Merge branch 'master' of git://1984.lsi.us.es/nf-next

Pablo Neira Ayuso says:

====================
The following changeset contains updates for IPVS from Jesper Dangaard
Brouer that did not reach the previous merge window in time.

More specifically, updates to improve IPv6 support in IPVS. More
relevantly, some of the existing code performed wrong handling of the
extensions headers and better fragmentation handling.

Jesper promised more follow-up patches to refine this after this batch
hits net-next. Yet to come.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

include/net/ip_vs.h

@@ -22,7 +22,10 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>			/* for struct ipv6hdr */
 #include <net/ipv6.h>
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_IP_VS_IPV6)
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#endif
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <net/netfilter/nf_conntrack.h>
 #endif
 #include <net/net_namespace.h>		/* Netw namespace */
@@ -103,30 +106,117 @@ static inline struct net *seq_file_single_net(struct seq_file *seq)
 /* Connections' size value needed by ip_vs_ctl.c */
 extern int ip_vs_conn_tab_size;
 
-
 struct ip_vs_iphdr {
-	int len;
-	__u8 protocol;
+	__u32 len;	/* IPv4 simply where L4 starts
+			   IPv6 where L4 Transport Header starts */
+	__u32 thoff_reasm; /* Transport Header Offset in nfct_reasm skb */
+	__u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/
+	__s16 protocol;
+	__s32 flags;
 	union nf_inet_addr saddr;
 	union nf_inet_addr daddr;
 };
 
+/* Dependency to module: nf_defrag_ipv6 */
+#if defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE)
+static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb)
+{
+	return skb->nfct_reasm;
+}
+static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
+				      int len, void *buffer,
+				      const struct ip_vs_iphdr *ipvsh)
+{
+	if (unlikely(ipvsh->fragoffs && skb_nfct_reasm(skb)))
+		return skb_header_pointer(skb_nfct_reasm(skb),
+					  ipvsh->thoff_reasm, len, buffer);
+
+	return skb_header_pointer(skb, offset, len, buffer);
+}
+#else
+static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb)
+{
+	return NULL;
+}
+static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
+				      int len, void *buffer,
+				      const struct ip_vs_iphdr *ipvsh)
+{
+	return skb_header_pointer(skb, offset, len, buffer);
+}
+#endif
+
 static inline void
-ip_vs_fill_iphdr(int af, const void *nh, struct ip_vs_iphdr *iphdr)
+ip_vs_fill_ip4hdr(const void *nh, struct ip_vs_iphdr *iphdr)
+{
+	const struct iphdr *iph = nh;
+
+	iphdr->len	= iph->ihl * 4;
+	iphdr->fragoffs	= 0;
+	iphdr->protocol	= iph->protocol;
+	iphdr->saddr.ip	= iph->saddr;
+	iphdr->daddr.ip	= iph->daddr;
+}
+
+/* This function handles filling *ip_vs_iphdr, both for IPv4 and IPv6.
+ * IPv6 requires some extra work, as finding proper header position,
+ * depend on the IPv6 extension headers.
+ */
+static inline void
+ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr *iphdr)
 {
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
-		const struct ipv6hdr *iph = nh;
-		iphdr->len = sizeof(struct ipv6hdr);
-		iphdr->protocol = iph->nexthdr;
+		const struct ipv6hdr *iph =
+			(struct ipv6hdr *)skb_network_header(skb);
 		iphdr->saddr.in6 = iph->saddr;
 		iphdr->daddr.in6 = iph->daddr;
+		/* ipv6_find_hdr() updates len, flags, thoff_reasm */
+		iphdr->thoff_reasm = 0;
+		iphdr->len	 = 0;
+		iphdr->flags	 = 0;
+		iphdr->protocol  = ipv6_find_hdr(skb, &iphdr->len, -1,
+						 &iphdr->fragoffs,
+						 &iphdr->flags);
+		/* get proto from re-assembled packet and it's offset */
+		if (skb_nfct_reasm(skb))
+			iphdr->protocol = ipv6_find_hdr(skb_nfct_reasm(skb),
+							&iphdr->thoff_reasm,
+							-1, NULL, NULL);
+
 	} else
 #endif
 	{
-		const struct iphdr *iph = nh;
-		iphdr->len = iph->ihl * 4;
-		iphdr->protocol = iph->protocol;
+		const struct iphdr *iph =
+			(struct iphdr *)skb_network_header(skb);
+		iphdr->len	= iph->ihl * 4;
+		iphdr->fragoffs	= 0;
+		iphdr->protocol	= iph->protocol;
+		iphdr->saddr.ip	= iph->saddr;
+		iphdr->daddr.ip	= iph->daddr;
+	}
+}
+
+/* This function is a faster version of ip_vs_fill_iph_skb().
+ * Where we only populate {s,d}addr (and avoid calling ipv6_find_hdr()).
+ * This is used by the some of the ip_vs_*_schedule() functions.
+ * (Mostly done to avoid ABI breakage of external schedulers)
+ */
+static inline void
+ip_vs_fill_iph_addr_only(int af, const struct sk_buff *skb,
+			 struct ip_vs_iphdr *iphdr)
+{
+#ifdef CONFIG_IP_VS_IPV6
+	if (af == AF_INET6) {
+		const struct ipv6hdr *iph =
+			(struct ipv6hdr *)skb_network_header(skb);
+		iphdr->saddr.in6 = iph->saddr;
+		iphdr->daddr.in6 = iph->daddr;
+	} else
+#endif
+	{
+		const struct iphdr *iph =
+			(struct iphdr *)skb_network_header(skb);
 		iphdr->saddr.ip = iph->saddr;
 		iphdr->daddr.ip = iph->daddr;
 	}
@@ -165,7 +255,7 @@ static inline const char *ip_vs_dbg_addr(int af, char *buf, size_t buf_len,
 	int len;
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6)
-		len = snprintf(&buf[*idx], buf_len - *idx, "[%pI6]",
+		len = snprintf(&buf[*idx], buf_len - *idx, "[%pI6c]",
 			       &addr->in6) + 1;
 	else
 #endif
@@ -398,27 +488,26 @@ struct ip_vs_protocol {
 
 	int (*conn_schedule)(int af, struct sk_buff *skb,
 			     struct ip_vs_proto_data *pd,
-			     int *verdict, struct ip_vs_conn **cpp);
+			     int *verdict, struct ip_vs_conn **cpp,
+			     struct ip_vs_iphdr *iph);
 
 	struct ip_vs_conn *
 	(*conn_in_get)(int af,
 		       const struct sk_buff *skb,
 		       const struct ip_vs_iphdr *iph,
-		       unsigned int proto_off,
 		       int inverse);
 
 	struct ip_vs_conn *
 	(*conn_out_get)(int af,
 			const struct sk_buff *skb,
 			const struct ip_vs_iphdr *iph,
-			unsigned int proto_off,
 			int inverse);
 
-	int (*snat_handler)(struct sk_buff *skb,
-			    struct ip_vs_protocol *pp, struct ip_vs_conn *cp);
+	int (*snat_handler)(struct sk_buff *skb, struct ip_vs_protocol *pp,
+			    struct ip_vs_conn *cp, struct ip_vs_iphdr *iph);
 
-	int (*dnat_handler)(struct sk_buff *skb,
-			    struct ip_vs_protocol *pp, struct ip_vs_conn *cp);
+	int (*dnat_handler)(struct sk_buff *skb, struct ip_vs_protocol *pp,
+			    struct ip_vs_conn *cp, struct ip_vs_iphdr *iph);
 
 	int (*csum_check)(int af, struct sk_buff *skb,
 			  struct ip_vs_protocol *pp);
@@ -518,7 +607,7 @@ struct ip_vs_conn {
 	   NF_ACCEPT can be returned when destination is local.
 	 */
 	int (*packet_xmit)(struct sk_buff *skb, struct ip_vs_conn *cp,
-			   struct ip_vs_protocol *pp);
+			   struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
 
 	/* Note: we can group the following members into a structure,
 	   in order to save more space, and the following members are
@@ -769,13 +858,11 @@ struct ip_vs_app {
 
 	struct ip_vs_conn *
 	(*conn_in_get)(const struct sk_buff *skb, struct ip_vs_app *app,
-		       const struct iphdr *iph, unsigned int proto_off,
-		       int inverse);
+		       const struct iphdr *iph, int inverse);
 
 	struct ip_vs_conn *
 	(*conn_out_get)(const struct sk_buff *skb, struct ip_vs_app *app,
-			const struct iphdr *iph, unsigned int proto_off,
-			int inverse);
+			const struct iphdr *iph, int inverse);
 
 	int (*state_transition)(struct ip_vs_conn *cp, int direction,
 				const struct sk_buff *skb,
@@ -1074,14 +1161,12 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p);
 
 struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
 					    const struct ip_vs_iphdr *iph,
-					    unsigned int proto_off,
 					    int inverse);
 
 struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p);
 
 struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
 					     const struct ip_vs_iphdr *iph,
-					     unsigned int proto_off,
 					     int inverse);
 
 /* put back the conn without restarting its timer */
@@ -1254,9 +1339,10 @@ extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
 extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
 extern struct ip_vs_conn *
 ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
-	       struct ip_vs_proto_data *pd, int *ignored);
+	       struct ip_vs_proto_data *pd, int *ignored,
+	       struct ip_vs_iphdr *iph);
 extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
-			struct ip_vs_proto_data *pd);
+			struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph);
 
 extern void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg);
 
@@ -1315,33 +1401,38 @@ extern void ip_vs_read_estimator(struct ip_vs_stats_user *dst,
 /*
  *	Various IPVS packet transmitters (from ip_vs_xmit.c)
  */
-extern int ip_vs_null_xmit
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_bypass_xmit
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_nat_xmit
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_tunnel_xmit
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_dr_xmit
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_icmp_xmit
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp,
- int offset, unsigned int hooknum);
+extern int ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+			   struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+extern int ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+			     struct ip_vs_protocol *pp,
+			     struct ip_vs_iphdr *iph);
+extern int ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+			  struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+extern int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+			     struct ip_vs_protocol *pp,
+			     struct ip_vs_iphdr *iph);
+extern int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+			 struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+extern int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+			   struct ip_vs_protocol *pp, int offset,
+			   unsigned int hooknum, struct ip_vs_iphdr *iph);
 extern void ip_vs_dst_reset(struct ip_vs_dest *dest);
 
 #ifdef CONFIG_IP_VS_IPV6
-extern int ip_vs_bypass_xmit_v6
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_nat_xmit_v6
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_tunnel_xmit_v6
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_dr_xmit_v6
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_icmp_xmit_v6
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp,
- int offset, unsigned int hooknum);
+extern int ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
+				struct ip_vs_protocol *pp,
+				struct ip_vs_iphdr *iph);
+extern int ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
+			     struct ip_vs_protocol *pp,
+			     struct ip_vs_iphdr *iph);
+extern int ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
+				struct ip_vs_protocol *pp,
+				struct ip_vs_iphdr *iph);
+extern int ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
+			    struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+extern int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
+			      struct ip_vs_protocol *pp, int offset,
+			      unsigned int hooknum, struct ip_vs_iphdr *iph);
 #endif
 
 #ifdef CONFIG_SYSCTL

net/netfilter/ipvs/Kconfig

@@ -28,12 +28,11 @@ if IP_VS
 config	IP_VS_IPV6
 	bool "IPv6 support for IPVS"
 	depends on IPV6 = y || IP_VS = IPV6
+	select IP6_NF_IPTABLES
 	---help---
-	  Add IPv6 support to IPVS. This is incomplete and might be dangerous.
+	  Add IPv6 support to IPVS.
 
-	  See http://www.mindbasket.com/ipvs for more information.
-
-	  Say N if unsure.
+	  Say Y if unsure.
 
 config	IP_VS_DEBUG
 	bool "IP virtual server debugging"

net/netfilter/ipvs/ip_vs_conn.c

@@ -308,13 +308,12 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p)
 static int
 ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb,
 			    const struct ip_vs_iphdr *iph,
-			    unsigned int proto_off, int inverse,
-			    struct ip_vs_conn_param *p)
+			    int inverse, struct ip_vs_conn_param *p)
 {
 	__be16 _ports[2], *pptr;
 	struct net *net = skb_net(skb);
 
-	pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
+	pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
 	if (pptr == NULL)
 		return 1;
 
@@ -329,12 +328,11 @@ ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb,
 
 struct ip_vs_conn *
 ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
-			const struct ip_vs_iphdr *iph,
-			unsigned int proto_off, int inverse)
+			const struct ip_vs_iphdr *iph, int inverse)
 {
 	struct ip_vs_conn_param p;
 
-	if (ip_vs_conn_fill_param_proto(af, skb, iph, proto_off, inverse, &p))
+	if (ip_vs_conn_fill_param_proto(af, skb, iph, inverse, &p))
 		return NULL;
 
 	return ip_vs_conn_in_get(&p);
@@ -432,12 +430,11 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 
 struct ip_vs_conn *
 ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
-			 const struct ip_vs_iphdr *iph,
-			 unsigned int proto_off, int inverse)
+			 const struct ip_vs_iphdr *iph, int inverse)
 {
 	struct ip_vs_conn_param p;
 
-	if (ip_vs_conn_fill_param_proto(af, skb, iph, proto_off, inverse, &p))
+	if (ip_vs_conn_fill_param_proto(af, skb, iph, inverse, &p))
 		return NULL;
 
 	return ip_vs_conn_out_get(&p);

net/netfilter/ipvs/ip_vs_core.c

@@ -222,11 +222,10 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
  */
 static struct ip_vs_conn *
 ip_vs_sched_persist(struct ip_vs_service *svc,
-		    struct sk_buff *skb,
-		    __be16 src_port, __be16 dst_port, int *ignored)
+		    struct sk_buff *skb, __be16 src_port, __be16 dst_port,
+		    int *ignored, struct ip_vs_iphdr *iph)
 {
 	struct ip_vs_conn *cp = NULL;
-	struct ip_vs_iphdr iph;
 	struct ip_vs_dest *dest;
 	struct ip_vs_conn *ct;
 	__be16 dport = 0;		/* destination port to forward */
@@ -236,20 +235,18 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	union nf_inet_addr snet;	/* source network of the client,
 					   after masking */
 
-	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
-
 	/* Mask saddr with the netmask to adjust template granularity */
 #ifdef CONFIG_IP_VS_IPV6
 	if (svc->af == AF_INET6)
-		ipv6_addr_prefix(&snet.in6, &iph.saddr.in6, svc->netmask);
+		ipv6_addr_prefix(&snet.in6, &iph->saddr.in6, svc->netmask);
 	else
 #endif
-		snet.ip = iph.saddr.ip & svc->netmask;
+		snet.ip = iph->saddr.ip & svc->netmask;
 
 	IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u "
 		      "mnet %s\n",
-		      IP_VS_DBG_ADDR(svc->af, &iph.saddr), ntohs(src_port),
-		      IP_VS_DBG_ADDR(svc->af, &iph.daddr), ntohs(dst_port),
+		      IP_VS_DBG_ADDR(svc->af, &iph->saddr), ntohs(src_port),
+		      IP_VS_DBG_ADDR(svc->af, &iph->daddr), ntohs(dst_port),
 		      IP_VS_DBG_ADDR(svc->af, &snet));
 
 	/*
@@ -266,8 +263,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	 * is created for other persistent services.
 	 */
 	{
-		int protocol = iph.protocol;
-		const union nf_inet_addr *vaddr = &iph.daddr;
+		int protocol = iph->protocol;
+		const union nf_inet_addr *vaddr = &iph->daddr;
 		__be16 vport = 0;
 
 		if (dst_port == svc->port) {
@@ -342,14 +339,14 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		dport = dest->port;
 
 	flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
-		 && iph.protocol == IPPROTO_UDP)?
+		 && iph->protocol == IPPROTO_UDP) ?
 		IP_VS_CONN_F_ONE_PACKET : 0;
 
 	/*
 	 *    Create a new connection according to the template
 	 */
-	ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, &iph.saddr,
-			      src_port, &iph.daddr, dst_port, &param);
+	ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, &iph->saddr,
+			      src_port, &iph->daddr, dst_port, &param);
 
 	cp = ip_vs_conn_new(&param, &dest->addr, dport, flags, dest, skb->mark);
 	if (cp == NULL) {
@@ -392,18 +389,20 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
  */
 struct ip_vs_conn *
 ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
-	       struct ip_vs_proto_data *pd, int *ignored)
+	       struct ip_vs_proto_data *pd, int *ignored,
+	       struct ip_vs_iphdr *iph)
 {
 	struct ip_vs_protocol *pp = pd->pp;
 	struct ip_vs_conn *cp = NULL;
-	struct ip_vs_iphdr iph;
 	struct ip_vs_dest *dest;
 	__be16 _ports[2], *pptr;
 	unsigned int flags;
 
 	*ignored = 1;
-	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
-	pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports);
+	/*
+	 * IPv6 frags, only the first hit here.
+	 */
+	pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
 	if (pptr == NULL)
 		return NULL;
 
@@ -423,7 +422,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	 *    Do not schedule replies from local real server.
 	 */
 	if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
-	    (cp = pp->conn_in_get(svc->af, skb, &iph, iph.len, 1))) {
+	    (cp = pp->conn_in_get(svc->af, skb, iph, 1))) {
 		IP_VS_DBG_PKT(12, svc->af, pp, skb, 0,
 			      "Not scheduling reply for existing connection");
 		__ip_vs_conn_put(cp);
@@ -434,7 +433,8 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	 *    Persistent service
 	 */
 	if (svc->flags & IP_VS_SVC_F_PERSISTENT)
-		return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1], ignored);
+		return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1], ignored,
+					   iph);
 
 	*ignored = 0;
 
@@ -456,7 +456,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	}
 
 	flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
-		 && iph.protocol == IPPROTO_UDP)?
+		 && iph->protocol == IPPROTO_UDP) ?
 		IP_VS_CONN_F_ONE_PACKET : 0;
 
 	/*
@@ -465,9 +465,9 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	{
 		struct ip_vs_conn_param p;
 
-		ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol,
-				      &iph.saddr, pptr[0], &iph.daddr, pptr[1],
-				      &p);
+		ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol,
+				      &iph->saddr, pptr[0], &iph->daddr,
+				      pptr[1], &p);
 		cp = ip_vs_conn_new(&p, &dest->addr,
 				    dest->port ? dest->port : pptr[1],
 				    flags, dest, skb->mark);
@@ -496,19 +496,16 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
  *  no destination is available for a new connection.
  */
 int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
-		struct ip_vs_proto_data *pd)
+		struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph)
 {
 	__be16 _ports[2], *pptr;
-	struct ip_vs_iphdr iph;
 #ifdef CONFIG_SYSCTL
 	struct net *net;
 	struct netns_ipvs *ipvs;
 	int unicast;
 #endif
 
-	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
-
-	pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports);
+	pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
 	if (pptr == NULL) {
 		ip_vs_service_put(svc);
 		return NF_DROP;
@@ -519,10 +516,10 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (svc->af == AF_INET6)
-		unicast = ipv6_addr_type(&iph.daddr.in6) & IPV6_ADDR_UNICAST;
+		unicast = ipv6_addr_type(&iph->daddr.in6) & IPV6_ADDR_UNICAST;
 	else
 #endif
-		unicast = (inet_addr_type(net, iph.daddr.ip) == RTN_UNICAST);
+		unicast = (inet_addr_type(net, iph->daddr.ip) == RTN_UNICAST);
 
 	/* if it is fwmark-based service, the cache_bypass sysctl is up
 	   and the destination is a non-local unicast, then create
@@ -532,7 +529,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		int ret;
 		struct ip_vs_conn *cp;
 		unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET &&
-				      iph.protocol == IPPROTO_UDP)?
+				      iph->protocol == IPPROTO_UDP) ?
 				      IP_VS_CONN_F_ONE_PACKET : 0;
 		union nf_inet_addr daddr =  { .all = { 0, 0, 0, 0 } };
 
@@ -542,9 +539,9 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__);
 		{
 			struct ip_vs_conn_param p;
-			ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol,
-					      &iph.saddr, pptr[0],
-					      &iph.daddr, pptr[1], &p);
+			ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol,
+					      &iph->saddr, pptr[0],
+					      &iph->daddr, pptr[1], &p);
 			cp = ip_vs_conn_new(&p, &daddr, 0,
 					    IP_VS_CONN_F_BYPASS | flags,
 					    NULL, skb->mark);
@@ -559,7 +556,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
 
 		/* transmit the first SYN packet */
-		ret = cp->packet_xmit(skb, cp, pd->pp);
+		ret = cp->packet_xmit(skb, cp, pd->pp, iph);
 		/* do not touch skb anymore */
 
 		atomic_inc(&cp->in_pkts);
@@ -654,14 +651,6 @@ static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user)
 	return err;
 }
 
-#ifdef CONFIG_IP_VS_IPV6
-static inline int ip_vs_gather_frags_v6(struct sk_buff *skb, u_int32_t user)
-{
-	/* TODO IPv6: Find out what to do here for IPv6 */
-	return 0;
-}
-#endif
-
 static int ip_vs_route_me_harder(int af, struct sk_buff *skb)
 {
 #ifdef CONFIG_IP_VS_IPV6
@@ -732,10 +721,19 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		    struct ip_vs_conn *cp, int inout)
 {
 	struct ipv6hdr *iph	 = ipv6_hdr(skb);
-	unsigned int icmp_offset = sizeof(struct ipv6hdr);
-	struct icmp6hdr *icmph	 = (struct icmp6hdr *)(skb_network_header(skb) +
-						      icmp_offset);
-	struct ipv6hdr *ciph	 = (struct ipv6hdr *)(icmph + 1);
+	unsigned int icmp_offset = 0;
+	unsigned int offs	 = 0; /* header offset*/
+	int protocol;
+	struct icmp6hdr *icmph;
+	struct ipv6hdr *ciph;
+	unsigned short fragoffs;
+
+	ipv6_find_hdr(skb, &icmp_offset, IPPROTO_ICMPV6, &fragoffs, NULL);
+	icmph = (struct icmp6hdr *)(skb_network_header(skb) + icmp_offset);
+	offs = icmp_offset + sizeof(struct icmp6hdr);
+	ciph = (struct ipv6hdr *)(skb_network_header(skb) + offs);
+
+	protocol = ipv6_find_hdr(skb, &offs, -1, &fragoffs, NULL);
 
 	if (inout) {
 		iph->saddr = cp->vaddr.in6;
@@ -746,10 +744,13 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
 	}
 
 	/* the TCP/UDP/SCTP port */
-	if (IPPROTO_TCP == ciph->nexthdr || IPPROTO_UDP == ciph->nexthdr ||
-	    IPPROTO_SCTP == ciph->nexthdr) {
-		__be16 *ports = (void *)ciph + sizeof(struct ipv6hdr);
+	if (!fragoffs && (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol ||
+			  IPPROTO_SCTP == protocol)) {
+		__be16 *ports = (void *)(skb_network_header(skb) + offs);
 
+		IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__,
+			      ntohs(inout ? ports[1] : ports[0]),
+			      ntohs(inout ? cp->vport : cp->dport));
 		if (inout)
 			ports[1] = cp->vport;
 		else
@@ -898,51 +899,35 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
 	IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
 		      "Checking outgoing ICMP for");
 
-	offset += cih->ihl * 4;
-
-	ip_vs_fill_iphdr(AF_INET, cih, &ciph);
+	ip_vs_fill_ip4hdr(cih, &ciph);
+	ciph.len += offset;
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_out_get(AF_INET, skb, &ciph, offset, 1);
+	cp = pp->conn_out_get(AF_INET, skb, &ciph, 1);
 	if (!cp)
 		return NF_ACCEPT;
 
 	snet.ip = iph->saddr;
 	return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp,
-				    pp, offset, ihl);
+				    pp, ciph.len, ihl);
 }
 
 #ifdef CONFIG_IP_VS_IPV6
 static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
-			     unsigned int hooknum)
+			     unsigned int hooknum, struct ip_vs_iphdr *ipvsh)
 {
-	struct ipv6hdr *iph;
 	struct icmp6hdr	_icmph, *ic;
-	struct ipv6hdr	_ciph, *cih;	/* The ip header contained
-					   within the ICMP */
-	struct ip_vs_iphdr ciph;
+	struct ipv6hdr _ip6h, *ip6h; /* The ip header contained within ICMP */
+	struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
-	unsigned int offset;
 	union nf_inet_addr snet;
+	unsigned int writable;
 
 	*related = 1;
-
-	/* reassemble IP fragments */
-	if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) {
-		if (ip_vs_gather_frags_v6(skb, ip_vs_defrag_user(hooknum)))
-			return NF_STOLEN;
-	}
-
-	iph = ipv6_hdr(skb);
-	offset = sizeof(struct ipv6hdr);
-	ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph);
+	ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph, ipvsh);
 	if (ic == NULL)
 		return NF_DROP;
 
-	IP_VS_DBG(12, "Outgoing ICMPv6 (%d,%d) %pI6->%pI6\n",
-		  ic->icmp6_type, ntohs(icmpv6_id(ic)),
-		  &iph->saddr, &iph->daddr);
-
 	/*
 	 * Work through seeing if this is for us.
 	 * These checks are supposed to be in an order that means easy
@@ -950,42 +935,45 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
 	 * this means that some packets will manage to get a long way
 	 * down this stack and then be rejected, but that's life.
 	 */
-	if ((ic->icmp6_type != ICMPV6_DEST_UNREACH) &&
-	    (ic->icmp6_type != ICMPV6_PKT_TOOBIG) &&
-	    (ic->icmp6_type != ICMPV6_TIME_EXCEED)) {
+	if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) {
 		*related = 0;
 		return NF_ACCEPT;
 	}
+	/* Fragment header that is before ICMP header tells us that:
+	 * it's not an error message since they can't be fragmented.
+	 */
+	if (ipvsh->flags & IP6T_FH_F_FRAG)
+		return NF_DROP;
+
+	IP_VS_DBG(8, "Outgoing ICMPv6 (%d,%d) %pI6c->%pI6c\n",
+		  ic->icmp6_type, ntohs(icmpv6_id(ic)),
+		  &ipvsh->saddr, &ipvsh->daddr);
 
 	/* Now find the contained IP header */
-	offset += sizeof(_icmph);
-	cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
-	if (cih == NULL)
+	ciph.len = ipvsh->len + sizeof(_icmph);
+	ip6h = skb_header_pointer(skb, ciph.len, sizeof(_ip6h), &_ip6h);
+	if (ip6h == NULL)
 		return NF_ACCEPT; /* The packet looks wrong, ignore */
-
-	pp = ip_vs_proto_get(cih->nexthdr);
+	ciph.saddr.in6 = ip6h->saddr; /* conn_out_get() handles reverse order */
+	ciph.daddr.in6 = ip6h->daddr;
+	/* skip possible IPv6 exthdrs of contained IPv6 packet */
+	ciph.protocol = ipv6_find_hdr(skb, &ciph.len, -1, &ciph.fragoffs, NULL);
+	if (ciph.protocol < 0)
+		return NF_ACCEPT; /* Contained IPv6 hdr looks wrong, ignore */
+
+	pp = ip_vs_proto_get(ciph.protocol);
 	if (!pp)
 		return NF_ACCEPT;
 
-	/* Is the embedded protocol header present? */
-	/* TODO: we don't support fragmentation at the moment anyways */
-	if (unlikely(cih->nexthdr == IPPROTO_FRAGMENT && pp->dont_defrag))
-		return NF_ACCEPT;
-
-	IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset,
-		      "Checking outgoing ICMPv6 for");
-
-	offset += sizeof(struct ipv6hdr);
-
-	ip_vs_fill_iphdr(AF_INET6, cih, &ciph);
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_out_get(AF_INET6, skb, &ciph, offset, 1);
+	cp = pp->conn_out_get(AF_INET6, skb, &ciph, 1);
 	if (!cp)
 		return NF_ACCEPT;
 
-	snet.in6 = iph->saddr;
-	return handle_response_icmp(AF_INET6, skb, &snet, cih->nexthdr, cp,
-				    pp, offset, sizeof(struct ipv6hdr));
+	snet.in6 = ciph.saddr.in6;
+	writable = ciph.len;
+	return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp,
+				    pp, writable, sizeof(struct ipv6hdr));
 }
 #endif
 
@@ -1018,17 +1006,17 @@ static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len)
  */
 static unsigned int
 handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
-		struct ip_vs_conn *cp, int ihl)
+		struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
 {
 	struct ip_vs_protocol *pp = pd->pp;
 
 	IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet");
 
-	if (!skb_make_writable(skb, ihl))
+	if (!skb_make_writable(skb, iph->len))
 		goto drop;
 
 	/* mangle the packet */
-	if (pp->snat_handler && !pp->snat_handler(skb, pp, cp))
+	if (pp->snat_handler && !pp->snat_handler(skb, pp, cp, iph))
 		goto drop;
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -1115,17 +1103,22 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	if (!net_ipvs(net)->enable)
 		return NF_ACCEPT;
 
-	ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_skb(af, skb, &iph);
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
+		if (!iph.fragoffs && skb_nfct_reasm(skb)) {
+			struct sk_buff *reasm = skb_nfct_reasm(skb);
+			/* Save fw mark for coming frags */
+			reasm->ipvs_property = 1;
+			reasm->mark = skb->mark;
+		}
 		if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
 			int related;
 			int verdict = ip_vs_out_icmp_v6(skb, &related,
-							hooknum);
+							hooknum, &iph);
 
 			if (related)
 				return verdict;
-			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 		}
 	} else
 #endif
@@ -1135,7 +1128,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 
 			if (related)
 				return verdict;
-			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 		}
 
 	pd = ip_vs_proto_data_get(net, iph.protocol);
@@ -1145,39 +1137,31 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 
 	/* reassemble IP fragments */
 #ifdef CONFIG_IP_VS_IPV6
-	if (af == AF_INET6) {
-		if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) {
-			if (ip_vs_gather_frags_v6(skb,
-						  ip_vs_defrag_user(hooknum)))
-				return NF_STOLEN;
-		}
-
-		ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
-	} else
+	if (af == AF_INET)
 #endif
 		if (unlikely(ip_is_fragment(ip_hdr(skb)) && !pp->dont_defrag)) {
 			if (ip_vs_gather_frags(skb,
 					       ip_vs_defrag_user(hooknum)))
 				return NF_STOLEN;
 
-			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+			ip_vs_fill_ip4hdr(skb_network_header(skb), &iph);
 		}
 
 	/*
 	 * Check if the packet belongs to an existing entry
 	 */
-	cp = pp->conn_out_get(af, skb, &iph, iph.len, 0);
+	cp = pp->conn_out_get(af, skb, &iph, 0);
 
 	if (likely(cp))
-		return handle_response(af, skb, pd, cp, iph.len);
+		return handle_response(af, skb, pd, cp, &iph);
 	if (sysctl_nat_icmp_send(net) &&
 	    (pp->protocol == IPPROTO_TCP ||
 	     pp->protocol == IPPROTO_UDP ||
 	     pp->protocol == IPPROTO_SCTP)) {
 		__be16 _ports[2], *pptr;
 
-		pptr = skb_header_pointer(skb, iph.len,
-					  sizeof(_ports), _ports);
+		pptr = frag_safe_skb_hp(skb, iph.len,
+					 sizeof(_ports), _ports, &iph);
 		if (pptr == NULL)
 			return NF_ACCEPT;	/* Not for me */
 		if (ip_vs_lookup_real_service(net, af, iph.protocol,
@@ -1375,13 +1359,13 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 		      "Checking incoming ICMP for");
 
 	offset2 = offset;
-	offset += cih->ihl * 4;
-
-	ip_vs_fill_iphdr(AF_INET, cih, &ciph);
+	ip_vs_fill_ip4hdr(cih, &ciph);
+	ciph.len += offset;
+	offset = ciph.len;
 	/* The embedded headers contain source and dest in reverse order.
 	 * For IPIP this is error for request, not for reply.
 	 */
-	cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, ipip ? 0 : 1);
+	cp = pp->conn_in_get(AF_INET, skb, &ciph, ipip ? 0 : 1);
 	if (!cp)
 		return NF_ACCEPT;
 
@@ -1450,7 +1434,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 	ip_vs_in_stats(cp, skb);
 	if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol)
 		offset += 2 * sizeof(__u16);
-	verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum);
+	verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph);
 
 out:
 	__ip_vs_conn_put(cp);
@@ -1459,38 +1443,24 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 }
 
 #ifdef CONFIG_IP_VS_IPV6
-static int
-ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
+static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related,
+			    unsigned int hooknum, struct ip_vs_iphdr *iph)
 {
 	struct net *net = NULL;
-	struct ipv6hdr *iph;
+	struct ipv6hdr _ip6h, *ip6h;
 	struct icmp6hdr	_icmph, *ic;
-	struct ipv6hdr	_ciph, *cih;	/* The ip header contained
-					   within the ICMP */
-	struct ip_vs_iphdr ciph;
+	struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
 	struct ip_vs_proto_data *pd;
-	unsigned int offset, verdict;
+	unsigned int offs_ciph, writable, verdict;
 
 	*related = 1;
 
-	/* reassemble IP fragments */
-	if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) {
-		if (ip_vs_gather_frags_v6(skb, ip_vs_defrag_user(hooknum)))
-			return NF_STOLEN;
-	}
-
-	iph = ipv6_hdr(skb);
-	offset = sizeof(struct ipv6hdr);
-	ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph);
+	ic = frag_safe_skb_hp(skb, iph->len, sizeof(_icmph), &_icmph, iph);
 	if (ic == NULL)
 		return NF_DROP;
 
-	IP_VS_DBG(12, "Incoming ICMPv6 (%d,%d) %pI6->%pI6\n",
-		  ic->icmp6_type, ntohs(icmpv6_id(ic)),
-		  &iph->saddr, &iph->daddr);
-
 	/*
 	 * Work through seeing if this is for us.
 	 * These checks are supposed to be in an order that means easy
@@ -1498,47 +1468,71 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 	 * this means that some packets will manage to get a long way
 	 * down this stack and then be rejected, but that's life.
 	 */
-	if ((ic->icmp6_type != ICMPV6_DEST_UNREACH) &&
-	    (ic->icmp6_type != ICMPV6_PKT_TOOBIG) &&
-	    (ic->icmp6_type != ICMPV6_TIME_EXCEED)) {
+	if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) {
 		*related = 0;
 		return NF_ACCEPT;
 	}
+	/* Fragment header that is before ICMP header tells us that:
+	 * it's not an error message since they can't be fragmented.
+	 */
+	if (iph->flags & IP6T_FH_F_FRAG)
+		return NF_DROP;
+
+	IP_VS_DBG(8, "Incoming ICMPv6 (%d,%d) %pI6c->%pI6c\n",
+		  ic->icmp6_type, ntohs(icmpv6_id(ic)),
+		  &iph->saddr, &iph->daddr);
 
 	/* Now find the contained IP header */
-	offset += sizeof(_icmph);
-	cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
-	if (cih == NULL)
+	ciph.len = iph->len + sizeof(_icmph);
+	offs_ciph = ciph.len; /* Save ip header offset */
+	ip6h = skb_header_pointer(skb, ciph.len, sizeof(_ip6h), &_ip6h);
+	if (ip6h == NULL)
 		return NF_ACCEPT; /* The packet looks wrong, ignore */
+	ciph.saddr.in6 = ip6h->saddr; /* conn_in_get() handles reverse order */
+	ciph.daddr.in6 = ip6h->daddr;
+	/* skip possible IPv6 exthdrs of contained IPv6 packet */
+	ciph.protocol = ipv6_find_hdr(skb, &ciph.len, -1, &ciph.fragoffs, NULL);
+	if (ciph.protocol < 0)
+		return NF_ACCEPT; /* Contained IPv6 hdr looks wrong, ignore */
 
 	net = skb_net(skb);
-	pd = ip_vs_proto_data_get(net, cih->nexthdr);
+	pd = ip_vs_proto_data_get(net, ciph.protocol);
 	if (!pd)
 		return NF_ACCEPT;
 	pp = pd->pp;
 
-	/* Is the embedded protocol header present? */
-	/* TODO: we don't support fragmentation at the moment anyways */
-	if (unlikely(cih->nexthdr == IPPROTO_FRAGMENT && pp->dont_defrag))
+	/* Cannot handle fragmented embedded protocol */
+	if (ciph.fragoffs)
 		return NF_ACCEPT;
 
-	IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset,
+	IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offs_ciph,
 		      "Checking incoming ICMPv6 for");
 
-	offset += sizeof(struct ipv6hdr);
+	/* The embedded headers contain source and dest in reverse order
+	 * if not from localhost
+	 */
+	cp = pp->conn_in_get(AF_INET6, skb, &ciph,
+			     (hooknum == NF_INET_LOCAL_OUT) ? 0 : 1);
 
-	ip_vs_fill_iphdr(AF_INET6, cih, &ciph);
-	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_in_get(AF_INET6, skb, &ciph, offset, 1);
 	if (!cp)
 		return NF_ACCEPT;
+	/* VS/TUN, VS/DR and LOCALNODE just let it go */
+	if ((hooknum == NF_INET_LOCAL_OUT) &&
+	    (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)) {
+		__ip_vs_conn_put(cp);
+		return NF_ACCEPT;
+	}
 
 	/* do the statistics and put it back */
 	ip_vs_in_stats(cp, skb);
-	if (IPPROTO_TCP == cih->nexthdr || IPPROTO_UDP == cih->nexthdr ||
-	    IPPROTO_SCTP == cih->nexthdr)
-		offset += 2 * sizeof(__u16);
-	verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum);
+
+	/* Need to mangle contained IPv6 header in ICMPv6 packet */
+	writable = ciph.len;
+	if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol ||
+	    IPPROTO_SCTP == ciph.protocol)
+		writable += 2 * sizeof(__u16); /* Also mangle ports */
+
+	verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, writable, hooknum, &ciph);
 
 	__ip_vs_conn_put(cp);
 
@@ -1574,7 +1568,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	if (unlikely((skb->pkt_type != PACKET_HOST &&
 		      hooknum != NF_INET_LOCAL_OUT) ||
 		     !skb_dst(skb))) {
-		ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+		ip_vs_fill_iph_skb(af, skb, &iph);
 		IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s"
 			      " ignored in hook %u\n",
 			      skb->pkt_type, iph.protocol,
@@ -1586,7 +1580,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	if (!net_ipvs(net)->enable)
 		return NF_ACCEPT;
 
-	ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_skb(af, skb, &iph);
 
 	/* Bad... Do not break raw sockets */
 	if (unlikely(skb->sk != NULL && hooknum == NF_INET_LOCAL_OUT &&
@@ -1600,13 +1594,19 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
+		if (!iph.fragoffs && skb_nfct_reasm(skb)) {
+			struct sk_buff *reasm = skb_nfct_reasm(skb);
+			/* Save fw mark for coming frags. */
+			reasm->ipvs_property = 1;
+			reasm->mark = skb->mark;
+		}
 		if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
 			int related;
-			int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum);
+			int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum,
+						       &iph);
 
 			if (related)
 				return verdict;
-			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 		}
 	} else
 #endif
@@ -1616,7 +1616,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 
 			if (related)
 				return verdict;
-			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 		}
 
 	/* Protocol supported? */
@@ -1627,12 +1626,15 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	/*
 	 * Check if the packet belongs to an existing connection entry
 	 */
-	cp = pp->conn_in_get(af, skb, &iph, iph.len, 0);
-
-	if (unlikely(!cp)) {
+	cp = pp->conn_in_get(af, skb, &iph, 0);
+	if (unlikely(!cp) && !iph.fragoffs) {
+		/* No (second) fragments need to enter here, as nf_defrag_ipv6
+		 * replayed fragment zero will already have created the cp
+		 */
 		int v;
 
-		if (!pp->conn_schedule(af, skb, pd, &v, &cp))
+		/* Schedule and create new connection entry into &cp */
+		if (!pp->conn_schedule(af, skb, pd, &v, &cp, &iph))
 			return v;
 	}
 
@@ -1640,6 +1642,14 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 		/* sorry, all this trouble for a no-hit :) */
 		IP_VS_DBG_PKT(12, af, pp, skb, 0,
 			      "ip_vs_in: packet continues traversal as normal");
+		if (iph.fragoffs && !skb_nfct_reasm(skb)) {
+			/* Fragment that couldn't be mapped to a conn entry
+			 * and don't have any pointer to a reasm skb
+			 * is missing module nf_defrag_ipv6
+			 */
+			IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n");
+			IP_VS_DBG_PKT(7, af, pp, skb, 0, "unhandled fragment");
+		}
 		return NF_ACCEPT;
 	}
 
@@ -1662,7 +1672,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	ip_vs_in_stats(cp, skb);
 	ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
 	if (cp->packet_xmit)
-		ret = cp->packet_xmit(skb, cp, pp);
+		ret = cp->packet_xmit(skb, cp, pp, &iph);
 		/* do not touch skb anymore */
 	else {
 		IP_VS_DBG_RL("warning: packet_xmit is null");
@@ -1723,6 +1733,38 @@ ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb,
 
 #ifdef CONFIG_IP_VS_IPV6
 
+/*
+ * AF_INET6 fragment handling
+ * Copy info from first fragment, to the rest of them.
+ */
+static unsigned int
+ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb,
+		     const struct net_device *in,
+		     const struct net_device *out,
+		     int (*okfn)(struct sk_buff *))
+{
+	struct sk_buff *reasm = skb_nfct_reasm(skb);
+	struct net *net;
+
+	/* Skip if not a "replay" from nf_ct_frag6_output or first fragment.
+	 * ipvs_property is set when checking first fragment
+	 * in ip_vs_in() and ip_vs_out().
+	 */
+	if (reasm)
+		IP_VS_DBG(2, "Fragment recv prop:%d\n", reasm->ipvs_property);
+	if (!reasm || !reasm->ipvs_property)
+		return NF_ACCEPT;
+
+	net = skb_net(skb);
+	if (!net_ipvs(net)->enable)
+		return NF_ACCEPT;
+
+	/* Copy stored fw mark, saved in ip_vs_{in,out} */
+	skb->mark = reasm->mark;
+
+	return NF_ACCEPT;
+}
+
 /*
  *	AF_INET6 handler in NF_INET_LOCAL_IN chain
  *	Schedule and forward packets from remote clients
@@ -1793,8 +1835,10 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb,
 {
 	int r;
 	struct net *net;
+	struct ip_vs_iphdr iphdr;
 
-	if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6)
+	ip_vs_fill_iph_skb(AF_INET6, skb, &iphdr);
+	if (iphdr.protocol != IPPROTO_ICMPV6)
 		return NF_ACCEPT;
 
 	/* ipvs enabled in this netns ? */
@@ -1802,7 +1846,7 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb,
 	if (!net_ipvs(net)->enable)
 		return NF_ACCEPT;
 
-	return ip_vs_in_icmp_v6(skb, &r, hooknum);
+	return ip_vs_in_icmp_v6(skb, &r, hooknum, &iphdr);
 }
 #endif
 
@@ -1860,6 +1904,14 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 		.priority	= 100,
 	},
 #ifdef CONFIG_IP_VS_IPV6
+	/* After mangle & nat fetch 2:nd fragment and following */
+	{
+		.hook		= ip_vs_preroute_frag6,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_PRE_ROUTING,
+		.priority	= NF_IP6_PRI_NAT_DST + 1,
+	},
 	/* After packet filtering, change source only for VS/NAT */
 	{
 		.hook		= ip_vs_reply6,

net/netfilter/ipvs/ip_vs_dh.c

@@ -215,7 +215,7 @@ ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	struct ip_vs_dh_bucket *tbl;
 	struct ip_vs_iphdr iph;
 
-	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_addr_only(svc->af, skb, &iph);
 
 	IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
 

net/netfilter/ipvs/ip_vs_lblc.c

@@ -479,7 +479,7 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	struct ip_vs_dest *dest = NULL;
 	struct ip_vs_lblc_entry *en;
 
-	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_addr_only(svc->af, skb, &iph);
 
 	IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
 

net/netfilter/ipvs/ip_vs_lblcr.c

@@ -649,7 +649,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	struct ip_vs_dest *dest = NULL;
 	struct ip_vs_lblcr_entry *en;
 
-	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_addr_only(svc->af, skb, &iph);
 
 	IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
 

net/netfilter/ipvs/ip_vs_pe_sip.c

@@ -68,23 +68,31 @@ static int get_callid(const char *dptr, unsigned int dataoff,
 static int
 ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 {
+	struct sk_buff *reasm = skb_nfct_reasm(skb);
 	struct ip_vs_iphdr iph;
 	unsigned int dataoff, datalen, matchoff, matchlen;
 	const char *dptr;
 	int retc;
 
-	ip_vs_fill_iphdr(p->af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_skb(p->af, skb, &iph);
 
 	/* Only useful with UDP */
 	if (iph.protocol != IPPROTO_UDP)
 		return -EINVAL;
+	/* todo: IPv6 fragments:
+	 *       I think this only should be done for the first fragment. /HS
+	 */
+	if (reasm) {
+		skb = reasm;
+		dataoff = iph.thoff_reasm + sizeof(struct udphdr);
+	} else
+		dataoff = iph.len + sizeof(struct udphdr);
 
-	/* No Data ? */
-	dataoff = iph.len + sizeof(struct udphdr);
 	if (dataoff >= skb->len)
 		return -EINVAL;
-
-	if ((retc=skb_linearize(skb)) < 0)
+	/* todo: Check if this will mess-up the reasm skb !!! /HS */
+	retc = skb_linearize(skb);
+	if (retc < 0)
 		return retc;
 	dptr = skb->data + dataoff;
 	datalen = skb->len - dataoff;

net/netfilter/ipvs/ip_vs_proto.c

@@ -280,17 +280,17 @@ ip_vs_tcpudp_debug_packet_v6(struct ip_vs_protocol *pp,
 	if (ih == NULL)
 		sprintf(buf, "TRUNCATED");
 	else if (ih->nexthdr == IPPROTO_FRAGMENT)
-		sprintf(buf, "%pI6->%pI6 frag",	&ih->saddr, &ih->daddr);
+		sprintf(buf, "%pI6c->%pI6c frag", &ih->saddr, &ih->daddr);
 	else {
 		__be16 _ports[2], *pptr;
 
 		pptr = skb_header_pointer(skb, offset + sizeof(struct ipv6hdr),
 					  sizeof(_ports), _ports);
 		if (pptr == NULL)
-			sprintf(buf, "TRUNCATED %pI6->%pI6",
+			sprintf(buf, "TRUNCATED %pI6c->%pI6c",
 				&ih->saddr, &ih->daddr);
 		else
-			sprintf(buf, "%pI6:%u->%pI6:%u",
+			sprintf(buf, "%pI6c:%u->%pI6c:%u",
 				&ih->saddr, ntohs(pptr[0]),
 				&ih->daddr, ntohs(pptr[1]));
 	}

net/netfilter/ipvs/ip_vs_proto_ah_esp.c

@@ -57,7 +57,7 @@ ah_esp_conn_fill_param_proto(struct net *net, int af,
 
 static struct ip_vs_conn *
 ah_esp_conn_in_get(int af, const struct sk_buff *skb,
-		   const struct ip_vs_iphdr *iph, unsigned int proto_off,
+		   const struct ip_vs_iphdr *iph,
 		   int inverse)
 {
 	struct ip_vs_conn *cp;
@@ -85,9 +85,7 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb,
 
 static struct ip_vs_conn *
 ah_esp_conn_out_get(int af, const struct sk_buff *skb,
-		    const struct ip_vs_iphdr *iph,
-		    unsigned int proto_off,
-		    int inverse)
+		    const struct ip_vs_iphdr *iph, int inverse)
 {
 	struct ip_vs_conn *cp;
 	struct ip_vs_conn_param p;
@@ -110,7 +108,8 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb,
 
 static int
 ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
-		     int *verdict, struct ip_vs_conn **cpp)
+		     int *verdict, struct ip_vs_conn **cpp,
+		     struct ip_vs_iphdr *iph)
 {
 	/*
 	 * AH/ESP is only related traffic. Pass the packet to IP stack.

net/netfilter/ipvs/ip_vs_proto_sctp.c

@@ -10,28 +10,26 @@
 
 static int
 sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
-		   int *verdict, struct ip_vs_conn **cpp)
+		   int *verdict, struct ip_vs_conn **cpp,
+		   struct ip_vs_iphdr *iph)
 {
 	struct net *net;
 	struct ip_vs_service *svc;
 	sctp_chunkhdr_t _schunkh, *sch;
 	sctp_sctphdr_t *sh, _sctph;
-	struct ip_vs_iphdr iph;
 
-	ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
-
-	sh = skb_header_pointer(skb, iph.len, sizeof(_sctph), &_sctph);
+	sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph);
 	if (sh == NULL)
 		return 0;
 
-	sch = skb_header_pointer(skb, iph.len + sizeof(sctp_sctphdr_t),
+	sch = skb_header_pointer(skb, iph->len + sizeof(sctp_sctphdr_t),
 				 sizeof(_schunkh), &_schunkh);
 	if (sch == NULL)
 		return 0;
 	net = skb_net(skb);
 	if ((sch->type == SCTP_CID_INIT) &&
-	    (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
-				     &iph.daddr, sh->dest))) {
+	    (svc = ip_vs_service_get(net, af, skb->mark, iph->protocol,
+				     &iph->daddr, sh->dest))) {
 		int ignored;
 
 		if (ip_vs_todrop(net_ipvs(net))) {
@@ -47,10 +45,10 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		 * Let the virtual server select a real server for the
 		 * incoming connection, and create a connection entry.
 		 */
-		*cpp = ip_vs_schedule(svc, skb, pd, &ignored);
+		*cpp = ip_vs_schedule(svc, skb, pd, &ignored, iph);
 		if (!*cpp && ignored <= 0) {
 			if (!ignored)
-				*verdict = ip_vs_leave(svc, skb, pd);
+				*verdict = ip_vs_leave(svc, skb, pd, iph);
 			else {
 				ip_vs_service_put(svc);
 				*verdict = NF_DROP;
@@ -64,20 +62,18 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 }
 
 static int
-sctp_snat_handler(struct sk_buff *skb,
-		  struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
+sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
+		  struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
 {
 	sctp_sctphdr_t *sctph;
-	unsigned int sctphoff;
+	unsigned int sctphoff = iph->len;
 	struct sk_buff *iter;
 	__be32 crc32;
 
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6)
-		sctphoff = sizeof(struct ipv6hdr);
-	else
+	if (cp->af == AF_INET6 && iph->fragoffs)
+		return 1;
 #endif
-		sctphoff = ip_hdrlen(skb);
 
 	/* csum_check requires unshared skb */
 	if (!skb_make_writable(skb, sctphoff + sizeof(*sctph)))
@@ -108,20 +104,18 @@ sctp_snat_handler(struct sk_buff *skb,
 }
 
 static int
-sctp_dnat_handler(struct sk_buff *skb,
-		  struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
+sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
+		  struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
 {
 	sctp_sctphdr_t *sctph;
-	unsigned int sctphoff;
+	unsigned int sctphoff = iph->len;
 	struct sk_buff *iter;
 	__be32 crc32;
 
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6)
-		sctphoff = sizeof(struct ipv6hdr);
-	else
+	if (cp->af == AF_INET6 && iph->fragoffs)
+		return 1;
 #endif
-		sctphoff = ip_hdrlen(skb);
 
 	/* csum_check requires unshared skb */
 	if (!skb_make_writable(skb, sctphoff + sizeof(*sctph)))

net/netfilter/ipvs/ip_vs_proto_tcp.c

@@ -33,16 +33,14 @@
 
 static int
 tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
-		  int *verdict, struct ip_vs_conn **cpp)
+		  int *verdict, struct ip_vs_conn **cpp,
+		  struct ip_vs_iphdr *iph)
 {
 	struct net *net;
 	struct ip_vs_service *svc;
 	struct tcphdr _tcph, *th;
-	struct ip_vs_iphdr iph;
 
-	ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
-
-	th = skb_header_pointer(skb, iph.len, sizeof(_tcph), &_tcph);
+	th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph);
 	if (th == NULL) {
 		*verdict = NF_DROP;
 		return 0;
@@ -50,8 +48,8 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 	net = skb_net(skb);
 	/* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */
 	if (th->syn &&
-	    (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
-				     &iph.daddr, th->dest))) {
+	    (svc = ip_vs_service_get(net, af, skb->mark, iph->protocol,
+				     &iph->daddr, th->dest))) {
 		int ignored;
 
 		if (ip_vs_todrop(net_ipvs(net))) {
@@ -68,10 +66,10 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		 * Let the virtual server select a real server for the
 		 * incoming connection, and create a connection entry.
 		 */
-		*cpp = ip_vs_schedule(svc, skb, pd, &ignored);
+		*cpp = ip_vs_schedule(svc, skb, pd, &ignored, iph);
 		if (!*cpp && ignored <= 0) {
 			if (!ignored)
-				*verdict = ip_vs_leave(svc, skb, pd);
+				*verdict = ip_vs_leave(svc, skb, pd, iph);
 			else {
 				ip_vs_service_put(svc);
 				*verdict = NF_DROP;
@@ -128,20 +126,18 @@ tcp_partial_csum_update(int af, struct tcphdr *tcph,
 
 
 static int
-tcp_snat_handler(struct sk_buff *skb,
-		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
+tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
+		 struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
 {
 	struct tcphdr *tcph;
-	unsigned int tcphoff;
+	unsigned int tcphoff = iph->len;
 	int oldlen;
 	int payload_csum = 0;
 
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6)
-		tcphoff = sizeof(struct ipv6hdr);
-	else
+	if (cp->af == AF_INET6 && iph->fragoffs)
+		return 1;
 #endif
-		tcphoff = ip_hdrlen(skb);
 	oldlen = skb->len - tcphoff;
 
 	/* csum_check requires unshared skb */
@@ -208,20 +204,18 @@ tcp_snat_handler(struct sk_buff *skb,
 
 
 static int
-tcp_dnat_handler(struct sk_buff *skb,
-		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
+tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
+		 struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
 {
 	struct tcphdr *tcph;
-	unsigned int tcphoff;
+	unsigned int tcphoff = iph->len;
 	int oldlen;
 	int payload_csum = 0;
 
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6)
-		tcphoff = sizeof(struct ipv6hdr);
-	else
+	if (cp->af == AF_INET6 && iph->fragoffs)
+		return 1;
 #endif
-		tcphoff = ip_hdrlen(skb);
 	oldlen = skb->len - tcphoff;
 
 	/* csum_check requires unshared skb */

net/netfilter/ipvs/ip_vs_proto_udp.c

@@ -30,23 +30,22 @@
 
 static int
 udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
-		  int *verdict, struct ip_vs_conn **cpp)
+		  int *verdict, struct ip_vs_conn **cpp,
+		  struct ip_vs_iphdr *iph)
 {
 	struct net *net;
 	struct ip_vs_service *svc;
 	struct udphdr _udph, *uh;
-	struct ip_vs_iphdr iph;
 
-	ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
-
-	uh = skb_header_pointer(skb, iph.len, sizeof(_udph), &_udph);
+	/* IPv6 fragments, only first fragment will hit this */
+	uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph);
 	if (uh == NULL) {
 		*verdict = NF_DROP;
 		return 0;
 	}
 	net = skb_net(skb);
-	svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
-				&iph.daddr, uh->dest);
+	svc = ip_vs_service_get(net, af, skb->mark, iph->protocol,
+				&iph->daddr, uh->dest);
 	if (svc) {
 		int ignored;
 
@@ -64,10 +63,10 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		 * Let the virtual server select a real server for the
 		 * incoming connection, and create a connection entry.
 		 */
-		*cpp = ip_vs_schedule(svc, skb, pd, &ignored);
+		*cpp = ip_vs_schedule(svc, skb, pd, &ignored, iph);
 		if (!*cpp && ignored <= 0) {
 			if (!ignored)
-				*verdict = ip_vs_leave(svc, skb, pd);
+				*verdict = ip_vs_leave(svc, skb, pd, iph);
 			else {
 				ip_vs_service_put(svc);
 				*verdict = NF_DROP;
@@ -125,20 +124,18 @@ udp_partial_csum_update(int af, struct udphdr *uhdr,
 
 
 static int
-udp_snat_handler(struct sk_buff *skb,
-		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
+udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
+		 struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
 {
 	struct udphdr *udph;
-	unsigned int udphoff;
+	unsigned int udphoff = iph->len;
 	int oldlen;
 	int payload_csum = 0;
 
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6)
-		udphoff = sizeof(struct ipv6hdr);
-	else
+	if (cp->af == AF_INET6 && iph->fragoffs)
+		return 1;
 #endif
-		udphoff = ip_hdrlen(skb);
 	oldlen = skb->len - udphoff;
 
 	/* csum_check requires unshared skb */
@@ -210,20 +207,18 @@ udp_snat_handler(struct sk_buff *skb,
 
 
 static int
-udp_dnat_handler(struct sk_buff *skb,
-		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
+udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
+		 struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
 {
 	struct udphdr *udph;
-	unsigned int udphoff;
+	unsigned int udphoff = iph->len;
 	int oldlen;
 	int payload_csum = 0;
 
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6)
-		udphoff = sizeof(struct ipv6hdr);
-	else
+	if (cp->af == AF_INET6 && iph->fragoffs)
+		return 1;
 #endif
-		udphoff = ip_hdrlen(skb);
 	oldlen = skb->len - udphoff;
 
 	/* csum_check requires unshared skb */

net/netfilter/ipvs/ip_vs_sched.c

@@ -159,7 +159,7 @@ void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg)
 			     svc->fwmark, msg);
 #ifdef CONFIG_IP_VS_IPV6
 	} else if (svc->af == AF_INET6) {
-		IP_VS_ERR_RL("%s: %s [%pI6]:%d - %s\n",
+		IP_VS_ERR_RL("%s: %s [%pI6c]:%d - %s\n",
 			     svc->scheduler->name,
 			     ip_vs_proto_name(svc->protocol),
 			     &svc->addr.in6, ntohs(svc->port), msg);

net/netfilter/ipvs/ip_vs_sh.c

@@ -228,7 +228,7 @@ ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	struct ip_vs_sh_bucket *tbl;
 	struct ip_vs_iphdr iph;
 
-	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_addr_only(svc->af, skb, &iph);
 
 	IP_VS_DBG(6, "ip_vs_sh_schedule(): Scheduling...\n");
 

net/netfilter/ipvs/ip_vs_xmit.c

@@ -338,7 +338,7 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
 	local = __ip_vs_is_local_route6(rt);
 	if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) &
 	      rt_mode)) {
-		IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6\n",
+		IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6c\n",
 			     local ? "local":"non-local", daddr);
 		dst_release(&rt->dst);
 		return NULL;
@@ -346,8 +346,8 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
 	if (local && !(rt_mode & IP_VS_RT_MODE_RDR) &&
 	    !((ort = (struct rt6_info *) skb_dst(skb)) &&
 	      __ip_vs_is_local_route6(ort))) {
-		IP_VS_DBG_RL("Redirect from non-local address %pI6 to local "
-			     "requires NAT method, dest: %pI6\n",
+		IP_VS_DBG_RL("Redirect from non-local address %pI6c to local "
+			     "requires NAT method, dest: %pI6c\n",
 			     &ipv6_hdr(skb)->daddr, daddr);
 		dst_release(&rt->dst);
 		return NULL;
@@ -355,8 +355,8 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
 	if (unlikely(!local && (!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
 		     ipv6_addr_type(&ipv6_hdr(skb)->saddr) &
 				    IPV6_ADDR_LOOPBACK)) {
-		IP_VS_DBG_RL("Stopping traffic from loopback address %pI6 "
-			     "to non-local address, dest: %pI6\n",
+		IP_VS_DBG_RL("Stopping traffic from loopback address %pI6c "
+			     "to non-local address, dest: %pI6c\n",
 			     &ipv6_hdr(skb)->saddr, daddr);
 		dst_release(&rt->dst);
 		return NULL;
@@ -427,7 +427,7 @@ do {							\
  */
 int
 ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-		struct ip_vs_protocol *pp)
+		struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
 {
 	/* we do not touch skb and do not need pskb ptr */
 	IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
@@ -441,7 +441,7 @@ ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
  */
 int
 ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-		  struct ip_vs_protocol *pp)
+		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
 {
 	struct rtable *rt;			/* Route to the other host */
 	struct iphdr  *iph = ip_hdr(skb);
@@ -496,16 +496,16 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 #ifdef CONFIG_IP_VS_IPV6
 int
 ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-		     struct ip_vs_protocol *pp)
+		     struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph)
 {
 	struct rt6_info *rt;			/* Route to the other host */
-	struct ipv6hdr  *iph = ipv6_hdr(skb);
 	int    mtu;
 
 	EnterFunction(10);
 
-	if (!(rt = __ip_vs_get_out_rt_v6(skb, NULL, &iph->daddr, NULL, 0,
-					 IP_VS_RT_MODE_NON_LOCAL)))
+	rt = __ip_vs_get_out_rt_v6(skb, NULL, &iph->daddr.in6, NULL, 0,
+				   IP_VS_RT_MODE_NON_LOCAL);
+	if (!rt)
 		goto tx_error_icmp;
 
 	/* MTU checking */
@@ -516,7 +516,9 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 			skb->dev = net->loopback_dev;
 		}
-		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		/* only send ICMP too big on first fragment */
+		if (!iph->fragoffs)
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		dst_release(&rt->dst);
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error;
@@ -559,7 +561,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
  */
 int
 ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-	       struct ip_vs_protocol *pp)
+	       struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
 {
 	struct rtable *rt;		/* Route to the other host */
 	int mtu;
@@ -629,7 +631,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		goto tx_error_put;
 
 	/* mangle the packet */
-	if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
+	if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp, ipvsh))
 		goto tx_error_put;
 	ip_hdr(skb)->daddr = cp->daddr.ip;
 	ip_send_check(ip_hdr(skb));
@@ -677,7 +679,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 #ifdef CONFIG_IP_VS_IPV6
 int
 ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-		  struct ip_vs_protocol *pp)
+		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph)
 {
 	struct rt6_info *rt;		/* Route to the other host */
 	int mtu;
@@ -686,10 +688,9 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	EnterFunction(10);
 
 	/* check if it is a connection of no-client-port */
-	if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) {
+	if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT && !iph->fragoffs)) {
 		__be16 _pt, *p;
-		p = skb_header_pointer(skb, sizeof(struct ipv6hdr),
-				       sizeof(_pt), &_pt);
+		p = skb_header_pointer(skb, iph->len, sizeof(_pt), &_pt);
 		if (p == NULL)
 			goto tx_error;
 		ip_vs_conn_fill_cport(cp, *p);
@@ -737,7 +738,9 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 			skb->dev = net->loopback_dev;
 		}
-		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		/* only send ICMP too big on first fragment */
+		if (!iph->fragoffs)
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		IP_VS_DBG_RL_PKT(0, AF_INET6, pp, skb, 0,
 				 "ip_vs_nat_xmit_v6(): frag needed for");
 		goto tx_error_put;
@@ -751,7 +754,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		goto tx_error_put;
 
 	/* mangle the packet */
-	if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
+	if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp, iph))
 		goto tx_error;
 	ipv6_hdr(skb)->daddr = cp->daddr.in6;
 
@@ -812,7 +815,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
  */
 int
 ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-		  struct ip_vs_protocol *pp)
+		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
 {
 	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
 	struct rtable *rt;			/* Route to the other host */
@@ -932,7 +935,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 #ifdef CONFIG_IP_VS_IPV6
 int
 ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-		     struct ip_vs_protocol *pp)
+		     struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
 {
 	struct rt6_info *rt;		/* Route to the other host */
 	struct in6_addr saddr;		/* Source for tunnel */
@@ -972,7 +975,9 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 			skb->dev = net->loopback_dev;
 		}
-		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		/* only send ICMP too big on first fragment */
+		if (!ipvsh->fragoffs)
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error_put;
 	}
@@ -1053,7 +1058,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
  */
 int
 ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-	      struct ip_vs_protocol *pp)
+	      struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
 {
 	struct rtable *rt;			/* Route to the other host */
 	struct iphdr  *iph = ip_hdr(skb);
@@ -1115,7 +1120,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 #ifdef CONFIG_IP_VS_IPV6
 int
 ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-		 struct ip_vs_protocol *pp)
+		 struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph)
 {
 	struct rt6_info *rt;			/* Route to the other host */
 	int    mtu;
@@ -1139,7 +1144,9 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 			skb->dev = net->loopback_dev;
 		}
-		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		/* only send ICMP too big on first fragment */
+		if (!iph->fragoffs)
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		dst_release(&rt->dst);
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error;
@@ -1183,7 +1190,8 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
  */
 int
 ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-		struct ip_vs_protocol *pp, int offset, unsigned int hooknum)
+		struct ip_vs_protocol *pp, int offset, unsigned int hooknum,
+		struct ip_vs_iphdr *iph)
 {
 	struct rtable	*rt;	/* Route to the other host */
 	int mtu;
@@ -1198,7 +1206,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	   translate address/port back */
 	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
 		if (cp->packet_xmit)
-			rc = cp->packet_xmit(skb, cp, pp);
+			rc = cp->packet_xmit(skb, cp, pp, iph);
 		else
 			rc = NF_ACCEPT;
 		/* do not touch skb anymore */
@@ -1304,7 +1312,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 #ifdef CONFIG_IP_VS_IPV6
 int
 ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-		struct ip_vs_protocol *pp, int offset, unsigned int hooknum)
+		struct ip_vs_protocol *pp, int offset, unsigned int hooknum,
+		struct ip_vs_iphdr *iph)
 {
 	struct rt6_info	*rt;	/* Route to the other host */
 	int mtu;
@@ -1319,7 +1328,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	   translate address/port back */
 	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
 		if (cp->packet_xmit)
-			rc = cp->packet_xmit(skb, cp, pp);
+			rc = cp->packet_xmit(skb, cp, pp, iph);
 		else
 			rc = NF_ACCEPT;
 		/* do not touch skb anymore */
@@ -1375,7 +1384,9 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 			skb->dev = net->loopback_dev;
 		}
-		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		/* only send ICMP too big on first fragment */
+		if (!iph->fragoffs)
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error_put;
 	}

net/netfilter/xt_ipvs.c

@@ -67,7 +67,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par)
 		goto out;
 	}
 
-	ip_vs_fill_iphdr(family, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_skb(family, skb, &iph);
 
 	if (data->bitmask & XT_IPVS_PROTO)
 		if ((iph.protocol == data->l4proto) ^
@@ -85,7 +85,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	/*
 	 * Check if the packet belongs to an existing entry
 	 */
-	cp = pp->conn_out_get(family, skb, &iph, iph.len, 1 /* inverse */);
+	cp = pp->conn_out_get(family, skb, &iph, 1 /* inverse */);
 	if (unlikely(cp == NULL)) {
 		match = false;
 		goto out;