Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next

Pablo Neira Ayuso says:

====================
Netfilter/IPVS updates for net-next

The following patchset contains another batch with Netfilter/IPVS updates
for net-next, they are:

1) Add abstracted ICMP codes to the nf_tables reject expression. We
introduce four reasons to reject using ICMP that overlap in IPv4
and IPv6 from the semantic point of view. This should simplify the
maintainance of dual stack rule-sets through the inet table.

2) Move nf_send_reset() functions from header files to per-family
nf_reject modules, suggested by Patrick McHardy.

3) We have to use IS_ENABLED(CONFIG_BRIDGE_NETFILTER) everywhere in the
code now that br_netfilter can be modularized. Convert remaining spots
in the network stack code.

4) Use rcu_barrier() in the nf_tables module removal path to ensure that
we don't leave object that are still pending to be released via
call_rcu (that may likely result in a crash).

5) Remove incomplete arch 32/64 compat from nft_compat. The original (bad)
idea was to probe the word size based on the xtables match/target info
size, but this assumption is wrong when you have to dump the information
back to userspace.

6) Allow to filter from prerouting and postrouting in the nf_tables bridge.
In order to emulate the ebtables NAT chains (which are actually simple
filter chains with no special semantics), we have support filtering from
this hooks too.

7) Add explicit module dependency between xt_physdev and br_netfilter.
This provides a way to detect if the user needs br_netfilter from
the configuration path. This should reduce the breakage of the
br_netfilter modularization.

8) Cleanup coding style in ip_vs.h, from Simon Horman.

9) Fix crash in the recently added nf_tables masq expression. We have
to register/unregister the notifiers to clean up the conntrack table
entries from the module init/exit path, not from the rule addition /
deletion path. From Arturo Borrero.
====================

Signed-off-by: David S. Miller <[e-mail]>

include/net/ip_vs.h

···
-/*
- *      IP Virtual Server
- *      data structure and functionality definitions
+/* IP Virtual Server
+ * data structure and functionality definitions
  */
 
 #ifndef _NET_IP_VS_H
···
 
 #include <linux/list.h>                 /* for struct list_head */
 #include <linux/spinlock.h>             /* for struct rwlock_t */
-#include <linux/atomic.h>                 /* for struct atomic_t */
+#include <linux/atomic.h>               /* for struct atomic_t */
 #include <linux/compiler.h>
 #include <linux/timer.h>
 #include <linux/bug.h>
···
 #endif
 #include <net/net_namespace.h>		/* Netw namespace */
 
-/*
- * Generic access of ipvs struct
- */
+/* Generic access of ipvs struct */
 static inline struct netns_ipvs *net_ipvs(struct net* net)
 {
 	return net->ipvs;
 }
-/*
- * Get net ptr from skb in traffic cases
+
+/* Get net ptr from skb in traffic cases
  * use skb_sknet when call is from userland (ioctl or netlink)
  */
 static inline struct net *skb_net(const struct sk_buff *skb)
···
 	return &init_net;
 #endif
 }
-/*
- * This one needed for single_open_net since net is stored directly in
+
+/* This one needed for single_open_net since net is stored directly in
  * private not as a struct i.e. seq_file_net can't be used.
  */
 static inline struct net *seq_file_single_net(struct seq_file *seq)
···
 
 struct ip_vs_iphdr {
 	__u32 len;	/* IPv4 simply where L4 starts
-			   IPv6 where L4 Transport Header starts */
+			 * IPv6 where L4 Transport Header starts */
 	__u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/
 	__s16 protocol;
 	__s32 flags;
···
 #define LeaveFunction(level)   do {} while (0)
 #endif
 
-
-/*
- *      The port number of FTP service (in network order).
- */
+/* The port number of FTP service (in network order). */
 #define FTPPORT  cpu_to_be16(21)
 #define FTPDATA  cpu_to_be16(20)
 
-/*
- *      TCP State Values
- */
+/* TCP State Values */
 enum {
 	IP_VS_TCP_S_NONE = 0,
 	IP_VS_TCP_S_ESTABLISHED,
···
 	IP_VS_TCP_S_LAST
 };
 
-/*
- *	UDP State Values
- */
+/* UDP State Values */
 enum {
 	IP_VS_UDP_S_NORMAL,
 	IP_VS_UDP_S_LAST,
 };
 
-/*
- *	ICMP State Values
- */
+/* ICMP State Values */
 enum {
 	IP_VS_ICMP_S_NORMAL,
 	IP_VS_ICMP_S_LAST,
 };
 
-/*
- *	SCTP State Values
- */
+/* SCTP State Values */
 enum ip_vs_sctp_states {
 	IP_VS_SCTP_S_NONE,
 	IP_VS_SCTP_S_INIT1,
···
 	IP_VS_SCTP_S_LAST
 };
 
-/*
- *	Delta sequence info structure
- *	Each ip_vs_conn has 2 (output AND input seq. changes).
- *      Only used in the VS/NAT.
+/* Delta sequence info structure
+ * Each ip_vs_conn has 2 (output AND input seq. changes).
+ * Only used in the VS/NAT.
  */
 struct ip_vs_seq {
 	__u32			init_seq;	/* Add delta from this seq */
 	__u32			delta;		/* Delta in sequence numbers */
 	__u32			previous_delta;	/* Delta in sequence numbers
-						   before last resized pkt */
+						 * before last resized pkt */
 };
 
-/*
- * counters per cpu
- */
+/* counters per cpu */
 struct ip_vs_counters {
 	__u32		conns;		/* connections scheduled */
 	__u32		inpkts;		/* incoming packets */
···
 	__u64		inbytes;	/* incoming bytes */
 	__u64		outbytes;	/* outgoing bytes */
 };
-/*
- * Stats per cpu
- */
+/* Stats per cpu */
 struct ip_vs_cpu_stats {
 	struct ip_vs_counters   ustats;
 	struct u64_stats_sync   syncp;
 };
 
-/*
- *	IPVS statistics objects
- */
+/* IPVS statistics objects */
 struct ip_vs_estimator {
 	struct list_head	list;
 
···
 	void (*timeout_change)(struct ip_vs_proto_data *pd, int flags);
 };
 
-/*
- * protocol data per netns
- */
+/* protocol data per netns */
 struct ip_vs_proto_data {
 	struct ip_vs_proto_data	*next;
 	struct ip_vs_protocol	*pp;
···
 	__u8				pe_data_len;
 };
 
-/*
- *	IP_VS structure allocated for each dynamically scheduled connection
- */
+/* IP_VS structure allocated for each dynamically scheduled connection */
 struct ip_vs_conn {
 	struct hlist_node	c_list;         /* hashed list heads */
 	/* Protocol, addresses and port numbers */
···
 	struct ip_vs_dest       *dest;          /* real server */
 	atomic_t                in_pkts;        /* incoming packet counter */
 
-	/* packet transmitter for different forwarding methods.  If it
-	   mangles the packet, it must return NF_DROP or better NF_STOLEN,
-	   otherwise this must be changed to a sk_buff **.
-	   NF_ACCEPT can be returned when destination is local.
+	/* Packet transmitter for different forwarding methods.  If it
+	 * mangles the packet, it must return NF_DROP or better NF_STOLEN,
+	 * otherwise this must be changed to a sk_buff **.
+	 * NF_ACCEPT can be returned when destination is local.
 	 */
 	int (*packet_xmit)(struct sk_buff *skb, struct ip_vs_conn *cp,
 			   struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
 
 	/* Note: we can group the following members into a structure,
-	   in order to save more space, and the following members are
-	   only used in VS/NAT anyway */
+	 * in order to save more space, and the following members are
+	 * only used in VS/NAT anyway
+	 */
 	struct ip_vs_app        *app;           /* bound ip_vs_app object */
 	void                    *app_data;      /* Application private data */
 	struct ip_vs_seq        in_seq;         /* incoming seq. struct */
···
 	struct rcu_head		rcu_head;
 };
 
-/*
- *  To save some memory in conn table when name space is disabled.
- */
+/* To save some memory in conn table when name space is disabled. */
 static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp)
 {
 #ifdef CONFIG_NET_NS
···
 	return &init_net;
 #endif
 }
+
 static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net)
 {
 #ifdef CONFIG_NET_NS
···
 #endif
 }
 
-/*
- *	Extended internal versions of struct ip_vs_service_user and
- *	ip_vs_dest_user for IPv6 support.
+/* Extended internal versions of struct ip_vs_service_user and ip_vs_dest_user
+ * for IPv6 support.
  *
- *	We need these to conveniently pass around service and destination
- *	options, but unfortunately, we also need to keep the old definitions to
- *	maintain userspace backwards compatibility for the setsockopt interface.
+ * We need these to conveniently pass around service and destination
+ * options, but unfortunately, we also need to keep the old definitions to
+ * maintain userspace backwards compatibility for the setsockopt interface.
  */
 struct ip_vs_service_user_kern {
 	/* virtual service addresses */
···
 
 
 /*
- *	The information about the virtual service offered to the net
- *	and the forwarding entries
+ * The information about the virtual service offered to the net and the
+ * forwarding entries.
  */
 struct ip_vs_service {
 	struct hlist_node	s_list;   /* for normal service table */
···
 	struct rcu_head		rcu_head;
 };
 
-/*
- *	The real server destination forwarding entry
- *	with ip address, port number, and so on.
+/* The real server destination forwarding entry with ip address, port number,
+ * and so on.
  */
 struct ip_vs_dest {
 	struct list_head	n_list;   /* for the dests in the service */
···
 	unsigned int		in_rs_table:1;	/* we are in rs_table */
 };
 
-
-/*
- *	The scheduler object
- */
+/* The scheduler object */
 struct ip_vs_scheduler {
 	struct list_head	n_list;		/* d-linked list head */
 	char			*name;		/* scheduler name */
···
 	int (*show_pe_data)(const struct ip_vs_conn *cp, char *buf);
 };
 
-/*
- *	The application module object (a.k.a. app incarnation)
- */
+/* The application module object (a.k.a. app incarnation) */
 struct ip_vs_app {
 	struct list_head	a_list;		/* member in app list */
 	int			type;		/* IP_VS_APP_TYPE_xxx */
···
 	atomic_t		usecnt;		/* usage counter */
 	struct rcu_head		rcu_head;
 
-	/*
-	 * output hook: Process packet in inout direction, diff set for TCP.
+	/* output hook: Process packet in inout direction, diff set for TCP.
 	 * Return: 0=Error, 1=Payload Not Mangled/Mangled but checksum is ok,
 	 *	   2=Mangled but checksum was not updated
 	 */
 	int (*pkt_out)(struct ip_vs_app *, struct ip_vs_conn *,
 		       struct sk_buff *, int *diff);
 
-	/*
-	 * input hook: Process packet in outin direction, diff set for TCP.
+	/* input hook: Process packet in outin direction, diff set for TCP.
 	 * Return: 0=Error, 1=Payload Not Mangled/Mangled but checksum is ok,
 	 *	   2=Mangled but checksum was not updated
 	 */
···
 struct netns_ipvs {
 	int			gen;		/* Generation */
 	int			enable;		/* enable like nf_hooks do */
-	/*
-	 *	Hash table: for real service lookups
-	 */
+	/* Hash table: for real service lookups */
 	#define IP_VS_RTAB_BITS 4
 	#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
 	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
···
 	struct list_head	sctp_apps[SCTP_APP_TAB_SIZE];
 #endif
 	/* ip_vs_conn */
-	atomic_t		conn_count;      /*  connection counter */
+	atomic_t		conn_count;      /* connection counter */
 
 	/* ip_vs_ctl */
 	struct ip_vs_stats		tot_stats;  /* Statistics & est. */
···
 	char			backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 	/* net name space ptr */
 	struct net		*net;            /* Needed by timer routines */
-	/* Number of heterogeneous destinations, needed because
-	 * heterogeneous are not supported when synchronization is
-	 * enabled */
+	/* Number of heterogeneous destinations, needed becaus heterogeneous
+	 * are not supported when synchronization is enabled.
+	 */
 	unsigned int		mixed_address_family_dests;
 };
 
···
 
 #endif
 
-/*
- *      IPVS core functions
- *      (from ip_vs_core.c)
+/* IPVS core functions
+ * (from ip_vs_core.c)
  */
 const char *ip_vs_proto_name(unsigned int proto);
 void ip_vs_init_hash_table(struct list_head *table, int rows);
···
 
 #define IP_VS_APP_TYPE_FTP	1
 
-/*
- *     ip_vs_conn handling functions
- *     (from ip_vs_conn.c)
+/* ip_vs_conn handling functions
+ * (from ip_vs_conn.c)
  */
-
 enum {
 	IP_VS_DIR_INPUT = 0,
 	IP_VS_DIR_OUTPUT,
···
 	atomic_inc(&ctl_cp->n_control);
 }
 
-/*
- * IPVS netns init & cleanup functions
- */
+/* IPVS netns init & cleanup functions */
 int ip_vs_estimator_net_init(struct net *net);
 int ip_vs_control_net_init(struct net *net);
 int ip_vs_protocol_net_init(struct net *net);
···
 void ip_vs_sync_net_cleanup(struct net *net);
 void ip_vs_service_net_cleanup(struct net *net);
 
-/*
- *      IPVS application functions
- *      (from ip_vs_app.c)
+/* IPVS application functions
+ * (from ip_vs_app.c)
  */
 #define IP_VS_APP_MAX_PORTS  8
 struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app);
···
 struct ip_vs_pe *ip_vs_pe_getbyname(const char *name);
 struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name);
 
-/*
- * Use a #define to avoid all of module.h just for these trivial ops
- */
+/* Use a #define to avoid all of module.h just for these trivial ops */
 #define ip_vs_pe_get(pe)			\
 	if (pe && pe->module)			\
 		__module_get(pe->module);
···
 	if (pe && pe->module)			\
 		module_put(pe->module);
 
-/*
- *	IPVS protocol functions (from ip_vs_proto.c)
- */
+/* IPVS protocol functions (from ip_vs_proto.c) */
 int ip_vs_protocol_init(void);
 void ip_vs_protocol_cleanup(void);
 void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags);
···
 extern struct ip_vs_protocol ip_vs_protocol_ah;
 extern struct ip_vs_protocol ip_vs_protocol_sctp;
 
-/*
- *      Registering/unregistering scheduler functions
- *      (from ip_vs_sched.c)
+/* Registering/unregistering scheduler functions
+ * (from ip_vs_sched.c)
  */
 int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
 int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
···
 
 void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg);
 
-
-/*
- *      IPVS control data and functions (from ip_vs_ctl.c)
- */
+/* IPVS control data and functions (from ip_vs_ctl.c) */
 extern struct ip_vs_stats ip_vs_stats;
 extern int sysctl_ip_vs_sync_ver;
 
···
 		kfree(dest);
 }
 
-/*
- *      IPVS sync daemon data and function prototypes
- *      (from ip_vs_sync.c)
+/* IPVS sync daemon data and function prototypes
+ * (from ip_vs_sync.c)
  */
 int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid);
 int stop_sync_thread(struct net *net, int state);
 void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts);
 
-/*
- *      IPVS rate estimator prototypes (from ip_vs_est.c)
- */
+/* IPVS rate estimator prototypes (from ip_vs_est.c) */
 void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats);
 void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats);
 void ip_vs_zero_estimator(struct ip_vs_stats *stats);
 void ip_vs_read_estimator(struct ip_vs_stats_user *dst,
 			  struct ip_vs_stats *stats);
 
-/*
- *	Various IPVS packet transmitters (from ip_vs_xmit.c)
- */
+/* Various IPVS packet transmitters (from ip_vs_xmit.c) */
 int ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		    struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
 int ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
···
 #endif
 
 #ifdef CONFIG_SYSCTL
-/*
- *	This is a simple mechanism to ignore packets when
- *	we are loaded. Just set ip_vs_drop_rate to 'n' and
- *	we start to drop 1/rate of the packets
+/* This is a simple mechanism to ignore packets when
+ * we are loaded. Just set ip_vs_drop_rate to 'n' and
+ * we start to drop 1/rate of the packets
  */
-
 static inline int ip_vs_todrop(struct netns_ipvs *ipvs)
 {
 	if (!ipvs->drop_rate)
···
 static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { return 0; }
 #endif
 
-/*
- *      ip_vs_fwd_tag returns the forwarding tag of the connection
- */
+/* ip_vs_fwd_tag returns the forwarding tag of the connection */
 #define IP_VS_FWD_METHOD(cp)  (cp->flags & IP_VS_CONN_F_FWD_MASK)
 
 static inline char ip_vs_fwd_tag(struct ip_vs_conn *cp)
···
 	return csum_partial(diff, sizeof(diff), oldsum);
 }
 
-/*
- * Forget current conntrack (unconfirmed) and attach notrack entry
- */
+/* Forget current conntrack (unconfirmed) and attach notrack entry */
 static inline void ip_vs_notrack(struct sk_buff *skb)
 {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
···
 }
 
 #ifdef CONFIG_IP_VS_NFCT
-/*
- *      Netfilter connection tracking
- *      (from ip_vs_nfct.c)
+/* Netfilter connection tracking
+ * (from ip_vs_nfct.c)
  */
 static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)
 {
···
 static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
 {
 }
-/* CONFIG_IP_VS_NFCT */
-#endif
+#endif /* CONFIG_IP_VS_NFCT */
 
 static inline int
 ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
 {
-	/*
-	 * We think the overhead of processing active connections is 256
+	/* We think the overhead of processing active connections is 256
 	 * times higher than that of inactive connections in average. (This
 	 * 256 times might not be accurate, we will change it later) We
 	 * use the following formula to estimate the overhead now:

include/net/netfilter/br_netfilter.h

···
+#ifndef _BR_NETFILTER_H_
+#define _BR_NETFILTER_H_
+
+void br_netfilter_enable(void);
+
+#endif /* _BR_NETFILTER_H_ */

include/net/netfilter/ipv4/nf_reject.h

···
 #ifndef _IPV4_NF_REJECT_H
 #define _IPV4_NF_REJECT_H
 
-#include <net/ip.h>
-#include <net/tcp.h>
-#include <net/route.h>
-#include <net/dst.h>
+#include <net/icmp.h>
 
 static inline void nf_send_unreach(struct sk_buff *skb_in, int code)
 {
 	icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0);
 }
 
-/* Send RST reply */
-static void nf_send_reset(struct sk_buff *oldskb, int hook)
-{
-	struct sk_buff *nskb;
-	const struct iphdr *oiph;
-	struct iphdr *niph;
-	const struct tcphdr *oth;
-	struct tcphdr _otcph, *tcph;
-
-	/* IP header checks: fragment. */
-	if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
-		return;
-
-	oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb),
-				 sizeof(_otcph), &_otcph);
-	if (oth == NULL)
-		return;
-
-	/* No RST for RST. */
-	if (oth->rst)
-		return;
-
-	if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
-		return;
-
-	/* Check checksum */
-	if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP))
-		return;
-	oiph = ip_hdr(oldskb);
-
-	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
-			 LL_MAX_HEADER, GFP_ATOMIC);
-	if (!nskb)
-		return;
-
-	skb_reserve(nskb, LL_MAX_HEADER);
-
-	skb_reset_network_header(nskb);
-	niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr));
-	niph->version	= 4;
-	niph->ihl	= sizeof(struct iphdr) / 4;
-	niph->tos	= 0;
-	niph->id	= 0;
-	niph->frag_off	= htons(IP_DF);
-	niph->protocol	= IPPROTO_TCP;
-	niph->check	= 0;
-	niph->saddr	= oiph->daddr;
-	niph->daddr	= oiph->saddr;
-
-	skb_reset_transport_header(nskb);
-	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
-	memset(tcph, 0, sizeof(*tcph));
-	tcph->source	= oth->dest;
-	tcph->dest	= oth->source;
-	tcph->doff	= sizeof(struct tcphdr) / 4;
-
-	if (oth->ack)
-		tcph->seq = oth->ack_seq;
-	else {
-		tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
-				      oldskb->len - ip_hdrlen(oldskb) -
-				      (oth->doff << 2));
-		tcph->ack = 1;
-	}
-
-	tcph->rst	= 1;
-	tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
-				    niph->daddr, 0);
-	nskb->ip_summed = CHECKSUM_PARTIAL;
-	nskb->csum_start = (unsigned char *)tcph - nskb->head;
-	nskb->csum_offset = offsetof(struct tcphdr, check);
-
-	/* ip_route_me_harder expects skb->dst to be set */
-	skb_dst_set_noref(nskb, skb_dst(oldskb));
-
-	nskb->protocol = htons(ETH_P_IP);
-	if (ip_route_me_harder(nskb, RTN_UNSPEC))
-		goto free_nskb;
-
-	niph->ttl	= ip4_dst_hoplimit(skb_dst(nskb));
-
-	/* "Never happens" */
-	if (nskb->len > dst_mtu(skb_dst(nskb)))
-		goto free_nskb;
-
-	nf_ct_attach(nskb, oldskb);
-
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	/* If we use ip_local_out for bridged traffic, the MAC source on
-	 * the RST will be ours, instead of the destination's.  This confuses
-	 * some routers/firewalls, and they drop the packet.  So we need to
-	 * build the eth header using the original destination's MAC as the
-	 * source, and send the RST packet directly.
-	 */
-	if (oldskb->nf_bridge) {
-		struct ethhdr *oeth = eth_hdr(oldskb);
-		nskb->dev = oldskb->nf_bridge->physindev;
-		niph->tot_len = htons(nskb->len);
-		ip_send_check(niph);
-		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
-				    oeth->h_source, oeth->h_dest, nskb->len) < 0)
-			goto free_nskb;
-		dev_queue_xmit(nskb);
-	} else
-#endif
-		ip_local_out(nskb);
-
-	return;
-
- free_nskb:
-	kfree_skb(nskb);
-}
-
+void nf_send_reset(struct sk_buff *oldskb, int hook);
 
 #endif /* _IPV4_NF_REJECT_H */

include/net/netfilter/nft_reject.h

···
 
 int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr);
 
-void nft_reject_ipv4_eval(const struct nft_expr *expr,
-			  struct nft_data data[NFT_REG_MAX + 1],
-			  const struct nft_pktinfo *pkt);
-
-void nft_reject_ipv6_eval(const struct nft_expr *expr,
-			  struct nft_data data[NFT_REG_MAX + 1],
-			  const struct nft_pktinfo *pkt);
+int nft_reject_icmp_code(u8 code);
+int nft_reject_icmpv6_code(u8 code);
 
 #endif

include/uapi/linux/netfilter/nf_tables.h

···
  *
  * @NFT_REJECT_ICMP_UNREACH: reject using ICMP unreachable
  * @NFT_REJECT_TCP_RST: reject using TCP RST
+ * @NFT_REJECT_ICMPX_UNREACH: abstracted ICMP unreachable for bridge and inet
  */
 enum nft_reject_types {
 	NFT_REJECT_ICMP_UNREACH,
 	NFT_REJECT_TCP_RST,
+	NFT_REJECT_ICMPX_UNREACH,
 };
+
+/**
+ * enum nft_reject_code - Generic reject codes for IPv4/IPv6
+ *
+ * @NFT_REJECT_ICMPX_NO_ROUTE: no route to host / network unreachable
+ * @NFT_REJECT_ICMPX_PORT_UNREACH: port unreachable
+ * @NFT_REJECT_ICMPX_HOST_UNREACH: host unreachable
+ * @NFT_REJECT_ICMPX_ADMIN_PROHIBITED: administratively prohibited
+ *
+ * These codes are mapped to real ICMP and ICMPv6 codes.
+ */
+enum nft_reject_inet_code {
+	NFT_REJECT_ICMPX_NO_ROUTE	= 0,
+	NFT_REJECT_ICMPX_PORT_UNREACH,
+	NFT_REJECT_ICMPX_HOST_UNREACH,
+	NFT_REJECT_ICMPX_ADMIN_PROHIBITED,
+	__NFT_REJECT_ICMPX_MAX
+};
+#define NFT_REJECT_ICMPX_MAX	(__NFT_REJECT_ICMPX_MAX + 1)
 
 /**
  * enum nft_reject_attributes - nf_tables reject expression netlink attributes

net/bridge/br_netfilter.c

···
 	return NF_ACCEPT;
 }
 
+void br_netfilter_enable(void)
+{
+}
+EXPORT_SYMBOL_GPL(br_netfilter_enable);
+
 /* For br_nf_post_routing, we need (prio = NF_BR_PRI_LAST), because
  * br_dev_queue_push_xmit is called afterwards */
 static struct nf_hook_ops br_nf_ops[] __read_mostly = {

net/bridge/netfilter/nf_tables_bridge.c

···
 	.owner		= THIS_MODULE,
 	.nops		= 1,
 	.hooks		= {
+		[NF_BR_PRE_ROUTING]	= nft_do_chain_bridge,
 		[NF_BR_LOCAL_IN]	= nft_do_chain_bridge,
 		[NF_BR_FORWARD]		= nft_do_chain_bridge,
 		[NF_BR_LOCAL_OUT]	= nft_do_chain_bridge,
+		[NF_BR_POST_ROUTING]	= nft_do_chain_bridge,
 	},
 };
 

net/bridge/netfilter/nft_reject_bridge.c

···
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nft_reject.h>
+#include <net/netfilter/ipv4/nf_reject.h>
+#include <net/netfilter/ipv6/nf_reject.h>
 
 static void nft_reject_bridge_eval(const struct nft_expr *expr,
 				 struct nft_data data[NFT_REG_MAX + 1],
 				 const struct nft_pktinfo *pkt)
 {
+	struct nft_reject *priv = nft_expr_priv(expr);
+	struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out);
+
 	switch (eth_hdr(pkt->skb)->h_proto) {
 	case htons(ETH_P_IP):
-		return nft_reject_ipv4_eval(expr, data, pkt);
+		switch (priv->type) {
+		case NFT_REJECT_ICMP_UNREACH:
+			nf_send_unreach(pkt->skb, priv->icmp_code);
+			break;
+		case NFT_REJECT_TCP_RST:
+			nf_send_reset(pkt->skb, pkt->ops->hooknum);
+			break;
+		case NFT_REJECT_ICMPX_UNREACH:
+			nf_send_unreach(pkt->skb,
+					nft_reject_icmp_code(priv->icmp_code));
+			break;
+		}
+		break;
 	case htons(ETH_P_IPV6):
-		return nft_reject_ipv6_eval(expr, data, pkt);
+		switch (priv->type) {
+		case NFT_REJECT_ICMP_UNREACH:
+			nf_send_unreach6(net, pkt->skb, priv->icmp_code,
+					 pkt->ops->hooknum);
+			break;
+		case NFT_REJECT_TCP_RST:
+			nf_send_reset6(net, pkt->skb, pkt->ops->hooknum);
+			break;
+		case NFT_REJECT_ICMPX_UNREACH:
+			nf_send_unreach6(net, pkt->skb,
+					 nft_reject_icmpv6_code(priv->icmp_code),
+					 pkt->ops->hooknum);
+			break;
+		}
+		break;
 	default:
 		/* No explicit way to reject this protocol, drop it. */
-		data[NFT_REG_VERDICT].verdict = NF_DROP;
 		break;
 	}
+	data[NFT_REG_VERDICT].verdict = NF_DROP;
+}
+
+static int nft_reject_bridge_init(const struct nft_ctx *ctx,
+				  const struct nft_expr *expr,
+				  const struct nlattr * const tb[])
+{
+	struct nft_reject *priv = nft_expr_priv(expr);
+	int icmp_code;
+
+	if (tb[NFTA_REJECT_TYPE] == NULL)
+		return -EINVAL;
+
+	priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+	case NFT_REJECT_ICMPX_UNREACH:
+		if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
+			return -EINVAL;
+
+		icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
+		if (priv->type == NFT_REJECT_ICMPX_UNREACH &&
+		    icmp_code > NFT_REJECT_ICMPX_MAX)
+			return -EINVAL;
+
+		priv->icmp_code = icmp_code;
+		break;
+	case NFT_REJECT_TCP_RST:
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int nft_reject_bridge_dump(struct sk_buff *skb,
+				  const struct nft_expr *expr)
+{
+	const struct nft_reject *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type)))
+		goto nla_put_failure;
+
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+	case NFT_REJECT_ICMPX_UNREACH:
+		if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
+			goto nla_put_failure;
+		break;
+	}
+
+	return 0;
+
+nla_put_failure:
+	return -1;
 }
 
 static struct nft_expr_type nft_reject_bridge_type;
···
 	.type		= &nft_reject_bridge_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
 	.eval		= nft_reject_bridge_eval,
-	.init		= nft_reject_init,
-	.dump		= nft_reject_dump,
+	.init		= nft_reject_bridge_init,
+	.dump		= nft_reject_bridge_dump,
 };
 
 static struct nft_expr_type nft_reject_bridge_type __read_mostly = {

net/core/skbuff.c

···
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	nf_conntrack_put(skb->nfct);
 #endif
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	nf_bridge_put(skb->nf_bridge);
 #endif
 /* XXX: IS this still necessary? - JHS */

net/ipv4/ip_output.c

···
 
 	hlen = iph->ihl * 4;
 	mtu = mtu - hlen;	/* Size of data space */
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (skb->nf_bridge)
 		mtu -= nf_bridge_mtu_reduction(skb);
 #endif

net/ipv4/netfilter/Kconfig

···
 	  fields such as the source, destination, type of service and
 	  the packet mark.
 
+config NF_REJECT_IPV4
+	tristate "IPv4 packet rejection"
+	default m if NETFILTER_ADVANCED=n
+
 config NFT_REJECT_IPV4
 	depends on NF_TABLES_IPV4
+	select NF_REJECT_IPV4
 	default NFT_REJECT
 	tristate
 
···
 config IP_NF_TARGET_REJECT
 	tristate "REJECT target support"
 	depends on IP_NF_FILTER
+	select NF_REJECT_IPV4
 	default m if NETFILTER_ADVANCED=n
 	help
 	  The REJECT target allows a filtering rule to specify that an ICMP

net/ipv4/netfilter/Makefile

···
 obj-$(CONFIG_NF_LOG_ARP) += nf_log_arp.o
 obj-$(CONFIG_NF_LOG_IPV4) += nf_log_ipv4.o
 
+# reject
+obj-$(CONFIG_NF_REJECT_IPV4) += nf_reject_ipv4.o
+
 # NAT helpers (nf_conntrack)
 obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o
 obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o

net/ipv4/netfilter/ipt_REJECT.c

···
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv4/ipt_REJECT.h>
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 #include <linux/netfilter_bridge.h>
 #endif
 

net/ipv4/netfilter/nf_defrag_ipv4.c

···
 		zone = nf_ct_zone((struct nf_conn *)skb->nfct);
 #endif
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (skb->nf_bridge &&
 	    skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)
 		return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone;

net/ipv4/netfilter/nf_reject_ipv4.c

···
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2004 Netfilter Core Team <[e-mail]>
+ *
+ * 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 <net/ip.h>
+#include <net/tcp.h>
+#include <net/route.h>
+#include <net/dst.h>
+#include <linux/netfilter_ipv4.h>
+
+/* Send RST reply */
+void nf_send_reset(struct sk_buff *oldskb, int hook)
+{
+	struct sk_buff *nskb;
+	const struct iphdr *oiph;
+	struct iphdr *niph;
+	const struct tcphdr *oth;
+	struct tcphdr _otcph, *tcph;
+
+	/* IP header checks: fragment. */
+	if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
+		return;
+
+	oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb),
+				 sizeof(_otcph), &_otcph);
+	if (oth == NULL)
+		return;
+
+	/* No RST for RST. */
+	if (oth->rst)
+		return;
+
+	if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
+		return;
+
+	/* Check checksum */
+	if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP))
+		return;
+	oiph = ip_hdr(oldskb);
+
+	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
+			 LL_MAX_HEADER, GFP_ATOMIC);
+	if (!nskb)
+		return;
+
+	skb_reserve(nskb, LL_MAX_HEADER);
+
+	skb_reset_network_header(nskb);
+	niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr));
+	niph->version	= 4;
+	niph->ihl	= sizeof(struct iphdr) / 4;
+	niph->tos	= 0;
+	niph->id	= 0;
+	niph->frag_off	= htons(IP_DF);
+	niph->protocol	= IPPROTO_TCP;
+	niph->check	= 0;
+	niph->saddr	= oiph->daddr;
+	niph->daddr	= oiph->saddr;
+
+	skb_reset_transport_header(nskb);
+	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
+	memset(tcph, 0, sizeof(*tcph));
+	tcph->source	= oth->dest;
+	tcph->dest	= oth->source;
+	tcph->doff	= sizeof(struct tcphdr) / 4;
+
+	if (oth->ack)
+		tcph->seq = oth->ack_seq;
+	else {
+		tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
+				      oldskb->len - ip_hdrlen(oldskb) -
+				      (oth->doff << 2));
+		tcph->ack = 1;
+	}
+
+	tcph->rst	= 1;
+	tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
+				    niph->daddr, 0);
+	nskb->ip_summed = CHECKSUM_PARTIAL;
+	nskb->csum_start = (unsigned char *)tcph - nskb->head;
+	nskb->csum_offset = offsetof(struct tcphdr, check);
+
+	/* ip_route_me_harder expects skb->dst to be set */
+	skb_dst_set_noref(nskb, skb_dst(oldskb));
+
+	nskb->protocol = htons(ETH_P_IP);
+	if (ip_route_me_harder(nskb, RTN_UNSPEC))
+		goto free_nskb;
+
+	niph->ttl	= ip4_dst_hoplimit(skb_dst(nskb));
+
+	/* "Never happens" */
+	if (nskb->len > dst_mtu(skb_dst(nskb)))
+		goto free_nskb;
+
+	nf_ct_attach(nskb, oldskb);
+
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+	/* If we use ip_local_out for bridged traffic, the MAC source on
+	 * the RST will be ours, instead of the destination's.  This confuses
+	 * some routers/firewalls, and they drop the packet.  So we need to
+	 * build the eth header using the original destination's MAC as the
+	 * source, and send the RST packet directly.
+	 */
+	if (oldskb->nf_bridge) {
+		struct ethhdr *oeth = eth_hdr(oldskb);
+		nskb->dev = oldskb->nf_bridge->physindev;
+		niph->tot_len = htons(nskb->len);
+		ip_send_check(niph);
+		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
+				    oeth->h_source, oeth->h_dest, nskb->len) < 0)
+			goto free_nskb;
+		dev_queue_xmit(nskb);
+	} else
+#endif
+		ip_local_out(nskb);
+
+	return;
+
+ free_nskb:
+	kfree_skb(nskb);
+}
+EXPORT_SYMBOL_GPL(nf_send_reset);

net/ipv4/netfilter/nft_masq_ipv4.c

···
 	data[NFT_REG_VERDICT].verdict = verdict;
 }
 
-static int nft_masq_ipv4_init(const struct nft_ctx *ctx,
-			      const struct nft_expr *expr,
-			      const struct nlattr * const tb[])
-{
-	int err;
-
-	err = nft_masq_init(ctx, expr, tb);
-	if (err < 0)
-		return err;
-
-	nf_nat_masquerade_ipv4_register_notifier();
-	return 0;
-}
-
-static void nft_masq_ipv4_destroy(const struct nft_ctx *ctx,
-				  const struct nft_expr *expr)
-{
-	nf_nat_masquerade_ipv4_unregister_notifier();
-}
-
 static struct nft_expr_type nft_masq_ipv4_type;
 static const struct nft_expr_ops nft_masq_ipv4_ops = {
 	.type		= &nft_masq_ipv4_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_masq)),
 	.eval		= nft_masq_ipv4_eval,
-	.init		= nft_masq_ipv4_init,
-	.destroy	= nft_masq_ipv4_destroy,
+	.init		= nft_masq_init,
 	.dump		= nft_masq_dump,
 };
 
···
 
 static int __init nft_masq_ipv4_module_init(void)
 {
-	return nft_register_expr(&nft_masq_ipv4_type);
+	int ret;
+
+	ret = nft_register_expr(&nft_masq_ipv4_type);
+	if (ret < 0)
+		return ret;
+
+	nf_nat_masquerade_ipv4_register_notifier();
+
+	return ret;
 }
 
 static void __exit nft_masq_ipv4_module_exit(void)
 {
 	nft_unregister_expr(&nft_masq_ipv4_type);
+	nf_nat_masquerade_ipv4_unregister_notifier();
 }
 
 module_init(nft_masq_ipv4_module_init);

net/ipv4/netfilter/nft_reject_ipv4.c

···
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
-#include <net/icmp.h>
 #include <net/netfilter/ipv4/nf_reject.h>
 #include <net/netfilter/nft_reject.h>
 

net/ipv6/netfilter/Kconfig

···
 	  fields such as the source, destination, flowlabel, hop-limit and
 	  the packet mark.
 
+config NF_REJECT_IPV6
+	tristate "IPv6 packet rejection"
+	default m if NETFILTER_ADVANCED=n
+
 config NFT_REJECT_IPV6
 	depends on NF_TABLES_IPV6
+	select NF_REJECT_IPV6
 	default NFT_REJECT
 	tristate
 
···
 config IP6_NF_TARGET_REJECT
 	tristate "REJECT target support"
 	depends on IP6_NF_FILTER
+	select NF_REJECT_IPV6
 	default m if NETFILTER_ADVANCED=n
 	help
 	  The REJECT target allows a filtering rule to specify that an ICMPv6

net/ipv6/netfilter/Makefile

···
 # logging
 obj-$(CONFIG_NF_LOG_IPV6) += nf_log_ipv6.o
 
+# reject
+obj-$(CONFIG_NF_REJECT_IPV6) += nf_reject_ipv6.o
+
 # nf_tables
 obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o

net/ipv6/netfilter/nf_defrag_ipv6_hooks.c

···
 		zone = nf_ct_zone((struct nf_conn *)skb->nfct);
 #endif
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (skb->nf_bridge &&
 	    skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)
 		return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone;

net/ipv6/netfilter/nf_reject_ipv6.c

···
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2004 Netfilter Core Team <[e-mail]>
+ *
+ * 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 <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/ip6_fib.h>
+#include <net/ip6_checksum.h>
+#include <linux/netfilter_ipv6.h>
+
+void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
+{
+	struct sk_buff *nskb;
+	struct tcphdr otcph, *tcph;
+	unsigned int otcplen, hh_len;
+	int tcphoff, needs_ack;
+	const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
+	struct ipv6hdr *ip6h;
+#define DEFAULT_TOS_VALUE	0x0U
+	const __u8 tclass = DEFAULT_TOS_VALUE;
+	struct dst_entry *dst = NULL;
+	u8 proto;
+	__be16 frag_off;
+	struct flowi6 fl6;
+
+	if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
+	    (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
+		pr_debug("addr is not unicast.\n");
+		return;
+	}
+
+	proto = oip6h->nexthdr;
+	tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto, &frag_off);
+
+	if ((tcphoff < 0) || (tcphoff > oldskb->len)) {
+		pr_debug("Cannot get TCP header.\n");
+		return;
+	}
+
+	otcplen = oldskb->len - tcphoff;
+
+	/* IP header checks: fragment, too short. */
+	if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) {
+		pr_debug("proto(%d) != IPPROTO_TCP, "
+			 "or too short. otcplen = %d\n",
+			 proto, otcplen);
+		return;
+	}
+
+	if (skb_copy_bits(oldskb, tcphoff, &otcph, sizeof(struct tcphdr)))
+		BUG();
+
+	/* No RST for RST. */
+	if (otcph.rst) {
+		pr_debug("RST is set\n");
+		return;
+	}
+
+	/* Check checksum. */
+	if (nf_ip6_checksum(oldskb, hook, tcphoff, IPPROTO_TCP)) {
+		pr_debug("TCP checksum is invalid\n");
+		return;
+	}
+
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_proto = IPPROTO_TCP;
+	fl6.saddr = oip6h->daddr;
+	fl6.daddr = oip6h->saddr;
+	fl6.fl6_sport = otcph.dest;
+	fl6.fl6_dport = otcph.source;
+	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
+	dst = ip6_route_output(net, NULL, &fl6);
+	if (dst == NULL || dst->error) {
+		dst_release(dst);
+		return;
+	}
+	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
+	if (IS_ERR(dst))
+		return;
+
+	hh_len = (dst->dev->hard_header_len + 15)&~15;
+	nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
+			 + sizeof(struct tcphdr) + dst->trailer_len,
+			 GFP_ATOMIC);
+
+	if (!nskb) {
+		net_dbg_ratelimited("cannot alloc skb\n");
+		dst_release(dst);
+		return;
+	}
+
+	skb_dst_set(nskb, dst);
+
+	skb_reserve(nskb, hh_len + dst->header_len);
+
+	skb_put(nskb, sizeof(struct ipv6hdr));
+	skb_reset_network_header(nskb);
+	ip6h = ipv6_hdr(nskb);
+	ip6_flow_hdr(ip6h, tclass, 0);
+	ip6h->hop_limit = ip6_dst_hoplimit(dst);
+	ip6h->nexthdr = IPPROTO_TCP;
+	ip6h->saddr = oip6h->daddr;
+	ip6h->daddr = oip6h->saddr;
+
+	skb_reset_transport_header(nskb);
+	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
+	/* Truncate to length (no data) */
+	tcph->doff = sizeof(struct tcphdr)/4;
+	tcph->source = otcph.dest;
+	tcph->dest = otcph.source;
+
+	if (otcph.ack) {
+		needs_ack = 0;
+		tcph->seq = otcph.ack_seq;
+		tcph->ack_seq = 0;
+	} else {
+		needs_ack = 1;
+		tcph->ack_seq = htonl(ntohl(otcph.seq) + otcph.syn + otcph.fin
+				      + otcplen - (otcph.doff<<2));
+		tcph->seq = 0;
+	}
+
+	/* Reset flags */
+	((u_int8_t *)tcph)[13] = 0;
+	tcph->rst = 1;
+	tcph->ack = needs_ack;
+	tcph->window = 0;
+	tcph->urg_ptr = 0;
+	tcph->check = 0;
+
+	/* Adjust TCP checksum */
+	tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr,
+				      &ipv6_hdr(nskb)->daddr,
+				      sizeof(struct tcphdr), IPPROTO_TCP,
+				      csum_partial(tcph,
+						   sizeof(struct tcphdr), 0));
+
+	nf_ct_attach(nskb, oldskb);
+
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+	/* If we use ip6_local_out for bridged traffic, the MAC source on
+	 * the RST will be ours, instead of the destination's.  This confuses
+	 * some routers/firewalls, and they drop the packet.  So we need to
+	 * build the eth header using the original destination's MAC as the
+	 * source, and send the RST packet directly.
+	 */
+	if (oldskb->nf_bridge) {
+		struct ethhdr *oeth = eth_hdr(oldskb);
+		nskb->dev = oldskb->nf_bridge->physindev;
+		nskb->protocol = htons(ETH_P_IPV6);
+		ip6h->payload_len = htons(sizeof(struct tcphdr));
+		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
+				    oeth->h_source, oeth->h_dest, nskb->len) < 0)
+			return;
+		dev_queue_xmit(nskb);
+	} else
+#endif
+		ip6_local_out(nskb);
+}
+EXPORT_SYMBOL_GPL(nf_send_reset6);

net/ipv6/netfilter/nft_masq_ipv6.c

···
 	data[NFT_REG_VERDICT].verdict = verdict;
 }
 
-static int nft_masq_ipv6_init(const struct nft_ctx *ctx,
-			      const struct nft_expr *expr,
-			      const struct nlattr * const tb[])
-{
-	int err;
-
-	err = nft_masq_init(ctx, expr, tb);
-	if (err < 0)
-		return err;
-
-	nf_nat_masquerade_ipv6_register_notifier();
-	return 0;
-}
-
-static void nft_masq_ipv6_destroy(const struct nft_ctx *ctx,
-				  const struct nft_expr *expr)
-{
-	nf_nat_masquerade_ipv6_unregister_notifier();
-}
-
 static struct nft_expr_type nft_masq_ipv6_type;
 static const struct nft_expr_ops nft_masq_ipv6_ops = {
 	.type		= &nft_masq_ipv6_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_masq)),
 	.eval		= nft_masq_ipv6_eval,
-	.init		= nft_masq_ipv6_init,
-	.destroy	= nft_masq_ipv6_destroy,
+	.init		= nft_masq_init,
 	.dump		= nft_masq_dump,
 };
 
···
 
 static int __init nft_masq_ipv6_module_init(void)
 {
-	return nft_register_expr(&nft_masq_ipv6_type);
+	int ret;
+
+	ret = nft_register_expr(&nft_masq_ipv6_type);
+	if (ret < 0)
+		return ret;
+
+	nf_nat_masquerade_ipv6_register_notifier();
+
+	return ret;
 }
 
 static void __exit nft_masq_ipv6_module_exit(void)
 {
 	nft_unregister_expr(&nft_masq_ipv6_type);
+	nf_nat_masquerade_ipv6_unregister_notifier();
 }
 
 module_init(nft_masq_ipv6_module_init);

net/netfilter/ipset/ip_set_hash_netiface.c

···
 #define SRCDIR		(opt->flags & IPSET_DIM_TWO_SRC)
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		const struct nf_bridge_info *nf_bridge = skb->nf_bridge;
 
 		if (!nf_bridge)
···
 	ip6_netmask(&e.ip, e.cidr);
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		const struct nf_bridge_info *nf_bridge = skb->nf_bridge;
 
 		if (!nf_bridge)

net/netfilter/nf_log_common.c

···
 	       '0' + loginfo->u.log.level, prefix,
 	       in ? in->name : "",
 	       out ? out->name : "");
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (skb->nf_bridge) {
 		const struct net_device *physindev;
 		const struct net_device *physoutdev;

net/netfilter/nf_queue.c

···
 		dev_put(entry->indev);
 	if (entry->outdev)
 		dev_put(entry->outdev);
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (entry->skb->nf_bridge) {
 		struct nf_bridge_info *nf_bridge = entry->skb->nf_bridge;
 
···
 		dev_hold(entry->indev);
 	if (entry->outdev)
 		dev_hold(entry->outdev);
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (entry->skb->nf_bridge) {
 		struct nf_bridge_info *nf_bridge = entry->skb->nf_bridge;
 		struct net_device *physdev;

net/netfilter/nf_tables_api.c

···
 {
 	unregister_pernet_subsys(&nf_tables_net_ops);
 	nfnetlink_subsys_unregister(&nf_tables_subsys);
+	rcu_barrier();
 	nf_tables_core_module_exit();
 	kfree(info);
 }

net/netfilter/nfnetlink_log.c

···
 
 #include <linux/atomic.h>
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 #include "../bridge/br_private.h"
 #endif
 
···
 		goto nla_put_failure;
 
 	if (indev) {
-#ifndef CONFIG_BRIDGE_NETFILTER
+#if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		if (nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV,
 				 htonl(indev->ifindex)))
 			goto nla_put_failure;
···
 	}
 
 	if (outdev) {
-#ifndef CONFIG_BRIDGE_NETFILTER
+#if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		if (nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV,
 				 htonl(outdev->ifindex)))
 			goto nla_put_failure;
···
 		+ nla_total_size(sizeof(struct nfulnl_msg_packet_hdr))
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
 #endif

net/netfilter/nfnetlink_queue_core.c

···
 
 #include <linux/atomic.h>
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 #include "../bridge/br_private.h"
 #endif
 
···
 		+ nla_total_size(sizeof(struct nfqnl_msg_packet_hdr))
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
 #endif
···
 
 	indev = entry->indev;
 	if (indev) {
-#ifndef CONFIG_BRIDGE_NETFILTER
+#if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		if (nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(indev->ifindex)))
 			goto nla_put_failure;
 #else
···
 	}
 
 	if (outdev) {
-#ifndef CONFIG_BRIDGE_NETFILTER
+#if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(outdev->ifindex)))
 			goto nla_put_failure;
 #else
···
 	return NULL;
 }
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 /* When called from bridge netfilter, skb->data must point to MAC header
  * before calling skb_gso_segment(). Else, original MAC header is lost
  * and segmented skbs will be sent to wrong destination.
···
 	if (entry->outdev)
 		if (entry->outdev->ifindex == ifindex)
 			return 1;
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (entry->skb->nf_bridge) {
 		if (entry->skb->nf_bridge->physindev &&
 		    entry->skb->nf_bridge->physindev->ifindex == ifindex)

net/netfilter/nft_compat.c

···
 
 static void target_compat_from_user(struct xt_target *t, void *in, void *out)
 {
-#ifdef CONFIG_COMPAT
-	if (t->compat_from_user) {
-		int pad;
+	int pad;
 
-		t->compat_from_user(out, in);
-		pad = XT_ALIGN(t->targetsize) - t->targetsize;
-		if (pad > 0)
-			memset(out + t->targetsize, 0, pad);
-	} else
-#endif
-		memcpy(out, in, XT_ALIGN(t->targetsize));
-}
-
-static inline int nft_compat_target_offset(struct xt_target *target)
-{
-#ifdef CONFIG_COMPAT
-	return xt_compat_target_offset(target);
-#else
-	return 0;
-#endif
+	memcpy(out, in, t->targetsize);
+	pad = XT_ALIGN(t->targetsize) - t->targetsize;
+	if (pad > 0)
+		memset(out + t->targetsize, 0, pad);
 }
 
 static const struct nla_policy nft_rule_compat_policy[NFTA_RULE_COMPAT_MAX + 1] = {
···
 	module_put(target->me);
 }
 
-static int
-target_dump_info(struct sk_buff *skb, const struct xt_target *t, const void *in)
-{
-	int ret;
-
-#ifdef CONFIG_COMPAT
-	if (t->compat_to_user) {
-		mm_segment_t old_fs;
-		void *out;
-
-		out = kmalloc(XT_ALIGN(t->targetsize), GFP_ATOMIC);
-		if (out == NULL)
-			return -ENOMEM;
-
-		/* We want to reuse existing compat_to_user */
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		t->compat_to_user(out, in);
-		set_fs(old_fs);
-		ret = nla_put(skb, NFTA_TARGET_INFO, XT_ALIGN(t->targetsize), out);
-		kfree(out);
-	} else
-#endif
-		ret = nla_put(skb, NFTA_TARGET_INFO, XT_ALIGN(t->targetsize), in);
-
-	return ret;
-}
-
 static int nft_target_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct xt_target *target = expr->ops->data;
···
 
 	if (nla_put_string(skb, NFTA_TARGET_NAME, target->name) ||
 	    nla_put_be32(skb, NFTA_TARGET_REV, htonl(target->revision)) ||
-	    target_dump_info(skb, target, info))
+	    nla_put(skb, NFTA_TARGET_INFO, XT_ALIGN(target->targetsize), info))
 		goto nla_put_failure;
 
 	return 0;
···
 
 static void match_compat_from_user(struct xt_match *m, void *in, void *out)
 {
-#ifdef CONFIG_COMPAT
-	if (m->compat_from_user) {
-		int pad;
+	int pad;
 
-		m->compat_from_user(out, in);
-		pad = XT_ALIGN(m->matchsize) - m->matchsize;
-		if (pad > 0)
-			memset(out + m->matchsize, 0, pad);
-	} else
-#endif
-		memcpy(out, in, XT_ALIGN(m->matchsize));
+	memcpy(out, in, m->matchsize);
+	pad = XT_ALIGN(m->matchsize) - m->matchsize;
+	if (pad > 0)
+		memset(out + m->matchsize, 0, pad);
 }
 
 static int
···
 	module_put(match->me);
 }
 
-static int
-match_dump_info(struct sk_buff *skb, const struct xt_match *m, const void *in)
-{
-	int ret;
-
-#ifdef CONFIG_COMPAT
-	if (m->compat_to_user) {
-		mm_segment_t old_fs;
-		void *out;
-
-		out = kmalloc(XT_ALIGN(m->matchsize), GFP_ATOMIC);
-		if (out == NULL)
-			return -ENOMEM;
-
-		/* We want to reuse existing compat_to_user */
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		m->compat_to_user(out, in);
-		set_fs(old_fs);
-		ret = nla_put(skb, NFTA_MATCH_INFO, XT_ALIGN(m->matchsize), out);
-		kfree(out);
-	} else
-#endif
-		ret = nla_put(skb, NFTA_MATCH_INFO, XT_ALIGN(m->matchsize), in);
-
-	return ret;
-}
-
-static inline int nft_compat_match_offset(struct xt_match *match)
-{
-#ifdef CONFIG_COMPAT
-	return xt_compat_match_offset(match);
-#else
-	return 0;
-#endif
-}
-
 static int nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	void *info = nft_expr_priv(expr);
···
 
 	if (nla_put_string(skb, NFTA_MATCH_NAME, match->name) ||
 	    nla_put_be32(skb, NFTA_MATCH_REV, htonl(match->revision)) ||
-	    match_dump_info(skb, match, info))
+	    nla_put(skb, NFTA_MATCH_INFO, XT_ALIGN(match->matchsize), info))
 		goto nla_put_failure;
 
 	return 0;
···
 		return ERR_PTR(-ENOMEM);
 
 	nft_match->ops.type = &nft_match_type;
-	nft_match->ops.size = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize) +
-					    nft_compat_match_offset(match));
+	nft_match->ops.size = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize));
 	nft_match->ops.eval = nft_match_eval;
 	nft_match->ops.init = nft_match_init;
 	nft_match->ops.destroy = nft_match_destroy;
···
 		return ERR_PTR(-ENOMEM);
 
 	nft_target->ops.type = &nft_target_type;
-	nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize) +
-					     nft_compat_target_offset(target));
+	nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize));
 	nft_target->ops.eval = nft_target_eval;
 	nft_target->ops.init = nft_target_init;
 	nft_target->ops.destroy = nft_target_destroy;

net/netfilter/nft_reject.c

···
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nft_reject.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
 
 const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = {
 	[NFTA_REJECT_TYPE]		= { .type = NLA_U32 },
···
 	return -1;
 }
 EXPORT_SYMBOL_GPL(nft_reject_dump);
+
+static u8 icmp_code_v4[NFT_REJECT_ICMPX_MAX] = {
+	[NFT_REJECT_ICMPX_NO_ROUTE]		= ICMP_NET_UNREACH,
+	[NFT_REJECT_ICMPX_PORT_UNREACH]		= ICMP_PORT_UNREACH,
+	[NFT_REJECT_ICMPX_HOST_UNREACH]		= ICMP_HOST_UNREACH,
+	[NFT_REJECT_ICMPX_ADMIN_PROHIBITED]	= ICMP_PKT_FILTERED,
+};
+
+int nft_reject_icmp_code(u8 code)
+{
+	if (code > NFT_REJECT_ICMPX_MAX)
+		return -EINVAL;
+
+	return icmp_code_v4[code];
+}
+
+EXPORT_SYMBOL_GPL(nft_reject_icmp_code);
+
+
+static u8 icmp_code_v6[NFT_REJECT_ICMPX_MAX] = {
+	[NFT_REJECT_ICMPX_NO_ROUTE]		= ICMPV6_NOROUTE,
+	[NFT_REJECT_ICMPX_PORT_UNREACH]		= ICMPV6_PORT_UNREACH,
+	[NFT_REJECT_ICMPX_HOST_UNREACH]		= ICMPV6_ADDR_UNREACH,
+	[NFT_REJECT_ICMPX_ADMIN_PROHIBITED]	= ICMPV6_ADM_PROHIBITED,
+};
+
+int nft_reject_icmpv6_code(u8 code)
+{
+	if (code > NFT_REJECT_ICMPX_MAX)
+		return -EINVAL;
+
+	return icmp_code_v6[code];
+}
+
+EXPORT_SYMBOL_GPL(nft_reject_icmpv6_code);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Patrick McHardy <[e-mail]>");

net/netfilter/nft_reject_inet.c

···
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nft_reject.h>
+#include <net/netfilter/ipv4/nf_reject.h>
+#include <net/netfilter/ipv6/nf_reject.h>
 
 static void nft_reject_inet_eval(const struct nft_expr *expr,
 				 struct nft_data data[NFT_REG_MAX + 1],
 				 const struct nft_pktinfo *pkt)
 {
+	struct nft_reject *priv = nft_expr_priv(expr);
+	struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out);
+
 	switch (pkt->ops->pf) {
 	case NFPROTO_IPV4:
-		return nft_reject_ipv4_eval(expr, data, pkt);
+		switch (priv->type) {
+		case NFT_REJECT_ICMP_UNREACH:
+			nf_send_unreach(pkt->skb, priv->icmp_code);
+			break;
+		case NFT_REJECT_TCP_RST:
+			nf_send_reset(pkt->skb, pkt->ops->hooknum);
+			break;
+		case NFT_REJECT_ICMPX_UNREACH:
+			nf_send_unreach(pkt->skb,
+					nft_reject_icmp_code(priv->icmp_code));
+			break;
+		}
+		break;
 	case NFPROTO_IPV6:
-		return nft_reject_ipv6_eval(expr, data, pkt);
+		switch (priv->type) {
+		case NFT_REJECT_ICMP_UNREACH:
+			nf_send_unreach6(net, pkt->skb, priv->icmp_code,
+					 pkt->ops->hooknum);
+			break;
+		case NFT_REJECT_TCP_RST:
+			nf_send_reset6(net, pkt->skb, pkt->ops->hooknum);
+			break;
+		case NFT_REJECT_ICMPX_UNREACH:
+			nf_send_unreach6(net, pkt->skb,
+					 nft_reject_icmpv6_code(priv->icmp_code),
+					 pkt->ops->hooknum);
+			break;
+		}
+		break;
 	}
+	data[NFT_REG_VERDICT].verdict = NF_DROP;
+}
+
+static int nft_reject_inet_init(const struct nft_ctx *ctx,
+				const struct nft_expr *expr,
+				const struct nlattr * const tb[])
+{
+	struct nft_reject *priv = nft_expr_priv(expr);
+	int icmp_code;
+
+	if (tb[NFTA_REJECT_TYPE] == NULL)
+		return -EINVAL;
+
+	priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+	case NFT_REJECT_ICMPX_UNREACH:
+		if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
+			return -EINVAL;
+
+		icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
+		if (priv->type == NFT_REJECT_ICMPX_UNREACH &&
+		    icmp_code > NFT_REJECT_ICMPX_MAX)
+			return -EINVAL;
+
+		priv->icmp_code = icmp_code;
+		break;
+	case NFT_REJECT_TCP_RST:
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int nft_reject_inet_dump(struct sk_buff *skb,
+				const struct nft_expr *expr)
+{
+	const struct nft_reject *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type)))
+		goto nla_put_failure;
+
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+	case NFT_REJECT_ICMPX_UNREACH:
+		if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
+			goto nla_put_failure;
+		break;
+	}
+
+	return 0;
+
+nla_put_failure:
+	return -1;
 }
 
 static struct nft_expr_type nft_reject_inet_type;
···
 	.type		= &nft_reject_inet_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
 	.eval		= nft_reject_inet_eval,
-	.init		= nft_reject_init,
-	.dump		= nft_reject_dump,
+	.init		= nft_reject_inet_init,
+	.dump		= nft_reject_inet_dump,
 };
 
 static struct nft_expr_type nft_reject_inet_type __read_mostly = {

net/netfilter/xt_physdev.c

···
 #include <linux/netfilter_bridge.h>
 #include <linux/netfilter/xt_physdev.h>
 #include <linux/netfilter/x_tables.h>
+#include <net/netfilter/br_netfilter.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Bart De Schuymer <[e-mail]>");
···
 static int physdev_mt_check(const struct xt_mtchk_param *par)
 {
 	const struct xt_physdev_info *info = par->matchinfo;
+
+	br_netfilter_enable();
 
 	if (!(info->bitmask & XT_PHYSDEV_OP_MASK) ||
 	    info->bitmask & ~XT_PHYSDEV_OP_MASK)