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

Pablo Neira Ayuso says:

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

1) Conntrack sets on CHECKSUM_UNNECESSARY for UDP packet with no checksum,
   from Kevin Mitchell.

2) skb->priority support for nfqueue, from Nicolas Dichtel.

3) Remove conntrack extension register API, from Florian Westphal.

4) Move nat destroy hook to nf_nat_hook instead, to remove
   nf_ct_ext_destroy(), also from Florian.

5) Wrap pptp conntrack NAT hooks into single structure, from Florian Westphal.

6) Support for tcp option set to noop for nf_tables, also from Florian.

7) Do not run x_tables comment match from packet path in nf_tables,
   from Florian Westphal.

8) Replace spinlock by cmpxchg() loop to update missed ct event,
   from Florian Westphal.

9) Wrap cttimeout hooks into single structure, from Florian.

10) Add fast nft_cmp expression for up to 16-bytes.

11) Use cb->ctx to store context in ctnetlink dump, instead of using
    cb->args[], from Florian Westphal.

* git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next:
  netfilter: ctnetlink: use dump structure instead of raw args
  nfqueue: enable to set skb->priority
  netfilter: nft_cmp: optimize comparison for 16-bytes
  netfilter: cttimeout: use option structure
  netfilter: ecache: don't use nf_conn spinlock
  netfilter: nft_compat: suppress comment match
  netfilter: exthdr: add support for tcp option removal
  netfilter: conntrack: pptp: use single option structure
  netfilter: conntrack: remove extension register api
  netfilter: conntrack: handle ->destroy hook via nat_ops instead
  netfilter: conntrack: move extension sizes into core
  netfilter: conntrack: make all extensions 8-byte alignned
  netfilter: nfqueue: enable to get skb->priority
  netfilter: conntrack: mark UDP zero checksum as CHECKSUM_UNNECESSARY
====================

Link: https://lore.kernel.org/r/20220209133616.165104-1-pablo@netfilter.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/netfilter.h

@@ -379,6 +379,7 @@ struct nf_nat_hook {
 	unsigned int (*manip_pkt)(struct sk_buff *skb, struct nf_conn *ct,
 				  enum nf_nat_manip_type mtype,
 				  enum ip_conntrack_dir dir);
+	void (*remove_nat_bysrc)(struct nf_conn *ct);
 };
 
 extern const struct nf_nat_hook __rcu *nf_nat_hook;

include/linux/netfilter/nf_conntrack_pptp.h

@@ -300,26 +300,22 @@ union pptp_ctrl_union {
 	struct PptpSetLinkInfo		setlink;
 };
 
-extern int
-(*nf_nat_pptp_hook_outbound)(struct sk_buff *skb,
-			     struct nf_conn *ct, enum ip_conntrack_info ctinfo,
-			     unsigned int protoff,
-			     struct PptpControlHeader *ctlh,
-			     union pptp_ctrl_union *pptpReq);
-
-extern int
-(*nf_nat_pptp_hook_inbound)(struct sk_buff *skb,
-			    struct nf_conn *ct, enum ip_conntrack_info ctinfo,
-			    unsigned int protoff,
-			    struct PptpControlHeader *ctlh,
-			    union pptp_ctrl_union *pptpReq);
-
-extern void
-(*nf_nat_pptp_hook_exp_gre)(struct nf_conntrack_expect *exp_orig,
-			    struct nf_conntrack_expect *exp_reply);
-
-extern void
-(*nf_nat_pptp_hook_expectfn)(struct nf_conn *ct,
-			     struct nf_conntrack_expect *exp);
+struct nf_nat_pptp_hook {
+	int (*outbound)(struct sk_buff *skb,
+			struct nf_conn *ct, enum ip_conntrack_info ctinfo,
+			unsigned int protoff,
+			struct PptpControlHeader *ctlh,
+			union pptp_ctrl_union *pptpReq);
+	int (*inbound)(struct sk_buff *skb,
+		       struct nf_conn *ct, enum ip_conntrack_info ctinfo,
+		       unsigned int protoff,
+		       struct PptpControlHeader *ctlh,
+		       union pptp_ctrl_union *pptpReq);
+	void (*exp_gre)(struct nf_conntrack_expect *exp_orig,
+			struct nf_conntrack_expect *exp_reply);
+	void (*expectfn)(struct nf_conn *ct,
+			 struct nf_conntrack_expect *exp);
+};
 
+extern const struct nf_nat_pptp_hook __rcu *nf_nat_pptp_hook;
 #endif /* _NF_CONNTRACK_PPTP_H */

include/net/netfilter/nf_conntrack_acct.h

@@ -78,7 +78,6 @@ static inline void nf_ct_acct_update(struct nf_conn *ct, u32 dir,
 
 void nf_conntrack_acct_pernet_init(struct net *net);
 
-int nf_conntrack_acct_init(void);
 void nf_conntrack_acct_fini(void);
 
 #endif /* _NF_CONNTRACK_ACCT_H */

include/net/netfilter/nf_conntrack_ecache.h

@@ -21,10 +21,10 @@ enum nf_ct_ecache_state {
 
 struct nf_conntrack_ecache {
 	unsigned long cache;		/* bitops want long */
-	u16 missed;			/* missed events */
 	u16 ctmask;			/* bitmask of ct events to be delivered */
 	u16 expmask;			/* bitmask of expect events to be delivered */
 	enum nf_ct_ecache_state state:8;/* ecache state */
+	u32 missed;			/* missed events */
 	u32 portid;			/* netlink portid of destroyer */
 };
 
@@ -166,9 +166,6 @@ void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state);
 void nf_conntrack_ecache_pernet_init(struct net *net);
 void nf_conntrack_ecache_pernet_fini(struct net *net);
 
-int nf_conntrack_ecache_init(void);
-void nf_conntrack_ecache_fini(void);
-
 static inline bool nf_conntrack_ecache_dwork_pending(const struct net *net)
 {
 	return net->ct.ecache_dwork_pending;
@@ -194,16 +191,6 @@ static inline void nf_conntrack_ecache_pernet_init(struct net *net)
 static inline void nf_conntrack_ecache_pernet_fini(struct net *net)
 {
 }
-
-static inline int nf_conntrack_ecache_init(void)
-{
-	return 0;
-}
-
-static inline void nf_conntrack_ecache_fini(void)
-{
-}
-
 static inline bool nf_conntrack_ecache_dwork_pending(const struct net *net) { return false; }
 #endif /* CONFIG_NF_CONNTRACK_EVENTS */
 #endif /*_NF_CONNTRACK_ECACHE_H*/

include/net/netfilter/nf_conntrack_extend.h

@@ -49,7 +49,7 @@ enum nf_ct_ext_id {
 struct nf_ct_ext {
 	u8 offset[NF_CT_EXT_NUM];
 	u8 len;
-	char data[];
+	char data[] __aligned(8);
 };
 
 static inline bool __nf_ct_ext_exist(const struct nf_ct_ext *ext, u8 id)
@@ -72,23 +72,7 @@ static inline void *__nf_ct_ext_find(const struct nf_conn *ct, u8 id)
 #define nf_ct_ext_find(ext, id)	\
 	((id##_TYPE *)__nf_ct_ext_find((ext), (id)))
 
-/* Destroy all relationships */
-void nf_ct_ext_destroy(struct nf_conn *ct);
-
 /* Add this type, returns pointer to data or NULL. */
 void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp);
 
-struct nf_ct_ext_type {
-	/* Destroys relationships (can be NULL). */
-	void (*destroy)(struct nf_conn *ct);
-
-	enum nf_ct_ext_id id;
-
-	/* Length and min alignment. */
-	u8 len;
-	u8 align;
-};
-
-int nf_ct_extend_register(const struct nf_ct_ext_type *type);
-void nf_ct_extend_unregister(const struct nf_ct_ext_type *type);
 #endif /* _NF_CONNTRACK_EXTEND_H */

include/net/netfilter/nf_conntrack_labels.h

@@ -45,12 +45,9 @@ int nf_connlabels_replace(struct nf_conn *ct,
 
 #ifdef CONFIG_NF_CONNTRACK_LABELS
 int nf_conntrack_labels_init(void);
-void nf_conntrack_labels_fini(void);
 int nf_connlabels_get(struct net *net, unsigned int bit);
 void nf_connlabels_put(struct net *net);
 #else
-static inline int nf_conntrack_labels_init(void) { return 0; }
-static inline void nf_conntrack_labels_fini(void) {}
 static inline int nf_connlabels_get(struct net *net, unsigned int bit) { return 0; }
 static inline void nf_connlabels_put(struct net *net) {}
 #endif

include/net/netfilter/nf_conntrack_seqadj.h

@@ -42,7 +42,4 @@ int nf_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct,
 		     enum ip_conntrack_info ctinfo, unsigned int protoff);
 s32 nf_ct_seq_offset(const struct nf_conn *ct, enum ip_conntrack_dir, u32 seq);
 
-int nf_conntrack_seqadj_init(void);
-void nf_conntrack_seqadj_fini(void);
-
 #endif /* _NF_CONNTRACK_SEQADJ_H */

include/net/netfilter/nf_conntrack_timeout.h

@@ -89,23 +89,11 @@ static inline unsigned int *nf_ct_timeout_lookup(const struct nf_conn *ct)
 }
 
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
-int nf_conntrack_timeout_init(void);
-void nf_conntrack_timeout_fini(void);
 void nf_ct_untimeout(struct net *net, struct nf_ct_timeout *timeout);
 int nf_ct_set_timeout(struct net *net, struct nf_conn *ct, u8 l3num, u8 l4num,
 		      const char *timeout_name);
 void nf_ct_destroy_timeout(struct nf_conn *ct);
 #else
-static inline int nf_conntrack_timeout_init(void)
-{
-        return 0;
-}
-
-static inline void nf_conntrack_timeout_fini(void)
-{
-        return;
-}
-
 static inline int nf_ct_set_timeout(struct net *net, struct nf_conn *ct,
 				    u8 l3num, u8 l4num,
 				    const char *timeout_name)
@@ -120,8 +108,12 @@ static inline void nf_ct_destroy_timeout(struct nf_conn *ct)
 #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
 
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
-extern struct nf_ct_timeout *(*nf_ct_timeout_find_get_hook)(struct net *net, const char *name);
-extern void (*nf_ct_timeout_put_hook)(struct nf_ct_timeout *timeout);
+struct nf_ct_timeout_hooks {
+	struct nf_ct_timeout *(*timeout_find_get)(struct net *net, const char *name);
+	void (*timeout_put)(struct nf_ct_timeout *timeout);
+};
+
+extern const struct nf_ct_timeout_hooks *nf_ct_timeout_hook;
 #endif
 
 #endif /* _NF_CONNTRACK_TIMEOUT_H */

include/net/netfilter/nf_conntrack_timestamp.h

@@ -40,21 +40,8 @@ struct nf_conn_tstamp *nf_ct_tstamp_ext_add(struct nf_conn *ct, gfp_t gfp)
 
 #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
 void nf_conntrack_tstamp_pernet_init(struct net *net);
-
-int nf_conntrack_tstamp_init(void);
-void nf_conntrack_tstamp_fini(void);
 #else
 static inline void nf_conntrack_tstamp_pernet_init(struct net *net) {}
-
-static inline int nf_conntrack_tstamp_init(void)
-{
-	return 0;
-}
-
-static inline void nf_conntrack_tstamp_fini(void)
-{
-	return;
-}
 #endif /* CONFIG_NF_CONNTRACK_TIMESTAMP */
 
 #endif /* _NF_CONNTRACK_TSTAMP_H */

include/net/netfilter/nf_tables_core.h

@@ -42,6 +42,14 @@ struct nft_cmp_fast_expr {
 	bool			inv;
 };
 
+struct nft_cmp16_fast_expr {
+	struct nft_data		data;
+	struct nft_data		mask;
+	u8			sreg;
+	u8			len;
+	bool			inv;
+};
+
 struct nft_immediate_expr {
 	struct nft_data		data;
 	u8			dreg;
@@ -59,6 +67,7 @@ static inline u32 nft_cmp_fast_mask(unsigned int len)
 }
 
 extern const struct nft_expr_ops nft_cmp_fast_ops;
+extern const struct nft_expr_ops nft_cmp16_fast_ops;
 
 struct nft_payload {
 	enum nft_payload_bases	base:8;

include/uapi/linux/netfilter/nfnetlink_queue.h

@@ -61,6 +61,7 @@ enum nfqnl_attr_type {
 	NFQA_SECCTX,			/* security context string */
 	NFQA_VLAN,			/* nested attribute: packet vlan info */
 	NFQA_L2HDR,			/* full L2 header */
+	NFQA_PRIORITY,			/* skb->priority */
 
 	__NFQA_MAX
 };

net/ipv4/netfilter/nf_nat_pptp.c

@@ -295,28 +295,24 @@ pptp_inbound_pkt(struct sk_buff *skb,
 	return NF_ACCEPT;
 }
 
+static const struct nf_nat_pptp_hook pptp_hooks = {
+	.outbound = pptp_outbound_pkt,
+	.inbound = pptp_inbound_pkt,
+	.exp_gre = pptp_exp_gre,
+	.expectfn = pptp_nat_expected,
+};
+
 static int __init nf_nat_helper_pptp_init(void)
 {
-	BUG_ON(nf_nat_pptp_hook_outbound != NULL);
-	RCU_INIT_POINTER(nf_nat_pptp_hook_outbound, pptp_outbound_pkt);
-
-	BUG_ON(nf_nat_pptp_hook_inbound != NULL);
-	RCU_INIT_POINTER(nf_nat_pptp_hook_inbound, pptp_inbound_pkt);
-
-	BUG_ON(nf_nat_pptp_hook_exp_gre != NULL);
-	RCU_INIT_POINTER(nf_nat_pptp_hook_exp_gre, pptp_exp_gre);
+	WARN_ON(nf_nat_pptp_hook != NULL);
+	RCU_INIT_POINTER(nf_nat_pptp_hook, &pptp_hooks);
 
-	BUG_ON(nf_nat_pptp_hook_expectfn != NULL);
-	RCU_INIT_POINTER(nf_nat_pptp_hook_expectfn, pptp_nat_expected);
 	return 0;
 }
 
 static void __exit nf_nat_helper_pptp_fini(void)
 {
-	RCU_INIT_POINTER(nf_nat_pptp_hook_expectfn, NULL);
-	RCU_INIT_POINTER(nf_nat_pptp_hook_exp_gre, NULL);
-	RCU_INIT_POINTER(nf_nat_pptp_hook_inbound, NULL);
-	RCU_INIT_POINTER(nf_nat_pptp_hook_outbound, NULL);
+	RCU_INIT_POINTER(nf_nat_pptp_hook, NULL);
 	synchronize_rcu();
 }
 

net/netfilter/nf_conntrack_acct.c

@@ -22,26 +22,7 @@ static bool nf_ct_acct __read_mostly;
 module_param_named(acct, nf_ct_acct, bool, 0644);
 MODULE_PARM_DESC(acct, "Enable connection tracking flow accounting.");
 
-static const struct nf_ct_ext_type acct_extend = {
-	.len	= sizeof(struct nf_conn_acct),
-	.align	= __alignof__(struct nf_conn_acct),
-	.id	= NF_CT_EXT_ACCT,
-};
-
 void nf_conntrack_acct_pernet_init(struct net *net)
 {
 	net->ct.sysctl_acct = nf_ct_acct;
 }
-
-int nf_conntrack_acct_init(void)
-{
-	int ret = nf_ct_extend_register(&acct_extend);
-	if (ret < 0)
-		pr_err("Unable to register extension\n");
-	return ret;
-}
-
-void nf_conntrack_acct_fini(void)
-{
-	nf_ct_extend_unregister(&acct_extend);
-}

net/netfilter/nf_conntrack_core.c

@@ -38,7 +38,6 @@
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_helper.h>
-#include <net/netfilter/nf_conntrack_seqadj.h>
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_extend.h>
 #include <net/netfilter/nf_conntrack_acct.h>
@@ -48,7 +47,6 @@
 #include <net/netfilter/nf_conntrack_timeout.h>
 #include <net/netfilter/nf_conntrack_labels.h>
 #include <net/netfilter/nf_conntrack_synproxy.h>
-#include <net/netfilter/nf_conntrack_act_ct.h>
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_helper.h>
 #include <net/netns/hash.h>
@@ -595,7 +593,7 @@ EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc);
 
 void nf_ct_tmpl_free(struct nf_conn *tmpl)
 {
-	nf_ct_ext_destroy(tmpl);
+	kfree(tmpl->ext);
 
 	if (ARCH_KMALLOC_MINALIGN <= NFCT_INFOMASK)
 		kfree((char *)tmpl - tmpl->proto.tmpl_padto);
@@ -1598,7 +1596,17 @@ void nf_conntrack_free(struct nf_conn *ct)
 	 */
 	WARN_ON(refcount_read(&ct->ct_general.use) != 0);
 
-	nf_ct_ext_destroy(ct);
+	if (ct->status & IPS_SRC_NAT_DONE) {
+		const struct nf_nat_hook *nat_hook;
+
+		rcu_read_lock();
+		nat_hook = rcu_dereference(nf_nat_hook);
+		if (nat_hook)
+			nat_hook->remove_nat_bysrc(ct);
+		rcu_read_unlock();
+	}
+
+	kfree(ct->ext);
 	kmem_cache_free(nf_conntrack_cachep, ct);
 	cnet = nf_ct_pernet(net);
 
@@ -2468,13 +2476,7 @@ void nf_conntrack_cleanup_end(void)
 	kvfree(nf_conntrack_hash);
 
 	nf_conntrack_proto_fini();
-	nf_conntrack_seqadj_fini();
-	nf_conntrack_labels_fini();
 	nf_conntrack_helper_fini();
-	nf_conntrack_timeout_fini();
-	nf_conntrack_ecache_fini();
-	nf_conntrack_tstamp_fini();
-	nf_conntrack_acct_fini();
 	nf_conntrack_expect_fini();
 
 	kmem_cache_destroy(nf_conntrack_cachep);
@@ -2629,39 +2631,6 @@ int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp)
 	return nf_conntrack_hash_resize(hashsize);
 }
 
-static __always_inline unsigned int total_extension_size(void)
-{
-	/* remember to add new extensions below */
-	BUILD_BUG_ON(NF_CT_EXT_NUM > 10);
-
-	return sizeof(struct nf_ct_ext) +
-	       sizeof(struct nf_conn_help)
-#if IS_ENABLED(CONFIG_NF_NAT)
-		+ sizeof(struct nf_conn_nat)
-#endif
-		+ sizeof(struct nf_conn_seqadj)
-		+ sizeof(struct nf_conn_acct)
-#ifdef CONFIG_NF_CONNTRACK_EVENTS
-		+ sizeof(struct nf_conntrack_ecache)
-#endif
-#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
-		+ sizeof(struct nf_conn_tstamp)
-#endif
-#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
-		+ sizeof(struct nf_conn_timeout)
-#endif
-#ifdef CONFIG_NF_CONNTRACK_LABELS
-		+ sizeof(struct nf_conn_labels)
-#endif
-#if IS_ENABLED(CONFIG_NETFILTER_SYNPROXY)
-		+ sizeof(struct nf_conn_synproxy)
-#endif
-#if IS_ENABLED(CONFIG_NET_ACT_CT)
-		+ sizeof(struct nf_conn_act_ct_ext)
-#endif
-	;
-};
-
 int nf_conntrack_init_start(void)
 {
 	unsigned long nr_pages = totalram_pages();
@@ -2669,9 +2638,6 @@ int nf_conntrack_init_start(void)
 	int ret = -ENOMEM;
 	int i;
 
-	/* struct nf_ct_ext uses u8 to store offsets/size */
-	BUILD_BUG_ON(total_extension_size() > 255u);
-
 	seqcount_spinlock_init(&nf_conntrack_generation,
 			       &nf_conntrack_locks_all_lock);
 
@@ -2716,34 +2682,10 @@ int nf_conntrack_init_start(void)
 	if (ret < 0)
 		goto err_expect;
 
-	ret = nf_conntrack_acct_init();
-	if (ret < 0)
-		goto err_acct;
-
-	ret = nf_conntrack_tstamp_init();
-	if (ret < 0)
-		goto err_tstamp;
-
-	ret = nf_conntrack_ecache_init();
-	if (ret < 0)
-		goto err_ecache;
-
-	ret = nf_conntrack_timeout_init();
-	if (ret < 0)
-		goto err_timeout;
-
 	ret = nf_conntrack_helper_init();
 	if (ret < 0)
 		goto err_helper;
 
-	ret = nf_conntrack_labels_init();
-	if (ret < 0)
-		goto err_labels;
-
-	ret = nf_conntrack_seqadj_init();
-	if (ret < 0)
-		goto err_seqadj;
-
 	ret = nf_conntrack_proto_init();
 	if (ret < 0)
 		goto err_proto;
@@ -2761,20 +2703,8 @@ int nf_conntrack_init_start(void)
 	cancel_delayed_work_sync(&conntrack_gc_work.dwork);
 	nf_conntrack_proto_fini();
 err_proto:
-	nf_conntrack_seqadj_fini();
-err_seqadj:
-	nf_conntrack_labels_fini();
-err_labels:
 	nf_conntrack_helper_fini();
 err_helper:
-	nf_conntrack_timeout_fini();
-err_timeout:
-	nf_conntrack_ecache_fini();
-err_ecache:
-	nf_conntrack_tstamp_fini();
-err_tstamp:
-	nf_conntrack_acct_fini();
-err_acct:
 	nf_conntrack_expect_fini();
 err_expect:
 	kmem_cache_destroy(nf_conntrack_cachep);

net/netfilter/nf_conntrack_ecache.c

@@ -131,13 +131,13 @@ static void ecache_work(struct work_struct *work)
 }
 
 static int __nf_conntrack_eventmask_report(struct nf_conntrack_ecache *e,
-					   const unsigned int events,
-					   const unsigned long missed,
+					   const u32 events,
+					   const u32 missed,
 					   const struct nf_ct_event *item)
 {
-	struct nf_conn *ct = item->ct;
 	struct net *net = nf_ct_net(item->ct);
 	struct nf_ct_event_notifier *notify;
+	u32 old, want;
 	int ret;
 
 	if (!((events | missed) & e->ctmask))
@@ -157,12 +157,13 @@ static int __nf_conntrack_eventmask_report(struct nf_conntrack_ecache *e,
 	if (likely(ret >= 0 && missed == 0))
 		return 0;
 
-	spin_lock_bh(&ct->lock);
-	if (ret < 0)
-		e->missed |= events;
-	else
-		e->missed &= ~missed;
-	spin_unlock_bh(&ct->lock);
+	do {
+		old = READ_ONCE(e->missed);
+		if (ret < 0)
+			want = old | events;
+		else
+			want = old & ~missed;
+	} while (cmpxchg(&e->missed, old, want) != old);
 
 	return ret;
 }
@@ -172,7 +173,7 @@ int nf_conntrack_eventmask_report(unsigned int events, struct nf_conn *ct,
 {
 	struct nf_conntrack_ecache *e;
 	struct nf_ct_event item;
-	unsigned long missed;
+	unsigned int missed;
 	int ret;
 
 	if (!nf_ct_is_confirmed(ct))
@@ -211,7 +212,7 @@ void nf_ct_deliver_cached_events(struct nf_conn *ct)
 {
 	struct nf_conntrack_ecache *e;
 	struct nf_ct_event item;
-	unsigned long events;
+	unsigned int events;
 
 	if (!nf_ct_is_confirmed(ct) || nf_ct_is_dying(ct))
 		return;
@@ -304,12 +305,6 @@ void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state)
 #define NF_CT_EVENTS_DEFAULT 1
 static int nf_ct_events __read_mostly = NF_CT_EVENTS_DEFAULT;
 
-static const struct nf_ct_ext_type event_extend = {
-	.len	= sizeof(struct nf_conntrack_ecache),
-	.align	= __alignof__(struct nf_conntrack_ecache),
-	.id	= NF_CT_EXT_ECACHE,
-};
-
 void nf_conntrack_ecache_pernet_init(struct net *net)
 {
 	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
@@ -317,6 +312,8 @@ void nf_conntrack_ecache_pernet_init(struct net *net)
 	net->ct.sysctl_events = nf_ct_events;
 	cnet->ct_net = &net->ct;
 	INIT_DELAYED_WORK(&cnet->ecache_dwork, ecache_work);
+
+	BUILD_BUG_ON(__IPCT_MAX >= 16);	/* e->ctmask is u16 */
 }
 
 void nf_conntrack_ecache_pernet_fini(struct net *net)
@@ -325,19 +322,3 @@ void nf_conntrack_ecache_pernet_fini(struct net *net)
 
 	cancel_delayed_work_sync(&cnet->ecache_dwork);
 }
-
-int nf_conntrack_ecache_init(void)
-{
-	int ret = nf_ct_extend_register(&event_extend);
-	if (ret < 0)
-		pr_err("Unable to register event extension\n");
-
-	BUILD_BUG_ON(__IPCT_MAX >= 16);	/* ctmask, missed use u16 */
-
-	return ret;
-}
-
-void nf_conntrack_ecache_fini(void)
-{
-	nf_ct_extend_unregister(&event_extend);
-}

net/netfilter/nf_conntrack_extend.c

@@ -13,40 +13,90 @@
 #include <linux/skbuff.h>
 #include <net/netfilter/nf_conntrack_extend.h>
 
-static struct nf_ct_ext_type __rcu *nf_ct_ext_types[NF_CT_EXT_NUM];
-static DEFINE_MUTEX(nf_ct_ext_type_mutex);
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_acct.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
+#include <net/netfilter/nf_conntrack_ecache.h>
+#include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_conntrack_timestamp.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
+#include <net/netfilter/nf_conntrack_labels.h>
+#include <net/netfilter/nf_conntrack_synproxy.h>
+#include <net/netfilter/nf_conntrack_act_ct.h>
+#include <net/netfilter/nf_nat.h>
+
 #define NF_CT_EXT_PREALLOC	128u /* conntrack events are on by default */
 
-void nf_ct_ext_destroy(struct nf_conn *ct)
+static const u8 nf_ct_ext_type_len[NF_CT_EXT_NUM] = {
+	[NF_CT_EXT_HELPER] = sizeof(struct nf_conn_help),
+#if IS_ENABLED(CONFIG_NF_NAT)
+	[NF_CT_EXT_NAT] = sizeof(struct nf_conn_nat),
+#endif
+	[NF_CT_EXT_SEQADJ] = sizeof(struct nf_conn_seqadj),
+	[NF_CT_EXT_ACCT] = sizeof(struct nf_conn_acct),
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+	[NF_CT_EXT_ECACHE] = sizeof(struct nf_conntrack_ecache),
+#endif
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	[NF_CT_EXT_TSTAMP] = sizeof(struct nf_conn_acct),
+#endif
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+	[NF_CT_EXT_TIMEOUT] = sizeof(struct nf_conn_tstamp),
+#endif
+#ifdef CONFIG_NF_CONNTRACK_LABELS
+	[NF_CT_EXT_LABELS] = sizeof(struct nf_conn_labels),
+#endif
+#if IS_ENABLED(CONFIG_NETFILTER_SYNPROXY)
+	[NF_CT_EXT_SYNPROXY] = sizeof(struct nf_conn_synproxy),
+#endif
+#if IS_ENABLED(CONFIG_NET_ACT_CT)
+	[NF_CT_EXT_ACT_CT] = sizeof(struct nf_conn_act_ct_ext),
+#endif
+};
+
+static __always_inline unsigned int total_extension_size(void)
 {
-	unsigned int i;
-	struct nf_ct_ext_type *t;
-
-	for (i = 0; i < NF_CT_EXT_NUM; i++) {
-		rcu_read_lock();
-		t = rcu_dereference(nf_ct_ext_types[i]);
-
-		/* Here the nf_ct_ext_type might have been unregisterd.
-		 * I.e., it has responsible to cleanup private
-		 * area in all conntracks when it is unregisterd.
-		 */
-		if (t && t->destroy)
-			t->destroy(ct);
-		rcu_read_unlock();
-	}
-
-	kfree(ct->ext);
+	/* remember to add new extensions below */
+	BUILD_BUG_ON(NF_CT_EXT_NUM > 10);
+
+	return sizeof(struct nf_ct_ext) +
+	       sizeof(struct nf_conn_help)
+#if IS_ENABLED(CONFIG_NF_NAT)
+		+ sizeof(struct nf_conn_nat)
+#endif
+		+ sizeof(struct nf_conn_seqadj)
+		+ sizeof(struct nf_conn_acct)
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+		+ sizeof(struct nf_conntrack_ecache)
+#endif
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+		+ sizeof(struct nf_conn_tstamp)
+#endif
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+		+ sizeof(struct nf_conn_timeout)
+#endif
+#ifdef CONFIG_NF_CONNTRACK_LABELS
+		+ sizeof(struct nf_conn_labels)
+#endif
+#if IS_ENABLED(CONFIG_NETFILTER_SYNPROXY)
+		+ sizeof(struct nf_conn_synproxy)
+#endif
+#if IS_ENABLED(CONFIG_NET_ACT_CT)
+		+ sizeof(struct nf_conn_act_ct_ext)
+#endif
+	;
 }
 
 void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
 {
 	unsigned int newlen, newoff, oldlen, alloc;
-	struct nf_ct_ext_type *t;
 	struct nf_ct_ext *new;
 
 	/* Conntrack must not be confirmed to avoid races on reallocation. */
 	WARN_ON(nf_ct_is_confirmed(ct));
 
+	/* struct nf_ct_ext uses u8 to store offsets/size */
+	BUILD_BUG_ON(total_extension_size() > 255u);
 
 	if (ct->ext) {
 		const struct nf_ct_ext *old = ct->ext;
@@ -58,16 +108,8 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
 		oldlen = sizeof(*new);
 	}
 
-	rcu_read_lock();
-	t = rcu_dereference(nf_ct_ext_types[id]);
-	if (!t) {
-		rcu_read_unlock();
-		return NULL;
-	}
-
-	newoff = ALIGN(oldlen, t->align);
-	newlen = newoff + t->len;
-	rcu_read_unlock();
+	newoff = ALIGN(oldlen, __alignof__(struct nf_ct_ext));
+	newlen = newoff + nf_ct_ext_type_len[id];
 
 	alloc = max(newlen, NF_CT_EXT_PREALLOC);
 	new = krealloc(ct->ext, alloc, gfp);
@@ -85,31 +127,3 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
 	return (void *)new + newoff;
 }
 EXPORT_SYMBOL(nf_ct_ext_add);
-
-/* This MUST be called in process context. */
-int nf_ct_extend_register(const struct nf_ct_ext_type *type)
-{
-	int ret = 0;
-
-	mutex_lock(&nf_ct_ext_type_mutex);
-	if (nf_ct_ext_types[type->id]) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	rcu_assign_pointer(nf_ct_ext_types[type->id], type);
-out:
-	mutex_unlock(&nf_ct_ext_type_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(nf_ct_extend_register);
-
-/* This MUST be called in process context. */
-void nf_ct_extend_unregister(const struct nf_ct_ext_type *type)
-{
-	mutex_lock(&nf_ct_ext_type_mutex);
-	RCU_INIT_POINTER(nf_ct_ext_types[type->id], NULL);
-	mutex_unlock(&nf_ct_ext_type_mutex);
-	synchronize_rcu();
-}
-EXPORT_SYMBOL_GPL(nf_ct_extend_unregister);

net/netfilter/nf_conntrack_helper.c

@@ -550,12 +550,6 @@ void nf_nat_helper_unregister(struct nf_conntrack_nat_helper *nat)
 }
 EXPORT_SYMBOL_GPL(nf_nat_helper_unregister);
 
-static const struct nf_ct_ext_type helper_extend = {
-	.len	= sizeof(struct nf_conn_help),
-	.align	= __alignof__(struct nf_conn_help),
-	.id	= NF_CT_EXT_HELPER,
-};
-
 void nf_conntrack_helper_pernet_init(struct net *net)
 {
 	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
@@ -565,28 +559,17 @@ void nf_conntrack_helper_pernet_init(struct net *net)
 
 int nf_conntrack_helper_init(void)
 {
-	int ret;
 	nf_ct_helper_hsize = 1; /* gets rounded up to use one page */
 	nf_ct_helper_hash =
 		nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0);
 	if (!nf_ct_helper_hash)
 		return -ENOMEM;
 
-	ret = nf_ct_extend_register(&helper_extend);
-	if (ret < 0) {
-		pr_err("nf_ct_helper: Unable to register helper extension.\n");
-		goto out_extend;
-	}
-
 	INIT_LIST_HEAD(&nf_ct_nat_helpers);
 	return 0;
-out_extend:
-	kvfree(nf_ct_helper_hash);
-	return ret;
 }
 
 void nf_conntrack_helper_fini(void)
 {
-	nf_ct_extend_unregister(&helper_extend);
 	kvfree(nf_ct_helper_hash);
 }

net/netfilter/nf_conntrack_labels.c

@@ -67,6 +67,8 @@ int nf_connlabels_get(struct net *net, unsigned int bits)
 	net->ct.labels_used++;
 	spin_unlock(&nf_connlabels_lock);
 
+	BUILD_BUG_ON(NF_CT_LABELS_MAX_SIZE / sizeof(long) >= U8_MAX);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nf_connlabels_get);
@@ -78,21 +80,3 @@ void nf_connlabels_put(struct net *net)
 	spin_unlock(&nf_connlabels_lock);
 }
 EXPORT_SYMBOL_GPL(nf_connlabels_put);
-
-static const struct nf_ct_ext_type labels_extend = {
-	.len    = sizeof(struct nf_conn_labels),
-	.align  = __alignof__(struct nf_conn_labels),
-	.id     = NF_CT_EXT_LABELS,
-};
-
-int nf_conntrack_labels_init(void)
-{
-	BUILD_BUG_ON(NF_CT_LABELS_MAX_SIZE / sizeof(long) >= U8_MAX);
-
-	return nf_ct_extend_register(&labels_extend);
-}
-
-void nf_conntrack_labels_fini(void)
-{
-	nf_ct_extend_unregister(&labels_extend);
-}

net/netfilter/nf_conntrack_netlink.c

@@ -58,6 +58,12 @@
 
 MODULE_LICENSE("GPL");
 
+struct ctnetlink_list_dump_ctx {
+	struct nf_conn *last;
+	unsigned int cpu;
+	bool done;
+};
+
 static int ctnetlink_dump_tuples_proto(struct sk_buff *skb,
 				const struct nf_conntrack_tuple *tuple,
 				const struct nf_conntrack_l4proto *l4proto)
@@ -1694,14 +1700,18 @@ static int ctnetlink_get_conntrack(struct sk_buff *skb,
 
 static int ctnetlink_done_list(struct netlink_callback *cb)
 {
-	if (cb->args[1])
-		nf_ct_put((struct nf_conn *)cb->args[1]);
+	struct ctnetlink_list_dump_ctx *ctx = (void *)cb->ctx;
+
+	if (ctx->last)
+		nf_ct_put(ctx->last);
+
 	return 0;
 }
 
 static int
 ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying)
 {
+	struct ctnetlink_list_dump_ctx *ctx = (void *)cb->ctx;
 	struct nf_conn *ct, *last;
 	struct nf_conntrack_tuple_hash *h;
 	struct hlist_nulls_node *n;
@@ -1712,12 +1722,12 @@ ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying
 	struct hlist_nulls_head *list;
 	struct net *net = sock_net(skb->sk);
 
-	if (cb->args[2])
+	if (ctx->done)
 		return 0;
 
-	last = (struct nf_conn *)cb->args[1];
+	last = ctx->last;
 
-	for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) {
+	for (cpu = ctx->cpu; cpu < nr_cpu_ids; cpu++) {
 		struct ct_pcpu *pcpu;
 
 		if (!cpu_possible(cpu))
@@ -1731,10 +1741,10 @@ ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying
 			ct = nf_ct_tuplehash_to_ctrack(h);
 			if (l3proto && nf_ct_l3num(ct) != l3proto)
 				continue;
-			if (cb->args[1]) {
+			if (ctx->last) {
 				if (ct != last)
 					continue;
-				cb->args[1] = 0;
+				ctx->last = NULL;
 			}
 
 			/* We can't dump extension info for the unconfirmed
@@ -1751,19 +1761,19 @@ ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying
 			if (res < 0) {
 				if (!refcount_inc_not_zero(&ct->ct_general.use))
 					continue;
-				cb->args[0] = cpu;
-				cb->args[1] = (unsigned long)ct;
+				ctx->cpu = cpu;
+				ctx->last = ct;
 				spin_unlock_bh(&pcpu->lock);
 				goto out;
 			}
 		}
-		if (cb->args[1]) {
-			cb->args[1] = 0;
+		if (ctx->last) {
+			ctx->last = NULL;
 			goto restart;
 		}
 		spin_unlock_bh(&pcpu->lock);
 	}
-	cb->args[2] = 1;
+	ctx->done = true;
 out:
 	if (last)
 		nf_ct_put(last);
@@ -3877,6 +3887,8 @@ static int __init ctnetlink_init(void)
 {
 	int ret;
 
+	BUILD_BUG_ON(sizeof(struct ctnetlink_list_dump_ctx) > sizeof_field(struct netlink_callback, ctx));
+
 	ret = nfnetlink_subsys_register(&ctnl_subsys);
 	if (ret < 0) {
 		pr_err("ctnetlink_init: cannot register with nfnetlink.\n");

net/netfilter/nf_conntrack_pptp.c

@@ -45,30 +45,8 @@ MODULE_ALIAS_NFCT_HELPER("pptp");
 
 static DEFINE_SPINLOCK(nf_pptp_lock);
 
-int
-(*nf_nat_pptp_hook_outbound)(struct sk_buff *skb,
-			     struct nf_conn *ct, enum ip_conntrack_info ctinfo,
-			     unsigned int protoff, struct PptpControlHeader *ctlh,
-			     union pptp_ctrl_union *pptpReq) __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_outbound);
-
-int
-(*nf_nat_pptp_hook_inbound)(struct sk_buff *skb,
-			    struct nf_conn *ct, enum ip_conntrack_info ctinfo,
-			    unsigned int protoff, struct PptpControlHeader *ctlh,
-			    union pptp_ctrl_union *pptpReq) __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_inbound);
-
-void
-(*nf_nat_pptp_hook_exp_gre)(struct nf_conntrack_expect *expect_orig,
-			    struct nf_conntrack_expect *expect_reply)
-			    __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_exp_gre);
-
-void
-(*nf_nat_pptp_hook_expectfn)(struct nf_conn *ct,
-			     struct nf_conntrack_expect *exp) __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_expectfn);
+const struct nf_nat_pptp_hook *nf_nat_pptp_hook;
+EXPORT_SYMBOL_GPL(nf_nat_pptp_hook);
 
 #if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG)
 /* PptpControlMessageType names */
@@ -111,8 +89,8 @@ EXPORT_SYMBOL(pptp_msg_name);
 static void pptp_expectfn(struct nf_conn *ct,
 			 struct nf_conntrack_expect *exp)
 {
+	const struct nf_nat_pptp_hook *hook;
 	struct net *net = nf_ct_net(ct);
-	typeof(nf_nat_pptp_hook_expectfn) nf_nat_pptp_expectfn;
 	pr_debug("increasing timeouts\n");
 
 	/* increase timeout of GRE data channel conntrack entry */
@@ -122,9 +100,9 @@ static void pptp_expectfn(struct nf_conn *ct,
 	/* Can you see how rusty this code is, compared with the pre-2.6.11
 	 * one? That's what happened to my shiny newnat of 2002 ;( -HW */
 
-	nf_nat_pptp_expectfn = rcu_dereference(nf_nat_pptp_hook_expectfn);
-	if (nf_nat_pptp_expectfn && ct->master->status & IPS_NAT_MASK)
-		nf_nat_pptp_expectfn(ct, exp);
+	hook = rcu_dereference(nf_nat_pptp_hook);
+	if (hook && ct->master->status & IPS_NAT_MASK)
+		hook->expectfn(ct, exp);
 	else {
 		struct nf_conntrack_tuple inv_t;
 		struct nf_conntrack_expect *exp_other;
@@ -209,9 +187,9 @@ static void pptp_destroy_siblings(struct nf_conn *ct)
 static int exp_gre(struct nf_conn *ct, __be16 callid, __be16 peer_callid)
 {
 	struct nf_conntrack_expect *exp_orig, *exp_reply;
+	const struct nf_nat_pptp_hook *hook;
 	enum ip_conntrack_dir dir;
 	int ret = 1;
-	typeof(nf_nat_pptp_hook_exp_gre) nf_nat_pptp_exp_gre;
 
 	exp_orig = nf_ct_expect_alloc(ct);
 	if (exp_orig == NULL)
@@ -239,9 +217,9 @@ static int exp_gre(struct nf_conn *ct, __be16 callid, __be16 peer_callid)
 			  IPPROTO_GRE, &callid, &peer_callid);
 	exp_reply->expectfn = pptp_expectfn;
 
-	nf_nat_pptp_exp_gre = rcu_dereference(nf_nat_pptp_hook_exp_gre);
-	if (nf_nat_pptp_exp_gre && ct->status & IPS_NAT_MASK)
-		nf_nat_pptp_exp_gre(exp_orig, exp_reply);
+	hook = rcu_dereference(nf_nat_pptp_hook);
+	if (hook && ct->status & IPS_NAT_MASK)
+		hook->exp_gre(exp_orig, exp_reply);
 	if (nf_ct_expect_related(exp_orig, 0) != 0)
 		goto out_put_both;
 	if (nf_ct_expect_related(exp_reply, 0) != 0)
@@ -279,9 +257,9 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		 enum ip_conntrack_info ctinfo)
 {
 	struct nf_ct_pptp_master *info = nfct_help_data(ct);
+	const struct nf_nat_pptp_hook *hook;
 	u_int16_t msg;
 	__be16 cid = 0, pcid = 0;
-	typeof(nf_nat_pptp_hook_inbound) nf_nat_pptp_inbound;
 
 	msg = ntohs(ctlh->messageType);
 	pr_debug("inbound control message %s\n", pptp_msg_name(msg));
@@ -383,10 +361,9 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		goto invalid;
 	}
 
-	nf_nat_pptp_inbound = rcu_dereference(nf_nat_pptp_hook_inbound);
-	if (nf_nat_pptp_inbound && ct->status & IPS_NAT_MASK)
-		return nf_nat_pptp_inbound(skb, ct, ctinfo,
-					   protoff, ctlh, pptpReq);
+	hook = rcu_dereference(nf_nat_pptp_hook);
+	if (hook && ct->status & IPS_NAT_MASK)
+		return hook->inbound(skb, ct, ctinfo, protoff, ctlh, pptpReq);
 	return NF_ACCEPT;
 
 invalid:
@@ -407,9 +384,9 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		  enum ip_conntrack_info ctinfo)
 {
 	struct nf_ct_pptp_master *info = nfct_help_data(ct);
+	const struct nf_nat_pptp_hook *hook;
 	u_int16_t msg;
 	__be16 cid = 0, pcid = 0;
-	typeof(nf_nat_pptp_hook_outbound) nf_nat_pptp_outbound;
 
 	msg = ntohs(ctlh->messageType);
 	pr_debug("outbound control message %s\n", pptp_msg_name(msg));
@@ -479,10 +456,9 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		goto invalid;
 	}
 
-	nf_nat_pptp_outbound = rcu_dereference(nf_nat_pptp_hook_outbound);
-	if (nf_nat_pptp_outbound && ct->status & IPS_NAT_MASK)
-		return nf_nat_pptp_outbound(skb, ct, ctinfo,
-					    protoff, ctlh, pptpReq);
+	hook = rcu_dereference(nf_nat_pptp_hook);
+	if (hook && ct->status & IPS_NAT_MASK)
+		return hook->outbound(skb, ct, ctinfo, protoff, ctlh, pptpReq);
 	return NF_ACCEPT;
 
 invalid:

net/netfilter/nf_conntrack_proto_udp.c

@@ -63,8 +63,10 @@ static bool udp_error(struct sk_buff *skb,
 	}
 
 	/* Packet with no checksum */
-	if (!hdr->check)
+	if (!hdr->check) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
 		return false;
+	}
 
 	/* Checksum invalid? Ignore.
 	 * We skip checking packets on the outgoing path

net/netfilter/nf_conntrack_seqadj.c

@@ -232,19 +232,3 @@ s32 nf_ct_seq_offset(const struct nf_conn *ct,
 		 this_way->offset_after : this_way->offset_before;
 }
 EXPORT_SYMBOL_GPL(nf_ct_seq_offset);
-
-static const struct nf_ct_ext_type nf_ct_seqadj_extend = {
-	.len	= sizeof(struct nf_conn_seqadj),
-	.align	= __alignof__(struct nf_conn_seqadj),
-	.id	= NF_CT_EXT_SEQADJ,
-};
-
-int nf_conntrack_seqadj_init(void)
-{
-	return nf_ct_extend_register(&nf_ct_seqadj_extend);
-}
-
-void nf_conntrack_seqadj_fini(void)
-{
-	nf_ct_extend_unregister(&nf_ct_seqadj_extend);
-}

net/netfilter/nf_conntrack_timeout.c

@@ -22,12 +22,8 @@
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_timeout.h>
 
-struct nf_ct_timeout *
-(*nf_ct_timeout_find_get_hook)(struct net *net, const char *name) __read_mostly;
-EXPORT_SYMBOL_GPL(nf_ct_timeout_find_get_hook);
-
-void (*nf_ct_timeout_put_hook)(struct nf_ct_timeout *timeout) __read_mostly;
-EXPORT_SYMBOL_GPL(nf_ct_timeout_put_hook);
+const struct nf_ct_timeout_hooks *nf_ct_timeout_hook __read_mostly;
+EXPORT_SYMBOL_GPL(nf_ct_timeout_hook);
 
 static int untimeout(struct nf_conn *ct, void *timeout)
 {
@@ -48,31 +44,30 @@ EXPORT_SYMBOL_GPL(nf_ct_untimeout);
 
 static void __nf_ct_timeout_put(struct nf_ct_timeout *timeout)
 {
-	typeof(nf_ct_timeout_put_hook) timeout_put;
+	const struct nf_ct_timeout_hooks *h = rcu_dereference(nf_ct_timeout_hook);
 
-	timeout_put = rcu_dereference(nf_ct_timeout_put_hook);
-	if (timeout_put)
-		timeout_put(timeout);
+	if (h)
+		h->timeout_put(timeout);
 }
 
 int nf_ct_set_timeout(struct net *net, struct nf_conn *ct,
 		      u8 l3num, u8 l4num, const char *timeout_name)
 {
-	typeof(nf_ct_timeout_find_get_hook) timeout_find_get;
+	const struct nf_ct_timeout_hooks *h;
 	struct nf_ct_timeout *timeout;
 	struct nf_conn_timeout *timeout_ext;
 	const char *errmsg = NULL;
 	int ret = 0;
 
 	rcu_read_lock();
-	timeout_find_get = rcu_dereference(nf_ct_timeout_find_get_hook);
-	if (!timeout_find_get) {
+	h = rcu_dereference(nf_ct_timeout_hook);
+	if (!h) {
 		ret = -ENOENT;
 		errmsg = "Timeout policy base is empty";
 		goto out;
 	}
 
-	timeout = timeout_find_get(net, timeout_name);
+	timeout = h->timeout_find_get(net, timeout_name);
 	if (!timeout) {
 		ret = -ENOENT;
 		pr_info_ratelimited("No such timeout policy \"%s\"\n",
@@ -119,37 +114,18 @@ EXPORT_SYMBOL_GPL(nf_ct_set_timeout);
 void nf_ct_destroy_timeout(struct nf_conn *ct)
 {
 	struct nf_conn_timeout *timeout_ext;
-	typeof(nf_ct_timeout_put_hook) timeout_put;
+	const struct nf_ct_timeout_hooks *h;
 
 	rcu_read_lock();
-	timeout_put = rcu_dereference(nf_ct_timeout_put_hook);
+	h = rcu_dereference(nf_ct_timeout_hook);
 
-	if (timeout_put) {
+	if (h) {
 		timeout_ext = nf_ct_timeout_find(ct);
 		if (timeout_ext) {
-			timeout_put(timeout_ext->timeout);
+			h->timeout_put(timeout_ext->timeout);
 			RCU_INIT_POINTER(timeout_ext->timeout, NULL);
 		}
 	}
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(nf_ct_destroy_timeout);
-
-static const struct nf_ct_ext_type timeout_extend = {
-	.len	= sizeof(struct nf_conn_timeout),
-	.align	= __alignof__(struct nf_conn_timeout),
-	.id	= NF_CT_EXT_TIMEOUT,
-};
-
-int nf_conntrack_timeout_init(void)
-{
-	int ret = nf_ct_extend_register(&timeout_extend);
-	if (ret < 0)
-		pr_err("nf_ct_timeout: Unable to register timeout extension.\n");
-	return ret;
-}
-
-void nf_conntrack_timeout_fini(void)
-{
-	nf_ct_extend_unregister(&timeout_extend);
-}

net/netfilter/nf_conntrack_timestamp.c

@@ -19,27 +19,7 @@ static bool nf_ct_tstamp __read_mostly;
 module_param_named(tstamp, nf_ct_tstamp, bool, 0644);
 MODULE_PARM_DESC(tstamp, "Enable connection tracking flow timestamping.");
 
-static const struct nf_ct_ext_type tstamp_extend = {
-	.len	= sizeof(struct nf_conn_tstamp),
-	.align	= __alignof__(struct nf_conn_tstamp),
-	.id	= NF_CT_EXT_TSTAMP,
-};
-
 void nf_conntrack_tstamp_pernet_init(struct net *net)
 {
 	net->ct.sysctl_tstamp = nf_ct_tstamp;
 }
-
-int nf_conntrack_tstamp_init(void)
-{
-	int ret;
-	ret = nf_ct_extend_register(&tstamp_extend);
-	if (ret < 0)
-		pr_err("Unable to register extension\n");
-	return ret;
-}
-
-void nf_conntrack_tstamp_fini(void)
-{
-	nf_ct_extend_unregister(&tstamp_extend);
-}

net/netfilter/nf_nat_core.c

@@ -838,7 +838,7 @@ static int nf_nat_proto_remove(struct nf_conn *i, void *data)
 	return i->status & IPS_NAT_MASK ? 1 : 0;
 }
 
-static void __nf_nat_cleanup_conntrack(struct nf_conn *ct)
+static void nf_nat_cleanup_conntrack(struct nf_conn *ct)
 {
 	unsigned int h;
 
@@ -860,7 +860,7 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
 	 * will delete entry from already-freed table.
 	 */
 	if (test_and_clear_bit(IPS_SRC_NAT_DONE_BIT, &ct->status))
-		__nf_nat_cleanup_conntrack(ct);
+		nf_nat_cleanup_conntrack(ct);
 
 	/* don't delete conntrack.  Although that would make things a lot
 	 * simpler, we'd end up flushing all conntracks on nat rmmod.
@@ -868,20 +868,6 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
 	return 0;
 }
 
-/* No one using conntrack by the time this called. */
-static void nf_nat_cleanup_conntrack(struct nf_conn *ct)
-{
-	if (ct->status & IPS_SRC_NAT_DONE)
-		__nf_nat_cleanup_conntrack(ct);
-}
-
-static struct nf_ct_ext_type nat_extend __read_mostly = {
-	.len		= sizeof(struct nf_conn_nat),
-	.align		= __alignof__(struct nf_conn_nat),
-	.destroy	= nf_nat_cleanup_conntrack,
-	.id		= NF_CT_EXT_NAT,
-};
-
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 
 #include <linux/netfilter/nfnetlink.h>
@@ -1173,6 +1159,7 @@ static const struct nf_nat_hook nat_hook = {
 	.decode_session		= __nf_nat_decode_session,
 #endif
 	.manip_pkt		= nf_nat_manip_pkt,
+	.remove_nat_bysrc	= nf_nat_cleanup_conntrack,
 };
 
 static int __init nf_nat_init(void)
@@ -1188,19 +1175,11 @@ static int __init nf_nat_init(void)
 	if (!nf_nat_bysource)
 		return -ENOMEM;
 
-	ret = nf_ct_extend_register(&nat_extend);
-	if (ret < 0) {
-		kvfree(nf_nat_bysource);
-		pr_err("Unable to register extension\n");
-		return ret;
-	}
-
 	for (i = 0; i < CONNTRACK_LOCKS; i++)
 		spin_lock_init(&nf_nat_locks[i]);
 
 	ret = register_pernet_subsys(&nat_net_ops);
 	if (ret < 0) {
-		nf_ct_extend_unregister(&nat_extend);
 		kvfree(nf_nat_bysource);
 		return ret;
 	}
@@ -1219,7 +1198,6 @@ static void __exit nf_nat_cleanup(void)
 
 	nf_ct_iterate_destroy(nf_nat_proto_clean, &clean);
 
-	nf_ct_extend_unregister(&nat_extend);
 	nf_ct_helper_expectfn_unregister(&follow_master_nat);
 	RCU_INIT_POINTER(nf_nat_hook, NULL);
 

net/netfilter/nf_synproxy_core.c

@@ -236,12 +236,6 @@ synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff,
 	return 1;
 }
 
-static struct nf_ct_ext_type nf_ct_synproxy_extend __read_mostly = {
-	.len		= sizeof(struct nf_conn_synproxy),
-	.align		= __alignof__(struct nf_conn_synproxy),
-	.id		= NF_CT_EXT_SYNPROXY,
-};
-
 #ifdef CONFIG_PROC_FS
 static void *synproxy_cpu_seq_start(struct seq_file *seq, loff_t *pos)
 {
@@ -387,28 +381,12 @@ static struct pernet_operations synproxy_net_ops = {
 
 static int __init synproxy_core_init(void)
 {
-	int err;
-
-	err = nf_ct_extend_register(&nf_ct_synproxy_extend);
-	if (err < 0)
-		goto err1;
-
-	err = register_pernet_subsys(&synproxy_net_ops);
-	if (err < 0)
-		goto err2;
-
-	return 0;
-
-err2:
-	nf_ct_extend_unregister(&nf_ct_synproxy_extend);
-err1:
-	return err;
+	return register_pernet_subsys(&synproxy_net_ops);
 }
 
 static void __exit synproxy_core_exit(void)
 {
 	unregister_pernet_subsys(&synproxy_net_ops);
-	nf_ct_extend_unregister(&nf_ct_synproxy_extend);
 }
 
 module_init(synproxy_core_init);

net/netfilter/nf_tables_core.c

@@ -67,6 +67,20 @@ static void nft_cmp_fast_eval(const struct nft_expr *expr,
 	regs->verdict.code = NFT_BREAK;
 }
 
+static void nft_cmp16_fast_eval(const struct nft_expr *expr,
+				struct nft_regs *regs)
+{
+	const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr);
+	const u64 *reg_data = (const u64 *)&regs->data[priv->sreg];
+	const u64 *mask = (const u64 *)&priv->mask;
+	const u64 *data = (const u64 *)&priv->data;
+
+	if (((reg_data[0] & mask[0]) == data[0] &&
+	    ((reg_data[1] & mask[1]) == data[1])) ^ priv->inv)
+		return;
+	regs->verdict.code = NFT_BREAK;
+}
+
 static noinline void __nft_trace_verdict(struct nft_traceinfo *info,
 					 const struct nft_chain *chain,
 					 const struct nft_regs *regs)
@@ -225,6 +239,8 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv)
 		nft_rule_dp_for_each_expr(expr, last, rule) {
 			if (expr->ops == &nft_cmp_fast_ops)
 				nft_cmp_fast_eval(expr, &regs);
+			else if (expr->ops == &nft_cmp16_fast_ops)
+				nft_cmp16_fast_eval(expr, &regs);
 			else if (expr->ops == &nft_bitwise_fast_ops)
 				nft_bitwise_fast_eval(expr, &regs);
 			else if (expr->ops != &nft_payload_fast_ops ||

net/netfilter/nfnetlink_cttimeout.c

@@ -605,6 +605,11 @@ static struct pernet_operations cttimeout_ops = {
 	.size   = sizeof(struct nfct_timeout_pernet),
 };
 
+static const struct nf_ct_timeout_hooks hooks = {
+	.timeout_find_get = ctnl_timeout_find_get,
+	.timeout_put = ctnl_timeout_put,
+};
+
 static int __init cttimeout_init(void)
 {
 	int ret;
@@ -619,8 +624,7 @@ static int __init cttimeout_init(void)
 			"nfnetlink.\n");
 		goto err_out;
 	}
-	RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, ctnl_timeout_find_get);
-	RCU_INIT_POINTER(nf_ct_timeout_put_hook, ctnl_timeout_put);
+	RCU_INIT_POINTER(nf_ct_timeout_hook, &hooks);
 	return 0;
 
 err_out:
@@ -633,8 +637,7 @@ static void __exit cttimeout_exit(void)
 	nfnetlink_subsys_unregister(&cttimeout_subsys);
 
 	unregister_pernet_subsys(&cttimeout_ops);
-	RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, NULL);
-	RCU_INIT_POINTER(nf_ct_timeout_put_hook, NULL);
+	RCU_INIT_POINTER(nf_ct_timeout_hook, NULL);
 	synchronize_rcu();
 }
 

net/netfilter/nfnetlink_queue.c

@@ -402,6 +402,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
 #endif
 		+ nla_total_size(sizeof(u_int32_t))	/* mark */
+		+ nla_total_size(sizeof(u_int32_t))	/* priority */
 		+ nla_total_size(sizeof(struct nfqnl_msg_packet_hw))
 		+ nla_total_size(sizeof(u_int32_t))	/* skbinfo */
 		+ nla_total_size(sizeof(u_int32_t));	/* cap_len */
@@ -559,6 +560,10 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 	    nla_put_be32(skb, NFQA_MARK, htonl(entskb->mark)))
 		goto nla_put_failure;
 
+	if (entskb->priority &&
+	    nla_put_be32(skb, NFQA_PRIORITY, htonl(entskb->priority)))
+		goto nla_put_failure;
+
 	if (indev && entskb->dev &&
 	    skb_mac_header_was_set(entskb) &&
 	    skb_mac_header_len(entskb) != 0) {
@@ -1014,11 +1019,13 @@ static const struct nla_policy nfqa_verdict_policy[NFQA_MAX+1] = {
 	[NFQA_CT]		= { .type = NLA_UNSPEC },
 	[NFQA_EXP]		= { .type = NLA_UNSPEC },
 	[NFQA_VLAN]		= { .type = NLA_NESTED },
+	[NFQA_PRIORITY]		= { .type = NLA_U32 },
 };
 
 static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = {
 	[NFQA_VERDICT_HDR]	= { .len = sizeof(struct nfqnl_msg_verdict_hdr) },
 	[NFQA_MARK]		= { .type = NLA_U32 },
+	[NFQA_PRIORITY]		= { .type = NLA_U32 },
 };
 
 static struct nfqnl_instance *
@@ -1099,6 +1106,9 @@ static int nfqnl_recv_verdict_batch(struct sk_buff *skb,
 		if (nfqa[NFQA_MARK])
 			entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK]));
 
+		if (nfqa[NFQA_PRIORITY])
+			entry->skb->priority = ntohl(nla_get_be32(nfqa[NFQA_PRIORITY]));
+
 		nfqnl_reinject(entry, verdict);
 	}
 	return 0;
@@ -1225,6 +1235,9 @@ static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info,
 	if (nfqa[NFQA_MARK])
 		entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK]));
 
+	if (nfqa[NFQA_PRIORITY])
+		entry->skb->priority = ntohl(nla_get_be32(nfqa[NFQA_PRIORITY]));
+
 	nfqnl_reinject(entry, verdict);
 	return 0;
 }

net/netfilter/nft_cmp.c

@@ -272,12 +272,103 @@ const struct nft_expr_ops nft_cmp_fast_ops = {
 	.offload	= nft_cmp_fast_offload,
 };
 
+static u32 nft_cmp_mask(u32 bitlen)
+{
+	return (__force u32)cpu_to_le32(~0U >> (sizeof(u32) * BITS_PER_BYTE - bitlen));
+}
+
+static void nft_cmp16_fast_mask(struct nft_data *data, unsigned int bitlen)
+{
+	int len = bitlen / BITS_PER_BYTE;
+	int i, words = len / sizeof(u32);
+
+	for (i = 0; i < words; i++) {
+		data->data[i] = 0xffffffff;
+		bitlen -= sizeof(u32) * BITS_PER_BYTE;
+	}
+
+	if (len % sizeof(u32))
+		data->data[i++] = nft_cmp_mask(bitlen);
+
+	for (; i < 4; i++)
+		data->data[i] = 0;
+}
+
+static int nft_cmp16_fast_init(const struct nft_ctx *ctx,
+			       const struct nft_expr *expr,
+			       const struct nlattr * const tb[])
+{
+	struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr);
+	struct nft_data_desc desc;
+	int err;
+
+	err = nft_data_init(NULL, &priv->data, sizeof(priv->data), &desc,
+			    tb[NFTA_CMP_DATA]);
+	if (err < 0)
+		return err;
+
+	err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len);
+	if (err < 0)
+		return err;
+
+	nft_cmp16_fast_mask(&priv->mask, desc.len * BITS_PER_BYTE);
+	priv->inv = ntohl(nla_get_be32(tb[NFTA_CMP_OP])) != NFT_CMP_EQ;
+	priv->len = desc.len;
+
+	return 0;
+}
+
+static int nft_cmp16_fast_offload(struct nft_offload_ctx *ctx,
+				  struct nft_flow_rule *flow,
+				  const struct nft_expr *expr)
+{
+	const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr);
+	struct nft_cmp_expr cmp = {
+		.data	= priv->data,
+		.sreg	= priv->sreg,
+		.len	= priv->len,
+		.op	= priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ,
+	};
+
+	return __nft_cmp_offload(ctx, flow, &cmp);
+}
+
+static int nft_cmp16_fast_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr);
+	enum nft_cmp_ops op = priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ;
+
+	if (nft_dump_register(skb, NFTA_CMP_SREG, priv->sreg))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_CMP_OP, htonl(op)))
+		goto nla_put_failure;
+
+	if (nft_data_dump(skb, NFTA_CMP_DATA, &priv->data,
+			  NFT_DATA_VALUE, priv->len) < 0)
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+
+const struct nft_expr_ops nft_cmp16_fast_ops = {
+	.type		= &nft_cmp_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_cmp16_fast_expr)),
+	.eval		= NULL,	/* inlined */
+	.init		= nft_cmp16_fast_init,
+	.dump		= nft_cmp16_fast_dump,
+	.offload	= nft_cmp16_fast_offload,
+};
+
 static const struct nft_expr_ops *
 nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
 {
 	struct nft_data_desc desc;
 	struct nft_data data;
 	enum nft_cmp_ops op;
+	u8 sreg;
 	int err;
 
 	if (tb[NFTA_CMP_SREG] == NULL ||
@@ -306,9 +397,16 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
 	if (desc.type != NFT_DATA_VALUE)
 		goto err1;
 
-	if (desc.len <= sizeof(u32) && (op == NFT_CMP_EQ || op == NFT_CMP_NEQ))
-		return &nft_cmp_fast_ops;
+	sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG]));
 
+	if (op == NFT_CMP_EQ || op == NFT_CMP_NEQ) {
+		if (desc.len <= sizeof(u32))
+			return &nft_cmp_fast_ops;
+		else if (desc.len <= sizeof(data) &&
+			 ((sreg >= NFT_REG_1 && sreg <= NFT_REG_4) ||
+			  (sreg >= NFT_REG32_00 && sreg <= NFT_REG32_12 && sreg % 2 == 0)))
+			return &nft_cmp16_fast_ops;
+	}
 	return &nft_cmp_ops;
 err1:
 	nft_data_release(&data, desc.type);

net/netfilter/nft_compat.c

@@ -731,6 +731,14 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = {
 
 static struct nft_expr_type nft_match_type;
 
+static bool nft_match_reduce(struct nft_regs_track *track,
+			     const struct nft_expr *expr)
+{
+	const struct xt_match *match = expr->ops->data;
+
+	return strcmp(match->name, "comment") == 0;
+}
+
 static const struct nft_expr_ops *
 nft_match_select_ops(const struct nft_ctx *ctx,
 		     const struct nlattr * const tb[])
@@ -773,6 +781,7 @@ nft_match_select_ops(const struct nft_ctx *ctx,
 	ops->dump = nft_match_dump;
 	ops->validate = nft_match_validate;
 	ops->data = match;
+	ops->reduce = nft_match_reduce;
 
 	matchsize = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize));
 	if (matchsize > NFT_MATCH_LARGE_THRESH) {

net/netfilter/nft_exthdr.c

@@ -308,6 +308,63 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr,
 	regs->verdict.code = NFT_BREAK;
 }
 
+static void nft_exthdr_tcp_strip_eval(const struct nft_expr *expr,
+				      struct nft_regs *regs,
+				      const struct nft_pktinfo *pkt)
+{
+	u8 buff[sizeof(struct tcphdr) + MAX_TCP_OPTION_SPACE];
+	struct nft_exthdr *priv = nft_expr_priv(expr);
+	unsigned int i, tcphdr_len, optl;
+	struct tcphdr *tcph;
+	u8 *opt;
+
+	tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len);
+	if (!tcph)
+		goto err;
+
+	if (skb_ensure_writable(pkt->skb, nft_thoff(pkt) + tcphdr_len))
+		goto drop;
+
+	opt = (u8 *)nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len);
+	if (!opt)
+		goto err;
+	for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) {
+		unsigned int j;
+
+		optl = optlen(opt, i);
+		if (priv->type != opt[i])
+			continue;
+
+		if (i + optl > tcphdr_len)
+			goto drop;
+
+		for (j = 0; j < optl; ++j) {
+			u16 n = TCPOPT_NOP;
+			u16 o = opt[i+j];
+
+			if ((i + j) % 2 == 0) {
+				o <<= 8;
+				n <<= 8;
+			}
+			inet_proto_csum_replace2(&tcph->check, pkt->skb, htons(o),
+						 htons(n), false);
+		}
+		memset(opt + i, TCPOPT_NOP, optl);
+		return;
+	}
+
+	/* option not found, continue. This allows to do multiple
+	 * option removals per rule.
+	 */
+	return;
+err:
+	regs->verdict.code = NFT_BREAK;
+	return;
+drop:
+	/* can't remove, no choice but to drop */
+	regs->verdict.code = NF_DROP;
+}
+
 static void nft_exthdr_sctp_eval(const struct nft_expr *expr,
 				 struct nft_regs *regs,
 				 const struct nft_pktinfo *pkt)
@@ -457,6 +514,28 @@ static int nft_exthdr_tcp_set_init(const struct nft_ctx *ctx,
 				       priv->len);
 }
 
+static int nft_exthdr_tcp_strip_init(const struct nft_ctx *ctx,
+				     const struct nft_expr *expr,
+				     const struct nlattr * const tb[])
+{
+	struct nft_exthdr *priv = nft_expr_priv(expr);
+
+	if (tb[NFTA_EXTHDR_SREG] ||
+	    tb[NFTA_EXTHDR_DREG] ||
+	    tb[NFTA_EXTHDR_FLAGS] ||
+	    tb[NFTA_EXTHDR_OFFSET] ||
+	    tb[NFTA_EXTHDR_LEN])
+		return -EINVAL;
+
+	if (!tb[NFTA_EXTHDR_TYPE])
+		return -EINVAL;
+
+	priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]);
+	priv->op = NFT_EXTHDR_OP_TCPOPT;
+
+	return 0;
+}
+
 static int nft_exthdr_ipv4_init(const struct nft_ctx *ctx,
 				const struct nft_expr *expr,
 				const struct nlattr * const tb[])
@@ -517,6 +596,13 @@ static int nft_exthdr_dump_set(struct sk_buff *skb, const struct nft_expr *expr)
 	return nft_exthdr_dump_common(skb, priv);
 }
 
+static int nft_exthdr_dump_strip(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_exthdr *priv = nft_expr_priv(expr);
+
+	return nft_exthdr_dump_common(skb, priv);
+}
+
 static const struct nft_expr_ops nft_exthdr_ipv6_ops = {
 	.type		= &nft_exthdr_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
@@ -549,6 +635,14 @@ static const struct nft_expr_ops nft_exthdr_tcp_set_ops = {
 	.dump		= nft_exthdr_dump_set,
 };
 
+static const struct nft_expr_ops nft_exthdr_tcp_strip_ops = {
+	.type		= &nft_exthdr_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
+	.eval		= nft_exthdr_tcp_strip_eval,
+	.init		= nft_exthdr_tcp_strip_init,
+	.dump		= nft_exthdr_dump_strip,
+};
+
 static const struct nft_expr_ops nft_exthdr_sctp_ops = {
 	.type		= &nft_exthdr_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
@@ -576,7 +670,7 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx,
 			return &nft_exthdr_tcp_set_ops;
 		if (tb[NFTA_EXTHDR_DREG])
 			return &nft_exthdr_tcp_ops;
-		break;
+		return &nft_exthdr_tcp_strip_ops;
 	case NFT_EXTHDR_OP_IPV6:
 		if (tb[NFTA_EXTHDR_DREG])
 			return &nft_exthdr_ipv6_ops;

net/sched/act_ct.c

@@ -57,12 +57,6 @@ static const struct rhashtable_params zones_params = {
 	.automatic_shrinking = true,
 };
 
-static struct nf_ct_ext_type act_ct_extend __read_mostly = {
-	.len		= sizeof(struct nf_conn_act_ct_ext),
-	.align		= __alignof__(struct nf_conn_act_ct_ext),
-	.id		= NF_CT_EXT_ACT_CT,
-};
-
 static struct flow_action_entry *
 tcf_ct_flow_table_flow_action_get_next(struct flow_action *flow_action)
 {
@@ -1608,16 +1602,10 @@ static int __init ct_init_module(void)
 	if (err)
 		goto err_register;
 
-	err = nf_ct_extend_register(&act_ct_extend);
-	if (err)
-		goto err_register_extend;
-
 	static_branch_inc(&tcf_frag_xmit_count);
 
 	return 0;
 
-err_register_extend:
-	tcf_unregister_action(&act_ct_ops, &ct_net_ops);
 err_register:
 	tcf_ct_flow_tables_uninit();
 err_tbl_init:
@@ -1628,7 +1616,6 @@ static int __init ct_init_module(void)
 static void __exit ct_cleanup_module(void)
 {
 	static_branch_dec(&tcf_frag_xmit_count);
-	nf_ct_extend_unregister(&act_ct_extend);
 	tcf_unregister_action(&act_ct_ops, &ct_net_ops);
 	tcf_ct_flow_tables_uninit();
 	destroy_workqueue(act_ct_wq);