net: Add VRF support to IPv6 stack
As with IPv4 support for VRFs added to IPv6 stack by replacing hardcoded
table ids with possibly device specific ones and manipulating the oif in
the flowi6. The flow flags are used to skip oif compare in nexthop lookups
if the device is enslaved to a VRF via the L3 master device.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index db5b54a..5fc1149 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -61,6 +61,7 @@
#include <net/nexthop.h>
#include <net/lwtunnel.h>
#include <net/ip_tunnels.h>
+#include <net/l3mdev.h>
#include <asm/uaccess.h>
@@ -1044,6 +1045,9 @@
fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
saved_fn = fn;
+ if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF)
+ oif = 0;
+
redo_rt6_select:
rt = rt6_select(fn, oif, strict);
if (rt->rt6i_nsiblings)
@@ -1141,7 +1145,7 @@
int flags = RT6_LOOKUP_F_HAS_SADDR;
struct ip_tunnel_info *tun_info;
struct flowi6 fl6 = {
- .flowi6_iif = skb->dev->ifindex,
+ .flowi6_iif = l3mdev_fib_oif(skb->dev),
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowlabel = ip6_flowinfo(iph),
@@ -1165,8 +1169,13 @@
struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
struct flowi6 *fl6)
{
+ struct dst_entry *dst;
int flags = 0;
+ dst = l3mdev_rt6_dst_by_oif(net, fl6);
+ if (dst)
+ return dst;
+
fl6->flowi6_iif = LOOPBACK_IFINDEX;
if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) ||
@@ -2263,7 +2272,6 @@
unsigned int pref)
{
struct fib6_config cfg = {
- .fc_table = RT6_TABLE_INFO,
.fc_metric = IP6_RT_PRIO_USER,
.fc_ifindex = ifindex,
.fc_dst_len = prefixlen,
@@ -2274,6 +2282,7 @@
.fc_nlinfo.nl_net = net,
};
+ cfg.fc_table = l3mdev_fib_table_by_index(net, ifindex) ? : RT6_TABLE_INFO;
cfg.fc_dst = *prefix;
cfg.fc_gateway = *gwaddr;
@@ -2314,7 +2323,7 @@
unsigned int pref)
{
struct fib6_config cfg = {
- .fc_table = RT6_TABLE_DFLT,
+ .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT,
.fc_metric = IP6_RT_PRIO_USER,
.fc_ifindex = dev->ifindex,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
@@ -2361,7 +2370,8 @@
{
memset(cfg, 0, sizeof(*cfg));
- cfg->fc_table = RT6_TABLE_MAIN;
+ cfg->fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ?
+ : RT6_TABLE_MAIN;
cfg->fc_ifindex = rtmsg->rtmsg_ifindex;
cfg->fc_metric = rtmsg->rtmsg_metric;
cfg->fc_expires = rtmsg->rtmsg_info;
@@ -2470,6 +2480,7 @@
const struct in6_addr *addr,
bool anycast)
{
+ u32 tb_id;
struct net *net = dev_net(idev->dev);
struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev,
DST_NOCOUNT);
@@ -2492,7 +2503,8 @@
rt->rt6i_gateway = *addr;
rt->rt6i_dst.addr = *addr;
rt->rt6i_dst.plen = 128;
- rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);
+ tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL;
+ rt->rt6i_table = fib6_get_table(net, tb_id);
rt->dst.flags |= DST_NOCACHE;
atomic_set(&rt->dst.__refcnt, 1);
@@ -3254,6 +3266,11 @@
} else {
fl6.flowi6_oif = oif;
+ if (netif_index_is_l3_master(net, oif)) {
+ fl6.flowi6_flags = FLOWI_FLAG_L3MDEV_SRC |
+ FLOWI_FLAG_SKIP_NH_OIF;
+ }
+
rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
}