Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nftables

Pablo Neira Ayuso says: <pablo@netfilter.org>

====================
nftables updates for net-next

The following patchset contains nftables updates for your net-next tree,
they are:

* Add set operation to the meta expression by means of the select_ops()
  infrastructure, this allows us to set the packet mark among other things.
  From Arturo Borrero Gonzalez.

* Fix wrong format in sscanf in nf_tables_set_alloc_name(), from Daniel
  Borkmann.

* Add new queue expression to nf_tables. These comes with two previous patches
  to prepare this new feature, one to add mask in nf_tables_core to
  evaluate the queue verdict appropriately and another to refactor common
  code with xt_NFQUEUE, from Eric Leblond.

* Do not hide nftables from Kconfig if nfnetlink is not enabled, also from
  Eric Leblond.

* Add the reject expression to nf_tables, this adds the missing TCP RST
  support. It comes with an initial patch to refactor common code with
  xt_NFQUEUE, again from Eric Leblond.

* Remove an unused variable assignment in nf_tables_dump_set(), from Michal
  Nazarewicz.

* Remove the nft_meta_target code, now that Arturo added the set operation
  to the meta expression, from me.

* Add help information for nf_tables to Kconfig, also from me.

* Allow to dump all sets by specifying NFPROTO_UNSPEC, similar feature is
  available to other nf_tables objects, requested by Arturo, from me.

* Expose the table usage counter, so we can know how many chains are using
  this table without dumping the list of chains, from Tomasz Bursztyka.
====================

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

2 files changed, 20 insertions, 171 deletions

diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 7702f9e90a0..35750df744d 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -28,15 +28,27 @@ config NF_CONNTRACK_IPV6
 config NF_TABLES_IPV6
 	depends on NF_TABLES
 	tristate "IPv6 nf_tables support"
+	help
+	  This option enables the IPv6 support for nf_tables.
 
 config NFT_CHAIN_ROUTE_IPV6
 	depends on NF_TABLES_IPV6
 	tristate "IPv6 nf_tables route chain support"
+	help
+	  This option enables the "route" chain for IPv6 in nf_tables. This
+	  chain type is used to force packet re-routing after mangling header
+	  fields such as the source, destination, flowlabel, hop-limit and
+	  the packet mark.
 
 config NFT_CHAIN_NAT_IPV6
 	depends on NF_TABLES_IPV6
 	depends on NF_NAT_IPV6 && NFT_NAT
 	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 IP6_NF_IPTABLES
 	tristate "IP6 tables support (required for filtering)"
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index da00a2ecde5..544b0a9da1b 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -23,181 +23,18 @@
 #include <linux/skbuff.h>
 #include <linux/icmpv6.h>
 #include <linux/netdevice.h>
-#include <net/ipv6.h>
-#include <net/tcp.h>
 #include <net/icmp.h>
-#include <net/ip6_checksum.h>
-#include <net/ip6_fib.h>
-#include <net/ip6_route.h>
 #include <net/flow.h>
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_ipv6/ip6_tables.h>
 #include <linux/netfilter_ipv6/ip6t_REJECT.h>
 
+#include <net/netfilter/ipv6/nf_reject.h>
+
 MODULE_AUTHOR("Yasuyuki KOZAKAI <yasuyuki.kozakai@toshiba.co.jp>");
 MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv6");
 MODULE_LICENSE("GPL");
 
-/* Send RST reply */
-static void send_reset(struct net *net, struct sk_buff *oldskb, int hook)
-{
-	struct sk_buff *nskb;
-	struct tcphdr otcph, *tcph;
-	unsigned int otcplen, hh_len;
-	int tcphoff, needs_ack;
-	const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
-	struct ipv6hdr *ip6h;
-#define DEFAULT_TOS_VALUE	0x0U
-	const __u8 tclass = DEFAULT_TOS_VALUE;
-	struct dst_entry *dst = NULL;
-	u8 proto;
-	__be16 frag_off;
-	struct flowi6 fl6;
-
-	if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
-	    (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
-		pr_debug("addr is not unicast.\n");
-		return;
-	}
-
-	proto = oip6h->nexthdr;
-	tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto, &frag_off);
-
-	if ((tcphoff < 0) || (tcphoff > oldskb->len)) {
-		pr_debug("Cannot get TCP header.\n");
-		return;
-	}
-
-	otcplen = oldskb->len - tcphoff;
-
-	/* IP header checks: fragment, too short. */
-	if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) {
-		pr_debug("proto(%d) != IPPROTO_TCP, "
-			 "or too short. otcplen = %d\n",
-			 proto, otcplen);
-		return;
-	}
-
-	if (skb_copy_bits(oldskb, tcphoff, &otcph, sizeof(struct tcphdr)))
-		BUG();
-
-	/* No RST for RST. */
-	if (otcph.rst) {
-		pr_debug("RST is set\n");
-		return;
-	}
-
-	/* Check checksum. */
-	if (nf_ip6_checksum(oldskb, hook, tcphoff, IPPROTO_TCP)) {
-		pr_debug("TCP checksum is invalid\n");
-		return;
-	}
-
-	memset(&fl6, 0, sizeof(fl6));
-	fl6.flowi6_proto = IPPROTO_TCP;
-	fl6.saddr = oip6h->daddr;
-	fl6.daddr = oip6h->saddr;
-	fl6.fl6_sport = otcph.dest;
-	fl6.fl6_dport = otcph.source;
-	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
-	dst = ip6_route_output(net, NULL, &fl6);
-	if (dst == NULL || dst->error) {
-		dst_release(dst);
-		return;
-	}
-	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
-	if (IS_ERR(dst))
-		return;
-
-	hh_len = (dst->dev->hard_header_len + 15)&~15;
-	nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
-			 + sizeof(struct tcphdr) + dst->trailer_len,
-			 GFP_ATOMIC);
-
-	if (!nskb) {
-		net_dbg_ratelimited("cannot alloc skb\n");
-		dst_release(dst);
-		return;
-	}
-
-	skb_dst_set(nskb, dst);
-
-	skb_reserve(nskb, hh_len + dst->header_len);
-
-	skb_put(nskb, sizeof(struct ipv6hdr));
-	skb_reset_network_header(nskb);
-	ip6h = ipv6_hdr(nskb);
-	ip6_flow_hdr(ip6h, tclass, 0);
-	ip6h->hop_limit = ip6_dst_hoplimit(dst);
-	ip6h->nexthdr = IPPROTO_TCP;
-	ip6h->saddr = oip6h->daddr;
-	ip6h->daddr = oip6h->saddr;
-
-	skb_reset_transport_header(nskb);
-	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
-	/* Truncate to length (no data) */
-	tcph->doff = sizeof(struct tcphdr)/4;
-	tcph->source = otcph.dest;
-	tcph->dest = otcph.source;
-
-	if (otcph.ack) {
-		needs_ack = 0;
-		tcph->seq = otcph.ack_seq;
-		tcph->ack_seq = 0;
-	} else {
-		needs_ack = 1;
-		tcph->ack_seq = htonl(ntohl(otcph.seq) + otcph.syn + otcph.fin
-				      + otcplen - (otcph.doff<<2));
-		tcph->seq = 0;
-	}
-
-	/* Reset flags */
-	((u_int8_t *)tcph)[13] = 0;
-	tcph->rst = 1;
-	tcph->ack = needs_ack;
-	tcph->window = 0;
-	tcph->urg_ptr = 0;
-	tcph->check = 0;
-
-	/* Adjust TCP checksum */
-	tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr,
-				      &ipv6_hdr(nskb)->daddr,
-				      sizeof(struct tcphdr), IPPROTO_TCP,
-				      csum_partial(tcph,
-						   sizeof(struct tcphdr), 0));
-
-	nf_ct_attach(nskb, oldskb);
-
-#ifdef CONFIG_BRIDGE_NETFILTER
-	/* If we use ip6_local_out for bridged traffic, the MAC source on
-	 * the RST will be ours, instead of the destination's.  This confuses
-	 * some routers/firewalls, and they drop the packet.  So we need to
-	 * build the eth header using the original destination's MAC as the
-	 * source, and send the RST packet directly.
-	 */
-	if (oldskb->nf_bridge) {
-		struct ethhdr *oeth = eth_hdr(oldskb);
-		nskb->dev = oldskb->nf_bridge->physindev;
-		nskb->protocol = htons(ETH_P_IPV6);
-		ip6h->payload_len = htons(sizeof(struct tcphdr));
-		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
-				    oeth->h_source, oeth->h_dest, nskb->len) < 0)
-			return;
-		dev_queue_xmit(nskb);
-	} else
-#endif
-		ip6_local_out(nskb);
-}
-
-static inline void
-send_unreach(struct net *net, struct sk_buff *skb_in, unsigned char code,
-	     unsigned int hooknum)
-{
-	if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL)
-		skb_in->dev = net->loopback_dev;
-
-	icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0);
-}
 
 static unsigned int
 reject_tg6(struct sk_buff *skb, const struct xt_action_param *par)
@@ -208,25 +45,25 @@ reject_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 	pr_debug("%s: medium point\n", __func__);
 	switch (reject->with) {
 	case IP6T_ICMP6_NO_ROUTE:
-		send_unreach(net, skb, ICMPV6_NOROUTE, par->hooknum);
+		nf_send_unreach6(net, skb, ICMPV6_NOROUTE, par->hooknum);
 		break;
 	case IP6T_ICMP6_ADM_PROHIBITED:
-		send_unreach(net, skb, ICMPV6_ADM_PROHIBITED, par->hooknum);
+		nf_send_unreach6(net, skb, ICMPV6_ADM_PROHIBITED, par->hooknum);
 		break;
 	case IP6T_ICMP6_NOT_NEIGHBOUR:
-		send_unreach(net, skb, ICMPV6_NOT_NEIGHBOUR, par->hooknum);
+		nf_send_unreach6(net, skb, ICMPV6_NOT_NEIGHBOUR, par->hooknum);
 		break;
 	case IP6T_ICMP6_ADDR_UNREACH:
-		send_unreach(net, skb, ICMPV6_ADDR_UNREACH, par->hooknum);
+		nf_send_unreach6(net, skb, ICMPV6_ADDR_UNREACH, par->hooknum);
 		break;
 	case IP6T_ICMP6_PORT_UNREACH:
-		send_unreach(net, skb, ICMPV6_PORT_UNREACH, par->hooknum);
+		nf_send_unreach6(net, skb, ICMPV6_PORT_UNREACH, par->hooknum);
 		break;
 	case IP6T_ICMP6_ECHOREPLY:
 		/* Do nothing */
 		break;
 	case IP6T_TCP_RESET:
-		send_reset(net, skb, par->hooknum);
+		nf_send_reset6(net, skb, par->hooknum);
 		break;
 	default:
 		net_info_ratelimited("case %u not handled yet\n", reject->with);