[linux-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/udp.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>

static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
				struct sk_buff *skb)
{
	if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) &&
	    !skb_dst(skb) && !skb->sk) {
		switch (ipv6_hdr(skb)->nexthdr) {
		case IPPROTO_TCP:
			if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux))
				tcp_v6_early_demux(skb);
			break;
		case IPPROTO_UDP:
			if (READ_ONCE(net->ipv4.sysctl_udp_early_demux))
				udp_v6_early_demux(skb);
			break;
		}
	}

	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)
{
	enum skb_drop_reason reason;
	const struct ipv6hdr *hdr;
	u32 pkt_len;
	struct inet6_dev *idev;

	if (skb->pkt_type == PACKET_OTHERHOST) {
		dev_core_stats_rx_otherhost_dropped_inc(skb->dev);
		kfree_skb_reason(skb, SKB_DROP_REASON_OTHERHOST);
		return NULL;
	}

	rcu_read_lock();

	idev = __in6_dev_get(skb->dev);

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

	SKB_DR_SET(reason, NOT_SPECIFIED);
	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
	    !idev || unlikely(idev->cnf.disable_ipv6)) {
		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
		if (idev && unlikely(idev->cnf.disable_ipv6))
			SKB_DR_SET(reason, IPV6DISABLED);
		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) {
		SKB_DR_SET(reason, UNHANDLED_PROTO);
		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) {
		SKB_DR_SET(reason, 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;

	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);
			SKB_DR_SET(reason, PKT_TOO_SMALL);
			goto drop;
		}
		if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr)))
			goto err;
		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);
	SKB_DR_OR(reason, IP_INHDR);
drop:
	rcu_read_unlock();
	kfree_skb_reason(skb, reason);
	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 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;
	SKB_DR(reason);
	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;


			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))) {
				SKB_DR_SET(reason, IP_INADDRERRORS);
				goto discard;
			}
		}
		if (!(ipprot->flags & INET6_PROTO_NOPOLICY)) {
			if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
				SKB_DR_SET(reason, XFRM_POLICY);
				goto discard;
			}
			nf_reset_ct(skb);
		}

		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);
				SKB_DR_SET(reason, IP_NOPROTO);
			} else {
				SKB_DR_SET(reason, XFRM_POLICY);
			}
			kfree_skb_reason(skb, reason);
		} else {
			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
			consume_skb(skb);
		}
	}
	return;

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

static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	skb_clear_delivery_time(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 (atomic_read(&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>
f9a4719c	35	#include <net/udp.h>
1da177e4 LT	36
	37	#include <net/ipv6.h>
	38	#include <net/protocol.h>
	39	#include <net/transp_v6.h>
	40	#include <net/rawv6.h>
	41	#include <net/ndisc.h>
	42	#include <net/ip6_route.h>
	43	#include <net/addrconf.h>
	44	#include <net/xfrm.h>
1f07d03e	45	#include <net/inet_ecn.h>
48fb6b55	46	#include <net/dst_metadata.h>
1da177e4	47
d8269e2c EC	48	static void ip6_rcv_finish_core(struct net net, struct sock sk,
d8269e2c EC	49	struct sk_buff *skb)
1da177e4	50	{
11052589 KI	51	if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) &&
	52	!skb_dst(skb) && !skb->sk) {
	53	switch (ipv6_hdr(skb)->nexthdr) {
	54	case IPPROTO_TCP:
	55	if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux))
	56	tcp_v6_early_demux(skb);
	57	break;
	58	case IPPROTO_UDP:
	59	if (READ_ONCE(net->ipv4.sysctl_udp_early_demux))
	60	udp_v6_early_demux(skb);
	61	break;
	62	}
c7109986	63	}
11052589	64
48fb6b55	65	if (!skb_valid_dst(skb))
1da177e4	66	ip6_route_input(skb);
d8269e2c EC	67	}
	68
	69	int ip6_rcv_finish(struct net net, struct sock sk, struct sk_buff *skb)
	70	{
	71	/* if ingress device is enslaved to an L3 master device pass the
	72	* skb to its handler for processing
	73	*/
	74	skb = l3mdev_ip6_rcv(skb);
	75	if (!skb)
	76	return NET_RX_SUCCESS;
	77	ip6_rcv_finish_core(net, sk, skb);
1da177e4 LT	78
	79	return dst_input(skb);
	80	}
	81
d8269e2c EC	82	static void ip6_sublist_rcv_finish(struct list_head *head)
	83	{
	84	struct sk_buff skb, next;
	85
c7a42eb4 XL	86	list_for_each_entry_safe(skb, next, head, list) {
c7a42eb4 XL	87	skb_list_del_init(skb);
d8269e2c	88	dst_input(skb);
c7a42eb4	89	}
d8269e2c EC	90	}
d8269e2c EC	91
197dbf24 PA	92	static bool ip6_can_use_hint(const struct sk_buff *skb,
	93	const struct sk_buff *hint)
	94	{
	95	return hint && !skb_dst(skb) &&
	96	ipv6_addr_equal(&ipv6_hdr(hint)->daddr, &ipv6_hdr(skb)->daddr);
	97	}
	98
	99	static struct sk_buff ip6_extract_route_hint(const struct net net,
	100	struct sk_buff *skb)
	101	{
	102	if (fib6_routes_require_src(net) \|\| fib6_has_custom_rules(net))
	103	return NULL;
	104
	105	return skb;
	106	}
	107
d8269e2c EC	108	static void ip6_list_rcv_finish(struct net net, struct sock sk,
	109	struct list_head *head)
	110	{
197dbf24	111	struct sk_buff skb, next, *hint = NULL;
d8269e2c	112	struct dst_entry *curr_dst = NULL;
d8269e2c EC	113	struct list_head sublist;
	114
	115	INIT_LIST_HEAD(&sublist);
	116	list_for_each_entry_safe(skb, next, head, list) {
	117	struct dst_entry *dst;
	118
22f6bbb7	119	skb_list_del_init(skb);
d8269e2c EC	120	/* if ingress device is enslaved to an L3 master device pass the
	121	* skb to its handler for processing
	122	*/
	123	skb = l3mdev_ip6_rcv(skb);
	124	if (!skb)
	125	continue;
197dbf24 PA	126
	127	if (ip6_can_use_hint(skb, hint))
	128	skb_dst_copy(skb, hint);
	129	else
	130	ip6_rcv_finish_core(net, sk, skb);
d8269e2c EC	131	dst = skb_dst(skb);
d8269e2c EC	132	if (curr_dst != dst) {
197dbf24 PA	133	hint = ip6_extract_route_hint(net, skb);
197dbf24 PA	134
d8269e2c EC	135	/* dispatch old sublist */
	136	if (!list_empty(&sublist))
	137	ip6_sublist_rcv_finish(&sublist);
	138	/* start new sublist */
	139	INIT_LIST_HEAD(&sublist);
	140	curr_dst = dst;
	141	}
	142	list_add_tail(&skb->list, &sublist);
	143	}
	144	/* dispatch final sublist */
	145	ip6_sublist_rcv_finish(&sublist);
	146	}
	147
	148	static struct sk_buff ip6_rcv_core(struct sk_buff skb, struct net_device *dev,
	149	struct net *net)
1da177e4	150	{
4daf841a	151	enum skb_drop_reason reason;
b71d1d42	152	const struct ipv6hdr *hdr;
67ba4152	153	u32 pkt_len;
a11d206d	154	struct inet6_dev *idev;
1da177e4	155
a11d206d	156	if (skb->pkt_type == PACKET_OTHERHOST) {
794c24e9	157	dev_core_stats_rx_otherhost_dropped_inc(skb->dev);
4daf841a	158	kfree_skb_reason(skb, SKB_DROP_REASON_OTHERHOST);
d8269e2c	159	return NULL;
a11d206d YH	160	}
	161
	162	rcu_read_lock();
1da177e4	163
a11d206d YH	164	idev = __in6_dev_get(skb->dev);
a11d206d YH	165
c2005eb0	166	__IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_IN, skb->len);
1da177e4	167
4daf841a	168	SKB_DR_SET(reason, NOT_SPECIFIED);
778d80be YH	169	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL \|\|
778d80be YH	170	!idev \|\| unlikely(idev->cnf.disable_ipv6)) {
1d015503	171	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
0339d25a	172	if (idev && unlikely(idev->cnf.disable_ipv6))
4daf841a	173	SKB_DR_SET(reason, IPV6DISABLED);
71f6f6df	174	goto drop;
1da177e4 LT	175	}
1da177e4 LT	176
6b7fdc3a GC	177	memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
6b7fdc3a GC	178
1da177e4 LT	179	/*
	180	* Store incoming device index. When the packet will
	181	* be queued, we cannot refer to skb->dev anymore.
	182	*
	183	* BTW, when we send a packet for our own local address on a
	184	* non-loopback interface (e.g. ethX), it is being delivered
de3cb747	185	* via the loopback interface (lo) here; skb->dev = loopback_dev.
1da177e4 LT	186	* It, however, should be considered as if it is being
	187	* arrived via the sending interface (ethX), because of the
	188	* nature of scoping architecture. --yoshfuji
	189	*/
48fb6b55	190	IP6CB(skb)->iif = skb_valid_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex;
1da177e4	191
2889139a	192	if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
1da177e4 LT	193	goto err;
1da177e4 LT	194
0660e03f	195	hdr = ipv6_hdr(skb);
1da177e4	196
4daf841a MD	197	if (hdr->version != 6) {
4daf841a MD	198	SKB_DR_SET(reason, UNHANDLED_PROTO);
1da177e4	199	goto err;
4daf841a	200	}
1da177e4	201
1d015503 ED	202	__IP6_ADD_STATS(net, idev,
1d015503 ED	203	IPSTATS_MIB_NOECTPKTS +
1f07d03e	204	(ipv6_get_dsfield(hdr) & INET_ECN_MASK),
1d015503	205	max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
f630e43a YH	206	/*
f630e43a YH	207	* RFC4291 2.5.3
0aa8c13e FW	208	* The loopback address must not be used as the source address in IPv6
0aa8c13e FW	209	* packets that are sent outside of a single node. [..]
f630e43a YH	210	* A packet received on an interface with a destination address
	211	* of loopback must be dropped.
	212	*/
0aa8c13e FW	213	if ((ipv6_addr_loopback(&hdr->saddr) \|\|
0aa8c13e FW	214	ipv6_addr_loopback(&hdr->daddr)) &&
3ede0bbc RS	215	!(dev->flags & IFF_LOOPBACK) &&
3ede0bbc RS	216	!netif_is_l3_master(dev))
f630e43a YH	217	goto err;
f630e43a YH	218
1c4a154e HFS	219	/* RFC4291 Errata ID: 3480
	220	* Interface-Local scope spans only a single interface on a
	221	* node and is useful only for loopback transmission of
	222	* multicast. Packets with interface-local scope received
	223	* from another node must be discarded.
	224	*/
	225	if (!(skb->pkt_type == PACKET_LOOPBACK \|\|
	226	dev->flags & IFF_LOOPBACK) &&
	227	ipv6_addr_is_multicast(&hdr->daddr) &&
	228	IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1)
	229	goto err;
	230
abbc3043 JB	231	/* If enabled, drop unicast packets that were encapsulated in link-layer
	232	* multicast or broadcast to protected against the so-called "hole-196"
	233	* attack in 802.11 wireless.
	234	*/
	235	if (!ipv6_addr_is_multicast(&hdr->daddr) &&
	236	(skb->pkt_type == PACKET_BROADCAST \|\|
	237	skb->pkt_type == PACKET_MULTICAST) &&
4daf841a MD	238	idev->cnf.drop_unicast_in_l2_multicast) {
4daf841a MD	239	SKB_DR_SET(reason, UNICAST_IN_L2_MULTICAST);
abbc3043	240	goto err;
4daf841a	241	}
abbc3043	242
20314092 HFS	243	/* RFC4291 2.7
	244	* Nodes must not originate a packet to a multicast address whose scope
	245	* field contains the reserved value 0; if such a packet is received, it
	246	* must be silently dropped.
	247	*/
	248	if (ipv6_addr_is_multicast(&hdr->daddr) &&
	249	IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0)
	250	goto err;
	251
c457338d BH	252	/*
	253	* RFC4291 2.7
	254	* Multicast addresses must not be used as source addresses in IPv6
	255	* packets or appear in any Routing header.
	256	*/
	257	if (ipv6_addr_is_multicast(&hdr->saddr))
	258	goto err;
	259
b0e380b1	260	skb->transport_header = skb->network_header + sizeof(*hdr);
951dbc8a PM	261	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
951dbc8a PM	262
1da177e4 LT	263	pkt_len = ntohs(hdr->payload_len);
	264
	265	/* pkt_len may be zero if Jumbo payload option is present */
	266	if (pkt_len \|\| hdr->nexthdr != NEXTHDR_HOP) {
60e5c166	267	if (pkt_len + sizeof(struct ipv6hdr) > skb->len) {
1d015503 ED	268	__IP6_INC_STATS(net,
1d015503 ED	269	idev, IPSTATS_MIB_INTRUNCATEDPKTS);
4daf841a	270	SKB_DR_SET(reason, PKT_TOO_SMALL);
60e5c166 MC	271	goto drop;
60e5c166 MC	272	}
4daf841a MD	273	if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr)))
4daf841a MD	274	goto err;
0660e03f	275	hdr = ipv6_hdr(skb);
1da177e4 LT	276	}
	277
	278	if (hdr->nexthdr == NEXTHDR_HOP) {
e5bbef20	279	if (ipv6_parse_hopopts(skb) < 0) {
1d015503	280	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
a11d206d	281	rcu_read_unlock();
d8269e2c	282	return NULL;
1da177e4	283	}
1da177e4 LT	284	}
1da177e4 LT	285
a11d206d YH	286	rcu_read_unlock();
a11d206d YH	287
71f9dacd	288	/* Must drop socket now because of tproxy. */
cf7fbe66 JS	289	if (!skb_sk_is_prefetched(skb))
cf7fbe66 JS	290	skb_orphan(skb);
71f9dacd	291
d8269e2c	292	return skb;
1da177e4	293	err:
1d015503	294	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
4daf841a	295	SKB_DR_OR(reason, IP_INHDR);
1da177e4	296	drop:
a11d206d	297	rcu_read_unlock();
4daf841a	298	kfree_skb_reason(skb, reason);
d8269e2c EC	299	return NULL;
	300	}
	301
	302	int ipv6_rcv(struct sk_buff skb, struct net_device dev, struct packet_type pt, struct net_device orig_dev)
	303	{
	304	struct net *net = dev_net(skb->dev);
	305
	306	skb = ip6_rcv_core(skb, dev, net);
	307	if (skb == NULL)
	308	return NET_RX_DROP;
	309	return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
	310	net, NULL, skb, dev, NULL,
	311	ip6_rcv_finish);
	312	}
	313
	314	static void ip6_sublist_rcv(struct list_head head, struct net_device dev,
	315	struct net *net)
	316	{
	317	NF_HOOK_LIST(NFPROTO_IPV6, NF_INET_PRE_ROUTING, net, NULL,
	318	head, dev, NULL, ip6_rcv_finish);
	319	ip6_list_rcv_finish(net, NULL, head);
	320	}
	321
	322	/* Receive a list of IPv6 packets */
	323	void ipv6_list_rcv(struct list_head head, struct packet_type pt,
	324	struct net_device *orig_dev)
	325	{
	326	struct net_device *curr_dev = NULL;
	327	struct net *curr_net = NULL;
	328	struct sk_buff skb, next;
	329	struct list_head sublist;
	330
	331	INIT_LIST_HEAD(&sublist);
	332	list_for_each_entry_safe(skb, next, head, list) {
	333	struct net_device *dev = skb->dev;
	334	struct net *net = dev_net(dev);
	335
22f6bbb7	336	skb_list_del_init(skb);
d8269e2c EC	337	skb = ip6_rcv_core(skb, dev, net);
	338	if (skb == NULL)
	339	continue;
	340
	341	if (curr_dev != dev \|\| curr_net != net) {
	342	/* dispatch old sublist */
	343	if (!list_empty(&sublist))
	344	ip6_sublist_rcv(&sublist, curr_dev, curr_net);
	345	/* start new sublist */
	346	INIT_LIST_HEAD(&sublist);
	347	curr_dev = dev;
	348	curr_net = net;
	349	}
	350	list_add_tail(&skb->list, &sublist);
	351	}
	352	/* dispatch final sublist */
51210ad5 FW	353	if (!list_empty(&sublist))
51210ad5 FW	354	ip6_sublist_rcv(&sublist, curr_dev, curr_net);
1da177e4 LT	355	}
1da177e4 LT	356
0e219ae4 PA	357	INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *));
0e219ae4 PA	358
1da177e4 LT	359	/*
	360	* Deliver the packet to the host
	361	*/
80bde363 PA	362	void ip6_protocol_deliver_rcu(struct net net, struct sk_buff skb, int nexthdr,
80bde363 PA	363	bool have_final)
1da177e4	364	{
41135cc8	365	const struct inet6_protocol *ipprot;
f9242b6b	366	struct inet6_dev *idev;
1da177e4	367	unsigned int nhoff;
eeab7e7f	368	SKB_DR(reason);
a50feda5	369	bool raw;
1da177e4	370
1da177e4 LT	371	/*
	372	* Parse extension headers
	373	*/
	374
1b0ccfe5	375	resubmit:
adf30907	376	idev = ip6_dst_idev(skb_dst(skb));
951dbc8a	377	nhoff = IP6CB(skb)->nhoff;
80bde363 PA	378	if (!have_final) {
	379	if (!pskb_pull(skb, skb_transport_offset(skb)))
	380	goto discard;
	381	nexthdr = skb_network_header(skb)[nhoff];
	382	}
1da177e4	383
4c64242a	384	resubmit_final:
69d6da0b	385	raw = raw6_local_deliver(skb, nexthdr);
e5d08d71	386	ipprot = rcu_dereference(inet6_protos[nexthdr]);
53b24b8f	387	if (ipprot) {
1da177e4	388	int ret;
1ab1457c	389
1da44f9c TH	390	if (have_final) {
	391	if (!(ipprot->flags & INET6_PROTO_FINAL)) {
	392	/* Once we've seen a final protocol don't
	393	* allow encapsulation on any non-final
	394	* ones. This allows foo in UDP encapsulation
	395	* to work.
	396	*/
	397	goto discard;
	398	}
	399	} else if (ipprot->flags & INET6_PROTO_FINAL) {
b71d1d42	400	const struct ipv6hdr *hdr;
5226b6a9 MM	401	int sdif = inet6_sdif(skb);
5226b6a9 MM	402	struct net_device *dev;
1da177e4	403
1da44f9c TH	404	/* Only do this once for first final protocol */
	405	have_final = true;
	406
9fb9cbb1	407
d56f90a7	408	skb_postpull_rcsum(skb, skb_network_header(skb),
cfe1fc77	409	skb_network_header_len(skb));
0660e03f	410	hdr = ipv6_hdr(skb);
5226b6a9 MM	411
	412	/* skb->dev passed may be master dev for vrfs. */
	413	if (sdif) {
	414	dev = dev_get_by_index_rcu(net, sdif);
	415	if (!dev)
	416	goto discard;
	417	} else {
	418	dev = skb->dev;
	419	}
	420
1da177e4	421	if (ipv6_addr_is_multicast(&hdr->daddr) &&
5226b6a9 MM	422	!ipv6_chk_mcast_addr(dev, &hdr->daddr,
5226b6a9 MM	423	&hdr->saddr) &&
eeab7e7f MD	424	!ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb))) {
eeab7e7f MD	425	SKB_DR_SET(reason, IP_INADDRERRORS);
1da177e4	426	goto discard;
eeab7e7f	427	}
1da177e4	428	}
b0e214d2 MK	429	if (!(ipprot->flags & INET6_PROTO_NOPOLICY)) {
	430	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
	431	SKB_DR_SET(reason, XFRM_POLICY);
	432	goto discard;
	433	}
	434	nf_reset_ct(skb);
eeab7e7f	435	}
1ab1457c	436
0e219ae4 PA	437	ret = INDIRECT_CALL_2(ipprot->handler, tcp_v6_rcv, udpv6_rcv,
0e219ae4 PA	438	skb);
4c64242a TH	439	if (ret > 0) {
	440	if (ipprot->flags & INET6_PROTO_FINAL) {
	441	/* Not an extension header, most likely UDP
	442	* encapsulation. Use return value as nexthdr
	443	* protocol not nhoff (which presumably is
	444	* not set by handler).
	445	*/
	446	nexthdr = ret;
	447	goto resubmit_final;
	448	} else {
	449	goto resubmit;
	450	}
	451	} else if (ret == 0) {
1d015503	452	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
4c64242a	453	}
1da177e4	454	} else {
69d6da0b	455	if (!raw) {
1da177e4	456	if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
1d015503 ED	457	__IP6_INC_STATS(net, idev,
1d015503 ED	458	IPSTATS_MIB_INUNKNOWNPROTOS);
fad87aca	459	icmpv6_send(skb, ICMPV6_PARAMPROB,
3ffe533c	460	ICMPV6_UNK_NEXTHDR, nhoff);
eeab7e7f MD	461	SKB_DR_SET(reason, IP_NOPROTO);
	462	} else {
	463	SKB_DR_SET(reason, XFRM_POLICY);
1da177e4	464	}
eeab7e7f	465	kfree_skb_reason(skb, reason);
d8c6f4b9	466	} else {
1d015503	467	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
d8c6f4b9 NH	468	consume_skb(skb);
d8c6f4b9 NH	469	}
1da177e4	470	}
80bde363	471	return;
1da177e4 LT	472
1da177e4 LT	473	discard:
1d015503	474	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
eeab7e7f	475	kfree_skb_reason(skb, reason);
80bde363 PA	476	}
	477
	478	static int ip6_input_finish(struct net net, struct sock sk, struct sk_buff *skb)
	479	{
cd14e9b7	480	skb_clear_delivery_time(skb);
80bde363 PA	481	rcu_read_lock();
	482	ip6_protocol_deliver_rcu(net, skb, 0, false);
	483	rcu_read_unlock();
	484
1da177e4 LT	485	return 0;
	486	}
	487
	488
	489	int ip6_input(struct sk_buff *skb)
	490	{
29a26a56 EB	491	return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN,
29a26a56 EB	492	dev_net(skb->dev), NULL, skb, skb->dev, NULL,
6e23ae2a	493	ip6_input_finish);
1da177e4	494	}
b4869aa2	495	EXPORT_SYMBOL_GPL(ip6_input);
1da177e4 LT	496
	497	int ip6_mc_input(struct sk_buff *skb)
	498	{
5226b6a9	499	int sdif = inet6_sdif(skb);
b71d1d42	500	const struct ipv6hdr *hdr;
5226b6a9	501	struct net_device *dev;
a50feda5	502	bool deliver;
1da177e4	503
c2005eb0	504	__IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev),
bdb7cc64	505	__in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST,
edf391ff	506	skb->len);
1da177e4	507
5226b6a9 MM	508	/* skb->dev passed may be master dev for vrfs. */
	509	if (sdif) {
	510	rcu_read_lock();
	511	dev = dev_get_by_index_rcu(dev_net(skb->dev), sdif);
	512	if (!dev) {
	513	rcu_read_unlock();
	514	kfree_skb(skb);
	515	return -ENODEV;
	516	}
	517	} else {
	518	dev = skb->dev;
	519	}
	520
0660e03f	521	hdr = ipv6_hdr(skb);
5226b6a9 MM	522	deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL);
	523	if (sdif)
	524	rcu_read_unlock();
1da177e4	525
7bc570c8	526	#ifdef CONFIG_IPV6_MROUTE
1da177e4	527	/*
7bc570c8	528	* IPv6 multicast router mode is now supported ;)
1da177e4	529	*/
145c7a79	530	if (atomic_read(&dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding) &&
ddf64354 HFS	531	!(ipv6_addr_type(&hdr->daddr) &
ddf64354 HFS	532	(IPV6_ADDR_LOOPBACK\|IPV6_ADDR_LINKLOCAL)) &&
7bc570c8 YH	533	likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) {
	534	/*
	535	* Okay, we try to forward - split and duplicate
	536	* packets.
	537	*/
	538	struct sk_buff *skb2;
	539	struct inet6_skb_parm *opt = IP6CB(skb);
	540
	541	/* Check for MLD */
dd3332bf	542	if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) {
7bc570c8	543	/* Check if this is a mld message */
7bc570c8	544	u8 nexthdr = hdr->nexthdr;
75f2811c	545	__be16 frag_off;
7bc570c8 YH	546	int offset;
	547
	548	/* Check if the value of Router Alert
	549	* is for MLD (0x0000).
	550	*/
dd3332bf	551	if (opt->ra == htons(IPV6_OPT_ROUTERALERT_MLD)) {
a50feda5	552	deliver = false;
aba6096b	553
7bc570c8 YH	554	if (!ipv6_ext_hdr(nexthdr)) {
7bc570c8 YH	555	/* BUG */
aba6096b	556	goto out;
7bc570c8 YH	557	}
7bc570c8 YH	558	offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
75f2811c	559	&nexthdr, &frag_off);
7bc570c8	560	if (offset < 0)
aba6096b	561	goto out;
7bc570c8	562
4c938d22 A	563	if (ipv6_is_mld(skb, nexthdr, offset))
4c938d22 A	564	deliver = true;
7bc570c8	565
4c938d22	566	goto out;
7bc570c8 YH	567	}
	568	/* unknown RA - process it normally */
	569	}
1da177e4	570
7bc570c8 YH	571	if (deliver)
	572	skb2 = skb_clone(skb, GFP_ATOMIC);
	573	else {
	574	skb2 = skb;
	575	skb = NULL;
	576	}
1ab1457c	577
7bc570c8	578	if (skb2) {
7bc570c8	579	ip6_mr_input(skb2);
1da177e4 LT	580	}
1da177e4 LT	581	}
7bc570c8	582	out:
aba6096b YH	583	#endif
aba6096b YH	584	if (likely(deliver))
1da177e4	585	ip6_input(skb);
aba6096b YH	586	else {
	587	/* discard */
	588	kfree_skb(skb);
1da177e4	589	}
1da177e4 LT	590
	591	return 0;
	592	}