devinet.c

linux 内核源代码

/*
 *	NET3	IP device support routines.
 *
 *	Version: $Id: devinet.c,v 1.44 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.
 *
 *	Derived from the IP parts of dev.c 1.0.19
 * 		Authors:	Ross Biro
 *				Fred N. van Kempen, <[e-mail]>
 *				Mark Evans, <[e-mail]>
 *
 *	Additional Authors:
 *		Alan Cox, <[e-mail]>
 *		Alexey Kuznetsov, <[e-mail]>
 *
 *	Changes:
 *		Alexey Kuznetsov:	pa_* fields are replaced with ifaddr
 *					lists.
 *		Cyrus Durgin:		updated for kmod
 *		Matthias Andree:	in devinet_ioctl, compare label and
 *					address (4.4BSD alias style support),
 *					fall back to comparing just the label
 *					if no match found.
 */


#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/if_addr.h>
#include <linux/if_ether.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/notifier.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <linux/kmod.h>

#include <net/arp.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/ip_fib.h>
#include <net/rtnetlink.h>

struct ipv4_devconf ipv4_devconf = {
	.data = {
		[NET_IPV4_CONF_ACCEPT_REDIRECTS - 1] = 1,
		[NET_IPV4_CONF_SEND_REDIRECTS - 1] = 1,
		[NET_IPV4_CONF_SECURE_REDIRECTS - 1] = 1,
		[NET_IPV4_CONF_SHARED_MEDIA - 1] = 1,
	},
};

static struct ipv4_devconf ipv4_devconf_dflt = {
	.data = {
		[NET_IPV4_CONF_ACCEPT_REDIRECTS - 1] = 1,
		[NET_IPV4_CONF_SEND_REDIRECTS - 1] = 1,
		[NET_IPV4_CONF_SECURE_REDIRECTS - 1] = 1,
		[NET_IPV4_CONF_SHARED_MEDIA - 1] = 1,
		[NET_IPV4_CONF_ACCEPT_SOURCE_ROUTE - 1] = 1,
	},
};

#define IPV4_DEVCONF_DFLT(attr) IPV4_DEVCONF(ipv4_devconf_dflt, attr)

static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
	[IFA_LOCAL]     	= { .type = NLA_U32 },
	[IFA_ADDRESS]   	= { .type = NLA_U32 },
	[IFA_BROADCAST] 	= { .type = NLA_U32 },
	[IFA_ANYCAST]   	= { .type = NLA_U32 },
	[IFA_LABEL]     	= { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
};

static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32);

static BLOCKING_NOTIFIER_HEAD(inetaddr_chain);
static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
			 int destroy);
#ifdef CONFIG_SYSCTL
static void devinet_sysctl_register(struct in_device *in_dev,
				    struct ipv4_devconf *p);
static void devinet_sysctl_unregister(struct ipv4_devconf *p);
#endif

/* Locks all the inet devices. */

static struct in_ifaddr *inet_alloc_ifa(void)
{
	struct in_ifaddr *ifa = kzalloc(sizeof(*ifa), GFP_KERNEL);

	if (ifa) {
		INIT_RCU_HEAD(&ifa->rcu_head);
	}

	return ifa;
}

static void inet_rcu_free_ifa(struct rcu_head *head)
{
	struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head);
	if (ifa->ifa_dev)
		in_dev_put(ifa->ifa_dev);
	kfree(ifa);
}

static inline void inet_free_ifa(struct in_ifaddr *ifa)
{
	call_rcu(&ifa->rcu_head, inet_rcu_free_ifa);
}

void in_dev_finish_destroy(struct in_device *idev)
{
	struct net_device *dev = idev->dev;

	BUG_TRAP(!idev->ifa_list);
	BUG_TRAP(!idev->mc_list);
#ifdef NET_REFCNT_DEBUG
	printk(KERN_DEBUG "in_dev_finish_destroy: %p=%s\n",
	       idev, dev ? dev->name : "NIL");
#endif
	dev_put(dev);
	if (!idev->dead)
		printk("Freeing alive in_device %p\n", idev);
	else {
		kfree(idev);
	}
}

static struct in_device *inetdev_init(struct net_device *dev)
{
	struct in_device *in_dev;

	ASSERT_RTNL();

	in_dev = kzalloc(sizeof(*in_dev), GFP_KERNEL);
	if (!in_dev)
		goto out;
	INIT_RCU_HEAD(&in_dev->rcu_head);
	memcpy(&in_dev->cnf, &ipv4_devconf_dflt, sizeof(in_dev->cnf));
	in_dev->cnf.sysctl = NULL;
	in_dev->dev = dev;
	if ((in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl)) == NULL)
		goto out_kfree;
	/* Reference in_dev->dev */
	dev_hold(dev);
#ifdef CONFIG_SYSCTL
	neigh_sysctl_register(dev, in_dev->arp_parms, NET_IPV4,
			      NET_IPV4_NEIGH, "ipv4", NULL, NULL);
#endif

	/* Account for reference dev->ip_ptr (below) */
	in_dev_hold(in_dev);

#ifdef CONFIG_SYSCTL
	devinet_sysctl_register(in_dev, &in_dev->cnf);
#endif
	ip_mc_init_dev(in_dev);
	if (dev->flags & IFF_UP)
		ip_mc_up(in_dev);

	/* we can receive as soon as ip_ptr is set -- do this last */
	rcu_assign_pointer(dev->ip_ptr, in_dev);
out:
	return in_dev;
out_kfree:
	kfree(in_dev);
	in_dev = NULL;
	goto out;
}

static void in_dev_rcu_put(struct rcu_head *head)
{
	struct in_device *idev = container_of(head, struct in_device, rcu_head);
	in_dev_put(idev);
}

static void inetdev_destroy(struct in_device *in_dev)
{
	struct in_ifaddr *ifa;
	struct net_device *dev;

	ASSERT_RTNL();

	dev = in_dev->dev;

	in_dev->dead = 1;

	ip_mc_destroy_dev(in_dev);

	while ((ifa = in_dev->ifa_list) != NULL) {
		inet_del_ifa(in_dev, &in_dev->ifa_list, 0);
		inet_free_ifa(ifa);
	}

#ifdef CONFIG_SYSCTL
	devinet_sysctl_unregister(&in_dev->cnf);
#endif

	dev->ip_ptr = NULL;

#ifdef CONFIG_SYSCTL
	neigh_sysctl_unregister(in_dev->arp_parms);
#endif
	neigh_parms_release(&arp_tbl, in_dev->arp_parms);
	arp_ifdown(dev);

	call_rcu(&in_dev->rcu_head, in_dev_rcu_put);
}

int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b)
{
	rcu_read_lock();
	for_primary_ifa(in_dev) {
		if (inet_ifa_match(a, ifa)) {
			if (!b || inet_ifa_match(b, ifa)) {
				rcu_read_unlock();
				return 1;
			}
		}
	} endfor_ifa(in_dev);
	rcu_read_unlock();
	return 0;
}

static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
			 int destroy, struct nlmsghdr *nlh, u32 pid)
{
	struct in_ifaddr *promote = NULL;
	struct in_ifaddr *ifa, *ifa1 = *ifap;
	struct in_ifaddr *last_prim = in_dev->ifa_list;
	struct in_ifaddr *prev_prom = NULL;
	int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev);

	ASSERT_RTNL();

	/* 1. Deleting primary ifaddr forces deletion all secondaries
	 * unless alias promotion is set
	 **/

	if (!(ifa1->ifa_flags & IFA_F_SECONDARY)) {
		struct in_ifaddr **ifap1 = &ifa1->ifa_next;

		while ((ifa = *ifap1) != NULL) {
			if (!(ifa->ifa_flags & IFA_F_SECONDARY) &&
			    ifa1->ifa_scope <= ifa->ifa_scope)
				last_prim = ifa;

			if (!(ifa->ifa_flags & IFA_F_SECONDARY) ||
			    ifa1->ifa_mask != ifa->ifa_mask ||
			    !inet_ifa_match(ifa1->ifa_address, ifa)) {
				ifap1 = &ifa->ifa_next;
				prev_prom = ifa;
				continue;
			}

			if (!do_promote) {
				*ifap1 = ifa->ifa_next;

				rtmsg_ifa(RTM_DELADDR, ifa, nlh, pid);
				blocking_notifier_call_chain(&inetaddr_chain,
						NETDEV_DOWN, ifa);
				inet_free_ifa(ifa);
			} else {
				promote = ifa;
				break;
			}
		}
	}

	/* 2. Unlink it */

	*ifap = ifa1->ifa_next;

	/* 3. Announce address deletion */

	/* Send message first, then call notifier.
	   At first sight, FIB update triggered by notifier
	   will refer to already deleted ifaddr, that could confuse
	   netlink listeners. It is not true: look, gated sees
	   that route deleted and if it still thinks that ifaddr
	   is valid, it will try to restore deleted routes... Grr.
	   So that, this order is correct.
	 */
	rtmsg_ifa(RTM_DELADDR, ifa1, nlh, pid);
	blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1);

	if (promote) {

		if (prev_prom) {
			prev_prom->ifa_next = promote->ifa_next;
			promote->ifa_next = last_prim->ifa_next;
			last_prim->ifa_next = promote;
		}

		promote->ifa_flags &= ~IFA_F_SECONDARY;
		rtmsg_ifa(RTM_NEWADDR, promote, nlh, pid);
		blocking_notifier_call_chain(&inetaddr_chain,
				NETDEV_UP, promote);
		for (ifa = promote->ifa_next; ifa; ifa = ifa->ifa_next) {
			if (ifa1->ifa_mask != ifa->ifa_mask ||
			    !inet_ifa_match(ifa1->ifa_address, ifa))
					continue;
			fib_add_ifaddr(ifa);
		}

	}
	if (destroy)
		inet_free_ifa(ifa1);
}

static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
			 int destroy)
{
	__inet_del_ifa(in_dev, ifap, destroy, NULL, 0);
}

static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
			     u32 pid)
{
	struct in_device *in_dev = ifa->ifa_dev;
	struct in_ifaddr *ifa1, **ifap, **last_primary;

	ASSERT_RTNL();

	if (!ifa->ifa_local) {
		inet_free_ifa(ifa);
		return 0;
	}

	ifa->ifa_flags &= ~IFA_F_SECONDARY;
	last_primary = &in_dev->ifa_list;

	for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL;
	     ifap = &ifa1->ifa_next) {
		if (!(ifa1->ifa_flags & IFA_F_SECONDARY) &&
		    ifa->ifa_scope <= ifa1->ifa_scope)
			last_primary = &ifa1->ifa_next;
		if (ifa1->ifa_mask == ifa->ifa_mask &&
		    inet_ifa_match(ifa1->ifa_address, ifa)) {
			if (ifa1->ifa_local == ifa->ifa_local) {
				inet_free_ifa(ifa);
				return -EEXIST;
			}
			if (ifa1->ifa_scope != ifa->ifa_scope) {
				inet_free_ifa(ifa);
				return -EINVAL;
			}
			ifa->ifa_flags |= IFA_F_SECONDARY;
		}
	}

	if (!(ifa->ifa_flags & IFA_F_SECONDARY)) {
		net_srandom(ifa->ifa_local);
		ifap = last_primary;
	}

	ifa->ifa_next = *ifap;
	*ifap = ifa;

	/* Send message first, then call notifier.
	   Notifier will trigger FIB update, so that
	   listeners of netlink will know about new ifaddr */
	rtmsg_ifa(RTM_NEWADDR, ifa, nlh, pid);
	blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);

	return 0;
}

static int inet_insert_ifa(struct in_ifaddr *ifa)
{
	return __inet_insert_ifa(ifa, NULL, 0);
}

static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa)
{
	struct in_device *in_dev = __in_dev_get_rtnl(dev);

	ASSERT_RTNL();

	if (!in_dev) {
		inet_free_ifa(ifa);
		return -ENOBUFS;
	}
	ipv4_devconf_setall(in_dev);
	if (ifa->ifa_dev != in_dev) {
		BUG_TRAP(!ifa->ifa_dev);
		in_dev_hold(in_dev);
		ifa->ifa_dev = in_dev;
	}
	if (LOOPBACK(ifa->ifa_local))
		ifa->ifa_scope = RT_SCOPE_HOST;
	return inet_insert_ifa(ifa);
}

struct in_device *inetdev_by_index(int ifindex)
{
	struct net_device *dev;
	struct in_device *in_dev = NULL;
	read_lock(&dev_base_lock);
	dev = __dev_get_by_index(&init_net, ifindex);
	if (dev)
		in_dev = in_dev_get(dev);
	read_unlock(&dev_base_lock);
	return in_dev;
}

/* Called only from RTNL semaphored context. No locks. */

struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
				    __be32 mask)
{
	ASSERT_RTNL();

	for_primary_ifa(in_dev) {
		if (ifa->ifa_mask == mask && inet_ifa_match(prefix, ifa))
			return ifa;
	} endfor_ifa(in_dev);
	return NULL;
}

static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct nlattr *tb[IFA_MAX+1];
	struct in_device *in_dev;
	struct ifaddrmsg *ifm;
	struct in_ifaddr *ifa, **ifap;
	int err = -EINVAL;

	ASSERT_RTNL();

	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy);
	if (err < 0)
		goto errout;

	ifm = nlmsg_data(nlh);
	in_dev = inetdev_by_index(ifm->ifa_index);
	if (in_dev == NULL) {
		err = -ENODEV;
		goto errout;
	}

	__in_dev_put(in_dev);

	for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
	     ifap = &ifa->ifa_next) {
		if (tb[IFA_LOCAL] &&
		    ifa->ifa_local != nla_get_be32(tb[IFA_LOCAL]))
			continue;

		if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label))
			continue;

		if (tb[IFA_ADDRESS] &&
		    (ifm->ifa_prefixlen != ifa->ifa_prefixlen ||
		    !inet_ifa_match(nla_get_be32(tb[IFA_ADDRESS]), ifa)))
			continue;

		__inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).pid);
		return 0;
	}

	err = -EADDRNOTAVAIL;
errout:
	return err;
}

static struct in_ifaddr *rtm_to_ifaddr(struct nlmsghdr *nlh)
{
	struct nlattr *tb[IFA_MAX+1];
	struct in_ifaddr *ifa;
	struct ifaddrmsg *ifm;
	struct net_device *dev;
	struct in_device *in_dev;
	int err = -EINVAL;

	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy);
	if (err < 0)
		goto errout;

	ifm = nlmsg_data(nlh);
	if (ifm->ifa_prefixlen > 32 || tb[IFA_LOCAL] == NULL) {
		err = -EINVAL;
		goto errout;
	}

	dev = __dev_get_by_index(&init_net, ifm->ifa_index);
	if (dev == NULL) {
		err = -ENODEV;
		goto errout;
	}

	in_dev = __in_dev_get_rtnl(dev);
	if (in_dev == NULL) {
		err = -ENOBUFS;
		goto errout;
	}

	ifa = inet_alloc_ifa();
	if (ifa == NULL) {
		/*
		 * A potential indev allocation can be left alive, it stays
		 * assigned to its device and is destroy with it.
		 */
		err = -ENOBUFS;
		goto errout;