X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fipv6%2Fip6_output.c;h=dabf108ad81131138a5923268231809ebdb51494;hb=d79b6f4de5db0103ceb4734e42ad101d836d61d9;hp=57a326080757dd4af4bcba3bdf1d8c5551d58353;hpb=cfe1fc7759fdacb0c650b575daed1692bf3eaece;p=safe%2Fjmp%2Flinux-2.6

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 57a3260..dabf108 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -5,8 +5,6 @@
  *	Authors:
  *	Pedro Roque		<roque@di.fc.ul.pt>
  *
- *	$Id: ip6_output.c,v 1.34 2002/02/01 22:01:04 davem Exp $
- *
  *	Based on linux/net/ipv4/ip_output.c
  *
  *	This program is free software; you can redistribute it and/or
@@ -29,7 +27,7 @@
  */
 
 #include <linux/errno.h>
-#include <linux/types.h>
+#include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/socket.h>
 #include <linux/net.h>
@@ -55,31 +53,46 @@
 #include <net/icmp.h>
 #include <net/xfrm.h>
 #include <net/checksum.h>
+#include <linux/mroute6.h>
 
 static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
 
-static __inline__ void ipv6_select_ident(struct sk_buff *skb, struct frag_hdr *fhdr)
+int __ip6_local_out(struct sk_buff *skb)
 {
-	static u32 ipv6_fragmentation_id = 1;
-	static DEFINE_SPINLOCK(ip6_id_lock);
-
-	spin_lock_bh(&ip6_id_lock);
-	fhdr->identification = htonl(ipv6_fragmentation_id);
-	if (++ipv6_fragmentation_id == 0)
-		ipv6_fragmentation_id = 1;
-	spin_unlock_bh(&ip6_id_lock);
+	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);
 }
 
-static inline int ip6_output_finish(struct sk_buff *skb)
+int ip6_local_out(struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb->dst;
+	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(ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+	IP6_INC_STATS_BH(dev_net(dst->dev),
+			 ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 	kfree_skb(skb);
 	return -EINVAL;
 
@@ -92,7 +105,7 @@ static int ip6_dev_loopback_xmit(struct sk_buff *newskb)
 	__skb_pull(newskb, skb_network_offset(newskb));
 	newskb->pkt_type = PACKET_LOOPBACK;
 	newskb->ip_summed = CHECKSUM_UNNECESSARY;
-	BUG_TRAP(newskb->dst);
+	WARN_ON(!skb_dst(newskb));
 
 	netif_rx(newskb);
 	return 0;
@@ -101,46 +114,66 @@ static int ip6_dev_loopback_xmit(struct sk_buff *newskb)
 
 static int ip6_output2(struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb->dst;
+	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *dev = dst->dev;
 
 	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);
+		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 
-		if (!(dev->flags & IFF_LOOPBACK) && (!np || np->mc_loop) &&
-		    ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
-					&ipv6_hdr(skb)->saddr)) {
+		if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) &&
+		    ((mroute6_socket(dev_net(dev)) &&
+		     !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
+		     ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
+					 &ipv6_hdr(skb)->saddr))) {
 			struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
 
 			/* Do not check for IFF_ALLMULTI; multicast routing
 			   is not supported in any case.
 			 */
 			if (newskb)
-				NF_HOOK(PF_INET6, NF_IP6_POST_ROUTING, newskb, NULL,
-					newskb->dev,
+				NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, newskb,
+					NULL, newskb->dev,
 					ip6_dev_loopback_xmit);
 
 			if (ipv6_hdr(skb)->hop_limit == 0) {
-				IP6_INC_STATS(idev, IPSTATS_MIB_OUTDISCARDS);
+				IP6_INC_STATS(dev_net(dev), idev,
+					      IPSTATS_MIB_OUTDISCARDS);
 				kfree_skb(skb);
 				return 0;
 			}
 		}
 
-		IP6_INC_STATS(idev, IPSTATS_MIB_OUTMCASTPKTS);
+		IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST,
+				skb->len);
 	}
 
-	return NF_HOOK(PF_INET6, NF_IP6_POST_ROUTING, skb,NULL, skb->dev,ip6_output_finish);
+	return NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, skb, NULL, skb->dev,
+		       ip6_output_finish);
+}
+
+static inline int ip6_skb_dst_mtu(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));
 }
 
 int ip6_output(struct sk_buff *skb)
 {
-	if ((skb->len > dst_mtu(skb->dst) && !skb_is_gso(skb)) ||
-				dst_allfrag(skb->dst))
+	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,
+			      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);
@@ -153,17 +186,19 @@ 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 net *net = sock_net(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct in6_addr *first_hop = &fl->fl6_dst;
-	struct dst_entry *dst = skb->dst;
+	struct dst_entry *dst = skb_dst(skb);
 	struct ipv6hdr *hdr;
 	u8  proto = fl->proto;
 	int seg_len = skb->len;
-	int hlimit, tclass;
+	int hlimit = -1;
+	int tclass = 0;
 	u32 mtu;
 
 	if (opt) {
-		int head_room;
+		unsigned int head_room;
 
 		/* First: exthdrs may take lots of space (~8K for now)
 		   MAX_HEADER is not enough.
@@ -175,7 +210,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 		if (skb_headroom(skb) < head_room) {
 			struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
 			if (skb2 == NULL) {
-				IP6_INC_STATS(ip6_dst_idev(skb->dst),
+				IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 					      IPSTATS_MIB_OUTDISCARDS);
 				kfree_skb(skb);
 				return -ENOBUFS;
@@ -195,23 +230,19 @@ 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
 	 */
-
-	hlimit = -1;
-	if (np)
+	if (np) {
+		tclass = np->tclass;
 		hlimit = np->hop_limit;
+	}
 	if (hlimit < 0)
-		hlimit = dst_metric(dst, RTAX_HOPLIMIT);
-	if (hlimit < 0)
-		hlimit = ipv6_get_hoplimit(dst->dev);
-
-	tclass = -1;
-	if (np)
-		tclass = np->tclass;
-	if (tclass < 0)
-		tclass = 0;
+		hlimit = ip6_dst_hoplimit(dst);
 
 	*(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel;
 
@@ -223,20 +254,21 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 	ipv6_addr_copy(&hdr->daddr, first_hop);
 
 	skb->priority = sk->sk_priority;
+	skb->mark = sk->sk_mark;
 
 	mtu = dst_mtu(dst);
-	if ((skb->len <= mtu) || ipfragok || skb_is_gso(skb)) {
-		IP6_INC_STATS(ip6_dst_idev(skb->dst),
-			      IPSTATS_MIB_OUTREQUESTS);
-		return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev,
+	if ((skb->len <= mtu) || skb->local_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);
 	}
 
 	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);
-	IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS);
+	icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
 	kfree_skb(skb);
 	return -EMSGSIZE;
 }
@@ -251,7 +283,7 @@ EXPORT_SYMBOL(ip6_xmit);
  */
 
 int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, struct net_device *dev,
-	       struct in6_addr *saddr, struct in6_addr *daddr,
+	       const struct in6_addr *saddr, const struct in6_addr *daddr,
 	       int proto, int len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
@@ -366,19 +398,24 @@ static inline int ip6_forward_finish(struct sk_buff *skb)
 
 int ip6_forward(struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb->dst;
+	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 (ipv6_devconf.forwarding == 0)
+	if (net->ipv6.devconf_all->forwarding == 0)
 		goto error;
 
+	if (skb_warn_if_lro(skb))
+		goto drop;
+
 	if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
-		IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
+		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
 		goto drop;
 	}
 
-	skb->ip_summed = CHECKSUM_NONE;
+	skb_forward_csum(skb);
 
 	/*
 	 *	We DO NOT make any processing on
@@ -405,36 +442,39 @@ 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(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;
 	}
 
 	/* XXX: idev->cnf.proxy_ndp? */
-	if (ipv6_devconf.proxy_ndp &&
-	    pneigh_lookup(&nd_tbl, &hdr->daddr, skb->dev, 0)) {
+	if (net->ipv6.devconf_all->proxy_ndp &&
+	    pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {
 		int proxied = ip6_forward_proxy_check(skb);
 		if (proxied > 0)
 			return ip6_input(skb);
 		else if (proxied < 0) {
-			IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
+			IP6_INC_STATS(net, ip6_dst_idev(dst),
+				      IPSTATS_MIB_INDISCARDS);
 			goto drop;
 		}
 	}
 
 	if (!xfrm6_route_forward(skb)) {
-		IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
+		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
 		goto drop;
 	}
-	dst = skb->dst;
+	dst = skb_dst(skb);
 
 	/* IPv6 specs say nothing about it, but it is clear that we cannot
 	   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) {
+	if (skb->dev == dst->dev && dst->neighbour && opt->srcrt == 0 &&
+	    !skb_sec_path(skb)) {
 		struct in6_addr *target = NULL;
 		struct rt6_info *rt;
 		struct neighbour *n = dst->neighbour;
@@ -455,24 +495,38 @@ int ip6_forward(struct sk_buff *skb)
 		 */
 		if (xrlim_allow(dst, 1*HZ))
 			ndisc_send_redirect(skb, n, target);
-	} else if (ipv6_addr_type(&hdr->saddr)&(IPV6_ADDR_MULTICAST|IPV6_ADDR_LOOPBACK
-						|IPV6_ADDR_LINKLOCAL)) {
+	} else {
+		int addrtype = ipv6_addr_type(&hdr->saddr);
+
 		/* This check is security critical. */
-		goto error;
+		if (addrtype == IPV6_ADDR_ANY ||
+		    addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK))
+			goto error;
+		if (addrtype & IPV6_ADDR_LINKLOCAL) {
+			icmpv6_send(skb, ICMPV6_DEST_UNREACH,
+				    ICMPV6_NOT_NEIGHBOUR, 0);
+			goto error;
+		}
 	}
 
-	if (skb->len > dst_mtu(dst)) {
+	mtu = dst_mtu(dst);
+	if (mtu < IPV6_MIN_MTU)
+		mtu = IPV6_MIN_MTU;
+
+	if (skb->len > 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(ip6_dst_idev(dst), IPSTATS_MIB_INTOOBIGERRORS);
-		IP6_INC_STATS_BH(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(ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS);
+		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS);
 		goto drop;
 	}
 
@@ -482,11 +536,12 @@ int ip6_forward(struct sk_buff *skb)
 
 	hdr->hop_limit--;
 
-	IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
-	return NF_HOOK(PF_INET6,NF_IP6_FORWARD, skb, skb->dev, dst->dev, ip6_forward_finish);
+	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_forward_finish);
 
 error:
-	IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS);
+	IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS);
 drop:
 	kfree_skb(skb);
 	return -EINVAL;
@@ -497,8 +552,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->pkt_type = from->pkt_type;
 	to->priority = from->priority;
 	to->protocol = from->protocol;
-	dst_release(to->dst);
-	to->dst = dst_clone(from->dst);
+	skb_dst_drop(to);
+	skb_dst_set(to, dst_clone(skb_dst(from)));
 	to->dev = from->dev;
 	to->mark = from->mark;
 
@@ -506,6 +561,10 @@ 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);
 }
 
@@ -514,7 +573,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 	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(skb);
+	unsigned int packet_len = skb->tail - skb->network_header;
 	int found_rhdr = 0;
 	*nexthdr = &ipv6_hdr(skb)->nexthdr;
 
@@ -528,7 +587,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 			found_rhdr = 1;
 			break;
 		case NEXTHDR_DEST:
-#ifdef CONFIG_IPV6_MIP6
+#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
 			if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0)
 				break;
 #endif
@@ -547,13 +606,11 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 
 	return offset;
 }
-EXPORT_SYMBOL_GPL(ip6_find_1stfragopt);
 
 static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
-	struct net_device *dev;
 	struct sk_buff *frag;
-	struct rt6_info *rt = (struct rt6_info*)skb->dst;
+	struct rt6_info *rt = (struct rt6_info*)skb_dst(skb);
 	struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
 	struct ipv6hdr *tmp_hdr;
 	struct frag_hdr *fh;
@@ -561,27 +618,41 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	__be32 frag_id = 0;
 	int ptr, offset = 0, err=0;
 	u8 *prevhdr, nexthdr = 0;
+	struct net *net = dev_net(skb_dst(skb)->dev);
 
-	dev = rt->u.dst.dev;
 	hlen = ip6_find_1stfragopt(skb, &prevhdr);
 	nexthdr = *prevhdr;
 
-	mtu = dst_mtu(&rt->u.dst);
+	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.
+	 */
+	if (!skb->local_df) {
+		skb->dev = skb_dst(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);
+		return -EMSGSIZE;
+	}
+
 	if (np && np->frag_size < mtu) {
 		if (np->frag_size)
 			mtu = np->frag_size;
 	}
 	mtu -= hlen + sizeof(struct frag_hdr);
 
-	if (skb_shinfo(skb)->frag_list) {
+	if (skb_has_frags(skb)) {
 		int first_len = skb_pagelen(skb);
+		int truesizes = 0;
 
 		if (first_len - hlen > mtu ||
 		    ((first_len - hlen) & 7) ||
 		    skb_cloned(skb))
 			goto slow_path;
 
-		for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) {
+		skb_walk_frags(skb, frag) {
 			/* Correct geometry. */
 			if (frag->len > mtu ||
 			    ((frag->len & 7) && frag->next) ||
@@ -594,23 +665,23 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 			BUG_ON(frag->sk);
 			if (skb->sk) {
-				sock_hold(skb->sk);
 				frag->sk = skb->sk;
 				frag->destructor = sock_wfree;
-				skb->truesize -= frag->truesize;
+				truesizes += frag->truesize;
 			}
 		}
 
 		err = 0;
 		offset = 0;
 		frag = skb_shinfo(skb)->frag_list;
-		skb_shinfo(skb)->frag_list = NULL;
+		skb_frag_list_init(skb);
 		/* BUILD HEADER */
 
 		*prevhdr = NEXTHDR_FRAGMENT;
 		tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC);
 		if (!tmp_hdr) {
-			IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS);
+			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+				      IPSTATS_MIB_FRAGFAILS);
 			return -ENOMEM;
 		}
 
@@ -620,7 +691,7 @@ 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(skb, fh);
+		ipv6_select_ident(fh);
 		fh->nexthdr = nexthdr;
 		fh->reserved = 0;
 		fh->frag_off = htons(IP6_MF);
@@ -628,6 +699,7 @@ 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));
@@ -660,7 +732,8 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 			err = output(skb);
 			if(!err)
-				IP6_INC_STATS(ip6_dst_idev(&rt->u.dst), IPSTATS_MIB_FRAGCREATES);
+				IP6_INC_STATS(net, ip6_dst_idev(&rt->u.dst),
+					      IPSTATS_MIB_FRAGCREATES);
 
 			if (err || !frag)
 				break;
@@ -673,7 +746,8 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 		kfree(tmp_hdr);
 
 		if (err == 0) {
-			IP6_INC_STATS(ip6_dst_idev(&rt->u.dst), IPSTATS_MIB_FRAGOKS);
+			IP6_INC_STATS(net, ip6_dst_idev(&rt->u.dst),
+				      IPSTATS_MIB_FRAGOKS);
 			dst_release(&rt->u.dst);
 			return 0;
 		}
@@ -684,7 +758,8 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 			frag = skb;
 		}
 
-		IP6_INC_STATS(ip6_dst_idev(&rt->u.dst), IPSTATS_MIB_FRAGFAILS);
+		IP6_INC_STATS(net, ip6_dst_idev(&rt->u.dst),
+			      IPSTATS_MIB_FRAGFAILS);
 		dst_release(&rt->u.dst);
 		return err;
 	}
@@ -716,9 +791,9 @@ slow_path:
 		 *	Allocate buffer.
 		 */
 
-		if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_RESERVED_SPACE(rt->u.dst.dev), GFP_ATOMIC)) == NULL) {
+		if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->u.dst.dev), GFP_ATOMIC)) == NULL) {
 			NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n");
-			IP6_INC_STATS(ip6_dst_idev(skb->dst),
+			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 				      IPSTATS_MIB_FRAGFAILS);
 			err = -ENOMEM;
 			goto fail;
@@ -733,7 +808,8 @@ slow_path:
 		skb_put(frag, len + hlen + sizeof(struct frag_hdr));
 		skb_reset_network_header(frag);
 		fh = (struct frag_hdr *)(skb_network_header(frag) + hlen);
-		frag->h.raw = frag->nh.raw + hlen + sizeof(struct frag_hdr);
+		frag->transport_header = (frag->network_header + hlen +
+					  sizeof(struct frag_hdr));
 
 		/*
 		 *	Charge the memory for the fragment to any owner
@@ -745,7 +821,7 @@ slow_path:
 		/*
 		 *	Copy the packet header into the new buffer.
 		 */
-		memcpy(skb_network_header(frag), skb->data, hlen);
+		skb_copy_from_linear_data(skb, skb_network_header(frag), hlen);
 
 		/*
 		 *	Build fragment header.
@@ -753,7 +829,7 @@ slow_path:
 		fh->nexthdr = nexthdr;
 		fh->reserved = 0;
 		if (!frag_id) {
-			ipv6_select_ident(skb, fh);
+			ipv6_select_ident(fh);
 			frag_id = fh->identification;
 		} else
 			fh->identification = frag_id;
@@ -761,7 +837,7 @@ slow_path:
 		/*
 		 *	Copy a block of the IP datagram.
 		 */
-		if (skb_copy_bits(skb, ptr, frag->h.raw, len))
+		if (skb_copy_bits(skb, ptr, skb_transport_header(frag), len))
 			BUG();
 		left -= len;
 
@@ -781,15 +857,16 @@ slow_path:
 		if (err)
 			goto fail;
 
-		IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGCREATES);
+		IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+			      IPSTATS_MIB_FRAGCREATES);
 	}
-	IP6_INC_STATS(ip6_dst_idev(skb->dst),
+	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 		      IPSTATS_MIB_FRAGOKS);
 	kfree_skb(skb);
 	return err;
 
 fail:
-	IP6_INC_STATS(ip6_dst_idev(skb->dst),
+	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 		      IPSTATS_MIB_FRAGFAILS);
 	kfree_skb(skb);
 	return err;
@@ -847,57 +924,64 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 			       struct dst_entry **dst, struct flowi *fl)
 {
 	int err;
+	struct net *net = sock_net(sk);
 
 	if (*dst == NULL)
-		*dst = ip6_route_output(sk, fl);
+		*dst = ip6_route_output(net, sk, fl);
 
 	if ((err = (*dst)->error))
 		goto out_err_release;
 
 	if (ipv6_addr_any(&fl->fl6_src)) {
-		err = ipv6_get_saddr(*dst, &fl->fl6_dst, &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 (err)
 			goto out_err_release;
 	}
 
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
-		/*
-		 * Here if the dst entry we've looked up
-		 * has a neighbour entry that is in the INCOMPLETE
-		 * state and the src address from the flow is
-		 * marked as OPTIMISTIC, we release the found
-		 * dst entry and replace it instead with the
-		 * dst entry of the nexthop router
-		 */
-		if (!((*dst)->neighbour->nud_state & NUD_VALID)) {
-			struct inet6_ifaddr *ifp;
-			struct flowi fl_gw;
-			int redirect;
-
-			ifp = ipv6_get_ifaddr(&fl->fl6_src, (*dst)->dev, 1);
-
-			redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
-			if (ifp)
-				in6_ifa_put(ifp);
-
-			if (redirect) {
-				/*
-				 * We need to get the dst entry for the
-				 * 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(sk, &fl_gw);
-				if ((err = (*dst)->error))
-					goto out_err_release;
-			}
+	/*
+	 * Here if the dst entry we've looked up
+	 * has a neighbour entry that is in the INCOMPLETE
+	 * state and the src address from the flow is
+	 * marked as OPTIMISTIC, we release the found
+	 * dst entry and replace it instead with the
+	 * dst entry of the nexthop router
+	 */
+	if ((*dst)->neighbour && !((*dst)->neighbour->nud_state & NUD_VALID)) {
+		struct inet6_ifaddr *ifp;
+		struct flowi fl_gw;
+		int redirect;
+
+		ifp = ipv6_get_ifaddr(net, &fl->fl6_src,
+				      (*dst)->dev, 1);
+
+		redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
+		if (ifp)
+			in6_ifa_put(ifp);
+
+		if (redirect) {
+			/*
+			 * We need to get the dst entry for the
+			 * 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);
+			if ((err = (*dst)->error))
+				goto out_err_release;
 		}
+	}
 #endif
 
 	return 0;
 
 out_err_release:
+	if (err == -ENETUNREACH)
+		IP6_INC_STATS_BH(net, NULL, IPSTATS_MIB_OUTNOROUTES);
 	dst_release(*dst);
 	*dst = NULL;
 	return err;
@@ -976,7 +1060,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 		skb_reset_network_header(skb);
 
 		/* initialize protocol header pointer */
-		skb->h.raw = skb->nh.raw + fragheaderlen;
+		skb->transport_header = skb->network_header + fragheaderlen;
 
 		skb->ip_summed = CHECKSUM_PARTIAL;
 		skb->csum = 0;
@@ -988,11 +1072,13 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 	if (!err) {
 		struct frag_hdr fhdr;
 
-		/* specify the length of each IP datagram fragment*/
-		skb_shinfo(skb)->gso_size = mtu - fragheaderlen -
-					    sizeof(struct frag_hdr);
+		/* 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(skb, &fhdr);
+		ipv6_select_ident(&fhdr);
 		skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
 		__skb_queue_tail(&sk->sk_write_queue, skb);
 
@@ -1006,6 +1092,18 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 	return err;
 }
 
+static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src,
+					       gfp_t gfp)
+{
+	return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
+}
+
+static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src,
+						gfp_t gfp)
+{
+	return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
+}
+
 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,
@@ -1031,25 +1129,46 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		 * setup for corking
 		 */
 		if (opt) {
-			if (np->cork.opt == NULL) {
-				np->cork.opt = kmalloc(opt->tot_len,
-						       sk->sk_allocation);
-				if (unlikely(np->cork.opt == NULL))
-					return -ENOBUFS;
-			} else if (np->cork.opt->tot_len < opt->tot_len) {
-				printk(KERN_DEBUG "ip6_append_data: invalid option length\n");
+			if (WARN_ON(np->cork.opt))
 				return -EINVAL;
-			}
-			memcpy(np->cork.opt, opt, opt->tot_len);
-			inet->cork.flags |= IPCORK_OPT;
+
+			np->cork.opt = kmalloc(opt->tot_len, sk->sk_allocation);
+			if (unlikely(np->cork.opt == NULL))
+				return -ENOBUFS;
+
+			np->cork.opt->tot_len = opt->tot_len;
+			np->cork.opt->opt_flen = opt->opt_flen;
+			np->cork.opt->opt_nflen = opt->opt_nflen;
+
+			np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt,
+							    sk->sk_allocation);
+			if (opt->dst0opt && !np->cork.opt->dst0opt)
+				return -ENOBUFS;
+
+			np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt,
+							    sk->sk_allocation);
+			if (opt->dst1opt && !np->cork.opt->dst1opt)
+				return -ENOBUFS;
+
+			np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt,
+							   sk->sk_allocation);
+			if (opt->hopopt && !np->cork.opt->hopopt)
+				return -ENOBUFS;
+
+			np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt,
+							    sk->sk_allocation);
+			if (opt->srcrt && !np->cork.opt->srcrt)
+				return -ENOBUFS;
+
 			/* need source address above miyazawa*/
 		}
 		dst_hold(&rt->u.dst);
-		np->cork.rt = rt;
+		inet->cork.dst = &rt->u.dst;
 		inet->cork.fl = *fl;
 		np->cork.hop_limit = hlimit;
 		np->cork.tclass = tclass;
-		mtu = dst_mtu(rt->u.dst.path);
+		mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+		      rt->u.dst.dev->mtu : dst_mtu(rt->u.dst.path);
 		if (np->frag_size < mtu) {
 			if (np->frag_size)
 				mtu = np->frag_size;
@@ -1060,14 +1179,14 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		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);
+		exthdrlen = rt->u.dst.header_len + (opt ? opt->opt_flen : 0) -
+			    rt->rt6i_nfheader_len;
 		length += exthdrlen;
 		transhdrlen += exthdrlen;
 	} else {
-		rt = np->cork.rt;
+		rt = (struct rt6_info *)inet->cork.dst;
 		fl = &inet->cork.fl;
-		if (inet->cork.flags & IPCORK_OPT)
-			opt = np->cork.opt;
+		opt = np->cork.opt;
 		transhdrlen = 0;
 		exthdrlen = 0;
 		mtu = inet->cork.fragsize;
@@ -1075,7 +1194,8 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 
 	hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);
 
-	fragheaderlen = sizeof(struct ipv6hdr) + rt->u.dst.nfheader_len + (opt ? opt->opt_nflen : 0);
+	fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
+			(opt ? opt->opt_nflen : 0);
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
 
 	if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
@@ -1198,8 +1318,8 @@ alloc_new_skb:
 			data = skb_put(skb, fraglen);
 			skb_set_network_header(skb, exthdrlen);
 			data += fragheaderlen;
-			skb->h.raw = skb->nh.raw + fragheaderlen;
-
+			skb->transport_header = (skb->network_header +
+						 fragheaderlen);
 			if (fraggap) {
 				skb->csum = skb_copy_and_csum_bits(
 					skb_prev, maxfraglen,
@@ -1278,8 +1398,6 @@ alloc_new_skb:
 
 				skb_fill_page_desc(skb, i, page, 0, 0);
 				frag = &skb_shinfo(skb)->frags[i];
-				skb->truesize += PAGE_SIZE;
-				atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc);
 			} else {
 				err = -EMSGSIZE;
 				goto error;
@@ -1292,6 +1410,8 @@ alloc_new_skb:
 			frag->size += copy;
 			skb->len += copy;
 			skb->data_len += copy;
+			skb->truesize += copy;
+			atomic_add(copy, &sk->sk_wmem_alloc);
 		}
 		offset += copy;
 		length -= copy;
@@ -1299,10 +1419,29 @@ alloc_new_skb:
 	return 0;
 error:
 	inet->cork.length -= length;
-	IP6_INC_STATS(rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
+	IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
 	return err;
 }
 
+static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np)
+{
+	if (np->cork.opt) {
+		kfree(np->cork.opt->dst0opt);
+		kfree(np->cork.opt->dst1opt);
+		kfree(np->cork.opt->hopopt);
+		kfree(np->cork.opt->srcrt);
+		kfree(np->cork.opt);
+		np->cork.opt = NULL;
+	}
+
+	if (inet->cork.dst) {
+		dst_release(inet->cork.dst);
+		inet->cork.dst = NULL;
+		inet->cork.flags &= ~IPCORK_ALLFRAG;
+	}
+	memset(&inet->cork.fl, 0, sizeof(inet->cork.fl));
+}
+
 int ip6_push_pending_frames(struct sock *sk)
 {
 	struct sk_buff *skb, *tmp_skb;
@@ -1310,9 +1449,10 @@ int ip6_push_pending_frames(struct sock *sk)
 	struct in6_addr final_dst_buf, *final_dst = &final_dst_buf;
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct net *net = sock_net(sk);
 	struct ipv6hdr *hdr;
 	struct ipv6_txoptions *opt = np->cork.opt;
-	struct rt6_info *rt = np->cork.rt;
+	struct rt6_info *rt = (struct rt6_info *)inet->cork.dst;
 	struct flowi *fl = &inet->cork.fl;
 	unsigned char proto = fl->proto;
 	int err = 0;
@@ -1331,11 +1471,14 @@ int ip6_push_pending_frames(struct sock *sk)
 		skb->len += tmp_skb->len;
 		skb->data_len += tmp_skb->len;
 		skb->truesize += tmp_skb->truesize;
-		__sock_put(tmp_skb->sk);
 		tmp_skb->destructor = NULL;
 		tmp_skb->sk = NULL;
 	}
 
+	/* Allow local fragmentation. */
+	if (np->pmtudisc < IPV6_PMTUDISC_DO)
+		skb->local_df = 1;
+
 	ipv6_addr_copy(final_dst, &fl->fl6_dst);
 	__skb_pull(skb, skb_network_header_len(skb));
 	if (opt && opt->opt_flen)
@@ -1350,62 +1493,49 @@ int ip6_push_pending_frames(struct sock *sk)
 	*(__be32*)hdr = fl->fl6_flowlabel |
 		     htonl(0x60000000 | ((int)np->cork.tclass << 20));
 
-	if (skb->len <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN)
-		hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
-	else
-		hdr->payload_len = 0;
 	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);
 
 	skb->priority = sk->sk_priority;
+	skb->mark = sk->sk_mark;
+
+	skb_dst_set(skb, dst_clone(&rt->u.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));
 
-	skb->dst = dst_clone(&rt->u.dst);
-	IP6_INC_STATS(rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS);
-	err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, skb->dst->dev, dst_output);
+		ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
+		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
+	}
+
+	err = ip6_local_out(skb);
 	if (err) {
 		if (err > 0)
-			err = np->recverr ? net_xmit_errno(err) : 0;
+			err = net_xmit_errno(err);
 		if (err)
 			goto error;
 	}
 
 out:
-	inet->cork.flags &= ~IPCORK_OPT;
-	kfree(np->cork.opt);
-	np->cork.opt = NULL;
-	if (np->cork.rt) {
-		dst_release(&np->cork.rt->u.dst);
-		np->cork.rt = NULL;
-		inet->cork.flags &= ~IPCORK_ALLFRAG;
-	}
-	memset(&inet->cork.fl, 0, sizeof(inet->cork.fl));
+	ip6_cork_release(inet, np);
 	return err;
 error:
+	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
 	goto out;
 }
 
 void ip6_flush_pending_frames(struct sock *sk)
 {
-	struct inet_sock *inet = inet_sk(sk);
-	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sk_buff *skb;
 
 	while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) {
-		IP6_INC_STATS(ip6_dst_idev(skb->dst),
-			      IPSTATS_MIB_OUTDISCARDS);
+		if (skb_dst(skb))
+			IP6_INC_STATS(sock_net(sk), ip6_dst_idev(skb_dst(skb)),
+				      IPSTATS_MIB_OUTDISCARDS);
 		kfree_skb(skb);
 	}
 
-	inet->cork.flags &= ~IPCORK_OPT;
-
-	kfree(np->cork.opt);
-	np->cork.opt = NULL;
-	if (np->cork.rt) {
-		dst_release(&np->cork.rt->u.dst);
-		np->cork.rt = NULL;
-		inet->cork.flags &= ~IPCORK_ALLFRAG;
-	}
-	memset(&inet->cork.fl, 0, sizeof(inet->cork.fl));
+	ip6_cork_release(inet_sk(sk), inet6_sk(sk));
 }