On Tue, Feb 12, 2019 at 6:58 PM David Ahern <dsah...@gmail.com> wrote:
>
> On 2/12/19 10:32 AM, Peter Oskolkov wrote:
> > @@ -148,6 +174,87 @@ static int xmit_check_hhlen(struct sk_buff *skb)
> > return 0;
> > }
> >
> > +static int bpf_lwt_xmit_reroute(struct sk_buff *skb)
> > +{
> > + struct net_device *l3mdev = l3mdev_master_dev_rcu(skb_dst(skb)->dev);
> > + int oif = l3mdev ? l3mdev->ifindex : 0;
> > + struct dst_entry *dst = NULL;
> > + struct sock *sk;
> > + struct net *net;
> > + bool ipv4;
> > + int err;
> > +
> > + if (skb->protocol == htons(ETH_P_IP))
> > + ipv4 = true;
> > + else if (skb->protocol == htons(ETH_P_IPV6))
> > + ipv4 = false;
> > + else
> > + return -EAFNOSUPPORT;
> > +
> > + sk = sk_to_full_sk(skb->sk);
> > + if (sk) {
> > + if (sk->sk_bound_dev_if)
> > + oif = sk->sk_bound_dev_if;
> > + net = sock_net(sk);
> > + } else {
> > + net = dev_net(skb_dst(skb)->dev);
> > + }
> > +
> > + if (ipv4) {
> > + struct iphdr *iph = ip_hdr(skb);
> > + struct flowi4 fl4 = {};
> > + struct rtable *rt;
> > +
> > + fl4.flowi4_oif = oif;
> > + fl4.flowi4_mark = skb->mark;
> > + fl4.flowi4_uid = sock_net_uid(net, sk);
> > + fl4.flowi4_tos = RT_TOS(iph->tos);
> > + fl4.flowi4_flags = FLOWI_FLAG_ANYSRC;
> > + fl4.flowi4_proto = iph->protocol;
> > + fl4.daddr = iph->daddr;
> > + fl4.saddr = iph->saddr;
> > +
> > + rt = ip_route_output_key(net, &fl4);
> > + if (IS_ERR(rt) || rt->dst.error)
> > + return -EINVAL;
>
> I think you have a dst leak here if rt is valid but the lookup is a
> reject (e.g., unreachable or blackhole).
Thanks, David! I was not able to reproduce the leak, but based on your
suggestion and similar code elsewhere I made a change in v11 to explicitly
release a dst with error.
>
> > + dst = &rt->dst;
> > + } else {
> > + struct ipv6hdr *iph6 = ipv6_hdr(skb);
> > + struct flowi6 fl6 = {};
> > +
> > + fl6.flowi6_oif = oif;
> > + fl6.flowi6_mark = skb->mark;
> > + fl6.flowi6_uid = sock_net_uid(net, sk);
> > + fl6.flowlabel = ip6_flowinfo(iph6);
> > + fl6.flowi6_proto = iph6->nexthdr;
> > + fl6.daddr = iph6->daddr;
> > + fl6.saddr = iph6->saddr;
> > +
> > + err = ipv6_stub->ipv6_dst_lookup(net, skb->sk, &dst, &fl6);
> > + if (err || IS_ERR(dst) || dst->error)
> > + return -EINVAL;
>
> same here.
>
> You could check this by adding a route with unreachable as the target in
> your tests. Test cleanup and namespace teardown will tell you pretty quick.
