[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/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) ||
	    IP6CB(skb)->flags & IP6SKB_MULTIPATH)
		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	{
8423be89 SY	102	if (fib6_routes_require_src(net) \|\| fib6_has_custom_rules(net) \|\|
8423be89 SY	103	IP6CB(skb)->flags & IP6SKB_MULTIPATH)
197dbf24 PA	104	return NULL;
	105
	106	return skb;
	107	}
	108
d8269e2c EC	109	static void ip6_list_rcv_finish(struct net net, struct sock sk,
	110	struct list_head *head)
	111	{
197dbf24	112	struct sk_buff skb, next, *hint = NULL;
d8269e2c	113	struct dst_entry *curr_dst = NULL;
d8269e2c EC	114	struct list_head sublist;
	115
	116	INIT_LIST_HEAD(&sublist);
	117	list_for_each_entry_safe(skb, next, head, list) {
	118	struct dst_entry *dst;
	119
22f6bbb7	120	skb_list_del_init(skb);
d8269e2c EC	121	/* if ingress device is enslaved to an L3 master device pass the
	122	* skb to its handler for processing
	123	*/
	124	skb = l3mdev_ip6_rcv(skb);
	125	if (!skb)
	126	continue;
197dbf24 PA	127
	128	if (ip6_can_use_hint(skb, hint))
	129	skb_dst_copy(skb, hint);
	130	else
	131	ip6_rcv_finish_core(net, sk, skb);
d8269e2c EC	132	dst = skb_dst(skb);
d8269e2c EC	133	if (curr_dst != dst) {
197dbf24 PA	134	hint = ip6_extract_route_hint(net, skb);
197dbf24 PA	135
d8269e2c EC	136	/* dispatch old sublist */
	137	if (!list_empty(&sublist))
	138	ip6_sublist_rcv_finish(&sublist);
	139	/* start new sublist */
	140	INIT_LIST_HEAD(&sublist);
	141	curr_dst = dst;
	142	}
	143	list_add_tail(&skb->list, &sublist);
	144	}
	145	/* dispatch final sublist */
	146	ip6_sublist_rcv_finish(&sublist);
	147	}
	148
	149	static struct sk_buff ip6_rcv_core(struct sk_buff skb, struct net_device *dev,
	150	struct net *net)
1da177e4	151	{
4daf841a	152	enum skb_drop_reason reason;
b71d1d42	153	const struct ipv6hdr *hdr;
67ba4152	154	u32 pkt_len;
a11d206d	155	struct inet6_dev *idev;
1da177e4	156
a11d206d	157	if (skb->pkt_type == PACKET_OTHERHOST) {
794c24e9	158	dev_core_stats_rx_otherhost_dropped_inc(skb->dev);
4daf841a	159	kfree_skb_reason(skb, SKB_DROP_REASON_OTHERHOST);
d8269e2c	160	return NULL;
a11d206d YH	161	}
	162
	163	rcu_read_lock();
1da177e4	164
a11d206d YH	165	idev = __in6_dev_get(skb->dev);
a11d206d YH	166
c2005eb0	167	__IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_IN, skb->len);
1da177e4	168
4daf841a	169	SKB_DR_SET(reason, NOT_SPECIFIED);
778d80be YH	170	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL \|\|
778d80be YH	171	!idev \|\| unlikely(idev->cnf.disable_ipv6)) {
1d015503	172	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
0339d25a	173	if (idev && unlikely(idev->cnf.disable_ipv6))
4daf841a	174	SKB_DR_SET(reason, IPV6DISABLED);
71f6f6df	175	goto drop;
1da177e4 LT	176	}
1da177e4 LT	177
6b7fdc3a GC	178	memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
6b7fdc3a GC	179
1da177e4 LT	180	/*
	181	* Store incoming device index. When the packet will
	182	* be queued, we cannot refer to skb->dev anymore.
	183	*
	184	* BTW, when we send a packet for our own local address on a
	185	* non-loopback interface (e.g. ethX), it is being delivered
de3cb747	186	* via the loopback interface (lo) here; skb->dev = loopback_dev.
1da177e4 LT	187	* It, however, should be considered as if it is being
	188	* arrived via the sending interface (ethX), because of the
	189	* nature of scoping architecture. --yoshfuji
	190	*/
48fb6b55	191	IP6CB(skb)->iif = skb_valid_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex;
1da177e4	192
2889139a	193	if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
1da177e4 LT	194	goto err;
1da177e4 LT	195
0660e03f	196	hdr = ipv6_hdr(skb);
1da177e4	197
4daf841a MD	198	if (hdr->version != 6) {
4daf841a MD	199	SKB_DR_SET(reason, UNHANDLED_PROTO);
1da177e4	200	goto err;
4daf841a	201	}
1da177e4	202
1d015503 ED	203	__IP6_ADD_STATS(net, idev,
1d015503 ED	204	IPSTATS_MIB_NOECTPKTS +
1f07d03e	205	(ipv6_get_dsfield(hdr) & INET_ECN_MASK),
1d015503	206	max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
f630e43a YH	207	/*
f630e43a YH	208	* RFC4291 2.5.3
0aa8c13e FW	209	* The loopback address must not be used as the source address in IPv6
0aa8c13e FW	210	* packets that are sent outside of a single node. [..]
f630e43a YH	211	* A packet received on an interface with a destination address
	212	* of loopback must be dropped.
	213	*/
0aa8c13e FW	214	if ((ipv6_addr_loopback(&hdr->saddr) \|\|
0aa8c13e FW	215	ipv6_addr_loopback(&hdr->daddr)) &&
3ede0bbc RS	216	!(dev->flags & IFF_LOOPBACK) &&
3ede0bbc RS	217	!netif_is_l3_master(dev))
f630e43a YH	218	goto err;
f630e43a YH	219
1c4a154e HFS	220	/* RFC4291 Errata ID: 3480
	221	* Interface-Local scope spans only a single interface on a
	222	* node and is useful only for loopback transmission of
	223	* multicast. Packets with interface-local scope received
	224	* from another node must be discarded.
	225	*/
	226	if (!(skb->pkt_type == PACKET_LOOPBACK \|\|
	227	dev->flags & IFF_LOOPBACK) &&
	228	ipv6_addr_is_multicast(&hdr->daddr) &&
	229	IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1)
	230	goto err;
	231
abbc3043 JB	232	/* If enabled, drop unicast packets that were encapsulated in link-layer
	233	* multicast or broadcast to protected against the so-called "hole-196"
	234	* attack in 802.11 wireless.
	235	*/
	236	if (!ipv6_addr_is_multicast(&hdr->daddr) &&
	237	(skb->pkt_type == PACKET_BROADCAST \|\|
	238	skb->pkt_type == PACKET_MULTICAST) &&
4daf841a MD	239	idev->cnf.drop_unicast_in_l2_multicast) {
4daf841a MD	240	SKB_DR_SET(reason, UNICAST_IN_L2_MULTICAST);
abbc3043	241	goto err;
4daf841a	242	}
abbc3043	243
20314092 HFS	244	/* RFC4291 2.7
	245	* Nodes must not originate a packet to a multicast address whose scope
	246	* field contains the reserved value 0; if such a packet is received, it
	247	* must be silently dropped.
	248	*/
	249	if (ipv6_addr_is_multicast(&hdr->daddr) &&
	250	IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0)
	251	goto err;
	252
c457338d BH	253	/*
	254	* RFC4291 2.7
	255	* Multicast addresses must not be used as source addresses in IPv6
	256	* packets or appear in any Routing header.
	257	*/
	258	if (ipv6_addr_is_multicast(&hdr->saddr))
	259	goto err;
	260
b0e380b1	261	skb->transport_header = skb->network_header + sizeof(*hdr);
951dbc8a PM	262	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
951dbc8a PM	263
1da177e4 LT	264	pkt_len = ntohs(hdr->payload_len);
	265
	266	/* pkt_len may be zero if Jumbo payload option is present */
	267	if (pkt_len \|\| hdr->nexthdr != NEXTHDR_HOP) {
60e5c166	268	if (pkt_len + sizeof(struct ipv6hdr) > skb->len) {
1d015503 ED	269	__IP6_INC_STATS(net,
1d015503 ED	270	idev, IPSTATS_MIB_INTRUNCATEDPKTS);
4daf841a	271	SKB_DR_SET(reason, PKT_TOO_SMALL);
60e5c166 MC	272	goto drop;
60e5c166 MC	273	}
4daf841a MD	274	if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr)))
4daf841a MD	275	goto err;
0660e03f	276	hdr = ipv6_hdr(skb);
1da177e4 LT	277	}
	278
	279	if (hdr->nexthdr == NEXTHDR_HOP) {
e5bbef20	280	if (ipv6_parse_hopopts(skb) < 0) {
1d015503	281	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
a11d206d	282	rcu_read_unlock();
d8269e2c	283	return NULL;
1da177e4	284	}
1da177e4 LT	285	}
1da177e4 LT	286
a11d206d YH	287	rcu_read_unlock();
a11d206d YH	288
71f9dacd	289	/* Must drop socket now because of tproxy. */
cf7fbe66 JS	290	if (!skb_sk_is_prefetched(skb))
cf7fbe66 JS	291	skb_orphan(skb);
71f9dacd	292
d8269e2c	293	return skb;
1da177e4	294	err:
1d015503	295	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
4daf841a	296	SKB_DR_OR(reason, IP_INHDR);
1da177e4	297	drop:
a11d206d	298	rcu_read_unlock();
4daf841a	299	kfree_skb_reason(skb, reason);
d8269e2c EC	300	return NULL;
	301	}
	302
	303	int ipv6_rcv(struct sk_buff skb, struct net_device dev, struct packet_type pt, struct net_device orig_dev)
	304	{
	305	struct net *net = dev_net(skb->dev);
	306
	307	skb = ip6_rcv_core(skb, dev, net);
	308	if (skb == NULL)
	309	return NET_RX_DROP;
	310	return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
	311	net, NULL, skb, dev, NULL,
	312	ip6_rcv_finish);
	313	}
	314
	315	static void ip6_sublist_rcv(struct list_head head, struct net_device dev,
	316	struct net *net)
	317	{
	318	NF_HOOK_LIST(NFPROTO_IPV6, NF_INET_PRE_ROUTING, net, NULL,
	319	head, dev, NULL, ip6_rcv_finish);
	320	ip6_list_rcv_finish(net, NULL, head);
	321	}
	322
	323	/* Receive a list of IPv6 packets */
	324	void ipv6_list_rcv(struct list_head head, struct packet_type pt,
	325	struct net_device *orig_dev)
	326	{
	327	struct net_device *curr_dev = NULL;
	328	struct net *curr_net = NULL;
	329	struct sk_buff skb, next;
	330	struct list_head sublist;
	331
	332	INIT_LIST_HEAD(&sublist);
	333	list_for_each_entry_safe(skb, next, head, list) {
	334	struct net_device *dev = skb->dev;
	335	struct net *net = dev_net(dev);
	336
22f6bbb7	337	skb_list_del_init(skb);
d8269e2c EC	338	skb = ip6_rcv_core(skb, dev, net);
	339	if (skb == NULL)
	340	continue;
	341
	342	if (curr_dev != dev \|\| curr_net != net) {
	343	/* dispatch old sublist */
	344	if (!list_empty(&sublist))
	345	ip6_sublist_rcv(&sublist, curr_dev, curr_net);
	346	/* start new sublist */
	347	INIT_LIST_HEAD(&sublist);
	348	curr_dev = dev;
	349	curr_net = net;
	350	}
	351	list_add_tail(&skb->list, &sublist);
	352	}
	353	/* dispatch final sublist */
51210ad5 FW	354	if (!list_empty(&sublist))
51210ad5 FW	355	ip6_sublist_rcv(&sublist, curr_dev, curr_net);
1da177e4 LT	356	}
1da177e4 LT	357
0e219ae4 PA	358	INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *));
0e219ae4 PA	359
1da177e4 LT	360	/*
	361	* Deliver the packet to the host
	362	*/
80bde363 PA	363	void ip6_protocol_deliver_rcu(struct net net, struct sk_buff skb, int nexthdr,
80bde363 PA	364	bool have_final)
1da177e4	365	{
41135cc8	366	const struct inet6_protocol *ipprot;
f9242b6b	367	struct inet6_dev *idev;
1da177e4	368	unsigned int nhoff;
eeab7e7f	369	SKB_DR(reason);
a50feda5	370	bool raw;
1da177e4	371
1da177e4 LT	372	/*
	373	* Parse extension headers
	374	*/
	375
1b0ccfe5	376	resubmit:
adf30907	377	idev = ip6_dst_idev(skb_dst(skb));
951dbc8a	378	nhoff = IP6CB(skb)->nhoff;
80bde363 PA	379	if (!have_final) {
	380	if (!pskb_pull(skb, skb_transport_offset(skb)))
	381	goto discard;
	382	nexthdr = skb_network_header(skb)[nhoff];
	383	}
1da177e4	384
4c64242a	385	resubmit_final:
69d6da0b	386	raw = raw6_local_deliver(skb, nexthdr);
e5d08d71	387	ipprot = rcu_dereference(inet6_protos[nexthdr]);
53b24b8f	388	if (ipprot) {
1da177e4	389	int ret;
1ab1457c	390
1da44f9c TH	391	if (have_final) {
	392	if (!(ipprot->flags & INET6_PROTO_FINAL)) {
	393	/* Once we've seen a final protocol don't
	394	* allow encapsulation on any non-final
	395	* ones. This allows foo in UDP encapsulation
	396	* to work.
	397	*/
	398	goto discard;
	399	}
	400	} else if (ipprot->flags & INET6_PROTO_FINAL) {
b71d1d42	401	const struct ipv6hdr *hdr;
5226b6a9 MM	402	int sdif = inet6_sdif(skb);
5226b6a9 MM	403	struct net_device *dev;
1da177e4	404
1da44f9c TH	405	/* Only do this once for first final protocol */
	406	have_final = true;
	407
9fb9cbb1	408
d56f90a7	409	skb_postpull_rcsum(skb, skb_network_header(skb),
cfe1fc77	410	skb_network_header_len(skb));
0660e03f	411	hdr = ipv6_hdr(skb);
5226b6a9 MM	412
	413	/* skb->dev passed may be master dev for vrfs. */
	414	if (sdif) {
	415	dev = dev_get_by_index_rcu(net, sdif);
	416	if (!dev)
	417	goto discard;
	418	} else {
	419	dev = skb->dev;
	420	}
	421
1da177e4	422	if (ipv6_addr_is_multicast(&hdr->daddr) &&
5226b6a9 MM	423	!ipv6_chk_mcast_addr(dev, &hdr->daddr,
5226b6a9 MM	424	&hdr->saddr) &&
eeab7e7f MD	425	!ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb))) {
eeab7e7f MD	426	SKB_DR_SET(reason, IP_INADDRERRORS);
1da177e4	427	goto discard;
eeab7e7f	428	}
1da177e4	429	}
b0e214d2 MK	430	if (!(ipprot->flags & INET6_PROTO_NOPOLICY)) {
	431	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
	432	SKB_DR_SET(reason, XFRM_POLICY);
	433	goto discard;
	434	}
	435	nf_reset_ct(skb);
eeab7e7f	436	}
1ab1457c	437
0e219ae4 PA	438	ret = INDIRECT_CALL_2(ipprot->handler, tcp_v6_rcv, udpv6_rcv,
0e219ae4 PA	439	skb);
4c64242a TH	440	if (ret > 0) {
	441	if (ipprot->flags & INET6_PROTO_FINAL) {
	442	/* Not an extension header, most likely UDP
	443	* encapsulation. Use return value as nexthdr
	444	* protocol not nhoff (which presumably is
	445	* not set by handler).
	446	*/
	447	nexthdr = ret;
	448	goto resubmit_final;
	449	} else {
	450	goto resubmit;
	451	}
	452	} else if (ret == 0) {
1d015503	453	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
4c64242a	454	}
1da177e4	455	} else {
69d6da0b	456	if (!raw) {
1da177e4	457	if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
1d015503 ED	458	__IP6_INC_STATS(net, idev,
1d015503 ED	459	IPSTATS_MIB_INUNKNOWNPROTOS);
fad87aca	460	icmpv6_send(skb, ICMPV6_PARAMPROB,
3ffe533c	461	ICMPV6_UNK_NEXTHDR, nhoff);
eeab7e7f MD	462	SKB_DR_SET(reason, IP_NOPROTO);
	463	} else {
	464	SKB_DR_SET(reason, XFRM_POLICY);
1da177e4	465	}
eeab7e7f	466	kfree_skb_reason(skb, reason);
d8c6f4b9	467	} else {
1d015503	468	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
d8c6f4b9 NH	469	consume_skb(skb);
d8c6f4b9 NH	470	}
1da177e4	471	}
80bde363	472	return;
1da177e4 LT	473
1da177e4 LT	474	discard:
1d015503	475	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
eeab7e7f	476	kfree_skb_reason(skb, reason);
80bde363 PA	477	}
	478
	479	static int ip6_input_finish(struct net net, struct sock sk, struct sk_buff *skb)
	480	{
cd14e9b7	481	skb_clear_delivery_time(skb);
80bde363 PA	482	rcu_read_lock();
	483	ip6_protocol_deliver_rcu(net, skb, 0, false);
	484	rcu_read_unlock();
	485
1da177e4 LT	486	return 0;
	487	}
	488
	489
	490	int ip6_input(struct sk_buff *skb)
	491	{
29a26a56 EB	492	return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN,
29a26a56 EB	493	dev_net(skb->dev), NULL, skb, skb->dev, NULL,
6e23ae2a	494	ip6_input_finish);
1da177e4	495	}
b4869aa2	496	EXPORT_SYMBOL_GPL(ip6_input);
1da177e4 LT	497
	498	int ip6_mc_input(struct sk_buff *skb)
	499	{
5226b6a9	500	int sdif = inet6_sdif(skb);
b71d1d42	501	const struct ipv6hdr *hdr;
5226b6a9	502	struct net_device *dev;
a50feda5	503	bool deliver;
1da177e4	504
c2005eb0	505	__IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev),
bdb7cc64	506	__in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST,
edf391ff	507	skb->len);
1da177e4	508
5226b6a9 MM	509	/* skb->dev passed may be master dev for vrfs. */
	510	if (sdif) {
	511	rcu_read_lock();
	512	dev = dev_get_by_index_rcu(dev_net(skb->dev), sdif);
	513	if (!dev) {
	514	rcu_read_unlock();
	515	kfree_skb(skb);
	516	return -ENODEV;
	517	}
	518	} else {
	519	dev = skb->dev;
	520	}
	521
0660e03f	522	hdr = ipv6_hdr(skb);
5226b6a9 MM	523	deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL);
	524	if (sdif)
	525	rcu_read_unlock();
1da177e4	526
7bc570c8	527	#ifdef CONFIG_IPV6_MROUTE
1da177e4	528	/*
7bc570c8	529	* IPv6 multicast router mode is now supported ;)
1da177e4	530	*/
145c7a79	531	if (atomic_read(&dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding) &&
ddf64354 HFS	532	!(ipv6_addr_type(&hdr->daddr) &
ddf64354 HFS	533	(IPV6_ADDR_LOOPBACK\|IPV6_ADDR_LINKLOCAL)) &&
7bc570c8 YH	534	likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) {
	535	/*
	536	* Okay, we try to forward - split and duplicate
	537	* packets.
	538	*/
	539	struct sk_buff *skb2;
	540	struct inet6_skb_parm *opt = IP6CB(skb);
	541
	542	/* Check for MLD */
dd3332bf	543	if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) {
7bc570c8	544	/* Check if this is a mld message */
7bc570c8	545	u8 nexthdr = hdr->nexthdr;
75f2811c	546	__be16 frag_off;
7bc570c8 YH	547	int offset;
	548
	549	/* Check if the value of Router Alert
	550	* is for MLD (0x0000).
	551	*/
dd3332bf	552	if (opt->ra == htons(IPV6_OPT_ROUTERALERT_MLD)) {
a50feda5	553	deliver = false;
aba6096b	554
7bc570c8 YH	555	if (!ipv6_ext_hdr(nexthdr)) {
7bc570c8 YH	556	/* BUG */
aba6096b	557	goto out;
7bc570c8 YH	558	}
7bc570c8 YH	559	offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
75f2811c	560	&nexthdr, &frag_off);
7bc570c8	561	if (offset < 0)
aba6096b	562	goto out;
7bc570c8	563
4c938d22 A	564	if (ipv6_is_mld(skb, nexthdr, offset))
4c938d22 A	565	deliver = true;
7bc570c8	566
4c938d22	567	goto out;
7bc570c8 YH	568	}
	569	/* unknown RA - process it normally */
	570	}
1da177e4	571
7bc570c8 YH	572	if (deliver)
	573	skb2 = skb_clone(skb, GFP_ATOMIC);
	574	else {
	575	skb2 = skb;
	576	skb = NULL;
	577	}
1ab1457c	578
7bc570c8	579	if (skb2) {
7bc570c8	580	ip6_mr_input(skb2);
1da177e4 LT	581	}
1da177e4 LT	582	}
7bc570c8	583	out:
aba6096b YH	584	#endif
aba6096b YH	585	if (likely(deliver))
1da177e4	586	ip6_input(skb);
aba6096b YH	587	else {
	588	/* discard */
	589	kfree_skb(skb);
1da177e4	590	}
1da177e4 LT	591
	592	return 0;
	593	}