addrconf.c

linux 内核源代码

/*
 *	IPv6 Address [auto]configuration
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<[e-mail]>
 *	Alexey Kuznetsov	<[e-mail]>
 *
 *	$Id: addrconf.c,v 1.69 2001/10/31 21:55:54 davem Exp $
 *
 *	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:
 *
 *	Janos Farkas			:	delete timer on ifdown
 *	<[e-mail]>
 *	Andi Kleen			:	kill double kfree on module
 *						unload.
 *	Maciej W. Rozycki		:	FDDI support
 *	sekiya@USAGI			:	Don't send too many RS
 *						packets.
 *	yoshfuji@USAGI			:       Fixed interval between DAD
 *						packets.
 *	YOSHIFUJI Hideaki @USAGI	:	improved accuracy of
 *						address validation timer.
 *	YOSHIFUJI Hideaki @USAGI	:	Privacy Extensions (RFC3041)
 *						support.
 *	Yuji SEKIYA @USAGI		:	Don't assign a same IPv6
 *						address on a same interface.
 *	YOSHIFUJI Hideaki @USAGI	:	ARCnet support
 *	YOSHIFUJI Hideaki @USAGI	:	convert /proc/net/if_inet6 to
 *						seq_file.
 *	YOSHIFUJI Hideaki @USAGI	:	improved source address
 *						selection; consider scope,
 *						status etc.
 */

#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_addr.h>
#include <linux/if_arp.h>
#include <linux/if_arcnet.h>
#include <linux/if_infiniband.h>
#include <linux/route.h>
#include <linux/inetdevice.h>
#include <linux/init.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <linux/capability.h>
#include <linux/delay.h>
#include <linux/notifier.h>
#include <linux/string.h>

#include <net/net_namespace.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/tcp.h>
#include <net/ip.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <linux/if_tunnel.h>
#include <linux/rtnetlink.h>

#ifdef CONFIG_IPV6_PRIVACY
#include <linux/random.h>
#endif

#include <asm/uaccess.h>
#include <asm/unaligned.h>

#include <linux/proc_fs.h>
#include <linux/seq_file.h>

/* Set to 3 to get tracing... */
#define ACONF_DEBUG 2

#if ACONF_DEBUG >= 3
#define ADBG(x) printk x
#else
#define ADBG(x)
#endif

#define	INFINITY_LIFE_TIME	0xFFFFFFFF
#define TIME_DELTA(a,b) ((unsigned long)((long)(a) - (long)(b)))

#ifdef CONFIG_SYSCTL
static void addrconf_sysctl_register(struct inet6_dev *idev, struct ipv6_devconf *p);
static void addrconf_sysctl_unregister(struct ipv6_devconf *p);
#endif

#ifdef CONFIG_IPV6_PRIVACY
static int __ipv6_regen_rndid(struct inet6_dev *idev);
static int __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr);
static void ipv6_regen_rndid(unsigned long data);

static int desync_factor = MAX_DESYNC_FACTOR * HZ;
#endif

static int ipv6_count_addresses(struct inet6_dev *idev);

/*
 *	Configured unicast address hash table
 */
static struct inet6_ifaddr		*inet6_addr_lst[IN6_ADDR_HSIZE];
static DEFINE_RWLOCK(addrconf_hash_lock);

static void addrconf_verify(unsigned long);

static DEFINE_TIMER(addr_chk_timer, addrconf_verify, 0, 0);
static DEFINE_SPINLOCK(addrconf_verify_lock);

static void addrconf_join_anycast(struct inet6_ifaddr *ifp);
static void addrconf_leave_anycast(struct inet6_ifaddr *ifp);

static int addrconf_ifdown(struct net_device *dev, int how);

static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags);
static void addrconf_dad_timer(unsigned long data);
static void addrconf_dad_completed(struct inet6_ifaddr *ifp);
static void addrconf_dad_run(struct inet6_dev *idev);
static void addrconf_rs_timer(unsigned long data);
static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);

static void inet6_prefix_notify(int event, struct inet6_dev *idev,
				struct prefix_info *pinfo);
static int ipv6_chk_same_addr(const struct in6_addr *addr, struct net_device *dev);

static ATOMIC_NOTIFIER_HEAD(inet6addr_chain);

struct ipv6_devconf ipv6_devconf __read_mostly = {
	.forwarding		= 0,
	.hop_limit		= IPV6_DEFAULT_HOPLIMIT,
	.mtu6			= IPV6_MIN_MTU,
	.accept_ra		= 1,
	.accept_redirects	= 1,
	.autoconf		= 1,
	.force_mld_version	= 0,
	.dad_transmits		= 1,
	.rtr_solicits		= MAX_RTR_SOLICITATIONS,
	.rtr_solicit_interval	= RTR_SOLICITATION_INTERVAL,
	.rtr_solicit_delay	= MAX_RTR_SOLICITATION_DELAY,
#ifdef CONFIG_IPV6_PRIVACY
	.use_tempaddr 		= 0,
	.temp_valid_lft		= TEMP_VALID_LIFETIME,
	.temp_prefered_lft	= TEMP_PREFERRED_LIFETIME,
	.regen_max_retry	= REGEN_MAX_RETRY,
	.max_desync_factor	= MAX_DESYNC_FACTOR,
#endif
	.max_addresses		= IPV6_MAX_ADDRESSES,
	.accept_ra_defrtr	= 1,
	.accept_ra_pinfo	= 1,
#ifdef CONFIG_IPV6_ROUTER_PREF
	.accept_ra_rtr_pref	= 1,
	.rtr_probe_interval	= 60 * HZ,
#ifdef CONFIG_IPV6_ROUTE_INFO
	.accept_ra_rt_info_max_plen = 0,
#endif
#endif
	.proxy_ndp		= 0,
	.accept_source_route	= 0,	/* we do not accept RH0 by default. */
};

static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
	.forwarding		= 0,
	.hop_limit		= IPV6_DEFAULT_HOPLIMIT,
	.mtu6			= IPV6_MIN_MTU,
	.accept_ra		= 1,
	.accept_redirects	= 1,
	.autoconf		= 1,
	.dad_transmits		= 1,
	.rtr_solicits		= MAX_RTR_SOLICITATIONS,
	.rtr_solicit_interval	= RTR_SOLICITATION_INTERVAL,
	.rtr_solicit_delay	= MAX_RTR_SOLICITATION_DELAY,
#ifdef CONFIG_IPV6_PRIVACY
	.use_tempaddr		= 0,
	.temp_valid_lft		= TEMP_VALID_LIFETIME,
	.temp_prefered_lft	= TEMP_PREFERRED_LIFETIME,
	.regen_max_retry	= REGEN_MAX_RETRY,
	.max_desync_factor	= MAX_DESYNC_FACTOR,
#endif
	.max_addresses		= IPV6_MAX_ADDRESSES,
	.accept_ra_defrtr	= 1,
	.accept_ra_pinfo	= 1,
#ifdef CONFIG_IPV6_ROUTER_PREF
	.accept_ra_rtr_pref	= 1,
	.rtr_probe_interval	= 60 * HZ,
#ifdef CONFIG_IPV6_ROUTE_INFO
	.accept_ra_rt_info_max_plen = 0,
#endif
#endif
	.proxy_ndp		= 0,
	.accept_source_route	= 0,	/* we do not accept RH0 by default. */
};

/* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */
const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT;
const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT;

/* Check if a valid qdisc is available */
static inline int addrconf_qdisc_ok(struct net_device *dev)
{
	return (dev->qdisc != &noop_qdisc);
}

static void addrconf_del_timer(struct inet6_ifaddr *ifp)
{
	if (del_timer(&ifp->timer))
		__in6_ifa_put(ifp);
}

enum addrconf_timer_t
{
	AC_NONE,
	AC_DAD,
	AC_RS,
};

static void addrconf_mod_timer(struct inet6_ifaddr *ifp,
			       enum addrconf_timer_t what,
			       unsigned long when)
{
	if (!del_timer(&ifp->timer))
		in6_ifa_hold(ifp);

	switch (what) {
	case AC_DAD:
		ifp->timer.function = addrconf_dad_timer;
		break;
	case AC_RS:
		ifp->timer.function = addrconf_rs_timer;
		break;
	default:;
	}
	ifp->timer.expires = jiffies + when;
	add_timer(&ifp->timer);
}

static int snmp6_alloc_dev(struct inet6_dev *idev)
{
	if (snmp_mib_init((void **)idev->stats.ipv6,
			  sizeof(struct ipstats_mib),
			  __alignof__(struct ipstats_mib)) < 0)
		goto err_ip;
	if (snmp_mib_init((void **)idev->stats.icmpv6,
			  sizeof(struct icmpv6_mib),
			  __alignof__(struct icmpv6_mib)) < 0)
		goto err_icmp;
	if (snmp_mib_init((void **)idev->stats.icmpv6msg,
			  sizeof(struct icmpv6msg_mib),
			  __alignof__(struct icmpv6msg_mib)) < 0)
		goto err_icmpmsg;

	return 0;

err_icmpmsg:
	snmp_mib_free((void **)idev->stats.icmpv6);
err_icmp:
	snmp_mib_free((void **)idev->stats.ipv6);
err_ip:
	return -ENOMEM;
}

static void snmp6_free_dev(struct inet6_dev *idev)
{
	snmp_mib_free((void **)idev->stats.icmpv6msg);
	snmp_mib_free((void **)idev->stats.icmpv6);
	snmp_mib_free((void **)idev->stats.ipv6);
}

/* Nobody refers to this device, we may destroy it. */

static void in6_dev_finish_destroy_rcu(struct rcu_head *head)
{
	struct inet6_dev *idev = container_of(head, struct inet6_dev, rcu);
	kfree(idev);
}

void in6_dev_finish_destroy(struct inet6_dev *idev)
{
	struct net_device *dev = idev->dev;
	BUG_TRAP(idev->addr_list==NULL);
	BUG_TRAP(idev->mc_list==NULL);
#ifdef NET_REFCNT_DEBUG
	printk(KERN_DEBUG "in6_dev_finish_destroy: %s\n", dev ? dev->name : "NIL");
#endif
	dev_put(dev);
	if (!idev->dead) {
		printk("Freeing alive inet6 device %p\n", idev);
		return;
	}
	snmp6_free_dev(idev);
	call_rcu(&idev->rcu, in6_dev_finish_destroy_rcu);
}

EXPORT_SYMBOL(in6_dev_finish_destroy);

static struct inet6_dev * ipv6_add_dev(struct net_device *dev)
{
	struct inet6_dev *ndev;
	struct in6_addr maddr;

	ASSERT_RTNL();

	if (dev->mtu < IPV6_MIN_MTU)
		return NULL;

	ndev = kzalloc(sizeof(struct inet6_dev), GFP_KERNEL);

	if (ndev == NULL)
		return NULL;

	rwlock_init(&ndev->lock);
	ndev->dev = dev;
	memcpy(&ndev->cnf, &ipv6_devconf_dflt, sizeof(ndev->cnf));
	ndev->cnf.mtu6 = dev->mtu;
	ndev->cnf.sysctl = NULL;
	ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl);
	if (ndev->nd_parms == NULL) {
		kfree(ndev);
		return NULL;
	}
	/* We refer to the device */
	dev_hold(dev);

	if (snmp6_alloc_dev(ndev) < 0) {
		ADBG((KERN_WARNING
			"%s(): cannot allocate memory for statistics; dev=%s.\n",
			__FUNCTION__, dev->name));
		neigh_parms_release(&nd_tbl, ndev->nd_parms);
		ndev->dead = 1;
		in6_dev_finish_destroy(ndev);
		return NULL;
	}

	if (snmp6_register_dev(ndev) < 0) {
		ADBG((KERN_WARNING
			"%s(): cannot create /proc/net/dev_snmp6/%s\n",
			__FUNCTION__, dev->name));
		neigh_parms_release(&nd_tbl, ndev->nd_parms);
		ndev->dead = 1;
		in6_dev_finish_destroy(ndev);
		return NULL;
	}

	/* One reference from device.  We must do this before
	 * we invoke __ipv6_regen_rndid().
	 */
	in6_dev_hold(ndev);

#ifdef CONFIG_IPV6_PRIVACY
	init_timer(&ndev->regen_timer);
	ndev->regen_timer.function = ipv6_regen_rndid;
	ndev->regen_timer.data = (unsigned long) ndev;
	if ((dev->flags&IFF_LOOPBACK) ||
	    dev->type == ARPHRD_TUNNEL ||
#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
	    dev->type == ARPHRD_SIT ||
#endif
	    dev->type == ARPHRD_NONE) {
		printk(KERN_INFO
		       "%s: Disabled Privacy Extensions\n",
		       dev->name);
		ndev->cnf.use_tempaddr = -1;
	} else {
		in6_dev_hold(ndev);
		ipv6_regen_rndid((unsigned long) ndev);
	}
#endif

	if (netif_running(dev) && addrconf_qdisc_ok(dev))
		ndev->if_flags |= IF_READY;

	ipv6_mc_init_dev(ndev);
	ndev->tstamp = jiffies;
#ifdef CONFIG_SYSCTL
	neigh_sysctl_register(dev, ndev->nd_parms, NET_IPV6,
			      NET_IPV6_NEIGH, "ipv6",
			      &ndisc_ifinfo_sysctl_change,
			      NULL);
	addrconf_sysctl_register(ndev, &ndev->cnf);
#endif
	/* protected by rtnl_lock */
	rcu_assign_pointer(dev->ip6_ptr, ndev);

	/* Join all-node multicast group */
	ipv6_addr_all_nodes(&maddr);
	ipv6_dev_mc_inc(dev, &maddr);

	return ndev;
}

static struct inet6_dev * ipv6_find_idev(struct net_device *dev)
{
	struct inet6_dev *idev;

	ASSERT_RTNL();

	if ((idev = __in6_dev_get(dev)) == NULL) {
		if ((idev = ipv6_add_dev(dev)) == NULL)
			return NULL;
	}

	if (dev->flags&IFF_UP)
		ipv6_mc_up(idev);
	return idev;
}

#ifdef CONFIG_SYSCTL
static void dev_forward_change(struct inet6_dev *idev)
{
	struct net_device *dev;
	struct inet6_ifaddr *ifa;
	struct in6_addr addr;

	if (!idev)
		return;
	dev = idev->dev;
	if (dev && (dev->flags & IFF_MULTICAST)) {
		ipv6_addr_all_routers(&addr);

		if (idev->cnf.forwarding)
			ipv6_dev_mc_inc(dev, &addr);
		else
			ipv6_dev_mc_dec(dev, &addr);
	}
	for (ifa=idev->addr_list; ifa; ifa=ifa->if_next) {
		if (ifa->flags&IFA_F_TENTATIVE)
			continue;
		if (idev->cnf.forwarding)
			addrconf_join_anycast(ifa);
		else
			addrconf_leave_anycast(ifa);
	}
}


static void addrconf_forward_change(void)
{
	struct net_device *dev;
	struct inet6_dev *idev;

	read_lock(&dev_base_lock);
	for_each_netdev(&init_net, dev) {
		rcu_read_lock();
		idev = __in6_dev_get(dev);
		if (idev) {
			int changed = (!idev->cnf.forwarding) ^ (!ipv6_devconf.forwarding);
			idev->cnf.forwarding = ipv6_devconf.forwarding;
			if (changed)
				dev_forward_change(idev);
		}
		rcu_read_unlock();
	}
	read_unlock(&dev_base_lock);
}
#endif

/* Nobody refers to this ifaddr, destroy it */

void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp)
{
	BUG_TRAP(ifp->if_next==NULL);
	BUG_TRAP(ifp->lst_next==NULL);
#ifdef NET_REFCNT_DEBUG
	printk(KERN_DEBUG "inet6_ifa_finish_destroy\n");
#endif

	in6_dev_put(ifp->idev);

	if (del_timer(&ifp->timer))
		printk("Timer is still running, when freeing ifa=%p\n", ifp);

	if (!ifp->dead) {
		printk("Freeing alive inet6 address %p\n", ifp);
		return;
	}
	dst_release(&ifp->rt->u.dst);

	kfree(ifp);
}

static void
ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp)
{
	struct inet6_ifaddr *ifa, **ifap;
	int ifp_scope = ipv6_addr_src_scope(&ifp->addr);

	/*
	 * Each device address list is sorted in order of scope -
	 * global before linklocal.
	 */
	for (ifap = &idev->addr_list; (ifa = *ifap) != NULL;
	     ifap = &ifa->if_next) {
		if (ifp_scope >= ipv6_addr_src_scope(&ifa->addr))
			break;
	}

	ifp->if_next = *ifap;
	*ifap = ifp;
}

/* On success it returns ifp with increased reference count */

static struct inet6_ifaddr *
ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
	      int scope, u32 flags)
{
	struct inet6_ifaddr *ifa = NULL;
	struct rt6_info *rt;
	int hash;
	int err = 0;

	rcu_read_lock_bh();
	if (idev->dead) {
		err = -ENODEV;			/*XXX*/
		goto out2;
	}

	write_lock(&addrconf_hash_lock);

	/* Ignore adding duplicate addresses on an interface */
	if (ipv6_chk_same_addr(addr, idev->dev)) {