1 files changed, 488 insertions, 405 deletions

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index cd48801a8d6..45702b8cd14 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -37,6 +37,7 @@
 #include <linux/tcp.h>
 #include <linux/route.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv6.h>
@@ -55,77 +56,22 @@
 #include <net/checksum.h>
 #include <linux/mroute6.h>
 
-static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
-
-int __ip6_local_out(struct sk_buff *skb)
-{
-	int len;
-
-	len = skb->len - sizeof(struct ipv6hdr);
-	if (len > IPV6_MAXPLEN)
-		len = 0;
-	ipv6_hdr(skb)->payload_len = htons(len);
-
-	return nf_hook(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev,
-		       dst_output);
-}
-
-int ip6_local_out(struct sk_buff *skb)
-{
-	int err;
-
-	err = __ip6_local_out(skb);
-	if (likely(err == 1))
-		err = dst_output(skb);
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(ip6_local_out);
-
-static int ip6_output_finish(struct sk_buff *skb)
-{
-	struct dst_entry *dst = skb_dst(skb);
-
-	if (dst->hh)
-		return neigh_hh_output(dst->hh, skb);
-	else if (dst->neighbour)
-		return dst->neighbour->output(skb);
-
-	IP6_INC_STATS_BH(dev_net(dst->dev),
-			 ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
-	kfree_skb(skb);
-	return -EINVAL;
-
-}
-
-/* dev_loopback_xmit for use with netfilter. */
-static int ip6_dev_loopback_xmit(struct sk_buff *newskb)
-{
-	skb_reset_mac_header(newskb);
-	__skb_pull(newskb, skb_network_offset(newskb));
-	newskb->pkt_type = PACKET_LOOPBACK;
-	newskb->ip_summed = CHECKSUM_UNNECESSARY;
-	WARN_ON(!skb_dst(newskb));
-
-	netif_rx(newskb);
-	return 0;
-}
-
-
-static int ip6_output2(struct sk_buff *skb)
+static int ip6_finish_output2(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *dev = dst->dev;
+	struct neighbour *neigh;
+	struct in6_addr *nexthop;
+	int ret;
 
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->dev = dev;
 
 	if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
-		struct ipv6_pinfo* np = skb->sk ? inet6_sk(skb->sk) : NULL;
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 
-		if (!(dev->flags & IFF_LOOPBACK) && (!np || np->mc_loop) &&
-		    ((mroute6_socket(dev_net(dev)) &&
+		if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) &&
+		    ((mroute6_socket(dev_net(dev), skb) &&
 		     !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
 		     ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
 					 &ipv6_hdr(skb)->saddr))) {
@@ -135,9 +81,9 @@ static int ip6_output2(struct sk_buff *skb)
 			   is not supported in any case.
 			 */
 			if (newskb)
-				NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, newskb,
-					NULL, newskb->dev,
-					ip6_dev_loopback_xmit);
+				NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
+					newskb, NULL, newskb->dev,
+					dev_loopback_xmit);
 
 			if (ipv6_hdr(skb)->hop_limit == 0) {
 				IP6_INC_STATS(dev_net(dev), idev,
@@ -149,53 +95,74 @@ static int ip6_output2(struct sk_buff *skb)
 
 		IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST,
 				skb->len);
+
+		if (IPV6_ADDR_MC_SCOPE(&ipv6_hdr(skb)->daddr) <=
+		    IPV6_ADDR_SCOPE_NODELOCAL &&
+		    !(dev->flags & IFF_LOOPBACK)) {
+			kfree_skb(skb);
+			return 0;
+		}
+	}
+
+	rcu_read_lock_bh();
+	nexthop = rt6_nexthop((struct rt6_info *)dst);
+	neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
+	if (unlikely(!neigh))
+		neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
+	if (!IS_ERR(neigh)) {
+		ret = dst_neigh_output(dst, neigh, skb);
+		rcu_read_unlock_bh();
+		return ret;
 	}
+	rcu_read_unlock_bh();
 
-	return NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, skb, NULL, skb->dev,
-		       ip6_output_finish);
+	IP6_INC_STATS(dev_net(dst->dev),
+		      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+	kfree_skb(skb);
+	return -EINVAL;
 }
 
-static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
+static int ip6_finish_output(struct sk_buff *skb)
 {
-	struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
-
-	return (np && np->pmtudisc == IPV6_PMTUDISC_PROBE) ?
-	       skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
+	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
+	    dst_allfrag(skb_dst(skb)) ||
+	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
+		return ip6_fragment(skb, ip6_finish_output2);
+	else
+		return ip6_finish_output2(skb);
 }
 
-int ip6_output(struct sk_buff *skb)
+int ip6_output(struct sock *sk, struct sk_buff *skb)
 {
+	struct net_device *dev = skb_dst(skb)->dev;
 	struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 	if (unlikely(idev->cnf.disable_ipv6)) {
-		IP6_INC_STATS(dev_net(skb_dst(skb)->dev), idev,
+		IP6_INC_STATS(dev_net(dev), idev,
 			      IPSTATS_MIB_OUTDISCARDS);
 		kfree_skb(skb);
 		return 0;
 	}
 
-	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
-				dst_allfrag(skb_dst(skb)))
-		return ip6_fragment(skb, ip6_output2);
-	else
-		return ip6_output2(skb);
+	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, dev,
+			    ip6_finish_output,
+			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }
 
 /*
- *	xmit an sk_buff (used by TCP)
+ *	xmit an sk_buff (used by TCP, SCTP and DCCP)
  */
 
-int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
-	     struct ipv6_txoptions *opt, int ipfragok)
+int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
+	     struct ipv6_txoptions *opt, int tclass)
 {
 	struct net *net = sock_net(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct in6_addr *first_hop = &fl->fl6_dst;
+	struct in6_addr *first_hop = &fl6->daddr;
 	struct dst_entry *dst = skb_dst(skb);
 	struct ipv6hdr *hdr;
-	u8  proto = fl->proto;
+	u8  proto = fl6->flowi6_proto;
 	int seg_len = skb->len;
 	int hlimit = -1;
-	int tclass = 0;
 	u32 mtu;
 
 	if (opt) {
@@ -216,10 +183,9 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 				kfree_skb(skb);
 				return -ENOBUFS;
 			}
-			kfree_skb(skb);
+			consume_skb(skb);
 			skb = skb2;
-			if (sk)
-				skb_set_owner_w(skb, sk);
+			skb_set_owner_w(skb, sk);
 		}
 		if (opt->opt_flen)
 			ipv6_push_frag_opts(skb, opt, &proto);
@@ -231,44 +197,37 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 	skb_reset_network_header(skb);
 	hdr = ipv6_hdr(skb);
 
-	/* Allow local fragmentation. */
-	if (ipfragok)
-		skb->local_df = 1;
-
 	/*
 	 *	Fill in the IPv6 header
 	 */
-	if (np) {
-		tclass = np->tclass;
+	if (np)
 		hlimit = np->hop_limit;
-	}
 	if (hlimit < 0)
 		hlimit = ip6_dst_hoplimit(dst);
 
-	*(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel;
+	ip6_flow_hdr(hdr, tclass, fl6->flowlabel);
 
 	hdr->payload_len = htons(seg_len);
 	hdr->nexthdr = proto;
 	hdr->hop_limit = hlimit;
 
-	ipv6_addr_copy(&hdr->saddr, &fl->fl6_src);
-	ipv6_addr_copy(&hdr->daddr, first_hop);
+	hdr->saddr = fl6->saddr;
+	hdr->daddr = *first_hop;
 
+	skb->protocol = htons(ETH_P_IPV6);
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
 
 	mtu = dst_mtu(dst);
-	if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) {
+	if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
 		IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
 			      IPSTATS_MIB_OUT, skb->len);
-		return NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev,
-				dst_output);
+		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
+			       dst->dev, dst_output);
 	}
 
-	if (net_ratelimit())
-		printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n");
 	skb->dev = dst->dev;
-	icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev);
+	ipv6_local_error(sk, EMSGSIZE, fl6, mtu);
 	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
 	kfree_skb(skb);
 	return -EMSGSIZE;
@@ -276,42 +235,6 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 
 EXPORT_SYMBOL(ip6_xmit);
 
-/*
- *	To avoid extra problems ND packets are send through this
- *	routine. It's code duplication but I really want to avoid
- *	extra checks since ipv6_build_header is used by TCP (which
- *	is for us performance critical)
- */
-
-int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, struct net_device *dev,
-	       const struct in6_addr *saddr, const struct in6_addr *daddr,
-	       int proto, int len)
-{
-	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct ipv6hdr *hdr;
-	int totlen;
-
-	skb->protocol = htons(ETH_P_IPV6);
-	skb->dev = dev;
-
-	totlen = len + sizeof(struct ipv6hdr);
-
-	skb_reset_network_header(skb);
-	skb_put(skb, sizeof(struct ipv6hdr));
-	hdr = ipv6_hdr(skb);
-
-	*(__be32*)hdr = htonl(0x60000000);
-
-	hdr->payload_len = htons(len);
-	hdr->nexthdr = proto;
-	hdr->hop_limit = np->hop_limit;
-
-	ipv6_addr_copy(&hdr->saddr, saddr);
-	ipv6_addr_copy(&hdr->daddr, daddr);
-
-	return 0;
-}
-
 static int ip6_call_ra_chain(struct sk_buff *skb, int sel)
 {
 	struct ip6_ra_chain *ra;
@@ -345,10 +268,11 @@ static int ip6_forward_proxy_check(struct sk_buff *skb)
 {
 	struct ipv6hdr *hdr = ipv6_hdr(skb);
 	u8 nexthdr = hdr->nexthdr;
+	__be16 frag_off;
 	int offset;
 
 	if (ipv6_ext_hdr(nexthdr)) {
-		offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr);
+		offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr, &frag_off);
 		if (offset < 0)
 			return 0;
 	} else
@@ -397,21 +321,65 @@ static inline int ip6_forward_finish(struct sk_buff *skb)
 	return dst_output(skb);
 }
 
+static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
+{
+	unsigned int mtu;
+	struct inet6_dev *idev;
+
+	if (dst_metric_locked(dst, RTAX_MTU)) {
+		mtu = dst_metric_raw(dst, RTAX_MTU);
+		if (mtu)
+			return mtu;
+	}
+
+	mtu = IPV6_MIN_MTU;
+	rcu_read_lock();
+	idev = __in6_dev_get(dst->dev);
+	if (idev)
+		mtu = idev->cnf.mtu6;
+	rcu_read_unlock();
+
+	return mtu;
+}
+
+static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
+{
+	if (skb->len <= mtu)
+		return false;
+
+	/* ipv6 conntrack defrag sets max_frag_size + ignore_df */
+	if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
+		return true;
+
+	if (skb->ignore_df)
+		return false;
+
+	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+		return false;
+
+	return true;
+}
+
 int ip6_forward(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct inet6_skb_parm *opt = IP6CB(skb);
 	struct net *net = dev_net(dst->dev);
+	u32 mtu;
 
 	if (net->ipv6.devconf_all->forwarding == 0)
 		goto error;
 
+	if (skb->pkt_type != PACKET_HOST)
+		goto drop;
+
 	if (skb_warn_if_lro(skb))
 		goto drop;
 
 	if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
-		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
+		IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+				 IPSTATS_MIB_INDISCARDS);
 		goto drop;
 	}
 
@@ -430,9 +398,8 @@ int ip6_forward(struct sk_buff *skb)
 	 *	cannot be fragmented, because there is no warranty
 	 *	that different fragments will go along one path. --ANK
 	 */
-	if (opt->ra) {
-		u8 *ptr = skb_network_header(skb) + opt->ra;
-		if (ip6_call_ra_chain(skb, (ptr[2]<<8) + ptr[3]))
+	if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) {
+		if (ip6_call_ra_chain(skb, ntohs(opt->ra)))
 			return 0;
 	}
 
@@ -442,10 +409,9 @@ int ip6_forward(struct sk_buff *skb)
 	if (hdr->hop_limit <= 1) {
 		/* Force OUTPUT device used as source address */
 		skb->dev = dst->dev;
-		icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
-			    0, skb->dev);
-		IP6_INC_STATS_BH(net,
-				 ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS);
+		icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0);
+		IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+				 IPSTATS_MIB_INHDRERRORS);
 
 		kfree_skb(skb);
 		return -ETIMEDOUT;
@@ -458,14 +424,15 @@ int ip6_forward(struct sk_buff *skb)
 		if (proxied > 0)
 			return ip6_input(skb);
 		else if (proxied < 0) {
-			IP6_INC_STATS(net, ip6_dst_idev(dst),
-				      IPSTATS_MIB_INDISCARDS);
+			IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+					 IPSTATS_MIB_INDISCARDS);
 			goto drop;
 		}
 	}
 
 	if (!xfrm6_route_forward(skb)) {
-		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
+		IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+				 IPSTATS_MIB_INDISCARDS);
 		goto drop;
 	}
 	dst = skb_dst(skb);
@@ -474,11 +441,10 @@ int ip6_forward(struct sk_buff *skb)
 	   send redirects to source routed frames.
 	   We don't send redirects to frames decapsulated from IPsec.
 	 */
-	if (skb->dev == dst->dev && dst->neighbour && opt->srcrt == 0 &&
-	    !skb_sec_path(skb)) {
+	if (skb->dev == dst->dev && opt->srcrt == 0 && !skb_sec_path(skb)) {
 		struct in6_addr *target = NULL;
+		struct inet_peer *peer;
 		struct rt6_info *rt;
-		struct neighbour *n = dst->neighbour;
 
 		/*
 		 *	incoming and outgoing devices are the same
@@ -486,16 +452,20 @@ int ip6_forward(struct sk_buff *skb)
 		 */
 
 		rt = (struct rt6_info *) dst;
-		if ((rt->rt6i_flags & RTF_GATEWAY))
-			target = (struct in6_addr*)&n->primary_key;
+		if (rt->rt6i_flags & RTF_GATEWAY)
+			target = &rt->rt6i_gateway;
 		else
 			target = &hdr->daddr;
 
+		peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
+
 		/* Limit redirects both by destination (here)
 		   and by source (inside ndisc_send_redirect)
 		 */
-		if (xrlim_allow(dst, 1*HZ))
-			ndisc_send_redirect(skb, n, target);
+		if (inet_peer_xrlim_allow(peer, 1*HZ))
+			ndisc_send_redirect(skb, target);
+		if (peer)
+			inet_putpeer(peer);
 	} else {
 		int addrtype = ipv6_addr_type(&hdr->saddr);
 
@@ -505,25 +475,30 @@ int ip6_forward(struct sk_buff *skb)
 			goto error;
 		if (addrtype & IPV6_ADDR_LINKLOCAL) {
 			icmpv6_send(skb, ICMPV6_DEST_UNREACH,
-				ICMPV6_NOT_NEIGHBOUR, 0, skb->dev);
+				    ICMPV6_NOT_NEIGHBOUR, 0);
 			goto error;
 		}
 	}
 
-	if (skb->len > dst_mtu(dst)) {
+	mtu = ip6_dst_mtu_forward(dst);
+	if (mtu < IPV6_MIN_MTU)
+		mtu = IPV6_MIN_MTU;
+
+	if (ip6_pkt_too_big(skb, mtu)) {
 		/* Again, force OUTPUT device used as source address */
 		skb->dev = dst->dev;
-		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, dst_mtu(dst), skb->dev);
-		IP6_INC_STATS_BH(net,
-				 ip6_dst_idev(dst), IPSTATS_MIB_INTOOBIGERRORS);
-		IP6_INC_STATS_BH(net,
-				 ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS);
+		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+				 IPSTATS_MIB_INTOOBIGERRORS);
+		IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+				 IPSTATS_MIB_FRAGFAILS);
 		kfree_skb(skb);
 		return -EMSGSIZE;
 	}
 
 	if (skb_cow(skb, dst->dev->hard_header_len)) {
-		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS);
+		IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+				 IPSTATS_MIB_OUTDISCARDS);
 		goto drop;
 	}
 
@@ -534,7 +509,8 @@ int ip6_forward(struct sk_buff *skb)
 	hdr->hop_limit--;
 
 	IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
-	return NF_HOOK(PF_INET6, NF_INET_FORWARD, skb, skb->dev, dst->dev,
+	IP6_ADD_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
+	return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dst->dev,
 		       ip6_forward_finish);
 
 error:
@@ -558,53 +534,24 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->tc_index = from->tc_index;
 #endif
 	nf_copy(to, from);
-#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
-    defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
-	to->nf_trace = from->nf_trace;
-#endif
 	skb_copy_secmark(to, from);
 }
 
-int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
+static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
 {
-	u16 offset = sizeof(struct ipv6hdr);
-	struct ipv6_opt_hdr *exthdr =
-				(struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1);
-	unsigned int packet_len = skb->tail - skb->network_header;
-	int found_rhdr = 0;
-	*nexthdr = &ipv6_hdr(skb)->nexthdr;
-
-	while (offset + 1 <= packet_len) {
+	static u32 ip6_idents_hashrnd __read_mostly;
+	u32 hash, id;
 
-		switch (**nexthdr) {
+	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
 
-		case NEXTHDR_HOP:
-			break;
-		case NEXTHDR_ROUTING:
-			found_rhdr = 1;
-			break;
-		case NEXTHDR_DEST:
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
-			if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0)
-				break;
-#endif
-			if (found_rhdr)
-				return offset;
-			break;
-		default :
-			return offset;
-		}
+	hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd);
+	hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash);
 
-		offset += ipv6_optlen(exthdr);
-		*nexthdr = &exthdr->nexthdr;
-		exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
-						 offset);
-	}
-
-	return offset;
+	id = ip_idents_reserve(hash, 1);
+	fhdr->identification = htonl(id);
 }
 
-static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
+int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
 	struct sk_buff *frag;
 	struct rt6_info *rt = (struct rt6_info*)skb_dst(skb);
@@ -612,6 +559,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	struct ipv6hdr *tmp_hdr;
 	struct frag_hdr *fh;
 	unsigned int mtu, hlen, left, len;
+	int hroom, troom;
 	__be32 frag_id = 0;
 	int ptr, offset = 0, err=0;
 	u8 *prevhdr, nexthdr = 0;
@@ -623,12 +571,16 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	mtu = ip6_skb_dst_mtu(skb);
 
 	/* We must not fragment if the socket is set to force MTU discovery
-	 * or if the skb it not generated by a local socket.  (This last
-	 * check should be redundant, but it's free.)
+	 * or if the skb it not generated by a local socket.
 	 */
-	if (!skb->local_df) {
+	if (unlikely(!skb->ignore_df && skb->len > mtu) ||
+		     (IP6CB(skb)->frag_max_size &&
+		      IP6CB(skb)->frag_max_size > mtu)) {
+		if (skb->sk && dst_allfrag(skb_dst(skb)))
+			sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
+
 		skb->dev = skb_dst(skb)->dev;
-		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev);
+		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 			      IPSTATS_MIB_FRAGFAILS);
 		kfree_skb(skb);
@@ -641,9 +593,9 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	}
 	mtu -= hlen + sizeof(struct frag_hdr);
 
-	if (skb_has_frags(skb)) {
+	if (skb_has_frag_list(skb)) {
 		int first_len = skb_pagelen(skb);
-		int truesizes = 0;
+		struct sk_buff *frag2;
 
 		if (first_len - hlen > mtu ||
 		    ((first_len - hlen) & 7) ||
@@ -655,18 +607,18 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 			if (frag->len > mtu ||
 			    ((frag->len & 7) && frag->next) ||
 			    skb_headroom(frag) < hlen)
-			    goto slow_path;
+				goto slow_path_clean;
 
 			/* Partially cloned skb? */
 			if (skb_shared(frag))
-				goto slow_path;
+				goto slow_path_clean;
 
 			BUG_ON(frag->sk);
 			if (skb->sk) {
 				frag->sk = skb->sk;
 				frag->destructor = sock_wfree;
-				truesizes += frag->truesize;
 			}
+			skb->truesize -= frag->truesize;
 		}
 
 		err = 0;
@@ -689,7 +641,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 		skb_reset_network_header(skb);
 		memcpy(skb_network_header(skb), tmp_hdr, hlen);
 
-		ipv6_select_ident(fh);
+		ipv6_select_ident(fh, rt);
 		fh->nexthdr = nexthdr;
 		fh->reserved = 0;
 		fh->frag_off = htons(IP6_MF);
@@ -697,12 +649,11 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 		first_len = skb_pagelen(skb);
 		skb->data_len = first_len - skb_headlen(skb);
-		skb->truesize -= truesizes;
 		skb->len = first_len;
 		ipv6_hdr(skb)->payload_len = htons(first_len -
 						   sizeof(struct ipv6hdr));
 
-		dst_hold(&rt->u.dst);
+		dst_hold(&rt->dst);
 
 		for (;;) {
 			/* Prepare header of the next frame,
@@ -730,7 +681,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 			err = output(skb);
 			if(!err)
-				IP6_INC_STATS(net, ip6_dst_idev(&rt->u.dst),
+				IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
 					      IPSTATS_MIB_FRAGCREATES);
 
 			if (err || !frag)
@@ -744,9 +695,9 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 		kfree(tmp_hdr);
 
 		if (err == 0) {
-			IP6_INC_STATS(net, ip6_dst_idev(&rt->u.dst),
+			IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
 				      IPSTATS_MIB_FRAGOKS);
-			dst_release(&rt->u.dst);
+			ip6_rt_put(rt);
 			return 0;
 		}
 
@@ -756,13 +707,26 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 			frag = skb;
 		}
 
-		IP6_INC_STATS(net, ip6_dst_idev(&rt->u.dst),
+		IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
 			      IPSTATS_MIB_FRAGFAILS);
-		dst_release(&rt->u.dst);
+		ip6_rt_put(rt);
 		return err;
+
+slow_path_clean:
+		skb_walk_frags(skb, frag2) {
+			if (frag2 == frag)
+				break;
+			frag2->sk = NULL;
+			frag2->destructor = NULL;
+			skb->truesize += frag2->truesize;
+		}
 	}
 
 slow_path:
+	if ((skb->ip_summed == CHECKSUM_PARTIAL) &&
+	    skb_checksum_help(skb))
+		goto fail;
+
 	left = skb->len - hlen;		/* Space per frame */
 	ptr = hlen;			/* Where to start from */
 
@@ -771,6 +735,8 @@ slow_path:
 	 */
 
 	*prevhdr = NEXTHDR_FRAGMENT;
+	hroom = LL_RESERVED_SPACE(rt->dst.dev);
+	troom = rt->dst.dev->needed_tailroom;
 
 	/*
 	 *	Keep copying data until we run out.
@@ -780,7 +746,7 @@ slow_path:
 		/* IF: it doesn't fit, use 'mtu' - the data space left */
 		if (len > mtu)
 			len = mtu;
-		/* IF: we are not sending upto and including the packet end
+		/* IF: we are not sending up to and including the packet end
 		   then align the next start on an eight byte boundary */
 		if (len < left)	{
 			len &= ~7;
@@ -789,7 +755,8 @@ slow_path:
 		 *	Allocate buffer.
 		 */
 
-		if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->u.dst.dev), GFP_ATOMIC)) == NULL) {
+		if ((frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) +
+				      hroom + troom, GFP_ATOMIC)) == NULL) {
 			NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n");
 			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 				      IPSTATS_MIB_FRAGFAILS);
@@ -802,7 +769,7 @@ slow_path:
 		 */
 
 		ip6_copy_metadata(frag, skb);
-		skb_reserve(frag, LL_RESERVED_SPACE(rt->u.dst.dev));
+		skb_reserve(frag, hroom);
 		skb_put(frag, len + hlen + sizeof(struct frag_hdr));
 		skb_reset_network_header(frag);
 		fh = (struct frag_hdr *)(skb_network_header(frag) + hlen);
@@ -827,7 +794,7 @@ slow_path:
 		fh->nexthdr = nexthdr;
 		fh->reserved = 0;
 		if (!frag_id) {
-			ipv6_select_ident(fh);
+			ipv6_select_ident(fh, rt);
 			frag_id = fh->identification;
 		} else
 			fh->identification = frag_id;
@@ -860,7 +827,7 @@ slow_path:
 	}
 	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 		      IPSTATS_MIB_FRAGOKS);
-	kfree_skb(skb);
+	consume_skb(skb);
 	return err;
 
 fail:
@@ -870,24 +837,30 @@ fail:
 	return err;
 }
 
-static inline int ip6_rt_check(struct rt6key *rt_key,
-			       struct in6_addr *fl_addr,
-			       struct in6_addr *addr_cache)
+static inline int ip6_rt_check(const struct rt6key *rt_key,
+			       const struct in6_addr *fl_addr,
+			       const struct in6_addr *addr_cache)
 {
-	return ((rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) &&
-		(addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache)));
+	return (rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) &&
+		(addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache));
 }
 
 static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
 					  struct dst_entry *dst,
-					  struct flowi *fl)
+					  const struct flowi6 *fl6)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct rt6_info *rt = (struct rt6_info *)dst;
+	struct rt6_info *rt;
 
 	if (!dst)
 		goto out;
 
+	if (dst->ops->family != AF_INET6) {
+		dst_release(dst);
+		return NULL;
+	}
+
+	rt = (struct rt6_info *)dst;
 	/* Yes, checking route validity in not connected
 	 * case is not very simple. Take into account,
 	 * that we do not support routing by source, TOS,
@@ -905,11 +878,11 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
 	 *    sockets.
 	 * 2. oif also should be the same.
 	 */
-	if (ip6_rt_check(&rt->rt6i_dst, &fl->fl6_dst, np->daddr_cache) ||
+	if (ip6_rt_check(&rt->rt6i_dst, &fl6->daddr, np->daddr_cache) ||
 #ifdef CONFIG_IPV6_SUBTREES
-	    ip6_rt_check(&rt->rt6i_src, &fl->fl6_src, np->saddr_cache) ||
+	    ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) ||
 #endif
-	    (fl->oif && fl->oif != dst->dev->ifindex)) {
+	    (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) {
 		dst_release(dst);
 		dst = NULL;
 	}
@@ -919,22 +892,26 @@ out:
 }
 
 static int ip6_dst_lookup_tail(struct sock *sk,
-			       struct dst_entry **dst, struct flowi *fl)
+			       struct dst_entry **dst, struct flowi6 *fl6)
 {
-	int err;
 	struct net *net = sock_net(sk);
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+	struct neighbour *n;
+	struct rt6_info *rt;
+#endif
+	int err;
 
 	if (*dst == NULL)
-		*dst = ip6_route_output(net, sk, fl);
+		*dst = ip6_route_output(net, sk, fl6);
 
 	if ((err = (*dst)->error))
 		goto out_err_release;
 
-	if (ipv6_addr_any(&fl->fl6_src)) {
-		err = ipv6_dev_get_saddr(net, ip6_dst_idev(*dst)->dev,
-					 &fl->fl6_dst,
-					 sk ? inet6_sk(sk)->srcprefs : 0,
-					 &fl->fl6_src);
+	if (ipv6_addr_any(&fl6->saddr)) {
+		struct rt6_info *rt = (struct rt6_info *) *dst;
+		err = ip6_route_get_saddr(net, rt, &fl6->daddr,
+					  sk ? inet6_sk(sk)->srcprefs : 0,
+					  &fl6->saddr);
 		if (err)
 			goto out_err_release;
 	}
@@ -948,12 +925,18 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 	 * dst entry and replace it instead with the
 	 * dst entry of the nexthop router
 	 */
-	if ((*dst)->neighbour && !((*dst)->neighbour->nud_state & NUD_VALID)) {
+	rt = (struct rt6_info *) *dst;
+	rcu_read_lock_bh();
+	n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt));
+	err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
+	rcu_read_unlock_bh();
+
+	if (err) {
 		struct inet6_ifaddr *ifp;
-		struct flowi fl_gw;
+		struct flowi6 fl_gw6;
 		int redirect;
 
-		ifp = ipv6_get_ifaddr(net, &fl->fl6_src,
+		ifp = ipv6_get_ifaddr(net, &fl6->saddr,
 				      (*dst)->dev, 1);
 
 		redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
@@ -966,9 +949,9 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 			 * default router instead
 			 */
 			dst_release(*dst);
-			memcpy(&fl_gw, fl, sizeof(struct flowi));
-			memset(&fl_gw.fl6_dst, 0, sizeof(struct in6_addr));
-			*dst = ip6_route_output(net, sk, &fl_gw);
+			memcpy(&fl_gw6, fl6, sizeof(struct flowi6));
+			memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr));
+			*dst = ip6_route_output(net, sk, &fl_gw6);
 			if ((err = (*dst)->error))
 				goto out_err_release;
 		}
@@ -979,7 +962,7 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 
 out_err_release:
 	if (err == -ENETUNREACH)
-		IP6_INC_STATS_BH(net, NULL, IPSTATS_MIB_OUTNOROUTES);
+		IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES);
 	dst_release(*dst);
 	*dst = NULL;
 	return err;
@@ -989,52 +972,88 @@ out_err_release:
  *	ip6_dst_lookup - perform route lookup on flow
  *	@sk: socket which provides route info
  *	@dst: pointer to dst_entry * for result
- *	@fl: flow to lookup
+ *	@fl6: flow to lookup
  *
  *	This function performs a route lookup on the given flow.
  *
  *	It returns zero on success, or a standard errno code on error.
  */
-int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl)
+int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6)
 {
 	*dst = NULL;
-	return ip6_dst_lookup_tail(sk, dst, fl);
+	return ip6_dst_lookup_tail(sk, dst, fl6);
 }
 EXPORT_SYMBOL_GPL(ip6_dst_lookup);
 
 /**
- *	ip6_sk_dst_lookup - perform socket cached route lookup on flow
+ *	ip6_dst_lookup_flow - perform route lookup on flow with ipsec
+ *	@sk: socket which provides route info
+ *	@fl6: flow to lookup
+ *	@final_dst: final destination address for ipsec lookup
+ *
+ *	This function performs a route lookup on the given flow.
+ *
+ *	It returns a valid dst pointer on success, or a pointer encoded
+ *	error code.
+ */
+struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
+				      const struct in6_addr *final_dst)
+{
+	struct dst_entry *dst = NULL;
+	int err;
+
+	err = ip6_dst_lookup_tail(sk, &dst, fl6);
+	if (err)
+		return ERR_PTR(err);
+	if (final_dst)
+		fl6->daddr = *final_dst;
+
+	return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
+}
+EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
+
+/**
+ *	ip6_sk_dst_lookup_flow - perform socket cached route lookup on flow
  *	@sk: socket which provides the dst cache and route info
- *	@dst: pointer to dst_entry * for result
- *	@fl: flow to lookup
+ *	@fl6: flow to lookup
+ *	@final_dst: final destination address for ipsec lookup
  *
  *	This function performs a route lookup on the given flow with the
  *	possibility of using the cached route in the socket if it is valid.
  *	It will take the socket dst lock when operating on the dst cache.
  *	As a result, this function can only be used in process context.
  *
- *	It returns zero on success, or a standard errno code on error.
+ *	It returns a valid dst pointer on success, or a pointer encoded
+ *	error code.
  */
-int ip6_sk_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl)
+struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
+					 const struct in6_addr *final_dst)
 {
-	*dst = NULL;
-	if (sk) {
-		*dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
-		*dst = ip6_sk_dst_check(sk, *dst, fl);
-	}
+	struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
+	int err;
 
-	return ip6_dst_lookup_tail(sk, dst, fl);
+	dst = ip6_sk_dst_check(sk, dst, fl6);
+
+	err = ip6_dst_lookup_tail(sk, &dst, fl6);
+	if (err)
+		return ERR_PTR(err);
+	if (final_dst)
+		fl6->daddr = *final_dst;
+
+	return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
 }
-EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup);
+EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
 static inline int ip6_ufo_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 hh_len, int fragheaderlen,
-			int transhdrlen, int mtu,unsigned int flags)
+			int transhdrlen, int mtu,unsigned int flags,
+			struct rt6_info *rt)
 
 {
 	struct sk_buff *skb;
+	struct frag_hdr fhdr;
 	int err;
 
 	/* There is support for UDP large send offload by network
@@ -1046,7 +1065,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 			hh_len + fragheaderlen + transhdrlen + 20,
 			(flags & MSG_DONTWAIT), &err);
 		if (skb == NULL)
-			return -ENOMEM;
+			return err;
 
 		/* reserve space for Hardware header */
 		skb_reserve(skb, hh_len);
@@ -1060,34 +1079,27 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 		/* initialize protocol header pointer */
 		skb->transport_header = skb->network_header + fragheaderlen;
 
-		skb->ip_summed = CHECKSUM_PARTIAL;
+		skb->protocol = htons(ETH_P_IPV6);
 		skb->csum = 0;
-		sk->sk_sndmsg_off = 0;
-	}
-
-	err = skb_append_datato_frags(sk,skb, getfrag, from,
-				      (length - transhdrlen));
-	if (!err) {
-		struct frag_hdr fhdr;
 
-		/* Specify the length of each IPv6 datagram fragment.
-		 * It has to be a multiple of 8.
-		 */
-		skb_shinfo(skb)->gso_size = (mtu - fragheaderlen -
-					     sizeof(struct frag_hdr)) & ~7;
-		skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
-		ipv6_select_ident(&fhdr);
-		skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
 		__skb_queue_tail(&sk->sk_write_queue, skb);
-
-		return 0;
+	} else if (skb_is_gso(skb)) {
+		goto append;
 	}
-	/* There is not enough support do UPD LSO,
-	 * so follow normal path
-	 */
-	kfree_skb(skb);
 
-	return err;
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	/* Specify the length of each IPv6 datagram fragment.
+	 * It has to be a multiple of 8.
+	 */
+	skb_shinfo(skb)->gso_size = (mtu - fragheaderlen -
+				     sizeof(struct frag_hdr)) & ~7;
+	skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+	ipv6_select_ident(&fhdr, rt);
+	skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
+
+append:
+	return skb_append_datato_frags(sk, skb, getfrag, from,
+				       (length - transhdrlen));
 }
 
 static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src,
@@ -1102,26 +1114,52 @@ static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src,
 	return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
 }
 
+static void ip6_append_data_mtu(unsigned int *mtu,
+				int *maxfraglen,
+				unsigned int fragheaderlen,
+				struct sk_buff *skb,
+				struct rt6_info *rt,
+				unsigned int orig_mtu)
+{
+	if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
+		if (skb == NULL) {
+			/* first fragment, reserve header_len */
+			*mtu = orig_mtu - rt->dst.header_len;
+
+		} else {
+			/*
+			 * this fragment is not first, the headers
+			 * space is regarded as data space.
+			 */
+			*mtu = orig_mtu;
+		}
+		*maxfraglen = ((*mtu - fragheaderlen) & ~7)
+			      + fragheaderlen - sizeof(struct frag_hdr);
+	}
+}
+
 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)
+	int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6,
+	struct rt6_info *rt, unsigned int flags, int dontfrag)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct sk_buff *skb;
-	unsigned int maxfraglen, fragheaderlen;
+	struct inet_cork *cork;
+	struct sk_buff *skb, *skb_prev = NULL;
+	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
 	int exthdrlen;
+	int dst_exthdrlen;
 	int hh_len;
-	int mtu;
 	int copy;
 	int err;
 	int offset = 0;
-	int csummode = CHECKSUM_NONE;
+	__u8 tx_flags = 0;
 
 	if (flags&MSG_PROBE)
 		return 0;
+	cork = &inet->cork.base;
 	if (skb_queue_empty(&sk->sk_write_queue)) {
 		/*
 		 * setup for corking
@@ -1130,7 +1168,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 			if (WARN_ON(np->cork.opt))
 				return -EINVAL;
 
-			np->cork.opt = kmalloc(opt->tot_len, sk->sk_allocation);
+			np->cork.opt = kzalloc(opt->tot_len, sk->sk_allocation);
 			if (unlikely(np->cork.opt == NULL))
 				return -ENOBUFS;
 
@@ -1160,49 +1198,83 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 
 			/* need source address above miyazawa*/
 		}
-		dst_hold(&rt->u.dst);
-		inet->cork.dst = &rt->u.dst;
-		inet->cork.fl = *fl;
+		dst_hold(&rt->dst);
+		cork->dst = &rt->dst;
+		inet->cork.fl.u.ip6 = *fl6;
 		np->cork.hop_limit = hlimit;
 		np->cork.tclass = tclass;
-		mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
-		      rt->u.dst.dev->mtu : dst_mtu(rt->u.dst.path);
+		if (rt->dst.flags & DST_XFRM_TUNNEL)
+			mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
+			      rt->dst.dev->mtu : dst_mtu(&rt->dst);
+		else
+			mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
+			      rt->dst.dev->mtu : dst_mtu(rt->dst.path);
 		if (np->frag_size < mtu) {
 			if (np->frag_size)
 				mtu = np->frag_size;
 		}
-		inet->cork.fragsize = mtu;
-		if (dst_allfrag(rt->u.dst.path))
-			inet->cork.flags |= IPCORK_ALLFRAG;
-		inet->cork.length = 0;
-		sk->sk_sndmsg_page = NULL;
-		sk->sk_sndmsg_off = 0;
-		exthdrlen = rt->u.dst.header_len + (opt ? opt->opt_flen : 0) -
-			    rt->rt6i_nfheader_len;
+		cork->fragsize = mtu;
+		if (dst_allfrag(rt->dst.path))
+			cork->flags |= IPCORK_ALLFRAG;
+		cork->length = 0;
+		exthdrlen = (opt ? opt->opt_flen : 0);
 		length += exthdrlen;
 		transhdrlen += exthdrlen;
+		dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len;
 	} else {
-		rt = (struct rt6_info *)inet->cork.dst;
-		fl = &inet->cork.fl;
+		rt = (struct rt6_info *)cork->dst;
+		fl6 = &inet->cork.fl.u.ip6;
 		opt = np->cork.opt;
 		transhdrlen = 0;
 		exthdrlen = 0;
-		mtu = inet->cork.fragsize;
+		dst_exthdrlen = 0;
+		mtu = cork->fragsize;
 	}
+	orig_mtu = mtu;
 
-	hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);
+	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
 	fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
 			(opt ? opt->opt_nflen : 0);
-	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
+	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen -
+		     sizeof(struct frag_hdr);
 
 	if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
-		if (inet->cork.length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
-			ipv6_local_error(sk, EMSGSIZE, fl, mtu-exthdrlen);
+		unsigned int maxnonfragsize, headersize;
+
+		headersize = sizeof(struct ipv6hdr) +
+			     (opt ? opt->opt_flen + opt->opt_nflen : 0) +
+			     (dst_allfrag(&rt->dst) ?
+			      sizeof(struct frag_hdr) : 0) +
+			     rt->rt6i_nfheader_len;
+
+		if (ip6_sk_ignore_df(sk))
+			maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
+		else
+			maxnonfragsize = mtu;
+
+		/* dontfrag active */
+		if ((cork->length + length > mtu - headersize) && dontfrag &&
+		    (sk->sk_protocol == IPPROTO_UDP ||
+		     sk->sk_protocol == IPPROTO_RAW)) {
+			ipv6_local_rxpmtu(sk, fl6, mtu - headersize +
+						   sizeof(struct ipv6hdr));
+			goto emsgsize;
+		}
+
+		if (cork->length + length > maxnonfragsize - headersize) {
+emsgsize:
+			ipv6_local_error(sk, EMSGSIZE, fl6,
+					 mtu - headersize +
+					 sizeof(struct ipv6hdr));
 			return -EMSGSIZE;
 		}
 	}
 
+	/* For UDP, check if TX timestamp is enabled */
+	if (sk->sk_type == SOCK_DGRAM)
+		sock_tx_timestamp(sk, &tx_flags);
+
 	/*
 	 * Let's try using as much space as possible.
 	 * Use MTU if total length of the message fits into the MTU.
@@ -1219,24 +1291,26 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	 * --yoshfuji
 	 */
 
-	inet->cork.length += length;
-	if (((length > mtu) && (sk->sk_protocol == 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);
+	skb = skb_peek_tail(&sk->sk_write_queue);
+	cork->length += length;
+	if (((length > mtu) ||
+	     (skb && skb_is_gso(skb))) &&
+	    (sk->sk_protocol == IPPROTO_UDP) &&
+	    (rt->dst.dev->features & NETIF_F_UFO)) {
+		err = ip6_ufo_append_data(sk, getfrag, from, length,
+					  hh_len, fragheaderlen,
+					  transhdrlen, mtu, flags, rt);
 		if (err)
 			goto error;
 		return 0;
 	}
 
-	if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
+	if (!skb)
 		goto alloc_new_skb;
 
 	while (length > 0) {
 		/* Check if the remaining data fits into current packet. */
-		copy = (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
+		copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
 		if (copy < length)
 			copy = maxfraglen - skb->len;
 
@@ -1246,38 +1320,46 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 			unsigned int fraglen;
 			unsigned int fraggap;
 			unsigned int alloclen;
-			struct sk_buff *skb_prev;
 alloc_new_skb:
-			skb_prev = skb;
-
 			/* There's no room in the current skb */
-			if (skb_prev)
-				fraggap = skb_prev->len - maxfraglen;
+			if (skb)
+				fraggap = skb->len - maxfraglen;
 			else
 				fraggap = 0;
+			/* update mtu and maxfraglen if necessary */
+			if (skb == NULL || skb_prev == NULL)
+				ip6_append_data_mtu(&mtu, &maxfraglen,
+						    fragheaderlen, skb, rt,
+						    orig_mtu);
+
+			skb_prev = skb;
 
 			/*
 			 * If remaining data exceeds the mtu,
 			 * we know we need more fragment(s).
 			 */
 			datalen = length + fraggap;
-			if (datalen > (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
-				datalen = maxfraglen - fragheaderlen;
 
-			fraglen = datalen + fragheaderlen;
+			if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
+				datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
 			if ((flags & MSG_MORE) &&
-			    !(rt->u.dst.dev->features&NETIF_F_SG))
+			    !(rt->dst.dev->features&NETIF_F_SG))
 				alloclen = mtu;
 			else
 				alloclen = datalen + fragheaderlen;
 
-			/*
-			 * The last fragment gets additional space at tail.
-			 * Note: we overallocate on fragments with MSG_MODE
-			 * because we have no idea if we're the last one.
-			 */
-			if (datalen == length + fraggap)
-				alloclen += rt->u.dst.trailer_len;
+			alloclen += dst_exthdrlen;
+
+			if (datalen != length + fraggap) {
+				/*
+				 * this is not the last fragment, the trailer
+				 * space is regarded as data space.
+				 */
+				datalen += rt->dst.trailer_len;
+			}
+
+			alloclen += rt->dst.trailer_len;
+			fraglen = datalen + fragheaderlen;
 
 			/*
 			 * We just reserve space for fragment header.
@@ -1299,16 +1381,27 @@ alloc_new_skb:
 							   sk->sk_allocation);
 				if (unlikely(skb == NULL))
 					err = -ENOBUFS;
+				else {
+					/* Only the initial fragment
+					 * is time stamped.
+					 */
+					tx_flags = 0;
+				}
 			}
 			if (skb == NULL)
 				goto error;
 			/*
 			 *	Fill in the control structures
 			 */
-			skb->ip_summed = csummode;
+			skb->protocol = htons(ETH_P_IPV6);
+			skb->ip_summed = CHECKSUM_NONE;
 			skb->csum = 0;
-			/* reserve for fragmentation */
-			skb_reserve(skb, hh_len+sizeof(struct frag_hdr));
+			/* reserve for fragmentation and ipsec header */
+			skb_reserve(skb, hh_len + sizeof(struct frag_hdr) +
+				    dst_exthdrlen);
+
+			if (sk->sk_type == SOCK_DGRAM)
+				skb_shinfo(skb)->tx_flags = tx_flags;
 
 			/*
 			 *	Find where to start putting bytes
@@ -1328,6 +1421,7 @@ alloc_new_skb:
 				pskb_trim_unique(skb_prev, maxfraglen);
 			}
 			copy = datalen - transhdrlen - fraggap;
+
 			if (copy < 0) {
 				err = -EINVAL;
 				kfree_skb(skb);
@@ -1342,7 +1436,7 @@ alloc_new_skb:
 			length -= datalen - fraggap;
 			transhdrlen = 0;
 			exthdrlen = 0;
-			csummode = CHECKSUM_NONE;
+			dst_exthdrlen = 0;
 
 			/*
 			 * Put the packet on the pending queue
@@ -1354,7 +1448,7 @@ alloc_new_skb:
 		if (copy > length)
 			copy = length;
 
-		if (!(rt->u.dst.dev->features&NETIF_F_SG)) {
+		if (!(rt->dst.dev->features&NETIF_F_SG)) {
 			unsigned int off;
 
 			off = skb->len;
@@ -1366,46 +1460,31 @@ alloc_new_skb:
 			}
 		} else {
 			int i = skb_shinfo(skb)->nr_frags;
-			skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
-			struct page *page = sk->sk_sndmsg_page;
-			int off = sk->sk_sndmsg_off;
-			unsigned int left;
-
-			if (page && (left = PAGE_SIZE - off) > 0) {
-				if (copy >= left)
-					copy = left;
-				if (page != frag->page) {
-					if (i == MAX_SKB_FRAGS) {
-						err = -EMSGSIZE;
-						goto error;
-					}
-					get_page(page);
-					skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0);
-					frag = &skb_shinfo(skb)->frags[i];
-				}
-			} else if(i < MAX_SKB_FRAGS) {
-				if (copy > PAGE_SIZE)
-					copy = PAGE_SIZE;
-				page = alloc_pages(sk->sk_allocation, 0);
-				if (page == NULL) {
-					err = -ENOMEM;
-					goto error;
-				}
-				sk->sk_sndmsg_page = page;
-				sk->sk_sndmsg_off = 0;
+			struct page_frag *pfrag = sk_page_frag(sk);
 
-				skb_fill_page_desc(skb, i, page, 0, 0);
-				frag = &skb_shinfo(skb)->frags[i];
-			} else {
-				err = -EMSGSIZE;
-				goto error;
-			}
-			if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) {
-				err = -EFAULT;
+			err = -ENOMEM;
+			if (!sk_page_frag_refill(sk, pfrag))
 				goto error;
+
+			if (!skb_can_coalesce(skb, i, pfrag->page,
+					      pfrag->offset)) {
+				err = -EMSGSIZE;
+				if (i == MAX_SKB_FRAGS)
+					goto error;
+
+				__skb_fill_page_desc(skb, i, pfrag->page,
+						     pfrag->offset, 0);
+				skb_shinfo(skb)->nr_frags = ++i;
+				get_page(pfrag->page);
 			}
-			sk->sk_sndmsg_off += copy;
-			frag->size += copy;
+			copy = min_t(int, copy, pfrag->size - pfrag->offset);
+			if (getfrag(from,
+				    page_address(pfrag->page) + pfrag->offset,
+				    offset, copy, skb->len, skb) < 0)
+				goto error_efault;
+
+			pfrag->offset += copy;
+			skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
 			skb->len += copy;
 			skb->data_len += copy;
 			skb->truesize += copy;
@@ -1414,12 +1493,17 @@ alloc_new_skb:
 		offset += copy;
 		length -= copy;
 	}
+
 	return 0;
+
+error_efault:
+	err = -EFAULT;
 error:
-	inet->cork.length -= length;
+	cork->length -= length;
 	IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
 	return err;
 }
+EXPORT_SYMBOL_GPL(ip6_append_data);
 
 static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np)
 {
@@ -1432,10 +1516,10 @@ static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np)
 		np->cork.opt = NULL;
 	}
 
-	if (inet->cork.dst) {
-		dst_release(inet->cork.dst);
-		inet->cork.dst = NULL;
-		inet->cork.flags &= ~IPCORK_ALLFRAG;
+	if (inet->cork.base.dst) {
+		dst_release(inet->cork.base.dst);
+		inet->cork.base.dst = NULL;
+		inet->cork.base.flags &= ~IPCORK_ALLFRAG;
 	}
 	memset(&inet->cork.fl, 0, sizeof(inet->cork.fl));
 }
@@ -1450,9 +1534,9 @@ int ip6_push_pending_frames(struct sock *sk)
 	struct net *net = sock_net(sk);
 	struct ipv6hdr *hdr;
 	struct ipv6_txoptions *opt = np->cork.opt;
-	struct rt6_info *rt = (struct rt6_info *)inet->cork.dst;
-	struct flowi *fl = &inet->cork.fl;
-	unsigned char proto = fl->proto;
+	struct rt6_info *rt = (struct rt6_info *)inet->cork.base.dst;
+	struct flowi6 *fl6 = &inet->cork.fl.u.ip6;
+	unsigned char proto = fl6->flowi6_proto;
 	int err = 0;
 
 	if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
@@ -1474,10 +1558,9 @@ int ip6_push_pending_frames(struct sock *sk)
 	}
 
 	/* Allow local fragmentation. */
-	if (np->pmtudisc < IPV6_PMTUDISC_DO)
-		skb->local_df = 1;
+	skb->ignore_df = ip6_sk_ignore_df(sk);
 
-	ipv6_addr_copy(final_dst, &fl->fl6_dst);
+	*final_dst = fl6->daddr;
 	__skb_pull(skb, skb_network_header_len(skb));
 	if (opt && opt->opt_flen)
 		ipv6_push_frag_opts(skb, opt, &proto);
@@ -1488,24 +1571,22 @@ int ip6_push_pending_frames(struct sock *sk)
 	skb_reset_network_header(skb);
 	hdr = ipv6_hdr(skb);
 
-	*(__be32*)hdr = fl->fl6_flowlabel |
-		     htonl(0x60000000 | ((int)np->cork.tclass << 20));
-
+	ip6_flow_hdr(hdr, np->cork.tclass, fl6->flowlabel);
 	hdr->hop_limit = np->cork.hop_limit;
 	hdr->nexthdr = proto;
-	ipv6_addr_copy(&hdr->saddr, &fl->fl6_src);
-	ipv6_addr_copy(&hdr->daddr, final_dst);
+	hdr->saddr = fl6->saddr;
+	hdr->daddr = *final_dst;
 
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
 
-	skb_dst_set(skb, dst_clone(&rt->u.dst));
+	skb_dst_set(skb, dst_clone(&rt->dst));
 	IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
 	if (proto == IPPROTO_ICMPV6) {
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 
-		ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
+		ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
 	}
 
 	err = ip6_local_out(skb);
@@ -1523,6 +1604,7 @@ error:
 	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
 	goto out;
 }
+EXPORT_SYMBOL_GPL(ip6_push_pending_frames);
 
 void ip6_flush_pending_frames(struct sock *sk)
 {
@@ -1537,3 +1619,4 @@ void ip6_flush_pending_frames(struct sock *sk)
 
 	ip6_cork_release(inet_sk(sk), inet6_sk(sk));
 }
+EXPORT_SYMBOL_GPL(ip6_flush_pending_frames);