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

Pablo Neira Ayuso says:

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

The following patchset contains Netfilter updates for net-next:

1) Clean up and consolidate ct ecache infrastructure by merging ct and
   expect notifiers, from Florian Westphal.

2) Missing counters and timestamp in nfnetlink_queue and _log conntrack
   information.

3) Missing error check for xt_register_template() in iptables mangle,
   as a incremental fix for the previous pull request, also from
   Florian Westphal.

4) Add netfilter hooks for the SRv6 lightweigh tunnel driver, from
   Ryoga Sato. The hooks are enabled via nf_hooks_lwtunnel sysctl
   to make sure existing netfilter rulesets do not break. There is
   a static key to disable the hooks by default.

   The pktgen_bench_xmit_mode_netif_receive.sh shows no noticeable
   impact in the seg6_input path for non-netfilter users: similar
   numbers with and without this patch.

   This is a sample of the perf report output:

    11.67%  kpktgend_0       [ipv6]                    [k] ipv6_get_saddr_eval
     7.89%  kpktgend_0       [ipv6]                    [k] __ipv6_addr_label
     7.52%  kpktgend_0       [ipv6]                    [k] __ipv6_dev_get_saddr
     6.63%  kpktgend_0       [kernel.vmlinux]          [k] asm_exc_nmi
     4.74%  kpktgend_0       [ipv6]                    [k] fib6_node_lookup_1
     3.48%  kpktgend_0       [kernel.vmlinux]          [k] pskb_expand_head
     3.33%  kpktgend_0       [ipv6]                    [k] ip6_rcv_core.isra.29
     3.33%  kpktgend_0       [ipv6]                    [k] seg6_do_srh_encap
     2.53%  kpktgend_0       [ipv6]                    [k] ipv6_dev_get_saddr
     2.45%  kpktgend_0       [ipv6]                    [k] fib6_table_lookup
     2.24%  kpktgend_0       [kernel.vmlinux]          [k] ___cache_free
     2.16%  kpktgend_0       [ipv6]                    [k] ip6_pol_route
     2.11%  kpktgend_0       [kernel.vmlinux]          [k] __ipv6_addr_type
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/nf_conntrack-sysctl.rst

@@ -184,6 +184,13 @@ nf_conntrack_gre_timeout_stream - INTEGER (seconds)
 	This extended timeout will be used in case there is an GRE stream
 	detected.
 
+nf_hooks_lwtunnel - BOOLEAN
+	- 0 - disabled (default)
+	- not 0 - enabled
+
+	If this option is enabled, the lightweight tunnel netfilter hooks are
+	enabled. This option cannot be disabled once it is enabled.
+
 nf_flowtable_tcp_timeout - INTEGER (seconds)
         default 30
 

include/net/lwtunnel.h

@@ -51,6 +51,9 @@ struct lwtunnel_encap_ops {
 };
 
 #ifdef CONFIG_LWTUNNEL
+
+DECLARE_STATIC_KEY_FALSE(nf_hooks_lwtunnel_enabled);
+
 void lwtstate_free(struct lwtunnel_state *lws);
 
 static inline struct lwtunnel_state *

include/net/netfilter/nf_conntrack_ecache.h

@@ -72,14 +72,20 @@ struct nf_ct_event {
 	int report;
 };
 
+struct nf_exp_event {
+	struct nf_conntrack_expect *exp;
+	u32 portid;
+	int report;
+};
+
 struct nf_ct_event_notifier {
-	int (*fcn)(unsigned int events, struct nf_ct_event *item);
+	int (*ct_event)(unsigned int events, const struct nf_ct_event *item);
+	int (*exp_event)(unsigned int events, const struct nf_exp_event *item);
 };
 
-int nf_conntrack_register_notifier(struct net *net,
-				   struct nf_ct_event_notifier *nb);
-void nf_conntrack_unregister_notifier(struct net *net,
-				      struct nf_ct_event_notifier *nb);
+void nf_conntrack_register_notifier(struct net *net,
+				   const struct nf_ct_event_notifier *nb);
+void nf_conntrack_unregister_notifier(struct net *net);
 
 void nf_ct_deliver_cached_events(struct nf_conn *ct);
 int nf_conntrack_eventmask_report(unsigned int eventmask, struct nf_conn *ct,
@@ -151,22 +157,6 @@ nf_conntrack_event(enum ip_conntrack_events event, struct nf_conn *ct)
 }
 
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
-
-struct nf_exp_event {
-	struct nf_conntrack_expect *exp;
-	u32 portid;
-	int report;
-};
-
-struct nf_exp_event_notifier {
-	int (*fcn)(unsigned int events, struct nf_exp_event *item);
-};
-
-int nf_ct_expect_register_notifier(struct net *net,
-				   struct nf_exp_event_notifier *nb);
-void nf_ct_expect_unregister_notifier(struct net *net,
-				      struct nf_exp_event_notifier *nb);
-
 void nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
 			       struct nf_conntrack_expect *exp,
 			       u32 portid, int report);

include/net/netfilter/nf_hooks_lwtunnel.h

+#include <linux/sysctl.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_SYSCTL
+int nf_hooks_lwtunnel_sysctl_handler(struct ctl_table *table, int write,
+				     void *buffer, size_t *lenp, loff_t *ppos);
+#endif

include/net/netns/conntrack.h

@@ -113,7 +113,6 @@ struct netns_ct {
 	struct ct_pcpu __percpu *pcpu_lists;
 	struct ip_conntrack_stat __percpu *stat;
 	struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
-	struct nf_exp_event_notifier __rcu *nf_expect_event_cb;
 	struct nf_ip_net	nf_ct_proto;
 #if defined(CONFIG_NF_CONNTRACK_LABELS)
 	unsigned int		labels_used;

net/core/lwtunnel.c

@@ -23,6 +23,9 @@
 #include <net/ip6_fib.h>
 #include <net/rtnh.h>
 
+DEFINE_STATIC_KEY_FALSE(nf_hooks_lwtunnel_enabled);
+EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_enabled);
+
 #ifdef CONFIG_MODULES
 
 static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type)

net/ipv4/netfilter/iptable_mangle.c

@@ -112,6 +112,8 @@ static int __init iptable_mangle_init(void)
 {
 	int ret = xt_register_template(&packet_mangler,
 				       iptable_mangle_table_init);
+	if (ret < 0)
+		return ret;
 
 	mangle_ops = xt_hook_ops_alloc(&packet_mangler, iptable_mangle_hook);
 	if (IS_ERR(mangle_ops)) {

net/ipv6/seg6_iptunnel.c

@@ -26,6 +26,8 @@
 #ifdef CONFIG_IPV6_SEG6_HMAC
 #include <net/seg6_hmac.h>
 #endif
+#include <net/lwtunnel.h>
+#include <linux/netfilter.h>
 
 static size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo)
 {
@@ -295,11 +297,19 @@ static int seg6_do_srh(struct sk_buff *skb)
 
 	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+	nf_reset_ct(skb);
 
 	return 0;
 }
 
-static int seg6_input(struct sk_buff *skb)
+static int seg6_input_finish(struct net *net, struct sock *sk,
+			     struct sk_buff *skb)
+{
+	return dst_input(skb);
+}
+
+static int seg6_input_core(struct net *net, struct sock *sk,
+			   struct sk_buff *skb)
 {
 	struct dst_entry *orig_dst = skb_dst(skb);
 	struct dst_entry *dst = NULL;
@@ -337,10 +347,41 @@ static int seg6_input(struct sk_buff *skb)
 	if (unlikely(err))
 		return err;
 
-	return dst_input(skb);
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
+		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
+			       dev_net(skb->dev), NULL, skb, NULL,
+			       skb_dst(skb)->dev, seg6_input_finish);
+
+	return seg6_input_finish(dev_net(skb->dev), NULL, skb);
 }
 
-static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+static int seg6_input_nf(struct sk_buff *skb)
+{
+	struct net_device *dev = skb_dst(skb)->dev;
+	struct net *net = dev_net(skb->dev);
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		return NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, NULL,
+			       skb, NULL, dev, seg6_input_core);
+	case htons(ETH_P_IPV6):
+		return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, NULL,
+			       skb, NULL, dev, seg6_input_core);
+	}
+
+	return -EINVAL;
+}
+
+static int seg6_input(struct sk_buff *skb)
+{
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
+		return seg6_input_nf(skb);
+
+	return seg6_input_core(dev_net(skb->dev), NULL, skb);
+}
+
+static int seg6_output_core(struct net *net, struct sock *sk,
+			    struct sk_buff *skb)
 {
 	struct dst_entry *orig_dst = skb_dst(skb);
 	struct dst_entry *dst = NULL;
@@ -387,12 +428,40 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (unlikely(err))
 		goto drop;
 
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
+		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb,
+			       NULL, skb_dst(skb)->dev, dst_output);
+
 	return dst_output(net, sk, skb);
 drop:
 	kfree_skb(skb);
 	return err;
 }
 
+static int seg6_output_nf(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	struct net_device *dev = skb_dst(skb)->dev;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		return NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb,
+			       NULL, dev, seg6_output_core);
+	case htons(ETH_P_IPV6):
+		return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb,
+			       NULL, dev, seg6_output_core);
+	}
+
+	return -EINVAL;
+}
+
+static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
+		return seg6_output_nf(net, sk, skb);
+
+	return seg6_output_core(net, sk, skb);
+}
+
 static int seg6_build_state(struct net *net, struct nlattr *nla,
 			    unsigned int family, const void *cfg,
 			    struct lwtunnel_state **ts,

net/ipv6/seg6_local.c

@@ -30,6 +30,8 @@
 #include <net/seg6_local.h>
 #include <linux/etherdevice.h>
 #include <linux/bpf.h>
+#include <net/lwtunnel.h>
+#include <linux/netfilter.h>
 
 #define SEG6_F_ATTR(i)		BIT(i)
 
@@ -413,12 +415,33 @@ static int input_action_end_dx2(struct sk_buff *skb,
 	return -EINVAL;
 }
 
+static int input_action_end_dx6_finish(struct net *net, struct sock *sk,
+				       struct sk_buff *skb)
+{
+	struct dst_entry *orig_dst = skb_dst(skb);
+	struct in6_addr *nhaddr = NULL;
+	struct seg6_local_lwt *slwt;
+
+	slwt = seg6_local_lwtunnel(orig_dst->lwtstate);
+
+	/* The inner packet is not associated to any local interface,
+	 * so we do not call netif_rx().
+	 *
+	 * If slwt->nh6 is set to ::, then lookup the nexthop for the
+	 * inner packet's DA. Otherwise, use the specified nexthop.
+	 */
+	if (!ipv6_addr_any(&slwt->nh6))
+		nhaddr = &slwt->nh6;
+
+	seg6_lookup_nexthop(skb, nhaddr, 0);
+
+	return dst_input(skb);
+}
+
 /* decapsulate and forward to specified nexthop */
 static int input_action_end_dx6(struct sk_buff *skb,
 				struct seg6_local_lwt *slwt)
 {
-	struct in6_addr *nhaddr = NULL;
-
 	/* this function accepts IPv6 encapsulated packets, with either
 	 * an SRH with SL=0, or no SRH.
 	 */
@@ -429,40 +452,30 @@ static int input_action_end_dx6(struct sk_buff *skb,
 	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
 		goto drop;
 
-	/* The inner packet is not associated to any local interface,
-	 * so we do not call netif_rx().
-	 *
-	 * If slwt->nh6 is set to ::, then lookup the nexthop for the
-	 * inner packet's DA. Otherwise, use the specified nexthop.
-	 */
-
-	if (!ipv6_addr_any(&slwt->nh6))
-		nhaddr = &slwt->nh6;
-
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+	nf_reset_ct(skb);
 
-	seg6_lookup_nexthop(skb, nhaddr, 0);
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
+		return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
+			       dev_net(skb->dev), NULL, skb, NULL,
+			       skb_dst(skb)->dev, input_action_end_dx6_finish);
 
-	return dst_input(skb);
+	return input_action_end_dx6_finish(dev_net(skb->dev), NULL, skb);
 drop:
 	kfree_skb(skb);
 	return -EINVAL;
 }
 
-static int input_action_end_dx4(struct sk_buff *skb,
-				struct seg6_local_lwt *slwt)
+static int input_action_end_dx4_finish(struct net *net, struct sock *sk,
+				       struct sk_buff *skb)
 {
+	struct dst_entry *orig_dst = skb_dst(skb);
+	struct seg6_local_lwt *slwt;
 	struct iphdr *iph;
 	__be32 nhaddr;
 	int err;
 
-	if (!decap_and_validate(skb, IPPROTO_IPIP))
-		goto drop;
-
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-		goto drop;
-
-	skb->protocol = htons(ETH_P_IP);
+	slwt = seg6_local_lwtunnel(orig_dst->lwtstate);
 
 	iph = ip_hdr(skb);
 
@@ -470,14 +483,34 @@ static int input_action_end_dx4(struct sk_buff *skb,
 
 	skb_dst_drop(skb);
 
-	skb_set_transport_header(skb, sizeof(struct iphdr));
-
 	err = ip_route_input(skb, nhaddr, iph->saddr, 0, skb->dev);
-	if (err)
-		goto drop;
+	if (err) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
 
 	return dst_input(skb);
+}
+
+static int input_action_end_dx4(struct sk_buff *skb,
+				struct seg6_local_lwt *slwt)
+{
+	if (!decap_and_validate(skb, IPPROTO_IPIP))
+		goto drop;
+
+	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		goto drop;
+
+	skb->protocol = htons(ETH_P_IP);
+	skb_set_transport_header(skb, sizeof(struct iphdr));
+	nf_reset_ct(skb);
+
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
+		return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
+			       dev_net(skb->dev), NULL, skb, NULL,
+			       skb_dst(skb)->dev, input_action_end_dx4_finish);
 
+	return input_action_end_dx4_finish(dev_net(skb->dev), NULL, skb);
 drop:
 	kfree_skb(skb);
 	return -EINVAL;
@@ -645,6 +678,7 @@ static struct sk_buff *end_dt_vrf_core(struct sk_buff *skb,
 	skb_dst_drop(skb);
 
 	skb_set_transport_header(skb, hdrlen);
+	nf_reset_ct(skb);
 
 	return end_dt_vrf_rcv(skb, family, vrf);
 
@@ -1078,7 +1112,8 @@ static void seg6_local_update_counters(struct seg6_local_lwt *slwt,
 	u64_stats_update_end(&pcounters->syncp);
 }
 
-static int seg6_local_input(struct sk_buff *skb)
+static int seg6_local_input_core(struct net *net, struct sock *sk,
+				 struct sk_buff *skb)
 {
 	struct dst_entry *orig_dst = skb_dst(skb);
 	struct seg6_action_desc *desc;
@@ -1086,11 +1121,6 @@ static int seg6_local_input(struct sk_buff *skb)
 	unsigned int len = skb->len;
 	int rc;
 
-	if (skb->protocol != htons(ETH_P_IPV6)) {
-		kfree_skb(skb);
-		return -EINVAL;
-	}
-
 	slwt = seg6_local_lwtunnel(orig_dst->lwtstate);
 	desc = slwt->desc;
 
@@ -1104,6 +1134,21 @@ static int seg6_local_input(struct sk_buff *skb)
 	return rc;
 }
 
+static int seg6_local_input(struct sk_buff *skb)
+{
+	if (skb->protocol != htons(ETH_P_IPV6)) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
+		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN,
+			       dev_net(skb->dev), NULL, skb, skb->dev, NULL,
+			       seg6_local_input_core);
+
+	return seg6_local_input_core(dev_net(skb->dev), NULL, skb);
+}
+
 static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = {
 	[SEG6_LOCAL_ACTION]	= { .type = NLA_U32 },
 	[SEG6_LOCAL_SRH]	= { .type = NLA_BINARY },

net/netfilter/Makefile

@@ -212,3 +212,6 @@ obj-$(CONFIG_IP_SET) += ipset/
 
 # IPVS
 obj-$(CONFIG_IP_VS) += ipvs/
+
+# lwtunnel
+obj-$(CONFIG_LWTUNNEL) += nf_hooks_lwtunnel.o

net/netfilter/nf_conntrack_ecache.c

@@ -130,58 +130,77 @@ static void ecache_work(struct work_struct *work)
 		schedule_delayed_work(&cnet->ecache_dwork, delay);
 }
 
-int nf_conntrack_eventmask_report(unsigned int eventmask, struct nf_conn *ct,
-				  u32 portid, int report)
+static int __nf_conntrack_eventmask_report(struct nf_conntrack_ecache *e,
+					   const unsigned int events,
+					   const unsigned long missed,
+					   const struct nf_ct_event *item)
 {
-	int ret = 0;
-	struct net *net = nf_ct_net(ct);
+	struct nf_conn *ct = item->ct;
+	struct net *net = nf_ct_net(item->ct);
 	struct nf_ct_event_notifier *notify;
-	struct nf_conntrack_ecache *e;
+	int ret;
+
+	if (!((events | missed) & e->ctmask))
+		return 0;
 
 	rcu_read_lock();
+
 	notify = rcu_dereference(net->ct.nf_conntrack_event_cb);
-	if (!notify)
-		goto out_unlock;
+	if (!notify) {
+		rcu_read_unlock();
+		return 0;
+	}
+
+	ret = notify->ct_event(events | missed, item);
+	rcu_read_unlock();
+
+	if (likely(ret >= 0 && missed == 0))
+		return 0;
+
+	spin_lock_bh(&ct->lock);
+	if (ret < 0)
+		e->missed |= events;
+	else
+		e->missed &= ~missed;
+	spin_unlock_bh(&ct->lock);
+
+	return ret;
+}
+
+int nf_conntrack_eventmask_report(unsigned int events, struct nf_conn *ct,
+				  u32 portid, int report)
+{
+	struct nf_conntrack_ecache *e;
+	struct nf_ct_event item;
+	unsigned long missed;
+	int ret;
+
+	if (!nf_ct_is_confirmed(ct))
+		return 0;
 
 	e = nf_ct_ecache_find(ct);
 	if (!e)
-		goto out_unlock;
+		return 0;
 
-	if (nf_ct_is_confirmed(ct)) {
-		struct nf_ct_event item = {
-			.ct	= ct,
-			.portid	= e->portid ? e->portid : portid,
-			.report = report
-		};
-		/* This is a resent of a destroy event? If so, skip missed */
-		unsigned long missed = e->portid ? 0 : e->missed;
-
-		if (!((eventmask | missed) & e->ctmask))
-			goto out_unlock;
-
-		ret = notify->fcn(eventmask | missed, &item);
-		if (unlikely(ret < 0 || missed)) {
-			spin_lock_bh(&ct->lock);
-			if (ret < 0) {
-				/* This is a destroy event that has been
-				 * triggered by a process, we store the PORTID
-				 * to include it in the retransmission.
-				 */
-				if (eventmask & (1 << IPCT_DESTROY)) {
-					if (e->portid == 0 && portid != 0)
-						e->portid = portid;
-					e->state = NFCT_ECACHE_DESTROY_FAIL;
-				} else {
-					e->missed |= eventmask;
-				}
-			} else {
-				e->missed &= ~missed;
-			}
-			spin_unlock_bh(&ct->lock);
-		}
+	memset(&item, 0, sizeof(item));
+
+	item.ct = ct;
+	item.portid = e->portid ? e->portid : portid;
+	item.report = report;
+
+	/* This is a resent of a destroy event? If so, skip missed */
+	missed = e->portid ? 0 : e->missed;
+
+	ret = __nf_conntrack_eventmask_report(e, events, missed, &item);
+	if (unlikely(ret < 0 && (events & (1 << IPCT_DESTROY)))) {
+		/* This is a destroy event that has been triggered by a process,
+		 * we store the PORTID to include it in the retransmission.
+		 */
+		if (e->portid == 0 && portid != 0)
+			e->portid = portid;
+		e->state = NFCT_ECACHE_DESTROY_FAIL;
 	}
-out_unlock:
-	rcu_read_unlock();
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_eventmask_report);
@@ -190,53 +209,28 @@ EXPORT_SYMBOL_GPL(nf_conntrack_eventmask_report);
  * disabled softirqs */
 void nf_ct_deliver_cached_events(struct nf_conn *ct)
 {
-	struct net *net = nf_ct_net(ct);
-	unsigned long events, missed;
-	struct nf_ct_event_notifier *notify;
 	struct nf_conntrack_ecache *e;
 	struct nf_ct_event item;
-	int ret;
-
-	rcu_read_lock();
-	notify = rcu_dereference(net->ct.nf_conntrack_event_cb);
-	if (notify == NULL)
-		goto out_unlock;
+	unsigned long events;
 
 	if (!nf_ct_is_confirmed(ct) || nf_ct_is_dying(ct))
-		goto out_unlock;
+		return;
 
 	e = nf_ct_ecache_find(ct);
 	if (e == NULL)
-		goto out_unlock;
+		return;
 
 	events = xchg(&e->cache, 0);
 
-	/* We make a copy of the missed event cache without taking
-	 * the lock, thus we may send missed events twice. However,
-	 * this does not harm and it happens very rarely. */
-	missed = e->missed;
-
-	if (!((events | missed) & e->ctmask))
-		goto out_unlock;
-
 	item.ct = ct;
 	item.portid = 0;
 	item.report = 0;
 
-	ret = notify->fcn(events | missed, &item);
-
-	if (likely(ret == 0 && !missed))
-		goto out_unlock;
-
-	spin_lock_bh(&ct->lock);
-	if (ret < 0)
-		e->missed |= events;
-	else
-		e->missed &= ~missed;
-	spin_unlock_bh(&ct->lock);
-
-out_unlock:
-	rcu_read_unlock();
+	/* We make a copy of the missed event cache without taking
+	 * the lock, thus we may send missed events twice. However,
+	 * this does not harm and it happens very rarely.
+	 */
+	__nf_conntrack_eventmask_report(e, events, e->missed, &item);
 }
 EXPORT_SYMBOL_GPL(nf_ct_deliver_cached_events);
 
@@ -246,11 +240,11 @@ void nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
 
 {
 	struct net *net = nf_ct_exp_net(exp);
-	struct nf_exp_event_notifier *notify;
+	struct nf_ct_event_notifier *notify;
 	struct nf_conntrack_ecache *e;
 
 	rcu_read_lock();
-	notify = rcu_dereference(net->ct.nf_expect_event_cb);
+	notify = rcu_dereference(net->ct.nf_conntrack_event_cb);
 	if (!notify)
 		goto out_unlock;
 
@@ -264,86 +258,35 @@ void nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
 			.portid	= portid,
 			.report = report
 		};
-		notify->fcn(1 << event, &item);
+		notify->exp_event(1 << event, &item);
 	}
 out_unlock:
 	rcu_read_unlock();
 }
 
-int nf_conntrack_register_notifier(struct net *net,
-				   struct nf_ct_event_notifier *new)
+void nf_conntrack_register_notifier(struct net *net,
+				    const struct nf_ct_event_notifier *new)
 {
-	int ret;
 	struct nf_ct_event_notifier *notify;
 
 	mutex_lock(&nf_ct_ecache_mutex);
 	notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb,
 					   lockdep_is_held(&nf_ct_ecache_mutex));
-	if (notify != NULL) {
-		ret = -EBUSY;
-		goto out_unlock;
-	}
+	WARN_ON_ONCE(notify);
 	rcu_assign_pointer(net->ct.nf_conntrack_event_cb, new);
-	ret = 0;
-
-out_unlock:
 	mutex_unlock(&nf_ct_ecache_mutex);
-	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_register_notifier);
 
-void nf_conntrack_unregister_notifier(struct net *net,
-				      struct nf_ct_event_notifier *new)
+void nf_conntrack_unregister_notifier(struct net *net)
 {
-	struct nf_ct_event_notifier *notify;
-
 	mutex_lock(&nf_ct_ecache_mutex);
-	notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb,
-					   lockdep_is_held(&nf_ct_ecache_mutex));
-	BUG_ON(notify != new);
 	RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, NULL);
 	mutex_unlock(&nf_ct_ecache_mutex);
-	/* synchronize_rcu() is called from ctnetlink_exit. */
+	/* synchronize_rcu() is called after netns pre_exit */
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier);
 
-int nf_ct_expect_register_notifier(struct net *net,
-				   struct nf_exp_event_notifier *new)
-{
-	int ret;
-	struct nf_exp_event_notifier *notify;
-
-	mutex_lock(&nf_ct_ecache_mutex);
-	notify = rcu_dereference_protected(net->ct.nf_expect_event_cb,
-					   lockdep_is_held(&nf_ct_ecache_mutex));
-	if (notify != NULL) {
-		ret = -EBUSY;
-		goto out_unlock;
-	}
-	rcu_assign_pointer(net->ct.nf_expect_event_cb, new);
-	ret = 0;
-
-out_unlock:
-	mutex_unlock(&nf_ct_ecache_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(nf_ct_expect_register_notifier);
-
-void nf_ct_expect_unregister_notifier(struct net *net,
-				      struct nf_exp_event_notifier *new)
-{
-	struct nf_exp_event_notifier *notify;
-
-	mutex_lock(&nf_ct_ecache_mutex);
-	notify = rcu_dereference_protected(net->ct.nf_expect_event_cb,
-					   lockdep_is_held(&nf_ct_ecache_mutex));
-	BUG_ON(notify != new);
-	RCU_INIT_POINTER(net->ct.nf_expect_event_cb, NULL);
-	mutex_unlock(&nf_ct_ecache_mutex);
-	/* synchronize_rcu() is called from ctnetlink_exit. */
-}
-EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier);
-
 void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state)
 {
 	struct nf_conntrack_net *cnet = nf_ct_pernet(net);

net/netfilter/nf_conntrack_netlink.c

@@ -706,7 +706,7 @@ static size_t ctnetlink_nlmsg_size(const struct nf_conn *ct)
 }
 
 static int
-ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
+ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item)
 {
 	const struct nf_conntrack_zone *zone;
 	struct net *net;
@@ -2669,6 +2669,8 @@ ctnetlink_glue_build_size(const struct nf_conn *ct)
 	       + nla_total_size(0) /* CTA_HELP */
 	       + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */
 	       + ctnetlink_secctx_size(ct)
+	       + ctnetlink_acct_size(ct)
+	       + ctnetlink_timestamp_size(ct)
 #if IS_ENABLED(CONFIG_NF_NAT)
 	       + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */
 	       + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */
@@ -2726,6 +2728,10 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct)
 	if (ctnetlink_dump_protoinfo(skb, ct, false) < 0)
 		goto nla_put_failure;
 
+	if (ctnetlink_dump_acct(skb, ct, IPCTNL_MSG_CT_GET) < 0 ||
+	    ctnetlink_dump_timestamp(skb, ct) < 0)
+		goto nla_put_failure;
+
 	if (ctnetlink_dump_helpinfo(skb, ct) < 0)
 		goto nla_put_failure;
 
@@ -3104,7 +3110,7 @@ ctnetlink_exp_fill_info(struct sk_buff *skb, u32 portid, u32 seq,
 
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
 static int
-ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item)
+ctnetlink_expect_event(unsigned int events, const struct nf_exp_event *item)
 {
 	struct nf_conntrack_expect *exp = item->exp;
 	struct net *net = nf_ct_exp_net(exp);
@@ -3755,11 +3761,8 @@ static int ctnetlink_stat_exp_cpu(struct sk_buff *skb,
 
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
 static struct nf_ct_event_notifier ctnl_notifier = {
-	.fcn = ctnetlink_conntrack_event,
-};
-
-static struct nf_exp_event_notifier ctnl_notifier_exp = {
-	.fcn = ctnetlink_expect_event,
+	.ct_event = ctnetlink_conntrack_event,
+	.exp_event = ctnetlink_expect_event,
 };
 #endif
 
@@ -3852,52 +3855,21 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP);
 static int __net_init ctnetlink_net_init(struct net *net)
 {
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
-	int ret;
-
-	ret = nf_conntrack_register_notifier(net, &ctnl_notifier);
-	if (ret < 0) {
-		pr_err("ctnetlink_init: cannot register notifier.\n");
-		goto err_out;
-	}
-
-	ret = nf_ct_expect_register_notifier(net, &ctnl_notifier_exp);
-	if (ret < 0) {
-		pr_err("ctnetlink_init: cannot expect register notifier.\n");
-		goto err_unreg_notifier;
-	}
+	nf_conntrack_register_notifier(net, &ctnl_notifier);
 #endif
 	return 0;
-
-#ifdef CONFIG_NF_CONNTRACK_EVENTS
-err_unreg_notifier:
-	nf_conntrack_unregister_notifier(net, &ctnl_notifier);
-err_out:
-	return ret;
-#endif
 }
 
-static void ctnetlink_net_exit(struct net *net)
+static void ctnetlink_net_pre_exit(struct net *net)
 {
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
-	nf_ct_expect_unregister_notifier(net, &ctnl_notifier_exp);
-	nf_conntrack_unregister_notifier(net, &ctnl_notifier);
+	nf_conntrack_unregister_notifier(net);
 #endif
 }
 
-static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list)
-{
-	struct net *net;
-
-	list_for_each_entry(net, net_exit_list, exit_list)
-		ctnetlink_net_exit(net);
-
-	/* wait for other cpus until they are done with ctnl_notifiers */
-	synchronize_rcu();
-}
-
 static struct pernet_operations ctnetlink_net_ops = {
 	.init		= ctnetlink_net_init,
-	.exit_batch	= ctnetlink_net_exit_batch,
+	.pre_exit	= ctnetlink_net_pre_exit,
 };
 
 static int __init ctnetlink_init(void)

net/netfilter/nf_conntrack_standalone.c

@@ -22,6 +22,9 @@
 #include <net/netfilter/nf_conntrack_acct.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/nf_conntrack_timestamp.h>
+#ifdef CONFIG_LWTUNNEL
+#include <net/netfilter/nf_hooks_lwtunnel.h>
+#endif
 #include <linux/rculist_nulls.h>
 
 static bool enable_hooks __read_mostly;
@@ -612,6 +615,9 @@ enum nf_ct_sysctl_index {
 	NF_SYSCTL_CT_PROTO_TIMEOUT_GRE,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM,
 #endif
+#ifdef CONFIG_LWTUNNEL
+	NF_SYSCTL_CT_LWTUNNEL,
+#endif
 
 	__NF_SYSCTL_CT_LAST_SYSCTL,
 };
@@ -958,6 +964,15 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 		.mode           = 0644,
 		.proc_handler   = proc_dointvec_jiffies,
 	},
+#endif
+#ifdef CONFIG_LWTUNNEL
+	[NF_SYSCTL_CT_LWTUNNEL] = {
+		.procname	= "nf_hooks_lwtunnel",
+		.data		= NULL,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= nf_hooks_lwtunnel_sysctl_handler,
+	},
 #endif
 	{}
 };

net/netfilter/nf_hooks_lwtunnel.c

+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/sysctl.h>
+#include <net/lwtunnel.h>
+#include <net/netfilter/nf_hooks_lwtunnel.h>
+
+static inline int nf_hooks_lwtunnel_get(void)
+{
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
+		return 1;
+	else
+		return 0;
+}
+
+static inline int nf_hooks_lwtunnel_set(int enable)
+{
+	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) {
+		if (!enable)
+			return -EBUSY;
+	} else if (enable) {
+		static_branch_enable(&nf_hooks_lwtunnel_enabled);
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_SYSCTL
+int nf_hooks_lwtunnel_sysctl_handler(struct ctl_table *table, int write,
+				     void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int proc_nf_hooks_lwtunnel_enabled = 0;
+	struct ctl_table tmp = {
+		.procname = table->procname,
+		.data = &proc_nf_hooks_lwtunnel_enabled,
+		.maxlen = sizeof(int),
+		.mode = table->mode,
+		.extra1 = SYSCTL_ZERO,
+		.extra2 = SYSCTL_ONE,
+	};
+	int ret;
+
+	if (!write)
+		proc_nf_hooks_lwtunnel_enabled = nf_hooks_lwtunnel_get();
+
+	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+
+	if (write && ret == 0)
+		ret = nf_hooks_lwtunnel_set(proc_nf_hooks_lwtunnel_enabled);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_sysctl_handler);
+#endif /* CONFIG_SYSCTL */