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 Netfilter updates for net-next:

1) The various ip(6)table_foo incarnations are updated to expect
   that the table is passed as 'void *priv' argument that netfilter core
   passes to the hook functions. This reduces the struct net size by 2
   cachelines on x86_64. From Florian Westphal.

2) Add cgroupsv2 support for nftables.

3) Fix bridge log family merge into nf_log_syslog: Missing
   unregistration from netns exit path, from Phil Sutter.

4) Add nft_pernet() helper to access nftables pernet area.

5) Add struct nfnl_info to reduce nfnetlink callback footprint and
   to facilite future updates. Consolidate nfnetlink callbacks.

6) Add CONFIG_NETFILTER_XTABLES_COMPAT Kconfig knob, also from Florian.
====================

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

14 files changed, 60 insertions, 75 deletions

diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index d4c14257db5d..515ce53aa20d 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -7,21 +7,26 @@
 #include <net/netlink.h>
 #include <uapi/linux/netfilter/nfnetlink.h>
 
+struct nfnl_info {
+	struct net		*net;
+	struct sock		*sk;
+	const struct nlmsghdr	*nlh;
+	struct netlink_ext_ack	*extack;
+};
+
+enum nfnl_callback_type {
+	NFNL_CB_UNSPEC	= 0,
+	NFNL_CB_MUTEX,
+	NFNL_CB_RCU,
+	NFNL_CB_BATCH,
+};
+
 struct nfnl_callback {
-	int (*call)(struct net *net, struct sock *nl, struct sk_buff *skb,
-		    const struct nlmsghdr *nlh,
-		    const struct nlattr * const cda[],
-		    struct netlink_ext_ack *extack);
-	int (*call_rcu)(struct net *net, struct sock *nl, struct sk_buff *skb,
-			const struct nlmsghdr *nlh,
-			const struct nlattr * const cda[],
-			struct netlink_ext_ack *extack);
-	int (*call_batch)(struct net *net, struct sock *nl, struct sk_buff *skb,
-			  const struct nlmsghdr *nlh,
-			  const struct nlattr * const cda[],
-			  struct netlink_ext_ack *extack);
-	const struct nla_policy *policy;	/* netlink attribute policy */
-	const u_int16_t attr_count;		/* number of nlattr's */
+	int (*call)(struct sk_buff *skb, const struct nfnl_info *info,
+		    const struct nlattr * const cda[]);
+	const struct nla_policy	*policy;
+	enum nfnl_callback_type	type;
+	__u16			attr_count;
 };
 
 enum nfnl_abort_action {
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 8ec48466410a..07c6ad8f2a02 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -158,7 +158,7 @@ struct xt_match {
 
 	/* Called when entry of this type deleted. */
 	void (*destroy)(const struct xt_mtdtor_param *);
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_NETFILTER_XTABLES_COMPAT
 	/* Called when userspace align differs from kernel space one */
 	void (*compat_from_user)(void *dst, const void *src);
 	int (*compat_to_user)(void __user *dst, const void *src);
@@ -169,7 +169,7 @@ struct xt_match {
 	const char *table;
 	unsigned int matchsize;
 	unsigned int usersize;
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_NETFILTER_XTABLES_COMPAT
 	unsigned int compatsize;
 #endif
 	unsigned int hooks;
@@ -199,7 +199,7 @@ struct xt_target {
 
 	/* Called when entry of this type deleted. */
 	void (*destroy)(const struct xt_tgdtor_param *);
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_NETFILTER_XTABLES_COMPAT
 	/* Called when userspace align differs from kernel space one */
 	void (*compat_from_user)(void *dst, const void *src);
 	int (*compat_to_user)(void __user *dst, const void *src);
@@ -210,7 +210,7 @@ struct xt_target {
 	const char *table;
 	unsigned int targetsize;
 	unsigned int usersize;
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_NETFILTER_XTABLES_COMPAT
 	unsigned int compatsize;
 #endif
 	unsigned int hooks;
@@ -229,6 +229,9 @@ struct xt_table {
 	/* Man behind the curtain... */
 	struct xt_table_info *private;
 
+	/* hook ops that register the table with the netfilter core */
+	struct nf_hook_ops *ops;
+
 	/* Set this to THIS_MODULE if you are a module, otherwise NULL */
 	struct module *me;
 
@@ -322,6 +325,7 @@ struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision);
 int xt_find_revision(u8 af, const char *name, u8 revision, int target,
 		     int *err);
 
+struct xt_table *xt_find_table(struct net *net, u8 af, const char *name);
 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,
@@ -448,7 +452,7 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu)
 
 struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *);
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_NETFILTER_XTABLES_COMPAT
 #include <net/compat.h>
 
 struct compat_xt_entry_match {
@@ -529,5 +533,5 @@ int xt_compat_check_entry_offsets(const void *base, const char *elems,
 				  unsigned int target_offset,
 				  unsigned int next_offset);
 
-#endif /* CONFIG_COMPAT */
+#endif /* CONFIG_NETFILTER_XTABLES_COMPAT */
 #endif /* _X_TABLES_H */
diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h
index 26a13294318c..2aab9612f6ab 100644
--- a/include/linux/netfilter_arp/arp_tables.h
+++ b/include/linux/netfilter_arp/arp_tables.h
@@ -51,15 +51,15 @@ struct arpt_error {
 extern void *arpt_alloc_initial_table(const struct xt_table *);
 int arpt_register_table(struct net *net, const struct xt_table *table,
 			const struct arpt_replace *repl,
-			const struct nf_hook_ops *ops, struct xt_table **res);
-void arpt_unregister_table(struct net *net, struct xt_table *table);
-void arpt_unregister_table_pre_exit(struct net *net, struct xt_table *table,
+			const struct nf_hook_ops *ops);
+void arpt_unregister_table(struct net *net, const char *name);
+void arpt_unregister_table_pre_exit(struct net *net, const char *name,
 				    const struct nf_hook_ops *ops);
 extern unsigned int arpt_do_table(struct sk_buff *skb,
 				  const struct nf_hook_state *state,
 				  struct xt_table *table);
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_NETFILTER_XTABLES_COMPAT
 #include <net/compat.h>
 
 struct compat_arpt_entry {
diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h
index 3a956145a25c..a8178253ce53 100644
--- a/include/linux/netfilter_bridge/ebtables.h
+++ b/include/linux/netfilter_bridge/ebtables.h
@@ -100,6 +100,7 @@ struct ebt_table {
 	   unsigned int valid_hooks);
 	/* the data used by the kernel */
 	struct ebt_table_info *private;
+	struct nf_hook_ops *ops;
 	struct module *me;
 };
 
@@ -108,11 +109,9 @@ struct ebt_table {
 
 extern int ebt_register_table(struct net *net,
 			      const struct ebt_table *table,
-			      const struct nf_hook_ops *ops,
-			      struct ebt_table **res);
-extern void ebt_unregister_table(struct net *net, struct ebt_table *table);
-void ebt_unregister_table_pre_exit(struct net *net, const char *tablename,
-				   const struct nf_hook_ops *ops);
+			      const struct nf_hook_ops *ops);
+extern void ebt_unregister_table(struct net *net, const char *tablename);
+void ebt_unregister_table_pre_exit(struct net *net, const char *tablename);
 extern unsigned int ebt_do_table(struct sk_buff *skb,
 				 const struct nf_hook_state *state,
 				 struct ebt_table *table);
diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h
index c4676d6feeff..8d09bfe850dc 100644
--- a/include/linux/netfilter_ipv4/ip_tables.h
+++ b/include/linux/netfilter_ipv4/ip_tables.h
@@ -24,15 +24,10 @@
 
 int ipt_register_table(struct net *net, const struct xt_table *table,
 		       const struct ipt_replace *repl,
-		       const struct nf_hook_ops *ops, struct xt_table **res);
-
-void ipt_unregister_table_pre_exit(struct net *net, struct xt_table *table,
 		       const struct nf_hook_ops *ops);
 
-void ipt_unregister_table_exit(struct net *net, struct xt_table *table);
-
-void ipt_unregister_table(struct net *net, struct xt_table *table,
-			  const struct nf_hook_ops *ops);
+void ipt_unregister_table_pre_exit(struct net *net, const char *name);
+void ipt_unregister_table_exit(struct net *net, const char *name);
 
 /* Standard entry. */
 struct ipt_standard {
@@ -72,7 +67,7 @@ extern unsigned int ipt_do_table(struct sk_buff *skb,
 				 const struct nf_hook_state *state,
 				 struct xt_table *table);
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_NETFILTER_XTABLES_COMPAT
 #include <net/compat.h>
 
 struct compat_ipt_entry {
diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h
index 1547d5f9ae06..79e73fd7d965 100644
--- a/include/linux/netfilter_ipv6/ip6_tables.h
+++ b/include/linux/netfilter_ipv6/ip6_tables.h
@@ -26,17 +26,14 @@ extern void *ip6t_alloc_initial_table(const struct xt_table *);
 
 int ip6t_register_table(struct net *net, const struct xt_table *table,
 			const struct ip6t_replace *repl,
-			const struct nf_hook_ops *ops, struct xt_table **res);
-void ip6t_unregister_table(struct net *net, struct xt_table *table,
-			   const struct nf_hook_ops *ops);
-void ip6t_unregister_table_pre_exit(struct net *net, struct xt_table *table,
-				    const struct nf_hook_ops *ops);
-void ip6t_unregister_table_exit(struct net *net, struct xt_table *table);
+			const struct nf_hook_ops *ops);
+void ip6t_unregister_table_pre_exit(struct net *net, const char *name);
+void ip6t_unregister_table_exit(struct net *net, const char *name);
 extern unsigned int ip6t_do_table(struct sk_buff *skb,
 				  const struct nf_hook_state *state,
 				  struct xt_table *table);
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_NETFILTER_XTABLES_COMPAT
 #include <net/compat.h>
 
 struct compat_ip6t_entry {
diff --git a/include/net/netfilter/ipv4/nf_defrag_ipv4.h b/include/net/netfilter/ipv4/nf_defrag_ipv4.h
index bcbd724cc048..7fda9ce9f694 100644
--- a/include/net/netfilter/ipv4/nf_defrag_ipv4.h
+++ b/include/net/netfilter/ipv4/nf_defrag_ipv4.h
@@ -3,6 +3,7 @@
 #define _NF_DEFRAG_IPV4_H
 
 struct net;
-int nf_defrag_ipv4_enable(struct net *);
+int nf_defrag_ipv4_enable(struct net *net);
+void nf_defrag_ipv4_disable(struct net *net);
 
 #endif /* _NF_DEFRAG_IPV4_H */
diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
index ece923e2035b..0fd8a4159662 100644
--- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
@@ -5,7 +5,8 @@
 #include <linux/skbuff.h>
 #include <linux/types.h>
 
-int nf_defrag_ipv6_enable(struct net *);
+int nf_defrag_ipv6_enable(struct net *net);
+void nf_defrag_ipv6_disable(struct net *net);
 
 int nf_ct_frag6_init(void);
 void nf_ct_frag6_cleanup(void);
diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index 0d412dd63707..987111ae5240 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -104,8 +104,6 @@ unsigned int
 nf_nat_inet_fn(void *priv, struct sk_buff *skb,
 	       const struct nf_hook_state *state);
 
-int nf_xfrm_me_harder(struct net *n, struct sk_buff *s, unsigned int family);
-
 static inline int nf_nat_initialized(struct nf_conn *ct,
 				     enum nf_nat_manip_type manip)
 {
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 4a75da2a2e1d..eb708b77c4a5 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -13,6 +13,7 @@
 #include <net/netfilter/nf_flow_table.h>
 #include <net/netlink.h>
 #include <net/flow_offload.h>
+#include <net/netns/generic.h>
 
 #define NFT_MAX_HOOKS	(NF_INET_INGRESS + 1)
 
@@ -1580,4 +1581,11 @@ struct nftables_pernet {
 	u8			validate_state;
 };
 
+extern unsigned int nf_tables_net_id;
+
+static inline struct nftables_pernet *nft_pernet(const struct net *net)
+{
+	return net_generic(net, nf_tables_net_id);
+}
+
 #endif /* _NET_NF_TABLES_H */
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 87e1612497ea..f6af8d96d3c6 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -76,16 +76,6 @@ struct netns_ipv4 {
 	struct inet_peer_base	*peers;
 	struct sock  * __percpu	*tcp_sk;
 	struct fqdir		*fqdir;
-#ifdef CONFIG_NETFILTER
-	struct xt_table		*iptable_filter;
-	struct xt_table		*iptable_mangle;
-	struct xt_table		*iptable_raw;
-	struct xt_table		*arptable_filter;
-#ifdef CONFIG_SECURITY
-	struct xt_table		*iptable_security;
-#endif
-	struct xt_table		*nat_table;
-#endif
 
 	u8 sysctl_icmp_echo_ignore_all;
 	u8 sysctl_icmp_echo_enable_probe;
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 808f0f79ea9c..6153c8067009 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -63,15 +63,6 @@ struct netns_ipv6 {
 	struct ipv6_devconf	*devconf_dflt;
 	struct inet_peer_base	*peers;
 	struct fqdir		*fqdir;
-#ifdef CONFIG_NETFILTER
-	struct xt_table		*ip6table_filter;
-	struct xt_table		*ip6table_mangle;
-	struct xt_table		*ip6table_raw;
-#ifdef CONFIG_SECURITY
-	struct xt_table		*ip6table_security;
-#endif
-	struct xt_table		*ip6table_nat;
-#endif
 	struct fib6_info	*fib6_null_entry;
 	struct rt6_info		*ip6_null_entry;
 	struct rt6_statistics   *rt6_stats;
diff --git a/include/net/netns/x_tables.h b/include/net/netns/x_tables.h
index 83c8ea2e87a6..d02316ec2906 100644
--- a/include/net/netns/x_tables.h
+++ b/include/net/netns/x_tables.h
@@ -5,16 +5,8 @@
 #include <linux/list.h>
 #include <linux/netfilter_defs.h>
 
-struct ebt_table;
-
 struct netns_xt {
 	bool notrack_deprecated_warning;
 	bool clusterip_deprecated_warning;
-#if defined(CONFIG_BRIDGE_NF_EBTABLES) || \
-    defined(CONFIG_BRIDGE_NF_EBTABLES_MODULE)
-	struct ebt_table *broute_table;
-	struct ebt_table *frame_filter;
-	struct ebt_table *frame_nat;
-#endif
 };
 #endif
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 79bab7a36b30..467365ed59a7 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -1014,11 +1014,13 @@ enum nft_rt_attributes {
  *
  * @NFTA_SOCKET_KEY: socket key to match
  * @NFTA_SOCKET_DREG: destination register
+ * @NFTA_SOCKET_LEVEL: cgroups2 ancestor level (only for cgroupsv2)
  */
 enum nft_socket_attributes {
 	NFTA_SOCKET_UNSPEC,
 	NFTA_SOCKET_KEY,
 	NFTA_SOCKET_DREG,
+	NFTA_SOCKET_LEVEL,
 	__NFTA_SOCKET_MAX
 };
 #define NFTA_SOCKET_MAX		(__NFTA_SOCKET_MAX - 1)
@@ -1029,11 +1031,13 @@ enum nft_socket_attributes {
  * @NFT_SOCKET_TRANSPARENT: Value of the IP(V6)_TRANSPARENT socket option
  * @NFT_SOCKET_MARK: Value of the socket mark
  * @NFT_SOCKET_WILDCARD: Whether the socket is zero-bound (e.g. 0.0.0.0 or ::0)
+ * @NFT_SOCKET_CGROUPV2: Match on cgroups version 2
  */
 enum nft_socket_keys {
 	NFT_SOCKET_TRANSPARENT,
 	NFT_SOCKET_MARK,
 	NFT_SOCKET_WILDCARD,
+	NFT_SOCKET_CGROUPV2,
 	__NFT_SOCKET_MAX
 };
 #define NFT_SOCKET_MAX	(__NFT_SOCKET_MAX - 1)