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 */
@@ -103,35 +106,122 @@ 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;
+		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;
+	}
+}
+
 static inline void ip_vs_addr_copy(int af, union nf_inet_addr *dst,
 				   const union nf_inet_addr *src)
 {
@@ -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_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;
-
-	/* No Data ? */
+	/* 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);
+
 	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 */
@@ -516,6 +516,8 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 			skb->dev = net->loopback_dev;
 		}
+		/* 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__);
@@ -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);
@@ -737,6 +738,8 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 			skb->dev = net->loopback_dev;
 		}
+		/* 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");
@@ -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 */
@@ -972,6 +975,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 			skb->dev = net->loopback_dev;
 		}
+		/* 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;
@@ -1139,6 +1144,8 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 			skb->dev = net->loopback_dev;
 		}
+		/* 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__);
@@ -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 */
@@ -1375,6 +1384,8 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 			skb->dev = net->loopback_dev;
 		}
+		/* 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;