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:

1) Infinite loop in IPVS when net namespace is released, from
   Tan Hu.

2) Do not show negative timeouts in ip_vs_conn by using the new
   jiffies_delta_to_msecs(), patches from Matteo Croce.

3) Set F_IFACE flag for linklocal addresses in ip6t_rpfilter,
   from Florian Westphal.

4) Fix overflow in set size allocation, from Taehee Yoo.

5) Use netlink_dump_start() from ctnetlink to fix memleak from
   the error path, again from Florian.

6) Register nfnetlink_subsys in last place, otherwise netns
   init path may lose race and see net->nft uninitialized data.
   This also reverts previous attempt to fix this by increase
   netns refcount, patches from Florian.

7) Remove conntrack entries on layer 4 protocol tracker module
   removal, from Florian.

8) Use GFP_KERNEL_ACCOUNT for xtables blob allocation, from
   Michal Hocko.

9) Get tproxy documentation in sync with existing codebase,
   from Mate Eckl.

10) Honor preset layer 3 protocol via ctx->family in the new nft_ct
    timeout infrastructure, from Harsha Sharma.

11) Let uapi nfnetlink_osf.h compile standalone with no errors,
    from Dmitry V. Levin.

12) Missing braces compilation warning in nft_tproxy, patch from
    Mate Eclk.

13) Disregard bogus check to bail out on non-anonymous sets from
    the dynamic set update extension.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/tproxy.txt

@@ -5,19 +5,28 @@ This feature adds Linux 2.2-like transparent proxy support to current kernels.
 To use it, enable the socket match and the TPROXY target in your kernel config.
 You will need policy routing too, so be sure to enable that as well.
 
+From Linux 4.18 transparent proxy support is also available in nf_tables.
 
 1. Making non-local sockets work
 ================================
 
 The idea is that you identify packets with destination address matching a local
-socket on your box, set the packet mark to a certain value, and then match on that
-value using policy routing to have those packets delivered locally:
+socket on your box, set the packet mark to a certain value:
 
 # iptables -t mangle -N DIVERT
 # iptables -t mangle -A PREROUTING -p tcp -m socket -j DIVERT
 # iptables -t mangle -A DIVERT -j MARK --set-mark 1
 # iptables -t mangle -A DIVERT -j ACCEPT
 
+Alternatively you can do this in nft with the following commands:
+
+# nft add table filter
+# nft add chain filter divert "{ type filter hook prerouting priority -150; }"
+# nft add rule filter divert meta l4proto tcp socket transparent 1 meta mark set 1 accept
+
+And then match on that value using policy routing to have those packets
+delivered locally:
+
 # ip rule add fwmark 1 lookup 100
 # ip route add local 0.0.0.0/0 dev lo table 100
 
@@ -57,17 +66,28 @@ add rules like this to the iptables ruleset above:
 # iptables -t mangle -A PREROUTING -p tcp --dport 80 -j TPROXY \
   --tproxy-mark 0x1/0x1 --on-port 50080
 
+Or the following rule to nft:
+
+# nft add rule filter divert tcp dport 80 tproxy to :50080 meta mark set 1 accept
+
 Note that for this to work you'll have to modify the proxy to enable (SOL_IP,
 IP_TRANSPARENT) for the listening socket.
 
+As an example implementation, tcprdr is available here:
+https://git.breakpoint.cc/cgit/fw/tcprdr.git/
+This tool is written by Florian Westphal and it was used for testing during the
+nf_tables implementation.
 
-3. Iptables extensions
-======================
+3. Iptables and nf_tables extensions
+====================================
 
-To use tproxy you'll need to have the 'socket' and 'TPROXY' modules
-compiled for iptables. A patched version of iptables is available
-here: http://git.balabit.hu/?p=bazsi/iptables-tproxy.git
+To use tproxy you'll need to have the following modules compiled for iptables:
+ - NETFILTER_XT_MATCH_SOCKET
+ - NETFILTER_XT_TARGET_TPROXY
 
+Or the floowing modules for nf_tables:
+ - NFT_SOCKET
+ - NFT_TPROXY
 
 4. Application support
 ======================

include/linux/jiffies.h

@@ -447,6 +447,11 @@ static inline clock_t jiffies_delta_to_clock_t(long delta)
 	return jiffies_to_clock_t(max(0L, delta));
 }
 
+static inline unsigned int jiffies_delta_to_msecs(long delta)
+{
+	return jiffies_to_msecs(max(0L, delta));
+}
+
 extern unsigned long clock_t_to_jiffies(unsigned long x);
 extern u64 jiffies_64_to_clock_t(u64 x);
 extern u64 nsec_to_clock_t(u64 x);

include/net/netfilter/nf_tables.h

@@ -274,7 +274,7 @@ enum nft_set_class {
  *	@space: memory class
  */
 struct nft_set_estimate {
-	unsigned int		size;
+	u64			size;
 	enum nft_set_class	lookup;
 	enum nft_set_class	space;
 };
@@ -336,7 +336,7 @@ struct nft_set_ops {
 					       const struct nft_set_elem *elem,
 					       unsigned int flags);
 
-	unsigned int			(*privsize)(const struct nlattr * const nla[],
+	u64				(*privsize)(const struct nlattr * const nla[],
 						    const struct nft_set_desc *desc);
 	bool				(*estimate)(const struct nft_set_desc *desc,
 						    u32 features,
@@ -1374,6 +1374,6 @@ struct nft_trans_flowtable {
 	(((struct nft_trans_flowtable *)trans->data)->flowtable)
 
 int __init nft_chain_filter_init(void);
-void __exit nft_chain_filter_fini(void);
+void nft_chain_filter_fini(void);
 
 #endif /* _NET_NF_TABLES_H */

include/uapi/linux/netfilter/nfnetlink_osf.h

@@ -2,6 +2,8 @@
 #define _NF_OSF_H
 
 #include <linux/types.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
 
 #define MAXGENRELEN	32
 

include/uapi/linux/netfilter/xt_osf.h

@@ -21,8 +21,6 @@
 #define _XT_OSF_H
 
 #include <linux/types.h>
-#include <linux/ip.h>
-#include <linux/tcp.h>
 #include <linux/netfilter/nfnetlink_osf.h>
 
 #define XT_OSF_GENRE		NF_OSF_GENRE

net/ipv6/netfilter/ip6t_rpfilter.c

@@ -26,6 +26,12 @@ static bool rpfilter_addr_unicast(const struct in6_addr *addr)
 	return addr_type & IPV6_ADDR_UNICAST;
 }
 
+static bool rpfilter_addr_linklocal(const struct in6_addr *addr)
+{
+	int addr_type = ipv6_addr_type(addr);
+	return addr_type & IPV6_ADDR_LINKLOCAL;
+}
+
 static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb,
 				     const struct net_device *dev, u8 flags)
 {
@@ -48,7 +54,11 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb,
 	}
 
 	fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
-	if ((flags & XT_RPFILTER_LOOSE) == 0)
+
+	if (rpfilter_addr_linklocal(&iph->saddr)) {
+		lookup_flags |= RT6_LOOKUP_F_IFACE;
+		fl6.flowi6_oif = dev->ifindex;
+	} else if ((flags & XT_RPFILTER_LOOSE) == 0)
 		fl6.flowi6_oif = dev->ifindex;
 
 	rt = (void *)ip6_route_lookup(net, &fl6, skb, lookup_flags);

net/netfilter/ipvs/ip_vs_conn.c

@@ -1117,24 +1117,28 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v)
 #ifdef CONFIG_IP_VS_IPV6
 		if (cp->af == AF_INET6)
 			seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X "
-				"%s %04X %-11s %7lu%s\n",
+				"%s %04X %-11s %7u%s\n",
 				ip_vs_proto_name(cp->protocol),
 				&cp->caddr.in6, ntohs(cp->cport),
 				&cp->vaddr.in6, ntohs(cp->vport),
 				dbuf, ntohs(cp->dport),
 				ip_vs_state_name(cp),
-				(cp->timer.expires-jiffies)/HZ, pe_data);
+				jiffies_delta_to_msecs(cp->timer.expires -
+						       jiffies) / 1000,
+				pe_data);
 		else
 #endif
 			seq_printf(seq,
 				"%-3s %08X %04X %08X %04X"
-				" %s %04X %-11s %7lu%s\n",
+				" %s %04X %-11s %7u%s\n",
 				ip_vs_proto_name(cp->protocol),
 				ntohl(cp->caddr.ip), ntohs(cp->cport),
 				ntohl(cp->vaddr.ip), ntohs(cp->vport),
 				dbuf, ntohs(cp->dport),
 				ip_vs_state_name(cp),
-				(cp->timer.expires-jiffies)/HZ, pe_data);
+				jiffies_delta_to_msecs(cp->timer.expires -
+						       jiffies) / 1000,
+				pe_data);
 	}
 	return 0;
 }
@@ -1179,26 +1183,28 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v)
 #ifdef CONFIG_IP_VS_IPV6
 		if (cp->af == AF_INET6)
 			seq_printf(seq, "%-3s %pI6 %04X %pI6 %04X "
-				"%s %04X %-11s %-6s %7lu\n",
+				"%s %04X %-11s %-6s %7u\n",
 				ip_vs_proto_name(cp->protocol),
 				&cp->caddr.in6, ntohs(cp->cport),
 				&cp->vaddr.in6, ntohs(cp->vport),
 				dbuf, ntohs(cp->dport),
 				ip_vs_state_name(cp),
 				ip_vs_origin_name(cp->flags),
-				(cp->timer.expires-jiffies)/HZ);
+				jiffies_delta_to_msecs(cp->timer.expires -
+						       jiffies) / 1000);
 		else
 #endif
 			seq_printf(seq,
 				"%-3s %08X %04X %08X %04X "
-				"%s %04X %-11s %-6s %7lu\n",
+				"%s %04X %-11s %-6s %7u\n",
 				ip_vs_proto_name(cp->protocol),
 				ntohl(cp->caddr.ip), ntohs(cp->cport),
 				ntohl(cp->vaddr.ip), ntohs(cp->vport),
 				dbuf, ntohs(cp->dport),
 				ip_vs_state_name(cp),
 				ip_vs_origin_name(cp->flags),
-				(cp->timer.expires-jiffies)/HZ);
+				jiffies_delta_to_msecs(cp->timer.expires -
+						       jiffies) / 1000);
 	}
 	return 0;
 }

net/netfilter/ipvs/ip_vs_core.c

@@ -1972,13 +1972,20 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
 	if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
 		/* the destination server is not available */
 
-		if (sysctl_expire_nodest_conn(ipvs)) {
+		__u32 flags = cp->flags;
+
+		/* when timer already started, silently drop the packet.*/
+		if (timer_pending(&cp->timer))
+			__ip_vs_conn_put(cp);
+		else
+			ip_vs_conn_put(cp);
+
+		if (sysctl_expire_nodest_conn(ipvs) &&
+		    !(flags & IP_VS_CONN_F_ONE_PACKET)) {
 			/* try to expire the connection immediately */
 			ip_vs_conn_expire_now(cp);
 		}
-		/* don't restart its timer, and silently
-		   drop the packet. */
-		__ip_vs_conn_put(cp);
+
 		return NF_DROP;
 	}
 

net/netfilter/nf_conntrack_netlink.c

@@ -846,6 +846,21 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[])
 #endif
 }
 
+static int ctnetlink_start(struct netlink_callback *cb)
+{
+	const struct nlattr * const *cda = cb->data;
+	struct ctnetlink_filter *filter = NULL;
+
+	if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) {
+		filter = ctnetlink_alloc_filter(cda);
+		if (IS_ERR(filter))
+			return PTR_ERR(filter);
+	}
+
+	cb->data = filter;
+	return 0;
+}
+
 static int ctnetlink_filter_match(struct nf_conn *ct, void *data)
 {
 	struct ctnetlink_filter *filter = data;
@@ -1290,19 +1305,12 @@ static int ctnetlink_get_conntrack(struct net *net, struct sock *ctnl,
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
+			.start = ctnetlink_start,
 			.dump = ctnetlink_dump_table,
 			.done = ctnetlink_done,
+			.data = (void *)cda,
 		};
 
-		if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) {
-			struct ctnetlink_filter *filter;
-
-			filter = ctnetlink_alloc_filter(cda);
-			if (IS_ERR(filter))
-				return PTR_ERR(filter);
-
-			c.data = filter;
-		}
 		return netlink_dump_start(ctnl, skb, nlh, &c);
 	}
 

net/netfilter/nf_conntrack_proto.c

@@ -312,7 +312,9 @@ void nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *l4proto)
 	__nf_ct_l4proto_unregister_one(l4proto);
 	mutex_unlock(&nf_ct_proto_mutex);
 
-	synchronize_rcu();
+	synchronize_net();
+	/* Remove all contrack entries for this protocol */
+	nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto);
 }
 EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister_one);
 
@@ -333,14 +335,17 @@ static void
 nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const l4proto[],
 			 unsigned int num_proto)
 {
+	int i;
+
 	mutex_lock(&nf_ct_proto_mutex);
-	while (num_proto-- != 0)
-		__nf_ct_l4proto_unregister_one(l4proto[num_proto]);
+	for (i = 0; i < num_proto; i++)
+		__nf_ct_l4proto_unregister_one(l4proto[i]);
 	mutex_unlock(&nf_ct_proto_mutex);
 
 	synchronize_net();
-	/* Remove all contrack entries for this protocol */
-	nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto);
+
+	for (i = 0; i < num_proto; i++)
+		nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto[i]);
 }
 
 static int

net/netfilter/nf_tables_api.c

@@ -3354,7 +3354,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 	struct nft_set *set;
 	struct nft_ctx ctx;
 	char *name;
-	unsigned int size;
+	u64 size;
 	u64 timeout;
 	u32 ktype, dtype, flags, policy, gc_int, objtype;
 	struct nft_set_desc desc;
@@ -5925,18 +5925,15 @@ static int nf_tables_flowtable_event(struct notifier_block *this,
 	if (event != NETDEV_UNREGISTER)
 		return 0;
 
-	net = maybe_get_net(dev_net(dev));
-	if (!net)
-		return 0;
-
+	net = dev_net(dev);
 	mutex_lock(&net->nft.commit_mutex);
 	list_for_each_entry(table, &net->nft.tables, list) {
 		list_for_each_entry(flowtable, &table->flowtables, list) {
 			nft_flowtable_event(event, dev, flowtable);
 		}
 	}
 	mutex_unlock(&net->nft.commit_mutex);
-	put_net(net);
+
 	return NOTIFY_DONE;
 }
 
@@ -7273,21 +7270,36 @@ static int __init nf_tables_module_init(void)
 {
 	int err;
 
-	nft_chain_filter_init();
+	err = register_pernet_subsys(&nf_tables_net_ops);
+	if (err < 0)
+		return err;
+
+	err = nft_chain_filter_init();
+	if (err < 0)
+		goto err1;
 
 	err = nf_tables_core_module_init();
 	if (err < 0)
-		return err;
+		goto err2;
 
-	err = nfnetlink_subsys_register(&nf_tables_subsys);
+	err = register_netdevice_notifier(&nf_tables_flowtable_notifier);
 	if (err < 0)
-		goto err;
+		goto err3;
 
-	register_netdevice_notifier(&nf_tables_flowtable_notifier);
+	/* must be last */
+	err = nfnetlink_subsys_register(&nf_tables_subsys);
+	if (err < 0)
+		goto err4;
 
-	return register_pernet_subsys(&nf_tables_net_ops);
-err:
+	return err;
+err4:
+	unregister_netdevice_notifier(&nf_tables_flowtable_notifier);
+err3:
 	nf_tables_core_module_exit();
+err2:
+	nft_chain_filter_fini();
+err1:
+	unregister_pernet_subsys(&nf_tables_net_ops);
 	return err;
 }