ipv6: yet another new IPV6_MTU_DISCOVER option IPV6_PMTUDISC_OMIT

This option has the same semantic as IP_PMTUDISC_OMIT for IPv4 which
got recently introduced. It doesn't honor the path mtu discovered by the
host but in contrary to IPV6_PMTUDISC_INTERFACE allows the generation of
fragments if the packet size exceeds the MTU of the outgoing interface
MTU.

Fixes: 93b36cf3425b9b ("ipv6: support IPV6_PMTU_INTERFACE on sockets")
Cc: Florian Weimer <fweimer@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 18 insertions, 6 deletions

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 017badb1aec7..00e3f12cb2f9 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -171,7 +171,14 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
 
 static inline bool ip6_sk_accept_pmtu(const struct sock *sk)
 {
-        return inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_INTERFACE;
+        return inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_INTERFACE &&
+               inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_OMIT;
+}
+
+static inline bool ip6_sk_local_df(const struct sock *sk)
+{
+        return inet6_sk(sk)->pmtudisc < IPV6_PMTUDISC_DO ||
+               inet6_sk(sk)->pmtudisc == IPV6_PMTUDISC_OMIT;
 }
 
 static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt)
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index e9a1d2d973b6..0d8e0f0342dc 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -185,6 +185,10 @@ struct in6_flowlabel_req {
  * also see comments on IP_PMTUDISC_INTERFACE
  */
 #define IPV6_PMTUDISC_INTERFACE         4
+/* weaker version of IPV6_PMTUDISC_INTERFACE, which allows packets to
+ * get fragmented if they exceed the interface mtu
+ */
+#define IPV6_PMTUDISC_OMIT              5
 
 /* Flowlabel */
 #define IPV6_FLOWLABEL_MGR      32
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 070a2fae2375..be1b7f5a3a54 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1234,8 +1234,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
                               sizeof(struct frag_hdr) : 0) +
                              rt->rt6i_nfheader_len;
 
-                maxnonfragsize = (np->pmtudisc >= IPV6_PMTUDISC_DO) ?
-                                 mtu : sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
+                if (ip6_sk_local_df(sk))
+                        maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
+                else
+                        maxnonfragsize = mtu;
 
                 /* dontfrag active */
                 if ((cork->length + length > mtu - headersize) && dontfrag &&
@@ -1543,8 +1545,7 @@ int ip6_push_pending_frames(struct sock *sk)
         }
 
         /* Allow local fragmentation. */
-        if (np->pmtudisc < IPV6_PMTUDISC_DO)
-                skb->local_df = 1;
+        skb->local_df = ip6_sk_local_df(sk);
 
         *final_dst = fl6->daddr;
         __skb_pull(skb, skb_network_header_len(skb));
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 0a00f449de5e..edb58aff4ae7 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -722,7 +722,7 @@ done:
         case IPV6_MTU_DISCOVER:
                 if (optlen < sizeof(int))
                         goto e_inval;
-                if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_INTERFACE)
+                if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_OMIT)
                         goto e_inval;
                 np->pmtudisc = val;
                 retv = 0;