devinet.c

linux 内核源代码

	}

	ipv4_devconf_setall(in_dev);
	in_dev_hold(in_dev);

	if (tb[IFA_ADDRESS] == NULL)
		tb[IFA_ADDRESS] = tb[IFA_LOCAL];

	ifa->ifa_prefixlen = ifm->ifa_prefixlen;
	ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen);
	ifa->ifa_flags = ifm->ifa_flags;
	ifa->ifa_scope = ifm->ifa_scope;
	ifa->ifa_dev = in_dev;

	ifa->ifa_local = nla_get_be32(tb[IFA_LOCAL]);
	ifa->ifa_address = nla_get_be32(tb[IFA_ADDRESS]);

	if (tb[IFA_BROADCAST])
		ifa->ifa_broadcast = nla_get_be32(tb[IFA_BROADCAST]);

	if (tb[IFA_ANYCAST])
		ifa->ifa_anycast = nla_get_be32(tb[IFA_ANYCAST]);

	if (tb[IFA_LABEL])
		nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
	else
		memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);

	return ifa;

errout:
	return ERR_PTR(err);
}

static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct in_ifaddr *ifa;

	ASSERT_RTNL();

	ifa = rtm_to_ifaddr(nlh);
	if (IS_ERR(ifa))
		return PTR_ERR(ifa);

	return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).pid);
}

/*
 *	Determine a default network mask, based on the IP address.
 */

static __inline__ int inet_abc_len(__be32 addr)
{
	int rc = -1;	/* Something else, probably a multicast. */

	if (ZERONET(addr))
		rc = 0;
	else {
		__u32 haddr = ntohl(addr);

		if (IN_CLASSA(haddr))
			rc = 8;
		else if (IN_CLASSB(haddr))
			rc = 16;
		else if (IN_CLASSC(haddr))
			rc = 24;
	}

	return rc;
}


int devinet_ioctl(unsigned int cmd, void __user *arg)
{
	struct ifreq ifr;
	struct sockaddr_in sin_orig;
	struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr;
	struct in_device *in_dev;
	struct in_ifaddr **ifap = NULL;
	struct in_ifaddr *ifa = NULL;
	struct net_device *dev;
	char *colon;
	int ret = -EFAULT;
	int tryaddrmatch = 0;

	/*
	 *	Fetch the caller's info block into kernel space
	 */

	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
		goto out;
	ifr.ifr_name[IFNAMSIZ - 1] = 0;

	/* save original address for comparison */
	memcpy(&sin_orig, sin, sizeof(*sin));

	colon = strchr(ifr.ifr_name, ':');
	if (colon)
		*colon = 0;

#ifdef CONFIG_KMOD
	dev_load(&init_net, ifr.ifr_name);
#endif

	switch (cmd) {
	case SIOCGIFADDR:	/* Get interface address */
	case SIOCGIFBRDADDR:	/* Get the broadcast address */
	case SIOCGIFDSTADDR:	/* Get the destination address */
	case SIOCGIFNETMASK:	/* Get the netmask for the interface */
		/* Note that these ioctls will not sleep,
		   so that we do not impose a lock.
		   One day we will be forced to put shlock here (I mean SMP)
		 */
		tryaddrmatch = (sin_orig.sin_family == AF_INET);
		memset(sin, 0, sizeof(*sin));
		sin->sin_family = AF_INET;
		break;

	case SIOCSIFFLAGS:
		ret = -EACCES;
		if (!capable(CAP_NET_ADMIN))
			goto out;
		break;
	case SIOCSIFADDR:	/* Set interface address (and family) */
	case SIOCSIFBRDADDR:	/* Set the broadcast address */
	case SIOCSIFDSTADDR:	/* Set the destination address */
	case SIOCSIFNETMASK: 	/* Set the netmask for the interface */
		ret = -EACCES;
		if (!capable(CAP_NET_ADMIN))
			goto out;
		ret = -EINVAL;
		if (sin->sin_family != AF_INET)
			goto out;
		break;
	default:
		ret = -EINVAL;
		goto out;
	}

	rtnl_lock();

	ret = -ENODEV;
	if ((dev = __dev_get_by_name(&init_net, ifr.ifr_name)) == NULL)
		goto done;

	if (colon)
		*colon = ':';

	if ((in_dev = __in_dev_get_rtnl(dev)) != NULL) {
		if (tryaddrmatch) {
			/* Matthias Andree */
			/* compare label and address (4.4BSD style) */
			/* note: we only do this for a limited set of ioctls
			   and only if the original address family was AF_INET.
			   This is checked above. */
			for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
			     ifap = &ifa->ifa_next) {
				if (!strcmp(ifr.ifr_name, ifa->ifa_label) &&
				    sin_orig.sin_addr.s_addr ==
							ifa->ifa_address) {
					break; /* found */
				}
			}
		}
		/* we didn't get a match, maybe the application is
		   4.3BSD-style and passed in junk so we fall back to
		   comparing just the label */
		if (!ifa) {
			for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
			     ifap = &ifa->ifa_next)
				if (!strcmp(ifr.ifr_name, ifa->ifa_label))
					break;
		}
	}

	ret = -EADDRNOTAVAIL;
	if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS)
		goto done;

	switch (cmd) {
	case SIOCGIFADDR:	/* Get interface address */
		sin->sin_addr.s_addr = ifa->ifa_local;
		goto rarok;

	case SIOCGIFBRDADDR:	/* Get the broadcast address */
		sin->sin_addr.s_addr = ifa->ifa_broadcast;
		goto rarok;

	case SIOCGIFDSTADDR:	/* Get the destination address */
		sin->sin_addr.s_addr = ifa->ifa_address;
		goto rarok;

	case SIOCGIFNETMASK:	/* Get the netmask for the interface */
		sin->sin_addr.s_addr = ifa->ifa_mask;
		goto rarok;

	case SIOCSIFFLAGS:
		if (colon) {
			ret = -EADDRNOTAVAIL;
			if (!ifa)
				break;
			ret = 0;
			if (!(ifr.ifr_flags & IFF_UP))
				inet_del_ifa(in_dev, ifap, 1);
			break;
		}
		ret = dev_change_flags(dev, ifr.ifr_flags);
		break;

	case SIOCSIFADDR:	/* Set interface address (and family) */
		ret = -EINVAL;
		if (inet_abc_len(sin->sin_addr.s_addr) < 0)
			break;

		if (!ifa) {
			ret = -ENOBUFS;
			if ((ifa = inet_alloc_ifa()) == NULL)
				break;
			if (colon)
				memcpy(ifa->ifa_label, ifr.ifr_name, IFNAMSIZ);
			else
				memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
		} else {
			ret = 0;
			if (ifa->ifa_local == sin->sin_addr.s_addr)
				break;
			inet_del_ifa(in_dev, ifap, 0);
			ifa->ifa_broadcast = 0;
			ifa->ifa_anycast = 0;
		}

		ifa->ifa_address = ifa->ifa_local = sin->sin_addr.s_addr;

		if (!(dev->flags & IFF_POINTOPOINT)) {
			ifa->ifa_prefixlen = inet_abc_len(ifa->ifa_address);
			ifa->ifa_mask = inet_make_mask(ifa->ifa_prefixlen);
			if ((dev->flags & IFF_BROADCAST) &&
			    ifa->ifa_prefixlen < 31)
				ifa->ifa_broadcast = ifa->ifa_address |
						     ~ifa->ifa_mask;
		} else {
			ifa->ifa_prefixlen = 32;
			ifa->ifa_mask = inet_make_mask(32);
		}
		ret = inet_set_ifa(dev, ifa);
		break;

	case SIOCSIFBRDADDR:	/* Set the broadcast address */
		ret = 0;
		if (ifa->ifa_broadcast != sin->sin_addr.s_addr) {
			inet_del_ifa(in_dev, ifap, 0);
			ifa->ifa_broadcast = sin->sin_addr.s_addr;
			inet_insert_ifa(ifa);
		}
		break;

	case SIOCSIFDSTADDR:	/* Set the destination address */
		ret = 0;
		if (ifa->ifa_address == sin->sin_addr.s_addr)
			break;
		ret = -EINVAL;
		if (inet_abc_len(sin->sin_addr.s_addr) < 0)
			break;
		ret = 0;
		inet_del_ifa(in_dev, ifap, 0);
		ifa->ifa_address = sin->sin_addr.s_addr;
		inet_insert_ifa(ifa);
		break;

	case SIOCSIFNETMASK: 	/* Set the netmask for the interface */

		/*
		 *	The mask we set must be legal.
		 */
		ret = -EINVAL;
		if (bad_mask(sin->sin_addr.s_addr, 0))
			break;
		ret = 0;
		if (ifa->ifa_mask != sin->sin_addr.s_addr) {
			__be32 old_mask = ifa->ifa_mask;
			inet_del_ifa(in_dev, ifap, 0);
			ifa->ifa_mask = sin->sin_addr.s_addr;
			ifa->ifa_prefixlen = inet_mask_len(ifa->ifa_mask);

			/* See if current broadcast address matches
			 * with current netmask, then recalculate
			 * the broadcast address. Otherwise it's a
			 * funny address, so don't touch it since
			 * the user seems to know what (s)he's doing...
			 */
			if ((dev->flags & IFF_BROADCAST) &&
			    (ifa->ifa_prefixlen < 31) &&
			    (ifa->ifa_broadcast ==
			     (ifa->ifa_local|~old_mask))) {
				ifa->ifa_broadcast = (ifa->ifa_local |
						      ~sin->sin_addr.s_addr);
			}
			inet_insert_ifa(ifa);
		}
		break;
	}
done:
	rtnl_unlock();
out:
	return ret;
rarok:
	rtnl_unlock();
	ret = copy_to_user(arg, &ifr, sizeof(struct ifreq)) ? -EFAULT : 0;
	goto out;
}

static int inet_gifconf(struct net_device *dev, char __user *buf, int len)
{
	struct in_device *in_dev = __in_dev_get_rtnl(dev);
	struct in_ifaddr *ifa;
	struct ifreq ifr;
	int done = 0;

	if (!in_dev || (ifa = in_dev->ifa_list) == NULL)
		goto out;

	for (; ifa; ifa = ifa->ifa_next) {
		if (!buf) {
			done += sizeof(ifr);
			continue;
		}
		if (len < (int) sizeof(ifr))
			break;
		memset(&ifr, 0, sizeof(struct ifreq));
		if (ifa->ifa_label)
			strcpy(ifr.ifr_name, ifa->ifa_label);
		else
			strcpy(ifr.ifr_name, dev->name);

		(*(struct sockaddr_in *)&ifr.ifr_addr).sin_family = AF_INET;
		(*(struct sockaddr_in *)&ifr.ifr_addr).sin_addr.s_addr =
								ifa->ifa_local;

		if (copy_to_user(buf, &ifr, sizeof(struct ifreq))) {
			done = -EFAULT;
			break;
		}
		buf  += sizeof(struct ifreq);
		len  -= sizeof(struct ifreq);
		done += sizeof(struct ifreq);
	}
out:
	return done;
}

__be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope)
{
	__be32 addr = 0;
	struct in_device *in_dev;

	rcu_read_lock();
	in_dev = __in_dev_get_rcu(dev);
	if (!in_dev)
		goto no_in_dev;

	for_primary_ifa(in_dev) {
		if (ifa->ifa_scope > scope)
			continue;
		if (!dst || inet_ifa_match(dst, ifa)) {
			addr = ifa->ifa_local;
			break;
		}
		if (!addr)
			addr = ifa->ifa_local;
	} endfor_ifa(in_dev);
no_in_dev:
	rcu_read_unlock();

	if (addr)
		goto out;

	/* Not loopback addresses on loopback should be preferred
	   in this case. It is importnat that lo is the first interface
	   in dev_base list.
	 */
	read_lock(&dev_base_lock);
	rcu_read_lock();
	for_each_netdev(&init_net, dev) {
		if ((in_dev = __in_dev_get_rcu(dev)) == NULL)
			continue;

		for_primary_ifa(in_dev) {
			if (ifa->ifa_scope != RT_SCOPE_LINK &&
			    ifa->ifa_scope <= scope) {
				addr = ifa->ifa_local;
				goto out_unlock_both;
			}
		} endfor_ifa(in_dev);
	}
out_unlock_both:
	read_unlock(&dev_base_lock);
	rcu_read_unlock();
out:
	return addr;
}

static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst,
			      __be32 local, int scope)
{
	int same = 0;
	__be32 addr = 0;

	for_ifa(in_dev) {
		if (!addr &&
		    (local == ifa->ifa_local || !local) &&
		    ifa->ifa_scope <= scope) {
			addr = ifa->ifa_local;
			if (same)
				break;
		}
		if (!same) {
			same = (!local || inet_ifa_match(local, ifa)) &&
				(!dst || inet_ifa_match(dst, ifa));
			if (same && addr) {
				if (local || !dst)
					break;
				/* Is the selected addr into dst subnet? */
				if (inet_ifa_match(addr, ifa))
					break;
				/* No, then can we use new local src? */
				if (ifa->ifa_scope <= scope) {
					addr = ifa->ifa_local;
					break;
				}
				/* search for large dst subnet for addr */
				same = 0;
			}
		}
	} endfor_ifa(in_dev);

	return same? addr : 0;
}

/*
 * Confirm that local IP address exists using wildcards:
 * - dev: only on this interface, 0=any interface
 * - dst: only in the same subnet as dst, 0=any dst
 * - local: address, 0=autoselect the local address
 * - scope: maximum allowed scope value for the local address
 */
__be32 inet_confirm_addr(const struct net_device *dev, __be32 dst, __be32 local, int scope)
{
	__be32 addr = 0;
	struct in_device *in_dev;

	if (dev) {
		rcu_read_lock();
		if ((in_dev = __in_dev_get_rcu(dev)))
			addr = confirm_addr_indev(in_dev, dst, local, scope);
		rcu_read_unlock();

		return addr;
	}

	read_lock(&dev_base_lock);
	rcu_read_lock();
	for_each_netdev(&init_net, dev) {
		if ((in_dev = __in_dev_get_rcu(dev))) {
			addr = confirm_addr_indev(in_dev, dst, local, scope);
			if (addr)
				break;
		}
	}
	rcu_read_unlock();
	read_unlock(&dev_base_lock);

	return addr;
}

/*
 *	Device notifier
 */

int register_inetaddr_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_register(&inetaddr_chain, nb);
}

int unregister_inetaddr_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_unregister(&inetaddr_chain, nb);
}

/* Rename ifa_labels for a device name change. Make some effort to preserve existing
 * alias numbering and to create unique labels if possible.
*/
static void inetdev_changename(struct net_device *dev, struct in_device *in_dev)
{
	struct in_ifaddr *ifa;
	int named = 0;

	for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
		char old[IFNAMSIZ], *dot;

		memcpy(old, ifa->ifa_label, IFNAMSIZ);
		memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
		if (named++ == 0)
			continue;
		dot = strchr(old, ':');
		if (dot == NULL) {
			sprintf(old, ":%d", named);
			dot = old;
		}
		if (strlen(dot) + strlen(dev->name) < IFNAMSIZ) {
			strcat(ifa->ifa_label, dot);
		} else {
			strcpy(ifa->ifa_label + (IFNAMSIZ - strlen(dot) - 1), dot);
		}
	}
}

/* Called only under RTNL semaphore */

static int inetdev_event(struct notifier_block *this, unsigned long event,
			 void *ptr)
{
	struct net_device *dev = ptr;
	struct in_device *in_dev = __in_dev_get_rtnl(dev);

	if (dev->nd_net != &init_net)
		return NOTIFY_DONE;