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

Pablo Neira Ayuso says:

====================
Netfilter/IPVS fixes for net

The following patchset contains Netfilter/IPVS fixes for your net tree,
they are:

1) Fix SIP conntrack with phones sending session descriptions for different
   media types but same port numbers, from Florian Westphal.

2) Fix incorrect rtnl_lock mutex logic from IPVS sync thread, from Julian
   Anastasov.

3) Skip compat array allocation in ebtables if there is no entries, also
   from Florian.

4) Do not lose left/right bits when shifting marks from xt_connmark, from
   Jack Ma.

5) Silence false positive memleak in conntrack extensions, from Cong Wang.

6) Fix CONFIG_NF_REJECT_IPV6=m link problems, from Arnd Bergmann.

7) Cannot kfree rule that is already in list in nf_tables, switch order
   so this error handling is not required, from Florian Westphal.

8) Release set name in error path, from Florian.

9) include kmemleak.h in nf_conntrack_extend.c, from Stepheh Rothwell.

10) NAT chain and extensions depend on NF_TABLES.

11) Out of bound access when renaming chains, from Taehee Yoo.

12) Incorrect casting in xt_connmark leads to wrong bitshifting.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

net/bridge/netfilter/ebtables.c

@@ -1825,13 +1825,14 @@ static int compat_table_info(const struct ebt_table_info *info,
 {
 	unsigned int size = info->entries_size;
 	const void *entries = info->entries;
-	int ret;
 
 	newinfo->entries_size = size;
-
-	ret = xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries);
-	if (ret)
-		return ret;
+	if (info->nentries) {
+		int ret = xt_compat_init_offsets(NFPROTO_BRIDGE,
+						 info->nentries);
+		if (ret)
+			return ret;
+	}
 
 	return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info,
 							entries, newinfo);

net/ipv6/netfilter/Kconfig

@@ -48,6 +48,34 @@ config NFT_CHAIN_ROUTE_IPV6
 	  fields such as the source, destination, flowlabel, hop-limit and
 	  the packet mark.
 
+if NF_NAT_IPV6
+
+config NFT_CHAIN_NAT_IPV6
+	tristate "IPv6 nf_tables nat chain support"
+	help
+	  This option enables the "nat" chain for IPv6 in nf_tables. This
+	  chain type is used to perform Network Address Translation (NAT)
+	  packet transformations such as the source, destination address and
+	  source and destination ports.
+
+config NFT_MASQ_IPV6
+	tristate "IPv6 masquerade support for nf_tables"
+	depends on NFT_MASQ
+	select NF_NAT_MASQUERADE_IPV6
+	help
+	  This is the expression that provides IPv4 masquerading support for
+	  nf_tables.
+
+config NFT_REDIR_IPV6
+	tristate "IPv6 redirect support for nf_tables"
+	depends on NFT_REDIR
+	select NF_NAT_REDIRECT
+	help
+	  This is the expression that provides IPv4 redirect support for
+	  nf_tables.
+
+endif # NF_NAT_IPV6
+
 config NFT_REJECT_IPV6
 	select NF_REJECT_IPV6
 	default NFT_REJECT
@@ -107,39 +135,12 @@ config NF_NAT_IPV6
 
 if NF_NAT_IPV6
 
-config NFT_CHAIN_NAT_IPV6
-	depends on NF_TABLES_IPV6
-	tristate "IPv6 nf_tables nat chain support"
-	help
-	  This option enables the "nat" chain for IPv6 in nf_tables. This
-	  chain type is used to perform Network Address Translation (NAT)
-	  packet transformations such as the source, destination address and
-	  source and destination ports.
-
 config NF_NAT_MASQUERADE_IPV6
 	tristate "IPv6 masquerade support"
 	help
 	  This is the kernel functionality to provide NAT in the masquerade
 	  flavour (automatic source address selection) for IPv6.
 
-config NFT_MASQ_IPV6
-	tristate "IPv6 masquerade support for nf_tables"
-	depends on NF_TABLES_IPV6
-	depends on NFT_MASQ
-	select NF_NAT_MASQUERADE_IPV6
-	help
-	  This is the expression that provides IPv4 masquerading support for
-	  nf_tables.
-
-config NFT_REDIR_IPV6
-	tristate "IPv6 redirect support for nf_tables"
-	depends on NF_TABLES_IPV6
-	depends on NFT_REDIR
-	select NF_NAT_REDIRECT
-	help
-	  This is the expression that provides IPv4 redirect support for
-	  nf_tables.
-
 endif # NF_NAT_IPV6
 
 config IP6_NF_IPTABLES

net/netfilter/Kconfig

@@ -594,6 +594,7 @@ config NFT_QUOTA
 config NFT_REJECT
 	default m if NETFILTER_ADVANCED=n
 	tristate "Netfilter nf_tables reject support"
+	depends on !NF_TABLES_INET || (IPV6!=m || m)
 	help
 	  This option adds the "reject" expression that you can use to
 	  explicitly deny and notify via TCP reset/ICMP informational errors

net/netfilter/ipvs/ip_vs_ctl.c

@@ -2384,11 +2384,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 			strlcpy(cfg.mcast_ifn, dm->mcast_ifn,
 				sizeof(cfg.mcast_ifn));
 			cfg.syncid = dm->syncid;
-			rtnl_lock();
-			mutex_lock(&ipvs->sync_mutex);
 			ret = start_sync_thread(ipvs, &cfg, dm->state);
-			mutex_unlock(&ipvs->sync_mutex);
-			rtnl_unlock();
 		} else {
 			mutex_lock(&ipvs->sync_mutex);
 			ret = stop_sync_thread(ipvs, dm->state);
@@ -3481,12 +3477,8 @@ static int ip_vs_genl_new_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs)
 	if (ipvs->mixed_address_family_dests > 0)
 		return -EINVAL;
 
-	rtnl_lock();
-	mutex_lock(&ipvs->sync_mutex);
 	ret = start_sync_thread(ipvs, &c,
 				nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
-	mutex_unlock(&ipvs->sync_mutex);
-	rtnl_unlock();
 	return ret;
 }
 

net/netfilter/ipvs/ip_vs_sync.c

@@ -49,6 +49,7 @@
 #include <linux/kthread.h>
 #include <linux/wait.h>
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 
 #include <asm/unaligned.h>		/* Used for ntoh_seq and hton_seq */
 
@@ -1360,15 +1361,9 @@ static void set_mcast_pmtudisc(struct sock *sk, int val)
 /*
  *      Specifiy default interface for outgoing multicasts
  */
-static int set_mcast_if(struct sock *sk, char *ifname)
+static int set_mcast_if(struct sock *sk, struct net_device *dev)
 {
-	struct net_device *dev;
 	struct inet_sock *inet = inet_sk(sk);
-	struct net *net = sock_net(sk);
-
-	dev = __dev_get_by_name(net, ifname);
-	if (!dev)
-		return -ENODEV;
 
 	if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
 		return -EINVAL;
@@ -1396,19 +1391,14 @@ static int set_mcast_if(struct sock *sk, char *ifname)
  *      in the in_addr structure passed in as a parameter.
  */
 static int
-join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
+join_mcast_group(struct sock *sk, struct in_addr *addr, struct net_device *dev)
 {
-	struct net *net = sock_net(sk);
 	struct ip_mreqn mreq;
-	struct net_device *dev;
 	int ret;
 
 	memset(&mreq, 0, sizeof(mreq));
 	memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr));
 
-	dev = __dev_get_by_name(net, ifname);
-	if (!dev)
-		return -ENODEV;
 	if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
 		return -EINVAL;
 
@@ -1423,15 +1413,10 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
 
 #ifdef CONFIG_IP_VS_IPV6
 static int join_mcast_group6(struct sock *sk, struct in6_addr *addr,
-			     char *ifname)
+			     struct net_device *dev)
 {
-	struct net *net = sock_net(sk);
-	struct net_device *dev;
 	int ret;
 
-	dev = __dev_get_by_name(net, ifname);
-	if (!dev)
-		return -ENODEV;
 	if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
 		return -EINVAL;
 
@@ -1443,24 +1428,18 @@ static int join_mcast_group6(struct sock *sk, struct in6_addr *addr,
 }
 #endif
 
-static int bind_mcastif_addr(struct socket *sock, char *ifname)
+static int bind_mcastif_addr(struct socket *sock, struct net_device *dev)
 {
-	struct net *net = sock_net(sock->sk);
-	struct net_device *dev;
 	__be32 addr;
 	struct sockaddr_in sin;
 
-	dev = __dev_get_by_name(net, ifname);
-	if (!dev)
-		return -ENODEV;
-
 	addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
 	if (!addr)
 		pr_err("You probably need to specify IP address on "
 		       "multicast interface.\n");
 
 	IP_VS_DBG(7, "binding socket with (%s) %pI4\n",
-		  ifname, &addr);
+		  dev->name, &addr);
 
 	/* Now bind the socket with the address of multicast interface */
 	sin.sin_family	     = AF_INET;
@@ -1493,7 +1472,8 @@ static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen,
 /*
  *      Set up sending multicast socket over UDP
  */
-static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
+static int make_send_sock(struct netns_ipvs *ipvs, int id,
+			  struct net_device *dev, struct socket **sock_ret)
 {
 	/* multicast addr */
 	union ipvs_sockaddr mcast_addr;
@@ -1505,9 +1485,10 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
 				  IPPROTO_UDP, &sock);
 	if (result < 0) {
 		pr_err("Error during creation of socket; terminating\n");
-		return ERR_PTR(result);
+		goto error;
 	}
-	result = set_mcast_if(sock->sk, ipvs->mcfg.mcast_ifn);
+	*sock_ret = sock;
+	result = set_mcast_if(sock->sk, dev);
 	if (result < 0) {
 		pr_err("Error setting outbound mcast interface\n");
 		goto error;
@@ -1522,7 +1503,7 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
 		set_sock_size(sock->sk, 1, result);
 
 	if (AF_INET == ipvs->mcfg.mcast_af)
-		result = bind_mcastif_addr(sock, ipvs->mcfg.mcast_ifn);
+		result = bind_mcastif_addr(sock, dev);
 	else
 		result = 0;
 	if (result < 0) {
@@ -1538,19 +1519,18 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
 		goto error;
 	}
 
-	return sock;
+	return 0;
 
 error:
-	sock_release(sock);
-	return ERR_PTR(result);
+	return result;
 }
 
 
 /*
  *      Set up receiving multicast socket over UDP
  */
-static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
-					int ifindex)
+static int make_receive_sock(struct netns_ipvs *ipvs, int id,
+			     struct net_device *dev, struct socket **sock_ret)
 {
 	/* multicast addr */
 	union ipvs_sockaddr mcast_addr;
@@ -1562,8 +1542,9 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
 				  IPPROTO_UDP, &sock);
 	if (result < 0) {
 		pr_err("Error during creation of socket; terminating\n");
-		return ERR_PTR(result);
+		goto error;
 	}
+	*sock_ret = sock;
 	/* it is equivalent to the REUSEADDR option in user-space */
 	sock->sk->sk_reuse = SK_CAN_REUSE;
 	result = sysctl_sync_sock_size(ipvs);
@@ -1571,7 +1552,7 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
 		set_sock_size(sock->sk, 0, result);
 
 	get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id);
-	sock->sk->sk_bound_dev_if = ifindex;
+	sock->sk->sk_bound_dev_if = dev->ifindex;
 	result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen);
 	if (result < 0) {
 		pr_err("Error binding to the multicast addr\n");
@@ -1582,21 +1563,20 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
 #ifdef CONFIG_IP_VS_IPV6
 	if (ipvs->bcfg.mcast_af == AF_INET6)
 		result = join_mcast_group6(sock->sk, &mcast_addr.in6.sin6_addr,
-					   ipvs->bcfg.mcast_ifn);
+					   dev);
 	else
 #endif
 		result = join_mcast_group(sock->sk, &mcast_addr.in.sin_addr,
-					  ipvs->bcfg.mcast_ifn);
+					  dev);
 	if (result < 0) {
 		pr_err("Error joining to the multicast group\n");
 		goto error;
 	}
 
-	return sock;
+	return 0;
 
 error:
-	sock_release(sock);
-	return ERR_PTR(result);
+	return result;
 }
 
 
@@ -1778,13 +1758,12 @@ static int sync_thread_backup(void *data)
 int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 		      int state)
 {
-	struct ip_vs_sync_thread_data *tinfo;
+	struct ip_vs_sync_thread_data *tinfo = NULL;
 	struct task_struct **array = NULL, *task;
-	struct socket *sock;
 	struct net_device *dev;
 	char *name;
 	int (*threadfn)(void *data);
-	int id, count, hlen;
+	int id = 0, count, hlen;
 	int result = -ENOMEM;
 	u16 mtu, min_mtu;
 
@@ -1792,6 +1771,18 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 	IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n",
 		  sizeof(struct ip_vs_sync_conn_v0));
 
+	/* Do not hold one mutex and then to block on another */
+	for (;;) {
+		rtnl_lock();
+		if (mutex_trylock(&ipvs->sync_mutex))
+			break;
+		rtnl_unlock();
+		mutex_lock(&ipvs->sync_mutex);
+		if (rtnl_trylock())
+			break;
+		mutex_unlock(&ipvs->sync_mutex);
+	}
+
 	if (!ipvs->sync_state) {
 		count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX);
 		ipvs->threads_mask = count - 1;
@@ -1810,7 +1801,8 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 	dev = __dev_get_by_name(ipvs->net, c->mcast_ifn);
 	if (!dev) {
 		pr_err("Unknown mcast interface: %s\n", c->mcast_ifn);
-		return -ENODEV;
+		result = -ENODEV;
+		goto out_early;
 	}
 	hlen = (AF_INET6 == c->mcast_af) ?
 	       sizeof(struct ipv6hdr) + sizeof(struct udphdr) :
@@ -1827,26 +1819,30 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 		c->sync_maxlen = mtu - hlen;
 
 	if (state == IP_VS_STATE_MASTER) {
+		result = -EEXIST;
 		if (ipvs->ms)
-			return -EEXIST;
+			goto out_early;
 
 		ipvs->mcfg = *c;
 		name = "ipvs-m:%d:%d";
 		threadfn = sync_thread_master;
 	} else if (state == IP_VS_STATE_BACKUP) {
+		result = -EEXIST;
 		if (ipvs->backup_threads)
-			return -EEXIST;
+			goto out_early;
 
 		ipvs->bcfg = *c;
 		name = "ipvs-b:%d:%d";
 		threadfn = sync_thread_backup;
 	} else {
-		return -EINVAL;
+		result = -EINVAL;
+		goto out_early;
 	}
 
 	if (state == IP_VS_STATE_MASTER) {
 		struct ipvs_master_sync_state *ms;
 
+		result = -ENOMEM;
 		ipvs->ms = kcalloc(count, sizeof(ipvs->ms[0]), GFP_KERNEL);
 		if (!ipvs->ms)
 			goto out;
@@ -1862,39 +1858,38 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 	} else {
 		array = kcalloc(count, sizeof(struct task_struct *),
 				GFP_KERNEL);
+		result = -ENOMEM;
 		if (!array)
 			goto out;
 	}
 
-	tinfo = NULL;
 	for (id = 0; id < count; id++) {
-		if (state == IP_VS_STATE_MASTER)
-			sock = make_send_sock(ipvs, id);
-		else
-			sock = make_receive_sock(ipvs, id, dev->ifindex);
-		if (IS_ERR(sock)) {
-			result = PTR_ERR(sock);
-			goto outtinfo;
-		}
+		result = -ENOMEM;
 		tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
 		if (!tinfo)
-			goto outsocket;
+			goto out;
 		tinfo->ipvs = ipvs;
-		tinfo->sock = sock;
+		tinfo->sock = NULL;
 		if (state == IP_VS_STATE_BACKUP) {
 			tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen,
 					     GFP_KERNEL);
 			if (!tinfo->buf)
-				goto outtinfo;
+				goto out;
 		} else {
 			tinfo->buf = NULL;
 		}
 		tinfo->id = id;
+		if (state == IP_VS_STATE_MASTER)
+			result = make_send_sock(ipvs, id, dev, &tinfo->sock);
+		else
+			result = make_receive_sock(ipvs, id, dev, &tinfo->sock);
+		if (result < 0)
+			goto out;
 
 		task = kthread_run(threadfn, tinfo, name, ipvs->gen, id);
 		if (IS_ERR(task)) {
 			result = PTR_ERR(task);
-			goto outtinfo;
+			goto out;
 		}
 		tinfo = NULL;
 		if (state == IP_VS_STATE_MASTER)
@@ -1911,20 +1906,20 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 	ipvs->sync_state |= state;
 	spin_unlock_bh(&ipvs->sync_buff_lock);
 
+	mutex_unlock(&ipvs->sync_mutex);
+	rtnl_unlock();
+
 	/* increase the module use count */
 	ip_vs_use_count_inc();
 
 	return 0;
 
-outsocket:
-	sock_release(sock);
-
-outtinfo:
-	if (tinfo) {
-		sock_release(tinfo->sock);
-		kfree(tinfo->buf);
-		kfree(tinfo);
-	}
+out:
+	/* We do not need RTNL lock anymore, release it here so that
+	 * sock_release below and in the kthreads can use rtnl_lock
+	 * to leave the mcast group.
+	 */
+	rtnl_unlock();
 	count = id;
 	while (count-- > 0) {
 		if (state == IP_VS_STATE_MASTER)
@@ -1932,13 +1927,23 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 		else
 			kthread_stop(array[count]);
 	}
-	kfree(array);
-
-out:
 	if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
 		kfree(ipvs->ms);
 		ipvs->ms = NULL;
 	}
+	mutex_unlock(&ipvs->sync_mutex);
+	if (tinfo) {
+		if (tinfo->sock)
+			sock_release(tinfo->sock);
+		kfree(tinfo->buf);
+		kfree(tinfo);
+	}
+	kfree(array);
+	return result;
+
+out_early:
+	mutex_unlock(&ipvs->sync_mutex);
+	rtnl_unlock();
 	return result;
 }
 

net/netfilter/nf_conntrack_expect.c

@@ -252,7 +252,7 @@ static inline int expect_clash(const struct nf_conntrack_expect *a,
 static inline int expect_matches(const struct nf_conntrack_expect *a,
 				 const struct nf_conntrack_expect *b)
 {
-	return a->master == b->master && a->class == b->class &&
+	return a->master == b->master &&
 	       nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
 	       nf_ct_tuple_mask_equal(&a->mask, &b->mask) &&
 	       net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) &&
@@ -421,6 +421,9 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
 	h = nf_ct_expect_dst_hash(net, &expect->tuple);
 	hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) {
 		if (expect_matches(i, expect)) {
+			if (i->class != expect->class)
+				return -EALREADY;
+
 			if (nf_ct_remove_expect(i))
 				break;
 		} else if (expect_clash(i, expect)) {

net/netfilter/nf_conntrack_extend.c

@@ -9,6 +9,7 @@
  *      2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
+#include <linux/kmemleak.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/rcupdate.h>
@@ -71,6 +72,7 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
 	rcu_read_unlock();
 
 	alloc = max(newlen, NF_CT_EXT_PREALLOC);
+	kmemleak_not_leak(old);
 	new = __krealloc(old, alloc, gfp);
 	if (!new)
 		return NULL;

net/netfilter/nf_conntrack_sip.c

@@ -938,11 +938,19 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
 				       datalen, rtp_exp, rtcp_exp,
 				       mediaoff, medialen, daddr);
 	else {
-		if (nf_ct_expect_related(rtp_exp) == 0) {
-			if (nf_ct_expect_related(rtcp_exp) != 0)
-				nf_ct_unexpect_related(rtp_exp);
-			else
+		/* -EALREADY handling works around end-points that send
+		 * SDP messages with identical port but different media type,
+		 * we pretend expectation was set up.
+		 */
+		int errp = nf_ct_expect_related(rtp_exp);
+
+		if (errp == 0 || errp == -EALREADY) {
+			int errcp = nf_ct_expect_related(rtcp_exp);
+
+			if (errcp == 0 || errcp == -EALREADY)
 				ret = NF_ACCEPT;
+			else if (errp == 0)
+				nf_ct_unexpect_related(rtp_exp);
 		}
 	}
 	nf_ct_expect_put(rtcp_exp);

net/netfilter/nf_tables_api.c

@@ -2361,41 +2361,46 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 	}
 
 	if (nlh->nlmsg_flags & NLM_F_REPLACE) {
-		if (nft_is_active_next(net, old_rule)) {
-			trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
-						   old_rule);
-			if (trans == NULL) {
-				err = -ENOMEM;
-				goto err2;
-			}
-			nft_deactivate_next(net, old_rule);
-			chain->use--;
-			list_add_tail_rcu(&rule->list, &old_rule->list);
-		} else {
+		if (!nft_is_active_next(net, old_rule)) {
 			err = -ENOENT;
 			goto err2;
 		}
-	} else if (nlh->nlmsg_flags & NLM_F_APPEND)
-		if (old_rule)
-			list_add_rcu(&rule->list, &old_rule->list);
-		else
-			list_add_tail_rcu(&rule->list, &chain->rules);
-	else {
-		if (old_rule)
-			list_add_tail_rcu(&rule->list, &old_rule->list);
-		else
-			list_add_rcu(&rule->list, &chain->rules);
-	}
+		trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
+					   old_rule);
+		if (trans == NULL) {
+			err = -ENOMEM;
+			goto err2;
+		}
+		nft_deactivate_next(net, old_rule);
+		chain->use--;
 
-	if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
-		err = -ENOMEM;
-		goto err3;
+		if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
+			err = -ENOMEM;
+			goto err2;
+		}
+
+		list_add_tail_rcu(&rule->list, &old_rule->list);
+	} else {
+		if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
+			err = -ENOMEM;
+			goto err2;
+		}
+
+		if (nlh->nlmsg_flags & NLM_F_APPEND) {
+			if (old_rule)
+				list_add_rcu(&rule->list, &old_rule->list);
+			else
+				list_add_tail_rcu(&rule->list, &chain->rules);
+		 } else {
+			if (old_rule)
+				list_add_tail_rcu(&rule->list, &old_rule->list);
+			else
+				list_add_rcu(&rule->list, &chain->rules);
+		}
 	}
 	chain->use++;
 	return 0;
 
-err3:
-	list_del_rcu(&rule->list);
 err2:
 	nf_tables_rule_destroy(&ctx, rule);
 err1:
@@ -3207,18 +3212,20 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 
 	err = ops->init(set, &desc, nla);
 	if (err < 0)
-		goto err2;
+		goto err3;
 
 	err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
 	if (err < 0)
-		goto err3;
+		goto err4;
 
 	list_add_tail_rcu(&set->list, &table->sets);
 	table->use++;
 	return 0;
 
-err3:
+err4:
 	ops->destroy(set);
+err3:
+	kfree(set->name);
 err2:
 	kvfree(set);
 err1:
@@ -5738,7 +5745,7 @@ static void nft_chain_commit_update(struct nft_trans *trans)
 	struct nft_base_chain *basechain;
 
 	if (nft_trans_chain_name(trans))
-		strcpy(trans->ctx.chain->name, nft_trans_chain_name(trans));
+		swap(trans->ctx.chain->name, nft_trans_chain_name(trans));
 
 	if (!nft_is_base_chain(trans->ctx.chain))
 		return;

net/netfilter/xt_connmark.c

@@ -36,11 +36,10 @@ MODULE_ALIAS("ipt_connmark");
 MODULE_ALIAS("ip6t_connmark");
 
 static unsigned int
-connmark_tg_shift(struct sk_buff *skb,
-		const struct xt_connmark_tginfo1 *info,
-		u8 shift_bits, u8 shift_dir)
+connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info)
 {
 	enum ip_conntrack_info ctinfo;
+	u_int32_t new_targetmark;
 	struct nf_conn *ct;
 	u_int32_t newmark;
 
@@ -51,34 +50,39 @@ connmark_tg_shift(struct sk_buff *skb,
 	switch (info->mode) {
 	case XT_CONNMARK_SET:
 		newmark = (ct->mark & ~info->ctmask) ^ info->ctmark;
-		if (shift_dir == D_SHIFT_RIGHT)
-			newmark >>= shift_bits;
+		if (info->shift_dir == D_SHIFT_RIGHT)
+			newmark >>= info->shift_bits;
 		else
-			newmark <<= shift_bits;
+			newmark <<= info->shift_bits;
+
 		if (ct->mark != newmark) {
 			ct->mark = newmark;
 			nf_conntrack_event_cache(IPCT_MARK, ct);
 		}
 		break;
 	case XT_CONNMARK_SAVE:
-		newmark = (ct->mark & ~info->ctmask) ^
-			  (skb->mark & info->nfmask);
-		if (shift_dir == D_SHIFT_RIGHT)
-			newmark >>= shift_bits;
+		new_targetmark = (skb->mark & info->nfmask);
+		if (info->shift_dir == D_SHIFT_RIGHT)
+			new_targetmark >>= info->shift_bits;
 		else
-			newmark <<= shift_bits;
+			new_targetmark <<= info->shift_bits;
+
+		newmark = (ct->mark & ~info->ctmask) ^
+			  new_targetmark;
 		if (ct->mark != newmark) {
 			ct->mark = newmark;
 			nf_conntrack_event_cache(IPCT_MARK, ct);
 		}
 		break;
 	case XT_CONNMARK_RESTORE:
-		newmark = (skb->mark & ~info->nfmask) ^
-			  (ct->mark & info->ctmask);
-		if (shift_dir == D_SHIFT_RIGHT)
-			newmark >>= shift_bits;
+		new_targetmark = (ct->mark & info->ctmask);
+		if (info->shift_dir == D_SHIFT_RIGHT)
+			new_targetmark >>= info->shift_bits;
 		else
-			newmark <<= shift_bits;
+			new_targetmark <<= info->shift_bits;
+
+		newmark = (skb->mark & ~info->nfmask) ^
+			  new_targetmark;
 		skb->mark = newmark;
 		break;
 	}
@@ -89,8 +93,14 @@ static unsigned int
 connmark_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct xt_connmark_tginfo1 *info = par->targinfo;
-
-	return connmark_tg_shift(skb, info, 0, 0);
+	const struct xt_connmark_tginfo2 info2 = {
+		.ctmark	= info->ctmark,
+		.ctmask	= info->ctmask,
+		.nfmask	= info->nfmask,
+		.mode	= info->mode,
+	};
+
+	return connmark_tg_shift(skb, &info2);
 }
 
 static unsigned int
@@ -98,8 +108,7 @@ connmark_tg_v2(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct xt_connmark_tginfo2 *info = par->targinfo;
 
-	return connmark_tg_shift(skb, (const struct xt_connmark_tginfo1 *)info,
-				 info->shift_bits, info->shift_dir);
+	return connmark_tg_shift(skb, info);
 }
 
 static int connmark_tg_check(const struct xt_tgchk_param *par)