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, more relevant updates in this batch are:

1) Add Maglev support to IPVS. Moreover, store lastest server weight in
   IPVS since this is needed by maglev, patches from from Inju Song.

2) Preparation works to add iptables flowtable support, patches
   from Felix Fietkau.

3) Hand over flows back to conntrack slow path in case of TCP RST/FIN
   packet is seen via new teardown state, also from Felix.

4) Add support for extended netlink error reporting for nf_tables.

5) Support for larger timeouts that 23 days in nf_tables, patch from
   Florian Westphal.

6) Always set an upper limit to dynamic sets, also from Florian.

7) Allow number generator to make map lookups, from Laura Garcia.

8) Use hash_32() instead of opencode hashing in IPVS, from Vicent Bernat.

9) Extend ip6tables SRH match to support previous, next and last SID,
   from Ahmed Abdelsalam.

10) Move Passive OS fingerprint nf_osf.c, from Fernando Fernandez.

11) Expose nf_conntrack_max through ctnetlink, from Florent Fourcot.

12) Several housekeeping patches for xt_NFLOG, x_tables and ebtables,
   from Taehee Yoo.

13) Unify meta bridge with core nft_meta, then make nft_meta built-in.
   Make rt and exthdr built-in too, again from Florian.

14) Missing initialization of tbl->entries in IPVS, from Cong Wang.
====================

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

14 files changed, 81 insertions, 128 deletions

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 8df4ff798b04..4cf1ef935ed9 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -279,6 +279,27 @@ static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *
 	       !lwtunnel_cmp_encap(a->fib6_nh.nh_lwtstate, b->fib6_nh.nh_lwtstate);
 }
 
+static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
+{
+	struct inet6_dev *idev;
+	unsigned int mtu;
+
+	if (dst_metric_locked(dst, RTAX_MTU)) {
+		mtu = dst_metric_raw(dst, RTAX_MTU);
+		if (mtu)
+			return mtu;
+	}
+
+	mtu = IPV6_MIN_MTU;
+	rcu_read_lock();
+	idev = __in6_dev_get(dst->dev);
+	if (idev)
+		mtu = idev->cnf.mtu6;
+	rcu_read_unlock();
+
+	return mtu;
+}
+
 struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw,
 				   struct net_device *dev, struct sk_buff *skb,
 				   const void *daddr);
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index eb0bec043c96..0ac795b41ab8 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -668,6 +668,7 @@ struct ip_vs_dest {
 	volatile unsigned int	flags;		/* dest status flags */
 	atomic_t		conn_flags;	/* flags to copy to conn */
 	atomic_t		weight;		/* server weight */
+	atomic_t		last_weight;	/* server latest weight */
 
 	refcount_t		refcnt;		/* reference counter */
 	struct ip_vs_stats      stats;          /* statistics */
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 0a872a7c33c8..798558fd1681 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -960,8 +960,6 @@ 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,
diff --git a/include/net/netfilter/ipv4/nf_nat_masquerade.h b/include/net/netfilter/ipv4/nf_nat_masquerade.h
index ebd869473603..cd24be4c4a99 100644
--- a/include/net/netfilter/ipv4/nf_nat_masquerade.h
+++ b/include/net/netfilter/ipv4/nf_nat_masquerade.h
@@ -6,7 +6,7 @@
 
 unsigned int
 nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
-		       const struct nf_nat_range *range,
+		       const struct nf_nat_range2 *range,
 		       const struct net_device *out);
 
 void nf_nat_masquerade_ipv4_register_notifier(void);
diff --git a/include/net/netfilter/ipv6/nf_nat_masquerade.h b/include/net/netfilter/ipv6/nf_nat_masquerade.h
index 1ed4f2631ed6..0c3b5ebf0bb8 100644
--- a/include/net/netfilter/ipv6/nf_nat_masquerade.h
+++ b/include/net/netfilter/ipv6/nf_nat_masquerade.h
@@ -3,7 +3,7 @@
 #define _NF_NAT_MASQUERADE_IPV6_H_
 
 unsigned int
-nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
 		       const struct net_device *out);
 void nf_nat_masquerade_ipv6_register_notifier(void);
 void nf_nat_masquerade_ipv6_unregister_notifier(void);
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 833752dd0c58..ba9fa4592f2b 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -6,6 +6,7 @@
 #include <linux/netdevice.h>
 #include <linux/rhashtable.h>
 #include <linux/rcupdate.h>
+#include <linux/netfilter/nf_conntrack_tuple_common.h>
 #include <net/dst.h>
 
 struct nf_flowtable;
@@ -13,25 +14,24 @@ struct nf_flowtable;
 struct nf_flowtable_type {
 	struct list_head		list;
 	int				family;
-	void				(*gc)(struct work_struct *work);
+	int				(*init)(struct nf_flowtable *ft);
 	void				(*free)(struct nf_flowtable *ft);
-	const struct rhashtable_params	*params;
 	nf_hookfn			*hook;
 	struct module			*owner;
 };
 
 struct nf_flowtable {
+	struct list_head		list;
 	struct rhashtable		rhashtable;
 	const struct nf_flowtable_type	*type;
 	struct delayed_work		gc_work;
 };
 
 enum flow_offload_tuple_dir {
-	FLOW_OFFLOAD_DIR_ORIGINAL,
-	FLOW_OFFLOAD_DIR_REPLY,
-	__FLOW_OFFLOAD_DIR_MAX		= FLOW_OFFLOAD_DIR_REPLY,
+	FLOW_OFFLOAD_DIR_ORIGINAL = IP_CT_DIR_ORIGINAL,
+	FLOW_OFFLOAD_DIR_REPLY = IP_CT_DIR_REPLY,
+	FLOW_OFFLOAD_DIR_MAX = IP_CT_DIR_MAX
 };
-#define FLOW_OFFLOAD_DIR_MAX	(__FLOW_OFFLOAD_DIR_MAX + 1)
 
 struct flow_offload_tuple {
 	union {
@@ -55,6 +55,8 @@ struct flow_offload_tuple {
 
 	int				oifidx;
 
+	u16				mtu;
+
 	struct dst_entry		*dst_cache;
 };
 
@@ -66,6 +68,7 @@ struct flow_offload_tuple_rhash {
 #define FLOW_OFFLOAD_SNAT	0x1
 #define FLOW_OFFLOAD_DNAT	0x2
 #define FLOW_OFFLOAD_DYING	0x4
+#define FLOW_OFFLOAD_TEARDOWN	0x8
 
 struct flow_offload {
 	struct flow_offload_tuple_rhash		tuplehash[FLOW_OFFLOAD_DIR_MAX];
@@ -98,11 +101,14 @@ int nf_flow_table_iterate(struct nf_flowtable *flow_table,
 
 void nf_flow_table_cleanup(struct net *net, struct net_device *dev);
 
+int nf_flow_table_init(struct nf_flowtable *flow_table);
 void nf_flow_table_free(struct nf_flowtable *flow_table);
-void nf_flow_offload_work_gc(struct work_struct *work);
-extern const struct rhashtable_params nf_flow_offload_rhash_params;
 
-void flow_offload_dead(struct flow_offload *flow);
+void flow_offload_teardown(struct flow_offload *flow);
+static inline void flow_offload_dead(struct flow_offload *flow)
+{
+	flow->flags |= FLOW_OFFLOAD_DYING;
+}
 
 int nf_flow_snat_port(const struct flow_offload *flow,
 		      struct sk_buff *skb, unsigned int thoff,
diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index 207a467e7ca6..da3d601cadee 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -39,7 +39,7 @@ struct nf_conn_nat {
 
 /* Set up the info structure to map into this range. */
 unsigned int nf_nat_setup_info(struct nf_conn *ct,
-			       const struct nf_nat_range *range,
+			       const struct nf_nat_range2 *range,
 			       enum nf_nat_manip_type maniptype);
 
 extern unsigned int nf_nat_alloc_null_binding(struct nf_conn *ct,
diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h
index ce7c2b4e64bb..8bad2560576f 100644
--- a/include/net/netfilter/nf_nat_l3proto.h
+++ b/include/net/netfilter/nf_nat_l3proto.h
@@ -7,7 +7,7 @@ struct nf_nat_l3proto {
 	u8	l3proto;
 
 	bool	(*in_range)(const struct nf_conntrack_tuple *t,
-			    const struct nf_nat_range *range);
+			    const struct nf_nat_range2 *range);
 
 	u32 	(*secure_port)(const struct nf_conntrack_tuple *t, __be16);
 
@@ -33,7 +33,7 @@ struct nf_nat_l3proto {
 				  struct flowi *fl);
 
 	int	(*nlattr_to_range)(struct nlattr *tb[],
-				   struct nf_nat_range *range);
+				   struct nf_nat_range2 *range);
 };
 
 int nf_nat_l3proto_register(const struct nf_nat_l3proto *);
@@ -48,30 +48,26 @@ unsigned int nf_nat_ipv4_in(void *priv, struct sk_buff *skb,
 			    const struct nf_hook_state *state,
 			    unsigned int (*do_chain)(void *priv,
 						     struct sk_buff *skb,
-						     const struct nf_hook_state *state,
-						     struct nf_conn *ct));
+						     const struct nf_hook_state *state));
 
 unsigned int nf_nat_ipv4_out(void *priv, struct sk_buff *skb,
 			     const struct nf_hook_state *state,
 			     unsigned int (*do_chain)(void *priv,
 						      struct sk_buff *skb,
-						      const struct nf_hook_state *state,
-						      struct nf_conn *ct));
+						      const struct nf_hook_state *state));
 
 unsigned int nf_nat_ipv4_local_fn(void *priv,
 				  struct sk_buff *skb,
 				  const struct nf_hook_state *state,
 				  unsigned int (*do_chain)(void *priv,
 							   struct sk_buff *skb,
-							   const struct nf_hook_state *state,
-							   struct nf_conn *ct));
+							   const struct nf_hook_state *state));
 
 unsigned int nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
 			    const struct nf_hook_state *state,
 			    unsigned int (*do_chain)(void *priv,
 						     struct sk_buff *skb,
-						     const struct nf_hook_state *state,
-						     struct nf_conn *ct));
+						     const struct nf_hook_state *state));
 
 int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct,
 				    enum ip_conntrack_info ctinfo,
@@ -81,29 +77,25 @@ unsigned int nf_nat_ipv6_in(void *priv, struct sk_buff *skb,
 			    const struct nf_hook_state *state,
 			    unsigned int (*do_chain)(void *priv,
 						     struct sk_buff *skb,
-						     const struct nf_hook_state *state,
-						     struct nf_conn *ct));
+						     const struct nf_hook_state *state));
 
 unsigned int nf_nat_ipv6_out(void *priv, struct sk_buff *skb,
 			     const struct nf_hook_state *state,
 			     unsigned int (*do_chain)(void *priv,
 						      struct sk_buff *skb,
-						      const struct nf_hook_state *state,
-						      struct nf_conn *ct));
+						      const struct nf_hook_state *state));
 
 unsigned int nf_nat_ipv6_local_fn(void *priv,
 				  struct sk_buff *skb,
 				  const struct nf_hook_state *state,
 				  unsigned int (*do_chain)(void *priv,
 							   struct sk_buff *skb,
-							   const struct nf_hook_state *state,
-							   struct nf_conn *ct));
+							   const struct nf_hook_state *state));
 
 unsigned int nf_nat_ipv6_fn(void *priv, struct sk_buff *skb,
 			    const struct nf_hook_state *state,
 			    unsigned int (*do_chain)(void *priv,
 						     struct sk_buff *skb,
-						     const struct nf_hook_state *state,
-						     struct nf_conn *ct));
+						     const struct nf_hook_state *state));
 
 #endif /* _NF_NAT_L3PROTO_H */
diff --git a/include/net/netfilter/nf_nat_l4proto.h b/include/net/netfilter/nf_nat_l4proto.h
index 67835ff8a2d9..b4d6b29bca62 100644
--- a/include/net/netfilter/nf_nat_l4proto.h
+++ b/include/net/netfilter/nf_nat_l4proto.h
@@ -34,12 +34,12 @@ struct nf_nat_l4proto {
 	 */
 	void (*unique_tuple)(const struct nf_nat_l3proto *l3proto,
 			     struct nf_conntrack_tuple *tuple,
-			     const struct nf_nat_range *range,
+			     const struct nf_nat_range2 *range,
 			     enum nf_nat_manip_type maniptype,
 			     const struct nf_conn *ct);
 
 	int (*nlattr_to_range)(struct nlattr *tb[],
-			       struct nf_nat_range *range);
+			       struct nf_nat_range2 *range);
 };
 
 /* Protocol registration. */
@@ -72,11 +72,11 @@ bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple,
 
 void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
 				 struct nf_conntrack_tuple *tuple,
-				 const struct nf_nat_range *range,
+				 const struct nf_nat_range2 *range,
 				 enum nf_nat_manip_type maniptype,
 				 const struct nf_conn *ct, u16 *rover);
 
 int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[],
-				   struct nf_nat_range *range);
+				   struct nf_nat_range2 *range);
 
 #endif /*_NF_NAT_L4PROTO_H*/
diff --git a/include/net/netfilter/nf_nat_redirect.h b/include/net/netfilter/nf_nat_redirect.h
index 5ddabb08c472..c129aacc8ae8 100644
--- a/include/net/netfilter/nf_nat_redirect.h
+++ b/include/net/netfilter/nf_nat_redirect.h
@@ -7,7 +7,7 @@ nf_nat_redirect_ipv4(struct sk_buff *skb,
 		     const struct nf_nat_ipv4_multi_range_compat *mr,
 		     unsigned int hooknum);
 unsigned int
-nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
 		     unsigned int hooknum);
 
 #endif /* _NF_NAT_REDIRECT_H_ */
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index cd368d1b8cb8..435c9e3b9181 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -275,23 +275,6 @@ struct nft_set_estimate {
 	enum nft_set_class	space;
 };
 
-/**
- *      struct nft_set_type - nf_tables set type
- *
- *      @select_ops: function to select nft_set_ops
- *      @ops: default ops, used when no select_ops functions is present
- *      @list: used internally
- *      @owner: module reference
- */
-struct nft_set_type {
-	const struct nft_set_ops	*(*select_ops)(const struct nft_ctx *,
-						       const struct nft_set_desc *desc,
-						       u32 flags);
-	const struct nft_set_ops	*ops;
-	struct list_head		list;
-	struct module			*owner;
-};
-
 struct nft_set_ext;
 struct nft_expr;
 
@@ -310,7 +293,6 @@ struct nft_expr;
  *	@init: initialize private data of new set instance
  *	@destroy: destroy private data of set instance
  *	@elemsize: element private size
- *	@features: features supported by the implementation
  */
 struct nft_set_ops {
 	bool				(*lookup)(const struct net *net,
@@ -361,9 +343,23 @@ struct nft_set_ops {
 	void				(*destroy)(const struct nft_set *set);
 
 	unsigned int			elemsize;
+};
+
+/**
+ *      struct nft_set_type - nf_tables set type
+ *
+ *      @ops: set ops for this type
+ *      @list: used internally
+ *      @owner: module reference
+ *      @features: features supported by the implementation
+ */
+struct nft_set_type {
+	const struct nft_set_ops	ops;
+	struct list_head		list;
+	struct module			*owner;
 	u32				features;
-	const struct nft_set_type	*type;
 };
+#define to_set_type(o) container_of(o, struct nft_set_type, ops)
 
 int nft_register_set(struct nft_set_type *type);
 void nft_unregister_set(struct nft_set_type *type);
@@ -589,7 +585,7 @@ static inline u64 *nft_set_ext_timeout(const struct nft_set_ext *ext)
 	return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT);
 }
 
-static inline unsigned long *nft_set_ext_expiration(const struct nft_set_ext *ext)
+static inline u64 *nft_set_ext_expiration(const struct nft_set_ext *ext)
 {
 	return nft_set_ext(ext, NFT_SET_EXT_EXPIRATION);
 }
@@ -607,7 +603,7 @@ static inline struct nft_expr *nft_set_ext_expr(const struct nft_set_ext *ext)
 static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
 {
 	return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) &&
-	       time_is_before_eq_jiffies(*nft_set_ext_expiration(ext));
+	       time_is_before_eq_jiffies64(*nft_set_ext_expiration(ext));
 }
 
 static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set,
@@ -1015,9 +1011,9 @@ static inline void *nft_obj_data(const struct nft_object *obj)
 
 #define nft_expr_obj(expr)	*((struct nft_object **)nft_expr_priv(expr))
 
-struct nft_object *nf_tables_obj_lookup(const struct nft_table *table,
-					const struct nlattr *nla, u32 objtype,
-					u8 genmask);
+struct nft_object *nft_obj_lookup(const struct nft_table *table,
+				  const struct nlattr *nla, u32 objtype,
+				  u8 genmask);
 
 void nft_obj_notify(struct net *net, struct nft_table *table,
 		    struct nft_object *obj, u32 portid, u32 seq,
@@ -1106,12 +1102,9 @@ struct nft_flowtable {
 	struct nf_flowtable		data;
 };
 
-struct nft_flowtable *nf_tables_flowtable_lookup(const struct nft_table *table,
-						 const struct nlattr *nla,
-						 u8 genmask);
-void nft_flow_table_iterate(struct net *net,
-			    void (*iter)(struct nf_flowtable *flowtable, void *data),
-			    void *data);
+struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table,
+					   const struct nlattr *nla,
+					   u8 genmask);
 
 void nft_register_flowtable_type(struct nf_flowtable_type *type);
 void nft_unregister_flowtable_type(struct nf_flowtable_type *type);
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index ea5aab568be8..cd6915b6c054 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -10,6 +10,9 @@ extern struct nft_expr_type nft_byteorder_type;
 extern struct nft_expr_type nft_payload_type;
 extern struct nft_expr_type nft_dynset_type;
 extern struct nft_expr_type nft_range_type;
+extern struct nft_expr_type nft_meta_type;
+extern struct nft_expr_type nft_rt_type;
+extern struct nft_expr_type nft_exthdr_type;
 
 int nf_tables_core_module_init(void);
 void nf_tables_core_module_exit(void);
diff --git a/include/net/netfilter/nfnetlink_log.h b/include/net/netfilter/nfnetlink_log.h
index 612cfb63ac68..ea32a7d3cf1b 100644
--- a/include/net/netfilter/nfnetlink_log.h
+++ b/include/net/netfilter/nfnetlink_log.h
@@ -1,18 +1 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _KER_NFNETLINK_LOG_H
-#define _KER_NFNETLINK_LOG_H
-
-void
-nfulnl_log_packet(struct net *net,
-		  u_int8_t pf,
-		  unsigned int hooknum,
-		  const struct sk_buff *skb,
-		  const struct net_device *in,
-		  const struct net_device *out,
-		  const struct nf_loginfo *li_user,
-		  const char *prefix);
-
-#define NFULNL_COPY_DISABLED    0xff
-
-#endif /* _KER_NFNETLINK_LOG_H */
-
diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h
deleted file mode 100644
index 5c69e9b09388..000000000000
--- a/include/net/netfilter/nft_meta.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NFT_META_H_
-#define _NFT_META_H_
-
-struct nft_meta {
-	enum nft_meta_keys	key:8;
-	union {
-		enum nft_registers	dreg:8;
-		enum nft_registers	sreg:8;
-	};
-};
-
-extern const struct nla_policy nft_meta_policy[];
-
-int nft_meta_get_init(const struct nft_ctx *ctx,
-		      const struct nft_expr *expr,
-		      const struct nlattr * const tb[]);
-
-int nft_meta_set_init(const struct nft_ctx *ctx,
-		      const struct nft_expr *expr,
-		      const struct nlattr * const tb[]);
-
-int nft_meta_get_dump(struct sk_buff *skb,
-		      const struct nft_expr *expr);
-
-int nft_meta_set_dump(struct sk_buff *skb,
-		      const struct nft_expr *expr);
-
-void nft_meta_get_eval(const struct nft_expr *expr,
-		       struct nft_regs *regs,
-		       const struct nft_pktinfo *pkt);
-
-void nft_meta_set_eval(const struct nft_expr *expr,
-		       struct nft_regs *regs,
-		       const struct nft_pktinfo *pkt);
-
-void nft_meta_set_destroy(const struct nft_ctx *ctx,
-			  const struct nft_expr *expr);
-
-int nft_meta_set_validate(const struct nft_ctx *ctx,
-			  const struct nft_expr *expr,
-			  const struct nft_data **data);
-
-#endif