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 <[email protected]>

Author: davem330

MAINTAINERS

@@ -6095,6 +6095,13 @@ F:	Documentation/auxdisplay/ks0108
 F:	drivers/auxdisplay/ks0108.c
 F:	include/linux/ks0108.h
 
+L3MDEV
+M:	David Ahern <[email protected]>
+L:	[email protected]
+S:	Maintained
+F:	net/l3mdev
+F:	include/net/l3mdev.h
+
 LAPB module
 L:	[email protected]
 S:	Orphan
@@ -11266,7 +11273,6 @@ M:	Shrijeet Mukherjee <[email protected]>
 L:	[email protected]
 S:	Maintained
 F:	drivers/net/vrf.c
-F:	include/net/vrf.h
 F:	Documentation/networking/vrf.txt
 
 VT1211 HARDWARE MONITOR DRIVER

drivers/net/Kconfig

@@ -299,6 +299,7 @@ config NLMON
 config NET_VRF
 	tristate "Virtual Routing and Forwarding (Lite)"
 	depends on IP_MULTIPLE_TABLES && IPV6_MULTIPLE_TABLES
+	depends on NET_L3_MASTER_DEV
 	---help---
 	  This option enables the support for mapping interfaces into VRF's. The
 	  support enables VRF devices.

drivers/net/vrf.c

@@ -34,7 +34,7 @@
 #include <net/rtnetlink.h>
 #include <net/route.h>
 #include <net/addrconf.h>
-#include <net/vrf.h>
+#include <net/l3mdev.h>
 
 #define DRV_NAME	"vrf"
 #define DRV_VERSION	"1.0"
@@ -44,6 +44,21 @@
 #define vrf_master_get_rcu(dev) \
 	((struct net_device *)rcu_dereference(dev->rx_handler_data))
 
+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;
+};
+
 struct pcpu_dstats {
 	u64			tx_pkts;
 	u64			tx_bytes;
@@ -395,18 +410,15 @@ static void __vrf_insert_slave(struct slave_queue *queue, struct slave *slave)
 
 static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
 {
-	struct net_vrf_dev *vrf_ptr = kmalloc(sizeof(*vrf_ptr), GFP_KERNEL);
 	struct slave *slave = kzalloc(sizeof(*slave), GFP_KERNEL);
 	struct net_vrf *vrf = netdev_priv(dev);
 	struct slave_queue *queue = &vrf->queue;
 	int ret = -ENOMEM;
 
-	if (!slave || !vrf_ptr)
+	if (!slave)
 		goto out_fail;
 
 	slave->dev = port_dev;
-	vrf_ptr->ifindex = dev->ifindex;
-	vrf_ptr->tb_id = vrf->tb_id;
 
 	/* register the packet handler for slave ports */
 	ret = netdev_rx_handler_register(port_dev, vrf_handle_frame, dev);
@@ -423,22 +435,20 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
 
 	port_dev->flags |= IFF_SLAVE;
 	__vrf_insert_slave(queue, slave);
-	rcu_assign_pointer(port_dev->vrf_ptr, vrf_ptr);
 	cycle_netdev(port_dev);
 
 	return 0;
 
 out_unregister:
 	netdev_rx_handler_unregister(port_dev);
 out_fail:
-	kfree(vrf_ptr);
 	kfree(slave);
 	return ret;
 }
 
 static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
 {
-	if (netif_is_vrf(port_dev) || vrf_is_slave(port_dev))
+	if (netif_is_l3_master(port_dev) || vrf_is_slave(port_dev))
 		return -EINVAL;
 
 	return do_vrf_add_slave(dev, port_dev);
@@ -447,21 +457,15 @@ static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
 /* inverse of do_vrf_add_slave */
 static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev)
 {
-	struct net_vrf_dev *vrf_ptr = rtnl_dereference(port_dev->vrf_ptr);
 	struct net_vrf *vrf = netdev_priv(dev);
 	struct slave_queue *queue = &vrf->queue;
 	struct slave *slave;
 
-	RCU_INIT_POINTER(port_dev->vrf_ptr, NULL);
-
 	netdev_upper_dev_unlink(port_dev, dev);
 	port_dev->flags &= ~IFF_SLAVE;
 
 	netdev_rx_handler_unregister(port_dev);
 
-	/* after netdev_rx_handler_unregister for synchronize_rcu */
-	kfree(vrf_ptr);
-
 	cycle_netdev(port_dev);
 
 	slave = __vrf_find_slave_dev(queue, port_dev);
@@ -529,6 +533,33 @@ static const struct net_device_ops vrf_netdev_ops = {
 	.ndo_del_slave		= vrf_del_slave,
 };
 
+static u32 vrf_fib_table(const struct net_device *dev)
+{
+	struct net_vrf *vrf = netdev_priv(dev);
+
+	return vrf->tb_id;
+}
+
+static struct rtable *vrf_get_rtable(const struct net_device *dev,
+				     const struct flowi4 *fl4)
+{
+	struct rtable *rth = NULL;
+
+	if (!(fl4->flowi4_flags & FLOWI_FLAG_VRFSRC)) {
+		struct net_vrf *vrf = netdev_priv(dev);
+
+		rth = vrf->rth;
+		atomic_inc(&rth->dst.__refcnt);
+	}
+
+	return rth;
+}
+
+static const struct l3mdev_ops vrf_l3mdev_ops = {
+	.l3mdev_fib_table	= vrf_fib_table,
+	.l3mdev_get_rtable	= vrf_get_rtable,
+};
+
 static void vrf_get_drvinfo(struct net_device *dev,
 			    struct ethtool_drvinfo *info)
 {
@@ -546,6 +577,7 @@ static void vrf_setup(struct net_device *dev)
 
 	/* Initialize the device structure. */
 	dev->netdev_ops = &vrf_netdev_ops;
+	dev->l3mdev_ops = &vrf_l3mdev_ops;
 	dev->ethtool_ops = &vrf_ethtool_ops;
 	dev->destructor = free_netdev;
 
@@ -572,45 +604,29 @@ static int vrf_validate(struct nlattr *tb[], struct nlattr *data[])
 
 static void vrf_dellink(struct net_device *dev, struct list_head *head)
 {
-	struct net_vrf_dev *vrf_ptr = rtnl_dereference(dev->vrf_ptr);
-
-	RCU_INIT_POINTER(dev->vrf_ptr, NULL);
-	kfree_rcu(vrf_ptr, rcu);
 	unregister_netdevice_queue(dev, head);
 }
 
 static int vrf_newlink(struct net *src_net, struct net_device *dev,
 		       struct nlattr *tb[], struct nlattr *data[])
 {
 	struct net_vrf *vrf = netdev_priv(dev);
-	struct net_vrf_dev *vrf_ptr;
 	int err;
 
 	if (!data || !data[IFLA_VRF_TABLE])
 		return -EINVAL;
 
 	vrf->tb_id = nla_get_u32(data[IFLA_VRF_TABLE]);
 
-	dev->priv_flags |= IFF_VRF_MASTER;
-
-	err = -ENOMEM;
-	vrf_ptr = kmalloc(sizeof(*dev->vrf_ptr), GFP_KERNEL);
-	if (!vrf_ptr)
-		goto out_fail;
-
-	vrf_ptr->ifindex = dev->ifindex;
-	vrf_ptr->tb_id = vrf->tb_id;
+	dev->priv_flags |= IFF_L3MDEV_MASTER;
 
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto out_fail;
 
-	rcu_assign_pointer(dev->vrf_ptr, vrf_ptr);
-
 	return 0;
 
 out_fail:
-	kfree(vrf_ptr);
 	free_netdev(dev);
 	return err;
 }
@@ -654,10 +670,9 @@ static int vrf_device_event(struct notifier_block *unused,
 
 	/* only care about unregister events to drop slave references */
 	if (event == NETDEV_UNREGISTER) {
-		struct net_vrf_dev *vrf_ptr = rtnl_dereference(dev->vrf_ptr);
 		struct net_device *vrf_dev;
 
-		if (!vrf_ptr || netif_is_vrf(dev))
+		if (netif_is_l3_master(dev))
 			goto out;
 
 		vrf_dev = netdev_master_upper_dev_get(dev);

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)
 {