	IFF_XMIT_DST_RELEASE_PERM	= 1<<17,
 	IFF_IPVLAN_MASTER		= 1<<18,
 	IFF_IPVLAN_SLAVE		= 1<<19,
-	IFF_VRF_MASTER			= 1<<20,
+	IFF_L3MDEV_MASTER		= 1<<20,
 	IFF_NO_QUEUE			= 1<<21,
 	IFF_OPENVSWITCH			= 1<<22,
 };
@@ -1308,7 +1308,7 @@ enum netdev_priv_flags {
 #define IFF_XMIT_DST_RELEASE_PERM	IFF_XMIT_DST_RELEASE_PERM
 #define IFF_IPVLAN_MASTER		IFF_IPVLAN_MASTER
 #define IFF_IPVLAN_SLAVE		IFF_IPVLAN_SLAVE
-#define IFF_VRF_MASTER			IFF_VRF_MASTER
+#define IFF_L3MDEV_MASTER		IFF_L3MDEV_MASTER
 #define IFF_NO_QUEUE			IFF_NO_QUEUE
 #define IFF_OPENVSWITCH			IFF_OPENVSWITCH
 
@@ -1427,7 +1427,6 @@ enum netdev_priv_flags {
  *	@dn_ptr:	DECnet specific data
  *	@ip6_ptr:	IPv6 specific data
  *	@ax25_ptr:	AX.25 specific data
- *	@vrf_ptr:	VRF specific data
  *	@ieee80211_ptr:	IEEE 802.11 specific data, assign before registering
  *
  *	@last_rx:	Time of last Rx
@@ -1587,6 +1586,9 @@ struct net_device {
 #ifdef CONFIG_NET_SWITCHDEV
 	const struct switchdev_ops *switchdev_ops;
 #endif
+#ifdef CONFIG_NET_L3_MASTER_DEV
+	const struct l3mdev_ops	*l3mdev_ops;
+#endif
 
 	const struct header_ops *header_ops;
 
@@ -1646,7 +1648,6 @@ struct net_device {
 	struct dn_dev __rcu     *dn_ptr;
 	struct inet6_dev __rcu	*ip6_ptr;
 	void			*ax25_ptr;
-	struct net_vrf_dev __rcu *vrf_ptr;
 	struct wireless_dev	*ieee80211_ptr;
 	struct wpan_dev		*ieee802154_ptr;
 #if IS_ENABLED(CONFIG_MPLS_ROUTING)
@@ -3824,9 +3825,9 @@ static inline bool netif_supports_nofcs(struct net_device *dev)
 	return dev->priv_flags & IFF_SUPP_NOFCS;
 }
 
-static inline bool netif_is_vrf(const struct net_device *dev)
+static inline bool netif_is_l3_master(const struct net_device *dev)
 {
-	return dev->priv_flags & IFF_VRF_MASTER;
+	return dev->priv_flags & IFF_L3MDEV_MASTER;
 }
 
 static inline bool netif_is_bridge_master(const struct net_device *dev)
@@ -3839,27 +3840,6 @@ static inline bool netif_is_ovs_master(const struct net_device *dev)
 	return dev->priv_flags & IFF_OPENVSWITCH;
 }
 
-static inline bool netif_index_is_vrf(struct net *net, int ifindex)
-{
-	bool rc = false;
-
-#if IS_ENABLED(CONFIG_NET_VRF)
-	struct net_device *dev;
-
-	if (ifindex == 0)
-		return false;
-
-	rcu_read_lock();
-
-	dev = dev_get_by_index_rcu(net, ifindex);
-	if (dev)
-		rc = netif_is_vrf(dev);
-
-	rcu_read_unlock();
-#endif
-	return rc;
-}
-
 /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */
 static inline void netif_keep_dst(struct net_device *dev)
 {
diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
new file mode 100644
index 000000000000..87cee05a0a17
--- /dev/null
+++ b/include/net/l3mdev.h
@@ -0,0 +1,149 @@
+/*
+ * include/net/l3mdev.h - L3 master device API
+ * 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.
+ */
+#ifndef _NET_L3MDEV_H_
+#define _NET_L3MDEV_H_
+
+/**
+ * struct l3mdev_ops - l3mdev operations
+ *
+ * @l3mdev_fib_table: Get FIB table id to use for lookups
+ *
+ * @l3mdev_get_rtable: Get cached IPv4 rtable (dst_entry) for device
+ */
+
+struct l3mdev_ops {
+	u32		(*l3mdev_fib_table)(const struct net_device *dev);
+	struct rtable *	(*l3mdev_get_rtable)(const struct net_device *dev,
+					     const struct flowi4 *fl4);
+};
+
+#ifdef CONFIG_NET_L3_MASTER_DEV
+
+int l3mdev_master_ifindex_rcu(struct net_device *dev);
+static inline int l3mdev_master_ifindex(struct net_device *dev)
+{
+	int ifindex;
+
+	rcu_read_lock();
+	ifindex = l3mdev_master_ifindex_rcu(dev);
+	rcu_read_unlock();
+
+	return ifindex;
+}
+
+/* get index of an interface to use for FIB lookups. For devices
+ * enslaved to an L3 master device FIB lookups are based on the
+ * master index
+ */
+static inline int l3mdev_fib_oif_rcu(struct net_device *dev)
+{
+	return l3mdev_master_ifindex_rcu(dev) ? : dev->ifindex;
+}
+
+static inline int l3mdev_fib_oif(struct net_device *dev)
+{
+	int oif;
+
+	rcu_read_lock();
+	oif = l3mdev_fib_oif_rcu(dev);
+	rcu_read_unlock();
+
+	return oif;
+}
+
+u32 l3mdev_fib_table_rcu(const struct net_device *dev);
+u32 l3mdev_fib_table_by_index(struct net *net, int ifindex);
+static inline u32 l3mdev_fib_table(const struct net_device *dev)
+{
+	u32 tb_id;
+
+	rcu_read_lock();
+	tb_id = l3mdev_fib_table_rcu(dev);
+	rcu_read_unlock();
+
+	return tb_id;
+}
+
+static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev,
+					       const struct flowi4 *fl4)
+{
+	if (netif_is_l3_master(dev) && dev->l3mdev_ops->l3mdev_get_rtable)
+		return dev->l3mdev_ops->l3mdev_get_rtable(dev, fl4);
+
+	return NULL;
+}
+
+static inline bool netif_index_is_l3_master(struct net *net, int ifindex)
+{
+	struct net_device *dev;
+	bool rc = false;
+
+	if (ifindex == 0)
+		return false;
+
+	rcu_read_lock();
+
+	dev = dev_get_by_index_rcu(net, ifindex);
+	if (dev)
+		rc = netif_is_l3_master(dev);
+
+	rcu_read_unlock();
+
+	return rc;
+}
+
+#else
+
+static inline int l3mdev_master_ifindex_rcu(struct net_device *dev)
+{
+	return 0;
+}
+static inline int l3mdev_master_ifindex(struct net_device *dev)
+{
+	return 0;
+}
+
+static inline int l3mdev_fib_oif_rcu(struct net_device *dev)
+{
+	return dev ? dev->ifindex : 0;
+}
+static inline int l3mdev_fib_oif(struct net_device *dev)
+{
+	return dev ? dev->ifindex : 0;
+}
+
+static inline u32 l3mdev_fib_table_rcu(const struct net_device *dev)
+{
+	return 0;
+}
+static inline u32 l3mdev_fib_table(const struct net_device *dev)
+{
+	return 0;
+}
+static inline u32 l3mdev_fib_table_by_index(struct net *net, int ifindex)
+{
+	return 0;
+}
+
+static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev,
+					       const struct flowi4 *fl4)
+{
+	return NULL;
+}
+
+static inline bool netif_index_is_l3_master(struct net *net, int ifindex)
+{
+	return false;
+}
+
+#endif
+
+#endif /* _NET_L3MDEV_H_ */
diff --git a/include/net/route.h b/include/net/route.h
index d1bd90bb3187..e211dc167db1 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -28,6 +28,7 @@
 #include <net/inetpeer.h>
 #include <net/flow.h>
 #include <net/inet_sock.h>
+#include <net/l3mdev.h>
 #include <linux/in_route.h>
 #include <linux/rtnetlink.h>
 #include <linux/rcupdate.h>
@@ -256,7 +257,7 @@ 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))
+	if (netif_index_is_l3_master(sock_net(sk), oif))
 		flow_flags |= FLOWI_FLAG_VRFSRC | FLOWI_FLAG_SKIP_NH_OIF;
 
 	flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
diff --git a/include/net/vrf.h b/include/net/vrf.h
deleted file mode 100644
index 593e6094ddd4..000000000000
--- a/include/net/vrf.h
+++ /dev/null
@@ -1,178 +0,0 @@
-/*
- * include/net/net_vrf.h - adds vrf dev structure definitions
- * Copyright (c) 2015 Cumulus Networks
- *
- * 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.
- */
-
-#ifndef __LINUX_NET_VRF_H
-#define __LINUX_NET_VRF_H
-
-struct net_vrf_dev {
-	struct rcu_head		rcu;
-	int                     ifindex; /* ifindex of master dev */
-	u32                     tb_id;   /* table id for VRF */
-};
-
-struct slave {
-	struct list_head	list;
-	struct net_device	*dev;
-};
-
-struct slave_queue {
-	struct list_head	all_slaves;
-};
-
-struct net_vrf {
-	struct slave_queue	queue;
-	struct rtable           *rth;
-	u32			tb_id;
-};
-
-
-#if IS_ENABLED(CONFIG_NET_VRF)
-/* called with rcu_read_lock() */
-static inline int vrf_master_ifindex_rcu(const struct net_device *dev)
-{
-	struct net_vrf_dev *vrf_ptr;
-	int ifindex = 0;
-
-	if (!dev)
-		return 0;
-
-	if (netif_is_vrf(dev)) {
-		ifindex = dev->ifindex;
-	} else {
-		vrf_ptr = rcu_dereference(dev->vrf_ptr);
-		if (vrf_ptr)
-			ifindex = vrf_ptr->ifindex;
-	}
-
-	return ifindex;
-}
-
-static inline int vrf_master_ifindex(const struct net_device *dev)
-{
-	int ifindex;
-
-	rcu_read_lock();
-	ifindex = vrf_master_ifindex_rcu(dev);
-	rcu_read_unlock();
-
-	return ifindex;
-}
-
-/* called with rcu_read_lock */
-static inline u32 vrf_dev_table_rcu(const struct net_device *dev)
-{
-	u32 tb_id = 0;
-
-	if (dev) {
-		struct net_vrf_dev *vrf_ptr;
-
-		vrf_ptr = rcu_dereference(dev->vrf_ptr);
-		if (vrf_ptr)
-			tb_id = vrf_ptr->tb_id;
-	}
-	return tb_id;
-}
-
-static inline u32 vrf_dev_table(const struct net_device *dev)
-{
-	u32 tb_id;
-
-	rcu_read_lock();
-	tb_id = vrf_dev_table_rcu(dev);
-	rcu_read_unlock();
-
-	return tb_id;
-}
-
-static inline u32 vrf_dev_table_ifindex(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 = vrf_dev_table_rcu(dev);
-
-	rcu_read_unlock();
-
-	return tb_id;
-}
-
-/* called with rtnl */
-static inline u32 vrf_dev_table_rtnl(const struct net_device *dev)
-{
-	u32 tb_id = 0;
-
-	if (dev) {
-		struct net_vrf_dev *vrf_ptr;
-
-		vrf_ptr = rtnl_dereference(dev->vrf_ptr);
-		if (vrf_ptr)
-			tb_id = vrf_ptr->tb_id;
-	}
-	return tb_id;
-}
-
-/* caller has already checked netif_is_vrf(dev) */
-static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev)
-{
-	struct rtable *rth = ERR_PTR(-ENETUNREACH);
-	struct net_vrf *vrf = netdev_priv(dev);
-
-	if (vrf) {
-		rth = vrf->rth;
-		atomic_inc(&rth->dst.__refcnt);
-	}
-	return rth;
-}
-
-#else
-static inline int vrf_master_ifindex_rcu(const struct net_device *dev)
-{
-	return 0;
-}
-
-static inline int vrf_master_ifindex(const struct net_device *dev)
-{
-	return 0;
-}
-
-static inline u32 vrf_dev_table_rcu(const struct net_device *dev)
-{
-	return 0;
-}
-
-static inline u32 vrf_dev_table(const struct net_device *dev)
-{
-	return 0;
-}
-
-static inline u32 vrf_dev_table_ifindex(struct net *net, int ifindex)
-{
-	return 0;
-}
-
-static inline u32 vrf_dev_table_rtnl(const struct net_device *dev)
-{
-	return 0;
-}
-
-static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev)
-{
-	return ERR_PTR(-ENETUNREACH);
-}
-#endif
-
-#endif /* __LINUX_NET_VRF_H */