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 Netfilter/IPVS updates for your
net-next tree:

1) Free hooks via call_rcu to speed up netns release path, from
   Florian Westphal.

2) Reduce memory footprint of hook arrays, skip allocation if family is
   not present - useful in case decnet support is not compiled built-in.
   Patches from Florian Westphal.

3) Remove defensive check for malformed IPv4 - including ihl field - and
   IPv6 headers in x_tables and nf_tables.

4) Add generic flow table offload infrastructure for nf_tables, this
   includes the netlink control plane and support for IPv4, IPv6 and
   mixed IPv4/IPv6 dataplanes. This comes with NAT support too. This
   patchset adds the IPS_OFFLOAD conntrack status bit to indicate that
   this flow has been offloaded.

5) Add secpath matching support for nf_tables, from Florian.

6) Save some code bytes in the fast path for the nf_tables netdev,
   bridge and inet families.

7) Allow one single NAT hook per point and do not allow to register NAT
   hooks in nf_tables before the conntrack hook, patches from Florian.

8) Seven patches to remove the struct nf_af_info abstraction, instead
   we perform direct calls for IPv4 which is faster. IPv6 indirections
   are still needed to avoid dependencies with the 'ipv6' module, but
   these now reside in struct nf_ipv6_ops.

9) Seven patches to handle NFPROTO_INET from the Netfilter core,
   hence we can remove specific code in nf_tables to handle this
   pseudofamily.

10) No need for synchronize_net() call for nf_queue after conversion
    to hook arrays. Also from Florian.

11) Call cond_resched_rcu() when dumping large sets in ipset to avoid
    softlockup. Again from Florian.

12) Pass lockdep_nfnl_is_held() to rcu_dereference_protected(), patch
    from Florian Westphal.

13) Fix matching of counters in ipset, from Jozsef Kadlecsik.

14) Missing nfnl lock protection in the ip_set_net_exit path, also
    from Jozsef.

15) Move connlimit code that we can reuse from nf_tables into
    nf_conncount, from Florian Westhal.

And asorted cleanups:

16) Get rid of nft_dereference(), it only has one single caller.

17) Add nft_set_is_anonymous() helper function.

18) Remove NF_ARP_FORWARD leftover chain definition in nf_tables_arp.

19) Remove unnecessary comments in nf_conntrack_h323_asn1.c
    From Varsha Rao.

20) Remove useless parameters in frag_safe_skb_hp(), from Gao Feng.

21) Constify layer 4 conntrack protocol definitions, function
    parameters to register/unregister these protocol trackers, and
    timeouts. Patches from Florian Westphal.

22) Remove nlattr_size indirection, from Florian Westphal.

23) Add fall-through comments as -Wimplicit-fallthrough needs this,
    from Gustavo A. R. Silva.

24) Use swap() macro to exchange values in ipset, patch from
    Gustavo A. R. Silva.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netfilter.h

@@ -67,6 +67,7 @@ struct nf_hook_ops {
 	struct net_device	*dev;
 	void			*priv;
 	u_int8_t		pf;
+	bool			nat_hook;
 	unsigned int		hooknum;
 	/* Hooks are ordered in ascending priority. */
 	int			priority;
@@ -77,17 +78,28 @@ struct nf_hook_entry {
 	void				*priv;
 };
 
+struct nf_hook_entries_rcu_head {
+	struct rcu_head head;
+	void	*allocation;
+};
+
 struct nf_hook_entries {
 	u16				num_hook_entries;
 	/* padding */
 	struct nf_hook_entry		hooks[];
 
-	/* trailer: pointers to original orig_ops of each hook.
-	 *
-	 * This is not part of struct nf_hook_entry since its only
-	 * needed in slow path (hook register/unregister).
+	/* trailer: pointers to original orig_ops of each hook,
+	 * followed by rcu_head and scratch space used for freeing
+	 * the structure via call_rcu.
 	 *
+	 *   This is not part of struct nf_hook_entry since its only
+	 *   needed in slow path (hook register/unregister):
 	 * const struct nf_hook_ops     *orig_ops[]
+	 *
+	 *   For the same reason, we store this at end -- its
+	 *   only needed when a hook is deleted, not during
+	 *   packet path processing:
+	 * struct nf_hook_entries_rcu_head     head
 	 */
 };
 
@@ -184,7 +196,7 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net,
 			  struct net_device *indev, struct net_device *outdev,
 			  int (*okfn)(struct net *, struct sock *, struct sk_buff *))
 {
-	struct nf_hook_entries *hook_head;
+	struct nf_hook_entries *hook_head = NULL;
 	int ret = 1;
 
 #ifdef HAVE_JUMP_LABEL
@@ -195,7 +207,33 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net,
 #endif
 
 	rcu_read_lock();
-	hook_head = rcu_dereference(net->nf.hooks[pf][hook]);
+	switch (pf) {
+	case NFPROTO_IPV4:
+		hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]);
+		break;
+	case NFPROTO_IPV6:
+		hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]);
+		break;
+	case NFPROTO_ARP:
+#ifdef CONFIG_NETFILTER_FAMILY_ARP
+		hook_head = rcu_dereference(net->nf.hooks_arp[hook]);
+#endif
+		break;
+	case NFPROTO_BRIDGE:
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+		hook_head = rcu_dereference(net->nf.hooks_bridge[hook]);
+#endif
+		break;
+#if IS_ENABLED(CONFIG_DECNET)
+	case NFPROTO_DECNET:
+		hook_head = rcu_dereference(net->nf.hooks_decnet[hook]);
+		break;
+#endif
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+
 	if (hook_head) {
 		struct nf_hook_state state;
 
@@ -271,64 +309,16 @@ int skb_make_writable(struct sk_buff *skb, unsigned int writable_len);
 struct flowi;
 struct nf_queue_entry;
 
-struct nf_afinfo {
-	unsigned short	family;
-	__sum16		(*checksum)(struct sk_buff *skb, unsigned int hook,
-				    unsigned int dataoff, u_int8_t protocol);
-	__sum16		(*checksum_partial)(struct sk_buff *skb,
-					    unsigned int hook,
-					    unsigned int dataoff,
-					    unsigned int len,
-					    u_int8_t protocol);
-	int		(*route)(struct net *net, struct dst_entry **dst,
-				 struct flowi *fl, bool strict);
-	void		(*saveroute)(const struct sk_buff *skb,
-				     struct nf_queue_entry *entry);
-	int		(*reroute)(struct net *net, struct sk_buff *skb,
-				   const struct nf_queue_entry *entry);
-	int		route_key_size;
-};
-
-extern const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO];
-static inline const struct nf_afinfo *nf_get_afinfo(unsigned short family)
-{
-	return rcu_dereference(nf_afinfo[family]);
-}
-
-static inline __sum16
-nf_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff,
-	    u_int8_t protocol, unsigned short family)
-{
-	const struct nf_afinfo *afinfo;
-	__sum16 csum = 0;
-
-	rcu_read_lock();
-	afinfo = nf_get_afinfo(family);
-	if (afinfo)
-		csum = afinfo->checksum(skb, hook, dataoff, protocol);
-	rcu_read_unlock();
-	return csum;
-}
-
-static inline __sum16
-nf_checksum_partial(struct sk_buff *skb, unsigned int hook,
-		    unsigned int dataoff, unsigned int len,
-		    u_int8_t protocol, unsigned short family)
-{
-	const struct nf_afinfo *afinfo;
-	__sum16 csum = 0;
-
-	rcu_read_lock();
-	afinfo = nf_get_afinfo(family);
-	if (afinfo)
-		csum = afinfo->checksum_partial(skb, hook, dataoff, len,
-						protocol);
-	rcu_read_unlock();
-	return csum;
-}
+__sum16 nf_checksum(struct sk_buff *skb, unsigned int hook,
+		    unsigned int dataoff, u_int8_t protocol,
+		    unsigned short family);
 
-int nf_register_afinfo(const struct nf_afinfo *afinfo);
-void nf_unregister_afinfo(const struct nf_afinfo *afinfo);
+__sum16 nf_checksum_partial(struct sk_buff *skb, unsigned int hook,
+			    unsigned int dataoff, unsigned int len,
+			    u_int8_t protocol, unsigned short family);
+int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl,
+	     bool strict, unsigned short family);
+int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry);
 
 #include <net/flow.h>
 extern void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *);

include/linux/netfilter/ipset/ip_set.h

@@ -122,6 +122,8 @@ struct ip_set_ext {
 	u64 bytes;
 	char *comment;
 	u32 timeout;
+	u8 packets_op;
+	u8 bytes_op;
 };
 
 struct ip_set;
@@ -339,6 +341,10 @@ extern int ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[],
 				 struct ip_set_ext *ext);
 extern int ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set,
 				 const void *e, bool active);
+extern bool ip_set_match_extensions(struct ip_set *set,
+				    const struct ip_set_ext *ext,
+				    struct ip_set_ext *mext,
+				    u32 flags, void *data);
 
 static inline int
 ip_set_get_hostipaddr4(struct nlattr *nla, u32 *ipaddr)

include/linux/netfilter/ipset/ip_set_counter.h

@@ -34,20 +34,33 @@ ip_set_get_packets(const struct ip_set_counter *counter)
 	return (u64)atomic64_read(&(counter)->packets);
 }
 
+static inline bool
+ip_set_match_counter(u64 counter, u64 match, u8 op)
+{
+	switch (op) {
+	case IPSET_COUNTER_NONE:
+		return true;
+	case IPSET_COUNTER_EQ:
+		return counter == match;
+	case IPSET_COUNTER_NE:
+		return counter != match;
+	case IPSET_COUNTER_LT:
+		return counter < match;
+	case IPSET_COUNTER_GT:
+		return counter > match;
+	}
+	return false;
+}
+
 static inline void
 ip_set_update_counter(struct ip_set_counter *counter,
-		      const struct ip_set_ext *ext,
-		      struct ip_set_ext *mext, u32 flags)
+		      const struct ip_set_ext *ext, u32 flags)
 {
 	if (ext->packets != ULLONG_MAX &&
 	    !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) {
 		ip_set_add_bytes(ext->bytes, counter);
 		ip_set_add_packets(ext->packets, counter);
 	}
-	if (flags & IPSET_FLAG_MATCH_COUNTERS) {
-		mext->packets = ip_set_get_packets(counter);
-		mext->bytes = ip_set_get_bytes(counter);
-	}
 }
 
 static inline bool

include/linux/netfilter/x_tables.h

@@ -320,6 +320,8 @@ int xt_find_revision(u8 af, const char *name, u8 revision, int target,
 
 struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
 				    const char *name);
+struct xt_table *xt_request_find_table_lock(struct net *net, u_int8_t af,
+					    const char *name);
 void xt_table_unlock(struct xt_table *t);
 
 int xt_proto_init(struct net *net, u_int8_t af);

include/linux/netfilter_defs.h

@@ -4,7 +4,17 @@
 
 #include <uapi/linux/netfilter.h>
 
+/* in/out/forward only */
+#define NF_ARP_NUMHOOKS 3
+
+/* max hook is NF_DN_ROUTE (6), also see uapi/linux/netfilter_decnet.h */
+#define NF_DN_NUMHOOKS 7
+
+#if IS_ENABLED(CONFIG_DECNET)
 /* Largest hook number + 1, see uapi/linux/netfilter_decnet.h */
-#define NF_MAX_HOOKS 8
+#define NF_MAX_HOOKS	NF_DN_NUMHOOKS
+#else
+#define NF_MAX_HOOKS	NF_INET_NUMHOOKS
+#endif
 
 #endif

include/linux/netfilter_ipv4.h

@@ -6,7 +6,53 @@
 
 #include <uapi/linux/netfilter_ipv4.h>
 
+/* Extra routing may needed on local out, as the QUEUE target never returns
+ * control to the table.
+ */
+struct ip_rt_info {
+	__be32 daddr;
+	__be32 saddr;
+	u_int8_t tos;
+	u_int32_t mark;
+};
+
 int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned addr_type);
+
+struct nf_queue_entry;
+
+#ifdef CONFIG_INET
 __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
 		       unsigned int dataoff, u_int8_t protocol);
+__sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook,
+			       unsigned int dataoff, unsigned int len,
+			       u_int8_t protocol);
+int nf_ip_route(struct net *net, struct dst_entry **dst, struct flowi *fl,
+		bool strict);
+int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry);
+#else
+static inline __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
+				     unsigned int dataoff, u_int8_t protocol)
+{
+	return 0;
+}
+static inline __sum16 nf_ip_checksum_partial(struct sk_buff *skb,
+					     unsigned int hook,
+					     unsigned int dataoff,
+					     unsigned int len,
+					     u_int8_t protocol)
+{
+	return 0;
+}
+static inline int nf_ip_route(struct net *net, struct dst_entry **dst,
+			      struct flowi *fl, bool strict)
+{
+	return -EOPNOTSUPP;
+}
+static inline int nf_ip_reroute(struct sk_buff *skb,
+				const struct nf_queue_entry *entry)
+{
+	return -EOPNOTSUPP;
+}
+#endif /* CONFIG_INET */
+
 #endif /*__LINUX_IP_NETFILTER_H*/

include/linux/netfilter_ipv6.h

@@ -9,6 +9,17 @@
 
 #include <uapi/linux/netfilter_ipv6.h>
 
+/* Extra routing may needed on local out, as the QUEUE target never returns
+ * control to the table.
+ */
+struct ip6_rt_info {
+	struct in6_addr daddr;
+	struct in6_addr saddr;
+	u_int32_t mark;
+};
+
+struct nf_queue_entry;
+
 /*
  * Hook functions for ipv6 to allow xt_* modules to be built-in even
  * if IPv6 is a module.
@@ -19,6 +30,14 @@ struct nf_ipv6_ops {
 	void (*route_input)(struct sk_buff *skb);
 	int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb,
 			int (*output)(struct net *, struct sock *, struct sk_buff *));
+	__sum16 (*checksum)(struct sk_buff *skb, unsigned int hook,
+			    unsigned int dataoff, u_int8_t protocol);
+	__sum16 (*checksum_partial)(struct sk_buff *skb, unsigned int hook,
+				    unsigned int dataoff, unsigned int len,
+				    u_int8_t protocol);
+	int (*route)(struct net *net, struct dst_entry **dst, struct flowi *fl,
+		     bool strict);
+	int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry);
 };
 
 #ifdef CONFIG_NETFILTER

include/net/ip_vs.h

@@ -69,8 +69,7 @@ struct ip_vs_iphdr {
 };
 
 static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
-				      int len, void *buffer,
-				      const struct ip_vs_iphdr *ipvsh)
+				      int len, void *buffer)
 {
 	return skb_header_pointer(skb, offset, len, buffer);
 }

include/net/ipv6.h

@@ -969,6 +969,8 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk)
 			      &inet6_sk(sk)->cork);
 }
 
+unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst);
+
 int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst,
 		   struct flowi6 *fl6);
 struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6,

include/net/netfilter/ipv4/nf_conntrack_ipv4.h

@@ -13,17 +13,17 @@
 
 const extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4;
 
-extern struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4;
-extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4;
-extern struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp;
+extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4;
+extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4;
+extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp;
 #ifdef CONFIG_NF_CT_PROTO_DCCP
-extern struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4;
+extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4;
 #endif
 #ifdef CONFIG_NF_CT_PROTO_SCTP
-extern struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4;
+extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4;
 #endif
 #ifdef CONFIG_NF_CT_PROTO_UDPLITE
-extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4;
+extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4;
 #endif
 
 int nf_conntrack_ipv4_compat_init(void);