From d57b8fb8a8f94bdf467a4435be7d8bbebf87fe2a Mon Sep 17 00:00:00 2001
From: YOSHIFUJI Hideaki / 吉藤英明 <yoshfuji@linux-ipv6.org>
Date: Mon, 29 Mar 2010 06:00:05 +0000
Subject: ipv6: Use __fls() instead of fls() in __ipv6_addr_diff().

Because we have ensured that the argument is non-zero,
it is better to use __fls() and generate better code.

Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/net/ipv6.h')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index e72fb10ce573..033ddd4652a5 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -422,7 +422,7 @@ static inline int __ipv6_addr_diff(const void *token1, const void *token2, int a
 	for (i = 0; i < addrlen; i++) {
 		__be32 xb = a1[i] ^ a2[i];
 		if (xb)
-			return i * 32 + 32 - fls(ntohl(xb));
+			return i * 32 + 31 - __fls(ntohl(xb));
 	}
 
 	/*
-- 
cgit v1.2.3


From 4e15ed4d930297c127d280ca1d0c785be870def4 Mon Sep 17 00:00:00 2001
From: Shan Wei <shanwei@cn.fujitsu.com>
Date: Thu, 15 Apr 2010 16:43:08 +0000
Subject: net: replace ipfragok with skb->local_df

As Herbert Xu said: we should be able to simply replace ipfragok
with skb->local_df. commit f88037(sctp: Drop ipfargok in sctp_xmit function)
has droped ipfragok and set local_df value properly.

The patch kills the ipfragok parameter of .queue_xmit().

Signed-off-by: Shan Wei <shanwei@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet6_connection_sock.h | 2 +-
 include/net/inet_connection_sock.h  | 2 +-
 include/net/ip.h                    | 2 +-
 include/net/ipv6.h                  | 3 +--
 net/dccp/ipv6.c                     | 4 ++--
 net/dccp/output.c                   | 2 +-
 net/ipv4/ip_output.c                | 4 ++--
 net/ipv4/tcp_output.c               | 2 +-
 net/ipv6/inet6_connection_sock.c    | 4 ++--
 net/ipv6/ip6_output.c               | 2 +-
 net/ipv6/tcp_ipv6.c                 | 4 ++--
 net/l2tp/l2tp_core.c                | 3 ++-
 net/l2tp/l2tp_ip.c                  | 2 +-
 net/sctp/ipv6.c                     | 2 +-
 net/sctp/protocol.c                 | 2 +-
 15 files changed, 20 insertions(+), 20 deletions(-)

(limited to 'include/net/ipv6.h')

diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h
index f13ddc2543b1..aae08f686633 100644
--- a/include/net/inet6_connection_sock.h
+++ b/include/net/inet6_connection_sock.h
@@ -38,5 +38,5 @@ extern void inet6_csk_reqsk_queue_hash_add(struct sock *sk,
 
 extern void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
 
-extern int inet6_csk_xmit(struct sk_buff *skb, int ipfragok);
+extern int inet6_csk_xmit(struct sk_buff *skb);
 #endif /* _INET6_CONNECTION_SOCK_H */
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 52c8b8b8a0b9..b6d3b55da19b 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -36,7 +36,7 @@ struct tcp_congestion_ops;
  * (i.e. things that depend on the address family)
  */
 struct inet_connection_sock_af_ops {
-	int	    (*queue_xmit)(struct sk_buff *skb, int ipfragok);
+	int	    (*queue_xmit)(struct sk_buff *skb);
 	void	    (*send_check)(struct sock *sk, struct sk_buff *skb);
 	int	    (*rebuild_header)(struct sock *sk);
 	int	    (*conn_request)(struct sock *sk, struct sk_buff *skb);
diff --git a/include/net/ip.h b/include/net/ip.h
index 503994a38ed1..a84ceb692687 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -101,7 +101,7 @@ extern int		ip_do_nat(struct sk_buff *skb);
 extern void		ip_send_check(struct iphdr *ip);
 extern int		__ip_local_out(struct sk_buff *skb);
 extern int		ip_local_out(struct sk_buff *skb);
-extern int		ip_queue_xmit(struct sk_buff *skb, int ipfragok);
+extern int		ip_queue_xmit(struct sk_buff *skb);
 extern void		ip_init(void);
 extern int		ip_append_data(struct sock *sk,
 				       int getfrag(void *from, char *to, int offset, int len,
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 033ddd4652a5..b1d8db90b214 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -482,8 +482,7 @@ extern int			ip6_rcv_finish(struct sk_buff *skb);
 extern int			ip6_xmit(struct sock *sk,
 					 struct sk_buff *skb,
 					 struct flowi *fl,
-					 struct ipv6_txoptions *opt,
-					 int ipfragok);
+					 struct ipv6_txoptions *opt);
 
 extern int			ip6_nd_hdr(struct sock *sk,
 					   struct sk_buff *skb,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index ab1ab95946df..091698899594 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -292,7 +292,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
 							 &ireq6->loc_addr,
 							 &ireq6->rmt_addr);
 		ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr);
-		err = ip6_xmit(sk, skb, &fl, opt, 0);
+		err = ip6_xmit(sk, skb, &fl, opt);
 		err = net_xmit_eval(err);
 	}
 
@@ -347,7 +347,7 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb)
 	if (!ip6_dst_lookup(ctl_sk, &dst, &fl)) {
 		if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) {
 			skb_dst_set(skb, dst);
-			ip6_xmit(ctl_sk, skb, &fl, NULL, 0);
+			ip6_xmit(ctl_sk, skb, &fl, NULL);
 			DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS);
 			DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS);
 			return;
diff --git a/net/dccp/output.c b/net/dccp/output.c
index b8d98e3c052a..e98b65e9569f 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -136,7 +136,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 
 		DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
 
-		err = icsk->icsk_af_ops->queue_xmit(skb, 0);
+		err = icsk->icsk_af_ops->queue_xmit(skb);
 		return net_xmit_eval(err);
 	}
 	return -ENOBUFS;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c65f18e0936e..512af81b750f 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -311,7 +311,7 @@ int ip_output(struct sk_buff *skb)
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
 
-int ip_queue_xmit(struct sk_buff *skb, int ipfragok)
+int ip_queue_xmit(struct sk_buff *skb)
 {
 	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(sk);
@@ -370,7 +370,7 @@ packet_routed:
 	skb_reset_network_header(skb);
 	iph = ip_hdr(skb);
 	*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff));
-	if (ip_dont_fragment(sk, &rt->u.dst) && !ipfragok)
+	if (ip_dont_fragment(sk, &rt->u.dst) && !skb->local_df)
 		iph->frag_off = htons(IP_DF);
 	else
 		iph->frag_off = 0;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e46849989a53..2b7d71fb8439 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -890,7 +890,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
 		TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
 
-	err = icsk->icsk_af_ops->queue_xmit(skb, 0);
+	err = icsk->icsk_af_ops->queue_xmit(skb);
 	if (likely(err <= 0))
 		return err;
 
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 628db24bcf22..0c5e3c3b7fd5 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -178,7 +178,7 @@ struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie)
 	return dst;
 }
 
-int inet6_csk_xmit(struct sk_buff *skb, int ipfragok)
+int inet6_csk_xmit(struct sk_buff *skb)
 {
 	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(sk);
@@ -234,7 +234,7 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok)
 	/* Restore final destination back after routing done */
 	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
 
-	return ip6_xmit(sk, skb, &fl, np->opt, 0);
+	return ip6_xmit(sk, skb, &fl, np->opt);
 }
 
 EXPORT_SYMBOL_GPL(inet6_csk_xmit);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f3a847e3ec88..141819f0c6f1 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -185,7 +185,7 @@ int ip6_output(struct sk_buff *skb)
  */
 
 int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
-	     struct ipv6_txoptions *opt, int ipfragok)
+	     struct ipv6_txoptions *opt)
 {
 	struct net *net = sock_net(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b429dfdd69dc..bd5ef7b6e48e 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -509,7 +509,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
 		__tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr);
 
 		ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
-		err = ip6_xmit(sk, skb, &fl, opt, 0);
+		err = ip6_xmit(sk, skb, &fl, opt);
 		err = net_xmit_eval(err);
 	}
 
@@ -1071,7 +1071,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 	if (!ip6_dst_lookup(ctl_sk, &dst, &fl)) {
 		if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) {
 			skb_dst_set(buff, dst);
-			ip6_xmit(ctl_sk, buff, &fl, NULL, 0);
+			ip6_xmit(ctl_sk, buff, &fl, NULL);
 			TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
 			if (rst)
 				TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 98dfcce1a5fc..ecc7aea9efe4 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -954,7 +954,8 @@ int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, size_t dat
 	}
 
 	/* Queue the packet to IP for output */
-	error = ip_queue_xmit(skb, 1);
+	skb->local_df = 1;
+	error = ip_queue_xmit(skb);
 
 	/* Update stats */
 	if (error >= 0) {
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 75bf784ba18d..0852512d392c 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -501,7 +501,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 	skb_dst_set(skb, dst_clone(&rt->u.dst));
 
 	/* Queue the packet to IP for output */
-	rc = ip_queue_xmit(skb, 0);
+	rc = ip_queue_xmit(skb);
 
 error:
 	/* Update stats */
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 14db5689fb89..732689140fb8 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -232,7 +232,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 	if (!(transport->param_flags & SPP_PMTUD_ENABLE))
 		skb->local_df = 1;
 
-	return ip6_xmit(sk, skb, &fl, np->opt, 0);
+	return ip6_xmit(sk, skb, &fl, np->opt);
 }
 
 /* Returns the dst cache entry for the given source and destination ip
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index a56f98e82f92..704298f4b284 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -854,7 +854,7 @@ static inline int sctp_v4_xmit(struct sk_buff *skb,
 			 IP_PMTUDISC_DO : IP_PMTUDISC_DONT;
 
 	SCTP_INC_STATS(SCTP_MIB_OUTSCTPPACKS);
-	return ip_queue_xmit(skb, 0);
+	return ip_queue_xmit(skb);
 }
 
 static struct sctp_af sctp_af_inet;
-- 
cgit v1.2.3


From 13b52cd44670e3359055e9918d0e766d89836425 Mon Sep 17 00:00:00 2001
From: Brian Haley <brian.haley@hp.com>
Date: Fri, 23 Apr 2010 11:26:08 +0000
Subject: IPv6: Add dontfrag argument to relevant functions

Add dontfrag argument to relevant functions for
IPV6_DONTFRAG support, as well as allowing the value
to be passed-in via ancillary cmsg data.

Signed-off-by: Brian Haley <brian.haley@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h       |  3 ++-
 include/net/transp_v6.h  |  3 ++-
 net/ipv6/datagram.c      | 21 ++++++++++++++++++++-
 net/ipv6/icmp.c          |  5 +++--
 net/ipv6/ip6_flowlabel.c |  3 ++-
 net/ipv6/ip6_output.c    |  2 +-
 net/ipv6/ipv6_sockglue.c |  3 ++-
 net/ipv6/raw.c           |  9 +++++++--
 net/ipv6/udp.c           |  9 +++++++--
 9 files changed, 46 insertions(+), 12 deletions(-)

(limited to 'include/net/ipv6.h')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index b1d8db90b214..7ab6323e631e 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -503,7 +503,8 @@ extern int			ip6_append_data(struct sock *sk,
 						struct ipv6_txoptions *opt,
 						struct flowi *fl,
 						struct rt6_info *rt,
-						unsigned int flags);
+						unsigned int flags,
+						int dontfrag);
 
 extern int			ip6_push_pending_frames(struct sock *sk);
 
diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h
index d65381cad0fc..42a0eb68b7b6 100644
--- a/include/net/transp_v6.h
+++ b/include/net/transp_v6.h
@@ -44,7 +44,8 @@ extern int			datagram_send_ctl(struct net *net,
 						  struct msghdr *msg,
 						  struct flowi *fl,
 						  struct ipv6_txoptions *opt,
-						  int *hlimit, int *tclass);
+						  int *hlimit, int *tclass,
+						  int *dontfrag);
 
 #define		LOOPBACK4_IPV6		cpu_to_be32(0x7f000006)
 
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 622dc7939a1b..f5076d349b18 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -497,7 +497,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
 int datagram_send_ctl(struct net *net,
 		      struct msghdr *msg, struct flowi *fl,
 		      struct ipv6_txoptions *opt,
-		      int *hlimit, int *tclass)
+		      int *hlimit, int *tclass, int *dontfrag)
 {
 	struct in6_pktinfo *src_info;
 	struct cmsghdr *cmsg;
@@ -735,6 +735,25 @@ int datagram_send_ctl(struct net *net,
 			err = 0;
 			*tclass = tc;
 
+			break;
+		    }
+
+		case IPV6_DONTFRAG:
+		    {
+			int df;
+
+			err = -EINVAL;
+			if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) {
+				goto exit_f;
+			}
+
+			df = *(int *)CMSG_DATA(cmsg);
+			if (df < 0 || df > 1)
+				goto exit_f;
+
+			err = 0;
+			*dontfrag = df;
+
 			break;
 		    }
 		default:
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 12d2fa42657d..ce7992982557 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -481,7 +481,7 @@ route_done:
 			      len + sizeof(struct icmp6hdr),
 			      sizeof(struct icmp6hdr), hlimit,
 			      np->tclass, NULL, &fl, (struct rt6_info*)dst,
-			      MSG_DONTWAIT);
+			      MSG_DONTWAIT, np->dontfrag);
 	if (err) {
 		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
 		ip6_flush_pending_frames(sk);
@@ -561,7 +561,8 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 
 	err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr),
 				sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl,
-				(struct rt6_info*)dst, MSG_DONTWAIT);
+				(struct rt6_info*)dst, MSG_DONTWAIT,
+				np->dontfrag);
 
 	if (err) {
 		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 14e23216eb28..13654686aeab 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -360,7 +360,8 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval,
 		msg.msg_control = (void*)(fl->opt+1);
 		flowi.oif = 0;
 
-		err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk, &junk);
+		err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk,
+					&junk, &junk);
 		if (err)
 			goto done;
 		err = -EINVAL;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 263d4cf5a8de..54d43dd1f085 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1105,7 +1105,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	int offset, int len, int odd, struct sk_buff *skb),
 	void *from, int length, int transhdrlen,
 	int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi *fl,
-	struct rt6_info *rt, unsigned int flags)
+	struct rt6_info *rt, unsigned int flags, int dontfrag)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 2bf9eda72788..bd43f0152c21 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -458,7 +458,8 @@ sticky_done:
 		msg.msg_controllen = optlen;
 		msg.msg_control = (void*)(opt+1);
 
-		retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk);
+		retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk,
+					 &junk);
 		if (retv)
 			goto done;
 update:
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 8763b1a0814a..44a84ea9b3e8 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -733,6 +733,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	int addr_len = msg->msg_namelen;
 	int hlimit = -1;
 	int tclass = -1;
+	int dontfrag = -1;
 	u16 proto;
 	int err;
 
@@ -811,7 +812,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
 		opt->tot_len = sizeof(struct ipv6_txoptions);
 
-		err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass);
+		err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit,
+					&tclass, &dontfrag);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
@@ -880,6 +882,9 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	if (tclass < 0)
 		tclass = np->tclass;
 
+	if (dontfrag < 0)
+		dontfrag = np->dontfrag;
+
 	if (msg->msg_flags&MSG_CONFIRM)
 		goto do_confirm;
 
@@ -890,7 +895,7 @@ back_from_confirm:
 		lock_sock(sk);
 		err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov,
 			len, 0, hlimit, tclass, opt, &fl, (struct rt6_info*)dst,
-			msg->msg_flags);
+			msg->msg_flags, dontfrag);
 
 		if (err)
 			ip6_flush_pending_frames(sk);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 92bf9033e245..39e3665d9460 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -919,6 +919,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	int ulen = len;
 	int hlimit = -1;
 	int tclass = -1;
+	int dontfrag = -1;
 	int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
 	int err;
 	int connected = 0;
@@ -1049,7 +1050,8 @@ do_udp_sendmsg:
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
 		opt->tot_len = sizeof(*opt);
 
-		err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass);
+		err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit,
+					&tclass, &dontfrag);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
@@ -1120,6 +1122,9 @@ do_udp_sendmsg:
 	if (tclass < 0)
 		tclass = np->tclass;
 
+	if (dontfrag < 0)
+		dontfrag = np->dontfrag;
+
 	if (msg->msg_flags&MSG_CONFIRM)
 		goto do_confirm;
 back_from_confirm:
@@ -1143,7 +1148,7 @@ do_append_data:
 	err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen,
 		sizeof(struct udphdr), hlimit, tclass, opt, &fl,
 		(struct rt6_info*)dst,
-		corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
+		corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag);
 	if (err)
 		udp_v6_flush_pending_frames(sk);
 	else if (!corkreq)
-- 
cgit v1.2.3


From 4b340ae20d0e2366792abe70f46629e576adaf5e Mon Sep 17 00:00:00 2001
From: Brian Haley <brian.haley@hp.com>
Date: Fri, 23 Apr 2010 11:26:09 +0000
Subject: IPv6: Complete IPV6_DONTFRAG support

Finally add support to detect a local IPV6_DONTFRAG event
and return the relevant data to the user if they've enabled
IPV6_RECVPATHMTU on the socket.  The next recvmsg() will
return no data, but have an IPV6_PATHMTU as ancillary data.

Signed-off-by: Brian Haley <brian.haley@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h  |  2 ++
 include/net/ipv6.h    |  2 ++
 net/ipv6/af_inet6.c   |  3 ++
 net/ipv6/datagram.c   | 87 +++++++++++++++++++++++++++++++++++++++++++++++++++
 net/ipv6/ip6_output.c | 24 +++++++++-----
 net/ipv6/raw.c        |  3 ++
 net/ipv6/udp.c        |  3 ++
 7 files changed, 116 insertions(+), 8 deletions(-)

(limited to 'include/net/ipv6.h')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 1976942cf6f9..2ab5509f6d49 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -257,6 +257,7 @@ struct inet6_skb_parm {
 };
 
 #define IP6CB(skb)	((struct inet6_skb_parm*)((skb)->cb))
+#define IP6CBMTU(skb)	((struct ip6_mtuinfo *)((skb)->cb))
 
 static inline int inet6_iif(const struct sk_buff *skb)
 {
@@ -366,6 +367,7 @@ struct ipv6_pinfo {
 
 	struct ipv6_txoptions	*opt;
 	struct sk_buff		*pktoptions;
+	struct sk_buff		*rxpmtu;
 	struct {
 		struct ipv6_txoptions *opt;
 		u8 hop_limit;
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 7ab6323e631e..eba5cc00325a 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -578,9 +578,11 @@ extern int			ip6_datagram_connect(struct sock *sk,
 						     struct sockaddr *addr, int addr_len);
 
 extern int 			ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len);
+extern int 			ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len);
 extern void			ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port,
 						u32 info, u8 *payload);
 extern void			ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info);
+extern void			ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu);
 
 extern int inet6_release(struct socket *sock);
 extern int inet6_bind(struct socket *sock, struct sockaddr *uaddr, 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 3192aa02ba5d..d2df3144429b 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -417,6 +417,9 @@ void inet6_destroy_sock(struct sock *sk)
 	if ((skb = xchg(&np->pktoptions, NULL)) != NULL)
 		kfree_skb(skb);
 
+	if ((skb = xchg(&np->rxpmtu, NULL)) != NULL)
+		kfree_skb(skb);
+
 	/* Free flowlabels */
 	fl6_free_socklist(sk);
 
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index f5076d349b18..5959230bc6c1 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -278,6 +278,45 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info)
 		kfree_skb(skb);
 }
 
+void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6hdr *iph;
+	struct sk_buff *skb;
+	struct ip6_mtuinfo *mtu_info;
+
+	if (!np->rxopt.bits.rxpmtu)
+		return;
+
+	skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	skb_put(skb, sizeof(struct ipv6hdr));
+	skb_reset_network_header(skb);
+	iph = ipv6_hdr(skb);
+	ipv6_addr_copy(&iph->daddr, &fl->fl6_dst);
+
+	mtu_info = IP6CBMTU(skb);
+	if (!mtu_info) {
+		kfree_skb(skb);
+		return;
+	}
+
+	mtu_info->ip6m_mtu = mtu;
+	mtu_info->ip6m_addr.sin6_family = AF_INET6;
+	mtu_info->ip6m_addr.sin6_port = 0;
+	mtu_info->ip6m_addr.sin6_flowinfo = 0;
+	mtu_info->ip6m_addr.sin6_scope_id = fl->oif;
+	ipv6_addr_copy(&mtu_info->ip6m_addr.sin6_addr, &ipv6_hdr(skb)->daddr);
+
+	__skb_pull(skb, skb_tail_pointer(skb) - skb->data);
+	skb_reset_transport_header(skb);
+
+	skb = xchg(&np->rxpmtu, skb);
+	kfree_skb(skb);
+}
+
 /*
  *	Handle MSG_ERRQUEUE
  */
@@ -381,6 +420,54 @@ out:
 	return err;
 }
 
+/*
+ *	Handle IPV6_RECVPATHMTU
+ */
+int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct sk_buff *skb;
+	struct sockaddr_in6 *sin;
+	struct ip6_mtuinfo mtu_info;
+	int err;
+	int copied;
+
+	err = -EAGAIN;
+	skb = xchg(&np->rxpmtu, NULL);
+	if (skb == NULL)
+		goto out;
+
+	copied = skb->len;
+	if (copied > len) {
+		msg->msg_flags |= MSG_TRUNC;
+		copied = len;
+	}
+	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	if (err)
+		goto out_free_skb;
+
+	sock_recv_timestamp(msg, sk, skb);
+
+	memcpy(&mtu_info, IP6CBMTU(skb), sizeof(mtu_info));
+
+	sin = (struct sockaddr_in6 *)msg->msg_name;
+	if (sin) {
+		sin->sin6_family = AF_INET6;
+		sin->sin6_flowinfo = 0;
+		sin->sin6_port = 0;
+		sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id;
+		ipv6_addr_copy(&sin->sin6_addr, &mtu_info.ip6m_addr.sin6_addr);
+	}
+
+	put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info);
+
+	err = copied;
+
+out_free_skb:
+	kfree_skb(skb);
+out:
+	return err;
+}
 
 
 int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 54d43dd1f085..61e2bef56090 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1219,15 +1219,23 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	 */
 
 	inet->cork.length += length;
-	if (((length > mtu) && (sk->sk_protocol == IPPROTO_UDP)) &&
-	    (rt->u.dst.dev->features & NETIF_F_UFO)) {
+	if (length > mtu) {
+		int proto = sk->sk_protocol;
+		if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){
+			ipv6_local_rxpmtu(sk, fl, mtu-exthdrlen);
+			return -EMSGSIZE;
+		}
 
-		err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len,
-					  fragheaderlen, transhdrlen, mtu,
-					  flags);
-		if (err)
-			goto error;
-		return 0;
+		if (proto == IPPROTO_UDP &&
+		    (rt->u.dst.dev->features & NETIF_F_UFO)) {
+
+			err = ip6_ufo_append_data(sk, getfrag, from, length,
+						  hh_len, fragheaderlen,
+						  transhdrlen, mtu, flags);
+			if (err)
+				goto error;
+			return 0;
+		}
 	}
 
 	if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 44a84ea9b3e8..85627386cb02 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -461,6 +461,9 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 	if (flags & MSG_ERRQUEUE)
 		return ipv6_recv_error(sk, msg, len);
 
+	if (np->rxpmtu && np->rxopt.bits.rxpmtu)
+		return ipv6_recv_rxpmtu(sk, msg, len);
+
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)
 		goto out;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 39e3665d9460..2850e35cee3d 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -335,6 +335,9 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 	if (flags & MSG_ERRQUEUE)
 		return ipv6_recv_error(sk, msg, len);
 
+	if (np->rxpmtu && np->rxopt.bits.rxpmtu)
+		return ipv6_recv_rxpmtu(sk, msg, len);
+
 try_again:
 	skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
 				  &peeked, &err);
-- 
cgit v1.2.3