vrf: Use orig netdev to count Ip6InNoRoutes and a fresh route lookup when sending...

When there is no route to an IPv6 dest addr, skb_dst(skb) points
to loopback dev in the case of that the IP6CB(skb)->iif is
enslaved to a vrf. This causes Ip6InNoRoutes to be incremented on the
loopback dev. This also causes the lookup to fail on icmpv6_send() and
the dest unreachable to not sent and Ip6OutNoRoutes gets incremented on
the loopback dev.

To reproduce:
* Gateway configuration:
        ip link add dev vrf_258 type vrf table 258
        ip link set dev enp0s9 master vrf_258
        ip addr add 66:1/64 dev enp0s9
        ip -6 route add unreachable default metric 8192 table 258
        sysctl -w net.ipv6.conf.all.forwarding=1
        sysctl -w net.ipv6.conf.enp0s9.forwarding=1
* Sender configuration:
        ip addr add 66::2/64 dev enp0s9
        ip -6 route add default via 66::1
and ping 67::1 for example from the sender.

Fix this by counting on the original netdev and reset the skb dst to
force a fresh lookup.

v2: Fix typo of destination address in the repro steps.
v3: Simplify the loopback check (per David Ahern) and use reverse
    Christmas tree format (per David Miller).

Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7178e32eb15d0a969eb39fcfec9973bb0150bf48..b4899f0de0d06031c6a833597469864085640a33 100644 (file)
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3668,23 +3668,34 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 
 static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
 {
-       int type;
        struct dst_entry *dst = skb_dst(skb);
+       struct net *net = dev_net(dst->dev);
+       struct inet6_dev *idev;
+       int type;
+
+       if (netif_is_l3_master(skb->dev) &&
+           dst->dev == net->loopback_dev)
+               idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
+       else
+               idev = ip6_dst_idev(dst);
+
        switch (ipstats_mib_noroutes) {
        case IPSTATS_MIB_INNOROUTES:
                type = ipv6_addr_type(&ipv6_hdr(skb)->daddr);
                if (type == IPV6_ADDR_ANY) {
-                       IP6_INC_STATS(dev_net(dst->dev),
-                                     __in6_dev_get_safely(skb->dev),
-                                     IPSTATS_MIB_INADDRERRORS);
+                       IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS);
                        break;
                }
                /* FALLTHROUGH */
        case IPSTATS_MIB_OUTNOROUTES:
-               IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst),
-                             ipstats_mib_noroutes);
+               IP6_INC_STATS(net, idev, ipstats_mib_noroutes);
                break;
        }
+
+       /* Start over by dropping the dst for l3mdev case */
+       if (netif_is_l3_master(skb->dev))
+               skb_dst_drop(skb);
+
        icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0);
        kfree_skb(skb);
        return 0;