devinet.c

linux 内核源代码

	ASSERT_RTNL();

	if (!in_dev) {
		if (event == NETDEV_REGISTER) {
			in_dev = inetdev_init(dev);
			if (!in_dev)
				return notifier_from_errno(-ENOMEM);
			if (dev->flags & IFF_LOOPBACK) {
				IN_DEV_CONF_SET(in_dev, NOXFRM, 1);
				IN_DEV_CONF_SET(in_dev, NOPOLICY, 1);
			}
		}
		goto out;
	}

	switch (event) {
	case NETDEV_REGISTER:
		printk(KERN_DEBUG "inetdev_event: bug\n");
		dev->ip_ptr = NULL;
		break;
	case NETDEV_UP:
		if (dev->mtu < 68)
			break;
		if (dev->flags & IFF_LOOPBACK) {
			struct in_ifaddr *ifa;
			if ((ifa = inet_alloc_ifa()) != NULL) {
				ifa->ifa_local =
				  ifa->ifa_address = htonl(INADDR_LOOPBACK);
				ifa->ifa_prefixlen = 8;
				ifa->ifa_mask = inet_make_mask(8);
				in_dev_hold(in_dev);
				ifa->ifa_dev = in_dev;
				ifa->ifa_scope = RT_SCOPE_HOST;
				memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
				inet_insert_ifa(ifa);
			}
		}
		ip_mc_up(in_dev);
		break;
	case NETDEV_DOWN:
		ip_mc_down(in_dev);
		break;
	case NETDEV_CHANGEMTU:
		if (dev->mtu >= 68)
			break;
		/* MTU falled under 68, disable IP */
	case NETDEV_UNREGISTER:
		inetdev_destroy(in_dev);
		break;
	case NETDEV_CHANGENAME:
		/* Do not notify about label change, this event is
		 * not interesting to applications using netlink.
		 */
		inetdev_changename(dev, in_dev);

#ifdef CONFIG_SYSCTL
		devinet_sysctl_unregister(&in_dev->cnf);
		neigh_sysctl_unregister(in_dev->arp_parms);
		neigh_sysctl_register(dev, in_dev->arp_parms, NET_IPV4,
				      NET_IPV4_NEIGH, "ipv4", NULL, NULL);
		devinet_sysctl_register(in_dev, &in_dev->cnf);
#endif
		break;
	}
out:
	return NOTIFY_DONE;
}

static struct notifier_block ip_netdev_notifier = {
	.notifier_call =inetdev_event,
};

static inline size_t inet_nlmsg_size(void)
{
	return NLMSG_ALIGN(sizeof(struct ifaddrmsg))
	       + nla_total_size(4) /* IFA_ADDRESS */
	       + nla_total_size(4) /* IFA_LOCAL */
	       + nla_total_size(4) /* IFA_BROADCAST */
	       + nla_total_size(4) /* IFA_ANYCAST */
	       + nla_total_size(IFNAMSIZ); /* IFA_LABEL */
}

static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
			    u32 pid, u32 seq, int event, unsigned int flags)
{
	struct ifaddrmsg *ifm;
	struct nlmsghdr  *nlh;

	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*ifm), flags);
	if (nlh == NULL)
		return -EMSGSIZE;

	ifm = nlmsg_data(nlh);
	ifm->ifa_family = AF_INET;
	ifm->ifa_prefixlen = ifa->ifa_prefixlen;
	ifm->ifa_flags = ifa->ifa_flags|IFA_F_PERMANENT;
	ifm->ifa_scope = ifa->ifa_scope;
	ifm->ifa_index = ifa->ifa_dev->dev->ifindex;

	if (ifa->ifa_address)
		NLA_PUT_BE32(skb, IFA_ADDRESS, ifa->ifa_address);

	if (ifa->ifa_local)
		NLA_PUT_BE32(skb, IFA_LOCAL, ifa->ifa_local);

	if (ifa->ifa_broadcast)
		NLA_PUT_BE32(skb, IFA_BROADCAST, ifa->ifa_broadcast);

	if (ifa->ifa_anycast)
		NLA_PUT_BE32(skb, IFA_ANYCAST, ifa->ifa_anycast);

	if (ifa->ifa_label[0])
		NLA_PUT_STRING(skb, IFA_LABEL, ifa->ifa_label);

	return nlmsg_end(skb, nlh);

nla_put_failure:
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
}

static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
{
	int idx, ip_idx;
	struct net_device *dev;
	struct in_device *in_dev;
	struct in_ifaddr *ifa;
	int s_ip_idx, s_idx = cb->args[0];

	s_ip_idx = ip_idx = cb->args[1];
	idx = 0;
	for_each_netdev(&init_net, dev) {
		if (idx < s_idx)
			goto cont;
		if (idx > s_idx)
			s_ip_idx = 0;
		if ((in_dev = __in_dev_get_rtnl(dev)) == NULL)
			goto cont;

		for (ifa = in_dev->ifa_list, ip_idx = 0; ifa;
		     ifa = ifa->ifa_next, ip_idx++) {
			if (ip_idx < s_ip_idx)
				continue;
			if (inet_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid,
					     cb->nlh->nlmsg_seq,
					     RTM_NEWADDR, NLM_F_MULTI) <= 0)
				goto done;
		}
cont:
		idx++;
	}

done:
	cb->args[0] = idx;
	cb->args[1] = ip_idx;

	return skb->len;
}

static void rtmsg_ifa(int event, struct in_ifaddr* ifa, struct nlmsghdr *nlh,
		      u32 pid)
{
	struct sk_buff *skb;
	u32 seq = nlh ? nlh->nlmsg_seq : 0;
	int err = -ENOBUFS;

	skb = nlmsg_new(inet_nlmsg_size(), GFP_KERNEL);
	if (skb == NULL)
		goto errout;

	err = inet_fill_ifaddr(skb, ifa, pid, seq, event, 0);
	if (err < 0) {
		/* -EMSGSIZE implies BUG in inet_nlmsg_size() */
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(skb);
		goto errout;
	}
	err = rtnl_notify(skb, pid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL);
errout:
	if (err < 0)
		rtnl_set_sk_err(RTNLGRP_IPV4_IFADDR, err);
}

#ifdef CONFIG_SYSCTL

static void devinet_copy_dflt_conf(int i)
{
	struct net_device *dev;

	read_lock(&dev_base_lock);
	for_each_netdev(&init_net, dev) {
		struct in_device *in_dev;
		rcu_read_lock();
		in_dev = __in_dev_get_rcu(dev);
		if (in_dev && !test_bit(i, in_dev->cnf.state))
			in_dev->cnf.data[i] = ipv4_devconf_dflt.data[i];
		rcu_read_unlock();
	}
	read_unlock(&dev_base_lock);
}

static int devinet_conf_proc(ctl_table *ctl, int write,
			     struct file* filp, void __user *buffer,
			     size_t *lenp, loff_t *ppos)
{
	int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos);

	if (write) {
		struct ipv4_devconf *cnf = ctl->extra1;
		int i = (int *)ctl->data - cnf->data;

		set_bit(i, cnf->state);

		if (cnf == &ipv4_devconf_dflt)
			devinet_copy_dflt_conf(i);
	}

	return ret;
}

static int devinet_conf_sysctl(ctl_table *table, int __user *name, int nlen,
			       void __user *oldval, size_t __user *oldlenp,
			       void __user *newval, size_t newlen)
{
	struct ipv4_devconf *cnf;
	int *valp = table->data;
	int new;
	int i;

	if (!newval || !newlen)
		return 0;

	if (newlen != sizeof(int))
		return -EINVAL;

	if (get_user(new, (int __user *)newval))
		return -EFAULT;

	if (new == *valp)
		return 0;

	if (oldval && oldlenp) {
		size_t len;

		if (get_user(len, oldlenp))
			return -EFAULT;

		if (len) {
			if (len > table->maxlen)
				len = table->maxlen;
			if (copy_to_user(oldval, valp, len))
				return -EFAULT;
			if (put_user(len, oldlenp))
				return -EFAULT;
		}
	}

	*valp = new;

	cnf = table->extra1;
	i = (int *)table->data - cnf->data;

	set_bit(i, cnf->state);

	if (cnf == &ipv4_devconf_dflt)
		devinet_copy_dflt_conf(i);

	return 1;
}

void inet_forward_change(void)
{
	struct net_device *dev;
	int on = IPV4_DEVCONF_ALL(FORWARDING);

	IPV4_DEVCONF_ALL(ACCEPT_REDIRECTS) = !on;
	IPV4_DEVCONF_DFLT(FORWARDING) = on;

	read_lock(&dev_base_lock);
	for_each_netdev(&init_net, dev) {
		struct in_device *in_dev;
		rcu_read_lock();
		in_dev = __in_dev_get_rcu(dev);
		if (in_dev)
			IN_DEV_CONF_SET(in_dev, FORWARDING, on);
		rcu_read_unlock();
	}
	read_unlock(&dev_base_lock);

	rt_cache_flush(0);
}

static int devinet_sysctl_forward(ctl_table *ctl, int write,
				  struct file* filp, void __user *buffer,
				  size_t *lenp, loff_t *ppos)
{
	int *valp = ctl->data;
	int val = *valp;
	int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos);

	if (write && *valp != val) {
		if (valp == &IPV4_DEVCONF_ALL(FORWARDING))
			inet_forward_change();
		else if (valp != &IPV4_DEVCONF_DFLT(FORWARDING))
			rt_cache_flush(0);
	}

	return ret;
}

int ipv4_doint_and_flush(ctl_table *ctl, int write,
			 struct file* filp, void __user *buffer,
			 size_t *lenp, loff_t *ppos)
{
	int *valp = ctl->data;
	int val = *valp;
	int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos);

	if (write && *valp != val)
		rt_cache_flush(0);

	return ret;
}

int ipv4_doint_and_flush_strategy(ctl_table *table, int __user *name, int nlen,
				  void __user *oldval, size_t __user *oldlenp,
				  void __user *newval, size_t newlen)
{
	int ret = devinet_conf_sysctl(table, name, nlen, oldval, oldlenp,
				      newval, newlen);

	if (ret == 1)
		rt_cache_flush(0);

	return ret;
}


#define DEVINET_SYSCTL_ENTRY(attr, name, mval, proc, sysctl) \
	{ \
		.ctl_name	= NET_IPV4_CONF_ ## attr, \
		.procname	= name, \
		.data		= ipv4_devconf.data + \
				  NET_IPV4_CONF_ ## attr - 1, \
		.maxlen		= sizeof(int), \
		.mode		= mval, \
		.proc_handler	= proc, \
		.strategy	= sysctl, \
		.extra1		= &ipv4_devconf, \
	}

#define DEVINET_SYSCTL_RW_ENTRY(attr, name) \
	DEVINET_SYSCTL_ENTRY(attr, name, 0644, devinet_conf_proc, \
			     devinet_conf_sysctl)

#define DEVINET_SYSCTL_RO_ENTRY(attr, name) \
	DEVINET_SYSCTL_ENTRY(attr, name, 0444, devinet_conf_proc, \
			     devinet_conf_sysctl)

#define DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, proc, sysctl) \
	DEVINET_SYSCTL_ENTRY(attr, name, 0644, proc, sysctl)

#define DEVINET_SYSCTL_FLUSHING_ENTRY(attr, name) \
	DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, ipv4_doint_and_flush, \
				     ipv4_doint_and_flush_strategy)

static struct devinet_sysctl_table {
	struct ctl_table_header *sysctl_header;
	ctl_table		devinet_vars[__NET_IPV4_CONF_MAX];
	ctl_table		devinet_dev[2];
	ctl_table		devinet_conf_dir[2];
	ctl_table		devinet_proto_dir[2];
	ctl_table		devinet_root_dir[2];
} devinet_sysctl = {
	.devinet_vars = {
		DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding",
					     devinet_sysctl_forward,
					     devinet_conf_sysctl),
		DEVINET_SYSCTL_RO_ENTRY(MC_FORWARDING, "mc_forwarding"),

		DEVINET_SYSCTL_RW_ENTRY(ACCEPT_REDIRECTS, "accept_redirects"),
		DEVINET_SYSCTL_RW_ENTRY(SECURE_REDIRECTS, "secure_redirects"),
		DEVINET_SYSCTL_RW_ENTRY(SHARED_MEDIA, "shared_media"),
		DEVINET_SYSCTL_RW_ENTRY(RP_FILTER, "rp_filter"),
		DEVINET_SYSCTL_RW_ENTRY(SEND_REDIRECTS, "send_redirects"),
		DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE,
					"accept_source_route"),
		DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"),
		DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"),
		DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"),
		DEVINET_SYSCTL_RW_ENTRY(LOG_MARTIANS, "log_martians"),
		DEVINET_SYSCTL_RW_ENTRY(TAG, "tag"),
		DEVINET_SYSCTL_RW_ENTRY(ARPFILTER, "arp_filter"),
		DEVINET_SYSCTL_RW_ENTRY(ARP_ANNOUNCE, "arp_announce"),
		DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"),
		DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"),

		DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"),
		DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"),
		DEVINET_SYSCTL_FLUSHING_ENTRY(FORCE_IGMP_VERSION,
					      "force_igmp_version"),
		DEVINET_SYSCTL_FLUSHING_ENTRY(PROMOTE_SECONDARIES,
					      "promote_secondaries"),
	},
	.devinet_dev = {
		{
			.ctl_name	= NET_PROTO_CONF_ALL,
			.procname	= "all",
			.mode		= 0555,
			.child		= devinet_sysctl.devinet_vars,
		},
	},
	.devinet_conf_dir = {
		{
			.ctl_name	= NET_IPV4_CONF,
			.procname	= "conf",
			.mode		= 0555,
			.child		= devinet_sysctl.devinet_dev,
		},
	},
	.devinet_proto_dir = {
		{
			.ctl_name	= NET_IPV4,
			.procname	= "ipv4",
			.mode		= 0555,
			.child 		= devinet_sysctl.devinet_conf_dir,
		},
	},
	.devinet_root_dir = {
		{
			.ctl_name	= CTL_NET,
			.procname 	= "net",
			.mode		= 0555,
			.child		= devinet_sysctl.devinet_proto_dir,
		},
	},
};

static void devinet_sysctl_register(struct in_device *in_dev,
				    struct ipv4_devconf *p)
{
	int i;
	struct net_device *dev = in_dev ? in_dev->dev : NULL;
	struct devinet_sysctl_table *t = kmemdup(&devinet_sysctl, sizeof(*t),
						 GFP_KERNEL);
	char *dev_name = NULL;

	if (!t)
		return;
	for (i = 0; i < ARRAY_SIZE(t->devinet_vars) - 1; i++) {
		t->devinet_vars[i].data += (char *)p - (char *)&ipv4_devconf;
		t->devinet_vars[i].extra1 = p;
	}

	if (dev) {
		dev_name = dev->name;
		t->devinet_dev[0].ctl_name = dev->ifindex;
	} else {
		dev_name = "default";
		t->devinet_dev[0].ctl_name = NET_PROTO_CONF_DEFAULT;
	}

	/*
	 * Make a copy of dev_name, because '.procname' is regarded as const
	 * by sysctl and we wouldn't want anyone to change it under our feet
	 * (see SIOCSIFNAME).
	 */
	dev_name = kstrdup(dev_name, GFP_KERNEL);
	if (!dev_name)
	    goto free;

	t->devinet_dev[0].procname    = dev_name;
	t->devinet_dev[0].child	      = t->devinet_vars;
	t->devinet_conf_dir[0].child  = t->devinet_dev;
	t->devinet_proto_dir[0].child = t->devinet_conf_dir;
	t->devinet_root_dir[0].child  = t->devinet_proto_dir;

	t->sysctl_header = register_sysctl_table(t->devinet_root_dir);
	if (!t->sysctl_header)
	    goto free_procname;

	p->sysctl = t;
	return;

	/* error path */
 free_procname:
	kfree(dev_name);
 free:
	kfree(t);
	return;
}

static void devinet_sysctl_unregister(struct ipv4_devconf *p)
{
	if (p->sysctl) {
		struct devinet_sysctl_table *t = p->sysctl;
		p->sysctl = NULL;
		unregister_sysctl_table(t->sysctl_header);
		kfree(t->devinet_dev[0].procname);
		kfree(t);
	}
}
#endif

void __init devinet_init(void)
{
	register_gifconf(PF_INET, inet_gifconf);
	register_netdevice_notifier(&ip_netdev_notifier);

	rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL);
	rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL);
	rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr);
#ifdef CONFIG_SYSCTL
	devinet_sysctl.sysctl_header =
		register_sysctl_table(devinet_sysctl.devinet_root_dir);
	devinet_sysctl_register(NULL, &ipv4_devconf_dflt);
#endif
}

EXPORT_SYMBOL(in_dev_finish_destroy);
EXPORT_SYMBOL(inet_select_addr);
EXPORT_SYMBOL(inetdev_by_index);
EXPORT_SYMBOL(register_inetaddr_notifier);
EXPORT_SYMBOL(unregister_inetaddr_notifier);