1 files changed, 83 insertions, 49 deletions

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index b7ca46161cb9..5b2d63ed793e 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -83,24 +83,12 @@ int ip6_local_out(struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(ip6_local_out);
 
-/* 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_ni(newskb);
-	return 0;
-}
-
 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 rt6_info *rt;
 
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->dev = dev;
@@ -121,7 +109,7 @@ static int ip6_finish_output2(struct sk_buff *skb)
 			if (newskb)
 				NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
 					newskb, NULL, newskb->dev,
-					ip6_dev_loopback_xmit);
+					dev_loopback_xmit);
 
 			if (ipv6_hdr(skb)->hop_limit == 0) {
 				IP6_INC_STATS(dev_net(dev), idev,
@@ -136,9 +124,10 @@ static int ip6_finish_output2(struct sk_buff *skb)
 	}
 
 	rcu_read_lock();
-	neigh = dst_get_neighbour_noref(dst);
+	rt = (struct rt6_info *) dst;
+	neigh = rt->n;
 	if (neigh) {
-		int res = neigh_output(neigh, skb);
+		int res = dst_neigh_output(dst, neigh, skb);
 
 		rcu_read_unlock();
 		return res;
@@ -210,7 +199,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 				kfree_skb(skb);
 				return -ENOBUFS;
 			}
-			kfree_skb(skb);
+			consume_skb(skb);
 			skb = skb2;
 			skb_set_owner_w(skb, sk);
 		}
@@ -252,8 +241,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 			       dst->dev, dst_output);
 	}
 
-	if (net_ratelimit())
-		printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n");
+	net_dbg_ratelimited("IPv6: sending pkt_too_big to self\n");
 	skb->dev = dst->dev;
 	icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
@@ -464,6 +452,7 @@ int ip6_forward(struct sk_buff *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;
 
 		/*
@@ -477,14 +466,15 @@ int ip6_forward(struct sk_buff *skb)
 		else
 			target = &hdr->daddr;
 
-		if (!rt->rt6i_peer)
-			rt6_bind_peer(rt, 1);
+		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 (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ))
+		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);
 
@@ -527,6 +517,7 @@ int ip6_forward(struct sk_buff *skb)
 	hdr->hop_limit--;
 
 	IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
+	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);
 
@@ -604,12 +595,13 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
 
 	if (rt && !(rt->dst.flags & DST_NOPEER)) {
 		struct inet_peer *peer;
+		struct net *net;
 
-		if (!rt->rt6i_peer)
-			rt6_bind_peer(rt, 1);
-		peer = rt->rt6i_peer;
+		net = dev_net(rt->dst.dev);
+		peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
 		if (peer) {
 			fhdr->identification = htonl(inet_getid(peer, 0));
+			inet_putpeer(peer);
 			return;
 		}
 	}
@@ -644,7 +636,10 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	/* 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->len > mtu) {
+	if (unlikely(!skb->local_df && skb->len > 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);
 		IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
@@ -789,6 +784,10 @@ slow_path_clean:
 	}
 
 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 */
 
@@ -889,7 +888,7 @@ slow_path:
 	}
 	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 		      IPSTATS_MIB_FRAGOKS);
-	kfree_skb(skb);
+	consume_skb(skb);
 	return err;
 
 fail:
@@ -953,6 +952,7 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 	struct net *net = sock_net(sk);
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
 	struct neighbour *n;
+	struct rt6_info *rt;
 #endif
 	int err;
 
@@ -981,7 +981,8 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 	 * dst entry of the nexthop router
 	 */
 	rcu_read_lock();
-	n = dst_get_neighbour_noref(*dst);
+	rt = (struct rt6_info *) *dst;
+	n = rt->n;
 	if (n && !(n->nud_state & NUD_VALID)) {
 		struct inet6_ifaddr *ifp;
 		struct flowi6 fl_gw6;
@@ -1181,6 +1182,29 @@ 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(int *mtu,
+				int *maxfraglen,
+				unsigned int fragheaderlen,
+				struct sk_buff *skb,
+				struct rt6_info *rt)
+{
+	if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
+		if (skb == NULL) {
+			/* first fragment, reserve header_len */
+			*mtu = *mtu - rt->dst.header_len;
+
+		} else {
+			/*
+			 * this fragment is not first, the headers
+			 * space is regarded as data space.
+			 */
+			*mtu = dst_mtu(rt->dst.path);
+		}
+		*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,
@@ -1190,7 +1214,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct inet_cork *cork;
-	struct sk_buff *skb;
+	struct sk_buff *skb, *skb_prev = NULL;
 	unsigned int maxfraglen, fragheaderlen;
 	int exthdrlen;
 	int dst_exthdrlen;
@@ -1199,7 +1223,6 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	int copy;
 	int err;
 	int offset = 0;
-	int csummode = CHECKSUM_NONE;
 	__u8 tx_flags = 0;
 
 	if (flags&MSG_PROBE)
@@ -1248,8 +1271,12 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		inet->cork.fl.u.ip6 = *fl6;
 		np->cork.hop_limit = hlimit;
 		np->cork.tclass = tclass;
-		mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
-		      rt->dst.dev->mtu : dst_mtu(&rt->dst);
+		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;
@@ -1345,25 +1372,27 @@ 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);
+
+			skb_prev = skb;
 
 			/*
 			 * If remaining data exceeds the mtu,
 			 * we know we need more fragment(s).
 			 */
 			datalen = length + fraggap;
-			if (datalen > (cork->length <= mtu && !(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->dst.dev->features&NETIF_F_SG))
 				alloclen = mtu;
@@ -1372,13 +1401,16 @@ alloc_new_skb:
 
 			alloclen += dst_exthdrlen;
 
-			/*
-			 * 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->dst.trailer_len;
+			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.
@@ -1412,7 +1444,7 @@ alloc_new_skb:
 			/*
 			 *	Fill in the control structures
 			 */
-			skb->ip_summed = csummode;
+			skb->ip_summed = CHECKSUM_NONE;
 			skb->csum = 0;
 			/* reserve for fragmentation and ipsec header */
 			skb_reserve(skb, hh_len + sizeof(struct frag_hdr) +
@@ -1455,7 +1487,6 @@ alloc_new_skb:
 			transhdrlen = 0;
 			exthdrlen = 0;
 			dst_exthdrlen = 0;
-			csummode = CHECKSUM_NONE;
 
 			/*
 			 * Put the packet on the pending queue
@@ -1535,6 +1566,7 @@ error:
 	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)
 {
@@ -1638,6 +1670,7 @@ 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)
 {
@@ -1652,3 +1685,4 @@ void ip6_flush_pending_frames(struct sock *sk)
 
 	ip6_cork_release(inet_sk(sk), inet6_sk(sk));
 }
+EXPORT_SYMBOL_GPL(ip6_flush_pending_frames);