ipv6: add the IPV6_FL_F_REFLECT flag to IPV6_FL_A_GET

With this option, the socket will reply with the flow label value read
on received packets.

The goal is to have a connection with the same flow label in both
direction of the communication.

Changelog of V4:
 * Do not erase the flow label on the listening socket. Use pktopts to
 store the received value

Signed-off-by: Florent Fourcot <florent.fourcot@enst-bretagne.fr>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 34 insertions, 1 deletions

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 7e1ded0d8e45..1084304fd75a 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -191,6 +191,7 @@ struct ipv6_pinfo {
         /* sockopt flags */
         __u16                   recverr:1,
                                 sndflow:1,
+                                repflow:1,
                                 pmtudisc:3,
                                 ipv6only:1,
                                 srcprefs:3,     /* 001: prefer temporary address
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index f94f1d013bf2..02c0cd685a27 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -85,6 +85,7 @@ struct in6_flowlabel_req {
 
 #define IPV6_FL_F_CREATE        1
 #define IPV6_FL_F_EXCL          2
+#define IPV6_FL_F_REFLECT       4
 
 #define IPV6_FL_S_NONE          0
 #define IPV6_FL_S_EXCL          1
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index cbc93517b455..55823f187446 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -486,6 +486,11 @@ int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq)
         struct ipv6_pinfo *np = inet6_sk(sk);
         struct ipv6_fl_socklist *sfl;
 
+        if (np->repflow) {
+                freq->flr_label = np->flow_label;
+                return 0;
+        }
+
         rcu_read_lock_bh();
 
         for_each_sk_fl_rcu(np, sfl) {
@@ -527,6 +532,15 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 
         switch (freq.flr_action) {
         case IPV6_FL_A_PUT:
+                if (freq.flr_flags & IPV6_FL_F_REFLECT) {
+                        if (sk->sk_protocol != IPPROTO_TCP)
+                                return -ENOPROTOOPT;
+                        if (!np->repflow)
+                                return -ESRCH;
+                        np->flow_label = 0;
+                        np->repflow = 0;
+                        return 0;
+                }
                 spin_lock_bh(&ip6_sk_fl_lock);
                 for (sflp = &np->ipv6_fl_list;
                      (sfl = rcu_dereference(*sflp))!=NULL;
@@ -567,6 +581,13 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
                 return -ESRCH;
 
         case IPV6_FL_A_GET:
+                if (freq.flr_flags & IPV6_FL_F_REFLECT) {
+                        if (sk->sk_protocol != IPPROTO_TCP)
+                                return -ENOPROTOOPT;
+                        np->repflow = 1;
+                        return 0;
+                }
+
                 if (freq.flr_label & ~IPV6_FLOWLABEL_MASK)
                         return -EINVAL;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b5512696e9ed..b61fa8bac3bd 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -483,6 +483,9 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
                                     &ireq->ir_v6_rmt_addr);
 
                 fl6->daddr = ireq->ir_v6_rmt_addr;
+                if (np->repflow && (ireq->pktopts != NULL))
+                        fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
+
                 skb_set_queue_mapping(skb, queue_mapping);
                 err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
                 err = net_xmit_eval(err);
@@ -1018,7 +1021,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
         if (!isn) {
                 if (ipv6_opt_accepted(sk, skb) ||
                     np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
-                    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
+                    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim ||
+                    np->repflow) {
                         atomic_inc(&skb->users);
                         ireq->pktopts = skb;
                 }
@@ -1143,6 +1147,8 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
                 newnp->mcast_oif   = inet6_iif(skb);
                 newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
                 newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
+                if (np->repflow)
+                        newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
 
                 /*
                  * No need to charge this sock to the relevant IPv6 refcnt debug socks count
@@ -1223,6 +1229,8 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
         newnp->mcast_oif  = inet6_iif(skb);
         newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
         newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
+        if (np->repflow)
+                newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
 
         /* Clone native IPv6 options from listening socket (if any)
 
@@ -1434,6 +1442,8 @@ ipv6_pktoptions:
                         np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
                 if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass)
                         np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb));
+                if (np->repflow)
+                        np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
                 if (ipv6_opt_accepted(sk, opt_skb)) {
                         skb_set_owner_r(opt_skb, sk);
                         opt_skb = xchg(&np->pktoptions, opt_skb);