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

Documentation/feature-removal-schedule.txt

@@ -353,14 +353,6 @@ Why:	Internal alias support has been present in module-init-tools for some
 
 Who:	Wey-Yi Guy <wey-yi.w.guy@intel.com>
 
----------------------------
-
-What:	xt_NOTRACK
-Files:	net/netfilter/xt_NOTRACK.c
-When:	April 2011
-Why:	Superseded by xt_CT
-Who:	Netfilter developer team <netfilter-devel@vger.kernel.org>
-
 ----------------------------
 
 What:	IRQF_DISABLED

arch/m68k/configs/amiga_defconfig

@@ -67,7 +67,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m

arch/m68k/configs/apollo_defconfig

@@ -67,7 +67,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m

arch/m68k/configs/atari_defconfig

@@ -65,7 +65,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m

arch/m68k/configs/bvme6000_defconfig

@@ -65,7 +65,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m

arch/m68k/configs/hp300_defconfig

@@ -66,7 +66,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m

arch/m68k/configs/mac_defconfig

@@ -61,7 +61,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m

arch/m68k/configs/multi_defconfig

@@ -80,7 +80,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m

arch/m68k/configs/mvme147_defconfig

@@ -64,7 +64,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m

arch/m68k/configs/mvme16x_defconfig

@@ -65,7 +65,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m

arch/m68k/configs/q40_defconfig

@@ -61,7 +61,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m

arch/m68k/configs/sun3_defconfig

@@ -62,7 +62,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m

arch/m68k/configs/sun3x_defconfig

@@ -62,7 +62,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m

arch/mips/configs/ar7_defconfig

@@ -56,7 +56,6 @@ CONFIG_NF_CONNTRACK_MARK=y
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_IRC=m
 CONFIG_NF_CONNTRACK_TFTP=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
 CONFIG_NETFILTER_XT_MATCH_MAC=m

arch/mips/configs/bcm47xx_defconfig

@@ -96,7 +96,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_SECMARK=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m

arch/mips/configs/ip22_defconfig

@@ -87,7 +87,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_SECMARK=m

arch/mips/configs/jazz_defconfig

@@ -60,7 +60,6 @@ CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_SECMARK=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m

arch/mips/configs/malta_defconfig

@@ -86,7 +86,6 @@ CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_SECMARK=m

arch/mips/configs/markeins_defconfig

@@ -59,7 +59,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_SECMARK=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m

arch/mips/configs/nlm_xlp_defconfig

@@ -108,7 +108,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_SECMARK=m

arch/mips/configs/nlm_xlr_defconfig

@@ -109,7 +109,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_SECMARK=m

arch/mips/configs/rm200_defconfig

@@ -68,7 +68,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_SECMARK=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m

arch/powerpc/configs/pmac32_defconfig

@@ -55,7 +55,6 @@ CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m

arch/powerpc/configs/ppc64_defconfig

@@ -92,7 +92,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m

arch/powerpc/configs/ppc64e_defconfig

@@ -66,7 +66,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m

arch/powerpc/configs/ppc6xx_defconfig

@@ -167,7 +167,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_SECMARK=m

arch/tile/configs/tilegx_defconfig

@@ -134,7 +134,6 @@ CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m

arch/tile/configs/tilepro_defconfig

@@ -132,7 +132,6 @@ CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m

include/linux/ipv6.h

@@ -256,6 +256,7 @@ struct inet6_skb_parm {
 #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
 	__u16			dsthao;
 #endif
+	__u16			frag_max_size;
 
 #define IP6SKB_XFRM_TRANSFORMED	1
 #define IP6SKB_FORWARDED	2

include/linux/netfilter.h

@@ -342,7 +342,7 @@ extern int nf_register_afinfo(const struct nf_afinfo *afinfo);
 extern void nf_unregister_afinfo(const struct nf_afinfo *afinfo);
 
 #include <net/flow.h>
-extern void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *);
+extern void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *);
 
 static inline void
 nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family)
@@ -350,13 +350,11 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family)
 #ifdef CONFIG_NF_NAT_NEEDED
 	void (*decodefn)(struct sk_buff *, struct flowi *);
 
-	if (family == AF_INET) {
-		rcu_read_lock();
-		decodefn = rcu_dereference(ip_nat_decode_session);
-		if (decodefn)
-			decodefn(skb, fl);
-		rcu_read_unlock();
-	}
+	rcu_read_lock();
+	decodefn = rcu_dereference(nf_nat_decode_session_hook);
+	if (decodefn)
+		decodefn(skb, fl);
+	rcu_read_unlock();
 #endif
 }
 

include/linux/netfilter/nf_conntrack_amanda.h

@@ -4,6 +4,7 @@
 
 extern unsigned int (*nf_nat_amanda_hook)(struct sk_buff *skb,
 					  enum ip_conntrack_info ctinfo,
+					  unsigned int protoff,
 					  unsigned int matchoff,
 					  unsigned int matchlen,
 					  struct nf_conntrack_expect *exp);

include/linux/netfilter/nf_conntrack_ftp.h

@@ -34,6 +34,7 @@ struct nf_conntrack_expect;
 extern unsigned int (*nf_nat_ftp_hook)(struct sk_buff *skb,
 				       enum ip_conntrack_info ctinfo,
 				       enum nf_ct_ftp_type type,
+				       unsigned int protoff,
 				       unsigned int matchoff,
 				       unsigned int matchlen,
 				       struct nf_conntrack_expect *exp);

include/linux/netfilter/nf_conntrack_h323.h

@@ -36,12 +36,12 @@ extern void nf_conntrack_h245_expect(struct nf_conn *new,
 				     struct nf_conntrack_expect *this);
 extern void nf_conntrack_q931_expect(struct nf_conn *new,
 				     struct nf_conntrack_expect *this);
-extern int (*set_h245_addr_hook) (struct sk_buff *skb,
+extern int (*set_h245_addr_hook) (struct sk_buff *skb, unsigned int protoff,
 				  unsigned char **data, int dataoff,
 				  H245_TransportAddress *taddr,
 				  union nf_inet_addr *addr,
 				  __be16 port);
-extern int (*set_h225_addr_hook) (struct sk_buff *skb,
+extern int (*set_h225_addr_hook) (struct sk_buff *skb, unsigned int protoff,
 				  unsigned char **data, int dataoff,
 				  TransportAddress *taddr,
 				  union nf_inet_addr *addr,
@@ -49,40 +49,45 @@ extern int (*set_h225_addr_hook) (struct sk_buff *skb,
 extern int (*set_sig_addr_hook) (struct sk_buff *skb,
 				 struct nf_conn *ct,
 				 enum ip_conntrack_info ctinfo,
-				 unsigned char **data,
+				 unsigned int protoff, unsigned char **data,
 				 TransportAddress *taddr, int count);
 extern int (*set_ras_addr_hook) (struct sk_buff *skb,
 				 struct nf_conn *ct,
 				 enum ip_conntrack_info ctinfo,
-				 unsigned char **data,
+				 unsigned int protoff, unsigned char **data,
 				 TransportAddress *taddr, int count);
 extern int (*nat_rtp_rtcp_hook) (struct sk_buff *skb,
 				 struct nf_conn *ct,
 				 enum ip_conntrack_info ctinfo,
-				 unsigned char **data, int dataoff,
+				 unsigned int protoff, unsigned char **data,
+				 int dataoff,
 				 H245_TransportAddress *taddr,
 				 __be16 port, __be16 rtp_port,
 				 struct nf_conntrack_expect *rtp_exp,
 				 struct nf_conntrack_expect *rtcp_exp);
 extern int (*nat_t120_hook) (struct sk_buff *skb, struct nf_conn *ct,
 			     enum ip_conntrack_info ctinfo,
+			     unsigned int protoff,
 			     unsigned char **data, int dataoff,
 			     H245_TransportAddress *taddr, __be16 port,
 			     struct nf_conntrack_expect *exp);
 extern int (*nat_h245_hook) (struct sk_buff *skb, struct nf_conn *ct,
 			     enum ip_conntrack_info ctinfo,
+			     unsigned int protoff,
 			     unsigned char **data, int dataoff,
 			     TransportAddress *taddr, __be16 port,
 			     struct nf_conntrack_expect *exp);
 extern int (*nat_callforwarding_hook) (struct sk_buff *skb,
 				       struct nf_conn *ct,
 				       enum ip_conntrack_info ctinfo,
+				       unsigned int protoff,
 				       unsigned char **data, int dataoff,
 				       TransportAddress *taddr,
 				       __be16 port,
 				       struct nf_conntrack_expect *exp);
 extern int (*nat_q931_hook) (struct sk_buff *skb, struct nf_conn *ct,
 			     enum ip_conntrack_info ctinfo,
+			     unsigned int protoff,
 			     unsigned char **data, TransportAddress *taddr,
 			     int idx, __be16 port,
 			     struct nf_conntrack_expect *exp);

include/linux/netfilter/nf_conntrack_irc.h

@@ -7,6 +7,7 @@
 
 extern unsigned int (*nf_nat_irc_hook)(struct sk_buff *skb,
 				       enum ip_conntrack_info ctinfo,
+				       unsigned int protoff,
 				       unsigned int matchoff,
 				       unsigned int matchlen,
 				       struct nf_conntrack_expect *exp);

include/linux/netfilter/nf_conntrack_pptp.h

@@ -303,12 +303,14 @@ struct nf_conntrack_expect;
 extern int
 (*nf_nat_pptp_hook_outbound)(struct sk_buff *skb,
 			     struct nf_conn *ct, enum ip_conntrack_info ctinfo,
+			     unsigned int protoff,
 			     struct PptpControlHeader *ctlh,
 			     union pptp_ctrl_union *pptpReq);
 
 extern int
 (*nf_nat_pptp_hook_inbound)(struct sk_buff *skb,
 			    struct nf_conn *ct, enum ip_conntrack_info ctinfo,
+			    unsigned int protoff,
 			    struct PptpControlHeader *ctlh,
 			    union pptp_ctrl_union *pptpReq);
 

include/linux/netfilter/nf_conntrack_sip.h

@@ -37,10 +37,12 @@ struct sdp_media_type {
 struct sip_handler {
 	const char	*method;
 	unsigned int	len;
-	int		(*request)(struct sk_buff *skb, unsigned int dataoff,
+	int		(*request)(struct sk_buff *skb, unsigned int protoff,
+				   unsigned int dataoff,
 				   const char **dptr, unsigned int *datalen,
 				   unsigned int cseq);
-	int		(*response)(struct sk_buff *skb, unsigned int dataoff,
+	int		(*response)(struct sk_buff *skb, unsigned int protoff,
+				    unsigned int dataoff,
 				    const char **dptr, unsigned int *datalen,
 				    unsigned int cseq, unsigned int code);
 };
@@ -97,19 +99,20 @@ enum sip_header_types {
 enum sdp_header_types {
 	SDP_HDR_UNSPEC,
 	SDP_HDR_VERSION,
-	SDP_HDR_OWNER_IP4,
-	SDP_HDR_CONNECTION_IP4,
-	SDP_HDR_OWNER_IP6,
-	SDP_HDR_CONNECTION_IP6,
+	SDP_HDR_OWNER,
+	SDP_HDR_CONNECTION,
 	SDP_HDR_MEDIA,
 };
 
 extern unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb,
+				       unsigned int protoff,
 				       unsigned int dataoff,
 				       const char **dptr,
 				       unsigned int *datalen);
-extern void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, s16 off);
+extern void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb,
+					  unsigned int protoff, s16 off);
 extern unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb,
+					      unsigned int protoff,
 					      unsigned int dataoff,
 					      const char **dptr,
 					      unsigned int *datalen,
@@ -117,6 +120,7 @@ extern unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb,
 					      unsigned int matchoff,
 					      unsigned int matchlen);
 extern unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb,
+					    unsigned int protoff,
 					    unsigned int dataoff,
 					    const char **dptr,
 					    unsigned int *datalen,
@@ -125,6 +129,7 @@ extern unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb,
 					    enum sdp_header_types term,
 					    const union nf_inet_addr *addr);
 extern unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb,
+					    unsigned int protoff,
 					    unsigned int dataoff,
 					    const char **dptr,
 					    unsigned int *datalen,
@@ -132,12 +137,14 @@ extern unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb,
 					    unsigned int matchlen,
 					    u_int16_t port);
 extern unsigned int (*nf_nat_sdp_session_hook)(struct sk_buff *skb,
+					       unsigned int protoff,
 					       unsigned int dataoff,
 					       const char **dptr,
 					       unsigned int *datalen,
 					       unsigned int sdpoff,
 					       const union nf_inet_addr *addr);
 extern unsigned int (*nf_nat_sdp_media_hook)(struct sk_buff *skb,
+					     unsigned int protoff,
 					     unsigned int dataoff,
 					     const char **dptr,
 					     unsigned int *datalen,

include/linux/netfilter/nf_nat.h

@@ -22,4 +22,12 @@ struct nf_nat_ipv4_multi_range_compat {
 	struct nf_nat_ipv4_range	range[1];
 };
 
+struct nf_nat_range {
+	unsigned int			flags;
+	union nf_inet_addr		min_addr;
+	union nf_inet_addr		max_addr;
+	union nf_conntrack_man_proto	min_proto;
+	union nf_conntrack_man_proto	max_proto;
+};
+
 #endif /* _NETFILTER_NF_NAT_H */

include/linux/netfilter/nfnetlink_conntrack.h

@@ -142,9 +142,13 @@ enum ctattr_tstamp {
 
 enum ctattr_nat {
 	CTA_NAT_UNSPEC,
-	CTA_NAT_MINIP,
-	CTA_NAT_MAXIP,
+	CTA_NAT_V4_MINIP,
+#define CTA_NAT_MINIP CTA_NAT_V4_MINIP
+	CTA_NAT_V4_MAXIP,
+#define CTA_NAT_MAXIP CTA_NAT_V4_MAXIP
 	CTA_NAT_PROTO,
+	CTA_NAT_V6_MINIP,
+	CTA_NAT_V6_MAXIP,
 	__CTA_NAT_MAX
 };
 #define CTA_NAT_MAX (__CTA_NAT_MAX - 1)

include/linux/netfilter_ipv4.h

@@ -79,7 +79,6 @@ enum nf_ip_hook_priorities {
 
 #ifdef __KERNEL__
 extern int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type);
-extern int ip_xfrm_me_harder(struct sk_buff *skb);
 extern __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
 				   unsigned int dataoff, u_int8_t protocol);
 #endif /*__KERNEL__*/

include/linux/netfilter_ipv6/Kbuild

 header-y += ip6_tables.h
 header-y += ip6t_HL.h
 header-y += ip6t_LOG.h
+header-y += ip6t_NPT.h
 header-y += ip6t_REJECT.h
 header-y += ip6t_ah.h
 header-y += ip6t_frag.h

include/linux/netfilter_ipv6/ip6t_NPT.h

+#ifndef __NETFILTER_IP6T_NPT
+#define __NETFILTER_IP6T_NPT
+
+#include <linux/types.h>
+#include <linux/netfilter.h>
+
+struct ip6t_npt_tginfo {
+	union nf_inet_addr	src_pfx;
+	union nf_inet_addr	dst_pfx;
+	__u8			src_pfx_len;
+	__u8			dst_pfx_len;
+	/* Used internally by the kernel */
+	__sum16			adjustment;
+};
+
+#endif /* __NETFILTER_IP6T_NPT */

include/net/addrconf.h

@@ -78,7 +78,7 @@ extern struct inet6_ifaddr      *ipv6_get_ifaddr(struct net *net,
 						 int strict);
 
 extern int			ipv6_dev_get_saddr(struct net *net,
-					       struct net_device *dev,
+					       const struct net_device *dev,
 					       const struct in6_addr *daddr,
 					       unsigned int srcprefs,
 					       struct in6_addr *saddr);

include/net/checksum.h

@@ -109,6 +109,9 @@ static inline void csum_replace2(__sum16 *sum, __be16 from, __be16 to)
 struct sk_buff;
 extern void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
 				     __be32 from, __be32 to, int pseudohdr);
+extern void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
+				      const __be32 *from, const __be32 *to,
+				      int pseudohdr);
 
 static inline void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb,
 					    __be16 from, __be16 to,

include/net/inet_frag.h

@@ -29,6 +29,8 @@ struct inet_frag_queue {
 #define INET_FRAG_COMPLETE	4
 #define INET_FRAG_FIRST_IN	2
 #define INET_FRAG_LAST_IN	1
+
+	u16			max_size;
 };
 
 #define INETFRAGS_HASHSZ		64

include/net/ip.h

@@ -42,6 +42,8 @@ struct inet_skb_parm {
 #define IPSKB_XFRM_TRANSFORMED	4
 #define IPSKB_FRAG_COMPLETE	8
 #define IPSKB_REROUTED		16
+
+	u16			frag_max_size;
 };
 
 static inline unsigned int ip_hdrlen(const struct sk_buff *skb)

include/net/netfilter/nf_conntrack_expect.h

@@ -43,7 +43,7 @@ struct nf_conntrack_expect {
 	unsigned int class;
 
 #ifdef CONFIG_NF_NAT_NEEDED
-	__be32 saved_ip;
+	union nf_inet_addr saved_addr;
 	/* This is the original per-proto part, used to map the
 	 * expected connection the way the recipient expects. */
 	union nf_conntrack_man_proto saved_proto;

include/net/netfilter/nf_conntrack_timeout.h

@@ -55,6 +55,26 @@ struct nf_conn_timeout *nf_ct_timeout_ext_add(struct nf_conn *ct,
 #endif
 };
 
+static inline unsigned int *
+nf_ct_timeout_lookup(struct net *net, struct nf_conn *ct,
+		     struct nf_conntrack_l4proto *l4proto)
+{
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+	struct nf_conn_timeout *timeout_ext;
+	unsigned int *timeouts;
+
+	timeout_ext = nf_ct_timeout_find(ct);
+	if (timeout_ext)
+		timeouts = NF_CT_TIMEOUT_EXT_DATA(timeout_ext);
+	else
+		timeouts = l4proto->get_timeouts(net);
+
+	return timeouts;
+#else
+	return l4proto->get_timeouts(net);
+#endif
+}
+
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
 extern int nf_conntrack_timeout_init(struct net *net);
 extern void nf_conntrack_timeout_fini(struct net *net);

include/net/netfilter/nf_nat.h

@@ -43,14 +43,16 @@ struct nf_conn_nat {
 	struct nf_conn *ct;
 	union nf_conntrack_nat_help help;
 #if defined(CONFIG_IP_NF_TARGET_MASQUERADE) || \
-    defined(CONFIG_IP_NF_TARGET_MASQUERADE_MODULE)
+    defined(CONFIG_IP_NF_TARGET_MASQUERADE_MODULE) || \
+    defined(CONFIG_IP6_NF_TARGET_MASQUERADE) || \
+    defined(CONFIG_IP6_NF_TARGET_MASQUERADE_MODULE)
 	int masq_index;
 #endif
 };
 
 /* Set up the info structure to map into this range. */
 extern unsigned int nf_nat_setup_info(struct nf_conn *ct,
-				      const struct nf_nat_ipv4_range *range,
+				      const struct nf_nat_range *range,
 				      enum nf_nat_manip_type maniptype);
 
 /* Is this tuple already taken? (not by us)*/

include/net/netfilter/nf_nat_core.h

@@ -12,10 +12,7 @@ extern unsigned int nf_nat_packet(struct nf_conn *ct,
 				  unsigned int hooknum,
 				  struct sk_buff *skb);
 
-extern int nf_nat_icmp_reply_translation(struct nf_conn *ct,
-					 enum ip_conntrack_info ctinfo,
-					 unsigned int hooknum,
-					 struct sk_buff *skb);
+extern int nf_xfrm_me_harder(struct sk_buff *skb, unsigned int family);
 
 static inline int nf_nat_initialized(struct nf_conn *ct,
 				     enum nf_nat_manip_type manip)

include/net/netfilter/nf_nat_helper.h

@@ -10,6 +10,7 @@ struct sk_buff;
 extern int __nf_nat_mangle_tcp_packet(struct sk_buff *skb,
 				      struct nf_conn *ct,
 				      enum ip_conntrack_info ctinfo,
+				      unsigned int protoff,
 				      unsigned int match_offset,
 				      unsigned int match_len,
 				      const char *rep_buffer,
@@ -18,12 +19,13 @@ extern int __nf_nat_mangle_tcp_packet(struct sk_buff *skb,
 static inline int nf_nat_mangle_tcp_packet(struct sk_buff *skb,
 					   struct nf_conn *ct,
 					   enum ip_conntrack_info ctinfo,
+					   unsigned int protoff,
 					   unsigned int match_offset,
 					   unsigned int match_len,
 					   const char *rep_buffer,
 					   unsigned int rep_len)
 {
-	return __nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
+	return __nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff,
 					  match_offset, match_len,
 					  rep_buffer, rep_len, true);
 }
@@ -31,6 +33,7 @@ static inline int nf_nat_mangle_tcp_packet(struct sk_buff *skb,
 extern int nf_nat_mangle_udp_packet(struct sk_buff *skb,
 				    struct nf_conn *ct,
 				    enum ip_conntrack_info ctinfo,
+				    unsigned int protoff,
 				    unsigned int match_offset,
 				    unsigned int match_len,
 				    const char *rep_buffer,
@@ -41,10 +44,12 @@ extern void nf_nat_set_seq_adjust(struct nf_conn *ct,
 				  __be32 seq, s16 off);
 extern int nf_nat_seq_adjust(struct sk_buff *skb,
 			     struct nf_conn *ct,
-			     enum ip_conntrack_info ctinfo);
+			     enum ip_conntrack_info ctinfo,
+			     unsigned int protoff);
 extern int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb,
 				     struct nf_conn *ct,
-				     enum ip_conntrack_info ctinfo);
+				     enum ip_conntrack_info ctinfo,
+				     unsigned int protoff);
 
 /* Setup NAT on this expected conntrack so it follows master, but goes
  * to port ct->master->saved_proto. */

include/net/netfilter/nf_nat_l3proto.h

+#ifndef _NF_NAT_L3PROTO_H
+#define _NF_NAT_L3PROTO_H
+
+struct nf_nat_l4proto;
+struct nf_nat_l3proto {
+	u8	l3proto;
+
+	bool	(*in_range)(const struct nf_conntrack_tuple *t,
+			    const struct nf_nat_range *range);
+
+	u32 	(*secure_port)(const struct nf_conntrack_tuple *t, __be16);
+
+	bool	(*manip_pkt)(struct sk_buff *skb,
+			     unsigned int iphdroff,
+			     const struct nf_nat_l4proto *l4proto,
+			     const struct nf_conntrack_tuple *target,
+			     enum nf_nat_manip_type maniptype);
+
+	void	(*csum_update)(struct sk_buff *skb, unsigned int iphdroff,
+			       __sum16 *check,
+			       const struct nf_conntrack_tuple *t,
+			       enum nf_nat_manip_type maniptype);
+
+	void	(*csum_recalc)(struct sk_buff *skb, u8 proto,
+			       void *data, __sum16 *check,
+			       int datalen, int oldlen);
+
+	void	(*decode_session)(struct sk_buff *skb,
+				  const struct nf_conn *ct,
+				  enum ip_conntrack_dir dir,
+				  unsigned long statusbit,
+				  struct flowi *fl);
+
+	int	(*nlattr_to_range)(struct nlattr *tb[],
+				   struct nf_nat_range *range);
+};
+
+extern int nf_nat_l3proto_register(const struct nf_nat_l3proto *);
+extern void nf_nat_l3proto_unregister(const struct nf_nat_l3proto *);
+extern const struct nf_nat_l3proto *__nf_nat_l3proto_find(u8 l3proto);
+
+extern int nf_nat_icmp_reply_translation(struct sk_buff *skb,
+					 struct nf_conn *ct,
+					 enum ip_conntrack_info ctinfo,
+					 unsigned int hooknum);
+extern int nf_nat_icmpv6_reply_translation(struct sk_buff *skb,
+					   struct nf_conn *ct,
+					   enum ip_conntrack_info ctinfo,
+					   unsigned int hooknum,
+					   unsigned int hdrlen);
+
+#endif /* _NF_NAT_L3PROTO_H */

include/net/netfilter/nf_nat_protocol.h → include/net/netfilter/nf_nat_l4proto.h

 /* Header for use in defining a given protocol. */
-#ifndef _NF_NAT_PROTOCOL_H
-#define _NF_NAT_PROTOCOL_H
+#ifndef _NF_NAT_L4PROTO_H
+#define _NF_NAT_L4PROTO_H
 #include <net/netfilter/nf_nat.h>
 #include <linux/netfilter/nfnetlink_conntrack.h>
 
-struct nf_nat_ipv4_range;
+struct nf_nat_range;
+struct nf_nat_l3proto;
 
-struct nf_nat_protocol {
+struct nf_nat_l4proto {
 	/* Protocol number. */
-	unsigned int protonum;
+	u8 l4proto;
 
 	/* Translate a packet to the target according to manip type.
-	   Return true if succeeded. */
+	 * Return true if succeeded.
+	 */
 	bool (*manip_pkt)(struct sk_buff *skb,
-			  unsigned int iphdroff,
+			  const struct nf_nat_l3proto *l3proto,
+			  unsigned int iphdroff, unsigned int hdroff,
 			  const struct nf_conntrack_tuple *tuple,
 			  enum nf_nat_manip_type maniptype);
 
@@ -24,44 +27,46 @@ struct nf_nat_protocol {
 			 const union nf_conntrack_man_proto *max);
 
 	/* Alter the per-proto part of the tuple (depending on
-	   maniptype), to give a unique tuple in the given range if
-	   possible.  Per-protocol part of tuple is initialized to the
-	   incoming packet. */
-	void (*unique_tuple)(struct nf_conntrack_tuple *tuple,
-			     const struct nf_nat_ipv4_range *range,
+	 * maniptype), to give a unique tuple in the given range if
+	 * possible.  Per-protocol part of tuple is initialized to the
+	 * incoming packet.
+	 */
+	void (*unique_tuple)(const struct nf_nat_l3proto *l3proto,
+			     struct nf_conntrack_tuple *tuple,
+			     const struct nf_nat_range *range,
 			     enum nf_nat_manip_type maniptype,
 			     const struct nf_conn *ct);
 
 	int (*nlattr_to_range)(struct nlattr *tb[],
-			       struct nf_nat_ipv4_range *range);
+			       struct nf_nat_range *range);
 };
 
 /* Protocol registration. */
-extern int nf_nat_protocol_register(const struct nf_nat_protocol *proto);
-extern void nf_nat_protocol_unregister(const struct nf_nat_protocol *proto);
+extern int nf_nat_l4proto_register(u8 l3proto, const struct nf_nat_l4proto *l4proto);
+extern void nf_nat_l4proto_unregister(u8 l3proto, const struct nf_nat_l4proto *l4proto);
 
-/* Built-in protocols. */
-extern const struct nf_nat_protocol nf_nat_protocol_tcp;
-extern const struct nf_nat_protocol nf_nat_protocol_udp;
-extern const struct nf_nat_protocol nf_nat_protocol_icmp;
-extern const struct nf_nat_protocol nf_nat_unknown_protocol;
+extern const struct nf_nat_l4proto *__nf_nat_l4proto_find(u8 l3proto, u8 l4proto);
 
-extern int init_protocols(void) __init;
-extern void cleanup_protocols(void);
-extern const struct nf_nat_protocol *find_nat_proto(u_int16_t protonum);
+/* Built-in protocols. */
+extern const struct nf_nat_l4proto nf_nat_l4proto_tcp;
+extern const struct nf_nat_l4proto nf_nat_l4proto_udp;
+extern const struct nf_nat_l4proto nf_nat_l4proto_icmp;
+extern const struct nf_nat_l4proto nf_nat_l4proto_icmpv6;
+extern const struct nf_nat_l4proto nf_nat_l4proto_unknown;
 
-extern bool nf_nat_proto_in_range(const struct nf_conntrack_tuple *tuple,
-				  enum nf_nat_manip_type maniptype,
-				  const union nf_conntrack_man_proto *min,
-				  const union nf_conntrack_man_proto *max);
+extern bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple,
+				    enum nf_nat_manip_type maniptype,
+				    const union nf_conntrack_man_proto *min,
+				    const union nf_conntrack_man_proto *max);
 
-extern void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
-				      const struct nf_nat_ipv4_range *range,
-				      enum nf_nat_manip_type maniptype,
-				      const struct nf_conn *ct,
-				      u_int16_t *rover);
+extern void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
+					struct nf_conntrack_tuple *tuple,
+					const struct nf_nat_range *range,
+					enum nf_nat_manip_type maniptype,
+					const struct nf_conn *ct,
+					u16 *rover);
 
-extern int nf_nat_proto_nlattr_to_range(struct nlattr *tb[],
-					struct nf_nat_ipv4_range *range);
+extern int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[],
+					  struct nf_nat_range *range);
 
-#endif /*_NF_NAT_PROTO_H*/
+#endif /*_NF_NAT_L4PROTO_H*/

include/net/netfilter/nf_nat_rule.h

-#ifndef _NF_NAT_RULE_H
-#define _NF_NAT_RULE_H
-#include <net/netfilter/nf_conntrack.h>
-#include <net/netfilter/nf_nat.h>
-#include <linux/netfilter_ipv4/ip_tables.h>
-
-extern int nf_nat_rule_init(void) __init;
-extern void nf_nat_rule_cleanup(void);
-extern int nf_nat_rule_find(struct sk_buff *skb,
-			    unsigned int hooknum,
-			    const struct net_device *in,
-			    const struct net_device *out,
-			    struct nf_conn *ct);
-
-#endif /* _NF_NAT_RULE_H */

include/net/netns/conntrack.h

@@ -83,6 +83,10 @@ struct netns_ct {
 	int			sysctl_auto_assign_helper;
 	bool			auto_assign_helper_warned;
 	struct nf_ip_net	nf_ct_proto;
+#ifdef CONFIG_NF_NAT_NEEDED
+	struct hlist_head	*nat_bysource;
+	unsigned int		nat_htable_size;
+#endif
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header	*sysctl_header;
 	struct ctl_table_header	*acct_sysctl_header;

include/net/netns/ipv4.h

@@ -52,8 +52,6 @@ struct netns_ipv4 {
 	struct xt_table		*iptable_security;
 #endif
 	struct xt_table		*nat_table;
-	struct hlist_head	*nat_bysource;
-	unsigned int		nat_htable_size;
 #endif
 
 	int sysctl_icmp_echo_ignore_all;

include/net/netns/ipv6.h

@@ -42,6 +42,7 @@ struct netns_ipv6 {
 #ifdef CONFIG_SECURITY
 	struct xt_table		*ip6table_security;
 #endif
+	struct xt_table		*ip6table_nat;
 #endif
 	struct rt6_info         *ip6_null_entry;
 	struct rt6_statistics   *rt6_stats;

net/core/secure_seq.c

@@ -76,6 +76,7 @@ u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 
 	return hash[0];
 }
+EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #endif
 
 #ifdef CONFIG_INET

net/core/utils.c

@@ -294,6 +294,26 @@ void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(inet_proto_csum_replace4);
 
+void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
+			       const __be32 *from, const __be32 *to,
+			       int pseudohdr)
+{
+	__be32 diff[] = {
+		~from[0], ~from[1], ~from[2], ~from[3],
+		to[0], to[1], to[2], to[3],
+	};
+	if (skb->ip_summed != CHECKSUM_PARTIAL) {
+		*sum = csum_fold(csum_partial(diff, sizeof(diff),
+				 ~csum_unfold(*sum)));
+		if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr)
+			skb->csum = ~csum_partial(diff, sizeof(diff),
+						  ~skb->csum);
+	} else if (pseudohdr)
+		*sum = ~csum_fold(csum_partial(diff, sizeof(diff),
+				  csum_unfold(*sum)));
+}
+EXPORT_SYMBOL(inet_proto_csum_replace16);
+
 int mac_pton(const char *s, u8 *mac)
 {
 	int i;

net/ipv4/ip_fragment.c

@@ -523,6 +523,10 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	if (offset == 0)
 		qp->q.last_in |= INET_FRAG_FIRST_IN;
 
+	if (ip_hdr(skb)->frag_off & htons(IP_DF) &&
+	    skb->len + ihl > qp->q.max_size)
+		qp->q.max_size = skb->len + ihl;
+
 	if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
 	    qp->q.meat == qp->q.len)
 		return ip_frag_reasm(qp, prev, dev);
@@ -646,9 +650,11 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 	head->next = NULL;
 	head->dev = dev;
 	head->tstamp = qp->q.stamp;
+	IPCB(head)->frag_max_size = qp->q.max_size;
 
 	iph = ip_hdr(head);
-	iph->frag_off = 0;
+	/* max_size != 0 implies at least one fragment had IP_DF set */
+	iph->frag_off = qp->q.max_size ? htons(IP_DF) : 0;
 	iph->tot_len = htons(len);
 	iph->tos |= ecn;
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);

net/ipv4/ip_output.c

@@ -467,7 +467,9 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 	iph = ip_hdr(skb);
 
-	if (unlikely((iph->frag_off & htons(IP_DF)) && !skb->local_df)) {
+	if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->local_df) ||
+		     (IPCB(skb)->frag_max_size &&
+		      IPCB(skb)->frag_max_size > dst_mtu(&rt->dst)))) {
 		IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 			  htonl(ip_skb_dst_mtu(skb)));

net/ipv4/netfilter.c

@@ -72,43 +72,6 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned int addr_type)
 }
 EXPORT_SYMBOL(ip_route_me_harder);
 
-#ifdef CONFIG_XFRM
-int ip_xfrm_me_harder(struct sk_buff *skb)
-{
-	struct flowi fl;
-	unsigned int hh_len;
-	struct dst_entry *dst;
-
-	if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
-		return 0;
-	if (xfrm_decode_session(skb, &fl, AF_INET) < 0)
-		return -1;
-
-	dst = skb_dst(skb);
-	if (dst->xfrm)
-		dst = ((struct xfrm_dst *)dst)->route;
-	dst_hold(dst);
-
-	dst = xfrm_lookup(dev_net(dst->dev), dst, &fl, skb->sk, 0);
-	if (IS_ERR(dst))
-		return -1;
-
-	skb_dst_drop(skb);
-	skb_dst_set(skb, dst);
-
-	/* Change in oif may mean change in hh_len. */
-	hh_len = skb_dst(skb)->dev->hard_header_len;
-	if (skb_headroom(skb) < hh_len &&
-	    pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC))
-		return -1;
-	return 0;
-}
-EXPORT_SYMBOL(ip_xfrm_me_harder);
-#endif
-
-void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *);
-EXPORT_SYMBOL(ip_nat_decode_session);
-
 /*
  * Extra routing may needed on local out, as the QUEUE target never
  * returns control to the table.
@@ -225,12 +188,12 @@ static const struct nf_afinfo nf_ip_afinfo = {
 	.route_key_size		= sizeof(struct ip_rt_info),
 };
 
-static int ipv4_netfilter_init(void)
+static int __init ipv4_netfilter_init(void)
 {
 	return nf_register_afinfo(&nf_ip_afinfo);
 }
 
-static void ipv4_netfilter_fini(void)
+static void __exit ipv4_netfilter_fini(void)
 {
 	nf_unregister_afinfo(&nf_ip_afinfo);
 }

net/ipv4/netfilter/Kconfig

@@ -143,25 +143,22 @@ config IP_NF_TARGET_ULOG
 	  To compile it as a module, choose M here.  If unsure, say N.
 
 # NAT + specific targets: nf_conntrack
-config NF_NAT
-	tristate "Full NAT"
+config NF_NAT_IPV4
+	tristate "IPv4 NAT"
 	depends on NF_CONNTRACK_IPV4
 	default m if NETFILTER_ADVANCED=n
+	select NF_NAT
 	help
-	  The Full NAT option allows masquerading, port forwarding and other
+	  The IPv4 NAT option allows masquerading, port forwarding and other
 	  forms of full Network Address Port Translation.  It is controlled by
 	  the `nat' table in iptables: see the man page for iptables(8).
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
-config NF_NAT_NEEDED
-	bool
-	depends on NF_NAT
-	default y
+if NF_NAT_IPV4
 
 config IP_NF_TARGET_MASQUERADE
 	tristate "MASQUERADE target support"
-	depends on NF_NAT
 	default m if NETFILTER_ADVANCED=n
 	help
 	  Masquerading is a special case of NAT: all outgoing connections are
@@ -174,7 +171,6 @@ config IP_NF_TARGET_MASQUERADE
 
 config IP_NF_TARGET_NETMAP
 	tristate "NETMAP target support"
-	depends on NF_NAT
 	depends on NETFILTER_ADVANCED
 	help
 	  NETMAP is an implementation of static 1:1 NAT mapping of network
@@ -185,7 +181,6 @@ config IP_NF_TARGET_NETMAP
 
 config IP_NF_TARGET_REDIRECT
 	tristate "REDIRECT target support"
-	depends on NF_NAT
 	depends on NETFILTER_ADVANCED
 	help
 	  REDIRECT is a special case of NAT: all incoming connections are
@@ -195,9 +190,11 @@ config IP_NF_TARGET_REDIRECT
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+endif
+
 config NF_NAT_SNMP_BASIC
 	tristate "Basic SNMP-ALG support"
-	depends on NF_CONNTRACK_SNMP && NF_NAT
+	depends on NF_CONNTRACK_SNMP && NF_NAT_IPV4
 	depends on NETFILTER_ADVANCED
 	default NF_NAT && NF_CONNTRACK_SNMP
 	---help---
@@ -219,61 +216,21 @@ config NF_NAT_SNMP_BASIC
 #           <expr> '&&' <expr>                   (6)
 #
 # (6) Returns the result of min(/expr/, /expr/).
-config NF_NAT_PROTO_DCCP
-	tristate
-	depends on NF_NAT && NF_CT_PROTO_DCCP
-	default NF_NAT && NF_CT_PROTO_DCCP
 
 config NF_NAT_PROTO_GRE
 	tristate
-	depends on NF_NAT && NF_CT_PROTO_GRE
-
-config NF_NAT_PROTO_UDPLITE
-	tristate
-	depends on NF_NAT && NF_CT_PROTO_UDPLITE
-	default NF_NAT && NF_CT_PROTO_UDPLITE
-
-config NF_NAT_PROTO_SCTP
-	tristate
-	default NF_NAT && NF_CT_PROTO_SCTP
-	depends on NF_NAT && NF_CT_PROTO_SCTP
-	select LIBCRC32C
-
-config NF_NAT_FTP
-	tristate
-	depends on NF_CONNTRACK && NF_NAT
-	default NF_NAT && NF_CONNTRACK_FTP
-
-config NF_NAT_IRC
-	tristate
-	depends on NF_CONNTRACK && NF_NAT
-	default NF_NAT && NF_CONNTRACK_IRC
-
-config NF_NAT_TFTP
-	tristate
-	depends on NF_CONNTRACK && NF_NAT
-	default NF_NAT && NF_CONNTRACK_TFTP
-
-config NF_NAT_AMANDA
-	tristate
-	depends on NF_CONNTRACK && NF_NAT
-	default NF_NAT && NF_CONNTRACK_AMANDA
+	depends on NF_NAT_IPV4 && NF_CT_PROTO_GRE
 
 config NF_NAT_PPTP
 	tristate
-	depends on NF_CONNTRACK && NF_NAT
-	default NF_NAT && NF_CONNTRACK_PPTP
+	depends on NF_CONNTRACK && NF_NAT_IPV4
+	default NF_NAT_IPV4 && NF_CONNTRACK_PPTP
 	select NF_NAT_PROTO_GRE
 
 config NF_NAT_H323
 	tristate
-	depends on NF_CONNTRACK && NF_NAT
-	default NF_NAT && NF_CONNTRACK_H323
-
-config NF_NAT_SIP
-	tristate
-	depends on NF_CONNTRACK && NF_NAT
-	default NF_NAT && NF_CONNTRACK_SIP
+	depends on NF_CONNTRACK && NF_NAT_IPV4
+	default NF_NAT_IPV4 && NF_CONNTRACK_H323
 
 # mangle + specific targets
 config IP_NF_MANGLE

net/ipv4/netfilter/Makefile

@@ -10,32 +10,22 @@ nf_conntrack_ipv4-objs	+= nf_conntrack_l3proto_ipv4_compat.o
 endif
 endif
 
-nf_nat-y		:= nf_nat_core.o nf_nat_helper.o nf_nat_proto_unknown.o nf_nat_proto_common.o nf_nat_proto_tcp.o nf_nat_proto_udp.o nf_nat_proto_icmp.o
-iptable_nat-y	:= nf_nat_rule.o nf_nat_standalone.o
-
 # connection tracking
 obj-$(CONFIG_NF_CONNTRACK_IPV4) += nf_conntrack_ipv4.o
 
-obj-$(CONFIG_NF_NAT) += nf_nat.o
+nf_nat_ipv4-y		:= nf_nat_l3proto_ipv4.o nf_nat_proto_icmp.o
+obj-$(CONFIG_NF_NAT_IPV4) += nf_nat_ipv4.o
 
 # defrag
 obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o
 
 # NAT helpers (nf_conntrack)
-obj-$(CONFIG_NF_NAT_AMANDA) += nf_nat_amanda.o
-obj-$(CONFIG_NF_NAT_FTP) += nf_nat_ftp.o
 obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o
-obj-$(CONFIG_NF_NAT_IRC) += nf_nat_irc.o
 obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o
-obj-$(CONFIG_NF_NAT_SIP) += nf_nat_sip.o
 obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o
-obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o
 
 # NAT protocols (nf_nat)
-obj-$(CONFIG_NF_NAT_PROTO_DCCP) += nf_nat_proto_dccp.o
 obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o
-obj-$(CONFIG_NF_NAT_PROTO_UDPLITE) += nf_nat_proto_udplite.o
-obj-$(CONFIG_NF_NAT_PROTO_SCTP) += nf_nat_proto_sctp.o
 
 # generic IP tables 
 obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o
@@ -43,7 +33,7 @@ obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o
 # the three instances of ip_tables
 obj-$(CONFIG_IP_NF_FILTER) += iptable_filter.o
 obj-$(CONFIG_IP_NF_MANGLE) += iptable_mangle.o
-obj-$(CONFIG_NF_NAT) += iptable_nat.o
+obj-$(CONFIG_NF_NAT_IPV4) += iptable_nat.o
 obj-$(CONFIG_IP_NF_RAW) += iptable_raw.o
 obj-$(CONFIG_IP_NF_SECURITY) += iptable_security.o
 

net/ipv4/netfilter/ipt_MASQUERADE.c

@@ -19,9 +19,9 @@
 #include <net/ip.h>
 #include <net/checksum.h>
 #include <net/route.h>
-#include <net/netfilter/nf_nat_rule.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter/x_tables.h>
+#include <net/netfilter/nf_nat.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
@@ -49,7 +49,7 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	struct nf_conn *ct;
 	struct nf_conn_nat *nat;
 	enum ip_conntrack_info ctinfo;
-	struct nf_nat_ipv4_range newrange;
+	struct nf_nat_range newrange;
 	const struct nf_nat_ipv4_multi_range_compat *mr;
 	const struct rtable *rt;
 	__be32 newsrc, nh;
@@ -80,10 +80,13 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	nat->masq_index = par->out->ifindex;
 
 	/* Transfer from original range. */
-	newrange = ((struct nf_nat_ipv4_range)
-		{ mr->range[0].flags | NF_NAT_RANGE_MAP_IPS,
-		  newsrc, newsrc,
-		  mr->range[0].min, mr->range[0].max });
+	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
+	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
+	newrange.flags       = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.ip = newsrc;
+	newrange.max_addr.ip = newsrc;
+	newrange.min_proto   = mr->range[0].min;
+	newrange.max_proto   = mr->range[0].max;
 
 	/* Hand modified range to generic setup. */
 	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
@@ -96,7 +99,8 @@ device_cmp(struct nf_conn *i, void *ifindex)
 
 	if (!nat)
 		return 0;
-
+	if (nf_ct_l3num(i) != NFPROTO_IPV4)
+		return 0;
 	return nat->masq_index == (int)(long)ifindex;
 }
 

net/ipv4/netfilter/ipt_NETMAP.c

@@ -16,7 +16,7 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter/x_tables.h>
-#include <net/netfilter/nf_nat_rule.h>
+#include <net/netfilter/nf_nat.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Svenning Soerensen <svenning@post5.tele.dk>");
@@ -44,7 +44,7 @@ netmap_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	enum ip_conntrack_info ctinfo;
 	__be32 new_ip, netmask;
 	const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
-	struct nf_nat_ipv4_range newrange;
+	struct nf_nat_range newrange;
 
 	NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
 		     par->hooknum == NF_INET_POST_ROUTING ||
@@ -61,10 +61,13 @@ netmap_tg(struct sk_buff *skb, const struct xt_action_param *par)
 		new_ip = ip_hdr(skb)->saddr & ~netmask;
 	new_ip |= mr->range[0].min_ip & netmask;
 
-	newrange = ((struct nf_nat_ipv4_range)
-		{ mr->range[0].flags | NF_NAT_RANGE_MAP_IPS,
-		  new_ip, new_ip,
-		  mr->range[0].min, mr->range[0].max });
+	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
+	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
+	newrange.flags	     = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.ip = new_ip;
+	newrange.max_addr.ip = new_ip;
+	newrange.min_proto   = mr->range[0].min;
+	newrange.max_proto   = mr->range[0].max;
 
 	/* Hand modified range to generic setup. */
 	return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(par->hooknum));

net/ipv4/netfilter/ipt_REDIRECT.c

@@ -19,7 +19,7 @@
 #include <net/checksum.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter/x_tables.h>
-#include <net/netfilter/nf_nat_rule.h>
+#include <net/netfilter/nf_nat.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
@@ -48,7 +48,7 @@ redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	enum ip_conntrack_info ctinfo;
 	__be32 newdst;
 	const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
-	struct nf_nat_ipv4_range newrange;
+	struct nf_nat_range newrange;
 
 	NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
 		     par->hooknum == NF_INET_LOCAL_OUT);
@@ -76,10 +76,13 @@ redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	}
 
 	/* Transfer from original range. */
-	newrange = ((struct nf_nat_ipv4_range)
-		{ mr->range[0].flags | NF_NAT_RANGE_MAP_IPS,
-		  newdst, newdst,
-		  mr->range[0].min, mr->range[0].max });
+	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
+	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
+	newrange.flags	     = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.ip = newdst;
+	newrange.max_addr.ip = newdst;
+	newrange.min_proto   = mr->range[0].min;
+	newrange.max_proto   = mr->range[0].max;
 
 	/* Hand modified range to generic setup. */
 	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);

net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c

@@ -29,11 +29,6 @@
 #include <net/netfilter/ipv4/nf_defrag_ipv4.h>
 #include <net/netfilter/nf_log.h>
 
-int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb,
-			      struct nf_conn *ct,
-			      enum ip_conntrack_info ctinfo);
-EXPORT_SYMBOL_GPL(nf_nat_seq_adjust_hook);
-
 static bool ipv4_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
 			      struct nf_conntrack_tuple *tuple)
 {
@@ -149,7 +144,8 @@ static unsigned int ipv4_confirm(unsigned int hooknum,
 		typeof(nf_nat_seq_adjust_hook) seq_adjust;
 
 		seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook);
-		if (!seq_adjust || !seq_adjust(skb, ct, ctinfo)) {
+		if (!seq_adjust ||
+		    !seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) {
 			NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
 			return NF_DROP;
 		}

net/ipv4/netfilter/nf_nat_l3proto_ipv4.c

+/*
+ * (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
+ * (C) 2011 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/icmp.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <net/secure_seq.h>
+#include <net/checksum.h>
+#include <net/route.h>
+#include <net/ip.h>
+
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_nat_core.h>
+#include <net/netfilter/nf_nat_l3proto.h>
+#include <net/netfilter/nf_nat_l4proto.h>
+
+static const struct nf_nat_l3proto nf_nat_l3proto_ipv4;
+
+#ifdef CONFIG_XFRM
+static void nf_nat_ipv4_decode_session(struct sk_buff *skb,
+				       const struct nf_conn *ct,
+				       enum ip_conntrack_dir dir,
+				       unsigned long statusbit,
+				       struct flowi *fl)
+{
+	const struct nf_conntrack_tuple *t = &ct->tuplehash[dir].tuple;
+	struct flowi4 *fl4 = &fl->u.ip4;
+
+	if (ct->status & statusbit) {
+		fl4->daddr = t->dst.u3.ip;
+		if (t->dst.protonum == IPPROTO_TCP ||
+		    t->dst.protonum == IPPROTO_UDP ||
+		    t->dst.protonum == IPPROTO_UDPLITE ||
+		    t->dst.protonum == IPPROTO_DCCP ||
+		    t->dst.protonum == IPPROTO_SCTP)
+			fl4->fl4_dport = t->dst.u.all;
+	}
+
+	statusbit ^= IPS_NAT_MASK;
+
+	if (ct->status & statusbit) {
+		fl4->saddr = t->src.u3.ip;
+		if (t->dst.protonum == IPPROTO_TCP ||
+		    t->dst.protonum == IPPROTO_UDP ||
+		    t->dst.protonum == IPPROTO_UDPLITE ||
+		    t->dst.protonum == IPPROTO_DCCP ||
+		    t->dst.protonum == IPPROTO_SCTP)
+			fl4->fl4_sport = t->src.u.all;
+	}
+}
+#endif /* CONFIG_XFRM */
+
+static bool nf_nat_ipv4_in_range(const struct nf_conntrack_tuple *t,
+				 const struct nf_nat_range *range)
+{
+	return ntohl(t->src.u3.ip) >= ntohl(range->min_addr.ip) &&
+	       ntohl(t->src.u3.ip) <= ntohl(range->max_addr.ip);
+}
+
+static u32 nf_nat_ipv4_secure_port(const struct nf_conntrack_tuple *t,
+				   __be16 dport)
+{
+	return secure_ipv4_port_ephemeral(t->src.u3.ip, t->dst.u3.ip, dport);
+}
+
+static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb,
+				  unsigned int iphdroff,
+				  const struct nf_nat_l4proto *l4proto,
+				  const struct nf_conntrack_tuple *target,
+				  enum nf_nat_manip_type maniptype)
+{
+	struct iphdr *iph;
+	unsigned int hdroff;
+
+	if (!skb_make_writable(skb, iphdroff + sizeof(*iph)))
+		return false;
+
+	iph = (void *)skb->data + iphdroff;
+	hdroff = iphdroff + iph->ihl * 4;
+
+	if (!l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv4, iphdroff, hdroff,
+				target, maniptype))
+		return false;
+	iph = (void *)skb->data + iphdroff;
+
+	if (maniptype == NF_NAT_MANIP_SRC) {
+		csum_replace4(&iph->check, iph->saddr, target->src.u3.ip);
+		iph->saddr = target->src.u3.ip;
+	} else {
+		csum_replace4(&iph->check, iph->daddr, target->dst.u3.ip);
+		iph->daddr = target->dst.u3.ip;
+	}
+	return true;
+}
+
+static void nf_nat_ipv4_csum_update(struct sk_buff *skb,
+				    unsigned int iphdroff, __sum16 *check,
+				    const struct nf_conntrack_tuple *t,
+				    enum nf_nat_manip_type maniptype)
+{
+	struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff);
+	__be32 oldip, newip;
+
+	if (maniptype == NF_NAT_MANIP_SRC) {
+		oldip = iph->saddr;
+		newip = t->src.u3.ip;
+	} else {
+		oldip = iph->daddr;
+		newip = t->dst.u3.ip;
+	}
+	inet_proto_csum_replace4(check, skb, oldip, newip, 1);
+}
+
+static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb,
+				    u8 proto, void *data, __sum16 *check,
+				    int datalen, int oldlen)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	struct rtable *rt = skb_rtable(skb);
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL) {
+		if (!(rt->rt_flags & RTCF_LOCAL) &&
+		    (!skb->dev || skb->dev->features & NETIF_F_V4_CSUM)) {
+			skb->ip_summed = CHECKSUM_PARTIAL;
+			skb->csum_start = skb_headroom(skb) +
+					  skb_network_offset(skb) +
+					  ip_hdrlen(skb);
+			skb->csum_offset = (void *)check - data;
+			*check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+						    datalen, proto, 0);
+		} else {
+			*check = 0;
+			*check = csum_tcpudp_magic(iph->saddr, iph->daddr,
+						   datalen, proto,
+						   csum_partial(data, datalen,
+								0));
+			if (proto == IPPROTO_UDP && !*check)
+				*check = CSUM_MANGLED_0;
+		}
+	} else
+		inet_proto_csum_replace2(check, skb,
+					 htons(oldlen), htons(datalen), 1);
+}
+
+static int nf_nat_ipv4_nlattr_to_range(struct nlattr *tb[],
+				       struct nf_nat_range *range)
+{
+	if (tb[CTA_NAT_V4_MINIP]) {
+		range->min_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MINIP]);
+		range->flags |= NF_NAT_RANGE_MAP_IPS;
+	}
+
+	if (tb[CTA_NAT_V4_MAXIP])
+		range->max_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MAXIP]);
+	else
+		range->max_addr.ip = range->min_addr.ip;
+
+	return 0;
+}
+
+static const struct nf_nat_l3proto nf_nat_l3proto_ipv4 = {
+	.l3proto		= NFPROTO_IPV4,
+	.in_range		= nf_nat_ipv4_in_range,
+	.secure_port		= nf_nat_ipv4_secure_port,
+	.manip_pkt		= nf_nat_ipv4_manip_pkt,
+	.csum_update		= nf_nat_ipv4_csum_update,
+	.csum_recalc		= nf_nat_ipv4_csum_recalc,
+	.nlattr_to_range	= nf_nat_ipv4_nlattr_to_range,
+#ifdef CONFIG_XFRM
+	.decode_session		= nf_nat_ipv4_decode_session,
+#endif
+};
+
+int nf_nat_icmp_reply_translation(struct sk_buff *skb,
+				  struct nf_conn *ct,
+				  enum ip_conntrack_info ctinfo,
+				  unsigned int hooknum)
+{
+	struct {
+		struct icmphdr	icmp;
+		struct iphdr	ip;
+	} *inside;
+	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+	enum nf_nat_manip_type manip = HOOK2MANIP(hooknum);
+	unsigned int hdrlen = ip_hdrlen(skb);
+	const struct nf_nat_l4proto *l4proto;
+	struct nf_conntrack_tuple target;
+	unsigned long statusbit;
+
+	NF_CT_ASSERT(ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY);
+
+	if (!skb_make_writable(skb, hdrlen + sizeof(*inside)))
+		return 0;
+	if (nf_ip_checksum(skb, hooknum, hdrlen, 0))
+		return 0;
+
+	inside = (void *)skb->data + hdrlen;
+	if (inside->icmp.type == ICMP_REDIRECT) {
+		if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK)
+			return 0;
+		if (ct->status & IPS_NAT_MASK)
+			return 0;
+	}
+
+	if (manip == NF_NAT_MANIP_SRC)
+		statusbit = IPS_SRC_NAT;
+	else
+		statusbit = IPS_DST_NAT;
+
+	/* Invert if this is reply direction */
+	if (dir == IP_CT_DIR_REPLY)
+		statusbit ^= IPS_NAT_MASK;
+
+	if (!(ct->status & statusbit))
+		return 1;
+
+	l4proto = __nf_nat_l4proto_find(NFPROTO_IPV4, inside->ip.protocol);
+	if (!nf_nat_ipv4_manip_pkt(skb, hdrlen + sizeof(inside->icmp),
+				   l4proto, &ct->tuplehash[!dir].tuple, !manip))
+		return 0;
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL) {
+		/* Reloading "inside" here since manip_pkt may reallocate */
+		inside = (void *)skb->data + hdrlen;
+		inside->icmp.checksum = 0;
+		inside->icmp.checksum =
+			csum_fold(skb_checksum(skb, hdrlen,
+					       skb->len - hdrlen, 0));
+	}
+
+	/* Change outer to look like the reply to an incoming packet */
+	nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
+	l4proto = __nf_nat_l4proto_find(NFPROTO_IPV4, 0);
+	if (!nf_nat_ipv4_manip_pkt(skb, 0, l4proto, &target, manip))
+		return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation);
+
+static int __init nf_nat_l3proto_ipv4_init(void)
+{
+	int err;
+
+	err = nf_nat_l4proto_register(NFPROTO_IPV4, &nf_nat_l4proto_icmp);
+	if (err < 0)
+		goto err1;
+	err = nf_nat_l3proto_register(&nf_nat_l3proto_ipv4);
+	if (err < 0)
+		goto err2;
+	return err;
+
+err2:
+	nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_icmp);
+err1:
+	return err;
+}
+
+static void __exit nf_nat_l3proto_ipv4_exit(void)
+{
+	nf_nat_l3proto_unregister(&nf_nat_l3proto_ipv4);
+	nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_icmp);
+}
+
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("nf-nat-" __stringify(AF_INET));
+
+module_init(nf_nat_l3proto_ipv4_init);
+module_exit(nf_nat_l3proto_ipv4_exit);

net/ipv4/netfilter/nf_nat_pptp.c

@@ -22,7 +22,6 @@
 
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_helper.h>
-#include <net/netfilter/nf_nat_rule.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_zones.h>
@@ -47,7 +46,7 @@ static void pptp_nat_expected(struct nf_conn *ct,
 	struct nf_conntrack_tuple t;
 	const struct nf_ct_pptp_master *ct_pptp_info;
 	const struct nf_nat_pptp *nat_pptp_info;
-	struct nf_nat_ipv4_range range;
+	struct nf_nat_range range;
 
 	ct_pptp_info = nfct_help_data(master);
 	nat_pptp_info = &nfct_nat(master)->help.nat_pptp_info;
@@ -89,21 +88,21 @@ static void pptp_nat_expected(struct nf_conn *ct,
 
 	/* Change src to where master sends to */
 	range.flags = NF_NAT_RANGE_MAP_IPS;
-	range.min_ip = range.max_ip
-		= ct->master->tuplehash[!exp->dir].tuple.dst.u3.ip;
+	range.min_addr = range.max_addr
+		= ct->master->tuplehash[!exp->dir].tuple.dst.u3;
 	if (exp->dir == IP_CT_DIR_ORIGINAL) {
 		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
-		range.min = range.max = exp->saved_proto;
+		range.min_proto = range.max_proto = exp->saved_proto;
 	}
 	nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC);
 
 	/* For DST manip, map port here to where it's expected. */
 	range.flags = NF_NAT_RANGE_MAP_IPS;
-	range.min_ip = range.max_ip
-		= ct->master->tuplehash[!exp->dir].tuple.src.u3.ip;
+	range.min_addr = range.max_addr
+		= ct->master->tuplehash[!exp->dir].tuple.src.u3;
 	if (exp->dir == IP_CT_DIR_REPLY) {
 		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
-		range.min = range.max = exp->saved_proto;
+		range.min_proto = range.max_proto = exp->saved_proto;
 	}
 	nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST);
 }
@@ -113,6 +112,7 @@ static int
 pptp_outbound_pkt(struct sk_buff *skb,
 		  struct nf_conn *ct,
 		  enum ip_conntrack_info ctinfo,
+		  unsigned int protoff,
 		  struct PptpControlHeader *ctlh,
 		  union pptp_ctrl_union *pptpReq)
 
@@ -175,7 +175,7 @@ pptp_outbound_pkt(struct sk_buff *skb,
 		 ntohs(REQ_CID(pptpReq, cid_off)), ntohs(new_callid));
 
 	/* mangle packet */
-	if (nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
+	if (nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff,
 				     cid_off + sizeof(struct pptp_pkt_hdr) +
 				     sizeof(struct PptpControlHeader),
 				     sizeof(new_callid), (char *)&new_callid,
@@ -216,6 +216,7 @@ static int
 pptp_inbound_pkt(struct sk_buff *skb,
 		 struct nf_conn *ct,
 		 enum ip_conntrack_info ctinfo,
+		 unsigned int protoff,
 		 struct PptpControlHeader *ctlh,
 		 union pptp_ctrl_union *pptpReq)
 {
@@ -268,7 +269,7 @@ pptp_inbound_pkt(struct sk_buff *skb,
 	pr_debug("altering peer call id from 0x%04x to 0x%04x\n",
 		 ntohs(REQ_CID(pptpReq, pcid_off)), ntohs(new_pcid));
 
-	if (nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
+	if (nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff,
 				     pcid_off + sizeof(struct pptp_pkt_hdr) +
 				     sizeof(struct PptpControlHeader),
 				     sizeof(new_pcid), (char *)&new_pcid,

net/ipv4/netfilter/nf_nat_proto_gre.c

@@ -28,8 +28,7 @@
 #include <linux/ip.h>
 
 #include <net/netfilter/nf_nat.h>
-#include <net/netfilter/nf_nat_rule.h>
-#include <net/netfilter/nf_nat_protocol.h>
+#include <net/netfilter/nf_nat_l4proto.h>
 #include <linux/netfilter/nf_conntrack_proto_gre.h>
 
 MODULE_LICENSE("GPL");
@@ -38,8 +37,9 @@ MODULE_DESCRIPTION("Netfilter NAT protocol helper module for GRE");
 
 /* generate unique tuple ... */
 static void
-gre_unique_tuple(struct nf_conntrack_tuple *tuple,
-		 const struct nf_nat_ipv4_range *range,
+gre_unique_tuple(const struct nf_nat_l3proto *l3proto,
+		 struct nf_conntrack_tuple *tuple,
+		 const struct nf_nat_range *range,
 		 enum nf_nat_manip_type maniptype,
 		 const struct nf_conn *ct)
 {
@@ -62,8 +62,8 @@ gre_unique_tuple(struct nf_conntrack_tuple *tuple,
 		min = 1;
 		range_size = 0xffff;
 	} else {
-		min = ntohs(range->min.gre.key);
-		range_size = ntohs(range->max.gre.key) - min + 1;
+		min = ntohs(range->min_proto.gre.key);
+		range_size = ntohs(range->max_proto.gre.key) - min + 1;
 	}
 
 	pr_debug("min = %u, range_size = %u\n", min, range_size);
@@ -80,14 +80,14 @@ gre_unique_tuple(struct nf_conntrack_tuple *tuple,
 
 /* manipulate a GRE packet according to maniptype */
 static bool
-gre_manip_pkt(struct sk_buff *skb, unsigned int iphdroff,
+gre_manip_pkt(struct sk_buff *skb,
+	      const struct nf_nat_l3proto *l3proto,
+	      unsigned int iphdroff, unsigned int hdroff,
 	      const struct nf_conntrack_tuple *tuple,
 	      enum nf_nat_manip_type maniptype)
 {
 	const struct gre_hdr *greh;
 	struct gre_hdr_pptp *pgreh;
-	const struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff);
-	unsigned int hdroff = iphdroff + iph->ihl * 4;
 
 	/* pgreh includes two optional 32bit fields which are not required
 	 * to be there.  That's where the magic '8' comes from */
@@ -117,24 +117,24 @@ gre_manip_pkt(struct sk_buff *skb, unsigned int iphdroff,
 	return true;
 }
 
-static const struct nf_nat_protocol gre = {
-	.protonum		= IPPROTO_GRE,
+static const struct nf_nat_l4proto gre = {
+	.l4proto		= IPPROTO_GRE,
 	.manip_pkt		= gre_manip_pkt,
-	.in_range		= nf_nat_proto_in_range,
+	.in_range		= nf_nat_l4proto_in_range,
 	.unique_tuple		= gre_unique_tuple,
 #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
-	.nlattr_to_range	= nf_nat_proto_nlattr_to_range,
+	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
 };
 
 static int __init nf_nat_proto_gre_init(void)
 {
-	return nf_nat_protocol_register(&gre);
+	return nf_nat_l4proto_register(NFPROTO_IPV4, &gre);
 }
 
 static void __exit nf_nat_proto_gre_fini(void)
 {
-	nf_nat_protocol_unregister(&gre);
+	nf_nat_l4proto_unregister(NFPROTO_IPV4, &gre);
 }
 
 module_init(nf_nat_proto_gre_init);

net/ipv4/netfilter/nf_nat_proto_icmp.c

@@ -15,8 +15,7 @@
 #include <linux/netfilter.h>
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_core.h>
-#include <net/netfilter/nf_nat_rule.h>
-#include <net/netfilter/nf_nat_protocol.h>
+#include <net/netfilter/nf_nat_l4proto.h>
 
 static bool
 icmp_in_range(const struct nf_conntrack_tuple *tuple,
@@ -29,8 +28,9 @@ icmp_in_range(const struct nf_conntrack_tuple *tuple,
 }
 
 static void
-icmp_unique_tuple(struct nf_conntrack_tuple *tuple,
-		  const struct nf_nat_ipv4_range *range,
+icmp_unique_tuple(const struct nf_nat_l3proto *l3proto,
+		  struct nf_conntrack_tuple *tuple,
+		  const struct nf_nat_range *range,
 		  enum nf_nat_manip_type maniptype,
 		  const struct nf_conn *ct)
 {
@@ -38,13 +38,14 @@ icmp_unique_tuple(struct nf_conntrack_tuple *tuple,
 	unsigned int range_size;
 	unsigned int i;
 
-	range_size = ntohs(range->max.icmp.id) - ntohs(range->min.icmp.id) + 1;
+	range_size = ntohs(range->max_proto.icmp.id) -
+		     ntohs(range->min_proto.icmp.id) + 1;
 	/* If no range specified... */
 	if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED))
 		range_size = 0xFFFF;
 
 	for (i = 0; ; ++id) {
-		tuple->src.u.icmp.id = htons(ntohs(range->min.icmp.id) +
+		tuple->src.u.icmp.id = htons(ntohs(range->min_proto.icmp.id) +
 					     (id % range_size));
 		if (++i == range_size || !nf_nat_used_tuple(tuple, ct))
 			return;
@@ -54,13 +55,12 @@ icmp_unique_tuple(struct nf_conntrack_tuple *tuple,
 
 static bool
 icmp_manip_pkt(struct sk_buff *skb,
-	       unsigned int iphdroff,
+	       const struct nf_nat_l3proto *l3proto,
+	       unsigned int iphdroff, unsigned int hdroff,
 	       const struct nf_conntrack_tuple *tuple,
 	       enum nf_nat_manip_type maniptype)
 {
-	const struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff);
 	struct icmphdr *hdr;
-	unsigned int hdroff = iphdroff + iph->ihl*4;
 
 	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
 		return false;
@@ -72,12 +72,12 @@ icmp_manip_pkt(struct sk_buff *skb,
 	return true;
 }
 
-const struct nf_nat_protocol nf_nat_protocol_icmp = {
-	.protonum		= IPPROTO_ICMP,
+const struct nf_nat_l4proto nf_nat_l4proto_icmp = {
+	.l4proto		= IPPROTO_ICMP,
 	.manip_pkt		= icmp_manip_pkt,
 	.in_range		= icmp_in_range,
 	.unique_tuple		= icmp_unique_tuple,
 #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
-	.nlattr_to_range	= nf_nat_proto_nlattr_to_range,
+	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
 #endif
 };

net/ipv4/netfilter/nf_nat_rule.c

-/* (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-/* Everything about the rules for NAT. */
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/types.h>
-#include <linux/ip.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv4.h>
-#include <linux/module.h>
-#include <linux/kmod.h>
-#include <linux/skbuff.h>
-#include <linux/proc_fs.h>
-#include <linux/slab.h>
-#include <net/checksum.h>
-#include <net/route.h>
-#include <linux/bitops.h>
-
-#include <linux/netfilter_ipv4/ip_tables.h>
-#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/nf_nat_core.h>
-#include <net/netfilter/nf_nat_rule.h>
-
-#define NAT_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | \
-			 (1 << NF_INET_POST_ROUTING) | \
-			 (1 << NF_INET_LOCAL_OUT) | \
-			 (1 << NF_INET_LOCAL_IN))
-
-static const struct xt_table nat_table = {
-	.name		= "nat",
-	.valid_hooks	= NAT_VALID_HOOKS,
-	.me		= THIS_MODULE,
-	.af		= NFPROTO_IPV4,
-};
-
-/* Source NAT */
-static unsigned int
-ipt_snat_target(struct sk_buff *skb, const struct xt_action_param *par)
-{
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
-
-	NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING ||
-		     par->hooknum == NF_INET_LOCAL_IN);
-
-	ct = nf_ct_get(skb, &ctinfo);
-
-	/* Connection must be valid and new. */
-	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
-			    ctinfo == IP_CT_RELATED_REPLY));
-	NF_CT_ASSERT(par->out != NULL);
-
-	return nf_nat_setup_info(ct, &mr->range[0], NF_NAT_MANIP_SRC);
-}
-
-static unsigned int
-ipt_dnat_target(struct sk_buff *skb, const struct xt_action_param *par)
-{
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
-
-	NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
-		     par->hooknum == NF_INET_LOCAL_OUT);
-
-	ct = nf_ct_get(skb, &ctinfo);
-
-	/* Connection must be valid and new. */
-	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED));
-
-	return nf_nat_setup_info(ct, &mr->range[0], NF_NAT_MANIP_DST);
-}
-
-static int ipt_snat_checkentry(const struct xt_tgchk_param *par)
-{
-	const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
-
-	/* Must be a valid range */
-	if (mr->rangesize != 1) {
-		pr_info("SNAT: multiple ranges no longer supported\n");
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static int ipt_dnat_checkentry(const struct xt_tgchk_param *par)
-{
-	const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
-
-	/* Must be a valid range */
-	if (mr->rangesize != 1) {
-		pr_info("DNAT: multiple ranges no longer supported\n");
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static unsigned int
-alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
-{
-	/* Force range to this IP; let proto decide mapping for
-	   per-proto parts (hence not NF_NAT_RANGE_PROTO_SPECIFIED).
-	*/
-	struct nf_nat_ipv4_range range;
-
-	range.flags = 0;
-	pr_debug("Allocating NULL binding for %p (%pI4)\n", ct,
-		 HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
-		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip :
-		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip);
-
-	return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
-}
-
-int nf_nat_rule_find(struct sk_buff *skb,
-		     unsigned int hooknum,
-		     const struct net_device *in,
-		     const struct net_device *out,
-		     struct nf_conn *ct)
-{
-	struct net *net = nf_ct_net(ct);
-	int ret;
-
-	ret = ipt_do_table(skb, hooknum, in, out, net->ipv4.nat_table);
-
-	if (ret == NF_ACCEPT) {
-		if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum)))
-			/* NUL mapping */
-			ret = alloc_null_binding(ct, hooknum);
-	}
-	return ret;
-}
-
-static struct xt_target ipt_snat_reg __read_mostly = {
-	.name		= "SNAT",
-	.target		= ipt_snat_target,
-	.targetsize	= sizeof(struct nf_nat_ipv4_multi_range_compat),
-	.table		= "nat",
-	.hooks		= (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_IN),
-	.checkentry	= ipt_snat_checkentry,
-	.family		= AF_INET,
-};
-
-static struct xt_target ipt_dnat_reg __read_mostly = {
-	.name		= "DNAT",
-	.target		= ipt_dnat_target,
-	.targetsize	= sizeof(struct nf_nat_ipv4_multi_range_compat),
-	.table		= "nat",
-	.hooks		= (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT),
-	.checkentry	= ipt_dnat_checkentry,
-	.family		= AF_INET,
-};
-
-static int __net_init nf_nat_rule_net_init(struct net *net)
-{
-	struct ipt_replace *repl;
-
-	repl = ipt_alloc_initial_table(&nat_table);
-	if (repl == NULL)
-		return -ENOMEM;
-	net->ipv4.nat_table = ipt_register_table(net, &nat_table, repl);
-	kfree(repl);
-	if (IS_ERR(net->ipv4.nat_table))
-		return PTR_ERR(net->ipv4.nat_table);
-	return 0;
-}
-
-static void __net_exit nf_nat_rule_net_exit(struct net *net)
-{
-	ipt_unregister_table(net, net->ipv4.nat_table);
-}
-
-static struct pernet_operations nf_nat_rule_net_ops = {
-	.init = nf_nat_rule_net_init,
-	.exit = nf_nat_rule_net_exit,
-};
-
-int __init nf_nat_rule_init(void)
-{
-	int ret;
-
-	ret = register_pernet_subsys(&nf_nat_rule_net_ops);
-	if (ret != 0)
-		goto out;
-	ret = xt_register_target(&ipt_snat_reg);
-	if (ret != 0)
-		goto unregister_table;
-
-	ret = xt_register_target(&ipt_dnat_reg);
-	if (ret != 0)
-		goto unregister_snat;
-
-	return ret;
-
- unregister_snat:
-	xt_unregister_target(&ipt_snat_reg);
- unregister_table:
-	unregister_pernet_subsys(&nf_nat_rule_net_ops);
- out:
-	return ret;
-}
-
-void nf_nat_rule_cleanup(void)
-{
-	xt_unregister_target(&ipt_dnat_reg);
-	xt_unregister_target(&ipt_snat_reg);
-	unregister_pernet_subsys(&nf_nat_rule_net_ops);
-}

net/ipv6/addrconf.c

@@ -1084,7 +1084,7 @@ static int ipv6_get_saddr_eval(struct net *net,
 	return ret;
 }
 
-int ipv6_dev_get_saddr(struct net *net, struct net_device *dst_dev,
+int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
 		       const struct in6_addr *daddr, unsigned int prefs,
 		       struct in6_addr *saddr)
 {

net/ipv6/ip6_output.c

@@ -493,7 +493,8 @@ int ip6_forward(struct sk_buff *skb)
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
-	if (skb->len > mtu && !skb_is_gso(skb)) {
+	if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) ||
+	    (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) {
 		/* Again, force OUTPUT device used as source address */
 		skb->dev = dst->dev;
 		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
@@ -636,7 +637,9 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	/* We must not fragment if the socket is set to force MTU discovery
 	 * or if the skb it not generated by a local socket.
 	 */
-	if (unlikely(!skb->local_df && skb->len > mtu)) {
+	if (unlikely(!skb->local_df && skb->len > mtu) ||
+		     (IP6CB(skb)->frag_max_size &&
+		      IP6CB(skb)->frag_max_size > mtu)) {
 		if (skb->sk && dst_allfrag(skb_dst(skb)))
 			sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
 

net/ipv6/netfilter.c

@@ -15,6 +15,7 @@ int ip6_route_me_harder(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb_dst(skb)->dev);
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
+	unsigned int hh_len;
 	struct dst_entry *dst;
 	struct flowi6 fl6 = {
 		.flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
@@ -47,6 +48,13 @@ int ip6_route_me_harder(struct sk_buff *skb)
 	}
 #endif
 
+	/* Change in oif may mean change in hh_len. */
+	hh_len = skb_dst(skb)->dev->hard_header_len;
+	if (skb_headroom(skb) < hh_len &&
+	    pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
+			     0, GFP_ATOMIC))
+		return -1;
+
 	return 0;
 }
 EXPORT_SYMBOL(ip6_route_me_harder);

net/ipv6/netfilter/Kconfig

@@ -25,6 +25,18 @@ config NF_CONNTRACK_IPV6
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NF_NAT_IPV6
+	tristate "IPv6 NAT"
+	depends on NF_CONNTRACK_IPV6
+	depends on NETFILTER_ADVANCED
+	select NF_NAT
+	help
+	  The IPv6 NAT option allows masquerading, port forwarding and other
+	  forms of full Network Address Port Translation. It is controlled by
+	  the `nat' table in ip6tables, see the man page for ip6tables(8).
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 config IP6_NF_IPTABLES
 	tristate "IP6 tables support (required for filtering)"
 	depends on INET && IPV6
@@ -132,6 +144,48 @@ config IP6_NF_TARGET_HL
 	(e.g. when running oldconfig). It selects
 	CONFIG_NETFILTER_XT_TARGET_HL.
 
+config IP6_NF_TARGET_MASQUERADE
+	tristate "MASQUERADE target support"
+	depends on NF_NAT_IPV6
+	help
+	  Masquerading is a special case of NAT: all outgoing connections are
+	  changed to seem to come from a particular interface's address, and
+	  if the interface goes down, those connections are lost.  This is
+	  only useful for dialup accounts with dynamic IP address (ie. your IP
+	  address will be different on next dialup).
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_TARGET_NETMAP
+	tristate "NETMAP target support"
+	depends on NF_NAT_IPV6
+	help
+	  NETMAP is an implementation of static 1:1 NAT mapping of network
+	  addresses. It maps the network address part, while keeping the host
+	  address part intact.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_TARGET_REDIRECT
+	tristate "REDIRECT target support"
+	depends on NF_NAT_IPV6
+	help
+	  REDIRECT is a special case of NAT: all incoming connections are
+	  mapped onto the incoming interface's address, causing the packets to
+	  come to the local machine instead of passing through.  This is
+	  useful for transparent proxies.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_TARGET_NPT
+	tristate "NPT (Network Prefix translation) target support"
+	depends on NETFILTER_ADVANCED
+	help
+	  This option adds the `SNPT' and `DNPT' target, which perform
+	  stateless IPv6-to-IPv6 Network Prefix Translation per RFC 6296.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 config IP6_NF_FILTER
 	tristate "Packet filtering"
 	default m if NETFILTER_ADVANCED=n

net/ipv6/netfilter/Makefile

@@ -8,6 +8,7 @@ obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o
 obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o
 obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o
 obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o
+obj-$(CONFIG_NF_NAT_IPV6) += ip6table_nat.o
 
 # objects for l3 independent conntrack
 nf_conntrack_ipv6-y  :=  nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o
@@ -15,6 +16,9 @@ nf_conntrack_ipv6-y  :=  nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o
 # l3 independent conntrack
 obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o nf_defrag_ipv6.o
 
+nf_nat_ipv6-y		:= nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o
+obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o
+
 # defrag
 nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o
 obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
@@ -30,4 +34,8 @@ obj-$(CONFIG_IP6_NF_MATCH_RPFILTER) += ip6t_rpfilter.o
 obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o
 
 # targets
+obj-$(CONFIG_IP6_NF_TARGET_MASQUERADE) += ip6t_MASQUERADE.o
+obj-$(CONFIG_IP6_NF_TARGET_NETMAP) += ip6t_NETMAP.o
+obj-$(CONFIG_IP6_NF_TARGET_NPT) += ip6t_NPT.o
+obj-$(CONFIG_IP6_NF_TARGET_REDIRECT) += ip6t_REDIRECT.o
 obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o

net/ipv6/netfilter/ip6t_MASQUERADE.c

+/*
+ * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on Rusty Russell's IPv6 MASQUERADE target. Development of IPv6
+ * NAT funded by Astaro.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/ipv6.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter/x_tables.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+
+static unsigned int
+masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct nf_nat_range *range = par->targinfo;
+	enum ip_conntrack_info ctinfo;
+	struct in6_addr src;
+	struct nf_conn *ct;
+	struct nf_nat_range newrange;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
+			    ctinfo == IP_CT_RELATED_REPLY));
+
+	if (ipv6_dev_get_saddr(dev_net(par->out), par->out,
+			       &ipv6_hdr(skb)->daddr, 0, &src) < 0)
+		return NF_DROP;
+
+	nfct_nat(ct)->masq_index = par->out->ifindex;
+
+	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.in6	= src;
+	newrange.max_addr.in6	= src;
+	newrange.min_proto	= range->min_proto;
+	newrange.max_proto	= range->max_proto;
+
+	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
+}
+
+static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par)
+{
+	const struct nf_nat_range *range = par->targinfo;
+
+	if (range->flags & NF_NAT_RANGE_MAP_IPS)
+		return -EINVAL;
+	return 0;
+}
+
+static int device_cmp(struct nf_conn *ct, void *ifindex)
+{
+	const struct nf_conn_nat *nat = nfct_nat(ct);
+
+	if (!nat)
+		return 0;
+	if (nf_ct_l3num(ct) != NFPROTO_IPV6)
+		return 0;
+	return nat->masq_index == (int)(long)ifindex;
+}
+
+static int masq_device_event(struct notifier_block *this,
+			     unsigned long event, void *ptr)
+{
+	const struct net_device *dev = ptr;
+	struct net *net = dev_net(dev);
+
+	if (event == NETDEV_DOWN)
+		nf_ct_iterate_cleanup(net, device_cmp,
+				      (void *)(long)dev->ifindex);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block masq_dev_notifier = {
+	.notifier_call	= masq_device_event,
+};
+
+static int masq_inet_event(struct notifier_block *this,
+			   unsigned long event, void *ptr)
+{
+	struct inet6_ifaddr *ifa = ptr;
+
+	return masq_device_event(this, event, ifa->idev->dev);
+}
+
+static struct notifier_block masq_inet_notifier = {
+	.notifier_call	= masq_inet_event,
+};
+
+static struct xt_target masquerade_tg6_reg __read_mostly = {
+	.name		= "MASQUERADE",
+	.family		= NFPROTO_IPV6,
+	.checkentry	= masquerade_tg6_checkentry,
+	.target		= masquerade_tg6,
+	.targetsize	= sizeof(struct nf_nat_range),
+	.table		= "nat",
+	.hooks		= 1 << NF_INET_POST_ROUTING,
+	.me		= THIS_MODULE,
+};
+
+static int __init masquerade_tg6_init(void)
+{
+	int err;
+
+	err = xt_register_target(&masquerade_tg6_reg);
+	if (err == 0) {
+		register_netdevice_notifier(&masq_dev_notifier);
+		register_inet6addr_notifier(&masq_inet_notifier);
+	}
+
+	return err;
+}
+static void __exit masquerade_tg6_exit(void)
+{
+	unregister_inet6addr_notifier(&masq_inet_notifier);
+	unregister_netdevice_notifier(&masq_dev_notifier);
+	xt_unregister_target(&masquerade_tg6_reg);
+}
+
+module_init(masquerade_tg6_init);
+module_exit(masquerade_tg6_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_DESCRIPTION("Xtables: automatic address SNAT");

net/ipv6/netfilter/ip6t_NETMAP.c

+/*
+ * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on Svenning Soerensen's IPv4 NETMAP target. Development of IPv6
+ * NAT funded by Astaro.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/ipv6.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter/x_tables.h>
+#include <net/netfilter/nf_nat.h>
+
+static unsigned int
+netmap_tg6(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct nf_nat_range *range = par->targinfo;
+	struct nf_nat_range newrange;
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	union nf_inet_addr new_addr, netmask;
+	unsigned int i;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	for (i = 0; i < ARRAY_SIZE(range->min_addr.ip6); i++)
+		netmask.ip6[i] = ~(range->min_addr.ip6[i] ^
+				   range->max_addr.ip6[i]);
+
+	if (par->hooknum == NF_INET_PRE_ROUTING ||
+	    par->hooknum == NF_INET_LOCAL_OUT)
+		new_addr.in6 = ipv6_hdr(skb)->daddr;
+	else
+		new_addr.in6 = ipv6_hdr(skb)->saddr;
+
+	for (i = 0; i < ARRAY_SIZE(new_addr.ip6); i++) {
+		new_addr.ip6[i] &= ~netmask.ip6[i];
+		new_addr.ip6[i] |= range->min_addr.ip6[i] &
+				   netmask.ip6[i];
+	}
+
+	newrange.flags	= range->flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr	= new_addr;
+	newrange.max_addr	= new_addr;
+	newrange.min_proto	= range->min_proto;
+	newrange.max_proto	= range->max_proto;
+
+	return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(par->hooknum));
+}
+
+static int netmap_tg6_checkentry(const struct xt_tgchk_param *par)
+{
+	const struct nf_nat_range *range = par->targinfo;
+
+	if (!(range->flags & NF_NAT_RANGE_MAP_IPS))
+		return -EINVAL;
+	return 0;
+}
+
+static struct xt_target netmap_tg6_reg __read_mostly = {
+	.name		= "NETMAP",
+	.family		= NFPROTO_IPV6,
+	.target		= netmap_tg6,
+	.targetsize	= sizeof(struct nf_nat_range),
+	.table		= "nat",
+	.hooks		= (1 << NF_INET_PRE_ROUTING) |
+			  (1 << NF_INET_POST_ROUTING) |
+			  (1 << NF_INET_LOCAL_OUT) |
+			  (1 << NF_INET_LOCAL_IN),
+	.checkentry	= netmap_tg6_checkentry,
+	.me		= THIS_MODULE,
+};
+
+static int __init netmap_tg6_init(void)
+{
+	return xt_register_target(&netmap_tg6_reg);
+}
+
+static void netmap_tg6_exit(void)
+{
+	xt_unregister_target(&netmap_tg6_reg);
+}
+
+module_init(netmap_tg6_init);
+module_exit(netmap_tg6_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Xtables: 1:1 NAT mapping of IPv6 subnets");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");

net/ipv6/netfilter/ip6t_NPT.c

+/*
+ * Copyright (c) 2011, 2012 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_ipv6/ip6t_NPT.h>
+#include <linux/netfilter/x_tables.h>
+
+static __sum16 csum16_complement(__sum16 a)
+{
+	return (__force __sum16)(0xffff - (__force u16)a);
+}
+
+static __sum16 csum16_add(__sum16 a, __sum16 b)
+{
+	u16 sum;
+
+	sum = (__force u16)a + (__force u16)b;
+	sum += (__force u16)a < (__force u16)b;
+	return (__force __sum16)sum;
+}
+
+static __sum16 csum16_sub(__sum16 a, __sum16 b)
+{
+	return csum16_add(a, csum16_complement(b));
+}
+
+static int ip6t_npt_checkentry(const struct xt_tgchk_param *par)
+{
+	struct ip6t_npt_tginfo *npt = par->targinfo;
+	__sum16 src_sum = 0, dst_sum = 0;
+	unsigned int i;
+
+	if (npt->src_pfx_len > 64 || npt->dst_pfx_len > 64)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(npt->src_pfx.in6.s6_addr16); i++) {
+		src_sum = csum16_add(src_sum,
+				(__force __sum16)npt->src_pfx.in6.s6_addr16[i]);
+		dst_sum = csum16_add(dst_sum,
+				(__force __sum16)npt->dst_pfx.in6.s6_addr16[i]);
+	}
+
+	npt->adjustment = csum16_sub(src_sum, dst_sum);
+	return 0;
+}
+
+static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt,
+			     struct in6_addr *addr)
+{
+	unsigned int pfx_len;
+	unsigned int i, idx;
+	__be32 mask;
+	__sum16 sum;
+
+	pfx_len = max(npt->src_pfx_len, npt->dst_pfx_len);
+	for (i = 0; i < pfx_len; i += 32) {
+		if (pfx_len - i >= 32)
+			mask = 0;
+		else
+			mask = htonl(~((1 << (pfx_len - i)) - 1));
+
+		idx = i / 32;
+		addr->s6_addr32[idx] &= mask;
+		addr->s6_addr32[idx] |= npt->dst_pfx.in6.s6_addr32[idx];
+	}
+
+	if (pfx_len <= 48)
+		idx = 3;
+	else {
+		for (idx = 4; idx < ARRAY_SIZE(addr->s6_addr16); idx++) {
+			if ((__force __sum16)addr->s6_addr16[idx] !=
+			    CSUM_MANGLED_0)
+				break;
+		}
+		if (idx == ARRAY_SIZE(addr->s6_addr16))
+			return false;
+	}
+
+	sum = csum16_add((__force __sum16)addr->s6_addr16[idx],
+			 npt->adjustment);
+	if (sum == CSUM_MANGLED_0)
+		sum = 0;
+	*(__force __sum16 *)&addr->s6_addr16[idx] = sum;
+
+	return true;
+}
+
+static unsigned int
+ip6t_snpt_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct ip6t_npt_tginfo *npt = par->targinfo;
+
+	if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->saddr)) {
+		icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD,
+			    offsetof(struct ipv6hdr, saddr));
+		return NF_DROP;
+	}
+	return XT_CONTINUE;
+}
+
+static unsigned int
+ip6t_dnpt_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct ip6t_npt_tginfo *npt = par->targinfo;
+
+	if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->daddr)) {
+		icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD,
+			    offsetof(struct ipv6hdr, daddr));
+		return NF_DROP;
+	}
+	return XT_CONTINUE;
+}
+
+static struct xt_target ip6t_npt_target_reg[] __read_mostly = {
+	{
+		.name		= "SNPT",
+		.target		= ip6t_snpt_tg,
+		.targetsize	= sizeof(struct ip6t_npt_tginfo),
+		.checkentry	= ip6t_npt_checkentry,
+		.family		= NFPROTO_IPV6,
+		.hooks		= (1 << NF_INET_LOCAL_IN) |
+				  (1 << NF_INET_POST_ROUTING),
+		.me		= THIS_MODULE,
+	},
+	{
+		.name		= "DNPT",
+		.target		= ip6t_dnpt_tg,
+		.targetsize	= sizeof(struct ip6t_npt_tginfo),
+		.checkentry	= ip6t_npt_checkentry,
+		.family		= NFPROTO_IPV6,
+		.hooks		= (1 << NF_INET_PRE_ROUTING) |
+				  (1 << NF_INET_LOCAL_OUT),
+		.me		= THIS_MODULE,
+	},
+};
+
+static int __init ip6t_npt_init(void)
+{
+	return xt_register_targets(ip6t_npt_target_reg,
+				   ARRAY_SIZE(ip6t_npt_target_reg));
+}
+
+static void __exit ip6t_npt_exit(void)
+{
+	xt_unregister_targets(ip6t_npt_target_reg,
+			      ARRAY_SIZE(ip6t_npt_target_reg));
+}
+
+module_init(ip6t_npt_init);
+module_exit(ip6t_npt_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv6-to-IPv6 Network Prefix Translation (RFC 6296)");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS("ip6t_SNPT");
+MODULE_ALIAS("ip6t_DNPT");

net/ipv6/netfilter/ip6t_REDIRECT.c

+/*
+ * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on Rusty Russell's IPv4 REDIRECT target. Development of IPv6
+ * NAT funded by Astaro.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter/x_tables.h>
+#include <net/addrconf.h>
+#include <net/netfilter/nf_nat.h>
+
+static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT;
+
+static unsigned int
+redirect_tg6(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct nf_nat_range *range = par->targinfo;
+	struct nf_nat_range newrange;
+	struct in6_addr newdst;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (par->hooknum == NF_INET_LOCAL_OUT)
+		newdst = loopback_addr;
+	else {
+		struct inet6_dev *idev;
+		struct inet6_ifaddr *ifa;
+		bool addr = false;
+
+		rcu_read_lock();
+		idev = __in6_dev_get(skb->dev);
+		if (idev != NULL) {
+			list_for_each_entry(ifa, &idev->addr_list, if_list) {
+				newdst = ifa->addr;
+				addr = true;
+				break;
+			}
+		}
+		rcu_read_unlock();
+
+		if (!addr)
+			return NF_DROP;
+	}
+
+	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.in6	= newdst;
+	newrange.max_addr.in6	= newdst;
+	newrange.min_proto	= range->min_proto;
+	newrange.max_proto	= range->max_proto;
+
+	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
+}
+
+static int redirect_tg6_checkentry(const struct xt_tgchk_param *par)
+{
+	const struct nf_nat_range *range = par->targinfo;
+
+	if (range->flags & NF_NAT_RANGE_MAP_IPS)
+		return -EINVAL;
+	return 0;
+}
+
+static struct xt_target redirect_tg6_reg __read_mostly = {
+	.name		= "REDIRECT",
+	.family		= NFPROTO_IPV6,
+	.checkentry	= redirect_tg6_checkentry,
+	.target		= redirect_tg6,
+	.targetsize	= sizeof(struct nf_nat_range),
+	.table		= "nat",
+	.hooks		= (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT),
+	.me		= THIS_MODULE,
+};
+
+static int __init redirect_tg6_init(void)
+{
+	return xt_register_target(&redirect_tg6_reg);
+}
+
+static void __exit redirect_tg6_exit(void)
+{
+	xt_unregister_target(&redirect_tg6_reg);
+}
+
+module_init(redirect_tg6_init);
+module_exit(redirect_tg6_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_DESCRIPTION("Xtables: Connection redirection to localhost");

net/ipv6/netfilter/ip6table_nat.c

+/*
+ * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on Rusty Russell's IPv4 NAT code. Development of IPv6 NAT
+ * funded by Astaro.
+ */
+
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/ipv6.h>
+#include <net/ipv6.h>
+
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_nat_core.h>
+#include <net/netfilter/nf_nat_l3proto.h>
+
+static const struct xt_table nf_nat_ipv6_table = {
+	.name		= "nat",
+	.valid_hooks	= (1 << NF_INET_PRE_ROUTING) |
+			  (1 << NF_INET_POST_ROUTING) |
+			  (1 << NF_INET_LOCAL_OUT) |
+			  (1 << NF_INET_LOCAL_IN),
+	.me		= THIS_MODULE,
+	.af		= NFPROTO_IPV6,
+};
+
+static unsigned int alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
+{
+	/* Force range to this IP; let proto decide mapping for
+	 * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
+	 */
+	struct nf_nat_range range;
+
+	range.flags = 0;
+	pr_debug("Allocating NULL binding for %p (%pI6)\n", ct,
+		 HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
+		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip6 :
+		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip6);
+
+	return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
+}
+
+static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum,
+				     const struct net_device *in,
+				     const struct net_device *out,
+				     struct nf_conn *ct)
+{
+	struct net *net = nf_ct_net(ct);
+	unsigned int ret;
+
+	ret = ip6t_do_table(skb, hooknum, in, out, net->ipv6.ip6table_nat);
+	if (ret == NF_ACCEPT) {
+		if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum)))
+			ret = alloc_null_binding(ct, hooknum);
+	}
+	return ret;
+}
+
+static unsigned int
+nf_nat_ipv6_fn(unsigned int hooknum,
+	       struct sk_buff *skb,
+	       const struct net_device *in,
+	       const struct net_device *out,
+	       int (*okfn)(struct sk_buff *))
+{
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn_nat *nat;
+	enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum);
+	__be16 frag_off;
+	int hdrlen;
+	u8 nexthdr;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	/* Can't track?  It's not due to stress, or conntrack would
+	 * have dropped it.  Hence it's the user's responsibilty to
+	 * packet filter it out, or implement conntrack/NAT for that
+	 * protocol. 8) --RR
+	 */
+	if (!ct)
+		return NF_ACCEPT;
+
+	/* Don't try to NAT if this packet is not conntracked */
+	if (nf_ct_is_untracked(ct))
+		return NF_ACCEPT;
+
+	nat = nfct_nat(ct);
+	if (!nat) {
+		/* NAT module was loaded late. */
+		if (nf_ct_is_confirmed(ct))
+			return NF_ACCEPT;
+		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
+		if (nat == NULL) {
+			pr_debug("failed to add NAT extension\n");
+			return NF_ACCEPT;
+		}
+	}
+
+	switch (ctinfo) {
+	case IP_CT_RELATED:
+	case IP_CT_RELATED_REPLY:
+		nexthdr = ipv6_hdr(skb)->nexthdr;
+		hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
+					  &nexthdr, &frag_off);
+
+		if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
+			if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo,
+							     hooknum, hdrlen))
+				return NF_DROP;
+			else
+				return NF_ACCEPT;
+		}
+		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
+	case IP_CT_NEW:
+		/* Seen it before?  This can happen for loopback, retrans,
+		 * or local packets.
+		 */
+		if (!nf_nat_initialized(ct, maniptype)) {
+			unsigned int ret;
+
+			ret = nf_nat_rule_find(skb, hooknum, in, out, ct);
+			if (ret != NF_ACCEPT)
+				return ret;
+		} else
+			pr_debug("Already setup manip %s for ct %p\n",
+				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
+				 ct);
+		break;
+
+	default:
+		/* ESTABLISHED */
+		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
+			     ctinfo == IP_CT_ESTABLISHED_REPLY);
+	}
+
+	return nf_nat_packet(ct, ctinfo, hooknum, skb);
+}
+
+static unsigned int
+nf_nat_ipv6_in(unsigned int hooknum,
+	       struct sk_buff *skb,
+	       const struct net_device *in,
+	       const struct net_device *out,
+	       int (*okfn)(struct sk_buff *))
+{
+	unsigned int ret;
+	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
+
+	ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
+		skb_dst_drop(skb);
+
+	return ret;
+}
+
+static unsigned int
+nf_nat_ipv6_out(unsigned int hooknum,
+		struct sk_buff *skb,
+		const struct net_device *in,
+		const struct net_device *out,
+		int (*okfn)(struct sk_buff *))
+{
+#ifdef CONFIG_XFRM
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+#endif
+	unsigned int ret;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct ipv6hdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn);
+#ifdef CONFIG_XFRM
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3,
+				      &ct->tuplehash[!dir].tuple.dst.u3) ||
+		    (ct->tuplehash[dir].tuple.src.u.all !=
+		     ct->tuplehash[!dir].tuple.dst.u.all))
+			if (nf_xfrm_me_harder(skb, AF_INET6) < 0)
+				ret = NF_DROP;
+	}
+#endif
+	return ret;
+}
+
+static unsigned int
+nf_nat_ipv6_local_fn(unsigned int hooknum,
+		     struct sk_buff *skb,
+		     const struct net_device *in,
+		     const struct net_device *out,
+		     int (*okfn)(struct sk_buff *))
+{
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	unsigned int ret;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct ipv6hdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
+				      &ct->tuplehash[!dir].tuple.src.u3)) {
+			if (ip6_route_me_harder(skb))
+				ret = NF_DROP;
+		}
+#ifdef CONFIG_XFRM
+		else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
+			 ct->tuplehash[dir].tuple.dst.u.all !=
+			 ct->tuplehash[!dir].tuple.src.u.all)
+			if (nf_xfrm_me_harder(skb, AF_INET6))
+				ret = NF_DROP;
+#endif
+	}
+	return ret;
+}
+
+static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
+	/* Before packet filtering, change destination */
+	{
+		.hook		= nf_nat_ipv6_in,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_PRE_ROUTING,
+		.priority	= NF_IP6_PRI_NAT_DST,
+	},
+	/* After packet filtering, change source */
+	{
+		.hook		= nf_nat_ipv6_out,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_POST_ROUTING,
+		.priority	= NF_IP6_PRI_NAT_SRC,
+	},
+	/* Before packet filtering, change destination */
+	{
+		.hook		= nf_nat_ipv6_local_fn,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_LOCAL_OUT,
+		.priority	= NF_IP6_PRI_NAT_DST,
+	},
+	/* After packet filtering, change source */
+	{
+		.hook		= nf_nat_ipv6_fn,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_LOCAL_IN,
+		.priority	= NF_IP6_PRI_NAT_SRC,
+	},
+};
+
+static int __net_init ip6table_nat_net_init(struct net *net)
+{
+	struct ip6t_replace *repl;
+
+	repl = ip6t_alloc_initial_table(&nf_nat_ipv6_table);
+	if (repl == NULL)
+		return -ENOMEM;
+	net->ipv6.ip6table_nat = ip6t_register_table(net, &nf_nat_ipv6_table, repl);
+	kfree(repl);
+	if (IS_ERR(net->ipv6.ip6table_nat))
+		return PTR_ERR(net->ipv6.ip6table_nat);
+	return 0;
+}
+
+static void __net_exit ip6table_nat_net_exit(struct net *net)
+{
+	ip6t_unregister_table(net, net->ipv6.ip6table_nat);
+}
+
+static struct pernet_operations ip6table_nat_net_ops = {
+	.init	= ip6table_nat_net_init,
+	.exit	= ip6table_nat_net_exit,
+};
+
+static int __init ip6table_nat_init(void)
+{
+	int err;
+
+	err = register_pernet_subsys(&ip6table_nat_net_ops);
+	if (err < 0)
+		goto err1;
+
+	err = nf_register_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops));
+	if (err < 0)
+		goto err2;
+	return 0;
+
+err2:
+	unregister_pernet_subsys(&ip6table_nat_net_ops);
+err1:
+	return err;
+}
+
+static void __exit ip6table_nat_exit(void)
+{
+	nf_unregister_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops));
+	unregister_pernet_subsys(&ip6table_nat_net_ops);
+}
+
+module_init(ip6table_nat_init);
+module_exit(ip6table_nat_exit);
+
+MODULE_LICENSE("GPL");

net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c

@@ -28,6 +28,7 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
+#include <net/netfilter/nf_nat_helper.h>
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 #include <net/netfilter/nf_log.h>
 
@@ -64,82 +65,31 @@ static int ipv6_print_tuple(struct seq_file *s,
 			  tuple->src.u3.ip6, tuple->dst.u3.ip6);
 }
 
-/*
- * Based on ipv6_skip_exthdr() in net/ipv6/exthdr.c
- *
- * This function parses (probably truncated) exthdr set "hdr"
- * of length "len". "nexthdrp" initially points to some place,
- * where type of the first header can be found.
- *
- * It skips all well-known exthdrs, and returns pointer to the start
- * of unparsable area i.e. the first header with unknown type.
- * if success, *nexthdr is updated by type/protocol of this header.
- *
- * NOTES: - it may return pointer pointing beyond end of packet,
- *          if the last recognized header is truncated in the middle.
- *        - if packet is truncated, so that all parsed headers are skipped,
- *          it returns -1.
- *        - if packet is fragmented, return pointer of the fragment header.
- *        - ESP is unparsable for now and considered like
- *          normal payload protocol.
- *        - Note also special handling of AUTH header. Thanks to IPsec wizards.
- */
-
-static int nf_ct_ipv6_skip_exthdr(const struct sk_buff *skb, int start,
-				  u8 *nexthdrp, int len)
-{
-	u8 nexthdr = *nexthdrp;
-
-	while (ipv6_ext_hdr(nexthdr)) {
-		struct ipv6_opt_hdr hdr;
-		int hdrlen;
-
-		if (len < (int)sizeof(struct ipv6_opt_hdr))
-			return -1;
-		if (nexthdr == NEXTHDR_NONE)
-			break;
-		if (nexthdr == NEXTHDR_FRAGMENT)
-			break;
-		if (skb_copy_bits(skb, start, &hdr, sizeof(hdr)))
-			BUG();
-		if (nexthdr == NEXTHDR_AUTH)
-			hdrlen = (hdr.hdrlen+2)<<2;
-		else
-			hdrlen = ipv6_optlen(&hdr);
-
-		nexthdr = hdr.nexthdr;
-		len -= hdrlen;
-		start += hdrlen;
-	}
-
-	*nexthdrp = nexthdr;
-	return start;
-}
-
 static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 			    unsigned int *dataoff, u_int8_t *protonum)
 {
 	unsigned int extoff = nhoff + sizeof(struct ipv6hdr);
-	unsigned char pnum;
+	__be16 frag_off;
 	int protoff;
+	u8 nexthdr;
 
 	if (skb_copy_bits(skb, nhoff + offsetof(struct ipv6hdr, nexthdr),
-			  &pnum, sizeof(pnum)) != 0) {
+			  &nexthdr, sizeof(nexthdr)) != 0) {
 		pr_debug("ip6_conntrack_core: can't get nexthdr\n");
 		return -NF_ACCEPT;
 	}
-	protoff = nf_ct_ipv6_skip_exthdr(skb, extoff, &pnum, skb->len - extoff);
+	protoff = ipv6_skip_exthdr(skb, extoff, &nexthdr, &frag_off);
 	/*
 	 * (protoff == skb->len) mean that the packet doesn't have no data
 	 * except of IPv6 & ext headers. but it's tracked anyway. - YK
 	 */
-	if ((protoff < 0) || (protoff > skb->len)) {
+	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
 		pr_debug("ip6_conntrack_core: can't find proto in pkt\n");
 		return -NF_ACCEPT;
 	}
 
 	*dataoff = protoff;
-	*protonum = pnum;
+	*protonum = nexthdr;
 	return NF_ACCEPT;
 }
 
@@ -153,10 +103,10 @@ static unsigned int ipv6_helper(unsigned int hooknum,
 	const struct nf_conn_help *help;
 	const struct nf_conntrack_helper *helper;
 	enum ip_conntrack_info ctinfo;
-	unsigned int ret, protoff;
-	unsigned int extoff = (u8 *)(ipv6_hdr(skb) + 1) - skb->data;
-	unsigned char pnum = ipv6_hdr(skb)->nexthdr;
-
+	unsigned int ret;
+	__be16 frag_off;
+	int protoff;
+	u8 nexthdr;
 
 	/* This is where we call the helper: as the packet goes out. */
 	ct = nf_ct_get(skb, &ctinfo);
@@ -171,9 +121,10 @@ static unsigned int ipv6_helper(unsigned int hooknum,
 	if (!helper)
 		return NF_ACCEPT;
 
-	protoff = nf_ct_ipv6_skip_exthdr(skb, extoff, &pnum,
-					 skb->len - extoff);
-	if (protoff > skb->len || pnum == NEXTHDR_FRAGMENT) {
+	nexthdr = ipv6_hdr(skb)->nexthdr;
+	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
+				   &frag_off);
+	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
 		pr_debug("proto header not found\n");
 		return NF_ACCEPT;
 	}
@@ -192,6 +143,36 @@ static unsigned int ipv6_confirm(unsigned int hooknum,
 				 const struct net_device *out,
 				 int (*okfn)(struct sk_buff *))
 {
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	unsigned char pnum = ipv6_hdr(skb)->nexthdr;
+	int protoff;
+	__be16 frag_off;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
+		goto out;
+
+	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum,
+				   &frag_off);
+	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
+		pr_debug("proto header not found\n");
+		goto out;
+	}
+
+	/* adjust seqs for loopback traffic only in outgoing direction */
+	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
+	    !nf_is_loopback_packet(skb)) {
+		typeof(nf_nat_seq_adjust_hook) seq_adjust;
+
+		seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook);
+		if (!seq_adjust ||
+		    !seq_adjust(skb, ct, ctinfo, protoff)) {
+			NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
+			return NF_DROP;
+		}
+	}
+out:
 	/* We've seen it coming out the other side: confirm it */
 	return nf_conntrack_confirm(skb);
 }
@@ -199,9 +180,14 @@ static unsigned int ipv6_confirm(unsigned int hooknum,
 static unsigned int __ipv6_conntrack_in(struct net *net,
 					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;
+	const struct nf_conn_help *help;
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
 
 	/* This packet is fragmented and has reassembled packet. */
 	if (reasm) {
@@ -213,6 +199,25 @@ static unsigned int __ipv6_conntrack_in(struct net *net,
 			if (ret != NF_ACCEPT)
 				return ret;
 		}
+
+		/* Conntrack helpers need the entire reassembled packet in the
+		 * POST_ROUTING hook. In case of unconfirmed connections NAT
+		 * might reassign a helper, so the entire packet is also
+		 * required.
+		 */
+		ct = nf_ct_get(reasm, &ctinfo);
+		if (ct != NULL && !nf_ct_is_untracked(ct)) {
+			help = nfct_help(ct);
+			if ((help && help->helper) || !nf_ct_is_confirmed(ct)) {
+				nf_conntrack_get_reasm(skb);
+				NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm,
+					       (struct net_device *)in,
+					       (struct net_device *)out,
+					       okfn, NF_IP6_PRI_CONNTRACK + 1);
+				return NF_DROP_ERR(-ECANCELED);
+			}
+		}
+
 		nf_conntrack_get(reasm->nfct);
 		skb->nfct = reasm->nfct;
 		skb->nfctinfo = reasm->nfctinfo;
@@ -228,7 +233,7 @@ static unsigned int ipv6_conntrack_in(unsigned int hooknum,
 				      const struct net_device *out,
 				      int (*okfn)(struct sk_buff *))
 {
-	return __ipv6_conntrack_in(dev_net(in), hooknum, skb, okfn);
+	return __ipv6_conntrack_in(dev_net(in), hooknum, skb, in, out, okfn);
 }
 
 static unsigned int ipv6_conntrack_local(unsigned int hooknum,
@@ -242,7 +247,7 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum,
 		net_notice_ratelimited("ipv6_conntrack_local: packet too short\n");
 		return NF_ACCEPT;
 	}
-	return __ipv6_conntrack_in(dev_net(out), hooknum, skb, okfn);
+	return __ipv6_conntrack_in(dev_net(out), hooknum, skb, in, out, okfn);
 }
 
 static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = {

net/ipv6/netfilter/nf_conntrack_reasm.c

@@ -190,6 +190,7 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb,
 			     const struct frag_hdr *fhdr, int nhoff)
 {
 	struct sk_buff *prev, *next;
+	unsigned int payload_len;
 	int offset, end;
 
 	if (fq->q.last_in & INET_FRAG_COMPLETE) {
@@ -197,8 +198,10 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb,
 		goto err;
 	}
 
+	payload_len = ntohs(ipv6_hdr(skb)->payload_len);
+
 	offset = ntohs(fhdr->frag_off) & ~0x7;
-	end = offset + (ntohs(ipv6_hdr(skb)->payload_len) -
+	end = offset + (payload_len -
 			((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));
 
 	if ((unsigned int)end > IPV6_MAXPLEN) {
@@ -307,6 +310,8 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb,
 	skb->dev = NULL;
 	fq->q.stamp = skb->tstamp;
 	fq->q.meat += skb->len;
+	if (payload_len > fq->q.max_size)
+		fq->q.max_size = payload_len;
 	atomic_add(skb->truesize, &nf_init_frags.mem);
 
 	/* The first fragment.
@@ -412,10 +417,12 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev)
 	}
 	atomic_sub(head->truesize, &nf_init_frags.mem);
 
+	head->local_df = 1;
 	head->next = NULL;
 	head->dev = dev;
 	head->tstamp = fq->q.stamp;
 	ipv6_hdr(head)->payload_len = htons(payload_len);
+	IP6CB(head)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size;
 
 	/* Yes, and fold redundant checksum back. 8) */
 	if (head->ip_summed == CHECKSUM_COMPLETE)
@@ -592,6 +599,7 @@ void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
 			int (*okfn)(struct sk_buff *))
 {
 	struct sk_buff *s, *s2;
+	unsigned int ret = 0;
 
 	for (s = NFCT_FRAG6_CB(skb)->orig; s;) {
 		nf_conntrack_put_reasm(s->nfct_reasm);
@@ -601,8 +609,13 @@ void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
 		s2 = s->next;
 		s->next = NULL;
 
-		NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s, in, out, okfn,
-			       NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
+		if (ret != -ECANCELED)
+			ret = NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s,
+					     in, out, okfn,
+					     NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
+		else
+			kfree_skb(s);
+
 		s = s2;
 	}
 	nf_conntrack_put_reasm(skb);

net/ipv6/netfilter/nf_nat_l3proto_ipv6.c

+/*
+ * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of IPv6 NAT funded by Astaro.
+ */
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <net/secure_seq.h>
+#include <net/checksum.h>
+#include <net/ip6_route.h>
+#include <net/ipv6.h>
+
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_nat_core.h>
+#include <net/netfilter/nf_nat_l3proto.h>
+#include <net/netfilter/nf_nat_l4proto.h>
+
+static const struct nf_nat_l3proto nf_nat_l3proto_ipv6;
+
+#ifdef CONFIG_XFRM
+static void nf_nat_ipv6_decode_session(struct sk_buff *skb,
+				       const struct nf_conn *ct,
+				       enum ip_conntrack_dir dir,
+				       unsigned long statusbit,
+				       struct flowi *fl)
+{
+	const struct nf_conntrack_tuple *t = &ct->tuplehash[dir].tuple;
+	struct flowi6 *fl6 = &fl->u.ip6;
+
+	if (ct->status & statusbit) {
+		fl6->daddr = t->dst.u3.in6;
+		if (t->dst.protonum == IPPROTO_TCP ||
+		    t->dst.protonum == IPPROTO_UDP ||
+		    t->dst.protonum == IPPROTO_UDPLITE ||
+		    t->dst.protonum == IPPROTO_DCCP ||
+		    t->dst.protonum == IPPROTO_SCTP)
+			fl6->fl6_dport = t->dst.u.all;
+	}
+
+	statusbit ^= IPS_NAT_MASK;
+
+	if (ct->status & statusbit) {
+		fl6->saddr = t->src.u3.in6;
+		if (t->dst.protonum == IPPROTO_TCP ||
+		    t->dst.protonum == IPPROTO_UDP ||
+		    t->dst.protonum == IPPROTO_UDPLITE ||
+		    t->dst.protonum == IPPROTO_DCCP ||
+		    t->dst.protonum == IPPROTO_SCTP)
+			fl6->fl6_sport = t->src.u.all;
+	}
+}
+#endif
+
+static bool nf_nat_ipv6_in_range(const struct nf_conntrack_tuple *t,
+				 const struct nf_nat_range *range)
+{
+	return ipv6_addr_cmp(&t->src.u3.in6, &range->min_addr.in6) >= 0 &&
+	       ipv6_addr_cmp(&t->src.u3.in6, &range->max_addr.in6) <= 0;
+}
+
+static u32 nf_nat_ipv6_secure_port(const struct nf_conntrack_tuple *t,
+				   __be16 dport)
+{
+	return secure_ipv6_port_ephemeral(t->src.u3.ip6, t->dst.u3.ip6, dport);
+}
+
+static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb,
+				  unsigned int iphdroff,
+				  const struct nf_nat_l4proto *l4proto,
+				  const struct nf_conntrack_tuple *target,
+				  enum nf_nat_manip_type maniptype)
+{
+	struct ipv6hdr *ipv6h;
+	__be16 frag_off;
+	int hdroff;
+	u8 nexthdr;
+
+	if (!skb_make_writable(skb, iphdroff + sizeof(*ipv6h)))
+		return false;
+
+	ipv6h = (void *)skb->data + iphdroff;
+	nexthdr = ipv6h->nexthdr;
+	hdroff = ipv6_skip_exthdr(skb, iphdroff + sizeof(*ipv6h),
+				  &nexthdr, &frag_off);
+	if (hdroff < 0)
+		goto manip_addr;
+
+	if ((frag_off & htons(~0x7)) == 0 &&
+	    !l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff,
+				target, maniptype))
+		return false;
+manip_addr:
+	if (maniptype == NF_NAT_MANIP_SRC)
+		ipv6h->saddr = target->src.u3.in6;
+	else
+		ipv6h->daddr = target->dst.u3.in6;
+
+	return true;
+}
+
+static void nf_nat_ipv6_csum_update(struct sk_buff *skb,
+				    unsigned int iphdroff, __sum16 *check,
+				    const struct nf_conntrack_tuple *t,
+				    enum nf_nat_manip_type maniptype)
+{
+	const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + iphdroff);
+	const struct in6_addr *oldip, *newip;
+
+	if (maniptype == NF_NAT_MANIP_SRC) {
+		oldip = &ipv6h->saddr;
+		newip = &t->src.u3.in6;
+	} else {
+		oldip = &ipv6h->daddr;
+		newip = &t->dst.u3.in6;
+	}
+	inet_proto_csum_replace16(check, skb, oldip->s6_addr32,
+				  newip->s6_addr32, 1);
+}
+
+static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb,
+				    u8 proto, void *data, __sum16 *check,
+				    int datalen, int oldlen)
+{
+	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL) {
+		if (!(rt->rt6i_flags & RTF_LOCAL) &&
+		    (!skb->dev || skb->dev->features & NETIF_F_V6_CSUM)) {
+			skb->ip_summed = CHECKSUM_PARTIAL;
+			skb->csum_start = skb_headroom(skb) +
+					  skb_network_offset(skb) +
+					  (data - (void *)skb->data);
+			skb->csum_offset = (void *)check - data;
+			*check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
+						  datalen, proto, 0);
+		} else {
+			*check = 0;
+			*check = csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
+						 datalen, proto,
+						 csum_partial(data, datalen,
+							      0));
+			if (proto == IPPROTO_UDP && !*check)
+				*check = CSUM_MANGLED_0;
+		}
+	} else
+		inet_proto_csum_replace2(check, skb,
+					 htons(oldlen), htons(datalen), 1);
+}
+
+static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[],
+				       struct nf_nat_range *range)
+{
+	if (tb[CTA_NAT_V6_MINIP]) {
+		nla_memcpy(&range->min_addr.ip6, tb[CTA_NAT_V6_MINIP],
+			   sizeof(struct in6_addr));
+		range->flags |= NF_NAT_RANGE_MAP_IPS;
+	}
+
+	if (tb[CTA_NAT_V6_MAXIP])
+		nla_memcpy(&range->max_addr.ip6, tb[CTA_NAT_V6_MAXIP],
+			   sizeof(struct in6_addr));
+	else
+		range->max_addr = range->min_addr;
+
+	return 0;
+}
+
+static const struct nf_nat_l3proto nf_nat_l3proto_ipv6 = {
+	.l3proto		= NFPROTO_IPV6,
+	.secure_port		= nf_nat_ipv6_secure_port,
+	.in_range		= nf_nat_ipv6_in_range,
+	.manip_pkt		= nf_nat_ipv6_manip_pkt,
+	.csum_update		= nf_nat_ipv6_csum_update,
+	.csum_recalc		= nf_nat_ipv6_csum_recalc,
+	.nlattr_to_range	= nf_nat_ipv6_nlattr_to_range,
+#ifdef CONFIG_XFRM
+	.decode_session	= nf_nat_ipv6_decode_session,
+#endif
+};
+
+int nf_nat_icmpv6_reply_translation(struct sk_buff *skb,
+				    struct nf_conn *ct,
+				    enum ip_conntrack_info ctinfo,
+				    unsigned int hooknum,
+				    unsigned int hdrlen)
+{
+	struct {
+		struct icmp6hdr	icmp6;
+		struct ipv6hdr	ip6;
+	} *inside;
+	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+	enum nf_nat_manip_type manip = HOOK2MANIP(hooknum);
+	const struct nf_nat_l4proto *l4proto;
+	struct nf_conntrack_tuple target;
+	unsigned long statusbit;
+
+	NF_CT_ASSERT(ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY);
+
+	if (!skb_make_writable(skb, hdrlen + sizeof(*inside)))
+		return 0;
+	if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6))
+		return 0;
+
+	inside = (void *)skb->data + hdrlen;
+	if (inside->icmp6.icmp6_type == NDISC_REDIRECT) {
+		if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK)
+			return 0;
+		if (ct->status & IPS_NAT_MASK)
+			return 0;
+	}
+
+	if (manip == NF_NAT_MANIP_SRC)
+		statusbit = IPS_SRC_NAT;
+	else
+		statusbit = IPS_DST_NAT;
+
+	/* Invert if this is reply direction */
+	if (dir == IP_CT_DIR_REPLY)
+		statusbit ^= IPS_NAT_MASK;
+
+	if (!(ct->status & statusbit))
+		return 1;
+
+	l4proto = __nf_nat_l4proto_find(NFPROTO_IPV6, inside->ip6.nexthdr);
+	if (!nf_nat_ipv6_manip_pkt(skb, hdrlen + sizeof(inside->icmp6),
+				   l4proto, &ct->tuplehash[!dir].tuple, !manip))
+		return 0;
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL) {
+		struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+		inside = (void *)skb->data + hdrlen;
+		inside->icmp6.icmp6_cksum = 0;
+		inside->icmp6.icmp6_cksum =
+			csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
+					skb->len - hdrlen, IPPROTO_ICMPV6,
+					csum_partial(&inside->icmp6,
+						     skb->len - hdrlen, 0));
+	}
+
+	nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
+	l4proto = __nf_nat_l4proto_find(NFPROTO_IPV6, IPPROTO_ICMPV6);
+	if (!nf_nat_ipv6_manip_pkt(skb, 0, l4proto, &target, manip))
+		return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation);
+
+static int __init nf_nat_l3proto_ipv6_init(void)
+{
+	int err;
+
+	err = nf_nat_l4proto_register(NFPROTO_IPV6, &nf_nat_l4proto_icmpv6);
+	if (err < 0)
+		goto err1;
+	err = nf_nat_l3proto_register(&nf_nat_l3proto_ipv6);
+	if (err < 0)
+		goto err2;
+	return err;
+
+err2:
+	nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_icmpv6);
+err1:
+	return err;
+}
+
+static void __exit nf_nat_l3proto_ipv6_exit(void)
+{
+	nf_nat_l3proto_unregister(&nf_nat_l3proto_ipv6);
+	nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_icmpv6);
+}
+
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("nf-nat-" __stringify(AF_INET6));
+
+module_init(nf_nat_l3proto_ipv6_init);
+module_exit(nf_nat_l3proto_ipv6_exit);

net/ipv6/netfilter/nf_nat_proto_icmpv6.c

+/*
+ * Copyright (c) 2011 Patrick Mchardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on Rusty Russell's IPv4 ICMP NAT code. Development of IPv6
+ * NAT funded by Astaro.
+ */
+
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/icmpv6.h>
+
+#include <linux/netfilter.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_nat_core.h>
+#include <net/netfilter/nf_nat_l3proto.h>
+#include <net/netfilter/nf_nat_l4proto.h>
+
+static bool
+icmpv6_in_range(const struct nf_conntrack_tuple *tuple,
+		enum nf_nat_manip_type maniptype,
+		const union nf_conntrack_man_proto *min,
+		const union nf_conntrack_man_proto *max)
+{
+	return ntohs(tuple->src.u.icmp.id) >= ntohs(min->icmp.id) &&
+	       ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id);
+}
+
+static void
+icmpv6_unique_tuple(const struct nf_nat_l3proto *l3proto,
+		    struct nf_conntrack_tuple *tuple,
+		    const struct nf_nat_range *range,
+		    enum nf_nat_manip_type maniptype,
+		    const struct nf_conn *ct)
+{
+	static u16 id;
+	unsigned int range_size;
+	unsigned int i;
+
+	range_size = ntohs(range->max_proto.icmp.id) -
+		     ntohs(range->min_proto.icmp.id) + 1;
+
+	if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED))
+		range_size = 0xffff;
+
+	for (i = 0; ; ++id) {
+		tuple->src.u.icmp.id = htons(ntohs(range->min_proto.icmp.id) +
+					     (id % range_size));
+		if (++i == range_size || !nf_nat_used_tuple(tuple, ct))
+			return;
+	}
+}
+
+static bool
+icmpv6_manip_pkt(struct sk_buff *skb,
+		 const struct nf_nat_l3proto *l3proto,
+		 unsigned int iphdroff, unsigned int hdroff,
+		 const struct nf_conntrack_tuple *tuple,
+		 enum nf_nat_manip_type maniptype)
+{
+	struct icmp6hdr *hdr;
+
+	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
+		return false;
+
+	hdr = (struct icmp6hdr *)(skb->data + hdroff);
+	l3proto->csum_update(skb, iphdroff, &hdr->icmp6_cksum,
+			     tuple, maniptype);
+	if (hdr->icmp6_code == ICMPV6_ECHO_REQUEST ||
+	    hdr->icmp6_code == ICMPV6_ECHO_REPLY) {
+		inet_proto_csum_replace2(&hdr->icmp6_cksum, skb,
+					 hdr->icmp6_identifier,
+					 tuple->src.u.icmp.id, 0);
+		hdr->icmp6_identifier = tuple->src.u.icmp.id;
+	}
+	return true;
+}
+
+const struct nf_nat_l4proto nf_nat_l4proto_icmpv6 = {
+	.l4proto		= IPPROTO_ICMPV6,
+	.manip_pkt		= icmpv6_manip_pkt,
+	.in_range		= icmpv6_in_range,
+	.unique_tuple		= icmpv6_unique_tuple,
+#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
+#endif
+};

net/netfilter/Kconfig

@@ -356,6 +356,55 @@ config NETFILTER_NETLINK_QUEUE_CT
 	  If this option is enabled, NFQUEUE can include Connection Tracking
 	  information together with the packet is the enqueued via NFNETLINK.
 
+config NF_NAT
+	tristate
+
+config NF_NAT_NEEDED
+	bool
+	depends on NF_NAT
+	default y
+
+config NF_NAT_PROTO_DCCP
+	tristate
+	depends on NF_NAT && NF_CT_PROTO_DCCP
+	default NF_NAT && NF_CT_PROTO_DCCP
+
+config NF_NAT_PROTO_UDPLITE
+	tristate
+	depends on NF_NAT && NF_CT_PROTO_UDPLITE
+	default NF_NAT && NF_CT_PROTO_UDPLITE
+
+config NF_NAT_PROTO_SCTP
+	tristate
+	default NF_NAT && NF_CT_PROTO_SCTP
+	depends on NF_NAT && NF_CT_PROTO_SCTP
+	select LIBCRC32C
+
+config NF_NAT_AMANDA
+	tristate
+	depends on NF_CONNTRACK && NF_NAT
+	default NF_NAT && NF_CONNTRACK_AMANDA
+
+config NF_NAT_FTP
+	tristate
+	depends on NF_CONNTRACK && NF_NAT
+	default NF_NAT && NF_CONNTRACK_FTP
+
+config NF_NAT_IRC
+	tristate
+	depends on NF_CONNTRACK && NF_NAT
+	default NF_NAT && NF_CONNTRACK_IRC
+
+config NF_NAT_SIP
+	tristate
+	depends on NF_CONNTRACK && NF_NAT
+	default NF_NAT && NF_CONNTRACK_SIP
+
+config NF_NAT_TFTP
+	tristate
+	depends on NF_CONNTRACK && NF_NAT
+	default NF_NAT && NF_CONNTRACK_TFTP
+
 endif # NF_CONNTRACK
 
 # transparent proxy support
@@ -621,19 +670,6 @@ config NETFILTER_XT_TARGET_NFQUEUE
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
-config NETFILTER_XT_TARGET_NOTRACK
-	tristate  '"NOTRACK" target support'
-	depends on IP_NF_RAW || IP6_NF_RAW
-	depends on NF_CONNTRACK
-	help
-	  The NOTRACK target allows a select rule to specify
-	  which packets *not* to enter the conntrack/NAT
-	  subsystem with all the consequences (no ICMP error tracking,
-	  no protocol helpers for the selected packets).
-
-	  If you want to compile it as a module, say M here and read
-	  <file:Documentation/kbuild/modules.txt>.  If unsure, say `N'.
-
 config NETFILTER_XT_TARGET_RATEEST
 	tristate '"RATEEST" target support'
 	depends on NETFILTER_ADVANCED

net/netfilter/Makefile

@@ -43,6 +43,24 @@ obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o
 obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o
 obj-$(CONFIG_NF_CONNTRACK_TFTP) += nf_conntrack_tftp.o
 
+nf_nat-y	:= nf_nat_core.o nf_nat_proto_unknown.o nf_nat_proto_common.o \
+		   nf_nat_proto_udp.o nf_nat_proto_tcp.o nf_nat_helper.o
+
+obj-$(CONFIG_NF_NAT) += nf_nat.o
+obj-$(CONFIG_NF_NAT) += xt_nat.o
+
+# NAT protocols (nf_nat)
+obj-$(CONFIG_NF_NAT_PROTO_DCCP) += nf_nat_proto_dccp.o
+obj-$(CONFIG_NF_NAT_PROTO_UDPLITE) += nf_nat_proto_udplite.o
+obj-$(CONFIG_NF_NAT_PROTO_SCTP) += nf_nat_proto_sctp.o
+
+# NAT helpers
+obj-$(CONFIG_NF_NAT_AMANDA) += nf_nat_amanda.o
+obj-$(CONFIG_NF_NAT_FTP) += nf_nat_ftp.o
+obj-$(CONFIG_NF_NAT_IRC) += nf_nat_irc.o
+obj-$(CONFIG_NF_NAT_SIP) += nf_nat_sip.o
+obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o
+
 # transparent proxy support
 obj-$(CONFIG_NETFILTER_TPROXY) += nf_tproxy_core.o
 
@@ -67,7 +85,6 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_LED) += xt_LED.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_LOG) += xt_LOG.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_NFLOG) += xt_NFLOG.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o
-obj-$(CONFIG_NETFILTER_XT_TARGET_NOTRACK) += xt_NOTRACK.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_RATEEST) += xt_RATEEST.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_SECMARK) += xt_SECMARK.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_TPROXY) += xt_TPROXY.o

net/netfilter/core.c

@@ -126,42 +126,38 @@ unsigned int nf_iterate(struct list_head *head,
 			unsigned int hook,
 			const struct net_device *indev,
 			const struct net_device *outdev,
-			struct list_head **i,
+			struct nf_hook_ops **elemp,
 			int (*okfn)(struct sk_buff *),
 			int hook_thresh)
 {
 	unsigned int verdict;
-	struct nf_hook_ops *elem = list_entry_rcu(*i, struct nf_hook_ops, list);
 
 	/*
 	 * The caller must not block between calls to this
 	 * function because of risk of continuing from deleted element.
 	 */
-	list_for_each_entry_continue_rcu(elem, head, list) {
-		if (hook_thresh > elem->priority)
+	list_for_each_entry_continue_rcu((*elemp), head, list) {
+		if (hook_thresh > (*elemp)->priority)
 			continue;
 
 		/* Optimization: we don't need to hold module
 		   reference here, since function can't sleep. --RR */
 repeat:
-		verdict = elem->hook(hook, skb, indev, outdev, okfn);
+		verdict = (*elemp)->hook(hook, skb, indev, outdev, okfn);
 		if (verdict != NF_ACCEPT) {
 #ifdef CONFIG_NETFILTER_DEBUG
 			if (unlikely((verdict & NF_VERDICT_MASK)
 							> NF_MAX_VERDICT)) {
 				NFDEBUG("Evil return from %p(%u).\n",
-					elem->hook, hook);
+					(*elemp)->hook, hook);
 				continue;
 			}
 #endif
-			if (verdict != NF_REPEAT) {
-				*i = &elem->list;
+			if (verdict != NF_REPEAT)
 				return verdict;
-			}
 			goto repeat;
 		}
 	}
-	*i = &elem->list;
 	return NF_ACCEPT;
 }
 
@@ -174,14 +170,14 @@ int nf_hook_slow(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
 		 int (*okfn)(struct sk_buff *),
 		 int hook_thresh)
 {
-	struct list_head *elem;
+	struct nf_hook_ops *elem;
 	unsigned int verdict;
 	int ret = 0;
 
 	/* We may already have this, but read-locks nest anyway */
 	rcu_read_lock();
 
-	elem = &nf_hooks[pf][hook];
+	elem = list_entry_rcu(&nf_hooks[pf][hook], struct nf_hook_ops, list);
 next_hook:
 	verdict = nf_iterate(&nf_hooks[pf][hook], skb, hook, indev,
 			     outdev, &elem, okfn, hook_thresh);
@@ -275,6 +271,11 @@ EXPORT_SYMBOL_GPL(nfq_ct_nat_hook);
 
 #endif /* CONFIG_NF_CONNTRACK */
 
+#ifdef CONFIG_NF_NAT_NEEDED
+void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *);
+EXPORT_SYMBOL(nf_nat_decode_session_hook);
+#endif
+
 #ifdef CONFIG_PROC_FS
 struct proc_dir_entry *proc_net_netfilter;
 EXPORT_SYMBOL(proc_net_netfilter);

net/netfilter/ipvs/ip_vs_ftp.c

@@ -268,6 +268,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 			 * packet.
 			 */
 			ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
+						       iph->ihl * 4,
 						       start-data, end-start,
 						       buf, buf_len);
 			if (ret) {

net/netfilter/ipvs/ip_vs_xmit.c

@@ -85,6 +85,22 @@ __ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos)
 	return dst;
 }
 
+static inline bool
+__mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu)
+{
+	if (IP6CB(skb)->frag_max_size) {
+		/* frag_max_size tell us that, this packet have been
+		 * defragmented by netfilter IPv6 conntrack module.
+		 */
+		if (IP6CB(skb)->frag_max_size > mtu)
+			return true; /* largest fragment violate MTU */
+	}
+	else if (skb->len > mtu && !skb_is_gso(skb)) {
+		return true; /* Packet size violate MTU size */
+	}
+	return false;
+}
+
 /* Get route to daddr, update *saddr, optionally bind route to saddr */
 static struct rtable *do_output_route4(struct net *net, __be32 daddr,
 				       u32 rtos, int rt_mode, __be32 *saddr)
@@ -491,7 +507,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if (skb->len > mtu && !skb_is_gso(skb)) {
+	if (__mtu_check_toobig_v6(skb, mtu)) {
 		if (!skb->dev) {
 			struct net *net = dev_net(skb_dst(skb)->dev);
 
@@ -712,7 +728,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if (skb->len > mtu && !skb_is_gso(skb)) {
+	if (__mtu_check_toobig_v6(skb, mtu)) {
 		if (!skb->dev) {
 			struct net *net = dev_net(skb_dst(skb)->dev);
 
@@ -946,8 +962,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	if (skb_dst(skb))
 		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
-	if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) &&
-	    !skb_is_gso(skb)) {
+	/* MTU checking: Notice that 'mtu' have been adjusted before hand */
+	if (__mtu_check_toobig_v6(skb, mtu)) {
 		if (!skb->dev) {
 			struct net *net = dev_net(skb_dst(skb)->dev);
 
@@ -1113,7 +1129,7 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if (skb->len > mtu) {
+	if (__mtu_check_toobig_v6(skb, mtu)) {
 		if (!skb->dev) {
 			struct net *net = dev_net(skb_dst(skb)->dev);
 
@@ -1349,7 +1365,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if (skb->len > mtu && !skb_is_gso(skb)) {
+	if (__mtu_check_toobig_v6(skb, mtu)) {
 		if (!skb->dev) {
 			struct net *net = dev_net(skb_dst(skb)->dev);
 

net/netfilter/nf_conntrack_amanda.c

@@ -40,6 +40,7 @@ MODULE_PARM_DESC(ts_algo, "textsearch algorithm to use (default kmp)");
 
 unsigned int (*nf_nat_amanda_hook)(struct sk_buff *skb,
 				   enum ip_conntrack_info ctinfo,
+				   unsigned int protoff,
 				   unsigned int matchoff,
 				   unsigned int matchlen,
 				   struct nf_conntrack_expect *exp)
@@ -155,8 +156,8 @@ static int amanda_help(struct sk_buff *skb,
 
 		nf_nat_amanda = rcu_dereference(nf_nat_amanda_hook);
 		if (nf_nat_amanda && ct->status & IPS_NAT_MASK)
-			ret = nf_nat_amanda(skb, ctinfo, off - dataoff,
-					    len, exp);
+			ret = nf_nat_amanda(skb, ctinfo, protoff,
+					    off - dataoff, len, exp);
 		else if (nf_ct_expect_related(exp) != 0)
 			ret = NF_DROP;
 		nf_ct_expect_put(exp);

net/netfilter/nf_conntrack_core.c

@@ -55,6 +55,12 @@ int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct,
 				      const struct nlattr *attr) __read_mostly;
 EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook);
 
+int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb,
+			      struct nf_conn *ct,
+			      enum ip_conntrack_info ctinfo,
+			      unsigned int protoff);
+EXPORT_SYMBOL_GPL(nf_nat_seq_adjust_hook);
+
 DEFINE_SPINLOCK(nf_conntrack_lock);
 EXPORT_SYMBOL_GPL(nf_conntrack_lock);
 
@@ -930,7 +936,6 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 	enum ip_conntrack_info ctinfo;
 	struct nf_conntrack_l3proto *l3proto;
 	struct nf_conntrack_l4proto *l4proto;
-	struct nf_conn_timeout *timeout_ext;
 	unsigned int *timeouts;
 	unsigned int dataoff;
 	u_int8_t protonum;
@@ -997,11 +1002,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 	NF_CT_ASSERT(skb->nfct);
 
 	/* Decide what timeout policy we want to apply to this flow. */
-	timeout_ext = nf_ct_timeout_find(ct);
-	if (timeout_ext)
-		timeouts = NF_CT_TIMEOUT_EXT_DATA(timeout_ext);
-	else
-		timeouts = l4proto->get_timeouts(net);
+	timeouts = nf_ct_timeout_lookup(net, ct, l4proto);
 
 	ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, hooknum, timeouts);
 	if (ret <= 0) {

net/netfilter/nf_conntrack_ftp.c

@@ -48,6 +48,7 @@ module_param(loose, bool, 0600);
 unsigned int (*nf_nat_ftp_hook)(struct sk_buff *skb,
 				enum ip_conntrack_info ctinfo,
 				enum nf_ct_ftp_type type,
+				unsigned int protoff,
 				unsigned int matchoff,
 				unsigned int matchlen,
 				struct nf_conntrack_expect *exp);
@@ -489,7 +490,7 @@ static int help(struct sk_buff *skb,
 	nf_nat_ftp = rcu_dereference(nf_nat_ftp_hook);
 	if (nf_nat_ftp && ct->status & IPS_NAT_MASK)
 		ret = nf_nat_ftp(skb, ctinfo, search[dir][i].ftptype,
-				 matchoff, matchlen, exp);
+				 protoff, matchoff, matchlen, exp);
 	else {
 		/* Can't expect this?  Best to drop packet now. */
 		if (nf_ct_expect_related(exp) != 0)

net/netfilter/nf_conntrack_irc.c

@@ -33,6 +33,7 @@ static DEFINE_SPINLOCK(irc_buffer_lock);
 
 unsigned int (*nf_nat_irc_hook)(struct sk_buff *skb,
 				enum ip_conntrack_info ctinfo,
+				unsigned int protoff,
 				unsigned int matchoff,
 				unsigned int matchlen,
 				struct nf_conntrack_expect *exp) __read_mostly;
@@ -205,7 +206,7 @@ static int help(struct sk_buff *skb, unsigned int protoff,
 
 			nf_nat_irc = rcu_dereference(nf_nat_irc_hook);
 			if (nf_nat_irc && ct->status & IPS_NAT_MASK)
-				ret = nf_nat_irc(skb, ctinfo,
+				ret = nf_nat_irc(skb, ctinfo, protoff,
 						 addr_beg_p - ib_ptr,
 						 addr_end_p - addr_beg_p,
 						 exp);

net/netfilter/nf_conntrack_netlink.c

@@ -45,7 +45,7 @@
 #include <net/netfilter/nf_conntrack_timestamp.h>
 #ifdef CONFIG_NF_NAT_NEEDED
 #include <net/netfilter/nf_nat_core.h>
-#include <net/netfilter/nf_nat_protocol.h>
+#include <net/netfilter/nf_nat_l4proto.h>
 #include <net/netfilter/nf_nat_helper.h>
 #endif
 
@@ -1096,13 +1096,14 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct,
 			  const struct nlattr *attr)
 {
 	typeof(nfnetlink_parse_nat_setup_hook) parse_nat_setup;
+	int err;
 
 	parse_nat_setup = rcu_dereference(nfnetlink_parse_nat_setup_hook);
 	if (!parse_nat_setup) {
 #ifdef CONFIG_MODULES
 		rcu_read_unlock();
 		nfnl_unlock();
-		if (request_module("nf-nat-ipv4") < 0) {
+		if (request_module("nf-nat") < 0) {
 			nfnl_lock();
 			rcu_read_lock();
 			return -EOPNOTSUPP;
@@ -1115,7 +1116,26 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct,
 		return -EOPNOTSUPP;
 	}
 
-	return parse_nat_setup(ct, manip, attr);
+	err = parse_nat_setup(ct, manip, attr);
+	if (err == -EAGAIN) {
+#ifdef CONFIG_MODULES
+		rcu_read_unlock();
+		spin_unlock_bh(&nf_conntrack_lock);
+		nfnl_unlock();
+		if (request_module("nf-nat-%u", nf_ct_l3num(ct)) < 0) {
+			nfnl_lock();
+			spin_lock_bh(&nf_conntrack_lock);
+			rcu_read_lock();
+			return -EOPNOTSUPP;
+		}
+		nfnl_lock();
+		spin_lock_bh(&nf_conntrack_lock);
+		rcu_read_lock();
+#else
+		err = -EOPNOTSUPP;
+#endif
+	}
+	return err;
 }
 #endif
 
@@ -1979,6 +1999,8 @@ ctnetlink_exp_dump_mask(struct sk_buff *skb,
 	return -1;
 }
 
+static const union nf_inet_addr any_addr;
+
 static int
 ctnetlink_exp_dump_expect(struct sk_buff *skb,
 			  const struct nf_conntrack_expect *exp)
@@ -2005,7 +2027,8 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
 		goto nla_put_failure;
 
 #ifdef CONFIG_NF_NAT_NEEDED
-	if (exp->saved_ip || exp->saved_proto.all) {
+	if (!nf_inet_addr_cmp(&exp->saved_addr, &any_addr) ||
+	    exp->saved_proto.all) {
 		nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT | NLA_F_NESTED);
 		if (!nest_parms)
 			goto nla_put_failure;
@@ -2014,7 +2037,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
 			goto nla_put_failure;
 
 		nat_tuple.src.l3num = nf_ct_l3num(master);
-		nat_tuple.src.u3.ip = exp->saved_ip;
+		nat_tuple.src.u3 = exp->saved_addr;
 		nat_tuple.dst.protonum = nf_ct_protonum(master);
 		nat_tuple.src.u = exp->saved_proto;
 
@@ -2410,7 +2433,7 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr,
 	if (err < 0)
 		return err;
 
-	exp->saved_ip = nat_tuple.src.u3.ip;
+	exp->saved_addr = nat_tuple.src.u3;
 	exp->saved_proto = nat_tuple.src.u;
 	exp->dir = ntohl(nla_get_be32(tb[CTA_EXPECT_NAT_DIR]));
 

net/netfilter/nf_conntrack_pptp.c

@@ -45,14 +45,14 @@ static DEFINE_SPINLOCK(nf_pptp_lock);
 int
 (*nf_nat_pptp_hook_outbound)(struct sk_buff *skb,
 			     struct nf_conn *ct, enum ip_conntrack_info ctinfo,
-			     struct PptpControlHeader *ctlh,
+			     unsigned int protoff, struct PptpControlHeader *ctlh,
 			     union pptp_ctrl_union *pptpReq) __read_mostly;
 EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_outbound);
 
 int
 (*nf_nat_pptp_hook_inbound)(struct sk_buff *skb,
 			    struct nf_conn *ct, enum ip_conntrack_info ctinfo,
-			    struct PptpControlHeader *ctlh,
+			    unsigned int protoff, struct PptpControlHeader *ctlh,
 			    union pptp_ctrl_union *pptpReq) __read_mostly;
 EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_inbound);
 
@@ -262,7 +262,7 @@ static int exp_gre(struct nf_conn *ct, __be16 callid, __be16 peer_callid)
 }
 
 static inline int
-pptp_inbound_pkt(struct sk_buff *skb,
+pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		 struct PptpControlHeader *ctlh,
 		 union pptp_ctrl_union *pptpReq,
 		 unsigned int reqlen,
@@ -376,7 +376,8 @@ pptp_inbound_pkt(struct sk_buff *skb,
 
 	nf_nat_pptp_inbound = rcu_dereference(nf_nat_pptp_hook_inbound);
 	if (nf_nat_pptp_inbound && ct->status & IPS_NAT_MASK)
-		return nf_nat_pptp_inbound(skb, ct, ctinfo, ctlh, pptpReq);
+		return nf_nat_pptp_inbound(skb, ct, ctinfo,
+					   protoff, ctlh, pptpReq);
 	return NF_ACCEPT;
 
 invalid:
@@ -389,7 +390,7 @@ pptp_inbound_pkt(struct sk_buff *skb,
 }
 
 static inline int
-pptp_outbound_pkt(struct sk_buff *skb,
+pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		  struct PptpControlHeader *ctlh,
 		  union pptp_ctrl_union *pptpReq,
 		  unsigned int reqlen,
@@ -471,7 +472,8 @@ pptp_outbound_pkt(struct sk_buff *skb,
 
 	nf_nat_pptp_outbound = rcu_dereference(nf_nat_pptp_hook_outbound);
 	if (nf_nat_pptp_outbound && ct->status & IPS_NAT_MASK)
-		return nf_nat_pptp_outbound(skb, ct, ctinfo, ctlh, pptpReq);
+		return nf_nat_pptp_outbound(skb, ct, ctinfo,
+					    protoff, ctlh, pptpReq);
 	return NF_ACCEPT;
 
 invalid:
@@ -570,11 +572,11 @@ conntrack_pptp_help(struct sk_buff *skb, unsigned int protoff,
 	 * established from PNS->PAC.  However, RFC makes no guarantee */
 	if (dir == IP_CT_DIR_ORIGINAL)
 		/* client -> server (PNS -> PAC) */
-		ret = pptp_outbound_pkt(skb, ctlh, pptpReq, reqlen, ct,
+		ret = pptp_outbound_pkt(skb, protoff, ctlh, pptpReq, reqlen, ct,
 					ctinfo);
 	else
 		/* server -> client (PAC -> PNS) */
-		ret = pptp_inbound_pkt(skb, ctlh, pptpReq, reqlen, ct,
+		ret = pptp_inbound_pkt(skb, protoff, ctlh, pptpReq, reqlen, ct,
 				       ctinfo);
 	pr_debug("sstate: %d->%d, cstate: %d->%d\n",
 		 oldsstate, info->sstate, oldcstate, info->cstate);