net: vrf: ipv6 support for local traffic to local addresses

Add support for locally originated traffic to VRF-local IPv6 addresses.
Similar to IPv4 a local dst is set on the skb and the packet is
reinserted with a call to netif_rx. With this patch, ping, tcp and udp
packets to a local IPv6 address are successfully routed:

    $ ip addr show dev eth1
    4: eth1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast master red state UP group default qlen 1000
        link/ether 02:e0:f9:1c:b9:74 brd ff:ff:ff:ff:ff:ff
        inet 10.100.1.1/24 brd 10.100.1.255 scope global eth1
           valid_lft forever preferred_lft forever
        inet6 2100:1::1/120 scope global
           valid_lft forever preferred_lft forever
        inet6 fe80::e0:f9ff:fe1c:b974/64 scope link
           valid_lft forever preferred_lft forever

    $ ping6 -c1 -I red 2100:1::1
    ping6: Warning: source address might be selected on device other than red.
    PING 2100:1::1(2100:1::1) from 2100:1::1 red: 56 data bytes
    64 bytes from 2100:1::1: icmp_seq=1 ttl=64 time=0.098 ms

ip6_input is exported so the VRF driver can use it for the dst input
function. The dst_alloc function for IPv4 defaults to setting the input and
output functions; IPv6's does not. VRF does not need to duplicate the Rx path
so just export the ipv6 input function.

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David Ahern 2016-06-02 13:15:12 -07:00 committed by David S. Miller
parent 671cd19ade
commit 625b47b507
1 changed files with 85 additions and 4 deletions

View File

@ -46,6 +46,7 @@ struct net_vrf {
struct rtable __rcu *rth;
struct rtable __rcu *rth_local;
struct rt6_info __rcu *rt6;
struct rt6_info __rcu *rt6_local;
u32 tb_id;
};
@ -157,6 +158,46 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
goto err;
skb_dst_drop(skb);
/* if dst.dev is loopback or the VRF device again this is locally
* originated traffic destined to a local address. Short circuit
* to Rx path using our local dst
*/
if (dst->dev == net->loopback_dev || dst->dev == dev) {
struct net_vrf *vrf = netdev_priv(dev);
struct rt6_info *rt6_local;
/* release looked up dst and use cached local dst */
dst_release(dst);
rcu_read_lock();
rt6_local = rcu_dereference(vrf->rt6_local);
if (unlikely(!rt6_local)) {
rcu_read_unlock();
goto err;
}
/* Ordering issue: cached local dst is created on newlink
* before the IPv6 initialization. Using the local dst
* requires rt6i_idev to be set so make sure it is.
*/
if (unlikely(!rt6_local->rt6i_idev)) {
rt6_local->rt6i_idev = in6_dev_get(dev);
if (!rt6_local->rt6i_idev) {
rcu_read_unlock();
goto err;
}
}
dst = &rt6_local->dst;
dst_hold(dst);
rcu_read_unlock();
return vrf_local_xmit(skb, dev, &rt6_local->dst);
}
skb_dst_set(skb, dst);
/* strip the ethernet header added for pass through VRF device */
@ -336,27 +377,38 @@ static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb)
static void vrf_rt6_release(struct net_vrf *vrf)
{
struct rt6_info *rt6 = rtnl_dereference(vrf->rt6);
struct rt6_info *rt6_local = rtnl_dereference(vrf->rt6_local);
rcu_assign_pointer(vrf->rt6, NULL);
RCU_INIT_POINTER(vrf->rt6, NULL);
RCU_INIT_POINTER(vrf->rt6_local, NULL);
synchronize_rcu();
if (rt6)
dst_release(&rt6->dst);
if (rt6_local) {
if (rt6_local->rt6i_idev)
in6_dev_put(rt6_local->rt6i_idev);
dst_release(&rt6_local->dst);
}
}
static int vrf_rt6_create(struct net_device *dev)
{
int flags = DST_HOST | DST_NOPOLICY | DST_NOXFRM | DST_NOCACHE;
struct net_vrf *vrf = netdev_priv(dev);
struct net *net = dev_net(dev);
struct fib6_table *rt6i_table;
struct rt6_info *rt6;
struct rt6_info *rt6, *rt6_local;
int rc = -ENOMEM;
rt6i_table = fib6_new_table(net, vrf->tb_id);
if (!rt6i_table)
goto out;
rt6 = ip6_dst_alloc(net, dev,
DST_HOST | DST_NOPOLICY | DST_NOXFRM | DST_NOCACHE);
/* create a dst for routing packets out a VRF device */
rt6 = ip6_dst_alloc(net, dev, flags);
if (!rt6)
goto out;
@ -364,7 +416,25 @@ static int vrf_rt6_create(struct net_device *dev)
rt6->rt6i_table = rt6i_table;
rt6->dst.output = vrf_output6;
/* create a dst for local routing - packets sent locally
* to local address via the VRF device as a loopback
*/
rt6_local = ip6_dst_alloc(net, dev, flags);
if (!rt6_local) {
dst_release(&rt6->dst);
goto out;
}
dst_hold(&rt6_local->dst);
rt6_local->rt6i_idev = in6_dev_get(dev);
rt6_local->rt6i_flags = RTF_UP | RTF_NONEXTHOP | RTF_LOCAL;
rt6_local->rt6i_table = rt6i_table;
rt6_local->dst.input = ip6_input;
rcu_assign_pointer(vrf->rt6, rt6);
rcu_assign_pointer(vrf->rt6_local, rt6_local);
rc = 0;
out:
@ -710,6 +780,16 @@ out:
static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
struct sk_buff *skb)
{
/* loopback traffic; do not push through packet taps again.
* Reset pkt_type for upper layers to process skb
*/
if (skb->pkt_type == PACKET_LOOPBACK) {
skb->dev = vrf_dev;
skb->skb_iif = vrf_dev->ifindex;
skb->pkt_type = PACKET_HOST;
goto out;
}
/* if packet is NDISC keep the ingress interface */
if (!ipv6_ndisc_frame(skb)) {
skb->dev = vrf_dev;
@ -722,6 +802,7 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
IP6CB(skb)->flags |= IP6SKB_L3SLAVE;
}
out:
return skb;
}