addrconf.c

linux 内核源代码

		ADBG(("ipv6_add_addr: already assigned\n"));
		err = -EEXIST;
		goto out;
	}

	ifa = kzalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC);

	if (ifa == NULL) {
		ADBG(("ipv6_add_addr: malloc failed\n"));
		err = -ENOBUFS;
		goto out;
	}

	rt = addrconf_dst_alloc(idev, addr, 0);
	if (IS_ERR(rt)) {
		err = PTR_ERR(rt);
		goto out;
	}

	ipv6_addr_copy(&ifa->addr, addr);

	spin_lock_init(&ifa->lock);
	init_timer(&ifa->timer);
	ifa->timer.data = (unsigned long) ifa;
	ifa->scope = scope;
	ifa->prefix_len = pfxlen;
	ifa->flags = flags | IFA_F_TENTATIVE;
	ifa->cstamp = ifa->tstamp = jiffies;

	ifa->rt = rt;

	/*
	 * part one of RFC 4429, section 3.3
	 * We should not configure an address as
	 * optimistic if we do not yet know the link
	 * layer address of our nexhop router
	 */

	if (rt->rt6i_nexthop == NULL)
		ifa->flags &= ~IFA_F_OPTIMISTIC;

	ifa->idev = idev;
	in6_dev_hold(idev);
	/* For caller */
	in6_ifa_hold(ifa);

	/* Add to big hash table */
	hash = ipv6_addr_hash(addr);

	ifa->lst_next = inet6_addr_lst[hash];
	inet6_addr_lst[hash] = ifa;
	in6_ifa_hold(ifa);
	write_unlock(&addrconf_hash_lock);

	write_lock(&idev->lock);
	/* Add to inet6_dev unicast addr list. */
	ipv6_link_dev_addr(idev, ifa);

#ifdef CONFIG_IPV6_PRIVACY
	if (ifa->flags&IFA_F_TEMPORARY) {
		ifa->tmp_next = idev->tempaddr_list;
		idev->tempaddr_list = ifa;
		in6_ifa_hold(ifa);
	}
#endif

	in6_ifa_hold(ifa);
	write_unlock(&idev->lock);
out2:
	rcu_read_unlock_bh();

	if (likely(err == 0))
		atomic_notifier_call_chain(&inet6addr_chain, NETDEV_UP, ifa);
	else {
		kfree(ifa);
		ifa = ERR_PTR(err);
	}

	return ifa;
out:
	write_unlock(&addrconf_hash_lock);
	goto out2;
}

/* This function wants to get referenced ifp and releases it before return */

static void ipv6_del_addr(struct inet6_ifaddr *ifp)
{
	struct inet6_ifaddr *ifa, **ifap;
	struct inet6_dev *idev = ifp->idev;
	int hash;
	int deleted = 0, onlink = 0;
	unsigned long expires = jiffies;

	hash = ipv6_addr_hash(&ifp->addr);

	ifp->dead = 1;

	write_lock_bh(&addrconf_hash_lock);
	for (ifap = &inet6_addr_lst[hash]; (ifa=*ifap) != NULL;
	     ifap = &ifa->lst_next) {
		if (ifa == ifp) {
			*ifap = ifa->lst_next;
			__in6_ifa_put(ifp);
			ifa->lst_next = NULL;
			break;
		}
	}
	write_unlock_bh(&addrconf_hash_lock);

	write_lock_bh(&idev->lock);
#ifdef CONFIG_IPV6_PRIVACY
	if (ifp->flags&IFA_F_TEMPORARY) {
		for (ifap = &idev->tempaddr_list; (ifa=*ifap) != NULL;
		     ifap = &ifa->tmp_next) {
			if (ifa == ifp) {
				*ifap = ifa->tmp_next;
				if (ifp->ifpub) {
					in6_ifa_put(ifp->ifpub);
					ifp->ifpub = NULL;
				}
				__in6_ifa_put(ifp);
				ifa->tmp_next = NULL;
				break;
			}
		}
	}
#endif

	for (ifap = &idev->addr_list; (ifa=*ifap) != NULL;) {
		if (ifa == ifp) {
			*ifap = ifa->if_next;
			__in6_ifa_put(ifp);
			ifa->if_next = NULL;
			if (!(ifp->flags & IFA_F_PERMANENT) || onlink > 0)
				break;
			deleted = 1;
			continue;
		} else if (ifp->flags & IFA_F_PERMANENT) {
			if (ipv6_prefix_equal(&ifa->addr, &ifp->addr,
					      ifp->prefix_len)) {
				if (ifa->flags & IFA_F_PERMANENT) {
					onlink = 1;
					if (deleted)
						break;
				} else {
					unsigned long lifetime;

					if (!onlink)
						onlink = -1;

					spin_lock(&ifa->lock);
					lifetime = min_t(unsigned long,
							 ifa->valid_lft, 0x7fffffffUL/HZ);
					if (time_before(expires,
							ifa->tstamp + lifetime * HZ))
						expires = ifa->tstamp + lifetime * HZ;
					spin_unlock(&ifa->lock);
				}
			}
		}
		ifap = &ifa->if_next;
	}
	write_unlock_bh(&idev->lock);

	ipv6_ifa_notify(RTM_DELADDR, ifp);

	atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifp);

	addrconf_del_timer(ifp);

	/*
	 * Purge or update corresponding prefix
	 *
	 * 1) we don't purge prefix here if address was not permanent.
	 *    prefix is managed by its own lifetime.
	 * 2) if there're no addresses, delete prefix.
	 * 3) if there're still other permanent address(es),
	 *    corresponding prefix is still permanent.
	 * 4) otherwise, update prefix lifetime to the
	 *    longest valid lifetime among the corresponding
	 *    addresses on the device.
	 *    Note: subsequent RA will update lifetime.
	 *
	 * --yoshfuji
	 */
	if ((ifp->flags & IFA_F_PERMANENT) && onlink < 1) {
		struct in6_addr prefix;
		struct rt6_info *rt;

		ipv6_addr_prefix(&prefix, &ifp->addr, ifp->prefix_len);
		rt = rt6_lookup(&prefix, NULL, ifp->idev->dev->ifindex, 1);

		if (rt && ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0)) {
			if (onlink == 0) {
				ip6_del_rt(rt);
				rt = NULL;
			} else if (!(rt->rt6i_flags & RTF_EXPIRES)) {
				rt->rt6i_expires = expires;
				rt->rt6i_flags |= RTF_EXPIRES;
			}
		}
		dst_release(&rt->u.dst);
	}

	in6_ifa_put(ifp);
}

#ifdef CONFIG_IPV6_PRIVACY
static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *ift)
{
	struct inet6_dev *idev = ifp->idev;
	struct in6_addr addr, *tmpaddr;
	unsigned long tmp_prefered_lft, tmp_valid_lft, tmp_cstamp, tmp_tstamp;
	int tmp_plen;
	int ret = 0;
	int max_addresses;
	u32 addr_flags;

	write_lock(&idev->lock);
	if (ift) {
		spin_lock_bh(&ift->lock);
		memcpy(&addr.s6_addr[8], &ift->addr.s6_addr[8], 8);
		spin_unlock_bh(&ift->lock);
		tmpaddr = &addr;
	} else {
		tmpaddr = NULL;
	}
retry:
	in6_dev_hold(idev);
	if (idev->cnf.use_tempaddr <= 0) {
		write_unlock(&idev->lock);
		printk(KERN_INFO
			"ipv6_create_tempaddr(): use_tempaddr is disabled.\n");
		in6_dev_put(idev);
		ret = -1;
		goto out;
	}
	spin_lock_bh(&ifp->lock);
	if (ifp->regen_count++ >= idev->cnf.regen_max_retry) {
		idev->cnf.use_tempaddr = -1;	/*XXX*/
		spin_unlock_bh(&ifp->lock);
		write_unlock(&idev->lock);
		printk(KERN_WARNING
			"ipv6_create_tempaddr(): regeneration time exceeded. disabled temporary address support.\n");
		in6_dev_put(idev);
		ret = -1;
		goto out;
	}
	in6_ifa_hold(ifp);
	memcpy(addr.s6_addr, ifp->addr.s6_addr, 8);
	if (__ipv6_try_regen_rndid(idev, tmpaddr) < 0) {
		spin_unlock_bh(&ifp->lock);
		write_unlock(&idev->lock);
		printk(KERN_WARNING
			"ipv6_create_tempaddr(): regeneration of randomized interface id failed.\n");
		in6_ifa_put(ifp);
		in6_dev_put(idev);
		ret = -1;
		goto out;
	}
	memcpy(&addr.s6_addr[8], idev->rndid, 8);
	tmp_valid_lft = min_t(__u32,
			      ifp->valid_lft,
			      idev->cnf.temp_valid_lft);
	tmp_prefered_lft = min_t(__u32,
				 ifp->prefered_lft,
				 idev->cnf.temp_prefered_lft - desync_factor / HZ);
	tmp_plen = ifp->prefix_len;
	max_addresses = idev->cnf.max_addresses;
	tmp_cstamp = ifp->cstamp;
	tmp_tstamp = ifp->tstamp;
	spin_unlock_bh(&ifp->lock);

	write_unlock(&idev->lock);

	addr_flags = IFA_F_TEMPORARY;
	/* set in addrconf_prefix_rcv() */
	if (ifp->flags & IFA_F_OPTIMISTIC)
		addr_flags |= IFA_F_OPTIMISTIC;

	ift = !max_addresses ||
	      ipv6_count_addresses(idev) < max_addresses ?
		ipv6_add_addr(idev, &addr, tmp_plen,
			      ipv6_addr_type(&addr)&IPV6_ADDR_SCOPE_MASK,
			      addr_flags) : NULL;
	if (!ift || IS_ERR(ift)) {
		in6_ifa_put(ifp);
		in6_dev_put(idev);
		printk(KERN_INFO
			"ipv6_create_tempaddr(): retry temporary address regeneration.\n");
		tmpaddr = &addr;
		write_lock(&idev->lock);
		goto retry;
	}

	spin_lock_bh(&ift->lock);
	ift->ifpub = ifp;
	ift->valid_lft = tmp_valid_lft;
	ift->prefered_lft = tmp_prefered_lft;
	ift->cstamp = tmp_cstamp;
	ift->tstamp = tmp_tstamp;
	spin_unlock_bh(&ift->lock);

	addrconf_dad_start(ift, 0);
	in6_ifa_put(ift);
	in6_dev_put(idev);
out:
	return ret;
}
#endif

/*
 *	Choose an appropriate source address (RFC3484)
 */
struct ipv6_saddr_score {
	int		addr_type;
	unsigned int	attrs;
	int		matchlen;
	int		scope;
	unsigned int	rule;
};

#define IPV6_SADDR_SCORE_LOCAL		0x0001
#define IPV6_SADDR_SCORE_PREFERRED	0x0004
#define IPV6_SADDR_SCORE_HOA		0x0008
#define IPV6_SADDR_SCORE_OIF		0x0010
#define IPV6_SADDR_SCORE_LABEL		0x0020
#define IPV6_SADDR_SCORE_PRIVACY	0x0040

static inline int ipv6_saddr_preferred(int type)
{
	if (type & (IPV6_ADDR_MAPPED|IPV6_ADDR_COMPATv4|
		    IPV6_ADDR_LOOPBACK|IPV6_ADDR_RESERVED))
		return 1;
	return 0;
}

/* static matching label */
static inline int ipv6_saddr_label(const struct in6_addr *addr, int type)
{
 /*
  * 	prefix (longest match)	label
  * 	-----------------------------
  * 	::1/128			0
  * 	::/0			1
  * 	2002::/16		2
  * 	::/96			3
  * 	::ffff:0:0/96		4
  *	fc00::/7		5
  * 	2001::/32		6
  */
	if (type & IPV6_ADDR_LOOPBACK)
		return 0;
	else if (type & IPV6_ADDR_COMPATv4)
		return 3;
	else if (type & IPV6_ADDR_MAPPED)
		return 4;
	else if (addr->s6_addr32[0] == htonl(0x20010000))
		return 6;
	else if (addr->s6_addr16[0] == htons(0x2002))
		return 2;
	else if ((addr->s6_addr[0] & 0xfe) == 0xfc)
		return 5;
	return 1;
}

int ipv6_dev_get_saddr(struct net_device *daddr_dev,
		       struct in6_addr *daddr, struct in6_addr *saddr)
{
	struct ipv6_saddr_score hiscore;
	struct inet6_ifaddr *ifa_result = NULL;
	int daddr_type = __ipv6_addr_type(daddr);
	int daddr_scope = __ipv6_addr_src_scope(daddr_type);
	u32 daddr_label = ipv6_saddr_label(daddr, daddr_type);
	struct net_device *dev;

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

	read_lock(&dev_base_lock);
	rcu_read_lock();

	for_each_netdev(&init_net, dev) {
		struct inet6_dev *idev;
		struct inet6_ifaddr *ifa;

		/* Rule 0: Candidate Source Address (section 4)
		 *  - multicast and link-local destination address,
		 *    the set of candidate source address MUST only
		 *    include addresses assigned to interfaces
		 *    belonging to the same link as the outgoing
		 *    interface.
		 * (- For site-local destination addresses, the
		 *    set of candidate source addresses MUST only
		 *    include addresses assigned to interfaces
		 *    belonging to the same site as the outgoing
		 *    interface.)
		 */
		if ((daddr_type & IPV6_ADDR_MULTICAST ||
		     daddr_scope <= IPV6_ADDR_SCOPE_LINKLOCAL) &&
		    daddr_dev && dev != daddr_dev)
			continue;

		idev = __in6_dev_get(dev);
		if (!idev)
			continue;

		read_lock_bh(&idev->lock);
		for (ifa = idev->addr_list; ifa; ifa = ifa->if_next) {
			struct ipv6_saddr_score score;

			score.addr_type = __ipv6_addr_type(&ifa->addr);

			/* Rule 0:
			 * - Tentative Address (RFC2462 section 5.4)
			 *  - A tentative address is not considered
			 *    "assigned to an interface" in the traditional
			 *    sense, unless it is also flagged as optimistic.
			 * - Candidate Source Address (section 4)
			 *  - In any case, anycast addresses, multicast
			 *    addresses, and the unspecified address MUST
			 *    NOT be included in a candidate set.
			 */
			if ((ifa->flags & IFA_F_TENTATIVE) &&
			    (!(ifa->flags & IFA_F_OPTIMISTIC)))
				continue;
			if (unlikely(score.addr_type == IPV6_ADDR_ANY ||
				     score.addr_type & IPV6_ADDR_MULTICAST)) {
				LIMIT_NETDEBUG(KERN_DEBUG
					       "ADDRCONF: unspecified / multicast address "
					       "assigned as unicast address on %s",
					       dev->name);
				continue;
			}

			score.attrs = 0;
			score.matchlen = 0;
			score.scope = 0;
			score.rule = 0;

			if (ifa_result == NULL) {
				/* record it if the first available entry */
				goto record_it;
			}

			/* Rule 1: Prefer same address */
			if (hiscore.rule < 1) {
				if (ipv6_addr_equal(&ifa_result->addr, daddr))
					hiscore.attrs |= IPV6_SADDR_SCORE_LOCAL;
				hiscore.rule++;
			}
			if (ipv6_addr_equal(&ifa->addr, daddr)) {
				score.attrs |= IPV6_SADDR_SCORE_LOCAL;
				if (!(hiscore.attrs & IPV6_SADDR_SCORE_LOCAL)) {
					score.rule = 1;
					goto record_it;
				}
			} else {
				if (hiscore.attrs & IPV6_SADDR_SCORE_LOCAL)
					continue;
			}

			/* Rule 2: Prefer appropriate scope */
			if (hiscore.rule < 2) {
				hiscore.scope = __ipv6_addr_src_scope(hiscore.addr_type);
				hiscore.rule++;
			}
			score.scope = __ipv6_addr_src_scope(score.addr_type);
			if (hiscore.scope < score.scope) {
				if (hiscore.scope < daddr_scope) {
					score.rule = 2;
					goto record_it;
				} else
					continue;
			} else if (score.scope < hiscore.scope) {
				if (score.scope < daddr_scope)
					break; /* addresses sorted by scope */
				else {
					score.rule = 2;
					goto record_it;
				}
			}

			/* Rule 3: Avoid deprecated and optimistic addresses */
			if (hiscore.rule < 3) {
				if (ipv6_saddr_preferred(hiscore.addr_type) ||
				   (((ifa_result->flags &
				    (IFA_F_DEPRECATED|IFA_F_OPTIMISTIC)) == 0)))
					hiscore.attrs |= IPV6_SADDR_SCORE_PREFERRED;
				hiscore.rule++;
			}
			if (ipv6_saddr_preferred(score.addr_type) ||
			   (((ifa->flags &
			    (IFA_F_DEPRECATED|IFA_F_OPTIMISTIC)) == 0))) {
				score.attrs |= IPV6_SADDR_SCORE_PREFERRED;
				if (!(hiscore.attrs & IPV6_SADDR_SCORE_PREFERRED)) {
					score.rule = 3;
					goto record_it;
				}
			} else {
				if (hiscore.attrs & IPV6_SADDR_SCORE_PREFERRED)
					continue;
			}

			/* Rule 4: Prefer home address */
#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
			if (hiscore.rule < 4) {
				if (ifa_result->flags & IFA_F_HOMEADDRESS)
					hiscore.attrs |= IPV6_SADDR_SCORE_HOA;
				hiscore.rule++;
			}
			if (ifa->flags & IFA_F_HOMEADDRESS) {
				score.attrs |= IPV6_SADDR_SCORE_HOA;
				if (!(ifa_result->flags & IFA_F_HOMEADDRESS)) {
					score.rule = 4;
					goto record_it;
				}
			} else {
				if (hiscore.attrs & IPV6_SADDR_SCORE_HOA)
					continue;
			}
#else
			if (hiscore.rule < 4)
				hiscore.rule++;
#endif

			/* Rule 5: Prefer outgoing interface */
			if (hiscore.rule < 5) {
				if (daddr_dev == NULL ||
				    daddr_dev == ifa_result->idev->dev)
					hiscore.attrs |= IPV6_SADDR_SCORE_OIF;
				hiscore.rule++;
			}
			if (daddr_dev == NULL ||
			    daddr_dev == ifa->idev->dev) {
				score.attrs |= IPV6_SADDR_SCORE_OIF;
				if (!(hiscore.attrs & IPV6_SADDR_SCORE_OIF)) {
					score.rule = 5;
					goto record_it;
				}