sctp: Drop ipfargok in sctp_xmit function

The ipfragok flag controls whether the packet may be fragmented
either on the local host on beyond.  The latter is only valid on
IPv4.

In fact, we never want to do the latter even on IPv4 when PMTU is
enabled.  This is because even though we can't fragment packets
within SCTP due to the prtocol's inherent faults, we can still
fragment it at IP layer.  By setting the DF bit we will improve
the PMTU process.

RFC 2960 only says that we SHOULD clear the DF bit in this case,
so we're compliant even if we set the DF bit.  In fact RFC 4960
no longer has this statement.

Once we make this change, we only need to control the local
fragmentation.  There is already a bit in the skb which controls
that, local_df.  So this patch sets that instead of using the
ipfragok argument.

The only complication is that there isn't a struct sock object
per transport, so for IPv4 we have to resort to changing the
pmtudisc field for every packet.  This should be safe though
as the protocol is single-threaded.

Note that after this patch we can remove ipfragok from the rest
of the stack too.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 14 insertions, 9 deletions

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index a238d683..483a01d 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -195,8 +195,7 @@ out:
 }
 
 /* Based on tcp_v6_xmit() in tcp_ipv6.c. */
-static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport,
-			int ipfragok)
+static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 {
 	struct sock *sk = skb->sk;
 	struct ipv6_pinfo *np = inet6_sk(sk);
@@ -231,7 +230,10 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport,
 
 	SCTP_INC_STATS(SCTP_MIB_OUTSCTPPACKS);
 
-	return ip6_xmit(sk, skb, &fl, np->opt, ipfragok);
+	if (!(transport->param_flags & SPP_PMTUD_ENABLE))
+		skb->local_df = 1;
+
+	return ip6_xmit(sk, skb, &fl, np->opt, 0);
 }
 
 /* Returns the dst cache entry for the given source and destination ip
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 4568464..0dc4a7d 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -586,10 +586,8 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 	SCTP_DEBUG_PRINTK("***sctp_transmit_packet*** skb len %d\n",
 			  nskb->len);
 
-	if (tp->param_flags & SPP_PMTUD_ENABLE)
-		(*tp->af_specific->sctp_xmit)(nskb, tp, packet->ipfragok);
-	else
-		(*tp->af_specific->sctp_xmit)(nskb, tp, 1);
+	nskb->local_df = packet->ipfragok;
+	(*tp->af_specific->sctp_xmit)(nskb, tp);
 
 out:
 	packet->size = packet->overhead;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index a6e0818..0b65354 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -862,16 +862,21 @@ static int sctp_inet_supported_addrs(const struct sctp_sock *opt,
 
 /* Wrapper routine that calls the ip transmit routine. */
 static inline int sctp_v4_xmit(struct sk_buff *skb,
-			       struct sctp_transport *transport, int ipfragok)
+			       struct sctp_transport *transport)
 {
+	struct inet_sock *inet = inet_sk(skb->sk);
+
 	SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, "
 			  "src:%u.%u.%u.%u, dst:%u.%u.%u.%u\n",
 			  __func__, skb, skb->len,
 			  NIPQUAD(skb->rtable->rt_src),
 			  NIPQUAD(skb->rtable->rt_dst));
 
+	inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ?
+			 IP_PMTUDISC_DO : IP_PMTUDISC_DONT;
+
 	SCTP_INC_STATS(SCTP_MIB_OUTSCTPPACKS);
-	return ip_queue_xmit(skb, ipfragok);
+	return ip_queue_xmit(skb, 0);
 }
 
 static struct sctp_af sctp_af_inet;