netfilter: nf_conntrack: make sequence number adjustments usuable wit…

…hout NAT Split out sequence number adjustments from NAT and move them to the conntrack core to make them usable for SYN proxying. The sequence number adjustment information is moved to a seperate extend. The extend is added to new conntracks when a NAT mapping is set up for a connection using a helper. As a side effect, this saves 24 bytes per connection with NAT in the common case that a connection does not have a helper assigned. Signed-off-by: Patrick McHardy <kaber@trash.net> Tested-by: Martin Topholm <mph@one.com> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Allyn69 · Aug 27, 2013 · 41d73ec · 41d73ec
1 parent 706f515
commit 41d73ec
Show file tree

Hide file tree

Showing 18 changed files with 369 additions and 376 deletions.
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
@@ -319,6 +319,7 @@ extern void nf_ct_attach(struct sk_buff *, const struct sk_buff *);
 extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu;
 
 struct nf_conn;
+enum ip_conntrack_info;
 struct nlattr;
 
 struct nfq_ct_hook {
@@ -327,14 +328,10 @@ struct nfq_ct_hook {
 	int (*parse)(const struct nlattr *attr, struct nf_conn *ct);
 	int (*attach_expect)(const struct nlattr *attr, struct nf_conn *ct,
 			     u32 portid, u32 report);
-};
-extern struct nfq_ct_hook __rcu *nfq_ct_hook;
-
-struct nfq_ct_nat_hook {
 	void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct,
-			   u32 ctinfo, s32 off);
+			   enum ip_conntrack_info ctinfo, s32 off);
 };
-extern struct nfq_ct_nat_hook __rcu *nfq_ct_nat_hook;
+extern struct nfq_ct_hook __rcu *nfq_ct_hook;
 #else
 static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {}
 #endif

diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
@@ -9,6 +9,7 @@ enum nf_ct_ext_id {
 	NF_CT_EXT_HELPER,
 #if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE)
 	NF_CT_EXT_NAT,
+	NF_CT_EXT_SEQADJ,
 #endif
 	NF_CT_EXT_ACCT,
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
@@ -31,6 +32,7 @@ enum nf_ct_ext_id {
 
 #define NF_CT_EXT_HELPER_TYPE struct nf_conn_help
 #define NF_CT_EXT_NAT_TYPE struct nf_conn_nat
+#define NF_CT_EXT_SEQADJ_TYPE struct nf_conn_seqadj
 #define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter
 #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache
 #define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone

diff --git a/include/net/netfilter/nf_conntrack_seqadj.h b/include/net/netfilter/nf_conntrack_seqadj.h
@@ -0,0 +1,49 @@
+#ifndef _NF_CONNTRACK_SEQADJ_H
+#define _NF_CONNTRACK_SEQADJ_H
+
+#include <net/netfilter/nf_conntrack_extend.h>
+
+/**
+ * struct nf_ct_seqadj - sequence number adjustment information
+ *
+ * @correction_pos: position of the last TCP sequence number modification
+ * @offset_before: sequence number offset before last modification
+ * @offset_after: sequence number offset after last modification
+ */
+struct nf_ct_seqadj {
+	u32		correction_pos;
+	s32		offset_before;
+	s32		offset_after;
+};
+
+struct nf_conn_seqadj {
+	struct nf_ct_seqadj	seq[IP_CT_DIR_MAX];
+};
+
+static inline struct nf_conn_seqadj *nfct_seqadj(const struct nf_conn *ct)
+{
+	return nf_ct_ext_find(ct, NF_CT_EXT_SEQADJ);
+}
+
+static inline struct nf_conn_seqadj *nfct_seqadj_ext_add(struct nf_conn *ct)
+{
+	return nf_ct_ext_add(ct, NF_CT_EXT_SEQADJ, GFP_ATOMIC);
+}
+
+extern int nf_ct_seqadj_set(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
+			    __be32 seq, s32 off);
+extern void nf_ct_tcp_seqadj_set(struct sk_buff *skb,
+				 struct nf_conn *ct,
+				 enum ip_conntrack_info ctinfo,
+				 s32 off);
+
+extern int nf_ct_seq_adjust(struct sk_buff *skb,
+			    struct nf_conn *ct, enum ip_conntrack_info ctinfo,
+			    unsigned int protoff);
+extern s32 nf_ct_seq_offset(const struct nf_conn *ct, enum ip_conntrack_dir,
+			    u32 seq);
+
+extern int nf_conntrack_seqadj_init(void);
+extern void nf_conntrack_seqadj_fini(void);
+
+#endif /* _NF_CONNTRACK_SEQADJ_H */
diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
@@ -13,15 +13,6 @@ enum nf_nat_manip_type {
 #define HOOK2MANIP(hooknum) ((hooknum) != NF_INET_POST_ROUTING && \
 			     (hooknum) != NF_INET_LOCAL_IN)
 
-/* NAT sequence number modifications */
-struct nf_nat_seq {
-	/* position of the last TCP sequence number modification (if any) */
-	u_int32_t correction_pos;
-
-	/* sequence number offset before and after last modification */
-	int32_t offset_before, offset_after;
-};
-
 #include <linux/list.h>
 #include <linux/netfilter/nf_conntrack_pptp.h>
 #include <net/netfilter/nf_conntrack_extend.h>
@@ -39,7 +30,6 @@ struct nf_conn;
 /* The structure embedded in the conntrack structure. */
 struct nf_conn_nat {
 	struct hlist_node bysource;
-	struct nf_nat_seq seq[IP_CT_DIR_MAX];
 	struct nf_conn *ct;
 	union nf_conntrack_nat_help help;
 #if defined(CONFIG_IP_NF_TARGET_MASQUERADE) || \

diff --git a/include/net/netfilter/nf_nat_helper.h b/include/net/netfilter/nf_nat_helper.h
@@ -39,28 +39,9 @@ extern int nf_nat_mangle_udp_packet(struct sk_buff *skb,
 				    const char *rep_buffer,
 				    unsigned int rep_len);
 
-extern void nf_nat_set_seq_adjust(struct nf_conn *ct,
-				  enum ip_conntrack_info ctinfo,
-				  __be32 seq, s32 off);
-extern int nf_nat_seq_adjust(struct sk_buff *skb,
-			     struct nf_conn *ct,
-			     enum ip_conntrack_info ctinfo,
-			     unsigned int protoff);
-extern int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb,
-				     struct nf_conn *ct,
-				     enum ip_conntrack_info ctinfo,
-				     unsigned int protoff);
-
 /* Setup NAT on this expected conntrack so it follows master, but goes
  * to port ct->master->saved_proto. */
 extern void nf_nat_follow_master(struct nf_conn *ct,
 				 struct nf_conntrack_expect *this);
 
-extern s32 nf_nat_get_offset(const struct nf_conn *ct,
-			     enum ip_conntrack_dir dir,
-			     u32 seq);
-
-extern void nf_nat_tcp_seq_adjust(struct sk_buff *skb, struct nf_conn *ct,
-				  u32 dir, s32 off);
-
 #endif
diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h
@@ -99,7 +99,8 @@ enum ip_conntrack_events {
 	IPCT_PROTOINFO,		/* protocol information has changed */
 	IPCT_HELPER,		/* new helper has been set */
 	IPCT_MARK,		/* new mark has been set */
-	IPCT_NATSEQADJ,		/* NAT is doing sequence adjustment */
+	IPCT_SEQADJ,		/* sequence adjustment has changed */
+	IPCT_NATSEQADJ = IPCT_SEQADJ,
 	IPCT_SECMARK,		/* new security mark has been set */
 	IPCT_LABEL,		/* new connlabel has been set */
 };

diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
@@ -42,8 +42,10 @@ enum ctattr_type {
 	CTA_ID,
 	CTA_NAT_DST,
 	CTA_TUPLE_MASTER,
-	CTA_NAT_SEQ_ADJ_ORIG,
-	CTA_NAT_SEQ_ADJ_REPLY,
+	CTA_SEQ_ADJ_ORIG,
+	CTA_NAT_SEQ_ADJ_ORIG	= CTA_SEQ_ADJ_ORIG,
+	CTA_SEQ_ADJ_REPLY,
+	CTA_NAT_SEQ_ADJ_REPLY	= CTA_SEQ_ADJ_REPLY,
 	CTA_SECMARK,		/* obsolete */
 	CTA_ZONE,
 	CTA_SECCTX,
@@ -165,6 +167,15 @@ enum ctattr_protonat {
 };
 #define CTA_PROTONAT_MAX (__CTA_PROTONAT_MAX - 1)
 
+enum ctattr_seqadj {
+	CTA_SEQADJ_UNSPEC,
+	CTA_SEQADJ_CORRECTION_POS,
+	CTA_SEQADJ_OFFSET_BEFORE,
+	CTA_SEQADJ_OFFSET_AFTER,
+	__CTA_SEQADJ_MAX
+};
+#define CTA_SEQADJ_MAX (__CTA_SEQADJ_MAX - 1)
+
 enum ctattr_natseq {
 	CTA_NAT_SEQ_UNSPEC,
 	CTA_NAT_SEQ_CORRECTION_POS,

diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -25,6 +25,7 @@
 #include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
 #include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
 #include <net/netfilter/nf_nat_helper.h>
 #include <net/netfilter/ipv4/nf_defrag_ipv4.h>
@@ -136,11 +137,7 @@ static unsigned int ipv4_confirm(unsigned int hooknum,
 	/* adjust seqs for loopback traffic only in outgoing direction */
 	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
 	    !nf_is_loopback_packet(skb)) {
-		typeof(nf_nat_seq_adjust_hook) seq_adjust;
-
-		seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook);
-		if (!seq_adjust ||
-		    !seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) {
+		if (!nf_ct_seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) {
 			NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
 			return NF_DROP;
 		}

diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -28,6 +28,7 @@
 #include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
 #include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
 #include <net/netfilter/nf_nat_helper.h>
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
@@ -158,11 +159,7 @@ static unsigned int ipv6_confirm(unsigned int hooknum,
 	/* adjust seqs for loopback traffic only in outgoing direction */
 	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
 	    !nf_is_loopback_packet(skb)) {
-		typeof(nf_nat_seq_adjust_hook) seq_adjust;
-
-		seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook);
-		if (!seq_adjust ||
-		    !seq_adjust(skb, ct, ctinfo, protoff)) {
+		if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) {
 			NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
 			return NF_DROP;
 		}

diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
@@ -1,6 +1,6 @@
 netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o
 
-nf_conntrack-y	:= nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o
+nf_conntrack-y	:= nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
@@ -39,6 +39,7 @@
 #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>
@@ -1326,6 +1327,7 @@ void nf_conntrack_cleanup_end(void)
 	nf_ct_extend_unregister(&nf_ct_zone_extend);
 #endif
 	nf_conntrack_proto_fini();
+	nf_conntrack_seqadj_fini();
 	nf_conntrack_labels_fini();
 	nf_conntrack_helper_fini();
 	nf_conntrack_timeout_fini();
@@ -1531,6 +1533,10 @@ int nf_conntrack_init_start(void)
 	if (ret < 0)
 		goto err_labels;
 
+	ret = nf_conntrack_seqadj_init();
+	if (ret < 0)
+		goto err_seqadj;
+
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	ret = nf_ct_extend_register(&nf_ct_zone_extend);
 	if (ret < 0)
@@ -1555,6 +1561,8 @@ int nf_conntrack_init_start(void)
 	nf_ct_extend_unregister(&nf_ct_zone_extend);
 err_extend:
 #endif
+	nf_conntrack_seqadj_fini();
+err_seqadj:
 	nf_conntrack_labels_fini();
 err_labels:
 	nf_conntrack_helper_fini();
@@ -1577,9 +1585,6 @@ void nf_conntrack_init_end(void)
 	/* For use by REJECT target */
 	RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach);
 	RCU_INIT_POINTER(nf_ct_destroy, destroy_conntrack);
-
-	/* Howto get NAT offsets */
-	RCU_INIT_POINTER(nf_ct_nat_offset, NULL);
 }
 
 /*
@@ -1666,8 +1671,3 @@ int nf_conntrack_init_net(struct net *net)
 err_stat:
 	return ret;
 }
-
-s32 (*nf_ct_nat_offset)(const struct nf_conn *ct,
-			enum ip_conntrack_dir dir,
-			u32 seq);
-EXPORT_SYMBOL_GPL(nf_ct_nat_offset);