ipv6: Fix the pmtu path for connected UDP socket

What about something like this:

 {
@@ -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)) {
+       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);
+   }
 }
 EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);


Thanks.
Wei

On Tue, Mar 22, 2016 at 4:36 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> On Tue, 2016-03-22 at 13:13 -0700, Cong Wang wrote:
>> On Tue, Mar 22, 2016 at 11:03 AM, Wei Wang <tracywwnj@gmail.com> wrote:
>> > Thanks Martin and Cong.
>> >
>> > I guess then we are going with the following fix in ip6_sk_update_pmtu():
>> > 1. call ip6_upate_pmtu() as it is
>> > 2. do a dst_check()
>> > 3. re-lookup() if it is invalid
>> > 4. and then do a ip6_dst_store()/dst_set
>>
>> Exactly, please try the attached patch. Note I did nothing more than a
>> compile test.
>>
>> Does it make sense to you now?
>
>
> Hard to reply on your patch as it was not inlined.
>
> 1) Lot of code duplication, for some reason I do not yet understand.
>
> ip6_sk_update_pmtu() and ip6_update_pmtu() will basically do the same
> thing...
>
> 2)
>
> +       if (sk->sk_state == TCP_ESTABLISHED)
> +               ip6_dst_store(sk, dst, &iph->daddr, &iph->saddr);
> +out:
>
>
> ip6_dst_store() will do :
>
> np->daddr_cache = daddr;  (&iph->daddr)
> np->saddr_cache = saddr;  (&iph->saddr)
>
> So when skb is freed, daddr_cache & saddr_cache point to freed data.
>
>
>
>

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.

On Thu, Mar 24, 2016 at 11:32:28AM -0700, Martin KaFai Lau wrote:
> Some fast path may do __sk_dst_get() which does not refcnt the sk->sk_dst_cache.
Ignore this comment.  This should have been protected by rcu grace period.