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

Pablo Neira Ayuso says:

====================
Netfilter fixes for net

The following patchset contains Netfilter fixes for net:

1) Incorrect netlink report logic in flowtable and genID.

2) Add a selftest to check that wireguard passes the right sk
   to ip_route_me_harder, from Jason A. Donenfeld.

3) Pass the actual sk to ip_route_me_harder(), also from Jason.

4) Missing expression validation of updates via nft --check.

5) Update byte and packet counters regardless of whether they
   match, from Stefano Brivio.
====================
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/netfilter/nfnetlink.h

@@ -24,6 +24,12 @@ struct nfnl_callback {
 	const u_int16_t attr_count;		/* number of nlattr's */
 };
 
+enum nfnl_abort_action {
+	NFNL_ABORT_NONE		= 0,
+	NFNL_ABORT_AUTOLOAD,
+	NFNL_ABORT_VALIDATE,
+};
+
 struct nfnetlink_subsystem {
 	const char *name;
 	__u8 subsys_id;			/* nfnetlink subsystem ID */
@@ -31,7 +37,8 @@ struct nfnetlink_subsystem {
 	const struct nfnl_callback *cb;	/* callback for individual types */
 	struct module *owner;
 	int (*commit)(struct net *net, struct sk_buff *skb);
-	int (*abort)(struct net *net, struct sk_buff *skb, bool autoload);
+	int (*abort)(struct net *net, struct sk_buff *skb,
+		     enum nfnl_abort_action action);
 	void (*cleanup)(struct net *net);
 	bool (*valid_genid)(struct net *net, u32 genid);
 };

include/linux/netfilter_ipv4.h

@@ -16,7 +16,7 @@ struct ip_rt_info {
 	u_int32_t mark;
 };
 
-int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned addr_type);
+int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned addr_type);
 
 struct nf_queue_entry;
 

include/linux/netfilter_ipv6.h

@@ -42,7 +42,7 @@ struct nf_ipv6_ops {
 #if IS_MODULE(CONFIG_IPV6)
 	int (*chk_addr)(struct net *net, const struct in6_addr *addr,
 			const struct net_device *dev, int strict);
-	int (*route_me_harder)(struct net *net, struct sk_buff *skb);
+	int (*route_me_harder)(struct net *net, struct sock *sk, struct sk_buff *skb);
 	int (*dev_get_saddr)(struct net *net, const struct net_device *dev,
 		       const struct in6_addr *daddr, unsigned int srcprefs,
 		       struct in6_addr *saddr);
@@ -143,9 +143,9 @@ static inline int nf_br_ip6_fragment(struct net *net, struct sock *sk,
 #endif
 }
 
-int ip6_route_me_harder(struct net *net, struct sk_buff *skb);
+int ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb);
 
-static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb)
+static inline int nf_ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 #if IS_MODULE(CONFIG_IPV6)
 	const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
@@ -153,9 +153,9 @@ static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb)
 	if (!v6_ops)
 		return -EHOSTUNREACH;
 
-	return v6_ops->route_me_harder(net, skb);
+	return v6_ops->route_me_harder(net, sk, skb);
 #elif IS_BUILTIN(CONFIG_IPV6)
-	return ip6_route_me_harder(net, skb);
+	return ip6_route_me_harder(net, sk, skb);
 #else
 	return -EHOSTUNREACH;
 #endif

net/ipv4/netfilter.c

@@ -17,17 +17,19 @@
 #include <net/netfilter/nf_queue.h>
 
 /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
-int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_type)
+int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int addr_type)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
 	struct flowi4 fl4 = {};
 	__be32 saddr = iph->saddr;
-	const struct sock *sk = skb_to_full_sk(skb);
-	__u8 flags = sk ? inet_sk_flowi_flags(sk) : 0;
+	__u8 flags;
 	struct net_device *dev = skb_dst(skb)->dev;
 	unsigned int hh_len;
 
+	sk = sk_to_full_sk(sk);
+	flags = sk ? inet_sk_flowi_flags(sk) : 0;
+
 	if (addr_type == RTN_UNSPEC)
 		addr_type = inet_addr_type_dev_table(net, dev, saddr);
 	if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)

net/ipv4/netfilter/iptable_mangle.c

@@ -62,7 +62,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state)
 		    iph->daddr != daddr ||
 		    skb->mark != mark ||
 		    iph->tos != tos) {
-			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+			err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}

net/ipv4/netfilter/nf_reject_ipv4.c

@@ -145,7 +145,7 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 				   ip4_dst_hoplimit(skb_dst(nskb)));
 	nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
 
-	if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
+	if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC))
 		goto free_nskb;
 
 	niph = ip_hdr(nskb);

net/ipv6/netfilter.c

@@ -20,10 +20,10 @@
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 #include "../bridge/br_private.h"
 
-int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
+int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff *skb)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
-	struct sock *sk = sk_to_full_sk(skb->sk);
+	struct sock *sk = sk_to_full_sk(sk_partial);
 	unsigned int hh_len;
 	struct dst_entry *dst;
 	int strict = (ipv6_addr_type(&iph->daddr) &
@@ -84,7 +84,7 @@ static int nf_ip6_reroute(struct sk_buff *skb,
 		if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
 		    !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
 		    skb->mark != rt_info->mark)
-			return ip6_route_me_harder(entry->state.net, skb);
+			return ip6_route_me_harder(entry->state.net, entry->state.sk, skb);
 	}
 	return 0;
 }

net/ipv6/netfilter/ip6table_mangle.c

@@ -57,7 +57,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state)
 	     skb->mark != mark ||
 	     ipv6_hdr(skb)->hop_limit != hop_limit ||
 	     flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
-		err = ip6_route_me_harder(state->net, skb);
+		err = ip6_route_me_harder(state->net, state->sk, skb);
 		if (err < 0)
 			ret = NF_DROP_ERR(err);
 	}

net/netfilter/ipset/ip_set_core.c

@@ -637,13 +637,14 @@ ip_set_match_extensions(struct ip_set *set, const struct ip_set_ext *ext,
 	if (SET_WITH_COUNTER(set)) {
 		struct ip_set_counter *counter = ext_counter(data, set);
 
+		ip_set_update_counter(counter, ext, flags);
+
 		if (flags & IPSET_FLAG_MATCH_COUNTERS &&
 		    !(ip_set_match_counter(ip_set_get_packets(counter),
 				mext->packets, mext->packets_op) &&
 		      ip_set_match_counter(ip_set_get_bytes(counter),
 				mext->bytes, mext->bytes_op)))
 			return false;
-		ip_set_update_counter(counter, ext, flags);
 	}
 	if (SET_WITH_SKBINFO(set))
 		ip_set_get_skbinfo(ext_skbinfo(data, set),

net/netfilter/ipvs/ip_vs_core.c

@@ -742,12 +742,12 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af,
 		struct dst_entry *dst = skb_dst(skb);
 
 		if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) &&
-		    ip6_route_me_harder(ipvs->net, skb) != 0)
+		    ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0)
 			return 1;
 	} else
 #endif
 		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
-		    ip_route_me_harder(ipvs->net, skb, RTN_LOCAL) != 0)
+		    ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0)
 			return 1;
 
 	return 0;

net/netfilter/nf_nat_proto.c

@@ -715,7 +715,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb,
 
 		if (ct->tuplehash[dir].tuple.dst.u3.ip !=
 		    ct->tuplehash[!dir].tuple.src.u3.ip) {
-			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+			err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}
@@ -953,7 +953,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
 
 		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
 				      &ct->tuplehash[!dir].tuple.src.u3)) {
-			err = nf_ip6_route_me_harder(state->net, skb);
+			err = nf_ip6_route_me_harder(state->net, state->sk, skb);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}

net/netfilter/nf_synproxy_core.c

@@ -446,7 +446,7 @@ synproxy_send_tcp(struct net *net,
 
 	skb_dst_set_noref(nskb, skb_dst(skb));
 	nskb->protocol = htons(ETH_P_IP);
-	if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
+	if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC))
 		goto free_nskb;
 
 	if (nfct) {

net/netfilter/nf_tables_api.c

@@ -7137,7 +7137,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx,
 			GFP_KERNEL);
 	kfree(buf);
 
-	if (ctx->report &&
+	if (!ctx->report &&
 	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
 		return;
 
@@ -7259,7 +7259,7 @@ static void nf_tables_gen_notify(struct net *net, struct sk_buff *skb,
 	audit_log_nfcfg("?:0;?:0", 0, net->nft.base_seq,
 			AUDIT_NFT_OP_GEN_REGISTER, GFP_KERNEL);
 
-	if (nlmsg_report(nlh) &&
+	if (!nlmsg_report(nlh) &&
 	    !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
 		return;
 
@@ -8053,12 +8053,16 @@ static void nf_tables_abort_release(struct nft_trans *trans)
 	kfree(trans);
 }
 
-static int __nf_tables_abort(struct net *net, bool autoload)
+static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 {
 	struct nft_trans *trans, *next;
 	struct nft_trans_elem *te;
 	struct nft_hook *hook;
 
+	if (action == NFNL_ABORT_VALIDATE &&
+	    nf_tables_validate(net) < 0)
+		return -EAGAIN;
+
 	list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list,
 					 list) {
 		switch (trans->msg_type) {
@@ -8190,7 +8194,7 @@ static int __nf_tables_abort(struct net *net, bool autoload)
 		nf_tables_abort_release(trans);
 	}
 
-	if (autoload)
+	if (action == NFNL_ABORT_AUTOLOAD)
 		nf_tables_module_autoload(net);
 	else
 		nf_tables_module_autoload_cleanup(net);
@@ -8203,9 +8207,10 @@ static void nf_tables_cleanup(struct net *net)
 	nft_validate_state_update(net, NFT_VALIDATE_SKIP);
 }
 
-static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload)
+static int nf_tables_abort(struct net *net, struct sk_buff *skb,
+			   enum nfnl_abort_action action)
 {
-	int ret = __nf_tables_abort(net, autoload);
+	int ret = __nf_tables_abort(net, action);
 
 	mutex_unlock(&net->nft.commit_mutex);
 
@@ -8836,7 +8841,7 @@ static void __net_exit nf_tables_exit_net(struct net *net)
 {
 	mutex_lock(&net->nft.commit_mutex);
 	if (!list_empty(&net->nft.commit_list))
-		__nf_tables_abort(net, false);
+		__nf_tables_abort(net, NFNL_ABORT_NONE);
 	__nft_release_tables(net);
 	mutex_unlock(&net->nft.commit_mutex);
 	WARN_ON_ONCE(!list_empty(&net->nft.tables));

net/netfilter/nfnetlink.c

@@ -333,7 +333,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return netlink_ack(skb, nlh, -EINVAL, NULL);
 replay:
 	status = 0;
-
+replay_abort:
 	skb = netlink_skb_clone(oskb, GFP_KERNEL);
 	if (!skb)
 		return netlink_ack(oskb, nlh, -ENOMEM, NULL);
@@ -499,7 +499,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 done:
 	if (status & NFNL_BATCH_REPLAY) {
-		ss->abort(net, oskb, true);
+		ss->abort(net, oskb, NFNL_ABORT_AUTOLOAD);
 		nfnl_err_reset(&err_list);
 		kfree_skb(skb);
 		module_put(ss->owner);
@@ -510,11 +510,25 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
 			status |= NFNL_BATCH_REPLAY;
 			goto done;
 		} else if (err) {
-			ss->abort(net, oskb, false);
+			ss->abort(net, oskb, NFNL_ABORT_NONE);
 			netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL);
 		}
 	} else {
-		ss->abort(net, oskb, false);
+		enum nfnl_abort_action abort_action;
+
+		if (status & NFNL_BATCH_FAILURE)
+			abort_action = NFNL_ABORT_NONE;
+		else
+			abort_action = NFNL_ABORT_VALIDATE;
+
+		err = ss->abort(net, oskb, abort_action);
+		if (err == -EAGAIN) {
+			nfnl_err_reset(&err_list);
+			kfree_skb(skb);
+			module_put(ss->owner);
+			status |= NFNL_BATCH_FAILURE;
+			goto replay_abort;
+		}
 	}
 	if (ss->cleanup)
 		ss->cleanup(net);

net/netfilter/nft_chain_route.c

@@ -42,7 +42,7 @@ static unsigned int nf_route_table_hook4(void *priv,
 		    iph->daddr != daddr ||
 		    skb->mark != mark ||
 		    iph->tos != tos) {
-			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+			err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}
@@ -92,7 +92,7 @@ static unsigned int nf_route_table_hook6(void *priv,
 	     skb->mark != mark ||
 	     ipv6_hdr(skb)->hop_limit != hop_limit ||
 	     flowlabel != *((u32 *)ipv6_hdr(skb)))) {
-		err = nf_ip6_route_me_harder(state->net, skb);
+		err = nf_ip6_route_me_harder(state->net, state->sk, skb);
 		if (err < 0)
 			ret = NF_DROP_ERR(err);
 	}

net/netfilter/utils.c

@@ -191,8 +191,8 @@ static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry
 		      skb->mark == rt_info->mark &&
 		      iph->daddr == rt_info->daddr &&
 		      iph->saddr == rt_info->saddr))
-			return ip_route_me_harder(entry->state.net, skb,
-						  RTN_UNSPEC);
+			return ip_route_me_harder(entry->state.net, entry->state.sk,
+						  skb, RTN_UNSPEC);
 	}
 #endif
 	return 0;

tools/testing/selftests/wireguard/netns.sh

@@ -316,6 +316,14 @@ pp sleep 3
 n2 ping -W 1 -c 1 192.168.241.1
 n1 wg set wg0 peer "$pub2" persistent-keepalive 0
 
+# Test that sk_bound_dev_if works
+n1 ping -I wg0 -c 1 -W 1 192.168.241.2
+# What about when the mark changes and the packet must be rerouted?
+n1 iptables -t mangle -I OUTPUT -j MARK --set-xmark 1
+n1 ping -c 1 -W 1 192.168.241.2 # First the boring case
+n1 ping -I wg0 -c 1 -W 1 192.168.241.2 # Then the sk_bound_dev_if case
+n1 iptables -t mangle -D OUTPUT -j MARK --set-xmark 1
+
 # Test that onion routing works, even when it loops
 n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5
 ip1 addr add 192.168.242.1/24 dev wg0

tools/testing/selftests/wireguard/qemu/kernel.config

@@ -18,10 +18,12 @@ CONFIG_NF_NAT=y
 CONFIG_NETFILTER_XTABLES=y
 CONFIG_NETFILTER_XT_NAT=y
 CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MARK=y
 CONFIG_NF_CONNTRACK_IPV4=y
 CONFIG_NF_NAT_IPV4=y
 CONFIG_IP_NF_IPTABLES=y
 CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_MANGLE=y
 CONFIG_IP_NF_NAT=y
 CONFIG_IP_ADVANCED_ROUTER=y
 CONFIG_IP_MULTIPLE_TABLES=y