On Wed, Mar 23, 2016 at 04:57:22PM -0700, Wei Wang wrote:
> What about something like this:
>
> diff --git a/net/ipv6/route.c b/net/ipv6/route.c
> index ed44663..21b4102 100644
> --- a/net/ipv6/route.c
> +++ b/net/ipv6/route.c
> @@ -1394,6 +1394,19 @@ static void ip6_rt_update_pmtu(struct dst_entry
> *dst, struct sock *sk,
> __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu);
> }
>
> +static void ip6_fill_in_flow(struct flowi6 *fl6, struct net *net,
> + struct sk_buff *skb, int oif, u32 mark)
> +{
> + const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
> +
> + memset(fl6, 0, sizeof(fl6));
> + fl6->flowi6_oif = oif;
> + fl6->flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark);
> + fl6->daddr = iph->daddr;
> + fl6->saddr = iph->saddr;
> + fl6->flowlabel = ip6_flowinfo(iph);
> +}
> +
> void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
> int oif, u32 mark)
> {
> @@ -1401,13 +1414,7 @@ void ip6_update_pmtu(struct sk_buff *skb,
> struct net *net, __be32 mtu,
> struct dst_entry *dst;
> struct flowi6 fl6;
>
> - memset(&fl6, 0, sizeof(fl6));
> - fl6.flowi6_oif = oif;
> - fl6.flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark);
> - fl6.daddr = iph->daddr;
> - fl6.saddr = iph->saddr;
> - fl6.flowlabel = ip6_flowinfo(iph);
> -
> + ip6_fill_in_flow(&fl6, net, skb, oif, mark);
> dst = ip6_route_output(net, NULL, &fl6);
> if (!dst->error)
> __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu));
> @@ -1417,8 +1424,22 @@ EXPORT_SYMBOL_GPL(ip6_update_pmtu);
>
> void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
> {
> - ip6_update_pmtu(skb, sock_net(sk), mtu,
> + struct ipv6_pinfo *np = inet6_sk(sk);
> + struct dst_entry *dst_new;
> + struct flowi6 fl6;
> + struct net *net = sock_net(sk);
> +
> + ip6_update_pmtu(skb, net, mtu,
> + sk->sk_bound_dev_if, sk->sk_mark);
> +
> + if (sk->sk_state == TCP_ESTABLISHED &&
> + !sk_dst_check(sk, np->dst_cookie)) {
sk_dst_check could hold a refcnt to the current sk->sk_dst_cache.
It has to be released.
> + ip6_fill_in_flow(&fl6, net, skb,
> sk->sk_bound_dev_if, sk->sk_mark);
> + dst_new = ip6_route_output(net, NULL, &fl6);
> + if (!IS_ERR(dst_new))
> + ip6_dst_store(sk, dst_new, NULL, NULL);
Has sk been locked before ip6_dst_store?
Some fast path may do __sk_dst_get() which does not refcnt the sk->sk_dst_cache.
However, after a quick look, it seems udpv6_sendmsg() is calling ip6_dst_store()
after release_sock also. I could be missing something.
