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) Add nfgenmsg field to nfnetlink's struct nfnl_info and use it.

2) Remove nft_ctx_init_from_elemattr() and nft_ctx_init_from_setattr()
   helper functions.

3) Add the nf_ct_pernet() helper function to fetch the conntrack
   pernetns data area.

4) Expose TCP and UDP flowtable offload timeouts through sysctl,
   from Oz Shlomo.

5) Add nfnetlink_hook subsystem to fetch the netfilter hook
   pipeline configuration, from Florian Westphal. This also includes
   a new field to annotate the hook type as metadata.

6) Fix unsafe memory access to non-linear skbuff in the new SCTP
   chunk support for nft_exthdr, from Phil Sutter.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netfilter.h

@@ -77,12 +77,18 @@ struct nf_hook_state {
 typedef unsigned int nf_hookfn(void *priv,
 			       struct sk_buff *skb,
 			       const struct nf_hook_state *state);
+enum nf_hook_ops_type {
+	NF_HOOK_OP_UNDEFINED,
+	NF_HOOK_OP_NF_TABLES,
+};
+
 struct nf_hook_ops {
 	/* User fills in from here down. */
 	nf_hookfn		*hook;
 	struct net_device	*dev;
 	void			*priv;
-	u_int8_t		pf;
+	u8			pf;
+	enum nf_hook_ops_type	hook_ops_type:8;
 	unsigned int		hooknum;
 	/* Hooks are ordered in ascending priority. */
 	int			priority;

include/linux/netfilter/nfnetlink.h

@@ -11,6 +11,7 @@ struct nfnl_info {
 	struct net		*net;
 	struct sock		*sk;
 	const struct nlmsghdr	*nlh;
+	const struct nfgenmsg	*nfmsg;
 	struct netlink_ext_ack	*extack;
 };
 

include/net/netfilter/nf_conntrack.h

@@ -346,6 +346,13 @@ nf_ct_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info info)
 	skb_set_nfct(skb, (unsigned long)ct | info);
 }
 
+extern unsigned int nf_conntrack_net_id;
+
+static inline struct nf_conntrack_net *nf_ct_pernet(const struct net *net)
+{
+	return net_generic(net, nf_conntrack_net_id);
+}
+
 #define NF_CT_STAT_INC(net, count)	  __this_cpu_inc((net)->ct.stat->count)
 #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count)
 #define NF_CT_STAT_ADD_ATOMIC(net, count, v) this_cpu_add((net)->ct.stat->count, (v))

include/net/netfilter/nf_flow_table.h

@@ -177,6 +177,8 @@ struct flow_offload {
 #define NF_FLOW_TIMEOUT (30 * HZ)
 #define nf_flowtable_time_stamp	(u32)jiffies
 
+unsigned long flow_offload_get_timeout(struct flow_offload *flow);
+
 static inline __s32 nf_flow_timeout_delta(unsigned int timeout)
 {
 	return (__s32)(timeout - nf_flowtable_time_stamp);

include/net/netns/conntrack.h

@@ -27,6 +27,10 @@ struct nf_tcp_net {
 	u8 tcp_loose;
 	u8 tcp_be_liberal;
 	u8 tcp_max_retrans;
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	unsigned int offload_timeout;
+	unsigned int offload_pickup;
+#endif
 };
 
 enum udp_conntrack {
@@ -37,6 +41,10 @@ enum udp_conntrack {
 
 struct nf_udp_net {
 	unsigned int timeouts[UDP_CT_MAX];
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	unsigned int offload_timeout;
+	unsigned int offload_pickup;
+#endif
 };
 
 struct nf_icmp_net {

include/uapi/linux/netfilter/nfnetlink.h

@@ -60,7 +60,8 @@ struct nfgenmsg {
 #define NFNL_SUBSYS_CTHELPER		9
 #define NFNL_SUBSYS_NFTABLES		10
 #define NFNL_SUBSYS_NFT_COMPAT		11
-#define NFNL_SUBSYS_COUNT		12
+#define NFNL_SUBSYS_HOOK		12
+#define NFNL_SUBSYS_COUNT		13
 
 /* Reserved control nfnetlink messages */
 #define NFNL_MSG_BATCH_BEGIN		NLMSG_MIN_TYPE

include/uapi/linux/netfilter/nfnetlink_hook.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _NFNL_HOOK_H_
+#define _NFNL_HOOK_H_
+
+enum nfnl_hook_msg_types {
+	NFNL_MSG_HOOK_GET,
+	NFNL_MSG_HOOK_MAX,
+};
+
+/**
+ * enum nfnl_hook_attributes - netfilter hook netlink attributes
+ *
+ * @NFNLA_HOOK_HOOKNUM: netfilter hook number (NLA_U32)
+ * @NFNLA_HOOK_PRIORITY: netfilter hook priority (NLA_U32)
+ * @NFNLA_HOOK_DEV: netdevice name (NLA_STRING)
+ * @NFNLA_HOOK_FUNCTION_NAME: hook function name (NLA_STRING)
+ * @NFNLA_HOOK_MODULE_NAME: kernel module that registered this hook (NLA_STRING)
+ * @NFNLA_HOOK_CHAIN_INFO: basechain hook metadata (NLA_NESTED)
+ */
+enum nfnl_hook_attributes {
+	NFNLA_HOOK_UNSPEC,
+	NFNLA_HOOK_HOOKNUM,
+	NFNLA_HOOK_PRIORITY,
+	NFNLA_HOOK_DEV,
+	NFNLA_HOOK_FUNCTION_NAME,
+	NFNLA_HOOK_MODULE_NAME,
+	NFNLA_HOOK_CHAIN_INFO,
+	__NFNLA_HOOK_MAX
+};
+#define NFNLA_HOOK_MAX		(__NFNLA_HOOK_MAX - 1)
+
+/**
+ * enum nfnl_hook_chain_info_attributes - chain description
+ *
+ * NFNLA_HOOK_INFO_DESC: nft chain and table name (enum nft_table_attributes) (NLA_NESTED)
+ * NFNLA_HOOK_INFO_TYPE: chain type (enum nfnl_hook_chaintype) (NLA_U32)
+ */
+enum nfnl_hook_chain_info_attributes {
+	NFNLA_HOOK_INFO_UNSPEC,
+	NFNLA_HOOK_INFO_DESC,
+	NFNLA_HOOK_INFO_TYPE,
+	__NFNLA_HOOK_INFO_MAX,
+};
+#define NFNLA_HOOK_INFO_MAX (__NFNLA_HOOK_INFO_MAX - 1)
+
+/**
+ * enum nfnl_hook_chaintype - chain type
+ *
+ * @NFNL_HOOK_TYPE_NFTABLES nf_tables base chain
+ */
+enum nfnl_hook_chaintype {
+	NFNL_HOOK_TYPE_NFTABLES = 0x1,
+};
+
+#endif /* _NFNL_HOOK_H */

net/netfilter/Kconfig

@@ -19,6 +19,16 @@ config NETFILTER_FAMILY_BRIDGE
 config NETFILTER_FAMILY_ARP
 	bool
 
+config NETFILTER_NETLINK_HOOK
+	tristate "Netfilter base hook dump support"
+	depends on NETFILTER_ADVANCED
+	depends on NF_TABLES
+	select NETFILTER_NETLINK
+	help
+	  If this option is enabled, the kernel will include support
+	  to list the base netfilter hooks via NFNETLINK.
+	  This is helpful for debugging.
+
 config NETFILTER_NETLINK_ACCT
 	tristate "Netfilter NFACCT over NFNETLINK interface"
 	depends on NETFILTER_ADVANCED

net/netfilter/Makefile

@@ -22,6 +22,7 @@ obj-$(CONFIG_NETFILTER_NETLINK_ACCT) += nfnetlink_acct.o
 obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += nfnetlink_queue.o
 obj-$(CONFIG_NETFILTER_NETLINK_LOG) += nfnetlink_log.o
 obj-$(CONFIG_NETFILTER_NETLINK_OSF) += nfnetlink_osf.o
+obj-$(CONFIG_NETFILTER_NETLINK_HOOK) += nfnetlink_hook.o
 
 # connection tracking
 obj-$(CONFIG_NF_CONNTRACK) += nf_conntrack.o

net/netfilter/nf_conntrack_core.c

@@ -55,8 +55,6 @@
 
 #include "nf_internals.h"
 
-extern unsigned int nf_conntrack_net_id;
-
 __cacheline_aligned_in_smp spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS];
 EXPORT_SYMBOL_GPL(nf_conntrack_locks);
 
@@ -87,8 +85,6 @@ static __read_mostly bool nf_conntrack_locks_all;
 
 static struct conntrack_gc_work conntrack_gc_work;
 
-extern unsigned int nf_conntrack_net_id;
-
 void nf_conntrack_lock(spinlock_t *lock) __acquires(lock)
 {
 	/* 1) Acquire the lock */
@@ -1404,7 +1400,7 @@ static void gc_worker(struct work_struct *work)
 				continue;
 
 			net = nf_ct_net(tmp);
-			cnet = net_generic(net, nf_conntrack_net_id);
+			cnet = nf_ct_pernet(net);
 			if (atomic_read(&cnet->count) < nf_conntrack_max95)
 				continue;
 
@@ -1484,7 +1480,7 @@ __nf_conntrack_alloc(struct net *net,
 		     const struct nf_conntrack_tuple *repl,
 		     gfp_t gfp, u32 hash)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	unsigned int ct_count;
 	struct nf_conn *ct;
 
@@ -1556,7 +1552,7 @@ void nf_conntrack_free(struct nf_conn *ct)
 
 	nf_ct_ext_destroy(ct);
 	kmem_cache_free(nf_conntrack_cachep, ct);
-	cnet = net_generic(net, nf_conntrack_net_id);
+	cnet = nf_ct_pernet(net);
 
 	smp_mb__before_atomic();
 	atomic_dec(&cnet->count);
@@ -1614,7 +1610,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 			     GFP_ATOMIC);
 
 	local_bh_disable();
-	cnet = net_generic(net, nf_conntrack_net_id);
+	cnet = nf_ct_pernet(net);
 	if (cnet->expect_count) {
 		spin_lock(&nf_conntrack_expect_lock);
 		exp = nf_ct_find_expectation(net, zone, tuple);
@@ -2317,7 +2313,7 @@ __nf_ct_unconfirmed_destroy(struct net *net)
 
 void nf_ct_unconfirmed_destroy(struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	might_sleep();
 
@@ -2333,7 +2329,7 @@ void nf_ct_iterate_cleanup_net(struct net *net,
 			       int (*iter)(struct nf_conn *i, void *data),
 			       void *data, u32 portid, int report)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	struct iter_data d;
 
 	might_sleep();
@@ -2367,7 +2363,7 @@ nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data)
 
 	down_read(&net_rwsem);
 	for_each_net(net) {
-		struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+		struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 		if (atomic_read(&cnet->count) == 0)
 			continue;
@@ -2449,7 +2445,7 @@ void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list)
 i_see_dead_people:
 	busy = 0;
 	list_for_each_entry(net, net_exit_list, exit_list) {
-		struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+		struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 		nf_ct_iterate_cleanup(kill_all, net, 0, 0);
 		if (atomic_read(&cnet->count) != 0)
@@ -2733,7 +2729,7 @@ void nf_conntrack_init_end(void)
 
 int nf_conntrack_init_net(struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	int ret = -ENOMEM;
 	int cpu;
 

net/netfilter/nf_conntrack_ecache.c

@@ -27,8 +27,6 @@
 #include <net/netfilter/nf_conntrack_ecache.h>
 #include <net/netfilter/nf_conntrack_extend.h>
 
-extern unsigned int nf_conntrack_net_id;
-
 static DEFINE_MUTEX(nf_ct_ecache_mutex);
 
 #define ECACHE_RETRY_WAIT (HZ/10)
@@ -348,7 +346,7 @@ 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 = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	if (state == NFCT_ECACHE_DESTROY_FAIL &&
 	    !delayed_work_pending(&cnet->ecache_dwork)) {
@@ -371,7 +369,7 @@ static const struct nf_ct_ext_type event_extend = {
 
 void nf_conntrack_ecache_pernet_init(struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	net->ct.sysctl_events = nf_ct_events;
 	cnet->ct_net = &net->ct;
@@ -380,7 +378,7 @@ void nf_conntrack_ecache_pernet_init(struct net *net)
 
 void nf_conntrack_ecache_pernet_fini(struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	cancel_delayed_work_sync(&cnet->ecache_dwork);
 }

net/netfilter/nf_conntrack_expect.c

@@ -43,8 +43,6 @@ unsigned int nf_ct_expect_max __read_mostly;
 static struct kmem_cache *nf_ct_expect_cachep __read_mostly;
 static unsigned int nf_ct_expect_hashrnd __read_mostly;
 
-extern unsigned int nf_conntrack_net_id;
-
 /* nf_conntrack_expect helper functions */
 void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
 				u32 portid, int report)
@@ -58,7 +56,7 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
 
 	hlist_del_rcu(&exp->hnode);
 
-	cnet = net_generic(net, nf_conntrack_net_id);
+	cnet = nf_ct_pernet(net);
 	cnet->expect_count--;
 
 	hlist_del_rcu(&exp->lnode);
@@ -123,7 +121,7 @@ __nf_ct_expect_find(struct net *net,
 		    const struct nf_conntrack_zone *zone,
 		    const struct nf_conntrack_tuple *tuple)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	struct nf_conntrack_expect *i;
 	unsigned int h;
 
@@ -164,7 +162,7 @@ nf_ct_find_expectation(struct net *net,
 		       const struct nf_conntrack_zone *zone,
 		       const struct nf_conntrack_tuple *tuple)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	struct nf_conntrack_expect *i, *exp = NULL;
 	unsigned int h;
 
@@ -397,7 +395,7 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp)
 	master_help->expecting[exp->class]++;
 
 	hlist_add_head_rcu(&exp->hnode, &nf_ct_expect_hash[h]);
-	cnet = net_generic(net, nf_conntrack_net_id);
+	cnet = nf_ct_pernet(net);
 	cnet->expect_count++;
 
 	NF_CT_STAT_INC(net, expect_create);
@@ -468,7 +466,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect,
 		}
 	}
 
-	cnet = net_generic(net, nf_conntrack_net_id);
+	cnet = nf_ct_pernet(net);
 	if (cnet->expect_count >= nf_ct_expect_max) {
 		net_warn_ratelimited("nf_conntrack: expectation table full\n");
 		ret = -EMFILE;

net/netfilter/nf_conntrack_helper.c

@@ -43,8 +43,6 @@ MODULE_PARM_DESC(nf_conntrack_helper,
 static DEFINE_MUTEX(nf_ct_nat_helpers_mutex);
 static struct list_head nf_ct_nat_helpers __read_mostly;
 
-extern unsigned int nf_conntrack_net_id;
-
 /* Stupid hash, but collision free for the default registrations of the
  * helpers currently in the kernel. */
 static unsigned int helper_hash(const struct nf_conntrack_tuple *tuple)
@@ -214,7 +212,7 @@ EXPORT_SYMBOL_GPL(nf_ct_helper_ext_add);
 static struct nf_conntrack_helper *
 nf_ct_lookup_helper(struct nf_conn *ct, struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	if (!cnet->sysctl_auto_assign_helper) {
 		if (cnet->auto_assign_helper_warned)
@@ -560,7 +558,7 @@ static const struct nf_ct_ext_type helper_extend = {
 
 void nf_conntrack_helper_pernet_init(struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	cnet->sysctl_auto_assign_helper = nf_ct_auto_assign_helper;
 }

net/netfilter/nf_conntrack_netlink.c

@@ -1528,7 +1528,7 @@ static int ctnetlink_del_conntrack(struct sk_buff *skb,
 				   const struct nfnl_info *info,
 				   const struct nlattr * const cda[])
 {
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
+	u8 family = info->nfmsg->nfgen_family;
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_zone zone;
@@ -1541,12 +1541,12 @@ static int ctnetlink_del_conntrack(struct sk_buff *skb,
 
 	if (cda[CTA_TUPLE_ORIG])
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG,
-					    nfmsg->nfgen_family, &zone);
+					    family, &zone);
 	else if (cda[CTA_TUPLE_REPLY])
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY,
-					    nfmsg->nfgen_family, &zone);
+					    family, &zone);
 	else {
-		u_int8_t u3 = nfmsg->version ? nfmsg->nfgen_family : AF_UNSPEC;
+		u_int8_t u3 = info->nfmsg->version ? family : AF_UNSPEC;
 
 		return ctnetlink_flush_conntrack(info->net, cda,
 						 NETLINK_CB(skb).portid,
@@ -1586,8 +1586,7 @@ static int ctnetlink_get_conntrack(struct sk_buff *skb,
 				   const struct nfnl_info *info,
 				   const struct nlattr * const cda[])
 {
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u_int8_t u3 = nfmsg->nfgen_family;
+	u_int8_t u3 = info->nfmsg->nfgen_family;
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_zone zone;
@@ -2363,10 +2362,9 @@ static int ctnetlink_new_conntrack(struct sk_buff *skb,
 				   const struct nfnl_info *info,
 				   const struct nlattr * const cda[])
 {
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct nf_conntrack_tuple otuple, rtuple;
 	struct nf_conntrack_tuple_hash *h = NULL;
-	u_int8_t u3 = nfmsg->nfgen_family;
+	u_int8_t u3 = info->nfmsg->nfgen_family;
 	struct nf_conntrack_zone zone;
 	struct nf_conn *ct;
 	int err;
@@ -3259,8 +3257,7 @@ static int ctnetlink_get_expect(struct sk_buff *skb,
 				const struct nfnl_info *info,
 				const struct nlattr * const cda[])
 {
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u_int8_t u3 = nfmsg->nfgen_family;
+	u_int8_t u3 = info->nfmsg->nfgen_family;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_expect *exp;
 	struct nf_conntrack_zone zone;
@@ -3349,8 +3346,7 @@ static int ctnetlink_del_expect(struct sk_buff *skb,
 				const struct nfnl_info *info,
 				const struct nlattr * const cda[])
 {
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u_int8_t u3 = nfmsg->nfgen_family;
+	u_int8_t u3 = info->nfmsg->nfgen_family;
 	struct nf_conntrack_expect *exp;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_zone zone;
@@ -3601,8 +3597,7 @@ static int ctnetlink_new_expect(struct sk_buff *skb,
 				const struct nfnl_info *info,
 				const struct nlattr * const cda[])
 {
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u_int8_t u3 = nfmsg->nfgen_family;
+	u_int8_t u3 = info->nfmsg->nfgen_family;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_expect *exp;
 	struct nf_conntrack_zone zone;

net/netfilter/nf_conntrack_proto.c

@@ -42,8 +42,6 @@
 #include <net/ipv6.h>
 #include <net/inet_frag.h>
 
-extern unsigned int nf_conntrack_net_id;
-
 static DEFINE_MUTEX(nf_ct_proto_mutex);
 
 #ifdef CONFIG_SYSCTL
@@ -446,7 +444,7 @@ static struct nf_ct_bridge_info *nf_ct_bridge_info;
 
 static int nf_ct_netns_do_get(struct net *net, u8 nfproto)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	bool fixup_needed = false, retry = true;
 	int err = 0;
 retry:
@@ -531,7 +529,7 @@ static int nf_ct_netns_do_get(struct net *net, u8 nfproto)
 
 static void nf_ct_netns_do_put(struct net *net, u8 nfproto)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	mutex_lock(&nf_ct_proto_mutex);
 	switch (nfproto) {

net/netfilter/nf_conntrack_proto_tcp.c

@@ -1441,6 +1441,11 @@ void nf_conntrack_tcp_init_net(struct net *net)
 	 * will be started.
 	 */
 	tn->tcp_max_retrans = 3;
+
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	tn->offload_timeout = 30 * HZ;
+	tn->offload_pickup = 120 * HZ;
+#endif
 }
 
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp =

net/netfilter/nf_conntrack_proto_udp.c

@@ -270,6 +270,11 @@ void nf_conntrack_udp_init_net(struct net *net)
 
 	for (i = 0; i < UDP_CT_MAX; i++)
 		un->timeouts[i] = udp_timeouts[i];
+
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	un->offload_timeout = 30 * HZ;
+	un->offload_pickup = 30 * HZ;
+#endif
 }
 
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp =

net/netfilter/nf_conntrack_standalone.c

@@ -512,9 +512,7 @@ static void nf_conntrack_standalone_fini_proc(struct net *net)
 
 u32 nf_conntrack_count(const struct net *net)
 {
-	const struct nf_conntrack_net *cnet;
-
-	cnet = net_generic(net, nf_conntrack_net_id);
+	const struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	return atomic_read(&cnet->count);
 }
@@ -575,11 +573,19 @@ enum nf_ct_sysctl_index {
 	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_RETRANS,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK,
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD,
+	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP,
+#endif
 	NF_SYSCTL_CT_PROTO_TCP_LOOSE,
 	NF_SYSCTL_CT_PROTO_TCP_LIBERAL,
 	NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_UDP,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM,
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD,
+	NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP,
+#endif
 	NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6,
 #ifdef CONFIG_NF_CT_PROTO_SCTP
@@ -762,6 +768,20 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD] = {
+		.procname	= "nf_flowtable_tcp_timeout",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP] = {
+		.procname	= "nf_flowtable_tcp_pickup",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+#endif
 	[NF_SYSCTL_CT_PROTO_TCP_LOOSE] = {
 		.procname	= "nf_conntrack_tcp_loose",
 		.maxlen		= sizeof(u8),
@@ -796,6 +816,20 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
+#if IS_ENABLED(CONFIG_NFT_FLOW_OFFLOAD)
+	[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD] = {
+		.procname	= "nf_flowtable_udp_timeout",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP] = {
+		.procname	= "nf_flowtable_udp_pickup",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+#endif
 	[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP] = {
 		.procname	= "nf_conntrack_icmp_timeout",
 		.maxlen		= sizeof(unsigned int),
@@ -971,6 +1005,12 @@ static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net,
 	XASSIGN(LIBERAL, &tn->tcp_be_liberal);
 	XASSIGN(MAX_RETRANS, &tn->tcp_max_retrans);
 #undef XASSIGN
+
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD].data = &tn->offload_timeout;
+	table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP].data = &tn->offload_pickup;
+#endif
+
 }
 
 static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net,
@@ -1032,7 +1072,7 @@ static void nf_conntrack_standalone_init_gre_sysctl(struct net *net,
 
 static int nf_conntrack_standalone_init_sysctl(struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	struct nf_udp_net *un = nf_udp_pernet(net);
 	struct ctl_table *table;
 
@@ -1059,6 +1099,10 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
 	table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6].data = &nf_icmpv6_pernet(net)->timeout;
 	table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP].data = &un->timeouts[UDP_CT_UNREPLIED];
 	table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM].data = &un->timeouts[UDP_CT_REPLIED];
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD].data = &un->offload_timeout;
+	table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP].data = &un->offload_pickup;
+#endif
 
 	nf_conntrack_standalone_init_tcp_sysctl(net, table);
 	nf_conntrack_standalone_init_sctp_sysctl(net, table);
@@ -1085,7 +1129,7 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
 
 static void nf_conntrack_standalone_fini_sysctl(struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	struct ctl_table *table;
 
 	table = cnet->sysctl_header->ctl_table_arg;

net/netfilter/nf_flow_table_core.c

@@ -178,12 +178,10 @@ 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_timeout(struct nf_conn *ct)
 {
 	const struct nf_conntrack_l4proto *l4proto;
+	struct net *net = nf_ct_net(ct);
 	int l4num = nf_ct_protonum(ct);
 	unsigned int timeout;
 
@@ -191,12 +189,17 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
 	if (!l4proto)
 		return;
 
-	if (l4num == IPPROTO_TCP)
-		timeout = NF_FLOWTABLE_TCP_PICKUP_TIMEOUT;
-	else if (l4num == IPPROTO_UDP)
-		timeout = NF_FLOWTABLE_UDP_PICKUP_TIMEOUT;
-	else
+	if (l4num == IPPROTO_TCP) {
+		struct nf_tcp_net *tn = nf_tcp_pernet(net);
+
+		timeout = tn->offload_pickup;
+	} else if (l4num == IPPROTO_UDP) {
+		struct nf_udp_net *tn = nf_udp_pernet(net);
+
+		timeout = tn->offload_pickup;
+	} else {
 		return;
+	}
 
 	if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout)
 		ct->timeout = nfct_time_stamp + timeout;
@@ -268,11 +271,35 @@ static const struct rhashtable_params nf_flow_offload_rhash_params = {
 	.automatic_shrinking	= true,
 };
 
+unsigned long flow_offload_get_timeout(struct flow_offload *flow)
+{
+	const struct nf_conntrack_l4proto *l4proto;
+	unsigned long timeout = NF_FLOW_TIMEOUT;
+	struct net *net = nf_ct_net(flow->ct);
+	int l4num = nf_ct_protonum(flow->ct);
+
+	l4proto = nf_ct_l4proto_find(l4num);
+	if (!l4proto)
+		return timeout;
+
+	if (l4num == IPPROTO_TCP) {
+		struct nf_tcp_net *tn = nf_tcp_pernet(net);
+
+		timeout = tn->offload_timeout;
+	} else if (l4num == IPPROTO_UDP) {
+		struct nf_udp_net *tn = nf_udp_pernet(net);
+
+		timeout = tn->offload_timeout;
+	}
+
+	return timeout;
+}
+
 int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
 {
 	int err;
 
-	flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT;
+	flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow);
 
 	err = rhashtable_insert_fast(&flow_table->rhashtable,
 				     &flow->tuplehash[0].node,
@@ -304,7 +331,7 @@ EXPORT_SYMBOL_GPL(flow_offload_add);
 void flow_offload_refresh(struct nf_flowtable *flow_table,
 			  struct flow_offload *flow)
 {
-	flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT;
+	flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow);
 
 	if (likely(!nf_flowtable_hw_offload(flow_table)))
 		return;

net/netfilter/nf_flow_table_offload.c

@@ -937,7 +937,7 @@ static void flow_offload_work_stats(struct flow_offload_work *offload)
 
 	lastused = max_t(u64, stats[0].lastused, stats[1].lastused);
 	offload->flow->timeout = max_t(u64, offload->flow->timeout,
-				       lastused + NF_FLOW_TIMEOUT);
+				       lastused + flow_offload_get_timeout(offload->flow));
 
 	if (offload->flowtable->flags & NF_FLOWTABLE_COUNTER) {
 		if (stats[0].pkts)
@@ -1041,7 +1041,7 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable,
 	__s32 delta;
 
 	delta = nf_flow_timeout_delta(flow->timeout);
-	if ((delta >= (9 * NF_FLOW_TIMEOUT) / 10))
+	if ((delta >= (9 * flow_offload_get_timeout(flow)) / 10))
 		return;
 
 	offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_STATS);

net/netfilter/nfnetlink.c

@@ -68,6 +68,7 @@ static const char *const nfnl_lockdep_names[NFNL_SUBSYS_COUNT] = {
 	[NFNL_SUBSYS_CTHELPER] = "nfnl_subsys_cthelper",
 	[NFNL_SUBSYS_NFTABLES] = "nfnl_subsys_nftables",
 	[NFNL_SUBSYS_NFT_COMPAT] = "nfnl_subsys_nftcompat",
+	[NFNL_SUBSYS_HOOK] = "nfnl_subsys_hook",
 };
 
 static const int nfnl_group2type[NFNLGRP_MAX+1] = {
@@ -256,6 +257,7 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 			.net	= net,
 			.sk	= nfnlnet->nfnl,
 			.nlh	= nlh,
+			.nfmsg	= nlmsg_data(nlh),
 			.extack	= extack,
 		};
 
@@ -491,6 +493,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
 				.net	= net,
 				.sk	= nfnlnet->nfnl,
 				.nlh	= nlh,
+				.nfmsg	= nlmsg_data(nlh),
 				.extack	= &extack,
 			};
 

net/netfilter/nfnetlink_hook.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021 Red Hat GmbH
+ *
+ * Author: Florian Westphal <fw@strlen.de>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+#include <linux/netlink.h>
+#include <linux/slab.h>
+
+#include <linux/netfilter.h>
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_hook.h>
+
+#include <net/netfilter/nf_tables.h>
+#include <net/sock.h>
+
+static const struct nla_policy nfnl_hook_nla_policy[NFNLA_HOOK_MAX + 1] = {
+	[NFNLA_HOOK_HOOKNUM]	= { .type = NLA_U32 },
+	[NFNLA_HOOK_PRIORITY]	= { .type = NLA_U32 },
+	[NFNLA_HOOK_DEV]	= { .type = NLA_STRING,
+				    .len = IFNAMSIZ - 1 },
+	[NFNLA_HOOK_FUNCTION_NAME] = { .type = NLA_NUL_STRING,
+				       .len = KSYM_NAME_LEN, },
+	[NFNLA_HOOK_MODULE_NAME] = { .type = NLA_NUL_STRING,
+				     .len = MODULE_NAME_LEN, },
+	[NFNLA_HOOK_CHAIN_INFO] = { .type = NLA_NESTED, },
+};
+
+static int nf_netlink_dump_start_rcu(struct sock *nlsk, struct sk_buff *skb,
+				     const struct nlmsghdr *nlh,
+				     struct netlink_dump_control *c)
+{
+	int err;
+
+	if (!try_module_get(THIS_MODULE))
+		return -EINVAL;
+
+	rcu_read_unlock();
+	err = netlink_dump_start(nlsk, skb, nlh, c);
+	rcu_read_lock();
+	module_put(THIS_MODULE);
+
+	return err;
+}
+
+struct nfnl_dump_hook_data {
+	char devname[IFNAMSIZ];
+	unsigned long headv;
+	u8 hook;
+};
+
+static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb,
+					const struct nfnl_dump_hook_data *ctx,
+					unsigned int seq,
+					const struct nf_hook_ops *ops)
+{
+	struct net *net = sock_net(nlskb->sk);
+	struct nlattr *nest, *nest2;
+	struct nft_chain *chain;
+	int ret = 0;
+
+	if (ops->hook_ops_type != NF_HOOK_OP_NF_TABLES)
+		return 0;
+
+	chain = ops->priv;
+	if (WARN_ON_ONCE(!chain))
+		return 0;
+
+	if (!nft_is_active(net, chain))
+		return 0;
+
+	nest = nla_nest_start(nlskb, NFNLA_HOOK_CHAIN_INFO);
+	if (!nest)
+		return -EMSGSIZE;
+
+	ret = nla_put_be32(nlskb, NFNLA_HOOK_INFO_TYPE,
+			   htonl(NFNL_HOOK_TYPE_NFTABLES));
+	if (ret)
+		goto cancel_nest;
+
+	nest2 = nla_nest_start(nlskb, NFNLA_HOOK_INFO_DESC);
+	if (!nest2)
+		goto cancel_nest;
+
+	ret = nla_put_string(nlskb, NFTA_CHAIN_TABLE, chain->table->name);
+	if (ret)
+		goto cancel_nest;
+
+	ret = nla_put_string(nlskb, NFTA_CHAIN_NAME, chain->name);
+	if (ret)
+		goto cancel_nest;
+
+	nla_nest_end(nlskb, nest2);
+	nla_nest_end(nlskb, nest);
+	return ret;
+
+cancel_nest:
+	nla_nest_cancel(nlskb, nest);
+	return -EMSGSIZE;
+}
+
+static int nfnl_hook_dump_one(struct sk_buff *nlskb,
+			      const struct nfnl_dump_hook_data *ctx,
+			      const struct nf_hook_ops *ops,
+			      unsigned int seq)
+{
+	u16 event = nfnl_msg_type(NFNL_SUBSYS_HOOK, NFNL_MSG_HOOK_GET);
+	unsigned int portid = NETLINK_CB(nlskb).portid;
+	struct nlmsghdr *nlh;
+	int ret = -EMSGSIZE;
+#ifdef CONFIG_KALLSYMS
+	char sym[KSYM_SYMBOL_LEN];
+	char *module_name;
+#endif
+	nlh = nfnl_msg_put(nlskb, portid, seq, event,
+			   NLM_F_MULTI, ops->pf, NFNETLINK_V0, 0);
+	if (!nlh)
+		goto nla_put_failure;
+
+#ifdef CONFIG_KALLSYMS
+	ret = snprintf(sym, sizeof(sym), "%ps", ops->hook);
+	if (ret < 0 || ret > (int)sizeof(sym))
+		goto nla_put_failure;
+
+	module_name = strstr(sym, " [");
+	if (module_name) {
+		char *end;
+
+		module_name += 2;
+		end = strchr(module_name, ']');
+		if (end) {
+			*end = 0;
+
+			ret = nla_put_string(nlskb, NFNLA_HOOK_MODULE_NAME, module_name);
+			if (ret)
+				goto nla_put_failure;
+		}
+	}
+
+	ret = nla_put_string(nlskb, NFNLA_HOOK_FUNCTION_NAME, sym);
+	if (ret)
+		goto nla_put_failure;
+#endif
+
+	ret = nla_put_be32(nlskb, NFNLA_HOOK_HOOKNUM, htonl(ops->hooknum));
+	if (ret)
+		goto nla_put_failure;
+
+	ret = nla_put_be32(nlskb, NFNLA_HOOK_PRIORITY, htonl(ops->priority));
+	if (ret)
+		goto nla_put_failure;
+
+	ret = nfnl_hook_put_nft_chain_info(nlskb, ctx, seq, ops);
+	if (ret)
+		goto nla_put_failure;
+
+	nlmsg_end(nlskb, nlh);
+	return 0;
+nla_put_failure:
+	nlmsg_trim(nlskb, nlh);
+	return ret;
+}
+
+static const struct nf_hook_entries *
+nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev)
+{
+	const struct nf_hook_entries *hook_head = NULL;
+	struct net_device *netdev;
+
+	switch (pf) {
+	case NFPROTO_IPV4:
+		if (hook >= ARRAY_SIZE(net->nf.hooks_ipv4))
+			return ERR_PTR(-EINVAL);
+		hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]);
+		break;
+	case NFPROTO_IPV6:
+		if (hook >= ARRAY_SIZE(net->nf.hooks_ipv6))
+			return ERR_PTR(-EINVAL);
+		hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]);
+		break;
+	case NFPROTO_ARP:
+#ifdef CONFIG_NETFILTER_FAMILY_ARP
+		if (hook >= ARRAY_SIZE(net->nf.hooks_arp))
+			return ERR_PTR(-EINVAL);
+		hook_head = rcu_dereference(net->nf.hooks_arp[hook]);
+#endif
+		break;
+	case NFPROTO_BRIDGE:
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+		if (hook >= ARRAY_SIZE(net->nf.hooks_bridge))
+			return ERR_PTR(-EINVAL);
+		hook_head = rcu_dereference(net->nf.hooks_bridge[hook]);
+#endif
+		break;
+#if IS_ENABLED(CONFIG_DECNET)
+	case NFPROTO_DECNET:
+		if (hook >= ARRAY_SIZE(net->nf.hooks_decnet))
+			return ERR_PTR(-EINVAL);
+		hook_head = rcu_dereference(net->nf.hooks_decnet[hook]);
+		break;
+#endif
+#ifdef CONFIG_NETFILTER_INGRESS
+	case NFPROTO_NETDEV:
+		if (hook != NF_NETDEV_INGRESS)
+			return ERR_PTR(-EOPNOTSUPP);
+
+		if (!dev)
+			return ERR_PTR(-ENODEV);
+
+		netdev = dev_get_by_name_rcu(net, dev);
+		if (!netdev)
+			return ERR_PTR(-ENODEV);
+
+		return rcu_dereference(netdev->nf_hooks_ingress);
+#endif
+	default:
+		return ERR_PTR(-EPROTONOSUPPORT);
+	}
+
+	return hook_head;
+}
+
+static int nfnl_hook_dump(struct sk_buff *nlskb,
+			  struct netlink_callback *cb)
+{
+	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+	struct nfnl_dump_hook_data *ctx = cb->data;
+	int err, family = nfmsg->nfgen_family;
+	struct net *net = sock_net(nlskb->sk);
+	struct nf_hook_ops * const *ops;
+	const struct nf_hook_entries *e;
+	unsigned int i = cb->args[0];
+
+	rcu_read_lock();
+
+	e = nfnl_hook_entries_head(family, ctx->hook, net, ctx->devname);
+	if (!e)
+		goto done;
+
+	if (IS_ERR(e)) {
+		cb->seq++;
+		goto done;
+	}
+
+	if ((unsigned long)e != ctx->headv || i >= e->num_hook_entries)
+		cb->seq++;
+
+	ops = nf_hook_entries_get_hook_ops(e);
+
+	for (; i < e->num_hook_entries; i++) {
+		err = nfnl_hook_dump_one(nlskb, ctx, ops[i], cb->seq);
+		if (err)
+			break;
+	}
+
+done:
+	nl_dump_check_consistent(cb, nlmsg_hdr(nlskb));
+	rcu_read_unlock();
+	cb->args[0] = i;
+	return nlskb->len;
+}
+
+static int nfnl_hook_dump_start(struct netlink_callback *cb)
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+	const struct nlattr * const *nla = cb->data;
+	struct nfnl_dump_hook_data *ctx = NULL;
+	struct net *net = sock_net(cb->skb->sk);
+	u8 family = nfmsg->nfgen_family;
+	char name[IFNAMSIZ] = "";
+	const void *head;
+	u32 hooknum;
+
+	hooknum = ntohl(nla_get_be32(nla[NFNLA_HOOK_HOOKNUM]));
+	if (hooknum > 255)
+		return -EINVAL;
+
+	if (family == NFPROTO_NETDEV) {
+		if (!nla[NFNLA_HOOK_DEV])
+			return -EINVAL;
+
+		nla_strscpy(name, nla[NFNLA_HOOK_DEV], sizeof(name));
+	}
+
+	rcu_read_lock();
+	/* Not dereferenced; for consistency check only */
+	head = nfnl_hook_entries_head(family, hooknum, net, name);
+	rcu_read_unlock();
+
+	if (head && IS_ERR(head))
+		return PTR_ERR(head);
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	strscpy(ctx->devname, name, sizeof(ctx->devname));
+	ctx->headv = (unsigned long)head;
+	ctx->hook = hooknum;
+
+	cb->seq = 1;
+	cb->data = ctx;
+
+	return 0;
+}
+
+static int nfnl_hook_dump_stop(struct netlink_callback *cb)
+{
+	kfree(cb->data);
+	return 0;
+}
+
+static int nfnl_hook_get(struct sk_buff *skb,
+			 const struct nfnl_info *info,
+			 const struct nlattr * const nla[])
+{
+	if (!nla[NFNLA_HOOK_HOOKNUM])
+		return -EINVAL;
+
+	if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.start = nfnl_hook_dump_start,
+			.done = nfnl_hook_dump_stop,
+			.dump = nfnl_hook_dump,
+			.module = THIS_MODULE,
+			.data = (void *)nla,
+		};
+
+		return nf_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c);
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static const struct nfnl_callback nfnl_hook_cb[NFNL_MSG_HOOK_MAX] = {
+	[NFNL_MSG_HOOK_GET] = {
+		.call		= nfnl_hook_get,
+		.type		= NFNL_CB_RCU,
+		.attr_count	= NFNLA_HOOK_MAX,
+		.policy		= nfnl_hook_nla_policy
+	},
+};
+
+static const struct nfnetlink_subsystem nfhook_subsys = {
+	.name				= "nfhook",
+	.subsys_id			= NFNL_SUBSYS_HOOK,
+	.cb_count			= NFNL_MSG_HOOK_MAX,
+	.cb				= nfnl_hook_cb,
+};
+
+MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_HOOK);
+
+static int __init nfnetlink_hook_init(void)
+{
+	return nfnetlink_subsys_register(&nfhook_subsys);
+}
+
+static void __exit nfnetlink_hook_exit(void)
+{
+	nfnetlink_subsys_unregister(&nfhook_subsys);
+}
+
+module_init(nfnetlink_hook_init);
+module_exit(nfnetlink_hook_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
+MODULE_DESCRIPTION("nfnetlink_hook: list registered netfilter hooks");

net/netfilter/nfnetlink_log.c

@@ -871,15 +871,14 @@ static int nfulnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info,
 			      const struct nlattr * const nfula[])
 {
 	struct nfnl_log_net *log = nfnl_log_pernet(info->net);
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u_int16_t group_num = ntohs(nfmsg->res_id);
+	u_int16_t group_num = ntohs(info->nfmsg->res_id);
 	struct nfulnl_msg_config_cmd *cmd = NULL;
 	struct nfulnl_instance *inst;
 	u16 flags = 0;
 	int ret = 0;
 
 	if (nfula[NFULA_CFG_CMD]) {
-		u_int8_t pf = nfmsg->nfgen_family;
+		u_int8_t pf = info->nfmsg->nfgen_family;
 		cmd = nla_data(nfula[NFULA_CFG_CMD]);
 
 		/* Commands without queue context */

net/netfilter/nfnetlink_queue.c

@@ -1051,8 +1051,7 @@ static int nfqnl_recv_verdict_batch(struct sk_buff *skb,
 				    const struct nlattr * const nfqa[])
 {
 	struct nfnl_queue_net *q = nfnl_queue_pernet(info->net);
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u16 queue_num = ntohs(nfmsg->res_id);
+	u16 queue_num = ntohs(info->nfmsg->res_id);
 	struct nf_queue_entry *entry, *tmp;
 	struct nfqnl_msg_verdict_hdr *vhdr;
 	struct nfqnl_instance *queue;
@@ -1160,8 +1159,7 @@ static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info,
 			      const struct nlattr * const nfqa[])
 {
 	struct nfnl_queue_net *q = nfnl_queue_pernet(info->net);
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u_int16_t queue_num = ntohs(nfmsg->res_id);
+	u_int16_t queue_num = ntohs(info->nfmsg->res_id);
 	struct nfqnl_msg_verdict_hdr *vhdr;
 	enum ip_conntrack_info ctinfo;
 	struct nfqnl_instance *queue;
@@ -1243,8 +1241,7 @@ static int nfqnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info,
 			     const struct nlattr * const nfqa[])
 {
 	struct nfnl_queue_net *q = nfnl_queue_pernet(info->net);
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u_int16_t queue_num = ntohs(nfmsg->res_id);
+	u_int16_t queue_num = ntohs(info->nfmsg->res_id);
 	struct nfqnl_msg_config_cmd *cmd = NULL;
 	struct nfqnl_instance *queue;
 	__u32 flags = 0, mask = 0;

net/netfilter/nft_compat.c

@@ -625,7 +625,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb,
 			       const struct nfnl_info *info,
 			       const struct nlattr * const tb[])
 {
-	struct nfgenmsg *nfmsg;
+	u8 family = info->nfmsg->nfgen_family;
 	const char *name, *fmt;
 	struct sk_buff *skb2;
 	int ret = 0, target;
@@ -640,9 +640,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb,
 	rev = ntohl(nla_get_be32(tb[NFTA_COMPAT_REV]));
 	target = ntohl(nla_get_be32(tb[NFTA_COMPAT_TYPE]));
 
-	nfmsg = nlmsg_data(info->nlh);
-
-	switch(nfmsg->nfgen_family) {
+	switch(family) {
 	case AF_INET:
 		fmt = "ipt_%s";
 		break;
@@ -656,8 +654,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb,
 		fmt = "arpt_%s";
 		break;
 	default:
-		pr_err("nft_compat: unsupported protocol %d\n",
-			nfmsg->nfgen_family);
+		pr_err("nft_compat: unsupported protocol %d\n", family);
 		return -EINVAL;
 	}
 
@@ -665,9 +662,8 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb,
 		return -EINVAL;
 
 	rcu_read_unlock();
-	try_then_request_module(xt_find_revision(nfmsg->nfgen_family, name,
-						 rev, target, &ret),
-						 fmt, name);
+	try_then_request_module(xt_find_revision(family, name, rev, target, &ret),
+				fmt, name);
 	if (ret < 0)
 		goto out_put;
 
@@ -682,8 +678,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb,
 				  info->nlh->nlmsg_seq,
 				  NFNL_MSG_TYPE(info->nlh->nlmsg_type),
 				  NFNL_MSG_COMPAT_GET,
-				  nfmsg->nfgen_family,
-				  name, ret, target) <= 0) {
+				  family, name, ret, target) <= 0) {
 		kfree_skb(skb2);
 		goto out_put;
 	}

net/netfilter/nft_exthdr.c

@@ -327,7 +327,9 @@ static void nft_exthdr_sctp_eval(const struct nft_expr *expr,
 				break;
 
 			dest[priv->len / NFT_REG32_SIZE] = 0;
-			memcpy(dest, (char *)sch + priv->offset, priv->len);
+			if (skb_copy_bits(pkt->skb, offset + priv->offset,
+					  dest, priv->len) < 0)
+				break;
 			return;
 		}
 		offset += SCTP_PAD4(ntohs(sch->length));