Merge tag 'nf-next-2023-03-30' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next

Florian Westphal says:

====================
netfilter updates for net-next

1. No need to disable BH in nfnetlink proc handler, freeing happens
   via call_rcu.
2. Expose classid in nfetlink_queue, from Eric Sage.
3. Fix nfnetlink message description comments, from Matthieu De Beule.
4. Allow removal of offloaded connections via ctnetlink, from Paul Blakey.

* tag 'nf-next-2023-03-30' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next:
  netfilter: ctnetlink: Support offloaded conntrack entry deletion
  netfilter: Correct documentation errors in nf_tables.h
  netfilter: nfnetlink_queue: enable classid socket info retrieval
  netfilter: nfnetlink_log: remove rcu_bh usage
====================

Link: https://lore.kernel.org/r/20230331104809.2959-1-fw@strlen.deSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/uapi/linux/netfilter/nf_tables.h

@@ -685,7 +685,7 @@ enum nft_range_ops {
  * enum nft_range_attributes - nf_tables range expression netlink attributes
  *
  * @NFTA_RANGE_SREG: source register of data to compare (NLA_U32: nft_registers)
- * @NFTA_RANGE_OP: cmp operation (NLA_U32: nft_cmp_ops)
+ * @NFTA_RANGE_OP: cmp operation (NLA_U32: nft_range_ops)
  * @NFTA_RANGE_FROM_DATA: data range from (NLA_NESTED: nft_data_attributes)
  * @NFTA_RANGE_TO_DATA: data range to (NLA_NESTED: nft_data_attributes)
  */
@@ -878,7 +878,7 @@ enum nft_exthdr_op {
  * @NFTA_EXTHDR_LEN: extension header length (NLA_U32)
  * @NFTA_EXTHDR_FLAGS: extension header flags (NLA_U32)
  * @NFTA_EXTHDR_OP: option match type (NLA_U32)
- * @NFTA_EXTHDR_SREG: option match type (NLA_U32)
+ * @NFTA_EXTHDR_SREG: source register (NLA_U32: nft_registers)
  */
 enum nft_exthdr_attributes {
 	NFTA_EXTHDR_UNSPEC,
@@ -1262,10 +1262,10 @@ enum nft_last_attributes {
 /**
  * enum nft_log_attributes - nf_tables log expression netlink attributes
  *
- * @NFTA_LOG_GROUP: netlink group to send messages to (NLA_U32)
+ * @NFTA_LOG_GROUP: netlink group to send messages to (NLA_U16)
  * @NFTA_LOG_PREFIX: prefix to prepend to log messages (NLA_STRING)
  * @NFTA_LOG_SNAPLEN: length of payload to include in netlink message (NLA_U32)
- * @NFTA_LOG_QTHRESHOLD: queue threshold (NLA_U32)
+ * @NFTA_LOG_QTHRESHOLD: queue threshold (NLA_U16)
  * @NFTA_LOG_LEVEL: log level (NLA_U32)
  * @NFTA_LOG_FLAGS: logging flags (NLA_U32)
  */

include/uapi/linux/netfilter/nfnetlink_queue.h

@@ -62,6 +62,7 @@ enum nfqnl_attr_type {
 	NFQA_VLAN,			/* nested attribute: packet vlan info */
 	NFQA_L2HDR,			/* full L2 header */
 	NFQA_PRIORITY,			/* skb->priority */
+	NFQA_CGROUP_CLASSID,		/* __u32 cgroup classid */
 
 	__NFQA_MAX
 };

net/netfilter/nf_conntrack_netlink.c

@@ -1554,9 +1554,6 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = {
 
 static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data)
 {
-	if (test_bit(IPS_OFFLOAD_BIT, &ct->status))
-		return 0;
-
 	return ctnetlink_filter_match(ct, data);
 }
 
@@ -1626,11 +1623,6 @@ static int ctnetlink_del_conntrack(struct sk_buff *skb,
 
 	ct = nf_ct_tuplehash_to_ctrack(h);
 
-	if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) {
-		nf_ct_put(ct);
-		return -EBUSY;
-	}
-
 	if (cda[CTA_ID]) {
 		__be32 id = nla_get_be32(cda[CTA_ID]);
 

net/netfilter/nfnetlink_log.c

@@ -103,9 +103,9 @@ static inline u_int8_t instance_hashfn(u_int16_t group_num)
 }
 
 static struct nfulnl_instance *
-__instance_lookup(struct nfnl_log_net *log, u_int16_t group_num)
+__instance_lookup(const struct nfnl_log_net *log, u16 group_num)
 {
-	struct hlist_head *head;
+	const struct hlist_head *head;
 	struct nfulnl_instance *inst;
 
 	head = &log->instance_table[instance_hashfn(group_num)];
@@ -123,15 +123,25 @@ instance_get(struct nfulnl_instance *inst)
 }
 
 static struct nfulnl_instance *
-instance_lookup_get(struct nfnl_log_net *log, u_int16_t group_num)
+instance_lookup_get_rcu(const struct nfnl_log_net *log, u16 group_num)
 {
 	struct nfulnl_instance *inst;
 
-	rcu_read_lock_bh();
 	inst = __instance_lookup(log, group_num);
 	if (inst && !refcount_inc_not_zero(&inst->use))
 		inst = NULL;
-	rcu_read_unlock_bh();
+
+	return inst;
+}
+
+static struct nfulnl_instance *
+instance_lookup_get(const struct nfnl_log_net *log, u16 group_num)
+{
+	struct nfulnl_instance *inst;
+
+	rcu_read_lock();
+	inst = instance_lookup_get_rcu(log, group_num);
+	rcu_read_unlock();
 
 	return inst;
 }
@@ -698,7 +708,7 @@ nfulnl_log_packet(struct net *net,
 	else
 		li = &default_loginfo;
 
-	inst = instance_lookup_get(log, li->u.ulog.group);
+	inst = instance_lookup_get_rcu(log, li->u.ulog.group);
 	if (!inst)
 		return;
 
@@ -1030,7 +1040,7 @@ static struct hlist_node *get_first(struct net *net, struct iter_state *st)
 		struct hlist_head *head = &log->instance_table[st->bucket];
 
 		if (!hlist_empty(head))
-			return rcu_dereference_bh(hlist_first_rcu(head));
+			return rcu_dereference(hlist_first_rcu(head));
 	}
 	return NULL;
 }
@@ -1038,7 +1048,7 @@ static struct hlist_node *get_first(struct net *net, struct iter_state *st)
 static struct hlist_node *get_next(struct net *net, struct iter_state *st,
 				   struct hlist_node *h)
 {
-	h = rcu_dereference_bh(hlist_next_rcu(h));
+	h = rcu_dereference(hlist_next_rcu(h));
 	while (!h) {
 		struct nfnl_log_net *log;
 		struct hlist_head *head;
@@ -1048,7 +1058,7 @@ static struct hlist_node *get_next(struct net *net, struct iter_state *st,
 
 		log = nfnl_log_pernet(net);
 		head = &log->instance_table[st->bucket];
-		h = rcu_dereference_bh(hlist_first_rcu(head));
+		h = rcu_dereference(hlist_first_rcu(head));
 	}
 	return h;
 }
@@ -1066,9 +1076,9 @@ static struct hlist_node *get_idx(struct net *net, struct iter_state *st,
 }
 
 static void *seq_start(struct seq_file *s, loff_t *pos)
-	__acquires(rcu_bh)
+	__acquires(rcu)
 {
-	rcu_read_lock_bh();
+	rcu_read_lock();
 	return get_idx(seq_file_net(s), s->private, *pos);
 }
 
@@ -1079,9 +1089,9 @@ static void *seq_next(struct seq_file *s, void *v, loff_t *pos)
 }
 
 static void seq_stop(struct seq_file *s, void *v)
-	__releases(rcu_bh)
+	__releases(rcu)
 {
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 }
 
 static int seq_show(struct seq_file *s, void *v)

net/netfilter/nfnetlink_queue.c

@@ -29,6 +29,7 @@
 #include <linux/netfilter/nfnetlink_queue.h>
 #include <linux/netfilter/nf_conntrack_common.h>
 #include <linux/list.h>
+#include <linux/cgroup-defs.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
 #include <net/netfilter/nf_queue.h>
@@ -301,6 +302,19 @@ static int nfqnl_put_sk_uidgid(struct sk_buff *skb, struct sock *sk)
 	return -1;
 }
 
+static int nfqnl_put_sk_classid(struct sk_buff *skb, struct sock *sk)
+{
+#if IS_ENABLED(CONFIG_CGROUP_NET_CLASSID)
+	if (sk && sk_fullsock(sk)) {
+		u32 classid = sock_cgroup_classid(&sk->sk_cgrp_data);
+
+		if (classid && nla_put_be32(skb, NFQA_CGROUP_CLASSID, htonl(classid)))
+			return -1;
+	}
+#endif
+	return 0;
+}
+
 static u32 nfqnl_get_sk_secctx(struct sk_buff *skb, char **secdata)
 {
 	u32 seclen = 0;
@@ -406,6 +420,9 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 		+ nla_total_size(sizeof(u_int32_t))	/* priority */
 		+ nla_total_size(sizeof(struct nfqnl_msg_packet_hw))
 		+ nla_total_size(sizeof(u_int32_t))	/* skbinfo */
+#if IS_ENABLED(CONFIG_CGROUP_NET_CLASSID)
+		+ nla_total_size(sizeof(u_int32_t))	/* classid */
+#endif
 		+ nla_total_size(sizeof(u_int32_t));	/* cap_len */
 
 	tstamp = skb_tstamp_cond(entskb, false);
@@ -599,6 +616,9 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 	    nfqnl_put_sk_uidgid(skb, entskb->sk) < 0)
 		goto nla_put_failure;
 
+	if (nfqnl_put_sk_classid(skb, entskb->sk) < 0)
+		goto nla_put_failure;
+
 	if (seclen && nla_put(skb, NFQA_SECCTX, seclen, secdata))
 		goto nla_put_failure;