ipv6.c

在linux环境下的流控制传输协议（sctp）的源代码

/* SCTP kernel implementation
 * (C) Copyright IBM Corp. 2002, 2004
 * Copyright (c) 2001 Nokia, Inc.
 * Copyright (c) 2001 La Monte H.P. Yarroll
 * Copyright (c) 2002-2003 Intel Corp.
 *
 * This file is part of the SCTP kernel implementation
 *
 * SCTP over IPv6.
 *
 * This SCTP implementation 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, or (at your option)
 * any later version.
 *
 * This SCTP implementation is distributed in the hope that it
 * will be useful, but WITHOUT ANY WARRANTY; without even the implied
 *		   ************************
 * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
 * See the GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with GNU CC; see the file COPYING.  If not, write to
 * the Free Software Foundation, 59 Temple Place - Suite 330,
 * Boston, MA 02111-1307, USA.
 *
 * Please send any bug reports or fixes you make to the
 * email address(es):
 *    lksctp developers <[e-mail]>
 *
 * Or submit a bug report through the following website:
 *    http://www.sf.net/projects/lksctp
 *
 * Written or modified by:
 *    Le Yanqun		    <[e-mail]>
 *    Hui Huang		    <[e-mail]>
 *    La Monte H.P. Yarroll <[e-mail]>
 *    Sridhar Samudrala	    <[e-mail]>
 *    Jon Grimm		    <[e-mail]>
 *    Ardelle Fan	    <[e-mail]>
 *
 * Based on:
 *	linux/net/ipv6/tcp_ipv6.c
 *
 * Any bugs reported given to us we will try to fix... any fixes shared will
 * be incorporated into the next SCTP release.
 */

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/init.h>
#include <linux/ipsec.h>

#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/random.h>
#include <linux/seq_file.h>

#include <net/protocol.h>
#include <net/ndisc.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/transp_v6.h>
#include <net/addrconf.h>
#include <net/ip6_route.h>
#include <net/inet_common.h>
#include <net/inet_ecn.h>
#include <net/sctp/sctp.h>

#include <asm/uaccess.h>

/* Event handler for inet6 address addition/deletion events.
 * The sctp_local_addr_list needs to be protocted by a spin lock since
 * multiple notifiers (say IPv4 and IPv6) may be running at the same
 * time and thus corrupt the list.
 * The reader side is protected with RCU.
 */
static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
				void *ptr)
{
	struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
	struct sctp_sockaddr_entry *addr = NULL;
	struct sctp_sockaddr_entry *temp;
	int found = 0;

	switch (ev) {
	case NETDEV_UP:
		addr = kmalloc(sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC);
		if (addr) {
			addr->a.v6.sin6_family = AF_INET6;
			addr->a.v6.sin6_port = 0;
			memcpy(&addr->a.v6.sin6_addr, &ifa->addr,
				 sizeof(struct in6_addr));
			addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex;
			addr->valid = 1;
			spin_lock_bh(&sctp_local_addr_lock);
			list_add_tail_rcu(&addr->list, &sctp_local_addr_list);
			spin_unlock_bh(&sctp_local_addr_lock);
		}
		break;
	case NETDEV_DOWN:
		spin_lock_bh(&sctp_local_addr_lock);
		list_for_each_entry_safe(addr, temp,
					&sctp_local_addr_list, list) {
			if (addr->a.sa.sa_family == AF_INET6 &&
					ipv6_addr_equal(&addr->a.v6.sin6_addr,
						&ifa->addr)) {
				found = 1;
				addr->valid = 0;
				list_del_rcu(&addr->list);
				break;
			}
		}
		spin_unlock_bh(&sctp_local_addr_lock);
		if (found)
			call_rcu(&addr->rcu, sctp_local_addr_free);
		break;
	}

	return NOTIFY_DONE;
}

static struct notifier_block sctp_inet6addr_notifier = {
	.notifier_call = sctp_inet6addr_event,
};

/* ICMP error handler. */
SCTP_STATIC void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
			     int type, int code, int offset, __be32 info)
{
	struct inet6_dev *idev;
	struct sock *sk;
	struct sctp_association *asoc;
	struct sctp_transport *transport;
	struct ipv6_pinfo *np;
	sk_buff_data_t saveip, savesctp;
	int err;

	idev = in6_dev_get(skb->dev);

	/* Fix up skb to look at the embedded net header. */
	saveip	 = skb->network_header;
	savesctp = skb->transport_header;
	skb_reset_network_header(skb);
	skb_set_transport_header(skb, offset);
	sk = sctp_err_lookup(AF_INET6, skb, sctp_hdr(skb), &asoc, &transport);
	/* Put back, the original pointers. */
	skb->network_header   = saveip;
	skb->transport_header = savesctp;
	if (!sk) {
		ICMP6_INC_STATS_BH(idev, ICMP6_MIB_INERRORS);
		goto out;
	}

	/* Warning:  The sock lock is held.  Remember to call
	 * sctp_err_finish!
	 */

	switch (type) {
	case ICMPV6_PKT_TOOBIG:
		sctp_icmp_frag_needed(sk, asoc, transport, ntohl(info));
		goto out_unlock;
	case ICMPV6_PARAMPROB:
		if (ICMPV6_UNK_NEXTHDR == code) {
			sctp_icmp_proto_unreachable(sk, asoc, transport);
			goto out_unlock;
		}
		break;
	default:
		break;
	}

	np = inet6_sk(sk);
	icmpv6_err_convert(type, code, &err);
	if (!sock_owned_by_user(sk) && np->recverr) {
		sk->sk_err = err;
		sk->sk_error_report(sk);
	} else {  /* Only an error on timeout */
		sk->sk_err_soft = err;
	}

out_unlock:
	sctp_err_finish(sk, asoc);
out:
	if (likely(idev != NULL))
		in6_dev_put(idev);
}

/* Based on tcp_v6_xmit() in tcp_ipv6.c. */
static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport,
			int ipfragok)
{
	struct sock *sk = skb->sk;
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct flowi fl;

	memset(&fl, 0, sizeof(fl));

	fl.proto = sk->sk_protocol;

	/* Fill in the dest address from the route entry passed with the skb
	 * and the source address from the transport.
	 */
	ipv6_addr_copy(&fl.fl6_dst, &transport->ipaddr.v6.sin6_addr);
	ipv6_addr_copy(&fl.fl6_src, &transport->saddr.v6.sin6_addr);

	fl.fl6_flowlabel = np->flow_label;
	IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel);
	if (ipv6_addr_type(&fl.fl6_src) & IPV6_ADDR_LINKLOCAL)
		fl.oif = transport->saddr.v6.sin6_scope_id;
	else
		fl.oif = sk->sk_bound_dev_if;

	if (np->opt && np->opt->srcrt) {
		struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt;
		ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
	}

	SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, "
			  "src:" NIP6_FMT " dst:" NIP6_FMT "\n",
			  __FUNCTION__, skb, skb->len,
			  NIP6(fl.fl6_src), NIP6(fl.fl6_dst));

	SCTP_INC_STATS(SCTP_MIB_OUTSCTPPACKS);

	return ip6_xmit(sk, skb, &fl, np->opt, ipfragok);
}

/* Returns the dst cache entry for the given source and destination ip
 * addresses.
 */
static struct dst_entry *sctp_v6_get_dst(struct sctp_association *asoc,
					 union sctp_addr *daddr,
					 union sctp_addr *saddr)
{
	struct dst_entry *dst;
	struct flowi fl;

	memset(&fl, 0, sizeof(fl));
	ipv6_addr_copy(&fl.fl6_dst, &daddr->v6.sin6_addr);
	if (ipv6_addr_type(&daddr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
		fl.oif = daddr->v6.sin6_scope_id;


	SCTP_DEBUG_PRINTK("%s: DST=" NIP6_FMT " ",
			  __FUNCTION__, NIP6(fl.fl6_dst));

	if (saddr) {
		ipv6_addr_copy(&fl.fl6_src, &saddr->v6.sin6_addr);
		SCTP_DEBUG_PRINTK(
			"SRC=" NIP6_FMT " - ",
			NIP6(fl.fl6_src));
	}

	dst = ip6_route_output(NULL, &fl);
	if (!dst->error) {
		struct rt6_info *rt;
		rt = (struct rt6_info *)dst;
		SCTP_DEBUG_PRINTK(
			"rt6_dst:" NIP6_FMT " rt6_src:" NIP6_FMT "\n",
			NIP6(rt->rt6i_dst.addr), NIP6(rt->rt6i_src.addr));
		return dst;
	}
	SCTP_DEBUG_PRINTK("NO ROUTE\n");
	dst_release(dst);
	return NULL;
}

/* Returns the number of consecutive initial bits that match in the 2 ipv6
 * addresses.
 */
static inline int sctp_v6_addr_match_len(union sctp_addr *s1,
					 union sctp_addr *s2)
{
	struct in6_addr *a1 = &s1->v6.sin6_addr;
	struct in6_addr *a2 = &s2->v6.sin6_addr;
	int i, j;

	for (i = 0; i < 4 ; i++) {
		__be32 a1xora2;

		a1xora2 = a1->s6_addr32[i] ^ a2->s6_addr32[i];

		if ((j = fls(ntohl(a1xora2))))
			return (i * 32 + 32 - j);
	}

	return (i*32);
}

/* Fills in the source address(saddr) based on the destination address(daddr)
 * and asoc's bind address list.
 */
static void sctp_v6_get_saddr(struct sctp_association *asoc,
			      struct dst_entry *dst,
			      union sctp_addr *daddr,
			      union sctp_addr *saddr)
{
	struct sctp_bind_addr *bp;
	struct sctp_sockaddr_entry *laddr;
	sctp_scope_t scope;
	union sctp_addr *baddr = NULL;
	__u8 matchlen = 0;
	__u8 bmatchlen;

	SCTP_DEBUG_PRINTK("%s: asoc:%p dst:%p "
			  "daddr:" NIP6_FMT " ",
			  __FUNCTION__, asoc, dst, NIP6(daddr->v6.sin6_addr));

	if (!asoc) {
		ipv6_get_saddr(dst, &daddr->v6.sin6_addr,&saddr->v6.sin6_addr);
		SCTP_DEBUG_PRINTK("saddr from ipv6_get_saddr: " NIP6_FMT "\n",
				  NIP6(saddr->v6.sin6_addr));
		return;
	}

	scope = sctp_scope(daddr);

	bp = &asoc->base.bind_addr;

	/* Go through the bind address list and find the best source address
	 * that matches the scope of the destination address.
	 */
	rcu_read_lock();
	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
		if (!laddr->valid)
			continue;
		if ((laddr->state == SCTP_ADDR_SRC) &&
		    (laddr->a.sa.sa_family == AF_INET6) &&
		    (scope <= sctp_scope(&laddr->a))) {
			bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
			if (!baddr || (matchlen < bmatchlen)) {
				baddr = &laddr->a;
				matchlen = bmatchlen;
			}
		}
	}

	if (baddr) {
		memcpy(saddr, baddr, sizeof(union sctp_addr));
		SCTP_DEBUG_PRINTK("saddr: " NIP6_FMT "\n",
				  NIP6(saddr->v6.sin6_addr));
	} else {
		printk(KERN_ERR "%s: asoc:%p Could not find a valid source "
		       "address for the dest:" NIP6_FMT "\n",
		       __FUNCTION__, asoc, NIP6(daddr->v6.sin6_addr));
	}

	rcu_read_unlock();
}

/* Make a copy of all potential local addresses. */
static void sctp_v6_copy_addrlist(struct list_head *addrlist,
				  struct net_device *dev)
{
	struct inet6_dev *in6_dev;
	struct inet6_ifaddr *ifp;
	struct sctp_sockaddr_entry *addr;

	rcu_read_lock();
	if ((in6_dev = __in6_dev_get(dev)) == NULL) {
		rcu_read_unlock();
		return;
	}

	read_lock_bh(&in6_dev->lock);
	for (ifp = in6_dev->addr_list; ifp; ifp = ifp->if_next) {
		/* Add the address to the local list.  */
		addr = t_new(struct sctp_sockaddr_entry, GFP_ATOMIC);
		if (addr) {
			addr->a.v6.sin6_family = AF_INET6;
			addr->a.v6.sin6_port = 0;
			addr->a.v6.sin6_addr = ifp->addr;
			addr->a.v6.sin6_scope_id = dev->ifindex;
			addr->valid = 1;
			INIT_LIST_HEAD(&addr->list);
			INIT_RCU_HEAD(&addr->rcu);
			list_add_tail(&addr->list, addrlist);
		}
	}

	read_unlock_bh(&in6_dev->lock);
	rcu_read_unlock();
}

/* Initialize a sockaddr_storage from in incoming skb. */
static void sctp_v6_from_skb(union sctp_addr *addr,struct sk_buff *skb,
			     int is_saddr)
{
	void *from;
	__be16 *port;
	struct sctphdr *sh;

	port = &addr->v6.sin6_port;
	addr->v6.sin6_family = AF_INET6;
	addr->v6.sin6_flowinfo = 0; /* FIXME */
	addr->v6.sin6_scope_id = ((struct inet6_skb_parm *)skb->cb)->iif;

	sh = sctp_hdr(skb);
	if (is_saddr) {
		*port  = sh->source;
		from = &ipv6_hdr(skb)->saddr;
	} else {
		*port = sh->dest;
		from = &ipv6_hdr(skb)->daddr;
	}
	ipv6_addr_copy(&addr->v6.sin6_addr, from);
}

/* Initialize an sctp_addr from a socket. */
static void sctp_v6_from_sk(union sctp_addr *addr, struct sock *sk)
{
	addr->v6.sin6_family = AF_INET6;
	addr->v6.sin6_port = 0;
	addr->v6.sin6_addr = inet6_sk(sk)->rcv_saddr;
}

/* Initialize sk->sk_rcv_saddr from sctp_addr. */
static void sctp_v6_to_sk_saddr(union sctp_addr *addr, struct sock *sk)
{
	if (addr->sa.sa_family == AF_INET && sctp_sk(sk)->v4mapped) {
		inet6_sk(sk)->rcv_saddr.s6_addr32[0] = 0;
		inet6_sk(sk)->rcv_saddr.s6_addr32[1] = 0;
		inet6_sk(sk)->rcv_saddr.s6_addr32[2] = htonl(0x0000ffff);
		inet6_sk(sk)->rcv_saddr.s6_addr32[3] =
			addr->v4.sin_addr.s_addr;
	} else {
		inet6_sk(sk)->rcv_saddr = addr->v6.sin6_addr;
	}
}

/* Initialize sk->sk_daddr from sctp_addr. */
static void sctp_v6_to_sk_daddr(union sctp_addr *addr, struct sock *sk)
{
	if (addr->sa.sa_family == AF_INET && sctp_sk(sk)->v4mapped) {
		inet6_sk(sk)->daddr.s6_addr32[0] = 0;
		inet6_sk(sk)->daddr.s6_addr32[1] = 0;
		inet6_sk(sk)->daddr.s6_addr32[2] = htonl(0x0000ffff);
		inet6_sk(sk)->daddr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
	} else {
		inet6_sk(sk)->daddr = addr->v6.sin6_addr;
	}
}

/* Initialize a sctp_addr from an address parameter. */
static void sctp_v6_from_addr_param(union sctp_addr *addr,
				    union sctp_addr_param *param,
				    __be16 port, int iif)
{
	addr->v6.sin6_family = AF_INET6;
	addr->v6.sin6_port = port;
	addr->v6.sin6_flowinfo = 0; /* BUG */
	ipv6_addr_copy(&addr->v6.sin6_addr, &param->v6.addr);
	addr->v6.sin6_scope_id = iif;
}

/* Initialize an address parameter from a sctp_addr and return the length
 * of the address parameter.
 */
static int sctp_v6_to_addr_param(const union sctp_addr *addr,
				 union sctp_addr_param *param)
{
	int length = sizeof(sctp_ipv6addr_param_t);

	param->v6.param_hdr.type = SCTP_PARAM_IPV6_ADDRESS;
	param->v6.param_hdr.length = htons(length);
	ipv6_addr_copy(&param->v6.addr, &addr->v6.sin6_addr);

	return length;
}

/* Initialize a sctp_addr from a dst_entry. */
static void sctp_v6_dst_saddr(union sctp_addr *addr, struct dst_entry *dst,
			      __be16 port)
{
	struct rt6_info *rt = (struct rt6_info *)dst;
	addr->sa.sa_family = AF_INET6;
	addr->v6.sin6_port = port;
	ipv6_addr_copy(&addr->v6.sin6_addr, &rt->rt6i_src.addr);
}

/* Compare addresses exactly.
 * v4-mapped-v6 is also in consideration.
 */
static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
			    const union sctp_addr *addr2)
{
	if (addr1->sa.sa_family != addr2->sa.sa_family) {
		if (addr1->sa.sa_family == AF_INET &&
		    addr2->sa.sa_family == AF_INET6 &&
		    ipv6_addr_v4mapped(&addr2->v6.sin6_addr)) {
			if (addr2->v6.sin6_port == addr1->v4.sin_port &&
			    addr2->v6.sin6_addr.s6_addr32[3] ==
			    addr1->v4.sin_addr.s_addr)
				return 1;
		}
		if (addr2->sa.sa_family == AF_INET &&
		    addr1->sa.sa_family == AF_INET6 &&
		    ipv6_addr_v4mapped(&addr1->v6.sin6_addr)) {
			if (addr1->v6.sin6_port == addr2->v4.sin_port &&
			    addr1->v6.sin6_addr.s6_addr32[3] ==
			    addr2->v4.sin_addr.s_addr)
				return 1;
		}
		return 0;
	}
	if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr))
		return 0;
	/* If this is a linklocal address, compare the scope_id. */
	if (ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) {
		if (addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id &&
		    (addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)) {
			return 0;
		}
	}

	return 1;
}

/* Initialize addr struct to INADDR_ANY. */
static void sctp_v6_inaddr_any(union sctp_addr *addr, __be16 port)
{
	memset(addr, 0x00, sizeof(union sctp_addr));
	addr->v6.sin6_family = AF_INET6;
	addr->v6.sin6_port = port;
}

/* Is this a wildcard address? */
static int sctp_v6_is_any(const union sctp_addr *addr)