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
to extend ctnetlink and the flowtable infrastructure:

1) Extend ctnetlink kernel side netlink dump filtering capabilities,
   from Romain Bellan.

2) Generalise the flowtable hook parser to take a hook list.

3) Pass a hook list to the flowtable hook registration/unregistration.

4) Add a helper function to release the flowtable hook list.

5) Update the flowtable event notifier to pass a flowtable hook list.

6) Allow users to add new devices to an existing flowtables.

7) Allow users to remove devices to an existing flowtables.

8) Allow for registering a flowtable with no initial devices.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/netfilter/nf_conntrack_l4proto.h

@@ -42,7 +42,8 @@ struct nf_conntrack_l4proto {
 	/* Calculate tuple nlattr size */
 	unsigned int (*nlattr_tuple_size)(void);
 	int (*nlattr_to_tuple)(struct nlattr *tb[],
-			       struct nf_conntrack_tuple *t);
+			       struct nf_conntrack_tuple *t,
+			       u_int32_t flags);
 	const struct nla_policy *nla_policy;
 
 	struct {
@@ -152,7 +153,8 @@ const struct nf_conntrack_l4proto *nf_ct_l4proto_find(u8 l4proto);
 int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb,
 			       const struct nf_conntrack_tuple *tuple);
 int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[],
-			       struct nf_conntrack_tuple *t);
+			       struct nf_conntrack_tuple *t,
+			       u_int32_t flags);
 unsigned int nf_ct_port_nlattr_tuple_size(void);
 extern const struct nla_policy nf_ct_port_nla_policy[];
 

include/net/netfilter/nf_tables.h

@@ -1002,6 +1002,7 @@ struct nft_stats {
 
 struct nft_hook {
 	struct list_head	list;
+	bool			inactive;
 	struct nf_hook_ops	ops;
 	struct rcu_head		rcu;
 };
@@ -1481,10 +1482,16 @@ struct nft_trans_obj {
 
 struct nft_trans_flowtable {
 	struct nft_flowtable		*flowtable;
+	bool				update;
+	struct list_head		hook_list;
 };
 
 #define nft_trans_flowtable(trans)	\
 	(((struct nft_trans_flowtable *)trans->data)->flowtable)
+#define nft_trans_flowtable_update(trans)	\
+	(((struct nft_trans_flowtable *)trans->data)->update)
+#define nft_trans_flowtable_hooks(trans)	\
+	(((struct nft_trans_flowtable *)trans->data)->hook_list)
 
 int __init nft_chain_filter_init(void);
 void nft_chain_filter_fini(void);

include/uapi/linux/netfilter/nfnetlink_conntrack.h

@@ -55,6 +55,7 @@ enum ctattr_type {
 	CTA_LABELS,
 	CTA_LABELS_MASK,
 	CTA_SYNPROXY,
+	CTA_FILTER,
 	__CTA_MAX
 };
 #define CTA_MAX (__CTA_MAX - 1)
@@ -276,4 +277,12 @@ enum ctattr_expect_stats {
 };
 #define CTA_STATS_EXP_MAX (__CTA_STATS_EXP_MAX - 1)
 
+enum ctattr_filter {
+	CTA_FILTER_UNSPEC,
+	CTA_FILTER_ORIG_FLAGS,
+	CTA_FILTER_REPLY_FLAGS,
+	__CTA_FILTER_MAX
+};
+#define CTA_FILTER_MAX (__CTA_FILTER_MAX - 1)
+
 #endif /* _IPCONNTRACK_NETLINK_H */

net/netfilter/nf_conntrack_core.c

@@ -1974,13 +1974,22 @@ const struct nla_policy nf_ct_port_nla_policy[CTA_PROTO_MAX+1] = {
 EXPORT_SYMBOL_GPL(nf_ct_port_nla_policy);
 
 int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[],
-			       struct nf_conntrack_tuple *t)
+			       struct nf_conntrack_tuple *t,
+			       u_int32_t flags)
 {
-	if (!tb[CTA_PROTO_SRC_PORT] || !tb[CTA_PROTO_DST_PORT])
-		return -EINVAL;
+	if (flags & CTA_FILTER_FLAG(CTA_PROTO_SRC_PORT)) {
+		if (!tb[CTA_PROTO_SRC_PORT])
+			return -EINVAL;
+
+		t->src.u.tcp.port = nla_get_be16(tb[CTA_PROTO_SRC_PORT]);
+	}
 
-	t->src.u.tcp.port = nla_get_be16(tb[CTA_PROTO_SRC_PORT]);
-	t->dst.u.tcp.port = nla_get_be16(tb[CTA_PROTO_DST_PORT]);
+	if (flags & CTA_FILTER_FLAG(CTA_PROTO_DST_PORT)) {
+		if (!tb[CTA_PROTO_DST_PORT])
+			return -EINVAL;
+
+		t->dst.u.tcp.port = nla_get_be16(tb[CTA_PROTO_DST_PORT]);
+	}
 
 	return 0;
 }

net/netfilter/nf_conntrack_netlink.c

@@ -54,6 +54,8 @@
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/nfnetlink_conntrack.h>
 
+#include "nf_internals.h"
+
 MODULE_LICENSE("GPL");
 
 static int ctnetlink_dump_tuples_proto(struct sk_buff *skb,
@@ -544,14 +546,16 @@ static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct)
 
 static int
 ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
-		    struct nf_conn *ct, bool extinfo)
+		    struct nf_conn *ct, bool extinfo, unsigned int flags)
 {
 	const struct nf_conntrack_zone *zone;
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
 	struct nlattr *nest_parms;
-	unsigned int flags = portid ? NLM_F_MULTI : 0, event;
+	unsigned int event;
 
+	if (portid)
+		flags |= NLM_F_MULTI;
 	event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_NEW);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
 	if (nlh == NULL)
@@ -847,17 +851,70 @@ static int ctnetlink_done(struct netlink_callback *cb)
 }
 
 struct ctnetlink_filter {
+	u_int32_t cta_flags;
 	u8 family;
+
+	u_int32_t orig_flags;
+	u_int32_t reply_flags;
+
+	struct nf_conntrack_tuple orig;
+	struct nf_conntrack_tuple reply;
+	struct nf_conntrack_zone zone;
+
 	struct {
 		u_int32_t val;
 		u_int32_t mask;
 	} mark;
 };
 
+static const struct nla_policy cta_filter_nla_policy[CTA_FILTER_MAX + 1] = {
+	[CTA_FILTER_ORIG_FLAGS]		= { .type = NLA_U32 },
+	[CTA_FILTER_REPLY_FLAGS]	= { .type = NLA_U32 },
+};
+
+static int ctnetlink_parse_filter(const struct nlattr *attr,
+				  struct ctnetlink_filter *filter)
+{
+	struct nlattr *tb[CTA_FILTER_MAX + 1];
+	int ret = 0;
+
+	ret = nla_parse_nested(tb, CTA_FILTER_MAX, attr, cta_filter_nla_policy,
+			       NULL);
+	if (ret)
+		return ret;
+
+	if (tb[CTA_FILTER_ORIG_FLAGS]) {
+		filter->orig_flags = nla_get_u32(tb[CTA_FILTER_ORIG_FLAGS]);
+		if (filter->orig_flags & ~CTA_FILTER_F_ALL)
+			return -EOPNOTSUPP;
+	}
+
+	if (tb[CTA_FILTER_REPLY_FLAGS]) {
+		filter->reply_flags = nla_get_u32(tb[CTA_FILTER_REPLY_FLAGS]);
+		if (filter->reply_flags & ~CTA_FILTER_F_ALL)
+			return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int ctnetlink_parse_zone(const struct nlattr *attr,
+				struct nf_conntrack_zone *zone);
+static int ctnetlink_parse_tuple_filter(const struct nlattr * const cda[],
+					 struct nf_conntrack_tuple *tuple,
+					 u32 type, u_int8_t l3num,
+					 struct nf_conntrack_zone *zone,
+					 u_int32_t flags);
+
+/* applied on filters */
+#define CTA_FILTER_F_CTA_MARK			(1 << 0)
+#define CTA_FILTER_F_CTA_MARK_MASK		(1 << 1)
+
 static struct ctnetlink_filter *
 ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family)
 {
 	struct ctnetlink_filter *filter;
+	int err;
 
 #ifndef CONFIG_NF_CONNTRACK_MARK
 	if (cda[CTA_MARK] || cda[CTA_MARK_MASK])
@@ -871,14 +928,65 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family)
 	filter->family = family;
 
 #ifdef CONFIG_NF_CONNTRACK_MARK
-	if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) {
+	if (cda[CTA_MARK]) {
 		filter->mark.val = ntohl(nla_get_be32(cda[CTA_MARK]));
-		filter->mark.mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK]));
+		filter->cta_flags |= CTA_FILTER_FLAG(CTA_MARK);
+
+		if (cda[CTA_MARK_MASK]) {
+			filter->mark.mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK]));
+			filter->cta_flags |= CTA_FILTER_FLAG(CTA_MARK_MASK);
+		} else {
+			filter->mark.mask = 0xffffffff;
+		}
+	} else if (cda[CTA_MARK_MASK]) {
+		return ERR_PTR(-EINVAL);
 	}
 #endif
+	if (!cda[CTA_FILTER])
+		return filter;
+
+	err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	err = ctnetlink_parse_filter(cda[CTA_FILTER], filter);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	if (filter->orig_flags) {
+		if (!cda[CTA_TUPLE_ORIG])
+			return ERR_PTR(-EINVAL);
+
+		err = ctnetlink_parse_tuple_filter(cda, &filter->orig,
+						   CTA_TUPLE_ORIG,
+						   filter->family,
+						   &filter->zone,
+						   filter->orig_flags);
+		if (err < 0)
+			return ERR_PTR(err);
+	}
+
+	if (filter->reply_flags) {
+		if (!cda[CTA_TUPLE_REPLY])
+			return ERR_PTR(-EINVAL);
+
+		err = ctnetlink_parse_tuple_filter(cda, &filter->reply,
+						   CTA_TUPLE_REPLY,
+						   filter->family,
+						   &filter->zone,
+						   filter->orig_flags);
+		if (err < 0)
+			return ERR_PTR(err);
+	}
+
 	return filter;
 }
 
+static bool ctnetlink_needs_filter(u8 family, const struct nlattr * const *cda)
+{
+	return family || cda[CTA_MARK] || cda[CTA_FILTER];
+}
+
 static int ctnetlink_start(struct netlink_callback *cb)
 {
 	const struct nlattr * const *cda = cb->data;
@@ -886,7 +994,7 @@ static int ctnetlink_start(struct netlink_callback *cb)
 	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
 	u8 family = nfmsg->nfgen_family;
 
-	if (family || (cda[CTA_MARK] && cda[CTA_MARK_MASK])) {
+	if (ctnetlink_needs_filter(family, cda)) {
 		filter = ctnetlink_alloc_filter(cda, family);
 		if (IS_ERR(filter))
 			return PTR_ERR(filter);
@@ -896,9 +1004,79 @@ static int ctnetlink_start(struct netlink_callback *cb)
 	return 0;
 }
 
+static int ctnetlink_filter_match_tuple(struct nf_conntrack_tuple *filter_tuple,
+					struct nf_conntrack_tuple *ct_tuple,
+					u_int32_t flags, int family)
+{
+	switch (family) {
+	case NFPROTO_IPV4:
+		if ((flags & CTA_FILTER_FLAG(CTA_IP_SRC)) &&
+		    filter_tuple->src.u3.ip != ct_tuple->src.u3.ip)
+			return  0;
+
+		if ((flags & CTA_FILTER_FLAG(CTA_IP_DST)) &&
+		    filter_tuple->dst.u3.ip != ct_tuple->dst.u3.ip)
+			return  0;
+		break;
+	case NFPROTO_IPV6:
+		if ((flags & CTA_FILTER_FLAG(CTA_IP_SRC)) &&
+		    !ipv6_addr_cmp(&filter_tuple->src.u3.in6,
+				   &ct_tuple->src.u3.in6))
+			return 0;
+
+		if ((flags & CTA_FILTER_FLAG(CTA_IP_DST)) &&
+		    !ipv6_addr_cmp(&filter_tuple->dst.u3.in6,
+				   &ct_tuple->dst.u3.in6))
+			return 0;
+		break;
+	}
+
+	if ((flags & CTA_FILTER_FLAG(CTA_PROTO_NUM)) &&
+	    filter_tuple->dst.protonum != ct_tuple->dst.protonum)
+		return 0;
+
+	switch (ct_tuple->dst.protonum) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+		if ((flags & CTA_FILTER_FLAG(CTA_PROTO_SRC_PORT)) &&
+		    filter_tuple->src.u.tcp.port != ct_tuple->src.u.tcp.port)
+			return 0;
+
+		if ((flags & CTA_FILTER_FLAG(CTA_PROTO_DST_PORT)) &&
+		    filter_tuple->dst.u.tcp.port != ct_tuple->dst.u.tcp.port)
+			return 0;
+		break;
+	case IPPROTO_ICMP:
+		if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_TYPE)) &&
+		    filter_tuple->dst.u.icmp.type != ct_tuple->dst.u.icmp.type)
+			return 0;
+		if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_CODE)) &&
+		    filter_tuple->dst.u.icmp.code != ct_tuple->dst.u.icmp.code)
+			return 0;
+		if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_ID)) &&
+		    filter_tuple->src.u.icmp.id != ct_tuple->src.u.icmp.id)
+			return 0;
+		break;
+	case IPPROTO_ICMPV6:
+		if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_TYPE)) &&
+		    filter_tuple->dst.u.icmp.type != ct_tuple->dst.u.icmp.type)
+			return 0;
+		if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_CODE)) &&
+		    filter_tuple->dst.u.icmp.code != ct_tuple->dst.u.icmp.code)
+			return 0;
+		if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_ID)) &&
+		    filter_tuple->src.u.icmp.id != ct_tuple->src.u.icmp.id)
+			return 0;
+		break;
+	}
+
+	return 1;
+}
+
 static int ctnetlink_filter_match(struct nf_conn *ct, void *data)
 {
 	struct ctnetlink_filter *filter = data;
+	struct nf_conntrack_tuple *tuple;
 
 	if (filter == NULL)
 		goto out;
@@ -910,8 +1088,28 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data)
 	if (filter->family && nf_ct_l3num(ct) != filter->family)
 		goto ignore_entry;
 
+	if (filter->orig_flags) {
+		tuple = nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL);
+		if (!ctnetlink_filter_match_tuple(&filter->orig, tuple,
+						  filter->orig_flags,
+						  filter->family))
+			goto ignore_entry;
+	}
+
+	if (filter->reply_flags) {
+		tuple = nf_ct_tuple(ct, IP_CT_DIR_REPLY);
+		if (!ctnetlink_filter_match_tuple(&filter->reply, tuple,
+						  filter->reply_flags,
+						  filter->family))
+			goto ignore_entry;
+	}
+
 #ifdef CONFIG_NF_CONNTRACK_MARK
-	if ((ct->mark & filter->mark.mask) != filter->mark.val)
+	if ((filter->cta_flags & CTA_FILTER_FLAG(CTA_MARK_MASK)) &&
+	    (ct->mark & filter->mark.mask) != filter->mark.val)
+		goto ignore_entry;
+	else if ((filter->cta_flags & CTA_FILTER_FLAG(CTA_MARK)) &&
+		 ct->mark != filter->mark.val)
 		goto ignore_entry;
 #endif
 
@@ -925,6 +1123,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data)
 static int
 ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 {
+	unsigned int flags = cb->data ? NLM_F_DUMP_FILTERED : 0;
 	struct net *net = sock_net(skb->sk);
 	struct nf_conn *ct, *last;
 	struct nf_conntrack_tuple_hash *h;
@@ -979,7 +1178,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 			ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid,
 					    cb->nlh->nlmsg_seq,
 					    NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
-					    ct, true);
+					    ct, true, flags);
 			if (res < 0) {
 				nf_conntrack_get(&ct->ct_general);
 				cb->args[1] = (unsigned long)ct;
@@ -1014,31 +1213,50 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 }
 
 static int ipv4_nlattr_to_tuple(struct nlattr *tb[],
-				struct nf_conntrack_tuple *t)
+				struct nf_conntrack_tuple *t,
+				u_int32_t flags)
 {
-	if (!tb[CTA_IP_V4_SRC] || !tb[CTA_IP_V4_DST])
-		return -EINVAL;
+	if (flags & CTA_FILTER_FLAG(CTA_IP_SRC)) {
+		if (!tb[CTA_IP_V4_SRC])
+			return -EINVAL;
+
+		t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]);
+	}
+
+	if (flags & CTA_FILTER_FLAG(CTA_IP_DST)) {
+		if (!tb[CTA_IP_V4_DST])
+			return -EINVAL;
 
-	t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]);
-	t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]);
+		t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]);
+	}
 
 	return 0;
 }
 
 static int ipv6_nlattr_to_tuple(struct nlattr *tb[],
-				struct nf_conntrack_tuple *t)
+				struct nf_conntrack_tuple *t,
+				u_int32_t flags)
 {
-	if (!tb[CTA_IP_V6_SRC] || !tb[CTA_IP_V6_DST])
-		return -EINVAL;
+	if (flags & CTA_FILTER_FLAG(CTA_IP_SRC)) {
+		if (!tb[CTA_IP_V6_SRC])
+			return -EINVAL;
 
-	t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]);
-	t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]);
+		t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]);
+	}
+
+	if (flags & CTA_FILTER_FLAG(CTA_IP_DST)) {
+		if (!tb[CTA_IP_V6_DST])
+			return -EINVAL;
+
+		t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]);
+	}
 
 	return 0;
 }
 
 static int ctnetlink_parse_tuple_ip(struct nlattr *attr,
-				    struct nf_conntrack_tuple *tuple)
+				    struct nf_conntrack_tuple *tuple,
+				    u_int32_t flags)
 {
 	struct nlattr *tb[CTA_IP_MAX+1];
 	int ret = 0;
@@ -1054,10 +1272,10 @@ static int ctnetlink_parse_tuple_ip(struct nlattr *attr,
 
 	switch (tuple->src.l3num) {
 	case NFPROTO_IPV4:
-		ret = ipv4_nlattr_to_tuple(tb, tuple);
+		ret = ipv4_nlattr_to_tuple(tb, tuple, flags);
 		break;
 	case NFPROTO_IPV6:
-		ret = ipv6_nlattr_to_tuple(tb, tuple);
+		ret = ipv6_nlattr_to_tuple(tb, tuple, flags);
 		break;
 	}
 
@@ -1069,7 +1287,8 @@ static const struct nla_policy proto_nla_policy[CTA_PROTO_MAX+1] = {
 };
 
 static int ctnetlink_parse_tuple_proto(struct nlattr *attr,
-				       struct nf_conntrack_tuple *tuple)
+				       struct nf_conntrack_tuple *tuple,
+				       u_int32_t flags)
 {
 	const struct nf_conntrack_l4proto *l4proto;
 	struct nlattr *tb[CTA_PROTO_MAX+1];
@@ -1080,8 +1299,12 @@ static int ctnetlink_parse_tuple_proto(struct nlattr *attr,
 	if (ret < 0)
 		return ret;
 
+	if (!(flags & CTA_FILTER_FLAG(CTA_PROTO_NUM)))
+		return 0;
+
 	if (!tb[CTA_PROTO_NUM])
 		return -EINVAL;
+
 	tuple->dst.protonum = nla_get_u8(tb[CTA_PROTO_NUM]);
 
 	rcu_read_lock();
@@ -1092,7 +1315,7 @@ static int ctnetlink_parse_tuple_proto(struct nlattr *attr,
 						     l4proto->nla_policy,
 						     NULL);
 		if (ret == 0)
-			ret = l4proto->nlattr_to_tuple(tb, tuple);
+			ret = l4proto->nlattr_to_tuple(tb, tuple, flags);
 	}
 
 	rcu_read_unlock();
@@ -1143,10 +1366,21 @@ static const struct nla_policy tuple_nla_policy[CTA_TUPLE_MAX+1] = {
 	[CTA_TUPLE_ZONE]	= { .type = NLA_U16 },
 };
 
+#define CTA_FILTER_F_ALL_CTA_PROTO \
+  (CTA_FILTER_F_CTA_PROTO_SRC_PORT | \
+   CTA_FILTER_F_CTA_PROTO_DST_PORT | \
+   CTA_FILTER_F_CTA_PROTO_ICMP_TYPE | \
+   CTA_FILTER_F_CTA_PROTO_ICMP_CODE | \
+   CTA_FILTER_F_CTA_PROTO_ICMP_ID | \
+   CTA_FILTER_F_CTA_PROTO_ICMPV6_TYPE | \
+   CTA_FILTER_F_CTA_PROTO_ICMPV6_CODE | \
+   CTA_FILTER_F_CTA_PROTO_ICMPV6_ID)
+
 static int
-ctnetlink_parse_tuple(const struct nlattr * const cda[],
-		      struct nf_conntrack_tuple *tuple, u32 type,
-		      u_int8_t l3num, struct nf_conntrack_zone *zone)
+ctnetlink_parse_tuple_filter(const struct nlattr * const cda[],
+			      struct nf_conntrack_tuple *tuple, u32 type,
+			      u_int8_t l3num, struct nf_conntrack_zone *zone,
+			      u_int32_t flags)
 {
 	struct nlattr *tb[CTA_TUPLE_MAX+1];
 	int err;
@@ -1158,23 +1392,32 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[],
 	if (err < 0)
 		return err;
 
-	if (!tb[CTA_TUPLE_IP])
-		return -EINVAL;
 
 	tuple->src.l3num = l3num;
 
-	err = ctnetlink_parse_tuple_ip(tb[CTA_TUPLE_IP], tuple);
-	if (err < 0)
-		return err;
+	if (flags & CTA_FILTER_FLAG(CTA_IP_DST) ||
+	    flags & CTA_FILTER_FLAG(CTA_IP_SRC)) {
+		if (!tb[CTA_TUPLE_IP])
+			return -EINVAL;
 
-	if (!tb[CTA_TUPLE_PROTO])
-		return -EINVAL;
+		err = ctnetlink_parse_tuple_ip(tb[CTA_TUPLE_IP], tuple, flags);
+		if (err < 0)
+			return err;
+	}
 
-	err = ctnetlink_parse_tuple_proto(tb[CTA_TUPLE_PROTO], tuple);
-	if (err < 0)
-		return err;
+	if (flags & CTA_FILTER_FLAG(CTA_PROTO_NUM)) {
+		if (!tb[CTA_TUPLE_PROTO])
+			return -EINVAL;
 
-	if (tb[CTA_TUPLE_ZONE]) {
+		err = ctnetlink_parse_tuple_proto(tb[CTA_TUPLE_PROTO], tuple, flags);
+		if (err < 0)
+			return err;
+	} else if (flags & CTA_FILTER_FLAG(ALL_CTA_PROTO)) {
+		/* Can't manage proto flags without a protonum  */
+		return -EINVAL;
+	}
+
+	if ((flags & CTA_FILTER_FLAG(CTA_TUPLE_ZONE)) && tb[CTA_TUPLE_ZONE]) {
 		if (!zone)
 			return -EINVAL;
 
@@ -1193,6 +1436,15 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[],
 	return 0;
 }
 
+static int
+ctnetlink_parse_tuple(const struct nlattr * const cda[],
+		      struct nf_conntrack_tuple *tuple, u32 type,
+		      u_int8_t l3num, struct nf_conntrack_zone *zone)
+{
+	return ctnetlink_parse_tuple_filter(cda, tuple, type, l3num, zone,
+					    CTA_FILTER_FLAG(ALL));
+}
+
 static const struct nla_policy help_nla_policy[CTA_HELP_MAX+1] = {
 	[CTA_HELP_NAME]		= { .type = NLA_NUL_STRING,
 				    .len = NF_CT_HELPER_NAME_LEN - 1 },
@@ -1240,6 +1492,7 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = {
 				    .len = NF_CT_LABELS_MAX_SIZE },
 	[CTA_LABELS_MASK]	= { .type = NLA_BINARY,
 				    .len = NF_CT_LABELS_MAX_SIZE },
+	[CTA_FILTER]		= { .type = NLA_NESTED },
 };
 
 static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data)
@@ -1256,7 +1509,10 @@ static int ctnetlink_flush_conntrack(struct net *net,
 {
 	struct ctnetlink_filter *filter = NULL;
 
-	if (family || (cda[CTA_MARK] && cda[CTA_MARK_MASK])) {
+	if (ctnetlink_needs_filter(family, cda)) {
+		if (cda[CTA_FILTER])
+			return -EOPNOTSUPP;
+
 		filter = ctnetlink_alloc_filter(cda, family);
 		if (IS_ERR(filter))
 			return PTR_ERR(filter);
@@ -1385,7 +1641,7 @@ static int ctnetlink_get_conntrack(struct net *net, struct sock *ctnl,
 	}
 
 	err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
-				  NFNL_MSG_TYPE(nlh->nlmsg_type), ct, true);
+				  NFNL_MSG_TYPE(nlh->nlmsg_type), ct, true, 0);
 	nf_ct_put(ct);
 	if (err <= 0)
 		goto free;
@@ -1458,7 +1714,7 @@ ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying
 			res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid,
 						  cb->nlh->nlmsg_seq,
 						  NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
-						  ct, dying ? true : false);
+						  ct, dying ? true : false, 0);
 			if (res < 0) {
 				if (!atomic_inc_not_zero(&ct->ct_general.use))
 					continue;

net/netfilter/nf_conntrack_proto_icmp.c

@@ -20,6 +20,8 @@
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/nf_log.h>
 
+#include "nf_internals.h"
+
 static const unsigned int nf_ct_icmp_timeout = 30*HZ;
 
 bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
@@ -271,20 +273,32 @@ static const struct nla_policy icmp_nla_policy[CTA_PROTO_MAX+1] = {
 };
 
 static int icmp_nlattr_to_tuple(struct nlattr *tb[],
-				struct nf_conntrack_tuple *tuple)
+				struct nf_conntrack_tuple *tuple,
+				u_int32_t flags)
 {
-	if (!tb[CTA_PROTO_ICMP_TYPE] ||
-	    !tb[CTA_PROTO_ICMP_CODE] ||
-	    !tb[CTA_PROTO_ICMP_ID])
-		return -EINVAL;
-
-	tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]);
-	tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]);
-	tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]);
-
-	if (tuple->dst.u.icmp.type >= sizeof(invmap) ||
-	    !invmap[tuple->dst.u.icmp.type])
-		return -EINVAL;
+	if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_TYPE)) {
+		if (!tb[CTA_PROTO_ICMP_TYPE])
+			return -EINVAL;
+
+		tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]);
+		if (tuple->dst.u.icmp.type >= sizeof(invmap) ||
+		    !invmap[tuple->dst.u.icmp.type])
+			return -EINVAL;
+	}
+
+	if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_CODE)) {
+		if (!tb[CTA_PROTO_ICMP_CODE])
+			return -EINVAL;
+
+		tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]);
+	}
+
+	if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_ID)) {
+		if (!tb[CTA_PROTO_ICMP_ID])
+			return -EINVAL;
+
+		tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]);
+	}
 
 	return 0;
 }

net/netfilter/nf_conntrack_proto_icmpv6.c

@@ -24,6 +24,8 @@
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/nf_log.h>
 
+#include "nf_internals.h"
+
 static const unsigned int nf_ct_icmpv6_timeout = 30*HZ;
 
 bool icmpv6_pkt_to_tuple(const struct sk_buff *skb,
@@ -193,21 +195,33 @@ static const struct nla_policy icmpv6_nla_policy[CTA_PROTO_MAX+1] = {
 };
 
 static int icmpv6_nlattr_to_tuple(struct nlattr *tb[],
-				struct nf_conntrack_tuple *tuple)
+				struct nf_conntrack_tuple *tuple,
+				u_int32_t flags)
 {
-	if (!tb[CTA_PROTO_ICMPV6_TYPE] ||
-	    !tb[CTA_PROTO_ICMPV6_CODE] ||
-	    !tb[CTA_PROTO_ICMPV6_ID])
-		return -EINVAL;
-
-	tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]);
-	tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]);
-	tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]);
-
-	if (tuple->dst.u.icmp.type < 128 ||
-	    tuple->dst.u.icmp.type - 128 >= sizeof(invmap) ||
-	    !invmap[tuple->dst.u.icmp.type - 128])
-		return -EINVAL;
+	if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_TYPE)) {
+		if (!tb[CTA_PROTO_ICMPV6_TYPE])
+			return -EINVAL;
+
+		tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]);
+		if (tuple->dst.u.icmp.type < 128 ||
+		    tuple->dst.u.icmp.type - 128 >= sizeof(invmap) ||
+		    !invmap[tuple->dst.u.icmp.type - 128])
+			return -EINVAL;
+	}
+
+	if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_CODE)) {
+		if (!tb[CTA_PROTO_ICMPV6_CODE])
+			return -EINVAL;
+
+		tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]);
+	}
+
+	if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_ID)) {
+		if (!tb[CTA_PROTO_ICMPV6_ID])
+			return -EINVAL;
+
+		tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]);
+	}
 
 	return 0;
 }

net/netfilter/nf_internals.h

@@ -6,6 +6,23 @@
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 
+/* nf_conntrack_netlink.c: applied on tuple filters */
+#define CTA_FILTER_F_CTA_IP_SRC			(1 << 0)
+#define CTA_FILTER_F_CTA_IP_DST			(1 << 1)
+#define CTA_FILTER_F_CTA_TUPLE_ZONE		(1 << 2)
+#define CTA_FILTER_F_CTA_PROTO_NUM		(1 << 3)
+#define CTA_FILTER_F_CTA_PROTO_SRC_PORT		(1 << 4)
+#define CTA_FILTER_F_CTA_PROTO_DST_PORT		(1 << 5)
+#define CTA_FILTER_F_CTA_PROTO_ICMP_TYPE	(1 << 6)
+#define CTA_FILTER_F_CTA_PROTO_ICMP_CODE	(1 << 7)
+#define CTA_FILTER_F_CTA_PROTO_ICMP_ID		(1 << 8)
+#define CTA_FILTER_F_CTA_PROTO_ICMPV6_TYPE	(1 << 9)
+#define CTA_FILTER_F_CTA_PROTO_ICMPV6_CODE	(1 << 10)
+#define CTA_FILTER_F_CTA_PROTO_ICMPV6_ID	(1 << 11)
+#define CTA_FILTER_F_MAX			(1 << 12)
+#define CTA_FILTER_F_ALL			(CTA_FILTER_F_MAX-1)
+#define CTA_FILTER_FLAG(ctattr) CTA_FILTER_F_ ## ctattr
+
 /* nf_queue.c */
 void nf_queue_nf_hook_drop(struct net *net);
 

net/netfilter/nf_tables_api.c

@@ -1669,6 +1669,7 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net,
 		goto err_hook_dev;
 	}
 	hook->ops.dev = dev;
+	hook->inactive = false;
 
 	return hook;
 
@@ -1678,17 +1679,17 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net,
 	return ERR_PTR(err);
 }
 
-static bool nft_hook_list_find(struct list_head *hook_list,
-			       const struct nft_hook *this)
+static struct nft_hook *nft_hook_list_find(struct list_head *hook_list,
+					   const struct nft_hook *this)
 {
 	struct nft_hook *hook;
 
 	list_for_each_entry(hook, hook_list, list) {
 		if (this->ops.dev == hook->ops.dev)
-			return true;
+			return hook;
 	}
 
-	return false;
+	return NULL;
 }
 
 static int nf_tables_parse_netdev_hooks(struct net *net,
@@ -1723,8 +1724,6 @@ static int nf_tables_parse_netdev_hooks(struct net *net,
 			goto err_hook;
 		}
 	}
-	if (!n)
-		return -EINVAL;
 
 	return 0;
 
@@ -1761,6 +1760,9 @@ static int nft_chain_parse_netdev(struct net *net,
 						   hook_list);
 		if (err < 0)
 			return err;
+
+		if (list_empty(hook_list))
+			return -EINVAL;
 	} else {
 		return -EINVAL;
 	}
@@ -6178,50 +6180,77 @@ nft_flowtable_lookup_byhandle(const struct nft_table *table,
        return ERR_PTR(-ENOENT);
 }
 
+struct nft_flowtable_hook {
+	u32			num;
+	int			priority;
+	struct list_head	list;
+};
+
 static const struct nla_policy nft_flowtable_hook_policy[NFTA_FLOWTABLE_HOOK_MAX + 1] = {
 	[NFTA_FLOWTABLE_HOOK_NUM]	= { .type = NLA_U32 },
 	[NFTA_FLOWTABLE_HOOK_PRIORITY]	= { .type = NLA_U32 },
 	[NFTA_FLOWTABLE_HOOK_DEVS]	= { .type = NLA_NESTED },
 };
 
-static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx,
-					  const struct nlattr *attr,
-					  struct nft_flowtable *flowtable)
+static int nft_flowtable_parse_hook(const struct nft_ctx *ctx,
+				    const struct nlattr *attr,
+				    struct nft_flowtable_hook *flowtable_hook,
+				    struct nft_flowtable *flowtable, bool add)
 {
 	struct nlattr *tb[NFTA_FLOWTABLE_HOOK_MAX + 1];
 	struct nft_hook *hook;
 	int hooknum, priority;
 	int err;
 
+	INIT_LIST_HEAD(&flowtable_hook->list);
+
 	err = nla_parse_nested_deprecated(tb, NFTA_FLOWTABLE_HOOK_MAX, attr,
 					  nft_flowtable_hook_policy, NULL);
 	if (err < 0)
 		return err;
 
-	if (!tb[NFTA_FLOWTABLE_HOOK_NUM] ||
-	    !tb[NFTA_FLOWTABLE_HOOK_PRIORITY] ||
-	    !tb[NFTA_FLOWTABLE_HOOK_DEVS])
-		return -EINVAL;
+	if (add) {
+		if (!tb[NFTA_FLOWTABLE_HOOK_NUM] ||
+		    !tb[NFTA_FLOWTABLE_HOOK_PRIORITY])
+			return -EINVAL;
 
-	hooknum = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_NUM]));
-	if (hooknum != NF_NETDEV_INGRESS)
-		return -EINVAL;
+		hooknum = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_NUM]));
+		if (hooknum != NF_NETDEV_INGRESS)
+			return -EOPNOTSUPP;
 
-	priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY]));
+		priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY]));
 
-	err = nf_tables_parse_netdev_hooks(ctx->net,
-					   tb[NFTA_FLOWTABLE_HOOK_DEVS],
-					   &flowtable->hook_list);
-	if (err < 0)
-		return err;
+		flowtable_hook->priority	= priority;
+		flowtable_hook->num		= hooknum;
+	} else {
+		if (tb[NFTA_FLOWTABLE_HOOK_NUM]) {
+			hooknum = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_NUM]));
+			if (hooknum != flowtable->hooknum)
+				return -EOPNOTSUPP;
+		}
 
-	flowtable->hooknum		= hooknum;
-	flowtable->data.priority	= priority;
+		if (tb[NFTA_FLOWTABLE_HOOK_PRIORITY]) {
+			priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY]));
+			if (priority != flowtable->data.priority)
+				return -EOPNOTSUPP;
+		}
 
-	list_for_each_entry(hook, &flowtable->hook_list, list) {
+		flowtable_hook->priority	= flowtable->data.priority;
+		flowtable_hook->num		= flowtable->hooknum;
+	}
+
+	if (tb[NFTA_FLOWTABLE_HOOK_DEVS]) {
+		err = nf_tables_parse_netdev_hooks(ctx->net,
+						   tb[NFTA_FLOWTABLE_HOOK_DEVS],
+						   &flowtable_hook->list);
+		if (err < 0)
+			return err;
+	}
+
+	list_for_each_entry(hook, &flowtable_hook->list, list) {
 		hook->ops.pf		= NFPROTO_NETDEV;
-		hook->ops.hooknum	= hooknum;
-		hook->ops.priority	= priority;
+		hook->ops.hooknum	= flowtable_hook->num;
+		hook->ops.priority	= flowtable_hook->priority;
 		hook->ops.priv		= &flowtable->data;
 		hook->ops.hook		= flowtable->data.type->hook;
 	}
@@ -6270,23 +6299,24 @@ static void nft_unregister_flowtable_hook(struct net *net,
 }
 
 static void nft_unregister_flowtable_net_hooks(struct net *net,
-					       struct nft_flowtable *flowtable)
+					       struct list_head *hook_list)
 {
 	struct nft_hook *hook;
 
-	list_for_each_entry(hook, &flowtable->hook_list, list)
+	list_for_each_entry(hook, hook_list, list)
 		nf_unregister_net_hook(net, &hook->ops);
 }
 
 static int nft_register_flowtable_net_hooks(struct net *net,
 					    struct nft_table *table,
+					    struct list_head *hook_list,
 					    struct nft_flowtable *flowtable)
 {
 	struct nft_hook *hook, *hook2, *next;
 	struct nft_flowtable *ft;
 	int err, i = 0;
 
-	list_for_each_entry(hook, &flowtable->hook_list, list) {
+	list_for_each_entry(hook, hook_list, list) {
 		list_for_each_entry(ft, &table->flowtables, list) {
 			list_for_each_entry(hook2, &ft->hook_list, list) {
 				if (hook->ops.dev == hook2->ops.dev &&
@@ -6317,7 +6347,7 @@ static int nft_register_flowtable_net_hooks(struct net *net,
 	return 0;
 
 err_unregister_net_hooks:
-	list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) {
+	list_for_each_entry_safe(hook, next, hook_list, list) {
 		if (i-- <= 0)
 			break;
 
@@ -6329,6 +6359,72 @@ static int nft_register_flowtable_net_hooks(struct net *net,
 	return err;
 }
 
+static void nft_flowtable_hooks_destroy(struct list_head *hook_list)
+{
+	struct nft_hook *hook, *next;
+
+	list_for_each_entry_safe(hook, next, hook_list, list) {
+		list_del_rcu(&hook->list);
+		kfree_rcu(hook, rcu);
+	}
+}
+
+static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh,
+				struct nft_flowtable *flowtable)
+{
+	const struct nlattr * const *nla = ctx->nla;
+	struct nft_flowtable_hook flowtable_hook;
+	struct nft_hook *hook, *next;
+	struct nft_trans *trans;
+	bool unregister = false;
+	int err;
+
+	err = nft_flowtable_parse_hook(ctx, nla[NFTA_FLOWTABLE_HOOK],
+				       &flowtable_hook, flowtable, false);
+	if (err < 0)
+		return err;
+
+	list_for_each_entry_safe(hook, next, &flowtable_hook.list, list) {
+		if (nft_hook_list_find(&flowtable->hook_list, hook)) {
+			list_del(&hook->list);
+			kfree(hook);
+		}
+	}
+
+	err = nft_register_flowtable_net_hooks(ctx->net, ctx->table,
+					       &flowtable_hook.list, flowtable);
+	if (err < 0)
+		goto err_flowtable_update_hook;
+
+	trans = nft_trans_alloc(ctx, NFT_MSG_NEWFLOWTABLE,
+				sizeof(struct nft_trans_flowtable));
+	if (!trans) {
+		unregister = true;
+		err = -ENOMEM;
+		goto err_flowtable_update_hook;
+	}
+
+	nft_trans_flowtable(trans) = flowtable;
+	nft_trans_flowtable_update(trans) = true;
+	INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans));
+	list_splice(&flowtable_hook.list, &nft_trans_flowtable_hooks(trans));
+
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+
+	return 0;
+
+err_flowtable_update_hook:
+	list_for_each_entry_safe(hook, next, &flowtable_hook.list, list) {
+		if (unregister)
+			nft_unregister_flowtable_hook(ctx->net, flowtable, hook);
+		list_del_rcu(&hook->list);
+		kfree_rcu(hook, rcu);
+	}
+
+	return err;
+
+}
+
 static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
 				  struct sk_buff *skb,
 				  const struct nlmsghdr *nlh,
@@ -6336,6 +6432,7 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
 				  struct netlink_ext_ack *extack)
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+	struct nft_flowtable_hook flowtable_hook;
 	const struct nf_flowtable_type *type;
 	u8 genmask = nft_genmask_next(net);
 	int family = nfmsg->nfgen_family;
@@ -6371,7 +6468,9 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
 			return -EEXIST;
 		}
 
-		return 0;
+		nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
+
+		return nft_flowtable_update(&ctx, nlh, flowtable);
 	}
 
 	nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
@@ -6409,17 +6508,20 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
 	if (err < 0)
 		goto err3;
 
-	err = nf_tables_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK],
-					     flowtable);
+	err = nft_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK],
+				       &flowtable_hook, flowtable, true);
 	if (err < 0)
 		goto err4;
 
-	err = nft_register_flowtable_net_hooks(ctx.net, table, flowtable);
+	list_splice(&flowtable_hook.list, &flowtable->hook_list);
+	flowtable->data.priority = flowtable_hook.priority;
+	flowtable->hooknum = flowtable_hook.num;
+
+	err = nft_register_flowtable_net_hooks(ctx.net, table,
+					       &flowtable->hook_list,
+					       flowtable);
 	if (err < 0) {
-		list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) {
-			list_del_rcu(&hook->list);
-			kfree_rcu(hook, rcu);
-		}
+		nft_flowtable_hooks_destroy(&flowtable->hook_list);
 		goto err4;
 	}
 
@@ -6448,6 +6550,51 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
 	return err;
 }
 
+static int nft_delflowtable_hook(struct nft_ctx *ctx,
+				 struct nft_flowtable *flowtable)
+{
+	const struct nlattr * const *nla = ctx->nla;
+	struct nft_flowtable_hook flowtable_hook;
+	struct nft_hook *this, *next, *hook;
+	struct nft_trans *trans;
+	int err;
+
+	err = nft_flowtable_parse_hook(ctx, nla[NFTA_FLOWTABLE_HOOK],
+				       &flowtable_hook, flowtable, false);
+	if (err < 0)
+		return err;
+
+	list_for_each_entry_safe(this, next, &flowtable_hook.list, list) {
+		hook = nft_hook_list_find(&flowtable->hook_list, this);
+		if (!hook) {
+			err = -ENOENT;
+			goto err_flowtable_del_hook;
+		}
+		hook->inactive = true;
+		list_del(&this->list);
+		kfree(this);
+	}
+
+	trans = nft_trans_alloc(ctx, NFT_MSG_DELFLOWTABLE,
+				sizeof(struct nft_trans_flowtable));
+	if (!trans)
+		return -ENOMEM;
+
+	nft_trans_flowtable(trans) = flowtable;
+	nft_trans_flowtable_update(trans) = true;
+	INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans));
+
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+
+	return 0;
+
+err_flowtable_del_hook:
+	list_for_each_entry(hook, &flowtable_hook.list, list)
+		hook->inactive = false;
+
+	return err;
+}
+
 static int nf_tables_delflowtable(struct net *net, struct sock *nlsk,
 				  struct sk_buff *skb,
 				  const struct nlmsghdr *nlh,
@@ -6486,20 +6633,25 @@ static int nf_tables_delflowtable(struct net *net, struct sock *nlsk,
 		NL_SET_BAD_ATTR(extack, attr);
 		return PTR_ERR(flowtable);
 	}
+
+	nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
+
+	if (nla[NFTA_FLOWTABLE_HOOK])
+		return nft_delflowtable_hook(&ctx, flowtable);
+
 	if (flowtable->use > 0) {
 		NL_SET_BAD_ATTR(extack, attr);
 		return -EBUSY;
 	}
 
-	nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
-
 	return nft_delflowtable(&ctx, flowtable);
 }
 
 static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
 					 u32 portid, u32 seq, int event,
 					 u32 flags, int family,
-					 struct nft_flowtable *flowtable)
+					 struct nft_flowtable *flowtable,
+					 struct list_head *hook_list)
 {
 	struct nlattr *nest, *nest_devs;
 	struct nfgenmsg *nfmsg;
@@ -6535,7 +6687,7 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
 	if (!nest_devs)
 		goto nla_put_failure;
 
-	list_for_each_entry_rcu(hook, &flowtable->hook_list, list) {
+	list_for_each_entry_rcu(hook, hook_list, list) {
 		if (nla_put_string(skb, NFTA_DEVICE_NAME, hook->ops.dev->name))
 			goto nla_put_failure;
 	}
@@ -6588,7 +6740,9 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb,
 							  cb->nlh->nlmsg_seq,
 							  NFT_MSG_NEWFLOWTABLE,
 							  NLM_F_MULTI | NLM_F_APPEND,
-							  table->family, flowtable) < 0)
+							  table->family,
+							  flowtable,
+							  &flowtable->hook_list) < 0)
 				goto done;
 
 			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
@@ -6685,7 +6839,7 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk,
 	err = nf_tables_fill_flowtable_info(skb2, net, NETLINK_CB(skb).portid,
 					    nlh->nlmsg_seq,
 					    NFT_MSG_NEWFLOWTABLE, 0, family,
-					    flowtable);
+					    flowtable, &flowtable->hook_list);
 	if (err < 0)
 		goto err;
 
@@ -6697,6 +6851,7 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk,
 
 static void nf_tables_flowtable_notify(struct nft_ctx *ctx,
 				       struct nft_flowtable *flowtable,
+				       struct list_head *hook_list,
 				       int event)
 {
 	struct sk_buff *skb;
@@ -6712,7 +6867,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx,
 
 	err = nf_tables_fill_flowtable_info(skb, ctx->net, ctx->portid,
 					    ctx->seq, event, 0,
-					    ctx->family, flowtable);
+					    ctx->family, flowtable, hook_list);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto err;
@@ -7098,7 +7253,10 @@ static void nft_commit_release(struct nft_trans *trans)
 		nft_obj_destroy(&trans->ctx, nft_trans_obj(trans));
 		break;
 	case NFT_MSG_DELFLOWTABLE:
-		nf_tables_flowtable_destroy(nft_trans_flowtable(trans));
+		if (nft_trans_flowtable_update(trans))
+			nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans));
+		else
+			nf_tables_flowtable_destroy(nft_trans_flowtable(trans));
 		break;
 	}
 
@@ -7259,6 +7417,17 @@ static void nft_chain_del(struct nft_chain *chain)
 	list_del_rcu(&chain->list);
 }
 
+static void nft_flowtable_hooks_del(struct nft_flowtable *flowtable,
+				    struct list_head *hook_list)
+{
+	struct nft_hook *hook, *next;
+
+	list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) {
+		if (hook->inactive)
+			list_move(&hook->list, hook_list);
+	}
+}
+
 static void nf_tables_module_autoload_cleanup(struct net *net)
 {
 	struct nft_module_request *req, *next;
@@ -7467,19 +7636,41 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 					     NFT_MSG_DELOBJ);
 			break;
 		case NFT_MSG_NEWFLOWTABLE:
-			nft_clear(net, nft_trans_flowtable(trans));
-			nf_tables_flowtable_notify(&trans->ctx,
-						   nft_trans_flowtable(trans),
-						   NFT_MSG_NEWFLOWTABLE);
+			if (nft_trans_flowtable_update(trans)) {
+				nf_tables_flowtable_notify(&trans->ctx,
+							   nft_trans_flowtable(trans),
+							   &nft_trans_flowtable_hooks(trans),
+							   NFT_MSG_NEWFLOWTABLE);
+				list_splice(&nft_trans_flowtable_hooks(trans),
+					    &nft_trans_flowtable(trans)->hook_list);
+			} else {
+				nft_clear(net, nft_trans_flowtable(trans));
+				nf_tables_flowtable_notify(&trans->ctx,
+							   nft_trans_flowtable(trans),
+							   &nft_trans_flowtable(trans)->hook_list,
+							   NFT_MSG_NEWFLOWTABLE);
+			}
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_DELFLOWTABLE:
-			list_del_rcu(&nft_trans_flowtable(trans)->list);
-			nf_tables_flowtable_notify(&trans->ctx,
-						   nft_trans_flowtable(trans),
-						   NFT_MSG_DELFLOWTABLE);
-			nft_unregister_flowtable_net_hooks(net,
-					nft_trans_flowtable(trans));
+			if (nft_trans_flowtable_update(trans)) {
+				nft_flowtable_hooks_del(nft_trans_flowtable(trans),
+							&nft_trans_flowtable_hooks(trans));
+				nf_tables_flowtable_notify(&trans->ctx,
+							   nft_trans_flowtable(trans),
+							   &nft_trans_flowtable_hooks(trans),
+							   NFT_MSG_DELFLOWTABLE);
+				nft_unregister_flowtable_net_hooks(net,
+								   &nft_trans_flowtable_hooks(trans));
+			} else {
+				list_del_rcu(&nft_trans_flowtable(trans)->list);
+				nf_tables_flowtable_notify(&trans->ctx,
+							   nft_trans_flowtable(trans),
+							   &nft_trans_flowtable(trans)->hook_list,
+							   NFT_MSG_DELFLOWTABLE);
+				nft_unregister_flowtable_net_hooks(net,
+						&nft_trans_flowtable(trans)->hook_list);
+			}
 			break;
 		}
 	}
@@ -7528,7 +7719,10 @@ static void nf_tables_abort_release(struct nft_trans *trans)
 		nft_obj_destroy(&trans->ctx, nft_trans_obj(trans));
 		break;
 	case NFT_MSG_NEWFLOWTABLE:
-		nf_tables_flowtable_destroy(nft_trans_flowtable(trans));
+		if (nft_trans_flowtable_update(trans))
+			nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans));
+		else
+			nf_tables_flowtable_destroy(nft_trans_flowtable(trans));
 		break;
 	}
 	kfree(trans);
@@ -7538,6 +7732,7 @@ static int __nf_tables_abort(struct net *net, bool autoload)
 {
 	struct nft_trans *trans, *next;
 	struct nft_trans_elem *te;
+	struct nft_hook *hook;
 
 	list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list,
 					 list) {
@@ -7635,14 +7830,24 @@ static int __nf_tables_abort(struct net *net, bool autoload)
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_NEWFLOWTABLE:
-			trans->ctx.table->use--;
-			list_del_rcu(&nft_trans_flowtable(trans)->list);
-			nft_unregister_flowtable_net_hooks(net,
-					nft_trans_flowtable(trans));
+			if (nft_trans_flowtable_update(trans)) {
+				nft_unregister_flowtable_net_hooks(net,
+						&nft_trans_flowtable_hooks(trans));
+			} else {
+				trans->ctx.table->use--;
+				list_del_rcu(&nft_trans_flowtable(trans)->list);
+				nft_unregister_flowtable_net_hooks(net,
+						&nft_trans_flowtable(trans)->hook_list);
+			}
 			break;
 		case NFT_MSG_DELFLOWTABLE:
-			trans->ctx.table->use++;
-			nft_clear(trans->ctx.net, nft_trans_flowtable(trans));
+			if (nft_trans_flowtable_update(trans)) {
+				list_for_each_entry(hook, &nft_trans_flowtable(trans)->hook_list, list)
+					hook->inactive = false;
+			} else {
+				trans->ctx.table->use++;
+				nft_clear(trans->ctx.net, nft_trans_flowtable(trans));
+			}
 			nft_trans_destroy(trans);
 			break;
 		}