Netfilter/IPVS updates for net-next

index 6de981270566..08cbed7d940e 100644
@@ -89,8 +89,7 @@ static void nft_reject_br_send_v4_tcp_reset(struct net *net,
 	niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
 				   net->ipv4.sysctl_ip_default_ttl);
 	nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
-	niph->ttl	= net->ipv4.sysctl_ip_default_ttl;
-	niph->tot_len	= htons(nskb->len);
+	niph->tot_len = htons(nskb->len);
 	ip_send_check(niph);
 
 	nft_reject_br_push_etherhdr(oldskb, nskb);

index eb0d1658ac05..d8125616edc7 100644
@@ -107,11 +107,12 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)
 	tcp->seen[1].td_maxwin = 0;
 }
 
+#define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT	(120 * HZ)
+#define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT	(30 * HZ)
+
 static void flow_offload_fixup_ct_state(struct nf_conn *ct)
 {
 	const struct nf_conntrack_l4proto *l4proto;
-	struct net *net = nf_ct_net(ct);
-	unsigned int *timeouts;
 	unsigned int timeout;
 	int l4num;
 

@@ -123,14 +124,10 @@ static void flow_offload_fixup_ct_state(struct nf_conn *ct)
 	if (!l4proto)
 		return;
 
-	timeouts = l4proto->get_timeouts(net);
-	if (!timeouts)
-		return;
-
 	if (l4num == IPPROTO_TCP)
-		timeout = timeouts[TCP_CONNTRACK_ESTABLISHED];
+		timeout = NF_FLOWTABLE_TCP_PICKUP_TIMEOUT;
 	else if (l4num == IPPROTO_UDP)
-		timeout = timeouts[UDP_CT_REPLIED];
+		timeout = NF_FLOWTABLE_UDP_PICKUP_TIMEOUT;
 	else
 		return;
 

index 9754a50ecde9..d5a80888cbe4 100644
@@ -17,6 +17,14 @@ static inline bool nf_tproxy_sk_is_transparent(struct sock *sk)
 	return false;
 }
 
+/* assign a socket to the skb -- consumes sk */
+static inline void nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk)
+{
+	skb_orphan(skb);
+	skb->sk = sk;
+	skb->destructor = sock_edemux;
+}
+
 __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr);
 
 /**

index 58fce4e749a9..35df0827e2ca 100644
@@ -36,15 +36,6 @@
 #include <net/netfilter/nf_tproxy.h>
 #include <linux/netfilter/xt_TPROXY.h>
 
-/* assign a socket to the skb -- consumes sk */
-static void
-nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk)
-{
-	skb_orphan(skb);
-	skb->sk = sk;
-	skb->destructor = sock_edemux;
-}
-
 static unsigned int
 tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport,
 	   u_int32_t mark_mask, u_int32_t mark_value)

index b31dabfdb453..95ab5cc64422 100644
@@ -23,9 +23,6 @@ struct nf_queue_entry;
 #ifdef CONFIG_INET
 __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
 		       unsigned int dataoff, u_int8_t protocol);
-__sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook,
-			       unsigned int dataoff, unsigned int len,
-			       u_int8_t protocol);
 int nf_ip_route(struct net *net, struct dst_entry **dst, struct flowi *fl,
 		bool strict);
 int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry);

@@ -35,14 +32,6 @@ static inline __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
 {
 	return 0;
 }
-static inline __sum16 nf_ip_checksum_partial(struct sk_buff *skb,
-					     unsigned int hook,
-					     unsigned int dataoff,
-					     unsigned int len,
-					     u_int8_t protocol)
-{
-	return 0;
-}
 static inline int nf_ip_route(struct net *net, struct dst_entry **dst,
 			      struct flowi *fl, bool strict)
 {

59 lines not on this page · raw message

64 lines not on this page · raw message

index 288c597e75b3..c0dc4dd78887 100644
@@ -30,11 +30,6 @@ struct nf_ipv6_ops {
 	void (*route_input)(struct sk_buff *skb);
 	int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb,
 			int (*output)(struct net *, struct sock *, struct sk_buff *));
-	__sum16 (*checksum)(struct sk_buff *skb, unsigned int hook,
-			    unsigned int dataoff, u_int8_t protocol);
-	__sum16 (*checksum_partial)(struct sk_buff *skb, unsigned int hook,
-				    unsigned int dataoff, unsigned int len,
-				    u_int8_t protocol);
 	int (*route)(struct net *net, struct dst_entry **dst, struct flowi *fl,
 		     bool strict);
 	int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry);

78 lines not on this page · raw message

110 lines not on this page · raw message

index 9b5e7634713e..90df45022c51 100644
@@ -40,13 +40,6 @@ void nf_conntrack_cleanup_start(void);
 void nf_conntrack_init_end(void);
 void nf_conntrack_cleanup_end(void);
 
-bool nf_ct_get_tuple(const struct sk_buff *skb, unsigned int nhoff,
-		     unsigned int dataoff, u_int16_t l3num, u_int8_t protonum,
-		     struct net *net,
-		     struct nf_conntrack_tuple *tuple,
-		     const struct nf_conntrack_l3proto *l3proto,
-		     const struct nf_conntrack_l4proto *l4proto);
-
 bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
 			const struct nf_conntrack_tuple *orig,
 			const struct nf_conntrack_l3proto *l3proto,

index 85ab2fd6a665..be0ab81e6b2c 100644
@@ -222,7 +222,7 @@ static u32 hash_conntrack(const struct net *net,
 	return scale_hash(hash_conntrack_raw(tuple, net));
 }
 
-bool
+static bool
 nf_ct_get_tuple(const struct sk_buff *skb,
 		unsigned int nhoff,
 		unsigned int dataoff,

@@ -244,7 +244,6 @@ nf_ct_get_tuple(const struct sk_buff *skb,
 
 	return l4proto->pkt_to_tuple(skb, dataoff, net, tuple);
 }
-EXPORT_SYMBOL_GPL(nf_ct_get_tuple);
 
 bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff,
 		       u_int16_t l3num,

index 284aca2a252d..e05bd3e53f0f 100644
@@ -607,23 +607,12 @@ static struct nf_conn *
 ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone,
 		     u8 l3num, struct sk_buff *skb, bool natted)
 {
-	const struct nf_conntrack_l3proto *l3proto;
-	const struct nf_conntrack_l4proto *l4proto;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
-	unsigned int dataoff;
-	u8 protonum;
 
-	l3proto = __nf_ct_l3proto_find(l3num);
-	if (l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff,
-				 &protonum) <= 0) {
-		pr_debug("ovs_ct_find_existing: Can't get protonum\n");
-		return NULL;
-	}
-	l4proto = __nf_ct_l4proto_find(l3num, protonum);
-	if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num,
-			     protonum, net, &tuple, l3proto, l4proto)) {
+	if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), l3num,
+			       net, &tuple)) {
 		pr_debug("ovs_ct_find_existing: Can't get tuple\n");
 		return NULL;
 	}

@@ -632,7 +621,7 @@ ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone,
 	if (natted) {
 		struct nf_conntrack_tuple inverse;
 
-		if (!nf_ct_invert_tuple(&inverse, &tuple, l3proto, l4proto)) {
+		if (!nf_ct_invert_tuplepr(&inverse, &tuple)) {
 			pr_debug("ovs_ct_find_existing: Inversion failed!\n");
 			return NULL;
 		}

index 90df45022c51..d454a53ba646 100644
@@ -68,10 +68,8 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb)
 	return ret;
 }
 
-void
-print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
-            const struct nf_conntrack_l3proto *l3proto,
-            const struct nf_conntrack_l4proto *proto);
+void print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
+		 const struct nf_conntrack_l4proto *proto);
 
 #define CONNTRACK_LOCKS 1024
 

index d5808f3e2715..d07b5216a925 100644
@@ -46,14 +46,6 @@ struct nf_conntrack_l3proto {
 	int (*get_l4proto)(const struct sk_buff *skb, unsigned int nhoff,
 			   unsigned int *dataoff, u_int8_t *protonum);
 
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	int (*tuple_to_nlattr)(struct sk_buff *skb,
-			       const struct nf_conntrack_tuple *t);
-	int (*nlattr_to_tuple)(struct nlattr *tb[],
-			       struct nf_conntrack_tuple *t);
-	const struct nla_policy *nla_policy;
-#endif
-
 	/* Called when netns wants to use connection tracking */
 	int (*net_ns_get)(struct net *);
 	void (*net_ns_put)(struct net *);

65 lines not on this page · raw message

66 lines not on this page · raw message

index c87b48359e8f..e631be25337e 100644
@@ -23,7 +23,6 @@
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
 #endif

index 853b23206bb7..3f586ba23d92 100644
@@ -610,7 +610,6 @@ static int exp_seq_show(struct seq_file *s, void *v)
 		   expect->tuple.src.l3num,
 		   expect->tuple.dst.protonum);
 	print_tuple(s, &expect->tuple,
-		    __nf_ct_l3proto_find(expect->tuple.src.l3num),
 		    __nf_ct_l4proto_find(expect->tuple.src.l3num,
 				       expect->tuple.dst.protonum));
 

index a75b11c39312..a55a58c706a9 100644
@@ -24,7 +24,6 @@
 #include <linux/rtnetlink.h>
 
 #include <net/netfilter/nf_conntrack.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_core.h>

168 lines not on this page · raw message

index d88841fbc560..859cb303bb91 100644
@@ -294,10 +294,7 @@ int nf_ct_l3proto_register(const struct nf_conntrack_l3proto *proto)
 
 	if (proto->l3proto >= NFPROTO_NUMPROTO)
 		return -EBUSY;
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	if (proto->tuple_to_nlattr && proto->nla_size == 0)
-		return -EINVAL;
-#endif
+
 	mutex_lock(&nf_ct_proto_mutex);
 	old = rcu_dereference_protected(nf_ct_l3protos[proto->l3proto],
 					lockdep_is_held(&nf_ct_proto_mutex));

index b642c0b2495c..47b80fd0d2c3 100644
@@ -24,7 +24,6 @@
 
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_core.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_helper.h>

@@ -38,10 +37,9 @@ MODULE_LICENSE("GPL");
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 void
 print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
-            const struct nf_conntrack_l3proto *l3proto,
             const struct nf_conntrack_l4proto *l4proto)
 {
-	switch (l3proto->l3proto) {
+	switch (tuple->src.l3num) {
 	case NFPROTO_IPV4:
 		seq_printf(s, "src=%pI4 dst=%pI4 ",
 			   &tuple->src.u3.ip, &tuple->dst.u3.ip);

@@ -282,7 +280,6 @@ static int ct_seq_show(struct seq_file *s, void *v)
 {
 	struct nf_conntrack_tuple_hash *hash = v;
 	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash);
-	const struct nf_conntrack_l3proto *l3proto;
 	const struct nf_conntrack_l4proto *l4proto;
 	struct net *net = seq_file_net(s);
 	int ret = 0;

@@ -303,14 +300,12 @@ static int ct_seq_show(struct seq_file *s, void *v)
 	if (!net_eq(nf_ct_net(ct), net))
 		goto release;
 
-	l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct));
-	WARN_ON(!l3proto);
 	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
 	WARN_ON(!l4proto);
 
 	ret = -ENOSPC;
 	seq_printf(s, "%-8s %u %-8s %u ",
-		   l3proto_name(l3proto->l3proto), nf_ct_l3num(ct),
+		   l3proto_name(nf_ct_l3num(ct)), nf_ct_l3num(ct),
 		   l4proto_name(l4proto->l4proto), nf_ct_protonum(ct));
 
 	if (!test_bit(IPS_OFFLOAD_BIT, &ct->status))

@@ -320,7 +315,7 @@ static int ct_seq_show(struct seq_file *s, void *v)
 		l4proto->print_conntrack(s, ct);
 
 	print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
-		    l3proto, l4proto);
+		    l4proto);
 
 	ct_show_zone(s, ct, NF_CT_ZONE_DIR_ORIG);
 

@@ -333,8 +328,7 @@ static int ct_seq_show(struct seq_file *s, void *v)
 	if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status)))
 		seq_puts(s, "[UNREPLIED] ");
 
-	print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
-		    l3proto, l4proto);
+	print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, l4proto);
 
 	ct_show_zone(s, ct, NF_CT_ZONE_DIR_REPL);
 

index 9ee5fa551fa6..9da4b8462004 100644
@@ -26,7 +26,6 @@
 #include <net/sock.h>
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_core.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_tuple.h>
 #include <net/netfilter/nf_conntrack_timeout.h>

index d07b5216a925..ece231450f30 100644
@@ -25,13 +25,6 @@ struct nf_conntrack_l3proto {
 	u16 nla_size;
 
 	/*
-	 * Try to fill in the third arg: nhoff is offset of l3 proto
-         * hdr.  Return true if possible.
-	 */
-	bool (*pkt_to_tuple)(const struct sk_buff *skb, unsigned int nhoff,
-			     struct nf_conntrack_tuple *tuple);
-
-	/*
 	 * Invert the per-proto part of the tuple: ie. turn xmit into reply.
 	 * Some packets can't be inverted: return 0 in that case.
 	 */

index 98ed12858c52..7ed56f61798b 100644
@@ -38,22 +38,6 @@ struct conntrack4_net {
 	unsigned int users;
 };
 
-static bool ipv4_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
-			      struct nf_conntrack_tuple *tuple)
-{
-	const __be32 *ap;
-	__be32 _addrs[2];
-	ap = skb_header_pointer(skb, nhoff + offsetof(struct iphdr, saddr),
-				sizeof(u_int32_t) * 2, _addrs);
-	if (ap == NULL)
-		return false;
-
-	tuple->src.u3.ip = ap[0];
-	tuple->dst.u3.ip = ap[1];
-
-	return true;
-}
-
 static bool ipv4_invert_tuple(struct nf_conntrack_tuple *tuple,
 			      const struct nf_conntrack_tuple *orig)
 {

@@ -322,7 +306,6 @@ static void ipv4_hooks_unregister(struct net *net)
 
 const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = {
 	.l3proto	 = PF_INET,
-	.pkt_to_tuple	 = ipv4_pkt_to_tuple,
 	.invert_tuple	 = ipv4_invert_tuple,
 	.get_l4proto	 = ipv4_get_l4proto,
 	.net_ns_get	 = ipv4_hooks_register,

index 13a660ae5799..bdb1709bb951 100644
@@ -41,23 +41,6 @@ struct conntrack6_net {
 	unsigned int users;
 };
 
-static bool ipv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
-			      struct nf_conntrack_tuple *tuple)
-{
-	const u_int32_t *ap;
-	u_int32_t _addrs[8];
-
-	ap = skb_header_pointer(skb, nhoff + offsetof(struct ipv6hdr, saddr),
-				sizeof(_addrs), _addrs);
-	if (ap == NULL)
-		return false;
-
-	memcpy(tuple->src.u3.ip6, ap, sizeof(tuple->src.u3.ip6));
-	memcpy(tuple->dst.u3.ip6, ap + 4, sizeof(tuple->dst.u3.ip6));
-
-	return true;
-}
-
 static bool ipv6_invert_tuple(struct nf_conntrack_tuple *tuple,
 			      const struct nf_conntrack_tuple *orig)
 {

@@ -307,7 +290,6 @@ static void ipv6_hooks_unregister(struct net *net)
 
 const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = {
 	.l3proto		= PF_INET6,
-	.pkt_to_tuple		= ipv6_pkt_to_tuple,
 	.invert_tuple		= ipv6_invert_tuple,
 	.get_l4proto		= ipv6_get_l4proto,
 	.net_ns_get		= ipv6_hooks_register,

index be0ab81e6b2c..66b2ebae2747 100644
@@ -230,15 +230,43 @@ nf_ct_get_tuple(const struct sk_buff *skb,
 		u_int8_t protonum,
 		struct net *net,
 		struct nf_conntrack_tuple *tuple,
-		const struct nf_conntrack_l3proto *l3proto,
 		const struct nf_conntrack_l4proto *l4proto)
 {
+	unsigned int size;
+	const __be32 *ap;
+	__be32 _addrs[8];
+
 	memset(tuple, 0, sizeof(*tuple));
 
 	tuple->src.l3num = l3num;
-	if (l3proto->pkt_to_tuple(skb, nhoff, tuple) == 0)
+	switch (l3num) {
+	case NFPROTO_IPV4:
+		nhoff += offsetof(struct iphdr, saddr);
+		size = 2 * sizeof(__be32);
+		break;
+	case NFPROTO_IPV6:
+		nhoff += offsetof(struct ipv6hdr, saddr);
+		size = sizeof(_addrs);
+		break;
+	default:
+		return true;
+	}
+
+	ap = skb_header_pointer(skb, nhoff, size, _addrs);
+	if (!ap)
 		return false;
 
+	switch (l3num) {
+	case NFPROTO_IPV4:
+		tuple->src.u3.ip = ap[0];
+		tuple->dst.u3.ip = ap[1];
+		break;
+	case NFPROTO_IPV6:
+		memcpy(tuple->src.u3.ip6, ap, sizeof(tuple->src.u3.ip6));
+		memcpy(tuple->dst.u3.ip6, ap + 4, sizeof(tuple->dst.u3.ip6));
+		break;
+	}
+
 	tuple->dst.protonum = protonum;
 	tuple->dst.dir = IP_CT_DIR_ORIGINAL;
 

@@ -267,7 +295,7 @@ bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff,
 	l4proto = __nf_ct_l4proto_find(l3num, protonum);
 
 	ret = nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, net, tuple,
-			      l3proto, l4proto);
+			      l4proto);
 
 	rcu_read_unlock();
 	return ret;

@@ -1318,8 +1346,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 	u32 hash;
 
 	if (!nf_ct_get_tuple(skb, skb_network_offset(skb),
-			     dataoff, l3num, protonum, net, &tuple, l3proto,
-			     l4proto)) {
+			     dataoff, l3num, protonum, net, &tuple, l4proto)) {
 		pr_debug("Can't get tuple\n");
 		return 0;
 	}

@@ -1633,7 +1660,7 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb)
 	l4proto = nf_ct_l4proto_find_get(l3num, l4num);
 
 	if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num,
-			     l4num, net, &tuple, l3proto, l4proto))
+			     l4num, net, &tuple, l4proto))
 		return -1;
 
 	if (ct->status & IPS_SRC_NAT) {

index 397e6911214f..0b01c9970e99 100644
@@ -31,15 +31,6 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
 
-static bool generic_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
-				 struct nf_conntrack_tuple *tuple)
-{
-	memset(&tuple->src.u3, 0, sizeof(tuple->src.u3));
-	memset(&tuple->dst.u3, 0, sizeof(tuple->dst.u3));
-
-	return true;
-}
-
 static bool generic_invert_tuple(struct nf_conntrack_tuple *tuple,
 				 const struct nf_conntrack_tuple *orig)
 {

@@ -59,7 +50,6 @@ static int generic_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 
 struct nf_conntrack_l3proto nf_conntrack_l3proto_generic __read_mostly = {
 	.l3proto	 = PF_UNSPEC,
-	.pkt_to_tuple	 = generic_pkt_to_tuple,
 	.invert_tuple	 = generic_invert_tuple,
 	.get_l4proto	 = generic_get_l4proto,
 };

index d454a53ba646..35461b2d3462 100644
@@ -42,7 +42,6 @@ void nf_conntrack_cleanup_end(void);
 
 bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
 			const struct nf_conntrack_tuple *orig,
-			const struct nf_conntrack_l3proto *l3proto,
 			const struct nf_conntrack_l4proto *l4proto);
 
 /* Find a connection corresponding to a tuple. */

index ece231450f30..164641c743a5 100644
@@ -25,13 +25,6 @@ struct nf_conntrack_l3proto {
 	u16 nla_size;
 
 	/*
-	 * Invert the per-proto part of the tuple: ie. turn xmit into reply.
-	 * Some packets can't be inverted: return 0 in that case.
-	 */
-	bool (*invert_tuple)(struct nf_conntrack_tuple *inverse,
-			     const struct nf_conntrack_tuple *orig);
-
-	/*
 	 * Called before tracking. 
 	 *	*dataoff: offset of protocol header (TCP, UDP,...) in skb
 	 *	*protonum: protocol number

index 7ed56f61798b..e10e38c443ab 100644
@@ -38,15 +38,6 @@ struct conntrack4_net {
 	unsigned int users;
 };
 
-static bool ipv4_invert_tuple(struct nf_conntrack_tuple *tuple,
-			      const struct nf_conntrack_tuple *orig)
-{
-	tuple->src.u3.ip = orig->dst.u3.ip;
-	tuple->dst.u3.ip = orig->src.u3.ip;
-
-	return true;
-}
-
 static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 			    unsigned int *dataoff, u_int8_t *protonum)
 {

@@ -306,7 +297,6 @@ static void ipv4_hooks_unregister(struct net *net)
 
 const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = {
 	.l3proto	 = PF_INET,
-	.invert_tuple	 = ipv4_invert_tuple,
 	.get_l4proto	 = ipv4_get_l4proto,
 	.net_ns_get	 = ipv4_hooks_register,
 	.net_ns_put	 = ipv4_hooks_unregister,

index 5c15beafa711..34095949a003 100644
@@ -142,8 +142,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
 
 	/* Ordinarily, we'd expect the inverted tupleproto, but it's
 	   been preserved inside the ICMP. */
-	if (!nf_ct_invert_tuple(&innertuple, &origtuple,
-				&nf_conntrack_l3proto_ipv4, innerproto)) {
+	if (!nf_ct_invert_tuple(&innertuple, &origtuple, innerproto)) {
 		pr_debug("icmp_error_message: no match\n");
 		return -NF_ACCEPT;
 	}

index bdb1709bb951..f8051fe20489 100644
@@ -41,15 +41,6 @@ struct conntrack6_net {
 	unsigned int users;
 };
 
-static bool ipv6_invert_tuple(struct nf_conntrack_tuple *tuple,
-			      const struct nf_conntrack_tuple *orig)
-{
-	memcpy(tuple->src.u3.ip6, orig->dst.u3.ip6, sizeof(tuple->src.u3.ip6));
-	memcpy(tuple->dst.u3.ip6, orig->src.u3.ip6, sizeof(tuple->dst.u3.ip6));
-
-	return true;
-}
-
 static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 			    unsigned int *dataoff, u_int8_t *protonum)
 {

@@ -290,7 +281,6 @@ static void ipv6_hooks_unregister(struct net *net)
 
 const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = {
 	.l3proto		= PF_INET6,
-	.invert_tuple		= ipv6_invert_tuple,
 	.get_l4proto		= ipv6_get_l4proto,
 	.net_ns_get		= ipv6_hooks_register,
 	.net_ns_put		= ipv6_hooks_unregister,

index 2548e2c8aedd..8bcbc2f15bd5 100644
@@ -152,8 +152,7 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
 
 	/* Ordinarily, we'd expect the inverted tupleproto, but it's
 	   been preserved inside the ICMP. */
-	if (!nf_ct_invert_tuple(&intuple, &origtuple,
-				&nf_conntrack_l3proto_ipv6, inproto)) {
+	if (!nf_ct_invert_tuple(&intuple, &origtuple, inproto)) {
 		pr_debug("icmpv6_error: Can't invert tuple\n");
 		return -NF_ACCEPT;
 	}

index 66b2ebae2747..14c040805b32 100644
@@ -305,14 +305,24 @@ EXPORT_SYMBOL_GPL(nf_ct_get_tuplepr);
 bool
 nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
 		   const struct nf_conntrack_tuple *orig,
-		   const struct nf_conntrack_l3proto *l3proto,
 		   const struct nf_conntrack_l4proto *l4proto)
 {
 	memset(inverse, 0, sizeof(*inverse));
 
 	inverse->src.l3num = orig->src.l3num;
-	if (l3proto->invert_tuple(inverse, orig) == 0)
-		return false;
+
+	switch (orig->src.l3num) {
+	case NFPROTO_IPV4:
+		inverse->src.u3.ip = orig->dst.u3.ip;
+		inverse->dst.u3.ip = orig->src.u3.ip;
+		break;
+	case NFPROTO_IPV6:
+		inverse->src.u3.in6 = orig->dst.u3.in6;
+		inverse->dst.u3.in6 = orig->src.u3.in6;
+		break;
+	default:
+		break;
+	}
 
 	inverse->dst.dir = !orig->dst.dir;
 

@@ -1222,7 +1232,6 @@ EXPORT_SYMBOL_GPL(nf_conntrack_free);
 static noinline struct nf_conntrack_tuple_hash *
 init_conntrack(struct net *net, struct nf_conn *tmpl,
 	       const struct nf_conntrack_tuple *tuple,
-	       const struct nf_conntrack_l3proto *l3proto,
 	       const struct nf_conntrack_l4proto *l4proto,
 	       struct sk_buff *skb,
 	       unsigned int dataoff, u32 hash)

@@ -1237,7 +1246,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	struct nf_conntrack_zone tmp;
 	unsigned int *timeouts;
 
-	if (!nf_ct_invert_tuple(&repl_tuple, tuple, l3proto, l4proto)) {
+	if (!nf_ct_invert_tuple(&repl_tuple, tuple, l4proto)) {
 		pr_debug("Can't invert tuple.\n");
 		return NULL;
 	}

@@ -1334,7 +1343,6 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 		  unsigned int dataoff,
 		  u_int16_t l3num,
 		  u_int8_t protonum,
-		  const struct nf_conntrack_l3proto *l3proto,
 		  const struct nf_conntrack_l4proto *l4proto)
 {
 	const struct nf_conntrack_zone *zone;

@@ -1356,7 +1364,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 	hash = hash_conntrack_raw(&tuple, net);
 	h = __nf_conntrack_find_get(net, zone, &tuple, hash);
 	if (!h) {
-		h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto,
+		h = init_conntrack(net, tmpl, &tuple, l4proto,
 				   skb, dataoff, hash);
 		if (!h)
 			return 0;

@@ -1439,8 +1447,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 			goto out;
 	}
 repeat:
-	ret = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum,
-				l3proto, l4proto);
+	ret = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum, l4proto);
 	if (ret < 0) {
 		/* Too stressed to deal. */
 		NF_CT_STAT_INC_ATOMIC(net, drop);

@@ -1497,7 +1504,6 @@ bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse,
 
 	rcu_read_lock();
 	ret = nf_ct_invert_tuple(inverse, orig,
-				 __nf_ct_l3proto_find(orig->src.l3num),
 				 __nf_ct_l4proto_find(orig->src.l3num,
 						      orig->dst.protonum));
 	rcu_read_unlock();

index 0b01c9970e99..d6a8fe591ccc 100644
@@ -31,15 +31,6 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
 
-static bool generic_invert_tuple(struct nf_conntrack_tuple *tuple,
-				 const struct nf_conntrack_tuple *orig)
-{
-	memset(&tuple->src.u3, 0, sizeof(tuple->src.u3));
-	memset(&tuple->dst.u3, 0, sizeof(tuple->dst.u3));
-
-	return true;
-}
-
 static int generic_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 			       unsigned int *dataoff, u_int8_t *protonum)
 {

@@ -50,7 +41,6 @@ static int generic_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 
 struct nf_conntrack_l3proto nf_conntrack_l3proto_generic __read_mostly = {
 	.l3proto	 = PF_UNSPEC,
-	.invert_tuple	 = generic_invert_tuple,
 	.get_l4proto	 = generic_get_l4proto,
 };
 EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_generic);

index 164641c743a5..5f160375c93a 100644
@@ -24,14 +24,6 @@ struct nf_conntrack_l3proto {
 	/* size of tuple nlattr, fills a hole */
 	u16 nla_size;
 
-	/*
-	 * Called before tracking. 
-	 *	*dataoff: offset of protocol header (TCP, UDP,...) in skb
-	 *	*protonum: protocol number
-	 */
-	int (*get_l4proto)(const struct sk_buff *skb, unsigned int nhoff,
-			   unsigned int *dataoff, u_int8_t *protonum);
-
 	/* Called when netns wants to use connection tracking */
 	int (*net_ns_get)(struct net *);
 	void (*net_ns_put)(struct net *);

index e10e38c443ab..9fbf6c7f8ece 100644
@@ -38,35 +38,6 @@ struct conntrack4_net {
 	unsigned int users;
 };
 
-static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
-			    unsigned int *dataoff, u_int8_t *protonum)
-{
-	const struct iphdr *iph;
-	struct iphdr _iph;
-
-	iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
-	if (iph == NULL)
-		return -NF_ACCEPT;
-
-	/* Conntrack defragments packets, we might still see fragments
-	 * inside ICMP packets though. */
-	if (iph->frag_off & htons(IP_OFFSET))
-		return -NF_ACCEPT;
-
-	*dataoff = nhoff + (iph->ihl << 2);
-	*protonum = iph->protocol;
-
-	/* Check bogus IP headers */
-	if (*dataoff > skb->len) {
-		pr_debug("nf_conntrack_ipv4: bogus IPv4 packet: "
-			 "nhoff %u, ihl %u, skblen %u\n",
-			 nhoff, iph->ihl << 2, skb->len);
-		return -NF_ACCEPT;
-	}
-
-	return NF_ACCEPT;
-}
-
 static unsigned int ipv4_helper(void *priv,
 				struct sk_buff *skb,
 				const struct nf_hook_state *state)

@@ -297,7 +268,6 @@ static void ipv4_hooks_unregister(struct net *net)
 
 const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = {
 	.l3proto	 = PF_INET,
-	.get_l4proto	 = ipv4_get_l4proto,
 	.net_ns_get	 = ipv4_hooks_register,
 	.net_ns_put	 = ipv4_hooks_unregister,
 	.me		 = THIS_MODULE,

index f8051fe20489..37ab25645cf2 100644
@@ -41,34 +41,6 @@ struct conntrack6_net {
 	unsigned int users;
 };
 
-static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
-			    unsigned int *dataoff, u_int8_t *protonum)
-{
-	unsigned int extoff = nhoff + sizeof(struct ipv6hdr);
-	__be16 frag_off;
-	int protoff;
-	u8 nexthdr;
-
-	if (skb_copy_bits(skb, nhoff + offsetof(struct ipv6hdr, nexthdr),
-			  &nexthdr, sizeof(nexthdr)) != 0) {
-		pr_debug("ip6_conntrack_core: can't get nexthdr\n");
-		return -NF_ACCEPT;
-	}
-	protoff = ipv6_skip_exthdr(skb, extoff, &nexthdr, &frag_off);
-	/*
-	 * (protoff == skb->len) means the packet has not data, just
-	 * IPv6 and possibly extensions headers, but it is tracked anyway
-	 */
-	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
-		pr_debug("ip6_conntrack_core: can't find proto in pkt\n");
-		return -NF_ACCEPT;
-	}
-
-	*dataoff = protoff;
-	*protonum = nexthdr;
-	return NF_ACCEPT;
-}
-
 static unsigned int ipv6_helper(void *priv,
 				struct sk_buff *skb,
 				const struct nf_hook_state *state)

@@ -281,7 +253,6 @@ static void ipv6_hooks_unregister(struct net *net)
 
 const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = {
 	.l3proto		= PF_INET6,
-	.get_l4proto		= ipv6_get_l4proto,
 	.net_ns_get		= ipv6_hooks_register,
 	.net_ns_put		= ipv6_hooks_unregister,
 	.me			= THIS_MODULE,

174 lines not on this page · raw message

46 lines not on this page · raw message

index 859cb303bb91..39df72bb9d56 100644
@@ -35,6 +35,11 @@ EXPORT_SYMBOL_GPL(nf_ct_l3protos);
 
 static DEFINE_MUTEX(nf_ct_proto_mutex);
 
+struct nf_conntrack_l3proto nf_conntrack_l3proto_generic __read_mostly = {
+	.l3proto	 = PF_UNSPEC,
+};
+EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_generic);
+
 #ifdef CONFIG_SYSCTL
 static int
 nf_ct_register_sysctl(struct net *net,

index a7220eef9aee..6a55e337a161 100644
@@ -36,7 +36,7 @@ struct nf_conntrack_l4proto {
 			     struct net *net, struct nf_conntrack_tuple *tuple);
 
 	/* Invert the per-proto part of the tuple: ie. turn xmit into reply.
-	 * Some packets can't be inverted: return 0 in that case.
+	 * Only used by icmp, most protocols use a generic version.
 	 */
 	bool (*invert_tuple)(struct nf_conntrack_tuple *inverse,
 			     const struct nf_conntrack_tuple *orig);

index 0674c6e5bfed..92efce69b690 100644
@@ -400,7 +400,13 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
 	inverse->dst.dir = !orig->dst.dir;
 
 	inverse->dst.protonum = orig->dst.protonum;
-	return l4proto->invert_tuple(inverse, orig);
+
+	if (unlikely(l4proto->invert_tuple))
+		return l4proto->invert_tuple(inverse, orig);
+
+	inverse->src.u.all = orig->dst.u.all;
+	inverse->dst.u.all = orig->src.u.all;
+	return true;
 }
 EXPORT_SYMBOL_GPL(nf_ct_invert_tuple);
 

index abe647d5b8c6..05620c03f138 100644
@@ -403,14 +403,6 @@ static bool dccp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
 	return true;
 }
 
-static bool dccp_invert_tuple(struct nf_conntrack_tuple *inv,
-			      const struct nf_conntrack_tuple *tuple)
-{
-	inv->src.u.dccp.port = tuple->dst.u.dccp.port;
-	inv->dst.u.dccp.port = tuple->src.u.dccp.port;
-	return true;
-}
-
 static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
 		     unsigned int dataoff, unsigned int *timeouts)
 {

@@ -865,7 +857,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = {
 	.l3proto		= AF_INET,
 	.l4proto		= IPPROTO_DCCP,
 	.pkt_to_tuple		= dccp_pkt_to_tuple,
-	.invert_tuple		= dccp_invert_tuple,
 	.new			= dccp_new,
 	.packet			= dccp_packet,
 	.get_timeouts		= dccp_get_timeouts,

@@ -901,7 +892,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = {
 	.l3proto		= AF_INET6,
 	.l4proto		= IPPROTO_DCCP,
 	.pkt_to_tuple		= dccp_pkt_to_tuple,
-	.invert_tuple		= dccp_invert_tuple,
 	.new			= dccp_new,
 	.packet			= dccp_packet,
 	.get_timeouts		= dccp_get_timeouts,

index 6c6896d21cd7..4dfe40aa9446 100644
@@ -41,15 +41,6 @@ static bool generic_pkt_to_tuple(const struct sk_buff *skb,
 	return true;
 }
 
-static bool generic_invert_tuple(struct nf_conntrack_tuple *tuple,
-				 const struct nf_conntrack_tuple *orig)
-{
-	tuple->src.u.all = 0;
-	tuple->dst.u.all = 0;
-
-	return true;
-}
-
 static unsigned int *generic_get_timeouts(struct net *net)
 {
 	return &(generic_pernet(net)->timeout);

@@ -168,7 +159,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic =
 	.l3proto		= PF_UNSPEC,
 	.l4proto		= 255,
 	.pkt_to_tuple		= generic_pkt_to_tuple,
-	.invert_tuple		= generic_invert_tuple,
 	.packet			= generic_packet,
 	.get_timeouts		= generic_get_timeouts,
 	.new			= generic_new,

index d049ea5a3770..0bd40eb06b55 100644
@@ -179,15 +179,6 @@ EXPORT_SYMBOL_GPL(nf_ct_gre_keymap_destroy);
 
 /* PUBLIC CONNTRACK PROTO HELPER FUNCTIONS */
 
-/* invert gre part of tuple */
-static bool gre_invert_tuple(struct nf_conntrack_tuple *tuple,
-			     const struct nf_conntrack_tuple *orig)
-{
-	tuple->dst.u.gre.key = orig->src.u.gre.key;
-	tuple->src.u.gre.key = orig->dst.u.gre.key;
-	return true;
-}
-
 /* gre hdr info to tuple */
 static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
 			     struct net *net, struct nf_conntrack_tuple *tuple)

@@ -356,7 +347,6 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = {
 	.l3proto	 = AF_INET,
 	.l4proto	 = IPPROTO_GRE,
 	.pkt_to_tuple	 = gre_pkt_to_tuple,
-	.invert_tuple	 = gre_invert_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack = gre_print_conntrack,
 #endif

index fb9a35d16069..148957a5cf3e 100644
@@ -166,14 +166,6 @@ static bool sctp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
 	return true;
 }
 
-static bool sctp_invert_tuple(struct nf_conntrack_tuple *tuple,
-			      const struct nf_conntrack_tuple *orig)
-{
-	tuple->src.u.sctp.port = orig->dst.u.sctp.port;
-	tuple->dst.u.sctp.port = orig->src.u.sctp.port;
-	return true;
-}
-
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 /* Print out the private part of the conntrack. */
 static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct)

@@ -781,7 +773,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = {
 	.l3proto		= PF_INET,
 	.l4proto 		= IPPROTO_SCTP,
 	.pkt_to_tuple 		= sctp_pkt_to_tuple,
-	.invert_tuple 		= sctp_invert_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack	= sctp_print_conntrack,
 #endif

@@ -818,7 +809,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = {
 	.l3proto		= PF_INET6,
 	.l4proto 		= IPPROTO_SCTP,
 	.pkt_to_tuple 		= sctp_pkt_to_tuple,
-	.invert_tuple 		= sctp_invert_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack	= sctp_print_conntrack,
 #endif

index 8e67910185a0..03cff1e3066a 100644
@@ -293,14 +293,6 @@ static bool tcp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
 	return true;
 }
 
-static bool tcp_invert_tuple(struct nf_conntrack_tuple *tuple,
-			     const struct nf_conntrack_tuple *orig)
-{
-	tuple->src.u.tcp.port = orig->dst.u.tcp.port;
-	tuple->dst.u.tcp.port = orig->src.u.tcp.port;
-	return true;
-}
-
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 /* Print out the private part of the conntrack. */
 static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)

@@ -1560,7 +1552,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 =
 	.l3proto		= PF_INET,
 	.l4proto 		= IPPROTO_TCP,
 	.pkt_to_tuple 		= tcp_pkt_to_tuple,
-	.invert_tuple 		= tcp_invert_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack 	= tcp_print_conntrack,
 #endif

@@ -1598,7 +1589,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 =
 	.l3proto		= PF_INET6,
 	.l4proto 		= IPPROTO_TCP,
 	.pkt_to_tuple 		= tcp_pkt_to_tuple,
-	.invert_tuple 		= tcp_invert_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack 	= tcp_print_conntrack,
 #endif

index fe7243970aa4..6fe2233c323a 100644
@@ -55,14 +55,6 @@ static bool udp_pkt_to_tuple(const struct sk_buff *skb,
 	return true;
 }
 
-static bool udp_invert_tuple(struct nf_conntrack_tuple *tuple,
-			     const struct nf_conntrack_tuple *orig)
-{
-	tuple->src.u.udp.port = orig->dst.u.udp.port;
-	tuple->dst.u.udp.port = orig->src.u.udp.port;
-	return true;
-}
-
 static unsigned int *udp_get_timeouts(struct net *net)
 {
 	return udp_pernet(net)->timeouts;

@@ -302,7 +294,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 =
 	.l4proto		= IPPROTO_UDP,
 	.allow_clash		= true,
 	.pkt_to_tuple		= udp_pkt_to_tuple,
-	.invert_tuple		= udp_invert_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,

@@ -334,7 +325,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 =
 	.l4proto		= IPPROTO_UDPLITE,
 	.allow_clash		= true,
 	.pkt_to_tuple		= udp_pkt_to_tuple,
-	.invert_tuple		= udp_invert_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,

@@ -366,7 +356,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 =
 	.l4proto		= IPPROTO_UDP,
 	.allow_clash		= true,
 	.pkt_to_tuple		= udp_pkt_to_tuple,
-	.invert_tuple		= udp_invert_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,

@@ -398,7 +387,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 =
 	.l4proto		= IPPROTO_UDPLITE,
 	.allow_clash		= true,
 	.pkt_to_tuple		= udp_pkt_to_tuple,
-	.invert_tuple		= udp_invert_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,

index 92efce69b690..994591fd9b96 100644
@@ -235,6 +235,10 @@ nf_ct_get_tuple(const struct sk_buff *skb,
 	unsigned int size;
 	const __be32 *ap;
 	__be32 _addrs[8];
+	struct {
+		__be16 sport;
+		__be16 dport;
+	} _inet_hdr, *inet_hdr;
 
 	memset(tuple, 0, sizeof(*tuple));
 

@@ -270,7 +274,17 @@ nf_ct_get_tuple(const struct sk_buff *skb,
 	tuple->dst.protonum = protonum;
 	tuple->dst.dir = IP_CT_DIR_ORIGINAL;
 
-	return l4proto->pkt_to_tuple(skb, dataoff, net, tuple);
+	if (unlikely(l4proto->pkt_to_tuple))
+		return l4proto->pkt_to_tuple(skb, dataoff, net, tuple);
+
+	/* Actually only need first 4 bytes to get ports. */
+	inet_hdr = skb_header_pointer(skb, dataoff, sizeof(_inet_hdr), &_inet_hdr);
+	if (!inet_hdr)
+		return false;
+
+	tuple->src.u.udp.port = inet_hdr->sport;
+	tuple->dst.u.udp.port = inet_hdr->dport;
+	return true;
 }
 
 static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,

index 05620c03f138..abfdce7baed5 100644
@@ -388,21 +388,6 @@ static inline struct nf_dccp_net *dccp_pernet(struct net *net)
 	return &net->ct.nf_ct_proto.dccp;
 }
 
-static bool dccp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
-			      struct net *net, struct nf_conntrack_tuple *tuple)
-{
-	struct dccp_hdr _hdr, *dh;
-
-	/* Actually only need first 4 bytes to get ports. */
-	dh = skb_header_pointer(skb, dataoff, 4, &_hdr);
-	if (dh == NULL)
-		return false;
-
-	tuple->src.u.dccp.port = dh->dccph_sport;
-	tuple->dst.u.dccp.port = dh->dccph_dport;
-	return true;
-}
-
 static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
 		     unsigned int dataoff, unsigned int *timeouts)
 {

@@ -856,7 +841,6 @@ static struct nf_proto_net *dccp_get_net_proto(struct net *net)
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = {
 	.l3proto		= AF_INET,
 	.l4proto		= IPPROTO_DCCP,
-	.pkt_to_tuple		= dccp_pkt_to_tuple,
 	.new			= dccp_new,
 	.packet			= dccp_packet,
 	.get_timeouts		= dccp_get_timeouts,

@@ -891,7 +875,6 @@ EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_dccp4);
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = {
 	.l3proto		= AF_INET6,
 	.l4proto		= IPPROTO_DCCP,
-	.pkt_to_tuple		= dccp_pkt_to_tuple,
 	.new			= dccp_new,
 	.packet			= dccp_packet,
 	.get_timeouts		= dccp_get_timeouts,

index 148957a5cf3e..b4126a842bfd 100644
@@ -150,22 +150,6 @@ static inline struct nf_sctp_net *sctp_pernet(struct net *net)
 	return &net->ct.nf_ct_proto.sctp;
 }
 
-static bool sctp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
-			      struct net *net, struct nf_conntrack_tuple *tuple)
-{
-	const struct sctphdr *hp;
-	struct sctphdr _hdr;
-
-	/* Actually only need first 4 bytes to get ports. */
-	hp = skb_header_pointer(skb, dataoff, 4, &_hdr);
-	if (hp == NULL)
-		return false;
-
-	tuple->src.u.sctp.port = hp->source;
-	tuple->dst.u.sctp.port = hp->dest;
-	return true;
-}
-
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 /* Print out the private part of the conntrack. */
 static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct)

@@ -772,7 +756,6 @@ static struct nf_proto_net *sctp_get_net_proto(struct net *net)
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = {
 	.l3proto		= PF_INET,
 	.l4proto 		= IPPROTO_SCTP,
-	.pkt_to_tuple 		= sctp_pkt_to_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack	= sctp_print_conntrack,
 #endif

@@ -808,7 +791,6 @@ EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_sctp4);
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = {
 	.l3proto		= PF_INET6,
 	.l4proto 		= IPPROTO_SCTP,
-	.pkt_to_tuple 		= sctp_pkt_to_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack	= sctp_print_conntrack,
 #endif

index 03cff1e3066a..13c89fd107b2 100644
@@ -276,23 +276,6 @@ static inline struct nf_tcp_net *tcp_pernet(struct net *net)
 	return &net->ct.nf_ct_proto.tcp;
 }
 
-static bool tcp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
-			     struct net *net, struct nf_conntrack_tuple *tuple)
-{
-	const struct tcphdr *hp;
-	struct tcphdr _hdr;
-
-	/* Actually only need first 4 bytes to get ports. */
-	hp = skb_header_pointer(skb, dataoff, 4, &_hdr);
-	if (hp == NULL)
-		return false;
-
-	tuple->src.u.tcp.port = hp->source;
-	tuple->dst.u.tcp.port = hp->dest;
-
-	return true;
-}
-
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 /* Print out the private part of the conntrack. */
 static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)

@@ -1551,7 +1534,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 =
 {
 	.l3proto		= PF_INET,
 	.l4proto 		= IPPROTO_TCP,
-	.pkt_to_tuple 		= tcp_pkt_to_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack 	= tcp_print_conntrack,
 #endif

@@ -1588,7 +1570,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 =
 {
 	.l3proto		= PF_INET6,
 	.l4proto 		= IPPROTO_TCP,
-	.pkt_to_tuple 		= tcp_pkt_to_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack 	= tcp_print_conntrack,
 #endif

index 6fe2233c323a..8b435d70ffe3 100644
@@ -36,25 +36,6 @@ static inline struct nf_udp_net *udp_pernet(struct net *net)
 	return &net->ct.nf_ct_proto.udp;
 }
 
-static bool udp_pkt_to_tuple(const struct sk_buff *skb,
-			     unsigned int dataoff,
-			     struct net *net,
-			     struct nf_conntrack_tuple *tuple)
-{
-	const struct udphdr *hp;
-	struct udphdr _hdr;
-
-	/* Actually only need first 4 bytes to get ports. */
-	hp = skb_header_pointer(skb, dataoff, 4, &_hdr);
-	if (hp == NULL)
-		return false;
-
-	tuple->src.u.udp.port = hp->source;
-	tuple->dst.u.udp.port = hp->dest;
-
-	return true;
-}
-
 static unsigned int *udp_get_timeouts(struct net *net)
 {
 	return udp_pernet(net)->timeouts;

@@ -293,7 +274,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 =
 	.l3proto		= PF_INET,
 	.l4proto		= IPPROTO_UDP,
 	.allow_clash		= true,
-	.pkt_to_tuple		= udp_pkt_to_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,

@@ -324,7 +304,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 =
 	.l3proto		= PF_INET,
 	.l4proto		= IPPROTO_UDPLITE,
 	.allow_clash		= true,
-	.pkt_to_tuple		= udp_pkt_to_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,

@@ -355,7 +334,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 =
 	.l3proto		= PF_INET6,
 	.l4proto		= IPPROTO_UDP,
 	.allow_clash		= true,
-	.pkt_to_tuple		= udp_pkt_to_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,

@@ -386,7 +364,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 =
 	.l3proto		= PF_INET6,
 	.l4proto		= IPPROTO_UDPLITE,
 	.allow_clash		= true,
-	.pkt_to_tuple		= udp_pkt_to_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,

index 6a55e337a161..c7a0075d96df 100644
@@ -45,13 +45,12 @@ struct nf_conntrack_l4proto {
 	int (*packet)(struct nf_conn *ct,
 		      const struct sk_buff *skb,
 		      unsigned int dataoff,
-		      enum ip_conntrack_info ctinfo,
-		      unsigned int *timeouts);
+		      enum ip_conntrack_info ctinfo);
 
 	/* Called when a new connection for this protocol found;
 	 * returns TRUE if it's OK.  If so, packet() called next. */
 	bool (*new)(struct nf_conn *ct, const struct sk_buff *skb,
-		    unsigned int dataoff, unsigned int *timeouts);
+		    unsigned int dataoff);
 
 	/* Called when a conntrack entry is destroyed */
 	void (*destroy)(struct nf_conn *ct);

@@ -63,9 +62,6 @@ struct nf_conntrack_l4proto {
 	/* called by gc worker if table is full */
 	bool (*can_early_drop)(const struct nf_conn *ct);
 
-	/* Return the array of timeouts for this protocol. */
-	unsigned int *(*get_timeouts)(struct net *net);
-
 	/* convert protoinfo to nfnetink attributes */
 	int (*to_nlattr)(struct sk_buff *skb, struct nlattr *nla,
 			 struct nf_conn *ct);

index 9468ab4ad12d..80ceb3d0291d 100644
@@ -67,27 +67,17 @@ struct nf_conn_timeout *nf_ct_timeout_ext_add(struct nf_conn *ct,
 #endif
 };
 
-static inline unsigned int *
-nf_ct_timeout_lookup(struct net *net, struct nf_conn *ct,
-		     const struct nf_conntrack_l4proto *l4proto)
+static inline unsigned int *nf_ct_timeout_lookup(const struct nf_conn *ct)
 {
+	unsigned int *timeouts = NULL;
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
 	struct nf_conn_timeout *timeout_ext;
-	unsigned int *timeouts;
 
 	timeout_ext = nf_ct_timeout_find(ct);
-	if (timeout_ext) {
+	if (timeout_ext)
 		timeouts = nf_ct_timeout_data(timeout_ext);
-		if (unlikely(!timeouts))
-			timeouts = l4proto->get_timeouts(net);
-	} else {
-		timeouts = l4proto->get_timeouts(net);
-	}
-
-	return timeouts;
-#else
-	return l4proto->get_timeouts(net);
 #endif
+	return timeouts;
 }
 
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT

index 34095949a003..036670b38282 100644
@@ -19,6 +19,7 @@
 #include <net/netfilter/nf_conntrack_tuple.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/nf_log.h>
 

@@ -80,12 +81,16 @@ static unsigned int *icmp_get_timeouts(struct net *net)
 static int icmp_packet(struct nf_conn *ct,
 		       const struct sk_buff *skb,
 		       unsigned int dataoff,
-		       enum ip_conntrack_info ctinfo,
-		       unsigned int *timeout)
+		       enum ip_conntrack_info ctinfo)
 {
 	/* Do not immediately delete the connection after the first
 	   successful reply to avoid excessive conntrackd traffic
 	   and also to handle correctly ICMP echo reply duplicates. */
+	unsigned int *timeout = nf_ct_timeout_lookup(ct);
+
+	if (!timeout)
+		timeout = icmp_get_timeouts(nf_ct_net(ct));
+
 	nf_ct_refresh_acct(ct, ctinfo, skb, *timeout);
 
 	return NF_ACCEPT;

@@ -93,7 +98,7 @@ static int icmp_packet(struct nf_conn *ct,
 
 /* Called when a new connection for this protocol found. */
 static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb,
-		     unsigned int dataoff, unsigned int *timeouts)
+		     unsigned int dataoff)
 {
 	static const u_int8_t valid_new[] = {
 		[ICMP_ECHO] = 1,

@@ -280,9 +285,11 @@ static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[],
 	struct nf_icmp_net *in = icmp_pernet(net);
 
 	if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) {
+		if (!timeout)
+			timeout = &in->timeout;
 		*timeout =
 			ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ;
-	} else {
+	} else if (timeout) {
 		/* Set default ICMP timeout. */
 		*timeout = in->timeout;
 	}

@@ -357,7 +364,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp =
 	.pkt_to_tuple		= icmp_pkt_to_tuple,
 	.invert_tuple		= icmp_invert_tuple,
 	.packet			= icmp_packet,
-	.get_timeouts		= icmp_get_timeouts,
 	.new			= icmp_new,
 	.error			= icmp_error,
 	.destroy		= NULL,

index 8bcbc2f15bd5..bed07b998a10 100644
@@ -23,6 +23,7 @@
 #include <net/netfilter/nf_conntrack_tuple.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/ipv6/nf_conntrack_icmpv6.h>
 #include <net/netfilter/nf_log.h>

@@ -93,9 +94,13 @@ static unsigned int *icmpv6_get_timeouts(struct net *net)
 static int icmpv6_packet(struct nf_conn *ct,
 		       const struct sk_buff *skb,
 		       unsigned int dataoff,
-		       enum ip_conntrack_info ctinfo,
-		       unsigned int *timeout)
+		       enum ip_conntrack_info ctinfo)
 {
+	unsigned int *timeout = nf_ct_timeout_lookup(ct);
+
+	if (!timeout)
+		timeout = icmpv6_get_timeouts(nf_ct_net(ct));
+
 	/* Do not immediately delete the connection after the first
 	   successful reply to avoid excessive conntrackd traffic
 	   and also to handle correctly ICMP echo reply duplicates. */

@@ -106,7 +111,7 @@ static int icmpv6_packet(struct nf_conn *ct,
 
 /* Called when a new connection for this protocol found. */
 static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb,
-		       unsigned int dataoff, unsigned int *timeouts)
+		       unsigned int dataoff)
 {
 	static const u_int8_t valid_new[] = {
 		[ICMPV6_ECHO_REQUEST - 128] = 1,

@@ -280,6 +285,8 @@ static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[],
 	unsigned int *timeout = data;
 	struct nf_icmp_net *in = icmpv6_pernet(net);
 
+	if (!timeout)
+		timeout = icmpv6_get_timeouts(net);
 	if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) {
 		*timeout =
 		    ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ;

@@ -358,7 +365,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 =
 	.pkt_to_tuple		= icmpv6_pkt_to_tuple,
 	.invert_tuple		= icmpv6_invert_tuple,
 	.packet			= icmpv6_packet,
-	.get_timeouts		= icmpv6_get_timeouts,
 	.new			= icmpv6_new,
 	.error			= icmpv6_error,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)

index 994591fd9b96..c069f2faff4c 100644
@@ -1337,7 +1337,6 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	const struct nf_conntrack_zone *zone;
 	struct nf_conn_timeout *timeout_ext;
 	struct nf_conntrack_zone tmp;
-	unsigned int *timeouts;
 
 	if (!nf_ct_invert_tuple(&repl_tuple, tuple, l4proto)) {
 		pr_debug("Can't invert tuple.\n");

@@ -1356,15 +1355,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	}
 
 	timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL;
-	if (timeout_ext) {
-		timeouts = nf_ct_timeout_data(timeout_ext);
-		if (unlikely(!timeouts))
-			timeouts = l4proto->get_timeouts(net);
-	} else {
-		timeouts = l4proto->get_timeouts(net);
-	}
 
-	if (!l4proto->new(ct, skb, dataoff, timeouts)) {
+	if (!l4proto->new(ct, skb, dataoff)) {
 		nf_conntrack_free(ct);
 		pr_debug("can't track with proto module\n");
 		return NULL;

@@ -1493,7 +1485,6 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 	const struct nf_conntrack_l4proto *l4proto;
 	struct nf_conn *ct, *tmpl;
 	enum ip_conntrack_info ctinfo;
-	unsigned int *timeouts;
 	u_int8_t protonum;
 	int dataoff, ret;
 

@@ -1552,10 +1543,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 		goto out;
 	}
 
-	/* Decide what timeout policy we want to apply to this flow. */
-	timeouts = nf_ct_timeout_lookup(net, ct, l4proto);
-
-	ret = l4proto->packet(ct, skb, dataoff, ctinfo, timeouts);
+	ret = l4proto->packet(ct, skb, dataoff, ctinfo);
 	if (ret <= 0) {
 		/* Invalid: inverse of the return code tells
 		 * the netfilter core what to do */

index abfdce7baed5..f476d116c816 100644
@@ -23,6 +23,7 @@
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_ecache.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 #include <net/netfilter/nf_log.h>
 
 /* Timeouts are based on values from RFC4340:

@@ -389,7 +390,7 @@ static inline struct nf_dccp_net *dccp_pernet(struct net *net)
 }
 
 static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
-		     unsigned int dataoff, unsigned int *timeouts)
+		     unsigned int dataoff)
 {
 	struct net *net = nf_ct_net(ct);
 	struct nf_dccp_net *dn;

@@ -437,19 +438,14 @@ static u64 dccp_ack_seq(const struct dccp_hdr *dh)
 		     ntohl(dhack->dccph_ack_nr_low);
 }
 
-static unsigned int *dccp_get_timeouts(struct net *net)
-{
-	return dccp_pernet(net)->dccp_timeout;
-}
-
 static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
-		       unsigned int dataoff, enum ip_conntrack_info ctinfo,
-		       unsigned int *timeouts)
+		       unsigned int dataoff, enum ip_conntrack_info ctinfo)
 {
 	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
 	struct dccp_hdr _dh, *dh;
 	u_int8_t type, old_state, new_state;
 	enum ct_dccp_roles role;
+	unsigned int *timeouts;
 
 	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
 	BUG_ON(dh == NULL);

@@ -523,6 +519,9 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
 	if (new_state != old_state)
 		nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
 
+	timeouts = nf_ct_timeout_lookup(ct);
+	if (!timeouts)
+		timeouts = dccp_pernet(nf_ct_net(ct))->dccp_timeout;
 	nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]);
 
 	return NF_ACCEPT;

@@ -843,7 +842,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = {
 	.l4proto		= IPPROTO_DCCP,
 	.new			= dccp_new,
 	.packet			= dccp_packet,
-	.get_timeouts		= dccp_get_timeouts,
 	.error			= dccp_error,
 	.can_early_drop		= dccp_can_early_drop,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS

@@ -877,7 +875,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = {
 	.l4proto		= IPPROTO_DCCP,
 	.new			= dccp_new,
 	.packet			= dccp_packet,
-	.get_timeouts		= dccp_get_timeouts,
 	.error			= dccp_error,
 	.can_early_drop		= dccp_can_early_drop,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS

index 4dfe40aa9446..ac4a0b296dcd 100644
@@ -11,6 +11,7 @@
 #include <linux/timer.h>
 #include <linux/netfilter.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 
 static const unsigned int nf_ct_generic_timeout = 600*HZ;
 

@@ -41,25 +42,24 @@ static bool generic_pkt_to_tuple(const struct sk_buff *skb,
 	return true;
 }
 
-static unsigned int *generic_get_timeouts(struct net *net)
-{
-	return &(generic_pernet(net)->timeout);
-}
-
 /* Returns verdict for packet, or -1 for invalid. */
 static int generic_packet(struct nf_conn *ct,
 			  const struct sk_buff *skb,
 			  unsigned int dataoff,
-			  enum ip_conntrack_info ctinfo,
-			  unsigned int *timeout)
+			  enum ip_conntrack_info ctinfo)
 {
+	const unsigned int *timeout = nf_ct_timeout_lookup(ct);
+
+	if (!timeout)
+		timeout = &generic_pernet(nf_ct_net(ct))->timeout;
+
 	nf_ct_refresh_acct(ct, ctinfo, skb, *timeout);
 	return NF_ACCEPT;
 }
 
 /* Called when a new connection for this protocol found. */
 static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb,
-			unsigned int dataoff, unsigned int *timeouts)
+			unsigned int dataoff)
 {
 	bool ret;
 

@@ -78,8 +78,11 @@ static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb,
 static int generic_timeout_nlattr_to_obj(struct nlattr *tb[],
 					 struct net *net, void *data)
 {
-	unsigned int *timeout = data;
 	struct nf_generic_net *gn = generic_pernet(net);
+	unsigned int *timeout = data;
+
+	if (!timeout)
+		timeout = &gn->timeout;
 
 	if (tb[CTA_TIMEOUT_GENERIC_TIMEOUT])
 		*timeout =

@@ -160,7 +163,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic =
 	.l4proto		= 255,
 	.pkt_to_tuple		= generic_pkt_to_tuple,
 	.packet			= generic_packet,
-	.get_timeouts		= generic_get_timeouts,
 	.new			= generic_new,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
 	.ctnl_timeout		= {

index 0bd40eb06b55..d1632252bf5b 100644
@@ -39,6 +39,7 @@
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 #include <linux/netfilter/nf_conntrack_proto_gre.h>
 #include <linux/netfilter/nf_conntrack_pptp.h>
 

@@ -234,8 +235,7 @@ static unsigned int *gre_get_timeouts(struct net *net)
 static int gre_packet(struct nf_conn *ct,
 		      const struct sk_buff *skb,
 		      unsigned int dataoff,
-		      enum ip_conntrack_info ctinfo,
-		      unsigned int *timeouts)
+		      enum ip_conntrack_info ctinfo)
 {
 	/* If we've seen traffic both ways, this is a GRE connection.
 	 * Extend timeout. */

@@ -254,8 +254,13 @@ static int gre_packet(struct nf_conn *ct,
 
 /* Called when a new connection for this protocol found. */
 static bool gre_new(struct nf_conn *ct, const struct sk_buff *skb,
-		    unsigned int dataoff, unsigned int *timeouts)
+		    unsigned int dataoff)
 {
+	unsigned int *timeouts = nf_ct_timeout_lookup(ct);
+
+	if (!timeouts)
+		timeouts = gre_get_timeouts(nf_ct_net(ct));
+
 	pr_debug(": ");
 	nf_ct_dump_tuple(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
 

@@ -291,6 +296,8 @@ static int gre_timeout_nlattr_to_obj(struct nlattr *tb[],
 	unsigned int *timeouts = data;
 	struct netns_proto_gre *net_gre = gre_pernet(net);
 
+	if (!timeouts)
+		timeouts = gre_get_timeouts(net);
 	/* set default timeouts for GRE. */
 	timeouts[GRE_CT_UNREPLIED] = net_gre->gre_timeouts[GRE_CT_UNREPLIED];
 	timeouts[GRE_CT_REPLIED] = net_gre->gre_timeouts[GRE_CT_REPLIED];

@@ -350,7 +357,6 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = {
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack = gre_print_conntrack,
 #endif
-	.get_timeouts    = gre_get_timeouts,
 	.packet		 = gre_packet,
 	.new		 = gre_new,
 	.destroy	 = gre_destroy,

index b4126a842bfd..8d1e085fc14a 100644
@@ -28,6 +28,7 @@
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_ecache.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 
 /* FIXME: Examine ipfilter's timeouts and conntrack transitions more
    closely.  They're more complex. --RR

@@ -272,17 +273,11 @@ static int sctp_new_state(enum ip_conntrack_dir dir,
 	return sctp_conntracks[dir][i][cur_state];
 }
 
-static unsigned int *sctp_get_timeouts(struct net *net)
-{
-	return sctp_pernet(net)->timeouts;
-}
-
 /* Returns verdict for packet, or -NF_ACCEPT for invalid. */
 static int sctp_packet(struct nf_conn *ct,
 		       const struct sk_buff *skb,
 		       unsigned int dataoff,
-		       enum ip_conntrack_info ctinfo,
-		       unsigned int *timeouts)
+		       enum ip_conntrack_info ctinfo)
 {
 	enum sctp_conntrack new_state, old_state;
 	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);

@@ -291,6 +286,7 @@ static int sctp_packet(struct nf_conn *ct,
 	const struct sctp_chunkhdr *sch;
 	struct sctp_chunkhdr _sch;
 	u_int32_t offset, count;
+	unsigned int *timeouts;
 	unsigned long map[256 / sizeof(unsigned long)] = { 0 };
 
 	sh = skb_header_pointer(skb, dataoff, sizeof(_sctph), &_sctph);

@@ -379,6 +375,10 @@ static int sctp_packet(struct nf_conn *ct,
 	}
 	spin_unlock_bh(&ct->lock);
 
+	timeouts = nf_ct_timeout_lookup(ct);
+	if (!timeouts)
+		timeouts = sctp_pernet(nf_ct_net(ct))->timeouts;
+
 	nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]);
 
 	if (old_state == SCTP_CONNTRACK_COOKIE_ECHOED &&

@@ -399,7 +399,7 @@ static int sctp_packet(struct nf_conn *ct,
 
 /* Called when a new connection for this protocol found. */
 static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb,
-		     unsigned int dataoff, unsigned int *timeouts)
+		     unsigned int dataoff)
 {
 	enum sctp_conntrack new_state;
 	const struct sctphdr *sh;

@@ -760,7 +760,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = {
 	.print_conntrack	= sctp_print_conntrack,
 #endif
 	.packet 		= sctp_packet,
-	.get_timeouts		= sctp_get_timeouts,
 	.new 			= sctp_new,
 	.error			= sctp_error,
 	.can_early_drop		= sctp_can_early_drop,

@@ -795,7 +794,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = {
 	.print_conntrack	= sctp_print_conntrack,
 #endif
 	.packet 		= sctp_packet,
-	.get_timeouts		= sctp_get_timeouts,
 	.new 			= sctp_new,
 	.error			= sctp_error,
 	.can_early_drop		= sctp_can_early_drop,

index 13c89fd107b2..d80d322b9d8b 100644
@@ -29,6 +29,7 @@
 #include <net/netfilter/nf_conntrack_ecache.h>
 #include <net/netfilter/nf_conntrack_seqadj.h>
 #include <net/netfilter/nf_conntrack_synproxy.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 #include <net/netfilter/nf_log.h>
 #include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
 #include <net/netfilter/ipv6/nf_conntrack_ipv6.h>

@@ -768,27 +769,21 @@ static int tcp_error(struct net *net, struct nf_conn *tmpl,
 	return NF_ACCEPT;
 }
 
-static unsigned int *tcp_get_timeouts(struct net *net)
-{
-	return tcp_pernet(net)->timeouts;
-}
-
 /* Returns verdict for packet, or -1 for invalid. */
 static int tcp_packet(struct nf_conn *ct,
 		      const struct sk_buff *skb,
 		      unsigned int dataoff,
-		      enum ip_conntrack_info ctinfo,
-		      unsigned int *timeouts)
+		      enum ip_conntrack_info ctinfo)
 {
 	struct net *net = nf_ct_net(ct);
 	struct nf_tcp_net *tn = tcp_pernet(net);
 	struct nf_conntrack_tuple *tuple;
 	enum tcp_conntrack new_state, old_state;
+	unsigned int index, *timeouts;
 	enum ip_conntrack_dir dir;
 	const struct tcphdr *th;
 	struct tcphdr _tcph;
 	unsigned long timeout;
-	unsigned int index;
 
 	th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
 	BUG_ON(th == NULL);

@@ -1021,6 +1016,10 @@ static int tcp_packet(struct nf_conn *ct,
 	    && new_state == TCP_CONNTRACK_FIN_WAIT)
 		ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT;
 
+	timeouts = nf_ct_timeout_lookup(ct);
+	if (!timeouts)
+		timeouts = tn->timeouts;
+
 	if (ct->proto.tcp.retrans >= tn->tcp_max_retrans &&
 	    timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS])
 		timeout = timeouts[TCP_CONNTRACK_RETRANS];

@@ -1070,7 +1069,7 @@ static int tcp_packet(struct nf_conn *ct,
 
 /* Called when a new connection for this protocol found. */
 static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
-		    unsigned int dataoff, unsigned int *timeouts)
+		    unsigned int dataoff)
 {
 	enum tcp_conntrack new_state;
 	const struct tcphdr *th;

@@ -1288,10 +1287,12 @@ static unsigned int tcp_nlattr_tuple_size(void)
 static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[],
 				     struct net *net, void *data)
 {
-	unsigned int *timeouts = data;
 	struct nf_tcp_net *tn = tcp_pernet(net);
+	unsigned int *timeouts = data;
 	int i;
 
+	if (!timeouts)
+		timeouts = tn->timeouts;
 	/* set default TCP timeouts. */
 	for (i=0; i<TCP_CONNTRACK_TIMEOUT_MAX; i++)
 		timeouts[i] = tn->timeouts[i];

@@ -1538,7 +1539,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 =
 	.print_conntrack 	= tcp_print_conntrack,
 #endif
 	.packet 		= tcp_packet,
-	.get_timeouts		= tcp_get_timeouts,
 	.new 			= tcp_new,
 	.error			= tcp_error,
 	.can_early_drop		= tcp_can_early_drop,

@@ -1574,7 +1574,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 =
 	.print_conntrack 	= tcp_print_conntrack,
 #endif
 	.packet 		= tcp_packet,
-	.get_timeouts		= tcp_get_timeouts,
 	.new 			= tcp_new,
 	.error			= tcp_error,
 	.can_early_drop		= tcp_can_early_drop,

index 8b435d70ffe3..7a1b8988a931 100644
@@ -22,6 +22,7 @@
 #include <linux/netfilter_ipv6.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_ecache.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 #include <net/netfilter/nf_log.h>
 #include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
 #include <net/netfilter/ipv6/nf_conntrack_ipv6.h>

@@ -45,9 +46,14 @@ static unsigned int *udp_get_timeouts(struct net *net)
 static int udp_packet(struct nf_conn *ct,
 		      const struct sk_buff *skb,
 		      unsigned int dataoff,
-		      enum ip_conntrack_info ctinfo,
-		      unsigned int *timeouts)
+		      enum ip_conntrack_info ctinfo)
 {
+	unsigned int *timeouts;
+
+	timeouts = nf_ct_timeout_lookup(ct);
+	if (!timeouts)
+		timeouts = udp_get_timeouts(nf_ct_net(ct));
+
 	/* If we've seen traffic both ways, this is some kind of UDP
 	   stream.  Extend timeout. */
 	if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {

@@ -65,7 +71,7 @@ static int udp_packet(struct nf_conn *ct,
 
 /* Called when a new connection for this protocol found. */
 static bool udp_new(struct nf_conn *ct, const struct sk_buff *skb,
-		    unsigned int dataoff, unsigned int *timeouts)
+		    unsigned int dataoff)
 {
 	return true;
 }

@@ -176,6 +182,9 @@ static int udp_timeout_nlattr_to_obj(struct nlattr *tb[],
 	unsigned int *timeouts = data;
 	struct nf_udp_net *un = udp_pernet(net);
 
+	if (!timeouts)
+		timeouts = un->timeouts;
+
 	/* set default timeouts for UDP. */
 	timeouts[UDP_CT_UNREPLIED] = un->timeouts[UDP_CT_UNREPLIED];
 	timeouts[UDP_CT_REPLIED] = un->timeouts[UDP_CT_REPLIED];

@@ -275,7 +284,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 =
 	.l4proto		= IPPROTO_UDP,
 	.allow_clash		= true,
 	.packet			= udp_packet,
-	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
 	.error			= udp_error,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)

@@ -305,7 +313,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 =
 	.l4proto		= IPPROTO_UDPLITE,
 	.allow_clash		= true,
 	.packet			= udp_packet,
-	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
 	.error			= udplite_error,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)

@@ -335,7 +342,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 =
 	.l4proto		= IPPROTO_UDP,
 	.allow_clash		= true,
 	.packet			= udp_packet,
-	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
 	.error			= udp_error,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)

@@ -365,7 +371,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 =
 	.l4proto		= IPPROTO_UDPLITE,
 	.allow_clash		= true,
 	.packet			= udp_packet,
-	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
 	.error			= udplite_error,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)

@@ -388,3 +393,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 =
 };
 EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udplite6);
 #endif
+#include <net/netfilter/nf_conntrack_timeout.h>

index 9da4b8462004..d9d952fad3e0 100644
@@ -46,7 +46,7 @@ static const struct nla_policy cttimeout_nla_policy[CTA_TIMEOUT_MAX+1] = {
 };
 
 static int
-ctnl_timeout_parse_policy(void *timeouts,
+ctnl_timeout_parse_policy(void *timeout,
 			  const struct nf_conntrack_l4proto *l4proto,
 			  struct net *net, const struct nlattr *attr)
 {

@@ -67,7 +67,7 @@ ctnl_timeout_parse_policy(void *timeouts,
 	if (ret < 0)
 		goto err;
 
-	ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, net, timeouts);
+	ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, net, timeout);
 
 err:
 	kfree(tb);

@@ -372,7 +372,6 @@ static int cttimeout_default_set(struct net *net, struct sock *ctnl,
 				 struct netlink_ext_ack *extack)
 {
 	const struct nf_conntrack_l4proto *l4proto;
-	unsigned int *timeouts;
 	__u16 l3num;
 	__u8 l4num;
 	int ret;

@@ -392,9 +391,7 @@ static int cttimeout_default_set(struct net *net, struct sock *ctnl,
 		goto err;
 	}
 
-	timeouts = l4proto->get_timeouts(net);
-
-	ret = ctnl_timeout_parse_policy(timeouts, l4proto, net,
+	ret = ctnl_timeout_parse_policy(NULL, l4proto, net,
 					cda[CTA_TIMEOUT_DATA]);
 	if (ret < 0)
 		goto err;

@@ -431,7 +428,6 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid,
 
 	if (likely(l4proto->ctnl_timeout.obj_to_nlattr)) {
 		struct nlattr *nest_parms;
-		unsigned int *timeouts = l4proto->get_timeouts(net);
 		int ret;
 
 		nest_parms = nla_nest_start(skb,

@@ -439,7 +435,7 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid,
 		if (!nest_parms)
 			goto nla_put_failure;
 
-		ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, timeouts);
+		ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, NULL);
 		if (ret < 0)
 			goto nla_put_failure;
 

index 73f825732326..c84b51682f08 100644
@@ -10,9 +10,6 @@
 #ifndef _NF_CONNTRACK_IPV4_H
 #define _NF_CONNTRACK_IPV4_H
 
-
-const extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4;
-
 extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4;
 extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4;
 extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp;

index 062dc19b5840..a2b0ed025908 100644
@@ -41,6 +41,11 @@ union nf_conntrack_expect_proto {
 	/* insert expect proto private data here */
 };
 
+struct nf_conntrack_net {
+	unsigned int users4;
+	unsigned int users6;
+};
+
 #include <linux/types.h>
 #include <linux/skbuff.h>
 

index 35461b2d3462..2a3e0974a6af 100644
@@ -14,7 +14,6 @@
 #define _NF_CONNTRACK_CORE_H
 
 #include <linux/netfilter.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_ecache.h>
 

54 lines not on this page · raw message

index c7a0075d96df..6068c6da3eac 100644
@@ -130,10 +130,6 @@ void nf_ct_l4proto_pernet_unregister(struct net *net,
 /* Protocol global registration. */
 int nf_ct_l4proto_register_one(const struct nf_conntrack_l4proto *proto);
 void nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *proto);
-int nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const proto[],
-			   unsigned int num_proto);
-void nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const proto[],
-			      unsigned int num_proto);
 
 /* Generic netlink helpers */
 int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb,

368 lines not on this page · raw message

355 lines not on this page · raw message

index c069f2faff4c..5123e91b1982 100644
@@ -291,7 +291,6 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 			    u_int8_t *protonum)
 {
 	int dataoff = -1;
-#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV4)
 	const struct iphdr *iph;
 	struct iphdr _iph;
 

@@ -314,15 +313,14 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 			 nhoff, iph->ihl << 2, skb->len);
 		return -1;
 	}
-#endif
 	return dataoff;
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 			    u8 *protonum)
 {
 	int protoff = -1;
-#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6)
 	unsigned int extoff = nhoff + sizeof(struct ipv6hdr);
 	__be16 frag_off;
 	u8 nexthdr;

@@ -343,9 +341,9 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 	}
 
 	*protonum = nexthdr;
-#endif
 	return protoff;
 }
+#endif
 
 static int get_l4proto(const struct sk_buff *skb,
 		       unsigned int nhoff, u8 pf, u8 *l4num)

@@ -353,8 +351,10 @@ static int get_l4proto(const struct sk_buff *skb,
 	switch (pf) {
 	case NFPROTO_IPV4:
 		return ipv4_get_l4proto(skb, nhoff, l4num);
+#if IS_ENABLED(CONFIG_IPV6)
 	case NFPROTO_IPV6:
 		return ipv6_get_l4proto(skb, nhoff, l4num);
+#endif
 	default:
 		*l4num = 0;
 		break;

@@ -2197,9 +2197,6 @@ int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp)
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize);
 
-module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
-		  &nf_conntrack_htable_size, 0600);
-
 static __always_inline unsigned int total_extension_size(void)
 {
 	/* remember to add new extensions below */

922 lines not on this page · raw message

similarity index 100%
rename from net/ipv4/netfilter/nf_conntrack_proto_icmp.c
rename to net/netfilter/nf_conntrack_proto_icmp.c

similarity index 100%
rename from net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
rename to net/netfilter/nf_conntrack_proto_icmpv6.c

index 47b80fd0d2c3..13279f683da9 100644
@@ -1,12 +1,4 @@
-/* (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2004 Netfilter Core Team <[email protected]>
- * (C) 2005-2012 Patrick McHardy <[email protected]>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
 #include <linux/netfilter.h>
 #include <linux/slab.h>

@@ -32,7 +24,7 @@
 #include <net/netfilter/nf_conntrack_timestamp.h>
 #include <linux/rculist_nulls.h>
 
-MODULE_LICENSE("GPL");
+unsigned int nf_conntrack_net_id __read_mostly;
 
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 void

@@ -674,6 +666,8 @@ static void nf_conntrack_pernet_exit(struct list_head *net_exit_list)
 static struct pernet_operations nf_conntrack_net_ops = {
 	.init		= nf_conntrack_pernet_init,
 	.exit_batch	= nf_conntrack_pernet_exit,
+	.id		= &nf_conntrack_net_id,
+	.size = sizeof(struct nf_conntrack_net),
 };
 
 static int __init nf_conntrack_standalone_init(void)

index 86df2a1666fd..6366f0c0b8c1 100644
@@ -28,7 +28,6 @@
 #include <net/netfilter/nf_nat_helper.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_seqadj.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <linux/netfilter/nf_nat.h>
 

@@ -743,12 +742,6 @@ EXPORT_SYMBOL_GPL(nf_nat_l4proto_unregister);
 
 int nf_nat_l3proto_register(const struct nf_nat_l3proto *l3proto)
 {
-	int err;
-
-	err = nf_ct_l3proto_try_module_get(l3proto->l3proto);
-	if (err < 0)
-		return err;
-
 	mutex_lock(&nf_nat_proto_mutex);
 	RCU_INIT_POINTER(nf_nat_l4protos[l3proto->l3proto][IPPROTO_TCP],
 			 &nf_nat_l4proto_tcp);

@@ -781,7 +774,6 @@ void nf_nat_l3proto_unregister(const struct nf_nat_l3proto *l3proto)
 	synchronize_rcu();
 
 	nf_nat_l3proto_clean(l3proto->l3proto);
-	nf_ct_l3proto_module_put(l3proto->l3proto);
 }
 EXPORT_SYMBOL_GPL(nf_nat_l3proto_unregister);
 

index 998c2b546f6d..e43c1939d25f 100644
@@ -31,7 +31,7 @@ static void nft_socket_eval(const struct nft_expr *expr,
 		case NFPROTO_IPV4:
 			sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, nft_in(pkt));
 			break;
-#if IS_ENABLED(CONFIG_NF_SOCKET_IPV6)
+#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
 		case NFPROTO_IPV6:
 			sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, nft_in(pkt));
 			break;

@@ -77,7 +77,7 @@ static int nft_socket_init(const struct nft_ctx *ctx,
 
 	switch(ctx->family) {
 	case NFPROTO_IPV4:
-#if IS_ENABLED(CONFIG_NF_SOCKET_IPV6)
+#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
 	case NFPROTO_IPV6:
 #endif
 	case NFPROTO_INET:

index 475957cfcf50..0d0d68c989df 100644
@@ -38,7 +38,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 	return XT_CONTINUE;
 }
 
-#if IS_ENABLED(CONFIG_IPV6)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 static unsigned int
 tee_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 {

@@ -141,7 +141,7 @@ static struct xt_target tee_tg_reg[] __read_mostly = {
 		.destroy    = tee_tg_destroy,
 		.me         = THIS_MODULE,
 	},
-#if IS_ENABLED(CONFIG_IPV6)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	{
 		.name       = "TEE",
 		.revision   = 1,

index 510039862aa9..81c02185b2e8 100644
@@ -189,6 +189,42 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
 }
 EXPORT_SYMBOL_GPL(nf_conncount_lookup);
 
+static void nf_conncount_gc_list(struct net *net,
+				 struct nf_conncount_rb *rbconn)
+{
+	const struct nf_conntrack_tuple_hash *found;
+	struct nf_conncount_tuple *conn;
+	struct hlist_node *n;
+	struct nf_conn *found_ct;
+	unsigned int collected = 0;
+
+	hlist_for_each_entry_safe(conn, n, &rbconn->hhead, node) {
+		found = find_or_evict(net, conn);
+		if (IS_ERR(found)) {
+			if (PTR_ERR(found) == -ENOENT)
+				collected++;
+			continue;
+		}
+
+		found_ct = nf_ct_tuplehash_to_ctrack(found);
+		if (already_closed(found_ct)) {
+			/*
+			 * we do not care about connections which are
+			 * closed already -> ditch it
+			 */
+			nf_ct_put(found_ct);
+			hlist_del(&conn->node);
+			kmem_cache_free(conncount_conn_cachep, conn);
+			collected++;
+			continue;
+		}
+
+		nf_ct_put(found_ct);
+		if (collected > CONNCOUNT_GC_MAX_NODES)
+			return;
+	}
+}
+
 static void tree_nodes_free(struct rb_root *root,
 			    struct nf_conncount_rb *gc_nodes[],
 			    unsigned int gc_count)

@@ -251,8 +287,7 @@ count_tree(struct net *net, struct rb_root *root,
 		if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes))
 			continue;
 
-		/* only used for GC on hhead, retval and 'addit' ignored */
-		nf_conncount_lookup(net, &rbconn->hhead, tuple, zone, &addit);
+		nf_conncount_gc_list(net, rbconn);
 		if (hlist_empty(&rbconn->hhead))
 			gc_nodes[gc_count++] = rbconn;
 	}

index 3a188a0923a3..e4884e0e4f69 100644
@@ -1,8 +1,15 @@
 #ifndef _NF_CONNTRACK_COUNT_H
 #define _NF_CONNTRACK_COUNT_H
 
+#include <linux/list.h>
+
 struct nf_conncount_data;
 
+struct nf_conncount_list {
+	struct list_head head;	/* connections with the same filtering key */
+	unsigned int count;	/* length of list */
+};
+
 struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family,
 					    unsigned int keylen);
 void nf_conncount_destroy(struct net *net, unsigned int family,

@@ -14,15 +21,17 @@ unsigned int nf_conncount_count(struct net *net,
 				const struct nf_conntrack_tuple *tuple,
 				const struct nf_conntrack_zone *zone);
 
-unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
+unsigned int nf_conncount_lookup(struct net *net, struct nf_conncount_list *list,
 				 const struct nf_conntrack_tuple *tuple,
 				 const struct nf_conntrack_zone *zone,
 				 bool *addit);
 
-bool nf_conncount_add(struct hlist_head *head,
+void nf_conncount_list_init(struct nf_conncount_list *list);
+
+bool nf_conncount_add(struct nf_conncount_list *list,
 		      const struct nf_conntrack_tuple *tuple,
 		      const struct nf_conntrack_zone *zone);
 
-void nf_conncount_cache_free(struct hlist_head *hhead);
+void nf_conncount_cache_free(struct nf_conncount_list *list);
 
 #endif

208 lines not on this page · raw message

index a832c59f0a9c..4f0491a36a1d 100644
@@ -14,10 +14,10 @@
 #include <net/netfilter/nf_conntrack_zones.h>
 
 struct nft_connlimit {
-	spinlock_t		lock;
-	struct hlist_head	hhead;
-	u32			limit;
-	bool			invert;
+	spinlock_t			lock;
+	struct nf_conncount_list	list;
+	u32				limit;
+	bool				invert;
 };
 
 static inline void nft_connlimit_do_eval(struct nft_connlimit *priv,

@@ -46,13 +46,13 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv,
 	}
 
 	spin_lock_bh(&priv->lock);
-	count = nf_conncount_lookup(nft_net(pkt), &priv->hhead, tuple_ptr, zone,
+	count = nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone,
 				    &addit);
 
 	if (!addit)
 		goto out;
 
-	if (!nf_conncount_add(&priv->hhead, tuple_ptr, zone)) {
+	if (!nf_conncount_add(&priv->list, tuple_ptr, zone)) {
 		regs->verdict.code = NF_DROP;
 		spin_unlock_bh(&priv->lock);
 		return;

@@ -88,7 +88,7 @@ static int nft_connlimit_do_init(const struct nft_ctx *ctx,
 	}
 
 	spin_lock_init(&priv->lock);
-	INIT_HLIST_HEAD(&priv->hhead);
+	nf_conncount_list_init(&priv->list);
 	priv->limit	= limit;
 	priv->invert	= invert;
 

@@ -99,7 +99,7 @@ static void nft_connlimit_do_destroy(const struct nft_ctx *ctx,
 				     struct nft_connlimit *priv)
 {
 	nf_ct_netns_put(ctx->net, ctx->family);
-	nf_conncount_cache_free(&priv->hhead);
+	nf_conncount_cache_free(&priv->list);
 }
 
 static int nft_connlimit_do_dump(struct sk_buff *skb,

@@ -213,7 +213,7 @@ static int nft_connlimit_clone(struct nft_expr *dst, const struct nft_expr *src)
 	struct nft_connlimit *priv_src = nft_expr_priv(src);
 
 	spin_lock_init(&priv_dst->lock);
-	INIT_HLIST_HEAD(&priv_dst->hhead);
+	nf_conncount_list_init(&priv_dst->list);
 	priv_dst->limit	 = priv_src->limit;
 	priv_dst->invert = priv_src->invert;
 

@@ -225,7 +225,7 @@ static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx,
 {
 	struct nft_connlimit *priv = nft_expr_priv(expr);
 
-	nf_conncount_cache_free(&priv->hhead);
+	nf_conncount_cache_free(&priv->list);
 }
 
 static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr)

@@ -234,9 +234,9 @@ static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr)
 	bool addit, ret;
 
 	spin_lock_bh(&priv->lock);
-	nf_conncount_lookup(net, &priv->hhead, NULL, &nf_ct_zone_dflt, &addit);
+	nf_conncount_lookup(net, &priv->list, NULL, &nf_ct_zone_dflt, &addit);
 
-	ret = hlist_empty(&priv->hhead);
+	ret = list_empty(&priv->list.head);
 	spin_unlock_bh(&priv->lock);
 
 	return ret;

index e4884e0e4f69..dbec17f674b7 100644
@@ -21,10 +21,10 @@ unsigned int nf_conncount_count(struct net *net,
 				const struct nf_conntrack_tuple *tuple,
 				const struct nf_conntrack_zone *zone);
 
-unsigned int nf_conncount_lookup(struct net *net, struct nf_conncount_list *list,
-				 const struct nf_conntrack_tuple *tuple,
-				 const struct nf_conntrack_zone *zone,
-				 bool *addit);
+void nf_conncount_lookup(struct net *net, struct nf_conncount_list *list,
+			 const struct nf_conntrack_tuple *tuple,
+			 const struct nf_conntrack_zone *zone,
+			 bool *addit);
 
 void nf_conncount_list_init(struct nf_conncount_list *list);
 

@@ -32,6 +32,9 @@ bool nf_conncount_add(struct nf_conncount_list *list,
 		      const struct nf_conntrack_tuple *tuple,
 		      const struct nf_conntrack_zone *zone);
 
+void nf_conncount_gc_list(struct net *net,
+			  struct nf_conncount_list *list);
+
 void nf_conncount_cache_free(struct nf_conncount_list *list);
 
 #endif

index 81b060adefef..7dfd9d5e6a3e 100644
@@ -144,26 +144,29 @@ find_or_evict(struct net *net, struct nf_conncount_list *list,
 	return ERR_PTR(-EAGAIN);
 }
 
-unsigned int nf_conncount_lookup(struct net *net,
-				 struct nf_conncount_list *list,
-				 const struct nf_conntrack_tuple *tuple,
-				 const struct nf_conntrack_zone *zone,
-				 bool *addit)
+void nf_conncount_lookup(struct net *net,
+			 struct nf_conncount_list *list,
+			 const struct nf_conntrack_tuple *tuple,
+			 const struct nf_conntrack_zone *zone,
+			 bool *addit)
 {
 	const struct nf_conntrack_tuple_hash *found;
 	struct nf_conncount_tuple *conn, *conn_n;
 	struct nf_conn *found_ct;
-	unsigned int length = 0;
+	unsigned int collect = 0;
 
+	/* best effort only */
 	*addit = tuple ? true : false;
 
 	/* check the saved connections */
 	list_for_each_entry_safe(conn, conn_n, &list->head, node) {
+		if (collect > CONNCOUNT_GC_MAX_NODES)
+			break;
+
 		found = find_or_evict(net, list, conn);
 		if (IS_ERR(found)) {
 			/* Not found, but might be about to be confirmed */
 			if (PTR_ERR(found) == -EAGAIN) {
-				length++;
 				if (!tuple)
 					continue;
 

@@ -171,8 +174,8 @@ unsigned int nf_conncount_lookup(struct net *net,
 				    nf_ct_zone_id(&conn->zone, conn->zone.dir) ==
 				    nf_ct_zone_id(zone, zone->dir))
 					*addit = false;
-			}
-
+			} else if (PTR_ERR(found) == -ENOENT)
+				collect++;
 			continue;
 		}
 

@@ -181,9 +184,10 @@ unsigned int nf_conncount_lookup(struct net *net,
 		if (tuple && nf_ct_tuple_equal(&conn->tuple, tuple) &&
 		    nf_ct_zone_equal(found_ct, zone, zone->dir)) {
 			/*
-			 * Just to be sure we have it only once in the list.
 			 * We should not see tuples twice unless someone hooks
 			 * this into a table without "-p tcp --syn".
+			 *
+			 * Attempt to avoid a re-add in this case.
 			 */
 			*addit = false;
 		} else if (already_closed(found_ct)) {

@@ -193,14 +197,12 @@ unsigned int nf_conncount_lookup(struct net *net,
 			 */
 			nf_ct_put(found_ct);
 			conn_free(list, conn);
+			collect++;
 			continue;
 		}
 
 		nf_ct_put(found_ct);
-		length++;
 	}
-
-	return length;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_lookup);
 

@@ -211,8 +213,8 @@ void nf_conncount_list_init(struct nf_conncount_list *list)
 }
 EXPORT_SYMBOL_GPL(nf_conncount_list_init);
 
-static void nf_conncount_gc_list(struct net *net,
-				 struct nf_conncount_list *list)
+void nf_conncount_gc_list(struct net *net,
+			  struct nf_conncount_list *list)
 {
 	const struct nf_conntrack_tuple_hash *found;
 	struct nf_conncount_tuple *conn, *conn_n;

@@ -244,6 +246,7 @@ static void nf_conncount_gc_list(struct net *net,
 			return;
 	}
 }
+EXPORT_SYMBOL_GPL(nf_conncount_gc_list);
 
 static void tree_nodes_free(struct rb_root *root,
 			    struct nf_conncount_rb *gc_nodes[],

@@ -291,8 +294,9 @@ count_tree(struct net *net, struct rb_root *root,
 			/* same source network -> be counted! */
 			unsigned int count;
 
-			count = nf_conncount_lookup(net, &rbconn->list, tuple,
-						    zone, &addit);
+			nf_conncount_lookup(net, &rbconn->list, tuple, zone,
+					    &addit);
+			count = rbconn->list.count;
 
 			tree_nodes_free(root, gc_nodes, gc_count);
 			if (!addit)

index 4f0491a36a1d..37c52ae06741 100644
@@ -46,8 +46,9 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv,
 	}
 
 	spin_lock_bh(&priv->lock);
-	count = nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone,
-				    &addit);
+	nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone,
+			    &addit);
+	count = priv->list.count;
 
 	if (!addit)
 		goto out;

@@ -231,10 +232,10 @@ static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx,
 static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr)
 {
 	struct nft_connlimit *priv = nft_expr_priv(expr);
-	bool addit, ret;
+	bool ret;
 
 	spin_lock_bh(&priv->lock);
-	nf_conncount_lookup(net, &priv->list, NULL, &nf_ct_zone_dflt, &addit);
+	nf_conncount_gc_list(net, &priv->list);
 
 	ret = list_empty(&priv->list.head);
 	spin_unlock_bh(&priv->lock);

index 7dfd9d5e6a3e..d1a4fd1c0f81 100644
@@ -262,18 +262,26 @@ static void tree_nodes_free(struct rb_root *root,
 }
 
 static unsigned int
-count_tree(struct net *net, struct rb_root *root,
-	   const u32 *key, u8 keylen,
+count_tree(struct net *net,
+	   struct nf_conncount_data *data,
+	   const u32 *key,
 	   const struct nf_conntrack_tuple *tuple,
 	   const struct nf_conntrack_zone *zone)
 {
 	struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES];
+	struct rb_root *root;
 	struct rb_node **rbnode, *parent;
 	struct nf_conncount_rb *rbconn;
 	struct nf_conncount_tuple *conn;
-	unsigned int gc_count;
+	unsigned int gc_count, hash;
 	bool no_gc = false;
+	unsigned int count = 0;
+	u8 keylen = data->keylen;
 
+	hash = jhash2(key, data->keylen, conncount_rnd) % CONNCOUNT_SLOTS;
+	root = &data->root[hash];
+
+	spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
  restart:
 	gc_count = 0;
 	parent = NULL;

@@ -292,20 +300,20 @@ count_tree(struct net *net, struct rb_root *root,
 			rbnode = &((*rbnode)->rb_right);
 		} else {
 			/* same source network -> be counted! */
-			unsigned int count;
-
 			nf_conncount_lookup(net, &rbconn->list, tuple, zone,
 					    &addit);
 			count = rbconn->list.count;
 
 			tree_nodes_free(root, gc_nodes, gc_count);
 			if (!addit)
-				return count;
+				goto out_unlock;
 
 			if (!nf_conncount_add(&rbconn->list, tuple, zone))
-				return 0; /* hotdrop */
+				count = 0; /* hotdrop */
+				goto out_unlock;
 
-			return count + 1;
+			count++;
+			goto out_unlock;
 		}
 
 		if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes))

@@ -328,18 +336,18 @@ count_tree(struct net *net, struct rb_root *root,
 		goto restart;
 	}
 
+	count = 0;
 	if (!tuple)
-		return 0;
-
+		goto out_unlock;
 	/* no match, need to insert new node */
 	rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC);
 	if (rbconn == NULL)
-		return 0;
+		goto out_unlock;
 
 	conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
 	if (conn == NULL) {
 		kmem_cache_free(conncount_rb_cachep, rbconn);
-		return 0;
+		goto out_unlock;
 	}
 
 	conn->tuple = *tuple;

@@ -348,10 +356,13 @@ count_tree(struct net *net, struct rb_root *root,
 
 	nf_conncount_list_init(&rbconn->list);
 	list_add(&conn->node, &rbconn->list.head);
+	count = 1;
 
 	rb_link_node(&rbconn->node, parent, rbnode);
 	rb_insert_color(&rbconn->node, root);
-	return 1;
+out_unlock:
+	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
+	return count;
 }
 
 /* Count and return number of conntrack entries in 'net' with particular 'key'.

@@ -363,20 +374,7 @@ unsigned int nf_conncount_count(struct net *net,
 				const struct nf_conntrack_tuple *tuple,
 				const struct nf_conntrack_zone *zone)
 {
-	struct rb_root *root;
-	int count;
-	u32 hash;
-
-	hash = jhash2(key, data->keylen, conncount_rnd) % CONNCOUNT_SLOTS;
-	root = &data->root[hash];
-
-	spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
-
-	count = count_tree(net, root, key, data->keylen, tuple, zone);
-
-	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
-
-	return count;
+	return count_tree(net, data, key, tuple, zone);
 }
 EXPORT_SYMBOL_GPL(nf_conncount_count);
 

index d1a4fd1c0f81..3f14806b7271 100644
@@ -262,6 +262,71 @@ static void tree_nodes_free(struct rb_root *root,
 }
 
 static unsigned int
+insert_tree(struct rb_root *root,
+	    unsigned int hash,
+	    const u32 *key,
+	    u8 keylen,
+	    const struct nf_conntrack_tuple *tuple,
+	    const struct nf_conntrack_zone *zone)
+{
+	struct rb_node **rbnode, *parent;
+	struct nf_conncount_rb *rbconn;
+	struct nf_conncount_tuple *conn;
+	unsigned int count = 0;
+
+	spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
+
+	parent = NULL;
+	rbnode = &(root->rb_node);
+	while (*rbnode) {
+		int diff;
+		rbconn = rb_entry(*rbnode, struct nf_conncount_rb, node);
+
+		parent = *rbnode;
+		diff = key_diff(key, rbconn->key, keylen);
+		if (diff < 0) {
+			rbnode = &((*rbnode)->rb_left);
+		} else if (diff > 0) {
+			rbnode = &((*rbnode)->rb_right);
+		} else {
+			/* unlikely: other cpu added node already */
+			if (!nf_conncount_add(&rbconn->list, tuple, zone)) {
+				count = 0; /* hotdrop */
+				goto out_unlock;
+			}
+
+			count = rbconn->list.count;
+			goto out_unlock;
+		}
+	}
+
+	/* expected case: match, insert new node */
+	rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC);
+	if (rbconn == NULL)
+		goto out_unlock;
+
+	conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
+	if (conn == NULL) {
+		kmem_cache_free(conncount_rb_cachep, rbconn);
+		goto out_unlock;
+	}
+
+	conn->tuple = *tuple;
+	conn->zone = *zone;
+	memcpy(rbconn->key, key, sizeof(u32) * keylen);
+
+	nf_conncount_list_init(&rbconn->list);
+	list_add(&conn->node, &rbconn->list.head);
+	count = 1;
+
+	rb_link_node(&rbconn->node, parent, rbnode);
+	rb_insert_color(&rbconn->node, root);
+out_unlock:
+	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
+	return count;
+}
+
+static unsigned int
 count_tree(struct net *net,
 	   struct nf_conncount_data *data,
 	   const u32 *key,

@@ -272,7 +337,6 @@ count_tree(struct net *net,
 	struct rb_root *root;
 	struct rb_node **rbnode, *parent;
 	struct nf_conncount_rb *rbconn;
-	struct nf_conncount_tuple *conn;
 	unsigned int gc_count, hash;
 	bool no_gc = false;
 	unsigned int count = 0;

@@ -339,27 +403,10 @@ count_tree(struct net *net,
 	count = 0;
 	if (!tuple)
 		goto out_unlock;
-	/* no match, need to insert new node */
-	rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC);
-	if (rbconn == NULL)
-		goto out_unlock;
-
-	conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
-	if (conn == NULL) {
-		kmem_cache_free(conncount_rb_cachep, rbconn);
-		goto out_unlock;
-	}
-
-	conn->tuple = *tuple;
-	conn->zone = *zone;
-	memcpy(rbconn->key, key, sizeof(u32) * keylen);
 
-	nf_conncount_list_init(&rbconn->list);
-	list_add(&conn->node, &rbconn->list.head);
-	count = 1;
+	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
+	return insert_tree(root, hash, key, keylen, tuple, zone);
 
-	rb_link_node(&rbconn->node, parent, rbnode);
-	rb_insert_color(&rbconn->node, root);
 out_unlock:
 	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
 	return count;

index dbec17f674b7..4b2b2baf8ab4 100644
@@ -5,9 +5,17 @@
 
 struct nf_conncount_data;
 
+enum nf_conncount_list_add {
+	NF_CONNCOUNT_ADDED, 	/* list add was ok */
+	NF_CONNCOUNT_ERR,	/* -ENOMEM, must drop skb */
+	NF_CONNCOUNT_SKIP,	/* list is already reclaimed by gc */
+};
+
 struct nf_conncount_list {
+	spinlock_t list_lock;
 	struct list_head head;	/* connections with the same filtering key */
 	unsigned int count;	/* length of list */
+	bool dead;
 };
 
 struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family,

@@ -28,11 +36,12 @@ void nf_conncount_lookup(struct net *net, struct nf_conncount_list *list,
 
 void nf_conncount_list_init(struct nf_conncount_list *list);
 
-bool nf_conncount_add(struct nf_conncount_list *list,
-		      const struct nf_conntrack_tuple *tuple,
-		      const struct nf_conntrack_zone *zone);
+enum nf_conncount_list_add
+nf_conncount_add(struct nf_conncount_list *list,
+		 const struct nf_conntrack_tuple *tuple,
+		 const struct nf_conntrack_zone *zone);
 
-void nf_conncount_gc_list(struct net *net,
+bool nf_conncount_gc_list(struct net *net,
 			  struct nf_conncount_list *list);
 
 void nf_conncount_cache_free(struct nf_conncount_list *list);

441 lines not on this page · raw message

index 37c52ae06741..b90d96ba4a12 100644
@@ -14,7 +14,6 @@
 #include <net/netfilter/nf_conntrack_zones.h>
 
 struct nft_connlimit {
-	spinlock_t			lock;
 	struct nf_conncount_list	list;
 	u32				limit;
 	bool				invert;

@@ -45,7 +44,6 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv,
 		return;
 	}
 
-	spin_lock_bh(&priv->lock);
 	nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone,
 			    &addit);
 	count = priv->list.count;

@@ -53,14 +51,12 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv,
 	if (!addit)
 		goto out;
 
-	if (!nf_conncount_add(&priv->list, tuple_ptr, zone)) {
+	if (nf_conncount_add(&priv->list, tuple_ptr, zone) == NF_CONNCOUNT_ERR) {
 		regs->verdict.code = NF_DROP;
-		spin_unlock_bh(&priv->lock);
 		return;
 	}
 	count++;
 out:
-	spin_unlock_bh(&priv->lock);
 
 	if ((count > priv->limit) ^ priv->invert) {
 		regs->verdict.code = NFT_BREAK;

@@ -88,7 +84,6 @@ static int nft_connlimit_do_init(const struct nft_ctx *ctx,
 			invert = true;
 	}
 
-	spin_lock_init(&priv->lock);
 	nf_conncount_list_init(&priv->list);
 	priv->limit	= limit;
 	priv->invert	= invert;

@@ -213,7 +208,6 @@ static int nft_connlimit_clone(struct nft_expr *dst, const struct nft_expr *src)
 	struct nft_connlimit *priv_dst = nft_expr_priv(dst);
 	struct nft_connlimit *priv_src = nft_expr_priv(src);
 
-	spin_lock_init(&priv_dst->lock);
 	nf_conncount_list_init(&priv_dst->list);
 	priv_dst->limit	 = priv_src->limit;
 	priv_dst->invert = priv_src->invert;

@@ -232,15 +226,8 @@ static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx,
 static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr)
 {
 	struct nft_connlimit *priv = nft_expr_priv(expr);
-	bool ret;
 
-	spin_lock_bh(&priv->lock);
-	nf_conncount_gc_list(net, &priv->list);
-
-	ret = list_empty(&priv->list.head);
-	spin_unlock_bh(&priv->lock);
-
-	return ret;
+	return nf_conncount_gc_list(net, &priv->list);
 }
 
 static struct nft_expr_type nft_connlimit_type;