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

Pablo Neira Ayuso says:

====================
Netfilter updates for net-next

The following patchset contains a second batch of Netfilter updates for
your net-next tree. This includes a rework of the core hook
infrastructure that improves Netfilter performance by ~15% according to
synthetic benchmarks. Then, a large batch with ipset updates, including
a new hash:ipmac set type, via Jozsef Kadlecsik. This also includes a
couple of assorted updates.

Regarding the core hook infrastructure rework to improve performance,
using this simple drop-all packets ruleset from ingress:

        nft add table netdev x
        nft add chain netdev x y { type filter hook ingress device eth0 priority 0\; }
        nft add rule netdev x y drop

And generating traffic through Jesper Brouer's
samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh script using -i
option. perf report shows nf_tables calls in its top 10:

    17.30%  kpktgend_0   [nf_tables]            [k] nft_do_chain
    15.75%  kpktgend_0   [kernel.vmlinux]       [k] __netif_receive_skb_core
    10.39%  kpktgend_0   [nf_tables_netdev]     [k] nft_do_chain_netdev

I'm measuring here an improvement of ~15% in performance with this
patchset, so we got +2.5Mpps more. I have used my old laptop Intel(R)
Core(TM) i5-3320M CPU @ 2.60GHz 4-cores.

This rework contains more specifically, in strict order, these patches:

1) Remove compile-time debugging from core.

2) Remove obsolete comments that predate the rcu era. These days it is
   well known that a Netfilter hook always runs under rcu_read_lock().

3) Remove threshold handling, this is only used by br_netfilter too.
   We already have specific code to handle this from br_netfilter,
   so remove this code from the core path.

4) Deprecate NF_STOP, as this is only used by br_netfilter.

5) Place nf_state_hook pointer into xt_action_param structure, so
   this structure fits into one single cacheline according to pahole.
   This also implicit affects nftables since it also relies on the
   xt_action_param structure.

6) Move state->hook_entries into nf_queue entry. The hook_entries
   pointer is only required by nf_queue(), so we can store this in the
   queue entry instead.

7) use switch() statement to handle verdict cases.

8) Remove hook_entries field from nf_hook_state structure, this is only
   required by nf_queue, so store it in nf_queue_entry structure.

9) Merge nf_iterate() into nf_hook_slow() that results in a much more
   simple and readable function.

10) Handle NF_REPEAT away from the core, so far the only client is
    nf_conntrack_in() and we can restart the packet processing using a
    simple goto to jump back there when the TCP requires it.
    This update required a second pass to fix fallout, fix from
    Arnd Bergmann.

11) Set random seed from nft_hash when no seed is specified from
    userspace.

12) Simplify nf_tables expression registration, in a much smarter way
    to save lots of boiler plate code, by Liping Zhang.

13) Simplify layer 4 protocol conntrack tracker registration, from
    Davide Caratti.

14) Missing CONFIG_NF_SOCKET_IPV4 dependency for udp4_lib_lookup, due
    to recent generalization of the socket infrastructure, from Arnd
    Bergmann.

15) Then, the ipset batch from Jozsef, he describes it as it follows:

* Cleanup: Remove extra whitespaces in ip_set.h
* Cleanup: Mark some of the helpers arguments as const in ip_set.h
* Cleanup: Group counter helper functions together in ip_set.h
* struct ip_set_skbinfo is introduced instead of open coded fields
  in skbinfo get/init helper funcions.
* Use kmalloc() in comment extension helper instead of kzalloc()
  because it is unnecessary to zero out the area just before
  explicit initialization.
* Cleanup: Split extensions into separate files.
* Cleanup: Separate memsize calculation code into dedicated function.
* Cleanup: group ip_set_put_extensions() and ip_set_get_extensions()
  together.
* Add element count to hash headers by Eric B Munson.
* Add element count to all set types header for uniform output
  across all set types.
* Count non-static extension memory into memsize calculation for
  userspace.
* Cleanup: Remove redundant mtype_expire() arguments, because
  they can be get from other parameters.
* Cleanup: Simplify mtype_expire() for hash types by removing
  one level of intendation.
* Make NLEN compile time constant for hash types.
* Make sure element data size is a multiple of u32 for the hash set
  types.
* Optimize hash creation routine, exit as early as possible.
* Make struct htype per ipset family so nets array becomes fixed size
  and thus simplifies the struct htype allocation.
* Collapse same condition body into a single one.
* Fix reported memory size for hash:* types, base hash bucket structure
  was not taken into account.
* hash:ipmac type support added to ipset by Tomasz Chilinski.
* Use setup_timer() and mod_timer() instead of init_timer()
  by Muhammad Falak R Wani, individually for the set type families.

16) Remove useless connlabel field in struct netns_ct, patch from
    Florian Westphal.

17) xt_find_table_lock() doesn't return ERR_PTR() anymore, so simplify
    {ip,ip6,arp}tables code that uses this.
====================

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

include/net/netfilter/nf_conntrack_l4proto.h

@@ -125,14 +125,24 @@ struct nf_conntrack_l4proto *nf_ct_l4proto_find_get(u_int16_t l3proto,
 void nf_ct_l4proto_put(struct nf_conntrack_l4proto *p);
 
 /* Protocol pernet registration. */
+int nf_ct_l4proto_pernet_register_one(struct net *net,
+				      struct nf_conntrack_l4proto *proto);
+void nf_ct_l4proto_pernet_unregister_one(struct net *net,
+					 struct nf_conntrack_l4proto *proto);
 int nf_ct_l4proto_pernet_register(struct net *net,
-				  struct nf_conntrack_l4proto *proto);
+				  struct nf_conntrack_l4proto *proto[],
+				  unsigned int num_proto);
 void nf_ct_l4proto_pernet_unregister(struct net *net,
-				     struct nf_conntrack_l4proto *proto);
+				     struct nf_conntrack_l4proto *proto[],
+				     unsigned int num_proto);
 
 /* Protocol global registration. */
-int nf_ct_l4proto_register(struct nf_conntrack_l4proto *proto);
-void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *proto);
+int nf_ct_l4proto_register_one(struct nf_conntrack_l4proto *proto);
+void nf_ct_l4proto_unregister_one(struct nf_conntrack_l4proto *proto);
+int nf_ct_l4proto_register(struct nf_conntrack_l4proto *proto[],
+			   unsigned int num_proto);
+void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *proto[],
+			      unsigned int num_proto);
 
 /* Generic netlink helpers */
 int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb,

include/net/netfilter/nf_queue.h

@@ -12,6 +12,7 @@ struct nf_queue_entry {
 	unsigned int		id;
 
 	struct nf_hook_state	state;
+	struct nf_hook_entry	*hook;
 	u16			size; /* sizeof(entry) + saved route keys */
 
 	/* extra space to store route keys */

include/net/netfilter/nf_tables.h

@@ -14,27 +14,43 @@
 
 struct nft_pktinfo {
 	struct sk_buff			*skb;
-	struct net			*net;
-	const struct net_device		*in;
-	const struct net_device		*out;
-	u8				pf;
-	u8				hook;
 	bool				tprot_set;
 	u8				tprot;
 	/* for x_tables compatibility */
 	struct xt_action_param		xt;
 };
 
+static inline struct net *nft_net(const struct nft_pktinfo *pkt)
+{
+	return pkt->xt.state->net;
+}
+
+static inline unsigned int nft_hook(const struct nft_pktinfo *pkt)
+{
+	return pkt->xt.state->hook;
+}
+
+static inline u8 nft_pf(const struct nft_pktinfo *pkt)
+{
+	return pkt->xt.state->pf;
+}
+
+static inline const struct net_device *nft_in(const struct nft_pktinfo *pkt)
+{
+	return pkt->xt.state->in;
+}
+
+static inline const struct net_device *nft_out(const struct nft_pktinfo *pkt)
+{
+	return pkt->xt.state->out;
+}
+
 static inline void nft_set_pktinfo(struct nft_pktinfo *pkt,
 				   struct sk_buff *skb,
 				   const struct nf_hook_state *state)
 {
 	pkt->skb = skb;
-	pkt->net = pkt->xt.net = state->net;
-	pkt->in = pkt->xt.in = state->in;
-	pkt->out = pkt->xt.out = state->out;
-	pkt->hook = pkt->xt.hooknum = state->hook;
-	pkt->pf = pkt->xt.family = state->pf;
+	pkt->xt.state = state;
 }
 
 static inline void nft_set_pktinfo_proto_unspec(struct nft_pktinfo *pkt,

include/net/netfilter/nf_tables_core.h

@@ -1,12 +1,18 @@
 #ifndef _NET_NF_TABLES_CORE_H
 #define _NET_NF_TABLES_CORE_H
 
+extern struct nft_expr_type nft_imm_type;
+extern struct nft_expr_type nft_cmp_type;
+extern struct nft_expr_type nft_lookup_type;
+extern struct nft_expr_type nft_bitwise_type;
+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;
+
 int nf_tables_core_module_init(void);
 void nf_tables_core_module_exit(void);
 
-int nft_immediate_module_init(void);
-void nft_immediate_module_exit(void);
-
 struct nft_cmp_fast_expr {
 	u32			data;
 	enum nft_registers	sreg:8;
@@ -25,24 +31,6 @@ static inline u32 nft_cmp_fast_mask(unsigned int len)
 
 extern const struct nft_expr_ops nft_cmp_fast_ops;
 
-int nft_cmp_module_init(void);
-void nft_cmp_module_exit(void);
-
-int nft_range_module_init(void);
-void nft_range_module_exit(void);
-
-int nft_lookup_module_init(void);
-void nft_lookup_module_exit(void);
-
-int nft_dynset_module_init(void);
-void nft_dynset_module_exit(void);
-
-int nft_bitwise_module_init(void);
-void nft_bitwise_module_exit(void);
-
-int nft_byteorder_module_init(void);
-void nft_byteorder_module_exit(void);
-
 struct nft_payload {
 	enum nft_payload_bases	base:8;
 	u8			offset;
@@ -62,7 +50,4 @@ struct nft_payload_set {
 extern const struct nft_expr_ops nft_payload_fast_ops;
 extern struct static_key_false nft_trace_enabled;
 
-int nft_payload_module_init(void);
-void nft_payload_module_exit(void);
-
 #endif /* _NET_NF_TABLES_CORE_H */

include/net/netns/conntrack.h

@@ -91,7 +91,6 @@ struct netns_ct {
 	struct nf_ip_net	nf_ct_proto;
 #if defined(CONFIG_NF_CONNTRACK_LABELS)
 	unsigned int		labels_used;
-	u8			label_words;
 #endif
 };
 #endif