linux/include/net/l3mdev.h
David Ahern 96c63fa739 net: Add l3mdev rule
Currently, VRFs require 1 oif and 1 iif rule per address family per
VRF. As the number of VRF devices increases it brings scalability
issues with the increasing rule list. All of the VRF rules have the
same format with the exception of the specific table id to direct the
lookup. Since the table id is available from the oif or iif in the
loopup, the VRF rules can be consolidated to a single rule that pulls
the table from the VRF device.

This patch introduces a new rule attribute l3mdev. The l3mdev rule
means the table id used for the lookup is pulled from the L3 master
device (e.g., VRF) rather than being statically defined. With the
l3mdev rule all of the basic VRF FIB rules are reduced to 1 l3mdev
rule per address family (IPv4 and IPv6).

If an admin wishes to insert higher priority rules for specific VRFs
those rules will co-exist with the l3mdev rule. This capability means
current VRF scripts will co-exist with this new simpler implementation.

Currently, the rules list for both ipv4 and ipv6 look like this:
    $ ip  ru ls
    1000:       from all oif vrf1 lookup 1001
    1000:       from all iif vrf1 lookup 1001
    1000:       from all oif vrf2 lookup 1002
    1000:       from all iif vrf2 lookup 1002
    1000:       from all oif vrf3 lookup 1003
    1000:       from all iif vrf3 lookup 1003
    1000:       from all oif vrf4 lookup 1004
    1000:       from all iif vrf4 lookup 1004
    1000:       from all oif vrf5 lookup 1005
    1000:       from all iif vrf5 lookup 1005
    1000:       from all oif vrf6 lookup 1006
    1000:       from all iif vrf6 lookup 1006
    1000:       from all oif vrf7 lookup 1007
    1000:       from all iif vrf7 lookup 1007
    1000:       from all oif vrf8 lookup 1008
    1000:       from all iif vrf8 lookup 1008
    ...
    32765:      from all lookup local
    32766:      from all lookup main
    32767:      from all lookup default

With the l3mdev rule the list is just the following regardless of the
number of VRFs:
    $ ip ru ls
    1000:       from all lookup [l3mdev table]
    32765:      from all lookup local
    32766:      from all lookup main
    32767:      from all lookup default

(Note: the above pretty print of the rule is based on an iproute2
       prototype. Actual verbage may change)

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-08 11:36:02 -07:00

254 lines
5.4 KiB
C

/*
* 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_
#include <net/fib_rules.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
*
* @l3mdev_get_saddr: Get source address for a flow
*
* @l3mdev_get_rt6_dst: Get cached IPv6 rt6_info (dst_entry) for device
*/
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,
const struct flowi4 *fl4);
int (*l3mdev_get_saddr)(struct net_device *dev,
struct flowi4 *fl4);
/* IPv6 ops */
struct dst_entry * (*l3mdev_get_rt6_dst)(const struct net_device *dev,
const struct flowi6 *fl6);
};
#ifdef CONFIG_NET_L3_MASTER_DEV
int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
struct fib_lookup_arg *arg);
int l3mdev_master_ifindex_rcu(const 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;
}
static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex)
{
struct net_device *dev;
int rc = 0;
if (likely(ifindex)) {
rcu_read_lock();
dev = dev_get_by_index_rcu(net, ifindex);
if (dev)
rc = l3mdev_master_ifindex_rcu(dev);
rcu_read_unlock();
}
return rc;
}
/* 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;
}
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)
{
return 0;
}
static inline int l3mdev_master_ifindex(struct net_device *dev)
{
return 0;
}
static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex)
{
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;
}
static inline int l3mdev_get_saddr(struct net *net, int ifindex,
struct flowi4 *fl4)
{
return 0;
}
static inline
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;
}
static inline
int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
struct fib_lookup_arg *arg)
{
return 1;
}
#endif
#endif /* _NET_L3MDEV_H_ */