[linux-2.6-block.git] / net / ipv6 / ip6_input.c

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *	IPv6 input
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *	Ian P. Morris		<I.P.Morris@soton.ac.uk>
 *
 *	Based in linux/net/ipv4/ip_input.c
 */
/* Changes
 *
 *	Mitsuru KANDA @USAGI and
 *	YOSHIFUJI Hideaki @USAGI: Remove ipv6_parse_exthdrs().
 */

#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/icmpv6.h>
#include <linux/mroute6.h>
#include <linux/slab.h>
#include <linux/indirect_call_wrapper.h>

#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>

#include <net/sock.h>
#include <net/snmp.h>

#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/rawv6.h>
#include <net/ndisc.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/xfrm.h>
#include <net/inet_ecn.h>
#include <net/dst_metadata.h>

INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *));
static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
				struct sk_buff *skb)
{
	void (*edemux)(struct sk_buff *skb);

	if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
		const struct inet6_protocol *ipprot;

		ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
		if (ipprot && (edemux = READ_ONCE(ipprot->early_demux)))
			INDIRECT_CALL_2(edemux, tcp_v6_early_demux,
					udp_v6_early_demux, skb);
	}
	if (!skb_valid_dst(skb))
		ip6_route_input(skb);
}

int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	/* if ingress device is enslaved to an L3 master device pass the
	 * skb to its handler for processing
	 */
	skb = l3mdev_ip6_rcv(skb);
	if (!skb)
		return NET_RX_SUCCESS;
	ip6_rcv_finish_core(net, sk, skb);

	return dst_input(skb);
}

static void ip6_sublist_rcv_finish(struct list_head *head)
{
	struct sk_buff *skb, *next;

	list_for_each_entry_safe(skb, next, head, list) {
		skb_list_del_init(skb);
		dst_input(skb);
	}
}

static bool ip6_can_use_hint(const struct sk_buff *skb,
			     const struct sk_buff *hint)
{
	return hint && !skb_dst(skb) &&
	       ipv6_addr_equal(&ipv6_hdr(hint)->daddr, &ipv6_hdr(skb)->daddr);
}

static struct sk_buff *ip6_extract_route_hint(const struct net *net,
					      struct sk_buff *skb)
{
	if (fib6_routes_require_src(net) || fib6_has_custom_rules(net))
		return NULL;

	return skb;
}

static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
				struct list_head *head)
{
	struct sk_buff *skb, *next, *hint = NULL;
	struct dst_entry *curr_dst = NULL;
	struct list_head sublist;

	INIT_LIST_HEAD(&sublist);
	list_for_each_entry_safe(skb, next, head, list) {
		struct dst_entry *dst;

		skb_list_del_init(skb);
		/* if ingress device is enslaved to an L3 master device pass the
		 * skb to its handler for processing
		 */
		skb = l3mdev_ip6_rcv(skb);
		if (!skb)
			continue;

		if (ip6_can_use_hint(skb, hint))
			skb_dst_copy(skb, hint);
		else
			ip6_rcv_finish_core(net, sk, skb);
		dst = skb_dst(skb);
		if (curr_dst != dst) {
			hint = ip6_extract_route_hint(net, skb);

			/* dispatch old sublist */
			if (!list_empty(&sublist))
				ip6_sublist_rcv_finish(&sublist);
			/* start new sublist */
			INIT_LIST_HEAD(&sublist);
			curr_dst = dst;
		}
		list_add_tail(&skb->list, &sublist);
	}
	/* dispatch final sublist */
	ip6_sublist_rcv_finish(&sublist);
}

static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
				    struct net *net)
{
	const struct ipv6hdr *hdr;
	u32 pkt_len;
	struct inet6_dev *idev;

	if (skb->pkt_type == PACKET_OTHERHOST) {
		kfree_skb(skb);
		return NULL;
	}

	rcu_read_lock();

	idev = __in6_dev_get(skb->dev);

	__IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_IN, skb->len);

	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
	    !idev || unlikely(idev->cnf.disable_ipv6)) {
		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
		goto drop;
	}

	memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));

	/*
	 * Store incoming device index. When the packet will
	 * be queued, we cannot refer to skb->dev anymore.
	 *
	 * BTW, when we send a packet for our own local address on a
	 * non-loopback interface (e.g. ethX), it is being delivered
	 * via the loopback interface (lo) here; skb->dev = loopback_dev.
	 * It, however, should be considered as if it is being
	 * arrived via the sending interface (ethX), because of the
	 * nature of scoping architecture. --yoshfuji
	 */
	IP6CB(skb)->iif = skb_valid_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex;

	if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
		goto err;

	hdr = ipv6_hdr(skb);

	if (hdr->version != 6)
		goto err;

	__IP6_ADD_STATS(net, idev,
			IPSTATS_MIB_NOECTPKTS +
				(ipv6_get_dsfield(hdr) & INET_ECN_MASK),
			max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
	/*
	 * RFC4291 2.5.3
	 * The loopback address must not be used as the source address in IPv6
	 * packets that are sent outside of a single node. [..]
	 * A packet received on an interface with a destination address
	 * of loopback must be dropped.
	 */
	if ((ipv6_addr_loopback(&hdr->saddr) ||
	     ipv6_addr_loopback(&hdr->daddr)) &&
	    !(dev->flags & IFF_LOOPBACK) &&
	    !netif_is_l3_master(dev))
		goto err;

	/* RFC4291 Errata ID: 3480
	 * Interface-Local scope spans only a single interface on a
	 * node and is useful only for loopback transmission of
	 * multicast.  Packets with interface-local scope received
	 * from another node must be discarded.
	 */
	if (!(skb->pkt_type == PACKET_LOOPBACK ||
	      dev->flags & IFF_LOOPBACK) &&
	    ipv6_addr_is_multicast(&hdr->daddr) &&
	    IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1)
		goto err;

	/* If enabled, drop unicast packets that were encapsulated in link-layer
	 * multicast or broadcast to protected against the so-called "hole-196"
	 * attack in 802.11 wireless.
	 */
	if (!ipv6_addr_is_multicast(&hdr->daddr) &&
	    (skb->pkt_type == PACKET_BROADCAST ||
	     skb->pkt_type == PACKET_MULTICAST) &&
	    idev->cnf.drop_unicast_in_l2_multicast)
		goto err;

	/* RFC4291 2.7
	 * Nodes must not originate a packet to a multicast address whose scope
	 * field contains the reserved value 0; if such a packet is received, it
	 * must be silently dropped.
	 */
	if (ipv6_addr_is_multicast(&hdr->daddr) &&
	    IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0)
		goto err;

	/*
	 * RFC4291 2.7
	 * Multicast addresses must not be used as source addresses in IPv6
	 * packets or appear in any Routing header.
	 */
	if (ipv6_addr_is_multicast(&hdr->saddr))
		goto err;

	/* While RFC4291 is not explicit about v4mapped addresses
	 * in IPv6 headers, it seems clear linux dual-stack
	 * model can not deal properly with these.
	 * Security models could be fooled by ::ffff:127.0.0.1 for example.
	 *
	 * https://tools.ietf.org/html/draft-itojun-v6ops-v4mapped-harmful-02
	 */
	if (ipv6_addr_v4mapped(&hdr->saddr))
		goto err;

	skb->transport_header = skb->network_header + sizeof(*hdr);
	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);

	pkt_len = ntohs(hdr->payload_len);

	/* pkt_len may be zero if Jumbo payload option is present */
	if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
		if (pkt_len + sizeof(struct ipv6hdr) > skb->len) {
			__IP6_INC_STATS(net,
					idev, IPSTATS_MIB_INTRUNCATEDPKTS);
			goto drop;
		}
		if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
			goto drop;
		}
		hdr = ipv6_hdr(skb);
	}

	if (hdr->nexthdr == NEXTHDR_HOP) {
		if (ipv6_parse_hopopts(skb) < 0) {
			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
			rcu_read_unlock();
			return NULL;
		}
	}

	rcu_read_unlock();

	/* Must drop socket now because of tproxy. */
	if (!skb_sk_is_prefetched(skb))
		skb_orphan(skb);

	return skb;
err:
	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
drop:
	rcu_read_unlock();
	kfree_skb(skb);
	return NULL;
}

int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
	struct net *net = dev_net(skb->dev);

	skb = ip6_rcv_core(skb, dev, net);
	if (skb == NULL)
		return NET_RX_DROP;
	return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
		       net, NULL, skb, dev, NULL,
		       ip6_rcv_finish);
}

static void ip6_sublist_rcv(struct list_head *head, struct net_device *dev,
			    struct net *net)
{
	NF_HOOK_LIST(NFPROTO_IPV6, NF_INET_PRE_ROUTING, net, NULL,
		     head, dev, NULL, ip6_rcv_finish);
	ip6_list_rcv_finish(net, NULL, head);
}

/* Receive a list of IPv6 packets */
void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
		   struct net_device *orig_dev)
{
	struct net_device *curr_dev = NULL;
	struct net *curr_net = NULL;
	struct sk_buff *skb, *next;
	struct list_head sublist;

	INIT_LIST_HEAD(&sublist);
	list_for_each_entry_safe(skb, next, head, list) {
		struct net_device *dev = skb->dev;
		struct net *net = dev_net(dev);

		skb_list_del_init(skb);
		skb = ip6_rcv_core(skb, dev, net);
		if (skb == NULL)
			continue;

		if (curr_dev != dev || curr_net != net) {
			/* dispatch old sublist */
			if (!list_empty(&sublist))
				ip6_sublist_rcv(&sublist, curr_dev, curr_net);
			/* start new sublist */
			INIT_LIST_HEAD(&sublist);
			curr_dev = dev;
			curr_net = net;
		}
		list_add_tail(&skb->list, &sublist);
	}
	/* dispatch final sublist */
	if (!list_empty(&sublist))
		ip6_sublist_rcv(&sublist, curr_dev, curr_net);
}

INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *));

/*
 *	Deliver the packet to the host
 */
void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
			      bool have_final)
{
	const struct inet6_protocol *ipprot;
	struct inet6_dev *idev;
	unsigned int nhoff;
	bool raw;

	/*
	 *	Parse extension headers
	 */

resubmit:
	idev = ip6_dst_idev(skb_dst(skb));
	nhoff = IP6CB(skb)->nhoff;
	if (!have_final) {
		if (!pskb_pull(skb, skb_transport_offset(skb)))
			goto discard;
		nexthdr = skb_network_header(skb)[nhoff];
	}

resubmit_final:
	raw = raw6_local_deliver(skb, nexthdr);
	ipprot = rcu_dereference(inet6_protos[nexthdr]);
	if (ipprot) {
		int ret;

		if (have_final) {
			if (!(ipprot->flags & INET6_PROTO_FINAL)) {
				/* Once we've seen a final protocol don't
				 * allow encapsulation on any non-final
				 * ones. This allows foo in UDP encapsulation
				 * to work.
				 */
				goto discard;
			}
		} else if (ipprot->flags & INET6_PROTO_FINAL) {
			const struct ipv6hdr *hdr;
			int sdif = inet6_sdif(skb);
			struct net_device *dev;

			/* Only do this once for first final protocol */
			have_final = true;

			/* Free reference early: we don't need it any more,
			   and it may hold ip_conntrack module loaded
			   indefinitely. */
			nf_reset_ct(skb);

			skb_postpull_rcsum(skb, skb_network_header(skb),
					   skb_network_header_len(skb));
			hdr = ipv6_hdr(skb);

			/* skb->dev passed may be master dev for vrfs. */
			if (sdif) {
				dev = dev_get_by_index_rcu(net, sdif);
				if (!dev)
					goto discard;
			} else {
				dev = skb->dev;
			}

			if (ipv6_addr_is_multicast(&hdr->daddr) &&
			    !ipv6_chk_mcast_addr(dev, &hdr->daddr,
						 &hdr->saddr) &&
			    !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb)))
				goto discard;
		}
		if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
		    !xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
			goto discard;

		ret = INDIRECT_CALL_2(ipprot->handler, tcp_v6_rcv, udpv6_rcv,
				      skb);
		if (ret > 0) {
			if (ipprot->flags & INET6_PROTO_FINAL) {
				/* Not an extension header, most likely UDP
				 * encapsulation. Use return value as nexthdr
				 * protocol not nhoff (which presumably is
				 * not set by handler).
				 */
				nexthdr = ret;
				goto resubmit_final;
			} else {
				goto resubmit;
			}
		} else if (ret == 0) {
			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
		}
	} else {
		if (!raw) {
			if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
				__IP6_INC_STATS(net, idev,
						IPSTATS_MIB_INUNKNOWNPROTOS);
				icmpv6_send(skb, ICMPV6_PARAMPROB,
					    ICMPV6_UNK_NEXTHDR, nhoff);
			}
			kfree_skb(skb);
		} else {
			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
			consume_skb(skb);
		}
	}
	return;

discard:
	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
	kfree_skb(skb);
}

static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	rcu_read_lock();
	ip6_protocol_deliver_rcu(net, skb, 0, false);
	rcu_read_unlock();

	return 0;
}


int ip6_input(struct sk_buff *skb)
{
	return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN,
		       dev_net(skb->dev), NULL, skb, skb->dev, NULL,
		       ip6_input_finish);
}
EXPORT_SYMBOL_GPL(ip6_input);

int ip6_mc_input(struct sk_buff *skb)
{
	int sdif = inet6_sdif(skb);
	const struct ipv6hdr *hdr;
	struct net_device *dev;
	bool deliver;

	__IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev),
			 __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST,
			 skb->len);

	/* skb->dev passed may be master dev for vrfs. */
	if (sdif) {
		rcu_read_lock();
		dev = dev_get_by_index_rcu(dev_net(skb->dev), sdif);
		if (!dev) {
			rcu_read_unlock();
			kfree_skb(skb);
			return -ENODEV;
		}
	} else {
		dev = skb->dev;
	}

	hdr = ipv6_hdr(skb);
	deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL);
	if (sdif)
		rcu_read_unlock();

#ifdef CONFIG_IPV6_MROUTE
	/*
	 *      IPv6 multicast router mode is now supported ;)
	 */
	if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding &&
	    !(ipv6_addr_type(&hdr->daddr) &
	      (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)) &&
	    likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) {
		/*
		 * Okay, we try to forward - split and duplicate
		 * packets.
		 */
		struct sk_buff *skb2;
		struct inet6_skb_parm *opt = IP6CB(skb);

		/* Check for MLD */
		if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) {
			/* Check if this is a mld message */
			u8 nexthdr = hdr->nexthdr;
			__be16 frag_off;
			int offset;

			/* Check if the value of Router Alert
			 * is for MLD (0x0000).
			 */
			if (opt->ra == htons(IPV6_OPT_ROUTERALERT_MLD)) {
				deliver = false;

				if (!ipv6_ext_hdr(nexthdr)) {
					/* BUG */
					goto out;
				}
				offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
							  &nexthdr, &frag_off);
				if (offset < 0)
					goto out;

				if (ipv6_is_mld(skb, nexthdr, offset))
					deliver = true;

				goto out;
			}
			/* unknown RA - process it normally */
		}

		if (deliver)
			skb2 = skb_clone(skb, GFP_ATOMIC);
		else {
			skb2 = skb;
			skb = NULL;
		}

		if (skb2) {
			ip6_mr_input(skb2);
		}
	}
out:
#endif
	if (likely(deliver))
		ip6_input(skb);
	else {
		/* discard */
		kfree_skb(skb);
	}

	return 0;
}
Commit	Line	Data
2874c5fd	1	// SPDX-License-Identifier: GPL-2.0-or-later
1da177e4 LT	2	/*
1da177e4 LT	3	* IPv6 input
1ab1457c	4	* Linux INET6 implementation
1da177e4 LT	5	*
	6	* Authors:
	7	* Pedro Roque <roque@di.fc.ul.pt>
	8	* Ian P. Morris <I.P.Morris@soton.ac.uk>
	9	*
1da177e4	10	* Based in linux/net/ipv4/ip_input.c
1da177e4 LT	11	*/
	12	/* Changes
	13	*
67ba4152 IM	14	* Mitsuru KANDA @USAGI and
67ba4152 IM	15	* YOSHIFUJI Hideaki @USAGI: Remove ipv6_parse_exthdrs().
1da177e4 LT	16	*/
	17
	18	#include <linux/errno.h>
	19	#include <linux/types.h>
	20	#include <linux/socket.h>
	21	#include <linux/sockios.h>
1da177e4 LT	22	#include <linux/net.h>
	23	#include <linux/netdevice.h>
	24	#include <linux/in6.h>
	25	#include <linux/icmpv6.h>
7bc570c8	26	#include <linux/mroute6.h>
5a0e3ad6	27	#include <linux/slab.h>
0e219ae4	28	#include <linux/indirect_call_wrapper.h>
1da177e4 LT	29
	30	#include <linux/netfilter.h>
	31	#include <linux/netfilter_ipv6.h>
	32
	33	#include <net/sock.h>
	34	#include <net/snmp.h>
	35
	36	#include <net/ipv6.h>
	37	#include <net/protocol.h>
	38	#include <net/transp_v6.h>
	39	#include <net/rawv6.h>
	40	#include <net/ndisc.h>
	41	#include <net/ip6_route.h>
	42	#include <net/addrconf.h>
	43	#include <net/xfrm.h>
1f07d03e	44	#include <net/inet_ecn.h>
48fb6b55	45	#include <net/dst_metadata.h>
1da177e4	46
97ff7ffb PA	47	INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *));
97ff7ffb PA	48	INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *));
d8269e2c EC	49	static void ip6_rcv_finish_core(struct net net, struct sock sk,
d8269e2c EC	50	struct sk_buff *skb)
1da177e4	51	{
dddb64bc	52	void (edemux)(struct sk_buff skb);
dddb64bc	53
e21145a9	54	if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
c7109986 ED	55	const struct inet6_protocol *ipprot;
c7109986 ED	56
c7109986	57	ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
dddb64bc	58	if (ipprot && (edemux = READ_ONCE(ipprot->early_demux)))
97ff7ffb PA	59	INDIRECT_CALL_2(edemux, tcp_v6_early_demux,
97ff7ffb PA	60	udp_v6_early_demux, skb);
c7109986	61	}
48fb6b55	62	if (!skb_valid_dst(skb))
1da177e4	63	ip6_route_input(skb);
d8269e2c EC	64	}
	65
	66	int ip6_rcv_finish(struct net net, struct sock sk, struct sk_buff *skb)
	67	{
	68	/* if ingress device is enslaved to an L3 master device pass the
	69	* skb to its handler for processing
	70	*/
	71	skb = l3mdev_ip6_rcv(skb);
	72	if (!skb)
	73	return NET_RX_SUCCESS;
	74	ip6_rcv_finish_core(net, sk, skb);
1da177e4 LT	75
	76	return dst_input(skb);
	77	}
	78
d8269e2c EC	79	static void ip6_sublist_rcv_finish(struct list_head *head)
	80	{
	81	struct sk_buff skb, next;
	82
c7a42eb4 XL	83	list_for_each_entry_safe(skb, next, head, list) {
c7a42eb4 XL	84	skb_list_del_init(skb);
d8269e2c	85	dst_input(skb);
c7a42eb4	86	}
d8269e2c EC	87	}
d8269e2c EC	88
197dbf24 PA	89	static bool ip6_can_use_hint(const struct sk_buff *skb,
	90	const struct sk_buff *hint)
	91	{
	92	return hint && !skb_dst(skb) &&
	93	ipv6_addr_equal(&ipv6_hdr(hint)->daddr, &ipv6_hdr(skb)->daddr);
	94	}
	95
	96	static struct sk_buff ip6_extract_route_hint(const struct net net,
	97	struct sk_buff *skb)
	98	{
	99	if (fib6_routes_require_src(net) \|\| fib6_has_custom_rules(net))
	100	return NULL;
	101
	102	return skb;
	103	}
	104
d8269e2c EC	105	static void ip6_list_rcv_finish(struct net net, struct sock sk,
	106	struct list_head *head)
	107	{
197dbf24	108	struct sk_buff skb, next, *hint = NULL;
d8269e2c	109	struct dst_entry *curr_dst = NULL;
d8269e2c EC	110	struct list_head sublist;
	111
	112	INIT_LIST_HEAD(&sublist);
	113	list_for_each_entry_safe(skb, next, head, list) {
	114	struct dst_entry *dst;
	115
22f6bbb7	116	skb_list_del_init(skb);
d8269e2c EC	117	/* if ingress device is enslaved to an L3 master device pass the
	118	* skb to its handler for processing
	119	*/
	120	skb = l3mdev_ip6_rcv(skb);
	121	if (!skb)
	122	continue;
197dbf24 PA	123
	124	if (ip6_can_use_hint(skb, hint))
	125	skb_dst_copy(skb, hint);
	126	else
	127	ip6_rcv_finish_core(net, sk, skb);
d8269e2c EC	128	dst = skb_dst(skb);
d8269e2c EC	129	if (curr_dst != dst) {
197dbf24 PA	130	hint = ip6_extract_route_hint(net, skb);
197dbf24 PA	131
d8269e2c EC	132	/* dispatch old sublist */
	133	if (!list_empty(&sublist))
	134	ip6_sublist_rcv_finish(&sublist);
	135	/* start new sublist */
	136	INIT_LIST_HEAD(&sublist);
	137	curr_dst = dst;
	138	}
	139	list_add_tail(&skb->list, &sublist);
	140	}
	141	/* dispatch final sublist */
	142	ip6_sublist_rcv_finish(&sublist);
	143	}
	144
	145	static struct sk_buff ip6_rcv_core(struct sk_buff skb, struct net_device *dev,
	146	struct net *net)
1da177e4	147	{
b71d1d42	148	const struct ipv6hdr *hdr;
67ba4152	149	u32 pkt_len;
a11d206d	150	struct inet6_dev *idev;
1da177e4	151
a11d206d YH	152	if (skb->pkt_type == PACKET_OTHERHOST) {
a11d206d YH	153	kfree_skb(skb);
d8269e2c	154	return NULL;
a11d206d YH	155	}
	156
	157	rcu_read_lock();
1da177e4	158
a11d206d YH	159	idev = __in6_dev_get(skb->dev);
a11d206d YH	160
c2005eb0	161	__IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_IN, skb->len);
1da177e4	162
778d80be YH	163	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL \|\|
778d80be YH	164	!idev \|\| unlikely(idev->cnf.disable_ipv6)) {
1d015503	165	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
71f6f6df	166	goto drop;
1da177e4 LT	167	}
1da177e4 LT	168
6b7fdc3a GC	169	memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
6b7fdc3a GC	170
1da177e4 LT	171	/*
	172	* Store incoming device index. When the packet will
	173	* be queued, we cannot refer to skb->dev anymore.
	174	*
	175	* BTW, when we send a packet for our own local address on a
	176	* non-loopback interface (e.g. ethX), it is being delivered
de3cb747	177	* via the loopback interface (lo) here; skb->dev = loopback_dev.
1da177e4 LT	178	* It, however, should be considered as if it is being
	179	* arrived via the sending interface (ethX), because of the
	180	* nature of scoping architecture. --yoshfuji
	181	*/
48fb6b55	182	IP6CB(skb)->iif = skb_valid_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex;
1da177e4	183
2889139a	184	if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
1da177e4 LT	185	goto err;
1da177e4 LT	186
0660e03f	187	hdr = ipv6_hdr(skb);
1da177e4 LT	188
	189	if (hdr->version != 6)
	190	goto err;
	191
1d015503 ED	192	__IP6_ADD_STATS(net, idev,
1d015503 ED	193	IPSTATS_MIB_NOECTPKTS +
1f07d03e	194	(ipv6_get_dsfield(hdr) & INET_ECN_MASK),
1d015503	195	max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
f630e43a YH	196	/*
f630e43a YH	197	* RFC4291 2.5.3
0aa8c13e FW	198	* The loopback address must not be used as the source address in IPv6
0aa8c13e FW	199	* packets that are sent outside of a single node. [..]
f630e43a YH	200	* A packet received on an interface with a destination address
	201	* of loopback must be dropped.
	202	*/
0aa8c13e FW	203	if ((ipv6_addr_loopback(&hdr->saddr) \|\|
0aa8c13e FW	204	ipv6_addr_loopback(&hdr->daddr)) &&
3ede0bbc RS	205	!(dev->flags & IFF_LOOPBACK) &&
3ede0bbc RS	206	!netif_is_l3_master(dev))
f630e43a YH	207	goto err;
f630e43a YH	208
1c4a154e HFS	209	/* RFC4291 Errata ID: 3480
	210	* Interface-Local scope spans only a single interface on a
	211	* node and is useful only for loopback transmission of
	212	* multicast. Packets with interface-local scope received
	213	* from another node must be discarded.
	214	*/
	215	if (!(skb->pkt_type == PACKET_LOOPBACK \|\|
	216	dev->flags & IFF_LOOPBACK) &&
	217	ipv6_addr_is_multicast(&hdr->daddr) &&
	218	IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1)
	219	goto err;
	220
abbc3043 JB	221	/* If enabled, drop unicast packets that were encapsulated in link-layer
	222	* multicast or broadcast to protected against the so-called "hole-196"
	223	* attack in 802.11 wireless.
	224	*/
	225	if (!ipv6_addr_is_multicast(&hdr->daddr) &&
	226	(skb->pkt_type == PACKET_BROADCAST \|\|
	227	skb->pkt_type == PACKET_MULTICAST) &&
	228	idev->cnf.drop_unicast_in_l2_multicast)
	229	goto err;
	230
20314092 HFS	231	/* RFC4291 2.7
	232	* Nodes must not originate a packet to a multicast address whose scope
	233	* field contains the reserved value 0; if such a packet is received, it
	234	* must be silently dropped.
	235	*/
	236	if (ipv6_addr_is_multicast(&hdr->daddr) &&
	237	IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0)
	238	goto err;
	239
c457338d BH	240	/*
	241	* RFC4291 2.7
	242	* Multicast addresses must not be used as source addresses in IPv6
	243	* packets or appear in any Routing header.
	244	*/
	245	if (ipv6_addr_is_multicast(&hdr->saddr))
	246	goto err;
	247
6af1799a ED	248	/* While RFC4291 is not explicit about v4mapped addresses
	249	* in IPv6 headers, it seems clear linux dual-stack
	250	* model can not deal properly with these.
	251	* Security models could be fooled by ::ffff:127.0.0.1 for example.
	252	*
	253	* https://tools.ietf.org/html/draft-itojun-v6ops-v4mapped-harmful-02
	254	*/
	255	if (ipv6_addr_v4mapped(&hdr->saddr))
	256	goto err;
	257
b0e380b1	258	skb->transport_header = skb->network_header + sizeof(*hdr);
951dbc8a PM	259	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
951dbc8a PM	260
1da177e4 LT	261	pkt_len = ntohs(hdr->payload_len);
	262
	263	/* pkt_len may be zero if Jumbo payload option is present */
	264	if (pkt_len \|\| hdr->nexthdr != NEXTHDR_HOP) {
60e5c166	265	if (pkt_len + sizeof(struct ipv6hdr) > skb->len) {
1d015503 ED	266	__IP6_INC_STATS(net,
1d015503 ED	267	idev, IPSTATS_MIB_INTRUNCATEDPKTS);
60e5c166 MC	268	goto drop;
60e5c166 MC	269	}
1da177e4	270	if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
1d015503	271	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
1da177e4 LT	272	goto drop;
1da177e4 LT	273	}
0660e03f	274	hdr = ipv6_hdr(skb);
1da177e4 LT	275	}
	276
	277	if (hdr->nexthdr == NEXTHDR_HOP) {
e5bbef20	278	if (ipv6_parse_hopopts(skb) < 0) {
1d015503	279	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
a11d206d	280	rcu_read_unlock();
d8269e2c	281	return NULL;
1da177e4	282	}
1da177e4 LT	283	}
1da177e4 LT	284
a11d206d YH	285	rcu_read_unlock();
a11d206d YH	286
71f9dacd	287	/* Must drop socket now because of tproxy. */
cf7fbe66 JS	288	if (!skb_sk_is_prefetched(skb))
cf7fbe66 JS	289	skb_orphan(skb);
71f9dacd	290
d8269e2c	291	return skb;
1da177e4	292	err:
1d015503	293	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
1da177e4	294	drop:
a11d206d	295	rcu_read_unlock();
1da177e4	296	kfree_skb(skb);
d8269e2c EC	297	return NULL;
	298	}
	299
	300	int ipv6_rcv(struct sk_buff skb, struct net_device dev, struct packet_type pt, struct net_device orig_dev)
	301	{
	302	struct net *net = dev_net(skb->dev);
	303
	304	skb = ip6_rcv_core(skb, dev, net);
	305	if (skb == NULL)
	306	return NET_RX_DROP;
	307	return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
	308	net, NULL, skb, dev, NULL,
	309	ip6_rcv_finish);
	310	}
	311
	312	static void ip6_sublist_rcv(struct list_head head, struct net_device dev,
	313	struct net *net)
	314	{
	315	NF_HOOK_LIST(NFPROTO_IPV6, NF_INET_PRE_ROUTING, net, NULL,
	316	head, dev, NULL, ip6_rcv_finish);
	317	ip6_list_rcv_finish(net, NULL, head);
	318	}
	319
	320	/* Receive a list of IPv6 packets */
	321	void ipv6_list_rcv(struct list_head head, struct packet_type pt,
	322	struct net_device *orig_dev)
	323	{
	324	struct net_device *curr_dev = NULL;
	325	struct net *curr_net = NULL;
	326	struct sk_buff skb, next;
	327	struct list_head sublist;
	328
	329	INIT_LIST_HEAD(&sublist);
	330	list_for_each_entry_safe(skb, next, head, list) {
	331	struct net_device *dev = skb->dev;
	332	struct net *net = dev_net(dev);
	333
22f6bbb7	334	skb_list_del_init(skb);
d8269e2c EC	335	skb = ip6_rcv_core(skb, dev, net);
	336	if (skb == NULL)
	337	continue;
	338
	339	if (curr_dev != dev \|\| curr_net != net) {
	340	/* dispatch old sublist */
	341	if (!list_empty(&sublist))
	342	ip6_sublist_rcv(&sublist, curr_dev, curr_net);
	343	/* start new sublist */
	344	INIT_LIST_HEAD(&sublist);
	345	curr_dev = dev;
	346	curr_net = net;
	347	}
	348	list_add_tail(&skb->list, &sublist);
	349	}
	350	/* dispatch final sublist */
51210ad5 FW	351	if (!list_empty(&sublist))
51210ad5 FW	352	ip6_sublist_rcv(&sublist, curr_dev, curr_net);
1da177e4 LT	353	}
1da177e4 LT	354
0e219ae4 PA	355	INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *));
	356	INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *));
	357
1da177e4 LT	358	/*
	359	* Deliver the packet to the host
	360	*/
80bde363 PA	361	void ip6_protocol_deliver_rcu(struct net net, struct sk_buff skb, int nexthdr,
80bde363 PA	362	bool have_final)
1da177e4	363	{
41135cc8	364	const struct inet6_protocol *ipprot;
f9242b6b	365	struct inet6_dev *idev;
1da177e4	366	unsigned int nhoff;
a50feda5	367	bool raw;
1da177e4	368
1da177e4 LT	369	/*
	370	* Parse extension headers
	371	*/
	372
1b0ccfe5	373	resubmit:
adf30907	374	idev = ip6_dst_idev(skb_dst(skb));
951dbc8a	375	nhoff = IP6CB(skb)->nhoff;
80bde363 PA	376	if (!have_final) {
	377	if (!pskb_pull(skb, skb_transport_offset(skb)))
	378	goto discard;
	379	nexthdr = skb_network_header(skb)[nhoff];
	380	}
1da177e4	381
4c64242a	382	resubmit_final:
69d6da0b	383	raw = raw6_local_deliver(skb, nexthdr);
e5d08d71	384	ipprot = rcu_dereference(inet6_protos[nexthdr]);
53b24b8f	385	if (ipprot) {
1da177e4	386	int ret;
1ab1457c	387
1da44f9c TH	388	if (have_final) {
	389	if (!(ipprot->flags & INET6_PROTO_FINAL)) {
	390	/* Once we've seen a final protocol don't
	391	* allow encapsulation on any non-final
	392	* ones. This allows foo in UDP encapsulation
	393	* to work.
	394	*/
	395	goto discard;
	396	}
	397	} else if (ipprot->flags & INET6_PROTO_FINAL) {
b71d1d42	398	const struct ipv6hdr *hdr;
5226b6a9 MM	399	int sdif = inet6_sdif(skb);
5226b6a9 MM	400	struct net_device *dev;
1da177e4	401
1da44f9c TH	402	/* Only do this once for first final protocol */
	403	have_final = true;
	404
9fb9cbb1 YK	405	/* Free reference early: we don't need it any more,
	406	and it may hold ip_conntrack module loaded
	407	indefinitely. */
895b5c9f	408	nf_reset_ct(skb);
9fb9cbb1	409
d56f90a7	410	skb_postpull_rcsum(skb, skb_network_header(skb),
cfe1fc77	411	skb_network_header_len(skb));
0660e03f	412	hdr = ipv6_hdr(skb);
5226b6a9 MM	413
	414	/* skb->dev passed may be master dev for vrfs. */
	415	if (sdif) {
	416	dev = dev_get_by_index_rcu(net, sdif);
	417	if (!dev)
	418	goto discard;
	419	} else {
	420	dev = skb->dev;
	421	}
	422
1da177e4	423	if (ipv6_addr_is_multicast(&hdr->daddr) &&
5226b6a9 MM	424	!ipv6_chk_mcast_addr(dev, &hdr->daddr,
5226b6a9 MM	425	&hdr->saddr) &&
daad1512	426	!ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb)))
1da177e4 LT	427	goto discard;
	428	}
	429	if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
1ab1457c	430	!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
1da177e4	431	goto discard;
1ab1457c	432
0e219ae4 PA	433	ret = INDIRECT_CALL_2(ipprot->handler, tcp_v6_rcv, udpv6_rcv,
0e219ae4 PA	434	skb);
4c64242a TH	435	if (ret > 0) {
	436	if (ipprot->flags & INET6_PROTO_FINAL) {
	437	/* Not an extension header, most likely UDP
	438	* encapsulation. Use return value as nexthdr
	439	* protocol not nhoff (which presumably is
	440	* not set by handler).
	441	*/
	442	nexthdr = ret;
	443	goto resubmit_final;
	444	} else {
	445	goto resubmit;
	446	}
	447	} else if (ret == 0) {
1d015503	448	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
4c64242a	449	}
1da177e4	450	} else {
69d6da0b	451	if (!raw) {
1da177e4	452	if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
1d015503 ED	453	__IP6_INC_STATS(net, idev,
1d015503 ED	454	IPSTATS_MIB_INUNKNOWNPROTOS);
fad87aca	455	icmpv6_send(skb, ICMPV6_PARAMPROB,
3ffe533c	456	ICMPV6_UNK_NEXTHDR, nhoff);
1da177e4	457	}
d8c6f4b9 NH	458	kfree_skb(skb);
d8c6f4b9 NH	459	} else {
1d015503	460	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
d8c6f4b9 NH	461	consume_skb(skb);
d8c6f4b9 NH	462	}
1da177e4	463	}
80bde363	464	return;
1da177e4 LT	465
1da177e4 LT	466	discard:
1d015503	467	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
1da177e4	468	kfree_skb(skb);
80bde363 PA	469	}
	470
	471	static int ip6_input_finish(struct net net, struct sock sk, struct sk_buff *skb)
	472	{
	473	rcu_read_lock();
	474	ip6_protocol_deliver_rcu(net, skb, 0, false);
	475	rcu_read_unlock();
	476
1da177e4 LT	477	return 0;
	478	}
	479
	480
	481	int ip6_input(struct sk_buff *skb)
	482	{
29a26a56 EB	483	return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN,
29a26a56 EB	484	dev_net(skb->dev), NULL, skb, skb->dev, NULL,
6e23ae2a	485	ip6_input_finish);
1da177e4	486	}
b4869aa2	487	EXPORT_SYMBOL_GPL(ip6_input);
1da177e4 LT	488
	489	int ip6_mc_input(struct sk_buff *skb)
	490	{
5226b6a9	491	int sdif = inet6_sdif(skb);
b71d1d42	492	const struct ipv6hdr *hdr;
5226b6a9	493	struct net_device *dev;
a50feda5	494	bool deliver;
1da177e4	495
c2005eb0	496	__IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev),
bdb7cc64	497	__in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST,
edf391ff	498	skb->len);
1da177e4	499
5226b6a9 MM	500	/* skb->dev passed may be master dev for vrfs. */
	501	if (sdif) {
	502	rcu_read_lock();
	503	dev = dev_get_by_index_rcu(dev_net(skb->dev), sdif);
	504	if (!dev) {
	505	rcu_read_unlock();
	506	kfree_skb(skb);
	507	return -ENODEV;
	508	}
	509	} else {
	510	dev = skb->dev;
	511	}
	512
0660e03f	513	hdr = ipv6_hdr(skb);
5226b6a9 MM	514	deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL);
	515	if (sdif)
	516	rcu_read_unlock();
1da177e4	517
7bc570c8	518	#ifdef CONFIG_IPV6_MROUTE
1da177e4	519	/*
7bc570c8	520	* IPv6 multicast router mode is now supported ;)
1da177e4	521	*/
53b7997f	522	if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding &&
ddf64354 HFS	523	!(ipv6_addr_type(&hdr->daddr) &
ddf64354 HFS	524	(IPV6_ADDR_LOOPBACK\|IPV6_ADDR_LINKLOCAL)) &&
7bc570c8 YH	525	likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) {
	526	/*
	527	* Okay, we try to forward - split and duplicate
	528	* packets.
	529	*/
	530	struct sk_buff *skb2;
	531	struct inet6_skb_parm *opt = IP6CB(skb);
	532
	533	/* Check for MLD */
dd3332bf	534	if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) {
7bc570c8	535	/* Check if this is a mld message */
7bc570c8	536	u8 nexthdr = hdr->nexthdr;
75f2811c	537	__be16 frag_off;
7bc570c8 YH	538	int offset;
	539
	540	/* Check if the value of Router Alert
	541	* is for MLD (0x0000).
	542	*/
dd3332bf	543	if (opt->ra == htons(IPV6_OPT_ROUTERALERT_MLD)) {
a50feda5	544	deliver = false;
aba6096b	545
7bc570c8 YH	546	if (!ipv6_ext_hdr(nexthdr)) {
7bc570c8 YH	547	/* BUG */
aba6096b	548	goto out;
7bc570c8 YH	549	}
7bc570c8 YH	550	offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
75f2811c	551	&nexthdr, &frag_off);
7bc570c8	552	if (offset < 0)
aba6096b	553	goto out;
7bc570c8	554
4c938d22 A	555	if (ipv6_is_mld(skb, nexthdr, offset))
4c938d22 A	556	deliver = true;
7bc570c8	557
4c938d22	558	goto out;
7bc570c8 YH	559	}
	560	/* unknown RA - process it normally */
	561	}
1da177e4	562
7bc570c8 YH	563	if (deliver)
	564	skb2 = skb_clone(skb, GFP_ATOMIC);
	565	else {
	566	skb2 = skb;
	567	skb = NULL;
	568	}
1ab1457c	569
7bc570c8	570	if (skb2) {
7bc570c8	571	ip6_mr_input(skb2);
1da177e4 LT	572	}
1da177e4 LT	573	}
7bc570c8	574	out:
aba6096b YH	575	#endif
aba6096b YH	576	if (likely(deliver))
1da177e4	577	ip6_input(skb);
aba6096b YH	578	else {
	579	/* discard */
	580	kfree_skb(skb);
1da177e4	581	}
1da177e4 LT	582
	583	return 0;
	584	}