ndisc.c

linux 内核源代码

/*
 *	Neighbour Discovery for IPv6
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<[e-mail]>
 *	Mike Shaver		<[e-mail]>
 *
 *	This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 */

/*
 *	Changes:
 *
 *	Pierre Ynard			:	export userland ND options
 *						through netlink (RDNSS support)
 *	Lars Fenneberg			:	fixed MTU setting on receipt
 *						of an RA.
 *	Janos Farkas			:	kmalloc failure checks
 *	Alexey Kuznetsov		:	state machine reworked
 *						and moved to net/core.
 *	Pekka Savola			:	RFC2461 validation
 *	YOSHIFUJI Hideaki @USAGI	:	Verify ND options properly
 */

/* Set to 3 to get tracing... */
#define ND_DEBUG 1

#define ND_PRINTK(fmt, args...) do { if (net_ratelimit()) { printk(fmt, ## args); } } while(0)
#define ND_NOPRINTK(x...) do { ; } while(0)
#define ND_PRINTK0 ND_PRINTK
#define ND_PRINTK1 ND_NOPRINTK
#define ND_PRINTK2 ND_NOPRINTK
#define ND_PRINTK3 ND_NOPRINTK
#if ND_DEBUG >= 1
#undef ND_PRINTK1
#define ND_PRINTK1 ND_PRINTK
#endif
#if ND_DEBUG >= 2
#undef ND_PRINTK2
#define ND_PRINTK2 ND_PRINTK
#endif
#if ND_DEBUG >= 3
#undef ND_PRINTK3
#define ND_PRINTK3 ND_PRINTK
#endif

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/sched.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/route.h>
#include <linux/init.h>
#include <linux/rcupdate.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif

#include <linux/if_addr.h>
#include <linux/if_arp.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/jhash.h>

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

#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/ndisc.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/icmp.h>

#include <net/netlink.h>
#include <linux/rtnetlink.h>

#include <net/flow.h>
#include <net/ip6_checksum.h>
#include <linux/proc_fs.h>

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

static struct socket *ndisc_socket;

static u32 ndisc_hash(const void *pkey, const struct net_device *dev);
static int ndisc_constructor(struct neighbour *neigh);
static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb);
static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
static int pndisc_constructor(struct pneigh_entry *n);
static void pndisc_destructor(struct pneigh_entry *n);
static void pndisc_redo(struct sk_buff *skb);

static struct neigh_ops ndisc_generic_ops = {
	.family =		AF_INET6,
	.solicit =		ndisc_solicit,
	.error_report =		ndisc_error_report,
	.output =		neigh_resolve_output,
	.connected_output =	neigh_connected_output,
	.hh_output =		dev_queue_xmit,
	.queue_xmit =		dev_queue_xmit,
};

static struct neigh_ops ndisc_hh_ops = {
	.family =		AF_INET6,
	.solicit =		ndisc_solicit,
	.error_report =		ndisc_error_report,
	.output =		neigh_resolve_output,
	.connected_output =	neigh_resolve_output,
	.hh_output =		dev_queue_xmit,
	.queue_xmit =		dev_queue_xmit,
};


static struct neigh_ops ndisc_direct_ops = {
	.family =		AF_INET6,
	.output =		dev_queue_xmit,
	.connected_output =	dev_queue_xmit,
	.hh_output =		dev_queue_xmit,
	.queue_xmit =		dev_queue_xmit,
};

struct neigh_table nd_tbl = {
	.family =	AF_INET6,
	.entry_size =	sizeof(struct neighbour) + sizeof(struct in6_addr),
	.key_len =	sizeof(struct in6_addr),
	.hash =		ndisc_hash,
	.constructor =	ndisc_constructor,
	.pconstructor =	pndisc_constructor,
	.pdestructor =	pndisc_destructor,
	.proxy_redo =	pndisc_redo,
	.id =		"ndisc_cache",
	.parms = {
		.tbl =			&nd_tbl,
		.base_reachable_time =	30 * HZ,
		.retrans_time =	 1 * HZ,
		.gc_staletime =	60 * HZ,
		.reachable_time =		30 * HZ,
		.delay_probe_time =	 5 * HZ,
		.queue_len =		 3,
		.ucast_probes =	 3,
		.mcast_probes =	 3,
		.anycast_delay =	 1 * HZ,
		.proxy_delay =		(8 * HZ) / 10,
		.proxy_qlen =		64,
	},
	.gc_interval =	  30 * HZ,
	.gc_thresh1 =	 128,
	.gc_thresh2 =	 512,
	.gc_thresh3 =	1024,
};

/* ND options */
struct ndisc_options {
	struct nd_opt_hdr *nd_opt_array[__ND_OPT_ARRAY_MAX];
#ifdef CONFIG_IPV6_ROUTE_INFO
	struct nd_opt_hdr *nd_opts_ri;
	struct nd_opt_hdr *nd_opts_ri_end;
#endif
	struct nd_opt_hdr *nd_useropts;
	struct nd_opt_hdr *nd_useropts_end;
};

#define nd_opts_src_lladdr	nd_opt_array[ND_OPT_SOURCE_LL_ADDR]
#define nd_opts_tgt_lladdr	nd_opt_array[ND_OPT_TARGET_LL_ADDR]
#define nd_opts_pi		nd_opt_array[ND_OPT_PREFIX_INFO]
#define nd_opts_pi_end		nd_opt_array[__ND_OPT_PREFIX_INFO_END]
#define nd_opts_rh		nd_opt_array[ND_OPT_REDIRECT_HDR]
#define nd_opts_mtu		nd_opt_array[ND_OPT_MTU]

#define NDISC_OPT_SPACE(len) (((len)+2+7)&~7)

/*
 * Return the padding between the option length and the start of the
 * link addr.  Currently only IP-over-InfiniBand needs this, although
 * if RFC 3831 IPv6-over-Fibre Channel is ever implemented it may
 * also need a pad of 2.
 */
static int ndisc_addr_option_pad(unsigned short type)
{
	switch (type) {
	case ARPHRD_INFINIBAND: return 2;
	default:                return 0;
	}
}

static inline int ndisc_opt_addr_space(struct net_device *dev)
{
	return NDISC_OPT_SPACE(dev->addr_len + ndisc_addr_option_pad(dev->type));
}

static u8 *ndisc_fill_addr_option(u8 *opt, int type, void *data, int data_len,
				  unsigned short addr_type)
{
	int space = NDISC_OPT_SPACE(data_len);
	int pad   = ndisc_addr_option_pad(addr_type);

	opt[0] = type;
	opt[1] = space>>3;

	memset(opt + 2, 0, pad);
	opt   += pad;
	space -= pad;

	memcpy(opt+2, data, data_len);
	data_len += 2;
	opt += data_len;
	if ((space -= data_len) > 0)
		memset(opt, 0, space);
	return opt + space;
}

static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
					    struct nd_opt_hdr *end)
{
	int type;
	if (!cur || !end || cur >= end)
		return NULL;
	type = cur->nd_opt_type;
	do {
		cur = ((void *)cur) + (cur->nd_opt_len << 3);
	} while(cur < end && cur->nd_opt_type != type);
	return (cur <= end && cur->nd_opt_type == type ? cur : NULL);
}

static inline int ndisc_is_useropt(struct nd_opt_hdr *opt)
{
	return (opt->nd_opt_type == ND_OPT_RDNSS);
}

static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur,
					     struct nd_opt_hdr *end)
{
	if (!cur || !end || cur >= end)
		return NULL;
	do {
		cur = ((void *)cur) + (cur->nd_opt_len << 3);
	} while(cur < end && !ndisc_is_useropt(cur));
	return (cur <= end && ndisc_is_useropt(cur) ? cur : NULL);
}

static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
						 struct ndisc_options *ndopts)
{
	struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt;

	if (!nd_opt || opt_len < 0 || !ndopts)
		return NULL;
	memset(ndopts, 0, sizeof(*ndopts));
	while (opt_len) {
		int l;
		if (opt_len < sizeof(struct nd_opt_hdr))
			return NULL;
		l = nd_opt->nd_opt_len << 3;
		if (opt_len < l || l == 0)
			return NULL;
		switch (nd_opt->nd_opt_type) {
		case ND_OPT_SOURCE_LL_ADDR:
		case ND_OPT_TARGET_LL_ADDR:
		case ND_OPT_MTU:
		case ND_OPT_REDIRECT_HDR:
			if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) {
				ND_PRINTK2(KERN_WARNING
					   "%s(): duplicated ND6 option found: type=%d\n",
					   __FUNCTION__,
					   nd_opt->nd_opt_type);
			} else {
				ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt;
			}
			break;
		case ND_OPT_PREFIX_INFO:
			ndopts->nd_opts_pi_end = nd_opt;
			if (!ndopts->nd_opt_array[nd_opt->nd_opt_type])
				ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt;
			break;
#ifdef CONFIG_IPV6_ROUTE_INFO
		case ND_OPT_ROUTE_INFO:
			ndopts->nd_opts_ri_end = nd_opt;
			if (!ndopts->nd_opts_ri)
				ndopts->nd_opts_ri = nd_opt;
			break;
#endif
		default:
			if (ndisc_is_useropt(nd_opt)) {
				ndopts->nd_useropts_end = nd_opt;
				if (!ndopts->nd_useropts)
					ndopts->nd_useropts = nd_opt;
			} else {
				/*
				 * Unknown options must be silently ignored,
				 * to accommodate future extension to the
				 * protocol.
				 */
				ND_PRINTK2(KERN_NOTICE
					   "%s(): ignored unsupported option; type=%d, len=%d\n",
					   __FUNCTION__,
					   nd_opt->nd_opt_type, nd_opt->nd_opt_len);
			}
		}
		opt_len -= l;
		nd_opt = ((void *)nd_opt) + l;
	}
	return ndopts;
}

static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p,
				      struct net_device *dev)
{
	u8 *lladdr = (u8 *)(p + 1);
	int lladdrlen = p->nd_opt_len << 3;
	int prepad = ndisc_addr_option_pad(dev->type);
	if (lladdrlen != NDISC_OPT_SPACE(dev->addr_len + prepad))
		return NULL;
	return (lladdr + prepad);
}

int ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int dir)
{
	switch (dev->type) {
	case ARPHRD_ETHER:
	case ARPHRD_IEEE802:	/* Not sure. Check it later. --ANK */
	case ARPHRD_FDDI:
		ipv6_eth_mc_map(addr, buf);
		return 0;
	case ARPHRD_IEEE802_TR:
		ipv6_tr_mc_map(addr,buf);
		return 0;
	case ARPHRD_ARCNET:
		ipv6_arcnet_mc_map(addr, buf);
		return 0;
	case ARPHRD_INFINIBAND:
		ipv6_ib_mc_map(addr, buf);
		return 0;
	default:
		if (dir) {
			memcpy(buf, dev->broadcast, dev->addr_len);
			return 0;
		}
	}
	return -EINVAL;
}

EXPORT_SYMBOL(ndisc_mc_map);

static u32 ndisc_hash(const void *pkey, const struct net_device *dev)
{
	const u32 *p32 = pkey;
	u32 addr_hash, i;

	addr_hash = 0;
	for (i = 0; i < (sizeof(struct in6_addr) / sizeof(u32)); i++)
		addr_hash ^= *p32++;

	return jhash_2words(addr_hash, dev->ifindex, nd_tbl.hash_rnd);
}

static int ndisc_constructor(struct neighbour *neigh)
{
	struct in6_addr *addr = (struct in6_addr*)&neigh->primary_key;
	struct net_device *dev = neigh->dev;
	struct inet6_dev *in6_dev;
	struct neigh_parms *parms;
	int is_multicast = ipv6_addr_is_multicast(addr);

	rcu_read_lock();
	in6_dev = in6_dev_get(dev);
	if (in6_dev == NULL) {
		rcu_read_unlock();
		return -EINVAL;
	}

	parms = in6_dev->nd_parms;
	__neigh_parms_put(neigh->parms);
	neigh->parms = neigh_parms_clone(parms);
	rcu_read_unlock();

	neigh->type = is_multicast ? RTN_MULTICAST : RTN_UNICAST;
	if (!dev->header_ops) {
		neigh->nud_state = NUD_NOARP;
		neigh->ops = &ndisc_direct_ops;
		neigh->output = neigh->ops->queue_xmit;
	} else {
		if (is_multicast) {
			neigh->nud_state = NUD_NOARP;
			ndisc_mc_map(addr, neigh->ha, dev, 1);
		} else if (dev->flags&(IFF_NOARP|IFF_LOOPBACK)) {
			neigh->nud_state = NUD_NOARP;
			memcpy(neigh->ha, dev->dev_addr, dev->addr_len);
			if (dev->flags&IFF_LOOPBACK)
				neigh->type = RTN_LOCAL;
		} else if (dev->flags&IFF_POINTOPOINT) {
			neigh->nud_state = NUD_NOARP;
			memcpy(neigh->ha, dev->broadcast, dev->addr_len);
		}
		if (dev->header_ops->cache)
			neigh->ops = &ndisc_hh_ops;
		else
			neigh->ops = &ndisc_generic_ops;
		if (neigh->nud_state&NUD_VALID)
			neigh->output = neigh->ops->connected_output;
		else
			neigh->output = neigh->ops->output;
	}
	in6_dev_put(in6_dev);
	return 0;
}

static int pndisc_constructor(struct pneigh_entry *n)
{
	struct in6_addr *addr = (struct in6_addr*)&n->key;
	struct in6_addr maddr;
	struct net_device *dev = n->dev;

	if (dev == NULL || __in6_dev_get(dev) == NULL)
		return -EINVAL;
	addrconf_addr_solict_mult(addr, &maddr);
	ipv6_dev_mc_inc(dev, &maddr);
	return 0;
}

static void pndisc_destructor(struct pneigh_entry *n)
{
	struct in6_addr *addr = (struct in6_addr*)&n->key;
	struct in6_addr maddr;
	struct net_device *dev = n->dev;

	if (dev == NULL || __in6_dev_get(dev) == NULL)
		return;
	addrconf_addr_solict_mult(addr, &maddr);
	ipv6_dev_mc_dec(dev, &maddr);
}

/*
 *	Send a Neighbour Advertisement
 */

static inline void ndisc_flow_init(struct flowi *fl, u8 type,
			    struct in6_addr *saddr, struct in6_addr *daddr,
			    int oif)
{
	memset(fl, 0, sizeof(*fl));
	ipv6_addr_copy(&fl->fl6_src, saddr);
	ipv6_addr_copy(&fl->fl6_dst, daddr);
	fl->proto	 	= IPPROTO_ICMPV6;
	fl->fl_icmp_type	= type;
	fl->fl_icmp_code	= 0;
	fl->oif			= oif;
	security_sk_classify_flow(ndisc_socket->sk, fl);
}

static void __ndisc_send(struct net_device *dev,
			 struct neighbour *neigh,
			 struct in6_addr *daddr, struct in6_addr *saddr,
			 struct icmp6hdr *icmp6h, struct in6_addr *target,
			 int llinfo)
{
	struct flowi fl;
	struct dst_entry *dst;
	struct sock *sk = ndisc_socket->sk;
	struct sk_buff *skb;
	struct icmp6hdr *hdr;
	struct inet6_dev *idev;
	int len;
	int err;
	u8 *opt, type;

	type = icmp6h->icmp6_type;

	ndisc_flow_init(&fl, type, saddr, daddr,
			dev->ifindex);

	dst = ndisc_dst_alloc(dev, neigh, daddr, ip6_output);
	if (!dst)
		return;

	err = xfrm_lookup(&dst, &fl, NULL, 0);
	if (err < 0)
		return;

	if (!dev->addr_len)
		llinfo = 0;

	len = sizeof(struct icmp6hdr) + (target ? sizeof(*target) : 0);
	if (llinfo)
		len += ndisc_opt_addr_space(dev);

	skb = sock_alloc_send_skb(sk,
				  (MAX_HEADER + sizeof(struct ipv6hdr) +
				   len + LL_RESERVED_SPACE(dev)),
				  1, &err);
	if (!skb) {
		ND_PRINTK0(KERN_ERR
			   "ICMPv6 ND: %s() failed to allocate an skb.\n",
			   __FUNCTION__);
		dst_release(dst);
		return;
	}

	skb_reserve(skb, LL_RESERVED_SPACE(dev));
	ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len);

	skb->transport_header = skb->tail;
	skb_put(skb, len);

	hdr = (struct icmp6hdr *)skb_transport_header(skb);
	memcpy(hdr, icmp6h, sizeof(*hdr));

	opt = skb_transport_header(skb) + sizeof(struct icmp6hdr);
	if (target) {
		ipv6_addr_copy((struct in6_addr *)opt, target);
		opt += sizeof(*target);
	}

	if (llinfo)
		ndisc_fill_addr_option(opt, llinfo, dev->dev_addr,
				       dev->addr_len, dev->type);

	hdr->icmp6_cksum = csum_ipv6_magic(saddr, daddr, len,
					   IPPROTO_ICMPV6,
					   csum_partial((__u8 *) hdr,
							len, 0));

	skb->dst = dst;

	idev = in6_dev_get(dst->dev);
	IP6_INC_STATS(idev, IPSTATS_MIB_OUTREQUESTS);

	err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, dst_output);
	if (!err) {
		ICMP6MSGOUT_INC_STATS(idev, type);
		ICMP6_INC_STATS(idev, ICMP6_MIB_OUTMSGS);
	}

	if (likely(idev != NULL))
		in6_dev_put(idev);
}

static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh,
		   struct in6_addr *daddr, struct in6_addr *solicited_addr,
		   int router, int solicited, int override, int inc_opt)
{
	struct in6_addr tmpaddr;
	struct inet6_ifaddr *ifp;
	struct in6_addr *src_addr;
	struct icmp6hdr icmp6h = {
		.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT,
	};

	/* for anycast or proxy, solicited_addr != src_addr */
	ifp = ipv6_get_ifaddr(solicited_addr, dev, 1);
	if (ifp) {
		src_addr = solicited_addr;
		if (ifp->flags & IFA_F_OPTIMISTIC)
			override = 0;
		in6_ifa_put(ifp);
	} else {
		if (ipv6_dev_get_saddr(dev, daddr, &tmpaddr))
			return;
		src_addr = &tmpaddr;
	}

	icmp6h.icmp6_router = router;
	icmp6h.icmp6_solicited = solicited;
	icmp6h.icmp6_override = override;

	__ndisc_send(dev, neigh, daddr, src_addr,
		     &icmp6h, solicited_addr,
		     inc_opt ? ND_OPT_TARGET_LL_ADDR : 0);
}

void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
		   struct in6_addr *solicit,
		   struct in6_addr *daddr, struct in6_addr *saddr)
{
	struct in6_addr addr_buf;
	struct icmp6hdr icmp6h = {
		.icmp6_type = NDISC_NEIGHBOUR_SOLICITATION,
	};

	if (saddr == NULL) {
		if (ipv6_get_lladdr(dev, &addr_buf,
				   (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)))
			return;
		saddr = &addr_buf;
	}